malhuda/msm-4.14
1
0
Fork 0
mirror of https://github.com/rd-stuffs/msm-4.14.git synced 2025-02-20 11:45:48 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge android-4.14 (73421a4) into msm-4.14

Browse Source 
* refs/heads/tmp-73421a4:
  Revert "f2fs: let discard thread wait a little longer if dev is busy"
  Revert "f2fs: clean up with is_valid_blkaddr()"
  Revert "f2fs: fix race in between GC and atomic open"
  treewide: Use array_size in f2fs_kvzalloc()
  treewide: Use array_size() in f2fs_kzalloc()
  treewide: Use array_size() in f2fs_kmalloc()
  overflow.h: Add allocation size calculation helpers
  f2fs: fix to clear FI_VOLATILE_FILE correctly
  f2fs: let sync node IO interrupt async one
  f2fs: don't change wbc->sync_mode
  f2fs: fix to update mtime correctly
  fs: f2fs: insert space around that ':' and ', '
  fs: f2fs: add missing blank lines after declarations
  fs: f2fs: changed variable type of offset "unsigned" to "loff_t"
  f2fs: clean up symbol namespace
  f2fs: make set_de_type() static
  f2fs: make __f2fs_write_data_pages() static
  f2fs: fix to avoid accessing cross the boundary
  f2fs: fix to let caller retry allocating block address
  disable loading f2fs module on PAGE_SIZE > 4KB
  f2fs: fix error path of move_data_page
  f2fs: don't drop dentry pages after fs shutdown
  f2fs: fix to avoid race during access gc_thread pointer
  f2fs: clean up with clear_radix_tree_dirty_tag
  f2fs: fix to don't trigger writeback during recovery
  f2fs: clear discard_wake earlier
  f2fs: let discard thread wait a little longer if dev is busy
  f2fs: avoid stucking GC due to atomic write
  f2fs: introduce sbi->gc_mode to determine the policy
  f2fs: keep migration IO order in LFS mode
  f2fs: fix to wait page writeback during revoking atomic write
  f2fs: Fix deadlock in shutdown ioctl
  f2fs: detect synchronous writeback more earlier
  mm: remove nr_pages argument from pagevec_lookup_{,range}_tag()
  ceph: use pagevec_lookup_range_nr_tag()
  mm: add variant of pagevec_lookup_range_tag() taking number of pages
  mm: use pagevec_lookup_range_tag() in write_cache_pages()
  mm: use pagevec_lookup_range_tag() in __filemap_fdatawait_range()
  nilfs2: use pagevec_lookup_range_tag()
  gfs2: use pagevec_lookup_range_tag()
  f2fs: use find_get_pages_tag() for looking up single page
  f2fs: simplify page iteration loops
  f2fs: use pagevec_lookup_range_tag()
  ext4: use pagevec_lookup_range_tag()
  ceph: use pagevec_lookup_range_tag()
  btrfs: use pagevec_lookup_range_tag()
  mm: implement find_get_pages_range_tag()
  f2fs: clean up with is_valid_blkaddr()
  f2fs: fix to initialize min_mtime with ULLONG_MAX
  f2fs: fix to let checkpoint guarantee atomic page persistence
  f2fs: fix to initialize i_current_depth according to inode type
  Revert "f2fs: add ovp valid_blocks check for bg gc victim to fg_gc"
  f2fs: don't drop any page on f2fs_cp_error() case
  f2fs: fix spelling mistake: "extenstion" -> "extension"
  f2fs: enhance sanity_check_raw_super() to avoid potential overflows
  f2fs: treat volatile file's data as hot one
  f2fs: introduce release_discard_addr() for cleanup
  f2fs: fix potential overflow
  f2fs: rename dio_rwsem to i_gc_rwsem
  f2fs: move mnt_want_write_file after range check
  f2fs: fix missing clear FI_NO_PREALLOC in some error case
  f2fs: enforce fsync_mode=strict for renamed directory
  f2fs: sanity check for total valid node blocks
  f2fs: sanity check on sit entry
  f2fs: avoid bug_on on corrupted inode
  f2fs: give message and set need_fsck given broken node id
  f2fs: clean up commit_inmem_pages()
  f2fs: do not check F2FS_INLINE_DOTS in recover
  f2fs: remove duplicated dquot_initialize and fix error handling
  f2fs: fix to detect failure of dquot_initialize
  f2fs: stop issue discard if something wrong with f2fs
  f2fs: fix return value in f2fs_ioc_commit_atomic_write
  f2fs: allocate hot_data for atomic write more strictly
  f2fs: check if inmem_pages list is empty correctly
  f2fs: fix race in between GC and atomic open
  f2fs: change le32 to le16 of f2fs_inode->i_extra_size
  f2fs: check cur_valid_map_mir & raw_sit block count when flush sit entries
  f2fs: correct return value of f2fs_trim_fs
  f2fs: fix to show missing bits in FS_IOC_GETFLAGS
  f2fs: remove unneeded F2FS_PROJINHERIT_FL
  f2fs: don't use GFP_ZERO for page caches
  f2fs: issue all big range discards in umount process
  f2fs: remove redundant block plug
  f2fs: remove unmatched zero_user_segment when convert inline dentry
  f2fs: introduce private inode status mapping
  fscrypt: log the crypto algorithm implementations
  fscrypt: add Speck128/256 support
  fscrypt: only derive the needed portion of the key
  fscrypt: separate key lookup from key derivation
  fscrypt: use a common logging function
  fscrypt: remove internal key size constants
  fscrypt: remove unnecessary check for non-logon key type
  fscrypt: make fscrypt_operations.max_namelen an integer
  fscrypt: drop empty name check from fname_decrypt()
  fscrypt: drop max_namelen check from fname_decrypt()
  fscrypt: don't special-case EOPNOTSUPP from fscrypt_get_encryption_info()
  fscrypt: don't clear flags on crypto transform
  fscrypt: remove stale comment from fscrypt_d_revalidate()
  fscrypt: remove error messages for skcipher_request_alloc() failure
  fscrypt: remove unnecessary NULL check when allocating skcipher
  fscrypt: clean up after fscrypt_prepare_lookup() conversions
  ubifs: switch to fscrypt_prepare_lookup()
  ext4: switch to fscrypt_prepare_lookup()
  fscrypt: use unbound workqueue for decryption

Conflicts:
	fs/crypto/keyinfo.c
	fs/ext4/super.c
	fs/f2fs/checkpoint.c
	fs/f2fs/data.c
	fs/f2fs/f2fs.h
	fs/f2fs/file.c
	fs/f2fs/gc.c
	fs/f2fs/inline.c
	fs/f2fs/inode.c
	fs/f2fs/node.c
	fs/f2fs/recovery.c
	fs/f2fs/segment.c
	fs/f2fs/super.c
	include/linux/fscrypt_supp.h
	include/linux/overflow.h

Extra changes were required in below files due to hard
conflicts against HW based FBE:

	fs/crypto/fscrypt_ice.c
	fs/crypto/fscrypt_ice.h
	fs/crypto/fscrypt_private.h
	fs/crypto/keyinfo.c

Change-Id: I01d788e7cd36539f6228742c99820a94a2cc5e46
Signed-off-by: Blagovest Kolenichev <bkolenichev@codeaurora.org>
This commit is contained in:
Blagovest Kolenichev 2019-03-29 05:25:31 -07:00
commit 5c033b4894
48 changed files with 2493 additions and 1596 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

626
Documentation/filesystems/fscrypt.rst Normal file
View File

@ -0,0 +1,626 @@
=====================================
Filesystem-level encryption (fscrypt)
=====================================
Introduction
============
fscrypt is a library which filesystems can hook into to support
transparent encryption of files and directories.
Note: "fscrypt" in this document refers to the kernel-level portion,
implemented in ``fs/crypto/``, as opposed to the userspace tool
`fscrypt <https://github.com/google/fscrypt>`_. This document only
covers the kernel-level portion. For command-line examples of how to
use encryption, see the documentation for the userspace tool `fscrypt
<https://github.com/google/fscrypt>`_. Also, it is recommended to use
the fscrypt userspace tool, or other existing userspace tools such as
`fscryptctl <https://github.com/google/fscryptctl>`_ or `Android's key
management system
<https://source.android.com/security/encryption/file-based>`_, over
using the kernel's API directly. Using existing tools reduces the
chance of introducing your own security bugs. (Nevertheless, for
completeness this documentation covers the kernel's API anyway.)
Unlike dm-crypt, fscrypt operates at the filesystem level rather than
at the block device level. This allows it to encrypt different files
with different keys and to have unencrypted files on the same
filesystem. This is useful for multi-user systems where each user's
data-at-rest needs to be cryptographically isolated from the others.
However, except for filenames, fscrypt does not encrypt filesystem
metadata.
Unlike eCryptfs, which is a stacked filesystem, fscrypt is integrated
directly into supported filesystems --- currently ext4, F2FS, and
UBIFS. This allows encrypted files to be read and written without
caching both the decrypted and encrypted pages in the pagecache,
thereby nearly halving the memory used and bringing it in line with
unencrypted files. Similarly, half as many dentries and inodes are
needed. eCryptfs also limits encrypted filenames to 143 bytes,
causing application compatibility issues; fscrypt allows the full 255
bytes (NAME_MAX). Finally, unlike eCryptfs, the fscrypt API can be
used by unprivileged users, with no need to mount anything.
fscrypt does not support encrypting files in-place. Instead, it
supports marking an empty directory as encrypted. Then, after
userspace provides the key, all regular files, directories, and
symbolic links created in that directory tree are transparently
encrypted.
Threat model
============
Offline attacks
---------------
Provided that userspace chooses a strong encryption key, fscrypt
protects the confidentiality of file contents and filenames in the
event of a single point-in-time permanent offline compromise of the
block device content. fscrypt does not protect the confidentiality of
non-filename metadata, e.g. file sizes, file permissions, file
timestamps, and extended attributes. Also, the existence and location
of holes (unallocated blocks which logically contain all zeroes) in
files is not protected.
fscrypt is not guaranteed to protect confidentiality or authenticity
if an attacker is able to manipulate the filesystem offline prior to
an authorized user later accessing the filesystem.
Online attacks
--------------
fscrypt (and storage encryption in general) can only provide limited
protection, if any at all, against online attacks. In detail:
fscrypt is only resistant to side-channel attacks, such as timing or
electromagnetic attacks, to the extent that the underlying Linux
Cryptographic API algorithms are. If a vulnerable algorithm is used,
such as a table-based implementation of AES, it may be possible for an
attacker to mount a side channel attack against the online system.
Side channel attacks may also be mounted against applications
consuming decrypted data.
After an encryption key has been provided, fscrypt is not designed to
hide the plaintext file contents or filenames from other users on the
same system, regardless of the visibility of the keyring key.
Instead, existing access control mechanisms such as file mode bits,
POSIX ACLs, LSMs, or mount namespaces should be used for this purpose.
Also note that as long as the encryption keys are *anywhere* in
memory, an online attacker can necessarily compromise them by mounting
a physical attack or by exploiting any kernel security vulnerability
which provides an arbitrary memory read primitive.
While it is ostensibly possible to "evict" keys from the system,
recently accessed encrypted files will remain accessible at least
until the filesystem is unmounted or the VFS caches are dropped, e.g.
using ``echo 2 > /proc/sys/vm/drop_caches``. Even after that, if the
RAM is compromised before being powered off, it will likely still be
possible to recover portions of the plaintext file contents, if not
some of the encryption keys as well. (Since Linux v4.12, all
in-kernel keys related to fscrypt are sanitized before being freed.
However, userspace would need to do its part as well.)
Currently, fscrypt does not prevent a user from maliciously providing
an incorrect key for another user's existing encrypted files. A
protection against this is planned.
Key hierarchy
=============
Master Keys
-----------
Each encrypted directory tree is protected by a *master key*. Master
keys can be up to 64 bytes long, and must be at least as long as the
greater of the key length needed by the contents and filenames
encryption modes being used. For example, if AES-256-XTS is used for
contents encryption, the master key must be 64 bytes (512 bits). Note
that the XTS mode is defined to require a key twice as long as that
required by the underlying block cipher.
To "unlock" an encrypted directory tree, userspace must provide the
appropriate master key. There can be any number of master keys, each
of which protects any number of directory trees on any number of
filesystems.
Userspace should generate master keys either using a cryptographically
secure random number generator, or by using a KDF (Key Derivation
Function). Note that whenever a KDF is used to "stretch" a
lower-entropy secret such as a passphrase, it is critical that a KDF
designed for this purpose be used, such as scrypt, PBKDF2, or Argon2.
Per-file keys
-------------
Master keys are not used to encrypt file contents or names directly.
Instead, a unique key is derived for each encrypted file, including
each regular file, directory, and symbolic link. This has several
advantages:
- In cryptosystems, the same key material should never be used for
different purposes. Using the master key as both an XTS key for
contents encryption and as a CTS-CBC key for filenames encryption
would violate this rule.
- Per-file keys simplify the choice of IVs (Initialization Vectors)
for contents encryption. Without per-file keys, to ensure IV
uniqueness both the inode and logical block number would need to be
encoded in the IVs. This would make it impossible to renumber
inodes, which e.g. ``resize2fs`` can do when resizing an ext4
filesystem. With per-file keys, it is sufficient to encode just the
logical block number in the IVs.
- Per-file keys strengthen the encryption of filenames, where IVs are
reused out of necessity. With a unique key per directory, IV reuse
is limited to within a single directory.
- Per-file keys allow individual files to be securely erased simply by
securely erasing their keys. (Not yet implemented.)
A KDF (Key Derivation Function) is used to derive per-file keys from
the master key. This is done instead of wrapping a randomly-generated
key for each file because it reduces the size of the encryption xattr,
which for some filesystems makes the xattr more likely to fit in-line
in the filesystem's inode table. With a KDF, only a 16-byte nonce is
required --- long enough to make key reuse extremely unlikely. A
wrapped key, on the other hand, would need to be up to 64 bytes ---
the length of an AES-256-XTS key. Furthermore, currently there is no
requirement to support unlocking a file with multiple alternative
master keys or to support rotating master keys. Instead, the master
keys may be wrapped in userspace, e.g. as done by the `fscrypt
<https://github.com/google/fscrypt>`_ tool.
The current KDF encrypts the master key using the 16-byte nonce as an
AES-128-ECB key. The output is used as the derived key. If the
output is longer than needed, then it is truncated to the needed
length. Truncation is the norm for directories and symlinks, since
those use the CTS-CBC encryption mode which requires a key half as
long as that required by the XTS encryption mode.
Note: this KDF meets the primary security requirement, which is to
produce unique derived keys that preserve the entropy of the master
key, assuming that the master key is already a good pseudorandom key.
However, it is nonstandard and has some problems such as being
reversible, so it is generally considered to be a mistake! It may be
replaced with HKDF or another more standard KDF in the future.
Encryption modes and usage
==========================
fscrypt allows one encryption mode to be specified for file contents
and one encryption mode to be specified for filenames. Different
directory trees are permitted to use different encryption modes.
Currently, the following pairs of encryption modes are supported:
- AES-256-XTS for contents and AES-256-CTS-CBC for filenames
- AES-128-CBC for contents and AES-128-CTS-CBC for filenames
- Speck128/256-XTS for contents and Speck128/256-CTS-CBC for filenames
It is strongly recommended to use AES-256-XTS for contents encryption.
AES-128-CBC was added only for low-powered embedded devices with
crypto accelerators such as CAAM or CESA that do not support XTS.
Similarly, Speck128/256 support was only added for older or low-end
CPUs which cannot do AES fast enough -- especially ARM CPUs which have
NEON instructions but not the Cryptography Extensions -- and for which
it would not otherwise be feasible to use encryption at all. It is
not recommended to use Speck on CPUs that have AES instructions.
Speck support is only available if it has been enabled in the crypto
API via CONFIG_CRYPTO_SPECK. Also, on ARM platforms, to get
acceptable performance CONFIG_CRYPTO_SPECK_NEON must be enabled.
New encryption modes can be added relatively easily, without changes
to individual filesystems. However, authenticated encryption (AE)
modes are not currently supported because of the difficulty of dealing
with ciphertext expansion.
For file contents, each filesystem block is encrypted independently.
Currently, only the case where the filesystem block size is equal to
the system's page size (usually 4096 bytes) is supported. With the
XTS mode of operation (recommended), the logical block number within
the file is used as the IV. With the CBC mode of operation (not
recommended), ESSIV is used; specifically, the IV for CBC is the
logical block number encrypted with AES-256, where the AES-256 key is
the SHA-256 hash of the inode's data encryption key.
For filenames, the full filename is encrypted at once. Because of the
requirements to retain support for efficient directory lookups and
filenames of up to 255 bytes, a constant initialization vector (IV) is
used. However, each encrypted directory uses a unique key, which
limits IV reuse to within a single directory. Note that IV reuse in
the context of CTS-CBC encryption means that when the original
filenames share a common prefix at least as long as the cipher block
size (16 bytes for AES), the corresponding encrypted filenames will
also share a common prefix. This is undesirable; it may be fixed in
the future by switching to an encryption mode that is a strong
pseudorandom permutation on arbitrary-length messages, e.g. the HEH
(Hash-Encrypt-Hash) mode.
Since filenames are encrypted with the CTS-CBC mode of operation, the
plaintext and ciphertext filenames need not be multiples of the AES
block size, i.e. 16 bytes. However, the minimum size that can be
encrypted is 16 bytes, so shorter filenames are NUL-padded to 16 bytes
before being encrypted. In addition, to reduce leakage of filename
lengths via their ciphertexts, all filenames are NUL-padded to the
next 4, 8, 16, or 32-byte boundary (configurable). 32 is recommended
since this provides the best confidentiality, at the cost of making
directory entries consume slightly more space. Note that since NUL
(``\0``) is not otherwise a valid character in filenames, the padding
will never produce duplicate plaintexts.
Symbolic link targets are considered a type of filename and are
encrypted in the same way as filenames in directory entries. Each
symlink also uses a unique key; hence, the hardcoded IV is not a
problem for symlinks.
User API
========
Setting an encryption policy
----------------------------
The FS_IOC_SET_ENCRYPTION_POLICY ioctl sets an encryption policy on an
empty directory or verifies that a directory or regular file already
has the specified encryption policy. It takes in a pointer to a
:c:type:`struct fscrypt_policy`, defined as follows::
#define FS_KEY_DESCRIPTOR_SIZE 8
struct fscrypt_policy {
__u8 version;
__u8 contents_encryption_mode;
__u8 filenames_encryption_mode;
__u8 flags;
__u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
};
This structure must be initialized as follows:
- ``version`` must be 0.
- ``contents_encryption_mode`` and ``filenames_encryption_mode`` must
be set to constants from ``<linux/fs.h>`` which identify the
encryption modes to use. If unsure, use
FS_ENCRYPTION_MODE_AES_256_XTS (1) for ``contents_encryption_mode``
and FS_ENCRYPTION_MODE_AES_256_CTS (4) for
``filenames_encryption_mode``.
- ``flags`` must be set to a value from ``<linux/fs.h>`` which
identifies the amount of NUL-padding to use when encrypting
filenames. If unsure, use FS_POLICY_FLAGS_PAD_32 (0x3).
- ``master_key_descriptor`` specifies how to find the master key in
the keyring; see `Adding keys`_. It is up to userspace to choose a
unique ``master_key_descriptor`` for each master key. The e4crypt
and fscrypt tools use the first 8 bytes of
``SHA-512(SHA-512(master_key))``, but this particular scheme is not
required. Also, the master key need not be in the keyring yet when
FS_IOC_SET_ENCRYPTION_POLICY is executed. However, it must be added
before any files can be created in the encrypted directory.
If the file is not yet encrypted, then FS_IOC_SET_ENCRYPTION_POLICY
verifies that the file is an empty directory. If so, the specified
encryption policy is assigned to the directory, turning it into an
encrypted directory. After that, and after providing the
corresponding master key as described in `Adding keys`_, all regular
files, directories (recursively), and symlinks created in the
directory will be encrypted, inheriting the same encryption policy.
The filenames in the directory's entries will be encrypted as well.
Alternatively, if the file is already encrypted, then
FS_IOC_SET_ENCRYPTION_POLICY validates that the specified encryption
policy exactly matches the actual one. If they match, then the ioctl
returns 0. Otherwise, it fails with EEXIST. This works on both
regular files and directories, including nonempty directories.
Note that the ext4 filesystem does not allow the root directory to be
encrypted, even if it is empty. Users who want to encrypt an entire
filesystem with one key should consider using dm-crypt instead.
FS_IOC_SET_ENCRYPTION_POLICY can fail with the following errors:
- ``EACCES``: the file is not owned by the process's uid, nor does the
process have the CAP_FOWNER capability in a namespace with the file
owner's uid mapped
- ``EEXIST``: the file is already encrypted with an encryption policy
different from the one specified
- ``EINVAL``: an invalid encryption policy was specified (invalid
version, mode(s), or flags)
- ``ENOTDIR``: the file is unencrypted and is a regular file, not a
directory
- ``ENOTEMPTY``: the file is unencrypted and is a nonempty directory
- ``ENOTTY``: this type of filesystem does not implement encryption
- ``EOPNOTSUPP``: the kernel was not configured with encryption
support for this filesystem, or the filesystem superblock has not
had encryption enabled on it. (For example, to use encryption on an
ext4 filesystem, CONFIG_EXT4_ENCRYPTION must be enabled in the
kernel config, and the superblock must have had the "encrypt"
feature flag enabled using ``tune2fs -O encrypt`` or ``mkfs.ext4 -O
encrypt``.)
- ``EPERM``: this directory may not be encrypted, e.g. because it is
the root directory of an ext4 filesystem
- ``EROFS``: the filesystem is readonly
Getting an encryption policy
----------------------------
The FS_IOC_GET_ENCRYPTION_POLICY ioctl retrieves the :c:type:`struct
fscrypt_policy`, if any, for a directory or regular file. See above
for the struct definition. No additional permissions are required
beyond the ability to open the file.
FS_IOC_GET_ENCRYPTION_POLICY can fail with the following errors:
- ``EINVAL``: the file is encrypted, but it uses an unrecognized
encryption context format
- ``ENODATA``: the file is not encrypted
- ``ENOTTY``: this type of filesystem does not implement encryption
- ``EOPNOTSUPP``: the kernel was not configured with encryption
support for this filesystem
Note: if you only need to know whether a file is encrypted or not, on
most filesystems it is also possible to use the FS_IOC_GETFLAGS ioctl
and check for FS_ENCRYPT_FL, or to use the statx() system call and
check for STATX_ATTR_ENCRYPTED in stx_attributes.
Getting the per-filesystem salt
-------------------------------
Some filesystems, such as ext4 and F2FS, also support the deprecated
ioctl FS_IOC_GET_ENCRYPTION_PWSALT. This ioctl retrieves a randomly
generated 16-byte value stored in the filesystem superblock. This
value is intended to used as a salt when deriving an encryption key
from a passphrase or other low-entropy user credential.
FS_IOC_GET_ENCRYPTION_PWSALT is deprecated. Instead, prefer to
generate and manage any needed salt(s) in userspace.
Adding keys
-----------
To provide a master key, userspace must add it to an appropriate
keyring using the add_key() system call (see:
``Documentation/security/keys/core.rst``). The key type must be
"logon"; keys of this type are kept in kernel memory and cannot be
read back by userspace. The key description must be "fscrypt:"
followed by the 16-character lower case hex representation of the
``master_key_descriptor`` that was set in the encryption policy. The
key payload must conform to the following structure::
#define FS_MAX_KEY_SIZE 64
struct fscrypt_key {
u32 mode;
u8 raw[FS_MAX_KEY_SIZE];
u32 size;
};
``mode`` is ignored; just set it to 0. The actual key is provided in
``raw`` with ``size`` indicating its size in bytes. That is, the
bytes ``raw[0..size-1]`` (inclusive) are the actual key.
The key description prefix "fscrypt:" may alternatively be replaced
with a filesystem-specific prefix such as "ext4:". However, the
filesystem-specific prefixes are deprecated and should not be used in
new programs.
There are several different types of keyrings in which encryption keys
may be placed, such as a session keyring, a user session keyring, or a
user keyring. Each key must be placed in a keyring that is "attached"
to all processes that might need to access files encrypted with it, in
the sense that request_key() will find the key. Generally, if only
processes belonging to a specific user need to access a given
encrypted directory and no session keyring has been installed, then
that directory's key should be placed in that user's user session
keyring or user keyring. Otherwise, a session keyring should be
installed if needed, and the key should be linked into that session
keyring, or in a keyring linked into that session keyring.
Note: introducing the complex visibility semantics of keyrings here
was arguably a mistake --- especially given that by design, after any
process successfully opens an encrypted file (thereby setting up the
per-file key), possessing the keyring key is not actually required for
any process to read/write the file until its in-memory inode is
evicted. In the future there probably should be a way to provide keys
directly to the filesystem instead, which would make the intended
semantics clearer.
Access semantics
================
With the key
------------
With the encryption key, encrypted regular files, directories, and
symlinks behave very similarly to their unencrypted counterparts ---
after all, the encryption is intended to be transparent. However,
astute users may notice some differences in behavior:
- Unencrypted files, or files encrypted with a different encryption
policy (i.e. different key, modes, or flags), cannot be renamed or
linked into an encrypted directory; see `Encryption policy
enforcement`_. Attempts to do so will fail with EPERM. However,
encrypted files can be renamed within an encrypted directory, or
into an unencrypted directory.
- Direct I/O is not supported on encrypted files. Attempts to use
direct I/O on such files will fall back to buffered I/O.
- The fallocate operations FALLOC_FL_COLLAPSE_RANGE,
FALLOC_FL_INSERT_RANGE, and FALLOC_FL_ZERO_RANGE are not supported
on encrypted files and will fail with EOPNOTSUPP.
- Online defragmentation of encrypted files is not supported. The
EXT4_IOC_MOVE_EXT and F2FS_IOC_MOVE_RANGE ioctls will fail with
EOPNOTSUPP.
- The ext4 filesystem does not support data journaling with encrypted
regular files. It will fall back to ordered data mode instead.
- DAX (Direct Access) is not supported on encrypted files.
- The st_size of an encrypted symlink will not necessarily give the
length of the symlink target as required by POSIX. It will actually
give the length of the ciphertext, which will be slightly longer
than the plaintext due to NUL-padding and an extra 2-byte overhead.
- The maximum length of an encrypted symlink is 2 bytes shorter than
the maximum length of an unencrypted symlink. For example, on an
EXT4 filesystem with a 4K block size, unencrypted symlinks can be up
to 4095 bytes long, while encrypted symlinks can only be up to 4093
bytes long (both lengths excluding the terminating null).
Note that mmap *is* supported. This is possible because the pagecache
for an encrypted file contains the plaintext, not the ciphertext.
Without the key
---------------
Some filesystem operations may be performed on encrypted regular
files, directories, and symlinks even before their encryption key has
been provided:
- File metadata may be read, e.g. using stat().
- Directories may be listed, in which case the filenames will be
listed in an encoded form derived from their ciphertext. The
current encoding algorithm is described in `Filename hashing and
encoding`_. The algorithm is subject to change, but it is
guaranteed that the presented filenames will be no longer than
NAME_MAX bytes, will not contain the ``/`` or ``\0`` characters, and
will uniquely identify directory entries.
The ``.`` and ``..`` directory entries are special. They are always
present and are not encrypted or encoded.
- Files may be deleted. That is, nondirectory files may be deleted
with unlink() as usual, and empty directories may be deleted with
rmdir() as usual. Therefore, ``rm`` and ``rm -r`` will work as
expected.
- Symlink targets may be read and followed, but they will be presented
in encrypted form, similar to filenames in directories. Hence, they
are unlikely to point to anywhere useful.
Without the key, regular files cannot be opened or truncated.
Attempts to do so will fail with ENOKEY. This implies that any
regular file operations that require a file descriptor, such as
read(), write(), mmap(), fallocate(), and ioctl(), are also forbidden.
Also without the key, files of any type (including directories) cannot
be created or linked into an encrypted directory, nor can a name in an
encrypted directory be the source or target of a rename, nor can an
O_TMPFILE temporary file be created in an encrypted directory. All
such operations will fail with ENOKEY.
It is not currently possible to backup and restore encrypted files
without the encryption key. This would require special APIs which
have not yet been implemented.
Encryption policy enforcement
=============================
After an encryption policy has been set on a directory, all regular
files, directories, and symbolic links created in that directory
(recursively) will inherit that encryption policy. Special files ---
that is, named pipes, device nodes, and UNIX domain sockets --- will
not be encrypted.
Except for those special files, it is forbidden to have unencrypted
files, or files encrypted with a different encryption policy, in an
encrypted directory tree. Attempts to link or rename such a file into
an encrypted directory will fail with EPERM. This is also enforced
during ->lookup() to provide limited protection against offline
attacks that try to disable or downgrade encryption in known locations
where applications may later write sensitive data. It is recommended
that systems implementing a form of "verified boot" take advantage of
this by validating all top-level encryption policies prior to access.
Implementation details
======================
Encryption context
------------------
An encryption policy is represented on-disk by a :c:type:`struct
fscrypt_context`. It is up to individual filesystems to decide where
to store it, but normally it would be stored in a hidden extended
attribute. It should *not* be exposed by the xattr-related system
calls such as getxattr() and setxattr() because of the special
semantics of the encryption xattr. (In particular, there would be
much confusion if an encryption policy were to be added to or removed
from anything other than an empty directory.) The struct is defined
as follows::
#define FS_KEY_DESCRIPTOR_SIZE 8
#define FS_KEY_DERIVATION_NONCE_SIZE 16
struct fscrypt_context {
u8 format;
u8 contents_encryption_mode;
u8 filenames_encryption_mode;
u8 flags;
u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE];
};
Note that :c:type:`struct fscrypt_context` contains the same
information as :c:type:`struct fscrypt_policy` (see `Setting an
encryption policy`_), except that :c:type:`struct fscrypt_context`
also contains a nonce. The nonce is randomly generated by the kernel
and is used to derive the inode's encryption key as described in
`Per-file keys`_.
Data path changes
-----------------
For the read path (->readpage()) of regular files, filesystems can
read the ciphertext into the page cache and decrypt it in-place. The
page lock must be held until decryption has finished, to prevent the
page from becoming visible to userspace prematurely.
For the write path (->writepage()) of regular files, filesystems
cannot encrypt data in-place in the page cache, since the cached
plaintext must be preserved. Instead, filesystems must encrypt into a
temporary buffer or "bounce page", then write out the temporary
buffer. Some filesystems, such as UBIFS, already use temporary
buffers regardless of encryption. Other filesystems, such as ext4 and
F2FS, have to allocate bounce pages specially for encryption.
Filename hashing and encoding
-----------------------------
Modern filesystems accelerate directory lookups by using indexed
directories. An indexed directory is organized as a tree keyed by
filename hashes. When a ->lookup() is requested, the filesystem
normally hashes the filename being looked up so that it can quickly
find the corresponding directory entry, if any.
With encryption, lookups must be supported and efficient both with and
without the encryption key. Clearly, it would not work to hash the
plaintext filenames, since the plaintext filenames are unavailable
without the key. (Hashing the plaintext filenames would also make it
impossible for the filesystem's fsck tool to optimize encrypted
directories.) Instead, filesystems hash the ciphertext filenames,
i.e. the bytes actually stored on-disk in the directory entries. When
asked to do a ->lookup() with the key, the filesystem just encrypts
the user-supplied name to get the ciphertext.
Lookups without the key are more complicated. The raw ciphertext may
contain the ``\0`` and ``/`` characters, which are illegal in
filenames. Therefore, readdir() must base64-encode the ciphertext for
presentation. For most filenames, this works fine; on ->lookup(), the
filesystem just base64-decodes the user-supplied name to get back to
the raw ciphertext.
However, for very long filenames, base64 encoding would cause the
filename length to exceed NAME_MAX. To prevent this, readdir()
actually presents long filenames in an abbreviated form which encodes
a strong "hash" of the ciphertext filename, along with the optional
filesystem-specific hash(es) needed for directory lookups. This
allows the filesystem to still, with a high degree of confidence, map
the filename given in ->lookup() back to a particular directory entry
that was previously listed by readdir(). See :c:type:`struct
fscrypt_digested_name` in the source for more details.
Note that the precise way that filenames are presented to userspace
without the key is subject to change in the future. It is only meant
as a way to temporarily present valid filenames so that commands like
``rm -r`` work as expected on encrypted directories.

10
drivers/md/dm-table.c
View File

@ -548,14 +548,14 @@ static int adjoin(struct dm_table *table, struct dm_target *ti)
* On the other hand, dm-switch needs to process bulk data using messages and
* excessive use of GFP_NOIO could cause trouble.
*/
static char **realloc_argv(unsigned *array_size, char **old_argv)
static char **realloc_argv(unsigned *size, char **old_argv)
{
char **argv;
unsigned new_size;
gfp_t gfp;
if (*array_size) {
new_size = *array_size * 2;
if (*size) {
new_size = *size * 2;
gfp = GFP_KERNEL;
} else {
new_size = 8;
@ -563,8 +563,8 @@ static char **realloc_argv(unsigned *array_size, char **old_argv)
}
argv = kmalloc(new_size * sizeof(*argv), gfp);
if (argv) {
memcpy(argv, old_argv, *array_size * sizeof(*argv));
*array_size = new_size;
memcpy(argv, old_argv, *size * sizeof(*argv));
*size = new_size;
}
kfree(old_argv);

19
fs/btrfs/extent_io.c
View File

@ -3819,8 +3819,8 @@ retry:
if (wbc->sync_mode == WB_SYNC_ALL)
tag_pages_for_writeback(mapping, index, end);
while (!done && !nr_to_write_done && (index <= end) &&
(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
(nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
tag))) {
unsigned i;
scanned = 1;
@ -3830,11 +3830,6 @@ retry:
if (!PagePrivate(page))
continue;
if (!wbc->range_cyclic && page->index > end) {
done = 1;
break;
}
spin_lock(&mapping->private_lock);
if (!PagePrivate(page)) {
spin_unlock(&mapping->private_lock);
@ -3966,8 +3961,8 @@ retry:
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && !nr_to_write_done && (index <= end) &&
(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
(nr_pages = pagevec_lookup_range_tag(&pvec, mapping,
&index, end, tag))) {
unsigned i;
scanned = 1;
@ -3992,12 +3987,6 @@ retry:
continue;
}
if (!wbc->range_cyclic && page->index > end) {
done = 1;
unlock_page(page);
continue;
}
if (wbc->sync_mode != WB_SYNC_NONE) {
if (PageWriteback(page))
flush_fn(data);

26
fs/ceph/addr.c
View File

@ -870,15 +870,10 @@ retry:
max_pages = wsize >> PAGE_SHIFT;
get_more_pages:
pvec_pages = min_t(unsigned, PAGEVEC_SIZE,
max_pages - locked_pages);
if (end - index < (u64)(pvec_pages - 1))
pvec_pages = (unsigned)(end - index) + 1;
pvec_pages = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_DIRTY,
pvec_pages);
dout("pagevec_lookup_tag got %d\n", pvec_pages);
pvec_pages = pagevec_lookup_range_nr_tag(&pvec, mapping, &index,
end, PAGECACHE_TAG_DIRTY,
max_pages - locked_pages);
dout("pagevec_lookup_range_tag got %d\n", pvec_pages);
if (!pvec_pages && !locked_pages)
break;
for (i = 0; i < pvec_pages && locked_pages < max_pages; i++) {
@ -896,16 +891,6 @@ get_more_pages:
unlock_page(page);
continue;
}
if (page->index > end) {
dout("end of range %p\n", page);
/* can't be range_cyclic (1st pass) because
* end == -1 in that case. */
stop = true;
if (ceph_wbc.head_snapc)
done = true;
unlock_page(page);
break;
}
if (strip_unit_end && (page->index > strip_unit_end)) {
dout("end of strip unit %p\n", page);
unlock_page(page);
@ -1177,8 +1162,7 @@ release_pvec_pages:
index = 0;
while ((index <= end) &&
(nr = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_WRITEBACK,
PAGEVEC_SIZE))) {
PAGECACHE_TAG_WRITEBACK))) {
for (i = 0; i < nr; i++) {
page = pvec.pages[i];
if (page_snap_context(page) != snapc)

36
fs/crypto/crypto.c
View File

@ -162,12 +162,8 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw,
}
req = skcipher_request_alloc(tfm, gfp_flags);
if (!req) {
printk_ratelimited(KERN_ERR
"%s: crypto_request_alloc() failed\n",
__func__);
if (!req)
return -ENOMEM;
}
skcipher_request_set_callback(
req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
@ -184,9 +180,10 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw,
res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
skcipher_request_free(req);
if (res) {
printk_ratelimited(KERN_ERR
"%s: crypto_skcipher_encrypt() returned %d\n",
__func__, res);
fscrypt_err(inode->i_sb,
"%scryption failed for inode %lu, block %llu: %d",
(rw == FS_DECRYPT ? "de" : "en"),
inode->i_ino, lblk_num, res);
return res;
}
return 0;
@ -332,7 +329,6 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
return 0;
}
/* this should eventually be an flag in d_flags */
spin_lock(&dentry->d_lock);
cached_with_key = dentry->d_flags & DCACHE_ENCRYPTED_WITH_KEY;
spin_unlock(&dentry->d_lock);
@ -359,7 +355,6 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
const struct dentry_operations fscrypt_d_ops = {
.d_revalidate = fscrypt_d_revalidate,
};
EXPORT_SYMBOL(fscrypt_d_ops);
void fscrypt_restore_control_page(struct page *page)
{
@ -428,6 +423,27 @@ fail:
return res;
}
void fscrypt_msg(struct super_block *sb, const char *level,
const char *fmt, ...)
{
static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
struct va_format vaf;
va_list args;
if (!__ratelimit(&rs))
return;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
if (sb)
printk("%sfscrypt (%s): %pV\n", level, sb->s_id, &vaf);
else
printk("%sfscrypt: %pV\n", level, &vaf);
va_end(args);
}
/**
* fscrypt_init() - Set up for fs encryption.
*/

32
fs/crypto/fname.c
View File

@ -59,11 +59,8 @@ int fname_encrypt(struct inode *inode, const struct qstr *iname,
/* Set up the encryption request */
req = skcipher_request_alloc(tfm, GFP_NOFS);
if (!req) {
printk_ratelimited(KERN_ERR
"%s: skcipher_request_alloc() failed\n", __func__);
if (!req)
return -ENOMEM;
}
skcipher_request_set_callback(req,
CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
crypto_req_done, &wait);
@ -74,8 +71,9 @@ int fname_encrypt(struct inode *inode, const struct qstr *iname,
res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
skcipher_request_free(req);
if (res < 0) {
printk_ratelimited(KERN_ERR
"%s: Error (error code %d)\n", __func__, res);
fscrypt_err(inode->i_sb,
"Filename encryption failed for inode %lu: %d",
inode->i_ino, res);
return res;
}
@ -96,23 +94,14 @@ static int fname_decrypt(struct inode *inode,
struct skcipher_request *req = NULL;
DECLARE_CRYPTO_WAIT(wait);
struct scatterlist src_sg, dst_sg;
struct fscrypt_info *ci = inode->i_crypt_info;
struct crypto_skcipher *tfm = ci->ci_ctfm;
struct crypto_skcipher *tfm = inode->i_crypt_info->ci_ctfm;
int res = 0;
char iv[FS_CRYPTO_BLOCK_SIZE];
unsigned lim;
lim = inode->i_sb->s_cop->max_namelen(inode);
if (iname->len <= 0 || iname->len > lim)
return -EIO;
/* Allocate request */
req = skcipher_request_alloc(tfm, GFP_NOFS);
if (!req) {
printk_ratelimited(KERN_ERR
"%s: crypto_request_alloc() failed\n", __func__);
if (!req)
return -ENOMEM;
}
skcipher_request_set_callback(req,
CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
crypto_req_done, &wait);
@ -127,8 +116,9 @@ static int fname_decrypt(struct inode *inode,
res = crypto_wait_req(crypto_skcipher_decrypt(req), &wait);
skcipher_request_free(req);
if (res < 0) {
printk_ratelimited(KERN_ERR
"%s: Error (error code %d)\n", __func__, res);
fscrypt_err(inode->i_sb,
"Filename decryption failed for inode %lu: %d",
inode->i_ino, res);
return res;
}
@ -341,12 +331,12 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
return 0;
}
ret = fscrypt_get_encryption_info(dir);
if (ret && ret != -EOPNOTSUPP)
if (ret)
return ret;
if (dir->i_crypt_info) {
if (!fscrypt_fname_encrypted_size(dir, iname->len,
dir->i_sb->s_cop->max_namelen(dir),
dir->i_sb->s_cop->max_namelen,
&fname->crypto_buf.len))
return -ENAMETOOLONG;
fname->crypto_buf.name = kmalloc(fname->crypto_buf.len,

33
fs/crypto/fscrypt_ice.c
View File

@ -12,6 +12,8 @@
#include "fscrypt_ice.h"
extern int fscrypt_get_mode_key_size(int mode);
int fscrypt_using_hardware_encryption(const struct inode *inode)
{
struct fscrypt_info *ci = inode->i_crypt_info;
@ -21,6 +23,30 @@ int fscrypt_using_hardware_encryption(const struct inode *inode)
}
EXPORT_SYMBOL(fscrypt_using_hardware_encryption);
size_t fscrypt_get_ice_encryption_key_size(const struct inode *inode)
{
struct fscrypt_info *ci = NULL;
if (inode)
ci = inode->i_crypt_info;
if (!ci)
return 0;
return fscrypt_get_mode_key_size(ci->ci_data_mode) / 2;
}
size_t fscrypt_get_ice_encryption_salt_size(const struct inode *inode)
{
struct fscrypt_info *ci = NULL;
if (inode)
ci = inode->i_crypt_info;
if (!ci)
return 0;
return fscrypt_get_mode_key_size(ci->ci_data_mode) / 2;
}
/*
* Retrieves encryption key from the inode
*/
@ -44,6 +70,7 @@ char *fscrypt_get_ice_encryption_key(const struct inode *inode)
char *fscrypt_get_ice_encryption_salt(const struct inode *inode)
{
struct fscrypt_info *ci = NULL;
int size = 0;
if (!inode)
return NULL;
@ -52,7 +79,11 @@ char *fscrypt_get_ice_encryption_salt(const struct inode *inode)
if (!ci)
return NULL;
return &(ci->ci_raw_key[fscrypt_get_ice_encryption_key_size(inode)]);
size = fscrypt_get_ice_encryption_key_size(inode);
if (!size)
return NULL;
return &(ci->ci_raw_key[size]);
}
/*

15
fs/crypto/fscrypt_ice.h
View File

@ -21,7 +21,7 @@ static inline bool fscrypt_should_be_processed_by_ice(const struct inode *inode)
{
if (!inode->i_sb->s_cop)
return 0;
if (!inode->i_sb->s_cop->is_encrypted((struct inode *)inode))
if (!IS_ENCRYPTED((struct inode *)inode))
return 0;
return fscrypt_using_hardware_encryption(inode);
@ -40,17 +40,10 @@ char *fscrypt_get_ice_encryption_salt(const struct inode *inode);
bool fscrypt_is_ice_encryption_info_equal(const struct inode *inode1,
const struct inode *inode2);
static inline size_t fscrypt_get_ice_encryption_key_size(
const struct inode *inode)
{
return FS_AES_256_XTS_KEY_SIZE / 2;
}
size_t fscrypt_get_ice_encryption_key_size(const struct inode *inode);
size_t fscrypt_get_ice_encryption_salt_size(const struct inode *inode);
static inline size_t fscrypt_get_ice_encryption_salt_size(
const struct inode *inode)
{
return FS_AES_256_XTS_KEY_SIZE / 2;
}
#else
static inline bool fscrypt_should_be_processed_by_ice(const struct inode *inode)
{

30
fs/crypto/fscrypt_private.h
View File

@ -21,15 +21,7 @@
/* Encryption parameters */
#define FS_IV_SIZE 16
#define FS_AES_128_ECB_KEY_SIZE 16
#define FS_AES_128_CBC_KEY_SIZE 16
#define FS_AES_128_CTS_KEY_SIZE 16
#define FS_AES_256_GCM_KEY_SIZE 32
#define FS_AES_256_CBC_KEY_SIZE 32
#define FS_AES_256_CTS_KEY_SIZE 32
#define FS_AES_256_XTS_KEY_SIZE 64
#define FS_KEY_DERIVATION_NONCE_SIZE 16
#define FS_KEY_DERIVATION_NONCE_SIZE 16
/**
* Encryption context for inode
@ -62,12 +54,6 @@ struct fscrypt_symlink_data {
char encrypted_path[1];
} __packed;
enum ci_mode_info {
CI_NONE_MODE = 0,
CI_DATA_MODE,
CI_FNAME_MODE,
};
/*
* A pointer to this structure is stored in the file system's in-core
* representation of an inode.
@ -113,10 +99,9 @@ static inline bool fscrypt_valid_enc_modes(u32 contents_mode,
return false;
}
static inline bool is_private_data_mode(struct fscrypt_info *ci)
static inline bool is_private_data_mode(const struct fscrypt_context *ctx)
{
return ci->ci_mode == CI_DATA_MODE &&
ci->ci_data_mode == FS_ENCRYPTION_MODE_PRIVATE;
return ctx->contents_encryption_mode == FS_ENCRYPTION_MODE_PRIVATE;
}
/* crypto.c */
@ -130,6 +115,15 @@ extern int fscrypt_do_page_crypto(const struct inode *inode,
gfp_t gfp_flags);
extern struct page *fscrypt_alloc_bounce_page(struct fscrypt_ctx *ctx,
gfp_t gfp_flags);
extern const struct dentry_operations fscrypt_d_ops;
extern void __printf(3, 4) __cold
fscrypt_msg(struct super_block *sb, const char *level, const char *fmt, ...);
#define fscrypt_warn(sb, fmt, ...) \
fscrypt_msg(sb, KERN_WARNING, fmt, ##__VA_ARGS__)
#define fscrypt_err(sb, fmt, ...) \
fscrypt_msg(sb, KERN_ERR, fmt, ##__VA_ARGS__)
/* fname.c */
extern int fname_encrypt(struct inode *inode, const struct qstr *iname,

5
fs/crypto/hooks.c
View File

@ -39,8 +39,9 @@ int fscrypt_file_open(struct inode *inode, struct file *filp)
dir = dget_parent(file_dentry(filp));
if (IS_ENCRYPTED(d_inode(dir)) &&
!fscrypt_has_permitted_context(d_inode(dir), inode)) {
pr_warn_ratelimited("fscrypt: inconsistent encryption contexts: %lu/%lu",
d_inode(dir)->i_ino, inode->i_ino);
fscrypt_warn(inode->i_sb,
"inconsistent encryption contexts: %lu/%lu",
d_inode(dir)->i_ino, inode->i_ino);
err = -EPERM;
}
dput(dir);

334
fs/crypto/keyinfo.c
View File

@ -20,17 +20,16 @@
static struct crypto_shash *essiv_hash_tfm;
/**
* derive_key_aes() - Derive a key using AES-128-ECB
* @deriving_key: Encryption key used for derivation.
* @source_key: Source key to which to apply derivation.
* @derived_raw_key: Derived raw key.
/*
* Key derivation function. This generates the derived key by encrypting the
* master key with AES-128-ECB using the inode's nonce as the AES key.
*
* Return: Zero on success; non-zero otherwise.
* The master key must be at least as long as the derived key. If the master
* key is longer, then only the first 'derived_keysize' bytes are used.
*/
static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE],
const struct fscrypt_key *source_key,
u8 derived_raw_key[FS_MAX_KEY_SIZE])
static int derive_key_aes(const u8 *master_key,
const struct fscrypt_context *ctx,
u8 *derived_key, unsigned int derived_keysize)
{
int res = 0;
struct skcipher_request *req = NULL;
@ -52,14 +51,13 @@ static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE],
skcipher_request_set_callback(req,
CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
crypto_req_done, &wait);
res = crypto_skcipher_setkey(tfm, deriving_key,
FS_AES_128_ECB_KEY_SIZE);
res = crypto_skcipher_setkey(tfm, ctx->nonce, sizeof(ctx->nonce));
if (res < 0)
goto out;
sg_init_one(&src_sg, source_key->raw, source_key->size);
sg_init_one(&dst_sg, derived_raw_key, source_key->size);
skcipher_request_set_crypt(req, &src_sg, &dst_sg, source_key->size,
sg_init_one(&src_sg, master_key, derived_keysize);
sg_init_one(&dst_sg, derived_key, derived_keysize);
skcipher_request_set_crypt(req, &src_sg, &dst_sg, derived_keysize,
NULL);
res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
out:
@ -68,123 +66,168 @@ out:
return res;
}
static int validate_user_key(struct fscrypt_info *crypt_info,
struct fscrypt_context *ctx,
const char *prefix, int min_keysize)
/*
* Search the current task's subscribed keyrings for a "logon" key with
* description prefix:descriptor, and if found acquire a read lock on it and
* return a pointer to its validated payload in *payload_ret.
*/
static struct key *
find_and_lock_process_key(const char *prefix,
const u8 descriptor[FS_KEY_DESCRIPTOR_SIZE],
unsigned int min_keysize,
const struct fscrypt_key **payload_ret)
{
char *description;
struct key *keyring_key;
struct fscrypt_key *master_key;
struct key *key;
const struct user_key_payload *ukp;
int res;
const struct fscrypt_key *payload;
description = kasprintf(GFP_NOFS, "%s%*phN", prefix,
FS_KEY_DESCRIPTOR_SIZE,
ctx->master_key_descriptor);
FS_KEY_DESCRIPTOR_SIZE, descriptor);
if (!description)
return -ENOMEM;
return ERR_PTR(-ENOMEM);
keyring_key = request_key(&key_type_logon, description, NULL);
key = request_key(&key_type_logon, description, NULL);
kfree(description);
if (IS_ERR(keyring_key))
return PTR_ERR(keyring_key);
down_read(&keyring_key->sem);
if (IS_ERR(key))
return key;
if (keyring_key->type != &key_type_logon) {
printk_once(KERN_WARNING
"%s: key type must be logon\n", __func__);
res = -ENOKEY;
goto out;
}
ukp = user_key_payload_locked(keyring_key);
if (!ukp) {
/* key was revoked before we acquired its semaphore */
res = -EKEYREVOKED;
goto out;
}
if (ukp->datalen != sizeof(struct fscrypt_key)) {
res = -EINVAL;
goto out;
}
master_key = (struct fscrypt_key *)ukp->data;
BUILD_BUG_ON(FS_AES_128_ECB_KEY_SIZE != FS_KEY_DERIVATION_NONCE_SIZE);
down_read(&key->sem);
ukp = user_key_payload_locked(key);
if (master_key->size < min_keysize || master_key->size > FS_MAX_KEY_SIZE
|| master_key->size % AES_BLOCK_SIZE != 0) {
printk_once(KERN_WARNING
"%s: key size incorrect: %d\n",
__func__, master_key->size);
res = -ENOKEY;
goto out;
if (!ukp) /* was the key revoked before we acquired its semaphore? */
goto invalid;
payload = (const struct fscrypt_key *)ukp->data;
if (ukp->datalen != sizeof(struct fscrypt_key) ||
payload->size < 1 || payload->size > FS_MAX_KEY_SIZE) {
fscrypt_warn(NULL,
"key with description '%s' has invalid payload",
key->description);
goto invalid;
}
if (payload->size < min_keysize) {
fscrypt_warn(NULL,
"key with description '%s' is too short (got %u bytes, need %u+ bytes)",
key->description, payload->size, min_keysize);
goto invalid;
}
*payload_ret = payload;
return key;
invalid:
up_read(&key->sem);
key_put(key);
return ERR_PTR(-ENOKEY);
}
/* Find the master key, then derive the inode's actual encryption key */
static int find_and_derive_key(const struct inode *inode,
const struct fscrypt_context *ctx,
u8 *derived_key, unsigned int derived_keysize)
{
struct key *key;
const struct fscrypt_key *payload;
int err;
key = find_and_lock_process_key(FS_KEY_DESC_PREFIX,
ctx->master_key_descriptor,
derived_keysize, &payload);
if (key == ERR_PTR(-ENOKEY) && inode->i_sb->s_cop->key_prefix) {
key = find_and_lock_process_key(inode->i_sb->s_cop->key_prefix,
ctx->master_key_descriptor,
derived_keysize, &payload);
}
if (IS_ERR(key))
return PTR_ERR(key);
/* If we don't need to derive, we still want to do everything
* up until now to validate the key. It's cleaner to fail now
* than to fail in block I/O.
*/
if (!is_private_data_mode(crypt_info)) {
res = derive_key_aes(ctx->nonce, master_key,
crypt_info->ci_raw_key);
} else {
if (S_ISREG(inode->i_mode) && is_private_data_mode(ctx)) {
/* Inline encryption: no key derivation required because IVs are
* assigned based on iv_sector.
*/
BUILD_BUG_ON(sizeof(crypt_info->ci_raw_key) !=
sizeof(master_key->raw));
memcpy(crypt_info->ci_raw_key,
master_key->raw, sizeof(crypt_info->ci_raw_key));
res = 0;
if (derived_keysize != sizeof(payload->raw)) {
err = -ENOKEY;
} else {
memcpy(derived_key, payload->raw, derived_keysize);
err = 0;
}
} else {
err = derive_key_aes(payload->raw, ctx, derived_key, derived_keysize);
}
out:
up_read(&keyring_key->sem);
key_put(keyring_key);
return res;
up_read(&key->sem);
key_put(key);
return err;
}
static const struct {
static struct fscrypt_mode {
const char *friendly_name;
const char *cipher_str;
int keysize;
bool logged_impl_name;
} available_modes[] = {
[FS_ENCRYPTION_MODE_AES_256_XTS] = { "xts(aes)",
FS_AES_256_XTS_KEY_SIZE },
[FS_ENCRYPTION_MODE_AES_256_CTS] = { "cts(cbc(aes))",
FS_AES_256_CTS_KEY_SIZE },
[FS_ENCRYPTION_MODE_AES_128_CBC] = { "cbc(aes)",
FS_AES_128_CBC_KEY_SIZE },
[FS_ENCRYPTION_MODE_AES_128_CTS] = { "cts(cbc(aes))",
FS_AES_128_CTS_KEY_SIZE },
[FS_ENCRYPTION_MODE_SPECK128_256_XTS] = { "xts(speck128)", 64 },
[FS_ENCRYPTION_MODE_SPECK128_256_CTS] = { "cts(cbc(speck128))", 32 },
[FS_ENCRYPTION_MODE_PRIVATE] = { "bugon",
FS_AES_256_XTS_KEY_SIZE },
[FS_ENCRYPTION_MODE_AES_256_XTS] = {
.friendly_name = "AES-256-XTS",
.cipher_str = "xts(aes)",
.keysize = 64,
},
[FS_ENCRYPTION_MODE_AES_256_CTS] = {
.friendly_name = "AES-256-CTS-CBC",
.cipher_str = "cts(cbc(aes))",
.keysize = 32,
},
[FS_ENCRYPTION_MODE_AES_128_CBC] = {
.friendly_name = "AES-128-CBC",
.cipher_str = "cbc(aes)",
.keysize = 16,
},
[FS_ENCRYPTION_MODE_AES_128_CTS] = {
.friendly_name = "AES-128-CTS-CBC",
.cipher_str = "cts(cbc(aes))",
.keysize = 16,
},
[FS_ENCRYPTION_MODE_SPECK128_256_XTS] = {
.friendly_name = "Speck128/256-XTS",
.cipher_str = "xts(speck128)",
.keysize = 64,
},
[FS_ENCRYPTION_MODE_SPECK128_256_CTS] = {
.friendly_name = "Speck128/256-CTS-CBC",
.cipher_str = "cts(cbc(speck128))",
.keysize = 32,
},
[FS_ENCRYPTION_MODE_PRIVATE] = {
.friendly_name = "ICE",
.cipher_str = "bugon",
.keysize = 64,
},
};
static int determine_cipher_type(struct fscrypt_info *ci, struct inode *inode,
const char **cipher_str_ret, int *keysize_ret)
static struct fscrypt_mode *
select_encryption_mode(const struct fscrypt_info *ci, const struct inode *inode)
{
u32 mode;
if (!fscrypt_valid_enc_modes(ci->ci_data_mode, ci->ci_filename_mode)) {
pr_warn_ratelimited("fscrypt: inode %lu uses unsupported encryption modes (contents mode %d, filenames mode %d)\n",
inode->i_ino,
ci->ci_data_mode, ci->ci_filename_mode);
return -EINVAL;
fscrypt_warn(inode->i_sb,
"inode %lu uses unsupported encryption modes (contents mode %d, filenames mode %d)",
inode->i_ino, ci->ci_data_mode,
ci->ci_filename_mode);
return ERR_PTR(-EINVAL);
}
if (S_ISREG(inode->i_mode)) {
ci->ci_mode = CI_DATA_MODE;
mode = ci->ci_data_mode;
} else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) {
ci->ci_mode = CI_FNAME_MODE;
mode = ci->ci_filename_mode;
} else {
WARN_ONCE(1, "fscrypt: filesystem tried to load encryption info for inode %lu, which is not encryptable (file type %d)\n",
inode->i_ino, (inode->i_mode & S_IFMT));
return -EINVAL;
}
if (S_ISREG(inode->i_mode))
return &available_modes[ci->ci_data_mode];
*cipher_str_ret = available_modes[mode].cipher_str;
*keysize_ret = available_modes[mode].keysize;
return 0;
if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
return &available_modes[ci->ci_filename_mode];
WARN_ONCE(1, "fscrypt: filesystem tried to load encryption info for inode %lu, which is not encryptable (file type %d)\n",
inode->i_ino, (inode->i_mode & S_IFMT));
return ERR_PTR(-EINVAL);
}
static void put_crypt_info(struct fscrypt_info *ci)
@ -209,8 +252,9 @@ static int derive_essiv_salt(const u8 *key, int keysize, u8 *salt)
tfm = crypto_alloc_shash("sha256", 0, 0);
if (IS_ERR(tfm)) {
pr_warn_ratelimited("fscrypt: error allocating SHA-256 transform: %ld\n",
PTR_ERR(tfm));
fscrypt_warn(NULL,
"error allocating SHA-256 transform: %ld",
PTR_ERR(tfm));
return PTR_ERR(tfm);
}
prev_tfm = cmpxchg(&essiv_hash_tfm, NULL, tfm);
@ -271,13 +315,18 @@ static int fscrypt_data_encryption_mode(struct inode *inode)
FS_ENCRYPTION_MODE_PRIVATE : FS_ENCRYPTION_MODE_AES_256_XTS;
}
int fscrypt_get_mode_key_size(int mode)
{
return available_modes[mode].keysize;
}
EXPORT_SYMBOL(fscrypt_get_mode_key_size);
int fscrypt_get_encryption_info(struct inode *inode)
{
struct fscrypt_info *crypt_info;
struct fscrypt_context ctx;
struct crypto_skcipher *ctfm;
const char *cipher_str;
int keysize;
struct fscrypt_mode *mode;
u8 *raw_key = NULL;
int res;
@ -322,77 +371,76 @@ int fscrypt_get_encryption_info(struct inode *inode)
memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
sizeof(crypt_info->ci_master_key));
res = determine_cipher_type(crypt_info, inode, &cipher_str, &keysize);
if (res)
mode = select_encryption_mode(crypt_info, inode);
if (IS_ERR(mode)) {
res = PTR_ERR(mode);
goto out;
}
/*
* This cannot be a stack buffer because it is passed to the scatterlist
* crypto API as part of key derivation.
*/
res = -ENOMEM;
raw_key = kmalloc(FS_MAX_KEY_SIZE, GFP_NOFS);
raw_key = kmalloc(mode->keysize, GFP_NOFS);
if (!raw_key)
goto out;
res = validate_user_key(crypt_info, &ctx, FS_KEY_DESC_PREFIX,
keysize);
if (res && inode->i_sb->s_cop->key_prefix) {
int res2 = validate_user_key(crypt_info, &ctx,
inode->i_sb->s_cop->key_prefix,
keysize);
if (res2) {
if (res2 == -ENOKEY)
res = -ENOKEY;
goto out;
}
res = 0;
} else if (res) {
goto out;
}
if (is_private_data_mode(crypt_info)) {
if (S_ISREG(inode->i_mode) && is_private_data_mode(&ctx)) {
if (!fscrypt_is_ice_capable(inode->i_sb)) {
pr_warn("%s: ICE support not available\n",
__func__);
res = -EINVAL;
goto out;
}
res = find_and_derive_key(inode, &ctx, crypt_info->ci_raw_key, mode->keysize);
if (res)
goto out;
/* Let's encrypt/decrypt by ICE */
goto do_ice;
}
} else {
res = find_and_derive_key(inode, &ctx, raw_key, mode->keysize);
if (res)
goto out;
}
ctfm = crypto_alloc_skcipher(cipher_str, 0, 0);
if (!ctfm || IS_ERR(ctfm)) {
res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
pr_debug("%s: error %d (inode %lu) allocating crypto tfm\n",
__func__, res, inode->i_ino);
ctfm = crypto_alloc_skcipher(mode->cipher_str, 0, 0);
if (IS_ERR(ctfm)) {
res = PTR_ERR(ctfm);
fscrypt_warn(inode->i_sb,
"error allocating '%s' transform for inode %lu: %d",
mode->cipher_str, inode->i_ino, res);
goto out;
}
if (unlikely(!mode->logged_impl_name)) {
/*
* fscrypt performance can vary greatly depending on which
* crypto algorithm implementation is used. Help people debug
* performance problems by logging the ->cra_driver_name the
* first time a mode is used. Note that multiple threads can
* race here, but it doesn't really matter.
*/
mode->logged_impl_name = true;
pr_info("fscrypt: %s using implementation \"%s\"\n",
mode->friendly_name,
crypto_skcipher_alg(ctfm)->base.cra_driver_name);
}
crypt_info->ci_ctfm = ctfm;
crypto_skcipher_clear_flags(ctfm, ~0);
crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_REQ_WEAK_KEY);
/*
* if the provided key is longer than keysize, we use the first
* keysize bytes of the derived key only
*/
res = crypto_skcipher_setkey(ctfm, crypt_info->ci_raw_key, keysize);
res = crypto_skcipher_setkey(ctfm, raw_key, mode->keysize);
if (res)
goto out;
if (S_ISREG(inode->i_mode) &&
crypt_info->ci_data_mode == FS_ENCRYPTION_MODE_AES_128_CBC) {
res = init_essiv_generator(crypt_info, crypt_info->ci_raw_key,
keysize);
res = init_essiv_generator(crypt_info, raw_key, mode->keysize);
if (res) {
pr_debug("%s: error %d (inode %lu) allocating essiv tfm\n",
__func__, res, inode->i_ino);
fscrypt_warn(inode->i_sb,
"error initializing ESSIV generator for inode %lu: %d",
inode->i_ino, res);
goto out;
}
}
memzero_explicit(crypt_info->ci_raw_key,
sizeof(crypt_info->ci_raw_key));
do_ice:
if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) == NULL)
crypt_info = NULL;

14
fs/ext4/inode.c
View File

@ -2642,24 +2642,14 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
mpd->map.m_len = 0;
mpd->next_page = index;
while (index <= end) {
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
tag);
if (nr_pages == 0)
goto out;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/*
* At this point, the page may be truncated or
* invalidated (changing page->mapping to NULL), or
* even swizzled back from swapper_space to tmpfs file
* mapping. However, page->index will not change
* because we have a reference on the page.
*/
if (page->index > end)
goto out;
/*
* Accumulated enough dirty pages? This doesn't apply
* to WB_SYNC_ALL mode. For integrity sync we have to

22
fs/ext4/namei.c
View File

@ -1545,24 +1545,14 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
struct inode *inode;
struct ext4_dir_entry_2 *de;
struct buffer_head *bh;
int err;
if (ext4_encrypted_inode(dir)) {
int res = fscrypt_get_encryption_info(dir);
err = fscrypt_prepare_lookup(dir, dentry, flags);
if (err)
return ERR_PTR(err);
/*
* DCACHE_ENCRYPTED_WITH_KEY is set if the dentry is
* created while the directory was encrypted and we
* have access to the key.
*/
if (fscrypt_has_encryption_key(dir))
fscrypt_set_encrypted_dentry(dentry);
fscrypt_set_d_op(dentry);
if (res && res != -ENOKEY)
return ERR_PTR(res);
}
if (dentry->d_name.len > EXT4_NAME_LEN)
return ERR_PTR(-ENAMETOOLONG);
if (dentry->d_name.len > EXT4_NAME_LEN)
return ERR_PTR(-ENAMETOOLONG);
bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL);
if (IS_ERR(bh))

14
fs/ext4/super.c
View File

@ -1275,25 +1275,13 @@ static bool ext4_dummy_context(struct inode *inode)
return DUMMY_ENCRYPTION_ENABLED(EXT4_SB(inode->i_sb));
}
static unsigned ext4_max_namelen(struct inode *inode)
{
return S_ISLNK(inode->i_mode) ? inode->i_sb->s_blocksize :
EXT4_NAME_LEN;
}
static inline bool ext4_is_encrypted(struct inode *inode)
{
return ext4_encrypted_inode(inode);
}
static const struct fscrypt_operations ext4_cryptops = {
.key_prefix = "ext4:",
.get_context = ext4_get_context,
.set_context = ext4_set_context,
.dummy_context = ext4_dummy_context,
.empty_dir = ext4_empty_dir,
.max_namelen = ext4_max_namelen,
.is_encrypted = ext4_is_encrypted,
.max_namelen = EXT4_NAME_LEN,
};
#endif

154
fs/f2fs/checkpoint.c
View File

@ -24,7 +24,7 @@
#include <trace/events/f2fs.h>
static struct kmem_cache *ino_entry_slab;
struct kmem_cache *inode_entry_slab;
struct kmem_cache *f2fs_inode_entry_slab;
void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
{
@ -36,7 +36,7 @@ void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
/*
* We guarantee no failure on the returned page.
*/
struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
{
struct address_space *mapping = META_MAPPING(sbi);
struct page *page = NULL;
@ -105,7 +105,7 @@ out:
return page;
}
struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
{
return __get_meta_page(sbi, index, true);
}
@ -127,7 +127,7 @@ retry:
}
/* for POR only */
struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index)
struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index)
{
return __get_meta_page(sbi, index, false);
}
@ -179,7 +179,7 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
/*
* Readahead CP/NAT/SIT/SSA pages
*/
int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
int type, bool sync)
{
struct page *page;
@ -245,7 +245,7 @@ out:
return blkno - start;
}
void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index)
void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index)
{
struct page *page;
bool readahead = false;
@ -256,7 +256,7 @@ void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index)
f2fs_put_page(page, 0);
if (readahead)
ra_meta_pages(sbi, index, BIO_MAX_PAGES, META_POR, true);
f2fs_ra_meta_pages(sbi, index, BIO_MAX_PAGES, META_POR, true);
}
static int __f2fs_write_meta_page(struct page *page,
@ -277,7 +277,7 @@ static int __f2fs_write_meta_page(struct page *page,
if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0))
goto redirty_out;
write_meta_page(sbi, page, io_type);
f2fs_do_write_meta_page(sbi, page, io_type);
dec_page_count(sbi, F2FS_DIRTY_META);
if (wbc->for_reclaim)
@ -322,7 +322,7 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
trace_f2fs_writepages(mapping->host, wbc, META);
diff = nr_pages_to_write(sbi, META, wbc);
written = sync_meta_pages(sbi, META, wbc->nr_to_write, FS_META_IO);
written = f2fs_sync_meta_pages(sbi, META, wbc->nr_to_write, FS_META_IO);
mutex_unlock(&sbi->cp_mutex);
wbc->nr_to_write = max((long)0, wbc->nr_to_write - written - diff);
return 0;
@ -333,13 +333,14 @@ skip_write:
return 0;
}
long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
long f2fs_sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
long nr_to_write, enum iostat_type io_type)
{
struct address_space *mapping = META_MAPPING(sbi);
pgoff_t index = 0, end = ULONG_MAX, prev = ULONG_MAX;
pgoff_t index = 0, prev = ULONG_MAX;
struct pagevec pvec;
long nwritten = 0;
int nr_pages;
struct writeback_control wbc = {
.for_reclaim = 0,
};
@ -349,13 +350,9 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
blk_start_plug(&plug);
while (index <= end) {
int i, nr_pages;
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_DIRTY,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (unlikely(nr_pages == 0))
break;
while ((nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_DIRTY))) {
int i;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
@ -486,20 +483,20 @@ static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
spin_unlock(&im->ino_lock);
}
void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
void f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
{
/* add new dirty ino entry into list */
__add_ino_entry(sbi, ino, 0, type);
}
void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
{
/* remove dirty ino entry from list */
__remove_ino_entry(sbi, ino, type);
}
/* mode should be APPEND_INO or UPDATE_INO */
bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode)
bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode)
{
struct inode_management *im = &sbi->im[mode];
struct ino_entry *e;
@ -510,7 +507,7 @@ bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode)
return e ? true : false;
}
void release_ino_entry(struct f2fs_sb_info *sbi, bool all)
void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all)
{
struct ino_entry *e, *tmp;
int i;
@ -529,13 +526,13 @@ void release_ino_entry(struct f2fs_sb_info *sbi, bool all)
}
}
void set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
void f2fs_set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
unsigned int devidx, int type)
{
__add_ino_entry(sbi, ino, devidx, type);
}
bool is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
unsigned int devidx, int type)
{
struct inode_management *im = &sbi->im[type];
@ -550,7 +547,7 @@ bool is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
return is_dirty;
}
int acquire_orphan_inode(struct f2fs_sb_info *sbi)
int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi)
{
struct inode_management *im = &sbi->im[ORPHAN_INO];
int err = 0;
@ -573,7 +570,7 @@ int acquire_orphan_inode(struct f2fs_sb_info *sbi)
return err;
}
void release_orphan_inode(struct f2fs_sb_info *sbi)
void f2fs_release_orphan_inode(struct f2fs_sb_info *sbi)
{
struct inode_management *im = &sbi->im[ORPHAN_INO];
@ -583,14 +580,14 @@ void release_orphan_inode(struct f2fs_sb_info *sbi)
spin_unlock(&im->ino_lock);
}
void add_orphan_inode(struct inode *inode)
void f2fs_add_orphan_inode(struct inode *inode)
{
/* add new orphan ino entry into list */
__add_ino_entry(F2FS_I_SB(inode), inode->i_ino, 0, ORPHAN_INO);
update_inode_page(inode);
f2fs_update_inode_page(inode);
}
void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
void f2fs_remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
/* remove orphan entry from orphan list */
__remove_ino_entry(sbi, ino, ORPHAN_INO);
@ -600,7 +597,7 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
struct inode *inode;
struct node_info ni;
int err = acquire_orphan_inode(sbi);
int err = f2fs_acquire_orphan_inode(sbi);
if (err)
goto err_out;
@ -618,16 +615,17 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
}
err = dquot_initialize(inode);
if (err)
if (err) {
iput(inode);
goto err_out;
}
dquot_initialize(inode);
clear_nlink(inode);
/* truncate all the data during iput */
iput(inode);
err = get_node_info(sbi, ino, &ni);
err = f2fs_get_node_info(sbi, ino, &ni);
if (err)
goto err_out;
@ -647,7 +645,7 @@ err_out:
return err;
}
int recover_orphan_inodes(struct f2fs_sb_info *sbi)
int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
{
block_t start_blk, orphan_blocks, i, j;
unsigned int s_flags = sbi->sb->s_flags;
@ -675,13 +673,13 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi)
start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi);
orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi);
ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true);
f2fs_ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true);
for (i = 0; i < orphan_blocks; i++) {
struct page *page;
struct f2fs_orphan_block *orphan_blk;
page = get_meta_page(sbi, start_blk + i);
page = f2fs_get_meta_page(sbi, start_blk + i);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto out;
@ -734,7 +732,7 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
/* loop for each orphan inode entry and write them in Jornal block */
list_for_each_entry(orphan, head, list) {
if (!page) {
page = grab_meta_page(sbi, start_blk++);
page = f2fs_grab_meta_page(sbi, start_blk++);
orphan_blk =
(struct f2fs_orphan_block *)page_address(page);
memset(orphan_blk, 0, sizeof(*orphan_blk));
@ -776,7 +774,7 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
size_t crc_offset = 0;
__u32 crc = 0;
*cp_page = get_meta_page(sbi, cp_addr);
*cp_page = f2fs_get_meta_page(sbi, cp_addr);
if (IS_ERR(*cp_page))
return PTR_ERR(*cp_page);
@ -841,7 +839,7 @@ invalid_cp:
return NULL;
}
int get_valid_checkpoint(struct f2fs_sb_info *sbi)
int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
{
struct f2fs_checkpoint *cp_block;
struct f2fs_super_block *fsb = sbi->raw_super;
@ -853,7 +851,8 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
block_t cp_blk_no;
int i;
sbi->ckpt = f2fs_kzalloc(sbi, cp_blks * blk_size, GFP_KERNEL);
sbi->ckpt = f2fs_kzalloc(sbi, array_size(blk_size, cp_blks),
GFP_KERNEL);
if (!sbi->ckpt)
return -ENOMEM;
/*
@ -890,7 +889,7 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
sbi->cur_cp_pack = 2;
/* Sanity checking of checkpoint */
if (sanity_check_ckpt(sbi))
if (f2fs_sanity_check_ckpt(sbi))
goto free_fail_no_cp;
if (cp_blks <= 1)
@ -904,7 +903,7 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
void *sit_bitmap_ptr;
unsigned char *ckpt = (unsigned char *)sbi->ckpt;
cur_page = get_meta_page(sbi, cp_blk_no + i);
cur_page = f2fs_get_meta_page(sbi, cp_blk_no + i);
if (IS_ERR(cur_page))
goto free_fail_no_cp;
sit_bitmap_ptr = page_address(cur_page);
@ -951,7 +950,7 @@ static void __remove_dirty_inode(struct inode *inode, enum inode_type type)
stat_dec_dirty_inode(F2FS_I_SB(inode), type);
}
void update_dirty_page(struct inode *inode, struct page *page)
void f2fs_update_dirty_page(struct inode *inode, struct page *page)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;
@ -970,7 +969,7 @@ void update_dirty_page(struct inode *inode, struct page *page)
f2fs_trace_pid(page);
}
void remove_dirty_inode(struct inode *inode)
void f2fs_remove_dirty_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;
@ -987,7 +986,7 @@ void remove_dirty_inode(struct inode *inode)
spin_unlock(&sbi->inode_lock[type]);
}
int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
{
struct list_head *head;
struct inode *inode;
@ -1070,7 +1069,7 @@ int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
/* it's on eviction */
if (is_inode_flag_set(inode, FI_DIRTY_INODE))
update_inode_page(inode);
f2fs_update_inode_page(inode);
iput(inode);
}
}
@ -1110,7 +1109,7 @@ retry_flush_dents:
/* write all the dirty dentry pages */
if (get_pages(sbi, F2FS_DIRTY_DENTS)) {
f2fs_unlock_all(sbi);
err = sync_dirty_inodes(sbi, DIR_INODE);
err = f2fs_sync_dirty_inodes(sbi, DIR_INODE);
if (err)
goto out;
cond_resched();
@ -1138,7 +1137,9 @@ retry_flush_nodes:
if (get_pages(sbi, F2FS_DIRTY_NODES)) {
up_write(&sbi->node_write);
err = sync_node_pages(sbi, &wbc, false, FS_CP_NODE_IO);
atomic_inc(&sbi->wb_sync_req[NODE]);
err = f2fs_sync_node_pages(sbi, &wbc, false, FS_CP_NODE_IO);
atomic_dec(&sbi->wb_sync_req[NODE]);
if (err) {
up_write(&sbi->node_change);
f2fs_unlock_all(sbi);
@ -1232,10 +1233,10 @@ static void commit_checkpoint(struct f2fs_sb_info *sbi,
/*
* pagevec_lookup_tag and lock_page again will take
* some extra time. Therefore, update_meta_pages and
* sync_meta_pages are combined in this function.
* some extra time. Therefore, f2fs_update_meta_pages and
* f2fs_sync_meta_pages are combined in this function.
*/
struct page *page = grab_meta_page(sbi, blk_addr);
struct page *page = f2fs_grab_meta_page(sbi, blk_addr);
int err;
memcpy(page_address(page), src, PAGE_SIZE);
@ -1273,7 +1274,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/* Flush all the NAT/SIT pages */
while (get_pages(sbi, F2FS_DIRTY_META)) {
sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
}
@ -1282,7 +1283,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
* modify checkpoint
* version number is already updated
*/
ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi));
ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi, true));
ckpt->free_segment_count = cpu_to_le32(free_segments(sbi));
for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
ckpt->cur_node_segno[i] =
@ -1302,7 +1303,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
}
/* 2 cp + n data seg summary + orphan inode blocks */
data_sum_blocks = npages_for_summary_flush(sbi, false);
data_sum_blocks = f2fs_npages_for_summary_flush(sbi, false);
spin_lock_irqsave(&sbi->cp_lock, flags);
if (data_sum_blocks < NR_CURSEG_DATA_TYPE)
__set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
@ -1347,22 +1348,23 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
blk = start_blk + sbi->blocks_per_seg - nm_i->nat_bits_blocks;
for (i = 0; i < nm_i->nat_bits_blocks; i++)
update_meta_page(sbi, nm_i->nat_bits +
f2fs_update_meta_page(sbi, nm_i->nat_bits +
(i << F2FS_BLKSIZE_BITS), blk + i);
/* Flush all the NAT BITS pages */
while (get_pages(sbi, F2FS_DIRTY_META)) {
sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
f2fs_sync_meta_pages(sbi, META, LONG_MAX,
FS_CP_META_IO);
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
}
}
/* write out checkpoint buffer at block 0 */
update_meta_page(sbi, ckpt, start_blk++);
f2fs_update_meta_page(sbi, ckpt, start_blk++);
for (i = 1; i < 1 + cp_payload_blks; i++)
update_meta_page(sbi, (char *)ckpt + i * F2FS_BLKSIZE,
f2fs_update_meta_page(sbi, (char *)ckpt + i * F2FS_BLKSIZE,
start_blk++);
if (orphan_num) {
@ -1370,7 +1372,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
start_blk += orphan_blocks;
}
write_data_summaries(sbi, start_blk);
f2fs_write_data_summaries(sbi, start_blk);
start_blk += data_sum_blocks;
/* Record write statistics in the hot node summary */
@ -1381,7 +1383,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
seg_i->journal->info.kbytes_written = cpu_to_le64(kbytes_written);
if (__remain_node_summaries(cpc->reason)) {
write_node_summaries(sbi, start_blk);
f2fs_write_node_summaries(sbi, start_blk);
start_blk += NR_CURSEG_NODE_TYPE;
}
@ -1390,7 +1392,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
percpu_counter_set(&sbi->alloc_valid_block_count, 0);
/* Here, we have one bio having CP pack except cp pack 2 page */
sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
/* wait for previous submitted meta pages writeback */
wait_on_all_pages_writeback(sbi);
@ -1407,7 +1409,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
commit_checkpoint(sbi, ckpt, start_blk);
wait_on_all_pages_writeback(sbi);
release_ino_entry(sbi, false);
f2fs_release_ino_entry(sbi, false);
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
@ -1432,7 +1434,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/*
* We guarantee that this checkpoint procedure will not fail.
*/
int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
unsigned long long ckpt_ver;
@ -1465,7 +1467,7 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/* this is the case of multiple fstrims without any changes */
if (cpc->reason & CP_DISCARD) {
if (!exist_trim_candidates(sbi, cpc)) {
if (!f2fs_exist_trim_candidates(sbi, cpc)) {
unblock_operations(sbi);
goto out;
}
@ -1473,8 +1475,8 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
if (NM_I(sbi)->dirty_nat_cnt == 0 &&
SIT_I(sbi)->dirty_sentries == 0 &&
prefree_segments(sbi) == 0) {
flush_sit_entries(sbi, cpc);
clear_prefree_segments(sbi, cpc);
f2fs_flush_sit_entries(sbi, cpc);
f2fs_clear_prefree_segments(sbi, cpc);
unblock_operations(sbi);
goto out;
}
@ -1489,18 +1491,18 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver);
/* write cached NAT/SIT entries to NAT/SIT area */
err = flush_nat_entries(sbi, cpc);
err = f2fs_flush_nat_entries(sbi, cpc);
if (err)
goto stop;
flush_sit_entries(sbi, cpc);
f2fs_flush_sit_entries(sbi, cpc);
/* unlock all the fs_lock[] in do_checkpoint() */
err = do_checkpoint(sbi, cpc);
if (err)
release_discard_addrs(sbi);
f2fs_release_discard_addrs(sbi);
else
clear_prefree_segments(sbi, cpc);
f2fs_clear_prefree_segments(sbi, cpc);
stop:
unblock_operations(sbi);
stat_inc_cp_count(sbi->stat_info);
@ -1517,7 +1519,7 @@ out:
return err;
}
void init_ino_entry_info(struct f2fs_sb_info *sbi)
void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi)
{
int i;
@ -1535,23 +1537,23 @@ void init_ino_entry_info(struct f2fs_sb_info *sbi)
F2FS_ORPHANS_PER_BLOCK;
}
int __init create_checkpoint_caches(void)
int __init f2fs_create_checkpoint_caches(void)
{
ino_entry_slab = f2fs_kmem_cache_create("f2fs_ino_entry",
sizeof(struct ino_entry));
if (!ino_entry_slab)
return -ENOMEM;
inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry",
f2fs_inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry",
sizeof(struct inode_entry));
if (!inode_entry_slab) {
if (!f2fs_inode_entry_slab) {
kmem_cache_destroy(ino_entry_slab);
return -ENOMEM;
}
return 0;
}
void destroy_checkpoint_caches(void)
void f2fs_destroy_checkpoint_caches(void)
{
kmem_cache_destroy(ino_entry_slab);
kmem_cache_destroy(inode_entry_slab);
kmem_cache_destroy(f2fs_inode_entry_slab);
}

175
fs/f2fs/data.c
View File

@ -49,6 +49,8 @@ static bool __is_cp_guaranteed(struct page *page)
if (inode->i_ino == F2FS_META_INO(sbi) ||
inode->i_ino == F2FS_NODE_INO(sbi) ||
S_ISDIR(inode->i_mode) ||
(S_ISREG(inode->i_mode) &&
is_inode_flag_set(inode, FI_ATOMIC_FILE)) ||
is_cold_data(page))
return true;
return false;
@ -246,7 +248,7 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
} else {
bio->bi_end_io = f2fs_write_end_io;
bio->bi_private = sbi;
bio->bi_write_hint = io_type_to_rw_hint(sbi, type, temp);
bio->bi_write_hint = f2fs_io_type_to_rw_hint(sbi, type, temp);
}
if (wbc)
wbc_init_bio(wbc, bio);
@ -470,7 +472,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
return 0;
}
int f2fs_submit_page_write(struct f2fs_io_info *fio)
void f2fs_submit_page_write(struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = fio->sbi;
enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
@ -480,7 +482,6 @@ int f2fs_submit_page_write(struct f2fs_io_info *fio)
bool bio_encrypted;
int bi_crypt_skip;
u64 dun;
int err = 0;
f2fs_bug_on(sbi, is_read_io(fio->op));
@ -490,7 +491,7 @@ next:
spin_lock(&io->io_lock);
if (list_empty(&io->io_list)) {
spin_unlock(&io->io_lock);
goto out_fail;
goto out;
}
fio = list_first_entry(&io->io_list,
struct f2fs_io_info, list);
@ -527,9 +528,9 @@ alloc_new:
if (io->bio == NULL) {
if ((fio->type == DATA || fio->type == NODE) &&
fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) {
err = -EAGAIN;
dec_page_count(sbi, WB_DATA_TYPE(bio_page));
goto out_fail;
fio->retry = true;
goto skip;
}
io->bio = __bio_alloc(sbi, fio->new_blkaddr, fio->io_wbc,
BIO_MAX_PAGES, false,
@ -552,12 +553,11 @@ alloc_new:
f2fs_trace_ios(fio, 0);
trace_f2fs_submit_page_write(fio->page, fio);
skip:
if (fio->in_list)
goto next;
out_fail:
out:
up_write(&io->io_rwsem);
return err;
}
static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
@ -641,7 +641,7 @@ static void __set_data_blkaddr(struct dnode_of_data *dn)
* ->node_page
* update block addresses in the node page
*/
void set_data_blkaddr(struct dnode_of_data *dn)
void f2fs_set_data_blkaddr(struct dnode_of_data *dn)
{
f2fs_wait_on_page_writeback(dn->node_page, NODE, true);
__set_data_blkaddr(dn);
@ -652,12 +652,12 @@ void set_data_blkaddr(struct dnode_of_data *dn)
void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
{
dn->data_blkaddr = blkaddr;
set_data_blkaddr(dn);
f2fs_set_data_blkaddr(dn);
f2fs_update_extent_cache(dn);
}
/* dn->ofs_in_node will be returned with up-to-date last block pointer */
int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
int err;
@ -691,12 +691,12 @@ int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
}
/* Should keep dn->ofs_in_node unchanged */
int reserve_new_block(struct dnode_of_data *dn)
int f2fs_reserve_new_block(struct dnode_of_data *dn)
{
unsigned int ofs_in_node = dn->ofs_in_node;
int ret;
ret = reserve_new_blocks(dn, 1);
ret = f2fs_reserve_new_blocks(dn, 1);
dn->ofs_in_node = ofs_in_node;
return ret;
}
@ -706,12 +706,12 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
bool need_put = dn->inode_page ? false : true;
int err;
err = get_dnode_of_data(dn, index, ALLOC_NODE);
err = f2fs_get_dnode_of_data(dn, index, ALLOC_NODE);
if (err)
return err;
if (dn->data_blkaddr == NULL_ADDR)
err = reserve_new_block(dn);
err = f2fs_reserve_new_block(dn);
if (err || need_put)
f2fs_put_dnode(dn);
return err;
@ -730,7 +730,7 @@ int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index)
return f2fs_reserve_block(dn, index);
}
struct page *get_read_data_page(struct inode *inode, pgoff_t index,
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
int op_flags, bool for_write)
{
struct address_space *mapping = inode->i_mapping;
@ -749,7 +749,7 @@ struct page *get_read_data_page(struct inode *inode, pgoff_t index,
}
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
if (err)
goto put_err;
f2fs_put_dnode(&dn);
@ -768,7 +768,8 @@ got_it:
* A new dentry page is allocated but not able to be written, since its
* new inode page couldn't be allocated due to -ENOSPC.
* In such the case, its blkaddr can be remained as NEW_ADDR.
* see, f2fs_add_link -> get_new_data_page -> init_inode_metadata.
* see, f2fs_add_link -> f2fs_get_new_data_page ->
* f2fs_init_inode_metadata.
*/
if (dn.data_blkaddr == NEW_ADDR) {
zero_user_segment(page, 0, PAGE_SIZE);
@ -788,7 +789,7 @@ put_err:
return ERR_PTR(err);
}
struct page *find_data_page(struct inode *inode, pgoff_t index)
struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
@ -798,7 +799,7 @@ struct page *find_data_page(struct inode *inode, pgoff_t index)
return page;
f2fs_put_page(page, 0);
page = get_read_data_page(inode, index, 0, false);
page = f2fs_get_read_data_page(inode, index, 0, false);
if (IS_ERR(page))
return page;
@ -818,13 +819,13 @@ struct page *find_data_page(struct inode *inode, pgoff_t index)
* Because, the callers, functions in dir.c and GC, should be able to know
* whether this page exists or not.
*/
struct page *get_lock_data_page(struct inode *inode, pgoff_t index,
struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index,
bool for_write)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
repeat:
page = get_read_data_page(inode, index, 0, for_write);
page = f2fs_get_read_data_page(inode, index, 0, for_write);
if (IS_ERR(page))
return page;
@ -850,7 +851,7 @@ repeat:
* Note that, ipage is set only by make_empty_dir, and if any error occur,
* ipage should be released by this function.
*/
struct page *get_new_data_page(struct inode *inode,
struct page *f2fs_get_new_data_page(struct inode *inode,
struct page *ipage, pgoff_t index, bool new_i_size)
{
struct address_space *mapping = inode->i_mapping;
@ -889,7 +890,7 @@ struct page *get_new_data_page(struct inode *inode,
/* if ipage exists, blkaddr should be NEW_ADDR */
f2fs_bug_on(F2FS_I_SB(inode), ipage);
page = get_lock_data_page(inode, index, true);
page = f2fs_get_lock_data_page(inode, index, true);
if (IS_ERR(page))
return page;
}
@ -912,7 +913,7 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return -EPERM;
err = get_node_info(sbi, dn->nid, &ni);
err = f2fs_get_node_info(sbi, dn->nid, &ni);
if (err)
return err;
@ -927,12 +928,12 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
alloc:
set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr,
f2fs_allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr,
&sum, seg_type, NULL, false);
set_data_blkaddr(dn);
f2fs_set_data_blkaddr(dn);
/* update i_size */
fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
dn->ofs_in_node;
if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_SHIFT))
f2fs_i_size_write(dn->inode,
@ -970,7 +971,7 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
map.m_seg_type = NO_CHECK_TYPE;
if (direct_io) {
map.m_seg_type = rw_hint_to_seg_type(iocb->ki_hint);
map.m_seg_type = f2fs_rw_hint_to_seg_type(iocb->ki_hint);
flag = f2fs_force_buffered_io(inode, WRITE) ?
F2FS_GET_BLOCK_PRE_AIO :
F2FS_GET_BLOCK_PRE_DIO;
@ -1060,7 +1061,7 @@ next_dnode:
/* When reading holes, we need its node page */
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, pgofs, mode);
err = f2fs_get_dnode_of_data(&dn, pgofs, mode);
if (err) {
if (flag == F2FS_GET_BLOCK_BMAP)
map->m_pblk = 0;
@ -1068,10 +1069,10 @@ next_dnode:
err = 0;
if (map->m_next_pgofs)
*map->m_next_pgofs =
get_next_page_offset(&dn, pgofs);
f2fs_get_next_page_offset(&dn, pgofs);
if (map->m_next_extent)
*map->m_next_extent =
get_next_page_offset(&dn, pgofs);
f2fs_get_next_page_offset(&dn, pgofs);
}
goto unlock_out;
}
@ -1163,7 +1164,7 @@ skip:
(pgofs == end || dn.ofs_in_node == end_offset)) {
dn.ofs_in_node = ofs_in_node;
err = reserve_new_blocks(&dn, prealloc);
err = f2fs_reserve_new_blocks(&dn, prealloc);
if (err)
goto sync_out;
@ -1282,7 +1283,7 @@ static int get_data_block_dio(struct inode *inode, sector_t iblock,
{
return __get_data_block(inode, iblock, bh_result, create,
F2FS_GET_BLOCK_DEFAULT, NULL,
rw_hint_to_seg_type(
f2fs_rw_hint_to_seg_type(
inode->i_write_hint));
}
@ -1327,7 +1328,7 @@ static int f2fs_xattr_fiemap(struct inode *inode,
if (!page)
return -ENOMEM;
err = get_node_info(sbi, inode->i_ino, &ni);
err = f2fs_get_node_info(sbi, inode->i_ino, &ni);
if (err) {
f2fs_put_page(page, 1);
return err;
@ -1359,7 +1360,7 @@ static int f2fs_xattr_fiemap(struct inode *inode,
if (!page)
return -ENOMEM;
err = get_node_info(sbi, xnid, &ni);
err = f2fs_get_node_info(sbi, xnid, &ni);
if (err) {
f2fs_put_page(page, 1);
return err;
@ -1691,12 +1692,12 @@ static inline bool check_inplace_update_policy(struct inode *inode,
if (policy & (0x1 << F2FS_IPU_FORCE))
return true;
if (policy & (0x1 << F2FS_IPU_SSR) && need_SSR(sbi))
if (policy & (0x1 << F2FS_IPU_SSR) && f2fs_need_SSR(sbi))
return true;
if (policy & (0x1 << F2FS_IPU_UTIL) &&
utilization(sbi) > SM_I(sbi)->min_ipu_util)
return true;
if (policy & (0x1 << F2FS_IPU_SSR_UTIL) && need_SSR(sbi) &&
if (policy & (0x1 << F2FS_IPU_SSR_UTIL) && f2fs_need_SSR(sbi) &&
utilization(sbi) > SM_I(sbi)->min_ipu_util)
return true;
@ -1717,7 +1718,7 @@ static inline bool check_inplace_update_policy(struct inode *inode,
return false;
}
bool should_update_inplace(struct inode *inode, struct f2fs_io_info *fio)
bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio)
{
if (f2fs_is_pinned_file(inode))
return true;
@ -1729,7 +1730,7 @@ bool should_update_inplace(struct inode *inode, struct f2fs_io_info *fio)
return check_inplace_update_policy(inode, fio);
}
bool should_update_outplace(struct inode *inode, struct f2fs_io_info *fio)
bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@ -1752,13 +1753,13 @@ static inline bool need_inplace_update(struct f2fs_io_info *fio)
{
struct inode *inode = fio->page->mapping->host;
if (should_update_outplace(inode, fio))
if (f2fs_should_update_outplace(inode, fio))
return false;
return should_update_inplace(inode, fio);
return f2fs_should_update_inplace(inode, fio);
}
int do_write_data_page(struct f2fs_io_info *fio)
int f2fs_do_write_data_page(struct f2fs_io_info *fio)
{
struct page *page = fio->page;
struct inode *inode = page->mapping->host;
@ -1786,7 +1787,7 @@ int do_write_data_page(struct f2fs_io_info *fio)
if (fio->need_lock == LOCK_REQ && !f2fs_trylock_op(fio->sbi))
return -EAGAIN;
err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
err = f2fs_get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
if (err)
goto out;
@ -1819,7 +1820,7 @@ got_it:
f2fs_put_dnode(&dn);
if (fio->need_lock == LOCK_REQ)
f2fs_unlock_op(fio->sbi);
err = rewrite_data_page(fio);
err = f2fs_inplace_write_data(fio);
trace_f2fs_do_write_data_page(fio->page, IPU);
set_inode_flag(inode, FI_UPDATE_WRITE);
return err;
@ -1833,7 +1834,7 @@ got_it:
fio->need_lock = LOCK_REQ;
}
err = get_node_info(fio->sbi, dn.nid, &ni);
err = f2fs_get_node_info(fio->sbi, dn.nid, &ni);
if (err)
goto out_writepage;
@ -1847,7 +1848,7 @@ got_it:
ClearPageError(page);
/* LFS mode write path */
write_data_page(&dn, fio);
f2fs_outplace_write_data(&dn, fio);
trace_f2fs_do_write_data_page(page, OPU);
set_inode_flag(inode, FI_APPEND_WRITE);
if (page->index == 0)
@ -1893,6 +1894,12 @@ static int __write_data_page(struct page *page, bool *submitted,
/* we should bypass data pages to proceed the kworkder jobs */
if (unlikely(f2fs_cp_error(sbi))) {
mapping_set_error(page->mapping, -EIO);
/*
* don't drop any dirty dentry pages for keeping lastest
* directory structure.
*/
if (S_ISDIR(inode->i_mode))
goto redirty_out;
goto out;
}
@ -1917,13 +1924,13 @@ write:
/* we should not write 0'th page having journal header */
if (f2fs_is_volatile_file(inode) && (!page->index ||
(!wbc->for_reclaim &&
available_free_memory(sbi, BASE_CHECK))))
f2fs_available_free_memory(sbi, BASE_CHECK))))
goto redirty_out;
/* Dentry blocks are controlled by checkpoint */
if (S_ISDIR(inode->i_mode)) {
fio.need_lock = LOCK_DONE;
err = do_write_data_page(&fio);
err = f2fs_do_write_data_page(&fio);
goto done;
}
@ -1942,10 +1949,10 @@ write:
}
if (err == -EAGAIN) {
err = do_write_data_page(&fio);
err = f2fs_do_write_data_page(&fio);
if (err == -EAGAIN) {
fio.need_lock = LOCK_REQ;
err = do_write_data_page(&fio);
err = f2fs_do_write_data_page(&fio);
}
}
@ -1970,7 +1977,7 @@ out:
if (wbc->for_reclaim) {
f2fs_submit_merged_write_cond(sbi, inode, 0, page->index, DATA);
clear_inode_flag(inode, FI_HOT_DATA);
remove_dirty_inode(inode);
f2fs_remove_dirty_inode(inode);
submitted = NULL;
}
@ -2020,6 +2027,7 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
int ret = 0;
int done = 0;
struct pagevec pvec;
struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
int nr_pages;
pgoff_t uninitialized_var(writeback_index);
pgoff_t index;
@ -2064,8 +2072,8 @@ retry:
while (!done && (index <= end)) {
int i;
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1);
nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
tag);
if (nr_pages == 0)
break;
@ -2073,7 +2081,9 @@ retry:
struct page *page = pvec.pages[i];
bool submitted = false;
if (page->index > end) {
/* give a priority to WB_SYNC threads */
if (atomic_read(&sbi->wb_sync_req[DATA]) &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
@ -2132,9 +2142,7 @@ continue_unlock:
last_idx = page->index;
}
/* give a priority to WB_SYNC threads */
if ((atomic_read(&F2FS_M_SB(mapping)->wb_sync_req) ||
--wbc->nr_to_write <= 0) &&
if (--wbc->nr_to_write <= 0 &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
@ -2172,7 +2180,7 @@ static inline bool __should_serialize_io(struct inode *inode,
return false;
}
int __f2fs_write_data_pages(struct address_space *mapping,
static int __f2fs_write_data_pages(struct address_space *mapping,
struct writeback_control *wbc,
enum iostat_type io_type)
{
@ -2196,7 +2204,7 @@ int __f2fs_write_data_pages(struct address_space *mapping,
if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE &&
get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) &&
available_free_memory(sbi, DIRTY_DENTS))
f2fs_available_free_memory(sbi, DIRTY_DENTS))
goto skip_write;
/* skip writing during file defragment */
@ -2207,8 +2215,8 @@ int __f2fs_write_data_pages(struct address_space *mapping,
/* to avoid spliting IOs due to mixed WB_SYNC_ALL and WB_SYNC_NONE */
if (wbc->sync_mode == WB_SYNC_ALL)
atomic_inc(&sbi->wb_sync_req);
else if (atomic_read(&sbi->wb_sync_req))
atomic_inc(&sbi->wb_sync_req[DATA]);
else if (atomic_read(&sbi->wb_sync_req[DATA]))
goto skip_write;
if (__should_serialize_io(inode, wbc)) {
@ -2224,13 +2232,13 @@ int __f2fs_write_data_pages(struct address_space *mapping,
mutex_unlock(&sbi->writepages);
if (wbc->sync_mode == WB_SYNC_ALL)
atomic_dec(&sbi->wb_sync_req);
atomic_dec(&sbi->wb_sync_req[DATA]);
/*
* if some pages were truncated, we cannot guarantee its mapping->host
* to detect pending bios.
*/
remove_dirty_inode(inode);
f2fs_remove_dirty_inode(inode);
return ret;
skip_write:
@ -2257,7 +2265,7 @@ static void f2fs_write_failed(struct address_space *mapping, loff_t to)
if (to > i_size) {
down_write(&F2FS_I(inode)->i_mmap_sem);
truncate_pagecache(inode, i_size);
truncate_blocks(inode, i_size, true);
f2fs_truncate_blocks(inode, i_size, true);
up_write(&F2FS_I(inode)->i_mmap_sem);
}
}
@ -2296,7 +2304,7 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi,
}
restart:
/* check inline_data */
ipage = get_node_page(sbi, inode->i_ino);
ipage = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto unlock_out;
@ -2306,7 +2314,7 @@ restart:
if (f2fs_has_inline_data(inode)) {
if (pos + len <= MAX_INLINE_DATA(inode)) {
read_inline_data(page, ipage);
f2fs_do_read_inline_data(page, ipage);
set_inode_flag(inode, FI_DATA_EXIST);
if (inode->i_nlink)
set_inline_node(ipage);
@ -2324,7 +2332,7 @@ restart:
dn.data_blkaddr = ei.blk + index - ei.fofs;
} else {
/* hole case */
err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
if (err || dn.data_blkaddr == NULL_ADDR) {
f2fs_put_dnode(&dn);
__do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO,
@ -2372,7 +2380,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
trace_f2fs_write_begin(inode, pos, len, flags);
if (f2fs_is_atomic_file(inode) &&
!available_free_memory(sbi, INMEM_PAGES)) {
!f2fs_available_free_memory(sbi, INMEM_PAGES)) {
err = -ENOMEM;
drop_atomic = true;
goto fail;
@ -2452,7 +2460,7 @@ fail:
f2fs_put_page(page, 1);
f2fs_write_failed(mapping, pos + len);
if (drop_atomic)
drop_inmem_pages_all(sbi);
f2fs_drop_inmem_pages_all(sbi, false);
return err;
}
@ -2550,17 +2558,17 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
if (rw == WRITE && whint_mode == WHINT_MODE_OFF)
iocb->ki_hint = WRITE_LIFE_NOT_SET;
if (!down_read_trylock(&F2FS_I(inode)->dio_rwsem[rw])) {
if (!down_read_trylock(&F2FS_I(inode)->i_gc_rwsem[rw])) {
if (iocb->ki_flags & IOCB_NOWAIT) {
iocb->ki_hint = hint;
err = -EAGAIN;
goto out;
}
down_read(&F2FS_I(inode)->dio_rwsem[rw]);
down_read(&F2FS_I(inode)->i_gc_rwsem[rw]);
}
err = blockdev_direct_IO(iocb, inode, iter, get_data_block_dio);
up_read(&F2FS_I(inode)->dio_rwsem[rw]);
up_read(&F2FS_I(inode)->i_gc_rwsem[rw]);
if (rw == WRITE) {
if (whint_mode == WHINT_MODE_OFF)
@ -2603,13 +2611,13 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset,
dec_page_count(sbi, F2FS_DIRTY_NODES);
} else {
inode_dec_dirty_pages(inode);
remove_dirty_inode(inode);
f2fs_remove_dirty_inode(inode);
}
}
/* This is atomic written page, keep Private */
if (IS_ATOMIC_WRITTEN_PAGE(page))
return drop_inmem_page(inode, page);
return f2fs_drop_inmem_page(inode, page);
set_page_private(page, 0);
ClearPagePrivate(page);
@ -2642,7 +2650,7 @@ static int f2fs_set_data_page_dirty(struct page *page)
if (f2fs_is_atomic_file(inode) && !f2fs_is_commit_atomic_write(inode)) {
if (!IS_ATOMIC_WRITTEN_PAGE(page)) {
register_inmem_page(inode, page);
f2fs_register_inmem_page(inode, page);
return 1;
}
/*
@ -2654,7 +2662,7 @@ static int f2fs_set_data_page_dirty(struct page *page)
if (!PageDirty(page)) {
__set_page_dirty_nobuffers(page);
update_dirty_page(inode, page);
f2fs_update_dirty_page(inode, page);
return 1;
}
return 0;
@ -2750,6 +2758,17 @@ const struct address_space_operations f2fs_dblock_aops = {
#endif
};
void f2fs_clear_radix_tree_dirty_tag(struct page *page)
{
struct address_space *mapping = page_mapping(page);
unsigned long flags;
spin_lock_irqsave(&mapping->tree_lock, flags);
radix_tree_tag_clear(&mapping->page_tree, page_index(page),
PAGECACHE_TAG_DIRTY);
spin_unlock_irqrestore(&mapping->tree_lock, flags);
}
int __init f2fs_init_post_read_processing(void)
{
bio_post_read_ctx_cache = KMEM_CACHE(bio_post_read_ctx, 0);

6
fs/f2fs/debug.c
View File

@ -104,6 +104,8 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->avail_nids = NM_I(sbi)->available_nids;
si->alloc_nids = NM_I(sbi)->nid_cnt[PREALLOC_NID];
si->bg_gc = sbi->bg_gc;
si->skipped_atomic_files[BG_GC] = sbi->skipped_atomic_files[BG_GC];
si->skipped_atomic_files[FG_GC] = sbi->skipped_atomic_files[FG_GC];
si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg)
* 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg)
/ 2;
@ -342,6 +344,10 @@ static int stat_show(struct seq_file *s, void *v)
si->bg_data_blks);
seq_printf(s, " - node blocks : %d (%d)\n", si->node_blks,
si->bg_node_blks);
seq_printf(s, "Skipped : atomic write %llu (%llu)\n",
si->skipped_atomic_files[BG_GC] +
si->skipped_atomic_files[FG_GC],
si->skipped_atomic_files[BG_GC]);
seq_puts(s, "\nExtent Cache:\n");
seq_printf(s, " - Hit Count: L1-1:%llu L1-2:%llu L2:%llu\n",
si->hit_largest, si->hit_cached,

76
fs/f2fs/dir.c
View File

@ -60,12 +60,12 @@ static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = {
[S_IFLNK >> S_SHIFT] = F2FS_FT_SYMLINK,
};
void set_de_type(struct f2fs_dir_entry *de, umode_t mode)
static void set_de_type(struct f2fs_dir_entry *de, umode_t mode)
{
de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT];
}
unsigned char get_de_type(struct f2fs_dir_entry *de)
unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de)
{
if (de->file_type < F2FS_FT_MAX)
return f2fs_filetype_table[de->file_type];
@ -97,14 +97,14 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
dentry_blk = (struct f2fs_dentry_block *)page_address(dentry_page);
make_dentry_ptr_block(NULL, &d, dentry_blk);
de = find_target_dentry(fname, namehash, max_slots, &d);
de = f2fs_find_target_dentry(fname, namehash, max_slots, &d);
if (de)
*res_page = dentry_page;
return de;
}
struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname,
f2fs_hash_t namehash, int *max_slots,
struct f2fs_dentry_ptr *d)
{
@ -171,7 +171,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
for (; bidx < end_block; bidx++) {
/* no need to allocate new dentry pages to all the indices */
dentry_page = find_data_page(dir, bidx);
dentry_page = f2fs_find_data_page(dir, bidx);
if (IS_ERR(dentry_page)) {
if (PTR_ERR(dentry_page) == -ENOENT) {
room = true;
@ -210,7 +210,7 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
if (f2fs_has_inline_dentry(dir)) {
*res_page = NULL;
de = find_in_inline_dir(dir, fname, res_page);
de = f2fs_find_in_inline_dir(dir, fname, res_page);
goto out;
}
@ -319,7 +319,7 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage)
set_page_dirty(ipage);
}
void do_make_empty_dir(struct inode *inode, struct inode *parent,
void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent,
struct f2fs_dentry_ptr *d)
{
struct qstr dot = QSTR_INIT(".", 1);
@ -340,23 +340,23 @@ static int make_empty_dir(struct inode *inode,
struct f2fs_dentry_ptr d;
if (f2fs_has_inline_dentry(inode))
return make_empty_inline_dir(inode, parent, page);
return f2fs_make_empty_inline_dir(inode, parent, page);
dentry_page = get_new_data_page(inode, page, 0, true);
dentry_page = f2fs_get_new_data_page(inode, page, 0, true);
if (IS_ERR(dentry_page))
return PTR_ERR(dentry_page);
dentry_blk = page_address(dentry_page);
make_dentry_ptr_block(NULL, &d, dentry_blk);
do_make_empty_dir(inode, parent, &d);
f2fs_do_make_empty_dir(inode, parent, &d);
set_page_dirty(dentry_page);
f2fs_put_page(dentry_page, 1);
return 0;
}
struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
const struct qstr *new_name, const struct qstr *orig_name,
struct page *dpage)
{
@ -365,7 +365,7 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
int err;
if (is_inode_flag_set(inode, FI_NEW_INODE)) {
page = new_inode_page(inode);
page = f2fs_new_inode_page(inode);
if (IS_ERR(page))
return page;
@ -395,7 +395,7 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
goto put_error;
}
} else {
page = get_node_page(F2FS_I_SB(dir), inode->i_ino);
page = f2fs_get_node_page(F2FS_I_SB(dir), inode->i_ino);
if (IS_ERR(page))
return page;
}
@ -418,19 +418,19 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
* we should remove this inode from orphan list.
*/
if (inode->i_nlink == 0)
remove_orphan_inode(F2FS_I_SB(dir), inode->i_ino);
f2fs_remove_orphan_inode(F2FS_I_SB(dir), inode->i_ino);
f2fs_i_links_write(inode, true);
}
return page;
put_error:
clear_nlink(inode);
update_inode(inode, page);
f2fs_update_inode(inode, page);
f2fs_put_page(page, 1);
return ERR_PTR(err);
}
void update_parent_metadata(struct inode *dir, struct inode *inode,
void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode,
unsigned int current_depth)
{
if (inode && is_inode_flag_set(inode, FI_NEW_INODE)) {
@ -448,7 +448,7 @@ void update_parent_metadata(struct inode *dir, struct inode *inode,
clear_inode_flag(inode, FI_INC_LINK);
}
int room_for_filename(const void *bitmap, int slots, int max_slots)
int f2fs_room_for_filename(const void *bitmap, int slots, int max_slots)
{
int bit_start = 0;
int zero_start, zero_end;
@ -537,12 +537,12 @@ start:
(le32_to_cpu(dentry_hash) % nbucket));
for (block = bidx; block <= (bidx + nblock - 1); block++) {
dentry_page = get_new_data_page(dir, NULL, block, true);
dentry_page = f2fs_get_new_data_page(dir, NULL, block, true);
if (IS_ERR(dentry_page))
return PTR_ERR(dentry_page);
dentry_blk = page_address(dentry_page);
bit_pos = room_for_filename(&dentry_blk->dentry_bitmap,
bit_pos = f2fs_room_for_filename(&dentry_blk->dentry_bitmap,
slots, NR_DENTRY_IN_BLOCK);
if (bit_pos < NR_DENTRY_IN_BLOCK)
goto add_dentry;
@ -558,7 +558,7 @@ add_dentry:
if (inode) {
down_write(&F2FS_I(inode)->i_sem);
page = init_inode_metadata(inode, dir, new_name,
page = f2fs_init_inode_metadata(inode, dir, new_name,
orig_name, NULL);
if (IS_ERR(page)) {
err = PTR_ERR(page);
@ -576,7 +576,7 @@ add_dentry:
f2fs_put_page(page, 1);
}
update_parent_metadata(dir, inode, current_depth);
f2fs_update_parent_metadata(dir, inode, current_depth);
fail:
if (inode)
up_write(&F2FS_I(inode)->i_sem);
@ -586,7 +586,7 @@ fail:
return err;
}
int __f2fs_do_add_link(struct inode *dir, struct fscrypt_name *fname,
int f2fs_add_dentry(struct inode *dir, struct fscrypt_name *fname,
struct inode *inode, nid_t ino, umode_t mode)
{
struct qstr new_name;
@ -610,7 +610,7 @@ int __f2fs_do_add_link(struct inode *dir, struct fscrypt_name *fname,
* Caller should grab and release a rwsem by calling f2fs_lock_op() and
* f2fs_unlock_op().
*/
int __f2fs_add_link(struct inode *dir, const struct qstr *name,
int f2fs_do_add_link(struct inode *dir, const struct qstr *name,
struct inode *inode, nid_t ino, umode_t mode)
{
struct fscrypt_name fname;
@ -639,7 +639,7 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
} else if (IS_ERR(page)) {
err = PTR_ERR(page);
} else {
err = __f2fs_do_add_link(dir, &fname, inode, ino, mode);
err = f2fs_add_dentry(dir, &fname, inode, ino, mode);
}
fscrypt_free_filename(&fname);
return err;
@ -651,7 +651,7 @@ int f2fs_do_tmpfile(struct inode *inode, struct inode *dir)
int err = 0;
down_write(&F2FS_I(inode)->i_sem);
page = init_inode_metadata(inode, dir, NULL, NULL, NULL);
page = f2fs_init_inode_metadata(inode, dir, NULL, NULL, NULL);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
@ -683,9 +683,9 @@ void f2fs_drop_nlink(struct inode *dir, struct inode *inode)
up_write(&F2FS_I(inode)->i_sem);
if (inode->i_nlink == 0)
add_orphan_inode(inode);
f2fs_add_orphan_inode(inode);
else
release_orphan_inode(sbi);
f2fs_release_orphan_inode(sbi);
}
/*
@ -698,14 +698,12 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
struct f2fs_dentry_block *dentry_blk;
unsigned int bit_pos;
int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
struct address_space *mapping = page_mapping(page);
unsigned long flags;
int i;
f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
if (F2FS_OPTION(F2FS_I_SB(dir)).fsync_mode == FSYNC_MODE_STRICT)
add_ino_entry(F2FS_I_SB(dir), dir->i_ino, TRANS_DIR_INO);
f2fs_add_ino_entry(F2FS_I_SB(dir), dir->i_ino, TRANS_DIR_INO);
if (f2fs_has_inline_dentry(dir))
return f2fs_delete_inline_entry(dentry, page, dir, inode);
@ -731,17 +729,13 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
f2fs_drop_nlink(dir, inode);
if (bit_pos == NR_DENTRY_IN_BLOCK &&
!truncate_hole(dir, page->index, page->index + 1)) {
spin_lock_irqsave(&mapping->tree_lock, flags);
radix_tree_tag_clear(&mapping->page_tree, page_index(page),
PAGECACHE_TAG_DIRTY);
spin_unlock_irqrestore(&mapping->tree_lock, flags);
!f2fs_truncate_hole(dir, page->index, page->index + 1)) {
f2fs_clear_radix_tree_dirty_tag(page);
clear_page_dirty_for_io(page);
ClearPagePrivate(page);
ClearPageUptodate(page);
inode_dec_dirty_pages(dir);
remove_dirty_inode(dir);
f2fs_remove_dirty_inode(dir);
}
f2fs_put_page(page, 1);
}
@ -758,7 +752,7 @@ bool f2fs_empty_dir(struct inode *dir)
return f2fs_empty_inline_dir(dir);
for (bidx = 0; bidx < nblock; bidx++) {
dentry_page = get_lock_data_page(dir, bidx, false);
dentry_page = f2fs_get_lock_data_page(dir, bidx, false);
if (IS_ERR(dentry_page)) {
if (PTR_ERR(dentry_page) == -ENOENT)
continue;
@ -806,7 +800,7 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
continue;
}
d_type = get_de_type(de);
d_type = f2fs_get_de_type(de);
de_name.name = d->filename[bit_pos];
de_name.len = le16_to_cpu(de->name_len);
@ -830,7 +824,7 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
return 1;
if (sbi->readdir_ra == 1)
ra_node_page(sbi, le32_to_cpu(de->ino));
f2fs_ra_node_page(sbi, le32_to_cpu(de->ino));
bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
ctx->pos = start_pos + bit_pos;
@ -880,7 +874,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
page_cache_sync_readahead(inode->i_mapping, ra, file, n,
min(npages - n, (pgoff_t)MAX_DIR_RA_PAGES));
dentry_page = get_lock_data_page(inode, n, false);
dentry_page = f2fs_get_lock_data_page(inode, n, false);
if (IS_ERR(dentry_page)) {
err = PTR_ERR(dentry_page);
if (err == -ENOENT) {

22
fs/f2fs/extent_cache.c
View File

@ -49,7 +49,7 @@ static struct rb_entry *__lookup_rb_tree_slow(struct rb_root *root,
return NULL;
}
struct rb_entry *__lookup_rb_tree(struct rb_root *root,
struct rb_entry *f2fs_lookup_rb_tree(struct rb_root *root,
struct rb_entry *cached_re, unsigned int ofs)
{
struct rb_entry *re;
@ -61,7 +61,7 @@ struct rb_entry *__lookup_rb_tree(struct rb_root *root,
return re;
}
struct rb_node **__lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
struct rb_root *root, struct rb_node **parent,
unsigned int ofs)
{
@ -92,7 +92,7 @@ struct rb_node **__lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
* in order to simpfy the insertion after.
* tree must stay unchanged between lookup and insertion.
*/
struct rb_entry *__lookup_rb_tree_ret(struct rb_root *root,
struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root *root,
struct rb_entry *cached_re,
unsigned int ofs,
struct rb_entry **prev_entry,
@ -159,7 +159,7 @@ lookup_neighbors:
return re;
}
bool __check_rb_tree_consistence(struct f2fs_sb_info *sbi,
bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
struct rb_root *root)
{
#ifdef CONFIG_F2FS_CHECK_FS
@ -390,7 +390,7 @@ static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
goto out;
}
en = (struct extent_node *)__lookup_rb_tree(&et->root,
en = (struct extent_node *)f2fs_lookup_rb_tree(&et->root,
(struct rb_entry *)et->cached_en, pgofs);
if (!en)
goto out;
@ -470,7 +470,7 @@ static struct extent_node *__insert_extent_tree(struct inode *inode,
goto do_insert;
}
p = __lookup_rb_tree_for_insert(sbi, &et->root, &parent, ei->fofs);
p = f2fs_lookup_rb_tree_for_insert(sbi, &et->root, &parent, ei->fofs);
do_insert:
en = __attach_extent_node(sbi, et, ei, parent, p);
if (!en)
@ -520,7 +520,7 @@ static void f2fs_update_extent_tree_range(struct inode *inode,
__drop_largest_extent(inode, fofs, len);
/* 1. lookup first extent node in range [fofs, fofs + len - 1] */
en = (struct extent_node *)__lookup_rb_tree_ret(&et->root,
en = (struct extent_node *)f2fs_lookup_rb_tree_ret(&et->root,
(struct rb_entry *)et->cached_en, fofs,
(struct rb_entry **)&prev_en,
(struct rb_entry **)&next_en,
@ -773,7 +773,7 @@ void f2fs_update_extent_cache(struct dnode_of_data *dn)
else
blkaddr = dn->data_blkaddr;
fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
dn->ofs_in_node;
f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, 1);
}
@ -788,7 +788,7 @@ void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, len);
}
void init_extent_cache_info(struct f2fs_sb_info *sbi)
void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi)
{
INIT_RADIX_TREE(&sbi->extent_tree_root, GFP_NOIO);
mutex_init(&sbi->extent_tree_lock);
@ -800,7 +800,7 @@ void init_extent_cache_info(struct f2fs_sb_info *sbi)
atomic_set(&sbi->total_ext_node, 0);
}
int __init create_extent_cache(void)
int __init f2fs_create_extent_cache(void)
{
extent_tree_slab = f2fs_kmem_cache_create("f2fs_extent_tree",
sizeof(struct extent_tree));
@ -815,7 +815,7 @@ int __init create_extent_cache(void)
return 0;
}
void destroy_extent_cache(void)
void f2fs_destroy_extent_cache(void)
{
kmem_cache_destroy(extent_node_slab);
kmem_cache_destroy(extent_tree_slab);

417
fs/f2fs/f2fs.h
View File

@ -25,6 +25,7 @@
#include <linux/blkdev.h>
#include <linux/quotaops.h>
#include <crypto/hash.h>
#include <linux/overflow.h>
#define __FS_HAS_ENCRYPTION IS_ENABLED(CONFIG_F2FS_FS_ENCRYPTION)
#include <linux/fscrypt.h>
@ -623,15 +624,20 @@ enum {
#define DEF_DIR_LEVEL 0
enum {
GC_FAILURE_PIN,
GC_FAILURE_ATOMIC,
MAX_GC_FAILURE
};
struct f2fs_inode_info {
struct inode vfs_inode; /* serve a vfs inode */
unsigned long i_flags; /* keep an inode flags for ioctl */
unsigned char i_advise; /* use to give file attribute hints */
unsigned char i_dir_level; /* use for dentry level for large dir */
union {
unsigned int i_current_depth; /* only for directory depth */
unsigned short i_gc_failures; /* only for regular file */
};
unsigned int i_current_depth; /* only for directory depth */
/* for gc failure statistic */
unsigned int i_gc_failures[MAX_GC_FAILURE];
unsigned int i_pino; /* parent inode number */
umode_t i_acl_mode; /* keep file acl mode temporarily */
@ -659,7 +665,9 @@ struct f2fs_inode_info {
struct task_struct *inmem_task; /* store inmemory task */
struct mutex inmem_lock; /* lock for inmemory pages */
struct extent_tree *extent_tree; /* cached extent_tree entry */
struct rw_semaphore dio_rwsem[2];/* avoid racing between dio and gc */
/* avoid racing between foreground op and gc */
struct rw_semaphore i_gc_rwsem[2];
struct rw_semaphore i_mmap_sem;
struct rw_semaphore i_xattr_sem; /* avoid racing between reading and changing EAs */
@ -1010,6 +1018,7 @@ struct f2fs_io_info {
int need_lock; /* indicate we need to lock cp_rwsem */
bool in_list; /* indicate fio is in io_list */
bool is_meta; /* indicate borrow meta inode mapping or not */
bool retry; /* need to reallocate block address */
enum iostat_type io_type; /* io type */
struct writeback_control *io_wbc; /* writeback control */
unsigned char version; /* version of the node */
@ -1072,6 +1081,13 @@ enum {
MAX_TIME,
};
enum {
GC_NORMAL,
GC_IDLE_CB,
GC_IDLE_GREEDY,
GC_URGENT,
};
enum {
WHINT_MODE_OFF, /* not pass down write hints */
WHINT_MODE_USER, /* try to pass down hints given by users */
@ -1121,6 +1137,8 @@ struct f2fs_sb_info {
struct f2fs_bio_info *write_io[NR_PAGE_TYPE]; /* for write bios */
struct mutex wio_mutex[NR_PAGE_TYPE - 1][NR_TEMP_TYPE];
/* bio ordering for NODE/DATA */
/* keep migration IO order for LFS mode */
struct rw_semaphore io_order_lock;
mempool_t *write_io_dummy; /* Dummy pages */
/* for checkpoint */
@ -1191,7 +1209,7 @@ struct f2fs_sb_info {
struct percpu_counter alloc_valid_block_count;
/* writeback control */
atomic_t wb_sync_req; /* count # of WB_SYNC threads */
atomic_t wb_sync_req[META]; /* count # of WB_SYNC threads */
/* valid inode count */
struct percpu_counter total_valid_inode_count;
@ -1202,9 +1220,9 @@ struct f2fs_sb_info {
struct mutex gc_mutex; /* mutex for GC */
struct f2fs_gc_kthread *gc_thread; /* GC thread */
unsigned int cur_victim_sec; /* current victim section num */
/* threshold for converting bg victims for fg */
u64 fggc_threshold;
unsigned int gc_mode; /* current GC state */
/* for skip statistic */
unsigned long long skipped_atomic_files[2]; /* FG_GC and BG_GC */
/* threshold for gc trials on pinned files */
u64 gc_pin_file_threshold;
@ -1594,18 +1612,6 @@ static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi)
is_set_ckpt_flags(sbi, CP_FASTBOOT_FLAG));
}
/*
* Check whether the given nid is within node id range.
*/
static inline int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
{
if (unlikely(nid < F2FS_ROOT_INO(sbi)))
return -EINVAL;
if (unlikely(nid >= NM_I(sbi)->max_nid))
return -EINVAL;
return 0;
}
/*
* Check whether the inode has blocks or not
*/
@ -2169,9 +2175,60 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr)
*addr ^= mask;
}
#define F2FS_REG_FLMASK (~(FS_DIRSYNC_FL | FS_TOPDIR_FL))
#define F2FS_OTHER_FLMASK (FS_NODUMP_FL | FS_NOATIME_FL)
#define F2FS_FL_INHERITED (FS_PROJINHERIT_FL)
/*
* Inode flags
*/
#define F2FS_SECRM_FL 0x00000001 /* Secure deletion */
#define F2FS_UNRM_FL 0x00000002 /* Undelete */
#define F2FS_COMPR_FL 0x00000004 /* Compress file */
#define F2FS_SYNC_FL 0x00000008 /* Synchronous updates */
#define F2FS_IMMUTABLE_FL 0x00000010 /* Immutable file */
#define F2FS_APPEND_FL 0x00000020 /* writes to file may only append */
#define F2FS_NODUMP_FL 0x00000040 /* do not dump file */
#define F2FS_NOATIME_FL 0x00000080 /* do not update atime */
/* Reserved for compression usage... */
#define F2FS_DIRTY_FL 0x00000100
#define F2FS_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */
#define F2FS_NOCOMPR_FL 0x00000400 /* Don't compress */
#define F2FS_ENCRYPT_FL 0x00000800 /* encrypted file */
/* End compression flags --- maybe not all used */
#define F2FS_INDEX_FL 0x00001000 /* hash-indexed directory */
#define F2FS_IMAGIC_FL 0x00002000 /* AFS directory */
#define F2FS_JOURNAL_DATA_FL 0x00004000 /* file data should be journaled */
#define F2FS_NOTAIL_FL 0x00008000 /* file tail should not be merged */
#define F2FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */
#define F2FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/
#define F2FS_HUGE_FILE_FL 0x00040000 /* Set to each huge file */
#define F2FS_EXTENTS_FL 0x00080000 /* Inode uses extents */
#define F2FS_EA_INODE_FL 0x00200000 /* Inode used for large EA */
#define F2FS_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */
#define F2FS_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */
#define F2FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */
#define F2FS_RESERVED_FL 0x80000000 /* reserved for ext4 lib */
#define F2FS_FL_USER_VISIBLE 0x304BDFFF /* User visible flags */
#define F2FS_FL_USER_MODIFIABLE 0x204BC0FF /* User modifiable flags */
/* Flags we can manipulate with through F2FS_IOC_FSSETXATTR */
#define F2FS_FL_XFLAG_VISIBLE (F2FS_SYNC_FL | \
F2FS_IMMUTABLE_FL | \
F2FS_APPEND_FL | \
F2FS_NODUMP_FL | \
F2FS_NOATIME_FL | \
F2FS_PROJINHERIT_FL)
/* Flags that should be inherited by new inodes from their parent. */
#define F2FS_FL_INHERITED (F2FS_SECRM_FL | F2FS_UNRM_FL | F2FS_COMPR_FL |\
F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL |\
F2FS_NOCOMPR_FL | F2FS_JOURNAL_DATA_FL |\
F2FS_NOTAIL_FL | F2FS_DIRSYNC_FL |\
F2FS_PROJINHERIT_FL)
/* Flags that are appropriate for regular files (all but dir-specific ones). */
#define F2FS_REG_FLMASK (~(F2FS_DIRSYNC_FL | F2FS_TOPDIR_FL))
/* Flags that are appropriate for non-directories/regular files. */
#define F2FS_OTHER_FLMASK (F2FS_NODUMP_FL | F2FS_NOATIME_FL)
static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags)
{
@ -2214,6 +2271,7 @@ enum {
FI_EXTRA_ATTR, /* indicate file has extra attribute */
FI_PROJ_INHERIT, /* indicate file inherits projectid */
FI_PIN_FILE, /* indicate file should not be gced */
FI_ATOMIC_REVOKE_REQUEST, /* request to drop atomic data */
};
static inline void __mark_inode_dirty_flag(struct inode *inode,
@ -2312,7 +2370,7 @@ static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth)
static inline void f2fs_i_gc_failures_write(struct inode *inode,
unsigned int count)
{
F2FS_I(inode)->i_gc_failures = count;
F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN] = count;
f2fs_mark_inode_dirty_sync(inode, true);
}
@ -2590,7 +2648,7 @@ static inline int get_inline_xattr_addrs(struct inode *inode)
return F2FS_I(inode)->i_inline_xattr_size;
}
#define get_inode_mode(i) \
#define f2fs_get_inode_mode(i) \
((is_inode_flag_set(i, FI_ACL_MODE)) ? \
(F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
@ -2666,14 +2724,14 @@ static inline bool is_valid_data_blkaddr(struct f2fs_sb_info *sbi,
* file.c
*/
int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
void truncate_data_blocks(struct dnode_of_data *dn);
int truncate_blocks(struct inode *inode, u64 from, bool lock);
void f2fs_truncate_data_blocks(struct dnode_of_data *dn);
int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock);
int f2fs_truncate(struct inode *inode);
int f2fs_getattr(const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int flags);
int f2fs_setattr(struct dentry *dentry, struct iattr *attr);
int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end);
void truncate_data_blocks_range(struct dnode_of_data *dn, int count);
int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end);
void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count);
int f2fs_precache_extents(struct inode *inode);
long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
@ -2687,38 +2745,37 @@ bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page);
void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page);
struct inode *f2fs_iget(struct super_block *sb, unsigned long ino);
struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino);
int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink);
void update_inode(struct inode *inode, struct page *node_page);
void update_inode_page(struct inode *inode);
int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink);
void f2fs_update_inode(struct inode *inode, struct page *node_page);
void f2fs_update_inode_page(struct inode *inode);
int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc);
void f2fs_evict_inode(struct inode *inode);
void handle_failed_inode(struct inode *inode);
void f2fs_handle_failed_inode(struct inode *inode);
/*
* namei.c
*/
int update_extension_list(struct f2fs_sb_info *sbi, const char *name,
int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name,
bool hot, bool set);
struct dentry *f2fs_get_parent(struct dentry *child);
/*
* dir.c
*/
void set_de_type(struct f2fs_dir_entry *de, umode_t mode);
unsigned char get_de_type(struct f2fs_dir_entry *de);
struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de);
struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname,
f2fs_hash_t namehash, int *max_slots,
struct f2fs_dentry_ptr *d);
int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
unsigned int start_pos, struct fscrypt_str *fstr);
void do_make_empty_dir(struct inode *inode, struct inode *parent,
void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent,
struct f2fs_dentry_ptr *d);
struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
const struct qstr *new_name,
const struct qstr *orig_name, struct page *dpage);
void update_parent_metadata(struct inode *dir, struct inode *inode,
void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode,
unsigned int current_depth);
int room_for_filename(const void *bitmap, int slots, int max_slots);
int f2fs_room_for_filename(const void *bitmap, int slots, int max_slots);
void f2fs_drop_nlink(struct inode *dir, struct inode *inode);
struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
struct fscrypt_name *fname, struct page **res_page);
@ -2735,9 +2792,9 @@ void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
const struct qstr *orig_name,
struct inode *inode, nid_t ino, umode_t mode);
int __f2fs_do_add_link(struct inode *dir, struct fscrypt_name *fname,
int f2fs_add_dentry(struct inode *dir, struct fscrypt_name *fname,
struct inode *inode, nid_t ino, umode_t mode);
int __f2fs_add_link(struct inode *dir, const struct qstr *name,
int f2fs_do_add_link(struct inode *dir, const struct qstr *name,
struct inode *inode, nid_t ino, umode_t mode);
void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
struct inode *dir, struct inode *inode);
@ -2746,7 +2803,7 @@ bool f2fs_empty_dir(struct inode *dir);
static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
{
return __f2fs_add_link(d_inode(dentry->d_parent), &dentry->d_name,
return f2fs_do_add_link(d_inode(dentry->d_parent), &dentry->d_name,
inode, inode->i_ino, inode->i_mode);
}
@ -2761,7 +2818,7 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover);
int f2fs_sync_fs(struct super_block *sb, int sync);
extern __printf(3, 4)
void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...);
int sanity_check_ckpt(struct f2fs_sb_info *sbi);
int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi);
/*
* hash.c
@ -2775,140 +2832,147 @@ f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info,
struct dnode_of_data;
struct node_info;
bool available_free_memory(struct f2fs_sb_info *sbi, int type);
int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid);
bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid);
bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino);
int get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni);
pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs);
int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode);
int truncate_inode_blocks(struct inode *inode, pgoff_t from);
int truncate_xattr_node(struct inode *inode);
int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino);
int remove_inode_page(struct inode *inode);
struct page *new_inode_page(struct inode *inode);
struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs);
void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid);
struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid);
struct page *get_node_page_ra(struct page *parent, int start);
int move_node_page(struct page *node_page, int gc_type);
int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid);
bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type);
int f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid);
bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid);
bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino);
int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
struct node_info *ni);
pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs);
int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode);
int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from);
int f2fs_truncate_xattr_node(struct inode *inode);
int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino);
int f2fs_remove_inode_page(struct inode *inode);
struct page *f2fs_new_inode_page(struct inode *inode);
struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs);
void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid);
struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid);
struct page *f2fs_get_node_page_ra(struct page *parent, int start);
int f2fs_move_node_page(struct page *node_page, int gc_type);
int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
struct writeback_control *wbc, bool atomic);
int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc,
int f2fs_sync_node_pages(struct f2fs_sb_info *sbi,
struct writeback_control *wbc,
bool do_balance, enum iostat_type io_type);
int build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount);
bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid);
void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid);
void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid);
int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink);
void recover_inline_xattr(struct inode *inode, struct page *page);
int recover_xattr_data(struct inode *inode, struct page *page);
int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page);
int restore_node_summary(struct f2fs_sb_info *sbi,
int f2fs_build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount);
bool f2fs_alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid);
void f2fs_alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid);
void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid);
int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink);
void f2fs_recover_inline_xattr(struct inode *inode, struct page *page);
int f2fs_recover_xattr_data(struct inode *inode, struct page *page);
int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page);
int f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
unsigned int segno, struct f2fs_summary_block *sum);
int flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
int build_node_manager(struct f2fs_sb_info *sbi);
void destroy_node_manager(struct f2fs_sb_info *sbi);
int __init create_node_manager_caches(void);
void destroy_node_manager_caches(void);
int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
int f2fs_build_node_manager(struct f2fs_sb_info *sbi);
void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi);
int __init f2fs_create_node_manager_caches(void);
void f2fs_destroy_node_manager_caches(void);
/*
* segment.c
*/
bool need_SSR(struct f2fs_sb_info *sbi);
void register_inmem_page(struct inode *inode, struct page *page);
void drop_inmem_pages_all(struct f2fs_sb_info *sbi);
void drop_inmem_pages(struct inode *inode);
void drop_inmem_page(struct inode *inode, struct page *page);
int commit_inmem_pages(struct inode *inode);
bool f2fs_need_SSR(struct f2fs_sb_info *sbi);
void f2fs_register_inmem_page(struct inode *inode, struct page *page);
void f2fs_drop_inmem_pages_all(struct f2fs_sb_info *sbi, bool gc_failure);
void f2fs_drop_inmem_pages(struct inode *inode);
void f2fs_drop_inmem_page(struct inode *inode, struct page *page);
int f2fs_commit_inmem_pages(struct inode *inode);
void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need);
void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi);
int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino);
int create_flush_cmd_control(struct f2fs_sb_info *sbi);
int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi);
int f2fs_flush_device_cache(struct f2fs_sb_info *sbi);
void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free);
void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr);
bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
void drop_discard_cmd(struct f2fs_sb_info *sbi);
void stop_discard_thread(struct f2fs_sb_info *sbi);
void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free);
void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr);
bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi);
void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi);
bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi);
void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc);
void release_discard_addrs(struct f2fs_sb_info *sbi);
int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
void allocate_new_segments(struct f2fs_sb_info *sbi);
void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
struct cp_control *cpc);
void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi);
int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi);
int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc);
struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno);
void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr);
void write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi,
struct cp_control *cpc);
struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno);
void f2fs_update_meta_page(struct f2fs_sb_info *sbi, void *src,
block_t blk_addr);
void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
enum iostat_type io_type);
void write_node_page(unsigned int nid, struct f2fs_io_info *fio);
void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio);
int rewrite_data_page(struct f2fs_io_info *fio);
void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio);
void f2fs_outplace_write_data(struct dnode_of_data *dn,
struct f2fs_io_info *fio);
int f2fs_inplace_write_data(struct f2fs_io_info *fio);
void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
block_t old_blkaddr, block_t new_blkaddr,
bool recover_curseg, bool recover_newaddr);
void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
block_t old_addr, block_t new_addr,
unsigned char version, bool recover_curseg,
bool recover_newaddr);
void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
block_t old_blkaddr, block_t *new_blkaddr,
struct f2fs_summary *sum, int type,
struct f2fs_io_info *fio, bool add_list);
void f2fs_wait_on_page_writeback(struct page *page,
enum page_type type, bool ordered);
void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr);
void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
int lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
unsigned int val, int alloc);
void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
int build_segment_manager(struct f2fs_sb_info *sbi);
void destroy_segment_manager(struct f2fs_sb_info *sbi);
int __init create_segment_manager_caches(void);
void destroy_segment_manager_caches(void);
int rw_hint_to_seg_type(enum rw_hint hint);
enum rw_hint io_type_to_rw_hint(struct f2fs_sb_info *sbi, enum page_type type,
enum temp_type temp);
void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
int f2fs_build_segment_manager(struct f2fs_sb_info *sbi);
void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi);
int __init f2fs_create_segment_manager_caches(void);
void f2fs_destroy_segment_manager_caches(void);
int f2fs_rw_hint_to_seg_type(enum rw_hint hint);
enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
enum page_type type, enum temp_type temp);
/*
* checkpoint.c
*/
void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io);
struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index);
struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
block_t blkaddr, int type);
int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
block_t blkaddr, int type);
int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
int type, bool sync);
void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index);
long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index);
long f2fs_sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
long nr_to_write, enum iostat_type io_type);
void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
void release_ino_entry(struct f2fs_sb_info *sbi, bool all);
bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode);
void set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
void f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all);
bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode);
void f2fs_set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
unsigned int devidx, int type);
bool is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
unsigned int devidx, int type);
int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi);
int acquire_orphan_inode(struct f2fs_sb_info *sbi);
void release_orphan_inode(struct f2fs_sb_info *sbi);
void add_orphan_inode(struct inode *inode);
void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino);
int recover_orphan_inodes(struct f2fs_sb_info *sbi);
int get_valid_checkpoint(struct f2fs_sb_info *sbi);
void update_dirty_page(struct inode *inode, struct page *page);
void remove_dirty_inode(struct inode *inode);
int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type);
int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
void init_ino_entry_info(struct f2fs_sb_info *sbi);
int __init create_checkpoint_caches(void);
void destroy_checkpoint_caches(void);
int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi);
void f2fs_release_orphan_inode(struct f2fs_sb_info *sbi);
void f2fs_add_orphan_inode(struct inode *inode);
void f2fs_remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino);
int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi);
int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi);
void f2fs_update_dirty_page(struct inode *inode, struct page *page);
void f2fs_remove_dirty_inode(struct inode *inode);
int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type);
int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi);
int __init f2fs_create_checkpoint_caches(void);
void f2fs_destroy_checkpoint_caches(void);
/*
* data.c
@ -2921,34 +2985,31 @@ void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
enum page_type type);
void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi);
int f2fs_submit_page_bio(struct f2fs_io_info *fio);
int f2fs_submit_page_write(struct f2fs_io_info *fio);
void f2fs_submit_page_write(struct f2fs_io_info *fio);
struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
block_t blk_addr, struct bio *bio);
int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr);
void set_data_blkaddr(struct dnode_of_data *dn);
void f2fs_set_data_blkaddr(struct dnode_of_data *dn);
void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr);
int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count);
int reserve_new_block(struct dnode_of_data *dn);
int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count);
int f2fs_reserve_new_block(struct dnode_of_data *dn);
int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index);
int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from);
int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
struct page *get_read_data_page(struct inode *inode, pgoff_t index,
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
int op_flags, bool for_write);
struct page *find_data_page(struct inode *inode, pgoff_t index);
struct page *get_lock_data_page(struct inode *inode, pgoff_t index,
struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index);
struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index,
bool for_write);
struct page *get_new_data_page(struct inode *inode,
struct page *f2fs_get_new_data_page(struct inode *inode,
struct page *ipage, pgoff_t index, bool new_i_size);
int do_write_data_page(struct f2fs_io_info *fio);
int f2fs_do_write_data_page(struct f2fs_io_info *fio);
int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
int create, int flag);
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len);
bool should_update_inplace(struct inode *inode, struct f2fs_io_info *fio);
bool should_update_outplace(struct inode *inode, struct f2fs_io_info *fio);
int __f2fs_write_data_pages(struct address_space *mapping,
struct writeback_control *wbc,
enum iostat_type io_type);
bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio);
bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio);
void f2fs_invalidate_page(struct page *page, unsigned int offset,
unsigned int length);
int f2fs_release_page(struct page *page, gfp_t wait);
@ -2957,22 +3018,23 @@ int f2fs_migrate_page(struct address_space *mapping, struct page *newpage,
struct page *page, enum migrate_mode mode);
#endif
bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len);
void f2fs_clear_radix_tree_dirty_tag(struct page *page);
/*
* gc.c
*/
int start_gc_thread(struct f2fs_sb_info *sbi);
void stop_gc_thread(struct f2fs_sb_info *sbi);
block_t start_bidx_of_node(unsigned int node_ofs, struct inode *inode);
int f2fs_start_gc_thread(struct f2fs_sb_info *sbi);
void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi);
block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode);
int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background,
unsigned int segno);
void build_gc_manager(struct f2fs_sb_info *sbi);
void f2fs_build_gc_manager(struct f2fs_sb_info *sbi);
/*
* recovery.c
*/
int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only);
bool space_for_roll_forward(struct f2fs_sb_info *sbi);
int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only);
bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi);
/*
* debug.c
@ -3010,6 +3072,7 @@ struct f2fs_stat_info {
int bg_node_segs, bg_data_segs;
int tot_blks, data_blks, node_blks;
int bg_data_blks, bg_node_blks;
unsigned long long skipped_atomic_files[2];
int curseg[NR_CURSEG_TYPE];
int cursec[NR_CURSEG_TYPE];
int curzone[NR_CURSEG_TYPE];
@ -3176,29 +3239,31 @@ extern const struct inode_operations f2fs_dir_inode_operations;
extern const struct inode_operations f2fs_symlink_inode_operations;
extern const struct inode_operations f2fs_encrypted_symlink_inode_operations;
extern const struct inode_operations f2fs_special_inode_operations;
extern struct kmem_cache *inode_entry_slab;
extern struct kmem_cache *f2fs_inode_entry_slab;
/*
* inline.c
*/
bool f2fs_may_inline_data(struct inode *inode);
bool f2fs_may_inline_dentry(struct inode *inode);
void read_inline_data(struct page *page, struct page *ipage);
void truncate_inline_inode(struct inode *inode, struct page *ipage, u64 from);
void f2fs_do_read_inline_data(struct page *page, struct page *ipage);
void f2fs_truncate_inline_inode(struct inode *inode,
struct page *ipage, u64 from);
int f2fs_read_inline_data(struct inode *inode, struct page *page);
int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page);
int f2fs_convert_inline_inode(struct inode *inode);
int f2fs_write_inline_data(struct inode *inode, struct page *page);
bool recover_inline_data(struct inode *inode, struct page *npage);
struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
bool f2fs_recover_inline_data(struct inode *inode, struct page *npage);
struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
struct fscrypt_name *fname, struct page **res_page);
int make_empty_inline_dir(struct inode *inode, struct inode *parent,
int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent,
struct page *ipage);
int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
const struct qstr *orig_name,
struct inode *inode, nid_t ino, umode_t mode);
void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page,
struct inode *dir, struct inode *inode);
void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry,
struct page *page, struct inode *dir,
struct inode *inode);
bool f2fs_empty_inline_dir(struct inode *dir);
int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
struct fscrypt_str *fstr);
@ -3219,17 +3284,17 @@ void f2fs_leave_shrinker(struct f2fs_sb_info *sbi);
/*
* extent_cache.c
*/
struct rb_entry *__lookup_rb_tree(struct rb_root *root,
struct rb_entry *f2fs_lookup_rb_tree(struct rb_root *root,
struct rb_entry *cached_re, unsigned int ofs);
struct rb_node **__lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
struct rb_root *root, struct rb_node **parent,
unsigned int ofs);
struct rb_entry *__lookup_rb_tree_ret(struct rb_root *root,
struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root *root,
struct rb_entry *cached_re, unsigned int ofs,
struct rb_entry **prev_entry, struct rb_entry **next_entry,
struct rb_node ***insert_p, struct rb_node **insert_parent,
bool force);
bool __check_rb_tree_consistence(struct f2fs_sb_info *sbi,
bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
struct rb_root *root);
unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink);
unsigned long __count_extent_cache(struct f2fs_sb_info *sbi);
@ -3242,9 +3307,9 @@ bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
void f2fs_update_extent_cache(struct dnode_of_data *dn);
void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
pgoff_t fofs, block_t blkaddr, unsigned int len);
void init_extent_cache_info(struct f2fs_sb_info *sbi);
int __init create_extent_cache(void);
void destroy_extent_cache(void);
void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi);
int __init f2fs_create_extent_cache(void);
void f2fs_destroy_extent_cache(void);
/*
* sysfs.c

322
fs/f2fs/file.c
View File

@ -95,7 +95,8 @@ static int f2fs_vm_page_mkwrite(struct vm_fault *vmf)
/* page is wholly or partially inside EOF */
if (((loff_t)(page->index + 1) << PAGE_SHIFT) >
i_size_read(inode)) {
unsigned offset;
loff_t offset;
offset = i_size_read(inode) & ~PAGE_MASK;
zero_user_segment(page, offset, PAGE_SIZE);
}
@ -156,17 +157,18 @@ static inline enum cp_reason_type need_do_checkpoint(struct inode *inode)
cp_reason = CP_SB_NEED_CP;
else if (file_wrong_pino(inode))
cp_reason = CP_WRONG_PINO;
else if (!space_for_roll_forward(sbi))
else if (!f2fs_space_for_roll_forward(sbi))
cp_reason = CP_NO_SPC_ROLL;
else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino))
else if (!f2fs_is_checkpointed_node(sbi, F2FS_I(inode)->i_pino))
cp_reason = CP_NODE_NEED_CP;
else if (test_opt(sbi, FASTBOOT))
cp_reason = CP_FASTBOOT_MODE;
else if (F2FS_OPTION(sbi).active_logs == 2)
cp_reason = CP_SPEC_LOG_NUM;
else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT &&
need_dentry_mark(sbi, inode->i_ino) &&
exist_written_data(sbi, F2FS_I(inode)->i_pino, TRANS_DIR_INO))
f2fs_need_dentry_mark(sbi, inode->i_ino) &&
f2fs_exist_written_data(sbi, F2FS_I(inode)->i_pino,
TRANS_DIR_INO))
cp_reason = CP_RECOVER_DIR;
return cp_reason;
@ -177,7 +179,7 @@ static bool need_inode_page_update(struct f2fs_sb_info *sbi, nid_t ino)
struct page *i = find_get_page(NODE_MAPPING(sbi), ino);
bool ret = false;
/* But we need to avoid that there are some inode updates */
if ((i && PageDirty(i)) || need_inode_block_update(sbi, ino))
if ((i && PageDirty(i)) || f2fs_need_inode_block_update(sbi, ino))
ret = true;
f2fs_put_page(i, 0);
return ret;
@ -240,14 +242,14 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
* if there is no written data, don't waste time to write recovery info.
*/
if (!is_inode_flag_set(inode, FI_APPEND_WRITE) &&
!exist_written_data(sbi, ino, APPEND_INO)) {
!f2fs_exist_written_data(sbi, ino, APPEND_INO)) {
/* it may call write_inode just prior to fsync */
if (need_inode_page_update(sbi, ino))
goto go_write;
if (is_inode_flag_set(inode, FI_UPDATE_WRITE) ||
exist_written_data(sbi, ino, UPDATE_INO))
f2fs_exist_written_data(sbi, ino, UPDATE_INO))
goto flush_out;
goto out;
}
@ -274,7 +276,9 @@ go_write:
goto out;
}
sync_nodes:
ret = fsync_node_pages(sbi, inode, &wbc, atomic);
atomic_inc(&sbi->wb_sync_req[NODE]);
ret = f2fs_fsync_node_pages(sbi, inode, &wbc, atomic);
atomic_dec(&sbi->wb_sync_req[NODE]);
if (ret)
goto out;
@ -284,7 +288,7 @@ sync_nodes:
goto out;
}
if (need_inode_block_update(sbi, ino)) {
if (f2fs_need_inode_block_update(sbi, ino)) {
f2fs_mark_inode_dirty_sync(inode, true);
f2fs_write_inode(inode, NULL);
goto sync_nodes;
@ -299,21 +303,21 @@ sync_nodes:
* given fsync mark.
*/
if (!atomic) {
ret = wait_on_node_pages_writeback(sbi, ino);
ret = f2fs_wait_on_node_pages_writeback(sbi, ino);
if (ret)
goto out;
}
/* once recovery info is written, don't need to tack this */
remove_ino_entry(sbi, ino, APPEND_INO);
f2fs_remove_ino_entry(sbi, ino, APPEND_INO);
clear_inode_flag(inode, FI_APPEND_WRITE);
flush_out:
if (!atomic && F2FS_OPTION(sbi).fsync_mode != FSYNC_MODE_NOBARRIER)
ret = f2fs_issue_flush(sbi, inode->i_ino);
if (!ret) {
remove_ino_entry(sbi, ino, UPDATE_INO);
f2fs_remove_ino_entry(sbi, ino, UPDATE_INO);
clear_inode_flag(inode, FI_UPDATE_WRITE);
remove_ino_entry(sbi, ino, FLUSH_INO);
f2fs_remove_ino_entry(sbi, ino, FLUSH_INO);
}
f2fs_update_time(sbi, REQ_TIME);
out:
@ -332,18 +336,19 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
static pgoff_t __get_first_dirty_index(struct address_space *mapping,
pgoff_t pgofs, int whence)
{
struct pagevec pvec;
struct page *page;
int nr_pages;
if (whence != SEEK_DATA)
return 0;
/* find first dirty page index */
pagevec_init(&pvec, 0);
nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs,
PAGECACHE_TAG_DIRTY, 1);
pgofs = nr_pages ? pvec.pages[0]->index : ULONG_MAX;
pagevec_release(&pvec);
nr_pages = find_get_pages_tag(mapping, &pgofs, PAGECACHE_TAG_DIRTY,
1, &page);
if (!nr_pages)
return ULONG_MAX;
pgofs = page->index;
put_page(page);
return pgofs;
}
@ -393,13 +398,13 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE);
err = f2fs_get_dnode_of_data(&dn, pgofs, LOOKUP_NODE);
if (err && err != -ENOENT) {
goto fail;
} else if (err == -ENOENT) {
/* direct node does not exists */
if (whence == SEEK_DATA) {
pgofs = get_next_page_offset(&dn, pgofs);
pgofs = f2fs_get_next_page_offset(&dn, pgofs);
continue;
} else {
goto found;
@ -413,6 +418,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
dn.ofs_in_node++, pgofs++,
data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
block_t blkaddr;
blkaddr = datablock_addr(dn.inode,
dn.node_page, dn.ofs_in_node);
@ -495,7 +501,7 @@ static int f2fs_file_open(struct inode *inode, struct file *filp)
return dquot_file_open(inode, filp);
}
void truncate_data_blocks_range(struct dnode_of_data *dn, int count)
void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct f2fs_node *raw_node;
@ -511,17 +517,18 @@ void truncate_data_blocks_range(struct dnode_of_data *dn, int count)
for (; count > 0; count--, addr++, dn->ofs_in_node++) {
block_t blkaddr = le32_to_cpu(*addr);
if (blkaddr == NULL_ADDR)
continue;
dn->data_blkaddr = NULL_ADDR;
set_data_blkaddr(dn);
f2fs_set_data_blkaddr(dn);
if (__is_valid_data_blkaddr(blkaddr) &&
!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC))
continue;
invalidate_blocks(sbi, blkaddr);
f2fs_invalidate_blocks(sbi, blkaddr);
if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page))
clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN);
nr_free++;
@ -533,7 +540,7 @@ void truncate_data_blocks_range(struct dnode_of_data *dn, int count)
* once we invalidate valid blkaddr in range [ofs, ofs + count],
* we will invalidate all blkaddr in the whole range.
*/
fofs = start_bidx_of_node(ofs_of_node(dn->node_page),
fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_page),
dn->inode) + ofs;
f2fs_update_extent_cache_range(dn, fofs, 0, len);
dec_valid_block_count(sbi, dn->inode, nr_free);
@ -545,15 +552,15 @@ void truncate_data_blocks_range(struct dnode_of_data *dn, int count)
dn->ofs_in_node, nr_free);
}
void truncate_data_blocks(struct dnode_of_data *dn)
void f2fs_truncate_data_blocks(struct dnode_of_data *dn)
{
truncate_data_blocks_range(dn, ADDRS_PER_BLOCK);
f2fs_truncate_data_blocks_range(dn, ADDRS_PER_BLOCK);
}
static int truncate_partial_data_page(struct inode *inode, u64 from,
bool cache_only)
{
unsigned offset = from & (PAGE_SIZE - 1);
loff_t offset = from & (PAGE_SIZE - 1);
pgoff_t index = from >> PAGE_SHIFT;
struct address_space *mapping = inode->i_mapping;
struct page *page;
@ -569,7 +576,7 @@ static int truncate_partial_data_page(struct inode *inode, u64 from,
return 0;
}
page = get_lock_data_page(inode, index, true);
page = f2fs_get_lock_data_page(inode, index, true);
if (IS_ERR(page))
return PTR_ERR(page) == -ENOENT ? 0 : PTR_ERR(page);
truncate_out:
@ -584,7 +591,7 @@ truncate_out:
return 0;
}
int truncate_blocks(struct inode *inode, u64 from, bool lock)
int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
@ -603,21 +610,21 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
if (lock)
f2fs_lock_op(sbi);
ipage = get_node_page(sbi, inode->i_ino);
ipage = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto out;
}
if (f2fs_has_inline_data(inode)) {
truncate_inline_inode(inode, ipage, from);
f2fs_truncate_inline_inode(inode, ipage, from);
f2fs_put_page(ipage, 1);
truncate_page = true;
goto out;
}
set_new_dnode(&dn, inode, ipage, NULL, 0);
err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE_RA);
err = f2fs_get_dnode_of_data(&dn, free_from, LOOKUP_NODE_RA);
if (err) {
if (err == -ENOENT)
goto free_next;
@ -630,13 +637,13 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
f2fs_bug_on(sbi, count < 0);
if (dn.ofs_in_node || IS_INODE(dn.node_page)) {
truncate_data_blocks_range(&dn, count);
f2fs_truncate_data_blocks_range(&dn, count);
free_from += count;
}
f2fs_put_dnode(&dn);
free_next:
err = truncate_inode_blocks(inode, free_from);
err = f2fs_truncate_inode_blocks(inode, free_from);
out:
if (lock)
f2fs_unlock_op(sbi);
@ -675,7 +682,7 @@ int f2fs_truncate(struct inode *inode)
return err;
}
err = truncate_blocks(inode, i_size_read(inode), true);
err = f2fs_truncate_blocks(inode, i_size_read(inode), true);
if (err)
return err;
@ -700,16 +707,16 @@ int f2fs_getattr(const struct path *path, struct kstat *stat,
stat->btime.tv_nsec = fi->i_crtime.tv_nsec;
}
flags = fi->i_flags & (FS_FL_USER_VISIBLE | FS_PROJINHERIT_FL);
if (flags & FS_APPEND_FL)
flags = fi->i_flags & F2FS_FL_USER_VISIBLE;
if (flags & F2FS_APPEND_FL)
stat->attributes |= STATX_ATTR_APPEND;
if (flags & FS_COMPR_FL)
if (flags & F2FS_COMPR_FL)
stat->attributes |= STATX_ATTR_COMPRESSED;
if (f2fs_encrypted_inode(inode))
stat->attributes |= STATX_ATTR_ENCRYPTED;
if (flags & FS_IMMUTABLE_FL)
if (flags & F2FS_IMMUTABLE_FL)
stat->attributes |= STATX_ATTR_IMMUTABLE;
if (flags & FS_NODUMP_FL)
if (flags & F2FS_NODUMP_FL)
stat->attributes |= STATX_ATTR_NODUMP;
stat->attributes_mask |= (STATX_ATTR_APPEND |
@ -825,7 +832,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
__setattr_copy(inode, attr);
if (attr->ia_valid & ATTR_MODE) {
err = posix_acl_chmod(inode, get_inode_mode(inode));
err = posix_acl_chmod(inode, f2fs_get_inode_mode(inode));
if (err || is_inode_flag_set(inode, FI_ACL_MODE)) {
inode->i_mode = F2FS_I(inode)->i_acl_mode;
clear_inode_flag(inode, FI_ACL_MODE);
@ -864,7 +871,7 @@ static int fill_zero(struct inode *inode, pgoff_t index,
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
page = get_new_data_page(inode, NULL, index, false);
page = f2fs_get_new_data_page(inode, NULL, index, false);
f2fs_unlock_op(sbi);
if (IS_ERR(page))
@ -877,7 +884,7 @@ static int fill_zero(struct inode *inode, pgoff_t index,
return 0;
}
int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
{
int err;
@ -886,10 +893,11 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
pgoff_t end_offset, count;
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, pg_start, LOOKUP_NODE);
err = f2fs_get_dnode_of_data(&dn, pg_start, LOOKUP_NODE);
if (err) {
if (err == -ENOENT) {
pg_start = get_next_page_offset(&dn, pg_start);
pg_start = f2fs_get_next_page_offset(&dn,
pg_start);
continue;
}
return err;
@ -900,7 +908,7 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset);
truncate_data_blocks_range(&dn, count);
f2fs_truncate_data_blocks_range(&dn, count);
f2fs_put_dnode(&dn);
pg_start += count;
@ -956,7 +964,7 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
blk_end - 1);
f2fs_lock_op(sbi);
ret = truncate_hole(inode, pg_start, pg_end);
ret = f2fs_truncate_hole(inode, pg_start, pg_end);
f2fs_unlock_op(sbi);
up_write(&F2FS_I(inode)->i_mmap_sem);
}
@ -974,7 +982,7 @@ static int __read_out_blkaddrs(struct inode *inode, block_t *blkaddr,
next_dnode:
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = get_dnode_of_data(&dn, off, LOOKUP_NODE_RA);
ret = f2fs_get_dnode_of_data(&dn, off, LOOKUP_NODE_RA);
if (ret && ret != -ENOENT) {
return ret;
} else if (ret == -ENOENT) {
@ -991,7 +999,7 @@ next_dnode:
for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) {
*blkaddr = datablock_addr(dn.inode,
dn.node_page, dn.ofs_in_node);
if (!is_checkpointed_data(sbi, *blkaddr)) {
if (!f2fs_is_checkpointed_data(sbi, *blkaddr)) {
if (test_opt(sbi, LFS)) {
f2fs_put_dnode(&dn);
@ -1024,10 +1032,10 @@ static int __roll_back_blkaddrs(struct inode *inode, block_t *blkaddr,
continue;
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA);
ret = f2fs_get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA);
if (ret) {
dec_valid_block_count(sbi, inode, 1);
invalidate_blocks(sbi, *blkaddr);
f2fs_invalidate_blocks(sbi, *blkaddr);
} else {
f2fs_update_data_blkaddr(&dn, *blkaddr);
}
@ -1057,11 +1065,11 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
pgoff_t ilen;
set_new_dnode(&dn, dst_inode, NULL, NULL, 0);
ret = get_dnode_of_data(&dn, dst + i, ALLOC_NODE);
ret = f2fs_get_dnode_of_data(&dn, dst + i, ALLOC_NODE);
if (ret)
return ret;
ret = get_node_info(sbi, dn.nid, &ni);
ret = f2fs_get_node_info(sbi, dn.nid, &ni);
if (ret) {
f2fs_put_dnode(&dn);
return ret;
@ -1073,7 +1081,7 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
do {
dn.data_blkaddr = datablock_addr(dn.inode,
dn.node_page, dn.ofs_in_node);
truncate_data_blocks_range(&dn, 1);
f2fs_truncate_data_blocks_range(&dn, 1);
if (do_replace[i]) {
f2fs_i_blocks_write(src_inode,
@ -1096,10 +1104,11 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
} else {
struct page *psrc, *pdst;
psrc = get_lock_data_page(src_inode, src + i, true);
psrc = f2fs_get_lock_data_page(src_inode,
src + i, true);
if (IS_ERR(psrc))
return PTR_ERR(psrc);
pdst = get_new_data_page(dst_inode, NULL, dst + i,
pdst = f2fs_get_new_data_page(dst_inode, NULL, dst + i,
true);
if (IS_ERR(pdst)) {
f2fs_put_page(psrc, 1);
@ -1110,7 +1119,8 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
f2fs_put_page(pdst, 1);
f2fs_put_page(psrc, 1);
ret = truncate_hole(src_inode, src + i, src + i + 1);
ret = f2fs_truncate_hole(src_inode,
src + i, src + i + 1);
if (ret)
return ret;
i++;
@ -1132,12 +1142,14 @@ static int __exchange_data_block(struct inode *src_inode,
olen = min((pgoff_t)4 * ADDRS_PER_BLOCK, len);
src_blkaddr = f2fs_kvzalloc(F2FS_I_SB(src_inode),
sizeof(block_t) * olen, GFP_KERNEL);
array_size(olen, sizeof(block_t)),
GFP_KERNEL);
if (!src_blkaddr)
return -ENOMEM;
do_replace = f2fs_kvzalloc(F2FS_I_SB(src_inode),
sizeof(int) * olen, GFP_KERNEL);
array_size(olen, sizeof(int)),
GFP_KERNEL);
if (!do_replace) {
kvfree(src_blkaddr);
return -ENOMEM;
@ -1163,7 +1175,7 @@ static int __exchange_data_block(struct inode *src_inode,
return 0;
roll_back:
__roll_back_blkaddrs(src_inode, src_blkaddr, do_replace, src, len);
__roll_back_blkaddrs(src_inode, src_blkaddr, do_replace, src, olen);
kvfree(src_blkaddr);
kvfree(do_replace);
return ret;
@ -1206,7 +1218,7 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
pg_end = (offset + len) >> PAGE_SHIFT;
/* avoid gc operation during block exchange */
down_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
down_write(&F2FS_I(inode)->i_mmap_sem);
/* write out all dirty pages from offset */
@ -1227,12 +1239,12 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
new_size = i_size_read(inode) - len;
truncate_pagecache(inode, new_size);
ret = truncate_blocks(inode, new_size, true);
ret = f2fs_truncate_blocks(inode, new_size, true);
if (!ret)
f2fs_i_size_write(inode, new_size);
out_unlock:
up_write(&F2FS_I(inode)->i_mmap_sem);
up_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
return ret;
}
@ -1252,7 +1264,7 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
}
dn->ofs_in_node = ofs_in_node;
ret = reserve_new_blocks(dn, count);
ret = f2fs_reserve_new_blocks(dn, count);
if (ret)
return ret;
@ -1261,7 +1273,7 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
dn->data_blkaddr = datablock_addr(dn->inode,
dn->node_page, dn->ofs_in_node);
/*
* reserve_new_blocks will not guarantee entire block
* f2fs_reserve_new_blocks will not guarantee entire block
* allocation.
*/
if (dn->data_blkaddr == NULL_ADDR) {
@ -1269,9 +1281,9 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
break;
}
if (dn->data_blkaddr != NEW_ADDR) {
invalidate_blocks(sbi, dn->data_blkaddr);
f2fs_invalidate_blocks(sbi, dn->data_blkaddr);
dn->data_blkaddr = NEW_ADDR;
set_data_blkaddr(dn);
f2fs_set_data_blkaddr(dn);
}
}
@ -1337,7 +1349,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
f2fs_lock_op(sbi);
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = get_dnode_of_data(&dn, index, ALLOC_NODE);
ret = f2fs_get_dnode_of_data(&dn, index, ALLOC_NODE);
if (ret) {
f2fs_unlock_op(sbi);
goto out;
@ -1408,10 +1420,10 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
f2fs_balance_fs(sbi, true);
/* avoid gc operation during block exchange */
down_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
down_write(&F2FS_I(inode)->i_mmap_sem);
ret = truncate_blocks(inode, i_size_read(inode), true);
ret = f2fs_truncate_blocks(inode, i_size_read(inode), true);
if (ret)
goto out;
@ -1449,7 +1461,7 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
f2fs_i_size_write(inode, new_size);
out:
up_write(&F2FS_I(inode)->i_mmap_sem);
up_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
return ret;
}
@ -1492,7 +1504,7 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
last_off = map.m_lblk + map.m_len - 1;
/* update new size to the failed position */
new_size = (last_off == pg_end) ? offset + len:
new_size = (last_off == pg_end) ? offset + len :
(loff_t)(last_off + 1) << PAGE_SHIFT;
} else {
new_size = ((loff_t)pg_end << PAGE_SHIFT) + off_end;
@ -1572,13 +1584,13 @@ static int f2fs_release_file(struct inode *inode, struct file *filp)
/* some remained atomic pages should discarded */
if (f2fs_is_atomic_file(inode))
drop_inmem_pages(inode);
f2fs_drop_inmem_pages(inode);
if (f2fs_is_volatile_file(inode)) {
clear_inode_flag(inode, FI_VOLATILE_FILE);
stat_dec_volatile_write(inode);
set_inode_flag(inode, FI_DROP_CACHE);
filemap_fdatawrite(inode->i_mapping);
clear_inode_flag(inode, FI_DROP_CACHE);
clear_inode_flag(inode, FI_VOLATILE_FILE);
stat_dec_volatile_write(inode);
}
return 0;
}
@ -1595,7 +1607,7 @@ static int f2fs_file_flush(struct file *file, fl_owner_t id)
*/
if (f2fs_is_atomic_file(inode) &&
F2FS_I(inode)->inmem_task == current)
drop_inmem_pages(inode);
f2fs_drop_inmem_pages(inode);
return 0;
}
@ -1603,8 +1615,15 @@ static int f2fs_ioc_getflags(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_inode_info *fi = F2FS_I(inode);
unsigned int flags = fi->i_flags &
(FS_FL_USER_VISIBLE | FS_PROJINHERIT_FL);
unsigned int flags = fi->i_flags;
if (file_is_encrypt(inode))
flags |= F2FS_ENCRYPT_FL;
if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode))
flags |= F2FS_INLINE_DATA_FL;
flags &= F2FS_FL_USER_VISIBLE;
return put_user(flags, (int __user *)arg);
}
@ -1621,15 +1640,15 @@ static int __f2fs_ioc_setflags(struct inode *inode, unsigned int flags)
oldflags = fi->i_flags;
if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL))
if ((flags ^ oldflags) & (F2FS_APPEND_FL | F2FS_IMMUTABLE_FL))
if (!capable(CAP_LINUX_IMMUTABLE))
return -EPERM;
flags = flags & (FS_FL_USER_MODIFIABLE | FS_PROJINHERIT_FL);
flags |= oldflags & ~(FS_FL_USER_MODIFIABLE | FS_PROJINHERIT_FL);
flags = flags & F2FS_FL_USER_MODIFIABLE;
flags |= oldflags & ~F2FS_FL_USER_MODIFIABLE;
fi->i_flags = flags;
if (fi->i_flags & FS_PROJINHERIT_FL)
if (fi->i_flags & F2FS_PROJINHERIT_FL)
set_inode_flag(inode, FI_PROJ_INHERIT);
else
clear_inode_flag(inode, FI_PROJ_INHERIT);
@ -1689,7 +1708,7 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
inode_lock(inode);
down_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
if (f2fs_is_atomic_file(inode))
goto out;
@ -1698,29 +1717,25 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
if (ret)
goto out;
set_inode_flag(inode, FI_ATOMIC_FILE);
set_inode_flag(inode, FI_HOT_DATA);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
if (!get_dirty_pages(inode))
goto inc_stat;
goto skip_flush;
f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING,
"Unexpected flush for atomic writes: ino=%lu, npages=%u",
inode->i_ino, get_dirty_pages(inode));
ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
if (ret) {
clear_inode_flag(inode, FI_ATOMIC_FILE);
clear_inode_flag(inode, FI_HOT_DATA);
if (ret)
goto out;
}
skip_flush:
set_inode_flag(inode, FI_ATOMIC_FILE);
clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
inc_stat:
F2FS_I(inode)->inmem_task = current;
stat_inc_atomic_write(inode);
stat_update_max_atomic_write(inode);
out:
up_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
inode_unlock(inode);
mnt_drop_write_file(filp);
return ret;
@ -1740,27 +1755,33 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
inode_lock(inode);
down_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
if (f2fs_is_volatile_file(inode))
if (f2fs_is_volatile_file(inode)) {
ret = -EINVAL;
goto err_out;
}
if (f2fs_is_atomic_file(inode)) {
ret = commit_inmem_pages(inode);
ret = f2fs_commit_inmem_pages(inode);
if (ret)
goto err_out;
ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
if (!ret) {
clear_inode_flag(inode, FI_ATOMIC_FILE);
clear_inode_flag(inode, FI_HOT_DATA);
F2FS_I(inode)->i_gc_failures[GC_FAILURE_ATOMIC] = 0;
stat_dec_atomic_write(inode);
}
} else {
ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 1, false);
}
err_out:
up_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
if (is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) {
clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
ret = -EINVAL;
}
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
inode_unlock(inode);
mnt_drop_write_file(filp);
return ret;
@ -1845,7 +1866,7 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp)
inode_lock(inode);
if (f2fs_is_atomic_file(inode))
drop_inmem_pages(inode);
f2fs_drop_inmem_pages(inode);
if (f2fs_is_volatile_file(inode)) {
clear_inode_flag(inode, FI_VOLATILE_FILE);
stat_dec_volatile_write(inode);
@ -1902,7 +1923,7 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
f2fs_stop_checkpoint(sbi, false);
break;
case F2FS_GOING_DOWN_METAFLUSH:
sync_meta_pages(sbi, META, LONG_MAX, FS_META_IO);
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_META_IO);
f2fs_stop_checkpoint(sbi, false);
break;
default:
@ -1910,10 +1931,10 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
goto out;
}
stop_gc_thread(sbi);
stop_discard_thread(sbi);
f2fs_stop_gc_thread(sbi);
f2fs_stop_discard_thread(sbi);
drop_discard_cmd(sbi);
f2fs_drop_discard_cmd(sbi);
clear_opt(sbi, DISCARD);
f2fs_update_time(sbi, REQ_TIME);
@ -2078,15 +2099,15 @@ static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg)
if (f2fs_readonly(sbi->sb))
return -EROFS;
end = range.start + range.len;
if (range.start < MAIN_BLKADDR(sbi) || end >= MAX_BLKADDR(sbi)) {
return -EINVAL;
}
ret = mnt_want_write_file(filp);
if (ret)
return ret;
end = range.start + range.len;
if (range.start < MAIN_BLKADDR(sbi) || end >= MAX_BLKADDR(sbi)) {
ret = -EINVAL;
goto out;
}
do_more:
if (!range.sync) {
if (!mutex_trylock(&sbi->gc_mutex)) {
@ -2106,7 +2127,7 @@ out:
return ret;
}
static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg)
static int f2fs_ioc_f2fs_write_checkpoint(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@ -2135,7 +2156,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
struct inode *inode = file_inode(filp);
struct f2fs_map_blocks map = { .m_next_extent = NULL,
.m_seg_type = NO_CHECK_TYPE };
struct extent_info ei = {0,0,0};
struct extent_info ei = {0, 0, 0};
pgoff_t pg_start, pg_end, next_pgofs;
unsigned int blk_per_seg = sbi->blocks_per_seg;
unsigned int total = 0, sec_num;
@ -2144,7 +2165,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
int err;
/* if in-place-update policy is enabled, don't waste time here */
if (should_update_inplace(inode, NULL))
if (f2fs_should_update_inplace(inode, NULL))
return -EINVAL;
pg_start = range->start >> PAGE_SHIFT;
@ -2239,7 +2260,7 @@ do_map:
while (idx < map.m_lblk + map.m_len && cnt < blk_per_seg) {
struct page *page;
page = get_lock_data_page(inode, idx, true);
page = f2fs_get_lock_data_page(inode, idx, true);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto clear_out;
@ -2350,12 +2371,12 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
}
inode_lock(src);
down_write(&F2FS_I(src)->dio_rwsem[WRITE]);
down_write(&F2FS_I(src)->i_gc_rwsem[WRITE]);
if (src != dst) {
ret = -EBUSY;
if (!inode_trylock(dst))
goto out;
if (!down_write_trylock(&F2FS_I(dst)->dio_rwsem[WRITE])) {
if (!down_write_trylock(&F2FS_I(dst)->i_gc_rwsem[WRITE])) {
inode_unlock(dst);
goto out;
}
@ -2417,11 +2438,11 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
f2fs_unlock_op(sbi);
out_unlock:
if (src != dst) {
up_write(&F2FS_I(dst)->dio_rwsem[WRITE]);
up_write(&F2FS_I(dst)->i_gc_rwsem[WRITE]);
inode_unlock(dst);
}
out:
up_write(&F2FS_I(src)->dio_rwsem[WRITE]);
up_write(&F2FS_I(src)->i_gc_rwsem[WRITE]);
inode_unlock(src);
return ret;
}
@ -2579,7 +2600,7 @@ static int f2fs_ioc_setproject(struct file *filp, __u32 projid)
if (IS_NOQUOTA(inode))
goto out_unlock;
ipage = get_node_page(sbi, inode->i_ino);
ipage = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto out_unlock;
@ -2628,17 +2649,17 @@ static inline __u32 f2fs_iflags_to_xflags(unsigned long iflags)
{
__u32 xflags = 0;
if (iflags & FS_SYNC_FL)
if (iflags & F2FS_SYNC_FL)
xflags |= FS_XFLAG_SYNC;
if (iflags & FS_IMMUTABLE_FL)
if (iflags & F2FS_IMMUTABLE_FL)
xflags |= FS_XFLAG_IMMUTABLE;
if (iflags & FS_APPEND_FL)
if (iflags & F2FS_APPEND_FL)
xflags |= FS_XFLAG_APPEND;
if (iflags & FS_NODUMP_FL)
if (iflags & F2FS_NODUMP_FL)
xflags |= FS_XFLAG_NODUMP;
if (iflags & FS_NOATIME_FL)
if (iflags & F2FS_NOATIME_FL)
xflags |= FS_XFLAG_NOATIME;
if (iflags & FS_PROJINHERIT_FL)
if (iflags & F2FS_PROJINHERIT_FL)
xflags |= FS_XFLAG_PROJINHERIT;
return xflags;
}
@ -2647,31 +2668,23 @@ static inline __u32 f2fs_iflags_to_xflags(unsigned long iflags)
FS_XFLAG_APPEND | FS_XFLAG_NODUMP | \
FS_XFLAG_NOATIME | FS_XFLAG_PROJINHERIT)
/* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */
#define F2FS_FL_XFLAG_VISIBLE (FS_SYNC_FL | \
FS_IMMUTABLE_FL | \
FS_APPEND_FL | \
FS_NODUMP_FL | \
FS_NOATIME_FL | \
FS_PROJINHERIT_FL)
/* Transfer xflags flags to internal */
static inline unsigned long f2fs_xflags_to_iflags(__u32 xflags)
{
unsigned long iflags = 0;
if (xflags & FS_XFLAG_SYNC)
iflags |= FS_SYNC_FL;
iflags |= F2FS_SYNC_FL;
if (xflags & FS_XFLAG_IMMUTABLE)
iflags |= FS_IMMUTABLE_FL;
iflags |= F2FS_IMMUTABLE_FL;
if (xflags & FS_XFLAG_APPEND)
iflags |= FS_APPEND_FL;
iflags |= F2FS_APPEND_FL;
if (xflags & FS_XFLAG_NODUMP)
iflags |= FS_NODUMP_FL;
iflags |= F2FS_NODUMP_FL;
if (xflags & FS_XFLAG_NOATIME)
iflags |= FS_NOATIME_FL;
iflags |= F2FS_NOATIME_FL;
if (xflags & FS_XFLAG_PROJINHERIT)
iflags |= FS_PROJINHERIT_FL;
iflags |= F2FS_PROJINHERIT_FL;
return iflags;
}
@ -2684,7 +2697,7 @@ static int f2fs_ioc_fsgetxattr(struct file *filp, unsigned long arg)
memset(&fa, 0, sizeof(struct fsxattr));
fa.fsx_xflags = f2fs_iflags_to_xflags(fi->i_flags &
(FS_FL_USER_VISIBLE | FS_PROJINHERIT_FL));
F2FS_FL_USER_VISIBLE);
if (f2fs_sb_has_project_quota(inode->i_sb))
fa.fsx_projid = (__u32)from_kprojid(&init_user_ns,
@ -2744,12 +2757,14 @@ int f2fs_pin_file_control(struct inode *inode, bool inc)
/* Use i_gc_failures for normal file as a risk signal. */
if (inc)
f2fs_i_gc_failures_write(inode, fi->i_gc_failures + 1);
f2fs_i_gc_failures_write(inode,
fi->i_gc_failures[GC_FAILURE_PIN] + 1);
if (fi->i_gc_failures > sbi->gc_pin_file_threshold) {
if (fi->i_gc_failures[GC_FAILURE_PIN] > sbi->gc_pin_file_threshold) {
f2fs_msg(sbi->sb, KERN_WARNING,
"%s: Enable GC = ino %lx after %x GC trials\n",
__func__, inode->i_ino, fi->i_gc_failures);
__func__, inode->i_ino,
fi->i_gc_failures[GC_FAILURE_PIN]);
clear_inode_flag(inode, FI_PIN_FILE);
return -EAGAIN;
}
@ -2780,14 +2795,14 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg)
inode_lock(inode);
if (should_update_outplace(inode, NULL)) {
if (f2fs_should_update_outplace(inode, NULL)) {
ret = -EINVAL;
goto out;
}
if (!pin) {
clear_inode_flag(inode, FI_PIN_FILE);
F2FS_I(inode)->i_gc_failures = 1;
F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN] = 1;
goto done;
}
@ -2800,7 +2815,7 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg)
goto out;
set_inode_flag(inode, FI_PIN_FILE);
ret = F2FS_I(inode)->i_gc_failures;
ret = F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN];
done:
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
out:
@ -2815,7 +2830,7 @@ static int f2fs_ioc_get_pin_file(struct file *filp, unsigned long arg)
__u32 pin = 0;
if (is_inode_flag_set(inode, FI_PIN_FILE))
pin = F2FS_I(inode)->i_gc_failures;
pin = F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN];
return put_user(pin, (u32 __user *)arg);
}
@ -2839,9 +2854,9 @@ int f2fs_precache_extents(struct inode *inode)
while (map.m_lblk < end) {
map.m_len = end - map.m_lblk;
down_write(&fi->dio_rwsem[WRITE]);
down_write(&fi->i_gc_rwsem[WRITE]);
err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_PRECACHE);
up_write(&fi->dio_rwsem[WRITE]);
up_write(&fi->i_gc_rwsem[WRITE]);
if (err)
return err;
@ -2893,7 +2908,7 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
case F2FS_IOC_GARBAGE_COLLECT_RANGE:
return f2fs_ioc_gc_range(filp, arg);
case F2FS_IOC_WRITE_CHECKPOINT:
return f2fs_ioc_write_checkpoint(filp, arg);
return f2fs_ioc_f2fs_write_checkpoint(filp, arg);
case F2FS_IOC_DEFRAGMENT:
return f2fs_ioc_defragment(filp, arg);
case F2FS_IOC_MOVE_RANGE:
@ -2921,7 +2936,6 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
struct blk_plug plug;
ssize_t ret;
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
@ -2951,6 +2965,8 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
iov_iter_count(from)) ||
f2fs_has_inline_data(inode) ||
f2fs_force_buffered_io(inode, WRITE)) {
clear_inode_flag(inode,
FI_NO_PREALLOC);
inode_unlock(inode);
return -EAGAIN;
}
@ -2966,9 +2982,7 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
return err;
}
}
blk_start_plug(&plug);
ret = __generic_file_write_iter(iocb, from);
blk_finish_plug(&plug);
clear_inode_flag(inode, FI_NO_PREALLOC);
/* if we couldn't write data, we should deallocate blocks. */

159
fs/f2fs/gc.c
View File

@ -76,7 +76,7 @@ static int gc_thread_func(void *data)
* invalidated soon after by user update or deletion.
* So, I'd like to wait some time to collect dirty segments.
*/
if (gc_th->gc_urgent) {
if (sbi->gc_mode == GC_URGENT) {
wait_ms = gc_th->urgent_sleep_time;
mutex_lock(&sbi->gc_mutex);
goto do_gc;
@ -114,7 +114,7 @@ next:
return 0;
}
int start_gc_thread(struct f2fs_sb_info *sbi)
int f2fs_start_gc_thread(struct f2fs_sb_info *sbi)
{
struct f2fs_gc_kthread *gc_th;
dev_t dev = sbi->sb->s_bdev->bd_dev;
@ -131,8 +131,6 @@ int start_gc_thread(struct f2fs_sb_info *sbi)
gc_th->max_sleep_time = DEF_GC_THREAD_MAX_SLEEP_TIME;
gc_th->no_gc_sleep_time = DEF_GC_THREAD_NOGC_SLEEP_TIME;
gc_th->gc_idle = 0;
gc_th->gc_urgent = 0;
gc_th->gc_wake= 0;
sbi->gc_thread = gc_th;
@ -148,7 +146,7 @@ out:
return err;
}
void stop_gc_thread(struct f2fs_sb_info *sbi)
void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi)
{
struct f2fs_gc_kthread *gc_th = sbi->gc_thread;
if (!gc_th)
@ -158,21 +156,19 @@ void stop_gc_thread(struct f2fs_sb_info *sbi)
sbi->gc_thread = NULL;
}
static int select_gc_type(struct f2fs_gc_kthread *gc_th, int gc_type)
static int select_gc_type(struct f2fs_sb_info *sbi, int gc_type)
{
int gc_mode = (gc_type == BG_GC) ? GC_CB : GC_GREEDY;
if (!gc_th)
return gc_mode;
if (gc_th->gc_idle) {
if (gc_th->gc_idle == 1)
gc_mode = GC_CB;
else if (gc_th->gc_idle == 2)
gc_mode = GC_GREEDY;
}
if (gc_th->gc_urgent)
switch (sbi->gc_mode) {
case GC_IDLE_CB:
gc_mode = GC_CB;
break;
case GC_IDLE_GREEDY:
case GC_URGENT:
gc_mode = GC_GREEDY;
break;
}
return gc_mode;
}
@ -187,7 +183,7 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
p->max_search = dirty_i->nr_dirty[type];
p->ofs_unit = 1;
} else {
p->gc_mode = select_gc_type(sbi->gc_thread, gc_type);
p->gc_mode = select_gc_type(sbi, gc_type);
p->dirty_segmap = dirty_i->dirty_segmap[DIRTY];
p->max_search = dirty_i->nr_dirty[DIRTY];
p->ofs_unit = sbi->segs_per_sec;
@ -195,7 +191,7 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
/* we need to check every dirty segments in the FG_GC case */
if (gc_type != FG_GC &&
(sbi->gc_thread && !sbi->gc_thread->gc_urgent) &&
(sbi->gc_mode != GC_URGENT) &&
p->max_search > sbi->max_victim_search)
p->max_search = sbi->max_victim_search;
@ -234,10 +230,6 @@ static unsigned int check_bg_victims(struct f2fs_sb_info *sbi)
for_each_set_bit(secno, dirty_i->victim_secmap, MAIN_SECS(sbi)) {
if (sec_usage_check(sbi, secno))
continue;
if (no_fggc_candidate(sbi, secno))
continue;
clear_bit(secno, dirty_i->victim_secmap);
return GET_SEG_FROM_SEC(sbi, secno);
}
@ -377,9 +369,6 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
goto next;
if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap))
goto next;
if (gc_type == FG_GC && p.alloc_mode == LFS &&
no_fggc_candidate(sbi, secno))
goto next;
cost = get_gc_cost(sbi, segno, &p);
@ -440,7 +429,7 @@ static void add_gc_inode(struct gc_inode_list *gc_list, struct inode *inode)
iput(inode);
return;
}
new_ie = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
new_ie = f2fs_kmem_cache_alloc(f2fs_inode_entry_slab, GFP_NOFS);
new_ie->inode = inode;
f2fs_radix_tree_insert(&gc_list->iroot, inode->i_ino, new_ie);
@ -454,7 +443,7 @@ static void put_gc_inode(struct gc_inode_list *gc_list)
radix_tree_delete(&gc_list->iroot, ie->inode->i_ino);
iput(ie->inode);
list_del(&ie->list);
kmem_cache_free(inode_entry_slab, ie);
kmem_cache_free(f2fs_inode_entry_slab, ie);
}
}
@ -485,12 +474,16 @@ static int gc_node_segment(struct f2fs_sb_info *sbi,
int off;
int phase = 0;
int submitted = 0;
bool fggc = (gc_type == FG_GC);
start_addr = START_BLOCK(sbi, segno);
next_step:
entry = sum;
if (fggc && phase == 2)
atomic_inc(&sbi->wb_sync_req[NODE]);
for (off = 0; off < sbi->blocks_per_seg; off++, entry++) {
nid_t nid = le32_to_cpu(entry->nid);
struct page *node_page;
@ -505,28 +498,28 @@ next_step:
continue;
if (phase == 0) {
ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1,
f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1,
META_NAT, true);
continue;
}
if (phase == 1) {
ra_node_page(sbi, nid);
f2fs_ra_node_page(sbi, nid);
continue;
}
/* phase == 2 */
node_page = get_node_page(sbi, nid);
node_page = f2fs_get_node_page(sbi, nid);
if (IS_ERR(node_page))
continue;
/* block may become invalid during get_node_page */
/* block may become invalid during f2fs_get_node_page */
if (check_valid_map(sbi, segno, off) == 0) {
f2fs_put_page(node_page, 1);
continue;
}
if (get_node_info(sbi, nid, &ni)) {
if (f2fs_get_node_info(sbi, nid, &ni)) {
f2fs_put_page(node_page, 1);
continue;
}
@ -536,7 +529,7 @@ next_step:
continue;
}
err = move_node_page(node_page, gc_type);
err = f2fs_move_node_page(node_page, gc_type);
if (!err && gc_type == FG_GC)
submitted++;
stat_inc_node_blk_count(sbi, 1, gc_type);
@ -544,6 +537,9 @@ next_step:
if (++phase < 3)
goto next_step;
if (fggc)
atomic_dec(&sbi->wb_sync_req[NODE]);
return submitted;
}
@ -554,7 +550,7 @@ next_step:
* as indirect or double indirect node blocks, are given, it must be a caller's
* bug.
*/
block_t start_bidx_of_node(unsigned int node_ofs, struct inode *inode)
block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode)
{
unsigned int indirect_blks = 2 * NIDS_PER_BLOCK + 4;
unsigned int bidx;
@ -585,11 +581,11 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
nid = le32_to_cpu(sum->nid);
ofs_in_node = le16_to_cpu(sum->ofs_in_node);
node_page = get_node_page(sbi, nid);
node_page = f2fs_get_node_page(sbi, nid);
if (IS_ERR(node_page))
return false;
if (get_node_info(sbi, nid, dni)) {
if (f2fs_get_node_info(sbi, nid, dni)) {
f2fs_put_page(node_page, 1);
return false;
}
@ -615,7 +611,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
* This can be used to move blocks, aka LBAs, directly on disk.
*/
static int move_data_block(struct inode *inode, block_t bidx,
unsigned int segno, int off)
int gc_type, unsigned int segno, int off)
{
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(inode),
@ -626,6 +622,7 @@ static int move_data_block(struct inode *inode, block_t bidx,
.op_flags = 0,
.encrypted_page = NULL,
.in_list = false,
.retry = false,
};
struct dnode_of_data dn;
struct f2fs_summary sum;
@ -633,6 +630,7 @@ static int move_data_block(struct inode *inode, block_t bidx,
struct page *page;
block_t newaddr;
int err = 0;
bool lfs_mode = test_opt(fio.sbi, LFS);
/* do not read out */
page = f2fs_grab_cache_page(inode->i_mapping, bidx, false);
@ -646,6 +644,8 @@ static int move_data_block(struct inode *inode, block_t bidx,
if (f2fs_is_atomic_file(inode)) {
err = -EAGAIN;
F2FS_I(inode)->i_gc_failures[GC_FAILURE_ATOMIC]++;
F2FS_I_SB(inode)->skipped_atomic_files[gc_type]++;
goto out;
}
@ -656,7 +656,7 @@ static int move_data_block(struct inode *inode, block_t bidx,
}
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, bidx, LOOKUP_NODE);
err = f2fs_get_dnode_of_data(&dn, bidx, LOOKUP_NODE);
if (err)
goto out;
@ -672,7 +672,7 @@ static int move_data_block(struct inode *inode, block_t bidx,
*/
f2fs_wait_on_page_writeback(page, DATA, true);
err = get_node_info(fio.sbi, dn.nid, &ni);
err = f2fs_get_node_info(fio.sbi, dn.nid, &ni);
if (err)
goto put_out;
@ -683,7 +683,10 @@ static int move_data_block(struct inode *inode, block_t bidx,
fio.page = page;
fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr;
allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
if (lfs_mode)
down_write(&fio.sbi->io_order_lock);
f2fs_allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
&sum, CURSEG_COLD_DATA, NULL, false);
fio.encrypted_page = f2fs_pagecache_get_page(META_MAPPING(fio.sbi),
@ -723,8 +726,8 @@ static int move_data_block(struct inode *inode, block_t bidx,
fio.op = REQ_OP_WRITE;
fio.op_flags = REQ_SYNC;
fio.new_blkaddr = newaddr;
err = f2fs_submit_page_write(&fio);
if (err) {
f2fs_submit_page_write(&fio);
if (fio.retry) {
if (PageWriteback(fio.encrypted_page))
end_page_writeback(fio.encrypted_page);
goto put_page_out;
@ -739,8 +742,10 @@ static int move_data_block(struct inode *inode, block_t bidx,
put_page_out:
f2fs_put_page(fio.encrypted_page, 1);
recover_block:
if (lfs_mode)
up_write(&fio.sbi->io_order_lock);
if (err)
__f2fs_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr,
f2fs_do_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr,
true, true);
put_out:
f2fs_put_dnode(&dn);
@ -755,7 +760,7 @@ static int move_data_page(struct inode *inode, block_t bidx, int gc_type,
struct page *page;
int err = 0;
page = get_lock_data_page(inode, bidx, true);
page = f2fs_get_lock_data_page(inode, bidx, true);
if (IS_ERR(page))
return PTR_ERR(page);
@ -766,6 +771,8 @@ static int move_data_page(struct inode *inode, block_t bidx, int gc_type,
if (f2fs_is_atomic_file(inode)) {
err = -EAGAIN;
F2FS_I(inode)->i_gc_failures[GC_FAILURE_ATOMIC]++;
F2FS_I_SB(inode)->skipped_atomic_files[gc_type]++;
goto out;
}
if (f2fs_is_pinned_file(inode)) {
@ -803,12 +810,12 @@ retry:
f2fs_wait_on_page_writeback(page, DATA, true);
if (clear_page_dirty_for_io(page)) {
inode_dec_dirty_pages(inode);
remove_dirty_inode(inode);
f2fs_remove_dirty_inode(inode);
}
set_cold_data(page);
err = do_write_data_page(&fio);
err = f2fs_do_write_data_page(&fio);
if (err) {
clear_cold_data(page);
if (err == -ENOMEM) {
@ -862,13 +869,13 @@ next_step:
continue;
if (phase == 0) {
ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1,
f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1,
META_NAT, true);
continue;
}
if (phase == 1) {
ra_node_page(sbi, nid);
f2fs_ra_node_page(sbi, nid);
continue;
}
@ -877,7 +884,7 @@ next_step:
continue;
if (phase == 2) {
ra_node_page(sbi, dni.ino);
f2fs_ra_node_page(sbi, dni.ino);
continue;
}
@ -895,16 +902,16 @@ next_step:
}
if (!down_write_trylock(
&F2FS_I(inode)->dio_rwsem[WRITE])) {
&F2FS_I(inode)->i_gc_rwsem[WRITE])) {
iput(inode);
continue;
}
start_bidx = start_bidx_of_node(nofs, inode);
data_page = get_read_data_page(inode,
start_bidx = f2fs_start_bidx_of_node(nofs, inode);
data_page = f2fs_get_read_data_page(inode,
start_bidx + ofs_in_node, REQ_RAHEAD,
true);
up_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
if (IS_ERR(data_page)) {
iput(inode);
continue;
@ -923,11 +930,11 @@ next_step:
int err;
if (S_ISREG(inode->i_mode)) {
if (!down_write_trylock(&fi->dio_rwsem[READ]))
if (!down_write_trylock(&fi->i_gc_rwsem[READ]))
continue;
if (!down_write_trylock(
&fi->dio_rwsem[WRITE])) {
up_write(&fi->dio_rwsem[READ]);
&fi->i_gc_rwsem[WRITE])) {
up_write(&fi->i_gc_rwsem[READ]);
continue;
}
locked = true;
@ -936,10 +943,11 @@ next_step:
inode_dio_wait(inode);
}
start_bidx = start_bidx_of_node(nofs, inode)
start_bidx = f2fs_start_bidx_of_node(nofs, inode)
+ ofs_in_node;
if (f2fs_post_read_required(inode))
err = move_data_block(inode, start_bidx, segno, off);
err = move_data_block(inode, start_bidx, gc_type,
segno, off);
else
err = move_data_page(inode, start_bidx, gc_type,
segno, off);
@ -949,8 +957,8 @@ next_step:
submitted++;
if (locked) {
up_write(&fi->dio_rwsem[WRITE]);
up_write(&fi->dio_rwsem[READ]);
up_write(&fi->i_gc_rwsem[WRITE]);
up_write(&fi->i_gc_rwsem[READ]);
}
stat_inc_data_blk_count(sbi, 1, gc_type);
@ -992,12 +1000,12 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
/* readahead multi ssa blocks those have contiguous address */
if (sbi->segs_per_sec > 1)
ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno),
f2fs_ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno),
sbi->segs_per_sec, META_SSA, true);
/* reference all summary page */
while (segno < end_segno) {
sum_page = get_sum_page(sbi, segno++);
sum_page = f2fs_get_sum_page(sbi, segno++);
if (IS_ERR(sum_page)) {
int err = PTR_ERR(sum_page);
@ -1082,6 +1090,8 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
.ilist = LIST_HEAD_INIT(gc_list.ilist),
.iroot = RADIX_TREE_INIT(GFP_NOFS),
};
unsigned long long last_skipped = sbi->skipped_atomic_files[FG_GC];
unsigned int skipped_round = 0, round = 0;
trace_f2fs_gc_begin(sbi->sb, sync, background,
get_pages(sbi, F2FS_DIRTY_NODES),
@ -1110,7 +1120,7 @@ gc_more:
* secure free segments which doesn't need fggc any more.
*/
if (prefree_segments(sbi)) {
ret = write_checkpoint(sbi, &cpc);
ret = f2fs_write_checkpoint(sbi, &cpc);
if (ret)
goto stop;
}
@ -1133,17 +1143,27 @@ gc_more:
sec_freed++;
total_freed += seg_freed;
if (gc_type == FG_GC) {
if (sbi->skipped_atomic_files[FG_GC] > last_skipped)
skipped_round++;
last_skipped = sbi->skipped_atomic_files[FG_GC];
round++;
}
if (gc_type == FG_GC)
sbi->cur_victim_sec = NULL_SEGNO;
if (!sync) {
if (has_not_enough_free_secs(sbi, sec_freed, 0)) {
if (skipped_round > MAX_SKIP_ATOMIC_COUNT &&
skipped_round * 2 >= round)
f2fs_drop_inmem_pages_all(sbi, true);
segno = NULL_SEGNO;
goto gc_more;
}
if (gc_type == FG_GC)
ret = write_checkpoint(sbi, &cpc);
ret = f2fs_write_checkpoint(sbi, &cpc);
}
stop:
SIT_I(sbi)->last_victim[ALLOC_NEXT] = 0;
@ -1167,19 +1187,10 @@ stop:
return ret;
}
void build_gc_manager(struct f2fs_sb_info *sbi)
void f2fs_build_gc_manager(struct f2fs_sb_info *sbi)
{
u64 main_count, resv_count, ovp_count;
DIRTY_I(sbi)->v_ops = &default_v_ops;
/* threshold of # of valid blocks in a section for victims of FG_GC */
main_count = SM_I(sbi)->main_segments << sbi->log_blocks_per_seg;
resv_count = SM_I(sbi)->reserved_segments << sbi->log_blocks_per_seg;
ovp_count = SM_I(sbi)->ovp_segments << sbi->log_blocks_per_seg;
sbi->fggc_threshold = div64_u64((main_count - ovp_count) *
BLKS_PER_SEC(sbi), (main_count - resv_count));
sbi->gc_pin_file_threshold = DEF_GC_FAILED_PINNED_FILES;
/* give warm/cold data area from slower device */

2
fs/f2fs/gc.h
View File

@ -36,8 +36,6 @@ struct f2fs_gc_kthread {
unsigned int no_gc_sleep_time;
/* for changing gc mode */
unsigned int gc_idle;
unsigned int gc_urgent;
unsigned int gc_wake;
};

77
fs/f2fs/inline.c
View File

@ -43,7 +43,7 @@ bool f2fs_may_inline_dentry(struct inode *inode)
return true;
}
void read_inline_data(struct page *page, struct page *ipage)
void f2fs_do_read_inline_data(struct page *page, struct page *ipage)
{
struct inode *inode = page->mapping->host;
void *src_addr, *dst_addr;
@ -65,7 +65,8 @@ void read_inline_data(struct page *page, struct page *ipage)
SetPageUptodate(page);
}
void truncate_inline_inode(struct inode *inode, struct page *ipage, u64 from)
void f2fs_truncate_inline_inode(struct inode *inode,
struct page *ipage, u64 from)
{
void *addr;
@ -97,7 +98,7 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page)
path, current->comm);
}
ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage)) {
trace_android_fs_dataread_end(inode, page_offset(page),
PAGE_SIZE);
@ -115,7 +116,7 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page)
if (page->index)
zero_user_segment(page, 0, PAGE_SIZE);
else
read_inline_data(page, ipage);
f2fs_do_read_inline_data(page, ipage);
if (!PageUptodate(page))
SetPageUptodate(page);
@ -147,7 +148,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
err = f2fs_reserve_block(dn, 0);
if (err)
return err;
err = get_node_info(fio.sbi, dn->nid, &ni);
err = f2fs_get_node_info(fio.sbi, dn->nid, &ni);
if (err) {
f2fs_put_dnode(dn);
return err;
@ -167,7 +168,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
f2fs_bug_on(F2FS_P_SB(page), PageWriteback(page));
read_inline_data(page, dn->inode_page);
f2fs_do_read_inline_data(page, dn->inode_page);
set_page_dirty(page);
/* clear dirty state */
@ -178,18 +179,18 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
ClearPageError(page);
fio.old_blkaddr = dn->data_blkaddr;
set_inode_flag(dn->inode, FI_HOT_DATA);
write_data_page(dn, &fio);
f2fs_outplace_write_data(dn, &fio);
f2fs_wait_on_page_writeback(page, DATA, true);
if (dirty) {
inode_dec_dirty_pages(dn->inode);
remove_dirty_inode(dn->inode);
f2fs_remove_dirty_inode(dn->inode);
}
/* this converted inline_data should be recovered. */
set_inode_flag(dn->inode, FI_APPEND_WRITE);
/* clear inline data and flag after data writeback */
truncate_inline_inode(dn->inode, dn->inode_page, 0);
f2fs_truncate_inline_inode(dn->inode, dn->inode_page, 0);
clear_inline_node(dn->inode_page);
clear_out:
stat_dec_inline_inode(dn->inode);
@ -214,7 +215,7 @@ int f2fs_convert_inline_inode(struct inode *inode)
f2fs_lock_op(sbi);
ipage = get_node_page(sbi, inode->i_ino);
ipage = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto out;
@ -240,12 +241,10 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
{
void *src_addr, *dst_addr;
struct dnode_of_data dn;
struct address_space *mapping = page_mapping(page);
unsigned long flags;
int err;
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, 0, LOOKUP_NODE);
err = f2fs_get_dnode_of_data(&dn, 0, LOOKUP_NODE);
if (err)
return err;
@ -263,10 +262,7 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
kunmap_atomic(src_addr);
set_page_dirty(dn.inode_page);
spin_lock_irqsave(&mapping->tree_lock, flags);
radix_tree_tag_clear(&mapping->page_tree, page_index(page),
PAGECACHE_TAG_DIRTY);
spin_unlock_irqrestore(&mapping->tree_lock, flags);
f2fs_clear_radix_tree_dirty_tag(page);
set_inode_flag(inode, FI_APPEND_WRITE);
set_inode_flag(inode, FI_DATA_EXIST);
@ -276,7 +272,7 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
return 0;
}
bool recover_inline_data(struct inode *inode, struct page *npage)
bool f2fs_recover_inline_data(struct inode *inode, struct page *npage)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode *ri = NULL;
@ -297,7 +293,7 @@ bool recover_inline_data(struct inode *inode, struct page *npage)
if (f2fs_has_inline_data(inode) &&
ri && (ri->i_inline & F2FS_INLINE_DATA)) {
process_inline:
ipage = get_node_page(sbi, inode->i_ino);
ipage = f2fs_get_node_page(sbi, inode->i_ino);
f2fs_bug_on(sbi, IS_ERR(ipage));
f2fs_wait_on_page_writeback(ipage, NODE, true);
@ -315,20 +311,20 @@ process_inline:
}
if (f2fs_has_inline_data(inode)) {
ipage = get_node_page(sbi, inode->i_ino);
ipage = f2fs_get_node_page(sbi, inode->i_ino);
f2fs_bug_on(sbi, IS_ERR(ipage));
truncate_inline_inode(inode, ipage, 0);
f2fs_truncate_inline_inode(inode, ipage, 0);
clear_inode_flag(inode, FI_INLINE_DATA);
f2fs_put_page(ipage, 1);
} else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) {
if (truncate_blocks(inode, 0, false))
if (f2fs_truncate_blocks(inode, 0, false))
return false;
goto process_inline;
}
return false;
}
struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
struct fscrypt_name *fname, struct page **res_page)
{
struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
@ -339,7 +335,7 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
void *inline_dentry;
f2fs_hash_t namehash;
ipage = get_node_page(sbi, dir->i_ino);
ipage = f2fs_get_node_page(sbi, dir->i_ino);
if (IS_ERR(ipage)) {
*res_page = ipage;
return NULL;
@ -350,7 +346,7 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
inline_dentry = inline_data_addr(dir, ipage);
make_dentry_ptr_inline(dir, &d, inline_dentry);
de = find_target_dentry(fname, namehash, NULL, &d);
de = f2fs_find_target_dentry(fname, namehash, NULL, &d);
unlock_page(ipage);
if (de)
*res_page = ipage;
@ -360,7 +356,7 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
return de;
}
int make_empty_inline_dir(struct inode *inode, struct inode *parent,
int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent,
struct page *ipage)
{
struct f2fs_dentry_ptr d;
@ -369,7 +365,7 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent,
inline_dentry = inline_data_addr(inode, ipage);
make_dentry_ptr_inline(inode, &d, inline_dentry);
do_make_empty_dir(inode, parent, &d);
f2fs_do_make_empty_dir(inode, parent, &d);
set_page_dirty(ipage);
@ -415,7 +411,6 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
}
f2fs_wait_on_page_writeback(page, DATA, true);
zero_user_segment(page, MAX_INLINE_DATA(dir), PAGE_SIZE);
dentry_blk = page_address(page);
@ -439,7 +434,7 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
set_page_dirty(page);
/* clear inline dir and flag after data writeback */
truncate_inline_inode(dir, ipage, 0);
f2fs_truncate_inline_inode(dir, ipage, 0);
stat_dec_inline_dir(dir);
clear_inode_flag(dir, FI_INLINE_DENTRY);
@ -482,7 +477,7 @@ static int f2fs_add_inline_entries(struct inode *dir, void *inline_dentry)
new_name.len = le16_to_cpu(de->name_len);
ino = le32_to_cpu(de->ino);
fake_mode = get_de_type(de) << S_SHIFT;
fake_mode = f2fs_get_de_type(de) << S_SHIFT;
err = f2fs_add_regular_entry(dir, &new_name, NULL, NULL,
ino, fake_mode);
@ -494,8 +489,8 @@ static int f2fs_add_inline_entries(struct inode *dir, void *inline_dentry)
return 0;
punch_dentry_pages:
truncate_inode_pages(&dir->i_data, 0);
truncate_blocks(dir, 0, false);
remove_dirty_inode(dir);
f2fs_truncate_blocks(dir, 0, false);
f2fs_remove_dirty_inode(dir);
return err;
}
@ -513,7 +508,7 @@ static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
}
memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA(dir));
truncate_inline_inode(dir, ipage, 0);
f2fs_truncate_inline_inode(dir, ipage, 0);
unlock_page(ipage);
@ -563,14 +558,14 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
struct page *page = NULL;
int err = 0;
ipage = get_node_page(sbi, dir->i_ino);
ipage = f2fs_get_node_page(sbi, dir->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
inline_dentry = inline_data_addr(dir, ipage);
make_dentry_ptr_inline(dir, &d, inline_dentry);
bit_pos = room_for_filename(d.bitmap, slots, d.max);
bit_pos = f2fs_room_for_filename(d.bitmap, slots, d.max);
if (bit_pos >= d.max) {
err = f2fs_convert_inline_dir(dir, ipage, inline_dentry);
if (err)
@ -581,7 +576,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
if (inode) {
down_write(&F2FS_I(inode)->i_sem);
page = init_inode_metadata(inode, dir, new_name,
page = f2fs_init_inode_metadata(inode, dir, new_name,
orig_name, ipage);
if (IS_ERR(page)) {
err = PTR_ERR(page);
@ -602,7 +597,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
f2fs_put_page(page, 1);
}
update_parent_metadata(dir, inode, 0);
f2fs_update_parent_metadata(dir, inode, 0);
fail:
if (inode)
up_write(&F2FS_I(inode)->i_sem);
@ -648,7 +643,7 @@ bool f2fs_empty_inline_dir(struct inode *dir)
void *inline_dentry;
struct f2fs_dentry_ptr d;
ipage = get_node_page(sbi, dir->i_ino);
ipage = f2fs_get_node_page(sbi, dir->i_ino);
if (IS_ERR(ipage))
return false;
@ -679,7 +674,7 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
if (ctx->pos == d.max)
return 0;
ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
@ -705,7 +700,7 @@ int f2fs_inline_data_fiemap(struct inode *inode,
struct page *ipage;
int err = 0;
ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
@ -721,7 +716,7 @@ int f2fs_inline_data_fiemap(struct inode *inode,
ilen = start + len;
ilen -= start;
err = get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni);
err = f2fs_get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni);
if (err)
goto out;

103
fs/f2fs/inode.c
View File

@ -36,15 +36,15 @@ void f2fs_set_inode_flags(struct inode *inode)
unsigned int flags = F2FS_I(inode)->i_flags;
unsigned int new_fl = 0;
if (flags & FS_SYNC_FL)
if (flags & F2FS_SYNC_FL)
new_fl |= S_SYNC;
if (flags & FS_APPEND_FL)
if (flags & F2FS_APPEND_FL)
new_fl |= S_APPEND;
if (flags & FS_IMMUTABLE_FL)
if (flags & F2FS_IMMUTABLE_FL)
new_fl |= S_IMMUTABLE;
if (flags & FS_NOATIME_FL)
if (flags & F2FS_NOATIME_FL)
new_fl |= S_NOATIME;
if (flags & FS_DIRSYNC_FL)
if (flags & F2FS_DIRSYNC_FL)
new_fl |= S_DIRSYNC;
if (f2fs_encrypted_inode(inode))
new_fl |= S_ENCRYPTED;
@ -120,7 +120,6 @@ static void __recover_inline_status(struct inode *inode, struct page *ipage)
static bool f2fs_enable_inode_chksum(struct f2fs_sb_info *sbi, struct page *page)
{
struct f2fs_inode *ri = &F2FS_NODE(page)->i;
int extra_isize = le32_to_cpu(ri->i_extra_isize);
if (!f2fs_sb_has_inode_chksum(sbi->sb))
return false;
@ -128,7 +127,8 @@ static bool f2fs_enable_inode_chksum(struct f2fs_sb_info *sbi, struct page *page
if (!RAW_IS_INODE(F2FS_NODE(page)) || !(ri->i_inline & F2FS_EXTRA_ATTR))
return false;
if (!F2FS_FITS_IN_INODE(ri, extra_isize, i_inode_checksum))
if (!F2FS_FITS_IN_INODE(ri, le16_to_cpu(ri->i_extra_isize),
i_inode_checksum))
return false;
return true;
@ -214,6 +214,15 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
return false;
}
if (f2fs_sb_has_flexible_inline_xattr(sbi->sb)
&& !f2fs_has_extra_attr(inode)) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"%s: corrupted inode ino=%lx, run fsck to fix.",
__func__, inode->i_ino);
return false;
}
if (f2fs_has_extra_attr(inode) &&
!f2fs_sb_has_extra_attr(sbi->sb)) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
@ -264,14 +273,10 @@ static int do_read_inode(struct inode *inode)
int err;
/* Check if ino is within scope */
if (check_nid_range(sbi, inode->i_ino)) {
f2fs_msg(inode->i_sb, KERN_ERR, "bad inode number: %lu",
(unsigned long) inode->i_ino);
WARN_ON(1);
if (f2fs_check_nid_range(sbi, inode->i_ino))
return -EINVAL;
}
node_page = get_node_page(sbi, inode->i_ino);
node_page = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(node_page))
return PTR_ERR(node_page);
@ -291,8 +296,11 @@ static int do_read_inode(struct inode *inode)
inode->i_ctime.tv_nsec = le32_to_cpu(ri->i_ctime_nsec);
inode->i_mtime.tv_nsec = le32_to_cpu(ri->i_mtime_nsec);
inode->i_generation = le32_to_cpu(ri->i_generation);
fi->i_current_depth = le32_to_cpu(ri->i_current_depth);
if (S_ISDIR(inode->i_mode))
fi->i_current_depth = le32_to_cpu(ri->i_current_depth);
else if (S_ISREG(inode->i_mode))
fi->i_gc_failures[GC_FAILURE_PIN] =
le16_to_cpu(ri->i_gc_failures);
fi->i_xattr_nid = le32_to_cpu(ri->i_xattr_nid);
fi->i_flags = le32_to_cpu(ri->i_flags);
fi->flags = 0;
@ -309,7 +317,6 @@ static int do_read_inode(struct inode *inode)
le16_to_cpu(ri->i_extra_isize) : 0;
if (f2fs_sb_has_flexible_inline_xattr(sbi->sb)) {
f2fs_bug_on(sbi, !f2fs_has_extra_attr(inode));
fi->i_inline_xattr_size = le16_to_cpu(ri->i_inline_xattr_size);
} else if (f2fs_has_inline_xattr(inode) ||
f2fs_has_inline_dentry(inode)) {
@ -345,10 +352,10 @@ static int do_read_inode(struct inode *inode)
if (!err)
set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
if (!need_inode_block_update(sbi, inode->i_ino))
if (!f2fs_need_inode_block_update(sbi, inode->i_ino))
fi->last_disk_size = inode->i_size;
if (fi->i_flags & FS_PROJINHERIT_FL)
if (fi->i_flags & F2FS_PROJINHERIT_FL)
set_inode_flag(inode, FI_PROJ_INHERIT);
if (f2fs_has_extra_attr(inode) && f2fs_sb_has_project_quota(sbi->sb) &&
@ -400,10 +407,10 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
make_now:
if (ino == F2FS_NODE_INO(sbi)) {
inode->i_mapping->a_ops = &f2fs_node_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
} else if (ino == F2FS_META_INO(sbi)) {
inode->i_mapping->a_ops = &f2fs_meta_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
} else if (S_ISREG(inode->i_mode)) {
inode->i_op = &f2fs_file_inode_operations;
inode->i_fop = &f2fs_file_operations;
@ -453,7 +460,7 @@ retry:
return inode;
}
void update_inode(struct inode *inode, struct page *node_page)
void f2fs_update_inode(struct inode *inode, struct page *node_page)
{
struct f2fs_inode *ri;
struct extent_tree *et = F2FS_I(inode)->extent_tree;
@ -488,7 +495,12 @@ void update_inode(struct inode *inode, struct page *node_page)
ri->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec);
ri->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
ri->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
ri->i_current_depth = cpu_to_le32(F2FS_I(inode)->i_current_depth);
if (S_ISDIR(inode->i_mode))
ri->i_current_depth =
cpu_to_le32(F2FS_I(inode)->i_current_depth);
else if (S_ISREG(inode->i_mode))
ri->i_gc_failures =
cpu_to_le16(F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN]);
ri->i_xattr_nid = cpu_to_le32(F2FS_I(inode)->i_xattr_nid);
ri->i_flags = cpu_to_le32(F2FS_I(inode)->i_flags);
ri->i_pino = cpu_to_le32(F2FS_I(inode)->i_pino);
@ -534,12 +546,12 @@ void update_inode(struct inode *inode, struct page *node_page)
F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime;
}
void update_inode_page(struct inode *inode)
void f2fs_update_inode_page(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *node_page;
retry:
node_page = get_node_page(sbi, inode->i_ino);
node_page = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(node_page)) {
int err = PTR_ERR(node_page);
if (err == -ENOMEM) {
@ -550,7 +562,7 @@ retry:
}
return;
}
update_inode(inode, node_page);
f2fs_update_inode(inode, node_page);
f2fs_put_page(node_page, 1);
}
@ -569,7 +581,7 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
* We need to balance fs here to prevent from producing dirty node pages
* during the urgent cleaning time when runing out of free sections.
*/
update_inode_page(inode);
f2fs_update_inode_page(inode);
if (wbc && wbc->nr_to_write)
f2fs_balance_fs(sbi, true);
return 0;
@ -586,7 +598,7 @@ void f2fs_evict_inode(struct inode *inode)
/* some remained atomic pages should discarded */
if (f2fs_is_atomic_file(inode))
drop_inmem_pages(inode);
f2fs_drop_inmem_pages(inode);
trace_f2fs_evict_inode(inode);
truncate_inode_pages_final(&inode->i_data);
@ -596,7 +608,7 @@ void f2fs_evict_inode(struct inode *inode)
goto out_clear;
f2fs_bug_on(sbi, get_dirty_pages(inode));
remove_dirty_inode(inode);
f2fs_remove_dirty_inode(inode);
f2fs_destroy_extent_tree(inode);
@ -605,9 +617,9 @@ void f2fs_evict_inode(struct inode *inode)
dquot_initialize(inode);
remove_ino_entry(sbi, inode->i_ino, APPEND_INO);
remove_ino_entry(sbi, inode->i_ino, UPDATE_INO);
remove_ino_entry(sbi, inode->i_ino, FLUSH_INO);
f2fs_remove_ino_entry(sbi, inode->i_ino, APPEND_INO);
f2fs_remove_ino_entry(sbi, inode->i_ino, UPDATE_INO);
f2fs_remove_ino_entry(sbi, inode->i_ino, FLUSH_INO);
sb_start_intwrite(inode->i_sb);
set_inode_flag(inode, FI_NO_ALLOC);
@ -624,7 +636,7 @@ retry:
#endif
if (!err) {
f2fs_lock_op(sbi);
err = remove_inode_page(inode);
err = f2fs_remove_inode_page(inode);
f2fs_unlock_op(sbi);
if (err == -ENOENT)
err = 0;
@ -637,7 +649,7 @@ retry:
}
if (err)
update_inode_page(inode);
f2fs_update_inode_page(inode);
dquot_free_inode(inode);
sb_end_intwrite(inode->i_sb);
no_delete:
@ -664,16 +676,19 @@ no_delete:
invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid);
if (inode->i_nlink) {
if (is_inode_flag_set(inode, FI_APPEND_WRITE))
add_ino_entry(sbi, inode->i_ino, APPEND_INO);
f2fs_add_ino_entry(sbi, inode->i_ino, APPEND_INO);
if (is_inode_flag_set(inode, FI_UPDATE_WRITE))
add_ino_entry(sbi, inode->i_ino, UPDATE_INO);
f2fs_add_ino_entry(sbi, inode->i_ino, UPDATE_INO);
}
if (is_inode_flag_set(inode, FI_FREE_NID)) {
alloc_nid_failed(sbi, inode->i_ino);
f2fs_alloc_nid_failed(sbi, inode->i_ino);
clear_inode_flag(inode, FI_FREE_NID);
} else {
f2fs_bug_on(sbi, err &&
!exist_written_data(sbi, inode->i_ino, ORPHAN_INO));
/*
* If xattr nid is corrupted, we can reach out error condition,
* err & !f2fs_exist_written_data(sbi, inode->i_ino, ORPHAN_INO)).
* In that case, f2fs_check_nid_range() is enough to give a clue.
*/
}
out_clear:
fscrypt_put_encryption_info(inode);
@ -681,7 +696,7 @@ out_clear:
}
/* caller should call f2fs_lock_op() */
void handle_failed_inode(struct inode *inode)
void f2fs_handle_failed_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct node_info ni;
@ -697,7 +712,7 @@ void handle_failed_inode(struct inode *inode)
* we must call this to avoid inode being remained as dirty, resulting
* in a panic when flushing dirty inodes in gdirty_list.
*/
update_inode_page(inode);
f2fs_update_inode_page(inode);
f2fs_inode_synced(inode);
/* don't make bad inode, since it becomes a regular file. */
@ -708,7 +723,7 @@ void handle_failed_inode(struct inode *inode)
* so we can prevent losing this orphan when encoutering checkpoint
* and following suddenly power-off.
*/
err = get_node_info(sbi, inode->i_ino, &ni);
err = f2fs_get_node_info(sbi, inode->i_ino, &ni);
if (err) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
@ -717,15 +732,15 @@ void handle_failed_inode(struct inode *inode)
}
if (ni.blk_addr != NULL_ADDR) {
err = acquire_orphan_inode(sbi);
err = f2fs_acquire_orphan_inode(sbi);
if (err) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"Too many orphan inodes, run fsck to fix.");
} else {
add_orphan_inode(inode);
f2fs_add_orphan_inode(inode);
}
alloc_nid_done(sbi, inode->i_ino);
f2fs_alloc_nid_done(sbi, inode->i_ino);
} else {
set_inode_flag(inode, FI_FREE_NID);
}

67
fs/f2fs/namei.c
View File

@ -37,7 +37,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
return ERR_PTR(-ENOMEM);
f2fs_lock_op(sbi);
if (!alloc_nid(sbi, &ino)) {
if (!f2fs_alloc_nid(sbi, &ino)) {
f2fs_unlock_op(sbi);
err = -ENOSPC;
goto fail;
@ -54,6 +54,9 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
F2FS_I(inode)->i_crtime = current_time(inode);
inode->i_generation = sbi->s_next_generation++;
if (S_ISDIR(inode->i_mode))
F2FS_I(inode)->i_current_depth = 1;
err = insert_inode_locked(inode);
if (err) {
err = -EINVAL;
@ -61,7 +64,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
}
if (f2fs_sb_has_project_quota(sbi->sb) &&
(F2FS_I(dir)->i_flags & FS_PROJINHERIT_FL))
(F2FS_I(dir)->i_flags & F2FS_PROJINHERIT_FL))
F2FS_I(inode)->i_projid = F2FS_I(dir)->i_projid;
else
F2FS_I(inode)->i_projid = make_kprojid(&init_user_ns,
@ -116,9 +119,9 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
f2fs_mask_flags(mode, F2FS_I(dir)->i_flags & F2FS_FL_INHERITED);
if (S_ISDIR(inode->i_mode))
F2FS_I(inode)->i_flags |= FS_INDEX_FL;
F2FS_I(inode)->i_flags |= F2FS_INDEX_FL;
if (F2FS_I(inode)->i_flags & FS_PROJINHERIT_FL)
if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL)
set_inode_flag(inode, FI_PROJ_INHERIT);
trace_f2fs_new_inode(inode, 0);
@ -193,7 +196,7 @@ static inline void set_file_temperature(struct f2fs_sb_info *sbi, struct inode *
up_read(&sbi->sb_lock);
}
int update_extension_list(struct f2fs_sb_info *sbi, const char *name,
int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name,
bool hot, bool set)
{
__u8 (*extlist)[F2FS_EXTENSION_LEN] = sbi->raw_super->extension_list;
@ -292,7 +295,7 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
goto out;
f2fs_unlock_op(sbi);
alloc_nid_done(sbi, ino);
f2fs_alloc_nid_done(sbi, ino);
d_instantiate_new(dentry, inode);
@ -302,7 +305,7 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
f2fs_balance_fs(sbi, true);
return 0;
out:
handle_failed_inode(inode);
f2fs_handle_failed_inode(inode);
return err;
}
@ -397,7 +400,7 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino)
err = PTR_ERR(page);
goto out;
} else {
err = __f2fs_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR);
err = f2fs_do_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR);
if (err)
goto out;
}
@ -408,7 +411,7 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino)
else if (IS_ERR(page))
err = PTR_ERR(page);
else
err = __f2fs_add_link(dir, &dotdot, NULL, pino, S_IFDIR);
err = f2fs_do_add_link(dir, &dotdot, NULL, pino, S_IFDIR);
out:
if (!err)
clear_inode_flag(dir, FI_INLINE_DOTS);
@ -520,7 +523,7 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
err = acquire_orphan_inode(sbi);
err = f2fs_acquire_orphan_inode(sbi);
if (err) {
f2fs_unlock_op(sbi);
f2fs_put_page(page, 0);
@ -585,9 +588,9 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
if (err)
goto out_handle_failed_inode;
goto out_f2fs_handle_failed_inode;
f2fs_unlock_op(sbi);
alloc_nid_done(sbi, inode->i_ino);
f2fs_alloc_nid_done(sbi, inode->i_ino);
err = fscrypt_encrypt_symlink(inode, symname, len, &disk_link);
if (err)
@ -620,8 +623,8 @@ err_out:
f2fs_balance_fs(sbi, true);
goto out_free_encrypted_link;
out_handle_failed_inode:
handle_failed_inode(inode);
out_f2fs_handle_failed_inode:
f2fs_handle_failed_inode(inode);
out_free_encrypted_link:
if (disk_link.name != (unsigned char *)symname)
kfree(disk_link.name);
@ -657,7 +660,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
goto out_fail;
f2fs_unlock_op(sbi);
alloc_nid_done(sbi, inode->i_ino);
f2fs_alloc_nid_done(sbi, inode->i_ino);
d_instantiate_new(dentry, inode);
@ -669,7 +672,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
out_fail:
clear_inode_flag(inode, FI_INC_LINK);
handle_failed_inode(inode);
f2fs_handle_failed_inode(inode);
return err;
}
@ -708,7 +711,7 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
goto out;
f2fs_unlock_op(sbi);
alloc_nid_done(sbi, inode->i_ino);
f2fs_alloc_nid_done(sbi, inode->i_ino);
d_instantiate_new(dentry, inode);
@ -718,7 +721,7 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
f2fs_balance_fs(sbi, true);
return 0;
out:
handle_failed_inode(inode);
f2fs_handle_failed_inode(inode);
return err;
}
@ -747,7 +750,7 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
}
f2fs_lock_op(sbi);
err = acquire_orphan_inode(sbi);
err = f2fs_acquire_orphan_inode(sbi);
if (err)
goto out;
@ -759,8 +762,8 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
* add this non-linked tmpfile to orphan list, in this way we could
* remove all unused data of tmpfile after abnormal power-off.
*/
add_orphan_inode(inode);
alloc_nid_done(sbi, inode->i_ino);
f2fs_add_orphan_inode(inode);
f2fs_alloc_nid_done(sbi, inode->i_ino);
if (whiteout) {
f2fs_i_links_write(inode, false);
@ -776,9 +779,9 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
return 0;
release_out:
release_orphan_inode(sbi);
f2fs_release_orphan_inode(sbi);
out:
handle_failed_inode(inode);
f2fs_handle_failed_inode(inode);
return err;
}
@ -885,7 +888,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
f2fs_lock_op(sbi);
err = acquire_orphan_inode(sbi);
err = f2fs_acquire_orphan_inode(sbi);
if (err)
goto put_out_dir;
@ -899,9 +902,9 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
up_write(&F2FS_I(new_inode)->i_sem);
if (!new_inode->i_nlink)
add_orphan_inode(new_inode);
f2fs_add_orphan_inode(new_inode);
else
release_orphan_inode(sbi);
f2fs_release_orphan_inode(sbi);
} else {
f2fs_balance_fs(sbi, true);
@ -969,8 +972,12 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
f2fs_put_page(old_dir_page, 0);
f2fs_i_links_write(old_dir, false);
}
if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT)
add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO);
if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) {
f2fs_add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO);
if (S_ISDIR(old_inode->i_mode))
f2fs_add_ino_entry(sbi, old_inode->i_ino,
TRANS_DIR_INO);
}
f2fs_unlock_op(sbi);
@ -1121,8 +1128,8 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
f2fs_mark_inode_dirty_sync(new_dir, false);
if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) {
add_ino_entry(sbi, old_dir->i_ino, TRANS_DIR_INO);
add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO);
f2fs_add_ino_entry(sbi, old_dir->i_ino, TRANS_DIR_INO);
f2fs_add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO);
}
f2fs_unlock_op(sbi);

340
fs/f2fs/node.c
View File

@ -23,13 +23,28 @@
#include "trace.h"
#include <trace/events/f2fs.h>
#define on_build_free_nids(nmi) mutex_is_locked(&(nm_i)->build_lock)
#define on_f2fs_build_free_nids(nmi) mutex_is_locked(&(nm_i)->build_lock)
static struct kmem_cache *nat_entry_slab;
static struct kmem_cache *free_nid_slab;
static struct kmem_cache *nat_entry_set_slab;
bool available_free_memory(struct f2fs_sb_info *sbi, int type)
/*
* Check whether the given nid is within node id range.
*/
int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
{
if (unlikely(nid < F2FS_ROOT_INO(sbi) || nid >= NM_I(sbi)->max_nid)) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"%s: out-of-range nid=%x, run fsck to fix.",
__func__, nid);
return -EINVAL;
}
return 0;
}
bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct sysinfo val;
@ -87,18 +102,10 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
static void clear_node_page_dirty(struct page *page)
{
struct address_space *mapping = page->mapping;
unsigned int long flags;
if (PageDirty(page)) {
spin_lock_irqsave(&mapping->tree_lock, flags);
radix_tree_tag_clear(&mapping->page_tree,
page_index(page),
PAGECACHE_TAG_DIRTY);
spin_unlock_irqrestore(&mapping->tree_lock, flags);
f2fs_clear_radix_tree_dirty_tag(page);
clear_page_dirty_for_io(page);
dec_page_count(F2FS_M_SB(mapping), F2FS_DIRTY_NODES);
dec_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES);
}
ClearPageUptodate(page);
}
@ -123,10 +130,10 @@ static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
dst_off = next_nat_addr(sbi, src_off);
/* get current nat block page with lock */
src_page = get_meta_page(sbi, src_off);
src_page = f2fs_get_meta_page(sbi, src_off);
if (IS_ERR(src_page))
return src_page;
dst_page = grab_meta_page(sbi, dst_off);
dst_page = f2fs_grab_meta_page(sbi, dst_off);
f2fs_bug_on(sbi, PageDirty(src_page));
src_addr = page_address(src_page);
@ -262,7 +269,7 @@ static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i,
start, nr);
}
int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid)
int f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
@ -279,7 +286,7 @@ int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid)
return need;
}
bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid)
bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
@ -293,7 +300,7 @@ bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid)
return is_cp;
}
bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino)
bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
@ -392,7 +399,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
up_write(&nm_i->nat_tree_lock);
}
int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
int nr = nr_shrink;
@ -414,7 +421,8 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
/*
* This function always returns success
*/
int get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
struct node_info *ni)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
@ -444,7 +452,7 @@ int get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
/* Check current segment summary */
down_read(&curseg->journal_rwsem);
i = lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0);
i = f2fs_lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0);
if (i >= 0) {
ne = nat_in_journal(journal, i);
node_info_from_raw_nat(ni, &ne);
@ -459,7 +467,7 @@ int get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
index = current_nat_addr(sbi, nid);
up_read(&nm_i->nat_tree_lock);
page = get_meta_page(sbi, index);
page = f2fs_get_meta_page(sbi, index);
if (IS_ERR(page))
return PTR_ERR(page);
@ -476,7 +484,7 @@ cache:
/*
* readahead MAX_RA_NODE number of node pages.
*/
static void ra_node_pages(struct page *parent, int start, int n)
static void f2fs_ra_node_pages(struct page *parent, int start, int n)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
struct blk_plug plug;
@ -490,13 +498,13 @@ static void ra_node_pages(struct page *parent, int start, int n)
end = min(end, NIDS_PER_BLOCK);
for (i = start; i < end; i++) {
nid = get_nid(parent, i, false);
ra_node_page(sbi, nid);
f2fs_ra_node_page(sbi, nid);
}
blk_finish_plug(&plug);
}
pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs)
pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs)
{
const long direct_index = ADDRS_PER_INODE(dn->inode);
const long direct_blks = ADDRS_PER_BLOCK;
@ -611,7 +619,7 @@ got:
* f2fs_unlock_op() only if ro is not set RDONLY_NODE.
* In the case of RDONLY_NODE, we don't need to care about mutex.
*/
int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct page *npage[4];
@ -630,7 +638,7 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
npage[0] = dn->inode_page;
if (!npage[0]) {
npage[0] = get_node_page(sbi, nids[0]);
npage[0] = f2fs_get_node_page(sbi, nids[0]);
if (IS_ERR(npage[0]))
return PTR_ERR(npage[0]);
}
@ -654,24 +662,24 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
if (!nids[i] && mode == ALLOC_NODE) {
/* alloc new node */
if (!alloc_nid(sbi, &(nids[i]))) {
if (!f2fs_alloc_nid(sbi, &(nids[i]))) {
err = -ENOSPC;
goto release_pages;
}
dn->nid = nids[i];
npage[i] = new_node_page(dn, noffset[i]);
npage[i] = f2fs_new_node_page(dn, noffset[i]);
if (IS_ERR(npage[i])) {
alloc_nid_failed(sbi, nids[i]);
f2fs_alloc_nid_failed(sbi, nids[i]);
err = PTR_ERR(npage[i]);
goto release_pages;
}
set_nid(parent, offset[i - 1], nids[i], i == 1);
alloc_nid_done(sbi, nids[i]);
f2fs_alloc_nid_done(sbi, nids[i]);
done = true;
} else if (mode == LOOKUP_NODE_RA && i == level && level > 1) {
npage[i] = get_node_page_ra(parent, offset[i - 1]);
npage[i] = f2fs_get_node_page_ra(parent, offset[i - 1]);
if (IS_ERR(npage[i])) {
err = PTR_ERR(npage[i]);
goto release_pages;
@ -686,7 +694,7 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
}
if (!done) {
npage[i] = get_node_page(sbi, nids[i]);
npage[i] = f2fs_get_node_page(sbi, nids[i]);
if (IS_ERR(npage[i])) {
err = PTR_ERR(npage[i]);
f2fs_put_page(npage[0], 0);
@ -727,17 +735,17 @@ static int truncate_node(struct dnode_of_data *dn)
int err;
pgoff_t index;
err = get_node_info(sbi, dn->nid, &ni);
err = f2fs_get_node_info(sbi, dn->nid, &ni);
if (err)
return err;
/* Deallocate node address */
invalidate_blocks(sbi, ni.blk_addr);
f2fs_invalidate_blocks(sbi, ni.blk_addr);
dec_valid_node_count(sbi, dn->inode, dn->nid == dn->inode->i_ino);
set_node_addr(sbi, &ni, NULL_ADDR, false);
if (dn->nid == dn->inode->i_ino) {
remove_orphan_inode(sbi, dn->nid);
f2fs_remove_orphan_inode(sbi, dn->nid);
dec_valid_inode_count(sbi);
f2fs_inode_synced(dn->inode);
}
@ -765,7 +773,7 @@ static int truncate_dnode(struct dnode_of_data *dn)
return 1;
/* get direct node */
page = get_node_page(F2FS_I_SB(dn->inode), dn->nid);
page = f2fs_get_node_page(F2FS_I_SB(dn->inode), dn->nid);
if (IS_ERR(page) && PTR_ERR(page) == -ENOENT)
return 1;
else if (IS_ERR(page))
@ -774,7 +782,7 @@ static int truncate_dnode(struct dnode_of_data *dn)
/* Make dnode_of_data for parameter */
dn->node_page = page;
dn->ofs_in_node = 0;
truncate_data_blocks(dn);
f2fs_truncate_data_blocks(dn);
err = truncate_node(dn);
if (err)
return err;
@ -797,13 +805,13 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs,
trace_f2fs_truncate_nodes_enter(dn->inode, dn->nid, dn->data_blkaddr);
page = get_node_page(F2FS_I_SB(dn->inode), dn->nid);
page = f2fs_get_node_page(F2FS_I_SB(dn->inode), dn->nid);
if (IS_ERR(page)) {
trace_f2fs_truncate_nodes_exit(dn->inode, PTR_ERR(page));
return PTR_ERR(page);
}
ra_node_pages(page, ofs, NIDS_PER_BLOCK);
f2fs_ra_node_pages(page, ofs, NIDS_PER_BLOCK);
rn = F2FS_NODE(page);
if (depth < 3) {
@ -875,7 +883,7 @@ static int truncate_partial_nodes(struct dnode_of_data *dn,
/* get indirect nodes in the path */
for (i = 0; i < idx + 1; i++) {
/* reference count'll be increased */
pages[i] = get_node_page(F2FS_I_SB(dn->inode), nid[i]);
pages[i] = f2fs_get_node_page(F2FS_I_SB(dn->inode), nid[i]);
if (IS_ERR(pages[i])) {
err = PTR_ERR(pages[i]);
idx = i - 1;
@ -884,7 +892,7 @@ static int truncate_partial_nodes(struct dnode_of_data *dn,
nid[i + 1] = get_nid(pages[i], offset[i + 1], false);
}
ra_node_pages(pages[idx], offset[idx + 1], NIDS_PER_BLOCK);
f2fs_ra_node_pages(pages[idx], offset[idx + 1], NIDS_PER_BLOCK);
/* free direct nodes linked to a partial indirect node */
for (i = offset[idx + 1]; i < NIDS_PER_BLOCK; i++) {
@ -923,7 +931,7 @@ fail:
/*
* All the block addresses of data and nodes should be nullified.
*/
int truncate_inode_blocks(struct inode *inode, pgoff_t from)
int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int err = 0, cont = 1;
@ -939,7 +947,7 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from)
if (level < 0)
return level;
page = get_node_page(sbi, inode->i_ino);
page = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(page)) {
trace_f2fs_truncate_inode_blocks_exit(inode, PTR_ERR(page));
return PTR_ERR(page);
@ -1019,7 +1027,7 @@ fail:
}
/* caller must lock inode page */
int truncate_xattr_node(struct inode *inode)
int f2fs_truncate_xattr_node(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t nid = F2FS_I(inode)->i_xattr_nid;
@ -1030,7 +1038,7 @@ int truncate_xattr_node(struct inode *inode)
if (!nid)
return 0;
npage = get_node_page(sbi, nid);
npage = f2fs_get_node_page(sbi, nid);
if (IS_ERR(npage))
return PTR_ERR(npage);
@ -1050,17 +1058,17 @@ int truncate_xattr_node(struct inode *inode)
* Caller should grab and release a rwsem by calling f2fs_lock_op() and
* f2fs_unlock_op().
*/
int remove_inode_page(struct inode *inode)
int f2fs_remove_inode_page(struct inode *inode)
{
struct dnode_of_data dn;
int err;
set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino);
err = get_dnode_of_data(&dn, 0, LOOKUP_NODE);
err = f2fs_get_dnode_of_data(&dn, 0, LOOKUP_NODE);
if (err)
return err;
err = truncate_xattr_node(inode);
err = f2fs_truncate_xattr_node(inode);
if (err) {
f2fs_put_dnode(&dn);
return err;
@ -1069,7 +1077,7 @@ int remove_inode_page(struct inode *inode)
/* remove potential inline_data blocks */
if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode))
truncate_data_blocks_range(&dn, 1);
f2fs_truncate_data_blocks_range(&dn, 1);
/* 0 is possible, after f2fs_new_inode() has failed */
f2fs_bug_on(F2FS_I_SB(inode),
@ -1084,7 +1092,7 @@ int remove_inode_page(struct inode *inode)
return 0;
}
struct page *new_inode_page(struct inode *inode)
struct page *f2fs_new_inode_page(struct inode *inode)
{
struct dnode_of_data dn;
@ -1092,10 +1100,10 @@ struct page *new_inode_page(struct inode *inode)
set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino);
/* caller should f2fs_put_page(page, 1); */
return new_node_page(&dn, 0);
return f2fs_new_node_page(&dn, 0);
}
struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs)
struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct node_info new_ni;
@ -1113,7 +1121,7 @@ struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs)
goto fail;
#ifdef CONFIG_F2FS_CHECK_FS
err = get_node_info(sbi, dn->nid, &new_ni);
err = f2fs_get_node_info(sbi, dn->nid, &new_ni);
if (err) {
dec_valid_node_count(sbi, dn->inode, !ofs);
goto fail;
@ -1170,7 +1178,7 @@ static int read_node_page(struct page *page, int op_flags)
if (PageUptodate(page))
return LOCKED_PAGE;
err = get_node_info(sbi, page->index, &ni);
err = f2fs_get_node_info(sbi, page->index, &ni);
if (err)
return err;
@ -1186,14 +1194,15 @@ static int read_node_page(struct page *page, int op_flags)
/*
* Readahead a node page
*/
void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
{
struct page *apage;
int err;
if (!nid)
return;
f2fs_bug_on(sbi, check_nid_range(sbi, nid));
if (f2fs_check_nid_range(sbi, nid))
return;
rcu_read_lock();
apage = radix_tree_lookup(&NODE_MAPPING(sbi)->page_tree, nid);
@ -1217,7 +1226,8 @@ static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
if (!nid)
return ERR_PTR(-ENOENT);
f2fs_bug_on(sbi, check_nid_range(sbi, nid));
if (f2fs_check_nid_range(sbi, nid))
return ERR_PTR(-EINVAL);
repeat:
page = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false);
if (!page)
@ -1233,7 +1243,7 @@ repeat:
}
if (parent)
ra_node_pages(parent, start + 1, MAX_RA_NODE);
f2fs_ra_node_pages(parent, start + 1, MAX_RA_NODE);
lock_page(page);
@ -1267,12 +1277,12 @@ out_err:
return page;
}
struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
{
return __get_node_page(sbi, nid, NULL, 0);
}
struct page *get_node_page_ra(struct page *parent, int start)
struct page *f2fs_get_node_page_ra(struct page *parent, int start)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
nid_t nid = get_nid(parent, start, false);
@ -1307,7 +1317,7 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
ret = f2fs_write_inline_data(inode, page);
inode_dec_dirty_pages(inode);
remove_dirty_inode(inode);
f2fs_remove_dirty_inode(inode);
if (ret)
set_page_dirty(page);
page_out:
@ -1318,21 +1328,17 @@ iput_out:
static struct page *last_fsync_dnode(struct f2fs_sb_info *sbi, nid_t ino)
{
pgoff_t index, end;
pgoff_t index;
struct pagevec pvec;
struct page *last_page = NULL;
int nr_pages;
pagevec_init(&pvec, 0);
index = 0;
end = ULONG_MAX;
while (index <= end) {
int i, nr_pages;
nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
PAGECACHE_TAG_DIRTY,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
break;
while ((nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
PAGECACHE_TAG_DIRTY))) {
int i;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
@ -1398,11 +1404,8 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
trace_f2fs_writepage(page, NODE);
if (unlikely(f2fs_cp_error(sbi))) {
dec_page_count(sbi, F2FS_DIRTY_NODES);
unlock_page(page);
return 0;
}
if (unlikely(f2fs_cp_error(sbi)))
goto redirty_out;
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
@ -1411,7 +1414,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
nid = nid_of_node(page);
f2fs_bug_on(sbi, page->index != nid);
if (get_node_info(sbi, nid, &ni))
if (f2fs_get_node_info(sbi, nid, &ni))
goto redirty_out;
if (wbc->for_reclaim) {
@ -1442,7 +1445,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
set_page_writeback(page);
ClearPageError(page);
fio.old_blkaddr = ni.blk_addr;
write_node_page(nid, &fio);
f2fs_do_write_node_page(nid, &fio);
set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page));
dec_page_count(sbi, F2FS_DIRTY_NODES);
up_read(&sbi->node_write);
@ -1471,7 +1474,7 @@ redirty_out:
return AOP_WRITEPAGE_ACTIVATE;
}
int move_node_page(struct page *node_page, int gc_type)
int f2fs_move_node_page(struct page *node_page, int gc_type)
{
int err = 0;
@ -1515,16 +1518,17 @@ static int f2fs_write_node_page(struct page *page,
return __write_node_page(page, false, NULL, wbc, false, FS_NODE_IO);
}
int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
struct writeback_control *wbc, bool atomic)
{
pgoff_t index, end;
pgoff_t index;
pgoff_t last_idx = ULONG_MAX;
struct pagevec pvec;
int ret = 0;
struct page *last_page = NULL;
bool marked = false;
nid_t ino = inode->i_ino;
int nr_pages;
if (atomic) {
last_page = last_fsync_dnode(sbi, ino);
@ -1534,15 +1538,10 @@ int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
retry:
pagevec_init(&pvec, 0);
index = 0;
end = ULONG_MAX;
while (index <= end) {
int i, nr_pages;
nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
PAGECACHE_TAG_DIRTY,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
break;
while ((nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
PAGECACHE_TAG_DIRTY))) {
int i;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
@ -1586,9 +1585,9 @@ continue_unlock:
if (IS_INODE(page)) {
if (is_inode_flag_set(inode,
FI_DIRTY_INODE))
update_inode(inode, page);
f2fs_update_inode(inode, page);
set_dentry_mark(page,
need_dentry_mark(sbi, ino));
f2fs_need_dentry_mark(sbi, ino));
}
/* may be written by other thread */
if (!PageDirty(page))
@ -1638,33 +1637,37 @@ out:
return ret ? -EIO: 0;
}
int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc,
int f2fs_sync_node_pages(struct f2fs_sb_info *sbi,
struct writeback_control *wbc,
bool do_balance, enum iostat_type io_type)
{
pgoff_t index, end;
pgoff_t index;
struct pagevec pvec;
int step = 0;
int nwritten = 0;
int ret = 0;
int nr_pages, done = 0;
pagevec_init(&pvec, 0);
next_step:
index = 0;
end = ULONG_MAX;
while (index <= end) {
int i, nr_pages;
nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
PAGECACHE_TAG_DIRTY,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
break;
while (!done && (nr_pages = pagevec_lookup_tag(&pvec,
NODE_MAPPING(sbi), &index, PAGECACHE_TAG_DIRTY))) {
int i;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
bool submitted = false;
/* give a priority to WB_SYNC threads */
if (atomic_read(&sbi->wb_sync_req[NODE]) &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
/*
* flushing sequence with step:
* 0. indirect nodes
@ -1745,29 +1748,22 @@ continue_unlock:
return ret;
}
int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino)
int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino)
{
pgoff_t index = 0, end = ULONG_MAX;
pgoff_t index = 0;
struct pagevec pvec;
int ret2, ret = 0;
int nr_pages;
pagevec_init(&pvec, 0);
while (index <= end) {
int i, nr_pages;
nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
PAGECACHE_TAG_WRITEBACK,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
break;
while ((nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
PAGECACHE_TAG_WRITEBACK))) {
int i;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/* until radix tree lookup accepts end_index */
if (unlikely(page->index > end))
continue;
if (ino && ino_of_node(page) == ino) {
f2fs_wait_on_page_writeback(page, NODE, true);
if (TestClearPageError(page))
@ -1801,14 +1797,21 @@ static int f2fs_write_node_pages(struct address_space *mapping,
if (get_pages(sbi, F2FS_DIRTY_NODES) < nr_pages_to_skip(sbi, NODE))
goto skip_write;
if (wbc->sync_mode == WB_SYNC_ALL)
atomic_inc(&sbi->wb_sync_req[NODE]);
else if (atomic_read(&sbi->wb_sync_req[NODE]))
goto skip_write;
trace_f2fs_writepages(mapping->host, wbc, NODE);
diff = nr_pages_to_write(sbi, NODE, wbc);
wbc->sync_mode = WB_SYNC_NONE;
blk_start_plug(&plug);
sync_node_pages(sbi, wbc, true, FS_NODE_IO);
f2fs_sync_node_pages(sbi, wbc, true, FS_NODE_IO);
blk_finish_plug(&plug);
wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff);
if (wbc->sync_mode == WB_SYNC_ALL)
atomic_dec(&sbi->wb_sync_req[NODE]);
return 0;
skip_write:
@ -1954,20 +1957,20 @@ static bool add_free_nid(struct f2fs_sb_info *sbi,
* Thread A Thread B
* - f2fs_create
* - f2fs_new_inode
* - alloc_nid
* - f2fs_alloc_nid
* - __insert_nid_to_list(PREALLOC_NID)
* - f2fs_balance_fs_bg
* - build_free_nids
* - __build_free_nids
* - f2fs_build_free_nids
* - __f2fs_build_free_nids
* - scan_nat_page
* - add_free_nid
* - __lookup_nat_cache
* - f2fs_add_link
* - init_inode_metadata
* - new_inode_page
* - new_node_page
* - f2fs_init_inode_metadata
* - f2fs_new_inode_page
* - f2fs_new_node_page
* - set_node_addr
* - alloc_nid_done
* - f2fs_alloc_nid_done
* - __remove_nid_from_list(PREALLOC_NID)
* - __insert_nid_to_list(FREE_NID)
*/
@ -2102,7 +2105,8 @@ out:
up_read(&nm_i->nat_tree_lock);
}
static int __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi,
bool sync, bool mount)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
int i = 0, ret;
@ -2115,7 +2119,7 @@ static int __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK)
return 0;
if (!sync && !available_free_memory(sbi, FREE_NIDS))
if (!sync && !f2fs_available_free_memory(sbi, FREE_NIDS))
return 0;
if (!mount) {
@ -2127,7 +2131,7 @@ static int __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
}
/* readahead nat pages to be scanned */
ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES,
f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES,
META_NAT, true);
down_read(&nm_i->nat_tree_lock);
@ -2169,16 +2173,16 @@ static int __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
up_read(&nm_i->nat_tree_lock);
ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
nm_i->ra_nid_pages, META_NAT, false);
return 0;
}
int build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
int f2fs_build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
{
int ret;
mutex_lock(&NM_I(sbi)->build_lock);
ret = __build_free_nids(sbi, sync, mount);
ret = __f2fs_build_free_nids(sbi, sync, mount);
mutex_unlock(&NM_I(sbi)->build_lock);
return ret;
}
@ -2188,7 +2192,7 @@ int build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
* from second parameter of this function.
* The returned nid could be used ino as well as nid when inode is created.
*/
bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid)
bool f2fs_alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i = NULL;
@ -2206,8 +2210,8 @@ retry:
return false;
}
/* We should not use stale free nids created by build_free_nids */
if (nm_i->nid_cnt[FREE_NID] && !on_build_free_nids(nm_i)) {
/* We should not use stale free nids created by f2fs_build_free_nids */
if (nm_i->nid_cnt[FREE_NID] && !on_f2fs_build_free_nids(nm_i)) {
f2fs_bug_on(sbi, list_empty(&nm_i->free_nid_list));
i = list_first_entry(&nm_i->free_nid_list,
struct free_nid, list);
@ -2224,14 +2228,14 @@ retry:
spin_unlock(&nm_i->nid_list_lock);
/* Let's scan nat pages and its caches to get free nids */
build_free_nids(sbi, true, false);
f2fs_build_free_nids(sbi, true, false);
goto retry;
}
/*
* alloc_nid() should be called prior to this function.
* f2fs_alloc_nid() should be called prior to this function.
*/
void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid)
void f2fs_alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i;
@ -2246,9 +2250,9 @@ void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid)
}
/*
* alloc_nid() should be called prior to this function.
* f2fs_alloc_nid() should be called prior to this function.
*/
void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i;
@ -2261,7 +2265,7 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
i = __lookup_free_nid_list(nm_i, nid);
f2fs_bug_on(sbi, !i);
if (!available_free_memory(sbi, FREE_NIDS)) {
if (!f2fs_available_free_memory(sbi, FREE_NIDS)) {
__remove_free_nid(sbi, i, PREALLOC_NID);
need_free = true;
} else {
@ -2278,7 +2282,7 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
kmem_cache_free(free_nid_slab, i);
}
int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink)
int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i, *next;
@ -2306,14 +2310,14 @@ int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink)
return nr - nr_shrink;
}
void recover_inline_xattr(struct inode *inode, struct page *page)
void f2fs_recover_inline_xattr(struct inode *inode, struct page *page)
{
void *src_addr, *dst_addr;
size_t inline_size;
struct page *ipage;
struct f2fs_inode *ri;
ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
f2fs_bug_on(F2FS_I_SB(inode), IS_ERR(ipage));
ri = F2FS_INODE(page);
@ -2331,11 +2335,11 @@ void recover_inline_xattr(struct inode *inode, struct page *page)
f2fs_wait_on_page_writeback(ipage, NODE, true);
memcpy(dst_addr, src_addr, inline_size);
update_inode:
update_inode(inode, ipage);
f2fs_update_inode(inode, ipage);
f2fs_put_page(ipage, 1);
}
int recover_xattr_data(struct inode *inode, struct page *page)
int f2fs_recover_xattr_data(struct inode *inode, struct page *page)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t prev_xnid = F2FS_I(inode)->i_xattr_nid;
@ -2349,27 +2353,27 @@ int recover_xattr_data(struct inode *inode, struct page *page)
goto recover_xnid;
/* 1: invalidate the previous xattr nid */
err = get_node_info(sbi, prev_xnid, &ni);
err = f2fs_get_node_info(sbi, prev_xnid, &ni);
if (err)
return err;
invalidate_blocks(sbi, ni.blk_addr);
f2fs_invalidate_blocks(sbi, ni.blk_addr);
dec_valid_node_count(sbi, inode, false);
set_node_addr(sbi, &ni, NULL_ADDR, false);
recover_xnid:
/* 2: update xattr nid in inode */
if (!alloc_nid(sbi, &new_xnid))
if (!f2fs_alloc_nid(sbi, &new_xnid))
return -ENOSPC;
set_new_dnode(&dn, inode, NULL, NULL, new_xnid);
xpage = new_node_page(&dn, XATTR_NODE_OFFSET);
xpage = f2fs_new_node_page(&dn, XATTR_NODE_OFFSET);
if (IS_ERR(xpage)) {
alloc_nid_failed(sbi, new_xnid);
f2fs_alloc_nid_failed(sbi, new_xnid);
return PTR_ERR(xpage);
}
alloc_nid_done(sbi, new_xnid);
update_inode_page(inode);
f2fs_alloc_nid_done(sbi, new_xnid);
f2fs_update_inode_page(inode);
/* 3: update and set xattr node page dirty */
memcpy(F2FS_NODE(xpage), F2FS_NODE(page), VALID_XATTR_BLOCK_SIZE);
@ -2380,7 +2384,7 @@ recover_xnid:
return 0;
}
int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
{
struct f2fs_inode *src, *dst;
nid_t ino = ino_of_node(page);
@ -2388,7 +2392,7 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
struct page *ipage;
int err;
err = get_node_info(sbi, ino, &old_ni);
err = f2fs_get_node_info(sbi, ino, &old_ni);
if (err)
return err;
@ -2444,7 +2448,7 @@ retry:
return 0;
}
int restore_node_summary(struct f2fs_sb_info *sbi,
int f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
unsigned int segno, struct f2fs_summary_block *sum)
{
struct f2fs_node *rn;
@ -2461,10 +2465,10 @@ int restore_node_summary(struct f2fs_sb_info *sbi,
nrpages = min(last_offset - i, BIO_MAX_PAGES);
/* readahead node pages */
ra_meta_pages(sbi, addr, nrpages, META_POR, true);
f2fs_ra_meta_pages(sbi, addr, nrpages, META_POR, true);
for (idx = addr; idx < addr + nrpages; idx++) {
struct page *page = get_tmp_page(sbi, idx);
struct page *page = f2fs_get_tmp_page(sbi, idx);
if (IS_ERR(page))
return PTR_ERR(page);
@ -2612,7 +2616,7 @@ static int __flush_nat_entry_set(struct f2fs_sb_info *sbi,
f2fs_bug_on(sbi, nat_get_blkaddr(ne) == NEW_ADDR);
if (to_journal) {
offset = lookup_journal_in_cursum(journal,
offset = f2fs_lookup_journal_in_cursum(journal,
NAT_JOURNAL, nid, 1);
f2fs_bug_on(sbi, offset < 0);
raw_ne = &nat_in_journal(journal, offset);
@ -2650,7 +2654,7 @@ static int __flush_nat_entry_set(struct f2fs_sb_info *sbi,
/*
* This function is called during the checkpointing process.
*/
int flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
@ -2721,7 +2725,7 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
for (i = 0; i < nm_i->nat_bits_blocks; i++) {
struct page *page;
page = get_meta_page(sbi, nat_bits_addr++);
page = f2fs_get_meta_page(sbi, nat_bits_addr++);
if (IS_ERR(page))
return PTR_ERR(page);
@ -2842,8 +2846,10 @@ static int init_free_nid_cache(struct f2fs_sb_info *sbi)
struct f2fs_nm_info *nm_i = NM_I(sbi);
int i;
nm_i->free_nid_bitmap = f2fs_kzalloc(sbi, nm_i->nat_blocks *
sizeof(unsigned char *), GFP_KERNEL);
nm_i->free_nid_bitmap =
f2fs_kzalloc(sbi, array_size(sizeof(unsigned char *),
nm_i->nat_blocks),
GFP_KERNEL);
if (!nm_i->free_nid_bitmap)
return -ENOMEM;
@ -2859,14 +2865,16 @@ static int init_free_nid_cache(struct f2fs_sb_info *sbi)
if (!nm_i->nat_block_bitmap)
return -ENOMEM;
nm_i->free_nid_count = f2fs_kvzalloc(sbi, nm_i->nat_blocks *
sizeof(unsigned short), GFP_KERNEL);
nm_i->free_nid_count =
f2fs_kvzalloc(sbi, array_size(sizeof(unsigned short),
nm_i->nat_blocks),
GFP_KERNEL);
if (!nm_i->free_nid_count)
return -ENOMEM;
return 0;
}
int build_node_manager(struct f2fs_sb_info *sbi)
int f2fs_build_node_manager(struct f2fs_sb_info *sbi)
{
int err;
@ -2886,10 +2894,10 @@ int build_node_manager(struct f2fs_sb_info *sbi)
/* load free nid status from nat_bits table */
load_free_nid_bitmap(sbi);
return build_free_nids(sbi, true, true);
return f2fs_build_free_nids(sbi, true, true);
}
void destroy_node_manager(struct f2fs_sb_info *sbi)
void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i, *next_i;
@ -2961,7 +2969,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
kfree(nm_i);
}
int __init create_node_manager_caches(void)
int __init f2fs_create_node_manager_caches(void)
{
nat_entry_slab = f2fs_kmem_cache_create("nat_entry",
sizeof(struct nat_entry));
@ -2987,7 +2995,7 @@ fail:
return -ENOMEM;
}
void destroy_node_manager_caches(void)
void f2fs_destroy_node_manager_caches(void)
{
kmem_cache_destroy(nat_entry_set_slab);
kmem_cache_destroy(free_nid_slab);

59
fs/f2fs/recovery.c
View File

@ -47,7 +47,7 @@
static struct kmem_cache *fsync_entry_slab;
bool space_for_roll_forward(struct f2fs_sb_info *sbi)
bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi)
{
s64 nalloc = percpu_counter_sum_positive(&sbi->alloc_valid_block_count);
@ -162,7 +162,7 @@ retry:
goto out_put;
}
err = acquire_orphan_inode(F2FS_I_SB(inode));
err = f2fs_acquire_orphan_inode(F2FS_I_SB(inode));
if (err) {
iput(einode);
goto out_put;
@ -173,7 +173,7 @@ retry:
} else if (IS_ERR(page)) {
err = PTR_ERR(page);
} else {
err = __f2fs_do_add_link(dir, &fname, inode,
err = f2fs_add_dentry(dir, &fname, inode,
inode->i_ino, inode->i_mode);
}
if (err == -ENOMEM)
@ -204,8 +204,6 @@ static void recover_inline_flags(struct inode *inode, struct f2fs_inode *ri)
set_inode_flag(inode, FI_DATA_EXIST);
else
clear_inode_flag(inode, FI_DATA_EXIST);
if (!(ri->i_inline & F2FS_INLINE_DOTS))
clear_inode_flag(inode, FI_INLINE_DOTS);
}
static void recover_inode(struct inode *inode, struct page *page)
@ -258,7 +256,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head,
if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
return 0;
page = get_tmp_page(sbi, blkaddr);
page = f2fs_get_tmp_page(sbi, blkaddr);
if (IS_ERR(page)) {
err = PTR_ERR(page);
break;
@ -276,7 +274,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head,
if (!check_only &&
IS_INODE(page) && is_dent_dnode(page)) {
err = recover_inode_page(sbi, page);
err = f2fs_recover_inode_page(sbi, page);
if (err)
break;
quota_inode = true;
@ -317,7 +315,7 @@ next:
blkaddr = next_blkaddr_of_node(page);
f2fs_put_page(page, 1);
ra_meta_pages_cond(sbi, blkaddr);
f2fs_ra_meta_pages_cond(sbi, blkaddr);
}
f2fs_put_page(page, 1);
return err;
@ -360,7 +358,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
}
}
sum_page = get_sum_page(sbi, segno);
sum_page = f2fs_get_sum_page(sbi, segno);
if (IS_ERR(sum_page))
return PTR_ERR(sum_page);
sum_node = (struct f2fs_summary_block *)page_address(sum_page);
@ -382,7 +380,7 @@ got_it:
}
/* Get the node page */
node_page = get_node_page(sbi, nid);
node_page = f2fs_get_node_page(sbi, nid);
if (IS_ERR(node_page))
return PTR_ERR(node_page);
@ -407,7 +405,8 @@ got_it:
inode = dn->inode;
}
bidx = start_bidx_of_node(offset, inode) + le16_to_cpu(sum.ofs_in_node);
bidx = f2fs_start_bidx_of_node(offset, inode) +
le16_to_cpu(sum.ofs_in_node);
/*
* if inode page is locked, unlock temporarily, but its reference
@ -417,11 +416,11 @@ got_it:
unlock_page(dn->inode_page);
set_new_dnode(&tdn, inode, NULL, NULL, 0);
if (get_dnode_of_data(&tdn, bidx, LOOKUP_NODE))
if (f2fs_get_dnode_of_data(&tdn, bidx, LOOKUP_NODE))
goto out;
if (tdn.data_blkaddr == blkaddr)
truncate_data_blocks_range(&tdn, 1);
f2fs_truncate_data_blocks_range(&tdn, 1);
f2fs_put_dnode(&tdn);
out:
@ -434,7 +433,7 @@ out:
truncate_out:
if (datablock_addr(tdn.inode, tdn.node_page,
tdn.ofs_in_node) == blkaddr)
truncate_data_blocks_range(&tdn, 1);
f2fs_truncate_data_blocks_range(&tdn, 1);
if (dn->inode->i_ino == nid && !dn->inode_page_locked)
unlock_page(dn->inode_page);
return 0;
@ -450,25 +449,25 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
/* step 1: recover xattr */
if (IS_INODE(page)) {
recover_inline_xattr(inode, page);
f2fs_recover_inline_xattr(inode, page);
} else if (f2fs_has_xattr_block(ofs_of_node(page))) {
err = recover_xattr_data(inode, page);
err = f2fs_recover_xattr_data(inode, page);
if (!err)
recovered++;
goto out;
}
/* step 2: recover inline data */
if (recover_inline_data(inode, page))
if (f2fs_recover_inline_data(inode, page))
goto out;
/* step 3: recover data indices */
start = start_bidx_of_node(ofs_of_node(page), inode);
start = f2fs_start_bidx_of_node(ofs_of_node(page), inode);
end = start + ADDRS_PER_PAGE(page, inode);
set_new_dnode(&dn, inode, NULL, NULL, 0);
retry_dn:
err = get_dnode_of_data(&dn, start, ALLOC_NODE);
err = f2fs_get_dnode_of_data(&dn, start, ALLOC_NODE);
if (err) {
if (err == -ENOMEM) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
@ -479,7 +478,7 @@ retry_dn:
f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
err = get_node_info(sbi, dn.nid, &ni);
err = f2fs_get_node_info(sbi, dn.nid, &ni);
if (err)
goto err;
@ -498,7 +497,7 @@ retry_dn:
/* dest is invalid, just invalidate src block */
if (dest == NULL_ADDR) {
truncate_data_blocks_range(&dn, 1);
f2fs_truncate_data_blocks_range(&dn, 1);
continue;
}
@ -512,8 +511,8 @@ retry_dn:
* and then reserve one new block in dnode page.
*/
if (dest == NEW_ADDR) {
truncate_data_blocks_range(&dn, 1);
reserve_new_block(&dn);
f2fs_truncate_data_blocks_range(&dn, 1);
f2fs_reserve_new_block(&dn);
continue;
}
@ -521,10 +520,10 @@ retry_dn:
if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {
if (src == NULL_ADDR) {
err = reserve_new_block(&dn);
err = f2fs_reserve_new_block(&dn);
#ifdef CONFIG_F2FS_FAULT_INJECTION
while (err)
err = reserve_new_block(&dn);
err = f2fs_reserve_new_block(&dn);
#endif
/* We should not get -ENOSPC */
f2fs_bug_on(sbi, err);
@ -582,9 +581,9 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
break;
ra_meta_pages_cond(sbi, blkaddr);
f2fs_ra_meta_pages_cond(sbi, blkaddr);
page = get_tmp_page(sbi, blkaddr);
page = f2fs_get_tmp_page(sbi, blkaddr);
if (IS_ERR(page)) {
err = PTR_ERR(page);
break;
@ -626,11 +625,11 @@ next:
f2fs_put_page(page, 1);
}
if (!err)
allocate_new_segments(sbi);
f2fs_allocate_new_segments(sbi);
return err;
}
int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
{
struct list_head inode_list;
struct list_head dir_list;
@ -705,7 +704,7 @@ skip:
struct cp_control cpc = {
.reason = CP_RECOVERY,
};
err = write_checkpoint(sbi, &cpc);
err = f2fs_write_checkpoint(sbi, &cpc);
}
kmem_cache_destroy(fsync_entry_slab);

344
fs/f2fs/segment.c
View File

@ -169,7 +169,7 @@ found:
return result - size + __reverse_ffz(tmp);
}
bool need_SSR(struct f2fs_sb_info *sbi)
bool f2fs_need_SSR(struct f2fs_sb_info *sbi)
{
int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
@ -177,14 +177,14 @@ bool need_SSR(struct f2fs_sb_info *sbi)
if (test_opt(sbi, LFS))
return false;
if (sbi->gc_thread && sbi->gc_thread->gc_urgent)
if (sbi->gc_mode == GC_URGENT)
return true;
return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs +
SM_I(sbi)->min_ssr_sections + reserved_sections(sbi));
}
void register_inmem_page(struct inode *inode, struct page *page)
void f2fs_register_inmem_page(struct inode *inode, struct page *page)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
@ -239,7 +239,8 @@ static int __revoke_inmem_pages(struct inode *inode,
trace_f2fs_commit_inmem_page(page, INMEM_REVOKE);
retry:
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
err = f2fs_get_dnode_of_data(&dn, page->index,
LOOKUP_NODE);
if (err) {
if (err == -ENOMEM) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
@ -249,13 +250,13 @@ retry:
err = -EAGAIN;
goto next;
}
err = get_node_info(sbi, dn.nid, &ni);
err = f2fs_get_node_info(sbi, dn.nid, &ni);
if (err) {
f2fs_put_dnode(&dn);
return err;
}
if (cur->old_addr == NEW_ADDR) {
invalidate_blocks(sbi, dn.data_blkaddr);
f2fs_invalidate_blocks(sbi, dn.data_blkaddr);
f2fs_update_data_blkaddr(&dn, NEW_ADDR);
} else
f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
@ -277,7 +278,7 @@ next:
return err;
}
void drop_inmem_pages_all(struct f2fs_sb_info *sbi)
void f2fs_drop_inmem_pages_all(struct f2fs_sb_info *sbi, bool gc_failure)
{
struct list_head *head = &sbi->inode_list[ATOMIC_FILE];
struct inode *inode;
@ -293,15 +294,23 @@ next:
spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
if (inode) {
drop_inmem_pages(inode);
if (gc_failure) {
if (fi->i_gc_failures[GC_FAILURE_ATOMIC])
goto drop;
goto skip;
}
drop:
set_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
f2fs_drop_inmem_pages(inode);
iput(inode);
}
skip:
congestion_wait(BLK_RW_ASYNC, HZ/50);
cond_resched();
goto next;
}
void drop_inmem_pages(struct inode *inode)
void f2fs_drop_inmem_pages(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
@ -315,11 +324,11 @@ void drop_inmem_pages(struct inode *inode)
mutex_unlock(&fi->inmem_lock);
clear_inode_flag(inode, FI_ATOMIC_FILE);
clear_inode_flag(inode, FI_HOT_DATA);
fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0;
stat_dec_atomic_write(inode);
}
void drop_inmem_page(struct inode *inode, struct page *page)
void f2fs_drop_inmem_page(struct inode *inode, struct page *page)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@ -334,7 +343,7 @@ void drop_inmem_page(struct inode *inode, struct page *page)
break;
}
f2fs_bug_on(sbi, !cur || cur->page != page);
f2fs_bug_on(sbi, list_empty(head) || cur->page != page);
list_del(&cur->list);
mutex_unlock(&fi->inmem_lock);
@ -349,8 +358,7 @@ void drop_inmem_page(struct inode *inode, struct page *page)
trace_f2fs_commit_inmem_page(page, INMEM_INVALIDATE);
}
static int __commit_inmem_pages(struct inode *inode,
struct list_head *revoke_list)
static int __f2fs_commit_inmem_pages(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
@ -363,9 +371,12 @@ static int __commit_inmem_pages(struct inode *inode,
.op_flags = REQ_SYNC | REQ_PRIO,
.io_type = FS_DATA_IO,
};
struct list_head revoke_list;
pgoff_t last_idx = ULONG_MAX;
int err = 0;
INIT_LIST_HEAD(&revoke_list);
list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) {
struct page *page = cur->page;
@ -377,14 +388,14 @@ static int __commit_inmem_pages(struct inode *inode,
f2fs_wait_on_page_writeback(page, DATA, true);
if (clear_page_dirty_for_io(page)) {
inode_dec_dirty_pages(inode);
remove_dirty_inode(inode);
f2fs_remove_dirty_inode(inode);
}
retry:
fio.page = page;
fio.old_blkaddr = NULL_ADDR;
fio.encrypted_page = NULL;
fio.need_lock = LOCK_DONE;
err = do_write_data_page(&fio);
err = f2fs_do_write_data_page(&fio);
if (err) {
if (err == -ENOMEM) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
@ -399,35 +410,13 @@ retry:
last_idx = page->index;
}
unlock_page(page);
list_move_tail(&cur->list, revoke_list);
list_move_tail(&cur->list, &revoke_list);
}
if (last_idx != ULONG_MAX)
f2fs_submit_merged_write_cond(sbi, inode, 0, last_idx, DATA);
if (!err)
__revoke_inmem_pages(inode, revoke_list, false, false);
return err;
}
int commit_inmem_pages(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct list_head revoke_list;
int err;
INIT_LIST_HEAD(&revoke_list);
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
set_inode_flag(inode, FI_ATOMIC_COMMIT);
mutex_lock(&fi->inmem_lock);
err = __commit_inmem_pages(inode, &revoke_list);
if (err) {
int ret;
/*
* try to revoke all committed pages, but still we could fail
* due to no memory or other reason, if that happened, EAGAIN
@ -436,13 +425,31 @@ int commit_inmem_pages(struct inode *inode)
* recovery or rewrite & commit last transaction. For other
* error number, revoking was done by filesystem itself.
*/
ret = __revoke_inmem_pages(inode, &revoke_list, false, true);
if (ret)
err = ret;
err = __revoke_inmem_pages(inode, &revoke_list, false, true);
/* drop all uncommitted pages */
__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
} else {
__revoke_inmem_pages(inode, &revoke_list, false, false);
}
return err;
}
int f2fs_commit_inmem_pages(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
int err;
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
set_inode_flag(inode, FI_ATOMIC_COMMIT);
mutex_lock(&fi->inmem_lock);
err = __f2fs_commit_inmem_pages(inode);
spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
if (!list_empty(&fi->inmem_ilist))
list_del_init(&fi->inmem_ilist);
@ -488,24 +495,24 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
return;
/* try to shrink extent cache when there is no enough memory */
if (!available_free_memory(sbi, EXTENT_CACHE))
if (!f2fs_available_free_memory(sbi, EXTENT_CACHE))
f2fs_shrink_extent_tree(sbi, EXTENT_CACHE_SHRINK_NUMBER);
/* check the # of cached NAT entries */
if (!available_free_memory(sbi, NAT_ENTRIES))
try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK);
if (!f2fs_available_free_memory(sbi, NAT_ENTRIES))
f2fs_try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK);
if (!available_free_memory(sbi, FREE_NIDS))
try_to_free_nids(sbi, MAX_FREE_NIDS);
if (!f2fs_available_free_memory(sbi, FREE_NIDS))
f2fs_try_to_free_nids(sbi, MAX_FREE_NIDS);
else
build_free_nids(sbi, false, false);
f2fs_build_free_nids(sbi, false, false);
if (!is_idle(sbi) && !excess_dirty_nats(sbi))
return;
/* checkpoint is the only way to shrink partial cached entries */
if (!available_free_memory(sbi, NAT_ENTRIES) ||
!available_free_memory(sbi, INO_ENTRIES) ||
if (!f2fs_available_free_memory(sbi, NAT_ENTRIES) ||
!f2fs_available_free_memory(sbi, INO_ENTRIES) ||
excess_prefree_segs(sbi) ||
excess_dirty_nats(sbi) ||
f2fs_time_over(sbi, CP_TIME)) {
@ -513,7 +520,7 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
struct blk_plug plug;
blk_start_plug(&plug);
sync_dirty_inodes(sbi, FILE_INODE);
f2fs_sync_dirty_inodes(sbi, FILE_INODE);
blk_finish_plug(&plug);
}
f2fs_sync_fs(sbi->sb, true);
@ -546,7 +553,7 @@ static int submit_flush_wait(struct f2fs_sb_info *sbi, nid_t ino)
return __submit_flush_wait(sbi, sbi->sb->s_bdev);
for (i = 0; i < sbi->s_ndevs; i++) {
if (!is_dirty_device(sbi, ino, i, FLUSH_INO))
if (!f2fs_is_dirty_device(sbi, ino, i, FLUSH_INO))
continue;
ret = __submit_flush_wait(sbi, FDEV(i).bdev);
if (ret)
@ -657,7 +664,7 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino)
return cmd.ret;
}
int create_flush_cmd_control(struct f2fs_sb_info *sbi)
int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi)
{
dev_t dev = sbi->sb->s_bdev->bd_dev;
struct flush_cmd_control *fcc;
@ -694,7 +701,7 @@ init_thread:
return err;
}
void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free)
void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free)
{
struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
@ -954,6 +961,7 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi,
} else if (discard_type == DPOLICY_FSTRIM) {
dpolicy->io_aware = false;
} else if (discard_type == DPOLICY_UMOUNT) {
dpolicy->max_requests = UINT_MAX;
dpolicy->io_aware = false;
}
}
@ -973,6 +981,9 @@ static void __submit_discard_cmd(struct f2fs_sb_info *sbi,
if (dc->state != D_PREP)
return;
if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
return;
trace_f2fs_issue_discard(dc->bdev, dc->start, dc->len);
dc->error = __blkdev_issue_discard(dc->bdev,
@ -1016,7 +1027,7 @@ static struct discard_cmd *__insert_discard_tree(struct f2fs_sb_info *sbi,
goto do_insert;
}
p = __lookup_rb_tree_for_insert(sbi, &dcc->root, &parent, lstart);
p = f2fs_lookup_rb_tree_for_insert(sbi, &dcc->root, &parent, lstart);
do_insert:
dc = __attach_discard_cmd(sbi, bdev, lstart, start, len, parent, p);
if (!dc)
@ -1081,7 +1092,7 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
mutex_lock(&dcc->cmd_lock);
dc = (struct discard_cmd *)__lookup_rb_tree_ret(&dcc->root,
dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
NULL, lstart,
(struct rb_entry **)&prev_dc,
(struct rb_entry **)&next_dc,
@ -1192,7 +1203,8 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
mutex_lock(&dcc->cmd_lock);
if (list_empty(pend_list))
goto next;
f2fs_bug_on(sbi, !__check_rb_tree_consistence(sbi, &dcc->root));
f2fs_bug_on(sbi,
!f2fs_check_rb_tree_consistence(sbi, &dcc->root));
blk_start_plug(&plug);
list_for_each_entry_safe(dc, tmp, pend_list, list) {
f2fs_bug_on(sbi, dc->state != D_PREP);
@ -1245,7 +1257,7 @@ static bool __drop_discard_cmd(struct f2fs_sb_info *sbi)
return dropped;
}
void drop_discard_cmd(struct f2fs_sb_info *sbi)
void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi)
{
__drop_discard_cmd(sbi);
}
@ -1336,7 +1348,8 @@ static void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr)
bool need_wait = false;
mutex_lock(&dcc->cmd_lock);
dc = (struct discard_cmd *)__lookup_rb_tree(&dcc->root, NULL, blkaddr);
dc = (struct discard_cmd *)f2fs_lookup_rb_tree(&dcc->root,
NULL, blkaddr);
if (dc) {
if (dc->state == D_PREP) {
__punch_discard_cmd(sbi, dc, blkaddr);
@ -1351,7 +1364,7 @@ static void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr)
__wait_one_discard_bio(sbi, dc);
}
void stop_discard_thread(struct f2fs_sb_info *sbi)
void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
@ -1401,17 +1414,22 @@ static int issue_discard_thread(void *data)
kthread_should_stop() || freezing(current) ||
dcc->discard_wake,
msecs_to_jiffies(wait_ms));
if (dcc->discard_wake)
dcc->discard_wake = 0;
if (try_to_freeze())
continue;
if (f2fs_readonly(sbi->sb))
continue;
if (kthread_should_stop())
return 0;
if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) {
wait_ms = dpolicy.max_interval;
continue;
}
if (dcc->discard_wake)
dcc->discard_wake = 0;
if (sbi->gc_thread && sbi->gc_thread->gc_urgent)
if (sbi->gc_mode == GC_URGENT)
__init_discard_policy(sbi, &dpolicy, DPOLICY_FORCE, 1);
sb_start_intwrite(sbi->sb);
@ -1594,20 +1612,24 @@ static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc,
return false;
}
void release_discard_addrs(struct f2fs_sb_info *sbi)
static void release_discard_addr(struct discard_entry *entry)
{
list_del(&entry->list);
kmem_cache_free(discard_entry_slab, entry);
}
void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi)
{
struct list_head *head = &(SM_I(sbi)->dcc_info->entry_list);
struct discard_entry *entry, *this;
/* drop caches */
list_for_each_entry_safe(entry, this, head, list) {
list_del(&entry->list);
kmem_cache_free(discard_entry_slab, entry);
}
list_for_each_entry_safe(entry, this, head, list)
release_discard_addr(entry);
}
/*
* Should call clear_prefree_segments after checkpoint is done.
* Should call f2fs_clear_prefree_segments after checkpoint is done.
*/
static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi)
{
@ -1620,7 +1642,8 @@ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi)
mutex_unlock(&dirty_i->seglist_lock);
}
void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
struct cp_control *cpc)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct list_head *head = &dcc->entry_list;
@ -1703,9 +1726,8 @@ skip:
if (cur_pos < sbi->blocks_per_seg)
goto find_next;
list_del(&entry->list);
release_discard_addr(entry);
dcc->nr_discards -= total_len;
kmem_cache_free(discard_entry_slab, entry);
}
wake_up_discard_thread(sbi, false);
@ -1763,7 +1785,7 @@ static void destroy_discard_cmd_control(struct f2fs_sb_info *sbi)
if (!dcc)
return;
stop_discard_thread(sbi);
f2fs_stop_discard_thread(sbi);
kfree(dcc);
SM_I(sbi)->dcc_info = NULL;
@ -1810,8 +1832,9 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
(new_vblocks > sbi->blocks_per_seg)));
se->valid_blocks = new_vblocks;
se->mtime = get_mtime(sbi);
SIT_I(sbi)->max_mtime = se->mtime;
se->mtime = get_mtime(sbi, false);
if (se->mtime > SIT_I(sbi)->max_mtime)
SIT_I(sbi)->max_mtime = se->mtime;
/* Update valid block bitmap */
if (del > 0) {
@ -1879,7 +1902,7 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
get_sec_entry(sbi, segno)->valid_blocks += del;
}
void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
{
unsigned int segno = GET_SEGNO(sbi, addr);
struct sit_info *sit_i = SIT_I(sbi);
@ -1899,7 +1922,7 @@ void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
up_write(&sit_i->sentry_lock);
}
bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
{
struct sit_info *sit_i = SIT_I(sbi);
unsigned int segno, offset;
@ -1938,7 +1961,7 @@ static void __add_sum_entry(struct f2fs_sb_info *sbi, int type,
/*
* Calculate the number of current summary pages for writing
*/
int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
{
int valid_sum_count = 0;
int i, sum_in_page;
@ -1968,14 +1991,15 @@ int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
/*
* Caller should put this summary page
*/
struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno)
struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno)
{
return f2fs_get_meta_page_nofail(sbi, GET_SUM_BLOCK(sbi, segno));
}
void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr)
void f2fs_update_meta_page(struct f2fs_sb_info *sbi,
void *src, block_t blk_addr)
{
struct page *page = grab_meta_page(sbi, blk_addr);
struct page *page = f2fs_grab_meta_page(sbi, blk_addr);
memcpy(page_address(page), src, PAGE_SIZE);
set_page_dirty(page);
@ -1985,18 +2009,19 @@ void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr)
static void write_sum_page(struct f2fs_sb_info *sbi,
struct f2fs_summary_block *sum_blk, block_t blk_addr)
{
update_meta_page(sbi, (void *)sum_blk, blk_addr);
f2fs_update_meta_page(sbi, (void *)sum_blk, blk_addr);
}
static void write_current_sum_page(struct f2fs_sb_info *sbi,
int type, block_t blk_addr)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
struct page *page = grab_meta_page(sbi, blk_addr);
struct page *page = f2fs_grab_meta_page(sbi, blk_addr);
struct f2fs_summary_block *src = curseg->sum_blk;
struct f2fs_summary_block *dst;
dst = (struct f2fs_summary_block *)page_address(page);
memset(dst, 0, PAGE_SIZE);
mutex_lock(&curseg->curseg_mutex);
@ -2236,7 +2261,7 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type)
curseg->alloc_type = SSR;
__next_free_blkoff(sbi, curseg, 0);
sum_page = get_sum_page(sbi, new_segno);
sum_page = f2fs_get_sum_page(sbi, new_segno);
f2fs_bug_on(sbi, IS_ERR(sum_page));
sum_node = (struct f2fs_summary_block *)page_address(sum_page);
memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE);
@ -2251,7 +2276,7 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
int i, cnt;
bool reversed = false;
/* need_SSR() already forces to do this */
/* f2fs_need_SSR() already forces to do this */
if (v_ops->get_victim(sbi, &segno, BG_GC, type, SSR)) {
curseg->next_segno = segno;
return 1;
@ -2303,7 +2328,7 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
new_curseg(sbi, type, false);
else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type))
new_curseg(sbi, type, false);
else if (need_SSR(sbi) && get_ssr_segment(sbi, type))
else if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type))
change_curseg(sbi, type);
else
new_curseg(sbi, type, false);
@ -2311,7 +2336,7 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
stat_inc_seg_type(sbi, curseg);
}
void allocate_new_segments(struct f2fs_sb_info *sbi)
void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi)
{
struct curseg_info *curseg;
unsigned int old_segno;
@ -2333,7 +2358,8 @@ static const struct segment_allocation default_salloc_ops = {
.allocate_segment = allocate_segment_by_default,
};
bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc)
bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi,
struct cp_control *cpc)
{
__u64 trim_start = cpc->trim_start;
bool has_candidate = false;
@ -2366,9 +2392,9 @@ next:
issued = 0;
mutex_lock(&dcc->cmd_lock);
f2fs_bug_on(sbi, !__check_rb_tree_consistence(sbi, &dcc->root));
f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi, &dcc->root));
dc = (struct discard_cmd *)__lookup_rb_tree_ret(&dcc->root,
dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
NULL, start,
(struct rb_entry **)&prev_dc,
(struct rb_entry **)&next_dc,
@ -2427,12 +2453,12 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
return -EINVAL;
if (end <= MAIN_BLKADDR(sbi))
goto out;
return -EINVAL;
if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) {
f2fs_msg(sbi->sb, KERN_WARNING,
"Found FS corruption, run fsck to fix.");
goto out;
return -EIO;
}
/* start/end segment number in main_area */
@ -2449,7 +2475,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
goto out;
mutex_lock(&sbi->gc_mutex);
err = write_checkpoint(sbi, &cpc);
err = f2fs_write_checkpoint(sbi, &cpc);
mutex_unlock(&sbi->gc_mutex);
if (err)
goto out;
@ -2484,7 +2510,7 @@ static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
return false;
}
int rw_hint_to_seg_type(enum rw_hint hint)
int f2fs_rw_hint_to_seg_type(enum rw_hint hint)
{
switch (hint) {
case WRITE_LIFE_SHORT:
@ -2557,7 +2583,7 @@ int rw_hint_to_seg_type(enum rw_hint hint)
* WRITE_LIFE_LONG " WRITE_LIFE_LONG
*/
enum rw_hint io_type_to_rw_hint(struct f2fs_sb_info *sbi,
enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
enum page_type type, enum temp_type temp)
{
if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER) {
@ -2624,9 +2650,11 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
if (is_cold_data(fio->page) || file_is_cold(inode))
return CURSEG_COLD_DATA;
if (file_is_hot(inode) ||
is_inode_flag_set(inode, FI_HOT_DATA))
is_inode_flag_set(inode, FI_HOT_DATA) ||
is_inode_flag_set(inode, FI_ATOMIC_FILE) ||
is_inode_flag_set(inode, FI_VOLATILE_FILE))
return CURSEG_HOT_DATA;
return rw_hint_to_seg_type(inode->i_write_hint);
return f2fs_rw_hint_to_seg_type(inode->i_write_hint);
} else {
if (IS_DNODE(fio->page))
return is_cold_node(fio->page) ? CURSEG_WARM_NODE :
@ -2662,7 +2690,7 @@ static int __get_segment_type(struct f2fs_io_info *fio)
return type;
}
void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
block_t old_blkaddr, block_t *new_blkaddr,
struct f2fs_summary *sum, int type,
struct f2fs_io_info *fio, bool add_list)
@ -2722,6 +2750,7 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
INIT_LIST_HEAD(&fio->list);
fio->in_list = true;
fio->retry = false;
io = sbi->write_io[fio->type] + fio->temp;
spin_lock(&io->io_lock);
list_add_tail(&fio->list, &io->io_list);
@ -2744,7 +2773,7 @@ static void update_device_state(struct f2fs_io_info *fio)
devidx = f2fs_target_device_index(sbi, fio->new_blkaddr);
/* update device state for fsync */
set_dirty_device(sbi, fio->ino, devidx, FLUSH_INO);
f2fs_set_dirty_device(sbi, fio->ino, devidx, FLUSH_INO);
/* update device state for checkpoint */
if (!f2fs_test_bit(devidx, (char *)&sbi->dirty_device)) {
@ -2757,23 +2786,28 @@ static void update_device_state(struct f2fs_io_info *fio)
static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
{
int type = __get_segment_type(fio);
int err;
bool keep_order = (test_opt(fio->sbi, LFS) && type == CURSEG_COLD_DATA);
if (keep_order)
down_read(&fio->sbi->io_order_lock);
reallocate:
allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
&fio->new_blkaddr, sum, type, fio, true);
/* writeout dirty page into bdev */
err = f2fs_submit_page_write(fio);
if (err == -EAGAIN) {
f2fs_submit_page_write(fio);
if (fio->retry) {
fio->old_blkaddr = fio->new_blkaddr;
goto reallocate;
} else if (!err) {
update_device_state(fio);
}
update_device_state(fio);
if (keep_order)
up_read(&fio->sbi->io_order_lock);
}
void write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
enum iostat_type io_type)
{
struct f2fs_io_info fio = {
@ -2799,7 +2833,7 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
f2fs_update_iostat(sbi, io_type, F2FS_BLKSIZE);
}
void write_node_page(unsigned int nid, struct f2fs_io_info *fio)
void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio)
{
struct f2fs_summary sum;
@ -2809,7 +2843,8 @@ void write_node_page(unsigned int nid, struct f2fs_io_info *fio)
f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE);
}
void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio)
void f2fs_outplace_write_data(struct dnode_of_data *dn,
struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = fio->sbi;
struct f2fs_summary sum;
@ -2822,7 +2857,7 @@ void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio)
f2fs_update_iostat(sbi, fio->io_type, F2FS_BLKSIZE);
}
int rewrite_data_page(struct f2fs_io_info *fio)
int f2fs_inplace_write_data(struct f2fs_io_info *fio)
{
int err;
struct f2fs_sb_info *sbi = fio->sbi;
@ -2857,7 +2892,7 @@ static inline int __f2fs_get_curseg(struct f2fs_sb_info *sbi,
return i;
}
void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
block_t old_blkaddr, block_t new_blkaddr,
bool recover_curseg, bool recover_newaddr)
{
@ -2942,7 +2977,7 @@ void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
set_summary(&sum, dn->nid, dn->ofs_in_node, version);
__f2fs_replace_block(sbi, &sum, old_addr, new_addr,
f2fs_do_replace_block(sbi, &sum, old_addr, new_addr,
recover_curseg, recover_newaddr);
f2fs_update_data_blkaddr(dn, new_addr);
@ -2992,7 +3027,7 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi)
start = start_sum_block(sbi);
page = get_meta_page(sbi, start++);
page = f2fs_get_meta_page(sbi, start++);
if (IS_ERR(page))
return PTR_ERR(page);
kaddr = (unsigned char *)page_address(page);
@ -3034,7 +3069,7 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi)
f2fs_put_page(page, 1);
page = NULL;
page = get_meta_page(sbi, start++);
page = f2fs_get_meta_page(sbi, start++);
if (IS_ERR(page))
return PTR_ERR(page);
kaddr = (unsigned char *)page_address(page);
@ -3077,7 +3112,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
blk_addr = GET_SUM_BLOCK(sbi, segno);
}
new = get_meta_page(sbi, blk_addr);
new = f2fs_get_meta_page(sbi, blk_addr);
if (IS_ERR(new))
return PTR_ERR(new);
sum = (struct f2fs_summary_block *)page_address(new);
@ -3091,7 +3126,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
ns->ofs_in_node = 0;
}
} else {
err = restore_node_summary(sbi, segno, sum);
err = f2fs_restore_node_summary(sbi, segno, sum);
if (err)
goto out;
}
@ -3126,10 +3161,10 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
int err;
if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG)) {
int npages = npages_for_summary_flush(sbi, true);
int npages = f2fs_npages_for_summary_flush(sbi, true);
if (npages >= 2)
ra_meta_pages(sbi, start_sum_block(sbi), npages,
f2fs_ra_meta_pages(sbi, start_sum_block(sbi), npages,
META_CP, true);
/* restore for compacted data summary */
@ -3140,7 +3175,7 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
}
if (__exist_node_summaries(sbi))
ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type),
f2fs_ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type),
NR_CURSEG_TYPE - type, META_CP, true);
for (; type <= CURSEG_COLD_NODE; type++) {
@ -3166,8 +3201,9 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr)
int written_size = 0;
int i, j;
page = grab_meta_page(sbi, blkaddr++);
page = f2fs_grab_meta_page(sbi, blkaddr++);
kaddr = (unsigned char *)page_address(page);
memset(kaddr, 0, PAGE_SIZE);
/* Step 1: write nat cache */
seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
@ -3190,8 +3226,9 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr)
for (j = 0; j < blkoff; j++) {
if (!page) {
page = grab_meta_page(sbi, blkaddr++);
page = f2fs_grab_meta_page(sbi, blkaddr++);
kaddr = (unsigned char *)page_address(page);
memset(kaddr, 0, PAGE_SIZE);
written_size = 0;
}
summary = (struct f2fs_summary *)(kaddr + written_size);
@ -3226,7 +3263,7 @@ static void write_normal_summaries(struct f2fs_sb_info *sbi,
write_current_sum_page(sbi, i, blkaddr + (i - type));
}
void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
{
if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG))
write_compacted_summaries(sbi, start_blk);
@ -3234,12 +3271,12 @@ void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
write_normal_summaries(sbi, start_blk, CURSEG_HOT_DATA);
}
void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
{
write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
}
int lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
unsigned int val, int alloc)
{
int i;
@ -3277,7 +3314,7 @@ static struct page *get_next_sit_page(struct f2fs_sb_info *sbi,
src_off = current_sit_addr(sbi, start);
dst_off = next_sit_addr(sbi, src_off);
page = grab_meta_page(sbi, dst_off);
page = f2fs_grab_meta_page(sbi, dst_off);
seg_info_to_sit_page(sbi, page, start);
set_page_dirty(page);
@ -3373,7 +3410,7 @@ static void remove_sits_in_journal(struct f2fs_sb_info *sbi)
* CP calls this function, which flushes SIT entries including sit_journal,
* and moves prefree segs to free segs.
*/
void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct sit_info *sit_i = SIT_I(sbi);
unsigned long *bitmap = sit_i->dirty_sentries_bitmap;
@ -3432,6 +3469,11 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
int offset, sit_offset;
se = get_seg_entry(sbi, segno);
#ifdef CONFIG_F2FS_CHECK_FS
if (memcmp(se->cur_valid_map, se->cur_valid_map_mir,
SIT_VBLOCK_MAP_SIZE))
f2fs_bug_on(sbi, 1);
#endif
/* add discard candidates */
if (!(cpc->reason & CP_DISCARD)) {
@ -3440,17 +3482,21 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
}
if (to_journal) {
offset = lookup_journal_in_cursum(journal,
offset = f2fs_lookup_journal_in_cursum(journal,
SIT_JOURNAL, segno, 1);
f2fs_bug_on(sbi, offset < 0);
segno_in_journal(journal, offset) =
cpu_to_le32(segno);
seg_info_to_raw_sit(se,
&sit_in_journal(journal, offset));
check_block_count(sbi, segno,
&sit_in_journal(journal, offset));
} else {
sit_offset = SIT_ENTRY_OFFSET(sit_i, segno);
seg_info_to_raw_sit(se,
&raw_sit->entries[sit_offset]);
check_block_count(sbi, segno,
&raw_sit->entries[sit_offset]);
}
__clear_bit(segno, bitmap);
@ -3498,8 +3544,10 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
SM_I(sbi)->sit_info = sit_i;
sit_i->sentries = f2fs_kvzalloc(sbi, MAIN_SEGS(sbi) *
sizeof(struct seg_entry), GFP_KERNEL);
sit_i->sentries =
f2fs_kvzalloc(sbi, array_size(sizeof(struct seg_entry),
MAIN_SEGS(sbi)),
GFP_KERNEL);
if (!sit_i->sentries)
return -ENOMEM;
@ -3539,8 +3587,10 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
return -ENOMEM;
if (sbi->segs_per_sec > 1) {
sit_i->sec_entries = f2fs_kvzalloc(sbi, MAIN_SECS(sbi) *
sizeof(struct sec_entry), GFP_KERNEL);
sit_i->sec_entries =
f2fs_kvzalloc(sbi, array_size(sizeof(struct sec_entry),
MAIN_SECS(sbi)),
GFP_KERNEL);
if (!sit_i->sec_entries)
return -ENOMEM;
}
@ -3616,7 +3666,8 @@ static int build_curseg(struct f2fs_sb_info *sbi)
struct curseg_info *array;
int i;
array = f2fs_kzalloc(sbi, sizeof(*array) * NR_CURSEG_TYPE, GFP_KERNEL);
array = f2fs_kzalloc(sbi, array_size(NR_CURSEG_TYPE, sizeof(*array)),
GFP_KERNEL);
if (!array)
return -ENOMEM;
@ -3652,7 +3703,7 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
block_t total_node_blocks = 0;
do {
readed = ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES,
readed = f2fs_ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES,
META_SIT, true);
start = start_blk * sit_i->sents_per_block;
@ -3734,14 +3785,17 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
} else {
memcpy(se->discard_map, se->cur_valid_map,
SIT_VBLOCK_MAP_SIZE);
sbi->discard_blks += old_valid_blocks -
se->valid_blocks;
sbi->discard_blks += old_valid_blocks;
sbi->discard_blks -= se->valid_blocks;
}
}
if (sbi->segs_per_sec > 1)
if (sbi->segs_per_sec > 1) {
get_sec_entry(sbi, start)->valid_blocks +=
se->valid_blocks - old_valid_blocks;
se->valid_blocks;
get_sec_entry(sbi, start)->valid_blocks -=
old_valid_blocks;
}
}
up_read(&curseg->journal_rwsem);
@ -3851,7 +3905,7 @@ static void init_min_max_mtime(struct f2fs_sb_info *sbi)
down_write(&sit_i->sentry_lock);
sit_i->min_mtime = LLONG_MAX;
sit_i->min_mtime = ULLONG_MAX;
for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
unsigned int i;
@ -3865,11 +3919,11 @@ static void init_min_max_mtime(struct f2fs_sb_info *sbi)
if (sit_i->min_mtime > mtime)
sit_i->min_mtime = mtime;
}
sit_i->max_mtime = get_mtime(sbi);
sit_i->max_mtime = get_mtime(sbi, false);
up_write(&sit_i->sentry_lock);
}
int build_segment_manager(struct f2fs_sb_info *sbi)
int f2fs_build_segment_manager(struct f2fs_sb_info *sbi)
{
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
@ -3907,7 +3961,7 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
init_rwsem(&sm_info->curseg_lock);
if (!f2fs_readonly(sbi->sb)) {
err = create_flush_cmd_control(sbi);
err = f2fs_create_flush_cmd_control(sbi);
if (err)
return err;
}
@ -4032,13 +4086,13 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi)
kfree(sit_i);
}
void destroy_segment_manager(struct f2fs_sb_info *sbi)
void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi)
{
struct f2fs_sm_info *sm_info = SM_I(sbi);
if (!sm_info)
return;
destroy_flush_cmd_control(sbi, true);
f2fs_destroy_flush_cmd_control(sbi, true);
destroy_discard_cmd_control(sbi);
destroy_dirty_segmap(sbi);
destroy_curseg(sbi);
@ -4048,7 +4102,7 @@ void destroy_segment_manager(struct f2fs_sb_info *sbi)
kfree(sm_info);
}
int __init create_segment_manager_caches(void)
int __init f2fs_create_segment_manager_caches(void)
{
discard_entry_slab = f2fs_kmem_cache_create("discard_entry",
sizeof(struct discard_entry));
@ -4081,7 +4135,7 @@ fail:
return -ENOMEM;
}
void destroy_segment_manager_caches(void)
void f2fs_destroy_segment_manager_caches(void)
{
kmem_cache_destroy(sit_entry_set_slab);
kmem_cache_destroy(discard_cmd_slab);

29
fs/f2fs/segment.h
View File

@ -215,6 +215,8 @@ struct segment_allocation {
#define IS_DUMMY_WRITTEN_PAGE(page) \
(page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE)
#define MAX_SKIP_ATOMIC_COUNT 16
struct inmem_pages {
struct list_head list;
struct page *page;
@ -375,6 +377,7 @@ static inline void seg_info_to_sit_page(struct f2fs_sb_info *sbi,
int i;
raw_sit = (struct f2fs_sit_block *)page_address(page);
memset(raw_sit, 0, PAGE_SIZE);
for (i = 0; i < end - start; i++) {
rs = &raw_sit->entries[i];
se = get_seg_entry(sbi, start + i);
@ -742,12 +745,23 @@ static inline void set_to_next_sit(struct sit_info *sit_i, unsigned int start)
#endif
}
static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi)
static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi,
bool base_time)
{
struct sit_info *sit_i = SIT_I(sbi);
time64_t now = ktime_get_real_seconds();
time64_t diff, now = ktime_get_real_seconds();
return sit_i->elapsed_time + now - sit_i->mounted_time;
if (now >= sit_i->mounted_time)
return sit_i->elapsed_time + now - sit_i->mounted_time;
/* system time is set to the past */
if (!base_time) {
diff = sit_i->mounted_time - now;
if (sit_i->elapsed_time >= diff)
return sit_i->elapsed_time - diff;
return 0;
}
return sit_i->elapsed_time;
}
static inline void set_summary(struct f2fs_summary *sum, nid_t nid,
@ -771,15 +785,6 @@ static inline block_t sum_blk_addr(struct f2fs_sb_info *sbi, int base, int type)
- (base + 1) + type;
}
static inline bool no_fggc_candidate(struct f2fs_sb_info *sbi,
unsigned int secno)
{
if (get_valid_blocks(sbi, GET_SEG_FROM_SEC(sbi, secno), true) >
sbi->fggc_threshold)
return true;
return false;
}
static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno)
{
if (IS_CURSEC(sbi, secno) || (sbi->cur_victim_sec == secno))

4
fs/f2fs/shrinker.c
View File

@ -109,11 +109,11 @@ unsigned long f2fs_shrink_scan(struct shrinker *shrink,
/* shrink clean nat cache entries */
if (freed < nr)
freed += try_to_free_nats(sbi, nr - freed);
freed += f2fs_try_to_free_nats(sbi, nr - freed);
/* shrink free nids cache entries */
if (freed < nr)
freed += try_to_free_nids(sbi, nr - freed);
freed += f2fs_try_to_free_nids(sbi, nr - freed);
spin_lock(&f2fs_list_lock);
p = p->next;

149
fs/f2fs/super.c
View File

@ -830,15 +830,14 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
/* Initialize f2fs-specific inode info */
atomic_set(&fi->dirty_pages, 0);
fi->i_current_depth = 1;
init_rwsem(&fi->i_sem);
INIT_LIST_HEAD(&fi->dirty_list);
INIT_LIST_HEAD(&fi->gdirty_list);
INIT_LIST_HEAD(&fi->inmem_ilist);
INIT_LIST_HEAD(&fi->inmem_pages);
mutex_init(&fi->inmem_lock);
init_rwsem(&fi->dio_rwsem[READ]);
init_rwsem(&fi->dio_rwsem[WRITE]);
init_rwsem(&fi->i_gc_rwsem[READ]);
init_rwsem(&fi->i_gc_rwsem[WRITE]);
init_rwsem(&fi->i_mmap_sem);
init_rwsem(&fi->i_xattr_sem);
@ -866,7 +865,7 @@ static int f2fs_drop_inode(struct inode *inode)
/* some remained atomic pages should discarded */
if (f2fs_is_atomic_file(inode))
drop_inmem_pages(inode);
f2fs_drop_inmem_pages(inode);
/* should remain fi->extent_tree for writepage */
f2fs_destroy_extent_node(inode);
@ -995,7 +994,7 @@ static void f2fs_umount_end(struct super_block *sb, int flags)
struct cp_control cpc = {
.reason = CP_UMOUNT,
};
write_checkpoint(F2FS_SB(sb), &cpc);
f2fs_write_checkpoint(F2FS_SB(sb), &cpc);
}
}
}
@ -1021,7 +1020,7 @@ static void f2fs_put_super(struct super_block *sb)
struct cp_control cpc = {
.reason = CP_UMOUNT,
};
write_checkpoint(sbi, &cpc);
f2fs_write_checkpoint(sbi, &cpc);
}
/* be sure to wait for any on-going discard commands */
@ -1031,14 +1030,14 @@ static void f2fs_put_super(struct super_block *sb)
struct cp_control cpc = {
.reason = CP_UMOUNT | CP_TRIMMED,
};
write_checkpoint(sbi, &cpc);
f2fs_write_checkpoint(sbi, &cpc);
}
/*
* normally superblock is clean, so we need to release this.
* In addition, EIO will skip do checkpoint, we need this as well.
*/
release_ino_entry(sbi, true);
f2fs_release_ino_entry(sbi, true);
f2fs_leave_shrinker(sbi);
mutex_unlock(&sbi->umount_mutex);
@ -1056,8 +1055,8 @@ static void f2fs_put_super(struct super_block *sb)
f2fs_destroy_stats(sbi);
/* destroy f2fs internal modules */
destroy_node_manager(sbi);
destroy_segment_manager(sbi);
f2fs_destroy_node_manager(sbi);
f2fs_destroy_segment_manager(sbi);
kfree(sbi->ckpt);
@ -1099,7 +1098,7 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
cpc.reason = __get_cp_reason(sbi);
mutex_lock(&sbi->gc_mutex);
err = write_checkpoint(sbi, &cpc);
err = f2fs_write_checkpoint(sbi, &cpc);
mutex_unlock(&sbi->gc_mutex);
}
f2fs_trace_ios(NULL, 1);
@ -1504,11 +1503,11 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
*/
if ((*flags & MS_RDONLY) || !test_opt(sbi, BG_GC)) {
if (sbi->gc_thread) {
stop_gc_thread(sbi);
f2fs_stop_gc_thread(sbi);
need_restart_gc = true;
}
} else if (!sbi->gc_thread) {
err = start_gc_thread(sbi);
err = f2fs_start_gc_thread(sbi);
if (err)
goto restore_opts;
need_stop_gc = true;
@ -1531,9 +1530,9 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
*/
if ((*flags & MS_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) {
clear_opt(sbi, FLUSH_MERGE);
destroy_flush_cmd_control(sbi, false);
f2fs_destroy_flush_cmd_control(sbi, false);
} else {
err = create_flush_cmd_control(sbi);
err = f2fs_create_flush_cmd_control(sbi);
if (err)
goto restore_gc;
}
@ -1551,11 +1550,11 @@ skip:
return 0;
restore_gc:
if (need_restart_gc) {
if (start_gc_thread(sbi))
if (f2fs_start_gc_thread(sbi))
f2fs_msg(sbi->sb, KERN_WARNING,
"background gc thread has stopped");
} else if (need_stop_gc) {
stop_gc_thread(sbi);
f2fs_stop_gc_thread(sbi);
}
restore_opts:
#ifdef CONFIG_QUOTA
@ -1827,7 +1826,7 @@ static int f2fs_quota_on(struct super_block *sb, int type, int format_id,
inode = d_inode(path->dentry);
inode_lock(inode);
F2FS_I(inode)->i_flags |= FS_NOATIME_FL | FS_IMMUTABLE_FL;
F2FS_I(inode)->i_flags |= F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL;
inode_set_flags(inode, S_NOATIME | S_IMMUTABLE,
S_NOATIME | S_IMMUTABLE);
inode_unlock(inode);
@ -1853,7 +1852,7 @@ static int f2fs_quota_off(struct super_block *sb, int type)
goto out_put;
inode_lock(inode);
F2FS_I(inode)->i_flags &= ~(FS_NOATIME_FL | FS_IMMUTABLE_FL);
F2FS_I(inode)->i_flags &= ~(F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL);
inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE);
inode_unlock(inode);
f2fs_mark_inode_dirty_sync(inode, false);
@ -1971,25 +1970,13 @@ static bool f2fs_dummy_context(struct inode *inode)
return DUMMY_ENCRYPTION_ENABLED(F2FS_I_SB(inode));
}
static unsigned f2fs_max_namelen(struct inode *inode)
{
return S_ISLNK(inode->i_mode) ?
inode->i_sb->s_blocksize : F2FS_NAME_LEN;
}
static inline bool f2fs_is_encrypted(struct inode *inode)
{
return f2fs_encrypted_file(inode);
}
static const struct fscrypt_operations f2fs_cryptops = {
.key_prefix = "f2fs:",
.get_context = f2fs_get_context,
.set_context = f2fs_set_context,
.dummy_context = f2fs_dummy_context,
.empty_dir = f2fs_empty_dir,
.max_namelen = f2fs_max_namelen,
.is_encrypted = f2fs_is_encrypted,
.max_namelen = F2FS_NAME_LEN,
};
#endif
@ -1999,7 +1986,7 @@ static struct inode *f2fs_nfs_get_inode(struct super_block *sb,
struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct inode *inode;
if (check_nid_range(sbi, ino))
if (f2fs_check_nid_range(sbi, ino))
return ERR_PTR(-ESTALE);
/*
@ -2285,10 +2272,14 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
secs_per_zone, total_sections);
return 1;
}
if (le32_to_cpu(raw_super->extension_count) > F2FS_MAX_EXTENSION) {
if (le32_to_cpu(raw_super->extension_count) > F2FS_MAX_EXTENSION ||
raw_super->hot_ext_count > F2FS_MAX_EXTENSION ||
(le32_to_cpu(raw_super->extension_count) +
raw_super->hot_ext_count) > F2FS_MAX_EXTENSION) {
f2fs_msg(sb, KERN_INFO,
"Corrupted extension count (%u > %u)",
"Corrupted extension count (%u + %u > %u)",
le32_to_cpu(raw_super->extension_count),
raw_super->hot_ext_count,
F2FS_MAX_EXTENSION);
return 1;
}
@ -2321,7 +2312,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
return 0;
}
int sanity_check_ckpt(struct f2fs_sb_info *sbi)
int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi)
{
unsigned int total, fsmeta;
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
@ -2442,13 +2433,15 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
for (i = 0; i < NR_COUNT_TYPE; i++)
atomic_set(&sbi->nr_pages[i], 0);
atomic_set(&sbi->wb_sync_req, 0);
for (i = 0; i < META; i++)
atomic_set(&sbi->wb_sync_req[i], 0);
INIT_LIST_HEAD(&sbi->s_list);
mutex_init(&sbi->umount_mutex);
for (i = 0; i < NR_PAGE_TYPE - 1; i++)
for (j = HOT; j < NR_TEMP_TYPE; j++)
mutex_init(&sbi->wio_mutex[i][j]);
init_rwsem(&sbi->io_order_lock);
spin_lock_init(&sbi->cp_lock);
sbi->dirty_device = 0;
@ -2503,8 +2496,10 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
#define F2FS_REPORT_NR_ZONES 4096
zones = f2fs_kzalloc(sbi, sizeof(struct blk_zone) *
F2FS_REPORT_NR_ZONES, GFP_KERNEL);
zones = f2fs_kzalloc(sbi,
array_size(F2FS_REPORT_NR_ZONES,
sizeof(struct blk_zone)),
GFP_KERNEL);
if (!zones)
return -ENOMEM;
@ -2644,8 +2639,10 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
* Initialize multiple devices information, or single
* zoned block device information.
*/
sbi->devs = f2fs_kzalloc(sbi, sizeof(struct f2fs_dev_info) *
max_devices, GFP_KERNEL);
sbi->devs = f2fs_kzalloc(sbi,
array_size(max_devices,
sizeof(struct f2fs_dev_info)),
GFP_KERNEL);
if (!sbi->devs)
return -ENOMEM;
@ -2878,9 +2875,11 @@ try_onemore:
int n = (i == META) ? 1: NR_TEMP_TYPE;
int j;
sbi->write_io[i] = f2fs_kmalloc(sbi,
n * sizeof(struct f2fs_bio_info),
GFP_KERNEL);
sbi->write_io[i] =
f2fs_kmalloc(sbi,
array_size(n,
sizeof(struct f2fs_bio_info)),
GFP_KERNEL);
if (!sbi->write_io[i]) {
err = -ENOMEM;
goto free_options;
@ -2920,7 +2919,7 @@ try_onemore:
goto free_io_dummy;
}
err = get_valid_checkpoint(sbi);
err = f2fs_get_valid_checkpoint(sbi);
if (err) {
f2fs_msg(sb, KERN_ERR, "Failed to get valid F2FS checkpoint");
goto free_meta_inode;
@ -2950,18 +2949,18 @@ try_onemore:
spin_lock_init(&sbi->inode_lock[i]);
}
init_extent_cache_info(sbi);
f2fs_init_extent_cache_info(sbi);
init_ino_entry_info(sbi);
f2fs_init_ino_entry_info(sbi);
/* setup f2fs internal modules */
err = build_segment_manager(sbi);
err = f2fs_build_segment_manager(sbi);
if (err) {
f2fs_msg(sb, KERN_ERR,
"Failed to initialize F2FS segment manager");
goto free_sm;
}
err = build_node_manager(sbi);
err = f2fs_build_node_manager(sbi);
if (err) {
f2fs_msg(sb, KERN_ERR,
"Failed to initialize F2FS node manager");
@ -2979,7 +2978,7 @@ try_onemore:
sbi->kbytes_written =
le64_to_cpu(seg_i->journal->info.kbytes_written);
build_gc_manager(sbi);
f2fs_build_gc_manager(sbi);
err = f2fs_build_stats(sbi);
if (err)
@ -3031,7 +3030,7 @@ try_onemore:
}
#endif
/* if there are nt orphan nodes free them */
err = recover_orphan_inodes(sbi);
err = f2fs_recover_orphan_inodes(sbi);
if (err)
goto free_meta;
@ -3053,7 +3052,7 @@ try_onemore:
if (!retry)
goto skip_recovery;
err = recover_fsync_data(sbi, false);
err = f2fs_recover_fsync_data(sbi, false);
if (err < 0) {
need_fsck = true;
f2fs_msg(sb, KERN_ERR,
@ -3061,7 +3060,7 @@ try_onemore:
goto free_meta;
}
} else {
err = recover_fsync_data(sbi, true);
err = f2fs_recover_fsync_data(sbi, true);
if (!f2fs_readonly(sb) && err > 0) {
err = -EINVAL;
@ -3071,7 +3070,7 @@ try_onemore:
}
}
skip_recovery:
/* recover_fsync_data() cleared this already */
/* f2fs_recover_fsync_data() cleared this already */
clear_sbi_flag(sbi, SBI_POR_DOING);
/*
@ -3080,7 +3079,7 @@ skip_recovery:
*/
if (test_opt(sbi, BG_GC) && !f2fs_readonly(sb)) {
/* After POR, we can run background GC thread.*/
err = start_gc_thread(sbi);
err = f2fs_start_gc_thread(sbi);
if (err)
goto free_meta;
}
@ -3111,10 +3110,10 @@ free_meta:
#endif
f2fs_sync_inode_meta(sbi);
/*
* Some dirty meta pages can be produced by recover_orphan_inodes()
* Some dirty meta pages can be produced by f2fs_recover_orphan_inodes()
* failed by EIO. Then, iput(node_inode) can trigger balance_fs_bg()
* followed by write_checkpoint() through f2fs_write_node_pages(), which
* falls into an infinite loop in sync_meta_pages().
* followed by f2fs_write_checkpoint() through f2fs_write_node_pages(), which
* falls into an infinite loop in f2fs_sync_meta_pages().
*/
truncate_inode_pages_final(META_MAPPING(sbi));
/* cleanup recovery and quota inodes */
@ -3127,15 +3126,15 @@ free_root_inode:
dput(sb->s_root);
sb->s_root = NULL;
free_node_inode:
release_ino_entry(sbi, true);
f2fs_release_ino_entry(sbi, true);
truncate_inode_pages_final(NODE_MAPPING(sbi));
iput(sbi->node_inode);
free_stats:
f2fs_destroy_stats(sbi);
free_nm:
destroy_node_manager(sbi);
f2fs_destroy_node_manager(sbi);
free_sm:
destroy_segment_manager(sbi);
f2fs_destroy_segment_manager(sbi);
free_devices:
destroy_device_list(sbi);
kfree(sbi->ckpt);
@ -3180,8 +3179,8 @@ static void kill_f2fs_super(struct super_block *sb)
{
if (sb->s_root) {
set_sbi_flag(F2FS_SB(sb), SBI_IS_CLOSE);
stop_gc_thread(F2FS_SB(sb));
stop_discard_thread(F2FS_SB(sb));
f2fs_stop_gc_thread(F2FS_SB(sb));
f2fs_stop_discard_thread(F2FS_SB(sb));
}
kill_block_super(sb);
}
@ -3230,16 +3229,16 @@ static int __init init_f2fs_fs(void)
err = init_inodecache();
if (err)
goto fail;
err = create_node_manager_caches();
err = f2fs_create_node_manager_caches();
if (err)
goto free_inodecache;
err = create_segment_manager_caches();
err = f2fs_create_segment_manager_caches();
if (err)
goto free_node_manager_caches;
err = create_checkpoint_caches();
err = f2fs_create_checkpoint_caches();
if (err)
goto free_segment_manager_caches;
err = create_extent_cache();
err = f2fs_create_extent_cache();
if (err)
goto free_checkpoint_caches;
err = f2fs_init_sysfs();
@ -3268,13 +3267,13 @@ free_shrinker:
free_sysfs:
f2fs_exit_sysfs();
free_extent_cache:
destroy_extent_cache();
f2fs_destroy_extent_cache();
free_checkpoint_caches:
destroy_checkpoint_caches();
f2fs_destroy_checkpoint_caches();
free_segment_manager_caches:
destroy_segment_manager_caches();
f2fs_destroy_segment_manager_caches();
free_node_manager_caches:
destroy_node_manager_caches();
f2fs_destroy_node_manager_caches();
free_inodecache:
destroy_inodecache();
fail:
@ -3288,10 +3287,10 @@ static void __exit exit_f2fs_fs(void)
unregister_filesystem(&f2fs_fs_type);
unregister_shrinker(&f2fs_shrinker_info);
f2fs_exit_sysfs();
destroy_extent_cache();
destroy_checkpoint_caches();
destroy_segment_manager_caches();
destroy_node_manager_caches();
f2fs_destroy_extent_cache();
f2fs_destroy_checkpoint_caches();
f2fs_destroy_segment_manager_caches();
f2fs_destroy_node_manager_caches();
destroy_inodecache();
f2fs_destroy_trace_ios();
}

60
fs/f2fs/sysfs.c
View File

@ -148,13 +148,13 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
int len = 0, i;
len += snprintf(buf + len, PAGE_SIZE - len,
"cold file extenstion:\n");
"cold file extension:\n");
for (i = 0; i < cold_count; i++)
len += snprintf(buf + len, PAGE_SIZE - len, "%s\n",
extlist[i]);
len += snprintf(buf + len, PAGE_SIZE - len,
"hot file extenstion:\n");
"hot file extension:\n");
for (i = cold_count; i < cold_count + hot_count; i++)
len += snprintf(buf + len, PAGE_SIZE - len, "%s\n",
extlist[i]);
@ -166,7 +166,7 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
}
static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
static ssize_t __sbi_store(struct f2fs_attr *a,
struct f2fs_sb_info *sbi,
const char *buf, size_t count)
{
@ -202,13 +202,13 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
down_write(&sbi->sb_lock);
ret = update_extension_list(sbi, name, hot, set);
ret = f2fs_update_extension_list(sbi, name, hot, set);
if (ret)
goto out;
ret = f2fs_commit_super(sbi, false);
if (ret)
update_extension_list(sbi, name, hot, !set);
f2fs_update_extension_list(sbi, name, hot, !set);
out:
up_write(&sbi->sb_lock);
return ret ? ret : count;
@ -249,19 +249,53 @@ out:
if (!strcmp(a->attr.name, "trim_sections"))
return -EINVAL;
if (!strcmp(a->attr.name, "gc_urgent")) {
if (t >= 1) {
sbi->gc_mode = GC_URGENT;
if (sbi->gc_thread) {
wake_up_interruptible_all(
&sbi->gc_thread->gc_wait_queue_head);
wake_up_discard_thread(sbi, true);
}
} else {
sbi->gc_mode = GC_NORMAL;
}
return count;
}
if (!strcmp(a->attr.name, "gc_idle")) {
if (t == GC_IDLE_CB)
sbi->gc_mode = GC_IDLE_CB;
else if (t == GC_IDLE_GREEDY)
sbi->gc_mode = GC_IDLE_GREEDY;
else
sbi->gc_mode = GC_NORMAL;
return count;
}
*ui = t;
if (!strcmp(a->attr.name, "iostat_enable") && *ui == 0)
f2fs_reset_iostat(sbi);
if (!strcmp(a->attr.name, "gc_urgent") && t == 1 && sbi->gc_thread) {
sbi->gc_thread->gc_wake = 1;
wake_up_interruptible_all(&sbi->gc_thread->gc_wait_queue_head);
wake_up_discard_thread(sbi, true);
}
return count;
}
static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
struct f2fs_sb_info *sbi,
const char *buf, size_t count)
{
ssize_t ret;
bool gc_entry = (!strcmp(a->attr.name, "gc_urgent") ||
a->struct_type == GC_THREAD);
if (gc_entry)
down_read(&sbi->sb->s_umount);
ret = __sbi_store(a, sbi, buf, count);
if (gc_entry)
up_read(&sbi->sb->s_umount);
return ret;
}
static ssize_t f2fs_attr_show(struct kobject *kobj,
struct attribute *attr, char *buf)
{
@ -350,8 +384,8 @@ F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_urgent_sleep_time,
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time);
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time);
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle);
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_urgent, gc_urgent);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_idle, gc_mode);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_urgent, gc_mode);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, max_small_discards, max_discards);
F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, discard_granularity, discard_granularity);

26
fs/f2fs/xattr.c
View File

@ -252,7 +252,7 @@ static int read_inline_xattr(struct inode *inode, struct page *ipage,
if (ipage) {
inline_addr = inline_xattr_addr(inode, ipage);
} else {
page = get_node_page(sbi, inode->i_ino);
page = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(page))
return PTR_ERR(page);
@ -273,7 +273,7 @@ static int read_xattr_block(struct inode *inode, void *txattr_addr)
void *xattr_addr;
/* The inode already has an extended attribute block. */
xpage = get_node_page(sbi, xnid);
xpage = f2fs_get_node_page(sbi, xnid);
if (IS_ERR(xpage))
return PTR_ERR(xpage);
@ -397,7 +397,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
int err = 0;
if (hsize > inline_size && !F2FS_I(inode)->i_xattr_nid)
if (!alloc_nid(sbi, &new_nid))
if (!f2fs_alloc_nid(sbi, &new_nid))
return -ENOSPC;
/* write to inline xattr */
@ -405,9 +405,9 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
if (ipage) {
inline_addr = inline_xattr_addr(inode, ipage);
} else {
in_page = get_node_page(sbi, inode->i_ino);
in_page = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(in_page)) {
alloc_nid_failed(sbi, new_nid);
f2fs_alloc_nid_failed(sbi, new_nid);
return PTR_ERR(in_page);
}
inline_addr = inline_xattr_addr(inode, in_page);
@ -417,8 +417,8 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
NODE, true);
/* no need to use xattr node block */
if (hsize <= inline_size) {
err = truncate_xattr_node(inode);
alloc_nid_failed(sbi, new_nid);
err = f2fs_truncate_xattr_node(inode);
f2fs_alloc_nid_failed(sbi, new_nid);
if (err) {
f2fs_put_page(in_page, 1);
return err;
@ -431,10 +431,10 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
/* write to xattr node block */
if (F2FS_I(inode)->i_xattr_nid) {
xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
xpage = f2fs_get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
if (IS_ERR(xpage)) {
err = PTR_ERR(xpage);
alloc_nid_failed(sbi, new_nid);
f2fs_alloc_nid_failed(sbi, new_nid);
goto in_page_out;
}
f2fs_bug_on(sbi, new_nid);
@ -442,13 +442,13 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
} else {
struct dnode_of_data dn;
set_new_dnode(&dn, inode, NULL, NULL, new_nid);
xpage = new_node_page(&dn, XATTR_NODE_OFFSET);
xpage = f2fs_new_node_page(&dn, XATTR_NODE_OFFSET);
if (IS_ERR(xpage)) {
err = PTR_ERR(xpage);
alloc_nid_failed(sbi, new_nid);
f2fs_alloc_nid_failed(sbi, new_nid);
goto in_page_out;
}
alloc_nid_done(sbi, new_nid);
f2fs_alloc_nid_done(sbi, new_nid);
}
xattr_addr = page_address(xpage);
@ -693,7 +693,7 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name,
if (err)
return err;
/* this case is only from init_inode_metadata */
/* this case is only from f2fs_init_inode_metadata */
if (ipage)
return __f2fs_setxattr(inode, index, name, value,
size, ipage, flags);

20
fs/gfs2/aops.c
View File

@ -280,22 +280,6 @@ static int gfs2_write_jdata_pagevec(struct address_space *mapping,
for(i = 0; i < nr_pages; i++) {
struct page *page = pvec->pages[i];
/*
* At this point, the page may be truncated or
* invalidated (changing page->mapping to NULL), or
* even swizzled back from swapper_space to tmpfs file
* mapping. However, page->index will not change
* because we have a reference on the page.
*/
if (page->index > end) {
/*
* can't be range_cyclic (1st pass) because
* end == -1 in that case.
*/
ret = 1;
break;
}
*done_index = page->index;
lock_page(page);
@ -413,8 +397,8 @@ retry:
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && (index <= end)) {
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
tag);
if (nr_pages == 0)
break;

4
fs/nilfs2/btree.c
View File

@ -2158,8 +2158,8 @@ static void nilfs_btree_lookup_dirty_buffers(struct nilfs_bmap *btree,
pagevec_init(&pvec, 0);
while (pagevec_lookup_tag(&pvec, btcache, &index, PAGECACHE_TAG_DIRTY,
PAGEVEC_SIZE)) {
while (pagevec_lookup_tag(&pvec, btcache, &index,
PAGECACHE_TAG_DIRTY)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
bh = head = page_buffers(pvec.pages[i]);
do {

7
fs/nilfs2/page.c
View File

@ -257,8 +257,7 @@ int nilfs_copy_dirty_pages(struct address_space *dmap,
pagevec_init(&pvec, 0);
repeat:
if (!pagevec_lookup_tag(&pvec, smap, &index, PAGECACHE_TAG_DIRTY,
PAGEVEC_SIZE))
if (!pagevec_lookup_tag(&pvec, smap, &index, PAGECACHE_TAG_DIRTY))
return 0;
for (i = 0; i < pagevec_count(&pvec); i++) {
@ -376,8 +375,8 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent)
pagevec_init(&pvec, 0);
while (pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY,
PAGEVEC_SIZE)) {
while (pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_DIRTY)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];

12
fs/nilfs2/segment.c
View File

@ -711,18 +711,14 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode,
pagevec_init(&pvec, 0);
repeat:
if (unlikely(index > last) ||
!pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY,
min_t(pgoff_t, last - index,
PAGEVEC_SIZE - 1) + 1))
!pagevec_lookup_range_tag(&pvec, mapping, &index, last,
PAGECACHE_TAG_DIRTY))
return ndirties;
for (i = 0; i < pagevec_count(&pvec); i++) {
struct buffer_head *bh, *head;
struct page *page = pvec.pages[i];
if (unlikely(page->index > last))
break;
lock_page(page);
if (!page_has_buffers(page))
create_empty_buffers(page, i_blocksize(inode), 0);
@ -759,8 +755,8 @@ static void nilfs_lookup_dirty_node_buffers(struct inode *inode,
pagevec_init(&pvec, 0);
while (pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY,
PAGEVEC_SIZE)) {
while (pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_DIRTY)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
bh = head = page_buffers(pvec.pages[i]);
do {

10
fs/ubifs/crypto.c
View File

@ -24,14 +24,6 @@ static bool ubifs_crypt_empty_dir(struct inode *inode)
return ubifs_check_dir_empty(inode) == 0;
}
static unsigned int ubifs_crypt_max_namelen(struct inode *inode)
{
if (S_ISLNK(inode->i_mode))
return UBIFS_MAX_INO_DATA;
else
return UBIFS_MAX_NLEN;
}
int ubifs_encrypt(const struct inode *inode, struct ubifs_data_node *dn,
unsigned int in_len, unsigned int *out_len, int block)
{
@ -89,5 +81,5 @@ const struct fscrypt_operations ubifs_crypt_operations = {
.get_context = ubifs_crypt_get_context,
.set_context = ubifs_crypt_set_context,
.empty_dir = ubifs_crypt_empty_dir,
.max_namelen = ubifs_crypt_max_namelen,
.max_namelen = UBIFS_MAX_NLEN,
};

17
fs/ubifs/dir.c
View File

@ -220,20 +220,9 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
dbg_gen("'%pd' in dir ino %lu", dentry, dir->i_ino);
if (ubifs_crypt_is_encrypted(dir)) {
err = fscrypt_get_encryption_info(dir);
/*
* DCACHE_ENCRYPTED_WITH_KEY is set if the dentry is
* created while the directory was encrypted and we
* have access to the key.
*/
if (fscrypt_has_encryption_key(dir))
fscrypt_set_encrypted_dentry(dentry);
fscrypt_set_d_op(dentry);
if (err && err != -ENOKEY)
return ERR_PTR(err);
}
err = fscrypt_prepare_lookup(dir, dentry, flags);
if (err)
return ERR_PTR(err);
err = fscrypt_setup_filename(dir, &dentry->d_name, 1, &nm);
if (err)

10
include/linux/fscrypt_notsupp.h
View File

@ -68,16 +68,6 @@ static inline void fscrypt_restore_control_page(struct page *page)
return;
}
static inline void fscrypt_set_d_op(struct dentry *dentry)
{
return;
}
static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry)
{
return;
}
/* policy.c */
static inline int fscrypt_ioctl_set_policy(struct file *filp,
const void __user *arg)

16
include/linux/fscrypt_supp.h
View File

@ -29,7 +29,7 @@ struct fscrypt_operations {
int (*set_context)(struct inode *, const void *, size_t, void *);
bool (*dummy_context)(struct inode *);
bool (*empty_dir)(struct inode *);
unsigned (*max_namelen)(struct inode *);
unsigned int max_namelen;
bool (*is_encrypted)(struct inode *);
};
@ -76,20 +76,6 @@ static inline struct page *fscrypt_control_page(struct page *page)
extern void fscrypt_restore_control_page(struct page *);
extern const struct dentry_operations fscrypt_d_ops;
static inline void fscrypt_set_d_op(struct dentry *dentry)
{
d_set_d_op(dentry, &fscrypt_d_ops);
}
static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry)
{
spin_lock(&dentry->d_lock);
dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY;
spin_unlock(&dentry->d_lock);
}
/* policy.c */
extern int fscrypt_ioctl_set_policy(struct file *, const void __user *);
extern int fscrypt_ioctl_get_policy(struct file *, void __user *);

73
include/linux/overflow.h
View File

@ -202,4 +202,77 @@
#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */
/**
* array_size() - Calculate size of 2-dimensional array.
*
* @a: dimension one
* @b: dimension two
*
* Calculates size of 2-dimensional array: @a * @b.
*
* Returns: number of bytes needed to represent the array or SIZE_MAX on
* overflow.
*/
static inline __must_check size_t array_size(size_t a, size_t b)
{
size_t bytes;
if (check_mul_overflow(a, b, &bytes))
return SIZE_MAX;
return bytes;
}
/**
* array3_size() - Calculate size of 3-dimensional array.
*
* @a: dimension one
* @b: dimension two
* @c: dimension three
*
* Calculates size of 3-dimensional array: @a * @b * @c.
*
* Returns: number of bytes needed to represent the array or SIZE_MAX on
* overflow.
*/
static inline __must_check size_t array3_size(size_t a, size_t b, size_t c)
{
size_t bytes;
if (check_mul_overflow(a, b, &bytes))
return SIZE_MAX;
if (check_mul_overflow(bytes, c, &bytes))
return SIZE_MAX;
return bytes;
}
static inline __must_check size_t __ab_c_size(size_t n, size_t size, size_t c)
{
size_t bytes;
if (check_mul_overflow(n, size, &bytes))
return SIZE_MAX;
if (check_add_overflow(bytes, c, &bytes))
return SIZE_MAX;
return bytes;
}
/**
* struct_size() - Calculate size of structure with trailing array.
* @p: Pointer to the structure.
* @member: Name of the array member.
* @n: Number of elements in the array.
*
* Calculates size of memory needed for structure @p followed by an
* array of @n @member elements.
*
* Return: number of bytes needed or SIZE_MAX on overflow.
*/
#define struct_size(p, member, n) \
__ab_c_size(n, \
sizeof(*(p)->member) + __must_be_array((p)->member),\
sizeof(*(p)))
#endif /* __LINUX_OVERFLOW_H */

12
include/linux/pagemap.h
View File

@ -366,8 +366,16 @@ static inline unsigned find_get_pages(struct address_space *mapping,
}
unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start,
unsigned int nr_pages, struct page **pages);
unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
int tag, unsigned int nr_pages, struct page **pages);
unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
pgoff_t end, int tag, unsigned int nr_pages,
struct page **pages);
static inline unsigned find_get_pages_tag(struct address_space *mapping,
pgoff_t *index, int tag, unsigned int nr_pages,
struct page **pages)
{
return find_get_pages_range_tag(mapping, index, (pgoff_t)-1, tag,
nr_pages, pages);
}
unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
int tag, unsigned int nr_entries,
struct page **entries, pgoff_t *indices);

14
include/linux/pagevec.h
View File

@ -38,9 +38,17 @@ static inline unsigned pagevec_lookup(struct pagevec *pvec,
return pagevec_lookup_range(pvec, mapping, start, (pgoff_t)-1);
}
unsigned pagevec_lookup_tag(struct pagevec *pvec,
struct address_space *mapping, pgoff_t *index, int tag,
unsigned nr_pages);
unsigned pagevec_lookup_range_tag(struct pagevec *pvec,
struct address_space *mapping, pgoff_t *index, pgoff_t end,
int tag);
unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec,
struct address_space *mapping, pgoff_t *index, pgoff_t end,
int tag, unsigned max_pages);
static inline unsigned pagevec_lookup_tag(struct pagevec *pvec,
struct address_space *mapping, pgoff_t *index, int tag)
{
return pagevec_lookup_range_tag(pvec, mapping, index, (pgoff_t)-1, tag);
}
static inline void pagevec_init(struct pagevec *pvec, int cold)
{

47
mm/filemap.c
View File

@ -424,19 +424,17 @@ static void __filemap_fdatawait_range(struct address_space *mapping,
return;
pagevec_init(&pvec, 0);
while ((index <= end) &&
(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_WRITEBACK,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1)) != 0) {
while (index <= end) {
unsigned i;
nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index,
end, PAGECACHE_TAG_WRITEBACK);
if (!nr_pages)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/* until radix tree lookup accepts end_index */
if (page->index > end)
continue;
wait_on_page_writeback(page);
ClearPageError(page);
}
@ -1757,9 +1755,10 @@ repeat:
EXPORT_SYMBOL(find_get_pages_contig);
/**
* find_get_pages_tag - find and return pages that match @tag
* find_get_pages_range_tag - find and return pages in given range matching @tag
* @mapping: the address_space to search
* @index: the starting page index
* @end: The final page index (inclusive)
* @tag: the tag index
* @nr_pages: the maximum number of pages
* @pages: where the resulting pages are placed
@ -1767,8 +1766,9 @@ EXPORT_SYMBOL(find_get_pages_contig);
* Like find_get_pages, except we only return pages which are tagged with
* @tag. We update @index to index the next page for the traversal.
*/
unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
int tag, unsigned int nr_pages, struct page **pages)
unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
pgoff_t end, int tag, unsigned int nr_pages,
struct page **pages)
{
struct radix_tree_iter iter;
void **slot;
@ -1781,6 +1781,9 @@ unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
radix_tree_for_each_tagged(slot, &mapping->page_tree,
&iter, *index, tag) {
struct page *head, *page;
if (iter.index > end)
break;
repeat:
page = radix_tree_deref_slot(slot);
if (unlikely(!page))
@ -1822,18 +1825,28 @@ repeat:
}
pages[ret] = page;
if (++ret == nr_pages)
break;
if (++ret == nr_pages) {
*index = pages[ret - 1]->index + 1;
goto out;
}
}
/*
* We come here when we got at @end. We take care to not overflow the
* index @index as it confuses some of the callers. This breaks the
* iteration when there is page at index -1 but that is already broken
* anyway.
*/
if (end == (pgoff_t)-1)
*index = (pgoff_t)-1;
else
*index = end + 1;
out:
rcu_read_unlock();
if (ret)
*index = pages[ret - 1]->index + 1;
return ret;
}
EXPORT_SYMBOL(find_get_pages_tag);
EXPORT_SYMBOL(find_get_pages_range_tag);
/**
* find_get_entries_tag - find and return entries that match @tag

20
mm/page-writeback.c
View File

@ -2195,30 +2195,14 @@ retry:
while (!done && (index <= end)) {
int i;
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
tag);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/*
* At this point, the page may be truncated or
* invalidated (changing page->mapping to NULL), or
* even swizzled back from swapper_space to tmpfs file
* mapping. However, page->index will not change
* because we have a reference on the page.
*/
if (page->index > end) {
/*
* can't be range_cyclic (1st pass) because
* end == -1 in that case.
*/
done = 1;
break;
}
done_index = page->index;
lock_page(page);

20
mm/swap.c
View File

@ -986,15 +986,25 @@ unsigned pagevec_lookup_range(struct pagevec *pvec,
}
EXPORT_SYMBOL(pagevec_lookup_range);
unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping,
pgoff_t *index, int tag, unsigned nr_pages)
unsigned pagevec_lookup_range_tag(struct pagevec *pvec,
struct address_space *mapping, pgoff_t *index, pgoff_t end,
int tag)
{
pvec->nr = find_get_pages_tag(mapping, index, tag,
nr_pages, pvec->pages);
pvec->nr = find_get_pages_range_tag(mapping, index, end, tag,
PAGEVEC_SIZE, pvec->pages);
return pagevec_count(pvec);
}
EXPORT_SYMBOL(pagevec_lookup_tag);
EXPORT_SYMBOL(pagevec_lookup_range_tag);
unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec,
struct address_space *mapping, pgoff_t *index, pgoff_t end,
int tag, unsigned max_pages)
{
pvec->nr = find_get_pages_range_tag(mapping, index, end, tag,
min_t(unsigned int, max_pages, PAGEVEC_SIZE), pvec->pages);
return pagevec_count(pvec);
}
EXPORT_SYMBOL(pagevec_lookup_range_nr_tag);
/*
* Perform any setup for the swap system
*/