linux/fs/cifs/file.c
Linus Torvalds f30adc0d33 iov_iter stuff, part 2, rebased
* more new_sync_{read,write}() speedups - ITER_UBUF introduction
 * ITER_PIPE cleanups
 * unification of iov_iter_get_pages/iov_iter_get_pages_alloc and
   switching them to advancing semantics
 * making ITER_PIPE take high-order pages without splitting them
 * handling copy_page_from_iter() for high-order pages properly
 
 Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQQqUNBr3gm4hGXdBJlZ7Krx/gZQ6wUCYvHI8QAKCRBZ7Krx/gZQ
 62CQAPsGlbebqBeAT2pMulaGDxfLAsgz5Yf4BEaMLhPtRqFOQgD+KrZQId7Sd8O0
 3IWucpTb2c4jvLlXhGMS+XWnusQH+AQ=
 =pBux
 -----END PGP SIGNATURE-----

Merge tag 'pull-work.iov_iter-rebased' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull more iov_iter updates from Al Viro:

 - more new_sync_{read,write}() speedups - ITER_UBUF introduction

 - ITER_PIPE cleanups

 - unification of iov_iter_get_pages/iov_iter_get_pages_alloc and
   switching them to advancing semantics

 - making ITER_PIPE take high-order pages without splitting them

 - handling copy_page_from_iter() for high-order pages properly

* tag 'pull-work.iov_iter-rebased' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (32 commits)
  fix copy_page_from_iter() for compound destinations
  hugetlbfs: copy_page_to_iter() can deal with compound pages
  copy_page_to_iter(): don't split high-order page in case of ITER_PIPE
  expand those iov_iter_advance()...
  pipe_get_pages(): switch to append_pipe()
  get rid of non-advancing variants
  ceph: switch the last caller of iov_iter_get_pages_alloc()
  9p: convert to advancing variant of iov_iter_get_pages_alloc()
  af_alg_make_sg(): switch to advancing variant of iov_iter_get_pages()
  iter_to_pipe(): switch to advancing variant of iov_iter_get_pages()
  block: convert to advancing variants of iov_iter_get_pages{,_alloc}()
  iov_iter: advancing variants of iov_iter_get_pages{,_alloc}()
  iov_iter: saner helper for page array allocation
  fold __pipe_get_pages() into pipe_get_pages()
  ITER_XARRAY: don't open-code DIV_ROUND_UP()
  unify the rest of iov_iter_get_pages()/iov_iter_get_pages_alloc() guts
  unify xarray_get_pages() and xarray_get_pages_alloc()
  unify pipe_get_pages() and pipe_get_pages_alloc()
  iov_iter_get_pages(): sanity-check arguments
  iov_iter_get_pages_alloc(): lift freeing pages array on failure exits into wrapper
  ...
2022-08-08 20:04:35 -07:00

5266 lines
134 KiB
C

// SPDX-License-Identifier: LGPL-2.1
/*
*
* vfs operations that deal with files
*
* Copyright (C) International Business Machines Corp., 2002,2010
* Author(s): Steve French (sfrench@us.ibm.com)
* Jeremy Allison (jra@samba.org)
*
*/
#include <linux/fs.h>
#include <linux/backing-dev.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/writeback.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/delay.h>
#include <linux/mount.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/mm.h>
#include <asm/div64.h>
#include "cifsfs.h"
#include "cifspdu.h"
#include "cifsglob.h"
#include "cifsproto.h"
#include "smb2proto.h"
#include "cifs_unicode.h"
#include "cifs_debug.h"
#include "cifs_fs_sb.h"
#include "fscache.h"
#include "smbdirect.h"
#include "fs_context.h"
#include "cifs_ioctl.h"
/*
* Mark as invalid, all open files on tree connections since they
* were closed when session to server was lost.
*/
void
cifs_mark_open_files_invalid(struct cifs_tcon *tcon)
{
struct cifsFileInfo *open_file = NULL;
struct list_head *tmp;
struct list_head *tmp1;
/* only send once per connect */
spin_lock(&tcon->ses->ses_lock);
if ((tcon->ses->ses_status != SES_GOOD) || (tcon->status != TID_NEED_RECON)) {
spin_unlock(&tcon->ses->ses_lock);
return;
}
tcon->status = TID_IN_FILES_INVALIDATE;
spin_unlock(&tcon->ses->ses_lock);
/* list all files open on tree connection and mark them invalid */
spin_lock(&tcon->open_file_lock);
list_for_each_safe(tmp, tmp1, &tcon->openFileList) {
open_file = list_entry(tmp, struct cifsFileInfo, tlist);
open_file->invalidHandle = true;
open_file->oplock_break_cancelled = true;
}
spin_unlock(&tcon->open_file_lock);
mutex_lock(&tcon->crfid.fid_mutex);
tcon->crfid.is_valid = false;
/* cached handle is not valid, so SMB2_CLOSE won't be sent below */
close_cached_dir_lease_locked(&tcon->crfid);
memset(tcon->crfid.fid, 0, sizeof(struct cifs_fid));
mutex_unlock(&tcon->crfid.fid_mutex);
spin_lock(&tcon->tc_lock);
if (tcon->status == TID_IN_FILES_INVALIDATE)
tcon->status = TID_NEED_TCON;
spin_unlock(&tcon->tc_lock);
/*
* BB Add call to invalidate_inodes(sb) for all superblocks mounted
* to this tcon.
*/
}
static inline int cifs_convert_flags(unsigned int flags)
{
if ((flags & O_ACCMODE) == O_RDONLY)
return GENERIC_READ;
else if ((flags & O_ACCMODE) == O_WRONLY)
return GENERIC_WRITE;
else if ((flags & O_ACCMODE) == O_RDWR) {
/* GENERIC_ALL is too much permission to request
can cause unnecessary access denied on create */
/* return GENERIC_ALL; */
return (GENERIC_READ | GENERIC_WRITE);
}
return (READ_CONTROL | FILE_WRITE_ATTRIBUTES | FILE_READ_ATTRIBUTES |
FILE_WRITE_EA | FILE_APPEND_DATA | FILE_WRITE_DATA |
FILE_READ_DATA);
}
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
static u32 cifs_posix_convert_flags(unsigned int flags)
{
u32 posix_flags = 0;
if ((flags & O_ACCMODE) == O_RDONLY)
posix_flags = SMB_O_RDONLY;
else if ((flags & O_ACCMODE) == O_WRONLY)
posix_flags = SMB_O_WRONLY;
else if ((flags & O_ACCMODE) == O_RDWR)
posix_flags = SMB_O_RDWR;
if (flags & O_CREAT) {
posix_flags |= SMB_O_CREAT;
if (flags & O_EXCL)
posix_flags |= SMB_O_EXCL;
} else if (flags & O_EXCL)
cifs_dbg(FYI, "Application %s pid %d has incorrectly set O_EXCL flag but not O_CREAT on file open. Ignoring O_EXCL\n",
current->comm, current->tgid);
if (flags & O_TRUNC)
posix_flags |= SMB_O_TRUNC;
/* be safe and imply O_SYNC for O_DSYNC */
if (flags & O_DSYNC)
posix_flags |= SMB_O_SYNC;
if (flags & O_DIRECTORY)
posix_flags |= SMB_O_DIRECTORY;
if (flags & O_NOFOLLOW)
posix_flags |= SMB_O_NOFOLLOW;
if (flags & O_DIRECT)
posix_flags |= SMB_O_DIRECT;
return posix_flags;
}
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
static inline int cifs_get_disposition(unsigned int flags)
{
if ((flags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
return FILE_CREATE;
else if ((flags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC))
return FILE_OVERWRITE_IF;
else if ((flags & O_CREAT) == O_CREAT)
return FILE_OPEN_IF;
else if ((flags & O_TRUNC) == O_TRUNC)
return FILE_OVERWRITE;
else
return FILE_OPEN;
}
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
int cifs_posix_open(const char *full_path, struct inode **pinode,
struct super_block *sb, int mode, unsigned int f_flags,
__u32 *poplock, __u16 *pnetfid, unsigned int xid)
{
int rc;
FILE_UNIX_BASIC_INFO *presp_data;
__u32 posix_flags = 0;
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
struct cifs_fattr fattr;
struct tcon_link *tlink;
struct cifs_tcon *tcon;
cifs_dbg(FYI, "posix open %s\n", full_path);
presp_data = kzalloc(sizeof(FILE_UNIX_BASIC_INFO), GFP_KERNEL);
if (presp_data == NULL)
return -ENOMEM;
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink)) {
rc = PTR_ERR(tlink);
goto posix_open_ret;
}
tcon = tlink_tcon(tlink);
mode &= ~current_umask();
posix_flags = cifs_posix_convert_flags(f_flags);
rc = CIFSPOSIXCreate(xid, tcon, posix_flags, mode, pnetfid, presp_data,
poplock, full_path, cifs_sb->local_nls,
cifs_remap(cifs_sb));
cifs_put_tlink(tlink);
if (rc)
goto posix_open_ret;
if (presp_data->Type == cpu_to_le32(-1))
goto posix_open_ret; /* open ok, caller does qpathinfo */
if (!pinode)
goto posix_open_ret; /* caller does not need info */
cifs_unix_basic_to_fattr(&fattr, presp_data, cifs_sb);
/* get new inode and set it up */
if (*pinode == NULL) {
cifs_fill_uniqueid(sb, &fattr);
*pinode = cifs_iget(sb, &fattr);
if (!*pinode) {
rc = -ENOMEM;
goto posix_open_ret;
}
} else {
cifs_revalidate_mapping(*pinode);
rc = cifs_fattr_to_inode(*pinode, &fattr);
}
posix_open_ret:
kfree(presp_data);
return rc;
}
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
static int
cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb,
struct cifs_tcon *tcon, unsigned int f_flags, __u32 *oplock,
struct cifs_fid *fid, unsigned int xid)
{
int rc;
int desired_access;
int disposition;
int create_options = CREATE_NOT_DIR;
FILE_ALL_INFO *buf;
struct TCP_Server_Info *server = tcon->ses->server;
struct cifs_open_parms oparms;
if (!server->ops->open)
return -ENOSYS;
desired_access = cifs_convert_flags(f_flags);
/*********************************************************************
* open flag mapping table:
*
* POSIX Flag CIFS Disposition
* ---------- ----------------
* O_CREAT FILE_OPEN_IF
* O_CREAT | O_EXCL FILE_CREATE
* O_CREAT | O_TRUNC FILE_OVERWRITE_IF
* O_TRUNC FILE_OVERWRITE
* none of the above FILE_OPEN
*
* Note that there is not a direct match between disposition
* FILE_SUPERSEDE (ie create whether or not file exists although
* O_CREAT | O_TRUNC is similar but truncates the existing
* file rather than creating a new file as FILE_SUPERSEDE does
* (which uses the attributes / metadata passed in on open call)
*?
*? O_SYNC is a reasonable match to CIFS writethrough flag
*? and the read write flags match reasonably. O_LARGEFILE
*? is irrelevant because largefile support is always used
*? by this client. Flags O_APPEND, O_DIRECT, O_DIRECTORY,
* O_FASYNC, O_NOFOLLOW, O_NONBLOCK need further investigation
*********************************************************************/
disposition = cifs_get_disposition(f_flags);
/* BB pass O_SYNC flag through on file attributes .. BB */
buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
if (!buf)
return -ENOMEM;
/* O_SYNC also has bit for O_DSYNC so following check picks up either */
if (f_flags & O_SYNC)
create_options |= CREATE_WRITE_THROUGH;
if (f_flags & O_DIRECT)
create_options |= CREATE_NO_BUFFER;
oparms.tcon = tcon;
oparms.cifs_sb = cifs_sb;
oparms.desired_access = desired_access;
oparms.create_options = cifs_create_options(cifs_sb, create_options);
oparms.disposition = disposition;
oparms.path = full_path;
oparms.fid = fid;
oparms.reconnect = false;
rc = server->ops->open(xid, &oparms, oplock, buf);
if (rc)
goto out;
/* TODO: Add support for calling posix query info but with passing in fid */
if (tcon->unix_ext)
rc = cifs_get_inode_info_unix(&inode, full_path, inode->i_sb,
xid);
else
rc = cifs_get_inode_info(&inode, full_path, buf, inode->i_sb,
xid, fid);
if (rc) {
server->ops->close(xid, tcon, fid);
if (rc == -ESTALE)
rc = -EOPENSTALE;
}
out:
kfree(buf);
return rc;
}
static bool
cifs_has_mand_locks(struct cifsInodeInfo *cinode)
{
struct cifs_fid_locks *cur;
bool has_locks = false;
down_read(&cinode->lock_sem);
list_for_each_entry(cur, &cinode->llist, llist) {
if (!list_empty(&cur->locks)) {
has_locks = true;
break;
}
}
up_read(&cinode->lock_sem);
return has_locks;
}
void
cifs_down_write(struct rw_semaphore *sem)
{
while (!down_write_trylock(sem))
msleep(10);
}
static void cifsFileInfo_put_work(struct work_struct *work);
struct cifsFileInfo *
cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
struct tcon_link *tlink, __u32 oplock)
{
struct dentry *dentry = file_dentry(file);
struct inode *inode = d_inode(dentry);
struct cifsInodeInfo *cinode = CIFS_I(inode);
struct cifsFileInfo *cfile;
struct cifs_fid_locks *fdlocks;
struct cifs_tcon *tcon = tlink_tcon(tlink);
struct TCP_Server_Info *server = tcon->ses->server;
cfile = kzalloc(sizeof(struct cifsFileInfo), GFP_KERNEL);
if (cfile == NULL)
return cfile;
fdlocks = kzalloc(sizeof(struct cifs_fid_locks), GFP_KERNEL);
if (!fdlocks) {
kfree(cfile);
return NULL;
}
INIT_LIST_HEAD(&fdlocks->locks);
fdlocks->cfile = cfile;
cfile->llist = fdlocks;
cfile->count = 1;
cfile->pid = current->tgid;
cfile->uid = current_fsuid();
cfile->dentry = dget(dentry);
cfile->f_flags = file->f_flags;
cfile->invalidHandle = false;
cfile->deferred_close_scheduled = false;
cfile->tlink = cifs_get_tlink(tlink);
INIT_WORK(&cfile->oplock_break, cifs_oplock_break);
INIT_WORK(&cfile->put, cifsFileInfo_put_work);
INIT_DELAYED_WORK(&cfile->deferred, smb2_deferred_work_close);
mutex_init(&cfile->fh_mutex);
spin_lock_init(&cfile->file_info_lock);
cifs_sb_active(inode->i_sb);
/*
* If the server returned a read oplock and we have mandatory brlocks,
* set oplock level to None.
*/
if (server->ops->is_read_op(oplock) && cifs_has_mand_locks(cinode)) {
cifs_dbg(FYI, "Reset oplock val from read to None due to mand locks\n");
oplock = 0;
}
cifs_down_write(&cinode->lock_sem);
list_add(&fdlocks->llist, &cinode->llist);
up_write(&cinode->lock_sem);
spin_lock(&tcon->open_file_lock);
if (fid->pending_open->oplock != CIFS_OPLOCK_NO_CHANGE && oplock)
oplock = fid->pending_open->oplock;
list_del(&fid->pending_open->olist);
fid->purge_cache = false;
server->ops->set_fid(cfile, fid, oplock);
list_add(&cfile->tlist, &tcon->openFileList);
atomic_inc(&tcon->num_local_opens);
/* if readable file instance put first in list*/
spin_lock(&cinode->open_file_lock);
if (file->f_mode & FMODE_READ)
list_add(&cfile->flist, &cinode->openFileList);
else
list_add_tail(&cfile->flist, &cinode->openFileList);
spin_unlock(&cinode->open_file_lock);
spin_unlock(&tcon->open_file_lock);
if (fid->purge_cache)
cifs_zap_mapping(inode);
file->private_data = cfile;
return cfile;
}
struct cifsFileInfo *
cifsFileInfo_get(struct cifsFileInfo *cifs_file)
{
spin_lock(&cifs_file->file_info_lock);
cifsFileInfo_get_locked(cifs_file);
spin_unlock(&cifs_file->file_info_lock);
return cifs_file;
}
static void cifsFileInfo_put_final(struct cifsFileInfo *cifs_file)
{
struct inode *inode = d_inode(cifs_file->dentry);
struct cifsInodeInfo *cifsi = CIFS_I(inode);
struct cifsLockInfo *li, *tmp;
struct super_block *sb = inode->i_sb;
/*
* Delete any outstanding lock records. We'll lose them when the file
* is closed anyway.
*/
cifs_down_write(&cifsi->lock_sem);
list_for_each_entry_safe(li, tmp, &cifs_file->llist->locks, llist) {
list_del(&li->llist);
cifs_del_lock_waiters(li);
kfree(li);
}
list_del(&cifs_file->llist->llist);
kfree(cifs_file->llist);
up_write(&cifsi->lock_sem);
cifs_put_tlink(cifs_file->tlink);
dput(cifs_file->dentry);
cifs_sb_deactive(sb);
kfree(cifs_file);
}
static void cifsFileInfo_put_work(struct work_struct *work)
{
struct cifsFileInfo *cifs_file = container_of(work,
struct cifsFileInfo, put);
cifsFileInfo_put_final(cifs_file);
}
/**
* cifsFileInfo_put - release a reference of file priv data
*
* Always potentially wait for oplock handler. See _cifsFileInfo_put().
*
* @cifs_file: cifs/smb3 specific info (eg refcounts) for an open file
*/
void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
{
_cifsFileInfo_put(cifs_file, true, true);
}
/**
* _cifsFileInfo_put - release a reference of file priv data
*
* This may involve closing the filehandle @cifs_file out on the
* server. Must be called without holding tcon->open_file_lock,
* cinode->open_file_lock and cifs_file->file_info_lock.
*
* If @wait_for_oplock_handler is true and we are releasing the last
* reference, wait for any running oplock break handler of the file
* and cancel any pending one.
*
* @cifs_file: cifs/smb3 specific info (eg refcounts) for an open file
* @wait_oplock_handler: must be false if called from oplock_break_handler
* @offload: not offloaded on close and oplock breaks
*
*/
void _cifsFileInfo_put(struct cifsFileInfo *cifs_file,
bool wait_oplock_handler, bool offload)
{
struct inode *inode = d_inode(cifs_file->dentry);
struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink);
struct TCP_Server_Info *server = tcon->ses->server;
struct cifsInodeInfo *cifsi = CIFS_I(inode);
struct super_block *sb = inode->i_sb;
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
struct cifs_fid fid;
struct cifs_pending_open open;
bool oplock_break_cancelled;
spin_lock(&tcon->open_file_lock);
spin_lock(&cifsi->open_file_lock);
spin_lock(&cifs_file->file_info_lock);
if (--cifs_file->count > 0) {
spin_unlock(&cifs_file->file_info_lock);
spin_unlock(&cifsi->open_file_lock);
spin_unlock(&tcon->open_file_lock);
return;
}
spin_unlock(&cifs_file->file_info_lock);
if (server->ops->get_lease_key)
server->ops->get_lease_key(inode, &fid);
/* store open in pending opens to make sure we don't miss lease break */
cifs_add_pending_open_locked(&fid, cifs_file->tlink, &open);
/* remove it from the lists */
list_del(&cifs_file->flist);
list_del(&cifs_file->tlist);
atomic_dec(&tcon->num_local_opens);
if (list_empty(&cifsi->openFileList)) {
cifs_dbg(FYI, "closing last open instance for inode %p\n",
d_inode(cifs_file->dentry));
/*
* In strict cache mode we need invalidate mapping on the last
* close because it may cause a error when we open this file
* again and get at least level II oplock.
*/
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO)
set_bit(CIFS_INO_INVALID_MAPPING, &cifsi->flags);
cifs_set_oplock_level(cifsi, 0);
}
spin_unlock(&cifsi->open_file_lock);
spin_unlock(&tcon->open_file_lock);
oplock_break_cancelled = wait_oplock_handler ?
cancel_work_sync(&cifs_file->oplock_break) : false;
if (!tcon->need_reconnect && !cifs_file->invalidHandle) {
struct TCP_Server_Info *server = tcon->ses->server;
unsigned int xid;
xid = get_xid();
if (server->ops->close_getattr)
server->ops->close_getattr(xid, tcon, cifs_file);
else if (server->ops->close)
server->ops->close(xid, tcon, &cifs_file->fid);
_free_xid(xid);
}
if (oplock_break_cancelled)
cifs_done_oplock_break(cifsi);
cifs_del_pending_open(&open);
if (offload)
queue_work(fileinfo_put_wq, &cifs_file->put);
else
cifsFileInfo_put_final(cifs_file);
}
int cifs_open(struct inode *inode, struct file *file)
{
int rc = -EACCES;
unsigned int xid;
__u32 oplock;
struct cifs_sb_info *cifs_sb;
struct TCP_Server_Info *server;
struct cifs_tcon *tcon;
struct tcon_link *tlink;
struct cifsFileInfo *cfile = NULL;
void *page;
const char *full_path;
bool posix_open_ok = false;
struct cifs_fid fid;
struct cifs_pending_open open;
xid = get_xid();
cifs_sb = CIFS_SB(inode->i_sb);
if (unlikely(cifs_forced_shutdown(cifs_sb))) {
free_xid(xid);
return -EIO;
}
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink)) {
free_xid(xid);
return PTR_ERR(tlink);
}
tcon = tlink_tcon(tlink);
server = tcon->ses->server;
page = alloc_dentry_path();
full_path = build_path_from_dentry(file_dentry(file), page);
if (IS_ERR(full_path)) {
rc = PTR_ERR(full_path);
goto out;
}
cifs_dbg(FYI, "inode = 0x%p file flags are 0x%x for %s\n",
inode, file->f_flags, full_path);
if (file->f_flags & O_DIRECT &&
cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO) {
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
file->f_op = &cifs_file_direct_nobrl_ops;
else
file->f_op = &cifs_file_direct_ops;
}
/* Get the cached handle as SMB2 close is deferred */
rc = cifs_get_readable_path(tcon, full_path, &cfile);
if (rc == 0) {
if (file->f_flags == cfile->f_flags) {
file->private_data = cfile;
spin_lock(&CIFS_I(inode)->deferred_lock);
cifs_del_deferred_close(cfile);
spin_unlock(&CIFS_I(inode)->deferred_lock);
goto use_cache;
} else {
_cifsFileInfo_put(cfile, true, false);
}
}
if (server->oplocks)
oplock = REQ_OPLOCK;
else
oplock = 0;
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
if (!tcon->broken_posix_open && tcon->unix_ext &&
cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP &
le64_to_cpu(tcon->fsUnixInfo.Capability))) {
/* can not refresh inode info since size could be stale */
rc = cifs_posix_open(full_path, &inode, inode->i_sb,
cifs_sb->ctx->file_mode /* ignored */,
file->f_flags, &oplock, &fid.netfid, xid);
if (rc == 0) {
cifs_dbg(FYI, "posix open succeeded\n");
posix_open_ok = true;
} else if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) {
if (tcon->ses->serverNOS)
cifs_dbg(VFS, "server %s of type %s returned unexpected error on SMB posix open, disabling posix open support. Check if server update available.\n",
tcon->ses->ip_addr,
tcon->ses->serverNOS);
tcon->broken_posix_open = true;
} else if ((rc != -EIO) && (rc != -EREMOTE) &&
(rc != -EOPNOTSUPP)) /* path not found or net err */
goto out;
/*
* Else fallthrough to retry open the old way on network i/o
* or DFS errors.
*/
}
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
if (server->ops->get_lease_key)
server->ops->get_lease_key(inode, &fid);
cifs_add_pending_open(&fid, tlink, &open);
if (!posix_open_ok) {
if (server->ops->get_lease_key)
server->ops->get_lease_key(inode, &fid);
rc = cifs_nt_open(full_path, inode, cifs_sb, tcon,
file->f_flags, &oplock, &fid, xid);
if (rc) {
cifs_del_pending_open(&open);
goto out;
}
}
cfile = cifs_new_fileinfo(&fid, file, tlink, oplock);
if (cfile == NULL) {
if (server->ops->close)
server->ops->close(xid, tcon, &fid);
cifs_del_pending_open(&open);
rc = -ENOMEM;
goto out;
}
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
if ((oplock & CIFS_CREATE_ACTION) && !posix_open_ok && tcon->unix_ext) {
/*
* Time to set mode which we can not set earlier due to
* problems creating new read-only files.
*/
struct cifs_unix_set_info_args args = {
.mode = inode->i_mode,
.uid = INVALID_UID, /* no change */
.gid = INVALID_GID, /* no change */
.ctime = NO_CHANGE_64,
.atime = NO_CHANGE_64,
.mtime = NO_CHANGE_64,
.device = 0,
};
CIFSSMBUnixSetFileInfo(xid, tcon, &args, fid.netfid,
cfile->pid);
}
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
use_cache:
fscache_use_cookie(cifs_inode_cookie(file_inode(file)),
file->f_mode & FMODE_WRITE);
if (file->f_flags & O_DIRECT &&
(!((file->f_flags & O_ACCMODE) != O_RDONLY) ||
file->f_flags & O_APPEND))
cifs_invalidate_cache(file_inode(file),
FSCACHE_INVAL_DIO_WRITE);
out:
free_dentry_path(page);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
}
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
static int cifs_push_posix_locks(struct cifsFileInfo *cfile);
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
/*
* Try to reacquire byte range locks that were released when session
* to server was lost.
*/
static int
cifs_relock_file(struct cifsFileInfo *cfile)
{
struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
int rc = 0;
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb);
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
down_read_nested(&cinode->lock_sem, SINGLE_DEPTH_NESTING);
if (cinode->can_cache_brlcks) {
/* can cache locks - no need to relock */
up_read(&cinode->lock_sem);
return rc;
}
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
if (cap_unix(tcon->ses) &&
(CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
rc = cifs_push_posix_locks(cfile);
else
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
rc = tcon->ses->server->ops->push_mand_locks(cfile);
up_read(&cinode->lock_sem);
return rc;
}
static int
cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
{
int rc = -EACCES;
unsigned int xid;
__u32 oplock;
struct cifs_sb_info *cifs_sb;
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
struct cifsInodeInfo *cinode;
struct inode *inode;
void *page;
const char *full_path;
int desired_access;
int disposition = FILE_OPEN;
int create_options = CREATE_NOT_DIR;
struct cifs_open_parms oparms;
xid = get_xid();
mutex_lock(&cfile->fh_mutex);
if (!cfile->invalidHandle) {
mutex_unlock(&cfile->fh_mutex);
free_xid(xid);
return 0;
}
inode = d_inode(cfile->dentry);
cifs_sb = CIFS_SB(inode->i_sb);
tcon = tlink_tcon(cfile->tlink);
server = tcon->ses->server;
/*
* Can not grab rename sem here because various ops, including those
* that already have the rename sem can end up causing writepage to get
* called and if the server was down that means we end up here, and we
* can never tell if the caller already has the rename_sem.
*/
page = alloc_dentry_path();
full_path = build_path_from_dentry(cfile->dentry, page);
if (IS_ERR(full_path)) {
mutex_unlock(&cfile->fh_mutex);
free_dentry_path(page);
free_xid(xid);
return PTR_ERR(full_path);
}
cifs_dbg(FYI, "inode = 0x%p file flags 0x%x for %s\n",
inode, cfile->f_flags, full_path);
if (tcon->ses->server->oplocks)
oplock = REQ_OPLOCK;
else
oplock = 0;
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
if (tcon->unix_ext && cap_unix(tcon->ses) &&
(CIFS_UNIX_POSIX_PATH_OPS_CAP &
le64_to_cpu(tcon->fsUnixInfo.Capability))) {
/*
* O_CREAT, O_EXCL and O_TRUNC already had their effect on the
* original open. Must mask them off for a reopen.
*/
unsigned int oflags = cfile->f_flags &
~(O_CREAT | O_EXCL | O_TRUNC);
rc = cifs_posix_open(full_path, NULL, inode->i_sb,
cifs_sb->ctx->file_mode /* ignored */,
oflags, &oplock, &cfile->fid.netfid, xid);
if (rc == 0) {
cifs_dbg(FYI, "posix reopen succeeded\n");
oparms.reconnect = true;
goto reopen_success;
}
/*
* fallthrough to retry open the old way on errors, especially
* in the reconnect path it is important to retry hard
*/
}
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
desired_access = cifs_convert_flags(cfile->f_flags);
/* O_SYNC also has bit for O_DSYNC so following check picks up either */
if (cfile->f_flags & O_SYNC)
create_options |= CREATE_WRITE_THROUGH;
if (cfile->f_flags & O_DIRECT)
create_options |= CREATE_NO_BUFFER;
if (server->ops->get_lease_key)
server->ops->get_lease_key(inode, &cfile->fid);
oparms.tcon = tcon;
oparms.cifs_sb = cifs_sb;
oparms.desired_access = desired_access;
oparms.create_options = cifs_create_options(cifs_sb, create_options);
oparms.disposition = disposition;
oparms.path = full_path;
oparms.fid = &cfile->fid;
oparms.reconnect = true;
/*
* Can not refresh inode by passing in file_info buf to be returned by
* ops->open and then calling get_inode_info with returned buf since
* file might have write behind data that needs to be flushed and server
* version of file size can be stale. If we knew for sure that inode was
* not dirty locally we could do this.
*/
rc = server->ops->open(xid, &oparms, &oplock, NULL);
if (rc == -ENOENT && oparms.reconnect == false) {
/* durable handle timeout is expired - open the file again */
rc = server->ops->open(xid, &oparms, &oplock, NULL);
/* indicate that we need to relock the file */
oparms.reconnect = true;
}
if (rc) {
mutex_unlock(&cfile->fh_mutex);
cifs_dbg(FYI, "cifs_reopen returned 0x%x\n", rc);
cifs_dbg(FYI, "oplock: %d\n", oplock);
goto reopen_error_exit;
}
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
reopen_success:
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
cfile->invalidHandle = false;
mutex_unlock(&cfile->fh_mutex);
cinode = CIFS_I(inode);
if (can_flush) {
rc = filemap_write_and_wait(inode->i_mapping);
if (!is_interrupt_error(rc))
mapping_set_error(inode->i_mapping, rc);
if (tcon->posix_extensions)
rc = smb311_posix_get_inode_info(&inode, full_path, inode->i_sb, xid);
else if (tcon->unix_ext)
rc = cifs_get_inode_info_unix(&inode, full_path,
inode->i_sb, xid);
else
rc = cifs_get_inode_info(&inode, full_path, NULL,
inode->i_sb, xid, NULL);
}
/*
* Else we are writing out data to server already and could deadlock if
* we tried to flush data, and since we do not know if we have data that
* would invalidate the current end of file on the server we can not go
* to the server to get the new inode info.
*/
/*
* If the server returned a read oplock and we have mandatory brlocks,
* set oplock level to None.
*/
if (server->ops->is_read_op(oplock) && cifs_has_mand_locks(cinode)) {
cifs_dbg(FYI, "Reset oplock val from read to None due to mand locks\n");
oplock = 0;
}
server->ops->set_fid(cfile, &cfile->fid, oplock);
if (oparms.reconnect)
cifs_relock_file(cfile);
reopen_error_exit:
free_dentry_path(page);
free_xid(xid);
return rc;
}
void smb2_deferred_work_close(struct work_struct *work)
{
struct cifsFileInfo *cfile = container_of(work,
struct cifsFileInfo, deferred.work);
spin_lock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock);
cifs_del_deferred_close(cfile);
cfile->deferred_close_scheduled = false;
spin_unlock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock);
_cifsFileInfo_put(cfile, true, false);
}
int cifs_close(struct inode *inode, struct file *file)
{
struct cifsFileInfo *cfile;
struct cifsInodeInfo *cinode = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifs_deferred_close *dclose;
cifs_fscache_unuse_inode_cookie(inode, file->f_mode & FMODE_WRITE);
if (file->private_data != NULL) {
cfile = file->private_data;
file->private_data = NULL;
dclose = kmalloc(sizeof(struct cifs_deferred_close), GFP_KERNEL);
if ((cinode->oplock == CIFS_CACHE_RHW_FLG) &&
cinode->lease_granted &&
!test_bit(CIFS_INO_CLOSE_ON_LOCK, &cinode->flags) &&
dclose) {
if (test_and_clear_bit(CIFS_INO_MODIFIED_ATTR, &cinode->flags)) {
inode->i_ctime = inode->i_mtime = current_time(inode);
}
spin_lock(&cinode->deferred_lock);
cifs_add_deferred_close(cfile, dclose);
if (cfile->deferred_close_scheduled &&
delayed_work_pending(&cfile->deferred)) {
/*
* If there is no pending work, mod_delayed_work queues new work.
* So, Increase the ref count to avoid use-after-free.
*/
if (!mod_delayed_work(deferredclose_wq,
&cfile->deferred, cifs_sb->ctx->acregmax))
cifsFileInfo_get(cfile);
} else {
/* Deferred close for files */
queue_delayed_work(deferredclose_wq,
&cfile->deferred, cifs_sb->ctx->acregmax);
cfile->deferred_close_scheduled = true;
spin_unlock(&cinode->deferred_lock);
return 0;
}
spin_unlock(&cinode->deferred_lock);
_cifsFileInfo_put(cfile, true, false);
} else {
_cifsFileInfo_put(cfile, true, false);
kfree(dclose);
}
}
/* return code from the ->release op is always ignored */
return 0;
}
void
cifs_reopen_persistent_handles(struct cifs_tcon *tcon)
{
struct cifsFileInfo *open_file, *tmp;
struct list_head tmp_list;
if (!tcon->use_persistent || !tcon->need_reopen_files)
return;
tcon->need_reopen_files = false;
cifs_dbg(FYI, "Reopen persistent handles\n");
INIT_LIST_HEAD(&tmp_list);
/* list all files open on tree connection, reopen resilient handles */
spin_lock(&tcon->open_file_lock);
list_for_each_entry(open_file, &tcon->openFileList, tlist) {
if (!open_file->invalidHandle)
continue;
cifsFileInfo_get(open_file);
list_add_tail(&open_file->rlist, &tmp_list);
}
spin_unlock(&tcon->open_file_lock);
list_for_each_entry_safe(open_file, tmp, &tmp_list, rlist) {
if (cifs_reopen_file(open_file, false /* do not flush */))
tcon->need_reopen_files = true;
list_del_init(&open_file->rlist);
cifsFileInfo_put(open_file);
}
}
int cifs_closedir(struct inode *inode, struct file *file)
{
int rc = 0;
unsigned int xid;
struct cifsFileInfo *cfile = file->private_data;
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
char *buf;
cifs_dbg(FYI, "Closedir inode = 0x%p\n", inode);
if (cfile == NULL)
return rc;
xid = get_xid();
tcon = tlink_tcon(cfile->tlink);
server = tcon->ses->server;
cifs_dbg(FYI, "Freeing private data in close dir\n");
spin_lock(&cfile->file_info_lock);
if (server->ops->dir_needs_close(cfile)) {
cfile->invalidHandle = true;
spin_unlock(&cfile->file_info_lock);
if (server->ops->close_dir)
rc = server->ops->close_dir(xid, tcon, &cfile->fid);
else
rc = -ENOSYS;
cifs_dbg(FYI, "Closing uncompleted readdir with rc %d\n", rc);
/* not much we can do if it fails anyway, ignore rc */
rc = 0;
} else
spin_unlock(&cfile->file_info_lock);
buf = cfile->srch_inf.ntwrk_buf_start;
if (buf) {
cifs_dbg(FYI, "closedir free smb buf in srch struct\n");
cfile->srch_inf.ntwrk_buf_start = NULL;
if (cfile->srch_inf.smallBuf)
cifs_small_buf_release(buf);
else
cifs_buf_release(buf);
}
cifs_put_tlink(cfile->tlink);
kfree(file->private_data);
file->private_data = NULL;
/* BB can we lock the filestruct while this is going on? */
free_xid(xid);
return rc;
}
static struct cifsLockInfo *
cifs_lock_init(__u64 offset, __u64 length, __u8 type, __u16 flags)
{
struct cifsLockInfo *lock =
kmalloc(sizeof(struct cifsLockInfo), GFP_KERNEL);
if (!lock)
return lock;
lock->offset = offset;
lock->length = length;
lock->type = type;
lock->pid = current->tgid;
lock->flags = flags;
INIT_LIST_HEAD(&lock->blist);
init_waitqueue_head(&lock->block_q);
return lock;
}
void
cifs_del_lock_waiters(struct cifsLockInfo *lock)
{
struct cifsLockInfo *li, *tmp;
list_for_each_entry_safe(li, tmp, &lock->blist, blist) {
list_del_init(&li->blist);
wake_up(&li->block_q);
}
}
#define CIFS_LOCK_OP 0
#define CIFS_READ_OP 1
#define CIFS_WRITE_OP 2
/* @rw_check : 0 - no op, 1 - read, 2 - write */
static bool
cifs_find_fid_lock_conflict(struct cifs_fid_locks *fdlocks, __u64 offset,
__u64 length, __u8 type, __u16 flags,
struct cifsFileInfo *cfile,
struct cifsLockInfo **conf_lock, int rw_check)
{
struct cifsLockInfo *li;
struct cifsFileInfo *cur_cfile = fdlocks->cfile;
struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server;
list_for_each_entry(li, &fdlocks->locks, llist) {
if (offset + length <= li->offset ||
offset >= li->offset + li->length)
continue;
if (rw_check != CIFS_LOCK_OP && current->tgid == li->pid &&
server->ops->compare_fids(cfile, cur_cfile)) {
/* shared lock prevents write op through the same fid */
if (!(li->type & server->vals->shared_lock_type) ||
rw_check != CIFS_WRITE_OP)
continue;
}
if ((type & server->vals->shared_lock_type) &&
((server->ops->compare_fids(cfile, cur_cfile) &&
current->tgid == li->pid) || type == li->type))
continue;
if (rw_check == CIFS_LOCK_OP &&
(flags & FL_OFDLCK) && (li->flags & FL_OFDLCK) &&
server->ops->compare_fids(cfile, cur_cfile))
continue;
if (conf_lock)
*conf_lock = li;
return true;
}
return false;
}
bool
cifs_find_lock_conflict(struct cifsFileInfo *cfile, __u64 offset, __u64 length,
__u8 type, __u16 flags,
struct cifsLockInfo **conf_lock, int rw_check)
{
bool rc = false;
struct cifs_fid_locks *cur;
struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
list_for_each_entry(cur, &cinode->llist, llist) {
rc = cifs_find_fid_lock_conflict(cur, offset, length, type,
flags, cfile, conf_lock,
rw_check);
if (rc)
break;
}
return rc;
}
/*
* Check if there is another lock that prevents us to set the lock (mandatory
* style). If such a lock exists, update the flock structure with its
* properties. Otherwise, set the flock type to F_UNLCK if we can cache brlocks
* or leave it the same if we can't. Returns 0 if we don't need to request to
* the server or 1 otherwise.
*/
static int
cifs_lock_test(struct cifsFileInfo *cfile, __u64 offset, __u64 length,
__u8 type, struct file_lock *flock)
{
int rc = 0;
struct cifsLockInfo *conf_lock;
struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server;
bool exist;
down_read(&cinode->lock_sem);
exist = cifs_find_lock_conflict(cfile, offset, length, type,
flock->fl_flags, &conf_lock,
CIFS_LOCK_OP);
if (exist) {
flock->fl_start = conf_lock->offset;
flock->fl_end = conf_lock->offset + conf_lock->length - 1;
flock->fl_pid = conf_lock->pid;
if (conf_lock->type & server->vals->shared_lock_type)
flock->fl_type = F_RDLCK;
else
flock->fl_type = F_WRLCK;
} else if (!cinode->can_cache_brlcks)
rc = 1;
else
flock->fl_type = F_UNLCK;
up_read(&cinode->lock_sem);
return rc;
}
static void
cifs_lock_add(struct cifsFileInfo *cfile, struct cifsLockInfo *lock)
{
struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
cifs_down_write(&cinode->lock_sem);
list_add_tail(&lock->llist, &cfile->llist->locks);
up_write(&cinode->lock_sem);
}
/*
* Set the byte-range lock (mandatory style). Returns:
* 1) 0, if we set the lock and don't need to request to the server;
* 2) 1, if no locks prevent us but we need to request to the server;
* 3) -EACCES, if there is a lock that prevents us and wait is false.
*/
static int
cifs_lock_add_if(struct cifsFileInfo *cfile, struct cifsLockInfo *lock,
bool wait)
{
struct cifsLockInfo *conf_lock;
struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
bool exist;
int rc = 0;
try_again:
exist = false;
cifs_down_write(&cinode->lock_sem);
exist = cifs_find_lock_conflict(cfile, lock->offset, lock->length,
lock->type, lock->flags, &conf_lock,
CIFS_LOCK_OP);
if (!exist && cinode->can_cache_brlcks) {
list_add_tail(&lock->llist, &cfile->llist->locks);
up_write(&cinode->lock_sem);
return rc;
}
if (!exist)
rc = 1;
else if (!wait)
rc = -EACCES;
else {
list_add_tail(&lock->blist, &conf_lock->blist);
up_write(&cinode->lock_sem);
rc = wait_event_interruptible(lock->block_q,
(lock->blist.prev == &lock->blist) &&
(lock->blist.next == &lock->blist));
if (!rc)
goto try_again;
cifs_down_write(&cinode->lock_sem);
list_del_init(&lock->blist);
}
up_write(&cinode->lock_sem);
return rc;
}
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
/*
* Check if there is another lock that prevents us to set the lock (posix
* style). If such a lock exists, update the flock structure with its
* properties. Otherwise, set the flock type to F_UNLCK if we can cache brlocks
* or leave it the same if we can't. Returns 0 if we don't need to request to
* the server or 1 otherwise.
*/
static int
cifs_posix_lock_test(struct file *file, struct file_lock *flock)
{
int rc = 0;
struct cifsInodeInfo *cinode = CIFS_I(file_inode(file));
unsigned char saved_type = flock->fl_type;
if ((flock->fl_flags & FL_POSIX) == 0)
return 1;
down_read(&cinode->lock_sem);
posix_test_lock(file, flock);
if (flock->fl_type == F_UNLCK && !cinode->can_cache_brlcks) {
flock->fl_type = saved_type;
rc = 1;
}
up_read(&cinode->lock_sem);
return rc;
}
/*
* Set the byte-range lock (posix style). Returns:
* 1) <0, if the error occurs while setting the lock;
* 2) 0, if we set the lock and don't need to request to the server;
* 3) FILE_LOCK_DEFERRED, if we will wait for some other file_lock;
* 4) FILE_LOCK_DEFERRED + 1, if we need to request to the server.
*/
static int
cifs_posix_lock_set(struct file *file, struct file_lock *flock)
{
struct cifsInodeInfo *cinode = CIFS_I(file_inode(file));
int rc = FILE_LOCK_DEFERRED + 1;
if ((flock->fl_flags & FL_POSIX) == 0)
return rc;
cifs_down_write(&cinode->lock_sem);
if (!cinode->can_cache_brlcks) {
up_write(&cinode->lock_sem);
return rc;
}
rc = posix_lock_file(file, flock, NULL);
up_write(&cinode->lock_sem);
return rc;
}
int
cifs_push_mandatory_locks(struct cifsFileInfo *cfile)
{
unsigned int xid;
int rc = 0, stored_rc;
struct cifsLockInfo *li, *tmp;
struct cifs_tcon *tcon;
unsigned int num, max_num, max_buf;
LOCKING_ANDX_RANGE *buf, *cur;
static const int types[] = {
LOCKING_ANDX_LARGE_FILES,
LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES
};
int i;
xid = get_xid();
tcon = tlink_tcon(cfile->tlink);
/*
* Accessing maxBuf is racy with cifs_reconnect - need to store value
* and check it before using.
*/
max_buf = tcon->ses->server->maxBuf;
if (max_buf < (sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE))) {
free_xid(xid);
return -EINVAL;
}
BUILD_BUG_ON(sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE) >
PAGE_SIZE);
max_buf = min_t(unsigned int, max_buf - sizeof(struct smb_hdr),
PAGE_SIZE);
max_num = (max_buf - sizeof(struct smb_hdr)) /
sizeof(LOCKING_ANDX_RANGE);
buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
if (!buf) {
free_xid(xid);
return -ENOMEM;
}
for (i = 0; i < 2; i++) {
cur = buf;
num = 0;
list_for_each_entry_safe(li, tmp, &cfile->llist->locks, llist) {
if (li->type != types[i])
continue;
cur->Pid = cpu_to_le16(li->pid);
cur->LengthLow = cpu_to_le32((u32)li->length);
cur->LengthHigh = cpu_to_le32((u32)(li->length>>32));
cur->OffsetLow = cpu_to_le32((u32)li->offset);
cur->OffsetHigh = cpu_to_le32((u32)(li->offset>>32));
if (++num == max_num) {
stored_rc = cifs_lockv(xid, tcon,
cfile->fid.netfid,
(__u8)li->type, 0, num,
buf);
if (stored_rc)
rc = stored_rc;
cur = buf;
num = 0;
} else
cur++;
}
if (num) {
stored_rc = cifs_lockv(xid, tcon, cfile->fid.netfid,
(__u8)types[i], 0, num, buf);
if (stored_rc)
rc = stored_rc;
}
}
kfree(buf);
free_xid(xid);
return rc;
}
static __u32
hash_lockowner(fl_owner_t owner)
{
return cifs_lock_secret ^ hash32_ptr((const void *)owner);
}
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
struct lock_to_push {
struct list_head llist;
__u64 offset;
__u64 length;
__u32 pid;
__u16 netfid;
__u8 type;
};
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
static int
cifs_push_posix_locks(struct cifsFileInfo *cfile)
{
struct inode *inode = d_inode(cfile->dentry);
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
struct file_lock *flock;
struct file_lock_context *flctx = inode->i_flctx;
unsigned int count = 0, i;
int rc = 0, xid, type;
struct list_head locks_to_send, *el;
struct lock_to_push *lck, *tmp;
__u64 length;
xid = get_xid();
if (!flctx)
goto out;
spin_lock(&flctx->flc_lock);
list_for_each(el, &flctx->flc_posix) {
count++;
}
spin_unlock(&flctx->flc_lock);
INIT_LIST_HEAD(&locks_to_send);
/*
* Allocating count locks is enough because no FL_POSIX locks can be
* added to the list while we are holding cinode->lock_sem that
* protects locking operations of this inode.
*/
for (i = 0; i < count; i++) {
lck = kmalloc(sizeof(struct lock_to_push), GFP_KERNEL);
if (!lck) {
rc = -ENOMEM;
goto err_out;
}
list_add_tail(&lck->llist, &locks_to_send);
}
el = locks_to_send.next;
spin_lock(&flctx->flc_lock);
list_for_each_entry(flock, &flctx->flc_posix, fl_list) {
if (el == &locks_to_send) {
/*
* The list ended. We don't have enough allocated
* structures - something is really wrong.
*/
cifs_dbg(VFS, "Can't push all brlocks!\n");
break;
}
length = cifs_flock_len(flock);
if (flock->fl_type == F_RDLCK || flock->fl_type == F_SHLCK)
type = CIFS_RDLCK;
else
type = CIFS_WRLCK;
lck = list_entry(el, struct lock_to_push, llist);
lck->pid = hash_lockowner(flock->fl_owner);
lck->netfid = cfile->fid.netfid;
lck->length = length;
lck->type = type;
lck->offset = flock->fl_start;
}
spin_unlock(&flctx->flc_lock);
list_for_each_entry_safe(lck, tmp, &locks_to_send, llist) {
int stored_rc;
stored_rc = CIFSSMBPosixLock(xid, tcon, lck->netfid, lck->pid,
lck->offset, lck->length, NULL,
lck->type, 0);
if (stored_rc)
rc = stored_rc;
list_del(&lck->llist);
kfree(lck);
}
out:
free_xid(xid);
return rc;
err_out:
list_for_each_entry_safe(lck, tmp, &locks_to_send, llist) {
list_del(&lck->llist);
kfree(lck);
}
goto out;
}
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
static int
cifs_push_locks(struct cifsFileInfo *cfile)
{
struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
int rc = 0;
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb);
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
/* we are going to update can_cache_brlcks here - need a write access */
cifs_down_write(&cinode->lock_sem);
if (!cinode->can_cache_brlcks) {
up_write(&cinode->lock_sem);
return rc;
}
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
if (cap_unix(tcon->ses) &&
(CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
rc = cifs_push_posix_locks(cfile);
else
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
rc = tcon->ses->server->ops->push_mand_locks(cfile);
cinode->can_cache_brlcks = false;
up_write(&cinode->lock_sem);
return rc;
}
static void
cifs_read_flock(struct file_lock *flock, __u32 *type, int *lock, int *unlock,
bool *wait_flag, struct TCP_Server_Info *server)
{
if (flock->fl_flags & FL_POSIX)
cifs_dbg(FYI, "Posix\n");
if (flock->fl_flags & FL_FLOCK)
cifs_dbg(FYI, "Flock\n");
if (flock->fl_flags & FL_SLEEP) {
cifs_dbg(FYI, "Blocking lock\n");
*wait_flag = true;
}
if (flock->fl_flags & FL_ACCESS)
cifs_dbg(FYI, "Process suspended by mandatory locking - not implemented yet\n");
if (flock->fl_flags & FL_LEASE)
cifs_dbg(FYI, "Lease on file - not implemented yet\n");
if (flock->fl_flags &
(~(FL_POSIX | FL_FLOCK | FL_SLEEP |
FL_ACCESS | FL_LEASE | FL_CLOSE | FL_OFDLCK)))
cifs_dbg(FYI, "Unknown lock flags 0x%x\n", flock->fl_flags);
*type = server->vals->large_lock_type;
if (flock->fl_type == F_WRLCK) {
cifs_dbg(FYI, "F_WRLCK\n");
*type |= server->vals->exclusive_lock_type;
*lock = 1;
} else if (flock->fl_type == F_UNLCK) {
cifs_dbg(FYI, "F_UNLCK\n");
*type |= server->vals->unlock_lock_type;
*unlock = 1;
/* Check if unlock includes more than one lock range */
} else if (flock->fl_type == F_RDLCK) {
cifs_dbg(FYI, "F_RDLCK\n");
*type |= server->vals->shared_lock_type;
*lock = 1;
} else if (flock->fl_type == F_EXLCK) {
cifs_dbg(FYI, "F_EXLCK\n");
*type |= server->vals->exclusive_lock_type;
*lock = 1;
} else if (flock->fl_type == F_SHLCK) {
cifs_dbg(FYI, "F_SHLCK\n");
*type |= server->vals->shared_lock_type;
*lock = 1;
} else
cifs_dbg(FYI, "Unknown type of lock\n");
}
static int
cifs_getlk(struct file *file, struct file_lock *flock, __u32 type,
bool wait_flag, bool posix_lck, unsigned int xid)
{
int rc = 0;
__u64 length = cifs_flock_len(flock);
struct cifsFileInfo *cfile = (struct cifsFileInfo *)file->private_data;
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
struct TCP_Server_Info *server = tcon->ses->server;
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
__u16 netfid = cfile->fid.netfid;
if (posix_lck) {
int posix_lock_type;
rc = cifs_posix_lock_test(file, flock);
if (!rc)
return rc;
if (type & server->vals->shared_lock_type)
posix_lock_type = CIFS_RDLCK;
else
posix_lock_type = CIFS_WRLCK;
rc = CIFSSMBPosixLock(xid, tcon, netfid,
hash_lockowner(flock->fl_owner),
flock->fl_start, length, flock,
posix_lock_type, wait_flag);
return rc;
}
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
rc = cifs_lock_test(cfile, flock->fl_start, length, type, flock);
if (!rc)
return rc;
/* BB we could chain these into one lock request BB */
rc = server->ops->mand_lock(xid, cfile, flock->fl_start, length, type,
1, 0, false);
if (rc == 0) {
rc = server->ops->mand_lock(xid, cfile, flock->fl_start, length,
type, 0, 1, false);
flock->fl_type = F_UNLCK;
if (rc != 0)
cifs_dbg(VFS, "Error unlocking previously locked range %d during test of lock\n",
rc);
return 0;
}
if (type & server->vals->shared_lock_type) {
flock->fl_type = F_WRLCK;
return 0;
}
type &= ~server->vals->exclusive_lock_type;
rc = server->ops->mand_lock(xid, cfile, flock->fl_start, length,
type | server->vals->shared_lock_type,
1, 0, false);
if (rc == 0) {
rc = server->ops->mand_lock(xid, cfile, flock->fl_start, length,
type | server->vals->shared_lock_type, 0, 1, false);
flock->fl_type = F_RDLCK;
if (rc != 0)
cifs_dbg(VFS, "Error unlocking previously locked range %d during test of lock\n",
rc);
} else
flock->fl_type = F_WRLCK;
return 0;
}
void
cifs_move_llist(struct list_head *source, struct list_head *dest)
{
struct list_head *li, *tmp;
list_for_each_safe(li, tmp, source)
list_move(li, dest);
}
void
cifs_free_llist(struct list_head *llist)
{
struct cifsLockInfo *li, *tmp;
list_for_each_entry_safe(li, tmp, llist, llist) {
cifs_del_lock_waiters(li);
list_del(&li->llist);
kfree(li);
}
}
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
int
cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
unsigned int xid)
{
int rc = 0, stored_rc;
static const int types[] = {
LOCKING_ANDX_LARGE_FILES,
LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES
};
unsigned int i;
unsigned int max_num, num, max_buf;
LOCKING_ANDX_RANGE *buf, *cur;
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
struct cifsLockInfo *li, *tmp;
__u64 length = cifs_flock_len(flock);
struct list_head tmp_llist;
INIT_LIST_HEAD(&tmp_llist);
/*
* Accessing maxBuf is racy with cifs_reconnect - need to store value
* and check it before using.
*/
max_buf = tcon->ses->server->maxBuf;
if (max_buf < (sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE)))
return -EINVAL;
BUILD_BUG_ON(sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE) >
PAGE_SIZE);
max_buf = min_t(unsigned int, max_buf - sizeof(struct smb_hdr),
PAGE_SIZE);
max_num = (max_buf - sizeof(struct smb_hdr)) /
sizeof(LOCKING_ANDX_RANGE);
buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
if (!buf)
return -ENOMEM;
cifs_down_write(&cinode->lock_sem);
for (i = 0; i < 2; i++) {
cur = buf;
num = 0;
list_for_each_entry_safe(li, tmp, &cfile->llist->locks, llist) {
if (flock->fl_start > li->offset ||
(flock->fl_start + length) <
(li->offset + li->length))
continue;
if (current->tgid != li->pid)
continue;
if (types[i] != li->type)
continue;
if (cinode->can_cache_brlcks) {
/*
* We can cache brlock requests - simply remove
* a lock from the file's list.
*/
list_del(&li->llist);
cifs_del_lock_waiters(li);
kfree(li);
continue;
}
cur->Pid = cpu_to_le16(li->pid);
cur->LengthLow = cpu_to_le32((u32)li->length);
cur->LengthHigh = cpu_to_le32((u32)(li->length>>32));
cur->OffsetLow = cpu_to_le32((u32)li->offset);
cur->OffsetHigh = cpu_to_le32((u32)(li->offset>>32));
/*
* We need to save a lock here to let us add it again to
* the file's list if the unlock range request fails on
* the server.
*/
list_move(&li->llist, &tmp_llist);
if (++num == max_num) {
stored_rc = cifs_lockv(xid, tcon,
cfile->fid.netfid,
li->type, num, 0, buf);
if (stored_rc) {
/*
* We failed on the unlock range
* request - add all locks from the tmp
* list to the head of the file's list.
*/
cifs_move_llist(&tmp_llist,
&cfile->llist->locks);
rc = stored_rc;
} else
/*
* The unlock range request succeed -
* free the tmp list.
*/
cifs_free_llist(&tmp_llist);
cur = buf;
num = 0;
} else
cur++;
}
if (num) {
stored_rc = cifs_lockv(xid, tcon, cfile->fid.netfid,
types[i], num, 0, buf);
if (stored_rc) {
cifs_move_llist(&tmp_llist,
&cfile->llist->locks);
rc = stored_rc;
} else
cifs_free_llist(&tmp_llist);
}
}
up_write(&cinode->lock_sem);
kfree(buf);
return rc;
}
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
static int
cifs_setlk(struct file *file, struct file_lock *flock, __u32 type,
bool wait_flag, bool posix_lck, int lock, int unlock,
unsigned int xid)
{
int rc = 0;
__u64 length = cifs_flock_len(flock);
struct cifsFileInfo *cfile = (struct cifsFileInfo *)file->private_data;
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
struct TCP_Server_Info *server = tcon->ses->server;
struct inode *inode = d_inode(cfile->dentry);
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
if (posix_lck) {
int posix_lock_type;
rc = cifs_posix_lock_set(file, flock);
if (rc <= FILE_LOCK_DEFERRED)
return rc;
if (type & server->vals->shared_lock_type)
posix_lock_type = CIFS_RDLCK;
else
posix_lock_type = CIFS_WRLCK;
if (unlock == 1)
posix_lock_type = CIFS_UNLCK;
rc = CIFSSMBPosixLock(xid, tcon, cfile->fid.netfid,
hash_lockowner(flock->fl_owner),
flock->fl_start, length,
NULL, posix_lock_type, wait_flag);
goto out;
}
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
if (lock) {
struct cifsLockInfo *lock;
lock = cifs_lock_init(flock->fl_start, length, type,
flock->fl_flags);
if (!lock)
return -ENOMEM;
rc = cifs_lock_add_if(cfile, lock, wait_flag);
if (rc < 0) {
kfree(lock);
return rc;
}
if (!rc)
goto out;
/*
* Windows 7 server can delay breaking lease from read to None
* if we set a byte-range lock on a file - break it explicitly
* before sending the lock to the server to be sure the next
* read won't conflict with non-overlapted locks due to
* pagereading.
*/
if (!CIFS_CACHE_WRITE(CIFS_I(inode)) &&
CIFS_CACHE_READ(CIFS_I(inode))) {
cifs_zap_mapping(inode);
cifs_dbg(FYI, "Set no oplock for inode=%p due to mand locks\n",
inode);
CIFS_I(inode)->oplock = 0;
}
rc = server->ops->mand_lock(xid, cfile, flock->fl_start, length,
type, 1, 0, wait_flag);
if (rc) {
kfree(lock);
return rc;
}
cifs_lock_add(cfile, lock);
} else if (unlock)
rc = server->ops->mand_unlock_range(cfile, flock, xid);
out:
if ((flock->fl_flags & FL_POSIX) || (flock->fl_flags & FL_FLOCK)) {
/*
* If this is a request to remove all locks because we
* are closing the file, it doesn't matter if the
* unlocking failed as both cifs.ko and the SMB server
* remove the lock on file close
*/
if (rc) {
cifs_dbg(VFS, "%s failed rc=%d\n", __func__, rc);
if (!(flock->fl_flags & FL_CLOSE))
return rc;
}
rc = locks_lock_file_wait(file, flock);
}
return rc;
}
int cifs_flock(struct file *file, int cmd, struct file_lock *fl)
{
int rc, xid;
int lock = 0, unlock = 0;
bool wait_flag = false;
bool posix_lck = false;
struct cifs_sb_info *cifs_sb;
struct cifs_tcon *tcon;
struct cifsFileInfo *cfile;
__u32 type;
rc = -EACCES;
xid = get_xid();
if (!(fl->fl_flags & FL_FLOCK))
return -ENOLCK;
cfile = (struct cifsFileInfo *)file->private_data;
tcon = tlink_tcon(cfile->tlink);
cifs_read_flock(fl, &type, &lock, &unlock, &wait_flag,
tcon->ses->server);
cifs_sb = CIFS_FILE_SB(file);
if (cap_unix(tcon->ses) &&
(CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
posix_lck = true;
if (!lock && !unlock) {
/*
* if no lock or unlock then nothing to do since we do not
* know what it is
*/
free_xid(xid);
return -EOPNOTSUPP;
}
rc = cifs_setlk(file, fl, type, wait_flag, posix_lck, lock, unlock,
xid);
free_xid(xid);
return rc;
}
int cifs_lock(struct file *file, int cmd, struct file_lock *flock)
{
int rc, xid;
int lock = 0, unlock = 0;
bool wait_flag = false;
bool posix_lck = false;
struct cifs_sb_info *cifs_sb;
struct cifs_tcon *tcon;
struct cifsFileInfo *cfile;
__u32 type;
rc = -EACCES;
xid = get_xid();
cifs_dbg(FYI, "Lock parm: 0x%x flockflags: 0x%x flocktype: 0x%x start: %lld end: %lld\n",
cmd, flock->fl_flags, flock->fl_type,
flock->fl_start, flock->fl_end);
cfile = (struct cifsFileInfo *)file->private_data;
tcon = tlink_tcon(cfile->tlink);
cifs_read_flock(flock, &type, &lock, &unlock, &wait_flag,
tcon->ses->server);
cifs_sb = CIFS_FILE_SB(file);
set_bit(CIFS_INO_CLOSE_ON_LOCK, &CIFS_I(d_inode(cfile->dentry))->flags);
if (cap_unix(tcon->ses) &&
(CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
posix_lck = true;
/*
* BB add code here to normalize offset and length to account for
* negative length which we can not accept over the wire.
*/
if (IS_GETLK(cmd)) {
rc = cifs_getlk(file, flock, type, wait_flag, posix_lck, xid);
free_xid(xid);
return rc;
}
if (!lock && !unlock) {
/*
* if no lock or unlock then nothing to do since we do not
* know what it is
*/
free_xid(xid);
return -EOPNOTSUPP;
}
rc = cifs_setlk(file, flock, type, wait_flag, posix_lck, lock, unlock,
xid);
free_xid(xid);
return rc;
}
/*
* update the file size (if needed) after a write. Should be called with
* the inode->i_lock held
*/
void
cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset,
unsigned int bytes_written)
{
loff_t end_of_write = offset + bytes_written;
if (end_of_write > cifsi->server_eof)
cifsi->server_eof = end_of_write;
}
static ssize_t
cifs_write(struct cifsFileInfo *open_file, __u32 pid, const char *write_data,
size_t write_size, loff_t *offset)
{
int rc = 0;
unsigned int bytes_written = 0;
unsigned int total_written;
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
unsigned int xid;
struct dentry *dentry = open_file->dentry;
struct cifsInodeInfo *cifsi = CIFS_I(d_inode(dentry));
struct cifs_io_parms io_parms = {0};
cifs_dbg(FYI, "write %zd bytes to offset %lld of %pd\n",
write_size, *offset, dentry);
tcon = tlink_tcon(open_file->tlink);
server = tcon->ses->server;
if (!server->ops->sync_write)
return -ENOSYS;
xid = get_xid();
for (total_written = 0; write_size > total_written;
total_written += bytes_written) {
rc = -EAGAIN;
while (rc == -EAGAIN) {
struct kvec iov[2];
unsigned int len;
if (open_file->invalidHandle) {
/* we could deadlock if we called
filemap_fdatawait from here so tell
reopen_file not to flush data to
server now */
rc = cifs_reopen_file(open_file, false);
if (rc != 0)
break;
}
len = min(server->ops->wp_retry_size(d_inode(dentry)),
(unsigned int)write_size - total_written);
/* iov[0] is reserved for smb header */
iov[1].iov_base = (char *)write_data + total_written;
iov[1].iov_len = len;
io_parms.pid = pid;
io_parms.tcon = tcon;
io_parms.offset = *offset;
io_parms.length = len;
rc = server->ops->sync_write(xid, &open_file->fid,
&io_parms, &bytes_written, iov, 1);
}
if (rc || (bytes_written == 0)) {
if (total_written)
break;
else {
free_xid(xid);
return rc;
}
} else {
spin_lock(&d_inode(dentry)->i_lock);
cifs_update_eof(cifsi, *offset, bytes_written);
spin_unlock(&d_inode(dentry)->i_lock);
*offset += bytes_written;
}
}
cifs_stats_bytes_written(tcon, total_written);
if (total_written > 0) {
spin_lock(&d_inode(dentry)->i_lock);
if (*offset > d_inode(dentry)->i_size) {
i_size_write(d_inode(dentry), *offset);
d_inode(dentry)->i_blocks = (512 - 1 + *offset) >> 9;
}
spin_unlock(&d_inode(dentry)->i_lock);
}
mark_inode_dirty_sync(d_inode(dentry));
free_xid(xid);
return total_written;
}
struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
bool fsuid_only)
{
struct cifsFileInfo *open_file = NULL;
struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode->netfs.inode.i_sb);
/* only filter by fsuid on multiuser mounts */
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
fsuid_only = false;
spin_lock(&cifs_inode->open_file_lock);
/* we could simply get the first_list_entry since write-only entries
are always at the end of the list but since the first entry might
have a close pending, we go through the whole list */
list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
if (fsuid_only && !uid_eq(open_file->uid, current_fsuid()))
continue;
if (OPEN_FMODE(open_file->f_flags) & FMODE_READ) {
if ((!open_file->invalidHandle)) {
/* found a good file */
/* lock it so it will not be closed on us */
cifsFileInfo_get(open_file);
spin_unlock(&cifs_inode->open_file_lock);
return open_file;
} /* else might as well continue, and look for
another, or simply have the caller reopen it
again rather than trying to fix this handle */
} else /* write only file */
break; /* write only files are last so must be done */
}
spin_unlock(&cifs_inode->open_file_lock);
return NULL;
}
/* Return -EBADF if no handle is found and general rc otherwise */
int
cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, int flags,
struct cifsFileInfo **ret_file)
{
struct cifsFileInfo *open_file, *inv_file = NULL;
struct cifs_sb_info *cifs_sb;
bool any_available = false;
int rc = -EBADF;
unsigned int refind = 0;
bool fsuid_only = flags & FIND_WR_FSUID_ONLY;
bool with_delete = flags & FIND_WR_WITH_DELETE;
*ret_file = NULL;
/*
* Having a null inode here (because mapping->host was set to zero by
* the VFS or MM) should not happen but we had reports of on oops (due
* to it being zero) during stress testcases so we need to check for it
*/
if (cifs_inode == NULL) {
cifs_dbg(VFS, "Null inode passed to cifs_writeable_file\n");
dump_stack();
return rc;
}
cifs_sb = CIFS_SB(cifs_inode->netfs.inode.i_sb);
/* only filter by fsuid on multiuser mounts */
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
fsuid_only = false;
spin_lock(&cifs_inode->open_file_lock);
refind_writable:
if (refind > MAX_REOPEN_ATT) {
spin_unlock(&cifs_inode->open_file_lock);
return rc;
}
list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
if (!any_available && open_file->pid != current->tgid)
continue;
if (fsuid_only && !uid_eq(open_file->uid, current_fsuid()))
continue;
if (with_delete && !(open_file->fid.access & DELETE))
continue;
if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) {
if (!open_file->invalidHandle) {
/* found a good writable file */
cifsFileInfo_get(open_file);
spin_unlock(&cifs_inode->open_file_lock);
*ret_file = open_file;
return 0;
} else {
if (!inv_file)
inv_file = open_file;
}
}
}
/* couldn't find useable FH with same pid, try any available */
if (!any_available) {
any_available = true;
goto refind_writable;
}
if (inv_file) {
any_available = false;
cifsFileInfo_get(inv_file);
}
spin_unlock(&cifs_inode->open_file_lock);
if (inv_file) {
rc = cifs_reopen_file(inv_file, false);
if (!rc) {
*ret_file = inv_file;
return 0;
}
spin_lock(&cifs_inode->open_file_lock);
list_move_tail(&inv_file->flist, &cifs_inode->openFileList);
spin_unlock(&cifs_inode->open_file_lock);
cifsFileInfo_put(inv_file);
++refind;
inv_file = NULL;
spin_lock(&cifs_inode->open_file_lock);
goto refind_writable;
}
return rc;
}
struct cifsFileInfo *
find_writable_file(struct cifsInodeInfo *cifs_inode, int flags)
{
struct cifsFileInfo *cfile;
int rc;
rc = cifs_get_writable_file(cifs_inode, flags, &cfile);
if (rc)
cifs_dbg(FYI, "Couldn't find writable handle rc=%d\n", rc);
return cfile;
}
int
cifs_get_writable_path(struct cifs_tcon *tcon, const char *name,
int flags,
struct cifsFileInfo **ret_file)
{
struct cifsFileInfo *cfile;
void *page = alloc_dentry_path();
*ret_file = NULL;
spin_lock(&tcon->open_file_lock);
list_for_each_entry(cfile, &tcon->openFileList, tlist) {
struct cifsInodeInfo *cinode;
const char *full_path = build_path_from_dentry(cfile->dentry, page);
if (IS_ERR(full_path)) {
spin_unlock(&tcon->open_file_lock);
free_dentry_path(page);
return PTR_ERR(full_path);
}
if (strcmp(full_path, name))
continue;
cinode = CIFS_I(d_inode(cfile->dentry));
spin_unlock(&tcon->open_file_lock);
free_dentry_path(page);
return cifs_get_writable_file(cinode, flags, ret_file);
}
spin_unlock(&tcon->open_file_lock);
free_dentry_path(page);
return -ENOENT;
}
int
cifs_get_readable_path(struct cifs_tcon *tcon, const char *name,
struct cifsFileInfo **ret_file)
{
struct cifsFileInfo *cfile;
void *page = alloc_dentry_path();
*ret_file = NULL;
spin_lock(&tcon->open_file_lock);
list_for_each_entry(cfile, &tcon->openFileList, tlist) {
struct cifsInodeInfo *cinode;
const char *full_path = build_path_from_dentry(cfile->dentry, page);
if (IS_ERR(full_path)) {
spin_unlock(&tcon->open_file_lock);
free_dentry_path(page);
return PTR_ERR(full_path);
}
if (strcmp(full_path, name))
continue;
cinode = CIFS_I(d_inode(cfile->dentry));
spin_unlock(&tcon->open_file_lock);
free_dentry_path(page);
*ret_file = find_readable_file(cinode, 0);
return *ret_file ? 0 : -ENOENT;
}
spin_unlock(&tcon->open_file_lock);
free_dentry_path(page);
return -ENOENT;
}
void
cifs_writedata_release(struct kref *refcount)
{
struct cifs_writedata *wdata = container_of(refcount,
struct cifs_writedata, refcount);
#ifdef CONFIG_CIFS_SMB_DIRECT
if (wdata->mr) {
smbd_deregister_mr(wdata->mr);
wdata->mr = NULL;
}
#endif
if (wdata->cfile)
cifsFileInfo_put(wdata->cfile);
kvfree(wdata->pages);
kfree(wdata);
}
/*
* Write failed with a retryable error. Resend the write request. It's also
* possible that the page was redirtied so re-clean the page.
*/
static void
cifs_writev_requeue(struct cifs_writedata *wdata)
{
int i, rc = 0;
struct inode *inode = d_inode(wdata->cfile->dentry);
struct TCP_Server_Info *server;
unsigned int rest_len;
server = tlink_tcon(wdata->cfile->tlink)->ses->server;
i = 0;
rest_len = wdata->bytes;
do {
struct cifs_writedata *wdata2;
unsigned int j, nr_pages, wsize, tailsz, cur_len;
wsize = server->ops->wp_retry_size(inode);
if (wsize < rest_len) {
nr_pages = wsize / PAGE_SIZE;
if (!nr_pages) {
rc = -EOPNOTSUPP;
break;
}
cur_len = nr_pages * PAGE_SIZE;
tailsz = PAGE_SIZE;
} else {
nr_pages = DIV_ROUND_UP(rest_len, PAGE_SIZE);
cur_len = rest_len;
tailsz = rest_len - (nr_pages - 1) * PAGE_SIZE;
}
wdata2 = cifs_writedata_alloc(nr_pages, cifs_writev_complete);
if (!wdata2) {
rc = -ENOMEM;
break;
}
for (j = 0; j < nr_pages; j++) {
wdata2->pages[j] = wdata->pages[i + j];
lock_page(wdata2->pages[j]);
clear_page_dirty_for_io(wdata2->pages[j]);
}
wdata2->sync_mode = wdata->sync_mode;
wdata2->nr_pages = nr_pages;
wdata2->offset = page_offset(wdata2->pages[0]);
wdata2->pagesz = PAGE_SIZE;
wdata2->tailsz = tailsz;
wdata2->bytes = cur_len;
rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY,
&wdata2->cfile);
if (!wdata2->cfile) {
cifs_dbg(VFS, "No writable handle to retry writepages rc=%d\n",
rc);
if (!is_retryable_error(rc))
rc = -EBADF;
} else {
wdata2->pid = wdata2->cfile->pid;
rc = server->ops->async_writev(wdata2,
cifs_writedata_release);
}
for (j = 0; j < nr_pages; j++) {
unlock_page(wdata2->pages[j]);
if (rc != 0 && !is_retryable_error(rc)) {
SetPageError(wdata2->pages[j]);
end_page_writeback(wdata2->pages[j]);
put_page(wdata2->pages[j]);
}
}
kref_put(&wdata2->refcount, cifs_writedata_release);
if (rc) {
if (is_retryable_error(rc))
continue;
i += nr_pages;
break;
}
rest_len -= cur_len;
i += nr_pages;
} while (i < wdata->nr_pages);
/* cleanup remaining pages from the original wdata */
for (; i < wdata->nr_pages; i++) {
SetPageError(wdata->pages[i]);
end_page_writeback(wdata->pages[i]);
put_page(wdata->pages[i]);
}
if (rc != 0 && !is_retryable_error(rc))
mapping_set_error(inode->i_mapping, rc);
kref_put(&wdata->refcount, cifs_writedata_release);
}
void
cifs_writev_complete(struct work_struct *work)
{
struct cifs_writedata *wdata = container_of(work,
struct cifs_writedata, work);
struct inode *inode = d_inode(wdata->cfile->dentry);
int i = 0;
if (wdata->result == 0) {
spin_lock(&inode->i_lock);
cifs_update_eof(CIFS_I(inode), wdata->offset, wdata->bytes);
spin_unlock(&inode->i_lock);
cifs_stats_bytes_written(tlink_tcon(wdata->cfile->tlink),
wdata->bytes);
} else if (wdata->sync_mode == WB_SYNC_ALL && wdata->result == -EAGAIN)
return cifs_writev_requeue(wdata);
for (i = 0; i < wdata->nr_pages; i++) {
struct page *page = wdata->pages[i];
if (wdata->result == -EAGAIN)
__set_page_dirty_nobuffers(page);
else if (wdata->result < 0)
SetPageError(page);
end_page_writeback(page);
cifs_readpage_to_fscache(inode, page);
put_page(page);
}
if (wdata->result != -EAGAIN)
mapping_set_error(inode->i_mapping, wdata->result);
kref_put(&wdata->refcount, cifs_writedata_release);
}
struct cifs_writedata *
cifs_writedata_alloc(unsigned int nr_pages, work_func_t complete)
{
struct page **pages =
kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
if (pages)
return cifs_writedata_direct_alloc(pages, complete);
return NULL;
}
struct cifs_writedata *
cifs_writedata_direct_alloc(struct page **pages, work_func_t complete)
{
struct cifs_writedata *wdata;
wdata = kzalloc(sizeof(*wdata), GFP_NOFS);
if (wdata != NULL) {
wdata->pages = pages;
kref_init(&wdata->refcount);
INIT_LIST_HEAD(&wdata->list);
init_completion(&wdata->done);
INIT_WORK(&wdata->work, complete);
}
return wdata;
}
static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to)
{
struct address_space *mapping = page->mapping;
loff_t offset = (loff_t)page->index << PAGE_SHIFT;
char *write_data;
int rc = -EFAULT;
int bytes_written = 0;
struct inode *inode;
struct cifsFileInfo *open_file;
if (!mapping || !mapping->host)
return -EFAULT;
inode = page->mapping->host;
offset += (loff_t)from;
write_data = kmap(page);
write_data += from;
if ((to > PAGE_SIZE) || (from > to)) {
kunmap(page);
return -EIO;
}
/* racing with truncate? */
if (offset > mapping->host->i_size) {
kunmap(page);
return 0; /* don't care */
}
/* check to make sure that we are not extending the file */
if (mapping->host->i_size - offset < (loff_t)to)
to = (unsigned)(mapping->host->i_size - offset);
rc = cifs_get_writable_file(CIFS_I(mapping->host), FIND_WR_ANY,
&open_file);
if (!rc) {
bytes_written = cifs_write(open_file, open_file->pid,
write_data, to - from, &offset);
cifsFileInfo_put(open_file);
/* Does mm or vfs already set times? */
inode->i_atime = inode->i_mtime = current_time(inode);
if ((bytes_written > 0) && (offset))
rc = 0;
else if (bytes_written < 0)
rc = bytes_written;
else
rc = -EFAULT;
} else {
cifs_dbg(FYI, "No writable handle for write page rc=%d\n", rc);
if (!is_retryable_error(rc))
rc = -EIO;
}
kunmap(page);
return rc;
}
static struct cifs_writedata *
wdata_alloc_and_fillpages(pgoff_t tofind, struct address_space *mapping,
pgoff_t end, pgoff_t *index,
unsigned int *found_pages)
{
struct cifs_writedata *wdata;
wdata = cifs_writedata_alloc((unsigned int)tofind,
cifs_writev_complete);
if (!wdata)
return NULL;
*found_pages = find_get_pages_range_tag(mapping, index, end,
PAGECACHE_TAG_DIRTY, tofind, wdata->pages);
return wdata;
}
static unsigned int
wdata_prepare_pages(struct cifs_writedata *wdata, unsigned int found_pages,
struct address_space *mapping,
struct writeback_control *wbc,
pgoff_t end, pgoff_t *index, pgoff_t *next, bool *done)
{
unsigned int nr_pages = 0, i;
struct page *page;
for (i = 0; i < found_pages; i++) {
page = wdata->pages[i];
/*
* At this point we hold neither the i_pages lock nor the
* page lock: the page may be truncated or invalidated
* (changing page->mapping to NULL), or even swizzled
* back from swapper_space to tmpfs file mapping
*/
if (nr_pages == 0)
lock_page(page);
else if (!trylock_page(page))
break;
if (unlikely(page->mapping != mapping)) {
unlock_page(page);
break;
}
if (!wbc->range_cyclic && page->index > end) {
*done = true;
unlock_page(page);
break;
}
if (*next && (page->index != *next)) {
/* Not next consecutive page */
unlock_page(page);
break;
}
if (wbc->sync_mode != WB_SYNC_NONE)
wait_on_page_writeback(page);
if (PageWriteback(page) ||
!clear_page_dirty_for_io(page)) {
unlock_page(page);
break;
}
/*
* This actually clears the dirty bit in the radix tree.
* See cifs_writepage() for more commentary.
*/
set_page_writeback(page);
if (page_offset(page) >= i_size_read(mapping->host)) {
*done = true;
unlock_page(page);
end_page_writeback(page);
break;
}
wdata->pages[i] = page;
*next = page->index + 1;
++nr_pages;
}
/* reset index to refind any pages skipped */
if (nr_pages == 0)
*index = wdata->pages[0]->index + 1;
/* put any pages we aren't going to use */
for (i = nr_pages; i < found_pages; i++) {
put_page(wdata->pages[i]);
wdata->pages[i] = NULL;
}
return nr_pages;
}
static int
wdata_send_pages(struct cifs_writedata *wdata, unsigned int nr_pages,
struct address_space *mapping, struct writeback_control *wbc)
{
int rc;
wdata->sync_mode = wbc->sync_mode;
wdata->nr_pages = nr_pages;
wdata->offset = page_offset(wdata->pages[0]);
wdata->pagesz = PAGE_SIZE;
wdata->tailsz = min(i_size_read(mapping->host) -
page_offset(wdata->pages[nr_pages - 1]),
(loff_t)PAGE_SIZE);
wdata->bytes = ((nr_pages - 1) * PAGE_SIZE) + wdata->tailsz;
wdata->pid = wdata->cfile->pid;
rc = adjust_credits(wdata->server, &wdata->credits, wdata->bytes);
if (rc)
return rc;
if (wdata->cfile->invalidHandle)
rc = -EAGAIN;
else
rc = wdata->server->ops->async_writev(wdata,
cifs_writedata_release);
return rc;
}
static int cifs_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct TCP_Server_Info *server;
bool done = false, scanned = false, range_whole = false;
pgoff_t end, index;
struct cifs_writedata *wdata;
struct cifsFileInfo *cfile = NULL;
int rc = 0;
int saved_rc = 0;
unsigned int xid;
/*
* If wsize is smaller than the page cache size, default to writing
* one page at a time via cifs_writepage
*/
if (cifs_sb->ctx->wsize < PAGE_SIZE)
return generic_writepages(mapping, wbc);
xid = get_xid();
if (wbc->range_cyclic) {
index = mapping->writeback_index; /* Start from prev offset */
end = -1;
} else {
index = wbc->range_start >> PAGE_SHIFT;
end = wbc->range_end >> PAGE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = true;
scanned = true;
}
server = cifs_pick_channel(cifs_sb_master_tcon(cifs_sb)->ses);
retry:
while (!done && index <= end) {
unsigned int i, nr_pages, found_pages, wsize;
pgoff_t next = 0, tofind, saved_index = index;
struct cifs_credits credits_on_stack;
struct cifs_credits *credits = &credits_on_stack;
int get_file_rc = 0;
if (cfile)
cifsFileInfo_put(cfile);
rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY, &cfile);
/* in case of an error store it to return later */
if (rc)
get_file_rc = rc;
rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->wsize,
&wsize, credits);
if (rc != 0) {
done = true;
break;
}
tofind = min((wsize / PAGE_SIZE) - 1, end - index) + 1;
wdata = wdata_alloc_and_fillpages(tofind, mapping, end, &index,
&found_pages);
if (!wdata) {
rc = -ENOMEM;
done = true;
add_credits_and_wake_if(server, credits, 0);
break;
}
if (found_pages == 0) {
kref_put(&wdata->refcount, cifs_writedata_release);
add_credits_and_wake_if(server, credits, 0);
break;
}
nr_pages = wdata_prepare_pages(wdata, found_pages, mapping, wbc,
end, &index, &next, &done);
/* nothing to write? */
if (nr_pages == 0) {
kref_put(&wdata->refcount, cifs_writedata_release);
add_credits_and_wake_if(server, credits, 0);
continue;
}
wdata->credits = credits_on_stack;
wdata->cfile = cfile;
wdata->server = server;
cfile = NULL;
if (!wdata->cfile) {
cifs_dbg(VFS, "No writable handle in writepages rc=%d\n",
get_file_rc);
if (is_retryable_error(get_file_rc))
rc = get_file_rc;
else
rc = -EBADF;
} else
rc = wdata_send_pages(wdata, nr_pages, mapping, wbc);
for (i = 0; i < nr_pages; ++i)
unlock_page(wdata->pages[i]);
/* send failure -- clean up the mess */
if (rc != 0) {
add_credits_and_wake_if(server, &wdata->credits, 0);
for (i = 0; i < nr_pages; ++i) {
if (is_retryable_error(rc))
redirty_page_for_writepage(wbc,
wdata->pages[i]);
else
SetPageError(wdata->pages[i]);
end_page_writeback(wdata->pages[i]);
put_page(wdata->pages[i]);
}
if (!is_retryable_error(rc))
mapping_set_error(mapping, rc);
}
kref_put(&wdata->refcount, cifs_writedata_release);
if (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN) {
index = saved_index;
continue;
}
/* Return immediately if we received a signal during writing */
if (is_interrupt_error(rc)) {
done = true;
break;
}
if (rc != 0 && saved_rc == 0)
saved_rc = rc;
wbc->nr_to_write -= nr_pages;
if (wbc->nr_to_write <= 0)
done = true;
index = next;
}
if (!scanned && !done) {
/*
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
*/
scanned = true;
index = 0;
goto retry;
}
if (saved_rc != 0)
rc = saved_rc;
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = index;
if (cfile)
cifsFileInfo_put(cfile);
free_xid(xid);
/* Indication to update ctime and mtime as close is deferred */
set_bit(CIFS_INO_MODIFIED_ATTR, &CIFS_I(inode)->flags);
return rc;
}
static int
cifs_writepage_locked(struct page *page, struct writeback_control *wbc)
{
int rc;
unsigned int xid;
xid = get_xid();
/* BB add check for wbc flags */
get_page(page);
if (!PageUptodate(page))
cifs_dbg(FYI, "ppw - page not up to date\n");
/*
* Set the "writeback" flag, and clear "dirty" in the radix tree.
*
* A writepage() implementation always needs to do either this,
* or re-dirty the page with "redirty_page_for_writepage()" in
* the case of a failure.
*
* Just unlocking the page will cause the radix tree tag-bits
* to fail to update with the state of the page correctly.
*/
set_page_writeback(page);
retry_write:
rc = cifs_partialpagewrite(page, 0, PAGE_SIZE);
if (is_retryable_error(rc)) {
if (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN)
goto retry_write;
redirty_page_for_writepage(wbc, page);
} else if (rc != 0) {
SetPageError(page);
mapping_set_error(page->mapping, rc);
} else {
SetPageUptodate(page);
}
end_page_writeback(page);
put_page(page);
free_xid(xid);
return rc;
}
static int cifs_writepage(struct page *page, struct writeback_control *wbc)
{
int rc = cifs_writepage_locked(page, wbc);
unlock_page(page);
return rc;
}
static int cifs_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
int rc;
struct inode *inode = mapping->host;
struct cifsFileInfo *cfile = file->private_data;
struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb);
__u32 pid;
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
pid = cfile->pid;
else
pid = current->tgid;
cifs_dbg(FYI, "write_end for page %p from pos %lld with %d bytes\n",
page, pos, copied);
if (PageChecked(page)) {
if (copied == len)
SetPageUptodate(page);
ClearPageChecked(page);
} else if (!PageUptodate(page) && copied == PAGE_SIZE)
SetPageUptodate(page);
if (!PageUptodate(page)) {
char *page_data;
unsigned offset = pos & (PAGE_SIZE - 1);
unsigned int xid;
xid = get_xid();
/* this is probably better than directly calling
partialpage_write since in this function the file handle is
known which we might as well leverage */
/* BB check if anything else missing out of ppw
such as updating last write time */
page_data = kmap(page);
rc = cifs_write(cfile, pid, page_data + offset, copied, &pos);
/* if (rc < 0) should we set writebehind rc? */
kunmap(page);
free_xid(xid);
} else {
rc = copied;
pos += copied;
set_page_dirty(page);
}
if (rc > 0) {
spin_lock(&inode->i_lock);
if (pos > inode->i_size) {
i_size_write(inode, pos);
inode->i_blocks = (512 - 1 + pos) >> 9;
}
spin_unlock(&inode->i_lock);
}
unlock_page(page);
put_page(page);
/* Indication to update ctime and mtime as close is deferred */
set_bit(CIFS_INO_MODIFIED_ATTR, &CIFS_I(inode)->flags);
return rc;
}
int cifs_strict_fsync(struct file *file, loff_t start, loff_t end,
int datasync)
{
unsigned int xid;
int rc = 0;
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
struct cifsFileInfo *smbfile = file->private_data;
struct inode *inode = file_inode(file);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
rc = file_write_and_wait_range(file, start, end);
if (rc) {
trace_cifs_fsync_err(inode->i_ino, rc);
return rc;
}
xid = get_xid();
cifs_dbg(FYI, "Sync file - name: %pD datasync: 0x%x\n",
file, datasync);
if (!CIFS_CACHE_READ(CIFS_I(inode))) {
rc = cifs_zap_mapping(inode);
if (rc) {
cifs_dbg(FYI, "rc: %d during invalidate phase\n", rc);
rc = 0; /* don't care about it in fsync */
}
}
tcon = tlink_tcon(smbfile->tlink);
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) {
server = tcon->ses->server;
if (server->ops->flush == NULL) {
rc = -ENOSYS;
goto strict_fsync_exit;
}
if ((OPEN_FMODE(smbfile->f_flags) & FMODE_WRITE) == 0) {
smbfile = find_writable_file(CIFS_I(inode), FIND_WR_ANY);
if (smbfile) {
rc = server->ops->flush(xid, tcon, &smbfile->fid);
cifsFileInfo_put(smbfile);
} else
cifs_dbg(FYI, "ignore fsync for file not open for write\n");
} else
rc = server->ops->flush(xid, tcon, &smbfile->fid);
}
strict_fsync_exit:
free_xid(xid);
return rc;
}
int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
unsigned int xid;
int rc = 0;
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
struct cifsFileInfo *smbfile = file->private_data;
struct inode *inode = file_inode(file);
struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
rc = file_write_and_wait_range(file, start, end);
if (rc) {
trace_cifs_fsync_err(file_inode(file)->i_ino, rc);
return rc;
}
xid = get_xid();
cifs_dbg(FYI, "Sync file - name: %pD datasync: 0x%x\n",
file, datasync);
tcon = tlink_tcon(smbfile->tlink);
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) {
server = tcon->ses->server;
if (server->ops->flush == NULL) {
rc = -ENOSYS;
goto fsync_exit;
}
if ((OPEN_FMODE(smbfile->f_flags) & FMODE_WRITE) == 0) {
smbfile = find_writable_file(CIFS_I(inode), FIND_WR_ANY);
if (smbfile) {
rc = server->ops->flush(xid, tcon, &smbfile->fid);
cifsFileInfo_put(smbfile);
} else
cifs_dbg(FYI, "ignore fsync for file not open for write\n");
} else
rc = server->ops->flush(xid, tcon, &smbfile->fid);
}
fsync_exit:
free_xid(xid);
return rc;
}
/*
* As file closes, flush all cached write data for this inode checking
* for write behind errors.
*/
int cifs_flush(struct file *file, fl_owner_t id)
{
struct inode *inode = file_inode(file);
int rc = 0;
if (file->f_mode & FMODE_WRITE)
rc = filemap_write_and_wait(inode->i_mapping);
cifs_dbg(FYI, "Flush inode %p file %p rc %d\n", inode, file, rc);
if (rc) {
/* get more nuanced writeback errors */
rc = filemap_check_wb_err(file->f_mapping, 0);
trace_cifs_flush_err(inode->i_ino, rc);
}
return rc;
}
static int
cifs_write_allocate_pages(struct page **pages, unsigned long num_pages)
{
int rc = 0;
unsigned long i;
for (i = 0; i < num_pages; i++) {
pages[i] = alloc_page(GFP_KERNEL|__GFP_HIGHMEM);
if (!pages[i]) {
/*
* save number of pages we have already allocated and
* return with ENOMEM error
*/
num_pages = i;
rc = -ENOMEM;
break;
}
}
if (rc) {
for (i = 0; i < num_pages; i++)
put_page(pages[i]);
}
return rc;
}
static inline
size_t get_numpages(const size_t wsize, const size_t len, size_t *cur_len)
{
size_t num_pages;
size_t clen;
clen = min_t(const size_t, len, wsize);
num_pages = DIV_ROUND_UP(clen, PAGE_SIZE);
if (cur_len)
*cur_len = clen;
return num_pages;
}
static void
cifs_uncached_writedata_release(struct kref *refcount)
{
int i;
struct cifs_writedata *wdata = container_of(refcount,
struct cifs_writedata, refcount);
kref_put(&wdata->ctx->refcount, cifs_aio_ctx_release);
for (i = 0; i < wdata->nr_pages; i++)
put_page(wdata->pages[i]);
cifs_writedata_release(refcount);
}
static void collect_uncached_write_data(struct cifs_aio_ctx *ctx);
static void
cifs_uncached_writev_complete(struct work_struct *work)
{
struct cifs_writedata *wdata = container_of(work,
struct cifs_writedata, work);
struct inode *inode = d_inode(wdata->cfile->dentry);
struct cifsInodeInfo *cifsi = CIFS_I(inode);
spin_lock(&inode->i_lock);
cifs_update_eof(cifsi, wdata->offset, wdata->bytes);
if (cifsi->server_eof > inode->i_size)
i_size_write(inode, cifsi->server_eof);
spin_unlock(&inode->i_lock);
complete(&wdata->done);
collect_uncached_write_data(wdata->ctx);
/* the below call can possibly free the last ref to aio ctx */
kref_put(&wdata->refcount, cifs_uncached_writedata_release);
}
static int
wdata_fill_from_iovec(struct cifs_writedata *wdata, struct iov_iter *from,
size_t *len, unsigned long *num_pages)
{
size_t save_len, copied, bytes, cur_len = *len;
unsigned long i, nr_pages = *num_pages;
save_len = cur_len;
for (i = 0; i < nr_pages; i++) {
bytes = min_t(const size_t, cur_len, PAGE_SIZE);
copied = copy_page_from_iter(wdata->pages[i], 0, bytes, from);
cur_len -= copied;
/*
* If we didn't copy as much as we expected, then that
* may mean we trod into an unmapped area. Stop copying
* at that point. On the next pass through the big
* loop, we'll likely end up getting a zero-length
* write and bailing out of it.
*/
if (copied < bytes)
break;
}
cur_len = save_len - cur_len;
*len = cur_len;
/*
* If we have no data to send, then that probably means that
* the copy above failed altogether. That's most likely because
* the address in the iovec was bogus. Return -EFAULT and let
* the caller free anything we allocated and bail out.
*/
if (!cur_len)
return -EFAULT;
/*
* i + 1 now represents the number of pages we actually used in
* the copy phase above.
*/
*num_pages = i + 1;
return 0;
}
static int
cifs_resend_wdata(struct cifs_writedata *wdata, struct list_head *wdata_list,
struct cifs_aio_ctx *ctx)
{
unsigned int wsize;
struct cifs_credits credits;
int rc;
struct TCP_Server_Info *server = wdata->server;
do {
if (wdata->cfile->invalidHandle) {
rc = cifs_reopen_file(wdata->cfile, false);
if (rc == -EAGAIN)
continue;
else if (rc)
break;
}
/*
* Wait for credits to resend this wdata.
* Note: we are attempting to resend the whole wdata not in
* segments
*/
do {
rc = server->ops->wait_mtu_credits(server, wdata->bytes,
&wsize, &credits);
if (rc)
goto fail;
if (wsize < wdata->bytes) {
add_credits_and_wake_if(server, &credits, 0);
msleep(1000);
}
} while (wsize < wdata->bytes);
wdata->credits = credits;
rc = adjust_credits(server, &wdata->credits, wdata->bytes);
if (!rc) {
if (wdata->cfile->invalidHandle)
rc = -EAGAIN;
else {
#ifdef CONFIG_CIFS_SMB_DIRECT
if (wdata->mr) {
wdata->mr->need_invalidate = true;
smbd_deregister_mr(wdata->mr);
wdata->mr = NULL;
}
#endif
rc = server->ops->async_writev(wdata,
cifs_uncached_writedata_release);
}
}
/* If the write was successfully sent, we are done */
if (!rc) {
list_add_tail(&wdata->list, wdata_list);
return 0;
}
/* Roll back credits and retry if needed */
add_credits_and_wake_if(server, &wdata->credits, 0);
} while (rc == -EAGAIN);
fail:
kref_put(&wdata->refcount, cifs_uncached_writedata_release);
return rc;
}
static int
cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
struct cifsFileInfo *open_file,
struct cifs_sb_info *cifs_sb, struct list_head *wdata_list,
struct cifs_aio_ctx *ctx)
{
int rc = 0;
size_t cur_len;
unsigned long nr_pages, num_pages, i;
struct cifs_writedata *wdata;
struct iov_iter saved_from = *from;
loff_t saved_offset = offset;
pid_t pid;
struct TCP_Server_Info *server;
struct page **pagevec;
size_t start;
unsigned int xid;
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
pid = open_file->pid;
else
pid = current->tgid;
server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses);
xid = get_xid();
do {
unsigned int wsize;
struct cifs_credits credits_on_stack;
struct cifs_credits *credits = &credits_on_stack;
if (open_file->invalidHandle) {
rc = cifs_reopen_file(open_file, false);
if (rc == -EAGAIN)
continue;
else if (rc)
break;
}
rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->wsize,
&wsize, credits);
if (rc)
break;
cur_len = min_t(const size_t, len, wsize);
if (ctx->direct_io) {
ssize_t result;
result = iov_iter_get_pages_alloc2(
from, &pagevec, cur_len, &start);
if (result < 0) {
cifs_dbg(VFS,
"direct_writev couldn't get user pages (rc=%zd) iter type %d iov_offset %zd count %zd\n",
result, iov_iter_type(from),
from->iov_offset, from->count);
dump_stack();
rc = result;
add_credits_and_wake_if(server, credits, 0);
break;
}
cur_len = (size_t)result;
nr_pages =
(cur_len + start + PAGE_SIZE - 1) / PAGE_SIZE;
wdata = cifs_writedata_direct_alloc(pagevec,
cifs_uncached_writev_complete);
if (!wdata) {
rc = -ENOMEM;
add_credits_and_wake_if(server, credits, 0);
break;
}
wdata->page_offset = start;
wdata->tailsz =
nr_pages > 1 ?
cur_len - (PAGE_SIZE - start) -
(nr_pages - 2) * PAGE_SIZE :
cur_len;
} else {
nr_pages = get_numpages(wsize, len, &cur_len);
wdata = cifs_writedata_alloc(nr_pages,
cifs_uncached_writev_complete);
if (!wdata) {
rc = -ENOMEM;
add_credits_and_wake_if(server, credits, 0);
break;
}
rc = cifs_write_allocate_pages(wdata->pages, nr_pages);
if (rc) {
kvfree(wdata->pages);
kfree(wdata);
add_credits_and_wake_if(server, credits, 0);
break;
}
num_pages = nr_pages;
rc = wdata_fill_from_iovec(
wdata, from, &cur_len, &num_pages);
if (rc) {
for (i = 0; i < nr_pages; i++)
put_page(wdata->pages[i]);
kvfree(wdata->pages);
kfree(wdata);
add_credits_and_wake_if(server, credits, 0);
break;
}
/*
* Bring nr_pages down to the number of pages we
* actually used, and free any pages that we didn't use.
*/
for ( ; nr_pages > num_pages; nr_pages--)
put_page(wdata->pages[nr_pages - 1]);
wdata->tailsz = cur_len - ((nr_pages - 1) * PAGE_SIZE);
}
wdata->sync_mode = WB_SYNC_ALL;
wdata->nr_pages = nr_pages;
wdata->offset = (__u64)offset;
wdata->cfile = cifsFileInfo_get(open_file);
wdata->server = server;
wdata->pid = pid;
wdata->bytes = cur_len;
wdata->pagesz = PAGE_SIZE;
wdata->credits = credits_on_stack;
wdata->ctx = ctx;
kref_get(&ctx->refcount);
rc = adjust_credits(server, &wdata->credits, wdata->bytes);
if (!rc) {
if (wdata->cfile->invalidHandle)
rc = -EAGAIN;
else
rc = server->ops->async_writev(wdata,
cifs_uncached_writedata_release);
}
if (rc) {
add_credits_and_wake_if(server, &wdata->credits, 0);
kref_put(&wdata->refcount,
cifs_uncached_writedata_release);
if (rc == -EAGAIN) {
*from = saved_from;
iov_iter_advance(from, offset - saved_offset);
continue;
}
break;
}
list_add_tail(&wdata->list, wdata_list);
offset += cur_len;
len -= cur_len;
} while (len > 0);
free_xid(xid);
return rc;
}
static void collect_uncached_write_data(struct cifs_aio_ctx *ctx)
{
struct cifs_writedata *wdata, *tmp;
struct cifs_tcon *tcon;
struct cifs_sb_info *cifs_sb;
struct dentry *dentry = ctx->cfile->dentry;
ssize_t rc;
tcon = tlink_tcon(ctx->cfile->tlink);
cifs_sb = CIFS_SB(dentry->d_sb);
mutex_lock(&ctx->aio_mutex);
if (list_empty(&ctx->list)) {
mutex_unlock(&ctx->aio_mutex);
return;
}
rc = ctx->rc;
/*
* Wait for and collect replies for any successful sends in order of
* increasing offset. Once an error is hit, then return without waiting
* for any more replies.
*/
restart_loop:
list_for_each_entry_safe(wdata, tmp, &ctx->list, list) {
if (!rc) {
if (!try_wait_for_completion(&wdata->done)) {
mutex_unlock(&ctx->aio_mutex);
return;
}
if (wdata->result)
rc = wdata->result;
else
ctx->total_len += wdata->bytes;
/* resend call if it's a retryable error */
if (rc == -EAGAIN) {
struct list_head tmp_list;
struct iov_iter tmp_from = ctx->iter;
INIT_LIST_HEAD(&tmp_list);
list_del_init(&wdata->list);
if (ctx->direct_io)
rc = cifs_resend_wdata(
wdata, &tmp_list, ctx);
else {
iov_iter_advance(&tmp_from,
wdata->offset - ctx->pos);
rc = cifs_write_from_iter(wdata->offset,
wdata->bytes, &tmp_from,
ctx->cfile, cifs_sb, &tmp_list,
ctx);
kref_put(&wdata->refcount,
cifs_uncached_writedata_release);
}
list_splice(&tmp_list, &ctx->list);
goto restart_loop;
}
}
list_del_init(&wdata->list);
kref_put(&wdata->refcount, cifs_uncached_writedata_release);
}
cifs_stats_bytes_written(tcon, ctx->total_len);
set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(dentry->d_inode)->flags);
ctx->rc = (rc == 0) ? ctx->total_len : rc;
mutex_unlock(&ctx->aio_mutex);
if (ctx->iocb && ctx->iocb->ki_complete)
ctx->iocb->ki_complete(ctx->iocb, ctx->rc);
else
complete(&ctx->done);
}
static ssize_t __cifs_writev(
struct kiocb *iocb, struct iov_iter *from, bool direct)
{
struct file *file = iocb->ki_filp;
ssize_t total_written = 0;
struct cifsFileInfo *cfile;
struct cifs_tcon *tcon;
struct cifs_sb_info *cifs_sb;
struct cifs_aio_ctx *ctx;
struct iov_iter saved_from = *from;
size_t len = iov_iter_count(from);
int rc;
/*
* iov_iter_get_pages_alloc doesn't work with ITER_KVEC.
* In this case, fall back to non-direct write function.
* this could be improved by getting pages directly in ITER_KVEC
*/
if (direct && iov_iter_is_kvec(from)) {
cifs_dbg(FYI, "use non-direct cifs_writev for kvec I/O\n");
direct = false;
}
rc = generic_write_checks(iocb, from);
if (rc <= 0)
return rc;
cifs_sb = CIFS_FILE_SB(file);
cfile = file->private_data;
tcon = tlink_tcon(cfile->tlink);
if (!tcon->ses->server->ops->async_writev)
return -ENOSYS;
ctx = cifs_aio_ctx_alloc();
if (!ctx)
return -ENOMEM;
ctx->cfile = cifsFileInfo_get(cfile);
if (!is_sync_kiocb(iocb))
ctx->iocb = iocb;
ctx->pos = iocb->ki_pos;
if (direct) {
ctx->direct_io = true;
ctx->iter = *from;
ctx->len = len;
} else {
rc = setup_aio_ctx_iter(ctx, from, WRITE);
if (rc) {
kref_put(&ctx->refcount, cifs_aio_ctx_release);
return rc;
}
}
/* grab a lock here due to read response handlers can access ctx */
mutex_lock(&ctx->aio_mutex);
rc = cifs_write_from_iter(iocb->ki_pos, ctx->len, &saved_from,
cfile, cifs_sb, &ctx->list, ctx);
/*
* If at least one write was successfully sent, then discard any rc
* value from the later writes. If the other write succeeds, then
* we'll end up returning whatever was written. If it fails, then
* we'll get a new rc value from that.
*/
if (!list_empty(&ctx->list))
rc = 0;
mutex_unlock(&ctx->aio_mutex);
if (rc) {
kref_put(&ctx->refcount, cifs_aio_ctx_release);
return rc;
}
if (!is_sync_kiocb(iocb)) {
kref_put(&ctx->refcount, cifs_aio_ctx_release);
return -EIOCBQUEUED;
}
rc = wait_for_completion_killable(&ctx->done);
if (rc) {
mutex_lock(&ctx->aio_mutex);
ctx->rc = rc = -EINTR;
total_written = ctx->total_len;
mutex_unlock(&ctx->aio_mutex);
} else {
rc = ctx->rc;
total_written = ctx->total_len;
}
kref_put(&ctx->refcount, cifs_aio_ctx_release);
if (unlikely(!total_written))
return rc;
iocb->ki_pos += total_written;
return total_written;
}
ssize_t cifs_direct_writev(struct kiocb *iocb, struct iov_iter *from)
{
return __cifs_writev(iocb, from, true);
}
ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from)
{
return __cifs_writev(iocb, from, false);
}
static ssize_t
cifs_writev(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct cifsFileInfo *cfile = (struct cifsFileInfo *)file->private_data;
struct inode *inode = file->f_mapping->host;
struct cifsInodeInfo *cinode = CIFS_I(inode);
struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server;
ssize_t rc;
inode_lock(inode);
/*
* We need to hold the sem to be sure nobody modifies lock list
* with a brlock that prevents writing.
*/
down_read(&cinode->lock_sem);
rc = generic_write_checks(iocb, from);
if (rc <= 0)
goto out;
if (!cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(from),
server->vals->exclusive_lock_type, 0,
NULL, CIFS_WRITE_OP))
rc = __generic_file_write_iter(iocb, from);
else
rc = -EACCES;
out:
up_read(&cinode->lock_sem);
inode_unlock(inode);
if (rc > 0)
rc = generic_write_sync(iocb, rc);
return rc;
}
ssize_t
cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from)
{
struct inode *inode = file_inode(iocb->ki_filp);
struct cifsInodeInfo *cinode = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifsFileInfo *cfile = (struct cifsFileInfo *)
iocb->ki_filp->private_data;
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
ssize_t written;
written = cifs_get_writer(cinode);
if (written)
return written;
if (CIFS_CACHE_WRITE(cinode)) {
if (cap_unix(tcon->ses) &&
(CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))
&& ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) {
written = generic_file_write_iter(iocb, from);
goto out;
}
written = cifs_writev(iocb, from);
goto out;
}
/*
* For non-oplocked files in strict cache mode we need to write the data
* to the server exactly from the pos to pos+len-1 rather than flush all
* affected pages because it may cause a error with mandatory locks on
* these pages but not on the region from pos to ppos+len-1.
*/
written = cifs_user_writev(iocb, from);
if (CIFS_CACHE_READ(cinode)) {
/*
* We have read level caching and we have just sent a write
* request to the server thus making data in the cache stale.
* Zap the cache and set oplock/lease level to NONE to avoid
* reading stale data from the cache. All subsequent read
* operations will read new data from the server.
*/
cifs_zap_mapping(inode);
cifs_dbg(FYI, "Set Oplock/Lease to NONE for inode=%p after write\n",
inode);
cinode->oplock = 0;
}
out:
cifs_put_writer(cinode);
return written;
}
static struct cifs_readdata *
cifs_readdata_direct_alloc(struct page **pages, work_func_t complete)
{
struct cifs_readdata *rdata;
rdata = kzalloc(sizeof(*rdata), GFP_KERNEL);
if (rdata != NULL) {
rdata->pages = pages;
kref_init(&rdata->refcount);
INIT_LIST_HEAD(&rdata->list);
init_completion(&rdata->done);
INIT_WORK(&rdata->work, complete);
}
return rdata;
}
static struct cifs_readdata *
cifs_readdata_alloc(unsigned int nr_pages, work_func_t complete)
{
struct page **pages =
kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL);
struct cifs_readdata *ret = NULL;
if (pages) {
ret = cifs_readdata_direct_alloc(pages, complete);
if (!ret)
kfree(pages);
}
return ret;
}
void
cifs_readdata_release(struct kref *refcount)
{
struct cifs_readdata *rdata = container_of(refcount,
struct cifs_readdata, refcount);
#ifdef CONFIG_CIFS_SMB_DIRECT
if (rdata->mr) {
smbd_deregister_mr(rdata->mr);
rdata->mr = NULL;
}
#endif
if (rdata->cfile)
cifsFileInfo_put(rdata->cfile);
kvfree(rdata->pages);
kfree(rdata);
}
static int
cifs_read_allocate_pages(struct cifs_readdata *rdata, unsigned int nr_pages)
{
int rc = 0;
struct page *page;
unsigned int i;
for (i = 0; i < nr_pages; i++) {
page = alloc_page(GFP_KERNEL|__GFP_HIGHMEM);
if (!page) {
rc = -ENOMEM;
break;
}
rdata->pages[i] = page;
}
if (rc) {
unsigned int nr_page_failed = i;
for (i = 0; i < nr_page_failed; i++) {
put_page(rdata->pages[i]);
rdata->pages[i] = NULL;
}
}
return rc;
}
static void
cifs_uncached_readdata_release(struct kref *refcount)
{
struct cifs_readdata *rdata = container_of(refcount,
struct cifs_readdata, refcount);
unsigned int i;
kref_put(&rdata->ctx->refcount, cifs_aio_ctx_release);
for (i = 0; i < rdata->nr_pages; i++) {
put_page(rdata->pages[i]);
}
cifs_readdata_release(refcount);
}
/**
* cifs_readdata_to_iov - copy data from pages in response to an iovec
* @rdata: the readdata response with list of pages holding data
* @iter: destination for our data
*
* This function copies data from a list of pages in a readdata response into
* an array of iovecs. It will first calculate where the data should go
* based on the info in the readdata and then copy the data into that spot.
*/
static int
cifs_readdata_to_iov(struct cifs_readdata *rdata, struct iov_iter *iter)
{
size_t remaining = rdata->got_bytes;
unsigned int i;
for (i = 0; i < rdata->nr_pages; i++) {
struct page *page = rdata->pages[i];
size_t copy = min_t(size_t, remaining, PAGE_SIZE);
size_t written;
if (unlikely(iov_iter_is_pipe(iter))) {
void *addr = kmap_atomic(page);
written = copy_to_iter(addr, copy, iter);
kunmap_atomic(addr);
} else
written = copy_page_to_iter(page, 0, copy, iter);
remaining -= written;
if (written < copy && iov_iter_count(iter) > 0)
break;
}
return remaining ? -EFAULT : 0;
}
static void collect_uncached_read_data(struct cifs_aio_ctx *ctx);
static void
cifs_uncached_readv_complete(struct work_struct *work)
{
struct cifs_readdata *rdata = container_of(work,
struct cifs_readdata, work);
complete(&rdata->done);
collect_uncached_read_data(rdata->ctx);
/* the below call can possibly free the last ref to aio ctx */
kref_put(&rdata->refcount, cifs_uncached_readdata_release);
}
static int
uncached_fill_pages(struct TCP_Server_Info *server,
struct cifs_readdata *rdata, struct iov_iter *iter,
unsigned int len)
{
int result = 0;
unsigned int i;
unsigned int nr_pages = rdata->nr_pages;
unsigned int page_offset = rdata->page_offset;
rdata->got_bytes = 0;
rdata->tailsz = PAGE_SIZE;
for (i = 0; i < nr_pages; i++) {
struct page *page = rdata->pages[i];
size_t n;
unsigned int segment_size = rdata->pagesz;
if (i == 0)
segment_size -= page_offset;
else
page_offset = 0;
if (len <= 0) {
/* no need to hold page hostage */
rdata->pages[i] = NULL;
rdata->nr_pages--;
put_page(page);
continue;
}
n = len;
if (len >= segment_size)
/* enough data to fill the page */
n = segment_size;
else
rdata->tailsz = len;
len -= n;
if (iter)
result = copy_page_from_iter(
page, page_offset, n, iter);
#ifdef CONFIG_CIFS_SMB_DIRECT
else if (rdata->mr)
result = n;
#endif
else
result = cifs_read_page_from_socket(
server, page, page_offset, n);
if (result < 0)
break;
rdata->got_bytes += result;
}
return rdata->got_bytes > 0 && result != -ECONNABORTED ?
rdata->got_bytes : result;
}
static int
cifs_uncached_read_into_pages(struct TCP_Server_Info *server,
struct cifs_readdata *rdata, unsigned int len)
{
return uncached_fill_pages(server, rdata, NULL, len);
}
static int
cifs_uncached_copy_into_pages(struct TCP_Server_Info *server,
struct cifs_readdata *rdata,
struct iov_iter *iter)
{
return uncached_fill_pages(server, rdata, iter, iter->count);
}
static int cifs_resend_rdata(struct cifs_readdata *rdata,
struct list_head *rdata_list,
struct cifs_aio_ctx *ctx)
{
unsigned int rsize;
struct cifs_credits credits;
int rc;
struct TCP_Server_Info *server;
/* XXX: should we pick a new channel here? */
server = rdata->server;
do {
if (rdata->cfile->invalidHandle) {
rc = cifs_reopen_file(rdata->cfile, true);
if (rc == -EAGAIN)
continue;
else if (rc)
break;
}
/*
* Wait for credits to resend this rdata.
* Note: we are attempting to resend the whole rdata not in
* segments
*/
do {
rc = server->ops->wait_mtu_credits(server, rdata->bytes,
&rsize, &credits);
if (rc)
goto fail;
if (rsize < rdata->bytes) {
add_credits_and_wake_if(server, &credits, 0);
msleep(1000);
}
} while (rsize < rdata->bytes);
rdata->credits = credits;
rc = adjust_credits(server, &rdata->credits, rdata->bytes);
if (!rc) {
if (rdata->cfile->invalidHandle)
rc = -EAGAIN;
else {
#ifdef CONFIG_CIFS_SMB_DIRECT
if (rdata->mr) {
rdata->mr->need_invalidate = true;
smbd_deregister_mr(rdata->mr);
rdata->mr = NULL;
}
#endif
rc = server->ops->async_readv(rdata);
}
}
/* If the read was successfully sent, we are done */
if (!rc) {
/* Add to aio pending list */
list_add_tail(&rdata->list, rdata_list);
return 0;
}
/* Roll back credits and retry if needed */
add_credits_and_wake_if(server, &rdata->credits, 0);
} while (rc == -EAGAIN);
fail:
kref_put(&rdata->refcount, cifs_uncached_readdata_release);
return rc;
}
static int
cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
struct cifs_sb_info *cifs_sb, struct list_head *rdata_list,
struct cifs_aio_ctx *ctx)
{
struct cifs_readdata *rdata;
unsigned int npages, rsize;
struct cifs_credits credits_on_stack;
struct cifs_credits *credits = &credits_on_stack;
size_t cur_len;
int rc;
pid_t pid;
struct TCP_Server_Info *server;
struct page **pagevec;
size_t start;
struct iov_iter direct_iov = ctx->iter;
server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
pid = open_file->pid;
else
pid = current->tgid;
if (ctx->direct_io)
iov_iter_advance(&direct_iov, offset - ctx->pos);
do {
if (open_file->invalidHandle) {
rc = cifs_reopen_file(open_file, true);
if (rc == -EAGAIN)
continue;
else if (rc)
break;
}
if (cifs_sb->ctx->rsize == 0)
cifs_sb->ctx->rsize =
server->ops->negotiate_rsize(tlink_tcon(open_file->tlink),
cifs_sb->ctx);
rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize,
&rsize, credits);
if (rc)
break;
cur_len = min_t(const size_t, len, rsize);
if (ctx->direct_io) {
ssize_t result;
result = iov_iter_get_pages_alloc2(
&direct_iov, &pagevec,
cur_len, &start);
if (result < 0) {
cifs_dbg(VFS,
"Couldn't get user pages (rc=%zd) iter type %d iov_offset %zd count %zd\n",
result, iov_iter_type(&direct_iov),
direct_iov.iov_offset,
direct_iov.count);
dump_stack();
rc = result;
add_credits_and_wake_if(server, credits, 0);
break;
}
cur_len = (size_t)result;
rdata = cifs_readdata_direct_alloc(
pagevec, cifs_uncached_readv_complete);
if (!rdata) {
add_credits_and_wake_if(server, credits, 0);
rc = -ENOMEM;
break;
}
npages = (cur_len + start + PAGE_SIZE-1) / PAGE_SIZE;
rdata->page_offset = start;
rdata->tailsz = npages > 1 ?
cur_len-(PAGE_SIZE-start)-(npages-2)*PAGE_SIZE :
cur_len;
} else {
npages = DIV_ROUND_UP(cur_len, PAGE_SIZE);
/* allocate a readdata struct */
rdata = cifs_readdata_alloc(npages,
cifs_uncached_readv_complete);
if (!rdata) {
add_credits_and_wake_if(server, credits, 0);
rc = -ENOMEM;
break;
}
rc = cifs_read_allocate_pages(rdata, npages);
if (rc) {
kvfree(rdata->pages);
kfree(rdata);
add_credits_and_wake_if(server, credits, 0);
break;
}
rdata->tailsz = PAGE_SIZE;
}
rdata->server = server;
rdata->cfile = cifsFileInfo_get(open_file);
rdata->nr_pages = npages;
rdata->offset = offset;
rdata->bytes = cur_len;
rdata->pid = pid;
rdata->pagesz = PAGE_SIZE;
rdata->read_into_pages = cifs_uncached_read_into_pages;
rdata->copy_into_pages = cifs_uncached_copy_into_pages;
rdata->credits = credits_on_stack;
rdata->ctx = ctx;
kref_get(&ctx->refcount);
rc = adjust_credits(server, &rdata->credits, rdata->bytes);
if (!rc) {
if (rdata->cfile->invalidHandle)
rc = -EAGAIN;
else
rc = server->ops->async_readv(rdata);
}
if (rc) {
add_credits_and_wake_if(server, &rdata->credits, 0);
kref_put(&rdata->refcount,
cifs_uncached_readdata_release);
if (rc == -EAGAIN) {
iov_iter_revert(&direct_iov, cur_len);
continue;
}
break;
}
list_add_tail(&rdata->list, rdata_list);
offset += cur_len;
len -= cur_len;
} while (len > 0);
return rc;
}
static void
collect_uncached_read_data(struct cifs_aio_ctx *ctx)
{
struct cifs_readdata *rdata, *tmp;
struct iov_iter *to = &ctx->iter;
struct cifs_sb_info *cifs_sb;
int rc;
cifs_sb = CIFS_SB(ctx->cfile->dentry->d_sb);
mutex_lock(&ctx->aio_mutex);
if (list_empty(&ctx->list)) {
mutex_unlock(&ctx->aio_mutex);
return;
}
rc = ctx->rc;
/* the loop below should proceed in the order of increasing offsets */
again:
list_for_each_entry_safe(rdata, tmp, &ctx->list, list) {
if (!rc) {
if (!try_wait_for_completion(&rdata->done)) {
mutex_unlock(&ctx->aio_mutex);
return;
}
if (rdata->result == -EAGAIN) {
/* resend call if it's a retryable error */
struct list_head tmp_list;
unsigned int got_bytes = rdata->got_bytes;
list_del_init(&rdata->list);
INIT_LIST_HEAD(&tmp_list);
/*
* Got a part of data and then reconnect has
* happened -- fill the buffer and continue
* reading.
*/
if (got_bytes && got_bytes < rdata->bytes) {
rc = 0;
if (!ctx->direct_io)
rc = cifs_readdata_to_iov(rdata, to);
if (rc) {
kref_put(&rdata->refcount,
cifs_uncached_readdata_release);
continue;
}
}
if (ctx->direct_io) {
/*
* Re-use rdata as this is a
* direct I/O
*/
rc = cifs_resend_rdata(
rdata,
&tmp_list, ctx);
} else {
rc = cifs_send_async_read(
rdata->offset + got_bytes,
rdata->bytes - got_bytes,
rdata->cfile, cifs_sb,
&tmp_list, ctx);
kref_put(&rdata->refcount,
cifs_uncached_readdata_release);
}
list_splice(&tmp_list, &ctx->list);
goto again;
} else if (rdata->result)
rc = rdata->result;
else if (!ctx->direct_io)
rc = cifs_readdata_to_iov(rdata, to);
/* if there was a short read -- discard anything left */
if (rdata->got_bytes && rdata->got_bytes < rdata->bytes)
rc = -ENODATA;
ctx->total_len += rdata->got_bytes;
}
list_del_init(&rdata->list);
kref_put(&rdata->refcount, cifs_uncached_readdata_release);
}
if (!ctx->direct_io)
ctx->total_len = ctx->len - iov_iter_count(to);
/* mask nodata case */
if (rc == -ENODATA)
rc = 0;
ctx->rc = (rc == 0) ? (ssize_t)ctx->total_len : rc;
mutex_unlock(&ctx->aio_mutex);
if (ctx->iocb && ctx->iocb->ki_complete)
ctx->iocb->ki_complete(ctx->iocb, ctx->rc);
else
complete(&ctx->done);
}
static ssize_t __cifs_readv(
struct kiocb *iocb, struct iov_iter *to, bool direct)
{
size_t len;
struct file *file = iocb->ki_filp;
struct cifs_sb_info *cifs_sb;
struct cifsFileInfo *cfile;
struct cifs_tcon *tcon;
ssize_t rc, total_read = 0;
loff_t offset = iocb->ki_pos;
struct cifs_aio_ctx *ctx;
/*
* iov_iter_get_pages_alloc() doesn't work with ITER_KVEC,
* fall back to data copy read path
* this could be improved by getting pages directly in ITER_KVEC
*/
if (direct && iov_iter_is_kvec(to)) {
cifs_dbg(FYI, "use non-direct cifs_user_readv for kvec I/O\n");
direct = false;
}
len = iov_iter_count(to);
if (!len)
return 0;
cifs_sb = CIFS_FILE_SB(file);
cfile = file->private_data;
tcon = tlink_tcon(cfile->tlink);
if (!tcon->ses->server->ops->async_readv)
return -ENOSYS;
if ((file->f_flags & O_ACCMODE) == O_WRONLY)
cifs_dbg(FYI, "attempting read on write only file instance\n");
ctx = cifs_aio_ctx_alloc();
if (!ctx)
return -ENOMEM;
ctx->cfile = cifsFileInfo_get(cfile);
if (!is_sync_kiocb(iocb))
ctx->iocb = iocb;
if (user_backed_iter(to))
ctx->should_dirty = true;
if (direct) {
ctx->pos = offset;
ctx->direct_io = true;
ctx->iter = *to;
ctx->len = len;
} else {
rc = setup_aio_ctx_iter(ctx, to, READ);
if (rc) {
kref_put(&ctx->refcount, cifs_aio_ctx_release);
return rc;
}
len = ctx->len;
}
/* grab a lock here due to read response handlers can access ctx */
mutex_lock(&ctx->aio_mutex);
rc = cifs_send_async_read(offset, len, cfile, cifs_sb, &ctx->list, ctx);
/* if at least one read request send succeeded, then reset rc */
if (!list_empty(&ctx->list))
rc = 0;
mutex_unlock(&ctx->aio_mutex);
if (rc) {
kref_put(&ctx->refcount, cifs_aio_ctx_release);
return rc;
}
if (!is_sync_kiocb(iocb)) {
kref_put(&ctx->refcount, cifs_aio_ctx_release);
return -EIOCBQUEUED;
}
rc = wait_for_completion_killable(&ctx->done);
if (rc) {
mutex_lock(&ctx->aio_mutex);
ctx->rc = rc = -EINTR;
total_read = ctx->total_len;
mutex_unlock(&ctx->aio_mutex);
} else {
rc = ctx->rc;
total_read = ctx->total_len;
}
kref_put(&ctx->refcount, cifs_aio_ctx_release);
if (total_read) {
iocb->ki_pos += total_read;
return total_read;
}
return rc;
}
ssize_t cifs_direct_readv(struct kiocb *iocb, struct iov_iter *to)
{
return __cifs_readv(iocb, to, true);
}
ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to)
{
return __cifs_readv(iocb, to, false);
}
ssize_t
cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to)
{
struct inode *inode = file_inode(iocb->ki_filp);
struct cifsInodeInfo *cinode = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifsFileInfo *cfile = (struct cifsFileInfo *)
iocb->ki_filp->private_data;
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
int rc = -EACCES;
/*
* In strict cache mode we need to read from the server all the time
* if we don't have level II oplock because the server can delay mtime
* change - so we can't make a decision about inode invalidating.
* And we can also fail with pagereading if there are mandatory locks
* on pages affected by this read but not on the region from pos to
* pos+len-1.
*/
if (!CIFS_CACHE_READ(cinode))
return cifs_user_readv(iocb, to);
if (cap_unix(tcon->ses) &&
(CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
return generic_file_read_iter(iocb, to);
/*
* We need to hold the sem to be sure nobody modifies lock list
* with a brlock that prevents reading.
*/
down_read(&cinode->lock_sem);
if (!cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(to),
tcon->ses->server->vals->shared_lock_type,
0, NULL, CIFS_READ_OP))
rc = generic_file_read_iter(iocb, to);
up_read(&cinode->lock_sem);
return rc;
}
static ssize_t
cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset)
{
int rc = -EACCES;
unsigned int bytes_read = 0;
unsigned int total_read;
unsigned int current_read_size;
unsigned int rsize;
struct cifs_sb_info *cifs_sb;
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
unsigned int xid;
char *cur_offset;
struct cifsFileInfo *open_file;
struct cifs_io_parms io_parms = {0};
int buf_type = CIFS_NO_BUFFER;
__u32 pid;
xid = get_xid();
cifs_sb = CIFS_FILE_SB(file);
/* FIXME: set up handlers for larger reads and/or convert to async */
rsize = min_t(unsigned int, cifs_sb->ctx->rsize, CIFSMaxBufSize);
if (file->private_data == NULL) {
rc = -EBADF;
free_xid(xid);
return rc;
}
open_file = file->private_data;
tcon = tlink_tcon(open_file->tlink);
server = cifs_pick_channel(tcon->ses);
if (!server->ops->sync_read) {
free_xid(xid);
return -ENOSYS;
}
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
pid = open_file->pid;
else
pid = current->tgid;
if ((file->f_flags & O_ACCMODE) == O_WRONLY)
cifs_dbg(FYI, "attempting read on write only file instance\n");
for (total_read = 0, cur_offset = read_data; read_size > total_read;
total_read += bytes_read, cur_offset += bytes_read) {
do {
current_read_size = min_t(uint, read_size - total_read,
rsize);
/*
* For windows me and 9x we do not want to request more
* than it negotiated since it will refuse the read
* then.
*/
if (!(tcon->ses->capabilities &
tcon->ses->server->vals->cap_large_files)) {
current_read_size = min_t(uint,
current_read_size, CIFSMaxBufSize);
}
if (open_file->invalidHandle) {
rc = cifs_reopen_file(open_file, true);
if (rc != 0)
break;
}
io_parms.pid = pid;
io_parms.tcon = tcon;
io_parms.offset = *offset;
io_parms.length = current_read_size;
io_parms.server = server;
rc = server->ops->sync_read(xid, &open_file->fid, &io_parms,
&bytes_read, &cur_offset,
&buf_type);
} while (rc == -EAGAIN);
if (rc || (bytes_read == 0)) {
if (total_read) {
break;
} else {
free_xid(xid);
return rc;
}
} else {
cifs_stats_bytes_read(tcon, total_read);
*offset += bytes_read;
}
}
free_xid(xid);
return total_read;
}
/*
* If the page is mmap'ed into a process' page tables, then we need to make
* sure that it doesn't change while being written back.
*/
static vm_fault_t
cifs_page_mkwrite(struct vm_fault *vmf)
{
struct page *page = vmf->page;
/* Wait for the page to be written to the cache before we allow it to
* be modified. We then assume the entire page will need writing back.
*/
#ifdef CONFIG_CIFS_FSCACHE
if (PageFsCache(page) &&
wait_on_page_fscache_killable(page) < 0)
return VM_FAULT_RETRY;
#endif
wait_on_page_writeback(page);
if (lock_page_killable(page) < 0)
return VM_FAULT_RETRY;
return VM_FAULT_LOCKED;
}
static const struct vm_operations_struct cifs_file_vm_ops = {
.fault = filemap_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = cifs_page_mkwrite,
};
int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma)
{
int xid, rc = 0;
struct inode *inode = file_inode(file);
xid = get_xid();
if (!CIFS_CACHE_READ(CIFS_I(inode)))
rc = cifs_zap_mapping(inode);
if (!rc)
rc = generic_file_mmap(file, vma);
if (!rc)
vma->vm_ops = &cifs_file_vm_ops;
free_xid(xid);
return rc;
}
int cifs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
int rc, xid;
xid = get_xid();
rc = cifs_revalidate_file(file);
if (rc)
cifs_dbg(FYI, "Validation prior to mmap failed, error=%d\n",
rc);
if (!rc)
rc = generic_file_mmap(file, vma);
if (!rc)
vma->vm_ops = &cifs_file_vm_ops;
free_xid(xid);
return rc;
}
static void
cifs_readv_complete(struct work_struct *work)
{
unsigned int i, got_bytes;
struct cifs_readdata *rdata = container_of(work,
struct cifs_readdata, work);
got_bytes = rdata->got_bytes;
for (i = 0; i < rdata->nr_pages; i++) {
struct page *page = rdata->pages[i];
if (rdata->result == 0 ||
(rdata->result == -EAGAIN && got_bytes)) {
flush_dcache_page(page);
SetPageUptodate(page);
} else
SetPageError(page);
if (rdata->result == 0 ||
(rdata->result == -EAGAIN && got_bytes))
cifs_readpage_to_fscache(rdata->mapping->host, page);
unlock_page(page);
got_bytes -= min_t(unsigned int, PAGE_SIZE, got_bytes);
put_page(page);
rdata->pages[i] = NULL;
}
kref_put(&rdata->refcount, cifs_readdata_release);
}
static int
readpages_fill_pages(struct TCP_Server_Info *server,
struct cifs_readdata *rdata, struct iov_iter *iter,
unsigned int len)
{
int result = 0;
unsigned int i;
u64 eof;
pgoff_t eof_index;
unsigned int nr_pages = rdata->nr_pages;
unsigned int page_offset = rdata->page_offset;
/* determine the eof that the server (probably) has */
eof = CIFS_I(rdata->mapping->host)->server_eof;
eof_index = eof ? (eof - 1) >> PAGE_SHIFT : 0;
cifs_dbg(FYI, "eof=%llu eof_index=%lu\n", eof, eof_index);
rdata->got_bytes = 0;
rdata->tailsz = PAGE_SIZE;
for (i = 0; i < nr_pages; i++) {
struct page *page = rdata->pages[i];
unsigned int to_read = rdata->pagesz;
size_t n;
if (i == 0)
to_read -= page_offset;
else
page_offset = 0;
n = to_read;
if (len >= to_read) {
len -= to_read;
} else if (len > 0) {
/* enough for partial page, fill and zero the rest */
zero_user(page, len + page_offset, to_read - len);
n = rdata->tailsz = len;
len = 0;
} else if (page->index > eof_index) {
/*
* The VFS will not try to do readahead past the
* i_size, but it's possible that we have outstanding
* writes with gaps in the middle and the i_size hasn't
* caught up yet. Populate those with zeroed out pages
* to prevent the VFS from repeatedly attempting to
* fill them until the writes are flushed.
*/
zero_user(page, 0, PAGE_SIZE);
flush_dcache_page(page);
SetPageUptodate(page);
unlock_page(page);
put_page(page);
rdata->pages[i] = NULL;
rdata->nr_pages--;
continue;
} else {
/* no need to hold page hostage */
unlock_page(page);
put_page(page);
rdata->pages[i] = NULL;
rdata->nr_pages--;
continue;
}
if (iter)
result = copy_page_from_iter(
page, page_offset, n, iter);
#ifdef CONFIG_CIFS_SMB_DIRECT
else if (rdata->mr)
result = n;
#endif
else
result = cifs_read_page_from_socket(
server, page, page_offset, n);
if (result < 0)
break;
rdata->got_bytes += result;
}
return rdata->got_bytes > 0 && result != -ECONNABORTED ?
rdata->got_bytes : result;
}
static int
cifs_readpages_read_into_pages(struct TCP_Server_Info *server,
struct cifs_readdata *rdata, unsigned int len)
{
return readpages_fill_pages(server, rdata, NULL, len);
}
static int
cifs_readpages_copy_into_pages(struct TCP_Server_Info *server,
struct cifs_readdata *rdata,
struct iov_iter *iter)
{
return readpages_fill_pages(server, rdata, iter, iter->count);
}
static void cifs_readahead(struct readahead_control *ractl)
{
int rc;
struct cifsFileInfo *open_file = ractl->file->private_data;
struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(ractl->file);
struct TCP_Server_Info *server;
pid_t pid;
unsigned int xid, nr_pages, last_batch_size = 0, cache_nr_pages = 0;
pgoff_t next_cached = ULONG_MAX;
bool caching = fscache_cookie_enabled(cifs_inode_cookie(ractl->mapping->host)) &&
cifs_inode_cookie(ractl->mapping->host)->cache_priv;
bool check_cache = caching;
xid = get_xid();
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
pid = open_file->pid;
else
pid = current->tgid;
rc = 0;
server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses);
cifs_dbg(FYI, "%s: file=%p mapping=%p num_pages=%u\n",
__func__, ractl->file, ractl->mapping, readahead_count(ractl));
/*
* Chop the readahead request up into rsize-sized read requests.
*/
while ((nr_pages = readahead_count(ractl) - last_batch_size)) {
unsigned int i, got, rsize;
struct page *page;
struct cifs_readdata *rdata;
struct cifs_credits credits_on_stack;
struct cifs_credits *credits = &credits_on_stack;
pgoff_t index = readahead_index(ractl) + last_batch_size;
/*
* Find out if we have anything cached in the range of
* interest, and if so, where the next chunk of cached data is.
*/
if (caching) {
if (check_cache) {
rc = cifs_fscache_query_occupancy(
ractl->mapping->host, index, nr_pages,
&next_cached, &cache_nr_pages);
if (rc < 0)
caching = false;
check_cache = false;
}
if (index == next_cached) {
/*
* TODO: Send a whole batch of pages to be read
* by the cache.
*/
struct folio *folio = readahead_folio(ractl);
last_batch_size = folio_nr_pages(folio);
if (cifs_readpage_from_fscache(ractl->mapping->host,
&folio->page) < 0) {
/*
* TODO: Deal with cache read failure
* here, but for the moment, delegate
* that to readpage.
*/
caching = false;
}
folio_unlock(folio);
next_cached++;
cache_nr_pages--;
if (cache_nr_pages == 0)
check_cache = true;
continue;
}
}
if (open_file->invalidHandle) {
rc = cifs_reopen_file(open_file, true);
if (rc) {
if (rc == -EAGAIN)
continue;
break;
}
}
if (cifs_sb->ctx->rsize == 0)
cifs_sb->ctx->rsize =
server->ops->negotiate_rsize(tlink_tcon(open_file->tlink),
cifs_sb->ctx);
rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize,
&rsize, credits);
if (rc)
break;
nr_pages = min_t(size_t, rsize / PAGE_SIZE, readahead_count(ractl));
nr_pages = min_t(size_t, nr_pages, next_cached - index);
/*
* Give up immediately if rsize is too small to read an entire
* page. The VFS will fall back to readpage. We should never
* reach this point however since we set ra_pages to 0 when the
* rsize is smaller than a cache page.
*/
if (unlikely(!nr_pages)) {
add_credits_and_wake_if(server, credits, 0);
break;
}
rdata = cifs_readdata_alloc(nr_pages, cifs_readv_complete);
if (!rdata) {
/* best to give up if we're out of mem */
add_credits_and_wake_if(server, credits, 0);
break;
}
got = __readahead_batch(ractl, rdata->pages, nr_pages);
if (got != nr_pages) {
pr_warn("__readahead_batch() returned %u/%u\n",
got, nr_pages);
nr_pages = got;
}
rdata->nr_pages = nr_pages;
rdata->bytes = readahead_batch_length(ractl);
rdata->cfile = cifsFileInfo_get(open_file);
rdata->server = server;
rdata->mapping = ractl->mapping;
rdata->offset = readahead_pos(ractl);
rdata->pid = pid;
rdata->pagesz = PAGE_SIZE;
rdata->tailsz = PAGE_SIZE;
rdata->read_into_pages = cifs_readpages_read_into_pages;
rdata->copy_into_pages = cifs_readpages_copy_into_pages;
rdata->credits = credits_on_stack;
rc = adjust_credits(server, &rdata->credits, rdata->bytes);
if (!rc) {
if (rdata->cfile->invalidHandle)
rc = -EAGAIN;
else
rc = server->ops->async_readv(rdata);
}
if (rc) {
add_credits_and_wake_if(server, &rdata->credits, 0);
for (i = 0; i < rdata->nr_pages; i++) {
page = rdata->pages[i];
unlock_page(page);
put_page(page);
}
/* Fallback to the readpage in error/reconnect cases */
kref_put(&rdata->refcount, cifs_readdata_release);
break;
}
kref_put(&rdata->refcount, cifs_readdata_release);
last_batch_size = nr_pages;
}
free_xid(xid);
}
/*
* cifs_readpage_worker must be called with the page pinned
*/
static int cifs_readpage_worker(struct file *file, struct page *page,
loff_t *poffset)
{
char *read_data;
int rc;
/* Is the page cached? */
rc = cifs_readpage_from_fscache(file_inode(file), page);
if (rc == 0)
goto read_complete;
read_data = kmap(page);
/* for reads over a certain size could initiate async read ahead */
rc = cifs_read(file, read_data, PAGE_SIZE, poffset);
if (rc < 0)
goto io_error;
else
cifs_dbg(FYI, "Bytes read %d\n", rc);
/* we do not want atime to be less than mtime, it broke some apps */
file_inode(file)->i_atime = current_time(file_inode(file));
if (timespec64_compare(&(file_inode(file)->i_atime), &(file_inode(file)->i_mtime)))
file_inode(file)->i_atime = file_inode(file)->i_mtime;
else
file_inode(file)->i_atime = current_time(file_inode(file));
if (PAGE_SIZE > rc)
memset(read_data + rc, 0, PAGE_SIZE - rc);
flush_dcache_page(page);
SetPageUptodate(page);
/* send this page to the cache */
cifs_readpage_to_fscache(file_inode(file), page);
rc = 0;
io_error:
kunmap(page);
unlock_page(page);
read_complete:
return rc;
}
static int cifs_read_folio(struct file *file, struct folio *folio)
{
struct page *page = &folio->page;
loff_t offset = page_file_offset(page);
int rc = -EACCES;
unsigned int xid;
xid = get_xid();
if (file->private_data == NULL) {
rc = -EBADF;
free_xid(xid);
return rc;
}
cifs_dbg(FYI, "read_folio %p at offset %d 0x%x\n",
page, (int)offset, (int)offset);
rc = cifs_readpage_worker(file, page, &offset);
free_xid(xid);
return rc;
}
static int is_inode_writable(struct cifsInodeInfo *cifs_inode)
{
struct cifsFileInfo *open_file;
spin_lock(&cifs_inode->open_file_lock);
list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) {
spin_unlock(&cifs_inode->open_file_lock);
return 1;
}
}
spin_unlock(&cifs_inode->open_file_lock);
return 0;
}
/* We do not want to update the file size from server for inodes
open for write - to avoid races with writepage extending
the file - in the future we could consider allowing
refreshing the inode only on increases in the file size
but this is tricky to do without racing with writebehind
page caching in the current Linux kernel design */
bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file)
{
if (!cifsInode)
return true;
if (is_inode_writable(cifsInode)) {
/* This inode is open for write at least once */
struct cifs_sb_info *cifs_sb;
cifs_sb = CIFS_SB(cifsInode->netfs.inode.i_sb);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) {
/* since no page cache to corrupt on directio
we can change size safely */
return true;
}
if (i_size_read(&cifsInode->netfs.inode) < end_of_file)
return true;
return false;
} else
return true;
}
static int cifs_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len,
struct page **pagep, void **fsdata)
{
int oncethru = 0;
pgoff_t index = pos >> PAGE_SHIFT;
loff_t offset = pos & (PAGE_SIZE - 1);
loff_t page_start = pos & PAGE_MASK;
loff_t i_size;
struct page *page;
int rc = 0;
cifs_dbg(FYI, "write_begin from %lld len %d\n", (long long)pos, len);
start:
page = grab_cache_page_write_begin(mapping, index);
if (!page) {
rc = -ENOMEM;
goto out;
}
if (PageUptodate(page))
goto out;
/*
* If we write a full page it will be up to date, no need to read from
* the server. If the write is short, we'll end up doing a sync write
* instead.
*/
if (len == PAGE_SIZE)
goto out;
/*
* optimize away the read when we have an oplock, and we're not
* expecting to use any of the data we'd be reading in. That
* is, when the page lies beyond the EOF, or straddles the EOF
* and the write will cover all of the existing data.
*/
if (CIFS_CACHE_READ(CIFS_I(mapping->host))) {
i_size = i_size_read(mapping->host);
if (page_start >= i_size ||
(offset == 0 && (pos + len) >= i_size)) {
zero_user_segments(page, 0, offset,
offset + len,
PAGE_SIZE);
/*
* PageChecked means that the parts of the page
* to which we're not writing are considered up
* to date. Once the data is copied to the
* page, it can be set uptodate.
*/
SetPageChecked(page);
goto out;
}
}
if ((file->f_flags & O_ACCMODE) != O_WRONLY && !oncethru) {
/*
* might as well read a page, it is fast enough. If we get
* an error, we don't need to return it. cifs_write_end will
* do a sync write instead since PG_uptodate isn't set.
*/
cifs_readpage_worker(file, page, &page_start);
put_page(page);
oncethru = 1;
goto start;
} else {
/* we could try using another file handle if there is one -
but how would we lock it to prevent close of that handle
racing with this read? In any case
this will be written out by write_end so is fine */
}
out:
*pagep = page;
return rc;
}
static bool cifs_release_folio(struct folio *folio, gfp_t gfp)
{
if (folio_test_private(folio))
return 0;
if (folio_test_fscache(folio)) {
if (current_is_kswapd() || !(gfp & __GFP_FS))
return false;
folio_wait_fscache(folio);
}
fscache_note_page_release(cifs_inode_cookie(folio->mapping->host));
return true;
}
static void cifs_invalidate_folio(struct folio *folio, size_t offset,
size_t length)
{
folio_wait_fscache(folio);
}
static int cifs_launder_folio(struct folio *folio)
{
int rc = 0;
loff_t range_start = folio_pos(folio);
loff_t range_end = range_start + folio_size(folio);
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = 0,
.range_start = range_start,
.range_end = range_end,
};
cifs_dbg(FYI, "Launder page: %lu\n", folio->index);
if (folio_clear_dirty_for_io(folio))
rc = cifs_writepage_locked(&folio->page, &wbc);
folio_wait_fscache(folio);
return rc;
}
void cifs_oplock_break(struct work_struct *work)
{
struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo,
oplock_break);
struct inode *inode = d_inode(cfile->dentry);
struct cifsInodeInfo *cinode = CIFS_I(inode);
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
struct TCP_Server_Info *server = tcon->ses->server;
int rc = 0;
bool purge_cache = false;
bool is_deferred = false;
struct cifs_deferred_close *dclose;
wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS,
TASK_UNINTERRUPTIBLE);
server->ops->downgrade_oplock(server, cinode, cfile->oplock_level,
cfile->oplock_epoch, &purge_cache);
if (!CIFS_CACHE_WRITE(cinode) && CIFS_CACHE_READ(cinode) &&
cifs_has_mand_locks(cinode)) {
cifs_dbg(FYI, "Reset oplock to None for inode=%p due to mand locks\n",
inode);
cinode->oplock = 0;
}
if (inode && S_ISREG(inode->i_mode)) {
if (CIFS_CACHE_READ(cinode))
break_lease(inode, O_RDONLY);
else
break_lease(inode, O_WRONLY);
rc = filemap_fdatawrite(inode->i_mapping);
if (!CIFS_CACHE_READ(cinode) || purge_cache) {
rc = filemap_fdatawait(inode->i_mapping);
mapping_set_error(inode->i_mapping, rc);
cifs_zap_mapping(inode);
}
cifs_dbg(FYI, "Oplock flush inode %p rc %d\n", inode, rc);
if (CIFS_CACHE_WRITE(cinode))
goto oplock_break_ack;
}
rc = cifs_push_locks(cfile);
if (rc)
cifs_dbg(VFS, "Push locks rc = %d\n", rc);
oplock_break_ack:
/*
* When oplock break is received and there are no active
* file handles but cached, then schedule deferred close immediately.
* So, new open will not use cached handle.
*/
spin_lock(&CIFS_I(inode)->deferred_lock);
is_deferred = cifs_is_deferred_close(cfile, &dclose);
spin_unlock(&CIFS_I(inode)->deferred_lock);
if (is_deferred &&
cfile->deferred_close_scheduled &&
delayed_work_pending(&cfile->deferred)) {
if (cancel_delayed_work(&cfile->deferred)) {
_cifsFileInfo_put(cfile, false, false);
goto oplock_break_done;
}
}
/*
* releasing stale oplock after recent reconnect of smb session using
* a now incorrect file handle is not a data integrity issue but do
* not bother sending an oplock release if session to server still is
* disconnected since oplock already released by the server
*/
if (!cfile->oplock_break_cancelled) {
rc = tcon->ses->server->ops->oplock_response(tcon, &cfile->fid,
cinode);
cifs_dbg(FYI, "Oplock release rc = %d\n", rc);
}
oplock_break_done:
_cifsFileInfo_put(cfile, false /* do not wait for ourself */, false);
cifs_done_oplock_break(cinode);
}
/*
* The presence of cifs_direct_io() in the address space ops vector
* allowes open() O_DIRECT flags which would have failed otherwise.
*
* In the non-cached mode (mount with cache=none), we shunt off direct read and write requests
* so this method should never be called.
*
* Direct IO is not yet supported in the cached mode.
*/
static ssize_t
cifs_direct_io(struct kiocb *iocb, struct iov_iter *iter)
{
/*
* FIXME
* Eventually need to support direct IO for non forcedirectio mounts
*/
return -EINVAL;
}
static int cifs_swap_activate(struct swap_info_struct *sis,
struct file *swap_file, sector_t *span)
{
struct cifsFileInfo *cfile = swap_file->private_data;
struct inode *inode = swap_file->f_mapping->host;
unsigned long blocks;
long long isize;
cifs_dbg(FYI, "swap activate\n");
if (!swap_file->f_mapping->a_ops->swap_rw)
/* Cannot support swap */
return -EINVAL;
spin_lock(&inode->i_lock);
blocks = inode->i_blocks;
isize = inode->i_size;
spin_unlock(&inode->i_lock);
if (blocks*512 < isize) {
pr_warn("swap activate: swapfile has holes\n");
return -EINVAL;
}
*span = sis->pages;
pr_warn_once("Swap support over SMB3 is experimental\n");
/*
* TODO: consider adding ACL (or documenting how) to prevent other
* users (on this or other systems) from reading it
*/
/* TODO: add sk_set_memalloc(inet) or similar */
if (cfile)
cfile->swapfile = true;
/*
* TODO: Since file already open, we can't open with DENY_ALL here
* but we could add call to grab a byte range lock to prevent others
* from reading or writing the file
*/
sis->flags |= SWP_FS_OPS;
return add_swap_extent(sis, 0, sis->max, 0);
}
static void cifs_swap_deactivate(struct file *file)
{
struct cifsFileInfo *cfile = file->private_data;
cifs_dbg(FYI, "swap deactivate\n");
/* TODO: undo sk_set_memalloc(inet) will eventually be needed */
if (cfile)
cfile->swapfile = false;
/* do we need to unpin (or unlock) the file */
}
/*
* Mark a page as having been made dirty and thus needing writeback. We also
* need to pin the cache object to write back to.
*/
#ifdef CONFIG_CIFS_FSCACHE
static bool cifs_dirty_folio(struct address_space *mapping, struct folio *folio)
{
return fscache_dirty_folio(mapping, folio,
cifs_inode_cookie(mapping->host));
}
#else
#define cifs_dirty_folio filemap_dirty_folio
#endif
const struct address_space_operations cifs_addr_ops = {
.read_folio = cifs_read_folio,
.readahead = cifs_readahead,
.writepage = cifs_writepage,
.writepages = cifs_writepages,
.write_begin = cifs_write_begin,
.write_end = cifs_write_end,
.dirty_folio = cifs_dirty_folio,
.release_folio = cifs_release_folio,
.direct_IO = cifs_direct_io,
.invalidate_folio = cifs_invalidate_folio,
.launder_folio = cifs_launder_folio,
/*
* TODO: investigate and if useful we could add an cifs_migratePage
* helper (under an CONFIG_MIGRATION) in the future, and also
* investigate and add an is_dirty_writeback helper if needed
*/
.swap_activate = cifs_swap_activate,
.swap_deactivate = cifs_swap_deactivate,
};
/*
* cifs_readahead requires the server to support a buffer large enough to
* contain the header plus one complete page of data. Otherwise, we need
* to leave cifs_readahead out of the address space operations.
*/
const struct address_space_operations cifs_addr_ops_smallbuf = {
.read_folio = cifs_read_folio,
.writepage = cifs_writepage,
.writepages = cifs_writepages,
.write_begin = cifs_write_begin,
.write_end = cifs_write_end,
.dirty_folio = cifs_dirty_folio,
.release_folio = cifs_release_folio,
.invalidate_folio = cifs_invalidate_folio,
.launder_folio = cifs_launder_folio,
};