linux/fs/nfs/nfs4file.c
Linus Torvalds 6860c981b9 NFS client updates for Linux 5.3
Highlights include:
 
 Stable fixes:
 - SUNRPC: Ensure bvecs are re-synced when we re-encode the RPC request
 - Fix an Oops in ff_layout_track_ds_error due to a PTR_ERR() dereference
 - Revert buggy NFS readdirplus optimisation
 - NFSv4: Handle the special Linux file open access mode
 - pnfs: Fix a problem where we gratuitously start doing I/O through the MDS
 
 Features:
 - Allow NFS client to set up multiple TCP connections to the server using
    a new 'nconnect=X' mount option. Queue length is used to balance load.
 - Enhance statistics reporting to report on all transports when using
    multiple connections.
 - Speed up SUNRPC by removing bh-safe spinlocks
 - Add a mechanism to allow NFSv4 to request that containers set a
    unique per-host identifier for when the hostname is not set.
 - Ensure NFSv4 updates the lease_time after a clientid update
 
 Bugfixes and cleanup:
 - Fix use-after-free in rpcrdma_post_recvs
 - Fix a memory leak when nfs_match_client() is interrupted
 - Fix buggy file access checking in NFSv4 open for execute
 - disable unsupported client side deduplication
 - Fix spurious client disconnections
 - Fix occasional RDMA transport deadlock
 - Various RDMA cleanups
 - Various tracepoint fixes
 - Fix the TCP callback channel to guarantee the server can actually send
    the number of callback requests that was negotiated at mount time.
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEESQctxSBg8JpV8KqEZwvnipYKAPIFAl0wz/EACgkQZwvnipYK
 APJUrQ/9FpbWTaI/H0BkBf+/iIDAwuGozldDDRkHpHvykvcbNSFPNk5CA4fV/lCq
 rI0tD9ijj0KJhAjS1RWLb9oXMUm/MDIIcZNvsbOiIfGftzGnxAz022KS2JyV+Xk6
 ul7sCQ8QmbQJzfZk+aFZxl5slS9i5nM+Sa//k5SK3JghOlLuYkW50OlmE6ME8rKP
 sLWD2quLh1J5mjG+B9ml4YWozNi0elFN6ZqdzO/SjIhIG7rn2Hkr0glWcEprdiS7
 qHoF6dIn80oR37YNrcbBtEGqBnMnWkpGAGq2Hgf5I2YtO+xfEgMqqs9FNIcahtQG
 SGa1bnpcys9+fG4fnwzgOgYkvGzKdi/bIYc8lhBowl+76z+6VgjwlwT3wRtnWfO9
 288LZDMMfOSYoDkbA9iGtoQRviIsoGMoeH/r5tZe7U1W35h60NGPVhH9sP9/Gc2s
 Va1xBYK6PaIg+UxeghJmCnNK3zANyEI7AtDVvn0wsJuDcgXO5/PAANenc6/Fl6nf
 U9XB4wmgaM2jN5uqLYT3bJAaAPAXTOayVnnd9oDYb87/31sYM6iwzSPkmm5+qIsi
 0Ftks4PSjpjTTrmUvs3CL+ll3Y9bWUd58qlooGwi6u1DnXDQDzbIoRQBezNFJ+Lc
 MahUVY7w9ATyJFJRvbscO7mRS8qTmr4qP91bAOsYQ0P2Yo02L7k=
 =eR7d
 -----END PGP SIGNATURE-----

Merge tag 'nfs-for-5.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

  Stable fixes:

   - SUNRPC: Ensure bvecs are re-synced when we re-encode the RPC
     request

   - Fix an Oops in ff_layout_track_ds_error due to a PTR_ERR()
     dereference

   - Revert buggy NFS readdirplus optimisation

   - NFSv4: Handle the special Linux file open access mode

   - pnfs: Fix a problem where we gratuitously start doing I/O through
     the MDS

  Features:

   - Allow NFS client to set up multiple TCP connections to the server
     using a new 'nconnect=X' mount option. Queue length is used to
     balance load.

   - Enhance statistics reporting to report on all transports when using
     multiple connections.

   - Speed up SUNRPC by removing bh-safe spinlocks

   - Add a mechanism to allow NFSv4 to request that containers set a
     unique per-host identifier for when the hostname is not set.

   - Ensure NFSv4 updates the lease_time after a clientid update

  Bugfixes and cleanup:

   - Fix use-after-free in rpcrdma_post_recvs

   - Fix a memory leak when nfs_match_client() is interrupted

   - Fix buggy file access checking in NFSv4 open for execute

   - disable unsupported client side deduplication

   - Fix spurious client disconnections

   - Fix occasional RDMA transport deadlock

   - Various RDMA cleanups

   - Various tracepoint fixes

   - Fix the TCP callback channel to guarantee the server can actually
     send the number of callback requests that was negotiated at mount
     time"

* tag 'nfs-for-5.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (68 commits)
  pnfs/flexfiles: Add tracepoints for detecting pnfs fallback to MDS
  pnfs: Fix a problem where we gratuitously start doing I/O through the MDS
  SUNRPC: Optimise transport balancing code
  SUNRPC: Ensure the bvecs are reset when we re-encode the RPC request
  pnfs/flexfiles: Fix PTR_ERR() dereferences in ff_layout_track_ds_error
  NFSv4: Don't use the zero stateid with layoutget
  SUNRPC: Fix up backchannel slot table accounting
  SUNRPC: Fix initialisation of struct rpc_xprt_switch
  SUNRPC: Skip zero-refcount transports
  SUNRPC: Replace division by multiplication in calculation of queue length
  NFSv4: Validate the stateid before applying it to state recovery
  nfs4.0: Refetch lease_time after clientid update
  nfs4: Rename nfs41_setup_state_renewal
  nfs4: Make nfs4_proc_get_lease_time available for nfs4.0
  nfs: Fix copy-and-paste error in debug message
  NFS: Replace 16 seq_printf() calls by seq_puts()
  NFS: Use seq_putc() in nfs_show_stats()
  Revert "NFS: readdirplus optimization by cache mechanism" (memleak)
  SUNRPC: Fix transport accounting when caller specifies an rpc_xprt
  NFS: Record task, client ID, and XID in xdr_status trace points
  ...
2019-07-18 14:32:33 -07:00

291 lines
7.1 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/nfs/file.c
*
* Copyright (C) 1992 Rick Sladkey
*/
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/falloc.h>
#include <linux/nfs_fs.h>
#include "delegation.h"
#include "internal.h"
#include "iostat.h"
#include "fscache.h"
#include "pnfs.h"
#include "nfstrace.h"
#ifdef CONFIG_NFS_V4_2
#include "nfs42.h"
#endif
#define NFSDBG_FACILITY NFSDBG_FILE
static int
nfs4_file_open(struct inode *inode, struct file *filp)
{
struct nfs_open_context *ctx;
struct dentry *dentry = file_dentry(filp);
struct dentry *parent = NULL;
struct inode *dir;
unsigned openflags = filp->f_flags;
struct iattr attr;
int err;
/*
* If no cached dentry exists or if it's negative, NFSv4 handled the
* opens in ->lookup() or ->create().
*
* We only get this far for a cached positive dentry. We skipped
* revalidation, so handle it here by dropping the dentry and returning
* -EOPENSTALE. The VFS will retry the lookup/create/open.
*/
dprintk("NFS: open file(%pd2)\n", dentry);
err = nfs_check_flags(openflags);
if (err)
return err;
if ((openflags & O_ACCMODE) == 3)
return nfs_open(inode, filp);
/* We can't create new files here */
openflags &= ~(O_CREAT|O_EXCL);
parent = dget_parent(dentry);
dir = d_inode(parent);
ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode, filp);
err = PTR_ERR(ctx);
if (IS_ERR(ctx))
goto out;
attr.ia_valid = ATTR_OPEN;
if (openflags & O_TRUNC) {
attr.ia_valid |= ATTR_SIZE;
attr.ia_size = 0;
filemap_write_and_wait(inode->i_mapping);
}
inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr, NULL);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
switch (err) {
case -EPERM:
case -EACCES:
case -EDQUOT:
case -ENOSPC:
case -EROFS:
goto out_put_ctx;
default:
goto out_drop;
}
}
if (inode != d_inode(dentry))
goto out_drop;
nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
nfs_file_set_open_context(filp, ctx);
nfs_fscache_open_file(inode, filp);
err = 0;
out_put_ctx:
put_nfs_open_context(ctx);
out:
dput(parent);
return err;
out_drop:
d_drop(dentry);
err = -EOPENSTALE;
goto out_put_ctx;
}
/*
* Flush all dirty pages, and check for write errors.
*/
static int
nfs4_file_flush(struct file *file, fl_owner_t id)
{
struct inode *inode = file_inode(file);
dprintk("NFS: flush(%pD2)\n", file);
nfs_inc_stats(inode, NFSIOS_VFSFLUSH);
if ((file->f_mode & FMODE_WRITE) == 0)
return 0;
/*
* If we're holding a write delegation, then check if we're required
* to flush the i/o on close. If not, then just start the i/o now.
*/
if (!nfs4_delegation_flush_on_close(inode))
return filemap_fdatawrite(file->f_mapping);
/* Flush writes to the server and return any errors */
return nfs_wb_all(inode);
}
#ifdef CONFIG_NFS_V4_2
static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
size_t count, unsigned int flags)
{
/* Only offload copy if superblock is the same */
if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
return -EXDEV;
if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY))
return -EOPNOTSUPP;
if (file_inode(file_in) == file_inode(file_out))
return -EOPNOTSUPP;
return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
}
static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
size_t count, unsigned int flags)
{
ssize_t ret;
ret = __nfs4_copy_file_range(file_in, pos_in, file_out, pos_out, count,
flags);
if (ret == -EOPNOTSUPP || ret == -EXDEV)
ret = generic_copy_file_range(file_in, pos_in, file_out,
pos_out, count, flags);
return ret;
}
static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence)
{
loff_t ret;
switch (whence) {
case SEEK_HOLE:
case SEEK_DATA:
ret = nfs42_proc_llseek(filep, offset, whence);
if (ret != -ENOTSUPP)
return ret;
/* Fall through */
default:
return nfs_file_llseek(filep, offset, whence);
}
}
static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t len)
{
struct inode *inode = file_inode(filep);
long ret;
if (!S_ISREG(inode->i_mode))
return -EOPNOTSUPP;
if ((mode != 0) && (mode != (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE)))
return -EOPNOTSUPP;
ret = inode_newsize_ok(inode, offset + len);
if (ret < 0)
return ret;
if (mode & FALLOC_FL_PUNCH_HOLE)
return nfs42_proc_deallocate(filep, offset, len);
return nfs42_proc_allocate(filep, offset, len);
}
static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off,
struct file *dst_file, loff_t dst_off, loff_t count,
unsigned int remap_flags)
{
struct inode *dst_inode = file_inode(dst_file);
struct nfs_server *server = NFS_SERVER(dst_inode);
struct inode *src_inode = file_inode(src_file);
unsigned int bs = server->clone_blksize;
bool same_inode = false;
int ret;
/* NFS does not support deduplication. */
if (remap_flags & REMAP_FILE_DEDUP)
return -EOPNOTSUPP;
if (remap_flags & ~REMAP_FILE_ADVISORY)
return -EINVAL;
/* check alignment w.r.t. clone_blksize */
ret = -EINVAL;
if (bs) {
if (!IS_ALIGNED(src_off, bs) || !IS_ALIGNED(dst_off, bs))
goto out;
if (!IS_ALIGNED(count, bs) && i_size_read(src_inode) != (src_off + count))
goto out;
}
if (src_inode == dst_inode)
same_inode = true;
/* XXX: do we lock at all? what if server needs CB_RECALL_LAYOUT? */
if (same_inode) {
inode_lock(src_inode);
} else if (dst_inode < src_inode) {
inode_lock_nested(dst_inode, I_MUTEX_PARENT);
inode_lock_nested(src_inode, I_MUTEX_CHILD);
} else {
inode_lock_nested(src_inode, I_MUTEX_PARENT);
inode_lock_nested(dst_inode, I_MUTEX_CHILD);
}
/* flush all pending writes on both src and dst so that server
* has the latest data */
ret = nfs_sync_inode(src_inode);
if (ret)
goto out_unlock;
ret = nfs_sync_inode(dst_inode);
if (ret)
goto out_unlock;
ret = nfs42_proc_clone(src_file, dst_file, src_off, dst_off, count);
/* truncate inode page cache of the dst range so that future reads can fetch
* new data from server */
if (!ret)
truncate_inode_pages_range(&dst_inode->i_data, dst_off, dst_off + count - 1);
out_unlock:
if (same_inode) {
inode_unlock(src_inode);
} else if (dst_inode < src_inode) {
inode_unlock(src_inode);
inode_unlock(dst_inode);
} else {
inode_unlock(dst_inode);
inode_unlock(src_inode);
}
out:
return ret < 0 ? ret : count;
}
#endif /* CONFIG_NFS_V4_2 */
const struct file_operations nfs4_file_operations = {
.read_iter = nfs_file_read,
.write_iter = nfs_file_write,
.mmap = nfs_file_mmap,
.open = nfs4_file_open,
.flush = nfs4_file_flush,
.release = nfs_file_release,
.fsync = nfs_file_fsync,
.lock = nfs_lock,
.flock = nfs_flock,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.check_flags = nfs_check_flags,
.setlease = simple_nosetlease,
#ifdef CONFIG_NFS_V4_2
.copy_file_range = nfs4_copy_file_range,
.llseek = nfs4_file_llseek,
.fallocate = nfs42_fallocate,
.remap_file_range = nfs42_remap_file_range,
#else
.llseek = nfs_file_llseek,
#endif
};