linux/fs/9p/vfs_file.c

609 lines
14 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* This file contians vfs file ops for 9P2000.
*
* Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
* Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
*/
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/filelock.h>
#include <linux/sched.h>
#include <linux/file.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/list.h>
#include <linux/pagemap.h>
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
#include <linux/utsname.h>
#include <linux/uaccess.h>
#include <linux/uio.h>
#include <linux/slab.h>
#include <net/9p/9p.h>
#include <net/9p/client.h>
#include "v9fs.h"
#include "v9fs_vfs.h"
#include "fid.h"
#include "cache.h"
static const struct vm_operations_struct v9fs_mmap_file_vm_ops;
/**
* v9fs_file_open - open a file (or directory)
* @inode: inode to be opened
* @file: file being opened
*
*/
int v9fs_file_open(struct inode *inode, struct file *file)
{
int err;
struct v9fs_session_info *v9ses;
struct p9_fid *fid;
int omode;
p9_debug(P9_DEBUG_VFS, "inode: %p file: %p\n", inode, file);
v9ses = v9fs_inode2v9ses(inode);
if (v9fs_proto_dotl(v9ses))
omode = v9fs_open_to_dotl_flags(file->f_flags);
else
omode = v9fs_uflags2omode(file->f_flags,
v9fs_proto_dotu(v9ses));
fid = file->private_data;
if (!fid) {
fid = v9fs_fid_clone(file_dentry(file));
if (IS_ERR(fid))
return PTR_ERR(fid);
if ((v9ses->cache & CACHE_WRITEBACK) && (omode & P9_OWRITE)) {
int writeback_omode = (omode & ~P9_OWRITE) | P9_ORDWR;
p9_debug(P9_DEBUG_CACHE, "write-only file with writeback enabled, try opening O_RDWR\n");
err = p9_client_open(fid, writeback_omode);
if (err < 0) {
p9_debug(P9_DEBUG_CACHE, "could not open O_RDWR, disabling caches\n");
err = p9_client_open(fid, omode);
fid->mode |= P9L_DIRECT;
}
} else {
err = p9_client_open(fid, omode);
}
if (err < 0) {
p9_fid_put(fid);
return err;
}
if ((file->f_flags & O_APPEND) &&
(!v9fs_proto_dotu(v9ses) && !v9fs_proto_dotl(v9ses)))
generic_file_llseek(file, 0, SEEK_END);
file->private_data = fid;
}
#ifdef CONFIG_9P_FSCACHE
if (v9ses->cache & CACHE_FSCACHE)
fscache_use_cookie(v9fs_inode_cookie(V9FS_I(inode)),
9p: Use fscache indexing rewrite and reenable caching Change the 9p filesystem to take account of the changes to fscache's indexing rewrite and reenable caching in 9p. The following changes have been made: (1) The fscache_netfs struct is no more, and there's no need to register the filesystem as a whole. (2) The session cookie is now an fscache_volume cookie, allocated with fscache_acquire_volume(). That takes three parameters: a string representing the "volume" in the index, a string naming the cache to use (or NULL) and a u64 that conveys coherency metadata for the volume. For 9p, I've made it render the volume name string as: "9p,<devname>,<cachetag>" where the cachetag is replaced by the aname if it wasn't supplied. This probably needs rethinking a bit as the aname can have slashes in it. It might be better to hash the cachetag and use the hash or I could substitute commas for the slashes or something. (3) The fscache_cookie_def is no more and needed information is passed directly to fscache_acquire_cookie(). The cache no longer calls back into the filesystem, but rather metadata changes are indicated at other times. fscache_acquire_cookie() is passed the same keying and coherency information as before. (4) The functions to set/reset/flush cookies are removed and fscache_use_cookie() and fscache_unuse_cookie() are used instead. fscache_use_cookie() is passed a flag to indicate if the cookie is opened for writing. fscache_unuse_cookie() is passed updates for the metadata if we changed it (ie. if the file was opened for writing). These are called when the file is opened or closed. (5) wait_on_page_bit[_killable]() is replaced with the specific wait functions for the bits waited upon. (6) I've got rid of some of the 9p-specific cache helper functions and called things like fscache_relinquish_cookie() directly as they'll optimise away if v9fs_inode_cookie() returns an unconditional NULL (which will be the case if CONFIG_9P_FSCACHE=n). (7) v9fs_vfs_setattr() is made to call fscache_resize() to change the size of the cache object. Notes: (A) We should call fscache_invalidate() if we detect that the server's copy of a file got changed by a third party, but I don't know where to do that. We don't need to do that when allocating the cookie as we get a check-and-invalidate when we initially bind to the cache object. (B) The copy-to-cache-on-writeback side of things will be handled in separate patch. Changes ======= ver #3: - Canonicalise the cookie key and coherency data to make them endianness-independent. ver #2: - Use gfpflags_allow_blocking() rather than using flag directly. - fscache_acquire_volume() now returns errors. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dominique Martinet <asmadeus@codewreck.org> cc: Eric Van Hensbergen <ericvh@gmail.com> cc: Latchesar Ionkov <lucho@ionkov.net> cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819664645.215744.1555314582005286846.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906975017.143852.3459573173204394039.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967178512.1823006.17377493641569138183.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021573143.640689.3977487095697717967.stgit@warthog.procyon.org.uk/ # v4
2020-11-18 09:06:42 +00:00
file->f_mode & FMODE_WRITE);
#endif
v9fs_fid_add_modes(fid, v9ses->flags, v9ses->cache, file->f_flags);
v9fs_open_fid_add(inode, &fid);
return 0;
}
/**
* v9fs_file_lock - lock a file (or directory)
* @filp: file to be locked
* @cmd: lock command
* @fl: file lock structure
*
* Bugs: this looks like a local only lock, we should extend into 9P
* by using open exclusive
*/
static int v9fs_file_lock(struct file *filp, int cmd, struct file_lock *fl)
{
struct inode *inode = file_inode(filp);
p9_debug(P9_DEBUG_VFS, "filp: %p lock: %p\n", filp, fl);
if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
filemap_write_and_wait(inode->i_mapping);
invalidate_mapping_pages(&inode->i_data, 0, -1);
}
return 0;
}
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
{
struct p9_flock flock;
struct p9_fid *fid;
uint8_t status = P9_LOCK_ERROR;
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
int res = 0;
unsigned char fl_type;
struct v9fs_session_info *v9ses;
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
fid = filp->private_data;
BUG_ON(fid == NULL);
BUG_ON((fl->fl_flags & FL_POSIX) != FL_POSIX);
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
res = locks_lock_file_wait(filp, fl);
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
if (res < 0)
goto out;
/* convert posix lock to p9 tlock args */
memset(&flock, 0, sizeof(flock));
/* map the lock type */
switch (fl->fl_type) {
case F_RDLCK:
flock.type = P9_LOCK_TYPE_RDLCK;
break;
case F_WRLCK:
flock.type = P9_LOCK_TYPE_WRLCK;
break;
case F_UNLCK:
flock.type = P9_LOCK_TYPE_UNLCK;
break;
}
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
flock.start = fl->fl_start;
if (fl->fl_end == OFFSET_MAX)
flock.length = 0;
else
flock.length = fl->fl_end - fl->fl_start + 1;
flock.proc_id = fl->fl_pid;
flock.client_id = fid->clnt->name;
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
if (IS_SETLKW(cmd))
flock.flags = P9_LOCK_FLAGS_BLOCK;
v9ses = v9fs_inode2v9ses(file_inode(filp));
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
/*
* if its a blocked request and we get P9_LOCK_BLOCKED as the status
* for lock request, keep on trying
*/
for (;;) {
res = p9_client_lock_dotl(fid, &flock, &status);
if (res < 0)
goto out_unlock;
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
if (status != P9_LOCK_BLOCKED)
break;
if (status == P9_LOCK_BLOCKED && !IS_SETLKW(cmd))
break;
if (schedule_timeout_interruptible(v9ses->session_lock_timeout)
!= 0)
break;
/*
* p9_client_lock_dotl overwrites flock.client_id with the
* server message, free and reuse the client name
*/
if (flock.client_id != fid->clnt->name) {
kfree(flock.client_id);
flock.client_id = fid->clnt->name;
}
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
}
/* map 9p status to VFS status */
switch (status) {
case P9_LOCK_SUCCESS:
res = 0;
break;
case P9_LOCK_BLOCKED:
res = -EAGAIN;
break;
default:
WARN_ONCE(1, "unknown lock status code: %d\n", status);
fallthrough;
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
case P9_LOCK_ERROR:
case P9_LOCK_GRACE:
res = -ENOLCK;
break;
}
out_unlock:
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
/*
* incase server returned error for lock request, revert
* it locally
*/
if (res < 0 && fl->fl_type != F_UNLCK) {
fl_type = fl->fl_type;
fl->fl_type = F_UNLCK;
/* Even if this fails we want to return the remote error */
locks_lock_file_wait(filp, fl);
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
fl->fl_type = fl_type;
}
if (flock.client_id != fid->clnt->name)
kfree(flock.client_id);
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
out:
return res;
}
static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
{
struct p9_getlock glock;
struct p9_fid *fid;
int res = 0;
fid = filp->private_data;
BUG_ON(fid == NULL);
posix_test_lock(filp, fl);
/*
* if we have a conflicting lock locally, no need to validate
* with server
*/
if (fl->fl_type != F_UNLCK)
return res;
/* convert posix lock to p9 tgetlock args */
memset(&glock, 0, sizeof(glock));
glock.type = P9_LOCK_TYPE_UNLCK;
glock.start = fl->fl_start;
if (fl->fl_end == OFFSET_MAX)
glock.length = 0;
else
glock.length = fl->fl_end - fl->fl_start + 1;
glock.proc_id = fl->fl_pid;
glock.client_id = fid->clnt->name;
res = p9_client_getlock_dotl(fid, &glock);
if (res < 0)
goto out;
/* map 9p lock type to os lock type */
switch (glock.type) {
case P9_LOCK_TYPE_RDLCK:
fl->fl_type = F_RDLCK;
break;
case P9_LOCK_TYPE_WRLCK:
fl->fl_type = F_WRLCK;
break;
case P9_LOCK_TYPE_UNLCK:
fl->fl_type = F_UNLCK;
break;
}
if (glock.type != P9_LOCK_TYPE_UNLCK) {
fl->fl_start = glock.start;
if (glock.length == 0)
fl->fl_end = OFFSET_MAX;
else
fl->fl_end = glock.start + glock.length - 1;
fs/locks: Remove fl_nspid and use fs-specific l_pid for remote locks Since commit c69899a17ca4 "NFSv4: Update of VFS byte range lock must be atomic with the stateid update", NFSv4 has been inserting locks in rpciod worker context. The result is that the file_lock's fl_nspid is the kworker's pid instead of the original userspace pid. The fl_nspid is only used to represent the namespaced virtual pid number when displaying locks or returning from F_GETLK. There's no reason to set it for every inserted lock, since we can usually just look it up from fl_pid. So, instead of looking up and holding struct pid for every lock, let's just look up the virtual pid number from fl_pid when it is needed. That means we can remove fl_nspid entirely. The translaton and presentation of fl_pid should handle the following four cases: 1 - F_GETLK on a remote file with a remote lock: In this case, the filesystem should determine the l_pid to return here. Filesystems should indicate that the fl_pid represents a non-local pid value that should not be translated by returning an fl_pid <= 0. 2 - F_GETLK on a local file with a remote lock: This should be the l_pid of the lock manager process, and translated. 3 - F_GETLK on a remote file with a local lock, and 4 - F_GETLK on a local file with a local lock: These should be the translated l_pid of the local locking process. Fuse was already doing the correct thing by translating the pid into the caller's namespace. With this change we must update fuse to translate to init's pid namespace, so that the locks API can then translate from init's pid namespace into the pid namespace of the caller. With this change, the locks API will expect that if a filesystem returns a remote pid as opposed to a local pid for F_GETLK, that remote pid will be <= 0. This signifies that the pid is remote, and the locks API will forego translating that pid into the pid namespace of the local calling process. Finally, we convert remote filesystems to present remote pids using negative numbers. Have lustre, 9p, ceph, cifs, and dlm negate the remote pid returned for F_GETLK lock requests. Since local pids will never be larger than PID_MAX_LIMIT (which is currently defined as <= 4 million), but pid_t is an unsigned int, we should have plenty of room to represent remote pids with negative numbers if we assume that remote pid numbers are similarly limited. If this is not the case, then we run the risk of having a remote pid returned for which there is also a corresponding local pid. This is a problem we have now, but this patch should reduce the chances of that occurring, while also returning those remote pid numbers, for whatever that may be worth. Signed-off-by: Benjamin Coddington <bcodding@redhat.com> Signed-off-by: Jeff Layton <jlayton@redhat.com>
2017-07-16 14:28:22 +00:00
fl->fl_pid = -glock.proc_id;
}
out:
if (glock.client_id != fid->clnt->name)
kfree(glock.client_id);
return res;
}
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
/**
* v9fs_file_lock_dotl - lock a file (or directory)
* @filp: file to be locked
* @cmd: lock command
* @fl: file lock structure
*
*/
static int v9fs_file_lock_dotl(struct file *filp, int cmd, struct file_lock *fl)
{
struct inode *inode = file_inode(filp);
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
int ret = -ENOLCK;
p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %pD\n",
filp, cmd, fl, filp);
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
filemap_write_and_wait(inode->i_mapping);
invalidate_mapping_pages(&inode->i_data, 0, -1);
}
if (IS_SETLK(cmd) || IS_SETLKW(cmd))
ret = v9fs_file_do_lock(filp, cmd, fl);
else if (IS_GETLK(cmd))
ret = v9fs_file_getlock(filp, fl);
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
else
ret = -EINVAL;
return ret;
}
/**
* v9fs_file_flock_dotl - lock a file
* @filp: file to be locked
* @cmd: lock command
* @fl: file lock structure
*
*/
static int v9fs_file_flock_dotl(struct file *filp, int cmd,
struct file_lock *fl)
{
struct inode *inode = file_inode(filp);
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
int ret = -ENOLCK;
p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %pD\n",
filp, cmd, fl, filp);
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
if (!(fl->fl_flags & FL_FLOCK))
goto out_err;
if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
filemap_write_and_wait(inode->i_mapping);
invalidate_mapping_pages(&inode->i_data, 0, -1);
}
/* Convert flock to posix lock */
fl->fl_flags |= FL_POSIX;
fl->fl_flags ^= FL_FLOCK;
if (IS_SETLK(cmd) | IS_SETLKW(cmd))
ret = v9fs_file_do_lock(filp, cmd, fl);
else
ret = -EINVAL;
out_err:
return ret;
}
/**
* v9fs_file_read_iter - read from a file
* @iocb: The operation parameters
* @to: The buffer to read into
*
*/
static ssize_t
v9fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct p9_fid *fid = iocb->ki_filp->private_data;
int ret, err = 0;
p9_debug(P9_DEBUG_VFS, "fid %d count %zu offset %lld\n",
fid->fid, iov_iter_count(to), iocb->ki_pos);
if (!(fid->mode & P9L_DIRECT)) {
p9_debug(P9_DEBUG_VFS, "(cached)\n");
return generic_file_read_iter(iocb, to);
}
if (iocb->ki_filp->f_flags & O_NONBLOCK)
ret = p9_client_read_once(fid, iocb->ki_pos, to, &err);
else
ret = p9_client_read(fid, iocb->ki_pos, to, &err);
if (!ret)
return err;
iocb->ki_pos += ret;
return ret;
}
/*
* v9fs_file_splice_read - splice-read from a file
* @in: The 9p file to read from
* @ppos: Where to find/update the file position
* @pipe: The pipe to splice into
* @len: The maximum amount of data to splice
* @flags: SPLICE_F_* flags
*/
static ssize_t v9fs_file_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe,
size_t len, unsigned int flags)
{
struct p9_fid *fid = in->private_data;
p9_debug(P9_DEBUG_VFS, "fid %d count %zu offset %lld\n",
fid->fid, len, *ppos);
if (fid->mode & P9L_DIRECT)
return copy_splice_read(in, ppos, pipe, len, flags);
return filemap_splice_read(in, ppos, pipe, len, flags);
}
/**
* v9fs_file_write_iter - write to a file
* @iocb: The operation parameters
* @from: The data to write
*
*/
static ssize_t
v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct p9_fid *fid = file->private_data;
ssize_t retval;
loff_t origin;
int err = 0;
p9_debug(P9_DEBUG_VFS, "fid %d\n", fid->fid);
if (!(fid->mode & (P9L_DIRECT | P9L_NOWRITECACHE))) {
p9_debug(P9_DEBUG_CACHE, "(cached)\n");
return generic_file_write_iter(iocb, from);
}
retval = generic_write_checks(iocb, from);
if (retval <= 0)
return retval;
origin = iocb->ki_pos;
retval = p9_client_write(file->private_data, iocb->ki_pos, from, &err);
if (retval > 0) {
struct inode *inode = file_inode(file);
loff_t i_size;
unsigned long pg_start, pg_end;
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 12:29:47 +00:00
pg_start = origin >> PAGE_SHIFT;
pg_end = (origin + retval - 1) >> PAGE_SHIFT;
if (inode->i_mapping && inode->i_mapping->nrpages)
invalidate_inode_pages2_range(inode->i_mapping,
pg_start, pg_end);
iocb->ki_pos += retval;
i_size = i_size_read(inode);
if (iocb->ki_pos > i_size) {
inode_add_bytes(inode, iocb->ki_pos - i_size);
9p: use inode->i_lock to protect i_size_write() under 32-bit Use inode->i_lock to protect i_size_write(), else i_size_read() in generic_fillattr() may loop infinitely in read_seqcount_begin() when multiple processes invoke v9fs_vfs_getattr() or v9fs_vfs_getattr_dotl() simultaneously under 32-bit SMP environment, and a soft lockup will be triggered as show below: watchdog: BUG: soft lockup - CPU#5 stuck for 22s! [stat:2217] Modules linked in: CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4 Hardware name: Generic DT based system PC is at generic_fillattr+0x104/0x108 LR is at 0xec497f00 pc : [<802b8898>] lr : [<ec497f00>] psr: 200c0013 sp : ec497e20 ip : ed608030 fp : ec497e3c r10: 00000000 r9 : ec497f00 r8 : ed608030 r7 : ec497ebc r6 : ec497f00 r5 : ee5c1550 r4 : ee005780 r3 : 0000052d r2 : 00000000 r1 : ec497f00 r0 : ed608030 Flags: nzCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none Control: 10c5387d Table: ac48006a DAC: 00000051 CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4 Hardware name: Generic DT based system Backtrace: [<8010d974>] (dump_backtrace) from [<8010dc88>] (show_stack+0x20/0x24) [<8010dc68>] (show_stack) from [<80a1d194>] (dump_stack+0xb0/0xdc) [<80a1d0e4>] (dump_stack) from [<80109f34>] (show_regs+0x1c/0x20) [<80109f18>] (show_regs) from [<801d0a80>] (watchdog_timer_fn+0x280/0x2f8) [<801d0800>] (watchdog_timer_fn) from [<80198658>] (__hrtimer_run_queues+0x18c/0x380) [<801984cc>] (__hrtimer_run_queues) from [<80198e60>] (hrtimer_run_queues+0xb8/0xf0) [<80198da8>] (hrtimer_run_queues) from [<801973e8>] (run_local_timers+0x28/0x64) [<801973c0>] (run_local_timers) from [<80197460>] (update_process_times+0x3c/0x6c) [<80197424>] (update_process_times) from [<801ab2b8>] (tick_nohz_handler+0xe0/0x1bc) [<801ab1d8>] (tick_nohz_handler) from [<80843050>] (arch_timer_handler_virt+0x38/0x48) [<80843018>] (arch_timer_handler_virt) from [<80180a64>] (handle_percpu_devid_irq+0x8c/0x240) [<801809d8>] (handle_percpu_devid_irq) from [<8017ac20>] (generic_handle_irq+0x34/0x44) [<8017abec>] (generic_handle_irq) from [<8017b344>] (__handle_domain_irq+0x6c/0xc4) [<8017b2d8>] (__handle_domain_irq) from [<801022e0>] (gic_handle_irq+0x4c/0x88) [<80102294>] (gic_handle_irq) from [<80101a30>] (__irq_svc+0x70/0x98) [<802b8794>] (generic_fillattr) from [<8056b284>] (v9fs_vfs_getattr_dotl+0x74/0xa4) [<8056b210>] (v9fs_vfs_getattr_dotl) from [<802b8904>] (vfs_getattr_nosec+0x68/0x7c) [<802b889c>] (vfs_getattr_nosec) from [<802b895c>] (vfs_getattr+0x44/0x48) [<802b8918>] (vfs_getattr) from [<802b8a74>] (vfs_statx+0x9c/0xec) [<802b89d8>] (vfs_statx) from [<802b9428>] (sys_lstat64+0x48/0x78) [<802b93e0>] (sys_lstat64) from [<80101000>] (ret_fast_syscall+0x0/0x28) [dominique.martinet@cea.fr: updated comment to not refer to a function in another subsystem] Link: http://lkml.kernel.org/r/20190124063514.8571-2-houtao1@huawei.com Cc: stable@vger.kernel.org Fixes: 7549ae3e81cc ("9p: Use the i_size_[read, write]() macros instead of using inode->i_size directly.") Reported-by: Xing Gaopeng <xingaopeng@huawei.com> Signed-off-by: Hou Tao <houtao1@huawei.com> Signed-off-by: Dominique Martinet <dominique.martinet@cea.fr>
2019-01-24 06:35:13 +00:00
/*
* Need to serialize against i_size_write() in
* v9fs_stat2inode()
*/
v9fs_i_size_write(inode, iocb->ki_pos);
}
return retval;
}
return err;
}
static int v9fs_file_fsync(struct file *filp, loff_t start, loff_t end,
int datasync)
{
struct p9_fid *fid;
struct inode *inode = filp->f_mapping->host;
struct p9_wstat wstat;
int retval;
retval = file_write_and_wait_range(filp, start, end);
if (retval)
return retval;
inode_lock(inode);
p9_debug(P9_DEBUG_VFS, "filp %p datasync %x\n", filp, datasync);
fid = filp->private_data;
v9fs_blank_wstat(&wstat);
retval = p9_client_wstat(fid, &wstat);
inode_unlock(inode);
return retval;
}
int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end,
int datasync)
{
struct p9_fid *fid;
struct inode *inode = filp->f_mapping->host;
int retval;
retval = file_write_and_wait_range(filp, start, end);
if (retval)
return retval;
inode_lock(inode);
p9_debug(P9_DEBUG_VFS, "filp %p datasync %x\n", filp, datasync);
fid = filp->private_data;
retval = p9_client_fsync(fid, datasync);
inode_unlock(inode);
return retval;
}
static int
v9fs_file_mmap(struct file *filp, struct vm_area_struct *vma)
{
int retval;
struct inode *inode = file_inode(filp);
struct v9fs_session_info *v9ses = v9fs_inode2v9ses(inode);
p9_debug(P9_DEBUG_MMAP, "filp :%p\n", filp);
if (!(v9ses->cache & CACHE_WRITEBACK)) {
p9_debug(P9_DEBUG_CACHE, "(read-only mmap mode)");
return generic_file_readonly_mmap(filp, vma);
}
retval = generic_file_mmap(filp, vma);
if (!retval)
vma->vm_ops = &v9fs_mmap_file_vm_ops;
return retval;
}
static vm_fault_t
v9fs_vm_page_mkwrite(struct vm_fault *vmf)
{
netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dominique Martinet <asmadeus@codewreck.org> Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) <willy@infradead.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5
2021-08-11 08:49:13 +00:00
struct folio *folio = page_folio(vmf->page);
struct file *filp = vmf->vma->vm_file;
struct inode *inode = file_inode(filp);
netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dominique Martinet <asmadeus@codewreck.org> Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) <willy@infradead.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5
2021-08-11 08:49:13 +00:00
p9_debug(P9_DEBUG_VFS, "folio %p fid %lx\n",
folio, (unsigned long)filp->private_data);
9p: Convert to using the netfs helper lib to do reads and caching Convert the 9p filesystem to use the netfs helper lib to handle readpage, readahead and write_begin, converting those into a common issue_op for the filesystem itself to handle. The netfs helper lib also handles reading from fscache if a cache is available, and interleaving reads from both sources. This change also switches from the old fscache I/O API to the new one, meaning that fscache no longer keeps track of netfs pages and instead does async DIO between the backing files and the 9p file pagecache. As a part of this change, the handling of PG_fscache changes. It now just means that the cache has a write I/O operation in progress on a page (PG_locked is used for a read I/O op). Note that this is a cut-down version of the fscache rewrite and does not change any of the cookie and cache coherency handling. Changes ======= ver #4: - Rebase on top of folios. - Don't use wait_on_page_bit_killable(). ver #3: - v9fs_req_issue_op() needs to terminate the subrequest. - v9fs_write_end() needs to call SetPageUptodate() a bit more often. - It's not CONFIG_{AFS,V9FS}_FSCACHE[1] - v9fs_init_rreq() should take a ref on the p9_fid and the cleanup should drop it [from Dominique Martinet]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-and-tested-by: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YUm+xucHxED+1MJp@codewreck.org/ [1] Link: https://lore.kernel.org/r/163162772646.438332.16323773205855053535.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/163189109885.2509237.7153668924503399173.stgit@warthog.procyon.org.uk/ # rfc v2 Link: https://lore.kernel.org/r/163363943896.1980952.1226527304649419689.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163551662876.1877519.14706391695553204156.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163584179557.4023316.11089762304657644342.stgit@warthog.procyon.org.uk # rebase on folio Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2021-11-02 08:29:55 +00:00
/* 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_9P_FSCACHE
netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dominique Martinet <asmadeus@codewreck.org> Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) <willy@infradead.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5
2021-08-11 08:49:13 +00:00
if (folio_test_fscache(folio) &&
folio_wait_fscache_killable(folio) < 0)
return VM_FAULT_NOPAGE;
9p: Convert to using the netfs helper lib to do reads and caching Convert the 9p filesystem to use the netfs helper lib to handle readpage, readahead and write_begin, converting those into a common issue_op for the filesystem itself to handle. The netfs helper lib also handles reading from fscache if a cache is available, and interleaving reads from both sources. This change also switches from the old fscache I/O API to the new one, meaning that fscache no longer keeps track of netfs pages and instead does async DIO between the backing files and the 9p file pagecache. As a part of this change, the handling of PG_fscache changes. It now just means that the cache has a write I/O operation in progress on a page (PG_locked is used for a read I/O op). Note that this is a cut-down version of the fscache rewrite and does not change any of the cookie and cache coherency handling. Changes ======= ver #4: - Rebase on top of folios. - Don't use wait_on_page_bit_killable(). ver #3: - v9fs_req_issue_op() needs to terminate the subrequest. - v9fs_write_end() needs to call SetPageUptodate() a bit more often. - It's not CONFIG_{AFS,V9FS}_FSCACHE[1] - v9fs_init_rreq() should take a ref on the p9_fid and the cleanup should drop it [from Dominique Martinet]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-and-tested-by: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YUm+xucHxED+1MJp@codewreck.org/ [1] Link: https://lore.kernel.org/r/163162772646.438332.16323773205855053535.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/163189109885.2509237.7153668924503399173.stgit@warthog.procyon.org.uk/ # rfc v2 Link: https://lore.kernel.org/r/163363943896.1980952.1226527304649419689.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163551662876.1877519.14706391695553204156.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163584179557.4023316.11089762304657644342.stgit@warthog.procyon.org.uk # rebase on folio Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2021-11-02 08:29:55 +00:00
#endif
/* Update file times before taking page lock */
file_update_time(filp);
netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dominique Martinet <asmadeus@codewreck.org> Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) <willy@infradead.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5
2021-08-11 08:49:13 +00:00
if (folio_lock_killable(folio) < 0)
9p: Convert to using the netfs helper lib to do reads and caching Convert the 9p filesystem to use the netfs helper lib to handle readpage, readahead and write_begin, converting those into a common issue_op for the filesystem itself to handle. The netfs helper lib also handles reading from fscache if a cache is available, and interleaving reads from both sources. This change also switches from the old fscache I/O API to the new one, meaning that fscache no longer keeps track of netfs pages and instead does async DIO between the backing files and the 9p file pagecache. As a part of this change, the handling of PG_fscache changes. It now just means that the cache has a write I/O operation in progress on a page (PG_locked is used for a read I/O op). Note that this is a cut-down version of the fscache rewrite and does not change any of the cookie and cache coherency handling. Changes ======= ver #4: - Rebase on top of folios. - Don't use wait_on_page_bit_killable(). ver #3: - v9fs_req_issue_op() needs to terminate the subrequest. - v9fs_write_end() needs to call SetPageUptodate() a bit more often. - It's not CONFIG_{AFS,V9FS}_FSCACHE[1] - v9fs_init_rreq() should take a ref on the p9_fid and the cleanup should drop it [from Dominique Martinet]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-and-tested-by: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YUm+xucHxED+1MJp@codewreck.org/ [1] Link: https://lore.kernel.org/r/163162772646.438332.16323773205855053535.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/163189109885.2509237.7153668924503399173.stgit@warthog.procyon.org.uk/ # rfc v2 Link: https://lore.kernel.org/r/163363943896.1980952.1226527304649419689.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163551662876.1877519.14706391695553204156.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163584179557.4023316.11089762304657644342.stgit@warthog.procyon.org.uk # rebase on folio Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2021-11-02 08:29:55 +00:00
return VM_FAULT_RETRY;
netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dominique Martinet <asmadeus@codewreck.org> Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) <willy@infradead.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5
2021-08-11 08:49:13 +00:00
if (folio_mapping(folio) != inode->i_mapping)
goto out_unlock;
netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dominique Martinet <asmadeus@codewreck.org> Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) <willy@infradead.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5
2021-08-11 08:49:13 +00:00
folio_wait_stable(folio);
return VM_FAULT_LOCKED;
out_unlock:
netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dominique Martinet <asmadeus@codewreck.org> Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) <willy@infradead.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5
2021-08-11 08:49:13 +00:00
folio_unlock(folio);
return VM_FAULT_NOPAGE;
}
static void v9fs_mmap_vm_close(struct vm_area_struct *vma)
{
struct inode *inode;
struct writeback_control wbc = {
.nr_to_write = LONG_MAX,
.sync_mode = WB_SYNC_ALL,
.range_start = (loff_t)vma->vm_pgoff * PAGE_SIZE,
/* absolute end, byte at end included */
.range_end = (loff_t)vma->vm_pgoff * PAGE_SIZE +
(vma->vm_end - vma->vm_start - 1),
};
if (!(vma->vm_flags & VM_SHARED))
return;
p9_debug(P9_DEBUG_VFS, "9p VMA close, %p, flushing", vma);
inode = file_inode(vma->vm_file);
filemap_fdatawrite_wbc(inode->i_mapping, &wbc);
}
static const struct vm_operations_struct v9fs_mmap_file_vm_ops = {
.close = v9fs_mmap_vm_close,
.fault = filemap_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = v9fs_vm_page_mkwrite,
};
const struct file_operations v9fs_file_operations = {
.llseek = generic_file_llseek,
.read_iter = v9fs_file_read_iter,
.write_iter = v9fs_file_write_iter,
.open = v9fs_file_open,
.release = v9fs_dir_release,
.lock = v9fs_file_lock,
.mmap = generic_file_readonly_mmap,
.splice_read = v9fs_file_splice_read,
.splice_write = iter_file_splice_write,
.fsync = v9fs_file_fsync,
};
const struct file_operations v9fs_file_operations_dotl = {
.llseek = generic_file_llseek,
.read_iter = v9fs_file_read_iter,
.write_iter = v9fs_file_write_iter,
.open = v9fs_file_open,
.release = v9fs_dir_release,
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 06:04:24 +00:00
.lock = v9fs_file_lock_dotl,
.flock = v9fs_file_flock_dotl,
.mmap = v9fs_file_mmap,
.splice_read = v9fs_file_splice_read,
.splice_write = iter_file_splice_write,
.fsync = v9fs_file_fsync_dotl,
};