linux_dsm_epyc7002/fs/afs/dir_silly.c

254 lines
6.6 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/* AFS silly rename handling
*
* Copyright (C) 2019 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
* - Derived from NFS's sillyrename.
*/
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/fsnotify.h>
#include "internal.h"
/*
* Actually perform the silly rename step.
*/
static int afs_do_silly_rename(struct afs_vnode *dvnode, struct afs_vnode *vnode,
struct dentry *old, struct dentry *new,
struct key *key)
{
struct afs_fs_cursor fc;
afs: Fix application of status and callback to be under same lock When applying the status and callback in the response of an operation, apply them in the same critical section so that there's no race between checking the callback state and checking status-dependent state (such as the data version). Fix this by: (1) Allocating a joint {status,callback} record (afs_status_cb) before calling the RPC function for each vnode for which the RPC reply contains a status or a status plus a callback. A flag is set in the record to indicate if a callback was actually received. (2) These records are passed into the RPC functions to be filled in. The afs_decode_status() and yfs_decode_status() functions are removed and the cb_lock is no longer taken. (3) xdr_decode_AFSFetchStatus() and xdr_decode_YFSFetchStatus() no longer update the vnode. (4) xdr_decode_AFSCallBack() and xdr_decode_YFSCallBack() no longer update the vnode. (5) vnodes, expected data-version numbers and callback break counters (cb_break) no longer need to be passed to the reply delivery functions. Note that, for the moment, the file locking functions still need access to both the call and the vnode at the same time. (6) afs_vnode_commit_status() is now given the cb_break value and the expected data_version and the task of applying the status and the callback to the vnode are now done here. This is done under a single taking of vnode->cb_lock. (7) afs_pages_written_back() is now called by afs_store_data() rather than by the reply delivery function. afs_pages_written_back() has been moved to before the call point and is now given the first and last page numbers rather than a pointer to the call. (8) The indicator from YFS.RemoveFile2 as to whether the target file actually got removed (status.abort_code == VNOVNODE) rather than merely dropping a link is now checked in afs_unlink rather than in xdr_decode_YFSFetchStatus(). Supplementary fixes: (*) afs_cache_permit() now gets the caller_access mask from the afs_status_cb object rather than picking it out of the vnode's status record. afs_fetch_status() returns caller_access through its argument list for this purpose also. (*) afs_inode_init_from_status() now uses a write lock on cb_lock rather than a read lock and now sets the callback inside the same critical section. Fixes: c435ee34551e ("afs: Overhaul the callback handling") Signed-off-by: David Howells <dhowells@redhat.com>
2019-05-09 21:16:10 +07:00
struct afs_status_cb *scb;
afs: Fix race between post-modification dir edit and readdir/d_revalidate AFS directories are retained locally as a structured file, with lookup being effected by a local search of the file contents. When a modification (such as mkdir) happens, the dir file content is modified locally rather than redownloading the directory. The directory contents are accessed in a number of ways, with a number of different locks schemes: (1) Download of contents - dvnode->validate_lock/write in afs_read_dir(). (2) Lookup and readdir - dvnode->validate_lock/read in afs_dir_iterate(), downgrading from (1) if necessary. (3) d_revalidate of child dentry - dvnode->validate_lock/read in afs_do_lookup_one() downgrading from (1) if necessary. (4) Edit of dir after modification - page locks on individual dir pages. Unfortunately, because (4) uses different locking scheme to (1) - (3), nothing protects against the page being scanned whilst the edit is underway. Even download is not safe as it doesn't lock the pages - relying instead on the validate_lock to serialise as a whole (the theory being that directory contents are treated as a block and always downloaded as a block). Fix this by write-locking dvnode->validate_lock around the edits. Care must be taken in the rename case as there may be two different dirs - but they need not be locked at the same time. In any case, once the lock is taken, the directory version must be rechecked, and the edit skipped if a later version has been downloaded by revalidation (there can't have been any local changes because the VFS holds the inode lock, but there can have been remote changes). Fixes: 63a4681ff39c ("afs: Locally edit directory data for mkdir/create/unlink/...") Signed-off-by: David Howells <dhowells@redhat.com>
2020-04-10 21:23:27 +07:00
afs_dataversion_t dir_data_version;
int ret = -ERESTARTSYS;
_enter("%pd,%pd", old, new);
afs: Fix application of status and callback to be under same lock When applying the status and callback in the response of an operation, apply them in the same critical section so that there's no race between checking the callback state and checking status-dependent state (such as the data version). Fix this by: (1) Allocating a joint {status,callback} record (afs_status_cb) before calling the RPC function for each vnode for which the RPC reply contains a status or a status plus a callback. A flag is set in the record to indicate if a callback was actually received. (2) These records are passed into the RPC functions to be filled in. The afs_decode_status() and yfs_decode_status() functions are removed and the cb_lock is no longer taken. (3) xdr_decode_AFSFetchStatus() and xdr_decode_YFSFetchStatus() no longer update the vnode. (4) xdr_decode_AFSCallBack() and xdr_decode_YFSCallBack() no longer update the vnode. (5) vnodes, expected data-version numbers and callback break counters (cb_break) no longer need to be passed to the reply delivery functions. Note that, for the moment, the file locking functions still need access to both the call and the vnode at the same time. (6) afs_vnode_commit_status() is now given the cb_break value and the expected data_version and the task of applying the status and the callback to the vnode are now done here. This is done under a single taking of vnode->cb_lock. (7) afs_pages_written_back() is now called by afs_store_data() rather than by the reply delivery function. afs_pages_written_back() has been moved to before the call point and is now given the first and last page numbers rather than a pointer to the call. (8) The indicator from YFS.RemoveFile2 as to whether the target file actually got removed (status.abort_code == VNOVNODE) rather than merely dropping a link is now checked in afs_unlink rather than in xdr_decode_YFSFetchStatus(). Supplementary fixes: (*) afs_cache_permit() now gets the caller_access mask from the afs_status_cb object rather than picking it out of the vnode's status record. afs_fetch_status() returns caller_access through its argument list for this purpose also. (*) afs_inode_init_from_status() now uses a write lock on cb_lock rather than a read lock and now sets the callback inside the same critical section. Fixes: c435ee34551e ("afs: Overhaul the callback handling") Signed-off-by: David Howells <dhowells@redhat.com>
2019-05-09 21:16:10 +07:00
scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL);
if (!scb)
return -ENOMEM;
trace_afs_silly_rename(vnode, false);
afs: Make some RPC operations non-interruptible Make certain RPC operations non-interruptible, including: (*) Set attributes (*) Store data We don't want to get interrupted during a flush on close, flush on unlock, writeback or an inode update, leaving us in a state where we still need to do the writeback or update. (*) Extend lock (*) Release lock We don't want to get lock extension interrupted as the file locks on the server are time-limited. Interruption during lock release is less of an issue since the lock is time-limited, but it's better to complete the release to avoid a several-minute wait to recover it. *Setting* the lock isn't a problem if it's interrupted since we can just return to the user and tell them they were interrupted - at which point they can elect to retry. (*) Silly unlink We want to remove silly unlink files if we can, rather than leaving them for the salvager to clear up. Note that whilst these calls are no longer interruptible, they do have timeouts on them, so if the server stops responding the call will fail with something like ETIME or ECONNRESET. Without this, the following: kAFS: Unexpected error from FS.StoreData -512 appears in dmesg when a pending store data gets interrupted and some processes may just hang. Additionally, make the code that checks/updates the server record ignore failure due to interruption if the main call is uninterruptible and if the server has an address list. The next op will check it again since the expiration time on the old list has past. Fixes: d2ddc776a458 ("afs: Overhaul volume and server record caching and fileserver rotation") Reported-by: Jonathan Billings <jsbillings@jsbillings.org> Reported-by: Marc Dionne <marc.dionne@auristor.com> Signed-off-by: David Howells <dhowells@redhat.com>
2019-05-08 22:16:31 +07:00
if (afs_begin_vnode_operation(&fc, dvnode, key, true)) {
afs: Fix race between post-modification dir edit and readdir/d_revalidate AFS directories are retained locally as a structured file, with lookup being effected by a local search of the file contents. When a modification (such as mkdir) happens, the dir file content is modified locally rather than redownloading the directory. The directory contents are accessed in a number of ways, with a number of different locks schemes: (1) Download of contents - dvnode->validate_lock/write in afs_read_dir(). (2) Lookup and readdir - dvnode->validate_lock/read in afs_dir_iterate(), downgrading from (1) if necessary. (3) d_revalidate of child dentry - dvnode->validate_lock/read in afs_do_lookup_one() downgrading from (1) if necessary. (4) Edit of dir after modification - page locks on individual dir pages. Unfortunately, because (4) uses different locking scheme to (1) - (3), nothing protects against the page being scanned whilst the edit is underway. Even download is not safe as it doesn't lock the pages - relying instead on the validate_lock to serialise as a whole (the theory being that directory contents are treated as a block and always downloaded as a block). Fix this by write-locking dvnode->validate_lock around the edits. Care must be taken in the rename case as there may be two different dirs - but they need not be locked at the same time. In any case, once the lock is taken, the directory version must be rechecked, and the edit skipped if a later version has been downloaded by revalidation (there can't have been any local changes because the VFS holds the inode lock, but there can have been remote changes). Fixes: 63a4681ff39c ("afs: Locally edit directory data for mkdir/create/unlink/...") Signed-off-by: David Howells <dhowells@redhat.com>
2020-04-10 21:23:27 +07:00
dir_data_version = dvnode->status.data_version + 1;
afs: Fix application of status and callback to be under same lock When applying the status and callback in the response of an operation, apply them in the same critical section so that there's no race between checking the callback state and checking status-dependent state (such as the data version). Fix this by: (1) Allocating a joint {status,callback} record (afs_status_cb) before calling the RPC function for each vnode for which the RPC reply contains a status or a status plus a callback. A flag is set in the record to indicate if a callback was actually received. (2) These records are passed into the RPC functions to be filled in. The afs_decode_status() and yfs_decode_status() functions are removed and the cb_lock is no longer taken. (3) xdr_decode_AFSFetchStatus() and xdr_decode_YFSFetchStatus() no longer update the vnode. (4) xdr_decode_AFSCallBack() and xdr_decode_YFSCallBack() no longer update the vnode. (5) vnodes, expected data-version numbers and callback break counters (cb_break) no longer need to be passed to the reply delivery functions. Note that, for the moment, the file locking functions still need access to both the call and the vnode at the same time. (6) afs_vnode_commit_status() is now given the cb_break value and the expected data_version and the task of applying the status and the callback to the vnode are now done here. This is done under a single taking of vnode->cb_lock. (7) afs_pages_written_back() is now called by afs_store_data() rather than by the reply delivery function. afs_pages_written_back() has been moved to before the call point and is now given the first and last page numbers rather than a pointer to the call. (8) The indicator from YFS.RemoveFile2 as to whether the target file actually got removed (status.abort_code == VNOVNODE) rather than merely dropping a link is now checked in afs_unlink rather than in xdr_decode_YFSFetchStatus(). Supplementary fixes: (*) afs_cache_permit() now gets the caller_access mask from the afs_status_cb object rather than picking it out of the vnode's status record. afs_fetch_status() returns caller_access through its argument list for this purpose also. (*) afs_inode_init_from_status() now uses a write lock on cb_lock rather than a read lock and now sets the callback inside the same critical section. Fixes: c435ee34551e ("afs: Overhaul the callback handling") Signed-off-by: David Howells <dhowells@redhat.com>
2019-05-09 21:16:10 +07:00
while (afs_select_fileserver(&fc)) {
fc.cb_break = afs_calc_vnode_cb_break(dvnode);
afs_fs_rename(&fc, old->d_name.name,
dvnode, new->d_name.name,
afs: Fix application of status and callback to be under same lock When applying the status and callback in the response of an operation, apply them in the same critical section so that there's no race between checking the callback state and checking status-dependent state (such as the data version). Fix this by: (1) Allocating a joint {status,callback} record (afs_status_cb) before calling the RPC function for each vnode for which the RPC reply contains a status or a status plus a callback. A flag is set in the record to indicate if a callback was actually received. (2) These records are passed into the RPC functions to be filled in. The afs_decode_status() and yfs_decode_status() functions are removed and the cb_lock is no longer taken. (3) xdr_decode_AFSFetchStatus() and xdr_decode_YFSFetchStatus() no longer update the vnode. (4) xdr_decode_AFSCallBack() and xdr_decode_YFSCallBack() no longer update the vnode. (5) vnodes, expected data-version numbers and callback break counters (cb_break) no longer need to be passed to the reply delivery functions. Note that, for the moment, the file locking functions still need access to both the call and the vnode at the same time. (6) afs_vnode_commit_status() is now given the cb_break value and the expected data_version and the task of applying the status and the callback to the vnode are now done here. This is done under a single taking of vnode->cb_lock. (7) afs_pages_written_back() is now called by afs_store_data() rather than by the reply delivery function. afs_pages_written_back() has been moved to before the call point and is now given the first and last page numbers rather than a pointer to the call. (8) The indicator from YFS.RemoveFile2 as to whether the target file actually got removed (status.abort_code == VNOVNODE) rather than merely dropping a link is now checked in afs_unlink rather than in xdr_decode_YFSFetchStatus(). Supplementary fixes: (*) afs_cache_permit() now gets the caller_access mask from the afs_status_cb object rather than picking it out of the vnode's status record. afs_fetch_status() returns caller_access through its argument list for this purpose also. (*) afs_inode_init_from_status() now uses a write lock on cb_lock rather than a read lock and now sets the callback inside the same critical section. Fixes: c435ee34551e ("afs: Overhaul the callback handling") Signed-off-by: David Howells <dhowells@redhat.com>
2019-05-09 21:16:10 +07:00
scb, scb);
}
afs: Fix application of status and callback to be under same lock When applying the status and callback in the response of an operation, apply them in the same critical section so that there's no race between checking the callback state and checking status-dependent state (such as the data version). Fix this by: (1) Allocating a joint {status,callback} record (afs_status_cb) before calling the RPC function for each vnode for which the RPC reply contains a status or a status plus a callback. A flag is set in the record to indicate if a callback was actually received. (2) These records are passed into the RPC functions to be filled in. The afs_decode_status() and yfs_decode_status() functions are removed and the cb_lock is no longer taken. (3) xdr_decode_AFSFetchStatus() and xdr_decode_YFSFetchStatus() no longer update the vnode. (4) xdr_decode_AFSCallBack() and xdr_decode_YFSCallBack() no longer update the vnode. (5) vnodes, expected data-version numbers and callback break counters (cb_break) no longer need to be passed to the reply delivery functions. Note that, for the moment, the file locking functions still need access to both the call and the vnode at the same time. (6) afs_vnode_commit_status() is now given the cb_break value and the expected data_version and the task of applying the status and the callback to the vnode are now done here. This is done under a single taking of vnode->cb_lock. (7) afs_pages_written_back() is now called by afs_store_data() rather than by the reply delivery function. afs_pages_written_back() has been moved to before the call point and is now given the first and last page numbers rather than a pointer to the call. (8) The indicator from YFS.RemoveFile2 as to whether the target file actually got removed (status.abort_code == VNOVNODE) rather than merely dropping a link is now checked in afs_unlink rather than in xdr_decode_YFSFetchStatus(). Supplementary fixes: (*) afs_cache_permit() now gets the caller_access mask from the afs_status_cb object rather than picking it out of the vnode's status record. afs_fetch_status() returns caller_access through its argument list for this purpose also. (*) afs_inode_init_from_status() now uses a write lock on cb_lock rather than a read lock and now sets the callback inside the same critical section. Fixes: c435ee34551e ("afs: Overhaul the callback handling") Signed-off-by: David Howells <dhowells@redhat.com>
2019-05-09 21:16:10 +07:00
afs_vnode_commit_status(&fc, dvnode, fc.cb_break,
&dir_data_version, scb);
ret = afs_end_vnode_operation(&fc);
}
if (ret == 0) {
spin_lock(&old->d_lock);
old->d_flags |= DCACHE_NFSFS_RENAMED;
spin_unlock(&old->d_lock);
if (dvnode->silly_key != key) {
key_put(dvnode->silly_key);
dvnode->silly_key = key_get(key);
}
afs: Fix race between post-modification dir edit and readdir/d_revalidate AFS directories are retained locally as a structured file, with lookup being effected by a local search of the file contents. When a modification (such as mkdir) happens, the dir file content is modified locally rather than redownloading the directory. The directory contents are accessed in a number of ways, with a number of different locks schemes: (1) Download of contents - dvnode->validate_lock/write in afs_read_dir(). (2) Lookup and readdir - dvnode->validate_lock/read in afs_dir_iterate(), downgrading from (1) if necessary. (3) d_revalidate of child dentry - dvnode->validate_lock/read in afs_do_lookup_one() downgrading from (1) if necessary. (4) Edit of dir after modification - page locks on individual dir pages. Unfortunately, because (4) uses different locking scheme to (1) - (3), nothing protects against the page being scanned whilst the edit is underway. Even download is not safe as it doesn't lock the pages - relying instead on the validate_lock to serialise as a whole (the theory being that directory contents are treated as a block and always downloaded as a block). Fix this by write-locking dvnode->validate_lock around the edits. Care must be taken in the rename case as there may be two different dirs - but they need not be locked at the same time. In any case, once the lock is taken, the directory version must be rechecked, and the edit skipped if a later version has been downloaded by revalidation (there can't have been any local changes because the VFS holds the inode lock, but there can have been remote changes). Fixes: 63a4681ff39c ("afs: Locally edit directory data for mkdir/create/unlink/...") Signed-off-by: David Howells <dhowells@redhat.com>
2020-04-10 21:23:27 +07:00
down_write(&dvnode->validate_lock);
if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) &&
dvnode->status.data_version == dir_data_version) {
afs_edit_dir_remove(dvnode, &old->d_name,
afs_edit_dir_for_silly_0);
afs_edit_dir_add(dvnode, &new->d_name,
&vnode->fid, afs_edit_dir_for_silly_1);
afs: Fix race between post-modification dir edit and readdir/d_revalidate AFS directories are retained locally as a structured file, with lookup being effected by a local search of the file contents. When a modification (such as mkdir) happens, the dir file content is modified locally rather than redownloading the directory. The directory contents are accessed in a number of ways, with a number of different locks schemes: (1) Download of contents - dvnode->validate_lock/write in afs_read_dir(). (2) Lookup and readdir - dvnode->validate_lock/read in afs_dir_iterate(), downgrading from (1) if necessary. (3) d_revalidate of child dentry - dvnode->validate_lock/read in afs_do_lookup_one() downgrading from (1) if necessary. (4) Edit of dir after modification - page locks on individual dir pages. Unfortunately, because (4) uses different locking scheme to (1) - (3), nothing protects against the page being scanned whilst the edit is underway. Even download is not safe as it doesn't lock the pages - relying instead on the validate_lock to serialise as a whole (the theory being that directory contents are treated as a block and always downloaded as a block). Fix this by write-locking dvnode->validate_lock around the edits. Care must be taken in the rename case as there may be two different dirs - but they need not be locked at the same time. In any case, once the lock is taken, the directory version must be rechecked, and the edit skipped if a later version has been downloaded by revalidation (there can't have been any local changes because the VFS holds the inode lock, but there can have been remote changes). Fixes: 63a4681ff39c ("afs: Locally edit directory data for mkdir/create/unlink/...") Signed-off-by: David Howells <dhowells@redhat.com>
2020-04-10 21:23:27 +07:00
}
up_write(&dvnode->validate_lock);
}
afs: Fix application of status and callback to be under same lock When applying the status and callback in the response of an operation, apply them in the same critical section so that there's no race between checking the callback state and checking status-dependent state (such as the data version). Fix this by: (1) Allocating a joint {status,callback} record (afs_status_cb) before calling the RPC function for each vnode for which the RPC reply contains a status or a status plus a callback. A flag is set in the record to indicate if a callback was actually received. (2) These records are passed into the RPC functions to be filled in. The afs_decode_status() and yfs_decode_status() functions are removed and the cb_lock is no longer taken. (3) xdr_decode_AFSFetchStatus() and xdr_decode_YFSFetchStatus() no longer update the vnode. (4) xdr_decode_AFSCallBack() and xdr_decode_YFSCallBack() no longer update the vnode. (5) vnodes, expected data-version numbers and callback break counters (cb_break) no longer need to be passed to the reply delivery functions. Note that, for the moment, the file locking functions still need access to both the call and the vnode at the same time. (6) afs_vnode_commit_status() is now given the cb_break value and the expected data_version and the task of applying the status and the callback to the vnode are now done here. This is done under a single taking of vnode->cb_lock. (7) afs_pages_written_back() is now called by afs_store_data() rather than by the reply delivery function. afs_pages_written_back() has been moved to before the call point and is now given the first and last page numbers rather than a pointer to the call. (8) The indicator from YFS.RemoveFile2 as to whether the target file actually got removed (status.abort_code == VNOVNODE) rather than merely dropping a link is now checked in afs_unlink rather than in xdr_decode_YFSFetchStatus(). Supplementary fixes: (*) afs_cache_permit() now gets the caller_access mask from the afs_status_cb object rather than picking it out of the vnode's status record. afs_fetch_status() returns caller_access through its argument list for this purpose also. (*) afs_inode_init_from_status() now uses a write lock on cb_lock rather than a read lock and now sets the callback inside the same critical section. Fixes: c435ee34551e ("afs: Overhaul the callback handling") Signed-off-by: David Howells <dhowells@redhat.com>
2019-05-09 21:16:10 +07:00
kfree(scb);
_leave(" = %d", ret);
return ret;
}
/**
* afs_sillyrename - Perform a silly-rename of a dentry
*
* AFS is stateless and the server doesn't know when the client is holding a
* file open. To prevent application problems when a file is unlinked while
* it's still open, the client performs a "silly-rename". That is, it renames
* the file to a hidden file in the same directory, and only performs the
* unlink once the last reference to it is put.
*
* The final cleanup is done during dentry_iput.
*/
int afs_sillyrename(struct afs_vnode *dvnode, struct afs_vnode *vnode,
struct dentry *dentry, struct key *key)
{
static unsigned int sillycounter;
struct dentry *sdentry = NULL;
unsigned char silly[16];
int ret = -EBUSY;
_enter("");
/* We don't allow a dentry to be silly-renamed twice. */
if (dentry->d_flags & DCACHE_NFSFS_RENAMED)
return -EBUSY;
sdentry = NULL;
do {
int slen;
dput(sdentry);
sillycounter++;
/* Create a silly name. Note that the ".__afs" prefix is
* understood by the salvager and must not be changed.
*/
slen = scnprintf(silly, sizeof(silly), ".__afs%04X", sillycounter);
sdentry = lookup_one_len(silly, dentry->d_parent, slen);
/* N.B. Better to return EBUSY here ... it could be dangerous
* to delete the file while it's in use.
*/
if (IS_ERR(sdentry))
goto out;
} while (!d_is_negative(sdentry));
ihold(&vnode->vfs_inode);
ret = afs_do_silly_rename(dvnode, vnode, dentry, sdentry, key);
switch (ret) {
case 0:
/* The rename succeeded. */
d_move(dentry, sdentry);
break;
case -ERESTARTSYS:
/* The result of the rename is unknown. Play it safe by forcing
* a new lookup.
*/
d_drop(dentry);
d_drop(sdentry);
}
iput(&vnode->vfs_inode);
dput(sdentry);
out:
_leave(" = %d", ret);
return ret;
}
/*
* Tell the server to remove a sillyrename file.
*/
static int afs_do_silly_unlink(struct afs_vnode *dvnode, struct afs_vnode *vnode,
struct dentry *dentry, struct key *key)
{
struct afs_fs_cursor fc;
afs: Fix application of status and callback to be under same lock When applying the status and callback in the response of an operation, apply them in the same critical section so that there's no race between checking the callback state and checking status-dependent state (such as the data version). Fix this by: (1) Allocating a joint {status,callback} record (afs_status_cb) before calling the RPC function for each vnode for which the RPC reply contains a status or a status plus a callback. A flag is set in the record to indicate if a callback was actually received. (2) These records are passed into the RPC functions to be filled in. The afs_decode_status() and yfs_decode_status() functions are removed and the cb_lock is no longer taken. (3) xdr_decode_AFSFetchStatus() and xdr_decode_YFSFetchStatus() no longer update the vnode. (4) xdr_decode_AFSCallBack() and xdr_decode_YFSCallBack() no longer update the vnode. (5) vnodes, expected data-version numbers and callback break counters (cb_break) no longer need to be passed to the reply delivery functions. Note that, for the moment, the file locking functions still need access to both the call and the vnode at the same time. (6) afs_vnode_commit_status() is now given the cb_break value and the expected data_version and the task of applying the status and the callback to the vnode are now done here. This is done under a single taking of vnode->cb_lock. (7) afs_pages_written_back() is now called by afs_store_data() rather than by the reply delivery function. afs_pages_written_back() has been moved to before the call point and is now given the first and last page numbers rather than a pointer to the call. (8) The indicator from YFS.RemoveFile2 as to whether the target file actually got removed (status.abort_code == VNOVNODE) rather than merely dropping a link is now checked in afs_unlink rather than in xdr_decode_YFSFetchStatus(). Supplementary fixes: (*) afs_cache_permit() now gets the caller_access mask from the afs_status_cb object rather than picking it out of the vnode's status record. afs_fetch_status() returns caller_access through its argument list for this purpose also. (*) afs_inode_init_from_status() now uses a write lock on cb_lock rather than a read lock and now sets the callback inside the same critical section. Fixes: c435ee34551e ("afs: Overhaul the callback handling") Signed-off-by: David Howells <dhowells@redhat.com>
2019-05-09 21:16:10 +07:00
struct afs_status_cb *scb;
int ret = -ERESTARTSYS;
_enter("");
afs: Fix application of status and callback to be under same lock When applying the status and callback in the response of an operation, apply them in the same critical section so that there's no race between checking the callback state and checking status-dependent state (such as the data version). Fix this by: (1) Allocating a joint {status,callback} record (afs_status_cb) before calling the RPC function for each vnode for which the RPC reply contains a status or a status plus a callback. A flag is set in the record to indicate if a callback was actually received. (2) These records are passed into the RPC functions to be filled in. The afs_decode_status() and yfs_decode_status() functions are removed and the cb_lock is no longer taken. (3) xdr_decode_AFSFetchStatus() and xdr_decode_YFSFetchStatus() no longer update the vnode. (4) xdr_decode_AFSCallBack() and xdr_decode_YFSCallBack() no longer update the vnode. (5) vnodes, expected data-version numbers and callback break counters (cb_break) no longer need to be passed to the reply delivery functions. Note that, for the moment, the file locking functions still need access to both the call and the vnode at the same time. (6) afs_vnode_commit_status() is now given the cb_break value and the expected data_version and the task of applying the status and the callback to the vnode are now done here. This is done under a single taking of vnode->cb_lock. (7) afs_pages_written_back() is now called by afs_store_data() rather than by the reply delivery function. afs_pages_written_back() has been moved to before the call point and is now given the first and last page numbers rather than a pointer to the call. (8) The indicator from YFS.RemoveFile2 as to whether the target file actually got removed (status.abort_code == VNOVNODE) rather than merely dropping a link is now checked in afs_unlink rather than in xdr_decode_YFSFetchStatus(). Supplementary fixes: (*) afs_cache_permit() now gets the caller_access mask from the afs_status_cb object rather than picking it out of the vnode's status record. afs_fetch_status() returns caller_access through its argument list for this purpose also. (*) afs_inode_init_from_status() now uses a write lock on cb_lock rather than a read lock and now sets the callback inside the same critical section. Fixes: c435ee34551e ("afs: Overhaul the callback handling") Signed-off-by: David Howells <dhowells@redhat.com>
2019-05-09 21:16:10 +07:00
scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL);
if (!scb)
return -ENOMEM;
trace_afs_silly_rename(vnode, true);
afs: Make some RPC operations non-interruptible Make certain RPC operations non-interruptible, including: (*) Set attributes (*) Store data We don't want to get interrupted during a flush on close, flush on unlock, writeback or an inode update, leaving us in a state where we still need to do the writeback or update. (*) Extend lock (*) Release lock We don't want to get lock extension interrupted as the file locks on the server are time-limited. Interruption during lock release is less of an issue since the lock is time-limited, but it's better to complete the release to avoid a several-minute wait to recover it. *Setting* the lock isn't a problem if it's interrupted since we can just return to the user and tell them they were interrupted - at which point they can elect to retry. (*) Silly unlink We want to remove silly unlink files if we can, rather than leaving them for the salvager to clear up. Note that whilst these calls are no longer interruptible, they do have timeouts on them, so if the server stops responding the call will fail with something like ETIME or ECONNRESET. Without this, the following: kAFS: Unexpected error from FS.StoreData -512 appears in dmesg when a pending store data gets interrupted and some processes may just hang. Additionally, make the code that checks/updates the server record ignore failure due to interruption if the main call is uninterruptible and if the server has an address list. The next op will check it again since the expiration time on the old list has past. Fixes: d2ddc776a458 ("afs: Overhaul volume and server record caching and fileserver rotation") Reported-by: Jonathan Billings <jsbillings@jsbillings.org> Reported-by: Marc Dionne <marc.dionne@auristor.com> Signed-off-by: David Howells <dhowells@redhat.com>
2019-05-08 22:16:31 +07:00
if (afs_begin_vnode_operation(&fc, dvnode, key, false)) {
afs: Fix application of status and callback to be under same lock When applying the status and callback in the response of an operation, apply them in the same critical section so that there's no race between checking the callback state and checking status-dependent state (such as the data version). Fix this by: (1) Allocating a joint {status,callback} record (afs_status_cb) before calling the RPC function for each vnode for which the RPC reply contains a status or a status plus a callback. A flag is set in the record to indicate if a callback was actually received. (2) These records are passed into the RPC functions to be filled in. The afs_decode_status() and yfs_decode_status() functions are removed and the cb_lock is no longer taken. (3) xdr_decode_AFSFetchStatus() and xdr_decode_YFSFetchStatus() no longer update the vnode. (4) xdr_decode_AFSCallBack() and xdr_decode_YFSCallBack() no longer update the vnode. (5) vnodes, expected data-version numbers and callback break counters (cb_break) no longer need to be passed to the reply delivery functions. Note that, for the moment, the file locking functions still need access to both the call and the vnode at the same time. (6) afs_vnode_commit_status() is now given the cb_break value and the expected data_version and the task of applying the status and the callback to the vnode are now done here. This is done under a single taking of vnode->cb_lock. (7) afs_pages_written_back() is now called by afs_store_data() rather than by the reply delivery function. afs_pages_written_back() has been moved to before the call point and is now given the first and last page numbers rather than a pointer to the call. (8) The indicator from YFS.RemoveFile2 as to whether the target file actually got removed (status.abort_code == VNOVNODE) rather than merely dropping a link is now checked in afs_unlink rather than in xdr_decode_YFSFetchStatus(). Supplementary fixes: (*) afs_cache_permit() now gets the caller_access mask from the afs_status_cb object rather than picking it out of the vnode's status record. afs_fetch_status() returns caller_access through its argument list for this purpose also. (*) afs_inode_init_from_status() now uses a write lock on cb_lock rather than a read lock and now sets the callback inside the same critical section. Fixes: c435ee34551e ("afs: Overhaul the callback handling") Signed-off-by: David Howells <dhowells@redhat.com>
2019-05-09 21:16:10 +07:00
afs_dataversion_t dir_data_version = dvnode->status.data_version + 1;
while (afs_select_fileserver(&fc)) {
fc.cb_break = afs_calc_vnode_cb_break(dvnode);
if (test_bit(AFS_SERVER_FL_IS_YFS, &fc.cbi->server->flags) &&
!test_bit(AFS_SERVER_FL_NO_RM2, &fc.cbi->server->flags)) {
yfs_fs_remove_file2(&fc, vnode, dentry->d_name.name,
afs: Fix application of status and callback to be under same lock When applying the status and callback in the response of an operation, apply them in the same critical section so that there's no race between checking the callback state and checking status-dependent state (such as the data version). Fix this by: (1) Allocating a joint {status,callback} record (afs_status_cb) before calling the RPC function for each vnode for which the RPC reply contains a status or a status plus a callback. A flag is set in the record to indicate if a callback was actually received. (2) These records are passed into the RPC functions to be filled in. The afs_decode_status() and yfs_decode_status() functions are removed and the cb_lock is no longer taken. (3) xdr_decode_AFSFetchStatus() and xdr_decode_YFSFetchStatus() no longer update the vnode. (4) xdr_decode_AFSCallBack() and xdr_decode_YFSCallBack() no longer update the vnode. (5) vnodes, expected data-version numbers and callback break counters (cb_break) no longer need to be passed to the reply delivery functions. Note that, for the moment, the file locking functions still need access to both the call and the vnode at the same time. (6) afs_vnode_commit_status() is now given the cb_break value and the expected data_version and the task of applying the status and the callback to the vnode are now done here. This is done under a single taking of vnode->cb_lock. (7) afs_pages_written_back() is now called by afs_store_data() rather than by the reply delivery function. afs_pages_written_back() has been moved to before the call point and is now given the first and last page numbers rather than a pointer to the call. (8) The indicator from YFS.RemoveFile2 as to whether the target file actually got removed (status.abort_code == VNOVNODE) rather than merely dropping a link is now checked in afs_unlink rather than in xdr_decode_YFSFetchStatus(). Supplementary fixes: (*) afs_cache_permit() now gets the caller_access mask from the afs_status_cb object rather than picking it out of the vnode's status record. afs_fetch_status() returns caller_access through its argument list for this purpose also. (*) afs_inode_init_from_status() now uses a write lock on cb_lock rather than a read lock and now sets the callback inside the same critical section. Fixes: c435ee34551e ("afs: Overhaul the callback handling") Signed-off-by: David Howells <dhowells@redhat.com>
2019-05-09 21:16:10 +07:00
&scb[0], &scb[1]);
if (fc.ac.error != -ECONNABORTED ||
fc.ac.abort_code != RXGEN_OPCODE)
continue;
set_bit(AFS_SERVER_FL_NO_RM2, &fc.cbi->server->flags);
}
afs: Fix application of status and callback to be under same lock When applying the status and callback in the response of an operation, apply them in the same critical section so that there's no race between checking the callback state and checking status-dependent state (such as the data version). Fix this by: (1) Allocating a joint {status,callback} record (afs_status_cb) before calling the RPC function for each vnode for which the RPC reply contains a status or a status plus a callback. A flag is set in the record to indicate if a callback was actually received. (2) These records are passed into the RPC functions to be filled in. The afs_decode_status() and yfs_decode_status() functions are removed and the cb_lock is no longer taken. (3) xdr_decode_AFSFetchStatus() and xdr_decode_YFSFetchStatus() no longer update the vnode. (4) xdr_decode_AFSCallBack() and xdr_decode_YFSCallBack() no longer update the vnode. (5) vnodes, expected data-version numbers and callback break counters (cb_break) no longer need to be passed to the reply delivery functions. Note that, for the moment, the file locking functions still need access to both the call and the vnode at the same time. (6) afs_vnode_commit_status() is now given the cb_break value and the expected data_version and the task of applying the status and the callback to the vnode are now done here. This is done under a single taking of vnode->cb_lock. (7) afs_pages_written_back() is now called by afs_store_data() rather than by the reply delivery function. afs_pages_written_back() has been moved to before the call point and is now given the first and last page numbers rather than a pointer to the call. (8) The indicator from YFS.RemoveFile2 as to whether the target file actually got removed (status.abort_code == VNOVNODE) rather than merely dropping a link is now checked in afs_unlink rather than in xdr_decode_YFSFetchStatus(). Supplementary fixes: (*) afs_cache_permit() now gets the caller_access mask from the afs_status_cb object rather than picking it out of the vnode's status record. afs_fetch_status() returns caller_access through its argument list for this purpose also. (*) afs_inode_init_from_status() now uses a write lock on cb_lock rather than a read lock and now sets the callback inside the same critical section. Fixes: c435ee34551e ("afs: Overhaul the callback handling") Signed-off-by: David Howells <dhowells@redhat.com>
2019-05-09 21:16:10 +07:00
afs_fs_remove(&fc, vnode, dentry->d_name.name, false, &scb[0]);
}
afs: Fix application of status and callback to be under same lock When applying the status and callback in the response of an operation, apply them in the same critical section so that there's no race between checking the callback state and checking status-dependent state (such as the data version). Fix this by: (1) Allocating a joint {status,callback} record (afs_status_cb) before calling the RPC function for each vnode for which the RPC reply contains a status or a status plus a callback. A flag is set in the record to indicate if a callback was actually received. (2) These records are passed into the RPC functions to be filled in. The afs_decode_status() and yfs_decode_status() functions are removed and the cb_lock is no longer taken. (3) xdr_decode_AFSFetchStatus() and xdr_decode_YFSFetchStatus() no longer update the vnode. (4) xdr_decode_AFSCallBack() and xdr_decode_YFSCallBack() no longer update the vnode. (5) vnodes, expected data-version numbers and callback break counters (cb_break) no longer need to be passed to the reply delivery functions. Note that, for the moment, the file locking functions still need access to both the call and the vnode at the same time. (6) afs_vnode_commit_status() is now given the cb_break value and the expected data_version and the task of applying the status and the callback to the vnode are now done here. This is done under a single taking of vnode->cb_lock. (7) afs_pages_written_back() is now called by afs_store_data() rather than by the reply delivery function. afs_pages_written_back() has been moved to before the call point and is now given the first and last page numbers rather than a pointer to the call. (8) The indicator from YFS.RemoveFile2 as to whether the target file actually got removed (status.abort_code == VNOVNODE) rather than merely dropping a link is now checked in afs_unlink rather than in xdr_decode_YFSFetchStatus(). Supplementary fixes: (*) afs_cache_permit() now gets the caller_access mask from the afs_status_cb object rather than picking it out of the vnode's status record. afs_fetch_status() returns caller_access through its argument list for this purpose also. (*) afs_inode_init_from_status() now uses a write lock on cb_lock rather than a read lock and now sets the callback inside the same critical section. Fixes: c435ee34551e ("afs: Overhaul the callback handling") Signed-off-by: David Howells <dhowells@redhat.com>
2019-05-09 21:16:10 +07:00
afs_vnode_commit_status(&fc, dvnode, fc.cb_break,
&dir_data_version, &scb[0]);
ret = afs_end_vnode_operation(&fc);
if (ret == 0) {
drop_nlink(&vnode->vfs_inode);
if (vnode->vfs_inode.i_nlink == 0) {
set_bit(AFS_VNODE_DELETED, &vnode->flags);
clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
}
}
afs: Fix race between post-modification dir edit and readdir/d_revalidate AFS directories are retained locally as a structured file, with lookup being effected by a local search of the file contents. When a modification (such as mkdir) happens, the dir file content is modified locally rather than redownloading the directory. The directory contents are accessed in a number of ways, with a number of different locks schemes: (1) Download of contents - dvnode->validate_lock/write in afs_read_dir(). (2) Lookup and readdir - dvnode->validate_lock/read in afs_dir_iterate(), downgrading from (1) if necessary. (3) d_revalidate of child dentry - dvnode->validate_lock/read in afs_do_lookup_one() downgrading from (1) if necessary. (4) Edit of dir after modification - page locks on individual dir pages. Unfortunately, because (4) uses different locking scheme to (1) - (3), nothing protects against the page being scanned whilst the edit is underway. Even download is not safe as it doesn't lock the pages - relying instead on the validate_lock to serialise as a whole (the theory being that directory contents are treated as a block and always downloaded as a block). Fix this by write-locking dvnode->validate_lock around the edits. Care must be taken in the rename case as there may be two different dirs - but they need not be locked at the same time. In any case, once the lock is taken, the directory version must be rechecked, and the edit skipped if a later version has been downloaded by revalidation (there can't have been any local changes because the VFS holds the inode lock, but there can have been remote changes). Fixes: 63a4681ff39c ("afs: Locally edit directory data for mkdir/create/unlink/...") Signed-off-by: David Howells <dhowells@redhat.com>
2020-04-10 21:23:27 +07:00
if (ret == 0) {
down_write(&dvnode->validate_lock);
if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) &&
dvnode->status.data_version == dir_data_version)
afs_edit_dir_remove(dvnode, &dentry->d_name,
afs_edit_dir_for_unlink);
up_write(&dvnode->validate_lock);
}
}
afs: Fix application of status and callback to be under same lock When applying the status and callback in the response of an operation, apply them in the same critical section so that there's no race between checking the callback state and checking status-dependent state (such as the data version). Fix this by: (1) Allocating a joint {status,callback} record (afs_status_cb) before calling the RPC function for each vnode for which the RPC reply contains a status or a status plus a callback. A flag is set in the record to indicate if a callback was actually received. (2) These records are passed into the RPC functions to be filled in. The afs_decode_status() and yfs_decode_status() functions are removed and the cb_lock is no longer taken. (3) xdr_decode_AFSFetchStatus() and xdr_decode_YFSFetchStatus() no longer update the vnode. (4) xdr_decode_AFSCallBack() and xdr_decode_YFSCallBack() no longer update the vnode. (5) vnodes, expected data-version numbers and callback break counters (cb_break) no longer need to be passed to the reply delivery functions. Note that, for the moment, the file locking functions still need access to both the call and the vnode at the same time. (6) afs_vnode_commit_status() is now given the cb_break value and the expected data_version and the task of applying the status and the callback to the vnode are now done here. This is done under a single taking of vnode->cb_lock. (7) afs_pages_written_back() is now called by afs_store_data() rather than by the reply delivery function. afs_pages_written_back() has been moved to before the call point and is now given the first and last page numbers rather than a pointer to the call. (8) The indicator from YFS.RemoveFile2 as to whether the target file actually got removed (status.abort_code == VNOVNODE) rather than merely dropping a link is now checked in afs_unlink rather than in xdr_decode_YFSFetchStatus(). Supplementary fixes: (*) afs_cache_permit() now gets the caller_access mask from the afs_status_cb object rather than picking it out of the vnode's status record. afs_fetch_status() returns caller_access through its argument list for this purpose also. (*) afs_inode_init_from_status() now uses a write lock on cb_lock rather than a read lock and now sets the callback inside the same critical section. Fixes: c435ee34551e ("afs: Overhaul the callback handling") Signed-off-by: David Howells <dhowells@redhat.com>
2019-05-09 21:16:10 +07:00
kfree(scb);
_leave(" = %d", ret);
return ret;
}
/*
* Remove sillyrename file on iput.
*/
int afs_silly_iput(struct dentry *dentry, struct inode *inode)
{
struct afs_vnode *dvnode = AFS_FS_I(d_inode(dentry->d_parent));
struct afs_vnode *vnode = AFS_FS_I(inode);
struct dentry *alias;
int ret;
DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
_enter("%p{%pd},%llx", dentry, dentry, vnode->fid.vnode);
down_read(&dvnode->rmdir_lock);
alias = d_alloc_parallel(dentry->d_parent, &dentry->d_name, &wq);
if (IS_ERR(alias)) {
up_read(&dvnode->rmdir_lock);
return 0;
}
if (!d_in_lookup(alias)) {
/* We raced with lookup... See if we need to transfer the
* sillyrename information to the aliased dentry.
*/
ret = 0;
spin_lock(&alias->d_lock);
if (d_really_is_positive(alias) &&
!(alias->d_flags & DCACHE_NFSFS_RENAMED)) {
alias->d_flags |= DCACHE_NFSFS_RENAMED;
ret = 1;
}
spin_unlock(&alias->d_lock);
up_read(&dvnode->rmdir_lock);
dput(alias);
return ret;
}
/* Stop lock-release from complaining. */
spin_lock(&vnode->lock);
vnode->lock_state = AFS_VNODE_LOCK_DELETED;
trace_afs_flock_ev(vnode, NULL, afs_flock_silly_delete, 0);
spin_unlock(&vnode->lock);
afs_do_silly_unlink(dvnode, vnode, dentry, dvnode->silly_key);
up_read(&dvnode->rmdir_lock);
d_lookup_done(alias);
dput(alias);
return 1;
}