2019-05-31 16:09:56 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-only
|
2006-01-17 16:47:12 +08:00
|
|
|
/*
|
2008-03-15 04:09:15 +08:00
|
|
|
* Copyright (C) 2005-2008 Red Hat, Inc. All rights reserved.
|
2006-01-17 16:47:12 +08:00
|
|
|
*/
|
|
|
|
|
2008-03-15 04:09:15 +08:00
|
|
|
#include <linux/fs.h>
|
2022-11-20 22:15:34 +08:00
|
|
|
#include <linux/filelock.h>
|
2006-01-17 16:47:12 +08:00
|
|
|
#include <linux/miscdevice.h>
|
2006-10-20 05:23:57 +08:00
|
|
|
#include <linux/poll.h>
|
2008-03-15 04:09:15 +08:00
|
|
|
#include <linux/dlm.h>
|
|
|
|
#include <linux/dlm_plock.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
|
|
|
#include <linux/slab.h>
|
2006-01-17 16:47:12 +08:00
|
|
|
|
2008-03-15 04:09:15 +08:00
|
|
|
#include "dlm_internal.h"
|
|
|
|
#include "lockspace.h"
|
2006-01-17 16:47:12 +08:00
|
|
|
|
2022-04-05 04:06:36 +08:00
|
|
|
static DEFINE_SPINLOCK(ops_lock);
|
|
|
|
static LIST_HEAD(send_list);
|
|
|
|
static LIST_HEAD(recv_list);
|
|
|
|
static DECLARE_WAIT_QUEUE_HEAD(send_wq);
|
|
|
|
static DECLARE_WAIT_QUEUE_HEAD(recv_wq);
|
2006-01-17 16:47:12 +08:00
|
|
|
|
2022-04-05 04:06:32 +08:00
|
|
|
struct plock_async_data {
|
2006-11-15 05:37:25 +08:00
|
|
|
void *fl;
|
|
|
|
void *file;
|
|
|
|
struct file_lock flc;
|
2022-04-05 04:06:32 +08:00
|
|
|
int (*callback)(struct file_lock *fl, int result);
|
2006-11-15 05:37:25 +08:00
|
|
|
};
|
|
|
|
|
2022-04-05 04:06:32 +08:00
|
|
|
struct plock_op {
|
|
|
|
struct list_head list;
|
|
|
|
int done;
|
2022-06-23 02:45:09 +08:00
|
|
|
/* if lock op got interrupted while waiting dlm_controld reply */
|
|
|
|
bool sigint;
|
2022-04-05 04:06:32 +08:00
|
|
|
struct dlm_plock_info info;
|
|
|
|
/* if set indicates async handling */
|
|
|
|
struct plock_async_data *data;
|
|
|
|
};
|
2006-11-15 05:37:25 +08:00
|
|
|
|
2008-03-15 04:09:15 +08:00
|
|
|
static inline void set_version(struct dlm_plock_info *info)
|
2006-01-17 16:47:12 +08:00
|
|
|
{
|
2008-03-15 04:09:15 +08:00
|
|
|
info->version[0] = DLM_PLOCK_VERSION_MAJOR;
|
|
|
|
info->version[1] = DLM_PLOCK_VERSION_MINOR;
|
|
|
|
info->version[2] = DLM_PLOCK_VERSION_PATCH;
|
2006-01-17 16:47:12 +08:00
|
|
|
}
|
|
|
|
|
2008-03-15 04:09:15 +08:00
|
|
|
static int check_version(struct dlm_plock_info *info)
|
2006-01-17 16:47:12 +08:00
|
|
|
{
|
2008-03-15 04:09:15 +08:00
|
|
|
if ((DLM_PLOCK_VERSION_MAJOR != info->version[0]) ||
|
|
|
|
(DLM_PLOCK_VERSION_MINOR < info->version[1])) {
|
|
|
|
log_print("plock device version mismatch: "
|
2006-01-17 16:47:12 +08:00
|
|
|
"kernel (%u.%u.%u), user (%u.%u.%u)",
|
2008-03-15 04:09:15 +08:00
|
|
|
DLM_PLOCK_VERSION_MAJOR,
|
|
|
|
DLM_PLOCK_VERSION_MINOR,
|
|
|
|
DLM_PLOCK_VERSION_PATCH,
|
2006-01-17 16:47:12 +08:00
|
|
|
info->version[0],
|
|
|
|
info->version[1],
|
|
|
|
info->version[2]);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2022-04-05 04:06:32 +08:00
|
|
|
static void dlm_release_plock_op(struct plock_op *op)
|
|
|
|
{
|
|
|
|
kfree(op->data);
|
|
|
|
kfree(op);
|
|
|
|
}
|
|
|
|
|
2006-01-17 16:47:12 +08:00
|
|
|
static void send_op(struct plock_op *op)
|
|
|
|
{
|
|
|
|
set_version(&op->info);
|
|
|
|
spin_lock(&ops_lock);
|
|
|
|
list_add_tail(&op->list, &send_list);
|
|
|
|
spin_unlock(&ops_lock);
|
|
|
|
wake_up(&send_wq);
|
|
|
|
}
|
|
|
|
|
2011-03-03 04:20:04 +08:00
|
|
|
/* If a process was killed while waiting for the only plock on a file,
|
|
|
|
locks_remove_posix will not see any lock on the file so it won't
|
|
|
|
send an unlock-close to us to pass on to userspace to clean up the
|
|
|
|
abandoned waiter. So, we have to insert the unlock-close when the
|
|
|
|
lock call is interrupted. */
|
|
|
|
|
2022-06-23 02:45:08 +08:00
|
|
|
static void do_unlock_close(const struct dlm_plock_info *info)
|
2011-03-03 04:20:04 +08:00
|
|
|
{
|
|
|
|
struct plock_op *op;
|
|
|
|
|
|
|
|
op = kzalloc(sizeof(*op), GFP_NOFS);
|
|
|
|
if (!op)
|
|
|
|
return;
|
|
|
|
|
|
|
|
op->info.optype = DLM_PLOCK_OP_UNLOCK;
|
2022-06-23 02:45:08 +08:00
|
|
|
op->info.pid = info->pid;
|
|
|
|
op->info.fsid = info->fsid;
|
|
|
|
op->info.number = info->number;
|
2011-03-03 04:20:04 +08:00
|
|
|
op->info.start = 0;
|
|
|
|
op->info.end = OFFSET_MAX;
|
2022-06-23 02:45:08 +08:00
|
|
|
op->info.owner = info->owner;
|
2011-03-03 04:20:04 +08:00
|
|
|
|
|
|
|
op->info.flags |= DLM_PLOCK_FL_CLOSE;
|
|
|
|
send_op(op);
|
|
|
|
}
|
|
|
|
|
2008-03-15 04:09:15 +08:00
|
|
|
int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
|
|
|
|
int cmd, struct file_lock *fl)
|
2006-01-17 16:47:12 +08:00
|
|
|
{
|
2022-04-05 04:06:32 +08:00
|
|
|
struct plock_async_data *op_data;
|
2008-03-15 04:09:15 +08:00
|
|
|
struct dlm_ls *ls;
|
2006-01-17 16:47:12 +08:00
|
|
|
struct plock_op *op;
|
|
|
|
int rv;
|
|
|
|
|
2008-03-15 04:09:15 +08:00
|
|
|
ls = dlm_find_lockspace_local(lockspace);
|
|
|
|
if (!ls)
|
|
|
|
return -EINVAL;
|
|
|
|
|
2022-04-05 04:06:32 +08:00
|
|
|
op = kzalloc(sizeof(*op), GFP_NOFS);
|
|
|
|
if (!op) {
|
2008-03-15 04:09:15 +08:00
|
|
|
rv = -ENOMEM;
|
|
|
|
goto out;
|
|
|
|
}
|
2006-01-17 16:47:12 +08:00
|
|
|
|
2008-03-15 04:09:15 +08:00
|
|
|
op->info.optype = DLM_PLOCK_OP_LOCK;
|
2006-04-26 03:45:51 +08:00
|
|
|
op->info.pid = fl->fl_pid;
|
2006-01-17 16:47:12 +08:00
|
|
|
op->info.ex = (fl->fl_type == F_WRLCK);
|
|
|
|
op->info.wait = IS_SETLKW(cmd);
|
2008-03-15 04:09:15 +08:00
|
|
|
op->info.fsid = ls->ls_global_id;
|
|
|
|
op->info.number = number;
|
2006-01-17 16:47:12 +08:00
|
|
|
op->info.start = fl->fl_start;
|
|
|
|
op->info.end = fl->fl_end;
|
2022-04-05 04:06:32 +08:00
|
|
|
/* async handling */
|
2011-07-21 08:21:59 +08:00
|
|
|
if (fl->fl_lmops && fl->fl_lmops->lm_grant) {
|
2022-04-05 04:06:32 +08:00
|
|
|
op_data = kzalloc(sizeof(*op_data), GFP_NOFS);
|
|
|
|
if (!op_data) {
|
|
|
|
dlm_release_plock_op(op);
|
|
|
|
rv = -ENOMEM;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2007-12-06 23:35:25 +08:00
|
|
|
/* fl_owner is lockd which doesn't distinguish
|
|
|
|
processes on the nfs client */
|
|
|
|
op->info.owner = (__u64) fl->fl_pid;
|
2022-04-05 04:06:32 +08:00
|
|
|
op_data->callback = fl->fl_lmops->lm_grant;
|
|
|
|
locks_init_lock(&op_data->flc);
|
|
|
|
locks_copy_lock(&op_data->flc, fl);
|
|
|
|
op_data->fl = fl;
|
|
|
|
op_data->file = file;
|
|
|
|
|
|
|
|
op->data = op_data;
|
2022-04-05 04:06:33 +08:00
|
|
|
|
|
|
|
send_op(op);
|
|
|
|
rv = FILE_LOCK_DEFERRED;
|
|
|
|
goto out;
|
2007-12-06 23:35:25 +08:00
|
|
|
} else {
|
|
|
|
op->info.owner = (__u64)(long) fl->fl_owner;
|
|
|
|
}
|
2006-01-17 16:47:12 +08:00
|
|
|
|
|
|
|
send_op(op);
|
2006-11-15 05:37:25 +08:00
|
|
|
|
2022-04-05 04:06:33 +08:00
|
|
|
rv = wait_event_interruptible(recv_wq, (op->done != 0));
|
|
|
|
if (rv == -ERESTARTSYS) {
|
|
|
|
spin_lock(&ops_lock);
|
2022-06-23 02:45:09 +08:00
|
|
|
/* recheck under ops_lock if we got a done != 0,
|
|
|
|
* if so this interrupt case should be ignored
|
|
|
|
*/
|
|
|
|
if (op->done != 0) {
|
|
|
|
spin_unlock(&ops_lock);
|
|
|
|
goto do_lock_wait;
|
|
|
|
}
|
|
|
|
|
|
|
|
op->sigint = true;
|
2022-04-05 04:06:33 +08:00
|
|
|
spin_unlock(&ops_lock);
|
2022-06-23 02:45:05 +08:00
|
|
|
log_debug(ls, "%s: wait interrupted %x %llx pid %d",
|
2022-04-05 04:06:34 +08:00
|
|
|
__func__, ls->ls_global_id,
|
2022-06-23 02:45:06 +08:00
|
|
|
(unsigned long long)number, op->info.pid);
|
2008-03-15 04:09:15 +08:00
|
|
|
goto out;
|
|
|
|
}
|
2006-01-17 16:47:12 +08:00
|
|
|
|
2022-06-23 02:45:09 +08:00
|
|
|
do_lock_wait:
|
|
|
|
|
2022-04-05 04:06:31 +08:00
|
|
|
WARN_ON(!list_empty(&op->list));
|
2006-01-17 16:47:12 +08:00
|
|
|
|
|
|
|
rv = op->info.rv;
|
|
|
|
|
|
|
|
if (!rv) {
|
2015-10-23 01:38:14 +08:00
|
|
|
if (locks_lock_file_wait(file, fl) < 0)
|
2008-03-15 04:09:15 +08:00
|
|
|
log_error(ls, "dlm_posix_lock: vfs lock error %llx",
|
|
|
|
(unsigned long long)number);
|
2006-01-17 16:47:12 +08:00
|
|
|
}
|
|
|
|
|
2022-04-05 04:06:32 +08:00
|
|
|
dlm_release_plock_op(op);
|
2008-03-15 04:09:15 +08:00
|
|
|
out:
|
|
|
|
dlm_put_lockspace(ls);
|
2006-11-15 05:37:25 +08:00
|
|
|
return rv;
|
|
|
|
}
|
2008-03-15 04:09:15 +08:00
|
|
|
EXPORT_SYMBOL_GPL(dlm_posix_lock);
|
2006-11-15 05:37:25 +08:00
|
|
|
|
tree-wide: fix assorted typos all over the place
That is "success", "unknown", "through", "performance", "[re|un]mapping"
, "access", "default", "reasonable", "[con]currently", "temperature"
, "channel", "[un]used", "application", "example","hierarchy", "therefore"
, "[over|under]flow", "contiguous", "threshold", "enough" and others.
Signed-off-by: André Goddard Rosa <andre.goddard@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2009-11-14 23:09:05 +08:00
|
|
|
/* Returns failure iff a successful lock operation should be canceled */
|
2008-03-15 04:09:15 +08:00
|
|
|
static int dlm_plock_callback(struct plock_op *op)
|
2006-11-15 05:37:25 +08:00
|
|
|
{
|
2022-04-05 04:06:32 +08:00
|
|
|
struct plock_async_data *op_data = op->data;
|
2006-11-15 05:37:25 +08:00
|
|
|
struct file *file;
|
|
|
|
struct file_lock *fl;
|
|
|
|
struct file_lock *flc;
|
2014-08-22 22:18:42 +08:00
|
|
|
int (*notify)(struct file_lock *fl, int result) = NULL;
|
2006-11-15 05:37:25 +08:00
|
|
|
int rv = 0;
|
|
|
|
|
2022-04-05 04:06:31 +08:00
|
|
|
WARN_ON(!list_empty(&op->list));
|
2006-11-15 05:37:25 +08:00
|
|
|
|
|
|
|
/* check if the following 2 are still valid or make a copy */
|
2022-04-05 04:06:32 +08:00
|
|
|
file = op_data->file;
|
|
|
|
flc = &op_data->flc;
|
|
|
|
fl = op_data->fl;
|
|
|
|
notify = op_data->callback;
|
2006-11-15 05:37:25 +08:00
|
|
|
|
|
|
|
if (op->info.rv) {
|
2014-08-22 22:18:42 +08:00
|
|
|
notify(fl, op->info.rv);
|
2006-11-15 05:37:25 +08:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* got fs lock; bookkeep locally as well: */
|
|
|
|
flc->fl_flags &= ~FL_SLEEP;
|
|
|
|
if (posix_lock_file(file, flc, NULL)) {
|
|
|
|
/*
|
|
|
|
* This can only happen in the case of kmalloc() failure.
|
|
|
|
* The filesystem's own lock is the authoritative lock,
|
|
|
|
* so a failure to get the lock locally is not a disaster.
|
2008-03-15 04:09:15 +08:00
|
|
|
* As long as the fs cannot reliably cancel locks (especially
|
2006-11-15 05:37:25 +08:00
|
|
|
* in a low-memory situation), we're better off ignoring
|
|
|
|
* this failure than trying to recover.
|
|
|
|
*/
|
2008-03-15 04:09:15 +08:00
|
|
|
log_print("dlm_plock_callback: vfs lock error %llx file %p fl %p",
|
|
|
|
(unsigned long long)op->info.number, file, fl);
|
2006-11-15 05:37:25 +08:00
|
|
|
}
|
|
|
|
|
2014-08-22 22:18:42 +08:00
|
|
|
rv = notify(fl, 0);
|
2006-11-15 05:37:25 +08:00
|
|
|
if (rv) {
|
|
|
|
/* XXX: We need to cancel the fs lock here: */
|
2008-03-15 04:09:15 +08:00
|
|
|
log_print("dlm_plock_callback: lock granted after lock request "
|
|
|
|
"failed; dangling lock!\n");
|
2006-11-15 05:37:25 +08:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
out:
|
2022-04-05 04:06:32 +08:00
|
|
|
dlm_release_plock_op(op);
|
2006-01-17 16:47:12 +08:00
|
|
|
return rv;
|
|
|
|
}
|
|
|
|
|
2008-03-15 04:09:15 +08:00
|
|
|
int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
|
|
|
|
struct file_lock *fl)
|
2006-01-17 16:47:12 +08:00
|
|
|
{
|
2008-03-15 04:09:15 +08:00
|
|
|
struct dlm_ls *ls;
|
2006-01-17 16:47:12 +08:00
|
|
|
struct plock_op *op;
|
|
|
|
int rv;
|
2013-04-05 17:57:15 +08:00
|
|
|
unsigned char fl_flags = fl->fl_flags;
|
2006-01-17 16:47:12 +08:00
|
|
|
|
2008-03-15 04:09:15 +08:00
|
|
|
ls = dlm_find_lockspace_local(lockspace);
|
|
|
|
if (!ls)
|
|
|
|
return -EINVAL;
|
|
|
|
|
2009-12-01 06:34:43 +08:00
|
|
|
op = kzalloc(sizeof(*op), GFP_NOFS);
|
2008-03-15 04:09:15 +08:00
|
|
|
if (!op) {
|
|
|
|
rv = -ENOMEM;
|
|
|
|
goto out;
|
|
|
|
}
|
2006-01-17 16:47:12 +08:00
|
|
|
|
2013-04-05 17:57:15 +08:00
|
|
|
/* cause the vfs unlock to return ENOENT if lock is not found */
|
|
|
|
fl->fl_flags |= FL_EXISTS;
|
|
|
|
|
2015-10-23 01:38:14 +08:00
|
|
|
rv = locks_lock_file_wait(file, fl);
|
2013-04-05 17:57:15 +08:00
|
|
|
if (rv == -ENOENT) {
|
|
|
|
rv = 0;
|
|
|
|
goto out_free;
|
|
|
|
}
|
|
|
|
if (rv < 0) {
|
|
|
|
log_error(ls, "dlm_posix_unlock: vfs unlock error %d %llx",
|
|
|
|
rv, (unsigned long long)number);
|
|
|
|
}
|
2006-01-17 16:47:12 +08:00
|
|
|
|
2008-03-15 04:09:15 +08:00
|
|
|
op->info.optype = DLM_PLOCK_OP_UNLOCK;
|
2006-04-26 03:45:51 +08:00
|
|
|
op->info.pid = fl->fl_pid;
|
2008-03-15 04:09:15 +08:00
|
|
|
op->info.fsid = ls->ls_global_id;
|
|
|
|
op->info.number = number;
|
2006-01-17 16:47:12 +08:00
|
|
|
op->info.start = fl->fl_start;
|
|
|
|
op->info.end = fl->fl_end;
|
2011-07-21 08:21:59 +08:00
|
|
|
if (fl->fl_lmops && fl->fl_lmops->lm_grant)
|
2007-12-06 23:35:25 +08:00
|
|
|
op->info.owner = (__u64) fl->fl_pid;
|
|
|
|
else
|
|
|
|
op->info.owner = (__u64)(long) fl->fl_owner;
|
2006-01-17 16:47:12 +08:00
|
|
|
|
2011-03-03 04:20:04 +08:00
|
|
|
if (fl->fl_flags & FL_CLOSE) {
|
|
|
|
op->info.flags |= DLM_PLOCK_FL_CLOSE;
|
|
|
|
send_op(op);
|
|
|
|
rv = 0;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2006-01-17 16:47:12 +08:00
|
|
|
send_op(op);
|
|
|
|
wait_event(recv_wq, (op->done != 0));
|
|
|
|
|
2022-04-05 04:06:31 +08:00
|
|
|
WARN_ON(!list_empty(&op->list));
|
2006-01-17 16:47:12 +08:00
|
|
|
|
|
|
|
rv = op->info.rv;
|
|
|
|
|
2006-11-15 05:37:25 +08:00
|
|
|
if (rv == -ENOENT)
|
|
|
|
rv = 0;
|
|
|
|
|
2013-04-05 17:57:15 +08:00
|
|
|
out_free:
|
2022-04-05 04:06:32 +08:00
|
|
|
dlm_release_plock_op(op);
|
2008-03-15 04:09:15 +08:00
|
|
|
out:
|
|
|
|
dlm_put_lockspace(ls);
|
2013-04-05 17:57:15 +08:00
|
|
|
fl->fl_flags = fl_flags;
|
2006-01-17 16:47:12 +08:00
|
|
|
return rv;
|
|
|
|
}
|
2008-03-15 04:09:15 +08:00
|
|
|
EXPORT_SYMBOL_GPL(dlm_posix_unlock);
|
2006-01-17 16:47:12 +08:00
|
|
|
|
2008-03-15 04:09:15 +08:00
|
|
|
int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file,
|
|
|
|
struct file_lock *fl)
|
2006-01-17 16:47:12 +08:00
|
|
|
{
|
2008-03-15 04:09:15 +08:00
|
|
|
struct dlm_ls *ls;
|
2006-01-17 16:47:12 +08:00
|
|
|
struct plock_op *op;
|
|
|
|
int rv;
|
|
|
|
|
2008-03-15 04:09:15 +08:00
|
|
|
ls = dlm_find_lockspace_local(lockspace);
|
|
|
|
if (!ls)
|
|
|
|
return -EINVAL;
|
|
|
|
|
2009-12-01 06:34:43 +08:00
|
|
|
op = kzalloc(sizeof(*op), GFP_NOFS);
|
2008-03-15 04:09:15 +08:00
|
|
|
if (!op) {
|
|
|
|
rv = -ENOMEM;
|
|
|
|
goto out;
|
|
|
|
}
|
2006-01-17 16:47:12 +08:00
|
|
|
|
2008-03-15 04:09:15 +08:00
|
|
|
op->info.optype = DLM_PLOCK_OP_GET;
|
2006-04-26 03:45:51 +08:00
|
|
|
op->info.pid = fl->fl_pid;
|
2006-01-17 16:47:12 +08:00
|
|
|
op->info.ex = (fl->fl_type == F_WRLCK);
|
2008-03-15 04:09:15 +08:00
|
|
|
op->info.fsid = ls->ls_global_id;
|
|
|
|
op->info.number = number;
|
2006-01-17 16:47:12 +08:00
|
|
|
op->info.start = fl->fl_start;
|
|
|
|
op->info.end = fl->fl_end;
|
2011-07-21 08:21:59 +08:00
|
|
|
if (fl->fl_lmops && fl->fl_lmops->lm_grant)
|
2007-12-06 23:35:25 +08:00
|
|
|
op->info.owner = (__u64) fl->fl_pid;
|
|
|
|
else
|
|
|
|
op->info.owner = (__u64)(long) fl->fl_owner;
|
2006-11-15 05:37:25 +08:00
|
|
|
|
2006-01-17 16:47:12 +08:00
|
|
|
send_op(op);
|
|
|
|
wait_event(recv_wq, (op->done != 0));
|
|
|
|
|
2022-04-05 04:06:31 +08:00
|
|
|
WARN_ON(!list_empty(&op->list));
|
2006-01-17 16:47:12 +08:00
|
|
|
|
2007-06-09 06:01:40 +08:00
|
|
|
/* info.rv from userspace is 1 for conflict, 0 for no-conflict,
|
|
|
|
-ENOENT if there are no locks on the file */
|
|
|
|
|
2006-01-17 16:47:12 +08:00
|
|
|
rv = op->info.rv;
|
|
|
|
|
2006-11-15 05:37:25 +08:00
|
|
|
fl->fl_type = F_UNLCK;
|
|
|
|
if (rv == -ENOENT)
|
|
|
|
rv = 0;
|
2007-06-09 06:01:40 +08:00
|
|
|
else if (rv > 0) {
|
2009-01-22 00:34:50 +08:00
|
|
|
locks_init_lock(fl);
|
2006-01-17 16:47:12 +08:00
|
|
|
fl->fl_type = (op->info.ex) ? F_WRLCK : F_RDLCK;
|
2009-01-22 00:34:50 +08:00
|
|
|
fl->fl_flags = FL_POSIX;
|
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 22:28:22 +08:00
|
|
|
fl->fl_pid = -op->info.pid;
|
2006-01-17 16:47:12 +08:00
|
|
|
fl->fl_start = op->info.start;
|
|
|
|
fl->fl_end = op->info.end;
|
2007-06-09 06:01:40 +08:00
|
|
|
rv = 0;
|
2006-01-17 16:47:12 +08:00
|
|
|
}
|
|
|
|
|
2022-04-05 04:06:32 +08:00
|
|
|
dlm_release_plock_op(op);
|
2008-03-15 04:09:15 +08:00
|
|
|
out:
|
|
|
|
dlm_put_lockspace(ls);
|
2006-01-17 16:47:12 +08:00
|
|
|
return rv;
|
|
|
|
}
|
2008-03-15 04:09:15 +08:00
|
|
|
EXPORT_SYMBOL_GPL(dlm_posix_get);
|
2006-01-17 16:47:12 +08:00
|
|
|
|
|
|
|
/* a read copies out one plock request from the send list */
|
|
|
|
static ssize_t dev_read(struct file *file, char __user *u, size_t count,
|
|
|
|
loff_t *ppos)
|
|
|
|
{
|
2008-03-15 04:09:15 +08:00
|
|
|
struct dlm_plock_info info;
|
2006-01-17 16:47:12 +08:00
|
|
|
struct plock_op *op = NULL;
|
|
|
|
|
|
|
|
if (count < sizeof(info))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
spin_lock(&ops_lock);
|
|
|
|
if (!list_empty(&send_list)) {
|
2022-06-23 02:45:04 +08:00
|
|
|
op = list_first_entry(&send_list, struct plock_op, list);
|
2011-03-03 04:20:04 +08:00
|
|
|
if (op->info.flags & DLM_PLOCK_FL_CLOSE)
|
|
|
|
list_del(&op->list);
|
|
|
|
else
|
|
|
|
list_move(&op->list, &recv_list);
|
2006-01-17 16:47:12 +08:00
|
|
|
memcpy(&info, &op->info, sizeof(info));
|
|
|
|
}
|
|
|
|
spin_unlock(&ops_lock);
|
|
|
|
|
|
|
|
if (!op)
|
|
|
|
return -EAGAIN;
|
|
|
|
|
2011-03-03 04:20:04 +08:00
|
|
|
/* there is no need to get a reply from userspace for unlocks
|
|
|
|
that were generated by the vfs cleaning up for a close
|
|
|
|
(the process did not make an unlock call). */
|
|
|
|
|
|
|
|
if (op->info.flags & DLM_PLOCK_FL_CLOSE)
|
2022-04-05 04:06:32 +08:00
|
|
|
dlm_release_plock_op(op);
|
2011-03-03 04:20:04 +08:00
|
|
|
|
2006-01-17 16:47:12 +08:00
|
|
|
if (copy_to_user(u, &info, sizeof(info)))
|
|
|
|
return -EFAULT;
|
|
|
|
return sizeof(info);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* a write copies in one plock result that should match a plock_op
|
|
|
|
on the recv list */
|
|
|
|
static ssize_t dev_write(struct file *file, const char __user *u, size_t count,
|
|
|
|
loff_t *ppos)
|
|
|
|
{
|
2022-04-07 02:05:31 +08:00
|
|
|
struct plock_op *op = NULL, *iter;
|
2008-03-15 04:09:15 +08:00
|
|
|
struct dlm_plock_info info;
|
2022-04-07 02:05:31 +08:00
|
|
|
int do_callback = 0;
|
2006-01-17 16:47:12 +08:00
|
|
|
|
|
|
|
if (count != sizeof(info))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (copy_from_user(&info, u, sizeof(info)))
|
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
if (check_version(&info))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
spin_lock(&ops_lock);
|
2022-04-07 02:05:31 +08:00
|
|
|
list_for_each_entry(iter, &recv_list, list) {
|
|
|
|
if (iter->info.fsid == info.fsid &&
|
|
|
|
iter->info.number == info.number &&
|
|
|
|
iter->info.owner == info.owner) {
|
2022-06-23 02:45:09 +08:00
|
|
|
if (iter->sigint) {
|
|
|
|
list_del(&iter->list);
|
|
|
|
spin_unlock(&ops_lock);
|
|
|
|
|
|
|
|
pr_debug("%s: sigint cleanup %x %llx pid %d",
|
|
|
|
__func__, iter->info.fsid,
|
|
|
|
(unsigned long long)iter->info.number,
|
|
|
|
iter->info.pid);
|
|
|
|
do_unlock_close(&iter->info);
|
|
|
|
memcpy(&iter->info, &info, sizeof(info));
|
|
|
|
dlm_release_plock_op(iter);
|
|
|
|
return count;
|
|
|
|
}
|
2022-04-07 02:05:31 +08:00
|
|
|
list_del_init(&iter->list);
|
|
|
|
memcpy(&iter->info, &info, sizeof(info));
|
|
|
|
if (iter->data)
|
2009-06-19 02:20:24 +08:00
|
|
|
do_callback = 1;
|
|
|
|
else
|
2022-04-07 02:05:31 +08:00
|
|
|
iter->done = 1;
|
|
|
|
op = iter;
|
2006-01-17 16:47:12 +08:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
spin_unlock(&ops_lock);
|
|
|
|
|
2022-04-07 02:05:31 +08:00
|
|
|
if (op) {
|
2009-06-19 02:20:24 +08:00
|
|
|
if (do_callback)
|
2008-05-14 03:28:26 +08:00
|
|
|
dlm_plock_callback(op);
|
2006-11-15 05:37:25 +08:00
|
|
|
else
|
|
|
|
wake_up(&recv_wq);
|
|
|
|
} else
|
2022-06-23 02:45:05 +08:00
|
|
|
log_print("%s: no op %x %llx", __func__,
|
2022-04-05 04:06:34 +08:00
|
|
|
info.fsid, (unsigned long long)info.number);
|
2006-01-17 16:47:12 +08:00
|
|
|
return count;
|
|
|
|
}
|
|
|
|
|
2017-07-03 13:02:18 +08:00
|
|
|
static __poll_t dev_poll(struct file *file, poll_table *wait)
|
2006-01-17 16:47:12 +08:00
|
|
|
{
|
2017-07-03 13:02:18 +08:00
|
|
|
__poll_t mask = 0;
|
2007-07-25 17:53:58 +08:00
|
|
|
|
2006-01-17 16:47:12 +08:00
|
|
|
poll_wait(file, &send_wq, wait);
|
|
|
|
|
|
|
|
spin_lock(&ops_lock);
|
2007-07-25 17:53:58 +08:00
|
|
|
if (!list_empty(&send_list))
|
2018-02-12 06:34:03 +08:00
|
|
|
mask = EPOLLIN | EPOLLRDNORM;
|
2006-01-17 16:47:12 +08:00
|
|
|
spin_unlock(&ops_lock);
|
2007-07-25 17:53:58 +08:00
|
|
|
|
|
|
|
return mask;
|
2006-01-17 16:47:12 +08:00
|
|
|
}
|
|
|
|
|
2007-02-12 16:55:34 +08:00
|
|
|
static const struct file_operations dev_fops = {
|
2006-01-17 16:47:12 +08:00
|
|
|
.read = dev_read,
|
|
|
|
.write = dev_write,
|
|
|
|
.poll = dev_poll,
|
llseek: automatically add .llseek fop
All file_operations should get a .llseek operation so we can make
nonseekable_open the default for future file operations without a
.llseek pointer.
The three cases that we can automatically detect are no_llseek, seq_lseek
and default_llseek. For cases where we can we can automatically prove that
the file offset is always ignored, we use noop_llseek, which maintains
the current behavior of not returning an error from a seek.
New drivers should normally not use noop_llseek but instead use no_llseek
and call nonseekable_open at open time. Existing drivers can be converted
to do the same when the maintainer knows for certain that no user code
relies on calling seek on the device file.
The generated code is often incorrectly indented and right now contains
comments that clarify for each added line why a specific variant was
chosen. In the version that gets submitted upstream, the comments will
be gone and I will manually fix the indentation, because there does not
seem to be a way to do that using coccinelle.
Some amount of new code is currently sitting in linux-next that should get
the same modifications, which I will do at the end of the merge window.
Many thanks to Julia Lawall for helping me learn to write a semantic
patch that does all this.
===== begin semantic patch =====
// This adds an llseek= method to all file operations,
// as a preparation for making no_llseek the default.
//
// The rules are
// - use no_llseek explicitly if we do nonseekable_open
// - use seq_lseek for sequential files
// - use default_llseek if we know we access f_pos
// - use noop_llseek if we know we don't access f_pos,
// but we still want to allow users to call lseek
//
@ open1 exists @
identifier nested_open;
@@
nested_open(...)
{
<+...
nonseekable_open(...)
...+>
}
@ open exists@
identifier open_f;
identifier i, f;
identifier open1.nested_open;
@@
int open_f(struct inode *i, struct file *f)
{
<+...
(
nonseekable_open(...)
|
nested_open(...)
)
...+>
}
@ read disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ read_no_fpos disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
... when != off
}
@ write @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ write_no_fpos @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
... when != off
}
@ fops0 @
identifier fops;
@@
struct file_operations fops = {
...
};
@ has_llseek depends on fops0 @
identifier fops0.fops;
identifier llseek_f;
@@
struct file_operations fops = {
...
.llseek = llseek_f,
...
};
@ has_read depends on fops0 @
identifier fops0.fops;
identifier read_f;
@@
struct file_operations fops = {
...
.read = read_f,
...
};
@ has_write depends on fops0 @
identifier fops0.fops;
identifier write_f;
@@
struct file_operations fops = {
...
.write = write_f,
...
};
@ has_open depends on fops0 @
identifier fops0.fops;
identifier open_f;
@@
struct file_operations fops = {
...
.open = open_f,
...
};
// use no_llseek if we call nonseekable_open
////////////////////////////////////////////
@ nonseekable1 depends on !has_llseek && has_open @
identifier fops0.fops;
identifier nso ~= "nonseekable_open";
@@
struct file_operations fops = {
... .open = nso, ...
+.llseek = no_llseek, /* nonseekable */
};
@ nonseekable2 depends on !has_llseek @
identifier fops0.fops;
identifier open.open_f;
@@
struct file_operations fops = {
... .open = open_f, ...
+.llseek = no_llseek, /* open uses nonseekable */
};
// use seq_lseek for sequential files
/////////////////////////////////////
@ seq depends on !has_llseek @
identifier fops0.fops;
identifier sr ~= "seq_read";
@@
struct file_operations fops = {
... .read = sr, ...
+.llseek = seq_lseek, /* we have seq_read */
};
// use default_llseek if there is a readdir
///////////////////////////////////////////
@ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier readdir_e;
@@
// any other fop is used that changes pos
struct file_operations fops = {
... .readdir = readdir_e, ...
+.llseek = default_llseek, /* readdir is present */
};
// use default_llseek if at least one of read/write touches f_pos
/////////////////////////////////////////////////////////////////
@ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read.read_f;
@@
// read fops use offset
struct file_operations fops = {
... .read = read_f, ...
+.llseek = default_llseek, /* read accesses f_pos */
};
@ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write.write_f;
@@
// write fops use offset
struct file_operations fops = {
... .write = write_f, ...
+ .llseek = default_llseek, /* write accesses f_pos */
};
// Use noop_llseek if neither read nor write accesses f_pos
///////////////////////////////////////////////////////////
@ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
identifier write_no_fpos.write_f;
@@
// write fops use offset
struct file_operations fops = {
...
.write = write_f,
.read = read_f,
...
+.llseek = noop_llseek, /* read and write both use no f_pos */
};
@ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write_no_fpos.write_f;
@@
struct file_operations fops = {
... .write = write_f, ...
+.llseek = noop_llseek, /* write uses no f_pos */
};
@ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
@@
struct file_operations fops = {
... .read = read_f, ...
+.llseek = noop_llseek, /* read uses no f_pos */
};
@ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
@@
struct file_operations fops = {
...
+.llseek = noop_llseek, /* no read or write fn */
};
===== End semantic patch =====
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Julia Lawall <julia@diku.dk>
Cc: Christoph Hellwig <hch@infradead.org>
2010-08-16 00:52:59 +08:00
|
|
|
.owner = THIS_MODULE,
|
|
|
|
.llseek = noop_llseek,
|
2006-01-17 16:47:12 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
static struct miscdevice plock_dev_misc = {
|
|
|
|
.minor = MISC_DYNAMIC_MINOR,
|
2008-03-15 04:09:15 +08:00
|
|
|
.name = DLM_PLOCK_MISC_NAME,
|
2006-01-17 16:47:12 +08:00
|
|
|
.fops = &dev_fops
|
|
|
|
};
|
|
|
|
|
2008-03-15 04:09:15 +08:00
|
|
|
int dlm_plock_init(void)
|
2006-01-17 16:47:12 +08:00
|
|
|
{
|
|
|
|
int rv;
|
|
|
|
|
|
|
|
rv = misc_register(&plock_dev_misc);
|
|
|
|
if (rv)
|
2008-03-15 04:09:15 +08:00
|
|
|
log_print("dlm_plock_init: misc_register failed %d", rv);
|
2006-01-17 16:47:12 +08:00
|
|
|
return rv;
|
|
|
|
}
|
|
|
|
|
2008-03-15 04:09:15 +08:00
|
|
|
void dlm_plock_exit(void)
|
2006-01-17 16:47:12 +08:00
|
|
|
{
|
2015-07-31 06:59:57 +08:00
|
|
|
misc_deregister(&plock_dev_misc);
|
2006-01-17 16:47:12 +08:00
|
|
|
}
|
|
|
|
|