9d5b86ac13
Since commit c69899a17c "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>
405 lines
10 KiB
C
405 lines
10 KiB
C
#include <linux/ceph/ceph_debug.h>
|
|
|
|
#include <linux/file.h>
|
|
#include <linux/namei.h>
|
|
#include <linux/random.h>
|
|
|
|
#include "super.h"
|
|
#include "mds_client.h"
|
|
#include <linux/ceph/pagelist.h>
|
|
|
|
static u64 lock_secret;
|
|
static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc,
|
|
struct ceph_mds_request *req);
|
|
|
|
static inline u64 secure_addr(void *addr)
|
|
{
|
|
u64 v = lock_secret ^ (u64)(unsigned long)addr;
|
|
/*
|
|
* Set the most significant bit, so that MDS knows the 'owner'
|
|
* is sufficient to identify the owner of lock. (old code uses
|
|
* both 'owner' and 'pid')
|
|
*/
|
|
v |= (1ULL << 63);
|
|
return v;
|
|
}
|
|
|
|
void __init ceph_flock_init(void)
|
|
{
|
|
get_random_bytes(&lock_secret, sizeof(lock_secret));
|
|
}
|
|
|
|
/**
|
|
* Implement fcntl and flock locking functions.
|
|
*/
|
|
static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
|
|
int cmd, u8 wait, struct file_lock *fl)
|
|
{
|
|
struct inode *inode = file_inode(file);
|
|
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
|
|
struct ceph_mds_request *req;
|
|
int err;
|
|
u64 length = 0;
|
|
u64 owner;
|
|
|
|
if (operation != CEPH_MDS_OP_SETFILELOCK || cmd == CEPH_LOCK_UNLOCK)
|
|
wait = 0;
|
|
|
|
req = ceph_mdsc_create_request(mdsc, operation, USE_AUTH_MDS);
|
|
if (IS_ERR(req))
|
|
return PTR_ERR(req);
|
|
req->r_inode = inode;
|
|
ihold(inode);
|
|
req->r_num_caps = 1;
|
|
|
|
/* mds requires start and length rather than start and end */
|
|
if (LLONG_MAX == fl->fl_end)
|
|
length = 0;
|
|
else
|
|
length = fl->fl_end - fl->fl_start + 1;
|
|
|
|
owner = secure_addr(fl->fl_owner);
|
|
|
|
dout("ceph_lock_message: rule: %d, op: %d, owner: %llx, pid: %llu, "
|
|
"start: %llu, length: %llu, wait: %d, type: %d", (int)lock_type,
|
|
(int)operation, owner, (u64)fl->fl_pid, fl->fl_start, length,
|
|
wait, fl->fl_type);
|
|
|
|
req->r_args.filelock_change.rule = lock_type;
|
|
req->r_args.filelock_change.type = cmd;
|
|
req->r_args.filelock_change.owner = cpu_to_le64(owner);
|
|
req->r_args.filelock_change.pid = cpu_to_le64((u64)fl->fl_pid);
|
|
req->r_args.filelock_change.start = cpu_to_le64(fl->fl_start);
|
|
req->r_args.filelock_change.length = cpu_to_le64(length);
|
|
req->r_args.filelock_change.wait = wait;
|
|
|
|
if (wait)
|
|
req->r_wait_for_completion = ceph_lock_wait_for_completion;
|
|
|
|
err = ceph_mdsc_do_request(mdsc, inode, req);
|
|
|
|
if (operation == CEPH_MDS_OP_GETFILELOCK) {
|
|
fl->fl_pid = -le64_to_cpu(req->r_reply_info.filelock_reply->pid);
|
|
if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type)
|
|
fl->fl_type = F_RDLCK;
|
|
else if (CEPH_LOCK_EXCL == req->r_reply_info.filelock_reply->type)
|
|
fl->fl_type = F_WRLCK;
|
|
else
|
|
fl->fl_type = F_UNLCK;
|
|
|
|
fl->fl_start = le64_to_cpu(req->r_reply_info.filelock_reply->start);
|
|
length = le64_to_cpu(req->r_reply_info.filelock_reply->start) +
|
|
le64_to_cpu(req->r_reply_info.filelock_reply->length);
|
|
if (length >= 1)
|
|
fl->fl_end = length -1;
|
|
else
|
|
fl->fl_end = 0;
|
|
|
|
}
|
|
ceph_mdsc_put_request(req);
|
|
dout("ceph_lock_message: rule: %d, op: %d, pid: %llu, start: %llu, "
|
|
"length: %llu, wait: %d, type: %d, err code %d", (int)lock_type,
|
|
(int)operation, (u64)fl->fl_pid, fl->fl_start,
|
|
length, wait, fl->fl_type, err);
|
|
return err;
|
|
}
|
|
|
|
static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc,
|
|
struct ceph_mds_request *req)
|
|
{
|
|
struct ceph_mds_request *intr_req;
|
|
struct inode *inode = req->r_inode;
|
|
int err, lock_type;
|
|
|
|
BUG_ON(req->r_op != CEPH_MDS_OP_SETFILELOCK);
|
|
if (req->r_args.filelock_change.rule == CEPH_LOCK_FCNTL)
|
|
lock_type = CEPH_LOCK_FCNTL_INTR;
|
|
else if (req->r_args.filelock_change.rule == CEPH_LOCK_FLOCK)
|
|
lock_type = CEPH_LOCK_FLOCK_INTR;
|
|
else
|
|
BUG_ON(1);
|
|
BUG_ON(req->r_args.filelock_change.type == CEPH_LOCK_UNLOCK);
|
|
|
|
err = wait_for_completion_interruptible(&req->r_completion);
|
|
if (!err)
|
|
return 0;
|
|
|
|
dout("ceph_lock_wait_for_completion: request %llu was interrupted\n",
|
|
req->r_tid);
|
|
|
|
mutex_lock(&mdsc->mutex);
|
|
if (test_bit(CEPH_MDS_R_GOT_RESULT, &req->r_req_flags)) {
|
|
err = 0;
|
|
} else {
|
|
/*
|
|
* ensure we aren't running concurrently with
|
|
* ceph_fill_trace or ceph_readdir_prepopulate, which
|
|
* rely on locks (dir mutex) held by our caller.
|
|
*/
|
|
mutex_lock(&req->r_fill_mutex);
|
|
req->r_err = err;
|
|
set_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags);
|
|
mutex_unlock(&req->r_fill_mutex);
|
|
|
|
if (!req->r_session) {
|
|
// haven't sent the request
|
|
err = 0;
|
|
}
|
|
}
|
|
mutex_unlock(&mdsc->mutex);
|
|
if (!err)
|
|
return 0;
|
|
|
|
intr_req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETFILELOCK,
|
|
USE_AUTH_MDS);
|
|
if (IS_ERR(intr_req))
|
|
return PTR_ERR(intr_req);
|
|
|
|
intr_req->r_inode = inode;
|
|
ihold(inode);
|
|
intr_req->r_num_caps = 1;
|
|
|
|
intr_req->r_args.filelock_change = req->r_args.filelock_change;
|
|
intr_req->r_args.filelock_change.rule = lock_type;
|
|
intr_req->r_args.filelock_change.type = CEPH_LOCK_UNLOCK;
|
|
|
|
err = ceph_mdsc_do_request(mdsc, inode, intr_req);
|
|
ceph_mdsc_put_request(intr_req);
|
|
|
|
if (err && err != -ERESTARTSYS)
|
|
return err;
|
|
|
|
wait_for_completion_killable(&req->r_safe_completion);
|
|
return 0;
|
|
}
|
|
|
|
/**
|
|
* Attempt to set an fcntl lock.
|
|
* For now, this just goes away to the server. Later it may be more awesome.
|
|
*/
|
|
int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
|
|
{
|
|
u8 lock_cmd;
|
|
int err;
|
|
u8 wait = 0;
|
|
u16 op = CEPH_MDS_OP_SETFILELOCK;
|
|
|
|
if (!(fl->fl_flags & FL_POSIX))
|
|
return -ENOLCK;
|
|
/* No mandatory locks */
|
|
if (__mandatory_lock(file->f_mapping->host) && fl->fl_type != F_UNLCK)
|
|
return -ENOLCK;
|
|
|
|
dout("ceph_lock, fl_owner: %p", fl->fl_owner);
|
|
|
|
/* set wait bit as appropriate, then make command as Ceph expects it*/
|
|
if (IS_GETLK(cmd))
|
|
op = CEPH_MDS_OP_GETFILELOCK;
|
|
else if (IS_SETLKW(cmd))
|
|
wait = 1;
|
|
|
|
if (F_RDLCK == fl->fl_type)
|
|
lock_cmd = CEPH_LOCK_SHARED;
|
|
else if (F_WRLCK == fl->fl_type)
|
|
lock_cmd = CEPH_LOCK_EXCL;
|
|
else
|
|
lock_cmd = CEPH_LOCK_UNLOCK;
|
|
|
|
err = ceph_lock_message(CEPH_LOCK_FCNTL, op, file, lock_cmd, wait, fl);
|
|
if (!err) {
|
|
if (op != CEPH_MDS_OP_GETFILELOCK) {
|
|
dout("mds locked, locking locally");
|
|
err = posix_lock_file(file, fl, NULL);
|
|
if (err && (CEPH_MDS_OP_SETFILELOCK == op)) {
|
|
/* undo! This should only happen if
|
|
* the kernel detects local
|
|
* deadlock. */
|
|
ceph_lock_message(CEPH_LOCK_FCNTL, op, file,
|
|
CEPH_LOCK_UNLOCK, 0, fl);
|
|
dout("got %d on posix_lock_file, undid lock",
|
|
err);
|
|
}
|
|
}
|
|
}
|
|
return err;
|
|
}
|
|
|
|
int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
|
|
{
|
|
u8 lock_cmd;
|
|
int err;
|
|
u8 wait = 0;
|
|
|
|
if (!(fl->fl_flags & FL_FLOCK))
|
|
return -ENOLCK;
|
|
/* No mandatory locks */
|
|
if (fl->fl_type & LOCK_MAND)
|
|
return -EOPNOTSUPP;
|
|
|
|
dout("ceph_flock, fl_file: %p", fl->fl_file);
|
|
|
|
if (IS_SETLKW(cmd))
|
|
wait = 1;
|
|
|
|
if (F_RDLCK == fl->fl_type)
|
|
lock_cmd = CEPH_LOCK_SHARED;
|
|
else if (F_WRLCK == fl->fl_type)
|
|
lock_cmd = CEPH_LOCK_EXCL;
|
|
else
|
|
lock_cmd = CEPH_LOCK_UNLOCK;
|
|
|
|
err = ceph_lock_message(CEPH_LOCK_FLOCK, CEPH_MDS_OP_SETFILELOCK,
|
|
file, lock_cmd, wait, fl);
|
|
if (!err) {
|
|
err = locks_lock_file_wait(file, fl);
|
|
if (err) {
|
|
ceph_lock_message(CEPH_LOCK_FLOCK,
|
|
CEPH_MDS_OP_SETFILELOCK,
|
|
file, CEPH_LOCK_UNLOCK, 0, fl);
|
|
dout("got %d on locks_lock_file_wait, undid lock", err);
|
|
}
|
|
}
|
|
return err;
|
|
}
|
|
|
|
/*
|
|
* Fills in the passed counter variables, so you can prepare pagelist metadata
|
|
* before calling ceph_encode_locks.
|
|
*/
|
|
void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
|
|
{
|
|
struct file_lock *lock;
|
|
struct file_lock_context *ctx;
|
|
|
|
*fcntl_count = 0;
|
|
*flock_count = 0;
|
|
|
|
ctx = inode->i_flctx;
|
|
if (ctx) {
|
|
spin_lock(&ctx->flc_lock);
|
|
list_for_each_entry(lock, &ctx->flc_posix, fl_list)
|
|
++(*fcntl_count);
|
|
list_for_each_entry(lock, &ctx->flc_flock, fl_list)
|
|
++(*flock_count);
|
|
spin_unlock(&ctx->flc_lock);
|
|
}
|
|
dout("counted %d flock locks and %d fcntl locks",
|
|
*flock_count, *fcntl_count);
|
|
}
|
|
|
|
/**
|
|
* Encode the flock and fcntl locks for the given inode into the ceph_filelock
|
|
* array. Must be called with inode->i_lock already held.
|
|
* If we encounter more of a specific lock type than expected, return -ENOSPC.
|
|
*/
|
|
int ceph_encode_locks_to_buffer(struct inode *inode,
|
|
struct ceph_filelock *flocks,
|
|
int num_fcntl_locks, int num_flock_locks)
|
|
{
|
|
struct file_lock *lock;
|
|
struct file_lock_context *ctx = inode->i_flctx;
|
|
int err = 0;
|
|
int seen_fcntl = 0;
|
|
int seen_flock = 0;
|
|
int l = 0;
|
|
|
|
dout("encoding %d flock and %d fcntl locks", num_flock_locks,
|
|
num_fcntl_locks);
|
|
|
|
if (!ctx)
|
|
return 0;
|
|
|
|
spin_lock(&ctx->flc_lock);
|
|
list_for_each_entry(lock, &ctx->flc_posix, fl_list) {
|
|
++seen_fcntl;
|
|
if (seen_fcntl > num_fcntl_locks) {
|
|
err = -ENOSPC;
|
|
goto fail;
|
|
}
|
|
err = lock_to_ceph_filelock(lock, &flocks[l]);
|
|
if (err)
|
|
goto fail;
|
|
++l;
|
|
}
|
|
list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
|
|
++seen_flock;
|
|
if (seen_flock > num_flock_locks) {
|
|
err = -ENOSPC;
|
|
goto fail;
|
|
}
|
|
err = lock_to_ceph_filelock(lock, &flocks[l]);
|
|
if (err)
|
|
goto fail;
|
|
++l;
|
|
}
|
|
fail:
|
|
spin_unlock(&ctx->flc_lock);
|
|
return err;
|
|
}
|
|
|
|
/**
|
|
* Copy the encoded flock and fcntl locks into the pagelist.
|
|
* Format is: #fcntl locks, sequential fcntl locks, #flock locks,
|
|
* sequential flock locks.
|
|
* Returns zero on success.
|
|
*/
|
|
int ceph_locks_to_pagelist(struct ceph_filelock *flocks,
|
|
struct ceph_pagelist *pagelist,
|
|
int num_fcntl_locks, int num_flock_locks)
|
|
{
|
|
int err = 0;
|
|
__le32 nlocks;
|
|
|
|
nlocks = cpu_to_le32(num_fcntl_locks);
|
|
err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks));
|
|
if (err)
|
|
goto out_fail;
|
|
|
|
err = ceph_pagelist_append(pagelist, flocks,
|
|
num_fcntl_locks * sizeof(*flocks));
|
|
if (err)
|
|
goto out_fail;
|
|
|
|
nlocks = cpu_to_le32(num_flock_locks);
|
|
err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks));
|
|
if (err)
|
|
goto out_fail;
|
|
|
|
err = ceph_pagelist_append(pagelist,
|
|
&flocks[num_fcntl_locks],
|
|
num_flock_locks * sizeof(*flocks));
|
|
out_fail:
|
|
return err;
|
|
}
|
|
|
|
/*
|
|
* Given a pointer to a lock, convert it to a ceph filelock
|
|
*/
|
|
int lock_to_ceph_filelock(struct file_lock *lock,
|
|
struct ceph_filelock *cephlock)
|
|
{
|
|
int err = 0;
|
|
cephlock->start = cpu_to_le64(lock->fl_start);
|
|
cephlock->length = cpu_to_le64(lock->fl_end - lock->fl_start + 1);
|
|
cephlock->client = cpu_to_le64(0);
|
|
cephlock->pid = cpu_to_le64((u64)lock->fl_pid);
|
|
cephlock->owner = cpu_to_le64(secure_addr(lock->fl_owner));
|
|
|
|
switch (lock->fl_type) {
|
|
case F_RDLCK:
|
|
cephlock->type = CEPH_LOCK_SHARED;
|
|
break;
|
|
case F_WRLCK:
|
|
cephlock->type = CEPH_LOCK_EXCL;
|
|
break;
|
|
case F_UNLCK:
|
|
cephlock->type = CEPH_LOCK_UNLOCK;
|
|
break;
|
|
default:
|
|
dout("Have unknown lock type %d", lock->fl_type);
|
|
err = -EINVAL;
|
|
}
|
|
|
|
return err;
|
|
}
|