/*
* Decrement the user count and bring down lockd if we're the last.
*/
void
lockd_down(struct net *net)
{
mutex_lock(&nlmsvc_mutex);
lockd_down_net(nlmsvc_rqst->rq_server, net);
if (nlmsvc_users) {
if (--nlmsvc_users)
goto out;
} else {
printk(KERN_ERR "lockd_down: no users! task=%p\n",
nlmsvc_task);
BUG();
}
if (!nlmsvc_task) {
printk(KERN_ERR "lockd_down: no lockd running.\n");
BUG();
}
kthread_stop(nlmsvc_task);
dprintk("lockd_down: service stopped\n");
svc_exit_thread(nlmsvc_rqst);
dprintk("lockd_down: service destroyed\n");
nlmsvc_task = NULL;
nlmsvc_rqst = NULL;
out:
mutex_unlock(&nlmsvc_mutex);
}
/*
* Create a server thread
*/
int
svc_create_thread(svc_thread_fn func, struct svc_serv *serv)
{
struct svc_rqst *rqstp;
int error = -ENOMEM;
rqstp = kmalloc(sizeof(*rqstp), GFP_KERNEL);
if (!rqstp)
goto out;
memset(rqstp, 0, sizeof(*rqstp));
if (!(rqstp->rq_argp = (u32 *) kmalloc(serv->sv_xdrsize, GFP_KERNEL))
|| !(rqstp->rq_resp = (u32 *) kmalloc(serv->sv_xdrsize, GFP_KERNEL))
|| !svc_init_buffer(&rqstp->rq_defbuf, serv->sv_bufsz))
goto out_thread;
serv->sv_nrthreads++;
rqstp->rq_server = serv;
error = kernel_thread((int (*)(void *)) func, rqstp, 0);
if (error < 0)
goto out_thread;
error = 0;
out:
return error;
out_thread:
svc_exit_thread(rqstp);
goto out;
}
/*
* Decrement the user count and bring down lockd if we're the last.
*/
void
lockd_down(void)
{
mutex_lock(&nlmsvc_mutex);
if (nlmsvc_users) {
if (--nlmsvc_users) {
lockd_down_net(current->nsproxy->net_ns);
goto out;
}
} else {
printk(KERN_ERR "lockd_down: no users! task=%p\n",
nlmsvc_task);
BUG();
}
if (!nlmsvc_task) {
printk(KERN_ERR "lockd_down: no lockd running.\n");
BUG();
}
kthread_stop(nlmsvc_task);
svc_exit_thread(nlmsvc_rqst);
nlmsvc_task = NULL;
nlmsvc_rqst = NULL;
out:
mutex_unlock(&nlmsvc_mutex);
}
/*
* Create a server thread
*/
int
svc_create_thread(svc_thread_fn func, struct svc_serv *serv)
{
struct svc_rqst *rqstp;
int error = -ENOMEM;
rqstp = kzalloc(sizeof(*rqstp), GFP_KERNEL);
if (!rqstp)
goto out;
init_waitqueue_head(&rqstp->rq_wait);
if (!(rqstp->rq_argp = kmalloc(serv->sv_xdrsize, GFP_KERNEL))
|| !(rqstp->rq_resp = kmalloc(serv->sv_xdrsize, GFP_KERNEL))
|| !svc_init_buffer(rqstp, serv->sv_bufsz))
goto out_thread;
serv->sv_nrthreads++;
rqstp->rq_server = serv;
error = kernel_thread((int (*)(void *)) func, rqstp, 0);
if (error < 0)
goto out_thread;
svc_sock_update_bufs(serv);
error = 0;
out:
return error;
out_thread:
svc_exit_thread(rqstp);
goto out;
}
/*
* Bring up the callback thread if it is not already up.
*/
int nfs_callback_up(void)
{
struct svc_serv *serv = NULL;
int ret = 0;
mutex_lock(&nfs_callback_mutex);
if (nfs_callback_info.users++ || nfs_callback_info.task != NULL)
goto out;
serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE,
nfs_callback_family, NULL);
ret = -ENOMEM;
if (!serv)
goto out_err;
ret = svc_create_xprt(serv, "tcp", nfs_callback_set_tcpport,
SVC_SOCK_ANONYMOUS);
if (ret <= 0)
goto out_err;
nfs_callback_tcpport = ret;
dprintk("NFS: Callback listener port = %u (af %u)\n",
nfs_callback_tcpport, nfs_callback_family);
nfs_callback_info.rqst = svc_prepare_thread(serv, &serv->sv_pools[0]);
if (IS_ERR(nfs_callback_info.rqst)) {
ret = PTR_ERR(nfs_callback_info.rqst);
nfs_callback_info.rqst = NULL;
goto out_err;
}
svc_sock_update_bufs(serv);
nfs_callback_info.task = kthread_run(nfs_callback_svc,
nfs_callback_info.rqst,
"nfsv4-svc");
if (IS_ERR(nfs_callback_info.task)) {
ret = PTR_ERR(nfs_callback_info.task);
svc_exit_thread(nfs_callback_info.rqst);
nfs_callback_info.rqst = NULL;
nfs_callback_info.task = NULL;
goto out_err;
}
out:
/*
* svc_create creates the svc_serv with sv_nrthreads == 1, and then
* svc_prepare_thread increments that. So we need to call svc_destroy
* on both success and failure so that the refcount is 1 when the
* thread exits.
*/
if (serv)
svc_destroy(serv);
mutex_unlock(&nfs_callback_mutex);
return ret;
out_err:
dprintk("NFS: Couldn't create callback socket or server thread; "
"err = %d\n", ret);
nfs_callback_info.users--;
goto out;
}
/*
* Create or destroy enough new threads to make the number
* of threads the given number. If `pool' is non-NULL, applies
* only to threads in that pool, otherwise round-robins between
* all pools. Caller must ensure that mutual exclusion between this and
* server startup or shutdown.
*
* Destroying threads relies on the service threads filling in
* rqstp->rq_task, which only the nfs ones do. Assumes the serv
* has been created using svc_create_pooled().
*
* Based on code that used to be in nfsd_svc() but tweaked
* to be pool-aware.
*/
int
svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
{
struct svc_rqst *rqstp;
struct task_struct *task;
struct svc_pool *chosen_pool;
int error = 0;
unsigned int state = serv->sv_nrthreads-1;
int node;
if (pool == NULL) {
/* The -1 assumes caller has done a svc_get() */
nrservs -= (serv->sv_nrthreads-1);
} else {
spin_lock_bh(&pool->sp_lock);
nrservs -= pool->sp_nrthreads;
spin_unlock_bh(&pool->sp_lock);
}
/* create new threads */
while (nrservs > 0) {
nrservs--;
chosen_pool = choose_pool(serv, pool, &state);
node = svc_pool_map_get_node(chosen_pool->sp_id);
rqstp = svc_prepare_thread(serv, chosen_pool, node);
if (IS_ERR(rqstp)) {
error = PTR_ERR(rqstp);
break;
}
__module_get(serv->sv_ops->svo_module);
task = kthread_create_on_node(serv->sv_ops->svo_function, rqstp,
node, "%s", serv->sv_name);
if (IS_ERR(task)) {
error = PTR_ERR(task);
module_put(serv->sv_ops->svo_module);
svc_exit_thread(rqstp);
break;
}
rqstp->rq_task = task;
if (serv->sv_nrpools > 1)
svc_pool_map_set_cpumask(task, chosen_pool->sp_id);
svc_sock_update_bufs(serv);
wake_up_process(task);
}
/* destroy old threads */
while (nrservs < 0 &&
(task = choose_victim(serv, pool, &state)) != NULL) {
send_sig(SIGINT, task, 1);
nrservs++;
}
return error;
}
/*
* Kill the callback thread if it's no longer being used.
*/
void nfs_callback_down(void)
{
mutex_lock(&nfs_callback_mutex);
nfs_callback_info.users--;
if (nfs_callback_info.users == 0 && nfs_callback_info.task != NULL) {
kthread_stop(nfs_callback_info.task);
svc_exit_thread(nfs_callback_info.rqst);
nfs_callback_info.rqst = NULL;
nfs_callback_info.task = NULL;
}
mutex_unlock(&nfs_callback_mutex);
}
/*
* This is the callback kernel thread.
*/
static void nfs_callback_svc(struct svc_rqst *rqstp)
{
struct svc_serv *serv = rqstp->rq_server;
int err;
__module_get(THIS_MODULE);
lock_kernel();
nfs_callback_info.pid = current->pid;
daemonize("nfsv4-svc");
/* Process request with signals blocked, but allow SIGKILL. */
allow_signal(SIGKILL);
complete(&nfs_callback_info.started);
for(;;) {
if (signalled()) {
if (nfs_callback_info.users == 0)
break;
flush_signals(current);
}
/*
* Listen for a request on the socket
*/
err = svc_recv(serv, rqstp, MAX_SCHEDULE_TIMEOUT);
if (err == -EAGAIN || err == -EINTR)
continue;
if (err < 0) {
printk(KERN_WARNING
"%s: terminating on error %d\n",
__FUNCTION__, -err);
break;
}
dprintk("%s: request from %u.%u.%u.%u\n", __FUNCTION__,
NIPQUAD(rqstp->rq_addr.sin_addr.s_addr));
svc_process(serv, rqstp);
}
flush_signals(current);
svc_exit_thread(rqstp);
nfs_callback_info.pid = 0;
complete(&nfs_callback_info.stopped);
unlock_kernel();
module_put_and_exit(0);
}
static int lockd_start_svc(struct svc_serv *serv)
{
int error;
if (nlmsvc_rqst)
return 0;
/*
* Create the kernel thread and wait for it to start.
*/
nlmsvc_rqst = svc_prepare_thread(serv, &serv->sv_pools[0], NUMA_NO_NODE);
if (IS_ERR(nlmsvc_rqst)) {
error = PTR_ERR(nlmsvc_rqst);
printk(KERN_WARNING
"lockd_up: svc_rqst allocation failed, error=%d\n",
error);
goto out_rqst;
}
svc_sock_update_bufs(serv);
serv->sv_maxconn = nlm_max_connections;
nlmsvc_task = kthread_create(lockd, nlmsvc_rqst, "%s", serv->sv_name);
if (IS_ERR(nlmsvc_task)) {
error = PTR_ERR(nlmsvc_task);
printk(KERN_WARNING
"lockd_up: kthread_run failed, error=%d\n", error);
goto out_task;
}
nlmsvc_rqst->rq_task = nlmsvc_task;
wake_up_process(nlmsvc_task);
dprintk("lockd_up: service started\n");
return 0;
out_task:
svc_exit_thread(nlmsvc_rqst);
nlmsvc_task = NULL;
out_rqst:
nlmsvc_rqst = NULL;
return error;
}
/*
* This is the NFSv4 callback kernel thread.
*/
static int
nfs4_callback_svc(void *vrqstp)
{
int err;
struct svc_rqst *rqstp = vrqstp;
set_freezable();
while (!kthread_freezable_should_stop(NULL)) {
if (signal_pending(current))
flush_signals(current);
/*
* Listen for a request on the socket
*/
err = svc_recv(rqstp, MAX_SCHEDULE_TIMEOUT);
if (err == -EAGAIN || err == -EINTR)
continue;
svc_process(rqstp);
}
svc_exit_thread(rqstp);
module_put_and_exit(0);
return 0;
}
/*
* Bring up the lockd process if it's not already up.
*/
int lockd_up(void)
{
struct svc_serv *serv;
int error = 0;
mutex_lock(&nlmsvc_mutex);
/*
* Check whether we're already up and running.
*/
if (nlmsvc_rqst)
goto out;
/*
* Sanity check: if there's no pid,
* we should be the first user ...
*/
if (nlmsvc_users)
printk(KERN_WARNING
"lockd_up: no pid, %d users??\n", nlmsvc_users);
error = -ENOMEM;
serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, NULL);
if (!serv) {
printk(KERN_WARNING "lockd_up: create service failed\n");
goto out;
}
error = make_socks(serv);
if (error < 0)
goto destroy_and_out;
/*
* Create the kernel thread and wait for it to start.
*/
nlmsvc_rqst = svc_prepare_thread(serv, &serv->sv_pools[0]);
if (IS_ERR(nlmsvc_rqst)) {
error = PTR_ERR(nlmsvc_rqst);
nlmsvc_rqst = NULL;
printk(KERN_WARNING
"lockd_up: svc_rqst allocation failed, error=%d\n",
error);
goto destroy_and_out;
}
svc_sock_update_bufs(serv);
serv->sv_maxconn = nlm_max_connections;
nlmsvc_task = kthread_run(lockd, nlmsvc_rqst, serv->sv_name);
if (IS_ERR(nlmsvc_task)) {
error = PTR_ERR(nlmsvc_task);
svc_exit_thread(nlmsvc_rqst);
nlmsvc_task = NULL;
nlmsvc_rqst = NULL;
printk(KERN_WARNING
"lockd_up: kthread_run failed, error=%d\n", error);
goto destroy_and_out;
}
/*
* Note: svc_serv structures have an initial use count of 1,
* so we exit through here on both success and failure.
*/
destroy_and_out:
svc_destroy(serv);
out:
if (!error)
nlmsvc_users++;
mutex_unlock(&nlmsvc_mutex);
return error;
}
/*
* This is the lockd kernel thread
*/
static void
lockd(struct svc_rqst *rqstp)
{
int err = 0;
unsigned long grace_period_expire;
/* Lock module and set up kernel thread */
/* lockd_up is waiting for us to startup, so will
* be holding a reference to this module, so it
* is safe to just claim another reference
*/
__module_get(THIS_MODULE);
lock_kernel();
/*
* Let our maker know we're running.
*/
nlmsvc_pid = current->pid;
nlmsvc_serv = rqstp->rq_server;
complete(&lockd_start_done);
daemonize("lockd");
set_freezable();
/* Process request with signals blocked, but allow SIGKILL. */
allow_signal(SIGKILL);
dprintk("NFS locking service started (ver " LOCKD_VERSION ").\n");
if (!nlm_timeout)
nlm_timeout = LOCKD_DFLT_TIMEO;
nlmsvc_timeout = nlm_timeout * HZ;
grace_period_expire = set_grace_period();
/*
* The main request loop. We don't terminate until the last
* NFS mount or NFS daemon has gone away, and we've been sent a
* signal, or else another process has taken over our job.
*/
while ((nlmsvc_users || !signalled()) && nlmsvc_pid == current->pid) {
long timeout = MAX_SCHEDULE_TIMEOUT;
char buf[RPC_MAX_ADDRBUFLEN];
if (signalled()) {
flush_signals(current);
if (nlmsvc_ops) {
nlmsvc_invalidate_all();
grace_period_expire = set_grace_period();
}
}
/*
* Retry any blocked locks that have been notified by
* the VFS. Don't do this during grace period.
* (Theoretically, there shouldn't even be blocked locks
* during grace period).
*/
if (!nlmsvc_grace_period) {
timeout = nlmsvc_retry_blocked();
} else if (time_before(grace_period_expire, jiffies))
clear_grace_period();
/*
* Find a socket with data available and call its
* recvfrom routine.
*/
err = svc_recv(rqstp, timeout);
if (err == -EAGAIN || err == -EINTR)
continue;
if (err < 0) {
printk(KERN_WARNING
"lockd: terminating on error %d\n",
-err);
break;
}
dprintk("lockd: request from %s\n",
svc_print_addr(rqstp, buf, sizeof(buf)));
svc_process(rqstp);
}
flush_signals(current);
/*
* Check whether there's a new lockd process before
* shutting down the hosts and clearing the slot.
*/
if (!nlmsvc_pid || current->pid == nlmsvc_pid) {
if (nlmsvc_ops)
nlmsvc_invalidate_all();
nlm_shutdown_hosts();
nlmsvc_pid = 0;
nlmsvc_serv = NULL;
} else
printk(KERN_DEBUG
"lockd: new process, skipping host shutdown\n");
wake_up(&lockd_exit);
/* Exit the RPC thread */
svc_exit_thread(rqstp);
/* Release module */
unlock_kernel();
module_put_and_exit(0);
}
/*
* This is the lockd kernel thread
*/
static void
lockd(struct svc_rqst *rqstp)
{
struct svc_serv *serv = rqstp->rq_server;
int err = 0;
unsigned long grace_period_expire;
/* Lock module and set up kernel thread */
MOD_INC_USE_COUNT;
lock_kernel();
/*
* Let our maker know we're running.
*/
nlmsvc_pid = current->pid;
up(&lockd_start);
daemonize();
reparent_to_init();
sprintf(current->comm, "lockd");
/* Process request with signals blocked. */
spin_lock_irq(¤t->sighand->siglock);
siginitsetinv(¤t->blocked, sigmask(SIGKILL));
recalc_sigpending();
spin_unlock_irq(¤t->sighand->siglock);
/* kick rpciod */
rpciod_up();
dprintk("NFS locking service started (ver " LOCKD_VERSION ").\n");
if (!nlm_timeout)
nlm_timeout = LOCKD_DFLT_TIMEO;
nlmsvc_timeout = nlm_timeout * HZ;
grace_period_expire = set_grace_period();
/*
* The main request loop. We don't terminate until the last
* NFS mount or NFS daemon has gone away, and we've been sent a
* signal, or else another process has taken over our job.
*/
while ((nlmsvc_users || !signalled()) && nlmsvc_pid == current->pid)
{
long timeout = MAX_SCHEDULE_TIMEOUT;
if (signalled()) {
spin_lock_irq(¤t->sighand->siglock);
flush_signals(current);
spin_unlock_irq(¤t->sighand->siglock);
if (nlmsvc_ops) {
nlmsvc_ops->detach();
grace_period_expire = set_grace_period();
}
}
/*
* Retry any blocked locks that have been notified by
* the VFS. Don't do this during grace period.
* (Theoretically, there shouldn't even be blocked locks
* during grace period).
*/
if (!nlmsvc_grace_period)
timeout = nlmsvc_retry_blocked();
/*
* Find a socket with data available and call its
* recvfrom routine.
*/
err = svc_recv(serv, rqstp, timeout);
if (err == -EAGAIN || err == -EINTR)
continue;
if (err < 0) {
printk(KERN_WARNING
"lockd: terminating on error %d\n",
-err);
break;
}
dprintk("lockd: request from %08x\n",
(unsigned)ntohl(rqstp->rq_addr.sin_addr.s_addr));
/*
* Look up the NFS client handle. The handle is needed for
* all but the GRANTED callback RPCs.
*/
rqstp->rq_client = NULL;
if (nlmsvc_ops) {
nlmsvc_ops->exp_readlock();
rqstp->rq_client =
nlmsvc_ops->exp_getclient(&rqstp->rq_addr);
}
if (nlmsvc_grace_period &&
time_before(grace_period_expire, jiffies))
nlmsvc_grace_period = 0;
svc_process(serv, rqstp);
/* Unlock export hash tables */
if (nlmsvc_ops)
nlmsvc_ops->exp_unlock();
}
/*
* Check whether there's a new lockd process before
* shutting down the hosts and clearing the slot.
*/
if (!nlmsvc_pid || current->pid == nlmsvc_pid) {
if (nlmsvc_ops)
nlmsvc_ops->detach();
nlm_shutdown_hosts();
nlmsvc_pid = 0;
} else
printk(KERN_DEBUG
"lockd: new process, skipping host shutdown\n");
wake_up(&lockd_exit);
/* Exit the RPC thread */
svc_exit_thread(rqstp);
/* release rpciod */
rpciod_down();
/* Release module */
MOD_DEC_USE_COUNT;
}
int lockd_up(struct net *net)
{
struct svc_serv *serv;
int error = 0;
struct lockd_net *ln = net_generic(net, lockd_net_id);
mutex_lock(&nlmsvc_mutex);
if (nlmsvc_rqst) {
error = lockd_up_net(nlmsvc_rqst->rq_server, net);
goto out;
}
if (nlmsvc_users)
printk(KERN_WARNING
"lockd_up: no pid, %d users??\n", nlmsvc_users);
error = -ENOMEM;
serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, NULL);
if (!serv) {
printk(KERN_WARNING "lockd_up: create service failed\n");
goto out;
}
error = svc_bind(serv, net);
if (error < 0) {
printk(KERN_WARNING "lockd_up: bind service failed\n");
goto destroy_and_out;
}
ln->nlmsvc_users++;
error = make_socks(serv, net);
if (error < 0)
goto err_start;
nlmsvc_rqst = svc_prepare_thread(serv, &serv->sv_pools[0], NUMA_NO_NODE);
if (IS_ERR(nlmsvc_rqst)) {
error = PTR_ERR(nlmsvc_rqst);
nlmsvc_rqst = NULL;
printk(KERN_WARNING
"lockd_up: svc_rqst allocation failed, error=%d\n",
error);
goto err_start;
}
svc_sock_update_bufs(serv);
serv->sv_maxconn = nlm_max_connections;
nlmsvc_task = kthread_run(lockd, nlmsvc_rqst, serv->sv_name);
if (IS_ERR(nlmsvc_task)) {
error = PTR_ERR(nlmsvc_task);
svc_exit_thread(nlmsvc_rqst);
nlmsvc_task = NULL;
nlmsvc_rqst = NULL;
printk(KERN_WARNING
"lockd_up: kthread_run failed, error=%d\n", error);
goto err_start;
}
destroy_and_out:
svc_destroy(serv);
out:
if (!error)
nlmsvc_users++;
mutex_unlock(&nlmsvc_mutex);
return error;
err_start:
lockd_down_net(serv, net);
goto destroy_and_out;
}
/*
* This is the NFS server kernel thread
*/
static void
nfsd(struct svc_rqst *rqstp)
{
struct svc_serv *serv = rqstp->rq_server;
struct fs_struct *fsp;
int err;
struct nfsd_list me;
sigset_t shutdown_mask, allowed_mask;
/* Lock module and set up kernel thread */
lock_kernel();
daemonize("nfsd");
current->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY;
/* After daemonize() this kernel thread shares current->fs
* with the init process. We need to create files with a
* umask of 0 instead of init's umask. */
fsp = copy_fs_struct(current->fs);
if (!fsp) {
printk("Unable to start nfsd thread: out of memory\n");
goto out;
}
exit_fs(current);
current->fs = fsp;
current->fs->umask = 0;
siginitsetinv(&shutdown_mask, SHUTDOWN_SIGS);
siginitsetinv(&allowed_mask, ALLOWED_SIGS);
nfsdstats.th_cnt++;
lockd_up(); /* start lockd */
me.task = current;
list_add(&me.list, &nfsd_list);
unlock_kernel();
/*
* We want less throttling in balance_dirty_pages() so that nfs to
* localhost doesn't cause nfsd to lock up due to all the client's
* dirty pages.
*/
current->flags |= PF_LESS_THROTTLE;
/*
* The main request loop
*/
for (;;) {
/* Block all but the shutdown signals */
sigprocmask(SIG_SETMASK, &shutdown_mask, NULL);
/*
* Find a socket with data available and call its
* recvfrom routine.
*/
while ((err = svc_recv(serv, rqstp,
60*60*HZ)) == -EAGAIN)
;
if (err < 0)
break;
update_thread_usage(atomic_read(&nfsd_busy));
atomic_inc(&nfsd_busy);
/* Lock the export hash tables for reading. */
exp_readlock();
/* Process request with signals blocked. */
sigprocmask(SIG_SETMASK, &allowed_mask, NULL);
svc_process(serv, rqstp);
/* Unlock export hash tables */
exp_readunlock();
update_thread_usage(atomic_read(&nfsd_busy));
atomic_dec(&nfsd_busy);
}
if (err != -EINTR) {
printk(KERN_WARNING "nfsd: terminating on error %d\n", -err);
} else {
unsigned int signo;
for (signo = 1; signo <= _NSIG; signo++)
if (sigismember(¤t->pending.signal, signo) &&
!sigismember(¤t->blocked, signo))
break;
err = signo;
}
lock_kernel();
/* Release lockd */
lockd_down();
/* Check if this is last thread */
if (serv->sv_nrthreads==1) {
printk(KERN_WARNING "nfsd: last server has exited\n");
if (err != SIG_NOCLEAN) {
printk(KERN_WARNING "nfsd: unexporting all filesystems\n");
nfsd_export_flush();
}
nfsd_serv = NULL;
nfsd_racache_shutdown(); /* release read-ahead cache */
nfs4_state_shutdown();
}
list_del(&me.list);
nfsdstats.th_cnt --;
out:
/* Release the thread */
svc_exit_thread(rqstp);
/* Release module */
module_put_and_exit(0);
}