*/
#include <linux/sched.h>
+#include <linux/smp_lock.h>
#include <linux/errno.h>
-#include <linux/fcntl.h>
-#include <linux/net.h>
-#include <linux/in.h>
-#include <linux/inet.h>
-#include <linux/udp.h>
-#include <linux/tcp.h>
-#include <linux/unistd.h>
-#include <linux/slab.h>
-#include <linux/netdevice.h>
-#include <linux/skbuff.h>
-#include <linux/file.h>
#include <linux/freezer.h>
+#include <linux/kthread.h>
#include <net/sock.h>
-#include <net/checksum.h>
-#include <net/ip.h>
-#include <net/ipv6.h>
-#include <net/tcp_states.h>
-#include <linux/uaccess.h>
-#include <asm/ioctls.h>
-
-#include <linux/sunrpc/types.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/xdr.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/svc_xprt.h>
+#include <linux/sunrpc/svcsock.h>
#define RPCDBG_FACILITY RPCDBG_SVCXPRT
}
EXPORT_SYMBOL_GPL(svc_unreg_xprt_class);
+/*
+ * Format the transport list for printing
+ */
+int svc_print_xprts(char *buf, int maxlen)
+{
+ struct list_head *le;
+ char tmpstr[80];
+ int len = 0;
+ buf[0] = '\0';
+
+ spin_lock(&svc_xprt_class_lock);
+ list_for_each(le, &svc_xprt_class_list) {
+ int slen;
+ struct svc_xprt_class *xcl =
+ list_entry(le, struct svc_xprt_class, xcl_list);
+
+ sprintf(tmpstr, "%s %d\n", xcl->xcl_name, xcl->xcl_max_payload);
+ slen = strlen(tmpstr);
+ if (len + slen > maxlen)
+ break;
+ len += slen;
+ strcat(buf, tmpstr);
+ }
+ spin_unlock(&svc_xprt_class_lock);
+
+ return len;
+}
+
static void svc_xprt_free(struct kref *kref)
{
struct svc_xprt *xprt =
container_of(kref, struct svc_xprt, xpt_ref);
struct module *owner = xprt->xpt_class->xcl_owner;
- if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags)
- && xprt->xpt_auth_cache != NULL)
+ if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags) &&
+ xprt->xpt_auth_cache != NULL)
svcauth_unix_info_release(xprt->xpt_auth_cache);
xprt->xpt_ops->xpo_free(xprt);
module_put(owner);
mutex_init(&xprt->xpt_mutex);
spin_lock_init(&xprt->xpt_lock);
set_bit(XPT_BUSY, &xprt->xpt_flags);
+ rpc_init_wait_queue(&xprt->xpt_bc_pending, "xpt_bc_pending");
}
EXPORT_SYMBOL_GPL(svc_xprt_init);
-int svc_create_xprt(struct svc_serv *serv, char *xprt_name, unsigned short port,
- int flags)
+static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
+ struct svc_serv *serv,
+ const int family,
+ const unsigned short port,
+ int flags)
{
- struct svc_xprt_class *xcl;
struct sockaddr_in sin = {
.sin_family = AF_INET,
- .sin_addr.s_addr = INADDR_ANY,
+ .sin_addr.s_addr = htonl(INADDR_ANY),
.sin_port = htons(port),
};
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ struct sockaddr_in6 sin6 = {
+ .sin6_family = AF_INET6,
+ .sin6_addr = IN6ADDR_ANY_INIT,
+ .sin6_port = htons(port),
+ };
+#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+ struct sockaddr *sap;
+ size_t len;
+
+ switch (family) {
+ case PF_INET:
+ sap = (struct sockaddr *)&sin;
+ len = sizeof(sin);
+ break;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ case PF_INET6:
+ sap = (struct sockaddr *)&sin6;
+ len = sizeof(sin6);
+ break;
+#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+ default:
+ return ERR_PTR(-EAFNOSUPPORT);
+ }
+
+ return xcl->xcl_ops->xpo_create(serv, sap, len, flags);
+}
+
+int svc_create_xprt(struct svc_serv *serv, const char *xprt_name,
+ const int family, const unsigned short port,
+ int flags)
+{
+ struct svc_xprt_class *xcl;
+
dprintk("svc: creating transport %s[%d]\n", xprt_name, port);
spin_lock(&svc_xprt_class_lock);
list_for_each_entry(xcl, &svc_xprt_class_list, xcl_list) {
goto err;
spin_unlock(&svc_xprt_class_lock);
- newxprt = xcl->xcl_ops->
- xpo_create(serv, (struct sockaddr *)&sin, sizeof(sin),
- flags);
+ newxprt = __svc_xpo_create(xcl, serv, family, port, flags);
if (IS_ERR(newxprt)) {
module_put(xcl->xcl_owner);
return PTR_ERR(newxprt);
err:
spin_unlock(&svc_xprt_class_lock);
dprintk("svc: transport %s not found\n", xprt_name);
- return -ENOENT;
+
+ /* This errno is exposed to user space. Provide a reasonable
+ * perror msg for a bad transport. */
+ return -EPROTONOSUPPORT;
}
EXPORT_SYMBOL_GPL(svc_create_xprt);
if (!(xprt->xpt_flags &
((1<<XPT_CONN)|(1<<XPT_DATA)|(1<<XPT_CLOSE)|(1<<XPT_DEFERRED))))
return;
- if (test_bit(XPT_DEAD, &xprt->xpt_flags))
- return;
cpu = get_cpu();
pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
goto out_unlock;
}
+ pool->sp_stats.packets++;
+
/* Mark transport as busy. It will remain in this state until
* the provider calls svc_xprt_received. We update XPT_BUSY
* atomically because it also guards against trying to enqueue
svc_xprt_get(xprt);
rqstp->rq_reserved = serv->sv_max_mesg;
atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
+ pool->sp_stats.threads_woken++;
BUG_ON(xprt->xpt_pool != pool);
wake_up(&rqstp->rq_wait);
} else {
dprintk("svc: transport %p put into queue\n", xprt);
list_add_tail(&xprt->xpt_ready, &pool->sp_sockets);
+ pool->sp_stats.sockets_queued++;
BUG_ON(xprt->xpt_pool != pool);
}
svc_xprt_enqueue(xprt);
}
}
+EXPORT_SYMBOL_GPL(svc_reserve);
static void svc_xprt_release(struct svc_rqst *rqstp)
{
rqstp->rq_xprt->xpt_ops->xpo_release_rqst(rqstp);
+ kfree(rqstp->rq_deferred);
+ rqstp->rq_deferred = NULL;
+
svc_free_res_pages(rqstp);
rqstp->rq_res.page_len = 0;
rqstp->rq_res.page_base = 0;
spin_unlock_bh(&pool->sp_lock);
}
}
+EXPORT_SYMBOL_GPL(svc_wake_up);
int svc_port_is_privileged(struct sockaddr *sin)
{
}
/*
- * Make sure that we don't have too many active connections. If we
- * have, something must be dropped.
+ * Make sure that we don't have too many active connections. If we have,
+ * something must be dropped. It's not clear what will happen if we allow
+ * "too many" connections, but when dealing with network-facing software,
+ * we have to code defensively. Here we do that by imposing hard limits.
*
* There's no point in trying to do random drop here for DoS
* prevention. The NFS clients does 1 reconnect in 15 seconds. An
* The only somewhat efficient mechanism would be if drop old
* connections from the same IP first. But right now we don't even
* record the client IP in svc_sock.
+ *
+ * single-threaded services that expect a lot of clients will probably
+ * need to set sv_maxconn to override the default value which is based
+ * on the number of threads
*/
static void svc_check_conn_limits(struct svc_serv *serv)
{
- if (serv->sv_tmpcnt > (serv->sv_nrthreads+3)*20) {
+ unsigned int limit = serv->sv_maxconn ? serv->sv_maxconn :
+ (serv->sv_nrthreads+3) * 20;
+
+ if (serv->sv_tmpcnt > limit) {
struct svc_xprt *xprt = NULL;
spin_lock_bh(&serv->sv_lock);
if (!list_empty(&serv->sv_tempsocks)) {
if (net_ratelimit()) {
/* Try to help the admin */
printk(KERN_NOTICE "%s: too many open "
- "connections, consider increasing the "
- "number of nfsd threads\n",
- serv->sv_name);
+ "connections, consider increasing %s\n",
+ serv->sv_name, serv->sv_maxconn ?
+ "the max number of connections." :
+ "the number of threads.");
}
/*
* Always select the oldest connection. It's not fair,
int pages;
struct xdr_buf *arg;
DECLARE_WAITQUEUE(wait, current);
+ long time_left;
dprintk("svc: server %p waiting for data (to = %ld)\n",
rqstp, timeout);
while (rqstp->rq_pages[i] == NULL) {
struct page *p = alloc_page(GFP_KERNEL);
if (!p) {
- int j = msecs_to_jiffies(500);
- schedule_timeout_uninterruptible(j);
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (signalled() || kthread_should_stop()) {
+ set_current_state(TASK_RUNNING);
+ return -EINTR;
+ }
+ schedule_timeout(msecs_to_jiffies(500));
}
rqstp->rq_pages[i] = p;
}
try_to_freeze();
cond_resched();
- if (signalled())
+ if (signalled() || kthread_should_stop())
return -EINTR;
spin_lock_bh(&pool->sp_lock);
* to bring down the daemons ...
*/
set_current_state(TASK_INTERRUPTIBLE);
+
+ /*
+ * checking kthread_should_stop() here allows us to avoid
+ * locking and signalling when stopping kthreads that call
+ * svc_recv. If the thread has already been woken up, then
+ * we can exit here without sleeping. If not, then it
+ * it'll be woken up quickly during the schedule_timeout
+ */
+ if (kthread_should_stop()) {
+ set_current_state(TASK_RUNNING);
+ spin_unlock_bh(&pool->sp_lock);
+ return -EINTR;
+ }
+
add_wait_queue(&rqstp->rq_wait, &wait);
spin_unlock_bh(&pool->sp_lock);
- schedule_timeout(timeout);
+ time_left = schedule_timeout(timeout);
try_to_freeze();
spin_lock_bh(&pool->sp_lock);
remove_wait_queue(&rqstp->rq_wait, &wait);
+ if (!time_left)
+ pool->sp_stats.threads_timedout++;
xprt = rqstp->rq_xprt;
if (!xprt) {
svc_thread_dequeue(pool, rqstp);
spin_unlock_bh(&pool->sp_lock);
dprintk("svc: server %p, no data yet\n", rqstp);
- return signalled()? -EINTR : -EAGAIN;
+ if (signalled() || kthread_should_stop())
+ return -EINTR;
+ else
+ return -EAGAIN;
}
}
spin_unlock_bh(&pool->sp_lock);
len = 0;
- if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) {
- dprintk("svc_recv: found XPT_CLOSE\n");
- svc_delete_xprt(xprt);
- } else if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) {
+ if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) {
struct svc_xprt *newxpt;
newxpt = xprt->xpt_ops->xpo_accept(xprt);
if (newxpt) {
svc_xprt_received(newxpt);
}
svc_xprt_received(xprt);
- } else {
+ } else if (!test_bit(XPT_CLOSE, &xprt->xpt_flags)) {
dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n",
rqstp, pool->sp_id, xprt,
atomic_read(&xprt->xpt_ref.refcount));
dprintk("svc: got len=%d\n", len);
}
+ if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) {
+ dprintk("svc_recv: found XPT_CLOSE\n");
+ svc_delete_xprt(xprt);
+ }
+
/* No data, incomplete (TCP) read, or accept() */
if (len == 0 || len == -EAGAIN) {
rqstp->rq_res.len = 0;
serv->sv_stats->netcnt++;
return len;
}
+EXPORT_SYMBOL_GPL(svc_recv);
/*
* Drop request
dprintk("svc: xprt %p dropped request\n", rqstp->rq_xprt);
svc_xprt_release(rqstp);
}
+EXPORT_SYMBOL_GPL(svc_drop);
/*
* Return reply to client.
else
len = xprt->xpt_ops->xpo_sendto(rqstp);
mutex_unlock(&xprt->xpt_mutex);
+ rpc_wake_up(&xprt->xpt_bc_pending);
svc_xprt_release(rqstp);
if (len == -ECONNREFUSED || len == -ENOTCONN || len == -EAGAIN)
* through, close it. */
if (!test_and_set_bit(XPT_OLD, &xprt->xpt_flags))
continue;
- if (atomic_read(&xprt->xpt_ref.refcount) > 1
- || test_bit(XPT_BUSY, &xprt->xpt_flags))
+ if (atomic_read(&xprt->xpt_ref.refcount) > 1 ||
+ test_bit(XPT_BUSY, &xprt->xpt_flags))
continue;
svc_xprt_get(xprt);
list_move(le, &to_be_aged);
void svc_delete_xprt(struct svc_xprt *xprt)
{
struct svc_serv *serv = xprt->xpt_server;
+ struct svc_deferred_req *dr;
+
+ /* Only do this once */
+ if (test_and_set_bit(XPT_DEAD, &xprt->xpt_flags))
+ return;
dprintk("svc: svc_delete_xprt(%p)\n", xprt);
xprt->xpt_ops->xpo_detach(xprt);
* while still attached to a queue, the queue itself
* is about to be destroyed (in svc_destroy).
*/
- if (!test_and_set_bit(XPT_DEAD, &xprt->xpt_flags)) {
- BUG_ON(atomic_read(&xprt->xpt_ref.refcount) < 2);
- if (test_bit(XPT_TEMP, &xprt->xpt_flags))
- serv->sv_tmpcnt--;
- svc_xprt_put(xprt);
- }
+ if (test_bit(XPT_TEMP, &xprt->xpt_flags))
+ serv->sv_tmpcnt--;
+
+ while ((dr = svc_deferred_dequeue(xprt)) != NULL)
+ kfree(dr);
+
+ svc_xprt_put(xprt);
spin_unlock_bh(&serv->sv_lock);
}
clear_bit(XPT_BUSY, &xprt->xpt_flags);
svc_xprt_put(xprt);
}
+EXPORT_SYMBOL_GPL(svc_close_xprt);
void svc_close_all(struct list_head *xprt_list)
{
container_of(dreq, struct svc_deferred_req, handle);
struct svc_xprt *xprt = dr->xprt;
- if (too_many) {
+ spin_lock(&xprt->xpt_lock);
+ set_bit(XPT_DEFERRED, &xprt->xpt_flags);
+ if (too_many || test_bit(XPT_DEAD, &xprt->xpt_flags)) {
+ spin_unlock(&xprt->xpt_lock);
+ dprintk("revisit canceled\n");
svc_xprt_put(xprt);
kfree(dr);
return;
}
dprintk("revisit queued\n");
dr->xprt = NULL;
- spin_lock(&xprt->xpt_lock);
list_add(&dr->handle.recent, &xprt->xpt_deferred);
spin_unlock(&xprt->xpt_lock);
- set_bit(XPT_DEFERRED, &xprt->xpt_flags);
svc_xprt_enqueue(xprt);
svc_xprt_put(xprt);
}
struct svc_rqst *rqstp = container_of(req, struct svc_rqst, rq_chandle);
struct svc_deferred_req *dr;
- if (rqstp->rq_arg.page_len)
+ if (rqstp->rq_arg.page_len || !rqstp->rq_usedeferral)
return NULL; /* if more than a page, give up FIXME */
if (rqstp->rq_deferred) {
dr = rqstp->rq_deferred;
spin_unlock(&xprt->xpt_lock);
return dr;
}
+
+/**
+ * svc_find_xprt - find an RPC transport instance
+ * @serv: pointer to svc_serv to search
+ * @xcl_name: C string containing transport's class name
+ * @af: Address family of transport's local address
+ * @port: transport's IP port number
+ *
+ * Return the transport instance pointer for the endpoint accepting
+ * connections/peer traffic from the specified transport class,
+ * address family and port.
+ *
+ * Specifying 0 for the address family or port is effectively a
+ * wild-card, and will result in matching the first transport in the
+ * service's list that has a matching class name.
+ */
+struct svc_xprt *svc_find_xprt(struct svc_serv *serv, const char *xcl_name,
+ const sa_family_t af, const unsigned short port)
+{
+ struct svc_xprt *xprt;
+ struct svc_xprt *found = NULL;
+
+ /* Sanity check the args */
+ if (serv == NULL || xcl_name == NULL)
+ return found;
+
+ spin_lock_bh(&serv->sv_lock);
+ list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list) {
+ if (strcmp(xprt->xpt_class->xcl_name, xcl_name))
+ continue;
+ if (af != AF_UNSPEC && af != xprt->xpt_local.ss_family)
+ continue;
+ if (port != 0 && port != svc_xprt_local_port(xprt))
+ continue;
+ found = xprt;
+ svc_xprt_get(xprt);
+ break;
+ }
+ spin_unlock_bh(&serv->sv_lock);
+ return found;
+}
+EXPORT_SYMBOL_GPL(svc_find_xprt);
+
+static int svc_one_xprt_name(const struct svc_xprt *xprt,
+ char *pos, int remaining)
+{
+ int len;
+
+ len = snprintf(pos, remaining, "%s %u\n",
+ xprt->xpt_class->xcl_name,
+ svc_xprt_local_port(xprt));
+ if (len >= remaining)
+ return -ENAMETOOLONG;
+ return len;
+}
+
+/**
+ * svc_xprt_names - format a buffer with a list of transport names
+ * @serv: pointer to an RPC service
+ * @buf: pointer to a buffer to be filled in
+ * @buflen: length of buffer to be filled in
+ *
+ * Fills in @buf with a string containing a list of transport names,
+ * each name terminated with '\n'.
+ *
+ * Returns positive length of the filled-in string on success; otherwise
+ * a negative errno value is returned if an error occurs.
+ */
+int svc_xprt_names(struct svc_serv *serv, char *buf, const int buflen)
+{
+ struct svc_xprt *xprt;
+ int len, totlen;
+ char *pos;
+
+ /* Sanity check args */
+ if (!serv)
+ return 0;
+
+ spin_lock_bh(&serv->sv_lock);
+
+ pos = buf;
+ totlen = 0;
+ list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list) {
+ len = svc_one_xprt_name(xprt, pos, buflen - totlen);
+ if (len < 0) {
+ *buf = '\0';
+ totlen = len;
+ }
+ if (len <= 0)
+ break;
+
+ pos += len;
+ totlen += len;
+ }
+
+ spin_unlock_bh(&serv->sv_lock);
+ return totlen;
+}
+EXPORT_SYMBOL_GPL(svc_xprt_names);
+
+
+/*----------------------------------------------------------------------------*/
+
+static void *svc_pool_stats_start(struct seq_file *m, loff_t *pos)
+{
+ unsigned int pidx = (unsigned int)*pos;
+ struct svc_serv *serv = m->private;
+
+ dprintk("svc_pool_stats_start, *pidx=%u\n", pidx);
+
+ if (!pidx)
+ return SEQ_START_TOKEN;
+ return (pidx > serv->sv_nrpools ? NULL : &serv->sv_pools[pidx-1]);
+}
+
+static void *svc_pool_stats_next(struct seq_file *m, void *p, loff_t *pos)
+{
+ struct svc_pool *pool = p;
+ struct svc_serv *serv = m->private;
+
+ dprintk("svc_pool_stats_next, *pos=%llu\n", *pos);
+
+ if (p == SEQ_START_TOKEN) {
+ pool = &serv->sv_pools[0];
+ } else {
+ unsigned int pidx = (pool - &serv->sv_pools[0]);
+ if (pidx < serv->sv_nrpools-1)
+ pool = &serv->sv_pools[pidx+1];
+ else
+ pool = NULL;
+ }
+ ++*pos;
+ return pool;
+}
+
+static void svc_pool_stats_stop(struct seq_file *m, void *p)
+{
+}
+
+static int svc_pool_stats_show(struct seq_file *m, void *p)
+{
+ struct svc_pool *pool = p;
+
+ if (p == SEQ_START_TOKEN) {
+ seq_puts(m, "# pool packets-arrived sockets-enqueued threads-woken threads-timedout\n");
+ return 0;
+ }
+
+ seq_printf(m, "%u %lu %lu %lu %lu\n",
+ pool->sp_id,
+ pool->sp_stats.packets,
+ pool->sp_stats.sockets_queued,
+ pool->sp_stats.threads_woken,
+ pool->sp_stats.threads_timedout);
+
+ return 0;
+}
+
+static const struct seq_operations svc_pool_stats_seq_ops = {
+ .start = svc_pool_stats_start,
+ .next = svc_pool_stats_next,
+ .stop = svc_pool_stats_stop,
+ .show = svc_pool_stats_show,
+};
+
+int svc_pool_stats_open(struct svc_serv *serv, struct file *file)
+{
+ int err;
+
+ err = seq_open(file, &svc_pool_stats_seq_ops);
+ if (!err)
+ ((struct seq_file *) file->private_data)->private = serv;
+ return err;
+}
+EXPORT_SYMBOL(svc_pool_stats_open);
+
+/*----------------------------------------------------------------------------*/
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff