#include <linux/sched.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>
#define RPCDBG_FACILITY RPCDBG_SVCXPRT
+#define SVC_MAX_WAKING 5
+
static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt);
static int svc_deferred_recv(struct svc_rqst *rqstp);
static struct cache_deferred_req *svc_defer(struct cache_req *req);
}
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 = htonl(INADDR_ANY),
.sin_port = htons(port),
};
+ struct sockaddr_in6 sin6 = {
+ .sin6_family = AF_INET6,
+ .sin6_addr = IN6ADDR_ANY_INIT,
+ .sin6_port = htons(port),
+ };
+ struct sockaddr *sap;
+ size_t len;
+
+ switch (family) {
+ case PF_INET:
+ sap = (struct sockaddr *)&sin;
+ len = sizeof(sin);
+ break;
+ case PF_INET6:
+ sap = (struct sockaddr *)&sin6;
+ len = sizeof(sin6);
+ break;
+ 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);
struct svc_pool *pool;
struct svc_rqst *rqstp;
int cpu;
+ int thread_avail;
if (!(xprt->xpt_flags &
((1<<XPT_CONN)|(1<<XPT_DATA)|(1<<XPT_CLOSE)|(1<<XPT_DEFERRED))))
spin_lock_bh(&pool->sp_lock);
- if (!list_empty(&pool->sp_threads) &&
- !list_empty(&pool->sp_sockets))
- printk(KERN_ERR
- "svc_xprt_enqueue: "
- "threads and transports both waiting??\n");
-
if (test_bit(XPT_DEAD, &xprt->xpt_flags)) {
/* Don't enqueue dead transports */
dprintk("svc: transport %p is dead, not enqueued\n", xprt);
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
}
process:
- if (!list_empty(&pool->sp_threads)) {
+ /* Work out whether threads are available */
+ thread_avail = !list_empty(&pool->sp_threads); /* threads are asleep */
+ if (pool->sp_nwaking >= SVC_MAX_WAKING) {
+ /* too many threads are runnable and trying to wake up */
+ thread_avail = 0;
+ pool->sp_stats.overloads_avoided++;
+ }
+
+ if (thread_avail) {
rqstp = list_entry(pool->sp_threads.next,
struct svc_rqst,
rq_list);
svc_xprt_get(xprt);
rqstp->rq_reserved = serv->sv_max_mesg;
atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
+ rqstp->rq_waking = 1;
+ pool->sp_nwaking++;
+ 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(svc_reserve);
+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(svc_wake_up);
+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);
return -EINTR;
spin_lock_bh(&pool->sp_lock);
+ if (rqstp->rq_waking) {
+ rqstp->rq_waking = 0;
+ pool->sp_nwaking--;
+ BUG_ON(pool->sp_nwaking < 0);
+ }
xprt = svc_xprt_dequeue(pool);
if (xprt) {
rqstp->rq_xprt = xprt;
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) {
serv->sv_stats->netcnt++;
return len;
}
-EXPORT_SYMBOL(svc_recv);
+EXPORT_SYMBOL_GPL(svc_recv);
/*
* Drop request
dprintk("svc: xprt %p dropped request\n", rqstp->rq_xprt);
svc_xprt_release(rqstp);
}
-EXPORT_SYMBOL(svc_drop);
+EXPORT_SYMBOL_GPL(svc_drop);
/*
* Return reply to client.
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--;
+ if (test_bit(XPT_TEMP, &xprt->xpt_flags))
+ serv->sv_tmpcnt--;
+
+ for (dr = svc_deferred_dequeue(xprt); dr;
+ dr = svc_deferred_dequeue(xprt)) {
svc_xprt_put(xprt);
+ kfree(dr);
}
+
+ svc_xprt_put(xprt);
spin_unlock_bh(&serv->sv_lock);
}
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;
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.
* 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, char *xcl_name,
- int af, int port)
+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 || !xcl_name)
+ if (serv == NULL || xcl_name == NULL)
return found;
spin_lock_bh(&serv->sv_lock);
continue;
if (af != AF_UNSPEC && af != xprt->xpt_local.ss_family)
continue;
- if (port && port != svc_xprt_local_port(xprt))
+ if (port != 0 && port != svc_xprt_local_port(xprt))
continue;
found = xprt;
svc_xprt_get(xprt);
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);
+
+ lock_kernel();
+ /* bump up the pseudo refcount while traversing */
+ svc_get(serv);
+ unlock_kernel();
+
+ 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)
+{
+ struct svc_serv *serv = m->private;
+
+ lock_kernel();
+ /* this function really, really should have been called svc_put() */
+ svc_destroy(serv);
+ unlock_kernel();
+}
+
+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 overloads-avoided threads-timedout\n");
+ return 0;
+ }
+
+ seq_printf(m, "%u %lu %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.overloads_avoided,
+ 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