#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/file.h>
+#include <linux/freezer.h>
#include <net/sock.h>
#include <net/checksum.h>
#include <net/ip.h>
* providing that certain rules are followed:
*
* SK_CONN, SK_DATA, can be set or cleared at any time.
- * after a set, svc_sock_enqueue must be called.
+ * after a set, svc_sock_enqueue must be called.
* after a clear, the socket must be read/accepted
* if this succeeds, it must be set again.
* SK_CLOSE can set at any time. It is never cleared.
+ * sk_inuse contains a bias of '1' until SK_DEAD is set.
+ * so when sk_inuse hits zero, we know the socket is dead
+ * and no-one is using it.
+ * SK_DEAD can only be set while SK_BUSY is held which ensures
+ * no other thread will be using the socket or will try to
+ * set SK_DEAD.
*
*/
static struct svc_sock *svc_setup_socket(struct svc_serv *, struct socket *,
int *errp, int pmap_reg);
+static void svc_delete_socket(struct svc_sock *svsk);
static void svc_udp_data_ready(struct sock *, int);
static int svc_udp_recvfrom(struct svc_rqst *);
static int svc_udp_sendto(struct svc_rqst *);
*/
static int svc_conn_age_period = 6*60;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static struct lock_class_key svc_key[2];
+static struct lock_class_key svc_slock_key[2];
+
+static inline void svc_reclassify_socket(struct socket *sock)
+{
+ struct sock *sk = sock->sk;
+ BUG_ON(sk->sk_lock.owner != NULL);
+ switch (sk->sk_family) {
+ case AF_INET:
+ sock_lock_init_class_and_name(sk, "slock-AF_INET-NFSD",
+ &svc_slock_key[0], "sk_lock-AF_INET-NFSD", &svc_key[0]);
+ break;
+
+ case AF_INET6:
+ sock_lock_init_class_and_name(sk, "slock-AF_INET6-NFSD",
+ &svc_slock_key[1], "sk_lock-AF_INET6-NFSD", &svc_key[1]);
+ break;
+
+ default:
+ BUG();
+ }
+}
+#else
+static inline void svc_reclassify_socket(struct socket *sock)
+{
+}
+#endif
+
/*
* Queue up an idle server thread. Must have pool->sp_lock held.
* Note: this is really a stack rather than a queue, so that we only
svsk->sk_pool = pool;
set_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
- if (((atomic_read(&svsk->sk_reserved) + serv->sv_bufsz)*2
+ if (((atomic_read(&svsk->sk_reserved) + serv->sv_max_mesg)*2
> svc_sock_wspace(svsk))
&& !test_bit(SK_CLOSE, &svsk->sk_flags)
&& !test_bit(SK_CONN, &svsk->sk_flags)) {
/* Don't enqueue while not enough space for reply */
dprintk("svc: socket %p no space, %d*2 > %ld, not enqueued\n",
- svsk->sk_sk, atomic_read(&svsk->sk_reserved)+serv->sv_bufsz,
+ svsk->sk_sk, atomic_read(&svsk->sk_reserved)+serv->sv_max_mesg,
svc_sock_wspace(svsk));
svsk->sk_pool = NULL;
clear_bit(SK_BUSY, &svsk->sk_flags);
svsk->sk_sk, rqstp);
svc_thread_dequeue(pool, rqstp);
if (rqstp->rq_sock)
- printk(KERN_ERR
+ printk(KERN_ERR
"svc_sock_enqueue: server %p, rq_sock=%p!\n",
rqstp, rqstp->rq_sock);
rqstp->rq_sock = svsk;
atomic_inc(&svsk->sk_inuse);
- rqstp->rq_reserved = serv->sv_bufsz;
+ rqstp->rq_reserved = serv->sv_max_mesg;
atomic_add(rqstp->rq_reserved, &svsk->sk_reserved);
BUG_ON(svsk->sk_pool != pool);
wake_up(&rqstp->rq_wait);
static inline void
svc_sock_put(struct svc_sock *svsk)
{
- if (atomic_dec_and_test(&svsk->sk_inuse) && test_bit(SK_DEAD, &svsk->sk_flags)) {
+ if (atomic_dec_and_test(&svsk->sk_inuse)) {
+ BUG_ON(! test_bit(SK_DEAD, &svsk->sk_flags));
+
dprintk("svc: releasing dead socket\n");
- sock_release(svsk->sk_sock);
+ if (svsk->sk_sock->file)
+ sockfd_put(svsk->sk_sock);
+ else
+ sock_release(svsk->sk_sock);
+ if (svsk->sk_info_authunix != NULL)
+ svcauth_unix_info_release(svsk->sk_info_authunix);
kfree(svsk);
}
}
svc_release_skb(rqstp);
- svc_free_allpages(rqstp);
+ svc_free_res_pages(rqstp);
rqstp->rq_res.page_len = 0;
rqstp->rq_res.page_base = 0;
/* send head */
if (slen == xdr->head[0].iov_len)
flags = 0;
- len = kernel_sendpage(sock, rqstp->rq_respages[0], 0, xdr->head[0].iov_len, flags);
+ len = kernel_sendpage(sock, rqstp->rq_respages[0], 0,
+ xdr->head[0].iov_len, flags);
if (len != xdr->head[0].iov_len)
goto out;
slen -= xdr->head[0].iov_len;
}
/* send tail */
if (xdr->tail[0].iov_len) {
- result = kernel_sendpage(sock, rqstp->rq_respages[rqstp->rq_restailpage],
- ((unsigned long)xdr->tail[0].iov_base)& (PAGE_SIZE-1),
+ result = kernel_sendpage(sock, rqstp->rq_respages[0],
+ ((unsigned long)xdr->tail[0].iov_base)
+ & (PAGE_SIZE-1),
xdr->tail[0].iov_len, 0);
if (result > 0)
if (!serv)
return 0;
- spin_lock(&serv->sv_lock);
+ spin_lock_bh(&serv->sv_lock);
list_for_each_entry(svsk, &serv->sv_permsocks, sk_list) {
int onelen = one_sock_name(buf+len, svsk);
if (toclose && strcmp(toclose, buf+len) == 0)
else
len += onelen;
}
- spin_unlock(&serv->sv_lock);
+ spin_unlock_bh(&serv->sv_lock);
if (closesk)
/* Should unregister with portmap, but you cannot
* unregister just one protocol...
*/
- svc_delete_socket(closesk);
+ svc_close_socket(closesk);
else if (toclose)
return -ENOENT;
return len;
* which will access the socket.
*/
svc_sock_setbufsize(svsk->sk_sock,
- (serv->sv_nrthreads+3) * serv->sv_bufsz,
- (serv->sv_nrthreads+3) * serv->sv_bufsz);
+ (serv->sv_nrthreads+3) * serv->sv_max_mesg,
+ (serv->sv_nrthreads+3) * serv->sv_max_mesg);
if ((rqstp->rq_deferred = svc_deferred_dequeue(svsk))) {
svc_sock_received(svsk);
return svc_deferred_recv(rqstp);
}
+ if (test_bit(SK_CLOSE, &svsk->sk_flags)) {
+ svc_delete_socket(svsk);
+ return 0;
+ }
+
clear_bit(SK_DATA, &svsk->sk_flags);
while ((skb = skb_recv_datagram(svsk->sk_sk, 0, 1, &err)) == NULL) {
if (err == -EAGAIN) {
tv.tv_sec = xtime.tv_sec;
tv.tv_usec = xtime.tv_nsec / NSEC_PER_USEC;
skb_set_timestamp(skb, &tv);
- /* Don't enable netstamp, sunrpc doesn't
+ /* Don't enable netstamp, sunrpc doesn't
need that much accuracy */
}
skb_get_timestamp(skb, &svsk->sk_sk->sk_stamp);
return 0;
}
local_bh_enable();
- skb_free_datagram(svsk->sk_sk, skb);
+ skb_free_datagram(svsk->sk_sk, skb);
} else {
/* we can use it in-place */
rqstp->rq_arg.head[0].iov_base = skb->data + sizeof(struct udphdr);
if (len <= rqstp->rq_arg.head[0].iov_len) {
rqstp->rq_arg.head[0].iov_len = len;
rqstp->rq_arg.page_len = 0;
+ rqstp->rq_respages = rqstp->rq_pages+1;
} else {
rqstp->rq_arg.page_len = len - rqstp->rq_arg.head[0].iov_len;
- rqstp->rq_argused += (rqstp->rq_arg.page_len + PAGE_SIZE - 1)/ PAGE_SIZE;
+ rqstp->rq_respages = rqstp->rq_pages + 1 +
+ (rqstp->rq_arg.page_len + PAGE_SIZE - 1)/ PAGE_SIZE;
}
if (serv->sv_stats)
svsk->sk_sendto = svc_udp_sendto;
/* initialise setting must have enough space to
- * receive and respond to one request.
+ * receive and respond to one request.
* svc_udp_recvfrom will re-adjust if necessary
*/
svc_sock_setbufsize(svsk->sk_sock,
- 3 * svsk->sk_server->sv_bufsz,
- 3 * svsk->sk_server->sv_bufsz);
+ 3 * svsk->sk_server->sv_max_mesg,
+ 3 * svsk->sk_server->sv_max_mesg);
set_bit(SK_DATA, &svsk->sk_flags); /* might have come in before data_ready set up */
set_bit(SK_CHNGBUF, &svsk->sk_flags);
if (ntohs(sin.sin_port) >= 1024) {
dprintk(KERN_WARNING
"%s: connect from unprivileged port: %u.%u.%u.%u:%d\n",
- serv->sv_name,
+ serv->sv_name,
NIPQUAD(sin.sin_addr.s_addr), ntohs(sin.sin_port));
}
struct svc_sock *svsk = rqstp->rq_sock;
struct svc_serv *serv = svsk->sk_server;
int len;
- struct kvec vec[RPCSVC_MAXPAGES];
+ struct kvec *vec;
int pnum, vlen;
dprintk("svc: tcp_recv %p data %d conn %d close %d\n",
return 0;
}
- if (test_bit(SK_CONN, &svsk->sk_flags)) {
+ if (svsk->sk_sk->sk_state == TCP_LISTEN) {
svc_tcp_accept(svsk);
svc_sock_received(svsk);
return 0;
* on the number of threads which will access the socket.
*
* rcvbuf just needs to be able to hold a few requests.
- * Normally they will be removed from the queue
+ * Normally they will be removed from the queue
* as soon a a complete request arrives.
*/
svc_sock_setbufsize(svsk->sk_sock,
- (serv->sv_nrthreads+3) * serv->sv_bufsz,
- 3 * serv->sv_bufsz);
+ (serv->sv_nrthreads+3) * serv->sv_max_mesg,
+ 3 * serv->sv_max_mesg);
clear_bit(SK_DATA, &svsk->sk_flags);
if (len < want) {
dprintk("svc: short recvfrom while reading record length (%d of %lu)\n",
- len, want);
+ len, want);
svc_sock_received(svsk);
return -EAGAIN; /* record header not complete */
}
* bit set in the fragment length header.
* But apparently no known nfs clients send fragmented
* records. */
- printk(KERN_NOTICE "RPC: bad TCP reclen 0x%08lx (non-terminal)\n",
- (unsigned long) svsk->sk_reclen);
+ if (net_ratelimit())
+ printk(KERN_NOTICE "RPC: bad TCP reclen 0x%08lx"
+ " (non-terminal)\n",
+ (unsigned long) svsk->sk_reclen);
goto err_delete;
}
svsk->sk_reclen &= 0x7fffffff;
dprintk("svc: TCP record, %d bytes\n", svsk->sk_reclen);
- if (svsk->sk_reclen > serv->sv_bufsz) {
- printk(KERN_NOTICE "RPC: bad TCP reclen 0x%08lx (large)\n",
- (unsigned long) svsk->sk_reclen);
+ if (svsk->sk_reclen > serv->sv_max_mesg) {
+ if (net_ratelimit())
+ printk(KERN_NOTICE "RPC: bad TCP reclen 0x%08lx"
+ " (large)\n",
+ (unsigned long) svsk->sk_reclen);
goto err_delete;
}
}
len = svsk->sk_reclen;
set_bit(SK_DATA, &svsk->sk_flags);
+ vec = rqstp->rq_vec;
vec[0] = rqstp->rq_arg.head[0];
vlen = PAGE_SIZE;
pnum = 1;
while (vlen < len) {
- vec[pnum].iov_base = page_address(rqstp->rq_argpages[rqstp->rq_argused++]);
+ vec[pnum].iov_base = page_address(rqstp->rq_pages[pnum]);
vec[pnum].iov_len = PAGE_SIZE;
pnum++;
vlen += PAGE_SIZE;
}
+ rqstp->rq_respages = &rqstp->rq_pages[pnum];
/* Now receive data */
len = svc_recvfrom(rqstp, vec, pnum, len);
rqstp->rq_sock->sk_server->sv_name,
(sent<0)?"got error":"sent only",
sent, xbufp->len);
- svc_delete_socket(rqstp->rq_sock);
+ set_bit(SK_CLOSE, &rqstp->rq_sock->sk_flags);
+ svc_sock_enqueue(rqstp->rq_sock);
sent = -EAGAIN;
}
return sent;
tp->nonagle = 1; /* disable Nagle's algorithm */
/* initialise setting must have enough space to
- * receive and respond to one request.
+ * receive and respond to one request.
* svc_tcp_recvfrom will re-adjust if necessary
*/
svc_sock_setbufsize(svsk->sk_sock,
- 3 * svsk->sk_server->sv_bufsz,
- 3 * svsk->sk_server->sv_bufsz);
+ 3 * svsk->sk_server->sv_max_mesg,
+ 3 * svsk->sk_server->sv_max_mesg);
set_bit(SK_CHNGBUF, &svsk->sk_flags);
set_bit(SK_DATA, &svsk->sk_flags);
- if (sk->sk_state != TCP_ESTABLISHED)
+ if (sk->sk_state != TCP_ESTABLISHED)
set_bit(SK_CLOSE, &svsk->sk_flags);
}
}
spin_lock_bh(&serv->sv_lock);
list_for_each(le, &serv->sv_permsocks) {
- struct svc_sock *svsk =
+ struct svc_sock *svsk =
list_entry(le, struct svc_sock, sk_list);
set_bit(SK_CHNGBUF, &svsk->sk_flags);
}
struct svc_sock *svsk =NULL;
struct svc_serv *serv = rqstp->rq_server;
struct svc_pool *pool = rqstp->rq_pool;
- int len;
+ int len, i;
int pages;
struct xdr_buf *arg;
DECLARE_WAITQUEUE(wait, current);
rqstp, timeout);
if (rqstp->rq_sock)
- printk(KERN_ERR
+ printk(KERN_ERR
"svc_recv: service %p, socket not NULL!\n",
rqstp);
if (waitqueue_active(&rqstp->rq_wait))
- printk(KERN_ERR
+ printk(KERN_ERR
"svc_recv: service %p, wait queue active!\n",
rqstp);
- /* Initialize the buffers */
- /* first reclaim pages that were moved to response list */
- svc_pushback_allpages(rqstp);
/* now allocate needed pages. If we get a failure, sleep briefly */
- pages = 2 + (serv->sv_bufsz + PAGE_SIZE -1) / PAGE_SIZE;
- while (rqstp->rq_arghi < pages) {
- struct page *p = alloc_page(GFP_KERNEL);
- if (!p) {
- schedule_timeout_uninterruptible(msecs_to_jiffies(500));
- continue;
+ pages = (serv->sv_max_mesg + PAGE_SIZE) / PAGE_SIZE;
+ for (i=0; i < pages ; i++)
+ while (rqstp->rq_pages[i] == NULL) {
+ struct page *p = alloc_page(GFP_KERNEL);
+ if (!p)
+ schedule_timeout_uninterruptible(msecs_to_jiffies(500));
+ rqstp->rq_pages[i] = p;
}
- rqstp->rq_argpages[rqstp->rq_arghi++] = p;
- }
+ rqstp->rq_pages[i++] = NULL; /* this might be seen in nfs_read_actor */
+ BUG_ON(pages >= RPCSVC_MAXPAGES);
/* Make arg->head point to first page and arg->pages point to rest */
arg = &rqstp->rq_arg;
- arg->head[0].iov_base = page_address(rqstp->rq_argpages[0]);
+ arg->head[0].iov_base = page_address(rqstp->rq_pages[0]);
arg->head[0].iov_len = PAGE_SIZE;
- rqstp->rq_argused = 1;
- arg->pages = rqstp->rq_argpages + 1;
+ arg->pages = rqstp->rq_pages + 1;
arg->page_base = 0;
/* save at least one page for response */
arg->page_len = (pages-2)*PAGE_SIZE;
if ((svsk = svc_sock_dequeue(pool)) != NULL) {
rqstp->rq_sock = svsk;
atomic_inc(&svsk->sk_inuse);
- rqstp->rq_reserved = serv->sv_bufsz;
+ rqstp->rq_reserved = serv->sv_max_mesg;
atomic_add(rqstp->rq_reserved, &svsk->sk_reserved);
} else {
/* No data pending. Go to sleep */
return len;
}
-/*
+/*
* Drop request
*/
void
svsk->sk_odata = inet->sk_data_ready;
svsk->sk_owspace = inet->sk_write_space;
svsk->sk_server = serv;
- atomic_set(&svsk->sk_inuse, 0);
+ atomic_set(&svsk->sk_inuse, 1);
svsk->sk_lastrecv = get_seconds();
spin_lock_init(&svsk->sk_defer_lock);
INIT_LIST_HEAD(&svsk->sk_deferred);
if ((error = sock_create_kern(PF_INET, type, protocol, &sock)) < 0)
return error;
+ svc_reclassify_socket(sock);
+
if (type == SOCK_STREAM)
sock->sk->sk_reuse = 1; /* allow address reuse */
error = kernel_bind(sock, (struct sockaddr *) sin,
/*
* Remove a dead socket
*/
-void
+static void
svc_delete_socket(struct svc_sock *svsk)
{
struct svc_serv *serv;
if (!test_and_set_bit(SK_DETACHED, &svsk->sk_flags))
list_del_init(&svsk->sk_list);
- /*
+ /*
* We used to delete the svc_sock from whichever list
* it's sk_ready node was on, but we don't actually
* need to. This is because the only time we're called
* while still attached to a queue, the queue itself
* is about to be destroyed (in svc_destroy).
*/
- if (!test_and_set_bit(SK_DEAD, &svsk->sk_flags))
+ if (!test_and_set_bit(SK_DEAD, &svsk->sk_flags)) {
+ BUG_ON(atomic_read(&svsk->sk_inuse)<2);
+ atomic_dec(&svsk->sk_inuse);
if (test_bit(SK_TEMP, &svsk->sk_flags))
serv->sv_tmpcnt--;
-
- if (!atomic_read(&svsk->sk_inuse)) {
- spin_unlock_bh(&serv->sv_lock);
- if (svsk->sk_sock->file)
- sockfd_put(svsk->sk_sock);
- else
- sock_release(svsk->sk_sock);
- kfree(svsk);
- } else {
- spin_unlock_bh(&serv->sv_lock);
- dprintk(KERN_NOTICE "svc: server socket destroy delayed\n");
- /* svsk->sk_server = NULL; */
}
+
+ spin_unlock_bh(&serv->sv_lock);
+}
+
+void svc_close_socket(struct svc_sock *svsk)
+{
+ set_bit(SK_CLOSE, &svsk->sk_flags);
+ if (test_and_set_bit(SK_BUSY, &svsk->sk_flags))
+ /* someone else will have to effect the close */
+ return;
+
+ atomic_inc(&svsk->sk_inuse);
+ svc_delete_socket(svsk);
+ clear_bit(SK_BUSY, &svsk->sk_flags);
+ svc_sock_put(svsk);
}
/*
}
/*
- * Handle defer and revisit of requests
+ * Handle defer and revisit of requests
*/
static void svc_revisit(struct cache_deferred_req *dreq, int too_many)
rqstp->rq_prot = dr->prot;
rqstp->rq_addr = dr->addr;
rqstp->rq_daddr = dr->daddr;
+ rqstp->rq_respages = rqstp->rq_pages;
return dr->argslen<<2;
}
static struct svc_deferred_req *svc_deferred_dequeue(struct svc_sock *svsk)
{
struct svc_deferred_req *dr = NULL;
-
+
if (!test_bit(SK_DEFERRED, &svsk->sk_flags))
return NULL;
spin_lock_bh(&svsk->sk_defer_lock);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff