summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/Kconfig1
-rw-r--r--net/Makefile1
-rw-r--r--net/core/dev.c16
-rw-r--r--net/core/skbuff.c2
-rw-r--r--net/dns_resolver/Kconfig27
-rw-r--r--net/dns_resolver/Makefile7
-rw-r--r--net/dns_resolver/dns_key.c293
-rw-r--r--net/dns_resolver/dns_query.c165
-rw-r--r--net/dns_resolver/internal.h44
-rw-r--r--net/ipv4/datagram.c5
-rw-r--r--net/ipv4/fib_frontend.c15
-rw-r--r--net/ipv4/fib_trie.c8
-rw-r--r--net/ipv4/route.c7
-rw-r--r--net/ipv4/udp.c44
-rw-r--r--net/ipv6/datagram.c7
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c80
-rw-r--r--net/ipv6/reassembly.c71
-rw-r--r--net/ipv6/udp.c10
-rw-r--r--net/irda/irlan/irlan_common.c2
-rw-r--r--net/mac80211/rate.c2
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c1
-rw-r--r--net/netfilter/ipvs/ip_vs_ftp.c6
-rw-r--r--net/netfilter/ipvs/ip_vs_xmit.c18
-rw-r--r--net/rxrpc/ar-internal.h16
-rw-r--r--net/sctp/sm_statefuns.c46
-rw-r--r--net/sunrpc/Kconfig9
-rw-r--r--net/sunrpc/auth.c162
-rw-r--r--net/sunrpc/auth_generic.c23
-rw-r--r--net/sunrpc/auth_gss/auth_gss.c29
-rw-r--r--net/sunrpc/auth_null.c2
-rw-r--r--net/sunrpc/auth_unix.c21
-rw-r--r--net/sunrpc/cache.c8
-rw-r--r--net/sunrpc/clnt.c182
-rw-r--r--net/sunrpc/sched.c104
-rw-r--r--net/sunrpc/sunrpc_syms.c16
-rw-r--r--net/sunrpc/xprt.c3
-rw-r--r--net/sunrpc/xprtrdma/rpc_rdma.c2
-rw-r--r--net/sunrpc/xprtrdma/verbs.c22
-rw-r--r--net/sunrpc/xprtsock.c54
-rw-r--r--net/unix/af_unix.c15
40 files changed, 1096 insertions, 450 deletions
diff --git a/net/Kconfig b/net/Kconfig
index e24fa0873f32..e330594d3709 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -213,6 +213,7 @@ source "net/phonet/Kconfig"
source "net/ieee802154/Kconfig"
source "net/sched/Kconfig"
source "net/dcb/Kconfig"
+source "net/dns_resolver/Kconfig"
config RPS
boolean
diff --git a/net/Makefile b/net/Makefile
index 41d420070a38..ea60fbce9b1b 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -67,3 +67,4 @@ ifeq ($(CONFIG_NET),y)
obj-$(CONFIG_SYSCTL) += sysctl_net.o
endif
obj-$(CONFIG_WIMAX) += wimax/
+obj-$(CONFIG_DNS_RESOLVER) += dns_resolver/
diff --git a/net/core/dev.c b/net/core/dev.c
index 3721fbb9a83c..b9b22a3c4c8f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2058,16 +2058,16 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev,
struct sk_buff *skb)
{
int queue_index;
- struct sock *sk = skb->sk;
+ const struct net_device_ops *ops = dev->netdev_ops;
- queue_index = sk_tx_queue_get(sk);
- if (queue_index < 0) {
- const struct net_device_ops *ops = dev->netdev_ops;
+ if (ops->ndo_select_queue) {
+ queue_index = ops->ndo_select_queue(dev, skb);
+ queue_index = dev_cap_txqueue(dev, queue_index);
+ } else {
+ struct sock *sk = skb->sk;
+ queue_index = sk_tx_queue_get(sk);
+ if (queue_index < 0) {
- if (ops->ndo_select_queue) {
- queue_index = ops->ndo_select_queue(dev, skb);
- queue_index = dev_cap_txqueue(dev, queue_index);
- } else {
queue_index = 0;
if (dev->real_num_tx_queues > 1)
queue_index = skb_tx_hash(dev, skb);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 26396ff67cf9..c83b421341c0 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2706,7 +2706,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
} else if (skb_gro_len(p) != pinfo->gso_size)
return -E2BIG;
- headroom = NET_SKB_PAD + NET_IP_ALIGN;
+ headroom = skb_headroom(p);
nskb = alloc_skb(headroom + skb_gro_offset(p), GFP_ATOMIC);
if (unlikely(!nskb))
return -ENOMEM;
diff --git a/net/dns_resolver/Kconfig b/net/dns_resolver/Kconfig
new file mode 100644
index 000000000000..50d49f7e0472
--- /dev/null
+++ b/net/dns_resolver/Kconfig
@@ -0,0 +1,27 @@
+#
+# Configuration for DNS Resolver
+#
+config DNS_RESOLVER
+ tristate "DNS Resolver support"
+ depends on NET && KEYS
+ help
+ Saying Y here will include support for the DNS Resolver key type
+ which can be used to make upcalls to perform DNS lookups in
+ userspace.
+
+ DNS Resolver is used to query DNS server for information. Examples
+ being resolving a UNC hostname element to an IP address for CIFS or
+ performing a DNS query for AFSDB records so that AFS can locate a
+ cell's volume location database servers.
+
+ DNS Resolver is used by the CIFS and AFS modules, and would support
+ SMB2 later. DNS Resolver is supported by the userspace upcall
+ helper "/sbin/dns.resolver" via /etc/request-key.conf.
+
+ See <file:Documentation/networking/dns_resolver.txt> for further
+ information.
+
+ To compile this as a module, choose M here: the module will be called
+ dnsresolver.
+
+ If unsure, say N.
diff --git a/net/dns_resolver/Makefile b/net/dns_resolver/Makefile
new file mode 100644
index 000000000000..c0ef4e71dc49
--- /dev/null
+++ b/net/dns_resolver/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the Linux DNS Resolver.
+#
+
+obj-$(CONFIG_DNS_RESOLVER) += dns_resolver.o
+
+dns_resolver-objs := dns_key.o dns_query.o
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
new file mode 100644
index 000000000000..739435a6af39
--- /dev/null
+++ b/net/dns_resolver/dns_key.c
@@ -0,0 +1,293 @@
+/* Key type used to cache DNS lookups made by the kernel
+ *
+ * See Documentation/networking/dns_resolver.txt
+ *
+ * Copyright (c) 2007 Igor Mammedov
+ * Author(s): Igor Mammedov (niallain@gmail.com)
+ * Steve French (sfrench@us.ibm.com)
+ * Wang Lei (wang840925@gmail.com)
+ * David Howells (dhowells@redhat.com)
+ *
+ * This library is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation; either version 2.1 of the License, or
+ * (at your option) any later version.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
+ * the GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with this library; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/keyctl.h>
+#include <linux/err.h>
+#include <linux/seq_file.h>
+#include <keys/dns_resolver-type.h>
+#include <keys/user-type.h>
+#include "internal.h"
+
+MODULE_DESCRIPTION("DNS Resolver");
+MODULE_AUTHOR("Wang Lei");
+MODULE_LICENSE("GPL");
+
+unsigned dns_resolver_debug;
+module_param_named(debug, dns_resolver_debug, uint, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(debug, "DNS Resolver debugging mask");
+
+const struct cred *dns_resolver_cache;
+
+#define DNS_ERRORNO_OPTION "dnserror"
+
+/*
+ * Instantiate a user defined key for dns_resolver.
+ *
+ * The data must be a NUL-terminated string, with the NUL char accounted in
+ * datalen.
+ *
+ * If the data contains a '#' characters, then we take the clause after each
+ * one to be an option of the form 'key=value'. The actual data of interest is
+ * the string leading up to the first '#'. For instance:
+ *
+ * "ip1,ip2,...#foo=bar"
+ */
+static int
+dns_resolver_instantiate(struct key *key, const void *_data, size_t datalen)
+{
+ struct user_key_payload *upayload;
+ unsigned long derrno;
+ int ret;
+ size_t result_len = 0;
+ const char *data = _data, *end, *opt;
+
+ kenter("%%%d,%s,'%s',%zu",
+ key->serial, key->description, data, datalen);
+
+ if (datalen <= 1 || !data || data[datalen - 1] != '\0')
+ return -EINVAL;
+ datalen--;
+
+ /* deal with any options embedded in the data */
+ end = data + datalen;
+ opt = memchr(data, '#', datalen);
+ if (!opt) {
+ /* no options: the entire data is the result */
+ kdebug("no options");
+ result_len = datalen;
+ } else {
+ const char *next_opt;
+
+ result_len = opt - data;
+ opt++;
+ kdebug("options: '%s'", opt);
+ do {
+ const char *eq;
+ int opt_len, opt_nlen, opt_vlen, tmp;
+
+ next_opt = memchr(opt, '#', end - opt) ?: end;
+ opt_len = next_opt - opt;
+ if (!opt_len) {
+ printk(KERN_WARNING
+ "Empty option to dns_resolver key %d\n",
+ key->serial);
+ return -EINVAL;
+ }
+
+ eq = memchr(opt, '=', opt_len) ?: end;
+ opt_nlen = eq - opt;
+ eq++;
+ opt_vlen = next_opt - eq; /* will be -1 if no value */
+
+ tmp = opt_vlen >= 0 ? opt_vlen : 0;
+ kdebug("option '%*.*s' val '%*.*s'",
+ opt_nlen, opt_nlen, opt, tmp, tmp, eq);
+
+ /* see if it's an error number representing a DNS error
+ * that's to be recorded as the result in this key */
+ if (opt_nlen == sizeof(DNS_ERRORNO_OPTION) - 1 &&
+ memcmp(opt, DNS_ERRORNO_OPTION, opt_nlen) == 0) {
+ kdebug("dns error number option");
+ if (opt_vlen <= 0)
+ goto bad_option_value;
+
+ ret = strict_strtoul(eq, 10, &derrno);
+ if (ret < 0)
+ goto bad_option_value;
+
+ if (derrno < 1 || derrno > 511)
+ goto bad_option_value;
+
+ kdebug("dns error no. = %lu", derrno);
+ key->type_data.x[0] = -derrno;
+ continue;
+ }
+
+ bad_option_value:
+ printk(KERN_WARNING
+ "Option '%*.*s' to dns_resolver key %d:"
+ " bad/missing value\n",
+ opt_nlen, opt_nlen, opt, key->serial);
+ return -EINVAL;
+ } while (opt = next_opt + 1, opt < end);
+ }
+
+ /* don't cache the result if we're caching an error saying there's no
+ * result */
+ if (key->type_data.x[0]) {
+ kleave(" = 0 [h_error %ld]", key->type_data.x[0]);
+ return 0;
+ }
+
+ kdebug("store result");
+ ret = key_payload_reserve(key, result_len);
+ if (ret < 0)
+ return -EINVAL;
+
+ upayload = kmalloc(sizeof(*upayload) + result_len + 1, GFP_KERNEL);
+ if (!upayload) {
+ kleave(" = -ENOMEM");
+ return -ENOMEM;
+ }
+
+ upayload->datalen = result_len;
+ memcpy(upayload->data, data, result_len);
+ upayload->data[result_len] = '\0';
+ rcu_assign_pointer(key->payload.data, upayload);
+
+ kleave(" = 0");
+ return 0;
+}
+
+/*
+ * The description is of the form "[<type>:]<domain_name>"
+ *
+ * The domain name may be a simple name or an absolute domain name (which
+ * should end with a period). The domain name is case-independent.
+ */
+static int
+dns_resolver_match(const struct key *key, const void *description)
+{
+ int slen, dlen, ret = 0;
+ const char *src = key->description, *dsp = description;
+
+ kenter("%s,%s", src, dsp);
+
+ if (!src || !dsp)
+ goto no_match;
+
+ if (strcasecmp(src, dsp) == 0)
+ goto matched;
+
+ slen = strlen(src);
+ dlen = strlen(dsp);
+ if (slen <= 0 || dlen <= 0)
+ goto no_match;
+ if (src[slen - 1] == '.')
+ slen--;
+ if (dsp[dlen - 1] == '.')
+ dlen--;
+ if (slen != dlen || strncasecmp(src, dsp, slen) != 0)
+ goto no_match;
+
+matched:
+ ret = 1;
+no_match:
+ kleave(" = %d", ret);
+ return ret;
+}
+
+/*
+ * Describe a DNS key
+ */
+static void dns_resolver_describe(const struct key *key, struct seq_file *m)
+{
+ int err = key->type_data.x[0];
+
+ seq_puts(m, key->description);
+ if (err)
+ seq_printf(m, ": %d", err);
+ else
+ seq_printf(m, ": %u", key->datalen);
+}
+
+struct key_type key_type_dns_resolver = {
+ .name = "dns_resolver",
+ .instantiate = dns_resolver_instantiate,
+ .match = dns_resolver_match,
+ .revoke = user_revoke,
+ .destroy = user_destroy,
+ .describe = dns_resolver_describe,
+ .read = user_read,
+};
+
+static int __init init_dns_resolver(void)
+{
+ struct cred *cred;
+ struct key *keyring;
+ int ret;
+
+ printk(KERN_NOTICE "Registering the %s key type\n",
+ key_type_dns_resolver.name);
+
+ /* create an override credential set with a special thread keyring in
+ * which DNS requests are cached
+ *
+ * this is used to prevent malicious redirections from being installed
+ * with add_key().
+ */
+ cred = prepare_kernel_cred(NULL);
+ if (!cred)
+ return -ENOMEM;
+
+ keyring = key_alloc(&key_type_keyring, ".dns_resolver", 0, 0, cred,
+ (KEY_POS_ALL & ~KEY_POS_SETATTR) |
+ KEY_USR_VIEW | KEY_USR_READ,
+ KEY_ALLOC_NOT_IN_QUOTA);
+ if (IS_ERR(keyring)) {
+ ret = PTR_ERR(keyring);
+ goto failed_put_cred;
+ }
+
+ ret = key_instantiate_and_link(keyring, NULL, 0, NULL, NULL);
+ if (ret < 0)
+ goto failed_put_key;
+
+ ret = register_key_type(&key_type_dns_resolver);
+ if (ret < 0)
+ goto failed_put_key;
+
+ /* instruct request_key() to use this special keyring as a cache for
+ * the results it looks up */
+ cred->thread_keyring = keyring;
+ cred->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING;
+ dns_resolver_cache = cred;
+
+ kdebug("DNS resolver keyring: %d\n", key_serial(keyring));
+ return 0;
+
+failed_put_key:
+ key_put(keyring);
+failed_put_cred:
+ put_cred(cred);
+ return ret;
+}
+
+static void __exit exit_dns_resolver(void)
+{
+ key_revoke(dns_resolver_cache->thread_keyring);
+ unregister_key_type(&key_type_dns_resolver);
+ put_cred(dns_resolver_cache);
+ printk(KERN_NOTICE "Unregistered %s key type\n",
+ key_type_dns_resolver.name);
+}
+
+module_init(init_dns_resolver)
+module_exit(exit_dns_resolver)
+MODULE_LICENSE("GPL");
diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c
new file mode 100644
index 000000000000..c32be292c7e3
--- /dev/null
+++ b/net/dns_resolver/dns_query.c
@@ -0,0 +1,165 @@
+/* Upcall routine, designed to work as a key type and working through
+ * /sbin/request-key to contact userspace when handling DNS queries.
+ *
+ * See Documentation/networking/dns_resolver.txt
+ *
+ * Copyright (c) 2007 Igor Mammedov
+ * Author(s): Igor Mammedov (niallain@gmail.com)
+ * Steve French (sfrench@us.ibm.com)
+ * Wang Lei (wang840925@gmail.com)
+ * David Howells (dhowells@redhat.com)
+ *
+ * The upcall wrapper used to make an arbitrary DNS query.
+ *
+ * This function requires the appropriate userspace tool dns.upcall to be
+ * installed and something like the following lines should be added to the
+ * /etc/request-key.conf file:
+ *
+ * create dns_resolver * * /sbin/dns.upcall %k
+ *
+ * For example to use this module to query AFSDB RR:
+ *
+ * create dns_resolver afsdb:* * /sbin/dns.afsdb %k
+ *
+ * This library is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation; either version 2.1 of the License, or
+ * (at your option) any later version.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
+ * the GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with this library; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/dns_resolver.h>
+#include <linux/err.h>
+#include <keys/dns_resolver-type.h>
+#include <keys/user-type.h>
+
+#include "internal.h"
+
+/**
+ * dns_query - Query the DNS
+ * @type: Query type (or NULL for straight host->IP lookup)
+ * @name: Name to look up
+ * @namelen: Length of name
+ * @options: Request options (or NULL if no options)
+ * @_result: Where to place the returned data.
+ * @_expiry: Where to store the result expiry time (or NULL)
+ *
+ * The data will be returned in the pointer at *result, and the caller is
+ * responsible for freeing it.
+ *
+ * The description should be of the form "[<query_type>:]<domain_name>", and
+ * the options need to be appropriate for the query type requested. If no
+ * query_type is given, then the query is a straight hostname to IP address
+ * lookup.
+ *
+ * The DNS resolution lookup is performed by upcalling to userspace by way of
+ * requesting a key of type dns_resolver.
+ *
+ * Returns the size of the result on success, -ve error code otherwise.
+ */
+int dns_query(const char *type, const char *name, size_t namelen,
+ const char *options, char **_result, time_t *_expiry)
+{
+ struct key *rkey;
+ struct user_key_payload *upayload;
+ const struct cred *saved_cred;
+ size_t typelen, desclen;
+ char *desc, *cp;
+ int ret, len;
+
+ kenter("%s,%*.*s,%zu,%s",
+ type, (int)namelen, (int)namelen, name, namelen, options);
+
+ if (!name || namelen == 0 || !_result)
+ return -EINVAL;
+
+ /* construct the query key description as "[<type>:]<name>" */
+ typelen = 0;
+ desclen = 0;
+ if (type) {
+ typelen = strlen(type);
+ if (typelen < 1)
+ return -EINVAL;
+ desclen += typelen + 1;
+ }
+
+ if (!namelen)
+ namelen = strlen(name);
+ if (namelen < 3)
+ return -EINVAL;
+ desclen += namelen + 1;
+
+ desc = kmalloc(desclen, GFP_KERNEL);
+ if (!desc)
+ return -ENOMEM;
+
+ cp = desc;
+ if (type) {
+ memcpy(cp, type, typelen);
+ cp += typelen;
+ *cp++ = ':';
+ }
+ memcpy(cp, name, namelen);
+ cp += namelen;
+ *cp = '\0';
+
+ if (!options)
+ options = "";
+ kdebug("call request_key(,%s,%s)", desc, options);
+
+ /* make the upcall, using special credentials to prevent the use of
+ * add_key() to preinstall malicious redirections
+ */
+ saved_cred = override_creds(dns_resolver_cache);
+ rkey = request_key(&key_type_dns_resolver, desc, options);
+ revert_creds(saved_cred);
+ kfree(desc);
+ if (IS_ERR(rkey)) {
+ ret = PTR_ERR(rkey);
+ goto out;
+ }
+
+ down_read(&rkey->sem);
+ rkey->perm |= KEY_USR_VIEW;
+
+ ret = key_validate(rkey);
+ if (ret < 0)
+ goto put;
+
+ /* If the DNS server gave an error, return that to the caller */
+ ret = rkey->type_data.x[0];
+ if (ret)
+ goto put;
+
+ upayload = rcu_dereference_protected(rkey->payload.data,
+ lockdep_is_held(&rkey->sem));
+ len = upayload->datalen;
+
+ ret = -ENOMEM;
+ *_result = kmalloc(len + 1, GFP_KERNEL);
+ if (!*_result)
+ goto put;
+
+ memcpy(*_result, upayload->data, len + 1);
+ if (_expiry)
+ *_expiry = rkey->expiry;
+
+ ret = len;
+put:
+ up_read(&rkey->sem);
+ key_put(rkey);
+out:
+ kleave(" = %d", ret);
+ return ret;
+}
+EXPORT_SYMBOL(dns_query);
diff --git a/net/dns_resolver/internal.h b/net/dns_resolver/internal.h
new file mode 100644
index 000000000000..189ca9e9b785
--- /dev/null
+++ b/net/dns_resolver/internal.h
@@ -0,0 +1,44 @@
+/*
+ * Copyright (c) 2010 Wang Lei
+ * Author(s): Wang Lei (wang840925@gmail.com). All Rights Reserved.
+ *
+ * Internal DNS Rsolver stuff
+ *
+ * This library is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation; either version 2.1 of the License, or
+ * (at your option) any later version.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
+ * the GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with this library; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+
+/*
+ * dns_key.c
+ */
+extern const struct cred *dns_resolver_cache;
+
+/*
+ * debug tracing
+ */
+extern unsigned dns_resolver_debug;
+
+#define kdebug(FMT, ...) \
+do { \
+ if (unlikely(dns_resolver_debug)) \
+ printk(KERN_DEBUG "[%-6.6s] "FMT"\n", \
+ current->comm, ##__VA_ARGS__); \
+} while (0)
+
+#define kenter(FMT, ...) kdebug("==> %s("FMT")", __func__, ##__VA_ARGS__)
+#define kleave(FMT, ...) kdebug("<== %s()"FMT"", __func__, ##__VA_ARGS__)
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index f0550941df7b..721a8a37b45c 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -62,8 +62,11 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
}
if (!inet->inet_saddr)
inet->inet_saddr = rt->rt_src; /* Update source address */
- if (!inet->inet_rcv_saddr)
+ if (!inet->inet_rcv_saddr) {
inet->inet_rcv_saddr = rt->rt_src;
+ if (sk->sk_prot->rehash)
+ sk->sk_prot->rehash(sk);
+ }
inet->inet_daddr = rt->rt_dst;
inet->inet_dport = usin->sin_port;
sk->sk_state = TCP_ESTABLISHED;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index a43968918350..7d02a9f999fa 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -246,6 +246,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
struct fib_result res;
int no_addr, rpf, accept_local;
+ bool dev_match;
int ret;
struct net *net;
@@ -273,12 +274,22 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
}
*spec_dst = FIB_RES_PREFSRC(res);
fib_combine_itag(itag, &res);
+ dev_match = false;
+
#ifdef CONFIG_IP_ROUTE_MULTIPATH
- if (FIB_RES_DEV(res) == dev || res.fi->fib_nhs > 1)
+ for (ret = 0; ret < res.fi->fib_nhs; ret++) {
+ struct fib_nh *nh = &res.fi->fib_nh[ret];
+
+ if (nh->nh_dev == dev) {
+ dev_match = true;
+ break;
+ }
+ }
#else
if (FIB_RES_DEV(res) == dev)
+ dev_match = true;
#endif
- {
+ if (dev_match) {
ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
fib_res_put(&res);
return ret;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 79d057a939ba..4a8e370862bc 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -186,7 +186,9 @@ static inline struct tnode *node_parent_rcu(struct node *node)
{
struct tnode *ret = node_parent(node);
- return rcu_dereference(ret);
+ return rcu_dereference_check(ret,
+ rcu_read_lock_held() ||
+ lockdep_rtnl_is_held());
}
/* Same as rcu_assign_pointer
@@ -1753,7 +1755,9 @@ static struct leaf *leaf_walk_rcu(struct tnode *p, struct node *c)
static struct leaf *trie_firstleaf(struct trie *t)
{
- struct tnode *n = (struct tnode *) rcu_dereference(t->trie);
+ struct tnode *n = (struct tnode *) rcu_dereference_check(t->trie,
+ rcu_read_lock_held() ||
+ lockdep_rtnl_is_held());
if (!n)
return NULL;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 3f56b6e6c6aa..6298f75d5e93 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2738,6 +2738,11 @@ slow_output:
}
EXPORT_SYMBOL_GPL(__ip_route_output_key);
+static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie)
+{
+ return NULL;
+}
+
static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
{
}
@@ -2746,7 +2751,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = {
.family = AF_INET,
.protocol = cpu_to_be16(ETH_P_IP),
.destroy = ipv4_dst_destroy,
- .check = ipv4_dst_check,
+ .check = ipv4_blackhole_dst_check,
.update_pmtu = ipv4_rt_blackhole_update_pmtu,
.entries = ATOMIC_INIT(0),
};
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 32e0bef60d0a..fb23c2e63b52 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1260,6 +1260,49 @@ void udp_lib_unhash(struct sock *sk)
}
EXPORT_SYMBOL(udp_lib_unhash);
+/*
+ * inet_rcv_saddr was changed, we must rehash secondary hash
+ */
+void udp_lib_rehash(struct sock *sk, u16 newhash)
+{
+ if (sk_hashed(sk)) {
+ struct udp_table *udptable = sk->sk_prot->h.udp_table;
+ struct udp_hslot *hslot, *hslot2, *nhslot2;
+
+ hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
+ nhslot2 = udp_hashslot2(udptable, newhash);
+ udp_sk(sk)->udp_portaddr_hash = newhash;
+ if (hslot2 != nhslot2) {
+ hslot = udp_hashslot(udptable, sock_net(sk),
+ udp_sk(sk)->udp_port_hash);
+ /* we must lock primary chain too */
+ spin_lock_bh(&hslot->lock);
+
+ spin_lock(&hslot2->lock);
+ hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node);
+ hslot2->count--;
+ spin_unlock(&hslot2->lock);
+
+ spin_lock(&nhslot2->lock);
+ hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
+ &nhslot2->head);
+ nhslot2->count++;
+ spin_unlock(&nhslot2->lock);
+
+ spin_unlock_bh(&hslot->lock);
+ }
+ }
+}
+EXPORT_SYMBOL(udp_lib_rehash);
+
+static void udp_v4_rehash(struct sock *sk)
+{
+ u16 new_hash = udp4_portaddr_hash(sock_net(sk),
+ inet_sk(sk)->inet_rcv_saddr,
+ inet_sk(sk)->inet_num);
+ udp_lib_rehash(sk, new_hash);
+}
+
static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
int rc;
@@ -1843,6 +1886,7 @@ struct proto udp_prot = {
.backlog_rcv = __udp_queue_rcv_skb,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
+ .rehash = udp_v4_rehash,
.get_port = udp_v4_get_port,
.memory_allocated = &udp_memory_allocated,
.sysctl_mem = sysctl_udp_mem,
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 7d929a22cbc2..ef371aa01ac5 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -105,9 +105,12 @@ ipv4_connected:
if (ipv6_addr_any(&np->saddr))
ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
- if (ipv6_addr_any(&np->rcv_saddr))
+ if (ipv6_addr_any(&np->rcv_saddr)) {
ipv6_addr_set_v4mapped(inet->inet_rcv_saddr,
&np->rcv_saddr);
+ if (sk->sk_prot->rehash)
+ sk->sk_prot->rehash(sk);
+ }
goto out;
}
@@ -181,6 +184,8 @@ ipv4_connected:
if (ipv6_addr_any(&np->rcv_saddr)) {
ipv6_addr_copy(&np->rcv_saddr, &fl.fl6_src);
inet->inet_rcv_saddr = LOOPBACK4_IPV6;
+ if (sk->sk_prot->rehash)
+ sk->sk_prot->rehash(sk);
}
ip6_dst_store(sk, dst,
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 13ef5bc05cf5..578f3c1a16db 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -113,14 +113,6 @@ static void nf_skb_free(struct sk_buff *skb)
kfree_skb(NFCT_FRAG6_CB(skb)->orig);
}
-/* Memory Tracking Functions. */
-static void frag_kfree_skb(struct sk_buff *skb)
-{
- atomic_sub(skb->truesize, &nf_init_frags.mem);
- nf_skb_free(skb);
- kfree_skb(skb);
-}
-
/* Destruction primitives. */
static __inline__ void fq_put(struct nf_ct_frag6_queue *fq)
@@ -282,66 +274,22 @@ static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb,
}
found:
- /* We found where to put this one. Check for overlap with
- * preceding fragment, and, if needed, align things so that
- * any overlaps are eliminated.
- */
- if (prev) {
- int i = (NFCT_FRAG6_CB(prev)->offset + prev->len) - offset;
-
- if (i > 0) {
- offset += i;
- if (end <= offset) {
- pr_debug("overlap\n");
- goto err;
- }
- if (!pskb_pull(skb, i)) {
- pr_debug("Can't pull\n");
- goto err;
- }
- if (skb->ip_summed != CHECKSUM_UNNECESSARY)
- skb->ip_summed = CHECKSUM_NONE;
- }
- }
-
- /* Look for overlap with succeeding segments.
- * If we can merge fragments, do it.
+ /* RFC5722, Section 4:
+ * When reassembling an IPv6 datagram, if
+ * one or more its constituent fragments is determined to be an
+ * overlapping fragment, the entire datagram (and any constituent
+ * fragments, including those not yet received) MUST be silently
+ * discarded.
*/
- while (next && NFCT_FRAG6_CB(next)->offset < end) {
- /* overlap is 'i' bytes */
- int i = end - NFCT_FRAG6_CB(next)->offset;
-
- if (i < next->len) {
- /* Eat head of the next overlapped fragment
- * and leave the loop. The next ones cannot overlap.
- */
- pr_debug("Eat head of the overlapped parts.: %d", i);
- if (!pskb_pull(next, i))
- goto err;
- /* next fragment */
- NFCT_FRAG6_CB(next)->offset += i;
- fq->q.meat -= i;
- if (next->ip_summed != CHECKSUM_UNNECESSARY)
- next->ip_summed = CHECKSUM_NONE;
- break;
- } else {
- struct sk_buff *free_it = next;
-
- /* Old fragmnet is completely overridden with
- * new one drop it.
- */
- next = next->next;
+ /* Check for overlap with preceding fragment. */
+ if (prev &&
+ (NFCT_FRAG6_CB(prev)->offset + prev->len) - offset > 0)
+ goto discard_fq;
- if (prev)
- prev->next = next;
- else
- fq->q.fragments = next;
-
- fq->q.meat -= free_it->len;
- frag_kfree_skb(free_it);
- }
- }
+ /* Look for overlap with succeeding segment. */
+ if (next && NFCT_FRAG6_CB(next)->offset < end)
+ goto discard_fq;
NFCT_FRAG6_CB(skb)->offset = offset;
@@ -371,6 +319,8 @@ found:
write_unlock(&nf_frags.lock);
return 0;
+discard_fq:
+ fq_kill(fq);
err:
return -1;
}
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 545c4141b755..64cfef1b0a4c 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -149,13 +149,6 @@ int ip6_frag_match(struct inet_frag_queue *q, void *a)
}
EXPORT_SYMBOL(ip6_frag_match);
-/* Memory Tracking Functions. */
-static void frag_kfree_skb(struct netns_frags *nf, struct sk_buff *skb)
-{
- atomic_sub(skb->truesize, &nf->mem);
- kfree_skb(skb);
-}
-
void ip6_frag_init(struct inet_frag_queue *q, void *a)
{
struct frag_queue *fq = container_of(q, struct frag_queue, q);
@@ -346,58 +339,22 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
}
found:
- /* We found where to put this one. Check for overlap with
- * preceding fragment, and, if needed, align things so that
- * any overlaps are eliminated.
+ /* RFC5722, Section 4:
+ * When reassembling an IPv6 datagram, if
+ * one or more its constituent fragments is determined to be an
+ * overlapping fragment, the entire datagram (and any constituent
+ * fragments, including those not yet received) MUST be silently
+ * discarded.
*/
- if (prev) {
- int i = (FRAG6_CB(prev)->offset + prev->len) - offset;
- if (i > 0) {
- offset += i;
- if (end <= offset)
- goto err;
- if (!pskb_pull(skb, i))
- goto err;
- if (skb->ip_summed != CHECKSUM_UNNECESSARY)
- skb->ip_summed = CHECKSUM_NONE;
- }
- }
+ /* Check for overlap with preceding fragment. */
+ if (prev &&
+ (FRAG6_CB(prev)->offset + prev->len) - offset > 0)
+ goto discard_fq;
- /* Look for overlap with succeeding segments.
- * If we can merge fragments, do it.
- */
- while (next && FRAG6_CB(next)->offset < end) {
- int i = end - FRAG6_CB(next)->offset; /* overlap is 'i' bytes */
-
- if (i < next->len) {
- /* Eat head of the next overlapped fragment
- * and leave the loop. The next ones cannot overlap.
- */
- if (!pskb_pull(next, i))
- goto err;
- FRAG6_CB(next)->offset += i; /* next fragment */
- fq->q.meat -= i;
- if (next->ip_summed != CHECKSUM_UNNECESSARY)
- next->ip_summed = CHECKSUM_NONE;
- break;
- } else {
- struct sk_buff *free_it = next;
-
- /* Old fragment is completely overridden with
- * new one drop it.
- */
- next = next->next;
-
- if (prev)
- prev->next = next;
- else
- fq->q.fragments = next;
-
- fq->q.meat -= free_it->len;
- frag_kfree_skb(fq->q.net, free_it);
- }
- }
+ /* Look for overlap with succeeding segment. */
+ if (next && FRAG6_CB(next)->offset < end)
+ goto discard_fq;
FRAG6_CB(skb)->offset = offset;
@@ -436,6 +393,8 @@ found:
write_unlock(&ip6_frags.lock);
return -1;
+discard_fq:
+ fq_kill(fq);
err:
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASMFAILS);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1dd1affdead2..5acb3560ff15 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -111,6 +111,15 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum)
return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal, hash2_nulladdr);
}
+static void udp_v6_rehash(struct sock *sk)
+{
+ u16 new_hash = udp6_portaddr_hash(sock_net(sk),
+ &inet6_sk(sk)->rcv_saddr,
+ inet_sk(sk)->inet_num);
+
+ udp_lib_rehash(sk, new_hash);
+}
+
static inline int compute_score(struct sock *sk, struct net *net,
unsigned short hnum,
struct in6_addr *saddr, __be16 sport,
@@ -1447,6 +1456,7 @@ struct proto udpv6_prot = {
.backlog_rcv = udpv6_queue_rcv_skb,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
+ .rehash = udp_v6_rehash,
.get_port = udp_v6_get_port,
.memory_allocated = &udp_memory_allocated,
.sysctl_mem = sysctl_udp_mem,
diff --git a/net/irda/irlan/irlan_common.c b/net/irda/irlan/irlan_common.c
index a788f9e9427d..6130f9d9dbe1 100644
--- a/net/irda/irlan/irlan_common.c
+++ b/net/irda/irlan/irlan_common.c
@@ -1102,7 +1102,7 @@ int irlan_extract_param(__u8 *buf, char *name, char *value, __u16 *len)
memcpy(&val_len, buf+n, 2); /* To avoid alignment problems */
le16_to_cpus(&val_len); n+=2;
- if (val_len > 1016) {
+ if (val_len >= 1016) {
IRDA_DEBUG(2, "%s(), parameter length to long\n", __func__ );
return -RSP_INVALID_COMMAND_FORMAT;
}
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index 6d0bd198af19..be04d46110fe 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -103,6 +103,7 @@ ieee80211_rate_control_ops_get(const char *name)
struct rate_control_ops *ops;
const char *alg_name;
+ kparam_block_sysfs_write(ieee80211_default_rc_algo);
if (!name)
alg_name = ieee80211_default_rc_algo;
else
@@ -120,6 +121,7 @@ ieee80211_rate_control_ops_get(const char *name)
/* try built-in one if specific alg requested but not found */
if (!ops && strlen(CONFIG_MAC80211_RC_DEFAULT))
ops = ieee80211_try_rate_control_ops_get(CONFIG_MAC80211_RC_DEFAULT);
+ kparam_unblock_sysfs_write(ieee80211_default_rc_algo);
return ops;
}
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 4f8ddba48011..4c2f89df5cce 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -924,6 +924,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
ip_vs_out_stats(cp, skb);
ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp);
+ ip_vs_update_conntrack(skb, cp, 0);
ip_vs_conn_put(cp);
skb->ipvs_property = 1;
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 33b329bfc2d2..7e9af5b76d9e 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -410,7 +410,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
union nf_inet_addr to;
__be16 port;
struct ip_vs_conn *n_cp;
- struct nf_conn *ct;
#ifdef CONFIG_IP_VS_IPV6
/* This application helper doesn't work with IPv6 yet,
@@ -497,11 +496,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
ip_vs_control_add(n_cp, cp);
}
- ct = (struct nf_conn *)skb->nfct;
- if (ct && ct != &nf_conntrack_untracked)
- ip_vs_expect_related(skb, ct, n_cp,
- IPPROTO_TCP, &n_cp->dport, 1);
-
/*
* Move tunnel to listen state
*/
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 21e1a5e9b9d3..49df6bea6a2d 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -349,8 +349,8 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
}
#endif
-static void
-ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp)
+void
+ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, int outin)
{
struct nf_conn *ct = (struct nf_conn *)skb->nfct;
struct nf_conntrack_tuple new_tuple;
@@ -365,11 +365,17 @@ ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp)
* real-server we will see RIP->DIP.
*/
new_tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
- new_tuple.src.u3 = cp->daddr;
+ if (outin)
+ new_tuple.src.u3 = cp->daddr;
+ else
+ new_tuple.dst.u3 = cp->vaddr;
/*
* This will also take care of UDP and other protocols.
*/
- new_tuple.src.u.tcp.port = cp->dport;
+ if (outin)
+ new_tuple.src.u.tcp.port = cp->dport;
+ else
+ new_tuple.dst.u.tcp.port = cp->vport;
nf_conntrack_alter_reply(ct, &new_tuple);
}
@@ -428,7 +434,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT");
- ip_vs_update_conntrack(skb, cp);
+ ip_vs_update_conntrack(skb, cp, 1);
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
@@ -506,7 +512,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT");
- ip_vs_update_conntrack(skb, cp);
+ ip_vs_update_conntrack(skb, cp, 1);
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 7043b294bb67..8e22bd345e71 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -597,12 +597,6 @@ extern unsigned rxrpc_debug;
#define dbgprintk(FMT,...) \
printk("[%-6.6s] "FMT"\n", current->comm ,##__VA_ARGS__)
-/* make sure we maintain the format strings, even when debugging is disabled */
-static inline __attribute__((format(printf,1,2)))
-void _dbprintk(const char *fmt, ...)
-{
-}
-
#define kenter(FMT,...) dbgprintk("==> %s("FMT")",__func__ ,##__VA_ARGS__)
#define kleave(FMT,...) dbgprintk("<== %s()"FMT"",__func__ ,##__VA_ARGS__)
#define kdebug(FMT,...) dbgprintk(" "FMT ,##__VA_ARGS__)
@@ -655,11 +649,11 @@ do { \
} while (0)
#else
-#define _enter(FMT,...) _dbprintk("==> %s("FMT")",__func__ ,##__VA_ARGS__)
-#define _leave(FMT,...) _dbprintk("<== %s()"FMT"",__func__ ,##__VA_ARGS__)
-#define _debug(FMT,...) _dbprintk(" "FMT ,##__VA_ARGS__)
-#define _proto(FMT,...) _dbprintk("### "FMT ,##__VA_ARGS__)
-#define _net(FMT,...) _dbprintk("@@@ "FMT ,##__VA_ARGS__)
+#define _enter(FMT,...) no_printk("==> %s("FMT")",__func__ ,##__VA_ARGS__)
+#define _leave(FMT,...) no_printk("<== %s()"FMT"",__func__ ,##__VA_ARGS__)
+#define _debug(FMT,...) no_printk(" "FMT ,##__VA_ARGS__)
+#define _proto(FMT,...) no_printk("### "FMT ,##__VA_ARGS__)
+#define _net(FMT,...) no_printk("@@@ "FMT ,##__VA_ARGS__)
#endif
/*
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 24b2cd555637..d344dc481ccc 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -1232,6 +1232,18 @@ out:
return 0;
}
+static bool list_has_sctp_addr(const struct list_head *list,
+ union sctp_addr *ipaddr)
+{
+ struct sctp_transport *addr;
+
+ list_for_each_entry(addr, list, transports) {
+ if (sctp_cmp_addr_exact(ipaddr, &addr->ipaddr))
+ return true;
+ }
+
+ return false;
+}
/* A restart is occurring, check to make sure no new addresses
* are being added as we may be under a takeover attack.
*/
@@ -1240,10 +1252,10 @@ static int sctp_sf_check_restart_addrs(const struct sctp_association *new_asoc,
struct sctp_chunk *init,
sctp_cmd_seq_t *commands)
{
- struct sctp_transport *new_addr, *addr;
- int found;
+ struct sctp_transport *new_addr;
+ int ret = 1;
- /* Implementor's Guide - Sectin 5.2.2
+ /* Implementor's Guide - Section 5.2.2
* ...
* Before responding the endpoint MUST check to see if the
* unexpected INIT adds new addresses to the association. If new
@@ -1254,31 +1266,19 @@ static int sctp_sf_check_restart_addrs(const struct sctp_association *new_asoc,
/* Search through all current addresses and make sure
* we aren't adding any new ones.
*/
- new_addr = NULL;
- found = 0;
-
list_for_each_entry(new_addr, &new_asoc->peer.transport_addr_list,
- transports) {
- found = 0;
- list_for_each_entry(addr, &asoc->peer.transport_addr_list,
- transports) {
- if (sctp_cmp_addr_exact(&new_addr->ipaddr,
- &addr->ipaddr)) {
- found = 1;
- break;
- }
- }
- if (!found)
+ transports) {
+ if (!list_has_sctp_addr(&asoc->peer.transport_addr_list,
+ &new_addr->ipaddr)) {
+ sctp_sf_send_restart_abort(&new_addr->ipaddr, init,
+ commands);
+ ret = 0;
break;
- }
-
- /* If a new address was added, ABORT the sender. */
- if (!found && new_addr) {
- sctp_sf_send_restart_abort(&new_addr->ipaddr, init, commands);
+ }
}
/* Return success if all addresses were found. */
- return found;
+ return ret;
}
/* Populate the verification/tie tags based on overlapping INIT
diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig
index 443c161eb8bd..3376d7657185 100644
--- a/net/sunrpc/Kconfig
+++ b/net/sunrpc/Kconfig
@@ -18,10 +18,11 @@ config SUNRPC_XPRT_RDMA
If unsure, say N.
config RPCSEC_GSS_KRB5
- tristate "Secure RPC: Kerberos V mechanism (EXPERIMENTAL)"
- depends on SUNRPC && EXPERIMENTAL
+ tristate
+ depends on SUNRPC && CRYPTO
+ prompt "Secure RPC: Kerberos V mechanism" if !(NFS_V4 || NFSD_V4)
+ default y
select SUNRPC_GSS
- select CRYPTO
select CRYPTO_MD5
select CRYPTO_DES
select CRYPTO_CBC
@@ -34,7 +35,7 @@ config RPCSEC_GSS_KRB5
available from http://linux-nfs.org/. In addition, user-space
Kerberos support should be installed.
- If unsure, say N.
+ If unsure, say Y.
config RPCSEC_GSS_SPKM3
tristate "Secure RPC: SPKM3 mechanism (EXPERIMENTAL)"
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 8dc47f1d0001..36cb66022a27 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -19,6 +19,15 @@
# define RPCDBG_FACILITY RPCDBG_AUTH
#endif
+#define RPC_CREDCACHE_DEFAULT_HASHBITS (4)
+struct rpc_cred_cache {
+ struct hlist_head *hashtable;
+ unsigned int hashbits;
+ spinlock_t lock;
+};
+
+static unsigned int auth_hashbits = RPC_CREDCACHE_DEFAULT_HASHBITS;
+
static DEFINE_SPINLOCK(rpc_authflavor_lock);
static const struct rpc_authops *auth_flavors[RPC_AUTH_MAXFLAVOR] = {
&authnull_ops, /* AUTH_NULL */
@@ -29,6 +38,47 @@ static const struct rpc_authops *auth_flavors[RPC_AUTH_MAXFLAVOR] = {
static LIST_HEAD(cred_unused);
static unsigned long number_cred_unused;
+#define MAX_HASHTABLE_BITS (10)
+static int param_set_hashtbl_sz(const char *val, const struct kernel_param *kp)
+{
+ unsigned long num;
+ unsigned int nbits;
+ int ret;
+
+ if (!val)
+ goto out_inval;
+ ret = strict_strtoul(val, 0, &num);
+ if (ret == -EINVAL)
+ goto out_inval;
+ nbits = fls(num);
+ if (num > (1U << nbits))
+ nbits++;
+ if (nbits > MAX_HASHTABLE_BITS || nbits < 2)
+ goto out_inval;
+ *(unsigned int *)kp->arg = nbits;
+ return 0;
+out_inval:
+ return -EINVAL;
+}
+
+static int param_get_hashtbl_sz(char *buffer, const struct kernel_param *kp)
+{
+ unsigned int nbits;
+
+ nbits = *(unsigned int *)kp->arg;
+ return sprintf(buffer, "%u", 1U << nbits);
+}
+
+#define param_check_hashtbl_sz(name, p) __param_check(name, p, unsigned int);
+
+static struct kernel_param_ops param_ops_hashtbl_sz = {
+ .set = param_set_hashtbl_sz,
+ .get = param_get_hashtbl_sz,
+};
+
+module_param_named(auth_hashtable_size, auth_hashbits, hashtbl_sz, 0644);
+MODULE_PARM_DESC(auth_hashtable_size, "RPC credential cache hashtable size");
+
static u32
pseudoflavor_to_flavor(u32 flavor) {
if (flavor >= RPC_AUTH_MAXFLAVOR)
@@ -145,16 +195,23 @@ int
rpcauth_init_credcache(struct rpc_auth *auth)
{
struct rpc_cred_cache *new;
- int i;
+ unsigned int hashsize;
new = kmalloc(sizeof(*new), GFP_KERNEL);
if (!new)
- return -ENOMEM;
- for (i = 0; i < RPC_CREDCACHE_NR; i++)
- INIT_HLIST_HEAD(&new->hashtable[i]);
+ goto out_nocache;
+ new->hashbits = auth_hashbits;
+ hashsize = 1U << new->hashbits;
+ new->hashtable = kcalloc(hashsize, sizeof(new->hashtable[0]), GFP_KERNEL);
+ if (!new->hashtable)
+ goto out_nohashtbl;
spin_lock_init(&new->lock);
auth->au_credcache = new;
return 0;
+out_nohashtbl:
+ kfree(new);
+out_nocache:
+ return -ENOMEM;
}
EXPORT_SYMBOL_GPL(rpcauth_init_credcache);
@@ -183,11 +240,12 @@ rpcauth_clear_credcache(struct rpc_cred_cache *cache)
LIST_HEAD(free);
struct hlist_head *head;
struct rpc_cred *cred;
+ unsigned int hashsize = 1U << cache->hashbits;
int i;
spin_lock(&rpc_credcache_lock);
spin_lock(&cache->lock);
- for (i = 0; i < RPC_CREDCACHE_NR; i++) {
+ for (i = 0; i < hashsize; i++) {
head = &cache->hashtable[i];
while (!hlist_empty(head)) {
cred = hlist_entry(head->first, struct rpc_cred, cr_hash);
@@ -216,6 +274,7 @@ rpcauth_destroy_credcache(struct rpc_auth *auth)
if (cache) {
auth->au_credcache = NULL;
rpcauth_clear_credcache(cache);
+ kfree(cache->hashtable);
kfree(cache);
}
}
@@ -297,7 +356,7 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred,
*entry, *new;
unsigned int nr;
- nr = hash_long(acred->uid, RPC_CREDCACHE_HASHBITS);
+ nr = hash_long(acred->uid, cache->hashbits);
rcu_read_lock();
hlist_for_each_entry_rcu(entry, pos, &cache->hashtable[nr], cr_hash) {
@@ -390,16 +449,16 @@ rpcauth_init_cred(struct rpc_cred *cred, const struct auth_cred *acred,
}
EXPORT_SYMBOL_GPL(rpcauth_init_cred);
-void
+struct rpc_cred *
rpcauth_generic_bind_cred(struct rpc_task *task, struct rpc_cred *cred, int lookupflags)
{
- task->tk_msg.rpc_cred = get_rpccred(cred);
dprintk("RPC: %5u holding %s cred %p\n", task->tk_pid,
cred->cr_auth->au_ops->au_name, cred);
+ return get_rpccred(cred);
}
EXPORT_SYMBOL_GPL(rpcauth_generic_bind_cred);
-static void
+static struct rpc_cred *
rpcauth_bind_root_cred(struct rpc_task *task, int lookupflags)
{
struct rpc_auth *auth = task->tk_client->cl_auth;
@@ -407,45 +466,43 @@ rpcauth_bind_root_cred(struct rpc_task *task, int lookupflags)
.uid = 0,
.gid = 0,
};
- struct rpc_cred *ret;
dprintk("RPC: %5u looking up %s cred\n",
task->tk_pid, task->tk_client->cl_auth->au_ops->au_name);
- ret = auth->au_ops->lookup_cred(auth, &acred, lookupflags);
- if (!IS_ERR(ret))
- task->tk_msg.rpc_cred = ret;
- else
- task->tk_status = PTR_ERR(ret);
+ return auth->au_ops->lookup_cred(auth, &acred, lookupflags);
}
-static void
+static struct rpc_cred *
rpcauth_bind_new_cred(struct rpc_task *task, int lookupflags)
{
struct rpc_auth *auth = task->tk_client->cl_auth;
- struct rpc_cred *ret;
dprintk("RPC: %5u looking up %s cred\n",
task->tk_pid, auth->au_ops->au_name);
- ret = rpcauth_lookupcred(auth, lookupflags);
- if (!IS_ERR(ret))
- task->tk_msg.rpc_cred = ret;
- else
- task->tk_status = PTR_ERR(ret);
+ return rpcauth_lookupcred(auth, lookupflags);
}
-void
+static int
rpcauth_bindcred(struct rpc_task *task, struct rpc_cred *cred, int flags)
{
+ struct rpc_rqst *req = task->tk_rqstp;
+ struct rpc_cred *new;
int lookupflags = 0;
if (flags & RPC_TASK_ASYNC)
lookupflags |= RPCAUTH_LOOKUP_NEW;
if (cred != NULL)
- cred->cr_ops->crbind(task, cred, lookupflags);
+ new = cred->cr_ops->crbind(task, cred, lookupflags);
else if (flags & RPC_TASK_ROOTCREDS)
- rpcauth_bind_root_cred(task, lookupflags);
+ new = rpcauth_bind_root_cred(task, lookupflags);
else
- rpcauth_bind_new_cred(task, lookupflags);
+ new = rpcauth_bind_new_cred(task, lookupflags);
+ if (IS_ERR(new))
+ return PTR_ERR(new);
+ if (req->rq_cred != NULL)
+ put_rpccred(req->rq_cred);
+ req->rq_cred = new;
+ return 0;
}
void
@@ -484,22 +541,10 @@ out_nodestroy:
}
EXPORT_SYMBOL_GPL(put_rpccred);
-void
-rpcauth_unbindcred(struct rpc_task *task)
-{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
-
- dprintk("RPC: %5u releasing %s cred %p\n",
- task->tk_pid, cred->cr_auth->au_ops->au_name, cred);
-
- put_rpccred(cred);
- task->tk_msg.rpc_cred = NULL;
-}
-
__be32 *
rpcauth_marshcred(struct rpc_task *task, __be32 *p)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
dprintk("RPC: %5u marshaling %s cred %p\n",
task->tk_pid, cred->cr_auth->au_ops->au_name, cred);
@@ -510,7 +555,7 @@ rpcauth_marshcred(struct rpc_task *task, __be32 *p)
__be32 *
rpcauth_checkverf(struct rpc_task *task, __be32 *p)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
dprintk("RPC: %5u validating %s cred %p\n",
task->tk_pid, cred->cr_auth->au_ops->au_name, cred);
@@ -522,7 +567,7 @@ int
rpcauth_wrap_req(struct rpc_task *task, kxdrproc_t encode, void *rqstp,
__be32 *data, void *obj)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
dprintk("RPC: %5u using %s cred %p to wrap rpc data\n",
task->tk_pid, cred->cr_ops->cr_name, cred);
@@ -536,7 +581,7 @@ int
rpcauth_unwrap_resp(struct rpc_task *task, kxdrproc_t decode, void *rqstp,
__be32 *data, void *obj)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
dprintk("RPC: %5u using %s cred %p to unwrap rpc data\n",
task->tk_pid, cred->cr_ops->cr_name, cred);
@@ -550,13 +595,21 @@ rpcauth_unwrap_resp(struct rpc_task *task, kxdrproc_t decode, void *rqstp,
int
rpcauth_refreshcred(struct rpc_task *task)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
int err;
+ cred = task->tk_rqstp->rq_cred;
+ if (cred == NULL) {
+ err = rpcauth_bindcred(task, task->tk_msg.rpc_cred, task->tk_flags);
+ if (err < 0)
+ goto out;
+ cred = task->tk_rqstp->rq_cred;
+ };
dprintk("RPC: %5u refreshing %s cred %p\n",
task->tk_pid, cred->cr_auth->au_ops->au_name, cred);
err = cred->cr_ops->crrefresh(task);
+out:
if (err < 0)
task->tk_status = err;
return err;
@@ -565,7 +618,7 @@ rpcauth_refreshcred(struct rpc_task *task)
void
rpcauth_invalcred(struct rpc_task *task)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
dprintk("RPC: %5u invalidating %s cred %p\n",
task->tk_pid, cred->cr_auth->au_ops->au_name, cred);
@@ -576,7 +629,7 @@ rpcauth_invalcred(struct rpc_task *task)
int
rpcauth_uptodatecred(struct rpc_task *task)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
return cred == NULL ||
test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) != 0;
@@ -587,14 +640,27 @@ static struct shrinker rpc_cred_shrinker = {
.seeks = DEFAULT_SEEKS,
};
-void __init rpcauth_init_module(void)
+int __init rpcauth_init_module(void)
{
- rpc_init_authunix();
- rpc_init_generic_auth();
+ int err;
+
+ err = rpc_init_authunix();
+ if (err < 0)
+ goto out1;
+ err = rpc_init_generic_auth();
+ if (err < 0)
+ goto out2;
register_shrinker(&rpc_cred_shrinker);
+ return 0;
+out2:
+ rpc_destroy_authunix();
+out1:
+ return err;
}
void __exit rpcauth_remove_module(void)
{
+ rpc_destroy_authunix();
+ rpc_destroy_generic_auth();
unregister_shrinker(&rpc_cred_shrinker);
}
diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c
index 8f623b0f03dd..43162bb3b78f 100644
--- a/net/sunrpc/auth_generic.c
+++ b/net/sunrpc/auth_generic.c
@@ -27,7 +27,6 @@ struct generic_cred {
};
static struct rpc_auth generic_auth;
-static struct rpc_cred_cache generic_cred_cache;
static const struct rpc_credops generic_credops;
/*
@@ -55,18 +54,13 @@ struct rpc_cred *rpc_lookup_machine_cred(void)
}
EXPORT_SYMBOL_GPL(rpc_lookup_machine_cred);
-static void
-generic_bind_cred(struct rpc_task *task, struct rpc_cred *cred, int lookupflags)
+static struct rpc_cred *generic_bind_cred(struct rpc_task *task,
+ struct rpc_cred *cred, int lookupflags)
{
struct rpc_auth *auth = task->tk_client->cl_auth;
struct auth_cred *acred = &container_of(cred, struct generic_cred, gc_base)->acred;
- struct rpc_cred *ret;
- ret = auth->au_ops->lookup_cred(auth, acred, lookupflags);
- if (!IS_ERR(ret))
- task->tk_msg.rpc_cred = ret;
- else
- task->tk_status = PTR_ERR(ret);
+ return auth->au_ops->lookup_cred(auth, acred, lookupflags);
}
/*
@@ -159,20 +153,16 @@ out_nomatch:
return 0;
}
-void __init rpc_init_generic_auth(void)
+int __init rpc_init_generic_auth(void)
{
- spin_lock_init(&generic_cred_cache.lock);
+ return rpcauth_init_credcache(&generic_auth);
}
void __exit rpc_destroy_generic_auth(void)
{
- rpcauth_clear_credcache(&generic_cred_cache);
+ rpcauth_destroy_credcache(&generic_auth);
}
-static struct rpc_cred_cache generic_cred_cache = {
- {{ NULL, },},
-};
-
static const struct rpc_authops generic_auth_ops = {
.owner = THIS_MODULE,
.au_name = "Generic",
@@ -183,7 +173,6 @@ static const struct rpc_authops generic_auth_ops = {
static struct rpc_auth generic_auth = {
.au_ops = &generic_auth_ops,
.au_count = ATOMIC_INIT(0),
- .au_credcache = &generic_cred_cache,
};
static const struct rpc_credops generic_credops = {
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 8da2a0e68574..dcfc66bab2bb 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -373,7 +373,7 @@ gss_handle_downcall_result(struct gss_cred *gss_cred, struct gss_upcall_msg *gss
static void
gss_upcall_callback(struct rpc_task *task)
{
- struct gss_cred *gss_cred = container_of(task->tk_msg.rpc_cred,
+ struct gss_cred *gss_cred = container_of(task->tk_rqstp->rq_cred,
struct gss_cred, gc_base);
struct gss_upcall_msg *gss_msg = gss_cred->gc_upcall;
struct inode *inode = &gss_msg->inode->vfs_inode;
@@ -502,7 +502,7 @@ static void warn_gssd(void)
static inline int
gss_refresh_upcall(struct rpc_task *task)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
struct gss_auth *gss_auth = container_of(cred->cr_auth,
struct gss_auth, rpc_auth);
struct gss_cred *gss_cred = container_of(cred,
@@ -928,6 +928,7 @@ gss_do_free_ctx(struct gss_cl_ctx *ctx)
{
dprintk("RPC: gss_free_ctx\n");
+ gss_delete_sec_context(&ctx->gc_gss_ctx);
kfree(ctx->gc_wire_ctx.data);
kfree(ctx);
}
@@ -942,13 +943,7 @@ gss_free_ctx_callback(struct rcu_head *head)
static void
gss_free_ctx(struct gss_cl_ctx *ctx)
{
- struct gss_ctx *gc_gss_ctx;
-
- gc_gss_ctx = rcu_dereference(ctx->gc_gss_ctx);
- rcu_assign_pointer(ctx->gc_gss_ctx, NULL);
call_rcu(&ctx->gc_rcu, gss_free_ctx_callback);
- if (gc_gss_ctx)
- gss_delete_sec_context(&gc_gss_ctx);
}
static void
@@ -1064,12 +1059,12 @@ out:
static __be32 *
gss_marshal(struct rpc_task *task, __be32 *p)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_rqst *req = task->tk_rqstp;
+ struct rpc_cred *cred = req->rq_cred;
struct gss_cred *gss_cred = container_of(cred, struct gss_cred,
gc_base);
struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);
__be32 *cred_len;
- struct rpc_rqst *req = task->tk_rqstp;
u32 maj_stat = 0;
struct xdr_netobj mic;
struct kvec iov;
@@ -1119,7 +1114,7 @@ out_put_ctx:
static int gss_renew_cred(struct rpc_task *task)
{
- struct rpc_cred *oldcred = task->tk_msg.rpc_cred;
+ struct rpc_cred *oldcred = task->tk_rqstp->rq_cred;
struct gss_cred *gss_cred = container_of(oldcred,
struct gss_cred,
gc_base);
@@ -1133,7 +1128,7 @@ static int gss_renew_cred(struct rpc_task *task)
new = gss_lookup_cred(auth, &acred, RPCAUTH_LOOKUP_NEW);
if (IS_ERR(new))
return PTR_ERR(new);
- task->tk_msg.rpc_cred = new;
+ task->tk_rqstp->rq_cred = new;
put_rpccred(oldcred);
return 0;
}
@@ -1161,7 +1156,7 @@ static int gss_cred_is_negative_entry(struct rpc_cred *cred)
static int
gss_refresh(struct rpc_task *task)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
int ret = 0;
if (gss_cred_is_negative_entry(cred))
@@ -1172,7 +1167,7 @@ gss_refresh(struct rpc_task *task)
ret = gss_renew_cred(task);
if (ret < 0)
goto out;
- cred = task->tk_msg.rpc_cred;
+ cred = task->tk_rqstp->rq_cred;
}
if (test_bit(RPCAUTH_CRED_NEW, &cred->cr_flags))
@@ -1191,7 +1186,7 @@ gss_refresh_null(struct rpc_task *task)
static __be32 *
gss_validate(struct rpc_task *task, __be32 *p)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);
__be32 seq;
struct kvec iov;
@@ -1400,7 +1395,7 @@ static int
gss_wrap_req(struct rpc_task *task,
kxdrproc_t encode, void *rqstp, __be32 *p, void *obj)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
struct gss_cred *gss_cred = container_of(cred, struct gss_cred,
gc_base);
struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);
@@ -1503,7 +1498,7 @@ static int
gss_unwrap_resp(struct rpc_task *task,
kxdrproc_t decode, void *rqstp, __be32 *p, void *obj)
{
- struct rpc_cred *cred = task->tk_msg.rpc_cred;
+ struct rpc_cred *cred = task->tk_rqstp->rq_cred;
struct gss_cred *gss_cred = container_of(cred, struct gss_cred,
gc_base);
struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);
diff --git a/net/sunrpc/auth_null.c b/net/sunrpc/auth_null.c
index 1db618f56ecb..a5c36c01707b 100644
--- a/net/sunrpc/auth_null.c
+++ b/net/sunrpc/auth_null.c
@@ -75,7 +75,7 @@ nul_marshal(struct rpc_task *task, __be32 *p)
static int
nul_refresh(struct rpc_task *task)
{
- set_bit(RPCAUTH_CRED_UPTODATE, &task->tk_msg.rpc_cred->cr_flags);
+ set_bit(RPCAUTH_CRED_UPTODATE, &task->tk_rqstp->rq_cred->cr_flags);
return 0;
}
diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c
index aac2f8b4ee21..4cb70dc6e7ad 100644
--- a/net/sunrpc/auth_unix.c
+++ b/net/sunrpc/auth_unix.c
@@ -29,7 +29,6 @@ struct unx_cred {
#endif
static struct rpc_auth unix_auth;
-static struct rpc_cred_cache unix_cred_cache;
static const struct rpc_credops unix_credops;
static struct rpc_auth *
@@ -141,7 +140,7 @@ static __be32 *
unx_marshal(struct rpc_task *task, __be32 *p)
{
struct rpc_clnt *clnt = task->tk_client;
- struct unx_cred *cred = container_of(task->tk_msg.rpc_cred, struct unx_cred, uc_base);
+ struct unx_cred *cred = container_of(task->tk_rqstp->rq_cred, struct unx_cred, uc_base);
__be32 *base, *hold;
int i;
@@ -174,7 +173,7 @@ unx_marshal(struct rpc_task *task, __be32 *p)
static int
unx_refresh(struct rpc_task *task)
{
- set_bit(RPCAUTH_CRED_UPTODATE, &task->tk_msg.rpc_cred->cr_flags);
+ set_bit(RPCAUTH_CRED_UPTODATE, &task->tk_rqstp->rq_cred->cr_flags);
return 0;
}
@@ -197,15 +196,20 @@ unx_validate(struct rpc_task *task, __be32 *p)
printk("RPC: giant verf size: %u\n", size);
return NULL;
}
- task->tk_msg.rpc_cred->cr_auth->au_rslack = (size >> 2) + 2;
+ task->tk_rqstp->rq_cred->cr_auth->au_rslack = (size >> 2) + 2;
p += (size >> 2);
return p;
}
-void __init rpc_init_authunix(void)
+int __init rpc_init_authunix(void)
{
- spin_lock_init(&unix_cred_cache.lock);
+ return rpcauth_init_credcache(&unix_auth);
+}
+
+void rpc_destroy_authunix(void)
+{
+ rpcauth_destroy_credcache(&unix_auth);
}
const struct rpc_authops authunix_ops = {
@@ -219,17 +223,12 @@ const struct rpc_authops authunix_ops = {
};
static
-struct rpc_cred_cache unix_cred_cache = {
-};
-
-static
struct rpc_auth unix_auth = {
.au_cslack = UNX_WRITESLACK,
.au_rslack = 2, /* assume AUTH_NULL verf */
.au_ops = &authunix_ops,
.au_flavor = RPC_AUTH_UNIX,
.au_count = ATOMIC_INIT(0),
- .au_credcache = &unix_cred_cache,
};
static
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 58de76c8540c..2b06410e584e 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -34,7 +34,6 @@
#include <linux/sunrpc/cache.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/rpc_pipe_fs.h>
-#include <linux/smp_lock.h>
#define RPCDBG_FACILITY RPCDBG_CACHE
@@ -320,7 +319,7 @@ static struct cache_detail *current_detail;
static int current_index;
static void do_cache_clean(struct work_struct *work);
-static DECLARE_DELAYED_WORK(cache_cleaner, do_cache_clean);
+static struct delayed_work cache_cleaner;
static void sunrpc_init_cache_detail(struct cache_detail *cd)
{
@@ -1504,6 +1503,11 @@ static int create_cache_proc_entries(struct cache_detail *cd)
}
#endif
+void __init cache_initialize(void)
+{
+ INIT_DELAYED_WORK_DEFERRABLE(&cache_cleaner, do_cache_clean);
+}
+
int cache_register(struct cache_detail *cd)
{
int ret;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 756fc324db9e..2388d83b68ff 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -414,6 +414,35 @@ out_no_clnt:
EXPORT_SYMBOL_GPL(rpc_clone_client);
/*
+ * Kill all tasks for the given client.
+ * XXX: kill their descendants as well?
+ */
+void rpc_killall_tasks(struct rpc_clnt *clnt)
+{
+ struct rpc_task *rovr;
+
+
+ if (list_empty(&clnt->cl_tasks))
+ return;
+ dprintk("RPC: killing all tasks for client %p\n", clnt);
+ /*
+ * Spin lock all_tasks to prevent changes...
+ */
+ spin_lock(&clnt->cl_lock);
+ list_for_each_entry(rovr, &clnt->cl_tasks, tk_task) {
+ if (!RPC_IS_ACTIVATED(rovr))
+ continue;
+ if (!(rovr->tk_flags & RPC_TASK_KILLED)) {
+ rovr->tk_flags |= RPC_TASK_KILLED;
+ rpc_exit(rovr, -EIO);
+ rpc_wake_up_queued_task(rovr->tk_waitqueue, rovr);
+ }
+ }
+ spin_unlock(&clnt->cl_lock);
+}
+EXPORT_SYMBOL_GPL(rpc_killall_tasks);
+
+/*
* Properly shut down an RPC client, terminating all outstanding
* requests.
*/
@@ -538,6 +567,49 @@ out:
}
EXPORT_SYMBOL_GPL(rpc_bind_new_program);
+void rpc_task_release_client(struct rpc_task *task)
+{
+ struct rpc_clnt *clnt = task->tk_client;
+
+ if (clnt != NULL) {
+ /* Remove from client task list */
+ spin_lock(&clnt->cl_lock);
+ list_del(&task->tk_task);
+ spin_unlock(&clnt->cl_lock);
+ task->tk_client = NULL;
+
+ rpc_release_client(clnt);
+ }
+}
+
+static
+void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt)
+{
+ if (clnt != NULL) {
+ rpc_task_release_client(task);
+ task->tk_client = clnt;
+ kref_get(&clnt->cl_kref);
+ if (clnt->cl_softrtry)
+ task->tk_flags |= RPC_TASK_SOFT;
+ /* Add to the client's list of all tasks */
+ spin_lock(&clnt->cl_lock);
+ list_add_tail(&task->tk_task, &clnt->cl_tasks);
+ spin_unlock(&clnt->cl_lock);
+ }
+}
+
+static void
+rpc_task_set_rpc_message(struct rpc_task *task, const struct rpc_message *msg)
+{
+ if (msg != NULL) {
+ task->tk_msg.rpc_proc = msg->rpc_proc;
+ task->tk_msg.rpc_argp = msg->rpc_argp;
+ task->tk_msg.rpc_resp = msg->rpc_resp;
+ if (msg->rpc_cred != NULL)
+ task->tk_msg.rpc_cred = get_rpccred(msg->rpc_cred);
+ }
+}
+
/*
* Default callback for async RPC calls
*/
@@ -562,6 +634,18 @@ struct rpc_task *rpc_run_task(const struct rpc_task_setup *task_setup_data)
if (IS_ERR(task))
goto out;
+ rpc_task_set_client(task, task_setup_data->rpc_client);
+ rpc_task_set_rpc_message(task, task_setup_data->rpc_message);
+
+ if (task->tk_status != 0) {
+ int ret = task->tk_status;
+ rpc_put_task(task);
+ return ERR_PTR(ret);
+ }
+
+ if (task->tk_action == NULL)
+ rpc_call_start(task);
+
atomic_inc(&task->tk_count);
rpc_execute(task);
out:
@@ -756,12 +840,13 @@ EXPORT_SYMBOL_GPL(rpc_force_rebind);
* Restart an (async) RPC call from the call_prepare state.
* Usually called from within the exit handler.
*/
-void
+int
rpc_restart_call_prepare(struct rpc_task *task)
{
if (RPC_ASSASSINATED(task))
- return;
+ return 0;
task->tk_action = rpc_prepare_task;
+ return 1;
}
EXPORT_SYMBOL_GPL(rpc_restart_call_prepare);
@@ -769,13 +854,13 @@ EXPORT_SYMBOL_GPL(rpc_restart_call_prepare);
* Restart an (async) RPC call. Usually called from within the
* exit handler.
*/
-void
+int
rpc_restart_call(struct rpc_task *task)
{
if (RPC_ASSASSINATED(task))
- return;
-
+ return 0;
task->tk_action = call_start;
+ return 1;
}
EXPORT_SYMBOL_GPL(rpc_restart_call);
@@ -824,11 +909,6 @@ call_reserve(struct rpc_task *task)
{
dprint_status(task);
- if (!rpcauth_uptodatecred(task)) {
- task->tk_action = call_refresh;
- return;
- }
-
task->tk_status = 0;
task->tk_action = call_reserveresult;
xprt_reserve(task);
@@ -892,7 +972,7 @@ call_reserveresult(struct rpc_task *task)
static void
call_allocate(struct rpc_task *task)
{
- unsigned int slack = task->tk_msg.rpc_cred->cr_auth->au_cslack;
+ unsigned int slack = task->tk_client->cl_auth->au_cslack;
struct rpc_rqst *req = task->tk_rqstp;
struct rpc_xprt *xprt = task->tk_xprt;
struct rpc_procinfo *proc = task->tk_msg.rpc_proc;
@@ -900,7 +980,7 @@ call_allocate(struct rpc_task *task)
dprint_status(task);
task->tk_status = 0;
- task->tk_action = call_bind;
+ task->tk_action = call_refresh;
if (req->rq_buffer)
return;
@@ -937,6 +1017,47 @@ call_allocate(struct rpc_task *task)
rpc_exit(task, -ERESTARTSYS);
}
+/*
+ * 2a. Bind and/or refresh the credentials
+ */
+static void
+call_refresh(struct rpc_task *task)
+{
+ dprint_status(task);
+
+ task->tk_action = call_refreshresult;
+ task->tk_status = 0;
+ task->tk_client->cl_stats->rpcauthrefresh++;
+ rpcauth_refreshcred(task);
+}
+
+/*
+ * 2b. Process the results of a credential refresh
+ */
+static void
+call_refreshresult(struct rpc_task *task)
+{
+ int status = task->tk_status;
+
+ dprint_status(task);
+
+ task->tk_status = 0;
+ task->tk_action = call_bind;
+ if (status >= 0 && rpcauth_uptodatecred(task))
+ return;
+ switch (status) {
+ case -EACCES:
+ rpc_exit(task, -EACCES);
+ return;
+ case -ENOMEM:
+ rpc_exit(task, -ENOMEM);
+ return;
+ case -ETIMEDOUT:
+ rpc_delay(task, 3*HZ);
+ }
+ task->tk_action = call_refresh;
+}
+
static inline int
rpc_task_need_encode(struct rpc_task *task)
{
@@ -1472,43 +1593,6 @@ out_retry:
}
}
-/*
- * 8. Refresh the credentials if rejected by the server
- */
-static void
-call_refresh(struct rpc_task *task)
-{
- dprint_status(task);
-
- task->tk_action = call_refreshresult;
- task->tk_status = 0;
- task->tk_client->cl_stats->rpcauthrefresh++;
- rpcauth_refreshcred(task);
-}
-
-/*
- * 8a. Process the results of a credential refresh
- */
-static void
-call_refreshresult(struct rpc_task *task)
-{
- int status = task->tk_status;
-
- dprint_status(task);
-
- task->tk_status = 0;
- task->tk_action = call_reserve;
- if (status >= 0 && rpcauth_uptodatecred(task))
- return;
- if (status == -EACCES) {
- rpc_exit(task, -EACCES);
- return;
- }
- task->tk_action = call_refresh;
- if (status != -ETIMEDOUT)
- rpc_delay(task, 3*HZ);
-}
-
static __be32 *
rpc_encode_header(struct rpc_task *task)
{
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 4a843b883b89..cace6049e4a5 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -246,17 +246,8 @@ static inline void rpc_task_set_debuginfo(struct rpc_task *task)
static void rpc_set_active(struct rpc_task *task)
{
- struct rpc_clnt *clnt;
- if (test_and_set_bit(RPC_TASK_ACTIVE, &task->tk_runstate) != 0)
- return;
rpc_task_set_debuginfo(task);
- /* Add to global list of all tasks */
- clnt = task->tk_client;
- if (clnt != NULL) {
- spin_lock(&clnt->cl_lock);
- list_add_tail(&task->tk_task, &clnt->cl_tasks);
- spin_unlock(&clnt->cl_lock);
- }
+ set_bit(RPC_TASK_ACTIVE, &task->tk_runstate);
}
/*
@@ -319,11 +310,6 @@ static void __rpc_sleep_on(struct rpc_wait_queue *q, struct rpc_task *task,
dprintk("RPC: %5u sleep_on(queue \"%s\" time %lu)\n",
task->tk_pid, rpc_qname(q), jiffies);
- if (!RPC_IS_ASYNC(task) && !RPC_IS_ACTIVATED(task)) {
- printk(KERN_ERR "RPC: Inactive synchronous task put to sleep!\n");
- return;
- }
-
__rpc_add_wait_queue(q, task);
BUG_ON(task->tk_callback != NULL);
@@ -334,8 +320,8 @@ static void __rpc_sleep_on(struct rpc_wait_queue *q, struct rpc_task *task,
void rpc_sleep_on(struct rpc_wait_queue *q, struct rpc_task *task,
rpc_action action)
{
- /* Mark the task as being activated if so needed */
- rpc_set_active(task);
+ /* We shouldn't ever put an inactive task to sleep */
+ BUG_ON(!RPC_IS_ACTIVATED(task));
/*
* Protect the queue operations.
@@ -406,14 +392,6 @@ void rpc_wake_up_queued_task(struct rpc_wait_queue *queue, struct rpc_task *task
EXPORT_SYMBOL_GPL(rpc_wake_up_queued_task);
/*
- * Wake up the specified task
- */
-static void rpc_wake_up_task(struct rpc_task *task)
-{
- rpc_wake_up_queued_task(task->tk_waitqueue, task);
-}
-
-/*
* Wake up the next task on a priority queue.
*/
static struct rpc_task * __rpc_wake_up_next_priority(struct rpc_wait_queue *queue)
@@ -600,7 +578,15 @@ void rpc_exit_task(struct rpc_task *task)
}
}
}
-EXPORT_SYMBOL_GPL(rpc_exit_task);
+
+void rpc_exit(struct rpc_task *task, int status)
+{
+ task->tk_status = status;
+ task->tk_action = rpc_exit_task;
+ if (RPC_IS_QUEUED(task))
+ rpc_wake_up_queued_task(task->tk_waitqueue, task);
+}
+EXPORT_SYMBOL_GPL(rpc_exit);
void rpc_release_calldata(const struct rpc_call_ops *ops, void *calldata)
{
@@ -690,7 +676,6 @@ static void __rpc_execute(struct rpc_task *task)
dprintk("RPC: %5u got signal\n", task->tk_pid);
task->tk_flags |= RPC_TASK_KILLED;
rpc_exit(task, -ERESTARTSYS);
- rpc_wake_up_task(task);
}
rpc_set_running(task);
dprintk("RPC: %5u sync task resuming\n", task->tk_pid);
@@ -714,8 +699,9 @@ static void __rpc_execute(struct rpc_task *task)
void rpc_execute(struct rpc_task *task)
{
rpc_set_active(task);
- rpc_set_running(task);
- __rpc_execute(task);
+ rpc_make_runnable(task);
+ if (!RPC_IS_ASYNC(task))
+ __rpc_execute(task);
}
static void rpc_async_schedule(struct work_struct *work)
@@ -808,26 +794,9 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta
/* Initialize workqueue for async tasks */
task->tk_workqueue = task_setup_data->workqueue;
- task->tk_client = task_setup_data->rpc_client;
- if (task->tk_client != NULL) {
- kref_get(&task->tk_client->cl_kref);
- if (task->tk_client->cl_softrtry)
- task->tk_flags |= RPC_TASK_SOFT;
- }
-
if (task->tk_ops->rpc_call_prepare != NULL)
task->tk_action = rpc_prepare_task;
- if (task_setup_data->rpc_message != NULL) {
- task->tk_msg.rpc_proc = task_setup_data->rpc_message->rpc_proc;
- task->tk_msg.rpc_argp = task_setup_data->rpc_message->rpc_argp;
- task->tk_msg.rpc_resp = task_setup_data->rpc_message->rpc_resp;
- /* Bind the user cred */
- rpcauth_bindcred(task, task_setup_data->rpc_message->rpc_cred, task_setup_data->flags);
- if (task->tk_action == NULL)
- rpc_call_start(task);
- }
-
/* starting timestamp */
task->tk_start = ktime_get();
@@ -896,11 +865,8 @@ void rpc_put_task(struct rpc_task *task)
if (task->tk_rqstp)
xprt_release(task);
if (task->tk_msg.rpc_cred)
- rpcauth_unbindcred(task);
- if (task->tk_client) {
- rpc_release_client(task->tk_client);
- task->tk_client = NULL;
- }
+ put_rpccred(task->tk_msg.rpc_cred);
+ rpc_task_release_client(task);
if (task->tk_workqueue != NULL) {
INIT_WORK(&task->u.tk_work, rpc_async_release);
queue_work(task->tk_workqueue, &task->u.tk_work);
@@ -913,13 +879,6 @@ static void rpc_release_task(struct rpc_task *task)
{
dprintk("RPC: %5u release task\n", task->tk_pid);
- if (!list_empty(&task->tk_task)) {
- struct rpc_clnt *clnt = task->tk_client;
- /* Remove from client task list */
- spin_lock(&clnt->cl_lock);
- list_del(&task->tk_task);
- spin_unlock(&clnt->cl_lock);
- }
BUG_ON (RPC_IS_QUEUED(task));
/* Wake up anyone who is waiting for task completion */
@@ -928,35 +887,6 @@ static void rpc_release_task(struct rpc_task *task)
rpc_put_task(task);
}
-/*
- * Kill all tasks for the given client.
- * XXX: kill their descendants as well?
- */
-void rpc_killall_tasks(struct rpc_clnt *clnt)
-{
- struct rpc_task *rovr;
-
-
- if (list_empty(&clnt->cl_tasks))
- return;
- dprintk("RPC: killing all tasks for client %p\n", clnt);
- /*
- * Spin lock all_tasks to prevent changes...
- */
- spin_lock(&clnt->cl_lock);
- list_for_each_entry(rovr, &clnt->cl_tasks, tk_task) {
- if (! RPC_IS_ACTIVATED(rovr))
- continue;
- if (!(rovr->tk_flags & RPC_TASK_KILLED)) {
- rovr->tk_flags |= RPC_TASK_KILLED;
- rpc_exit(rovr, -EIO);
- rpc_wake_up_task(rovr);
- }
- }
- spin_unlock(&clnt->cl_lock);
-}
-EXPORT_SYMBOL_GPL(rpc_killall_tasks);
-
int rpciod_up(void)
{
return try_module_get(THIS_MODULE) ? 0 : -EINVAL;
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index f438347d817b..c0d085013a2b 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -33,21 +33,27 @@ init_sunrpc(void)
if (err)
goto out;
err = rpc_init_mempool();
- if (err) {
- unregister_rpc_pipefs();
- goto out;
- }
+ if (err)
+ goto out2;
+ err = rpcauth_init_module();
+ if (err)
+ goto out3;
#ifdef RPC_DEBUG
rpc_register_sysctl();
#endif
#ifdef CONFIG_PROC_FS
rpc_proc_init();
#endif
+ cache_initialize();
cache_register(&ip_map_cache);
cache_register(&unix_gid_cache);
svc_init_xprt_sock(); /* svc sock transport */
init_socket_xprt(); /* clnt sock transport */
- rpcauth_init_module();
+ return 0;
+out3:
+ rpc_destroy_mempool();
+out2:
+ unregister_rpc_pipefs();
out:
return err;
}
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index dcd0132396ba..970fb00f388c 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1032,6 +1032,8 @@ void xprt_release(struct rpc_task *task)
spin_unlock_bh(&xprt->transport_lock);
if (req->rq_buffer)
xprt->ops->buf_free(req->rq_buffer);
+ if (req->rq_cred != NULL)
+ put_rpccred(req->rq_cred);
task->tk_rqstp = NULL;
if (req->rq_release_snd_buf)
req->rq_release_snd_buf(req);
@@ -1129,6 +1131,7 @@ static void xprt_destroy(struct kref *kref)
rpc_destroy_wait_queue(&xprt->sending);
rpc_destroy_wait_queue(&xprt->resend);
rpc_destroy_wait_queue(&xprt->backlog);
+ cancel_work_sync(&xprt->task_cleanup);
/*
* Tear down transport state and free the rpc_xprt
*/
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index e5e28d1946a4..2ac3f6e8adff 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -249,6 +249,8 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
req->rl_nchunks = nchunks;
BUG_ON(nchunks == 0);
+ BUG_ON((r_xprt->rx_ia.ri_memreg_strategy == RPCRDMA_FRMR)
+ && (nchunks > 3));
/*
* finish off header. If write, marshal discrim and nchunks.
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 27015c6d8eb5..5f4c7b3bc711 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -650,10 +650,22 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
ep->rep_attr.cap.max_send_wr = cdata->max_requests;
switch (ia->ri_memreg_strategy) {
case RPCRDMA_FRMR:
- /* Add room for frmr register and invalidate WRs */
- ep->rep_attr.cap.max_send_wr *= 3;
- if (ep->rep_attr.cap.max_send_wr > devattr.max_qp_wr)
- return -EINVAL;
+ /* Add room for frmr register and invalidate WRs.
+ * 1. FRMR reg WR for head
+ * 2. FRMR invalidate WR for head
+ * 3. FRMR reg WR for pagelist
+ * 4. FRMR invalidate WR for pagelist
+ * 5. FRMR reg WR for tail
+ * 6. FRMR invalidate WR for tail
+ * 7. The RDMA_SEND WR
+ */
+ ep->rep_attr.cap.max_send_wr *= 7;
+ if (ep->rep_attr.cap.max_send_wr > devattr.max_qp_wr) {
+ cdata->max_requests = devattr.max_qp_wr / 7;
+ if (!cdata->max_requests)
+ return -EINVAL;
+ ep->rep_attr.cap.max_send_wr = cdata->max_requests * 7;
+ }
break;
case RPCRDMA_MEMWINDOWS_ASYNC:
case RPCRDMA_MEMWINDOWS:
@@ -1490,7 +1502,7 @@ rpcrdma_register_frmr_external(struct rpcrdma_mr_seg *seg,
memset(&frmr_wr, 0, sizeof frmr_wr);
frmr_wr.opcode = IB_WR_FAST_REG_MR;
frmr_wr.send_flags = 0; /* unsignaled */
- frmr_wr.wr.fast_reg.iova_start = (unsigned long)seg1->mr_dma;
+ frmr_wr.wr.fast_reg.iova_start = seg1->mr_dma;
frmr_wr.wr.fast_reg.page_list = seg1->mr_chunk.rl_mw->r.frmr.fr_pgl;
frmr_wr.wr.fast_reg.page_list_len = i;
frmr_wr.wr.fast_reg.page_shift = PAGE_SHIFT;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 7ca65c7005ea..b6309db56226 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1305,10 +1305,11 @@ static void xs_tcp_state_change(struct sock *sk)
if (!(xprt = xprt_from_sock(sk)))
goto out;
dprintk("RPC: xs_tcp_state_change client %p...\n", xprt);
- dprintk("RPC: state %x conn %d dead %d zapped %d\n",
+ dprintk("RPC: state %x conn %d dead %d zapped %d sk_shutdown %d\n",
sk->sk_state, xprt_connected(xprt),
sock_flag(sk, SOCK_DEAD),
- sock_flag(sk, SOCK_ZAPPED));
+ sock_flag(sk, SOCK_ZAPPED),
+ sk->sk_shutdown);
switch (sk->sk_state) {
case TCP_ESTABLISHED:
@@ -1779,10 +1780,25 @@ static void xs_tcp_reuse_connection(struct rpc_xprt *xprt, struct sock_xprt *tra
{
unsigned int state = transport->inet->sk_state;
- if (state == TCP_CLOSE && transport->sock->state == SS_UNCONNECTED)
- return;
- if ((1 << state) & (TCPF_ESTABLISHED|TCPF_SYN_SENT))
- return;
+ if (state == TCP_CLOSE && transport->sock->state == SS_UNCONNECTED) {
+ /* we don't need to abort the connection if the socket
+ * hasn't undergone a shutdown
+ */
+ if (transport->inet->sk_shutdown == 0)
+ return;
+ dprintk("RPC: %s: TCP_CLOSEd and sk_shutdown set to %d\n",
+ __func__, transport->inet->sk_shutdown);
+ }
+ if ((1 << state) & (TCPF_ESTABLISHED|TCPF_SYN_SENT)) {
+ /* we don't need to abort the connection if the socket
+ * hasn't undergone a shutdown
+ */
+ if (transport->inet->sk_shutdown == 0)
+ return;
+ dprintk("RPC: %s: ESTABLISHED/SYN_SENT "
+ "sk_shutdown set to %d\n",
+ __func__, transport->inet->sk_shutdown);
+ }
xs_abort_connection(xprt, transport);
}
@@ -2577,7 +2593,8 @@ void cleanup_socket_xprt(void)
xprt_unregister_transport(&xs_bc_tcp_transport);
}
-static int param_set_uint_minmax(const char *val, struct kernel_param *kp,
+static int param_set_uint_minmax(const char *val,
+ const struct kernel_param *kp,
unsigned int min, unsigned int max)
{
unsigned long num;
@@ -2592,34 +2609,37 @@ static int param_set_uint_minmax(const char *val, struct kernel_param *kp,
return 0;
}
-static int param_set_portnr(const char *val, struct kernel_param *kp)
+static int param_set_portnr(const char *val, const struct kernel_param *kp)
{
return param_set_uint_minmax(val, kp,
RPC_MIN_RESVPORT,
RPC_MAX_RESVPORT);
}
-static int param_get_portnr(char *buffer, struct kernel_param *kp)
-{
- return param_get_uint(buffer, kp);
-}
+static struct kernel_param_ops param_ops_portnr = {
+ .set = param_set_portnr,
+ .get = param_get_uint,
+};
+
#define param_check_portnr(name, p) \
__param_check(name, p, unsigned int);
module_param_named(min_resvport, xprt_min_resvport, portnr, 0644);
module_param_named(max_resvport, xprt_max_resvport, portnr, 0644);
-static int param_set_slot_table_size(const char *val, struct kernel_param *kp)
+static int param_set_slot_table_size(const char *val,
+ const struct kernel_param *kp)
{
return param_set_uint_minmax(val, kp,
RPC_MIN_SLOT_TABLE,
RPC_MAX_SLOT_TABLE);
}
-static int param_get_slot_table_size(char *buffer, struct kernel_param *kp)
-{
- return param_get_uint(buffer, kp);
-}
+static struct kernel_param_ops param_ops_slot_table_size = {
+ .set = param_set_slot_table_size,
+ .get = param_get_uint,
+};
+
#define param_check_slot_table_size(name, p) \
__param_check(name, p, unsigned int);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 4414a18c63b4..0b39b2451ea5 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -692,6 +692,7 @@ static int unix_autobind(struct socket *sock)
static u32 ordernum = 1;
struct unix_address *addr;
int err;
+ unsigned int retries = 0;
mutex_lock(&u->readlock);
@@ -717,9 +718,17 @@ retry:
if (__unix_find_socket_byname(net, addr->name, addr->len, sock->type,
addr->hash)) {
spin_unlock(&unix_table_lock);
- /* Sanity yield. It is unusual case, but yet... */
- if (!(ordernum&0xFF))
- yield();
+ /*
+ * __unix_find_socket_byname() may take long time if many names
+ * are already in use.
+ */
+ cond_resched();
+ /* Give up if all names seems to be in use. */
+ if (retries++ == 0xFFFFF) {
+ err = -ENOSPC;
+ kfree(addr);
+ goto out;
+ }
goto retry;
}
addr->hash ^= sk->sk_type;