summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/appletalk/aarp.c24
-rw-r--r--net/ceph/messenger_v2.c12
-rw-r--r--net/core/net_namespace.c8
-rw-r--r--net/core/scm.c32
-rw-r--r--net/ipv4/ipcomp.c2
-rw-r--r--net/ipv4/xfrm4_input.c3
-rw-r--r--net/ipv6/addrconf.c2
-rw-r--r--net/ipv6/ipcomp6.c2
-rw-r--r--net/ipv6/xfrm6_input.c3
-rw-r--r--net/ipv6/xfrm6_tunnel.c2
-rw-r--r--net/key/af_key.c2
-rw-r--r--net/sched/sch_qfq.c7
-rw-r--r--net/socket.c46
-rw-r--r--net/sunrpc/auth_gss/auth_gss.c13
-rw-r--r--net/sunrpc/auth_gss/svcauth_gss.c3
-rw-r--r--net/sunrpc/clnt.c36
-rw-r--r--net/sunrpc/rpc_pipe.c532
-rw-r--r--net/sunrpc/socklib.c164
-rw-r--r--net/sunrpc/svc.c20
-rw-r--r--net/sunrpc/svcsock.c5
-rw-r--r--net/sunrpc/xdr.c11
-rw-r--r--net/unix/af_unix.c78
-rw-r--r--net/xfrm/xfrm_device.c1
-rw-r--r--net/xfrm/xfrm_interface_core.c7
-rw-r--r--net/xfrm/xfrm_ipcomp.c3
-rw-r--r--net/xfrm/xfrm_state.c69
-rw-r--r--net/xfrm/xfrm_user.c3
27 files changed, 437 insertions, 653 deletions
diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c
index 9c787e2e4b17..4744e3fd4544 100644
--- a/net/appletalk/aarp.c
+++ b/net/appletalk/aarp.c
@@ -35,6 +35,7 @@
#include <linux/seq_file.h>
#include <linux/export.h>
#include <linux/etherdevice.h>
+#include <linux/refcount.h>
int sysctl_aarp_expiry_time = AARP_EXPIRY_TIME;
int sysctl_aarp_tick_time = AARP_TICK_TIME;
@@ -44,6 +45,7 @@ int sysctl_aarp_resolve_time = AARP_RESOLVE_TIME;
/* Lists of aarp entries */
/**
* struct aarp_entry - AARP entry
+ * @refcnt: Reference count
* @last_sent: Last time we xmitted the aarp request
* @packet_queue: Queue of frames wait for resolution
* @status: Used for proxy AARP
@@ -55,6 +57,7 @@ int sysctl_aarp_resolve_time = AARP_RESOLVE_TIME;
* @next: Next entry in chain
*/
struct aarp_entry {
+ refcount_t refcnt;
/* These first two are only used for unresolved entries */
unsigned long last_sent;
struct sk_buff_head packet_queue;
@@ -79,6 +82,17 @@ static DEFINE_RWLOCK(aarp_lock);
/* Used to walk the list and purge/kick entries. */
static struct timer_list aarp_timer;
+static inline void aarp_entry_get(struct aarp_entry *a)
+{
+ refcount_inc(&a->refcnt);
+}
+
+static inline void aarp_entry_put(struct aarp_entry *a)
+{
+ if (refcount_dec_and_test(&a->refcnt))
+ kfree(a);
+}
+
/*
* Delete an aarp queue
*
@@ -87,7 +101,7 @@ static struct timer_list aarp_timer;
static void __aarp_expire(struct aarp_entry *a)
{
skb_queue_purge(&a->packet_queue);
- kfree(a);
+ aarp_entry_put(a);
}
/*
@@ -380,9 +394,11 @@ static void aarp_purge(void)
static struct aarp_entry *aarp_alloc(void)
{
struct aarp_entry *a = kmalloc(sizeof(*a), GFP_ATOMIC);
+ if (!a)
+ return NULL;
- if (a)
- skb_queue_head_init(&a->packet_queue);
+ refcount_set(&a->refcnt, 1);
+ skb_queue_head_init(&a->packet_queue);
return a;
}
@@ -477,6 +493,7 @@ int aarp_proxy_probe_network(struct atalk_iface *atif, struct atalk_addr *sa)
entry->dev = atif->dev;
write_lock_bh(&aarp_lock);
+ aarp_entry_get(entry);
hash = sa->s_node % (AARP_HASH_SIZE - 1);
entry->next = proxies[hash];
@@ -502,6 +519,7 @@ int aarp_proxy_probe_network(struct atalk_iface *atif, struct atalk_addr *sa)
retval = 1;
}
+ aarp_entry_put(entry);
write_unlock_bh(&aarp_lock);
out:
return retval;
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index bd608ffa0627..5483b4eed94e 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -793,8 +793,8 @@ static int setup_crypto(struct ceph_connection *con,
return 0; /* auth_x, secure mode */
}
-static int hmac_sha256(struct ceph_connection *con, const struct kvec *kvecs,
- int kvec_cnt, u8 *hmac)
+static int ceph_hmac_sha256(struct ceph_connection *con,
+ const struct kvec *kvecs, int kvec_cnt, u8 *hmac)
{
SHASH_DESC_ON_STACK(desc, con->v2.hmac_tfm); /* tfm arg is ignored */
int ret;
@@ -1462,8 +1462,8 @@ static int prepare_auth_signature(struct ceph_connection *con)
if (!buf)
return -ENOMEM;
- ret = hmac_sha256(con, con->v2.in_sign_kvecs, con->v2.in_sign_kvec_cnt,
- CTRL_BODY(buf));
+ ret = ceph_hmac_sha256(con, con->v2.in_sign_kvecs,
+ con->v2.in_sign_kvec_cnt, CTRL_BODY(buf));
if (ret)
return ret;
@@ -2460,8 +2460,8 @@ static int process_auth_signature(struct ceph_connection *con,
return -EINVAL;
}
- ret = hmac_sha256(con, con->v2.out_sign_kvecs,
- con->v2.out_sign_kvec_cnt, hmac);
+ ret = ceph_hmac_sha256(con, con->v2.out_sign_kvecs,
+ con->v2.out_sign_kvec_cnt, hmac);
if (ret)
return ret;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index ae54f26709ca..03cf87d3b380 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -796,11 +796,19 @@ static __net_init int net_ns_net_init(struct net *net)
#ifdef CONFIG_NET_NS
net->ns.ops = &netns_operations;
#endif
+ if (net == &init_net) {
+ net->ns.inum = PROC_NET_INIT_INO;
+ return 0;
+ }
return ns_alloc_inum(&net->ns);
}
static __net_exit void net_ns_net_exit(struct net *net)
{
+ /*
+ * Initial network namespace doesn't exit so we don't need any
+ * special checks here.
+ */
ns_free_inum(&net->ns);
}
diff --git a/net/core/scm.c b/net/core/scm.c
index 0225bd94170f..072d5742440a 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -23,6 +23,8 @@
#include <linux/security.h>
#include <linux/pid_namespace.h>
#include <linux/pid.h>
+#include <uapi/linux/pidfd.h>
+#include <linux/pidfs.h>
#include <linux/nsproxy.h>
#include <linux/slab.h>
#include <linux/errqueue.h>
@@ -145,6 +147,22 @@ void __scm_destroy(struct scm_cookie *scm)
}
EXPORT_SYMBOL(__scm_destroy);
+static inline int scm_replace_pid(struct scm_cookie *scm, struct pid *pid)
+{
+ int err;
+
+ /* drop all previous references */
+ scm_destroy_cred(scm);
+
+ err = pidfs_register_pid(pid);
+ if (unlikely(err))
+ return err;
+
+ scm->pid = pid;
+ scm->creds.pid = pid_vnr(pid);
+ return 0;
+}
+
int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p)
{
const struct proto_ops *ops = READ_ONCE(sock->ops);
@@ -189,15 +207,21 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p)
if (err)
goto error;
- p->creds.pid = creds.pid;
if (!p->pid || pid_vnr(p->pid) != creds.pid) {
struct pid *pid;
err = -ESRCH;
pid = find_get_pid(creds.pid);
if (!pid)
goto error;
- put_pid(p->pid);
- p->pid = pid;
+
+ /* pass a struct pid reference from
+ * find_get_pid() to scm_replace_pid().
+ */
+ err = scm_replace_pid(p, pid);
+ if (err) {
+ put_pid(pid);
+ goto error;
+ }
}
err = -EINVAL;
@@ -459,7 +483,7 @@ static void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm)
if (!scm->pid)
return;
- pidfd = pidfd_prepare(scm->pid, 0, &pidfd_file);
+ pidfd = pidfd_prepare(scm->pid, PIDFD_STALE, &pidfd_file);
if (put_cmsg(msg, SOL_SOCKET, SCM_PIDFD, sizeof(int), &pidfd)) {
if (pidfd_file) {
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index 5a4fb2539b08..9a45aed508d1 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -54,6 +54,7 @@ static int ipcomp4_err(struct sk_buff *skb, u32 info)
}
/* We always hold one tunnel user reference to indicate a tunnel */
+static struct lock_class_key xfrm_state_lock_key;
static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x)
{
struct net *net = xs_net(x);
@@ -62,6 +63,7 @@ static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x)
t = xfrm_state_alloc(net);
if (!t)
goto out;
+ lockdep_set_class(&t->lock, &xfrm_state_lock_key);
t->id.proto = IPPROTO_IPIP;
t->id.spi = x->props.saddr.a4;
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index 0d31a8c108d4..f28cfd88eaf5 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -202,6 +202,9 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0)
goto out;
+ /* set the transport header to ESP */
+ skb_set_transport_header(skb, offset);
+
NAPI_GRO_CB(skb)->proto = IPPROTO_UDP;
pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 870a0bd6c2ba..940387572e06 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3367,7 +3367,7 @@ static int ipv6_generate_stable_address(struct in6_addr *address,
retry:
spin_lock_bh(&lock);
- sha1_init(digest);
+ sha1_init_raw(digest);
memset(&data, 0, sizeof(data));
memset(workspace, 0, sizeof(workspace));
memcpy(data.hwaddr, idev->dev->perm_addr, idev->dev->addr_len);
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index 72d4858dec18..8607569de34f 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -71,6 +71,7 @@ static int ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
return 0;
}
+static struct lock_class_key xfrm_state_lock_key;
static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x)
{
struct net *net = xs_net(x);
@@ -79,6 +80,7 @@ static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x)
t = xfrm_state_alloc(net);
if (!t)
goto out;
+ lockdep_set_class(&t->lock, &xfrm_state_lock_key);
t->id.proto = IPPROTO_IPV6;
t->id.spi = xfrm6_tunnel_alloc_spi(net, (xfrm_address_t *)&x->props.saddr);
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 841c81abaaf4..9005fc156a20 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -202,6 +202,9 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0)
goto out;
+ /* set the transport header to ESP */
+ skb_set_transport_header(skb, offset);
+
NAPI_GRO_CB(skb)->proto = IPPROTO_UDP;
pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index bf140ef781c1..5120a763da0d 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -334,8 +334,8 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net)
struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net);
unsigned int i;
+ xfrm_state_flush(net, IPSEC_PROTO_ANY, false);
xfrm_flush_gc();
- xfrm_state_flush(net, 0, false, true);
for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++)
WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i]));
diff --git a/net/key/af_key.c b/net/key/af_key.c
index efc2a91f4c48..b5d761700776 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1766,7 +1766,7 @@ static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_m
if (proto == 0)
return -EINVAL;
- err = xfrm_state_flush(net, proto, true, false);
+ err = xfrm_state_flush(net, proto, true);
err2 = unicast_flush_resp(sk, hdr);
if (err || err2) {
if (err == -ESRCH) /* empty table - go quietly */
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index f0eb70353744..2255355e51d3 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -536,9 +536,6 @@ destroy_class:
static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl)
{
- struct qfq_sched *q = qdisc_priv(sch);
-
- qfq_rm_from_agg(q, cl);
gen_kill_estimator(&cl->rate_est);
qdisc_put(cl->qdisc);
kfree(cl);
@@ -559,10 +556,11 @@ static int qfq_delete_class(struct Qdisc *sch, unsigned long arg,
qdisc_purge_queue(cl->qdisc);
qdisc_class_hash_remove(&q->clhash, &cl->common);
- qfq_destroy_class(sch, cl);
+ qfq_rm_from_agg(q, cl);
sch_tree_unlock(sch);
+ qfq_destroy_class(sch, cl);
return 0;
}
@@ -1503,6 +1501,7 @@ static void qfq_destroy_qdisc(struct Qdisc *sch)
for (i = 0; i < q->clhash.hashsize; i++) {
hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i],
common.hnode) {
+ qfq_rm_from_agg(q, cl);
qfq_destroy_class(sch, cl);
}
}
diff --git a/net/socket.c b/net/socket.c
index 9a0e720f0859..2cab805943c0 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -843,6 +843,52 @@ static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb,
sizeof(ts_pktinfo), &ts_pktinfo);
}
+bool skb_has_tx_timestamp(struct sk_buff *skb, const struct sock *sk)
+{
+ const struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
+ u32 tsflags = READ_ONCE(sk->sk_tsflags);
+
+ if (serr->ee.ee_errno != ENOMSG ||
+ serr->ee.ee_origin != SO_EE_ORIGIN_TIMESTAMPING)
+ return false;
+
+ /* software time stamp available and wanted */
+ if ((tsflags & SOF_TIMESTAMPING_SOFTWARE) && skb->tstamp)
+ return true;
+ /* hardware time stamps available and wanted */
+ return (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
+ skb_hwtstamps(skb)->hwtstamp;
+}
+
+int skb_get_tx_timestamp(struct sk_buff *skb, struct sock *sk,
+ struct timespec64 *ts)
+{
+ u32 tsflags = READ_ONCE(sk->sk_tsflags);
+ ktime_t hwtstamp;
+ int if_index = 0;
+
+ if ((tsflags & SOF_TIMESTAMPING_SOFTWARE) &&
+ ktime_to_timespec64_cond(skb->tstamp, ts))
+ return SOF_TIMESTAMPING_TX_SOFTWARE;
+
+ if (!(tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) ||
+ skb_is_swtx_tstamp(skb, false))
+ return -ENOENT;
+
+ if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NETDEV)
+ hwtstamp = get_timestamp(sk, skb, &if_index);
+ else
+ hwtstamp = skb_hwtstamps(skb)->hwtstamp;
+
+ if (tsflags & SOF_TIMESTAMPING_BIND_PHC)
+ hwtstamp = ptp_convert_timestamp(&hwtstamp,
+ READ_ONCE(sk->sk_bind_phc));
+ if (!ktime_to_timespec64_cond(hwtstamp, ts))
+ return -ENOENT;
+
+ return SOF_TIMESTAMPING_TX_HARDWARE;
+}
+
/*
* called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP)
*/
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 7b943fbafcc3..5c095cb8cb20 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -887,25 +887,16 @@ static void gss_pipe_dentry_destroy(struct dentry *dir,
struct rpc_pipe_dir_object *pdo)
{
struct gss_pipe *gss_pipe = pdo->pdo_data;
- struct rpc_pipe *pipe = gss_pipe->pipe;
- if (pipe->dentry != NULL) {
- rpc_unlink(pipe->dentry);
- pipe->dentry = NULL;
- }
+ rpc_unlink(gss_pipe->pipe);
}
static int gss_pipe_dentry_create(struct dentry *dir,
struct rpc_pipe_dir_object *pdo)
{
struct gss_pipe *p = pdo->pdo_data;
- struct dentry *dentry;
- dentry = rpc_mkpipe_dentry(dir, p->name, p->clnt, p->pipe);
- if (IS_ERR(dentry))
- return PTR_ERR(dentry);
- p->pipe->dentry = dentry;
- return 0;
+ return rpc_mkpipe_dentry(dir, p->name, p->clnt, p->pipe);
}
static const struct rpc_pipe_dir_object_ops gss_pipe_dir_object_ops = {
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 73a90ad873fb..e82212f6b562 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -1628,7 +1628,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp)
int ret;
struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id);
- rqstp->rq_auth_stat = rpc_autherr_badcred;
+ rqstp->rq_auth_stat = rpc_autherr_failed;
if (!svcdata)
svcdata = kmalloc(sizeof(*svcdata), GFP_KERNEL);
if (!svcdata)
@@ -1638,6 +1638,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp)
svcdata->rsci = NULL;
gc = &svcdata->clcred;
+ rqstp->rq_auth_stat = rpc_autherr_badcred;
if (!svcauth_gss_decode_credbody(&rqstp->rq_arg_stream, gc, &rpcstart))
goto auth_err;
if (gc->gc_v != RPC_GSS_VERSION)
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 21426c3049d3..8ca354ecfd02 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -112,47 +112,46 @@ static void rpc_clnt_remove_pipedir(struct rpc_clnt *clnt)
}
}
-static struct dentry *rpc_setup_pipedir_sb(struct super_block *sb,
+static int rpc_setup_pipedir_sb(struct super_block *sb,
struct rpc_clnt *clnt)
{
static uint32_t clntid;
const char *dir_name = clnt->cl_program->pipe_dir_name;
char name[15];
- struct dentry *dir, *dentry;
+ struct dentry *dir;
+ int err;
dir = rpc_d_lookup_sb(sb, dir_name);
if (dir == NULL) {
pr_info("RPC: pipefs directory doesn't exist: %s\n", dir_name);
- return dir;
+ return -ENOENT;
}
for (;;) {
snprintf(name, sizeof(name), "clnt%x", (unsigned int)clntid++);
name[sizeof(name) - 1] = '\0';
- dentry = rpc_create_client_dir(dir, name, clnt);
- if (!IS_ERR(dentry))
+ err = rpc_create_client_dir(dir, name, clnt);
+ if (!err)
break;
- if (dentry == ERR_PTR(-EEXIST))
+ if (err == -EEXIST)
continue;
printk(KERN_INFO "RPC: Couldn't create pipefs entry"
- " %s/%s, error %ld\n",
- dir_name, name, PTR_ERR(dentry));
+ " %s/%s, error %d\n",
+ dir_name, name, err);
break;
}
dput(dir);
- return dentry;
+ return err;
}
static int
rpc_setup_pipedir(struct super_block *pipefs_sb, struct rpc_clnt *clnt)
{
- struct dentry *dentry;
-
clnt->pipefs_sb = pipefs_sb;
if (clnt->cl_program->pipe_dir_name != NULL) {
- dentry = rpc_setup_pipedir_sb(pipefs_sb, clnt);
- if (IS_ERR(dentry))
- return PTR_ERR(dentry);
+ int err = rpc_setup_pipedir_sb(pipefs_sb, clnt);
+ if (err && err != -ENOENT)
+ return err;
}
return 0;
}
@@ -180,16 +179,9 @@ static int rpc_clnt_skip_event(struct rpc_clnt *clnt, unsigned long event)
static int __rpc_clnt_handle_event(struct rpc_clnt *clnt, unsigned long event,
struct super_block *sb)
{
- struct dentry *dentry;
-
switch (event) {
case RPC_PIPEFS_MOUNT:
- dentry = rpc_setup_pipedir_sb(sb, clnt);
- if (!dentry)
- return -ENOENT;
- if (IS_ERR(dentry))
- return PTR_ERR(dentry);
- break;
+ return rpc_setup_pipedir_sb(sb, clnt);
case RPC_PIPEFS_UMOUNT:
__rpc_clnt_remove_pipedir(clnt);
break;
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 98f78cd55905..0bd1df2ebb47 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -168,8 +168,9 @@ rpc_inode_setowner(struct inode *inode, void *private)
}
static void
-rpc_close_pipes(struct inode *inode)
+rpc_close_pipes(struct dentry *dentry)
{
+ struct inode *inode = dentry->d_inode;
struct rpc_pipe *pipe = RPC_I(inode)->pipe;
int need_release;
LIST_HEAD(free_list);
@@ -484,60 +485,6 @@ rpc_get_inode(struct super_block *sb, umode_t mode)
return inode;
}
-static int __rpc_create_common(struct inode *dir, struct dentry *dentry,
- umode_t mode,
- const struct file_operations *i_fop,
- void *private)
-{
- struct inode *inode;
-
- d_drop(dentry);
- inode = rpc_get_inode(dir->i_sb, mode);
- if (!inode)
- goto out_err;
- inode->i_ino = iunique(dir->i_sb, 100);
- if (i_fop)
- inode->i_fop = i_fop;
- if (private)
- rpc_inode_setowner(inode, private);
- d_add(dentry, inode);
- return 0;
-out_err:
- printk(KERN_WARNING "%s: %s failed to allocate inode for dentry %pd\n",
- __FILE__, __func__, dentry);
- dput(dentry);
- return -ENOMEM;
-}
-
-static int __rpc_create(struct inode *dir, struct dentry *dentry,
- umode_t mode,
- const struct file_operations *i_fop,
- void *private)
-{
- int err;
-
- err = __rpc_create_common(dir, dentry, S_IFREG | mode, i_fop, private);
- if (err)
- return err;
- fsnotify_create(dir, dentry);
- return 0;
-}
-
-static int __rpc_mkdir(struct inode *dir, struct dentry *dentry,
- umode_t mode,
- const struct file_operations *i_fop,
- void *private)
-{
- int err;
-
- err = __rpc_create_common(dir, dentry, S_IFDIR | mode, i_fop, private);
- if (err)
- return err;
- inc_nlink(dir);
- fsnotify_mkdir(dir, dentry);
- return 0;
-}
-
static void
init_pipe(struct rpc_pipe *pipe)
{
@@ -574,119 +521,60 @@ struct rpc_pipe *rpc_mkpipe_data(const struct rpc_pipe_ops *ops, int flags)
}
EXPORT_SYMBOL_GPL(rpc_mkpipe_data);
-static int __rpc_mkpipe_dentry(struct inode *dir, struct dentry *dentry,
- umode_t mode,
- const struct file_operations *i_fop,
- void *private,
- struct rpc_pipe *pipe)
+static int rpc_new_file(struct dentry *parent,
+ const char *name,
+ umode_t mode,
+ const struct file_operations *i_fop,
+ void *private)
{
- struct rpc_inode *rpci;
- int err;
+ struct dentry *dentry = simple_start_creating(parent, name);
+ struct inode *dir = parent->d_inode;
+ struct inode *inode;
- err = __rpc_create_common(dir, dentry, S_IFIFO | mode, i_fop, private);
- if (err)
- return err;
- rpci = RPC_I(d_inode(dentry));
- rpci->private = private;
- rpci->pipe = pipe;
+ if (IS_ERR(dentry))
+ return PTR_ERR(dentry);
+
+ inode = rpc_get_inode(dir->i_sb, S_IFREG | mode);
+ if (unlikely(!inode)) {
+ dput(dentry);
+ inode_unlock(dir);
+ return -ENOMEM;
+ }
+ inode->i_ino = iunique(dir->i_sb, 100);
+ if (i_fop)
+ inode->i_fop = i_fop;
+ rpc_inode_setowner(inode, private);
+ d_instantiate(dentry, inode);
fsnotify_create(dir, dentry);
+ inode_unlock(dir);
return 0;
}
-static int __rpc_rmdir(struct inode *dir, struct dentry *dentry)
-{
- int ret;
-
- dget(dentry);
- ret = simple_rmdir(dir, dentry);
- d_drop(dentry);
- if (!ret)
- fsnotify_rmdir(dir, dentry);
- dput(dentry);
- return ret;
-}
-
-static int __rpc_unlink(struct inode *dir, struct dentry *dentry)
-{
- int ret;
-
- dget(dentry);
- ret = simple_unlink(dir, dentry);
- d_drop(dentry);
- if (!ret)
- fsnotify_unlink(dir, dentry);
- dput(dentry);
- return ret;
-}
-
-static int __rpc_rmpipe(struct inode *dir, struct dentry *dentry)
+static struct dentry *rpc_new_dir(struct dentry *parent,
+ const char *name,
+ umode_t mode)
{
- struct inode *inode = d_inode(dentry);
-
- rpc_close_pipes(inode);
- return __rpc_unlink(dir, dentry);
-}
+ struct dentry *dentry = simple_start_creating(parent, name);
+ struct inode *dir = parent->d_inode;
+ struct inode *inode;
-static struct dentry *__rpc_lookup_create_exclusive(struct dentry *parent,
- const char *name)
-{
- struct qstr q = QSTR(name);
- struct dentry *dentry = try_lookup_noperm(&q, parent);
- if (!dentry) {
- dentry = d_alloc(parent, &q);
- if (!dentry)
- return ERR_PTR(-ENOMEM);
- }
- if (d_really_is_negative(dentry))
+ if (IS_ERR(dentry))
return dentry;
- dput(dentry);
- return ERR_PTR(-EEXIST);
-}
-/*
- * FIXME: This probably has races.
- */
-static void __rpc_depopulate(struct dentry *parent,
- const struct rpc_filelist *files,
- int start, int eof)
-{
- struct inode *dir = d_inode(parent);
- struct dentry *dentry;
- struct qstr name;
- int i;
-
- for (i = start; i < eof; i++) {
- name.name = files[i].name;
- name.len = strlen(files[i].name);
- dentry = try_lookup_noperm(&name, parent);
-
- if (dentry == NULL)
- continue;
- if (d_really_is_negative(dentry))
- goto next;
- switch (d_inode(dentry)->i_mode & S_IFMT) {
- default:
- BUG();
- case S_IFREG:
- __rpc_unlink(dir, dentry);
- break;
- case S_IFDIR:
- __rpc_rmdir(dir, dentry);
- }
-next:
+ inode = rpc_get_inode(dir->i_sb, S_IFDIR | mode);
+ if (unlikely(!inode)) {
dput(dentry);
+ inode_unlock(dir);
+ return ERR_PTR(-ENOMEM);
}
-}
-static void rpc_depopulate(struct dentry *parent,
- const struct rpc_filelist *files,
- int start, int eof)
-{
- struct inode *dir = d_inode(parent);
-
- inode_lock_nested(dir, I_MUTEX_CHILD);
- __rpc_depopulate(parent, files, start, eof);
+ inode->i_ino = iunique(dir->i_sb, 100);
+ inc_nlink(dir);
+ d_instantiate(dentry, inode);
+ fsnotify_mkdir(dir, dentry);
inode_unlock(dir);
+
+ return dentry;
}
static int rpc_populate(struct dentry *parent,
@@ -694,92 +582,39 @@ static int rpc_populate(struct dentry *parent,
int start, int eof,
void *private)
{
- struct inode *dir = d_inode(parent);
struct dentry *dentry;
int i, err;
- inode_lock(dir);
for (i = start; i < eof; i++) {
- dentry = __rpc_lookup_create_exclusive(parent, files[i].name);
- err = PTR_ERR(dentry);
- if (IS_ERR(dentry))
- goto out_bad;
switch (files[i].mode & S_IFMT) {
default:
BUG();
case S_IFREG:
- err = __rpc_create(dir, dentry,
+ err = rpc_new_file(parent,
+ files[i].name,
files[i].mode,
files[i].i_fop,
private);
+ if (err)
+ goto out_bad;
break;
case S_IFDIR:
- err = __rpc_mkdir(dir, dentry,
- files[i].mode,
- NULL,
- private);
+ dentry = rpc_new_dir(parent,
+ files[i].name,
+ files[i].mode);
+ if (IS_ERR(dentry)) {
+ err = PTR_ERR(dentry);
+ goto out_bad;
+ }
}
- if (err != 0)
- goto out_bad;
}
- inode_unlock(dir);
return 0;
out_bad:
- __rpc_depopulate(parent, files, start, eof);
- inode_unlock(dir);
printk(KERN_WARNING "%s: %s failed to populate directory %pd\n",
__FILE__, __func__, parent);
return err;
}
-static struct dentry *rpc_mkdir_populate(struct dentry *parent,
- const char *name, umode_t mode, void *private,
- int (*populate)(struct dentry *, void *), void *args_populate)
-{
- struct dentry *dentry;
- struct inode *dir = d_inode(parent);
- int error;
-
- inode_lock_nested(dir, I_MUTEX_PARENT);
- dentry = __rpc_lookup_create_exclusive(parent, name);
- if (IS_ERR(dentry))
- goto out;
- error = __rpc_mkdir(dir, dentry, mode, NULL, private);
- if (error != 0)
- goto out_err;
- if (populate != NULL) {
- error = populate(dentry, args_populate);
- if (error)
- goto err_rmdir;
- }
-out:
- inode_unlock(dir);
- return dentry;
-err_rmdir:
- __rpc_rmdir(dir, dentry);
-out_err:
- dentry = ERR_PTR(error);
- goto out;
-}
-
-static int rpc_rmdir_depopulate(struct dentry *dentry,
- void (*depopulate)(struct dentry *))
-{
- struct dentry *parent;
- struct inode *dir;
- int error;
-
- parent = dget_parent(dentry);
- dir = d_inode(parent);
- inode_lock_nested(dir, I_MUTEX_PARENT);
- if (depopulate != NULL)
- depopulate(dentry);
- error = __rpc_rmdir(dir, dentry);
- inode_unlock(dir);
- dput(parent);
- return error;
-}
-
/**
* rpc_mkpipe_dentry - make an rpc_pipefs file for kernel<->userspace
* communication
@@ -799,11 +634,13 @@ static int rpc_rmdir_depopulate(struct dentry *dentry,
* The @private argument passed here will be available to all these methods
* from the file pointer, via RPC_I(file_inode(file))->private.
*/
-struct dentry *rpc_mkpipe_dentry(struct dentry *parent, const char *name,
+int rpc_mkpipe_dentry(struct dentry *parent, const char *name,
void *private, struct rpc_pipe *pipe)
{
- struct dentry *dentry;
struct inode *dir = d_inode(parent);
+ struct dentry *dentry;
+ struct inode *inode;
+ struct rpc_inode *rpci;
umode_t umode = S_IFIFO | 0600;
int err;
@@ -812,48 +649,53 @@ struct dentry *rpc_mkpipe_dentry(struct dentry *parent, const char *name,
if (pipe->ops->downcall == NULL)
umode &= ~0222;
- inode_lock_nested(dir, I_MUTEX_PARENT);
- dentry = __rpc_lookup_create_exclusive(parent, name);
- if (IS_ERR(dentry))
- goto out;
- err = __rpc_mkpipe_dentry(dir, dentry, umode, &rpc_pipe_fops,
- private, pipe);
- if (err)
- goto out_err;
-out:
+ dentry = simple_start_creating(parent, name);
+ if (IS_ERR(dentry)) {
+ err = PTR_ERR(dentry);
+ goto failed;
+ }
+
+ inode = rpc_get_inode(dir->i_sb, umode);
+ if (unlikely(!inode)) {
+ dput(dentry);
+ inode_unlock(dir);
+ err = -ENOMEM;
+ goto failed;
+ }
+ inode->i_ino = iunique(dir->i_sb, 100);
+ inode->i_fop = &rpc_pipe_fops;
+ rpci = RPC_I(inode);
+ rpci->private = private;
+ rpci->pipe = pipe;
+ rpc_inode_setowner(inode, private);
+ d_instantiate(dentry, inode);
+ pipe->dentry = dentry;
+ fsnotify_create(dir, dentry);
inode_unlock(dir);
- return dentry;
-out_err:
- dentry = ERR_PTR(err);
- printk(KERN_WARNING "%s: %s() failed to create pipe %pd/%s (errno = %d)\n",
- __FILE__, __func__, parent, name,
- err);
- goto out;
+ return 0;
+
+failed:
+ pr_warn("%s() failed to create pipe %pd/%s (errno = %d)\n",
+ __func__, parent, name, err);
+ return err;
}
EXPORT_SYMBOL_GPL(rpc_mkpipe_dentry);
/**
* rpc_unlink - remove a pipe
- * @dentry: dentry for the pipe, as returned from rpc_mkpipe
+ * @pipe: the pipe to be removed
*
* After this call, lookups will no longer find the pipe, and any
* attempts to read or write using preexisting opens of the pipe will
* return -EPIPE.
*/
-int
-rpc_unlink(struct dentry *dentry)
+void
+rpc_unlink(struct rpc_pipe *pipe)
{
- struct dentry *parent;
- struct inode *dir;
- int error = 0;
-
- parent = dget_parent(dentry);
- dir = d_inode(parent);
- inode_lock_nested(dir, I_MUTEX_PARENT);
- error = __rpc_rmpipe(dir, dentry);
- inode_unlock(dir);
- dput(parent);
- return error;
+ if (pipe->dentry) {
+ simple_recursive_removal(pipe->dentry, rpc_close_pipes);
+ pipe->dentry = NULL;
+ }
}
EXPORT_SYMBOL_GPL(rpc_unlink);
@@ -1010,31 +852,6 @@ rpc_destroy_pipe_dir_objects(struct rpc_pipe_dir_head *pdh)
pdo->pdo_ops->destroy(dir, pdo);
}
-enum {
- RPCAUTH_info,
- RPCAUTH_EOF
-};
-
-static const struct rpc_filelist authfiles[] = {
- [RPCAUTH_info] = {
- .name = "info",
- .i_fop = &rpc_info_operations,
- .mode = S_IFREG | 0400,
- },
-};
-
-static int rpc_clntdir_populate(struct dentry *dentry, void *private)
-{
- return rpc_populate(dentry,
- authfiles, RPCAUTH_info, RPCAUTH_EOF,
- private);
-}
-
-static void rpc_clntdir_depopulate(struct dentry *dentry)
-{
- rpc_depopulate(dentry, authfiles, RPCAUTH_info, RPCAUTH_EOF);
-}
-
/**
* rpc_create_client_dir - Create a new rpc_client directory in rpc_pipefs
* @dentry: the parent of new directory
@@ -1046,19 +863,27 @@ static void rpc_clntdir_depopulate(struct dentry *dentry)
* information about the client, together with any "pipes" that may
* later be created using rpc_mkpipe().
*/
-struct dentry *rpc_create_client_dir(struct dentry *dentry,
- const char *name,
- struct rpc_clnt *rpc_client)
+int rpc_create_client_dir(struct dentry *dentry,
+ const char *name,
+ struct rpc_clnt *rpc_client)
{
struct dentry *ret;
+ int err;
- ret = rpc_mkdir_populate(dentry, name, 0555, NULL,
- rpc_clntdir_populate, rpc_client);
- if (!IS_ERR(ret)) {
- rpc_client->cl_pipedir_objects.pdh_dentry = ret;
- rpc_create_pipe_dir_objects(&rpc_client->cl_pipedir_objects);
+ ret = rpc_new_dir(dentry, name, 0555);
+ if (IS_ERR(ret))
+ return PTR_ERR(ret);
+ err = rpc_new_file(ret, "info", S_IFREG | 0400,
+ &rpc_info_operations, rpc_client);
+ if (err) {
+ pr_warn("%s failed to populate directory %pd\n",
+ __func__, ret);
+ simple_recursive_removal(ret, NULL);
+ return err;
}
- return ret;
+ rpc_client->cl_pipedir_objects.pdh_dentry = ret;
+ rpc_create_pipe_dir_objects(&rpc_client->cl_pipedir_objects);
+ return 0;
}
/**
@@ -1073,7 +898,8 @@ int rpc_remove_client_dir(struct rpc_clnt *rpc_client)
return 0;
rpc_destroy_pipe_dir_objects(&rpc_client->cl_pipedir_objects);
rpc_client->cl_pipedir_objects.pdh_dentry = NULL;
- return rpc_rmdir_depopulate(dentry, rpc_clntdir_depopulate);
+ simple_recursive_removal(dentry, NULL);
+ return 0;
}
static const struct rpc_filelist cache_pipefs_files[3] = {
@@ -1094,28 +920,25 @@ static const struct rpc_filelist cache_pipefs_files[3] = {
},
};
-static int rpc_cachedir_populate(struct dentry *dentry, void *private)
-{
- return rpc_populate(dentry,
- cache_pipefs_files, 0, 3,
- private);
-}
-
-static void rpc_cachedir_depopulate(struct dentry *dentry)
-{
- rpc_depopulate(dentry, cache_pipefs_files, 0, 3);
-}
-
struct dentry *rpc_create_cache_dir(struct dentry *parent, const char *name,
umode_t umode, struct cache_detail *cd)
{
- return rpc_mkdir_populate(parent, name, umode, NULL,
- rpc_cachedir_populate, cd);
+ struct dentry *dentry;
+
+ dentry = rpc_new_dir(parent, name, umode);
+ if (!IS_ERR(dentry)) {
+ int error = rpc_populate(dentry, cache_pipefs_files, 0, 3, cd);
+ if (error) {
+ simple_recursive_removal(dentry, NULL);
+ return ERR_PTR(error);
+ }
+ }
+ return dentry;
}
void rpc_remove_cache_dir(struct dentry *dentry)
{
- rpc_rmdir_depopulate(dentry, rpc_cachedir_depopulate);
+ simple_recursive_removal(dentry, NULL);
}
/*
@@ -1141,7 +964,6 @@ enum {
RPCAUTH_nfsd4_cb,
RPCAUTH_cache,
RPCAUTH_nfsd,
- RPCAUTH_gssd,
RPCAUTH_RootEOF
};
@@ -1178,10 +1000,6 @@ static const struct rpc_filelist files[] = {
.name = "nfsd",
.mode = S_IFDIR | 0555,
},
- [RPCAUTH_gssd] = {
- .name = "gssd",
- .mode = S_IFDIR | 0555,
- },
};
/*
@@ -1241,13 +1059,6 @@ void rpc_put_sb_net(const struct net *net)
}
EXPORT_SYMBOL_GPL(rpc_put_sb_net);
-static const struct rpc_filelist gssd_dummy_clnt_dir[] = {
- [0] = {
- .name = "clntXX",
- .mode = S_IFDIR | 0555,
- },
-};
-
static ssize_t
dummy_downcall(struct file *filp, const char __user *src, size_t len)
{
@@ -1276,14 +1087,6 @@ rpc_dummy_info_show(struct seq_file *m, void *v)
}
DEFINE_SHOW_ATTRIBUTE(rpc_dummy_info);
-static const struct rpc_filelist gssd_dummy_info_file[] = {
- [0] = {
- .name = "info",
- .i_fop = &rpc_dummy_info_fops,
- .mode = S_IFREG | 0400,
- },
-};
-
/**
* rpc_gssd_dummy_populate - create a dummy gssd pipe
* @root: root of the rpc_pipefs filesystem
@@ -1292,69 +1095,32 @@ static const struct rpc_filelist gssd_dummy_info_file[] = {
* Create a dummy set of directories and a pipe that gssd can hold open to
* indicate that it is up and running.
*/
-static struct dentry *
+static int
rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data)
{
- int ret = 0;
- struct dentry *gssd_dentry;
- struct dentry *clnt_dentry = NULL;
- struct dentry *pipe_dentry = NULL;
-
- /* We should never get this far if "gssd" doesn't exist */
- gssd_dentry = try_lookup_noperm(&QSTR(files[RPCAUTH_gssd].name), root);
- if (!gssd_dentry)
- return ERR_PTR(-ENOENT);
-
- ret = rpc_populate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1, NULL);
- if (ret) {
- pipe_dentry = ERR_PTR(ret);
- goto out;
- }
+ struct dentry *gssd_dentry, *clnt_dentry;
+ int err;
- clnt_dentry = try_lookup_noperm(&QSTR(gssd_dummy_clnt_dir[0].name),
- gssd_dentry);
- if (!clnt_dentry) {
- __rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1);
- pipe_dentry = ERR_PTR(-ENOENT);
- goto out;
- }
+ gssd_dentry = rpc_new_dir(root, "gssd", 0555);
+ if (IS_ERR(gssd_dentry))
+ return -ENOENT;
- ret = rpc_populate(clnt_dentry, gssd_dummy_info_file, 0, 1, NULL);
- if (ret) {
- __rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1);
- pipe_dentry = ERR_PTR(ret);
- goto out;
- }
+ clnt_dentry = rpc_new_dir(gssd_dentry, "clntXX", 0555);
+ if (IS_ERR(clnt_dentry))
+ return -ENOENT;
- pipe_dentry = rpc_mkpipe_dentry(clnt_dentry, "gssd", NULL, pipe_data);
- if (IS_ERR(pipe_dentry)) {
- __rpc_depopulate(clnt_dentry, gssd_dummy_info_file, 0, 1);
- __rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1);
- }
-out:
- dput(clnt_dentry);
- dput(gssd_dentry);
- return pipe_dentry;
-}
-
-static void
-rpc_gssd_dummy_depopulate(struct dentry *pipe_dentry)
-{
- struct dentry *clnt_dir = pipe_dentry->d_parent;
- struct dentry *gssd_dir = clnt_dir->d_parent;
-
- dget(pipe_dentry);
- __rpc_rmpipe(d_inode(clnt_dir), pipe_dentry);
- __rpc_depopulate(clnt_dir, gssd_dummy_info_file, 0, 1);
- __rpc_depopulate(gssd_dir, gssd_dummy_clnt_dir, 0, 1);
- dput(pipe_dentry);
+ err = rpc_new_file(clnt_dentry, "info", 0400,
+ &rpc_dummy_info_fops, NULL);
+ if (!err)
+ err = rpc_mkpipe_dentry(clnt_dentry, "gssd", NULL, pipe_data);
+ return err;
}
static int
rpc_fill_super(struct super_block *sb, struct fs_context *fc)
{
struct inode *inode;
- struct dentry *root, *gssd_dentry;
+ struct dentry *root;
struct net *net = sb->s_fs_info;
struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
int err;
@@ -1363,7 +1129,7 @@ rpc_fill_super(struct super_block *sb, struct fs_context *fc)
sb->s_blocksize_bits = PAGE_SHIFT;
sb->s_magic = RPCAUTH_GSSMAGIC;
sb->s_op = &s_ops;
- sb->s_d_op = &simple_dentry_operations;
+ sb->s_d_flags = DCACHE_DONTCACHE;
sb->s_time_gran = 1;
inode = rpc_get_inode(sb, S_IFDIR | 0555);
@@ -1373,11 +1139,9 @@ rpc_fill_super(struct super_block *sb, struct fs_context *fc)
if (rpc_populate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF, NULL))
return -ENOMEM;
- gssd_dentry = rpc_gssd_dummy_populate(root, sn->gssd_dummy);
- if (IS_ERR(gssd_dentry)) {
- __rpc_depopulate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF);
- return PTR_ERR(gssd_dentry);
- }
+ err = rpc_gssd_dummy_populate(root, sn->gssd_dummy);
+ if (err)
+ return err;
dprintk("RPC: sending pipefs MOUNT notification for net %x%s\n",
net->ns.inum, NET_NAME(net));
@@ -1386,18 +1150,6 @@ rpc_fill_super(struct super_block *sb, struct fs_context *fc)
err = blocking_notifier_call_chain(&rpc_pipefs_notifier_list,
RPC_PIPEFS_MOUNT,
sb);
- if (err)
- goto err_depopulate;
- mutex_unlock(&sn->pipefs_sb_lock);
- return 0;
-
-err_depopulate:
- rpc_gssd_dummy_depopulate(gssd_dentry);
- blocking_notifier_call_chain(&rpc_pipefs_notifier_list,
- RPC_PIPEFS_UMOUNT,
- sb);
- sn->pipefs_sb = NULL;
- __rpc_depopulate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF);
mutex_unlock(&sn->pipefs_sb_lock);
return err;
}
diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c
index 1b2b84feeec6..4e92e2a50168 100644
--- a/net/sunrpc/socklib.c
+++ b/net/sunrpc/socklib.c
@@ -27,97 +27,60 @@
struct xdr_skb_reader {
struct sk_buff *skb;
unsigned int offset;
+ bool need_checksum;
size_t count;
__wsum csum;
};
-typedef size_t (*xdr_skb_read_actor)(struct xdr_skb_reader *desc, void *to,
- size_t len);
-
/**
* xdr_skb_read_bits - copy some data bits from skb to internal buffer
* @desc: sk_buff copy helper
* @to: copy destination
* @len: number of bytes to copy
*
- * Possibly called several times to iterate over an sk_buff and copy
- * data out of it.
+ * Possibly called several times to iterate over an sk_buff and copy data out of
+ * it.
*/
static size_t
xdr_skb_read_bits(struct xdr_skb_reader *desc, void *to, size_t len)
{
- if (len > desc->count)
- len = desc->count;
- if (unlikely(skb_copy_bits(desc->skb, desc->offset, to, len)))
- return 0;
- desc->count -= len;
- desc->offset += len;
- return len;
-}
+ len = min(len, desc->count);
+
+ if (desc->need_checksum) {
+ __wsum csum;
+
+ csum = skb_copy_and_csum_bits(desc->skb, desc->offset, to, len);
+ desc->csum = csum_block_add(desc->csum, csum, desc->offset);
+ } else {
+ if (unlikely(skb_copy_bits(desc->skb, desc->offset, to, len)))
+ return 0;
+ }
-/**
- * xdr_skb_read_and_csum_bits - copy and checksum from skb to buffer
- * @desc: sk_buff copy helper
- * @to: copy destination
- * @len: number of bytes to copy
- *
- * Same as skb_read_bits, but calculate a checksum at the same time.
- */
-static size_t xdr_skb_read_and_csum_bits(struct xdr_skb_reader *desc, void *to, size_t len)
-{
- unsigned int pos;
- __wsum csum2;
-
- if (len > desc->count)
- len = desc->count;
- pos = desc->offset;
- csum2 = skb_copy_and_csum_bits(desc->skb, pos, to, len);
- desc->csum = csum_block_add(desc->csum, csum2, pos);
desc->count -= len;
desc->offset += len;
return len;
}
-/**
- * xdr_partial_copy_from_skb - copy data out of an skb
- * @xdr: target XDR buffer
- * @base: starting offset
- * @desc: sk_buff copy helper
- * @copy_actor: virtual method for copying data
- *
- */
static ssize_t
-xdr_partial_copy_from_skb(struct xdr_buf *xdr, unsigned int base, struct xdr_skb_reader *desc, xdr_skb_read_actor copy_actor)
+xdr_partial_copy_from_skb(struct xdr_buf *xdr, struct xdr_skb_reader *desc)
{
- struct page **ppage = xdr->pages;
- unsigned int len, pglen = xdr->page_len;
- ssize_t copied = 0;
- size_t ret;
-
- len = xdr->head[0].iov_len;
- if (base < len) {
- len -= base;
- ret = copy_actor(desc, (char *)xdr->head[0].iov_base + base, len);
- copied += ret;
- if (ret != len || !desc->count)
- goto out;
- base = 0;
- } else
- base -= len;
-
- if (unlikely(pglen == 0))
- goto copy_tail;
- if (unlikely(base >= pglen)) {
- base -= pglen;
- goto copy_tail;
- }
- if (base || xdr->page_base) {
- pglen -= base;
- base += xdr->page_base;
- ppage += base >> PAGE_SHIFT;
- base &= ~PAGE_MASK;
- }
- do {
+ struct page **ppage = xdr->pages + (xdr->page_base >> PAGE_SHIFT);
+ unsigned int poff = xdr->page_base & ~PAGE_MASK;
+ unsigned int pglen = xdr->page_len;
+ ssize_t copied = 0;
+ size_t ret;
+
+ if (xdr->head[0].iov_len == 0)
+ return 0;
+
+ ret = xdr_skb_read_bits(desc, xdr->head[0].iov_base,
+ xdr->head[0].iov_len);
+ if (ret != xdr->head[0].iov_len || !desc->count)
+ return ret;
+ copied += ret;
+
+ while (pglen) {
+ unsigned int len = min(PAGE_SIZE - poff, pglen);
char *kaddr;
/* ACL likes to be lazy in allocating pages - ACLs
@@ -126,36 +89,29 @@ xdr_partial_copy_from_skb(struct xdr_buf *xdr, unsigned int base, struct xdr_skb
*ppage = alloc_page(GFP_NOWAIT | __GFP_NOWARN);
if (unlikely(*ppage == NULL)) {
if (copied == 0)
- copied = -ENOMEM;
- goto out;
+ return -ENOMEM;
+ return copied;
}
}
- len = PAGE_SIZE;
kaddr = kmap_atomic(*ppage);
- if (base) {
- len -= base;
- if (pglen < len)
- len = pglen;
- ret = copy_actor(desc, kaddr + base, len);
- base = 0;
- } else {
- if (pglen < len)
- len = pglen;
- ret = copy_actor(desc, kaddr, len);
- }
+ ret = xdr_skb_read_bits(desc, kaddr + poff, len);
flush_dcache_page(*ppage);
kunmap_atomic(kaddr);
+
copied += ret;
if (ret != len || !desc->count)
- goto out;
+ return copied;
ppage++;
- } while ((pglen -= len) != 0);
-copy_tail:
- len = xdr->tail[0].iov_len;
- if (base < len)
- copied += copy_actor(desc, (char *)xdr->tail[0].iov_base + base, len - base);
-out:
+ pglen -= len;
+ poff = 0;
+ }
+
+ if (xdr->tail[0].iov_len) {
+ copied += xdr_skb_read_bits(desc, xdr->tail[0].iov_base,
+ xdr->tail[0].iov_len);
+ }
+
return copied;
}
@@ -169,17 +125,22 @@ out:
*/
int csum_partial_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb)
{
- struct xdr_skb_reader desc;
-
- desc.skb = skb;
- desc.offset = 0;
- desc.count = skb->len - desc.offset;
+ struct xdr_skb_reader desc = {
+ .skb = skb,
+ .count = skb->len - desc.offset,
+ };
- if (skb_csum_unnecessary(skb))
- goto no_checksum;
+ if (skb_csum_unnecessary(skb)) {
+ if (xdr_partial_copy_from_skb(xdr, &desc) < 0)
+ return -1;
+ if (desc.count)
+ return -1;
+ return 0;
+ }
+ desc.need_checksum = true;
desc.csum = csum_partial(skb->data, desc.offset, skb->csum);
- if (xdr_partial_copy_from_skb(xdr, 0, &desc, xdr_skb_read_and_csum_bits) < 0)
+ if (xdr_partial_copy_from_skb(xdr, &desc) < 0)
return -1;
if (desc.offset != skb->len) {
__wsum csum2;
@@ -194,14 +155,7 @@ int csum_partial_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb)
!skb->csum_complete_sw)
netdev_rx_csum_fault(skb->dev, skb);
return 0;
-no_checksum:
- if (xdr_partial_copy_from_skb(xdr, 0, &desc, xdr_skb_read_bits) < 0)
- return -1;
- if (desc.count)
- return -1;
- return 0;
}
-EXPORT_SYMBOL_GPL(csum_partial_copy_to_xdr);
static inline int xprt_sendmsg(struct socket *sock, struct msghdr *msg,
size_t seek)
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 9c93b854e809..b1fab3a69544 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -751,14 +751,16 @@ void svc_pool_wake_idle_thread(struct svc_pool *pool)
WRITE_ONCE(rqstp->rq_qtime, ktime_get());
if (!task_is_running(rqstp->rq_task)) {
wake_up_process(rqstp->rq_task);
- trace_svc_wake_up(rqstp->rq_task->pid);
+ trace_svc_pool_thread_wake(pool, rqstp->rq_task->pid);
percpu_counter_inc(&pool->sp_threads_woken);
+ } else {
+ trace_svc_pool_thread_running(pool, rqstp->rq_task->pid);
}
rcu_read_unlock();
return;
}
rcu_read_unlock();
-
+ trace_svc_pool_thread_noidle(pool, 0);
}
EXPORT_SYMBOL_GPL(svc_pool_wake_idle_thread);
@@ -1332,6 +1334,9 @@ svc_process_common(struct svc_rqst *rqstp)
int pr, rc;
__be32 *p;
+ /* Reset the accept_stat for the RPC */
+ rqstp->rq_accept_statp = NULL;
+
/* Will be turned off only when NFSv4 Sessions are used */
set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
clear_bit(RQ_DROPME, &rqstp->rq_flags);
@@ -1373,8 +1378,6 @@ svc_process_common(struct svc_rqst *rqstp)
case SVC_GARBAGE:
rqstp->rq_auth_stat = rpc_autherr_badcred;
goto err_bad_auth;
- case SVC_SYSERR:
- goto err_system_err;
case SVC_DENIED:
goto err_bad_auth;
case SVC_CLOSE:
@@ -1385,7 +1388,8 @@ svc_process_common(struct svc_rqst *rqstp)
goto sendit;
default:
pr_warn_once("Unexpected svc_auth_status (%d)\n", auth_res);
- goto err_system_err;
+ rqstp->rq_auth_stat = rpc_autherr_failed;
+ goto err_bad_auth;
}
if (progp == NULL)
@@ -1512,12 +1516,6 @@ err_bad_proc:
serv->sv_stats->rpcbadfmt++;
*rqstp->rq_accept_statp = rpc_proc_unavail;
goto sendit;
-
-err_system_err:
- if (serv->sv_stats)
- serv->sv_stats->rpcbadfmt++;
- *rqstp->rq_accept_statp = rpc_system_err;
- goto sendit;
}
/*
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index e1c85123b445..46c156b121db 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1197,7 +1197,7 @@ err_noclose:
* that the pages backing @xdr are unchanging.
*/
static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp,
- rpc_fraghdr marker, unsigned int *sentp)
+ rpc_fraghdr marker, int *sentp)
{
struct msghdr msg = {
.msg_flags = MSG_SPLICE_PAGES,
@@ -1247,8 +1247,7 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp)
struct xdr_buf *xdr = &rqstp->rq_res;
rpc_fraghdr marker = cpu_to_be32(RPC_LAST_STREAM_FRAGMENT |
(u32)xdr->len);
- unsigned int sent;
- int err;
+ int sent, err;
svc_tcp_release_ctxt(xprt, rqstp->rq_xprt_ctxt);
rqstp->rq_xprt_ctxt = NULL;
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 2ea00e354ba6..1346fdf33835 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -993,21 +993,18 @@ EXPORT_SYMBOL_GPL(xdr_init_encode);
* xdr_init_encode_pages - Initialize an xdr_stream for encoding into pages
* @xdr: pointer to xdr_stream struct
* @buf: pointer to XDR buffer into which to encode data
- * @pages: list of pages to decode into
- * @rqst: pointer to controlling rpc_rqst, for debugging
*
*/
-void xdr_init_encode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
- struct page **pages, struct rpc_rqst *rqst)
+void xdr_init_encode_pages(struct xdr_stream *xdr, struct xdr_buf *buf)
{
xdr_reset_scratch_buffer(xdr);
xdr->buf = buf;
- xdr->page_ptr = pages;
+ xdr->page_ptr = buf->pages;
xdr->iov = NULL;
- xdr->p = page_address(*pages);
+ xdr->p = page_address(*xdr->page_ptr);
xdr->end = (void *)xdr->p + min_t(u32, buf->buflen, PAGE_SIZE);
- xdr->rqst = rqst;
+ xdr->rqst = NULL;
}
EXPORT_SYMBOL_GPL(xdr_init_encode_pages);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 52b155123985..a8895786e016 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -646,9 +646,6 @@ static void unix_sock_destructor(struct sock *sk)
return;
}
- if (sk->sk_peer_pid)
- pidfs_put_pid(sk->sk_peer_pid);
-
if (u->addr)
unix_release_addr(u->addr);
@@ -780,7 +777,6 @@ static void drop_peercred(struct unix_peercred *peercred)
swap(peercred->peer_pid, pid);
swap(peercred->peer_cred, cred);
- pidfs_put_pid(pid);
put_pid(pid);
put_cred(cred);
}
@@ -813,7 +809,6 @@ static void copy_peercred(struct sock *sk, struct sock *peersk)
spin_lock(&sk->sk_peer_lock);
sk->sk_peer_pid = get_pid(peersk->sk_peer_pid);
- pidfs_get_pid(sk->sk_peer_pid);
sk->sk_peer_cred = get_cred(peersk->sk_peer_cred);
spin_unlock(&sk->sk_peer_lock);
}
@@ -1945,7 +1940,7 @@ static void unix_destruct_scm(struct sk_buff *skb)
struct scm_cookie scm;
memset(&scm, 0, sizeof(scm));
- scm.pid = UNIXCB(skb).pid;
+ scm.pid = UNIXCB(skb).pid;
if (UNIXCB(skb).fp)
unix_detach_fds(&scm, skb);
@@ -1971,22 +1966,46 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen
return err;
}
-/*
+static void unix_skb_to_scm(struct sk_buff *skb, struct scm_cookie *scm)
+{
+ scm_set_cred(scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
+ unix_set_secdata(scm, skb);
+}
+
+/**
+ * unix_maybe_add_creds() - Adds current task uid/gid and struct pid to skb if needed.
+ * @skb: skb to attach creds to.
+ * @sk: Sender sock.
+ * @other: Receiver sock.
+ *
* Some apps rely on write() giving SCM_CREDENTIALS
* We include credentials if source or destination socket
* asserted SOCK_PASSCRED.
+ *
+ * Context: May sleep.
+ * Return: On success zero, on error a negative error code is returned.
*/
-static void unix_maybe_add_creds(struct sk_buff *skb, const struct sock *sk,
- const struct sock *other)
+static int unix_maybe_add_creds(struct sk_buff *skb, const struct sock *sk,
+ const struct sock *other)
{
if (UNIXCB(skb).pid)
- return;
+ return 0;
if (unix_may_passcred(sk) || unix_may_passcred(other) ||
!other->sk_socket) {
- UNIXCB(skb).pid = get_pid(task_tgid(current));
+ struct pid *pid;
+ int err;
+
+ pid = task_tgid(current);
+ err = pidfs_register_pid(pid);
+ if (unlikely(err))
+ return err;
+
+ UNIXCB(skb).pid = get_pid(pid);
current_uid_gid(&UNIXCB(skb).uid, &UNIXCB(skb).gid);
}
+
+ return 0;
}
static bool unix_skb_scm_eq(struct sk_buff *skb,
@@ -2121,6 +2140,10 @@ lookup:
goto out_sock_put;
}
+ err = unix_maybe_add_creds(skb, sk, other);
+ if (err)
+ goto out_sock_put;
+
restart:
sk_locked = 0;
unix_state_lock(other);
@@ -2229,7 +2252,6 @@ restart_locked:
if (sock_flag(other, SOCK_RCVTSTAMP))
__net_timestamp(skb);
- unix_maybe_add_creds(skb, sk, other);
scm_stat_add(other, skb);
skb_queue_tail(&other->sk_receive_queue, skb);
unix_state_unlock(other);
@@ -2273,6 +2295,10 @@ static int queue_oob(struct sock *sk, struct msghdr *msg, struct sock *other,
if (err < 0)
goto out;
+ err = unix_maybe_add_creds(skb, sk, other);
+ if (err)
+ goto out;
+
skb_put(skb, 1);
err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, 1);
@@ -2292,7 +2318,6 @@ static int queue_oob(struct sock *sk, struct msghdr *msg, struct sock *other,
goto out_unlock;
}
- unix_maybe_add_creds(skb, sk, other);
scm_stat_add(other, skb);
spin_lock(&other->sk_receive_queue.lock);
@@ -2386,6 +2411,10 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
fds_sent = true;
+ err = unix_maybe_add_creds(skb, sk, other);
+ if (err)
+ goto out_free;
+
if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
err = skb_splice_from_iter(skb, &msg->msg_iter, size,
@@ -2416,7 +2445,6 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
goto out_free;
}
- unix_maybe_add_creds(skb, sk, other);
scm_stat_add(other, skb);
skb_queue_tail(&other->sk_receive_queue, skb);
unix_state_unlock(other);
@@ -2564,8 +2592,7 @@ int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size,
memset(&scm, 0, sizeof(scm));
- scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
- unix_set_secdata(&scm, skb);
+ unix_skb_to_scm(skb, &scm);
if (!(flags & MSG_PEEK)) {
if (UNIXCB(skb).fp)
@@ -2954,8 +2981,7 @@ unlock:
break;
} else if (unix_may_passcred(sk)) {
/* Copy credentials */
- scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
- unix_set_secdata(&scm, skb);
+ unix_skb_to_scm(skb, &scm);
check_creds = true;
}
@@ -3191,7 +3217,6 @@ EXPORT_SYMBOL_GPL(unix_outq_len);
static int unix_open_file(struct sock *sk)
{
- struct path path;
struct file *f;
int fd;
@@ -3201,27 +3226,20 @@ static int unix_open_file(struct sock *sk)
if (!smp_load_acquire(&unix_sk(sk)->addr))
return -ENOENT;
- path = unix_sk(sk)->path;
- if (!path.dentry)
+ if (!unix_sk(sk)->path.dentry)
return -ENOENT;
- path_get(&path);
-
fd = get_unused_fd_flags(O_CLOEXEC);
if (fd < 0)
- goto out;
+ return fd;
- f = dentry_open(&path, O_PATH, current_cred());
+ f = dentry_open(&unix_sk(sk)->path, O_PATH, current_cred());
if (IS_ERR(f)) {
put_unused_fd(fd);
- fd = PTR_ERR(f);
- goto out;
+ return PTR_ERR(f);
}
fd_install(fd, f);
-out:
- path_put(&path);
-
return fd;
}
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 81fd486b5e56..d2819baea414 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -305,7 +305,6 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
return -EINVAL;
}
- xfrm_set_type_offload(x);
if (!x->type_offload) {
NL_SET_ERR_MSG(extack, "Type doesn't support offload");
dev_put(dev);
diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c
index cb1e12740c87..330a05286a56 100644
--- a/net/xfrm/xfrm_interface_core.c
+++ b/net/xfrm/xfrm_interface_core.c
@@ -875,7 +875,7 @@ static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[],
return -EINVAL;
}
- if (p.collect_md) {
+ if (p.collect_md || xi->p.collect_md) {
NL_SET_ERR_MSG(extack, "collect_md can't be changed");
return -EINVAL;
}
@@ -886,11 +886,6 @@ static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[],
} else {
if (xi->dev != dev)
return -EEXIST;
- if (xi->p.collect_md) {
- NL_SET_ERR_MSG(extack,
- "device can't be changed to collect_md");
- return -EINVAL;
- }
}
return xfrmi_update(xi, &p);
diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c
index 907c3ccb440d..43fdc6ed8dd1 100644
--- a/net/xfrm/xfrm_ipcomp.c
+++ b/net/xfrm/xfrm_ipcomp.c
@@ -97,7 +97,7 @@ static int ipcomp_input_done2(struct sk_buff *skb, int err)
struct ip_comp_hdr *ipch = ip_comp_hdr(skb);
const int plen = skb->len;
- skb_reset_transport_header(skb);
+ skb->transport_header = skb->network_header + sizeof(*ipch);
return ipcomp_post_acomp(skb, err, 0) ?:
skb->len < (plen + sizeof(ip_comp_hdr)) ? -EINVAL :
@@ -313,7 +313,6 @@ void ipcomp_destroy(struct xfrm_state *x)
struct ipcomp_data *ipcd = x->data;
if (!ipcd)
return;
- xfrm_state_delete_tunnel(x);
ipcomp_free_data(ipcd);
kfree(ipcd);
}
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 77cc418ad69e..97ff756191ba 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -424,11 +424,10 @@ void xfrm_unregister_type_offload(const struct xfrm_type_offload *type,
}
EXPORT_SYMBOL(xfrm_unregister_type_offload);
-void xfrm_set_type_offload(struct xfrm_state *x)
+void xfrm_set_type_offload(struct xfrm_state *x, bool try_load)
{
const struct xfrm_type_offload *type = NULL;
struct xfrm_state_afinfo *afinfo;
- bool try_load = true;
retry:
afinfo = xfrm_state_get_afinfo(x->props.family);
@@ -593,7 +592,7 @@ void xfrm_state_free(struct xfrm_state *x)
}
EXPORT_SYMBOL(xfrm_state_free);
-static void ___xfrm_state_destroy(struct xfrm_state *x)
+static void xfrm_state_gc_destroy(struct xfrm_state *x)
{
if (x->mode_cbs && x->mode_cbs->destroy_state)
x->mode_cbs->destroy_state(x);
@@ -607,6 +606,7 @@ static void ___xfrm_state_destroy(struct xfrm_state *x)
kfree(x->coaddr);
kfree(x->replay_esn);
kfree(x->preplay_esn);
+ xfrm_unset_type_offload(x);
if (x->type) {
x->type->destructor(x);
xfrm_put_type(x->type);
@@ -631,7 +631,7 @@ static void xfrm_state_gc_task(struct work_struct *work)
synchronize_rcu();
hlist_for_each_entry_safe(x, tmp, &gc_list, gclist)
- ___xfrm_state_destroy(x);
+ xfrm_state_gc_destroy(x);
}
static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
@@ -780,8 +780,6 @@ void xfrm_dev_state_free(struct xfrm_state *x)
struct xfrm_dev_offload *xso = &x->xso;
struct net_device *dev = READ_ONCE(xso->dev);
- xfrm_unset_type_offload(x);
-
if (dev && dev->xfrmdev_ops) {
spin_lock_bh(&xfrm_state_dev_gc_lock);
if (!hlist_unhashed(&x->dev_gclist))
@@ -797,22 +795,18 @@ void xfrm_dev_state_free(struct xfrm_state *x)
}
#endif
-void __xfrm_state_destroy(struct xfrm_state *x, bool sync)
+void __xfrm_state_destroy(struct xfrm_state *x)
{
WARN_ON(x->km.state != XFRM_STATE_DEAD);
- if (sync) {
- synchronize_rcu();
- ___xfrm_state_destroy(x);
- } else {
- spin_lock_bh(&xfrm_state_gc_lock);
- hlist_add_head(&x->gclist, &xfrm_state_gc_list);
- spin_unlock_bh(&xfrm_state_gc_lock);
- schedule_work(&xfrm_state_gc_work);
- }
+ spin_lock_bh(&xfrm_state_gc_lock);
+ hlist_add_head(&x->gclist, &xfrm_state_gc_list);
+ spin_unlock_bh(&xfrm_state_gc_lock);
+ schedule_work(&xfrm_state_gc_work);
}
EXPORT_SYMBOL(__xfrm_state_destroy);
+static void xfrm_state_delete_tunnel(struct xfrm_state *x);
int __xfrm_state_delete(struct xfrm_state *x)
{
struct net *net = xs_net(x);
@@ -840,6 +834,8 @@ int __xfrm_state_delete(struct xfrm_state *x)
xfrm_dev_state_delete(x);
+ xfrm_state_delete_tunnel(x);
+
/* All xfrm_state objects are created by xfrm_state_alloc.
* The xfrm_state_alloc call gives a reference, and that
* is what we are dropping here.
@@ -921,7 +917,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool
}
#endif
-int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync)
+int xfrm_state_flush(struct net *net, u8 proto, bool task_valid)
{
int i, err = 0, cnt = 0;
@@ -943,10 +939,7 @@ restart:
err = xfrm_state_delete(x);
xfrm_audit_state_delete(x, err ? 0 : 1,
task_valid);
- if (sync)
- xfrm_state_put_sync(x);
- else
- xfrm_state_put(x);
+ xfrm_state_put(x);
if (!err)
cnt++;
@@ -1307,14 +1300,8 @@ static void xfrm_hash_grow_check(struct net *net, int have_hash_collision)
static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x,
const struct flowi *fl, unsigned short family,
struct xfrm_state **best, int *acq_in_progress,
- int *error)
+ int *error, unsigned int pcpu_id)
{
- /* We need the cpu id just as a lookup key,
- * we don't require it to be stable.
- */
- unsigned int pcpu_id = get_cpu();
- put_cpu();
-
/* Resolution logic:
* 1. There is a valid state with matching selector. Done.
* 2. Valid state with inappropriate selector. Skip.
@@ -1381,14 +1368,15 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
/* We need the cpu id just as a lookup key,
* we don't require it to be stable.
*/
- pcpu_id = get_cpu();
- put_cpu();
+ pcpu_id = raw_smp_processor_id();
to_put = NULL;
sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation);
rcu_read_lock();
+ xfrm_hash_ptrs_get(net, &state_ptrs);
+
hlist_for_each_entry_rcu(x, &pol->state_cache_list, state_cache) {
if (x->props.family == encap_family &&
x->props.reqid == tmpl->reqid &&
@@ -1400,7 +1388,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
tmpl->id.proto == x->id.proto &&
(tmpl->id.spi == x->id.spi || !tmpl->id.spi))
xfrm_state_look_at(pol, x, fl, encap_family,
- &best, &acquire_in_progress, &error);
+ &best, &acquire_in_progress, &error, pcpu_id);
}
if (best)
@@ -1417,7 +1405,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
tmpl->id.proto == x->id.proto &&
(tmpl->id.spi == x->id.spi || !tmpl->id.spi))
xfrm_state_look_at(pol, x, fl, family,
- &best, &acquire_in_progress, &error);
+ &best, &acquire_in_progress, &error, pcpu_id);
}
cached:
@@ -1429,8 +1417,6 @@ cached:
else if (acquire_in_progress) /* XXX: acquire_in_progress should not happen */
WARN_ON(1);
- xfrm_hash_ptrs_get(net, &state_ptrs);
-
h = __xfrm_dst_hash(daddr, saddr, tmpl->reqid, encap_family, state_ptrs.hmask);
hlist_for_each_entry_rcu(x, state_ptrs.bydst + h, bydst) {
#ifdef CONFIG_XFRM_OFFLOAD
@@ -1460,7 +1446,7 @@ cached:
tmpl->id.proto == x->id.proto &&
(tmpl->id.spi == x->id.spi || !tmpl->id.spi))
xfrm_state_look_at(pol, x, fl, family,
- &best, &acquire_in_progress, &error);
+ &best, &acquire_in_progress, &error, pcpu_id);
}
if (best || acquire_in_progress)
goto found;
@@ -1495,7 +1481,7 @@ cached:
tmpl->id.proto == x->id.proto &&
(tmpl->id.spi == x->id.spi || !tmpl->id.spi))
xfrm_state_look_at(pol, x, fl, family,
- &best, &acquire_in_progress, &error);
+ &best, &acquire_in_progress, &error, pcpu_id);
}
found:
@@ -3077,20 +3063,17 @@ void xfrm_flush_gc(void)
}
EXPORT_SYMBOL(xfrm_flush_gc);
-/* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */
-void xfrm_state_delete_tunnel(struct xfrm_state *x)
+static void xfrm_state_delete_tunnel(struct xfrm_state *x)
{
if (x->tunnel) {
struct xfrm_state *t = x->tunnel;
- if (atomic_read(&t->tunnel_users) == 2)
+ if (atomic_dec_return(&t->tunnel_users) == 1)
xfrm_state_delete(t);
- atomic_dec(&t->tunnel_users);
- xfrm_state_put_sync(t);
+ xfrm_state_put(t);
x->tunnel = NULL;
}
}
-EXPORT_SYMBOL(xfrm_state_delete_tunnel);
u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
{
@@ -3295,8 +3278,8 @@ void xfrm_state_fini(struct net *net)
unsigned int sz;
flush_work(&net->xfrm.state_hash_work);
+ xfrm_state_flush(net, IPSEC_PROTO_ANY, false);
flush_work(&xfrm_state_gc_work);
- xfrm_state_flush(net, 0, false, true);
WARN_ON(!list_empty(&net->xfrm.state_all));
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 59f258daf830..684239018bec 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -977,6 +977,7 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
/* override default values from above */
xfrm_update_ae_params(x, attrs, 0);
+ xfrm_set_type_offload(x, attrs[XFRMA_OFFLOAD_DEV]);
/* configure the hardware if offload is requested */
if (attrs[XFRMA_OFFLOAD_DEV]) {
err = xfrm_dev_state_add(net, x,
@@ -2634,7 +2635,7 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
struct xfrm_usersa_flush *p = nlmsg_data(nlh);
int err;
- err = xfrm_state_flush(net, p->proto, true, false);
+ err = xfrm_state_flush(net, p->proto, true);
if (err) {
if (err == -ESRCH) /* empty table */
return 0;
generated by cgit (git 2.34.1) at 2025-07-29 21:25:27 +0000