summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-06-16 11:51:32 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-06-16 11:51:32 -0700
commit48a23ec6ff2b2a5effe8d3ae5f17fc6b7f35df65 (patch)
treebac89e47b33e4df377677e2bdbe5c2e02c451435 /net
parent30306f6194cadcc29c77f6ddcd416a75bf5c0232 (diff)
parent2e7bf4a6af482f73f01245f08b4a953412c77070 (diff)
Merge tag 'net-5.19-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski: "Mostly driver fixes. Current release - regressions: - Revert "net: Add a second bind table hashed by port and address", needs more work - amd-xgbe: use platform_irq_count(), static setup of IRQ resources had been removed from DT core - dts: at91: ksz9477_evb: add phy-mode to fix port/phy validation Current release - new code bugs: - hns3: modify the ring param print info Previous releases - always broken: - axienet: make the 64b addressable DMA depends on 64b architectures - iavf: fix issue with MAC address of VF shown as zero - ice: fix PTP TX timestamp offset calculation - usb: ax88179_178a needs FLAG_SEND_ZLP Misc: - document some net.sctp.* sysctls" * tag 'net-5.19-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (31 commits) net: axienet: add missing error return code in axienet_probe() Revert "net: Add a second bind table hashed by port and address" net: ax25: Fix deadlock caused by skb_recv_datagram in ax25_recvmsg net: usb: ax88179_178a needs FLAG_SEND_ZLP MAINTAINERS: add include/dt-bindings/net to NETWORKING DRIVERS ARM: dts: at91: ksz9477_evb: fix port/phy validation net: bgmac: Fix an erroneous kfree() in bgmac_remove() ice: Fix memory corruption in VF driver ice: Fix queue config fail handling ice: Sync VLAN filtering features for DVM ice: Fix PTP TX timestamp offset calculation mlxsw: spectrum_cnt: Reorder counter pools docs: networking: phy: Fix a typo amd-xgbe: Use platform_irq_count() octeontx2-vf: Add support for adaptive interrupt coalescing xilinx: Fix build on x86. net: axienet: Use iowrite64 to write all 64b descriptor pointers net: axienet: make the 64b addresable DMA depends on 64b archectures net: hns3: fix tm port shapping of fibre port is incorrect after driver initialization net: hns3: fix PF rss size initialization bug ...
Diffstat (limited to 'net')
-rw-r--r--net/ax25/af_ax25.c33
-rw-r--r--net/dccp/proto.c33
-rw-r--r--net/ipv4/inet_connection_sock.c247
-rw-r--r--net/ipv4/inet_hashtables.c193
-rw-r--r--net/ipv4/tcp.c14
5 files changed, 110 insertions, 410 deletions
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 95393bb2760b..4c7030ed8d33 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1661,9 +1661,12 @@ static int ax25_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
int flags)
{
struct sock *sk = sock->sk;
- struct sk_buff *skb;
+ struct sk_buff *skb, *last;
+ struct sk_buff_head *sk_queue;
int copied;
int err = 0;
+ int off = 0;
+ long timeo;
lock_sock(sk);
/*
@@ -1675,10 +1678,29 @@ static int ax25_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
goto out;
}
- /* Now we can treat all alike */
- skb = skb_recv_datagram(sk, flags, &err);
- if (skb == NULL)
- goto out;
+ /* We need support for non-blocking reads. */
+ sk_queue = &sk->sk_receive_queue;
+ skb = __skb_try_recv_datagram(sk, sk_queue, flags, &off, &err, &last);
+ /* If no packet is available, release_sock(sk) and try again. */
+ if (!skb) {
+ if (err != -EAGAIN)
+ goto out;
+ release_sock(sk);
+ timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
+ while (timeo && !__skb_wait_for_more_packets(sk, sk_queue, &err,
+ &timeo, last)) {
+ skb = __skb_try_recv_datagram(sk, sk_queue, flags, &off,
+ &err, &last);
+ if (skb)
+ break;
+
+ if (err != -EAGAIN)
+ goto done;
+ }
+ if (!skb)
+ goto done;
+ lock_sock(sk);
+ }
if (!sk_to_ax25(sk)->pidincl)
skb_pull(skb, 1); /* Remove PID */
@@ -1725,6 +1747,7 @@ static int ax25_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
out:
release_sock(sk);
+done:
return err;
}
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 2e78458900f2..eb8e128e43e8 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1120,12 +1120,6 @@ static int __init dccp_init(void)
SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL);
if (!dccp_hashinfo.bind_bucket_cachep)
goto out_free_hashinfo2;
- dccp_hashinfo.bind2_bucket_cachep =
- kmem_cache_create("dccp_bind2_bucket",
- sizeof(struct inet_bind2_bucket), 0,
- SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL);
- if (!dccp_hashinfo.bind2_bucket_cachep)
- goto out_free_bind_bucket_cachep;
/*
* Size and allocate the main established and bind bucket
@@ -1156,7 +1150,7 @@ static int __init dccp_init(void)
if (!dccp_hashinfo.ehash) {
DCCP_CRIT("Failed to allocate DCCP established hash table");
- goto out_free_bind2_bucket_cachep;
+ goto out_free_bind_bucket_cachep;
}
for (i = 0; i <= dccp_hashinfo.ehash_mask; i++)
@@ -1182,23 +1176,14 @@ static int __init dccp_init(void)
goto out_free_dccp_locks;
}
- dccp_hashinfo.bhash2 = (struct inet_bind2_hashbucket *)
- __get_free_pages(GFP_ATOMIC | __GFP_NOWARN, bhash_order);
-
- if (!dccp_hashinfo.bhash2) {
- DCCP_CRIT("Failed to allocate DCCP bind2 hash table");
- goto out_free_dccp_bhash;
- }
-
for (i = 0; i < dccp_hashinfo.bhash_size; i++) {
spin_lock_init(&dccp_hashinfo.bhash[i].lock);
INIT_HLIST_HEAD(&dccp_hashinfo.bhash[i].chain);
- INIT_HLIST_HEAD(&dccp_hashinfo.bhash2[i].chain);
}
rc = dccp_mib_init();
if (rc)
- goto out_free_dccp_bhash2;
+ goto out_free_dccp_bhash;
rc = dccp_ackvec_init();
if (rc)
@@ -1222,38 +1207,30 @@ out_ackvec_exit:
dccp_ackvec_exit();
out_free_dccp_mib:
dccp_mib_exit();
-out_free_dccp_bhash2:
- free_pages((unsigned long)dccp_hashinfo.bhash2, bhash_order);
out_free_dccp_bhash:
free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order);
out_free_dccp_locks:
inet_ehash_locks_free(&dccp_hashinfo);
out_free_dccp_ehash:
free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order);
-out_free_bind2_bucket_cachep:
- kmem_cache_destroy(dccp_hashinfo.bind2_bucket_cachep);
out_free_bind_bucket_cachep:
kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
out_free_hashinfo2:
inet_hashinfo2_free_mod(&dccp_hashinfo);
out_fail:
dccp_hashinfo.bhash = NULL;
- dccp_hashinfo.bhash2 = NULL;
dccp_hashinfo.ehash = NULL;
dccp_hashinfo.bind_bucket_cachep = NULL;
- dccp_hashinfo.bind2_bucket_cachep = NULL;
return rc;
}
static void __exit dccp_fini(void)
{
- int bhash_order = get_order(dccp_hashinfo.bhash_size *
- sizeof(struct inet_bind_hashbucket));
-
ccid_cleanup_builtins();
dccp_mib_exit();
- free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order);
- free_pages((unsigned long)dccp_hashinfo.bhash2, bhash_order);
+ free_pages((unsigned long)dccp_hashinfo.bhash,
+ get_order(dccp_hashinfo.bhash_size *
+ sizeof(struct inet_bind_hashbucket)));
free_pages((unsigned long)dccp_hashinfo.ehash,
get_order((dccp_hashinfo.ehash_mask + 1) *
sizeof(struct inet_ehash_bucket)));
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index c0b7e6c21360..53f5f956d948 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -117,32 +117,6 @@ bool inet_rcv_saddr_any(const struct sock *sk)
return !sk->sk_rcv_saddr;
}
-static bool use_bhash2_on_bind(const struct sock *sk)
-{
-#if IS_ENABLED(CONFIG_IPV6)
- int addr_type;
-
- if (sk->sk_family == AF_INET6) {
- addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr);
- return addr_type != IPV6_ADDR_ANY &&
- addr_type != IPV6_ADDR_MAPPED;
- }
-#endif
- return sk->sk_rcv_saddr != htonl(INADDR_ANY);
-}
-
-static u32 get_bhash2_nulladdr_hash(const struct sock *sk, struct net *net,
- int port)
-{
-#if IS_ENABLED(CONFIG_IPV6)
- struct in6_addr nulladdr = {};
-
- if (sk->sk_family == AF_INET6)
- return ipv6_portaddr_hash(net, &nulladdr, port);
-#endif
- return ipv4_portaddr_hash(net, 0, port);
-}
-
void inet_get_local_port_range(struct net *net, int *low, int *high)
{
unsigned int seq;
@@ -156,71 +130,16 @@ void inet_get_local_port_range(struct net *net, int *low, int *high)
}
EXPORT_SYMBOL(inet_get_local_port_range);
-static bool bind_conflict_exist(const struct sock *sk, struct sock *sk2,
- kuid_t sk_uid, bool relax,
- bool reuseport_cb_ok, bool reuseport_ok)
-{
- int bound_dev_if2;
-
- if (sk == sk2)
- return false;
-
- bound_dev_if2 = READ_ONCE(sk2->sk_bound_dev_if);
-
- if (!sk->sk_bound_dev_if || !bound_dev_if2 ||
- sk->sk_bound_dev_if == bound_dev_if2) {
- if (sk->sk_reuse && sk2->sk_reuse &&
- sk2->sk_state != TCP_LISTEN) {
- if (!relax || (!reuseport_ok && sk->sk_reuseport &&
- sk2->sk_reuseport && reuseport_cb_ok &&
- (sk2->sk_state == TCP_TIME_WAIT ||
- uid_eq(sk_uid, sock_i_uid(sk2)))))
- return true;
- } else if (!reuseport_ok || !sk->sk_reuseport ||
- !sk2->sk_reuseport || !reuseport_cb_ok ||
- (sk2->sk_state != TCP_TIME_WAIT &&
- !uid_eq(sk_uid, sock_i_uid(sk2)))) {
- return true;
- }
- }
- return false;
-}
-
-static bool check_bhash2_conflict(const struct sock *sk,
- struct inet_bind2_bucket *tb2, kuid_t sk_uid,
- bool relax, bool reuseport_cb_ok,
- bool reuseport_ok)
-{
- struct sock *sk2;
-
- sk_for_each_bound_bhash2(sk2, &tb2->owners) {
- if (sk->sk_family == AF_INET && ipv6_only_sock(sk2))
- continue;
-
- if (bind_conflict_exist(sk, sk2, sk_uid, relax,
- reuseport_cb_ok, reuseport_ok))
- return true;
- }
- return false;
-}
-
-/* This should be called only when the corresponding inet_bind_bucket spinlock
- * is held
- */
-static int inet_csk_bind_conflict(const struct sock *sk, int port,
- struct inet_bind_bucket *tb,
- struct inet_bind2_bucket *tb2, /* may be null */
+static int inet_csk_bind_conflict(const struct sock *sk,
+ const struct inet_bind_bucket *tb,
bool relax, bool reuseport_ok)
{
- struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo;
- kuid_t uid = sock_i_uid((struct sock *)sk);
- struct sock_reuseport *reuseport_cb;
- struct inet_bind2_hashbucket *head2;
- bool reuseport_cb_ok;
struct sock *sk2;
- struct net *net;
- int l3mdev;
- u32 hash;
+ bool reuseport_cb_ok;
+ bool reuse = sk->sk_reuse;
+ bool reuseport = !!sk->sk_reuseport;
+ struct sock_reuseport *reuseport_cb;
+ kuid_t uid = sock_i_uid((struct sock *)sk);
rcu_read_lock();
reuseport_cb = rcu_dereference(sk->sk_reuseport_cb);
@@ -231,42 +150,40 @@ static int inet_csk_bind_conflict(const struct sock *sk, int port,
/*
* Unlike other sk lookup places we do not check
* for sk_net here, since _all_ the socks listed
- * in tb->owners and tb2->owners list belong
- * to the same net
+ * in tb->owners list belong to the same net - the
+ * one this bucket belongs to.
*/
- if (!use_bhash2_on_bind(sk)) {
- sk_for_each_bound(sk2, &tb->owners)
- if (bind_conflict_exist(sk, sk2, uid, relax,
- reuseport_cb_ok, reuseport_ok) &&
- inet_rcv_saddr_equal(sk, sk2, true))
- return true;
+ sk_for_each_bound(sk2, &tb->owners) {
+ int bound_dev_if2;
- return false;
+ if (sk == sk2)
+ continue;
+ bound_dev_if2 = READ_ONCE(sk2->sk_bound_dev_if);
+ if ((!sk->sk_bound_dev_if ||
+ !bound_dev_if2 ||
+ sk->sk_bound_dev_if == bound_dev_if2)) {
+ if (reuse && sk2->sk_reuse &&
+ sk2->sk_state != TCP_LISTEN) {
+ if ((!relax ||
+ (!reuseport_ok &&
+ reuseport && sk2->sk_reuseport &&
+ reuseport_cb_ok &&
+ (sk2->sk_state == TCP_TIME_WAIT ||
+ uid_eq(uid, sock_i_uid(sk2))))) &&
+ inet_rcv_saddr_equal(sk, sk2, true))
+ break;
+ } else if (!reuseport_ok ||
+ !reuseport || !sk2->sk_reuseport ||
+ !reuseport_cb_ok ||
+ (sk2->sk_state != TCP_TIME_WAIT &&
+ !uid_eq(uid, sock_i_uid(sk2)))) {
+ if (inet_rcv_saddr_equal(sk, sk2, true))
+ break;
+ }
+ }
}
-
- if (tb2 && check_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok,
- reuseport_ok))
- return true;
-
- net = sock_net(sk);
-
- /* check there's no conflict with an existing IPV6_ADDR_ANY (if ipv6) or
- * INADDR_ANY (if ipv4) socket.
- */
- hash = get_bhash2_nulladdr_hash(sk, net, port);
- head2 = &hinfo->bhash2[hash & (hinfo->bhash_size - 1)];
-
- l3mdev = inet_sk_bound_l3mdev(sk);
- inet_bind_bucket_for_each(tb2, &head2->chain)
- if (check_bind2_bucket_match_nulladdr(tb2, net, port, l3mdev, sk))
- break;
-
- if (tb2 && check_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok,
- reuseport_ok))
- return true;
-
- return false;
+ return sk2 != NULL;
}
/*
@@ -274,20 +191,16 @@ static int inet_csk_bind_conflict(const struct sock *sk, int port,
* inet_bind_hashbucket lock held.
*/
static struct inet_bind_hashbucket *
-inet_csk_find_open_port(struct sock *sk, struct inet_bind_bucket **tb_ret,
- struct inet_bind2_bucket **tb2_ret,
- struct inet_bind2_hashbucket **head2_ret, int *port_ret)
+inet_csk_find_open_port(struct sock *sk, struct inet_bind_bucket **tb_ret, int *port_ret)
{
struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo;
- struct inet_bind2_hashbucket *head2;
+ int port = 0;
struct inet_bind_hashbucket *head;
struct net *net = sock_net(sk);
+ bool relax = false;
int i, low, high, attempt_half;
- struct inet_bind2_bucket *tb2;
struct inet_bind_bucket *tb;
u32 remaining, offset;
- bool relax = false;
- int port = 0;
int l3mdev;
l3mdev = inet_sk_bound_l3mdev(sk);
@@ -326,12 +239,10 @@ other_parity_scan:
head = &hinfo->bhash[inet_bhashfn(net, port,
hinfo->bhash_size)];
spin_lock_bh(&head->lock);
- tb2 = inet_bind2_bucket_find(hinfo, net, port, l3mdev, sk,
- &head2);
inet_bind_bucket_for_each(tb, &head->chain)
- if (check_bind_bucket_match(tb, net, port, l3mdev)) {
- if (!inet_csk_bind_conflict(sk, port, tb, tb2,
- relax, false))
+ if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+ tb->port == port) {
+ if (!inet_csk_bind_conflict(sk, tb, relax, false))
goto success;
goto next_port;
}
@@ -361,8 +272,6 @@ next_port:
success:
*port_ret = port;
*tb_ret = tb;
- *tb2_ret = tb2;
- *head2_ret = head2;
return head;
}
@@ -458,81 +367,54 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
{
bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo;
- bool bhash_created = false, bhash2_created = false;
- struct inet_bind2_bucket *tb2 = NULL;
- struct inet_bind2_hashbucket *head2;
- struct inet_bind_bucket *tb = NULL;
+ int ret = 1, port = snum;
struct inet_bind_hashbucket *head;
struct net *net = sock_net(sk);
- int ret = 1, port = snum;
- bool found_port = false;
+ struct inet_bind_bucket *tb = NULL;
int l3mdev;
l3mdev = inet_sk_bound_l3mdev(sk);
if (!port) {
- head = inet_csk_find_open_port(sk, &tb, &tb2, &head2, &port);
+ head = inet_csk_find_open_port(sk, &tb, &port);
if (!head)
return ret;
- if (tb && tb2)
- goto success;
- found_port = true;
- } else {
- head = &hinfo->bhash[inet_bhashfn(net, port,
- hinfo->bhash_size)];
- spin_lock_bh(&head->lock);
- inet_bind_bucket_for_each(tb, &head->chain)
- if (check_bind_bucket_match(tb, net, port, l3mdev))
- break;
-
- tb2 = inet_bind2_bucket_find(hinfo, net, port, l3mdev, sk,
- &head2);
- }
-
- if (!tb) {
- tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep, net,
- head, port, l3mdev);
if (!tb)
- goto fail_unlock;
- bhash_created = true;
- }
-
- if (!tb2) {
- tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep,
- net, head2, port, l3mdev, sk);
- if (!tb2)
- goto fail_unlock;
- bhash2_created = true;
+ goto tb_not_found;
+ goto success;
}
-
- /* If we had to find an open port, we already checked for conflicts */
- if (!found_port && !hlist_empty(&tb->owners)) {
+ head = &hinfo->bhash[inet_bhashfn(net, port,
+ hinfo->bhash_size)];
+ spin_lock_bh(&head->lock);
+ inet_bind_bucket_for_each(tb, &head->chain)
+ if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+ tb->port == port)
+ goto tb_found;
+tb_not_found:
+ tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
+ net, head, port, l3mdev);
+ if (!tb)
+ goto fail_unlock;
+tb_found:
+ if (!hlist_empty(&tb->owners)) {
if (sk->sk_reuse == SK_FORCE_REUSE)
goto success;
if ((tb->fastreuse > 0 && reuse) ||
sk_reuseport_match(tb, sk))
goto success;
- if (inet_csk_bind_conflict(sk, port, tb, tb2, true, true))
+ if (inet_csk_bind_conflict(sk, tb, true, true))
goto fail_unlock;
}
success:
inet_csk_update_fastreuse(tb, sk);
if (!inet_csk(sk)->icsk_bind_hash)
- inet_bind_hash(sk, tb, tb2, port);
+ inet_bind_hash(sk, tb, port);
WARN_ON(inet_csk(sk)->icsk_bind_hash != tb);
- WARN_ON(inet_csk(sk)->icsk_bind2_hash != tb2);
ret = 0;
fail_unlock:
- if (ret) {
- if (bhash_created)
- inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb);
- if (bhash2_created)
- inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep,
- tb2);
- }
spin_unlock_bh(&head->lock);
return ret;
}
@@ -1079,7 +961,6 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
inet_sk_set_state(newsk, TCP_SYN_RECV);
newicsk->icsk_bind_hash = NULL;
- newicsk->icsk_bind2_hash = NULL;
inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port;
inet_sk(newsk)->inet_num = inet_rsk(req)->ir_num;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 545f91b6cb5e..b9d995b5ce24 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -81,41 +81,6 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
return tb;
}
-struct inet_bind2_bucket *inet_bind2_bucket_create(struct kmem_cache *cachep,
- struct net *net,
- struct inet_bind2_hashbucket *head,
- const unsigned short port,
- int l3mdev,
- const struct sock *sk)
-{
- struct inet_bind2_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC);
-
- if (tb) {
- write_pnet(&tb->ib_net, net);
- tb->l3mdev = l3mdev;
- tb->port = port;
-#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family == AF_INET6)
- tb->v6_rcv_saddr = sk->sk_v6_rcv_saddr;
- else
-#endif
- tb->rcv_saddr = sk->sk_rcv_saddr;
- INIT_HLIST_HEAD(&tb->owners);
- hlist_add_head(&tb->node, &head->chain);
- }
- return tb;
-}
-
-static bool bind2_bucket_addr_match(struct inet_bind2_bucket *tb2, struct sock *sk)
-{
-#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family == AF_INET6)
- return ipv6_addr_equal(&tb2->v6_rcv_saddr,
- &sk->sk_v6_rcv_saddr);
-#endif
- return tb2->rcv_saddr == sk->sk_rcv_saddr;
-}
-
/*
* Caller must hold hashbucket lock for this tb with local BH disabled
*/
@@ -127,25 +92,12 @@ void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket
}
}
-/* Caller must hold the lock for the corresponding hashbucket in the bhash table
- * with local BH disabled
- */
-void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb)
-{
- if (hlist_empty(&tb->owners)) {
- __hlist_del(&tb->node);
- kmem_cache_free(cachep, tb);
- }
-}
-
void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
- struct inet_bind2_bucket *tb2, const unsigned short snum)
+ const unsigned short snum)
{
inet_sk(sk)->inet_num = snum;
sk_add_bind_node(sk, &tb->owners);
inet_csk(sk)->icsk_bind_hash = tb;
- sk_add_bind2_node(sk, &tb2->owners);
- inet_csk(sk)->icsk_bind2_hash = tb2;
}
/*
@@ -157,7 +109,6 @@ static void __inet_put_port(struct sock *sk)
const int bhash = inet_bhashfn(sock_net(sk), inet_sk(sk)->inet_num,
hashinfo->bhash_size);
struct inet_bind_hashbucket *head = &hashinfo->bhash[bhash];
- struct inet_bind2_bucket *tb2;
struct inet_bind_bucket *tb;
spin_lock(&head->lock);
@@ -166,13 +117,6 @@ static void __inet_put_port(struct sock *sk)
inet_csk(sk)->icsk_bind_hash = NULL;
inet_sk(sk)->inet_num = 0;
inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
-
- if (inet_csk(sk)->icsk_bind2_hash) {
- tb2 = inet_csk(sk)->icsk_bind2_hash;
- __sk_del_bind2_node(sk);
- inet_csk(sk)->icsk_bind2_hash = NULL;
- inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2);
- }
spin_unlock(&head->lock);
}
@@ -189,19 +133,14 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
struct inet_hashinfo *table = sk->sk_prot->h.hashinfo;
unsigned short port = inet_sk(child)->inet_num;
const int bhash = inet_bhashfn(sock_net(sk), port,
- table->bhash_size);
+ table->bhash_size);
struct inet_bind_hashbucket *head = &table->bhash[bhash];
- struct inet_bind2_hashbucket *head_bhash2;
- bool created_inet_bind_bucket = false;
- struct net *net = sock_net(sk);
- struct inet_bind2_bucket *tb2;
struct inet_bind_bucket *tb;
int l3mdev;
spin_lock(&head->lock);
tb = inet_csk(sk)->icsk_bind_hash;
- tb2 = inet_csk(sk)->icsk_bind2_hash;
- if (unlikely(!tb || !tb2)) {
+ if (unlikely(!tb)) {
spin_unlock(&head->lock);
return -ENOENT;
}
@@ -214,45 +153,25 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
* as that of the child socket. We have to look up or
* create a new bind bucket for the child here. */
inet_bind_bucket_for_each(tb, &head->chain) {
- if (check_bind_bucket_match(tb, net, port, l3mdev))
+ if (net_eq(ib_net(tb), sock_net(sk)) &&
+ tb->l3mdev == l3mdev && tb->port == port)
break;
}
if (!tb) {
tb = inet_bind_bucket_create(table->bind_bucket_cachep,
- net, head, port, l3mdev);
+ sock_net(sk), head, port,
+ l3mdev);
if (!tb) {
spin_unlock(&head->lock);
return -ENOMEM;
}
- created_inet_bind_bucket = true;
}
inet_csk_update_fastreuse(tb, child);
-
- goto bhash2_find;
- } else if (!bind2_bucket_addr_match(tb2, child)) {
- l3mdev = inet_sk_bound_l3mdev(sk);
-
-bhash2_find:
- tb2 = inet_bind2_bucket_find(table, net, port, l3mdev, child,
- &head_bhash2);
- if (!tb2) {
- tb2 = inet_bind2_bucket_create(table->bind2_bucket_cachep,
- net, head_bhash2, port,
- l3mdev, child);
- if (!tb2)
- goto error;
- }
}
- inet_bind_hash(child, tb, tb2, port);
+ inet_bind_hash(child, tb, port);
spin_unlock(&head->lock);
return 0;
-
-error:
- if (created_inet_bind_bucket)
- inet_bind_bucket_destroy(table->bind_bucket_cachep, tb);
- spin_unlock(&head->lock);
- return -ENOMEM;
}
EXPORT_SYMBOL_GPL(__inet_inherit_port);
@@ -756,76 +675,6 @@ void inet_unhash(struct sock *sk)
}
EXPORT_SYMBOL_GPL(inet_unhash);
-static bool check_bind2_bucket_match(struct inet_bind2_bucket *tb,
- struct net *net, unsigned short port,
- int l3mdev, struct sock *sk)
-{
-#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family == AF_INET6)
- return net_eq(ib2_net(tb), net) && tb->port == port &&
- tb->l3mdev == l3mdev &&
- ipv6_addr_equal(&tb->v6_rcv_saddr, &sk->sk_v6_rcv_saddr);
- else
-#endif
- return net_eq(ib2_net(tb), net) && tb->port == port &&
- tb->l3mdev == l3mdev && tb->rcv_saddr == sk->sk_rcv_saddr;
-}
-
-bool check_bind2_bucket_match_nulladdr(struct inet_bind2_bucket *tb,
- struct net *net, const unsigned short port,
- int l3mdev, const struct sock *sk)
-{
-#if IS_ENABLED(CONFIG_IPV6)
- struct in6_addr nulladdr = {};
-
- if (sk->sk_family == AF_INET6)
- return net_eq(ib2_net(tb), net) && tb->port == port &&
- tb->l3mdev == l3mdev &&
- ipv6_addr_equal(&tb->v6_rcv_saddr, &nulladdr);
- else
-#endif
- return net_eq(ib2_net(tb), net) && tb->port == port &&
- tb->l3mdev == l3mdev && tb->rcv_saddr == 0;
-}
-
-static struct inet_bind2_hashbucket *
-inet_bhashfn_portaddr(struct inet_hashinfo *hinfo, const struct sock *sk,
- const struct net *net, unsigned short port)
-{
- u32 hash;
-
-#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family == AF_INET6)
- hash = ipv6_portaddr_hash(net, &sk->sk_v6_rcv_saddr, port);
- else
-#endif
- hash = ipv4_portaddr_hash(net, sk->sk_rcv_saddr, port);
- return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)];
-}
-
-/* This should only be called when the spinlock for the socket's corresponding
- * bind_hashbucket is held
- */
-struct inet_bind2_bucket *
-inet_bind2_bucket_find(struct inet_hashinfo *hinfo, struct net *net,
- const unsigned short port, int l3mdev, struct sock *sk,
- struct inet_bind2_hashbucket **head)
-{
- struct inet_bind2_bucket *bhash2 = NULL;
- struct inet_bind2_hashbucket *h;
-
- h = inet_bhashfn_portaddr(hinfo, sk, net, port);
- inet_bind_bucket_for_each(bhash2, &h->chain) {
- if (check_bind2_bucket_match(bhash2, net, port, l3mdev, sk))
- break;
- }
-
- if (head)
- *head = h;
-
- return bhash2;
-}
-
/* RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm
* Note that we use 32bit integers (vs RFC 'short integers')
* because 2^16 is not a multiple of num_ephemeral and this
@@ -846,13 +695,10 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
{
struct inet_hashinfo *hinfo = death_row->hashinfo;
struct inet_timewait_sock *tw = NULL;
- struct inet_bind2_hashbucket *head2;
struct inet_bind_hashbucket *head;
int port = inet_sk(sk)->inet_num;
struct net *net = sock_net(sk);
- struct inet_bind2_bucket *tb2;
struct inet_bind_bucket *tb;
- bool tb_created = false;
u32 remaining, offset;
int ret, i, low, high;
int l3mdev;
@@ -909,7 +755,8 @@ other_parity_scan:
* the established check is already unique enough.
*/
inet_bind_bucket_for_each(tb, &head->chain) {
- if (check_bind_bucket_match(tb, net, port, l3mdev)) {
+ if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+ tb->port == port) {
if (tb->fastreuse >= 0 ||
tb->fastreuseport >= 0)
goto next_port;
@@ -927,7 +774,6 @@ other_parity_scan:
spin_unlock_bh(&head->lock);
return -ENOMEM;
}
- tb_created = true;
tb->fastreuse = -1;
tb->fastreuseport = -1;
goto ok;
@@ -943,17 +789,6 @@ next_port:
return -EADDRNOTAVAIL;
ok:
- /* Find the corresponding tb2 bucket since we need to
- * add the socket to the bhash2 table as well
- */
- tb2 = inet_bind2_bucket_find(hinfo, net, port, l3mdev, sk, &head2);
- if (!tb2) {
- tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep, net,
- head2, port, l3mdev, sk);
- if (!tb2)
- goto error;
- }
-
/* Here we want to add a little bit of randomness to the next source
* port that will be chosen. We use a max() with a random here so that
* on low contention the randomness is maximal and on high contention
@@ -963,7 +798,7 @@ ok:
WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2);
/* Head lock still held and bh's disabled */
- inet_bind_hash(sk, tb, tb2, port);
+ inet_bind_hash(sk, tb, port);
if (sk_unhashed(sk)) {
inet_sk(sk)->inet_sport = htons(port);
inet_ehash_nolisten(sk, (struct sock *)tw, NULL);
@@ -975,12 +810,6 @@ ok:
inet_twsk_deschedule_put(tw);
local_bh_enable();
return 0;
-
-error:
- if (tb_created)
- inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb);
- spin_unlock_bh(&head->lock);
- return -ENOMEM;
}
/*
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9984d23a7f3e..028513d3e2a2 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -4604,12 +4604,6 @@ void __init tcp_init(void)
SLAB_HWCACHE_ALIGN | SLAB_PANIC |
SLAB_ACCOUNT,
NULL);
- tcp_hashinfo.bind2_bucket_cachep =
- kmem_cache_create("tcp_bind2_bucket",
- sizeof(struct inet_bind2_bucket), 0,
- SLAB_HWCACHE_ALIGN | SLAB_PANIC |
- SLAB_ACCOUNT,
- NULL);
/* Size and allocate the main established and bind bucket
* hash tables.
@@ -4632,9 +4626,8 @@ void __init tcp_init(void)
if (inet_ehash_locks_alloc(&tcp_hashinfo))
panic("TCP: failed to alloc ehash_locks");
tcp_hashinfo.bhash =
- alloc_large_system_hash("TCP bind bhash tables",
- sizeof(struct inet_bind_hashbucket) +
- sizeof(struct inet_bind2_hashbucket),
+ alloc_large_system_hash("TCP bind",
+ sizeof(struct inet_bind_hashbucket),
tcp_hashinfo.ehash_mask + 1,
17, /* one slot per 128 KB of memory */
0,
@@ -4643,12 +4636,9 @@ void __init tcp_init(void)
0,
64 * 1024);
tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size;
- tcp_hashinfo.bhash2 =
- (struct inet_bind2_hashbucket *)(tcp_hashinfo.bhash + tcp_hashinfo.bhash_size);
for (i = 0; i < tcp_hashinfo.bhash_size; i++) {
spin_lock_init(&tcp_hashinfo.bhash[i].lock);
INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain);
- INIT_HLIST_HEAD(&tcp_hashinfo.bhash2[i].chain);
}