summaryrefslogtreecommitdiffstats
path: root/net/core/sock.c
diff options
context:
space:
mode:
authorIngo Molnar <mingo@kernel.org>2012-08-21 11:27:00 +0200
committerIngo Molnar <mingo@kernel.org>2012-08-21 11:27:00 +0200
commitbcada3d4b8c96b8792c2306f363992ca5ab9da42 (patch)
treee420679a5db6ea4e1694eef57f9abb6acac8d4d3 /net/core/sock.c
parent26198c21d1b286a084fe5d514a30bc7e6c712a34 (diff)
parent000078bc3ee69efb1124b8478c7527389a826074 (diff)
Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core
Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo: * Fix include order for bison/flex-generated C files, from Ben Hutchings * Build fixes and documentation corrections from David Ahern * Group parsing support, from Jiri Olsa * UI/gtk refactorings and improvements from Namhyung Kim * NULL deref fix for perf script, from Namhyung Kim * Assorted cleanups from Robert Richter * Let O= makes handle relative paths, from Steven Rostedt * perf script python fixes, from Feng Tang. * Improve 'perf lock' error message when the needed tracepoints are not present, from David Ahern. * Initial bash completion support, from Frederic Weisbecker * Allow building without libelf, from Namhyung Kim. * Support DWARF CFI based unwind to have callchains when %bp based unwinding is not possible, from Jiri Olsa. * Symbol resolution fixes, while fixing support PPC64 files with an .opt ELF section was the end goal, several fixes for code that handles all architectures and cleanups are included, from Cody Schafer. * Add a description for the JIT interface, from Andi Kleen. * Assorted fixes for Documentation and build in 32 bit, from Robert Richter * Add support for non-tracepoint events in perf script python, from Feng Tang * Cache the libtraceevent event_format associated to each evsel early, so that we avoid relookups, i.e. calling pevent_find_event repeatedly when processing tracepoint events. [ This is to reduce the surface contact with libtraceevents and make clear what is that the perf tools needs from that lib: so far parsing the common and per event fields. ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'net/core/sock.c')
-rw-r--r--net/core/sock.c74
1 files changed, 69 insertions, 5 deletions
diff --git a/net/core/sock.c b/net/core/sock.c
index 9e5b71fda6e..6b654b3ddfd 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -142,7 +142,7 @@
static DEFINE_MUTEX(proto_list_mutex);
static LIST_HEAD(proto_list);
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
{
struct proto *proto;
@@ -271,6 +271,61 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
EXPORT_SYMBOL(sysctl_optmem_max);
+struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE;
+EXPORT_SYMBOL_GPL(memalloc_socks);
+
+/**
+ * sk_set_memalloc - sets %SOCK_MEMALLOC
+ * @sk: socket to set it on
+ *
+ * Set %SOCK_MEMALLOC on a socket for access to emergency reserves.
+ * It's the responsibility of the admin to adjust min_free_kbytes
+ * to meet the requirements
+ */
+void sk_set_memalloc(struct sock *sk)
+{
+ sock_set_flag(sk, SOCK_MEMALLOC);
+ sk->sk_allocation |= __GFP_MEMALLOC;
+ static_key_slow_inc(&memalloc_socks);
+}
+EXPORT_SYMBOL_GPL(sk_set_memalloc);
+
+void sk_clear_memalloc(struct sock *sk)
+{
+ sock_reset_flag(sk, SOCK_MEMALLOC);
+ sk->sk_allocation &= ~__GFP_MEMALLOC;
+ static_key_slow_dec(&memalloc_socks);
+
+ /*
+ * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward
+ * progress of swapping. However, if SOCK_MEMALLOC is cleared while
+ * it has rmem allocations there is a risk that the user of the
+ * socket cannot make forward progress due to exceeding the rmem
+ * limits. By rights, sk_clear_memalloc() should only be called
+ * on sockets being torn down but warn and reset the accounting if
+ * that assumption breaks.
+ */
+ if (WARN_ON(sk->sk_forward_alloc))
+ sk_mem_reclaim(sk);
+}
+EXPORT_SYMBOL_GPL(sk_clear_memalloc);
+
+int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
+{
+ int ret;
+ unsigned long pflags = current->flags;
+
+ /* these should have been dropped before queueing */
+ BUG_ON(!sock_flag(sk, SOCK_MEMALLOC));
+
+ current->flags |= PF_MEMALLOC;
+ ret = sk->sk_backlog_rcv(sk, skb);
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
+
+ return ret;
+}
+EXPORT_SYMBOL(__sk_backlog_rcv);
+
#if defined(CONFIG_CGROUPS)
#if !defined(CONFIG_NET_CLS_CGROUP)
int net_cls_subsys_id = -1;
@@ -353,7 +408,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
if (err)
return err;
- if (!sk_rmem_schedule(sk, skb->truesize)) {
+ if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
atomic_inc(&sk->sk_drops);
return -ENOBUFS;
}
@@ -1180,12 +1235,12 @@ void sock_update_classid(struct sock *sk)
}
EXPORT_SYMBOL(sock_update_classid);
-void sock_update_netprioidx(struct sock *sk)
+void sock_update_netprioidx(struct sock *sk, struct task_struct *task)
{
if (in_interrupt())
return;
- sk->sk_cgrp_prioidx = task_netprioidx(current);
+ sk->sk_cgrp_prioidx = task_netprioidx(task);
}
EXPORT_SYMBOL_GPL(sock_update_netprioidx);
#endif
@@ -1215,7 +1270,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
atomic_set(&sk->sk_wmem_alloc, 1);
sock_update_classid(sk);
- sock_update_netprioidx(sk);
+ sock_update_netprioidx(sk, current);
}
return sk;
@@ -1465,6 +1520,11 @@ void sock_rfree(struct sk_buff *skb)
}
EXPORT_SYMBOL(sock_rfree);
+void sock_edemux(struct sk_buff *skb)
+{
+ sock_put(skb->sk);
+}
+EXPORT_SYMBOL(sock_edemux);
int sock_i_uid(struct sock *sk)
{
@@ -2154,6 +2214,10 @@ void release_sock(struct sock *sk)
spin_lock_bh(&sk->sk_lock.slock);
if (sk->sk_backlog.tail)
__release_sock(sk);
+
+ if (sk->sk_prot->release_cb)
+ sk->sk_prot->release_cb(sk);
+
sk->sk_lock.owned = 0;
if (waitqueue_active(&sk->sk_lock.wq))
wake_up(&sk->sk_lock.wq);