summaryrefslogtreecommitdiffstats
path: root/net/core/sock.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/core/sock.c')
-rw-r--r--net/core/sock.c134
1 files changed, 93 insertions, 41 deletions
diff --git a/net/core/sock.c b/net/core/sock.c
index 9777da86aea..002939cfc06 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -111,6 +111,7 @@
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/user_namespace.h>
+#include <linux/jump_label.h>
#include <asm/uaccess.h>
#include <asm/system.h>
@@ -135,6 +136,46 @@
#include <net/tcp.h>
#endif
+static DEFINE_MUTEX(proto_list_mutex);
+static LIST_HEAD(proto_list);
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+ struct proto *proto;
+ int ret = 0;
+
+ mutex_lock(&proto_list_mutex);
+ list_for_each_entry(proto, &proto_list, node) {
+ if (proto->init_cgroup) {
+ ret = proto->init_cgroup(cgrp, ss);
+ if (ret)
+ goto out;
+ }
+ }
+
+ mutex_unlock(&proto_list_mutex);
+ return ret;
+out:
+ list_for_each_entry_continue_reverse(proto, &proto_list, node)
+ if (proto->destroy_cgroup)
+ proto->destroy_cgroup(cgrp, ss);
+ mutex_unlock(&proto_list_mutex);
+ return ret;
+}
+
+void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+ struct proto *proto;
+
+ mutex_lock(&proto_list_mutex);
+ list_for_each_entry_reverse(proto, &proto_list, node)
+ if (proto->destroy_cgroup)
+ proto->destroy_cgroup(cgrp, ss);
+ mutex_unlock(&proto_list_mutex);
+}
+#endif
+
/*
* Each address family might have different locking rules, so we have
* one slock key per address family:
@@ -142,6 +183,9 @@
static struct lock_class_key af_family_keys[AF_MAX];
static struct lock_class_key af_family_slock_keys[AF_MAX];
+struct jump_label_key memcg_socket_limit_enabled;
+EXPORT_SYMBOL(memcg_socket_limit_enabled);
+
/*
* Make lock validator output more readable. (we pre-construct these
* strings build-time, so that runtime initialization of socket
@@ -295,11 +339,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
unsigned long flags;
struct sk_buff_head *list = &sk->sk_receive_queue;
- /* Cast sk->rcvbuf to unsigned... It's pointless, but reduces
- number of warnings when compiling with -W --ANK
- */
- if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
- (unsigned)sk->sk_rcvbuf) {
+ if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) {
atomic_inc(&sk->sk_drops);
trace_sock_rcvqueue_full(sk, skb);
return -ENOMEM;
@@ -1323,7 +1363,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
newsk->sk_wq = NULL;
if (newsk->sk_prot->sockets_allocated)
- percpu_counter_inc(newsk->sk_prot->sockets_allocated);
+ sk_sockets_allocated_inc(newsk);
if (newsk->sk_flags & SK_FLAGS_TIMESTAMP)
net_enable_timestamp();
@@ -1711,30 +1751,34 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind)
struct proto *prot = sk->sk_prot;
int amt = sk_mem_pages(size);
long allocated;
+ int parent_status = UNDER_LIMIT;
sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
- allocated = atomic_long_add_return(amt, prot->memory_allocated);
+
+ allocated = sk_memory_allocated_add(sk, amt, &parent_status);
/* Under limit. */
- if (allocated <= prot->sysctl_mem[0]) {
- if (prot->memory_pressure && *prot->memory_pressure)
- *prot->memory_pressure = 0;
+ if (parent_status == UNDER_LIMIT &&
+ allocated <= sk_prot_mem_limits(sk, 0)) {
+ sk_leave_memory_pressure(sk);
return 1;
}
- /* Under pressure. */
- if (allocated > prot->sysctl_mem[1])
- if (prot->enter_memory_pressure)
- prot->enter_memory_pressure(sk);
+ /* Under pressure. (we or our parents) */
+ if ((parent_status > SOFT_LIMIT) ||
+ allocated > sk_prot_mem_limits(sk, 1))
+ sk_enter_memory_pressure(sk);
- /* Over hard limit. */
- if (allocated > prot->sysctl_mem[2])
+ /* Over hard limit (we or our parents) */
+ if ((parent_status == OVER_LIMIT) ||
+ (allocated > sk_prot_mem_limits(sk, 2)))
goto suppress_allocation;
/* guarantee minimum buffer size under pressure */
if (kind == SK_MEM_RECV) {
if (atomic_read(&sk->sk_rmem_alloc) < prot->sysctl_rmem[0])
return 1;
+
} else { /* SK_MEM_SEND */
if (sk->sk_type == SOCK_STREAM) {
if (sk->sk_wmem_queued < prot->sysctl_wmem[0])
@@ -1744,13 +1788,13 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind)
return 1;
}
- if (prot->memory_pressure) {
+ if (sk_has_memory_pressure(sk)) {
int alloc;
- if (!*prot->memory_pressure)
+ if (!sk_under_memory_pressure(sk))
return 1;
- alloc = percpu_counter_read_positive(prot->sockets_allocated);
- if (prot->sysctl_mem[2] > alloc *
+ alloc = sk_sockets_allocated_read_positive(sk);
+ if (sk_prot_mem_limits(sk, 2) > alloc *
sk_mem_pages(sk->sk_wmem_queued +
atomic_read(&sk->sk_rmem_alloc) +
sk->sk_forward_alloc))
@@ -1773,7 +1817,9 @@ suppress_allocation:
/* Alas. Undo changes. */
sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM;
- atomic_long_sub(amt, prot->memory_allocated);
+
+ sk_memory_allocated_sub(sk, amt, parent_status);
+
return 0;
}
EXPORT_SYMBOL(__sk_mem_schedule);
@@ -1784,15 +1830,13 @@ EXPORT_SYMBOL(__sk_mem_schedule);
*/
void __sk_mem_reclaim(struct sock *sk)
{
- struct proto *prot = sk->sk_prot;
-
- atomic_long_sub(sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT,
- prot->memory_allocated);
+ sk_memory_allocated_sub(sk,
+ sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT, 0);
sk->sk_forward_alloc &= SK_MEM_QUANTUM - 1;
- if (prot->memory_pressure && *prot->memory_pressure &&
- (atomic_long_read(prot->memory_allocated) < prot->sysctl_mem[0]))
- *prot->memory_pressure = 0;
+ if (sk_under_memory_pressure(sk) &&
+ (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)))
+ sk_leave_memory_pressure(sk);
}
EXPORT_SYMBOL(__sk_mem_reclaim);
@@ -2283,9 +2327,6 @@ void sk_common_release(struct sock *sk)
}
EXPORT_SYMBOL(sk_common_release);
-static DEFINE_RWLOCK(proto_list_lock);
-static LIST_HEAD(proto_list);
-
#ifdef CONFIG_PROC_FS
#define PROTO_INUSE_NR 64 /* should be enough for the first time */
struct prot_inuse {
@@ -2434,10 +2475,10 @@ int proto_register(struct proto *prot, int alloc_slab)
}
}
- write_lock(&proto_list_lock);
+ mutex_lock(&proto_list_mutex);
list_add(&prot->node, &proto_list);
assign_proto_idx(prot);
- write_unlock(&proto_list_lock);
+ mutex_unlock(&proto_list_mutex);
return 0;
out_free_timewait_sock_slab_name:
@@ -2460,10 +2501,10 @@ EXPORT_SYMBOL(proto_register);
void proto_unregister(struct proto *prot)
{
- write_lock(&proto_list_lock);
+ mutex_lock(&proto_list_mutex);
release_proto_idx(prot);
list_del(&prot->node);
- write_unlock(&proto_list_lock);
+ mutex_unlock(&proto_list_mutex);
if (prot->slab != NULL) {
kmem_cache_destroy(prot->slab);
@@ -2486,9 +2527,9 @@ EXPORT_SYMBOL(proto_unregister);
#ifdef CONFIG_PROC_FS
static void *proto_seq_start(struct seq_file *seq, loff_t *pos)
- __acquires(proto_list_lock)
+ __acquires(proto_list_mutex)
{
- read_lock(&proto_list_lock);
+ mutex_lock(&proto_list_mutex);
return seq_list_start_head(&proto_list, *pos);
}
@@ -2498,25 +2539,36 @@ static void *proto_seq_next(struct seq_file *seq, void *v, loff_t *pos)
}
static void proto_seq_stop(struct seq_file *seq, void *v)
- __releases(proto_list_lock)
+ __releases(proto_list_mutex)
{
- read_unlock(&proto_list_lock);
+ mutex_unlock(&proto_list_mutex);
}
static char proto_method_implemented(const void *method)
{
return method == NULL ? 'n' : 'y';
}
+static long sock_prot_memory_allocated(struct proto *proto)
+{
+ return proto->memory_allocated != NULL ? proto_memory_allocated(proto): -1L;
+}
+
+static char *sock_prot_memory_pressure(struct proto *proto)
+{
+ return proto->memory_pressure != NULL ?
+ proto_memory_pressure(proto) ? "yes" : "no" : "NI";
+}
static void proto_seq_printf(struct seq_file *seq, struct proto *proto)
{
+
seq_printf(seq, "%-9s %4u %6d %6ld %-3s %6u %-3s %-10s "
"%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n",
proto->name,
proto->obj_size,
sock_prot_inuse_get(seq_file_net(seq), proto),
- proto->memory_allocated != NULL ? atomic_long_read(proto->memory_allocated) : -1L,
- proto->memory_pressure != NULL ? *proto->memory_pressure ? "yes" : "no" : "NI",
+ sock_prot_memory_allocated(proto),
+ sock_prot_memory_pressure(proto),
proto->max_header,
proto->slab == NULL ? "no" : "yes",
module_name(proto->owner),
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-04-18 03:43:33 +0000