summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorGlauber Costa <glommer@parallels.com>2011-12-11 22:47:02 +0100
committerDavid S. Miller <davem@davemloft.net>2011-12-13 01:04:10 +0100
commit180d8cd942ce336b2c869d324855c40c5db478ad (patch)
tree2424d854345d81464d6030ef8090a8e22bd414b0 /net
parentBasic kernel memory functionality for the Memory Controller (diff)
downloadlinux-180d8cd942ce336b2c869d324855c40c5db478ad.tar.xz
linux-180d8cd942ce336b2c869d324855c40c5db478ad.zip
foundations of per-cgroup memory pressure controlling.
This patch replaces all uses of struct sock fields' memory_pressure, memory_allocated, sockets_allocated, and sysctl_mem to acessor macros. Those macros can either receive a socket argument, or a mem_cgroup argument, depending on the context they live in. Since we're only doing a macro wrapping here, no performance impact at all is expected in the case where we don't have cgroups disabled. Signed-off-by: Glauber Costa <glommer@parallels.com> Reviewed-by: Hiroyouki Kamezawa <kamezawa.hiroyu@jp.fujitsu.com> CC: David S. Miller <davem@davemloft.net> CC: Eric W. Biederman <ebiederm@xmission.com> CC: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/core/sock.c57
-rw-r--r--net/ipv4/proc.c6
-rw-r--r--net/ipv4/tcp_input.c12
-rw-r--r--net/ipv4/tcp_ipv4.c4
-rw-r--r--net/ipv4/tcp_output.c2
-rw-r--r--net/ipv4/tcp_timer.c2
-rw-r--r--net/ipv6/tcp_ipv6.c2
7 files changed, 48 insertions, 37 deletions
diff --git a/net/core/sock.c b/net/core/sock.c
index 9777da86aeac..a3d4205e7238 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1323,7 +1323,7 @@ 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();
@@ -1713,28 +1713,28 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind)
long allocated;
sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
- allocated = atomic_long_add_return(amt, prot->memory_allocated);
+
+ allocated = sk_memory_allocated_add(sk, amt);
/* Under limit. */
- if (allocated <= prot->sysctl_mem[0]) {
- if (prot->memory_pressure && *prot->memory_pressure)
- *prot->memory_pressure = 0;
+ if (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);
+ if (allocated > sk_prot_mem_limits(sk, 1))
+ sk_enter_memory_pressure(sk);
/* Over hard limit. */
- if (allocated > prot->sysctl_mem[2])
+ if (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 +1744,13 @@ 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 +1773,9 @@ 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);
+
return 0;
}
EXPORT_SYMBOL(__sk_mem_schedule);
@@ -1784,15 +1786,13 @@ 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);
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);
@@ -2507,16 +2507,27 @@ 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),
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 961eed4f510a..3569d8ecaeac 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -56,17 +56,17 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
local_bh_disable();
orphans = percpu_counter_sum_positive(&tcp_orphan_count);
- sockets = percpu_counter_sum_positive(&tcp_sockets_allocated);
+ sockets = proto_sockets_allocated_sum_positive(&tcp_prot);
local_bh_enable();
socket_seq_show(seq);
seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n",
sock_prot_inuse_get(net, &tcp_prot), orphans,
tcp_death_row.tw_count, sockets,
- atomic_long_read(&tcp_memory_allocated));
+ proto_memory_allocated(&tcp_prot));
seq_printf(seq, "UDP: inuse %d mem %ld\n",
sock_prot_inuse_get(net, &udp_prot),
- atomic_long_read(&udp_memory_allocated));
+ proto_memory_allocated(&udp_prot));
seq_printf(seq, "UDPLITE: inuse %d\n",
sock_prot_inuse_get(net, &udplite_prot));
seq_printf(seq, "RAW: inuse %d\n",
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b9cbc351c511..f131d92d25ee 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -322,7 +322,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
/* Check #1 */
if (tp->rcv_ssthresh < tp->window_clamp &&
(int)tp->rcv_ssthresh < tcp_space(sk) &&
- !tcp_memory_pressure) {
+ !sk_under_memory_pressure(sk)) {
int incr;
/* Check #2. Increase window, if skb with such overhead
@@ -411,8 +411,8 @@ static void tcp_clamp_window(struct sock *sk)
if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
- !tcp_memory_pressure &&
- atomic_long_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) {
+ !sk_under_memory_pressure(sk) &&
+ sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
sysctl_tcp_rmem[2]);
}
@@ -4866,7 +4866,7 @@ static int tcp_prune_queue(struct sock *sk)
if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
tcp_clamp_window(sk);
- else if (tcp_memory_pressure)
+ else if (sk_under_memory_pressure(sk))
tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
tcp_collapse_ofo_queue(sk);
@@ -4932,11 +4932,11 @@ static int tcp_should_expand_sndbuf(const struct sock *sk)
return 0;
/* If we are under global TCP memory pressure, do not expand. */
- if (tcp_memory_pressure)
+ if (sk_under_memory_pressure(sk))
return 0;
/* If we are under soft global TCP memory pressure, do not expand. */
- if (atomic_long_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0])
+ if (sk_memory_allocated(sk) >= sk_prot_mem_limits(sk, 0))
return 0;
/* If we filled the congestion window, do not expand. */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index c4b8b09db9f5..f48bf312cfe8 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1917,7 +1917,7 @@ static int tcp_v4_init_sock(struct sock *sk)
sk->sk_rcvbuf = sysctl_tcp_rmem[1];
local_bh_disable();
- percpu_counter_inc(&tcp_sockets_allocated);
+ sk_sockets_allocated_inc(sk);
local_bh_enable();
return 0;
@@ -1973,7 +1973,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
tp->cookie_values = NULL;
}
- percpu_counter_dec(&tcp_sockets_allocated);
+ sk_sockets_allocated_dec(sk);
}
EXPORT_SYMBOL(tcp_v4_destroy_sock);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index cf3068038942..8c8de2780c7a 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1922,7 +1922,7 @@ u32 __tcp_select_window(struct sock *sk)
if (free_space < (full_space >> 1)) {
icsk->icsk_ack.quick = 0;
- if (tcp_memory_pressure)
+ if (sk_under_memory_pressure(sk))
tp->rcv_ssthresh = min(tp->rcv_ssthresh,
4U * tp->advmss);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index aa39a692f4c8..40a41f077981 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -261,7 +261,7 @@ static void tcp_delack_timer(unsigned long data)
}
out:
- if (tcp_memory_pressure)
+ if (sk_under_memory_pressure(sk))
sk_mem_reclaim(sk);
out_unlock:
bh_unlock_sock(sk);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 9d74eee334d6..b69c7030aba9 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1994,7 +1994,7 @@ static int tcp_v6_init_sock(struct sock *sk)
sk->sk_rcvbuf = sysctl_tcp_rmem[1];
local_bh_disable();
- percpu_counter_inc(&tcp_sockets_allocated);
+ sk_sockets_allocated_inc(sk);
local_bh_enable();
return 0;