snmp: reduce percpu needs by 50%
SNMP mibs use two percpu arrays, one used in BH context, another in USER
context. With increasing number of cpus in machines, and fact that ipv6
uses per network device ipstats_mib, this is consuming a lot of memory
if many network devices are registered.
commit be281e554e2a (ipv6: reduce per device ICMP mib sizes) shrinked
percpu needs for ipv6, but we can reduce memory use a bit more.
With recent percpu infrastructure (irqsafe_cpu_inc() ...), we no longer
need this BH/USER separation since we can update counters in a single
x86 instruction, regardless of the BH/USER context.
Other arches than x86 might need to disable irq in their
irqsafe_cpu_inc() implementation : If this happens to be a problem, we
can make SNMP_ARRAY_SZ arch dependent, but a previous poll
( https://lkml.org/lkml/2011/3/17/174 ) to arch maintainers did not
raise strong opposition.
Only on 32bit arches, we need to disable BH for 64bit counters updates
done from USER context (currently used for IP MIB)
This also reduces vmlinux size :
1) x86_64 build
$ size vmlinux.before vmlinux.after
text data bss dec hex filename
7853650 1293772 1896448 11043870 a8841e vmlinux.before
7850578 1293772 1896448 11040798 a8781e vmlinux.after
2) i386 build
$ size vmlinux.before vmlinux.afterpatch
text data bss dec hex filename
6039335 635076 3670016 10344427 9dd7eb vmlinux.before
6037342 635076 3670016 10342434 9dd022 vmlinux.afterpatch
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Andi Kleen <andi@firstfloor.org>
CC: Ingo Molnar <mingo@elte.hu>
CC: Tejun Heo <tj@kernel.org>
CC: Christoph Lameter <cl@linux-foundation.org>
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org
CC: linux-arch@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 9c19260..83673d2 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1437,11 +1437,11 @@
unsigned long snmp_fold_field(void __percpu *mib[], int offt)
{
unsigned long res = 0;
- int i;
+ int i, j;
for_each_possible_cpu(i) {
- res += *(((unsigned long *) per_cpu_ptr(mib[0], i)) + offt);
- res += *(((unsigned long *) per_cpu_ptr(mib[1], i)) + offt);
+ for (j = 0; j < SNMP_ARRAY_SZ; j++)
+ res += *(((unsigned long *) per_cpu_ptr(mib[j], i)) + offt);
}
return res;
}
@@ -1455,28 +1455,19 @@
int cpu;
for_each_possible_cpu(cpu) {
- void *bhptr, *userptr;
+ void *bhptr;
struct u64_stats_sync *syncp;
- u64 v_bh, v_user;
+ u64 v;
unsigned int start;
- /* first mib used by softirq context, we must use _bh() accessors */
- bhptr = per_cpu_ptr(SNMP_STAT_BHPTR(mib), cpu);
+ bhptr = per_cpu_ptr(mib[0], cpu);
syncp = (struct u64_stats_sync *)(bhptr + syncp_offset);
do {
start = u64_stats_fetch_begin_bh(syncp);
- v_bh = *(((u64 *) bhptr) + offt);
+ v = *(((u64 *) bhptr) + offt);
} while (u64_stats_fetch_retry_bh(syncp, start));
- /* second mib used in USER context */
- userptr = per_cpu_ptr(SNMP_STAT_USRPTR(mib), cpu);
- syncp = (struct u64_stats_sync *)(userptr + syncp_offset);
- do {
- start = u64_stats_fetch_begin(syncp);
- v_user = *(((u64 *) userptr) + offt);
- } while (u64_stats_fetch_retry(syncp, start));
-
- res += v_bh + v_user;
+ res += v;
}
return res;
}
@@ -1488,25 +1479,28 @@
BUG_ON(ptr == NULL);
ptr[0] = __alloc_percpu(mibsize, align);
if (!ptr[0])
- goto err0;
+ return -ENOMEM;
+#if SNMP_ARRAY_SZ == 2
ptr[1] = __alloc_percpu(mibsize, align);
- if (!ptr[1])
- goto err1;
+ if (!ptr[1]) {
+ free_percpu(ptr[0]);
+ ptr[0] = NULL;
+ return -ENOMEM;
+ }
+#endif
return 0;
-err1:
- free_percpu(ptr[0]);
- ptr[0] = NULL;
-err0:
- return -ENOMEM;
}
EXPORT_SYMBOL_GPL(snmp_mib_init);
-void snmp_mib_free(void __percpu *ptr[2])
+void snmp_mib_free(void __percpu *ptr[SNMP_ARRAY_SZ])
{
+ int i;
+
BUG_ON(ptr == NULL);
- free_percpu(ptr[0]);
- free_percpu(ptr[1]);
- ptr[0] = ptr[1] = NULL;
+ for (i = 0; i < SNMP_ARRAY_SZ; i++) {
+ free_percpu(ptr[i]);
+ ptr[i] = NULL;
+ }
}
EXPORT_SYMBOL_GPL(snmp_mib_free);