| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Fri, 4 Mar 2016 21:51:38 -0500
From: Waiman Long <Waiman.Long@....com>
To: Tejun Heo <tj@...nel.org>,
Christoph Lameter <cl@...ux-foundation.org>,
Dave Chinner <dchinner@...hat.com>
Cc: xfs@....sgi.com, linux-kernel@...r.kernel.org,
Ingo Molnar <mingo@...hat.com>,
Peter Zijlstra <peterz@...radead.org>,
Scott J Norton <scott.norton@...com>,
Douglas Hatch <doug.hatch@...com>,
Waiman Long <Waiman.Long@....com>
Subject: [RFC PATCH 1/2] percpu_counter: Allow falling back to global counter on large system
Per-cpu counters are used in quite a number of places within
the kernel. On large system with a lot of CPUs, however, doing a
percpu_counter_sum() can be very expensive as nr_cpu cachelines will
need to be read. In __percpu_counter_compare(), the chance of calling
percpu_counter_sum() also increases with increasing number of CPUs
if the global counter value is relatively small.
On large system, using a global counter with lock may actually be
faster than doing a percpu_counter_sum() which can be frequently
called from __percpu_counter_compare().
This patch provides a mechanism to selectively degenerate per-cpu
counters to global counters at per-cpu counter initialization time. The
following new API is added:
percpu_counter_set_limit(struct percpu_counter *fbc,
u32 percpu_limit)
The function should be called after percpu_counter_set(). It will
compare the total limit (nr_cpu * percpu_limit) against the current
counter value. If the limit is not smaller, it will disable per-cpu
counter and use only the global counter instead. At run time, when
the counter value grows past the total limit, per-cpu counter will
be enabled again.
Runtime disabling of per-cpu counters, however, is not currently
supported as it will slow down the per-cpu fast path.
Signed-off-by: Waiman Long <Waiman.Long@....com>
---
include/linux/percpu_counter.h | 10 +++++
lib/percpu_counter.c | 72 +++++++++++++++++++++++++++++++++++++++-
2 files changed, 81 insertions(+), 1 deletions(-)
diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index 84a1094..04a3783 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -16,8 +16,14 @@
#ifdef CONFIG_SMP
+/*
+ * The per-cpu counter will be degenerated into a global counter when limit
+ * is set at initialization time. It will change back to a real per-cpu
+ * counter once the count exceed the given limit.
+ */
struct percpu_counter {
raw_spinlock_t lock;
+ u32 limit;
s64 count;
#ifdef CONFIG_HOTPLUG_CPU
struct list_head list; /* All percpu_counters are on a list */
@@ -42,6 +48,7 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount);
void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch);
s64 __percpu_counter_sum(struct percpu_counter *fbc);
int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch);
+void percpu_counter_set_limit(struct percpu_counter *fbc, u32 percpu_limit);
static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
{
@@ -170,6 +177,9 @@ static inline int percpu_counter_initialized(struct percpu_counter *fbc)
return 1;
}
+static inline void percpu_counter_set_limit(struct percpu_counter *fbc,
+ u32 percpu_limit) { }
+
#endif /* CONFIG_SMP */
static inline void percpu_counter_inc(struct percpu_counter *fbc)
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index f051d69..f101c06 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -75,11 +75,25 @@ EXPORT_SYMBOL(percpu_counter_set);
void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch)
{
s64 count;
+ unsigned long flags;
+
+ if (fbc->limit) {
+ raw_spin_lock_irqsave(&fbc->lock, flags);
+ if (unlikely(!fbc->limit)) {
+ raw_spin_unlock_irqrestore(&fbc->lock, flags);
+ goto percpu_add;
+ }
+ fbc->count += amount;
+ if (abs(fbc->count) > fbc->limit)
+ fbc->limit = 0; /* Revert back to per-cpu counter */
+ raw_spin_unlock_irqrestore(&fbc->lock, flags);
+ return;
+ }
+percpu_add:
preempt_disable();
count = __this_cpu_read(*fbc->counters) + amount;
if (count >= batch || count <= -batch) {
- unsigned long flags;
raw_spin_lock_irqsave(&fbc->lock, flags);
fbc->count += count;
__this_cpu_sub(*fbc->counters, count - amount);
@@ -94,6 +108,8 @@ EXPORT_SYMBOL(__percpu_counter_add);
/*
* Add up all the per-cpu counts, return the result. This is a more accurate
* but much slower version of percpu_counter_read_positive()
+ *
+ * If a limit is set, the count can be returned directly without locking.
*/
s64 __percpu_counter_sum(struct percpu_counter *fbc)
{
@@ -101,6 +117,9 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc)
int cpu;
unsigned long flags;
+ if (READ_ONCE(fbc->limit))
+ return READ_ONCE(fbc->count);
+
raw_spin_lock_irqsave(&fbc->lock, flags);
ret = fbc->count;
for_each_online_cpu(cpu) {
@@ -120,6 +139,7 @@ int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp,
raw_spin_lock_init(&fbc->lock);
lockdep_set_class(&fbc->lock, key);
fbc->count = amount;
+ fbc->limit = 0;
fbc->counters = alloc_percpu_gfp(s32, gfp);
if (!fbc->counters)
return -ENOMEM;
@@ -202,6 +222,9 @@ int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch)
s64 count;
count = percpu_counter_read(fbc);
+ if (READ_ONCE(fbc->limit))
+ goto compare;
+
/* Check to see if rough count will be sufficient for comparison */
if (abs(count - rhs) > (batch * num_online_cpus())) {
if (count > rhs)
@@ -211,6 +234,7 @@ int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch)
}
/* Need to use precise count */
count = percpu_counter_sum(fbc);
+compare:
if (count > rhs)
return 1;
else if (count < rhs)
@@ -220,6 +244,52 @@ int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch)
}
EXPORT_SYMBOL(__percpu_counter_compare);
+/*
+ * Set the limit if the count is less than the given per-cpu limit * # of cpus.
+ *
+ * This function should only be called at initialization time right after
+ * percpu_counter_set(). Limit will only be set if there is more than
+ * 32 cpus in the system and the current counter value is not bigger than
+ * the limit. Once it is set, it can be cleared as soon as the counter
+ * value exceeds the given limit and real per-cpu counters are used again.
+ * However, switching from per-cpu counters back to global counter is not
+ * currently supported as that will slow down the per-cpu counter fastpath.
+ *
+ * The magic number 32 is chosen to be a compromise between the cost of
+ * reading all the per-cpu counters and that of locking. It can be changed
+ * if there is a better value.
+ */
+#define PERCPU_SET_LIMIT_CPU_THRESHOLD 32
+void percpu_counter_set_limit(struct percpu_counter *fbc, u32 percpu_limit)
+{
+ unsigned long flags;
+ int nrcpus = num_possible_cpus();
+ u32 limit;
+
+ if (nrcpus <= PERCPU_SET_LIMIT_CPU_THRESHOLD)
+ return;
+
+ if (!fbc->count) {
+ WARN(1, "percpu_counter_set_limit() called without an initial counter value!\n");
+ return;
+ }
+ /*
+ * Use default batch size if the given percpu limit is 0.
+ */
+ if (!percpu_limit)
+ percpu_limit = percpu_counter_batch;
+ limit = percpu_limit * nrcpus;
+
+ /*
+ * Limit will not be set if the count is large enough
+ */
+ raw_spin_lock_irqsave(&fbc->lock, flags);
+ if (abs(fbc->count) <= limit)
+ fbc->limit = limit;
+ raw_spin_unlock_irqrestore(&fbc->lock, flags);
+}
+EXPORT_SYMBOL(percpu_counter_set_limit);
+
static int __init percpu_counter_startup(void)
{
compute_batch_value();
--
1.7.1
Powered by blists - more mailing lists