diff mbox series

[RFC,1/3] Lazy percpu counters

Message ID 20240412092441.3112481-2-zhangpeng362@huawei.com (mailing list archive)
State New
Headers show
Series mm: convert mm's rss stats into lazy_percpu_counter | expand

Commit Message

Peng Zhang April 12, 2024, 9:24 a.m. UTC
From: Kent Overstreet <kent.overstreet@linux.dev>

This patch adds lib/lazy-percpu-counter.c, which implements counters
that start out as atomics, but lazily switch to percpu mode if the
update rate crosses some threshold (arbitrarily set at 256 per second).

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: ZhangPeng <zhangpeng362@huawei.com>
---
 include/linux/lazy-percpu-counter.h | 82 +++++++++++++++++++++++++++++
 lib/Makefile                        |  2 +-
 lib/lazy-percpu-counter.c           | 82 +++++++++++++++++++++++++++++
 3 files changed, 165 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/lazy-percpu-counter.h
 create mode 100644 lib/lazy-percpu-counter.c
diff mbox series

Patch

diff --git a/include/linux/lazy-percpu-counter.h b/include/linux/lazy-percpu-counter.h
new file mode 100644
index 000000000000..281b8dd88cb2
--- /dev/null
+++ b/include/linux/lazy-percpu-counter.h
@@ -0,0 +1,82 @@ 
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Lazy percpu counters:
+ * (C) 2022 Kent Overstreet
+ *
+ * Lazy percpu counters start out in atomic mode, then switch to percpu mode if
+ * the update rate crosses some threshold.
+ *
+ * This means we don't have to decide between low memory overhead atomic
+ * counters and higher performance percpu counters - we can have our cake and
+ * eat it, too!
+ *
+ * Internally we use an atomic64_t, where the low bit indicates whether we're in
+ * percpu mode, and the high 8 bits are a secondary counter that's incremented
+ * when the counter is modified - meaning 55 bits of precision are available for
+ * the counter itself.
+ */
+
+#ifndef _LINUX_LAZY_PERCPU_COUNTER_H
+#define _LINUX_LAZY_PERCPU_COUNTER_H
+
+#include <linux/atomic.h>
+#include <asm/percpu.h>
+
+struct lazy_percpu_counter {
+	atomic64_t			v;
+	unsigned long			last_wrap;
+};
+
+void lazy_percpu_counter_exit(struct lazy_percpu_counter *c);
+void lazy_percpu_counter_add_slowpath(struct lazy_percpu_counter *c, s64 i);
+
+/*
+ * We use the high bits of the atomic counter for a secondary counter, which is
+ * incremented every time the counter is touched. When the secondary counter
+ * wraps, we check the time the counter last wrapped, and if it was recent
+ * enough that means the update frequency has crossed our threshold and we
+ * switch to percpu mode:
+ */
+#define COUNTER_MOD_BITS		8
+#define COUNTER_MOD_MASK		~(~0ULL >> COUNTER_MOD_BITS)
+#define COUNTER_MOD_BITS_START		(64 - COUNTER_MOD_BITS)
+
+/*
+ * We use the low bit of the counter to indicate whether we're in atomic mode
+ * (low bit clear), or percpu mode (low bit set, counter is a pointer to actual
+ * percpu counters:
+ */
+#define COUNTER_IS_PCPU_BIT		1
+
+static inline u64 __percpu *lazy_percpu_counter_is_pcpu(u64 v)
+{
+	if (!(v & COUNTER_IS_PCPU_BIT))
+		return NULL;
+
+	v ^= COUNTER_IS_PCPU_BIT;
+	return (u64 __percpu *)(unsigned long)v;
+}
+
+/**
+ * lazy_percpu_counter_add: Add a value to a lazy_percpu_counter
+ *
+ * @c: counter to modify
+ * @i: value to add
+ */
+static inline void lazy_percpu_counter_add(struct lazy_percpu_counter *c, s64 i)
+{
+	u64 v = atomic64_read(&c->v);
+	u64 __percpu *pcpu_v = lazy_percpu_counter_is_pcpu(v);
+
+	if (likely(pcpu_v))
+		this_cpu_add(*pcpu_v, i);
+	else
+		lazy_percpu_counter_add_slowpath(c, i);
+}
+
+static inline void lazy_percpu_counter_sub(struct lazy_percpu_counter *c, s64 i)
+{
+	lazy_percpu_counter_add(c, -i);
+}
+
+#endif /* _LINUX_LAZY_PERCPU_COUNTER_H */
diff --git a/lib/Makefile b/lib/Makefile
index 2f4e17bfb299..7afa0c3e7cc7 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -46,7 +46,7 @@  obj-y += bcd.o sort.o parser.o debug_locks.o random32.o \
 	 bust_spinlocks.o kasprintf.o bitmap.o scatterlist.o \
 	 list_sort.o uuid.o iov_iter.o clz_ctz.o \
 	 bsearch.o find_bit.o llist.o lwq.o memweight.o kfifo.o \
-	 percpu-refcount.o rhashtable.o base64.o \
+	 percpu-refcount.o lazy-percpu-counter.o rhashtable.o base64.o \
 	 once.o refcount.o rcuref.o usercopy.o errseq.o bucket_locks.o \
 	 generic-radix-tree.o bitmap-str.o
 obj-$(CONFIG_STRING_KUNIT_TEST) += string_kunit.o
diff --git a/lib/lazy-percpu-counter.c b/lib/lazy-percpu-counter.c
new file mode 100644
index 000000000000..e1914207214d
--- /dev/null
+++ b/lib/lazy-percpu-counter.c
@@ -0,0 +1,82 @@ 
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/atomic.h>
+#include <linux/gfp.h>
+#include <linux/jiffies.h>
+#include <linux/lazy-percpu-counter.h>
+#include <linux/percpu.h>
+
+static inline s64 lazy_percpu_counter_atomic_val(s64 v)
+{
+	/* Ensure output is sign extended properly: */
+	return (v << COUNTER_MOD_BITS) >>
+		(COUNTER_MOD_BITS + COUNTER_IS_PCPU_BIT);
+}
+
+static void lazy_percpu_counter_switch_to_pcpu(struct lazy_percpu_counter *c)
+{
+	u64 __percpu *pcpu_v = alloc_percpu_gfp(u64, GFP_ATOMIC|__GFP_NOWARN);
+	u64 old, new, v;
+
+	if (!pcpu_v)
+		return;
+
+	preempt_disable();
+	v = atomic64_read(&c->v);
+	do {
+		if (lazy_percpu_counter_is_pcpu(v)) {
+			free_percpu(pcpu_v);
+			return;
+		}
+
+		old = v;
+		new = (unsigned long)pcpu_v | 1;
+
+		*this_cpu_ptr(pcpu_v) = lazy_percpu_counter_atomic_val(v);
+	} while ((v = atomic64_cmpxchg(&c->v, old, new)) != old);
+	preempt_enable();
+}
+
+/**
+ * lazy_percpu_counter_exit: Free resources associated with a
+ * lazy_percpu_counter
+ *
+ * @c: counter to exit
+ */
+void lazy_percpu_counter_exit(struct lazy_percpu_counter *c)
+{
+	free_percpu(lazy_percpu_counter_is_pcpu(atomic64_read(&c->v)));
+}
+EXPORT_SYMBOL_GPL(lazy_percpu_counter_exit);
+
+void lazy_percpu_counter_add_slowpath(struct lazy_percpu_counter *c, s64 i)
+{
+	u64 atomic_i;
+	u64 old, v = atomic64_read(&c->v);
+	u64 __percpu *pcpu_v;
+
+	atomic_i  = i << COUNTER_IS_PCPU_BIT;
+	atomic_i &= ~COUNTER_MOD_MASK;
+	atomic_i |= 1ULL << COUNTER_MOD_BITS_START;
+
+	do {
+		pcpu_v = lazy_percpu_counter_is_pcpu(v);
+		if (pcpu_v) {
+			this_cpu_add(*pcpu_v, i);
+			return;
+		}
+
+		old = v;
+	} while ((v = atomic64_cmpxchg(&c->v, old, old + atomic_i)) != old);
+
+	if (unlikely(!(v & COUNTER_MOD_MASK))) {
+		unsigned long now = jiffies;
+
+		if (c->last_wrap &&
+		    unlikely(time_after(c->last_wrap + HZ, now)))
+			lazy_percpu_counter_switch_to_pcpu(c);
+		else
+			c->last_wrap = now;
+	}
+}
+EXPORT_SYMBOL(lazy_percpu_counter_add_slowpath);