[PATCH 4/5 v1] mm: enable per numa node rss_stat count

From: Gang Li <ligang.bdlg@bytedance.com>
To: akpm@linux-foundation.org
Cc: songmuchun@bytedance.com, hca@linux.ibm.com, gor@linux.ibm.com,
	agordeev@linux.ibm.com, borntraeger@linux.ibm.com,
	svens@linux.ibm.com, ebiederm@xmission.com,
	keescook@chromium.org, viro@zeniv.linux.org.uk,
	rostedt@goodmis.org, mingo@redhat.com, peterz@infradead.org,
	acme@kernel.org, mark.rutland@arm.com,
	alexander.shishkin@linux.intel.com, jolsa@kernel.org,
	namhyung@kernel.org, david@redhat.com, imbrenda@linux.ibm.com,
	apopple@nvidia.com, adobriyan@gmail.com,
	stephen.s.brennan@oracle.com, ohoono.kwon@samsung.com,
	haolee.swjtu@gmail.com, kaleshsingh@google.com,
	zhengqi.arch@bytedance.com, peterx@redhat.com,
	shy828301@gmail.com, surenb@google.com, ccross@google.com,
	vincent.whitchurch@axis.com, tglx@linutronix.de,
	bigeasy@linutronix.de, fenghua.yu@intel.com,
	linux-s390@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
	linux-perf-users@vger.kernel.org,
	Gang Li <ligang.bdlg@bytedance.com>
Subject: [PATCH 4/5 v1] mm: enable per numa node rss_stat count
Date: Thu, 12 May 2022 12:46:33 +0800	[thread overview]
Message-ID: <20220512044634.63586-5-ligang.bdlg@bytedance.com> (raw)
In-Reply-To: <20220512044634.63586-1-ligang.bdlg@bytedance.com>

Now we have all the infrastructure ready. Modify `get/add/inc/dec_mm_counter`,
`sync_mm_rss`, `add_mm_counter_fast` and `add_mm_rss_vec` to enable per numa
node rss_stat count.

Signed-off-by: Gang Li <ligang.bdlg@bytedance.com>
---
 include/linux/mm.h | 42 +++++++++++++++++++++++++++++++++++-------
 mm/memory.c        | 20 ++++++++++++++++++--
 2 files changed, 53 insertions(+), 9 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index cde5529285d6..f0f21065b81b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1994,8 +1994,18 @@ static inline bool get_user_page_fast_only(unsigned long addr,
  */
 static inline unsigned long get_mm_counter(struct mm_struct *mm, int member, int node)
 {
-	long val = atomic_long_read(&mm->rss_stat.count[member]);
+	long val;
 
+	WARN_ON(node == NUMA_NO_NODE && member == MM_NO_TYPE);
+
+	if (node == NUMA_NO_NODE)
+		val = atomic_long_read(&mm->rss_stat.count[member]);
+	else
+#ifdef CONFIG_NUMA
+		val = atomic_long_read(&mm->rss_stat.numa_count[node]);
+#else
+		val = 0;
+#endif
 #ifdef SPLIT_RSS_COUNTING
 	/*
 	 * counter is updated in asynchronous manner and may go to minus.
@@ -2012,23 +2022,41 @@ void mm_trace_rss_stat(struct mm_struct *mm, int member, long member_count, int
 
 static inline void add_mm_counter(struct mm_struct *mm, int member, long value, int node)
 {
-	long count = atomic_long_add_return(value, &mm->rss_stat.count[member]);
+	long member_count = 0, numa_count = 0;
 
-	mm_trace_rss_stat(mm, member, count, NUMA_NO_NODE, 0, value);
+	if (member != MM_NO_TYPE)
+		member_count = atomic_long_add_return(value, &mm->rss_stat.count[member]);
+#ifdef CONFIG_NUMA
+	if (node != NUMA_NO_NODE)
+		numa_count = atomic_long_add_return(value, &mm->rss_stat.numa_count[node]);
+#endif
+	mm_trace_rss_stat(mm, member, member_count, node, numa_count, value);
 }
 
 static inline void inc_mm_counter(struct mm_struct *mm, int member, int node)
 {
-	long count = atomic_long_inc_return(&mm->rss_stat.count[member]);
+	long member_count = 0, numa_count = 0;
 
-	mm_trace_rss_stat(mm, member, count, NUMA_NO_NODE, 0, 1);
+	if (member != MM_NO_TYPE)
+		member_count = atomic_long_inc_return(&mm->rss_stat.count[member]);
+#ifdef CONFIG_NUMA
+	if (node != NUMA_NO_NODE)
+		numa_count = atomic_long_inc_return(&mm->rss_stat.numa_count[node]);
+#endif
+	mm_trace_rss_stat(mm, member, member_count, node, numa_count, 1);
 }
 
 static inline void dec_mm_counter(struct mm_struct *mm, int member, int node)
 {
-	long count = atomic_long_dec_return(&mm->rss_stat.count[member]);
+	long member_count = 0, numa_count = 0;
 
-	mm_trace_rss_stat(mm, member, count, NUMA_NO_NODE, 0, -1);
+	if (member != MM_NO_TYPE)
+		member_count = atomic_long_dec_return(&mm->rss_stat.count[member]);
+#ifdef CONFIG_NUMA
+	if (node != NUMA_NO_NODE)
+		numa_count = atomic_long_dec_return(&mm->rss_stat.numa_count[node]);
+#endif
+	mm_trace_rss_stat(mm, member, member_count, node, numa_count, -1);
 }
 
 /* Optimized variant when page is already known not to be PageAnon */
diff --git a/mm/memory.c b/mm/memory.c
index 2d3040a190f6..f7b67da772b2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -188,6 +188,14 @@ void sync_mm_rss(struct mm_struct *mm)
 			current->rss_stat.count[i] = 0;
 		}
 	}
+#ifdef CONFIG_NUMA
+	for_each_node(i) {
+		if (current->rss_stat.numa_count[i]) {
+			add_mm_counter(mm, MM_NO_TYPE, current->rss_stat.numa_count[i], i);
+			current->rss_stat.numa_count[i] = 0;
+		}
+	}
+#endif
 	current->rss_stat.events = 0;
 }
 
@@ -195,9 +203,12 @@ static void add_mm_counter_fast(struct mm_struct *mm, int member, int val, int n
 {
 	struct task_struct *task = current;
 
-	if (likely(task->mm == mm))
+	if (likely(task->mm == mm)) {
 		task->rss_stat.count[member] += val;
-	else
+#ifdef CONFIG_NUMA
+		task->rss_stat.numa_count[node] += val;
+#endif
+	} else
 		add_mm_counter(mm, member, val, node);
 }
 #define inc_mm_counter_fast(mm, member, node) add_mm_counter_fast(mm, member, 1, node)
@@ -508,6 +519,11 @@ static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss, int *numa_rss)
 	for (i = 0; i < NR_MM_COUNTERS; i++)
 		if (rss[i])
 			add_mm_counter(mm, i, rss[i], NUMA_NO_NODE);
+#ifdef CONFIG_NUMA
+	for_each_node(i)
+		if (numa_rss[i] != 0)
+			add_mm_counter(mm, MM_NO_TYPE, numa_rss[i], i);
+#endif
 }
 
 /*
-- 
2.20.1

