diff mbox series

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

Message ID 20220512044634.63586-5-ligang.bdlg@bytedance.com (mailing list archive)
State New
Headers show
Series mm, oom: Introduce per numa node oom for CONSTRAINT_MEMORY_POLICY | expand

Commit Message

Gang Li May 12, 2022, 4:46 a.m. UTC 
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(-)

Comments

kernel test robot May 17, 2022, 2:28 a.m. UTC | #1 
Greeting,

FYI, we noticed the following commit (built with gcc-11):

commit: c9dc81ef10c33656280058c29dfaa1d549d1daee ("[PATCH 4/5 v1] mm: enable per numa node rss_stat count")
url: https://github.com/intel-lab-lkp/linux/commits/Gang-Li/mm-oom-Introduce-per-numa-node-oom-for-CONSTRAINT_MEMORY_POLICY/20220512-124948
base: https://git.kernel.org/cgit/linux/kernel/git/s390/linux.git features
patch link: https://lore.kernel.org/lkml/20220512044634.63586-5-ligang.bdlg@bytedance.com

in testcase: will-it-scale
version: will-it-scale-x86_64-a34a85c-1_20220502
with following parameters:

	nr_task: 100%
	mode: process
	test: page_fault1
	cpufreq_governor: performance
	ucode: 0x42e

test-description: Will It Scale takes a testcase and runs it from 1 through to n parallel copies to see if the testcase will scale. It builds both a process and threads based test in order to see any differences between the two.
test-url: https://github.com/antonblanchard/will-it-scale


on test machine: 48 threads 2 sockets Intel(R) Xeon(R) CPU E5-2697 v2 @ 2.70GHz with 112G memory

caused below changes (please refer to attached dmesg/kmsg for entire log/backtrace):



If you fix the issue, kindly add following tag
Reported-by: kernel test robot <oliver.sang@intel.com>



[  160.153480][ T3850] BUG: Bad rss-counter state mm:0000000041b404d2 node:0 val:512
[  160.163467][ T3850] BUG: Bad rss-counter state mm:0000000041b404d2 node:1 val:-512



To reproduce:

        git clone https://github.com/intel/lkp-tests.git
        cd lkp-tests
        sudo bin/lkp install job.yaml           # job file is attached in this email
        bin/lkp split-job --compatible job.yaml # generate the yaml file for lkp run
        sudo bin/lkp run generated-yaml-file

        # if come across any failure that blocks the test,
        # please remove ~/.lkp and /lkp dir to run from a clean state.
diff mbox series

Patch

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
 }
 
 /*