mm: convert mm's rss stats into percpu_counter

Currently mm_struct maintains rss_stats which are updated on page fault
and the unmapping codepaths.  For page fault codepath the updates are
cached per thread with the batch of TASK_RSS_EVENTS_THRESH which is 64. 
The reason for caching is performance for multithreaded applications
otherwise the rss_stats updates may become hotspot for such applications.

However this optimization comes with the cost of error margin in the rss
stats.  The rss_stats for applications with large number of threads can be
very skewed.  At worst the error margin is (nr_threads * 64) and we have a
lot of applications with 100s of threads, so the error margin can be very
high.  Internally we had to reduce TASK_RSS_EVENTS_THRESH to 32.

Recently we started seeing the unbounded errors for rss_stats for specific
applications which use TCP rx0cp.  It seems like vm_insert_pages()
codepath does not sync rss_stats at all.

This patch converts the rss_stats into percpu_counter to convert the error
margin from (nr_threads * 64) to approximately (nr_cpus ^ 2).  However
this conversion enable us to get the accurate stats for situations where
accuracy is more important than the cpu cost.

This patch does not make such tradeoffs - we can just use
percpu_counter_add_local() for the updates and percpu_counter_sum() (or
percpu_counter_sync() + percpu_counter_read) for the readers.  At the
moment the readers are either procfs interface, oom_killer and memory
reclaim which I think are not performance critical and should be ok with
slow read.  However I think we can make that change in a separate patch.

Link: https://lkml.kernel.org/r/20221024052841.3291983-1-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 11 insertions, 62 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 7826143ec9cd..e0555ddd71b5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -162,58 +162,11 @@ static int __init init_zero_pfn(void)
 }
 early_initcall(init_zero_pfn);
 
-void mm_trace_rss_stat(struct mm_struct *mm, int member, long count)
+void mm_trace_rss_stat(struct mm_struct *mm, int member)
 {
-	trace_rss_stat(mm, member, count);
+	trace_rss_stat(mm, member);
 }
 
-#if defined(SPLIT_RSS_COUNTING)
-
-void sync_mm_rss(struct mm_struct *mm)
-{
-	int i;
-
-	for (i = 0; i < NR_MM_COUNTERS; i++) {
-		if (current->rss_stat.count[i]) {
-			add_mm_counter(mm, i, current->rss_stat.count[i]);
-			current->rss_stat.count[i] = 0;
-		}
-	}
-	current->rss_stat.events = 0;
-}
-
-static void add_mm_counter_fast(struct mm_struct *mm, int member, int val)
-{
-	struct task_struct *task = current;
-
-	if (likely(task->mm == mm))
-		task->rss_stat.count[member] += val;
-	else
-		add_mm_counter(mm, member, val);
-}
-#define inc_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, 1)
-#define dec_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, -1)
-
-/* sync counter once per 64 page faults */
-#define TASK_RSS_EVENTS_THRESH	(64)
-static void check_sync_rss_stat(struct task_struct *task)
-{
-	if (unlikely(task != current))
-		return;
-	if (unlikely(task->rss_stat.events++ > TASK_RSS_EVENTS_THRESH))
-		sync_mm_rss(task->mm);
-}
-#else /* SPLIT_RSS_COUNTING */
-
-#define inc_mm_counter_fast(mm, member) inc_mm_counter(mm, member)
-#define dec_mm_counter_fast(mm, member) dec_mm_counter(mm, member)
-
-static void check_sync_rss_stat(struct task_struct *task)
-{
-}
-
-#endif /* SPLIT_RSS_COUNTING */
-
 /*
  * Note: this doesn't free the actual pages themselves. That
  * has been handled earlier when unmapping all the memory regions.
@@ -1857,7 +1810,7 @@ static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte,
 		return -EBUSY;
 	/* Ok, finally just insert the thing.. */
 	get_page(page);
-	inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
+	inc_mm_counter(vma->vm_mm, mm_counter_file(page));
 	page_add_file_rmap(page, vma, false);
 	set_pte_at(vma->vm_mm, addr, pte, mk_pte(page, prot));
 	return 0;
@@ -3153,12 +3106,11 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 	if (likely(pte_same(*vmf->pte, vmf->orig_pte))) {
 		if (old_page) {
 			if (!PageAnon(old_page)) {
-				dec_mm_counter_fast(mm,
-						mm_counter_file(old_page));
-				inc_mm_counter_fast(mm, MM_ANONPAGES);
+				dec_mm_counter(mm, mm_counter_file(old_page));
+				inc_mm_counter(mm, MM_ANONPAGES);
 			}
 		} else {
-			inc_mm_counter_fast(mm, MM_ANONPAGES);
+			inc_mm_counter(mm, MM_ANONPAGES);
 		}
 		flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
 		entry = mk_pte(new_page, vma->vm_page_prot);
@@ -3965,8 +3917,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	if (should_try_to_free_swap(folio, vma, vmf->flags))
 		folio_free_swap(folio);
 
-	inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
-	dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS);
+	inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
+	dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
 	pte = mk_pte(page, vma->vm_page_prot);
 
 	/*
@@ -4146,7 +4098,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 		return handle_userfault(vmf, VM_UFFD_MISSING);
 	}
 
-	inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
+	inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
 	page_add_new_anon_rmap(page, vma, vmf->address);
 	lru_cache_add_inactive_or_unevictable(page, vma);
 setpte:
@@ -4336,11 +4288,11 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr)
 		entry = pte_mkuffd_wp(pte_wrprotect(entry));
 	/* copy-on-write page */
 	if (write && !(vma->vm_flags & VM_SHARED)) {
-		inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
+		inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
 		page_add_new_anon_rmap(page, vma, addr);
 		lru_cache_add_inactive_or_unevictable(page, vma);
 	} else {
-		inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
+		inc_mm_counter(vma->vm_mm, mm_counter_file(page));
 		page_add_file_rmap(page, vma, false);
 	}
 	set_pte_at(vma->vm_mm, addr, vmf->pte, entry);
@@ -5192,9 +5144,6 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 	count_vm_event(PGFAULT);
 	count_memcg_event_mm(vma->vm_mm, PGFAULT);
 
-	/* do counter updates before entering really critical section. */
-	check_sync_rss_stat(current);
-
 	if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE,
 					    flags & FAULT_FLAG_INSTRUCTION,
 					    flags & FAULT_FLAG_REMOTE))