Received-SPF: pass (google.com: domain of linux-kernel+bounces-142160-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
From: Barry Song <21cnbao@gmail.com>
To: akpm@linux-foundation.org,
	linux-mm@kvack.org
Cc: cerasuolodomenico@gmail.com,
	chrisl@kernel.org,
	david@redhat.com,
	kasong@tencent.com,
	linux-kernel@vger.kernel.org,
	peterx@redhat.com,
	ryan.roberts@arm.com,
	surenb@google.com,
	v-songbaohua@oppo.com,
	willy@infradead.org,
	yosryahmed@google.com,
	yuzhao@google.com,
	corbet@lwn.net
Subject: [PATCH v5 1/4] mm: add per-order mTHP anon_fault_alloc and anon_fault_fallback counters
Date: Fri, 12 Apr 2024 19:37:37 +1200
Message-Id: <20240412073740.294272-2-21cnbao@gmail.com>
In-Reply-To: <20240412073740.294272-1-21cnbao@gmail.com>
References: <20240412073740.294272-1-21cnbao@gmail.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

From: Barry Song <v-songbaohua@oppo.com>

Profiling a system blindly with mTHP has become challenging due to the
lack of visibility into its operations.  Presenting the success rate of
mTHP allocations appears to be pressing need.

Recently, I've been experiencing significant difficulty debugging
performance improvements and regressions without these figures.  It's
crucial for us to understand the true effectiveness of mTHP in real-world
scenarios, especially in systems with fragmented memory.

This patch establishes the framework for per-order mTHP
counters. It begins by introducing the anon_fault_alloc and
anon_fault_fallback counters. Additionally, to maintain consistency
with thp_fault_fallback_charge in /proc/vmstat, this patch also tracks
anon_fault_fallback_charge when mem_cgroup_charge fails for mTHP.
Incorporating additional counters should now be straightforward as well.

Signed-off-by: Barry Song <v-songbaohua@oppo.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Cc: Kairui Song <kasong@tencent.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Cc: Yu Zhao <yuzhao@google.com>
---
 include/linux/huge_mm.h | 51 ++++++++++++++++++++++++++++++++++
 mm/huge_memory.c        | 61 +++++++++++++++++++++++++++++++++++++++++
 mm/memory.c             |  3 ++
 mm/page_alloc.c         |  4 +++
 4 files changed, 119 insertions(+)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index e896ca4760f6..c5beb54b97cb 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -264,6 +264,57 @@ unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma,
 					  enforce_sysfs, orders);
 }
 
+enum mthp_stat_item {
+	MTHP_STAT_ANON_FAULT_ALLOC,
+	MTHP_STAT_ANON_FAULT_FALLBACK,
+	MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE,
+	__MTHP_STAT_COUNT
+};
+
+struct mthp_stat {
+	unsigned long stats[0][__MTHP_STAT_COUNT];
+};
+
+extern struct mthp_stat __percpu *mthp_stats;
+
+static inline void count_mthp_stat(int order, enum mthp_stat_item item)
+{
+	if (order <= 0 || order > PMD_ORDER || !mthp_stats)
+		return;
+
+	this_cpu_inc(mthp_stats->stats[order][item]);
+}
+
+static inline void count_mthp_stats(int order, enum mthp_stat_item item, long delta)
+{
+	if (order <= 0 || order > PMD_ORDER || !mthp_stats)
+		return;
+
+	this_cpu_add(mthp_stats->stats[order][item], delta);
+}
+
+/*
+ * Fold the foreign cpu mthp stats into our own.
+ *
+ * This is adding to the stats on one processor
+ * but keeps the global counts constant.
+ */
+static inline void mthp_stats_fold_cpu(int cpu)
+{
+	struct mthp_stat *fold_stat;
+	int i, j;
+
+	if (!mthp_stats)
+		return;
+	fold_stat = per_cpu_ptr(mthp_stats, cpu);
+	for (i = 1; i <= PMD_ORDER; i++) {
+		for (j = 0; j < __MTHP_STAT_COUNT; j++) {
+			count_mthp_stats(i, j, fold_stat->stats[i][j]);
+			fold_stat->stats[i][j] = 0;
+		}
+	}
+}
+
 #define transparent_hugepage_use_zero_page()				\
 	(transparent_hugepage_flags &					\
 	 (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG))
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index dc30139590e6..21c4ac74b484 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -526,6 +526,50 @@ static const struct kobj_type thpsize_ktype = {
 	.sysfs_ops = &kobj_sysfs_ops,
 };
 
+struct mthp_stat __percpu *mthp_stats;
+
+static unsigned long sum_mthp_stat(int order, enum mthp_stat_item item)
+{
+	unsigned long sum = 0;
+	int cpu;
+
+	cpus_read_lock();
+	for_each_online_cpu(cpu) {
+		struct mthp_stat *this = per_cpu_ptr(mthp_stats, cpu);
+
+		sum += this->stats[order][item];
+	}
+	cpus_read_unlock();
+
+	return sum;
+}
+
+#define DEFINE_MTHP_STAT_ATTR(_name, _index)					\
+static ssize_t _name##_show(struct kobject *kobj,			\
+			struct kobj_attribute *attr, char *buf)		\
+{									\
+	int order = to_thpsize(kobj)->order;				\
+									\
+	return sysfs_emit(buf, "%lu\n", sum_mthp_stat(order, _index));	\
+}									\
+static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
+
+DEFINE_MTHP_STAT_ATTR(anon_fault_alloc, MTHP_STAT_ANON_FAULT_ALLOC);
+DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK);
+DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
+
+static struct attribute *stats_attrs[] = {
+	&anon_fault_alloc_attr.attr,
+	&anon_fault_fallback_attr.attr,
+	&anon_fault_fallback_charge_attr.attr,
+	NULL,
+};
+
+static struct attribute_group stats_attr_group = {
+	.name = "stats",
+	.attrs = stats_attrs,
+};
+
 static struct thpsize *thpsize_create(int order, struct kobject *parent)
 {
 	unsigned long size = (PAGE_SIZE << order) / SZ_1K;
@@ -549,6 +593,12 @@ static struct thpsize *thpsize_create(int order, struct kobject *parent)
 		return ERR_PTR(ret);
 	}
 
+	ret = sysfs_create_group(&thpsize->kobj, &stats_attr_group);
+	if (ret) {
+		kobject_put(&thpsize->kobj);
+		return ERR_PTR(ret);
+	}
+
 	thpsize->order = order;
 	return thpsize;
 }
@@ -691,6 +741,11 @@ static int __init hugepage_init(void)
 	 */
 	MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER < 2);
 
+	mthp_stats = __alloc_percpu((PMD_ORDER + 1) * sizeof(mthp_stats->stats[0]),
+			sizeof(unsigned long));
+	if (!mthp_stats)
+		return -ENOMEM;
+
 	err = hugepage_init_sysfs(&hugepage_kobj);
 	if (err)
 		goto err_sysfs;
@@ -725,6 +780,8 @@ static int __init hugepage_init(void)
 err_slab:
 	hugepage_exit_sysfs(hugepage_kobj);
 err_sysfs:
+	free_percpu(mthp_stats);
+	mthp_stats = NULL;
 	return err;
 }
 subsys_initcall(hugepage_init);
@@ -880,6 +937,8 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 		folio_put(folio);
 		count_vm_event(THP_FAULT_FALLBACK);
 		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
+		count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK);
+		count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
 		return VM_FAULT_FALLBACK;
 	}
 	folio_throttle_swaprate(folio, gfp);
@@ -929,6 +988,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 		mm_inc_nr_ptes(vma->vm_mm);
 		spin_unlock(vmf->ptl);
 		count_vm_event(THP_FAULT_ALLOC);
+		count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC);
 		count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC);
 	}
 
@@ -1050,6 +1110,7 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 	folio = vma_alloc_folio(gfp, HPAGE_PMD_ORDER, vma, haddr, true);
 	if (unlikely(!folio)) {
 		count_vm_event(THP_FAULT_FALLBACK);
+		count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
 	}
 	return __do_huge_pmd_anonymous_page(vmf, &folio->page, gfp);
diff --git a/mm/memory.c b/mm/memory.c
index 649a547fe8e3..06048af7cf9a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4368,6 +4368,7 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf)
 		folio = vma_alloc_folio(gfp, order, vma, addr, true);
 		if (folio) {
 			if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) {
+				count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
 				folio_put(folio);
 				goto next;
 			}
@@ -4376,6 +4377,7 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf)
 			return folio;
 		}
 next:
+		count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK);
 		order = next_order(&orders, order);
 	}
 
@@ -4485,6 +4487,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 
 	folio_ref_add(folio, nr_pages - 1);
 	add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages);
+	count_mthp_stat(folio_order(folio), MTHP_STAT_ANON_FAULT_ALLOC);
 	folio_add_new_anon_rmap(folio, vma, addr);
 	folio_add_lru_vma(folio, vma);
 setpte:
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b51becf03d1e..3135b5ca2457 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5840,6 +5840,10 @@ static int page_alloc_cpu_dead(unsigned int cpu)
 	 */
 	vm_events_fold_cpu(cpu);
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	mthp_stats_fold_cpu(cpu);
+#endif
+
 	/*
 	 * Zero the differential counters of the dead processor
 	 * so that the vm statistics are consistent.
-- 
2.34.1