mm-commits.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Andrew Morton <akpm@linux-foundation.org>
To: akpm@linux-foundation.org, bsingharora@gmail.com, guro@fb.com,
	hannes@cmpxchg.org, linux-mm@kvack.org, mhocko@suse.com,
	mkoutny@suse.com, mm-commits@vger.kernel.org,
	shakeelb@google.com, tj@kernel.org,
	torvalds@linux-foundation.org
Subject: [patch 064/178] mm: memcontrol: switch to rstat
Date: Thu, 29 Apr 2021 22:56:26 -0700	[thread overview]
Message-ID: <20210430055626.WZK5r2afb%akpm@linux-foundation.org> (raw)
In-Reply-To: <20210429225251.02b6386d21b69255b4f6c163@linux-foundation.org>

From: Johannes Weiner <hannes@cmpxchg.org>
Subject: mm: memcontrol: switch to rstat

Replace the memory controller's custom hierarchical stats code with the
generic rstat infrastructure provided by the cgroup core.

The current implementation does batched upward propagation from the write
side (i.e.  as stats change).  The per-cpu batches introduce an error,
which is multiplied by the number of subgroups in a tree.  In systems with
many CPUs and sizable cgroup trees, the error can be large enough to
confuse users (e.g.  32 batch pages * 32 CPUs * 32 subgroups results in an
error of up to 128M per stat item).  This can entirely swallow allocation
bursts inside a workload that the user is expecting to see reflected in
the statistics.

In the past, we've done read-side aggregation, where a memory.stat read
would have to walk the entire subtree and add up per-cpu counts.  This
became problematic with lazily-freed cgroups: we could have large subtrees
where most cgroups were entirely idle.  Hence the switch to change-driven
upward propagation.  Unfortunately, it needed to trade accuracy for speed
due to the write side being so hot.

Rstat combines the best of both worlds: from the write side, it cheaply
maintains a queue of cgroups that have pending changes, so that the read
side can do selective tree aggregation.  This way the reported stats will
always be precise and recent as can be, while the aggregation can skip
over potentially large numbers of idle cgroups.

The way rstat works is that it implements a tree for tracking cgroups with
pending local changes, as well as a flush function that walks the tree
upwards.  The controller then drives this by 1) telling rstat when a local
cgroup stat changes (e.g.  mod_memcg_state) and 2) when a flush is
required to get uptodate hierarchy stats for a given subtree (e.g.  when
memory.stat is read).  The controller also provides a flush callback that
is called during the rstat flush walk for each cgroup and aggregates its
local per-cpu counters and propagates them upwards.

This adds a second vmstats to struct mem_cgroup (MEMCG_NR_STAT +
NR_VM_EVENT_ITEMS) to track pending subtree deltas during upward
aggregation.  It removes 3 words from the per-cpu data.  It eliminates
memcg_exact_page_state(), since memcg_page_state() is now exact.

[akpm@linux-foundation.org: merge fix]
[hannes@cmpxchg.org: fix a sleep in atomic section problem]
  Link: https://lkml.kernel.org/r/20210315234100.64307-1-hannes@cmpxchg.org
Link: https://lkml.kernel.org/r/20210209163304.77088-7-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Roman Gushchin <guro@fb.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Michal Koutný <mkoutny@suse.com>
Acked-by: Balbir Singh <bsingharora@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/linux/memcontrol.h |   67 ++++++----
 mm/memcontrol.c            |  218 +++++++++++++----------------------
 2 files changed, 127 insertions(+), 158 deletions(-)

--- a/include/linux/memcontrol.h~mm-memcontrol-switch-to-rstat
+++ a/include/linux/memcontrol.h
@@ -76,10 +76,27 @@ enum mem_cgroup_events_target {
 };
 
 struct memcg_vmstats_percpu {
-	long stat[MEMCG_NR_STAT];
-	unsigned long events[NR_VM_EVENT_ITEMS];
-	unsigned long nr_page_events;
-	unsigned long targets[MEM_CGROUP_NTARGETS];
+	/* Local (CPU and cgroup) page state & events */
+	long			state[MEMCG_NR_STAT];
+	unsigned long		events[NR_VM_EVENT_ITEMS];
+
+	/* Delta calculation for lockless upward propagation */
+	long			state_prev[MEMCG_NR_STAT];
+	unsigned long		events_prev[NR_VM_EVENT_ITEMS];
+
+	/* Cgroup1: threshold notifications & softlimit tree updates */
+	unsigned long		nr_page_events;
+	unsigned long		targets[MEM_CGROUP_NTARGETS];
+};
+
+struct memcg_vmstats {
+	/* Aggregated (CPU and subtree) page state & events */
+	long			state[MEMCG_NR_STAT];
+	unsigned long		events[NR_VM_EVENT_ITEMS];
+
+	/* Pending child counts during tree propagation */
+	long			state_pending[MEMCG_NR_STAT];
+	unsigned long		events_pending[NR_VM_EVENT_ITEMS];
 };
 
 struct mem_cgroup_reclaim_iter {
@@ -287,8 +304,8 @@ struct mem_cgroup {
 
 	MEMCG_PADDING(_pad1_);
 
-	atomic_long_t		vmstats[MEMCG_NR_STAT];
-	atomic_long_t		vmevents[NR_VM_EVENT_ITEMS];
+	/* memory.stat */
+	struct memcg_vmstats	vmstats;
 
 	/* memory.events */
 	atomic_long_t		memory_events[MEMCG_NR_MEMORY_EVENTS];
@@ -315,10 +332,6 @@ struct mem_cgroup {
 	atomic_t		moving_account;
 	struct task_struct	*move_lock_task;
 
-	/* Legacy local VM stats and events */
-	struct memcg_vmstats_percpu __percpu *vmstats_local;
-
-	/* Subtree VM stats and events (batched updates) */
 	struct memcg_vmstats_percpu __percpu *vmstats_percpu;
 
 #ifdef CONFIG_CGROUP_WRITEBACK
@@ -939,10 +952,6 @@ static inline void mod_memcg_lruvec_stat
 	local_irq_restore(flags);
 }
 
-unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
-						gfp_t gfp_mask,
-						unsigned long *total_scanned);
-
 void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
 			  unsigned long count);
 
@@ -1023,6 +1032,10 @@ static inline void memcg_memory_event_mm
 
 void split_page_memcg(struct page *head, unsigned int nr);
 
+unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
+						gfp_t gfp_mask,
+						unsigned long *total_scanned);
+
 #else /* CONFIG_MEMCG */
 
 #define MEM_CGROUP_ID_SHIFT	0
@@ -1131,6 +1144,10 @@ static inline bool lruvec_holds_page_lru
 	return lruvec == &pgdat->__lruvec;
 }
 
+static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
+{
+}
+
 static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 {
 	return NULL;
@@ -1334,18 +1351,6 @@ static inline void mod_lruvec_kmem_state
 	mod_node_page_state(page_pgdat(page), idx, val);
 }
 
-static inline
-unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
-					    gfp_t gfp_mask,
-					    unsigned long *total_scanned)
-{
-	return 0;
-}
-
-static inline void split_page_memcg(struct page *head, unsigned int nr)
-{
-}
-
 static inline void count_memcg_events(struct mem_cgroup *memcg,
 				      enum vm_event_item idx,
 				      unsigned long count)
@@ -1368,9 +1373,17 @@ void count_memcg_event_mm(struct mm_stru
 {
 }
 
-static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
+static inline void split_page_memcg(struct page *head, unsigned int nr)
 {
 }
+
+static inline
+unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
+					    gfp_t gfp_mask,
+					    unsigned long *total_scanned)
+{
+	return 0;
+}
 #endif /* CONFIG_MEMCG */
 
 static inline void __inc_lruvec_kmem_state(void *p, enum node_stat_item idx)
--- a/mm/memcontrol.c~mm-memcontrol-switch-to-rstat
+++ a/mm/memcontrol.c
@@ -765,37 +765,17 @@ mem_cgroup_largest_soft_limit_node(struc
  */
 void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val)
 {
-	long x, threshold = MEMCG_CHARGE_BATCH;
-
 	if (mem_cgroup_disabled())
 		return;
 
-	if (memcg_stat_item_in_bytes(idx))
-		threshold <<= PAGE_SHIFT;
-
-	x = val + __this_cpu_read(memcg->vmstats_percpu->stat[idx]);
-	if (unlikely(abs(x) > threshold)) {
-		struct mem_cgroup *mi;
-
-		/*
-		 * Batch local counters to keep them in sync with
-		 * the hierarchical ones.
-		 */
-		__this_cpu_add(memcg->vmstats_local->stat[idx], x);
-		for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
-			atomic_long_add(x, &mi->vmstats[idx]);
-		x = 0;
-	}
-	__this_cpu_write(memcg->vmstats_percpu->stat[idx], x);
+	__this_cpu_add(memcg->vmstats_percpu->state[idx], val);
+	cgroup_rstat_updated(memcg->css.cgroup, smp_processor_id());
 }
 
-/*
- * idx can be of type enum memcg_stat_item or node_stat_item.
- * Keep in sync with memcg_exact_page_state().
- */
+/* idx can be of type enum memcg_stat_item or node_stat_item. */
 static unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
 {
-	long x = atomic_long_read(&memcg->vmstats[idx]);
+	long x = READ_ONCE(memcg->vmstats.state[idx]);
 #ifdef CONFIG_SMP
 	if (x < 0)
 		x = 0;
@@ -803,17 +783,14 @@ static unsigned long memcg_page_state(st
 	return x;
 }
 
-/*
- * idx can be of type enum memcg_stat_item or node_stat_item.
- * Keep in sync with memcg_exact_page_state().
- */
+/* idx can be of type enum memcg_stat_item or node_stat_item. */
 static unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx)
 {
 	long x = 0;
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		x += per_cpu(memcg->vmstats_local->stat[idx], cpu);
+		x += per_cpu(memcg->vmstats_percpu->state[idx], cpu);
 #ifdef CONFIG_SMP
 	if (x < 0)
 		x = 0;
@@ -936,30 +913,16 @@ void __mod_lruvec_kmem_state(void *p, en
 void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
 			  unsigned long count)
 {
-	unsigned long x;
-
 	if (mem_cgroup_disabled())
 		return;
 
-	x = count + __this_cpu_read(memcg->vmstats_percpu->events[idx]);
-	if (unlikely(x > MEMCG_CHARGE_BATCH)) {
-		struct mem_cgroup *mi;
-
-		/*
-		 * Batch local counters to keep them in sync with
-		 * the hierarchical ones.
-		 */
-		__this_cpu_add(memcg->vmstats_local->events[idx], x);
-		for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
-			atomic_long_add(x, &mi->vmevents[idx]);
-		x = 0;
-	}
-	__this_cpu_write(memcg->vmstats_percpu->events[idx], x);
+	__this_cpu_add(memcg->vmstats_percpu->events[idx], count);
+	cgroup_rstat_updated(memcg->css.cgroup, smp_processor_id());
 }
 
 static unsigned long memcg_events(struct mem_cgroup *memcg, int event)
 {
-	return atomic_long_read(&memcg->vmevents[event]);
+	return READ_ONCE(memcg->vmstats.events[event]);
 }
 
 static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event)
@@ -968,7 +931,7 @@ static unsigned long memcg_events_local(
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		x += per_cpu(memcg->vmstats_local->events[event], cpu);
+		x += per_cpu(memcg->vmstats_percpu->events[event], cpu);
 	return x;
 }
 
@@ -1604,6 +1567,7 @@ static char *memory_stat_format(struct m
 	 *
 	 * Current memory state:
 	 */
+	cgroup_rstat_flush(memcg->css.cgroup);
 
 	for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
 		u64 size;
@@ -2409,22 +2373,11 @@ static int memcg_hotplug_cpu_dead(unsign
 	drain_stock(stock);
 
 	for_each_mem_cgroup(memcg) {
-		struct memcg_vmstats_percpu *statc;
 		int i;
 
-		statc = per_cpu_ptr(memcg->vmstats_percpu, cpu);
-
-		for (i = 0; i < MEMCG_NR_STAT; i++) {
+		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
 			int nid;
 
-			if (statc->stat[i]) {
-				mod_memcg_state(memcg, i, statc->stat[i]);
-				statc->stat[i] = 0;
-			}
-
-			if (i >= NR_VM_NODE_STAT_ITEMS)
-				continue;
-
 			for_each_node(nid) {
 				struct batched_lruvec_stat *lstatc;
 				struct mem_cgroup_per_node *pn;
@@ -2443,13 +2396,6 @@ static int memcg_hotplug_cpu_dead(unsign
 				}
 			}
 		}
-
-		for (i = 0; i < NR_VM_EVENT_ITEMS; i++) {
-			if (statc->events[i]) {
-				count_memcg_events(memcg, i, statc->events[i]);
-				statc->events[i] = 0;
-			}
-		}
 	}
 
 	return 0;
@@ -3572,6 +3518,7 @@ static unsigned long mem_cgroup_usage(st
 	unsigned long val;
 
 	if (mem_cgroup_is_root(memcg)) {
+		cgroup_rstat_flush(memcg->css.cgroup);
 		val = memcg_page_state(memcg, NR_FILE_PAGES) +
 			memcg_page_state(memcg, NR_ANON_MAPPED);
 		if (swap)
@@ -3636,26 +3583,15 @@ static u64 mem_cgroup_read_u64(struct cg
 	}
 }
 
-static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg)
+static void memcg_flush_lruvec_page_state(struct mem_cgroup *memcg)
 {
-	unsigned long stat[MEMCG_NR_STAT] = {0};
-	struct mem_cgroup *mi;
-	int node, cpu, i;
-
-	for_each_online_cpu(cpu)
-		for (i = 0; i < MEMCG_NR_STAT; i++)
-			stat[i] += per_cpu(memcg->vmstats_percpu->stat[i], cpu);
-
-	for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
-		for (i = 0; i < MEMCG_NR_STAT; i++)
-			atomic_long_add(stat[i], &mi->vmstats[i]);
+	int node;
 
 	for_each_node(node) {
 		struct mem_cgroup_per_node *pn = memcg->nodeinfo[node];
+		unsigned long stat[NR_VM_NODE_STAT_ITEMS] = { 0 };
 		struct mem_cgroup_per_node *pi;
-
-		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
-			stat[i] = 0;
+		int cpu, i;
 
 		for_each_online_cpu(cpu)
 			for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
@@ -3668,25 +3604,6 @@ static void memcg_flush_percpu_vmstats(s
 	}
 }
 
-static void memcg_flush_percpu_vmevents(struct mem_cgroup *memcg)
-{
-	unsigned long events[NR_VM_EVENT_ITEMS];
-	struct mem_cgroup *mi;
-	int cpu, i;
-
-	for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
-		events[i] = 0;
-
-	for_each_online_cpu(cpu)
-		for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
-			events[i] += per_cpu(memcg->vmstats_percpu->events[i],
-					     cpu);
-
-	for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
-		for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
-			atomic_long_add(events[i], &mi->vmevents[i]);
-}
-
 #ifdef CONFIG_MEMCG_KMEM
 static int memcg_online_kmem(struct mem_cgroup *memcg)
 {
@@ -4003,6 +3920,8 @@ static int memcg_numa_stat_show(struct s
 	int nid;
 	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 
+	cgroup_rstat_flush(memcg->css.cgroup);
+
 	for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) {
 		seq_printf(m, "%s=%lu", stat->name,
 			   mem_cgroup_nr_lru_pages(memcg, stat->lru_mask,
@@ -4073,6 +3992,8 @@ static int memcg_stat_show(struct seq_fi
 
 	BUILD_BUG_ON(ARRAY_SIZE(memcg1_stat_names) != ARRAY_SIZE(memcg1_stats));
 
+	cgroup_rstat_flush(memcg->css.cgroup);
+
 	for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
 		unsigned long nr;
 
@@ -4549,22 +4470,6 @@ struct wb_domain *mem_cgroup_wb_domain(s
 	return &memcg->cgwb_domain;
 }
 
-/*
- * idx can be of type enum memcg_stat_item or node_stat_item.
- * Keep in sync with memcg_exact_page().
- */
-static unsigned long memcg_exact_page_state(struct mem_cgroup *memcg, int idx)
-{
-	long x = atomic_long_read(&memcg->vmstats[idx]);
-	int cpu;
-
-	for_each_online_cpu(cpu)
-		x += per_cpu_ptr(memcg->vmstats_percpu, cpu)->stat[idx];
-	if (x < 0)
-		x = 0;
-	return x;
-}
-
 /**
  * mem_cgroup_wb_stats - retrieve writeback related stats from its memcg
  * @wb: bdi_writeback in question
@@ -4590,13 +4495,14 @@ void mem_cgroup_wb_stats(struct bdi_writ
 	struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
 	struct mem_cgroup *parent;
 
-	*pdirty = memcg_exact_page_state(memcg, NR_FILE_DIRTY);
+	cgroup_rstat_flush_irqsafe(memcg->css.cgroup);
 
-	*pwriteback = memcg_exact_page_state(memcg, NR_WRITEBACK);
-	*pfilepages = memcg_exact_page_state(memcg, NR_INACTIVE_FILE) +
-			memcg_exact_page_state(memcg, NR_ACTIVE_FILE);
-	*pheadroom = PAGE_COUNTER_MAX;
+	*pdirty = memcg_page_state(memcg, NR_FILE_DIRTY);
+	*pwriteback = memcg_page_state(memcg, NR_WRITEBACK);
+	*pfilepages = memcg_page_state(memcg, NR_INACTIVE_FILE) +
+			memcg_page_state(memcg, NR_ACTIVE_FILE);
 
+	*pheadroom = PAGE_COUNTER_MAX;
 	while ((parent = parent_mem_cgroup(memcg))) {
 		unsigned long ceiling = min(READ_ONCE(memcg->memory.max),
 					    READ_ONCE(memcg->memory.high));
@@ -5228,7 +5134,6 @@ static void __mem_cgroup_free(struct mem
 	for_each_node(node)
 		free_mem_cgroup_per_node_info(memcg, node);
 	free_percpu(memcg->vmstats_percpu);
-	free_percpu(memcg->vmstats_local);
 	kfree(memcg);
 }
 
@@ -5236,11 +5141,10 @@ static void mem_cgroup_free(struct mem_c
 {
 	memcg_wb_domain_exit(memcg);
 	/*
-	 * Flush percpu vmstats and vmevents to guarantee the value correctness
-	 * on parent's and all ancestor levels.
+	 * Flush percpu lruvec stats to guarantee the value
+	 * correctness on parent's and all ancestor levels.
 	 */
-	memcg_flush_percpu_vmstats(memcg);
-	memcg_flush_percpu_vmevents(memcg);
+	memcg_flush_lruvec_page_state(memcg);
 	__mem_cgroup_free(memcg);
 }
 
@@ -5267,11 +5171,6 @@ static struct mem_cgroup *mem_cgroup_all
 		goto fail;
 	}
 
-	memcg->vmstats_local = alloc_percpu_gfp(struct memcg_vmstats_percpu,
-						GFP_KERNEL_ACCOUNT);
-	if (!memcg->vmstats_local)
-		goto fail;
-
 	memcg->vmstats_percpu = alloc_percpu_gfp(struct memcg_vmstats_percpu,
 						 GFP_KERNEL_ACCOUNT);
 	if (!memcg->vmstats_percpu)
@@ -5471,6 +5370,62 @@ static void mem_cgroup_css_reset(struct
 	memcg_wb_domain_size_changed(memcg);
 }
 
+static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
+	struct memcg_vmstats_percpu *statc;
+	long delta, v;
+	int i;
+
+	statc = per_cpu_ptr(memcg->vmstats_percpu, cpu);
+
+	for (i = 0; i < MEMCG_NR_STAT; i++) {
+		/*
+		 * Collect the aggregated propagation counts of groups
+		 * below us. We're in a per-cpu loop here and this is
+		 * a global counter, so the first cycle will get them.
+		 */
+		delta = memcg->vmstats.state_pending[i];
+		if (delta)
+			memcg->vmstats.state_pending[i] = 0;
+
+		/* Add CPU changes on this level since the last flush */
+		v = READ_ONCE(statc->state[i]);
+		if (v != statc->state_prev[i]) {
+			delta += v - statc->state_prev[i];
+			statc->state_prev[i] = v;
+		}
+
+		if (!delta)
+			continue;
+
+		/* Aggregate counts on this level and propagate upwards */
+		memcg->vmstats.state[i] += delta;
+		if (parent)
+			parent->vmstats.state_pending[i] += delta;
+	}
+
+	for (i = 0; i < NR_VM_EVENT_ITEMS; i++) {
+		delta = memcg->vmstats.events_pending[i];
+		if (delta)
+			memcg->vmstats.events_pending[i] = 0;
+
+		v = READ_ONCE(statc->events[i]);
+		if (v != statc->events_prev[i]) {
+			delta += v - statc->events_prev[i];
+			statc->events_prev[i] = v;
+		}
+
+		if (!delta)
+			continue;
+
+		memcg->vmstats.events[i] += delta;
+		if (parent)
+			parent->vmstats.events_pending[i] += delta;
+	}
+}
+
 #ifdef CONFIG_MMU
 /* Handlers for move charge at task migration. */
 static int mem_cgroup_do_precharge(unsigned long count)
@@ -6524,6 +6479,7 @@ struct cgroup_subsys memory_cgrp_subsys
 	.css_released = mem_cgroup_css_released,
 	.css_free = mem_cgroup_css_free,
 	.css_reset = mem_cgroup_css_reset,
+	.css_rstat_flush = mem_cgroup_css_rstat_flush,
 	.can_attach = mem_cgroup_can_attach,
 	.cancel_attach = mem_cgroup_cancel_attach,
 	.post_attach = mem_cgroup_move_task,
_

  parent reply	other threads:[~2021-04-30  5:56 UTC|newest]

Thread overview: 189+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-30  5:52 incoming Andrew Morton
2021-04-30  5:53 ` [patch 001/178] arch/ia64/kernel/head.S: remove duplicate include Andrew Morton
2021-04-30  5:53 ` [patch 002/178] arch/ia64/kernel/fsys.S: fix typos Andrew Morton
2021-04-30  5:53 ` [patch 003/178] arch/ia64/include/asm/pgtable.h: minor typo fixes Andrew Morton
2021-04-30  5:53 ` [patch 004/178] ia64: ensure proper NUMA distance and possible map initialization Andrew Morton
2021-04-30  5:53 ` [patch 005/178] ia64: drop unused IA64_FW_EMU ifdef Andrew Morton
2021-04-30  5:53 ` [patch 006/178] ia64: simplify code flow around swiotlb init Andrew Morton
2021-04-30  5:53 ` [patch 007/178] ia64: trivial spelling fixes Andrew Morton
2021-04-30  5:53 ` [patch 008/178] ia64: fix EFI_DEBUG build Andrew Morton
2021-04-30  5:53 ` [patch 009/178] ia64: mca: always make IA64_MCA_DEBUG an expression Andrew Morton
2021-04-30  5:53 ` [patch 010/178] ia64: drop marked broken DISCONTIGMEM and VIRTUAL_MEM_MAP Andrew Morton
2021-04-30  5:53 ` [patch 011/178] ia64: module: fix symbolizer crash on fdescr Andrew Morton
2021-04-30  5:53 ` [patch 012/178] include/linux/compiler-gcc.h: sparse can do constant folding of __builtin_bswap*() Andrew Morton
2021-04-30  5:53 ` [patch 013/178] scripts/spelling.txt: add entries for recent discoveries Andrew Morton
2021-04-30  5:53 ` [patch 014/178] scripts: a new script for checking duplicate struct declaration Andrew Morton
2021-04-30  5:53 ` [patch 015/178] arch/sh/include/asm/tlb.h: remove duplicate include Andrew Morton
2021-04-30  5:54 ` [patch 016/178] ocfs2: replace DEFINE_SIMPLE_ATTRIBUTE with DEFINE_DEBUGFS_ATTRIBUTE Andrew Morton
2021-04-30  5:54 ` [patch 017/178] ocfs2: map flags directly in flags_to_o2dlm() Andrew Morton
2021-04-30  5:54 ` [patch 018/178] ocfs2: fix a typo Andrew Morton
2021-04-30  5:54 ` [patch 019/178] ocfs2/dlm: remove unused function Andrew Morton
2021-04-30  5:54 ` [patch 020/178] kfifo: fix ternary sign extension bugs Andrew Morton
2021-04-30  5:54 ` [patch 021/178] vfs: fs_parser: clean up kernel-doc warnings Andrew Morton
2021-04-30  5:54 ` [patch 022/178] watchdog: rename __touch_watchdog() to a better descriptive name Andrew Morton
2021-04-30  5:54 ` [patch 023/178] watchdog: explicitly update timestamp when reporting softlockup Andrew Morton
2021-04-30  5:54 ` [patch 024/178] watchdog/softlockup: report the overall time of softlockups Andrew Morton
2021-04-30  5:54 ` [patch 025/178] watchdog/softlockup: remove logic that tried to prevent repeated reports Andrew Morton
2021-04-30  5:54 ` [patch 026/178] watchdog: fix barriers when printing backtraces from all CPUs Andrew Morton
2021-04-30  5:54 ` [patch 027/178] watchdog: cleanup handling of false positives Andrew Morton
2021-04-30  5:54 ` [patch 028/178] mm/slab_common: provide "slab_merge" option for !IS_ENABLED(CONFIG_SLAB_MERGE_DEFAULT) builds Andrew Morton
2021-04-30  5:54 ` [patch 029/178] mm, slub: enable slub_debug static key when creating cache with explicit debug flags Andrew Morton
2021-04-30  5:54 ` [patch 030/178] kunit: add a KUnit test for SLUB debugging functionality Andrew Morton
2021-04-30  8:50   ` Vlastimil Babka
2021-04-30 16:31     ` Linus Torvalds
2021-04-30  5:54 ` [patch 031/178] slub: remove resiliency_test() function Andrew Morton
2021-04-30  5:54 ` [patch 032/178] mm/slub.c: trivial typo fixes Andrew Morton
2021-04-30  5:54 ` [patch 033/178] mm/kmemleak.c: fix a typo Andrew Morton
2021-04-30  5:54 ` [patch 034/178] mm/page_owner: record the timestamp of all pages during free Andrew Morton
2021-04-30  5:55 ` [patch 035/178] mm, page_owner: remove unused parameter in __set_page_owner_handle Andrew Morton
2021-04-30  5:55 ` [patch 036/178] mm: page_owner: fetch backtrace only for tracked pages Andrew Morton
2021-04-30  5:55 ` [patch 037/178] mm: page_owner: use kstrtobool() to parse bool option Andrew Morton
2021-04-30  5:55 ` [patch 038/178] mm: page_owner: detect page_owner recursion via task_struct Andrew Morton
2021-04-30  5:55 ` [patch 039/178] mm: page_poison: print page info when corruption is caught Andrew Morton
2021-04-30  5:55 ` [patch 040/178] mm/memtest: add ARCH_USE_MEMTEST Andrew Morton
2021-04-30  5:55 ` [patch 041/178] mm: provide filemap_range_needs_writeback() helper Andrew Morton
2021-04-30 16:50   ` Linus Torvalds
2021-05-09 19:40     ` Matthew Wilcox
2021-04-30  5:55 ` [patch 042/178] mm: use filemap_range_needs_writeback() for O_DIRECT reads Andrew Morton
2021-04-30  5:55 ` [patch 043/178] iomap: " Andrew Morton
2021-04-30  5:55 ` [patch 044/178] mm/filemap: use filemap_read_page in filemap_fault Andrew Morton
2021-04-30  5:55 ` [patch 045/178] mm/filemap: drop check for truncated page after I/O Andrew Morton
2021-04-30  5:55 ` [patch 046/178] mm: page-writeback: simplify memcg handling in test_clear_page_writeback() Andrew Morton
2021-04-30  5:55 ` [patch 047/178] mm: move page_mapping_file to pagemap.h Andrew Morton
2021-04-30  5:55 ` [patch 048/178] mm/filemap: update stale comment Andrew Morton
2021-04-30  5:55 ` [patch 049/178] mm/msync: exit early when the flags is an MS_ASYNC and start < vm_start Andrew Morton
2021-04-30  5:55 ` [patch 050/178] mm/gup: add compound page list iterator Andrew Morton
2021-04-30  5:55 ` [patch 051/178] mm/gup: decrement head page once for group of subpages Andrew Morton
2021-04-30  5:55 ` [patch 052/178] mm/gup: add a range variant of unpin_user_pages_dirty_lock() Andrew Morton
2021-04-30  5:55 ` [patch 053/178] RDMA/umem: batch page unpin in __ib_umem_release() Andrew Morton
2021-04-30  5:55 ` [patch 054/178] mm: gup: remove FOLL_SPLIT Andrew Morton
2021-04-30  5:55 ` [patch 055/178] mm/memremap.c: fix improper SPDX comment style Andrew Morton
2021-04-30  5:56 ` [patch 056/178] mm: memcontrol: fix kernel stack account Andrew Morton
2021-04-30  5:56 ` [patch 057/178] memcg: cleanup root memcg checks Andrew Morton
2021-04-30  5:56 ` [patch 058/178] memcg: enable memcg oom-kill for __GFP_NOFAIL Andrew Morton
2021-04-30  5:56 ` [patch 059/178] mm: memcontrol: fix cpuhotplug statistics flushing Andrew Morton
2021-04-30  5:56 ` [patch 060/178] mm: memcontrol: kill mem_cgroup_nodeinfo() Andrew Morton
2021-04-30  5:56 ` [patch 061/178] mm: memcontrol: privatize memcg_page_state query functions Andrew Morton
2021-04-30  5:56 ` [patch 062/178] cgroup: rstat: support cgroup1 Andrew Morton
2021-04-30  5:56 ` [patch 063/178] cgroup: rstat: punt root-level optimization to individual controllers Andrew Morton
2021-04-30  5:56 ` Andrew Morton [this message]
2021-04-30  5:56 ` [patch 065/178] mm: memcontrol: consolidate lruvec stat flushing Andrew Morton
2021-04-30  5:56 ` [patch 066/178] kselftests: cgroup: update kmem test for new vmstat implementation Andrew Morton
2021-04-30  5:56 ` [patch 067/178] memcg: charge before adding to swapcache on swapin Andrew Morton
2021-04-30  5:56 ` [patch 068/178] mm: memcontrol: slab: fix obtain a reference to a freeing memcg Andrew Morton
2021-04-30  5:56 ` [patch 069/178] mm: memcontrol: introduce obj_cgroup_{un}charge_pages Andrew Morton
2021-04-30  5:56 ` [patch 070/178] mm: memcontrol: directly access page->memcg_data in mm/page_alloc.c Andrew Morton
2021-04-30  5:56 ` [patch 071/178] mm: memcontrol: change ug->dummy_page only if memcg changed Andrew Morton
2021-04-30  5:56 ` [patch 072/178] mm: memcontrol: use obj_cgroup APIs to charge kmem pages Andrew Morton
2021-04-30  5:56 ` [patch 073/178] mm: memcontrol: inline __memcg_kmem_{un}charge() into obj_cgroup_{un}charge_pages() Andrew Morton
2021-04-30  5:56 ` [patch 074/178] mm: memcontrol: move PageMemcgKmem to the scope of CONFIG_MEMCG_KMEM Andrew Morton
2021-04-30  5:57 ` [patch 075/178] linux/memcontrol.h: remove duplicate struct declaration Andrew Morton
2021-04-30  5:57 ` [patch 076/178] mm: page_counter: mitigate consequences of a page_counter underflow Andrew Morton
2021-04-30  5:57 ` [patch 077/178] mm/memory.c: do_numa_page(): delete bool "migrated" Andrew Morton
2021-04-30  5:57 ` [patch 078/178] mm/interval_tree: add comments to improve code readability Andrew Morton
2021-04-30  5:57 ` [patch 079/178] x86/vmemmap: drop handling of 4K unaligned vmemmap range Andrew Morton
2021-04-30  5:57 ` [patch 080/178] x86/vmemmap: drop handling of 1GB vmemmap ranges Andrew Morton
2021-04-30  5:57 ` [patch 081/178] x86/vmemmap: handle unpopulated sub-pmd ranges Andrew Morton
2021-04-30  5:57 ` [patch 082/178] x86/vmemmap: optimize for consecutive sections in partial populated PMDs Andrew Morton
2021-04-30  5:57 ` [patch 083/178] mm, tracing: improve rss_stat tracepoint message Andrew Morton
2021-04-30  5:57 ` [patch 084/178] mm: add remap_pfn_range_notrack Andrew Morton
2021-04-30  5:57 ` [patch 085/178] mm: add a io_mapping_map_user helper Andrew Morton
2021-04-30  5:57 ` [patch 086/178] i915: use io_mapping_map_user Andrew Morton
2021-04-30  5:57 ` [patch 087/178] i915: fix remap_io_sg to verify the pgprot Andrew Morton
2021-04-30  5:57 ` [patch 088/178] NUMA balancing: reduce TLB flush via delaying mapping on hint page fault Andrew Morton
2021-04-30  5:57 ` [patch 089/178] mm: extend MREMAP_DONTUNMAP to non-anonymous mappings Andrew Morton
2021-04-30  5:57 ` [patch 090/178] Revert "mremap: don't allow MREMAP_DONTUNMAP on special_mappings and aio" Andrew Morton
2021-04-30  5:57 ` [patch 091/178] selftests: add a MREMAP_DONTUNMAP selftest for shmem Andrew Morton
2021-04-30  5:57 ` [patch 092/178] mm/dmapool: switch from strlcpy to strscpy Andrew Morton
2021-04-30  5:57 ` [patch 093/178] mm/sparse: add the missing sparse_buffer_fini() in error branch Andrew Morton
2021-04-30  5:58 ` [patch 094/178] samples/vfio-mdev/mdpy: use remap_vmalloc_range Andrew Morton
2021-04-30  5:58 ` [patch 095/178] mm: unexport remap_vmalloc_range_partial Andrew Morton
2021-04-30  5:58 ` [patch 096/178] mm/vmalloc: use rb_tree instead of list for vread() lookups Andrew Morton
2021-04-30  5:58 ` [patch 097/178] ARM: mm: add missing pud_page define to 2-level page tables Andrew Morton
2021-04-30  5:58 ` [patch 098/178] mm/vmalloc: fix HUGE_VMAP regression by enabling huge pages in vmalloc_to_page Andrew Morton
2021-04-30  5:58 ` [patch 099/178] mm: apply_to_pte_range warn and fail if a large pte is encountered Andrew Morton
2021-04-30  5:58 ` [patch 100/178] mm/vmalloc: rename vmap_*_range vmap_pages_*_range Andrew Morton
2021-04-30  5:58 ` [patch 101/178] mm/ioremap: rename ioremap_*_range to vmap_*_range Andrew Morton
2021-04-30  5:58 ` [patch 102/178] mm: HUGE_VMAP arch support cleanup Andrew Morton
2021-04-30  5:58 ` [patch 103/178] powerpc: inline huge vmap supported functions Andrew Morton
2021-04-30  5:58 ` [patch 104/178] arm64: " Andrew Morton
2021-04-30  5:58 ` [patch 105/178] x86: " Andrew Morton
2021-04-30  5:58 ` [patch 106/178] mm/vmalloc: provide fallback arch huge vmap support functions Andrew Morton
2021-04-30  5:58 ` [patch 107/178] mm: move vmap_range from mm/ioremap.c to mm/vmalloc.c Andrew Morton
2021-04-30  5:58 ` [patch 108/178] mm/vmalloc: add vmap_range_noflush variant Andrew Morton
2021-04-30  5:58 ` [patch 109/178] mm/vmalloc: hugepage vmalloc mappings Andrew Morton
2021-04-30  5:58 ` [patch 110/178] mm/vmalloc: remove map_kernel_range Andrew Morton
2021-04-30  5:58 ` [patch 111/178] kernel/dma: remove unnecessary unmap_kernel_range Andrew Morton
2021-04-30  5:58 ` [patch 112/178] powerpc/xive: " Andrew Morton
2021-04-30  5:59 ` [patch 113/178] mm/vmalloc: remove unmap_kernel_range Andrew Morton
2021-04-30  5:59 ` [patch 114/178] mm/vmalloc: improve allocation failure error messages Andrew Morton
2021-04-30  5:59 ` [patch 115/178] mm: vmalloc: prevent use after free in _vm_unmap_aliases Andrew Morton
2021-04-30  5:59 ` [patch 116/178] lib/test_vmalloc.c: remove two kvfree_rcu() tests Andrew Morton
2021-04-30  5:59 ` [patch 117/178] lib/test_vmalloc.c: add a new 'nr_threads' parameter Andrew Morton
2021-04-30  5:59 ` [patch 118/178] vm/test_vmalloc.sh: adapt for updated driver interface Andrew Morton
2021-04-30  5:59 ` [patch 119/178] mm/vmalloc: refactor the preloading loagic Andrew Morton
2021-04-30  5:59 ` [patch 120/178] mm/vmalloc: remove an empty line Andrew Morton
2021-04-30  5:59 ` [patch 121/178] mm/doc: fix fault_flag_allow_retry_first kerneldoc Andrew Morton
2021-04-30  5:59 ` [patch 122/178] mm/doc: fix page_maybe_dma_pinned kerneldoc Andrew Morton
2021-04-30  5:59 ` [patch 123/178] mm/doc: turn fault flags into an enum Andrew Morton
2021-04-30  5:59 ` [patch 124/178] mm/doc: add mm.h and mm_types.h to the mm-api document Andrew Morton
2021-04-30  5:59 ` [patch 125/178] MAINTAINERS: assign pagewalk.h to MEMORY MANAGEMENT Andrew Morton
2021-04-30  5:59 ` [patch 126/178] pagewalk: prefix struct kernel-doc descriptions Andrew Morton
2021-04-30  5:59 ` [patch 127/178] mm/kasan: switch from strlcpy to strscpy Andrew Morton
2021-04-30  5:59 ` [patch 128/178] kasan: fix kasan_byte_accessible() to be consistent with actual checks Andrew Morton
2021-04-30  5:59 ` [patch 129/178] kasan: initialize shadow to TAG_INVALID for SW_TAGS Andrew Morton
2021-04-30  5:59 ` [patch 130/178] mm, kasan: don't poison boot memory with tag-based modes Andrew Morton
2021-04-30  5:59 ` [patch 131/178] arm64: kasan: allow to init memory when setting tags Andrew Morton
2021-04-30  5:59 ` [patch 132/178] kasan: init memory in kasan_(un)poison for HW_TAGS Andrew Morton
2021-04-30  6:00 ` [patch 133/178] kasan, mm: integrate page_alloc init with HW_TAGS Andrew Morton
2021-04-30  6:00 ` [patch 134/178] kasan, mm: integrate slab init_on_alloc " Andrew Morton
2021-04-30  6:00 ` [patch 135/178] kasan, mm: integrate slab init_on_free " Andrew Morton
2021-04-30  6:00 ` [patch 136/178] kasan: docs: clean up sections Andrew Morton
2021-04-30  6:00 ` [patch 137/178] kasan: docs: update overview section Andrew Morton
2021-04-30  6:00 ` [patch 138/178] kasan: docs: update usage section Andrew Morton
2021-04-30  6:00 ` [patch 139/178] kasan: docs: update error reports section Andrew Morton
2021-04-30  6:00 ` [patch 140/178] kasan: docs: update boot parameters section Andrew Morton
2021-04-30  6:00 ` [patch 141/178] kasan: docs: update GENERIC implementation details section Andrew Morton
2021-04-30  6:00 ` [patch 142/178] kasan: docs: update SW_TAGS " Andrew Morton
2021-04-30  6:00 ` [patch 143/178] kasan: docs: update HW_TAGS " Andrew Morton
2021-04-30  6:00 ` [patch 144/178] kasan: docs: update shadow memory section Andrew Morton
2021-04-30  6:00 ` [patch 145/178] kasan: docs: update ignoring accesses section Andrew Morton
2021-04-30  6:00 ` [patch 146/178] kasan: docs: update tests section Andrew Morton
2021-04-30  6:00 ` [patch 147/178] kasan: record task_work_add() call stack Andrew Morton
2021-04-30  6:00 ` [patch 148/178] kasan: detect false-positives in tests Andrew Morton
2021-04-30 18:32   ` Linus Torvalds
2021-05-02 18:04     ` Andrew Morton
2021-05-02 19:08       ` Linus Torvalds
2021-05-03 18:44         ` Andrew Morton
2021-04-30  6:00 ` [patch 149/178] irq_work: record irq_work_queue() call stack Andrew Morton
2021-04-30  6:00 ` [patch 150/178] mm: move mem_init_print_info() into mm_init() Andrew Morton
2021-04-30  6:00 ` [patch 151/178] mm/page_alloc: drop pr_info_ratelimited() in alloc_contig_range() Andrew Morton
2021-04-30  6:01 ` [patch 152/178] mm: remove lru_add_drain_all in alloc_contig_range Andrew Morton
2021-04-30  6:01 ` [patch 153/178] include/linux/page-flags-layout.h: correctly determine LAST_CPUPID_WIDTH Andrew Morton
2021-04-30  6:01 ` [patch 154/178] include/linux/page-flags-layout.h: cleanups Andrew Morton
2021-04-30  6:01 ` [patch 155/178] mm/page_alloc: rename alloc_mask to alloc_gfp Andrew Morton
2021-04-30  6:01 ` [patch 156/178] mm/page_alloc: rename gfp_mask to gfp Andrew Morton
2021-04-30  6:01 ` [patch 157/178] mm/page_alloc: combine __alloc_pages and __alloc_pages_nodemask Andrew Morton
2021-04-30  6:01 ` [patch 158/178] mm/mempolicy: rename alloc_pages_current to alloc_pages Andrew Morton
2021-04-30  6:01 ` [patch 159/178] mm/mempolicy: rewrite alloc_pages documentation Andrew Morton
2021-04-30  6:01 ` [patch 160/178] mm/mempolicy: rewrite alloc_pages_vma documentation Andrew Morton
2021-04-30  6:01 ` [patch 161/178] mm/mempolicy: fix mpol_misplaced kernel-doc Andrew Morton
2021-04-30  6:01 ` [patch 162/178] mm: page_alloc: dump migrate-failed pages Andrew Morton
2021-05-02  3:10   ` jim.cromie
2021-04-30  6:01 ` [patch 163/178] mm/Kconfig: remove default DISCONTIGMEM_MANUAL Andrew Morton
2021-04-30  6:01 ` [patch 164/178] mm, page_alloc: avoid page_to_pfn() in move_freepages() Andrew Morton
2021-04-30  6:01 ` [patch 165/178] mm/page_alloc: duplicate include linux/vmalloc.h Andrew Morton
2021-04-30  6:01 ` [patch 166/178] mm/page_alloc: rename alloced to allocated Andrew Morton
2021-04-30  6:01 ` [patch 167/178] mm/page_alloc: add a bulk page allocator Andrew Morton
2021-04-30  6:01 ` [patch 168/178] mm/page_alloc: add an array-based interface to the " Andrew Morton
2021-04-30  6:01 ` [patch 169/178] mm/page_alloc: optimize code layout for __alloc_pages_bulk Andrew Morton
2021-04-30  6:01 ` [patch 170/178] mm/page_alloc: inline __rmqueue_pcplist Andrew Morton
2021-04-30  6:01 ` [patch 171/178] SUNRPC: set rq_page_end differently Andrew Morton
2021-04-30  6:02 ` [patch 172/178] SUNRPC: refresh rq_pages using a bulk page allocator Andrew Morton
2021-04-30  6:02 ` [patch 173/178] net: page_pool: refactor dma_map into own function page_pool_dma_map Andrew Morton
2021-04-30  6:02 ` [patch 174/178] net: page_pool: use alloc_pages_bulk in refill code path Andrew Morton
2021-04-30  6:02 ` [patch 175/178] mm: page_alloc: ignore init_on_free=1 for debug_pagealloc=1 Andrew Morton
2021-04-30  6:02 ` [patch 176/178] mm/page_alloc: redundant definition variables of pfn in for loop Andrew Morton
2021-04-30 17:10   ` Linus Torvalds
2021-04-30  6:02 ` [patch 177/178] mm/mmzone.h: fix existing kernel-doc comments and link them to core-api Andrew Morton
2021-04-30  6:02 ` [patch 178/178] mm/memory-failure: unnecessary amount of unmapping Andrew Morton

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210430055626.WZK5r2afb%akpm@linux-foundation.org \
    --to=akpm@linux-foundation.org \
    --cc=bsingharora@gmail.com \
    --cc=guro@fb.com \
    --cc=hannes@cmpxchg.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.com \
    --cc=mkoutny@suse.com \
    --cc=mm-commits@vger.kernel.org \
    --cc=shakeelb@google.com \
    --cc=tj@kernel.org \
    --cc=torvalds@linux-foundation.org \
    --subject='Re: [patch 064/178] mm: memcontrol: switch to rstat' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
on how to clone and mirror all data and code used for this inbox