Merge tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of
   switching from a user process to a kernel thread.

 - More folio conversions from Kefeng Wang, Zhang Peng and Pankaj
   Raghav.

 - zsmalloc performance improvements from Sergey Senozhatsky.

 - Yue Zhao has found and fixed some data race issues around the
   alteration of memcg userspace tunables.

 - VFS rationalizations from Christoph Hellwig:
     - removal of most of the callers of write_one_page()
     - make __filemap_get_folio()'s return value more useful

 - Luis Chamberlain has changed tmpfs so it no longer requires swap
   backing. Use `mount -o noswap'.

 - Qi Zheng has made the slab shrinkers operate locklessly, providing
   some scalability benefits.

 - Keith Busch has improved dmapool's performance, making part of its
   operations O(1) rather than O(n).

 - Peter Xu adds the UFFD_FEATURE_WP_UNPOPULATED feature to userfaultd,
   permitting userspace to wr-protect anon memory unpopulated ptes.

 - Kirill Shutemov has changed MAX_ORDER's meaning to be inclusive
   rather than exclusive, and has fixed a bunch of errors which were
   caused by its unintuitive meaning.

 - Axel Rasmussen give userfaultfd the UFFDIO_CONTINUE_MODE_WP feature,
   which causes minor faults to install a write-protected pte.

 - Vlastimil Babka has done some maintenance work on vma_merge():
   cleanups to the kernel code and improvements to our userspace test
   harness.

 - Cleanups to do_fault_around() by Lorenzo Stoakes.

 - Mike Rapoport has moved a lot of initialization code out of various
   mm/ files and into mm/mm_init.c.

 - Lorenzo Stoakes removd vmf_insert_mixed_prot(), which was added for
   DRM, but DRM doesn't use it any more.

 - Lorenzo has also coverted read_kcore() and vread() to use iterators
   and has thereby removed the use of bounce buffers in some cases.

 - Lorenzo has also contributed further cleanups of vma_merge().

 - Chaitanya Prakash provides some fixes to the mmap selftesting code.

 - Matthew Wilcox changes xfs and afs so they no longer take sleeping
   locks in ->map_page(), a step towards RCUification of pagefaults.

 - Suren Baghdasaryan has improved mmap_lock scalability by switching to
   per-VMA locking.

 - Frederic Weisbecker has reworked the percpu cache draining so that it
   no longer causes latency glitches on cpu isolated workloads.

 - Mike Rapoport cleans up and corrects the ARCH_FORCE_MAX_ORDER Kconfig
   logic.

 - Liu Shixin has changed zswap's initialization so we no longer waste a
   chunk of memory if zswap is not being used.

 - Yosry Ahmed has improved the performance of memcg statistics
   flushing.

 - David Stevens has fixed several issues involving khugepaged,
   userfaultfd and shmem.

 - Christoph Hellwig has provided some cleanup work to zram's IO-related
   code paths.

 - David Hildenbrand has fixed up some issues in the selftest code's
   testing of our pte state changing.

 - Pankaj Raghav has made page_endio() unneeded and has removed it.

 - Peter Xu contributed some rationalizations of the userfaultfd
   selftests.

 - Yosry Ahmed has fixed an issue around memcg's page recalim
   accounting.

 - Chaitanya Prakash has fixed some arm-related issues in the
   selftests/mm code.

 - Longlong Xia has improved the way in which KSM handles hwpoisoned
   pages.

 - Peter Xu fixes a few issues with uffd-wp at fork() time.

 - Stefan Roesch has changed KSM so that it may now be used on a
   per-process and per-cgroup basis.

* tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (369 commits)
  mm,unmap: avoid flushing TLB in batch if PTE is inaccessible
  shmem: restrict noswap option to initial user namespace
  mm/khugepaged: fix conflicting mods to collapse_file()
  sparse: remove unnecessary 0 values from rc
  mm: move 'mmap_min_addr' logic from callers into vm_unmapped_area()
  hugetlb: pte_alloc_huge() to replace huge pte_alloc_map()
  maple_tree: fix allocation in mas_sparse_area()
  mm: do not increment pgfault stats when page fault handler retries
  zsmalloc: allow only one active pool compaction context
  selftests/mm: add new selftests for KSM
  mm: add new KSM process and sysfs knobs
  mm: add new api to enable ksm per process
  mm: shrinkers: fix debugfs file permissions
  mm: don't check VMA write permissions if the PTE/PMD indicates write permissions
  migrate_pages_batch: fix statistics for longterm pin retry
  userfaultfd: use helper function range_in_vma()
  lib/show_mem.c: use for_each_populated_zone() simplify code
  mm: correct arg in reclaim_pages()/reclaim_clean_pages_from_list()
  fs/buffer: convert create_page_buffers to folio_create_buffers
  fs/buffer: add folio_create_empty_buffers helper
  ...

1 files changed, 94 insertions, 33 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5abffe6f8389..4b27e245a055 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -63,6 +63,7 @@
 #include <linux/resume_user_mode.h>
 #include <linux/psi.h>
 #include <linux/seq_buf.h>
+#include <linux/sched/isolation.h>
 #include "internal.h"
 #include <net/sock.h>
 #include <net/ip.h>
@@ -395,7 +396,8 @@ ino_t page_cgroup_ino(struct page *page)
 	unsigned long ino = 0;
 
 	rcu_read_lock();
-	memcg = page_memcg_check(page);
+	/* page_folio() is racy here, but the entire function is racy anyway */
+	memcg = folio_memcg_check(page_folio(page));
 
 	while (memcg && !(memcg->css.flags & CSS_ONLINE))
 		memcg = parent_mem_cgroup(memcg);
@@ -585,8 +587,8 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
  */
 static void flush_memcg_stats_dwork(struct work_struct *w);
 static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork);
-static DEFINE_SPINLOCK(stats_flush_lock);
 static DEFINE_PER_CPU(unsigned int, stats_updates);
+static atomic_t stats_flush_ongoing = ATOMIC_INIT(0);
 static atomic_t stats_flush_threshold = ATOMIC_INIT(0);
 static u64 flush_next_time;
 
@@ -618,6 +620,9 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
 {
 	unsigned int x;
 
+	if (!val)
+		return;
+
 	cgroup_rstat_updated(memcg->css.cgroup, smp_processor_id());
 
 	x = __this_cpu_add_return(stats_updates, abs(val));
@@ -634,34 +639,58 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
 	}
 }
 
-static void __mem_cgroup_flush_stats(void)
+static void do_flush_stats(bool atomic)
 {
-	unsigned long flag;
-
-	if (!spin_trylock_irqsave(&stats_flush_lock, flag))
+	/*
+	 * We always flush the entire tree, so concurrent flushers can just
+	 * skip. This avoids a thundering herd problem on the rstat global lock
+	 * from memcg flushers (e.g. reclaim, refault, etc).
+	 */
+	if (atomic_read(&stats_flush_ongoing) ||
+	    atomic_xchg(&stats_flush_ongoing, 1))
 		return;
 
-	flush_next_time = jiffies_64 + 2*FLUSH_TIME;
-	cgroup_rstat_flush_irqsafe(root_mem_cgroup->css.cgroup);
+	WRITE_ONCE(flush_next_time, jiffies_64 + 2*FLUSH_TIME);
+
+	if (atomic)
+		cgroup_rstat_flush_atomic(root_mem_cgroup->css.cgroup);
+	else
+		cgroup_rstat_flush(root_mem_cgroup->css.cgroup);
+
 	atomic_set(&stats_flush_threshold, 0);
-	spin_unlock_irqrestore(&stats_flush_lock, flag);
+	atomic_set(&stats_flush_ongoing, 0);
+}
+
+static bool should_flush_stats(void)
+{
+	return atomic_read(&stats_flush_threshold) > num_online_cpus();
 }
 
 void mem_cgroup_flush_stats(void)
 {
-	if (atomic_read(&stats_flush_threshold) > num_online_cpus())
-		__mem_cgroup_flush_stats();
+	if (should_flush_stats())
+		do_flush_stats(false);
 }
 
-void mem_cgroup_flush_stats_delayed(void)
+void mem_cgroup_flush_stats_atomic(void)
 {
-	if (time_after64(jiffies_64, flush_next_time))
+	if (should_flush_stats())
+		do_flush_stats(true);
+}
+
+void mem_cgroup_flush_stats_ratelimited(void)
+{
+	if (time_after64(jiffies_64, READ_ONCE(flush_next_time)))
 		mem_cgroup_flush_stats();
 }
 
 static void flush_memcg_stats_dwork(struct work_struct *w)
 {
-	__mem_cgroup_flush_stats();
+	/*
+	 * Always flush here so that flushing in latency-sensitive paths is
+	 * as cheap as possible.
+	 */
+	do_flush_stats(false);
 	queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME);
 }
 
@@ -1929,7 +1958,7 @@ static bool mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
 	 * Please note that mem_cgroup_out_of_memory might fail to find a
 	 * victim and then we have to bail out from the charge path.
 	 */
-	if (memcg->oom_kill_disable) {
+	if (READ_ONCE(memcg->oom_kill_disable)) {
 		if (current->in_user_fault) {
 			css_get(&memcg->css);
 			current->memcg_in_oom = memcg;
@@ -1999,7 +2028,7 @@ bool mem_cgroup_oom_synchronize(bool handle)
 	if (locked)
 		mem_cgroup_oom_notify(memcg);
 
-	if (locked && !memcg->oom_kill_disable) {
+	if (locked && !READ_ONCE(memcg->oom_kill_disable)) {
 		mem_cgroup_unmark_under_oom(memcg);
 		finish_wait(&memcg_oom_waitq, &owait.wait);
 		mem_cgroup_out_of_memory(memcg, current->memcg_oom_gfp_mask,
@@ -2067,7 +2096,7 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim,
 	 * highest-level memory cgroup with oom.group set.
 	 */
 	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
-		if (memcg->oom_group)
+		if (READ_ONCE(memcg->oom_group))
 			oom_group = memcg;
 
 		if (memcg == oom_domain)
@@ -2366,7 +2395,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg)
 		    !test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) {
 			if (cpu == curcpu)
 				drain_local_stock(&stock->work);
-			else
+			else if (!cpu_is_isolated(cpu))
 				schedule_work_on(cpu, &stock->work);
 		}
 	}
@@ -3669,7 +3698,24 @@ static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
 	unsigned long val;
 
 	if (mem_cgroup_is_root(memcg)) {
-		mem_cgroup_flush_stats();
+		/*
+		 * We can reach here from irq context through:
+		 * uncharge_batch()
+		 * |--memcg_check_events()
+		 *    |--mem_cgroup_threshold()
+		 *       |--__mem_cgroup_threshold()
+		 *          |--mem_cgroup_usage
+		 *
+		 * rstat flushing is an expensive operation that should not be
+		 * done from irq context; use stale stats in this case.
+		 * Arguably, usage threshold events are not reliable on the root
+		 * memcg anyway since its usage is ill-defined.
+		 *
+		 * Additionally, other call paths through memcg_check_events()
+		 * disable irqs, so make sure we are flushing stats atomically.
+		 */
+		if (in_task())
+			mem_cgroup_flush_stats_atomic();
 		val = memcg_page_state(memcg, NR_FILE_PAGES) +
 			memcg_page_state(memcg, NR_ANON_MAPPED);
 		if (swap)
@@ -3728,12 +3774,22 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
 	case RES_FAILCNT:
 		return counter->failcnt;
 	case RES_SOFT_LIMIT:
-		return (u64)memcg->soft_limit * PAGE_SIZE;
+		return (u64)READ_ONCE(memcg->soft_limit) * PAGE_SIZE;
 	default:
 		BUG();
 	}
 }
 
+/*
+ * This function doesn't do anything useful. Its only job is to provide a read
+ * handler for a file so that cgroup_file_mode() will add read permissions.
+ */
+static int mem_cgroup_dummy_seq_show(__always_unused struct seq_file *m,
+				     __always_unused void *v)
+{
+	return -EINVAL;
+}
+
 #ifdef CONFIG_MEMCG_KMEM
 static int memcg_online_kmem(struct mem_cgroup *memcg)
 {
@@ -3870,7 +3926,7 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of,
 		if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
 			ret = -EOPNOTSUPP;
 		} else {
-			memcg->soft_limit = nr_pages;
+			WRITE_ONCE(memcg->soft_limit, nr_pages);
 			ret = 0;
 		}
 		break;
@@ -4179,9 +4235,9 @@ static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css,
 		return -EINVAL;
 
 	if (!mem_cgroup_is_root(memcg))
-		memcg->swappiness = val;
+		WRITE_ONCE(memcg->swappiness, val);
 	else
-		vm_swappiness = val;
+		WRITE_ONCE(vm_swappiness, val);
 
 	return 0;
 }
@@ -4515,7 +4571,7 @@ static int mem_cgroup_oom_control_read(struct seq_file *sf, void *v)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_seq(sf);
 
-	seq_printf(sf, "oom_kill_disable %d\n", memcg->oom_kill_disable);
+	seq_printf(sf, "oom_kill_disable %d\n", READ_ONCE(memcg->oom_kill_disable));
 	seq_printf(sf, "under_oom %d\n", (bool)memcg->under_oom);
 	seq_printf(sf, "oom_kill %lu\n",
 		   atomic_long_read(&memcg->memory_events[MEMCG_OOM_KILL]));
@@ -4531,7 +4587,7 @@ static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css,
 	if (mem_cgroup_is_root(memcg) || !((val == 0) || (val == 1)))
 		return -EINVAL;
 
-	memcg->oom_kill_disable = val;
+	WRITE_ONCE(memcg->oom_kill_disable, val);
 	if (!val)
 		memcg_oom_recover(memcg);
 
@@ -4592,7 +4648,11 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
 	struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
 	struct mem_cgroup *parent;
 
-	mem_cgroup_flush_stats();
+	/*
+	 * wb_writeback() takes a spinlock and calls
+	 * wb_over_bg_thresh()->mem_cgroup_wb_stats(). Do not sleep.
+	 */
+	mem_cgroup_flush_stats_atomic();
 
 	*pdirty = memcg_page_state(memcg, NR_FILE_DIRTY);
 	*pwriteback = memcg_page_state(memcg, NR_WRITEBACK);
@@ -5064,6 +5124,7 @@ static struct cftype mem_cgroup_legacy_files[] = {
 	},
 	{
 		.name = "pressure_level",
+		.seq_show = mem_cgroup_dummy_seq_show,
 	},
 #ifdef CONFIG_NUMA
 	{
@@ -5347,14 +5408,14 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 		return ERR_CAST(memcg);
 
 	page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX);
-	memcg->soft_limit = PAGE_COUNTER_MAX;
+	WRITE_ONCE(memcg->soft_limit, PAGE_COUNTER_MAX);
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
 	memcg->zswap_max = PAGE_COUNTER_MAX;
 #endif
 	page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
 	if (parent) {
-		memcg->swappiness = mem_cgroup_swappiness(parent);
-		memcg->oom_kill_disable = parent->oom_kill_disable;
+		WRITE_ONCE(memcg->swappiness, mem_cgroup_swappiness(parent));
+		WRITE_ONCE(memcg->oom_kill_disable, READ_ONCE(parent->oom_kill_disable));
 
 		page_counter_init(&memcg->memory, &parent->memory);
 		page_counter_init(&memcg->swap, &parent->swap);
@@ -5502,7 +5563,7 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css)
 	page_counter_set_min(&memcg->memory, 0);
 	page_counter_set_low(&memcg->memory, 0);
 	page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX);
-	memcg->soft_limit = PAGE_COUNTER_MAX;
+	WRITE_ONCE(memcg->soft_limit, PAGE_COUNTER_MAX);
 	page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
 	memcg_wb_domain_size_changed(memcg);
 }
@@ -5705,7 +5766,7 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
 	/* shmem/tmpfs may report page out on swap: account for that too. */
 	index = linear_page_index(vma, addr);
 	folio = filemap_get_incore_folio(vma->vm_file->f_mapping, index);
-	if (!folio)
+	if (IS_ERR(folio))
 		return NULL;
 	return folio_file_page(folio, index);
 }
@@ -6623,7 +6684,7 @@ static int memory_oom_group_show(struct seq_file *m, void *v)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 
-	seq_printf(m, "%d\n", memcg->oom_group);
+	seq_printf(m, "%d\n", READ_ONCE(memcg->oom_group));
 
 	return 0;
 }
@@ -6645,7 +6706,7 @@ static ssize_t memory_oom_group_write(struct kernfs_open_file *of,
 	if (oom_group != 0 && oom_group != 1)
 		return -EINVAL;
 
-	memcg->oom_group = oom_group;
+	WRITE_ONCE(memcg->oom_group, oom_group);
 
 	return nbytes;
 }