Merge tag 'mm-hotfixes-stable-2024-02-10-11-16' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "21 hotfixes. 12 are cc:stable and the remainder pertain to post-6.7
  issues or aren't considered to be needed in earlier kernel versions"

* tag 'mm-hotfixes-stable-2024-02-10-11-16' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (21 commits)
  nilfs2: fix potential bug in end_buffer_async_write
  mm/damon/sysfs-schemes: fix wrong DAMOS tried regions update timeout setup
  nilfs2: fix hang in nilfs_lookup_dirty_data_buffers()
  MAINTAINERS: Leo Yan has moved
  mm/zswap: don't return LRU_SKIP if we have dropped lru lock
  fs,hugetlb: fix NULL pointer dereference in hugetlbs_fill_super
  mailmap: switch email address for John Moon
  mm: zswap: fix objcg use-after-free in entry destruction
  mm/madvise: don't forget to leave lazy MMU mode in madvise_cold_or_pageout_pte_range()
  arch/arm/mm: fix major fault accounting when retrying under per-VMA lock
  selftests: core: include linux/close_range.h for CLOSE_RANGE_* macros
  mm/memory-failure: fix crash in split_huge_page_to_list from soft_offline_page
  mm: memcg: optimize parent iteration in memcg_rstat_updated()
  nilfs2: fix data corruption in dsync block recovery for small block sizes
  mm/userfaultfd: UFFDIO_MOVE implementation should use ptep_get()
  exit: wait_task_zombie: kill the no longer necessary spin_lock_irq(siglock)
  fs/proc: do_task_stat: use sig->stats_lock to gather the threads/children stats
  fs/proc: do_task_stat: move thread_group_cputime_adjusted() outside of lock_task_sighand()
  getrusage: use sig->stats_lock rather than lock_task_sighand()
  getrusage: move thread_group_cputime_adjusted() outside of lock_task_sighand()
  ...

6 files changed, 52 insertions, 36 deletions

diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c
index 8dbaac6e5c2d..dd2fb5127009 100644
--- a/mm/damon/sysfs-schemes.c
+++ b/mm/damon/sysfs-schemes.c
@@ -2194,7 +2194,7 @@ static void damos_tried_regions_init_upd_status(
 		sysfs_regions->upd_timeout_jiffies = jiffies +
 			2 * usecs_to_jiffies(scheme->apply_interval_us ?
 					scheme->apply_interval_us :
-					ctx->attrs.sample_interval);
+					ctx->attrs.aggr_interval);
 	}
 }
 
diff --git a/mm/madvise.c b/mm/madvise.c
index 912155a94ed5..cfa5e7288261 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -429,6 +429,7 @@ restart:
 		if (++batch_count == SWAP_CLUSTER_MAX) {
 			batch_count = 0;
 			if (need_resched()) {
+				arch_leave_lazy_mmu_mode();
 				pte_unmap_unlock(start_pte, ptl);
 				cond_resched();
 				goto restart;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 46d8d02114cf..1ed40f9d3a27 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -621,6 +621,15 @@ static inline int memcg_events_index(enum vm_event_item idx)
 }
 
 struct memcg_vmstats_percpu {
+	/* Stats updates since the last flush */
+	unsigned int			stats_updates;
+
+	/* Cached pointers for fast iteration in memcg_rstat_updated() */
+	struct memcg_vmstats_percpu	*parent;
+	struct memcg_vmstats		*vmstats;
+
+	/* The above should fit a single cacheline for memcg_rstat_updated() */
+
 	/* Local (CPU and cgroup) page state & events */
 	long			state[MEMCG_NR_STAT];
 	unsigned long		events[NR_MEMCG_EVENTS];
@@ -632,10 +641,7 @@ struct memcg_vmstats_percpu {
 	/* Cgroup1: threshold notifications & softlimit tree updates */
 	unsigned long		nr_page_events;
 	unsigned long		targets[MEM_CGROUP_NTARGETS];
-
-	/* Stats updates since the last flush */
-	unsigned int		stats_updates;
-};
+} ____cacheline_aligned;
 
 struct memcg_vmstats {
 	/* Aggregated (CPU and subtree) page state & events */
@@ -698,36 +704,35 @@ static void memcg_stats_unlock(void)
 }
 
 
-static bool memcg_should_flush_stats(struct mem_cgroup *memcg)
+static bool memcg_vmstats_needs_flush(struct memcg_vmstats *vmstats)
 {
-	return atomic64_read(&memcg->vmstats->stats_updates) >
+	return atomic64_read(&vmstats->stats_updates) >
 		MEMCG_CHARGE_BATCH * num_online_cpus();
 }
 
 static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
 {
+	struct memcg_vmstats_percpu *statc;
 	int cpu = smp_processor_id();
-	unsigned int x;
 
 	if (!val)
 		return;
 
 	cgroup_rstat_updated(memcg->css.cgroup, cpu);
-
-	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
-		x = __this_cpu_add_return(memcg->vmstats_percpu->stats_updates,
-					  abs(val));
-
-		if (x < MEMCG_CHARGE_BATCH)
+	statc = this_cpu_ptr(memcg->vmstats_percpu);
+	for (; statc; statc = statc->parent) {
+		statc->stats_updates += abs(val);
+		if (statc->stats_updates < MEMCG_CHARGE_BATCH)
 			continue;
 
 		/*
 		 * If @memcg is already flush-able, increasing stats_updates is
 		 * redundant. Avoid the overhead of the atomic update.
 		 */
-		if (!memcg_should_flush_stats(memcg))
-			atomic64_add(x, &memcg->vmstats->stats_updates);
-		__this_cpu_write(memcg->vmstats_percpu->stats_updates, 0);
+		if (!memcg_vmstats_needs_flush(statc->vmstats))
+			atomic64_add(statc->stats_updates,
+				     &statc->vmstats->stats_updates);
+		statc->stats_updates = 0;
 	}
 }
 
@@ -756,7 +761,7 @@ void mem_cgroup_flush_stats(struct mem_cgroup *memcg)
 	if (!memcg)
 		memcg = root_mem_cgroup;
 
-	if (memcg_should_flush_stats(memcg))
+	if (memcg_vmstats_needs_flush(memcg->vmstats))
 		do_flush_stats(memcg);
 }
 
@@ -770,7 +775,7 @@ void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg)
 static void flush_memcg_stats_dwork(struct work_struct *w)
 {
 	/*
-	 * Deliberately ignore memcg_should_flush_stats() here so that flushing
+	 * Deliberately ignore memcg_vmstats_needs_flush() here so that flushing
 	 * in latency-sensitive paths is as cheap as possible.
 	 */
 	do_flush_stats(root_mem_cgroup);
@@ -5477,10 +5482,11 @@ static void mem_cgroup_free(struct mem_cgroup *memcg)
 	__mem_cgroup_free(memcg);
 }
 
-static struct mem_cgroup *mem_cgroup_alloc(void)
+static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent)
 {
+	struct memcg_vmstats_percpu *statc, *pstatc;
 	struct mem_cgroup *memcg;
-	int node;
+	int node, cpu;
 	int __maybe_unused i;
 	long error = -ENOMEM;
 
@@ -5504,6 +5510,14 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	if (!memcg->vmstats_percpu)
 		goto fail;
 
+	for_each_possible_cpu(cpu) {
+		if (parent)
+			pstatc = per_cpu_ptr(parent->vmstats_percpu, cpu);
+		statc = per_cpu_ptr(memcg->vmstats_percpu, cpu);
+		statc->parent = parent ? pstatc : NULL;
+		statc->vmstats = memcg->vmstats;
+	}
+
 	for_each_node(node)
 		if (alloc_mem_cgroup_per_node_info(memcg, node))
 			goto fail;
@@ -5549,7 +5563,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	struct mem_cgroup *memcg, *old_memcg;
 
 	old_memcg = set_active_memcg(parent);
-	memcg = mem_cgroup_alloc();
+	memcg = mem_cgroup_alloc(parent);
 	set_active_memcg(old_memcg);
 	if (IS_ERR(memcg))
 		return ERR_CAST(memcg);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 636280d04008..9349948f1abf 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1377,6 +1377,9 @@ void ClearPageHWPoisonTakenOff(struct page *page)
  */
 static inline bool HWPoisonHandlable(struct page *page, unsigned long flags)
 {
+	if (PageSlab(page))
+		return false;
+
 	/* Soft offline could migrate non-LRU movable pages */
 	if ((flags & MF_SOFT_OFFLINE) && __PageMovable(page))
 		return true;
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 75fcf1f783bc..7cf7d4384259 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -902,8 +902,8 @@ static int move_present_pte(struct mm_struct *mm,
 
 	double_pt_lock(dst_ptl, src_ptl);
 
-	if (!pte_same(*src_pte, orig_src_pte) ||
-	    !pte_same(*dst_pte, orig_dst_pte)) {
+	if (!pte_same(ptep_get(src_pte), orig_src_pte) ||
+	    !pte_same(ptep_get(dst_pte), orig_dst_pte)) {
 		err = -EAGAIN;
 		goto out;
 	}
@@ -946,8 +946,8 @@ static int move_swap_pte(struct mm_struct *mm,
 
 	double_pt_lock(dst_ptl, src_ptl);
 
-	if (!pte_same(*src_pte, orig_src_pte) ||
-	    !pte_same(*dst_pte, orig_dst_pte)) {
+	if (!pte_same(ptep_get(src_pte), orig_src_pte) ||
+	    !pte_same(ptep_get(dst_pte), orig_dst_pte)) {
 		double_pt_unlock(dst_ptl, src_ptl);
 		return -EAGAIN;
 	}
@@ -1016,7 +1016,7 @@ retry:
 	}
 
 	spin_lock(dst_ptl);
-	orig_dst_pte = *dst_pte;
+	orig_dst_pte = ptep_get(dst_pte);
 	spin_unlock(dst_ptl);
 	if (!pte_none(orig_dst_pte)) {
 		err = -EEXIST;
@@ -1024,7 +1024,7 @@ retry:
 	}
 
 	spin_lock(src_ptl);
-	orig_src_pte = *src_pte;
+	orig_src_pte = ptep_get(src_pte);
 	spin_unlock(src_ptl);
 	if (pte_none(orig_src_pte)) {
 		if (!(mode & UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES))
@@ -1054,7 +1054,7 @@ retry:
 			 * page isn't freed under us
 			 */
 			spin_lock(src_ptl);
-			if (!pte_same(orig_src_pte, *src_pte)) {
+			if (!pte_same(orig_src_pte, ptep_get(src_pte))) {
 				spin_unlock(src_ptl);
 				err = -EAGAIN;
 				goto out;
diff --git a/mm/zswap.c b/mm/zswap.c
index ca25b676048e..350dd2fc8159 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -536,10 +536,6 @@ static struct zpool *zswap_find_zpool(struct zswap_entry *entry)
  */
 static void zswap_free_entry(struct zswap_entry *entry)
 {
-	if (entry->objcg) {
-		obj_cgroup_uncharge_zswap(entry->objcg, entry->length);
-		obj_cgroup_put(entry->objcg);
-	}
 	if (!entry->length)
 		atomic_dec(&zswap_same_filled_pages);
 	else {
@@ -548,6 +544,10 @@ static void zswap_free_entry(struct zswap_entry *entry)
 		atomic_dec(&entry->pool->nr_stored);
 		zswap_pool_put(entry->pool);
 	}
+	if (entry->objcg) {
+		obj_cgroup_uncharge_zswap(entry->objcg, entry->length);
+		obj_cgroup_put(entry->objcg);
+	}
 	zswap_entry_cache_free(entry);
 	atomic_dec(&zswap_stored_pages);
 	zswap_update_total_size();
@@ -895,10 +895,8 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o
 		 * into the warmer region. We should terminate shrinking (if we're in the dynamic
 		 * shrinker context).
 		 */
-		if (writeback_result == -EEXIST && encountered_page_in_swapcache) {
-			ret = LRU_SKIP;
+		if (writeback_result == -EEXIST && encountered_page_in_swapcache)
 			*encountered_page_in_swapcache = true;
-		}
 
 		goto put_unlock;
 	}