Merge tag 'mm-hotfixes-stable-2024-02-10-11-16' of...

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()
  ...

.mailmap

@@ -289,6 +289,7 @@ Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com>
 John Crispin <john@phrozen.org> <blogic@openwrt.org>
 John Fastabend <john.fastabend@gmail.com> <john.r.fastabend@intel.com>
 John Keeping <john@keeping.me.uk> <john@metanate.com>
+John Moon <john@jmoon.dev> <quic_johmoo@quicinc.com>
 John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
 John Stultz <johnstul@us.ibm.com>
 <jon.toppins+linux@gmail.com> <jtoppins@cumulusnetworks.com>
@@ -344,6 +345,7 @@ Leonid I Ananiev <leonid.i.ananiev@intel.com>
 Leon Romanovsky <leon@kernel.org> <leon@leon.nu>
 Leon Romanovsky <leon@kernel.org> <leonro@mellanox.com>
 Leon Romanovsky <leon@kernel.org> <leonro@nvidia.com>
+Leo Yan <leo.yan@linux.dev> <leo.yan@linaro.org>
 Liam Mark <quic_lmark@quicinc.com> <lmark@codeaurora.org>
 Linas Vepstas <linas@austin.ibm.com>
 Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch>

MAINTAINERS

@@ -17182,7 +17182,7 @@ R:	John Garry <john.g.garry@oracle.com>
 R:	Will Deacon <will@kernel.org>
 R:	James Clark <james.clark@arm.com>
 R:	Mike Leach <mike.leach@linaro.org>
-R:	Leo Yan <leo.yan@linaro.org>
+R:	Leo Yan <leo.yan@linux.dev>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
 F:	tools/build/feature/test-libopencsd.c

arch/arm/mm/fault.c

@@ -298,6 +298,8 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 		goto done;
 	}
 	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		flags |= FAULT_FLAG_TRIED;
 
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {

fs/hugetlbfs/inode.c

@@ -100,6 +100,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	loff_t len, vma_len;
 	int ret;
 	struct hstate *h = hstate_file(file);
+	vm_flags_t vm_flags;
 
 	/*
 	 * vma address alignment (but not the pgoff alignment) has
@@ -141,10 +142,20 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	file_accessed(file);
 
 	ret = -ENOMEM;
+
+	vm_flags = vma->vm_flags;
+	/*
+	 * for SHM_HUGETLB, the pages are reserved in the shmget() call so skip
+	 * reserving here. Note: only for SHM hugetlbfs file, the inode
+	 * flag S_PRIVATE is set.
+	 */
+	if (inode->i_flags & S_PRIVATE)
+		vm_flags |= VM_NORESERVE;
+
 	if (!hugetlb_reserve_pages(inode,
 				vma->vm_pgoff >> huge_page_order(h),
 				len >> huge_page_shift(h), vma,
-				vma->vm_flags))
+				vm_flags))
 		goto out;
 
 	ret = 0;
@@ -1354,6 +1365,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par
 {
 	struct hugetlbfs_fs_context *ctx = fc->fs_private;
 	struct fs_parse_result result;
+	struct hstate *h;
 	char *rest;
 	unsigned long ps;
 	int opt;
@@ -1398,11 +1410,12 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par
 
 	case Opt_pagesize:
 		ps = memparse(param->string, &rest);
-		ctx->hstate = size_to_hstate(ps);
-		if (!ctx->hstate) {
+		h = size_to_hstate(ps);
+		if (!h) {
 			pr_err("Unsupported page size %lu MB\n", ps / SZ_1M);
 			return -EINVAL;
 		}
+		ctx->hstate = h;
 		return 0;
 
 	case Opt_min_size:

fs/nilfs2/file.c

@@ -107,7 +107,13 @@ static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf)
 	nilfs_transaction_commit(inode->i_sb);
 
  mapped:
-	folio_wait_stable(folio);
+	/*
+	 * Since checksumming including data blocks is performed to determine
+	 * the validity of the log to be written and used for recovery, it is
+	 * necessary to wait for writeback to finish here, regardless of the
+	 * stable write requirement of the backing device.
+	 */
+	folio_wait_writeback(folio);
  out:
 	sb_end_pagefault(inode->i_sb);
 	return vmf_fs_error(ret);

fs/nilfs2/recovery.c

@@ -472,9 +472,10 @@ static int nilfs_prepare_segment_for_recovery(struct the_nilfs *nilfs,
 
 static int nilfs_recovery_copy_block(struct the_nilfs *nilfs,
 				     struct nilfs_recovery_block *rb,
-				     struct page *page)
+				     loff_t pos, struct page *page)
 {
 	struct buffer_head *bh_org;
+	size_t from = pos & ~PAGE_MASK;
 	void *kaddr;
 
 	bh_org = __bread(nilfs->ns_bdev, rb->blocknr, nilfs->ns_blocksize);
@@ -482,7 +483,7 @@ static int nilfs_recovery_copy_block(struct the_nilfs *nilfs,
 		return -EIO;
 
 	kaddr = kmap_atomic(page);
-	memcpy(kaddr + bh_offset(bh_org), bh_org->b_data, bh_org->b_size);
+	memcpy(kaddr + from, bh_org->b_data, bh_org->b_size);
 	kunmap_atomic(kaddr);
 	brelse(bh_org);
 	return 0;
@@ -521,7 +522,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
 			goto failed_inode;
 		}
 
-		err = nilfs_recovery_copy_block(nilfs, rb, page);
+		err = nilfs_recovery_copy_block(nilfs, rb, pos, page);
 		if (unlikely(err))
 			goto failed_page;
 

fs/nilfs2/segment.c

@@ -1703,7 +1703,6 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
 
 		list_for_each_entry(bh, &segbuf->sb_payload_buffers,
 				    b_assoc_buffers) {
-			set_buffer_async_write(bh);
 			if (bh == segbuf->sb_super_root) {
 				if (bh->b_folio != bd_folio) {
 					folio_lock(bd_folio);
@@ -1714,6 +1713,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
 				}
 				break;
 			}
+			set_buffer_async_write(bh);
 			if (bh->b_folio != fs_folio) {
 				nilfs_begin_folio_io(fs_folio);
 				fs_folio = bh->b_folio;
@@ -1800,7 +1800,6 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
 
 		list_for_each_entry(bh, &segbuf->sb_payload_buffers,
 				    b_assoc_buffers) {
-			clear_buffer_async_write(bh);
 			if (bh == segbuf->sb_super_root) {
 				clear_buffer_uptodate(bh);
 				if (bh->b_folio != bd_folio) {
@@ -1809,6 +1808,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
 				}
 				break;
 			}
+			clear_buffer_async_write(bh);
 			if (bh->b_folio != fs_folio) {
 				nilfs_end_folio_io(fs_folio, err);
 				fs_folio = bh->b_folio;
@@ -1896,8 +1896,9 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
 				 BIT(BH_Delay) | BIT(BH_NILFS_Volatile) |
 				 BIT(BH_NILFS_Redirected));
 
-			set_mask_bits(&bh->b_state, clear_bits, set_bits);
 			if (bh == segbuf->sb_super_root) {
+				set_buffer_uptodate(bh);
+				clear_buffer_dirty(bh);
 				if (bh->b_folio != bd_folio) {
 					folio_end_writeback(bd_folio);
 					bd_folio = bh->b_folio;
@@ -1905,6 +1906,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
 				update_sr = true;
 				break;
 			}
+			set_mask_bits(&bh->b_state, clear_bits, set_bits);
 			if (bh->b_folio != fs_folio) {
 				nilfs_end_folio_io(fs_folio, 0);
 				fs_folio = bh->b_folio;

fs/proc/array.c

@@ -477,13 +477,13 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	int permitted;
 	struct mm_struct *mm;
 	unsigned long long start_time;
-	unsigned long cmin_flt = 0, cmaj_flt = 0;
-	unsigned long  min_flt = 0,  maj_flt = 0;
-	u64 cutime, cstime, utime, stime;
-	u64 cgtime, gtime;
+	unsigned long cmin_flt, cmaj_flt, min_flt, maj_flt;
+	u64 cutime, cstime, cgtime, utime, stime, gtime;
 	unsigned long rsslim = 0;
 	unsigned long flags;
 	int exit_code = task->exit_code;
+	struct signal_struct *sig = task->signal;
+	unsigned int seq = 1;
 
 	state = *get_task_state(task);
 	vsize = eip = esp = 0;
@@ -511,12 +511,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
 	sigemptyset(&sigign);
 	sigemptyset(&sigcatch);
-	cutime = cstime = utime = stime = 0;
-	cgtime = gtime = 0;
 
 	if (lock_task_sighand(task, &flags)) {
-		struct signal_struct *sig = task->signal;
-
 		if (sig->tty) {
 			struct pid *pgrp = tty_get_pgrp(sig->tty);
 			tty_pgrp = pid_nr_ns(pgrp, ns);
@@ -527,28 +523,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 		num_threads = get_nr_threads(task);
 		collect_sigign_sigcatch(task, &sigign, &sigcatch);
 
-		cmin_flt = sig->cmin_flt;
-		cmaj_flt = sig->cmaj_flt;
-		cutime = sig->cutime;
-		cstime = sig->cstime;
-		cgtime = sig->cgtime;
 		rsslim = READ_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur);
 
-		/* add up live thread stats at the group level */
 		if (whole) {
-			struct task_struct *t;
-
-			__for_each_thread(sig, t) {
-				min_flt += t->min_flt;
-				maj_flt += t->maj_flt;
-				gtime += task_gtime(t);
-			}
-
-			min_flt += sig->min_flt;
-			maj_flt += sig->maj_flt;
-			thread_group_cputime_adjusted(task, &utime, &stime);
-			gtime += sig->gtime;
-
 			if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED))
 				exit_code = sig->group_exit_code;
 		}
@@ -562,10 +539,41 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
 	if (permitted && (!whole || num_threads < 2))
 		wchan = !task_is_running(task);
-	if (!whole) {
+
+	do {
+		seq++; /* 2 on the 1st/lockless path, otherwise odd */
+		flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
+
+		cmin_flt = sig->cmin_flt;
+		cmaj_flt = sig->cmaj_flt;
+		cutime = sig->cutime;
+		cstime = sig->cstime;
+		cgtime = sig->cgtime;
+
+		if (whole) {
+			struct task_struct *t;
+
+			min_flt = sig->min_flt;
+			maj_flt = sig->maj_flt;
+			gtime = sig->gtime;
+
+			rcu_read_lock();
+			__for_each_thread(sig, t) {
+				min_flt += t->min_flt;
+				maj_flt += t->maj_flt;
+				gtime += task_gtime(t);
+			}
+			rcu_read_unlock();
+		}
+	} while (need_seqretry(&sig->stats_lock, seq));
+	done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
+
+	if (whole) {
+		thread_group_cputime_adjusted(task, &utime, &stime);
+	} else {
+		task_cputime_adjusted(task, &utime, &stime);
 		min_flt = task->min_flt;
 		maj_flt = task->maj_flt;
-		task_cputime_adjusted(task, &utime, &stime);
 		gtime = task_gtime(task);
 	}
 

kernel/exit.c

@@ -1127,17 +1127,14 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		 * and nobody can change them.
 		 *
 		 * psig->stats_lock also protects us from our sub-threads
-		 * which can reap other children at the same time. Until
-		 * we change k_getrusage()-like users to rely on this lock
-		 * we have to take ->siglock as well.
+		 * which can reap other children at the same time.
 		 *
 		 * We use thread_group_cputime_adjusted() to get times for
 		 * the thread group, which consolidates times for all threads
 		 * in the group including the group leader.
 		 */
 		thread_group_cputime_adjusted(p, &tgutime, &tgstime);
-		spin_lock_irq(&current->sighand->siglock);
-		write_seqlock(&psig->stats_lock);
+		write_seqlock_irq(&psig->stats_lock);
 		psig->cutime += tgutime + sig->cutime;
 		psig->cstime += tgstime + sig->cstime;
 		psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime;
@@ -1160,8 +1157,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 			psig->cmaxrss = maxrss;
 		task_io_accounting_add(&psig->ioac, &p->ioac);
 		task_io_accounting_add(&psig->ioac, &sig->ioac);
-		write_sequnlock(&psig->stats_lock);
-		spin_unlock_irq(&current->sighand->siglock);
+		write_sequnlock_irq(&psig->stats_lock);
 	}
 
 	if (wo->wo_rusage)

kernel/sys.c

@@ -1785,21 +1785,24 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 	struct task_struct *t;
 	unsigned long flags;
 	u64 tgutime, tgstime, utime, stime;
-	unsigned long maxrss = 0;
+	unsigned long maxrss;
+	struct mm_struct *mm;
 	struct signal_struct *sig = p->signal;
+	unsigned int seq = 0;
 
-	memset((char *)r, 0, sizeof (*r));
+retry:
+	memset(r, 0, sizeof(*r));
 	utime = stime = 0;
+	maxrss = 0;
 
 	if (who == RUSAGE_THREAD) {
 		task_cputime_adjusted(current, &utime, &stime);
 		accumulate_thread_rusage(p, r);
 		maxrss = sig->maxrss;
-		goto out;
+		goto out_thread;
 	}
 
-	if (!lock_task_sighand(p, &flags))
-		return;
+	flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
 
 	switch (who) {
 	case RUSAGE_BOTH:
@@ -1819,9 +1822,6 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 		fallthrough;
 
 	case RUSAGE_SELF:
-		thread_group_cputime_adjusted(p, &tgutime, &tgstime);
-		utime += tgutime;
-		stime += tgstime;
 		r->ru_nvcsw += sig->nvcsw;
 		r->ru_nivcsw += sig->nivcsw;
 		r->ru_minflt += sig->min_flt;
@@ -1830,28 +1830,42 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 		r->ru_oublock += sig->oublock;
 		if (maxrss < sig->maxrss)
 			maxrss = sig->maxrss;
+
+		rcu_read_lock();
 		__for_each_thread(sig, t)
 			accumulate_thread_rusage(t, r);
+		rcu_read_unlock();
+
 		break;
 
 	default:
 		BUG();
 	}
-	unlock_task_sighand(p, &flags);
 
-out:
-	r->ru_utime = ns_to_kernel_old_timeval(utime);
-	r->ru_stime = ns_to_kernel_old_timeval(stime);
+	if (need_seqretry(&sig->stats_lock, seq)) {
+		seq = 1;
+		goto retry;
+	}
+	done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
 
-	if (who != RUSAGE_CHILDREN) {
-		struct mm_struct *mm = get_task_mm(p);
+	if (who == RUSAGE_CHILDREN)
+		goto out_children;
 
-		if (mm) {
-			setmax_mm_hiwater_rss(&maxrss, mm);
-			mmput(mm);
-		}
+	thread_group_cputime_adjusted(p, &tgutime, &tgstime);
+	utime += tgutime;
+	stime += tgstime;
+
+out_thread:
+	mm = get_task_mm(p);
+	if (mm) {
+		setmax_mm_hiwater_rss(&maxrss, mm);
+		mmput(mm);
 	}
+
+out_children:
 	r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */
+	r->ru_utime = ns_to_kernel_old_timeval(utime);
+	r->ru_stime = ns_to_kernel_old_timeval(stime);
 }
 
 SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru)

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);
 	}
 }
 

mm/madvise.c

@@ -429,6 +429,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
 		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;

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);

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;

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 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 	}
 
 	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 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 	}
 
 	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 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 			 * 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;

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;
 	}

tools/testing/selftests/core/close_range_test.c

@@ -12,6 +12,7 @@
 #include <syscall.h>
 #include <unistd.h>
 #include <sys/resource.h>
+#include <linux/close_range.h>
 
 #include "../kselftest_harness.h"
 #include "../clone3/clone3_selftests.h"