Merge tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull mm updates from Andrew Morton:

 - Yosry Ahmed brought back some cgroup v1 stats in OOM logs

 - Yosry has also eliminated cgroup's atomic rstat flushing

 - Nhat Pham adds the new cachestat() syscall. It provides userspace
   with the ability to query pagecache status - a similar concept to
   mincore() but more powerful and with improved usability

 - Mel Gorman provides more optimizations for compaction, reducing the
   prevalence of page rescanning

 - Lorenzo Stoakes has done some maintanance work on the
   get_user_pages() interface

 - Liam Howlett continues with cleanups and maintenance work to the
   maple tree code. Peng Zhang also does some work on maple tree

 - Johannes Weiner has done some cleanup work on the compaction code

 - David Hildenbrand has contributed additional selftests for
   get_user_pages()

 - Thomas Gleixner has contributed some maintenance and optimization
   work for the vmalloc code

 - Baolin Wang has provided some compaction cleanups,

 - SeongJae Park continues maintenance work on the DAMON code

 - Huang Ying has done some maintenance on the swap code's usage of
   device refcounting

 - Christoph Hellwig has some cleanups for the filemap/directio code

 - Ryan Roberts provides two patch series which yield some
   rationalization of the kernel's access to pte entries - use the
   provided APIs rather than open-coding accesses

 - Lorenzo Stoakes has some fixes to the interaction between pagecache
   and directio access to file mappings

 - John Hubbard has a series of fixes to the MM selftesting code

 - ZhangPeng continues the folio conversion campaign

 - Hugh Dickins has been working on the pagetable handling code, mainly
   with a view to reducing the load on the mmap_lock

 - Catalin Marinas has reduced the arm64 kmalloc() minimum alignment
   from 128 to 8

 - Domenico Cerasuolo has improved the zswap reclaim mechanism by
   reorganizing the LRU management

 - Matthew Wilcox provides some fixups to make gfs2 work better with the
   buffer_head code

 - Vishal Moola also has done some folio conversion work

 - Matthew Wilcox has removed the remnants of the pagevec code - their
   functionality is migrated over to struct folio_batch

* tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (380 commits)
  mm/hugetlb: remove hugetlb_set_page_subpool()
  mm: nommu: correct the range of mmap_sem_read_lock in task_mem()
  hugetlb: revert use of page_cache_next_miss()
  Revert "page cache: fix page_cache_next/prev_miss off by one"
  mm/vmscan: fix root proactive reclaim unthrottling unbalanced node
  mm: memcg: rename and document global_reclaim()
  mm: kill [add|del]_page_to_lru_list()
  mm: compaction: convert to use a folio in isolate_migratepages_block()
  mm: zswap: fix double invalidate with exclusive loads
  mm: remove unnecessary pagevec includes
  mm: remove references to pagevec
  mm: rename invalidate_mapping_pagevec to mapping_try_invalidate
  mm: remove struct pagevec
  net: convert sunrpc from pagevec to folio_batch
  i915: convert i915_gpu_error to use a folio_batch
  pagevec: rename fbatch_count()
  mm: remove check_move_unevictable_pages()
  drm: convert drm_gem_put_pages() to use a folio_batch
  i915: convert shmem_sg_free_table() to use a folio_batch
  scatterlist: add sg_set_folio()
  ...

13 files changed, 111 insertions, 101 deletions

diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 9c4c55228567..2542c21b6b6d 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -171,7 +171,7 @@ __weak noinline void bpf_rstat_flush(struct cgroup *cgrp,
 __diag_pop();
 
 /* see cgroup_rstat_flush() */
-static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep)
+static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
 	__releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock)
 {
 	int cpu;
@@ -207,9 +207,8 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep)
 		}
 		raw_spin_unlock_irqrestore(cpu_lock, flags);
 
-		/* if @may_sleep, play nice and yield if necessary */
-		if (may_sleep && (need_resched() ||
-				  spin_needbreak(&cgroup_rstat_lock))) {
+		/* play nice and yield if necessary */
+		if (need_resched() || spin_needbreak(&cgroup_rstat_lock)) {
 			spin_unlock_irq(&cgroup_rstat_lock);
 			if (!cond_resched())
 				cpu_relax();
@@ -236,26 +235,11 @@ __bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp)
 	might_sleep();
 
 	spin_lock_irq(&cgroup_rstat_lock);
-	cgroup_rstat_flush_locked(cgrp, true);
+	cgroup_rstat_flush_locked(cgrp);
 	spin_unlock_irq(&cgroup_rstat_lock);
 }
 
 /**
- * cgroup_rstat_flush_atomic- atomic version of cgroup_rstat_flush()
- * @cgrp: target cgroup
- *
- * This function can be called from any context.
- */
-void cgroup_rstat_flush_atomic(struct cgroup *cgrp)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&cgroup_rstat_lock, flags);
-	cgroup_rstat_flush_locked(cgrp, false);
-	spin_unlock_irqrestore(&cgroup_rstat_lock, flags);
-}
-
-/**
  * cgroup_rstat_flush_hold - flush stats in @cgrp's subtree and hold
  * @cgrp: target cgroup
  *
@@ -269,7 +253,7 @@ void cgroup_rstat_flush_hold(struct cgroup *cgrp)
 {
 	might_sleep();
 	spin_lock_irq(&cgroup_rstat_lock);
-	cgroup_rstat_flush_locked(cgrp, true);
+	cgroup_rstat_flush_locked(cgrp);
 }
 
 /**
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 6677d0e64d27..abea1823fe21 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -24,6 +24,9 @@ config DMA_OPS_BYPASS
 config ARCH_HAS_DMA_MAP_DIRECT
 	bool
 
+config NEED_SG_DMA_FLAGS
+	bool
+
 config NEED_SG_DMA_LENGTH
 	bool
 
@@ -87,6 +90,10 @@ config SWIOTLB
 	bool
 	select NEED_DMA_MAP_STATE
 
+config DMA_BOUNCE_UNALIGNED_KMALLOC
+	bool
+	depends on SWIOTLB
+
 config DMA_RESTRICTED_POOL
 	bool "DMA Restricted Pool"
 	depends on OF && OF_RESERVED_MEM && SWIOTLB
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 5595d1d5cdcc..d29cade048db 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -463,7 +463,7 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 	int i;
 
 	for_each_sg(sgl,  sg, nents, i) {
-		if (sg_is_dma_bus_address(sg))
+		if (sg_dma_is_bus_address(sg))
 			sg_dma_unmark_bus_address(sg);
 		else
 			dma_direct_unmap_page(dev, sg->dma_address,
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index e38ffc5e6bdd..97ec892ea0b5 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -94,7 +94,8 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev,
 		return swiotlb_map(dev, phys, size, dir, attrs);
 	}
 
-	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+	if (unlikely(!dma_capable(dev, dma_addr, size, true)) ||
+	    dma_kmalloc_needs_bounce(dev, size, dir)) {
 		if (is_pci_p2pdma_page(page))
 			return DMA_MAPPING_ERROR;
 		if (is_swiotlb_active(dev))
diff --git a/kernel/events/core.c b/kernel/events/core.c
index b2f1053d61b2..3060427f6c9e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7490,6 +7490,7 @@ static u64 perf_get_pgtable_size(struct mm_struct *mm, unsigned long addr)
 		return pud_leaf_size(pud);
 
 	pmdp = pmd_offset_lockless(pudp, pud, addr);
+again:
 	pmd = pmdp_get_lockless(pmdp);
 	if (!pmd_present(pmd))
 		return 0;
@@ -7498,6 +7499,9 @@ static u64 perf_get_pgtable_size(struct mm_struct *mm, unsigned long addr)
 		return pmd_leaf_size(pmd);
 
 	ptep = pte_offset_map(&pmd, addr);
+	if (!ptep)
+		goto again;
+
 	pte = ptep_get_lockless(ptep);
 	if (pte_present(pte))
 		size = pte_leaf_size(pte);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 59887c69d54c..f0ac5b874919 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -192,7 +192,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 		inc_mm_counter(mm, MM_ANONPAGES);
 	}
 
-	flush_cache_page(vma, addr, pte_pfn(*pvmw.pte));
+	flush_cache_page(vma, addr, pte_pfn(ptep_get(pvmw.pte)));
 	ptep_clear_flush_notify(vma, addr, pvmw.pte);
 	if (new_page)
 		set_pte_at_notify(mm, addr, pvmw.pte,
@@ -365,7 +365,6 @@ __update_ref_ctr(struct mm_struct *mm, unsigned long vaddr, short d)
 {
 	void *kaddr;
 	struct page *page;
-	struct vm_area_struct *vma;
 	int ret;
 	short *ptr;
 
@@ -373,7 +372,7 @@ __update_ref_ctr(struct mm_struct *mm, unsigned long vaddr, short d)
 		return -EINVAL;
 
 	ret = get_user_pages_remote(mm, vaddr, 1,
-			FOLL_WRITE, &page, &vma, NULL);
+				    FOLL_WRITE, &page, NULL);
 	if (unlikely(ret <= 0)) {
 		/*
 		 * We are asking for 1 page. If get_user_pages_remote() fails,
@@ -474,10 +473,9 @@ retry:
 	if (is_register)
 		gup_flags |= FOLL_SPLIT_PMD;
 	/* Read the page with vaddr into memory */
-	ret = get_user_pages_remote(mm, vaddr, 1, gup_flags,
-				    &old_page, &vma, NULL);
-	if (ret <= 0)
-		return ret;
+	old_page = get_user_page_vma_remote(mm, vaddr, gup_flags, &vma);
+	if (IS_ERR_OR_NULL(old_page))
+		return old_page ? PTR_ERR(old_page) : 0;
 
 	ret = verify_opcode(old_page, vaddr, &opcode);
 	if (ret <= 0)
@@ -2027,8 +2025,7 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr)
 	 * but we treat this as a 'remote' access since it is
 	 * essentially a kernel access to the memory.
 	 */
-	result = get_user_pages_remote(mm, vaddr, 1, FOLL_FORCE, &page,
-			NULL, NULL);
+	result = get_user_pages_remote(mm, vaddr, 1, FOLL_FORCE, &page, NULL);
 	if (result < 0)
 		return result;
 
diff --git a/kernel/pid_sysctl.h b/kernel/pid_sysctl.h
index d67a4d45bb42..b26e027fc9cd 100644
--- a/kernel/pid_sysctl.h
+++ b/kernel/pid_sysctl.h
@@ -52,7 +52,6 @@ static inline void register_pid_ns_sysctl_table_vm(void)
 }
 #else
 static inline void initialize_memfd_noexec_scope(struct pid_namespace *ns) {}
-static inline void set_memfd_noexec_scope(struct pid_namespace *ns) {}
 static inline void register_pid_ns_sysctl_table_vm(void) {}
 #endif
 
diff --git a/kernel/power/main.c b/kernel/power/main.c
index daa535012e51..f6425ae3e8b0 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -21,6 +21,33 @@
 #include "power.h"
 
 #ifdef CONFIG_PM_SLEEP
+/*
+ * The following functions are used by the suspend/hibernate code to temporarily
+ * change gfp_allowed_mask in order to avoid using I/O during memory allocations
+ * while devices are suspended.  To avoid races with the suspend/hibernate code,
+ * they should always be called with system_transition_mutex held
+ * (gfp_allowed_mask also should only be modified with system_transition_mutex
+ * held, unless the suspend/hibernate code is guaranteed not to run in parallel
+ * with that modification).
+ */
+static gfp_t saved_gfp_mask;
+
+void pm_restore_gfp_mask(void)
+{
+	WARN_ON(!mutex_is_locked(&system_transition_mutex));
+	if (saved_gfp_mask) {
+		gfp_allowed_mask = saved_gfp_mask;
+		saved_gfp_mask = 0;
+	}
+}
+
+void pm_restrict_gfp_mask(void)
+{
+	WARN_ON(!mutex_is_locked(&system_transition_mutex));
+	WARN_ON(saved_gfp_mask);
+	saved_gfp_mask = gfp_allowed_mask;
+	gfp_allowed_mask &= ~(__GFP_IO | __GFP_FS);
+}
 
 unsigned int lock_system_sleep(void)
 {
diff --git a/kernel/power/power.h b/kernel/power/power.h
index f4a380b1aa00..46eb14dc50c3 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -210,6 +210,11 @@ static inline void suspend_test_finish(const char *label) {}
 /* kernel/power/main.c */
 extern int pm_notifier_call_chain_robust(unsigned long val_up, unsigned long val_down);
 extern int pm_notifier_call_chain(unsigned long val);
+void pm_restrict_gfp_mask(void);
+void pm_restore_gfp_mask(void);
+#else
+static inline void pm_restrict_gfp_mask(void) {}
+static inline void pm_restore_gfp_mask(void) {}
 #endif
 
 #ifdef CONFIG_HIGHMEM
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index b27affb7503f..0415d5ecb977 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1228,6 +1228,58 @@ unsigned int snapshot_additional_pages(struct zone *zone)
 	return 2 * rtree;
 }
 
+/*
+ * Touch the watchdog for every WD_PAGE_COUNT pages.
+ */
+#define WD_PAGE_COUNT	(128*1024)
+
+static void mark_free_pages(struct zone *zone)
+{
+	unsigned long pfn, max_zone_pfn, page_count = WD_PAGE_COUNT;
+	unsigned long flags;
+	unsigned int order, t;
+	struct page *page;
+
+	if (zone_is_empty(zone))
+		return;
+
+	spin_lock_irqsave(&zone->lock, flags);
+
+	max_zone_pfn = zone_end_pfn(zone);
+	for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
+		if (pfn_valid(pfn)) {
+			page = pfn_to_page(pfn);
+
+			if (!--page_count) {
+				touch_nmi_watchdog();
+				page_count = WD_PAGE_COUNT;
+			}
+
+			if (page_zone(page) != zone)
+				continue;
+
+			if (!swsusp_page_is_forbidden(page))
+				swsusp_unset_page_free(page);
+		}
+
+	for_each_migratetype_order(order, t) {
+		list_for_each_entry(page,
+				&zone->free_area[order].free_list[t], buddy_list) {
+			unsigned long i;
+
+			pfn = page_to_pfn(page);
+			for (i = 0; i < (1UL << order); i++) {
+				if (!--page_count) {
+					touch_nmi_watchdog();
+					page_count = WD_PAGE_COUNT;
+				}
+				swsusp_set_page_free(pfn_to_page(pfn + i));
+			}
+		}
+	}
+	spin_unlock_irqrestore(&zone->lock, flags);
+}
+
 #ifdef CONFIG_HIGHMEM
 /**
  * count_free_highmem_pages - Compute the total number of free highmem pages.
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 860b2dcf3ac4..04bfb1e4d377 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -299,6 +299,7 @@ COND_SYSCALL(set_mempolicy);
 COND_SYSCALL(migrate_pages);
 COND_SYSCALL(move_pages);
 COND_SYSCALL(set_mempolicy_home_node);
+COND_SYSCALL(cachestat);
 
 COND_SYSCALL(perf_event_open);
 COND_SYSCALL(accept4);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index bfe53e835524..a57de67f032f 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2120,13 +2120,6 @@ static struct ctl_table vm_table[] = {
 	},
 #endif
 	{
-		.procname	= "lowmem_reserve_ratio",
-		.data		= &sysctl_lowmem_reserve_ratio,
-		.maxlen		= sizeof(sysctl_lowmem_reserve_ratio),
-		.mode		= 0644,
-		.proc_handler	= lowmem_reserve_ratio_sysctl_handler,
-	},
-	{
 		.procname	= "drop_caches",
 		.data		= &sysctl_drop_caches,
 		.maxlen		= sizeof(int),
@@ -2136,39 +2129,6 @@ static struct ctl_table vm_table[] = {
 		.extra2		= SYSCTL_FOUR,
 	},
 	{
-		.procname	= "min_free_kbytes",
-		.data		= &min_free_kbytes,
-		.maxlen		= sizeof(min_free_kbytes),
-		.mode		= 0644,
-		.proc_handler	= min_free_kbytes_sysctl_handler,
-		.extra1		= SYSCTL_ZERO,
-	},
-	{
-		.procname	= "watermark_boost_factor",
-		.data		= &watermark_boost_factor,
-		.maxlen		= sizeof(watermark_boost_factor),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
-	},
-	{
-		.procname	= "watermark_scale_factor",
-		.data		= &watermark_scale_factor,
-		.maxlen		= sizeof(watermark_scale_factor),
-		.mode		= 0644,
-		.proc_handler	= watermark_scale_factor_sysctl_handler,
-		.extra1		= SYSCTL_ONE,
-		.extra2		= SYSCTL_THREE_THOUSAND,
-	},
-	{
-		.procname	= "percpu_pagelist_high_fraction",
-		.data		= &percpu_pagelist_high_fraction,
-		.maxlen		= sizeof(percpu_pagelist_high_fraction),
-		.mode		= 0644,
-		.proc_handler	= percpu_pagelist_high_fraction_sysctl_handler,
-		.extra1		= SYSCTL_ZERO,
-	},
-	{
 		.procname	= "page_lock_unfairness",
 		.data		= &sysctl_page_lock_unfairness,
 		.maxlen		= sizeof(sysctl_page_lock_unfairness),
@@ -2223,24 +2183,6 @@ static struct ctl_table vm_table[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
 	},
-	{
-		.procname	= "min_unmapped_ratio",
-		.data		= &sysctl_min_unmapped_ratio,
-		.maxlen		= sizeof(sysctl_min_unmapped_ratio),
-		.mode		= 0644,
-		.proc_handler	= sysctl_min_unmapped_ratio_sysctl_handler,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE_HUNDRED,
-	},
-	{
-		.procname	= "min_slab_ratio",
-		.data		= &sysctl_min_slab_ratio,
-		.maxlen		= sizeof(sysctl_min_slab_ratio),
-		.mode		= 0644,
-		.proc_handler	= sysctl_min_slab_ratio_sysctl_handler,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE_HUNDRED,
-	},
 #endif
 #ifdef CONFIG_SMP
 	{
@@ -2267,15 +2209,6 @@ static struct ctl_table vm_table[] = {
 		.proc_handler	= mmap_min_addr_handler,
 	},
 #endif
-#ifdef CONFIG_NUMA
-	{
-		.procname	= "numa_zonelist_order",
-		.data		= &numa_zonelist_order,
-		.maxlen		= NUMA_ZONELIST_ORDER_LEN,
-		.mode		= 0644,
-		.proc_handler	= numa_zonelist_order_handler,
-	},
-#endif
 #if (defined(CONFIG_X86_32) && !defined(CONFIG_UML))|| \
    (defined(CONFIG_SUPERH) && defined(CONFIG_VSYSCALL))
 	{
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 8df0550415e7..0536db7fef61 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -498,7 +498,7 @@ static int user_event_enabler_write(struct user_event_mm *mm,
 		return -EBUSY;
 
 	ret = pin_user_pages_remote(mm->mm, uaddr, 1, FOLL_WRITE | FOLL_NOFAULT,
-				    &page, NULL, NULL);
+				    &page, NULL);
 
 	if (unlikely(ret <= 0)) {
 		if (!fixup_fault)