Merge tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:
 "Almost all of MM here. A few things are still getting finished off,
  reviewed, etc.

   - Yang Shi has improved the behaviour of khugepaged collapsing of
     readonly file-backed transparent hugepages.

   - Johannes Weiner has arranged for zswap memory use to be tracked and
     managed on a per-cgroup basis.

   - Munchun Song adds a /proc knob ("hugetlb_optimize_vmemmap") for
     runtime enablement of the recent huge page vmemmap optimization
     feature.

   - Baolin Wang contributes a series to fix some issues around hugetlb
     pagetable invalidation.

   - Zhenwei Pi has fixed some interactions between hwpoisoned pages and
     virtualization.

   - Tong Tiangen has enabled the use of the presently x86-only
     page_table_check debugging feature on arm64 and riscv.

   - David Vernet has done some fixup work on the memcg selftests.

   - Peter Xu has taught userfaultfd to handle write protection faults
     against shmem- and hugetlbfs-backed files.

   - More DAMON development from SeongJae Park - adding online tuning of
     the feature and support for monitoring of fixed virtual address
     ranges. Also easier discovery of which monitoring operations are
     available.

   - Nadav Amit has done some optimization of TLB flushing during
     mprotect().

   - Neil Brown continues to labor away at improving our swap-over-NFS
     support.

   - David Hildenbrand has some fixes to anon page COWing versus
     get_user_pages().

   - Peng Liu fixed some errors in the core hugetlb code.

   - Joao Martins has reduced the amount of memory consumed by
     device-dax's compound devmaps.

   - Some cleanups of the arch-specific pagemap code from Anshuman
     Khandual.

   - Muchun Song has found and fixed some errors in the TLB flushing of
     transparent hugepages.

   - Roman Gushchin has done more work on the memcg selftests.

  ... and, of course, many smaller fixes and cleanups. Notably, the
  customary million cleanup serieses from Miaohe Lin"

* tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (381 commits)
  mm: kfence: use PAGE_ALIGNED helper
  selftests: vm: add the "settings" file with timeout variable
  selftests: vm: add "test_hmm.sh" to TEST_FILES
  selftests: vm: check numa_available() before operating "merge_across_nodes" in ksm_tests
  selftests: vm: add migration to the .gitignore
  selftests/vm/pkeys: fix typo in comment
  ksm: fix typo in comment
  selftests: vm: add process_mrelease tests
  Revert "mm/vmscan: never demote for memcg reclaim"
  mm/kfence: print disabling or re-enabling message
  include/trace/events/percpu.h: cleanup for "percpu: improve percpu_alloc_percpu event trace"
  include/trace/events/mmflags.h: cleanup for "tracing: incorrect gfp_t conversion"
  mm: fix a potential infinite loop in start_isolate_page_range()
  MAINTAINERS: add Muchun as co-maintainer for HugeTLB
  zram: fix Kconfig dependency warning
  mm/shmem: fix shmem folio swapoff hang
  cgroup: fix an error handling path in alloc_pagecache_max_30M()
  mm: damon: use HPAGE_PMD_SIZE
  tracing: incorrect isolate_mote_t cast in mm_vmscan_lru_isolate
  nodemask.h: fix compilation error with GCC12
  ...

6 files changed, 89 insertions, 72 deletions

diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 290f07eb050a..9ae94ef3e270 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -1344,13 +1344,13 @@ TRACE_EVENT(alloc_extent_state,
 
 	TP_STRUCT__entry(
 		__field(const struct extent_state *, state)
-		__field(gfp_t, mask)
+		__field(unsigned long, mask)
 		__field(const void*, ip)
 	),
 
 	TP_fast_assign(
 		__entry->state	= state,
-		__entry->mask	= mask,
+		__entry->mask	= (__force unsigned long)mask,
 		__entry->ip	= (const void *)IP
 	),
 
diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index c6d5d70dc7a5..3313eb83c117 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -162,13 +162,13 @@ TRACE_EVENT(mm_compaction_try_to_compact_pages,
 
 	TP_STRUCT__entry(
 		__field(int, order)
-		__field(gfp_t, gfp_mask)
+		__field(unsigned long, gfp_mask)
 		__field(int, prio)
 	),
 
 	TP_fast_assign(
 		__entry->order = order;
-		__entry->gfp_mask = gfp_mask;
+		__entry->gfp_mask = (__force unsigned long)gfp_mask;
 		__entry->prio = prio;
 	),
 
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index ddc8c944f417..f76668305ac5 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -24,7 +24,7 @@ DECLARE_EVENT_CLASS(kmem_alloc,
 		__field(	const void *,	ptr		)
 		__field(	size_t,		bytes_req	)
 		__field(	size_t,		bytes_alloc	)
-		__field(	gfp_t,		gfp_flags	)
+		__field(	unsigned long,	gfp_flags	)
 	),
 
 	TP_fast_assign(
@@ -32,7 +32,7 @@ DECLARE_EVENT_CLASS(kmem_alloc,
 		__entry->ptr		= ptr;
 		__entry->bytes_req	= bytes_req;
 		__entry->bytes_alloc	= bytes_alloc;
-		__entry->gfp_flags	= gfp_flags;
+		__entry->gfp_flags	= (__force unsigned long)gfp_flags;
 	),
 
 	TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s",
@@ -75,7 +75,7 @@ DECLARE_EVENT_CLASS(kmem_alloc_node,
 		__field(	const void *,	ptr		)
 		__field(	size_t,		bytes_req	)
 		__field(	size_t,		bytes_alloc	)
-		__field(	gfp_t,		gfp_flags	)
+		__field(	unsigned long,	gfp_flags	)
 		__field(	int,		node		)
 	),
 
@@ -84,7 +84,7 @@ DECLARE_EVENT_CLASS(kmem_alloc_node,
 		__entry->ptr		= ptr;
 		__entry->bytes_req	= bytes_req;
 		__entry->bytes_alloc	= bytes_alloc;
-		__entry->gfp_flags	= gfp_flags;
+		__entry->gfp_flags	= (__force unsigned long)gfp_flags;
 		__entry->node		= node;
 	),
 
@@ -208,14 +208,14 @@ TRACE_EVENT(mm_page_alloc,
 	TP_STRUCT__entry(
 		__field(	unsigned long,	pfn		)
 		__field(	unsigned int,	order		)
-		__field(	gfp_t,		gfp_flags	)
+		__field(	unsigned long,	gfp_flags	)
 		__field(	int,		migratetype	)
 	),
 
 	TP_fast_assign(
 		__entry->pfn		= page ? page_to_pfn(page) : -1UL;
 		__entry->order		= order;
-		__entry->gfp_flags	= gfp_flags;
+		__entry->gfp_flags	= (__force unsigned long)gfp_flags;
 		__entry->migratetype	= migratetype;
 	),
 
@@ -229,20 +229,23 @@ TRACE_EVENT(mm_page_alloc,
 
 DECLARE_EVENT_CLASS(mm_page,
 
-	TP_PROTO(struct page *page, unsigned int order, int migratetype),
+	TP_PROTO(struct page *page, unsigned int order, int migratetype,
+		 int percpu_refill),
 
-	TP_ARGS(page, order, migratetype),
+	TP_ARGS(page, order, migratetype, percpu_refill),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,	pfn		)
 		__field(	unsigned int,	order		)
 		__field(	int,		migratetype	)
+		__field(	int,		percpu_refill	)
 	),
 
 	TP_fast_assign(
 		__entry->pfn		= page ? page_to_pfn(page) : -1UL;
 		__entry->order		= order;
 		__entry->migratetype	= migratetype;
+		__entry->percpu_refill	= percpu_refill;
 	),
 
 	TP_printk("page=%p pfn=0x%lx order=%u migratetype=%d percpu_refill=%d",
@@ -250,14 +253,15 @@ DECLARE_EVENT_CLASS(mm_page,
 		__entry->pfn != -1UL ? __entry->pfn : 0,
 		__entry->order,
 		__entry->migratetype,
-		__entry->order == 0)
+		__entry->percpu_refill)
 );
 
 DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked,
 
-	TP_PROTO(struct page *page, unsigned int order, int migratetype),
+	TP_PROTO(struct page *page, unsigned int order, int migratetype,
+		 int percpu_refill),
 
-	TP_ARGS(page, order, migratetype)
+	TP_ARGS(page, order, migratetype, percpu_refill)
 );
 
 TRACE_EVENT(mm_page_pcpu_drain,
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 6532119a6bf1..e87cb2b80ed3 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -13,49 +13,51 @@
  * Thus most bits set go first.
  */
 
-#define __def_gfpflag_names						\
-	{(unsigned long)GFP_TRANSHUGE,		"GFP_TRANSHUGE"},	\
-	{(unsigned long)GFP_TRANSHUGE_LIGHT,	"GFP_TRANSHUGE_LIGHT"}, \
-	{(unsigned long)GFP_HIGHUSER_MOVABLE,	"GFP_HIGHUSER_MOVABLE"},\
-	{(unsigned long)GFP_HIGHUSER,		"GFP_HIGHUSER"},	\
-	{(unsigned long)GFP_USER,		"GFP_USER"},		\
-	{(unsigned long)GFP_KERNEL_ACCOUNT,	"GFP_KERNEL_ACCOUNT"},	\
-	{(unsigned long)GFP_KERNEL,		"GFP_KERNEL"},		\
-	{(unsigned long)GFP_NOFS,		"GFP_NOFS"},		\
-	{(unsigned long)GFP_ATOMIC,		"GFP_ATOMIC"},		\
-	{(unsigned long)GFP_NOIO,		"GFP_NOIO"},		\
-	{(unsigned long)GFP_NOWAIT,		"GFP_NOWAIT"},		\
-	{(unsigned long)GFP_DMA,		"GFP_DMA"},		\
-	{(unsigned long)__GFP_HIGHMEM,		"__GFP_HIGHMEM"},	\
-	{(unsigned long)GFP_DMA32,		"GFP_DMA32"},		\
-	{(unsigned long)__GFP_HIGH,		"__GFP_HIGH"},		\
-	{(unsigned long)__GFP_ATOMIC,		"__GFP_ATOMIC"},	\
-	{(unsigned long)__GFP_IO,		"__GFP_IO"},		\
-	{(unsigned long)__GFP_FS,		"__GFP_FS"},		\
-	{(unsigned long)__GFP_NOWARN,		"__GFP_NOWARN"},	\
-	{(unsigned long)__GFP_RETRY_MAYFAIL,	"__GFP_RETRY_MAYFAIL"},	\
-	{(unsigned long)__GFP_NOFAIL,		"__GFP_NOFAIL"},	\
-	{(unsigned long)__GFP_NORETRY,		"__GFP_NORETRY"},	\
-	{(unsigned long)__GFP_COMP,		"__GFP_COMP"},		\
-	{(unsigned long)__GFP_ZERO,		"__GFP_ZERO"},		\
-	{(unsigned long)__GFP_NOMEMALLOC,	"__GFP_NOMEMALLOC"},	\
-	{(unsigned long)__GFP_MEMALLOC,		"__GFP_MEMALLOC"},	\
-	{(unsigned long)__GFP_HARDWALL,		"__GFP_HARDWALL"},	\
-	{(unsigned long)__GFP_THISNODE,		"__GFP_THISNODE"},	\
-	{(unsigned long)__GFP_RECLAIMABLE,	"__GFP_RECLAIMABLE"},	\
-	{(unsigned long)__GFP_MOVABLE,		"__GFP_MOVABLE"},	\
-	{(unsigned long)__GFP_ACCOUNT,		"__GFP_ACCOUNT"},	\
-	{(unsigned long)__GFP_WRITE,		"__GFP_WRITE"},		\
-	{(unsigned long)__GFP_RECLAIM,		"__GFP_RECLAIM"},	\
-	{(unsigned long)__GFP_DIRECT_RECLAIM,	"__GFP_DIRECT_RECLAIM"},\
-	{(unsigned long)__GFP_KSWAPD_RECLAIM,	"__GFP_KSWAPD_RECLAIM"},\
-	{(unsigned long)__GFP_ZEROTAGS,		"__GFP_ZEROTAGS"}	\
+#define gfpflag_string(flag) {(__force unsigned long)flag, #flag}
+
+#define __def_gfpflag_names			\
+	gfpflag_string(GFP_TRANSHUGE),		\
+	gfpflag_string(GFP_TRANSHUGE_LIGHT),	\
+	gfpflag_string(GFP_HIGHUSER_MOVABLE),	\
+	gfpflag_string(GFP_HIGHUSER),		\
+	gfpflag_string(GFP_USER),		\
+	gfpflag_string(GFP_KERNEL_ACCOUNT),	\
+	gfpflag_string(GFP_KERNEL),		\
+	gfpflag_string(GFP_NOFS),		\
+	gfpflag_string(GFP_ATOMIC),		\
+	gfpflag_string(GFP_NOIO),		\
+	gfpflag_string(GFP_NOWAIT),		\
+	gfpflag_string(GFP_DMA),		\
+	gfpflag_string(__GFP_HIGHMEM),		\
+	gfpflag_string(GFP_DMA32),		\
+	gfpflag_string(__GFP_HIGH),		\
+	gfpflag_string(__GFP_ATOMIC),		\
+	gfpflag_string(__GFP_IO),		\
+	gfpflag_string(__GFP_FS),		\
+	gfpflag_string(__GFP_NOWARN),		\
+	gfpflag_string(__GFP_RETRY_MAYFAIL),	\
+	gfpflag_string(__GFP_NOFAIL),		\
+	gfpflag_string(__GFP_NORETRY),		\
+	gfpflag_string(__GFP_COMP),		\
+	gfpflag_string(__GFP_ZERO),		\
+	gfpflag_string(__GFP_NOMEMALLOC),	\
+	gfpflag_string(__GFP_MEMALLOC),		\
+	gfpflag_string(__GFP_HARDWALL),		\
+	gfpflag_string(__GFP_THISNODE),		\
+	gfpflag_string(__GFP_RECLAIMABLE),	\
+	gfpflag_string(__GFP_MOVABLE),		\
+	gfpflag_string(__GFP_ACCOUNT),		\
+	gfpflag_string(__GFP_WRITE),		\
+	gfpflag_string(__GFP_RECLAIM),		\
+	gfpflag_string(__GFP_DIRECT_RECLAIM),	\
+	gfpflag_string(__GFP_KSWAPD_RECLAIM),	\
+	gfpflag_string(__GFP_ZEROTAGS)
 
 #ifdef CONFIG_KASAN_HW_TAGS
-#define __def_gfpflag_names_kasan ,					       \
-	{(unsigned long)__GFP_SKIP_ZERO,	   "__GFP_SKIP_ZERO"},	       \
-	{(unsigned long)__GFP_SKIP_KASAN_POISON,   "__GFP_SKIP_KASAN_POISON"}, \
-	{(unsigned long)__GFP_SKIP_KASAN_UNPOISON, "__GFP_SKIP_KASAN_UNPOISON"}
+#define __def_gfpflag_names_kasan ,			\
+	gfpflag_string(__GFP_SKIP_ZERO),		\
+	gfpflag_string(__GFP_SKIP_KASAN_POISON),	\
+	gfpflag_string(__GFP_SKIP_KASAN_UNPOISON)
 #else
 #define __def_gfpflag_names_kasan
 #endif
diff --git a/include/trace/events/percpu.h b/include/trace/events/percpu.h
index df112a64f6c9..5b8211ca8950 100644
--- a/include/trace/events/percpu.h
+++ b/include/trace/events/percpu.h
@@ -6,15 +6,20 @@
 #define _TRACE_PERCPU_H
 
 #include <linux/tracepoint.h>
+#include <trace/events/mmflags.h>
 
 TRACE_EVENT(percpu_alloc_percpu,
 
-	TP_PROTO(bool reserved, bool is_atomic, size_t size,
-		 size_t align, void *base_addr, int off, void __percpu *ptr),
+	TP_PROTO(unsigned long call_site,
+		 bool reserved, bool is_atomic, size_t size,
+		 size_t align, void *base_addr, int off,
+		 void __percpu *ptr, size_t bytes_alloc, gfp_t gfp_flags),
 
-	TP_ARGS(reserved, is_atomic, size, align, base_addr, off, ptr),
+	TP_ARGS(call_site, reserved, is_atomic, size, align, base_addr, off,
+		ptr, bytes_alloc, gfp_flags),
 
 	TP_STRUCT__entry(
+		__field(	unsigned long,		call_site	)
 		__field(	bool,			reserved	)
 		__field(	bool,			is_atomic	)
 		__field(	size_t,			size		)
@@ -22,9 +27,11 @@ TRACE_EVENT(percpu_alloc_percpu,
 		__field(	void *,			base_addr	)
 		__field(	int,			off		)
 		__field(	void __percpu *,	ptr		)
+		__field(	size_t,			bytes_alloc	)
+		__field(	unsigned long,		gfp_flags	)
 	),
-
 	TP_fast_assign(
+		__entry->call_site	= call_site;
 		__entry->reserved	= reserved;
 		__entry->is_atomic	= is_atomic;
 		__entry->size		= size;
@@ -32,12 +39,16 @@ TRACE_EVENT(percpu_alloc_percpu,
 		__entry->base_addr	= base_addr;
 		__entry->off		= off;
 		__entry->ptr		= ptr;
+		__entry->bytes_alloc	= bytes_alloc;
+		__entry->gfp_flags	= (__force unsigned long)gfp_flags;
 	),
 
-	TP_printk("reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p",
+	TP_printk("call_site=%pS reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p bytes_alloc=%zu gfp_flags=%s",
+		  (void *)__entry->call_site,
 		  __entry->reserved, __entry->is_atomic,
 		  __entry->size, __entry->align,
-		  __entry->base_addr, __entry->off, __entry->ptr)
+		  __entry->base_addr, __entry->off, __entry->ptr,
+		  __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags))
 );
 
 TRACE_EVENT(percpu_free_percpu,
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index de136dbd623a..d2123dd960d5 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -96,14 +96,14 @@ TRACE_EVENT(mm_vmscan_wakeup_kswapd,
 		__field(	int,	nid		)
 		__field(	int,	zid		)
 		__field(	int,	order		)
-		__field(	gfp_t,	gfp_flags	)
+		__field(	unsigned long,	gfp_flags	)
 	),
 
 	TP_fast_assign(
 		__entry->nid		= nid;
 		__entry->zid		= zid;
 		__entry->order		= order;
-		__entry->gfp_flags	= gfp_flags;
+		__entry->gfp_flags	= (__force unsigned long)gfp_flags;
 	),
 
 	TP_printk("nid=%d order=%d gfp_flags=%s",
@@ -120,12 +120,12 @@ DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template,
 
 	TP_STRUCT__entry(
 		__field(	int,	order		)
-		__field(	gfp_t,	gfp_flags	)
+		__field(	unsigned long,	gfp_flags	)
 	),
 
 	TP_fast_assign(
 		__entry->order		= order;
-		__entry->gfp_flags	= gfp_flags;
+		__entry->gfp_flags	= (__force unsigned long)gfp_flags;
 	),
 
 	TP_printk("order=%d gfp_flags=%s",
@@ -210,7 +210,7 @@ TRACE_EVENT(mm_shrink_slab_start,
 		__field(void *, shrink)
 		__field(int, nid)
 		__field(long, nr_objects_to_shrink)
-		__field(gfp_t, gfp_flags)
+		__field(unsigned long, gfp_flags)
 		__field(unsigned long, cache_items)
 		__field(unsigned long long, delta)
 		__field(unsigned long, total_scan)
@@ -222,7 +222,7 @@ TRACE_EVENT(mm_shrink_slab_start,
 		__entry->shrink = shr->scan_objects;
 		__entry->nid = sc->nid;
 		__entry->nr_objects_to_shrink = nr_objects_to_shrink;
-		__entry->gfp_flags = sc->gfp_mask;
+		__entry->gfp_flags = (__force unsigned long)sc->gfp_mask;
 		__entry->cache_items = cache_items;
 		__entry->delta = delta;
 		__entry->total_scan = total_scan;
@@ -297,7 +297,7 @@ TRACE_EVENT(mm_vmscan_lru_isolate,
 		__field(unsigned long, nr_scanned)
 		__field(unsigned long, nr_skipped)
 		__field(unsigned long, nr_taken)
-		__field(isolate_mode_t, isolate_mode)
+		__field(unsigned int, isolate_mode)
 		__field(int, lru)
 	),
 
@@ -308,7 +308,7 @@ TRACE_EVENT(mm_vmscan_lru_isolate,
 		__entry->nr_scanned = nr_scanned;
 		__entry->nr_skipped = nr_skipped;
 		__entry->nr_taken = nr_taken;
-		__entry->isolate_mode = isolate_mode;
+		__entry->isolate_mode = (__force unsigned int)isolate_mode;
 		__entry->lru = lru;
 	),
 
@@ -446,13 +446,13 @@ TRACE_EVENT(mm_vmscan_node_reclaim_begin,
 	TP_STRUCT__entry(
 		__field(int, nid)
 		__field(int, order)
-		__field(gfp_t, gfp_flags)
+		__field(unsigned long, gfp_flags)
 	),
 
 	TP_fast_assign(
 		__entry->nid = nid;
 		__entry->order = order;
-		__entry->gfp_flags = gfp_flags;
+		__entry->gfp_flags = (__force unsigned long)gfp_flags;
 	),
 
 	TP_printk("nid=%d order=%d gfp_flags=%s",