Merge tag 'mm-stable-2022-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Yu Zhao's Multi-Gen LRU patches are here. They've been under test in
   linux-next for a couple of months without, to my knowledge, any
   negative reports (or any positive ones, come to that).

 - Also the Maple Tree from Liam Howlett. An overlapping range-based
   tree for vmas. It it apparently slightly more efficient in its own
   right, but is mainly targeted at enabling work to reduce mmap_lock
   contention.

   Liam has identified a number of other tree users in the kernel which
   could be beneficially onverted to mapletrees.

   Yu Zhao has identified a hard-to-hit but "easy to fix" lockdep splat
   at [1]. This has yet to be addressed due to Liam's unfortunately
   timed vacation. He is now back and we'll get this fixed up.

 - Dmitry Vyukov introduces KMSAN: the Kernel Memory Sanitizer. It uses
   clang-generated instrumentation to detect used-unintialized bugs down
   to the single bit level.

   KMSAN keeps finding bugs. New ones, as well as the legacy ones.

 - Yang Shi adds a userspace mechanism (madvise) to induce a collapse of
   memory into THPs.

 - Zach O'Keefe has expanded Yang Shi's madvise(MADV_COLLAPSE) to
   support file/shmem-backed pages.

 - userfaultfd updates from Axel Rasmussen

 - zsmalloc cleanups from Alexey Romanov

 - cleanups from Miaohe Lin: vmscan, hugetlb_cgroup, hugetlb and
   memory-failure

 - Huang Ying adds enhancements to NUMA balancing memory tiering mode's
   page promotion, with a new way of detecting hot pages.

 - memcg updates from Shakeel Butt: charging optimizations and reduced
   memory consumption.

 - memcg cleanups from Kairui Song.

 - memcg fixes and cleanups from Johannes Weiner.

 - Vishal Moola provides more folio conversions

 - Zhang Yi removed ll_rw_block() :(

 - migration enhancements from Peter Xu

 - migration error-path bugfixes from Huang Ying

 - Aneesh Kumar added ability for a device driver to alter the memory
   tiering promotion paths. For optimizations by PMEM drivers, DRM
   drivers, etc.

 - vma merging improvements from Jakub Matěn.

 - NUMA hinting cleanups from David Hildenbrand.

 - xu xin added aditional userspace visibility into KSM merging
   activity.

 - THP & KSM code consolidation from Qi Zheng.

 - more folio work from Matthew Wilcox.

 - KASAN updates from Andrey Konovalov.

 - DAMON cleanups from Kaixu Xia.

 - DAMON work from SeongJae Park: fixes, cleanups.

 - hugetlb sysfs cleanups from Muchun Song.

 - Mike Kravetz fixes locking issues in hugetlbfs and in hugetlb core.

Link: https://lkml.kernel.org/r/CAOUHufZabH85CeUN-MEMgL8gJGzJEWUrkiM58JkTbBhh-jew0Q@mail.gmail.com [1]

* tag 'mm-stable-2022-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (555 commits)
  hugetlb: allocate vma lock for all sharable vmas
  hugetlb: take hugetlb vma_lock when clearing vma_lock->vma pointer
  hugetlb: fix vma lock handling during split vma and range unmapping
  mglru: mm/vmscan.c: fix imprecise comments
  mm/mglru: don't sync disk for each aging cycle
  mm: memcontrol: drop dead CONFIG_MEMCG_SWAP config symbol
  mm: memcontrol: use do_memsw_account() in a few more places
  mm: memcontrol: deprecate swapaccounting=0 mode
  mm: memcontrol: don't allocate cgroup swap arrays when memcg is disabled
  mm/secretmem: remove reduntant return value
  mm/hugetlb: add available_huge_pages() func
  mm: remove unused inline functions from include/linux/mm_inline.h
  selftests/vm: add selftest for MADV_COLLAPSE of uffd-minor memory
  selftests/vm: add file/shmem MADV_COLLAPSE selftest for cleared pmd
  selftests/vm: add thp collapse shmem testing
  selftests/vm: add thp collapse file and tmpfs testing
  selftests/vm: modularize thp collapse memory operations
  selftests/vm: dedup THP helpers
  mm/khugepaged: add tracepoint to hpage_collapse_scan_file()
  mm/madvise: add file and shmem support to MADV_COLLAPSE
  ...

3 files changed, 233 insertions, 0 deletions

diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h
index d651f3437367..935af4947917 100644
--- a/include/trace/events/huge_memory.h
+++ b/include/trace/events/huge_memory.h
@@ -11,11 +11,14 @@
 	EM( SCAN_FAIL,			"failed")			\
 	EM( SCAN_SUCCEED,		"succeeded")			\
 	EM( SCAN_PMD_NULL,		"pmd_null")			\
+	EM( SCAN_PMD_NONE,		"pmd_none")			\
+	EM( SCAN_PMD_MAPPED,		"page_pmd_mapped")		\
 	EM( SCAN_EXCEED_NONE_PTE,	"exceed_none_pte")		\
 	EM( SCAN_EXCEED_SWAP_PTE,	"exceed_swap_pte")		\
 	EM( SCAN_EXCEED_SHARED_PTE,	"exceed_shared_pte")		\
 	EM( SCAN_PTE_NON_PRESENT,	"pte_non_present")		\
 	EM( SCAN_PTE_UFFD_WP,		"pte_uffd_wp")			\
+	EM( SCAN_PTE_MAPPED_HUGEPAGE,	"pte_mapped_hugepage")		\
 	EM( SCAN_PAGE_RO,		"no_writable_page")		\
 	EM( SCAN_LACK_REFERENCED_PAGE,	"lack_referenced_page")		\
 	EM( SCAN_PAGE_NULL,		"page_null")			\
@@ -166,5 +169,39 @@ TRACE_EVENT(mm_collapse_huge_page_swapin,
 		__entry->ret)
 );
 
+TRACE_EVENT(mm_khugepaged_scan_file,
+
+	TP_PROTO(struct mm_struct *mm, struct page *page, const char *filename,
+		 int present, int swap, int result),
+
+	TP_ARGS(mm, page, filename, present, swap, result),
+
+	TP_STRUCT__entry(
+		__field(struct mm_struct *, mm)
+		__field(unsigned long, pfn)
+		__string(filename, filename)
+		__field(int, present)
+		__field(int, swap)
+		__field(int, result)
+	),
+
+	TP_fast_assign(
+		__entry->mm = mm;
+		__entry->pfn = page ? page_to_pfn(page) : -1;
+		__assign_str(filename, filename);
+		__entry->present = present;
+		__entry->swap = swap;
+		__entry->result = result;
+	),
+
+	TP_printk("mm=%p, scan_pfn=0x%lx, filename=%s, present=%d, swap=%d, result=%s",
+		__entry->mm,
+		__entry->pfn,
+		__get_str(filename),
+		__entry->present,
+		__entry->swap,
+		__print_symbolic(__entry->result, SCAN_STATUS))
+);
+
 #endif /* __HUGE_MEMORY_H */
 #include <trace/define_trace.h>
diff --git a/include/trace/events/maple_tree.h b/include/trace/events/maple_tree.h
new file mode 100644
index 000000000000..2be403bdc2bd
--- /dev/null
+++ b/include/trace/events/maple_tree.h
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM maple_tree
+
+#if !defined(_TRACE_MM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MM_H
+
+
+#include <linux/tracepoint.h>
+
+struct ma_state;
+
+TRACE_EVENT(ma_op,
+
+	TP_PROTO(const char *fn, struct ma_state *mas),
+
+	TP_ARGS(fn, mas),
+
+	TP_STRUCT__entry(
+			__field(const char *, fn)
+			__field(unsigned long, min)
+			__field(unsigned long, max)
+			__field(unsigned long, index)
+			__field(unsigned long, last)
+			__field(void *, node)
+	),
+
+	TP_fast_assign(
+			__entry->fn		= fn;
+			__entry->min		= mas->min;
+			__entry->max		= mas->max;
+			__entry->index		= mas->index;
+			__entry->last		= mas->last;
+			__entry->node		= mas->node;
+	),
+
+	TP_printk("%s\tNode: %p (%lu %lu) range: %lu-%lu",
+		  __entry->fn,
+		  (void *) __entry->node,
+		  (unsigned long) __entry->min,
+		  (unsigned long) __entry->max,
+		  (unsigned long) __entry->index,
+		  (unsigned long) __entry->last
+	)
+)
+TRACE_EVENT(ma_read,
+
+	TP_PROTO(const char *fn, struct ma_state *mas),
+
+	TP_ARGS(fn, mas),
+
+	TP_STRUCT__entry(
+			__field(const char *, fn)
+			__field(unsigned long, min)
+			__field(unsigned long, max)
+			__field(unsigned long, index)
+			__field(unsigned long, last)
+			__field(void *, node)
+	),
+
+	TP_fast_assign(
+			__entry->fn		= fn;
+			__entry->min		= mas->min;
+			__entry->max		= mas->max;
+			__entry->index		= mas->index;
+			__entry->last		= mas->last;
+			__entry->node		= mas->node;
+	),
+
+	TP_printk("%s\tNode: %p (%lu %lu) range: %lu-%lu",
+		  __entry->fn,
+		  (void *) __entry->node,
+		  (unsigned long) __entry->min,
+		  (unsigned long) __entry->max,
+		  (unsigned long) __entry->index,
+		  (unsigned long) __entry->last
+	)
+)
+
+TRACE_EVENT(ma_write,
+
+	TP_PROTO(const char *fn, struct ma_state *mas, unsigned long piv,
+		 void *val),
+
+	TP_ARGS(fn, mas, piv, val),
+
+	TP_STRUCT__entry(
+			__field(const char *, fn)
+			__field(unsigned long, min)
+			__field(unsigned long, max)
+			__field(unsigned long, index)
+			__field(unsigned long, last)
+			__field(unsigned long, piv)
+			__field(void *, val)
+			__field(void *, node)
+	),
+
+	TP_fast_assign(
+			__entry->fn		= fn;
+			__entry->min		= mas->min;
+			__entry->max		= mas->max;
+			__entry->index		= mas->index;
+			__entry->last		= mas->last;
+			__entry->piv		= piv;
+			__entry->val		= val;
+			__entry->node		= mas->node;
+	),
+
+	TP_printk("%s\tNode %p (%lu %lu) range:%lu-%lu piv (%lu) val %p",
+		  __entry->fn,
+		  (void *) __entry->node,
+		  (unsigned long) __entry->min,
+		  (unsigned long) __entry->max,
+		  (unsigned long) __entry->index,
+		  (unsigned long) __entry->last,
+		  (unsigned long) __entry->piv,
+		  (void *) __entry->val
+	)
+)
+#endif /* _TRACE_MM_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/mmap.h b/include/trace/events/mmap.h
index 4661f7ba07c0..216de5f03621 100644
--- a/include/trace/events/mmap.h
+++ b/include/trace/events/mmap.h
@@ -42,6 +42,79 @@ TRACE_EVENT(vm_unmapped_area,
 		__entry->low_limit, __entry->high_limit, __entry->align_mask,
 		__entry->align_offset)
 );
+
+TRACE_EVENT(vma_mas_szero,
+	TP_PROTO(struct maple_tree *mt, unsigned long start,
+		 unsigned long end),
+
+	TP_ARGS(mt, start, end),
+
+	TP_STRUCT__entry(
+			__field(struct maple_tree *, mt)
+			__field(unsigned long, start)
+			__field(unsigned long, end)
+	),
+
+	TP_fast_assign(
+			__entry->mt		= mt;
+			__entry->start		= start;
+			__entry->end		= end;
+	),
+
+	TP_printk("mt_mod %p, (NULL), SNULL, %lu, %lu,",
+		  __entry->mt,
+		  (unsigned long) __entry->start,
+		  (unsigned long) __entry->end
+	)
+);
+
+TRACE_EVENT(vma_store,
+	TP_PROTO(struct maple_tree *mt, struct vm_area_struct *vma),
+
+	TP_ARGS(mt, vma),
+
+	TP_STRUCT__entry(
+			__field(struct maple_tree *, mt)
+			__field(struct vm_area_struct *, vma)
+			__field(unsigned long, vm_start)
+			__field(unsigned long, vm_end)
+	),
+
+	TP_fast_assign(
+			__entry->mt		= mt;
+			__entry->vma		= vma;
+			__entry->vm_start	= vma->vm_start;
+			__entry->vm_end		= vma->vm_end - 1;
+	),
+
+	TP_printk("mt_mod %p, (%p), STORE, %lu, %lu,",
+		  __entry->mt, __entry->vma,
+		  (unsigned long) __entry->vm_start,
+		  (unsigned long) __entry->vm_end
+	)
+);
+
+
+TRACE_EVENT(exit_mmap,
+	TP_PROTO(struct mm_struct *mm),
+
+	TP_ARGS(mm),
+
+	TP_STRUCT__entry(
+			__field(struct mm_struct *, mm)
+			__field(struct maple_tree *, mt)
+	),
+
+	TP_fast_assign(
+		       __entry->mm		= mm;
+		       __entry->mt		= &mm->mm_mt;
+	),
+
+	TP_printk("mt_mod %p, DESTROY\n",
+		  __entry->mt
+	)
+);
+
 #endif
 
 /* This part must be outside protection */