Merge tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - More userfaultfs work from Peter Xu

 - Several convert-to-folios series from Sidhartha Kumar and Huang Ying

 - Some filemap cleanups from Vishal Moola

 - David Hildenbrand added the ability to selftest anon memory COW
   handling

 - Some cpuset simplifications from Liu Shixin

 - Addition of vmalloc tracing support by Uladzislau Rezki

 - Some pagecache folioifications and simplifications from Matthew
   Wilcox

 - A pagemap cleanup from Kefeng Wang: we have VM_ACCESS_FLAGS, so use
   it

 - Miguel Ojeda contributed some cleanups for our use of the
   __no_sanitize_thread__ gcc keyword.

   This series should have been in the non-MM tree, my bad

 - Naoya Horiguchi improved the interaction between memory poisoning and
   memory section removal for huge pages

 - DAMON cleanups and tuneups from SeongJae Park

 - Tony Luck fixed the handling of COW faults against poisoned pages

 - Peter Xu utilized the PTE marker code for handling swapin errors

 - Hugh Dickins reworked compound page mapcount handling, simplifying it
   and making it more efficient

 - Removal of the autonuma savedwrite infrastructure from Nadav Amit and
   David Hildenbrand

 - zram support for multiple compression streams from Sergey Senozhatsky

 - David Hildenbrand reworked the GUP code's R/O long-term pinning so
   that drivers no longer need to use the FOLL_FORCE workaround which
   didn't work very well anyway

 - Mel Gorman altered the page allocator so that local IRQs can remnain
   enabled during per-cpu page allocations

 - Vishal Moola removed the try_to_release_page() wrapper

 - Stefan Roesch added some per-BDI sysfs tunables which are used to
   prevent network block devices from dirtying excessive amounts of
   pagecache

 - David Hildenbrand did some cleanup and repair work on KSM COW
   breaking

 - Nhat Pham and Johannes Weiner have implemented writeback in zswap's
   zsmalloc backend

 - Brian Foster has fixed a longstanding corner-case oddity in
   file[map]_write_and_wait_range()

 - sparse-vmemmap changes for MIPS, LoongArch and NIOS2 from Feiyang
   Chen

 - Shiyang Ruan has done some work on fsdax, to make its reflink mode
   work better under xfstests. Better, but still not perfect

 - Christoph Hellwig has removed the .writepage() method from several
   filesystems. They only need .writepages()

 - Yosry Ahmed wrote a series which fixes the memcg reclaim target
   beancounting

 - David Hildenbrand has fixed some of our MM selftests for 32-bit
   machines

 - Many singleton patches, as usual

* tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (313 commits)
  mm/hugetlb: set head flag before setting compound_order in __prep_compound_gigantic_folio
  mm: mmu_gather: allow more than one batch of delayed rmaps
  mm: fix typo in struct pglist_data code comment
  kmsan: fix memcpy tests
  mm: add cond_resched() in swapin_walk_pmd_entry()
  mm: do not show fs mm pc for VM_LOCKONFAULT pages
  selftests/vm: ksm_functional_tests: fixes for 32bit
  selftests/vm: cow: fix compile warning on 32bit
  selftests/vm: madv_populate: fix missing MADV_POPULATE_(READ|WRITE) definitions
  mm/gup_test: fix PIN_LONGTERM_TEST_READ with highmem
  mm,thp,rmap: fix races between updates of subpages_mapcount
  mm: memcg: fix swapcached stat accounting
  mm: add nodes= arg to memory.reclaim
  mm: disable top-tier fallback to reclaim on proactive reclaim
  selftests: cgroup: make sure reclaim target memcg is unprotected
  selftests: cgroup: refactor proactive reclaim code to reclaim_until()
  mm: memcg: fix stale protection of reclaim target memcg
  mm/mmap: properly unaccount memory on mas_preallocate() failure
  omfs: remove ->writepage
  jfs: remove ->writepage
  ...

3 files changed, 165 insertions, 4 deletions

diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h
index 760455dfa860..3e6fb05852f9 100644
--- a/include/trace/events/huge_memory.h
+++ b/include/trace/events/huge_memory.h
@@ -203,5 +203,43 @@ TRACE_EVENT(mm_khugepaged_scan_file,
 		__print_symbolic(__entry->result, SCAN_STATUS))
 );
 
+TRACE_EVENT(mm_khugepaged_collapse_file,
+	TP_PROTO(struct mm_struct *mm, struct page *hpage, pgoff_t index,
+			bool is_shmem, unsigned long addr, struct file *file,
+			int nr, int result),
+	TP_ARGS(mm, hpage, index, addr, is_shmem, file, nr, result),
+	TP_STRUCT__entry(
+		__field(struct mm_struct *, mm)
+		__field(unsigned long, hpfn)
+		__field(pgoff_t, index)
+		__field(unsigned long, addr)
+		__field(bool, is_shmem)
+		__string(filename, file->f_path.dentry->d_iname)
+		__field(int, nr)
+		__field(int, result)
+	),
+
+	TP_fast_assign(
+		__entry->mm = mm;
+		__entry->hpfn = hpage ? page_to_pfn(hpage) : -1;
+		__entry->index = index;
+		__entry->addr = addr;
+		__entry->is_shmem = is_shmem;
+		__assign_str(filename, file->f_path.dentry->d_iname);
+		__entry->nr = nr;
+		__entry->result = result;
+	),
+
+	TP_printk("mm=%p, hpage_pfn=0x%lx, index=%ld, addr=%ld, is_shmem=%d, filename=%s, nr=%d, result=%s",
+		__entry->mm,
+		__entry->hpfn,
+		__entry->index,
+		__entry->addr,
+		__entry->is_shmem,
+		__get_str(filename),
+		__entry->nr,
+		__print_symbolic(__entry->result, SCAN_STATUS))
+);
+
 #endif /* __HUGE_MEMORY_H */
 #include <trace/define_trace.h>
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index 243073cfc29d..58688768ef0f 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -346,10 +346,9 @@ TRACE_MM_PAGES
 TRACE_EVENT(rss_stat,
 
 	TP_PROTO(struct mm_struct *mm,
-		int member,
-		long count),
+		int member),
 
-	TP_ARGS(mm, member, count),
+	TP_ARGS(mm, member),
 
 	TP_STRUCT__entry(
 		__field(unsigned int, mm_id)
@@ -362,7 +361,8 @@ TRACE_EVENT(rss_stat,
 		__entry->mm_id = mm_ptr_to_hash(mm);
 		__entry->curr = !!(current->mm == mm);
 		__entry->member = member;
-		__entry->size = (count << PAGE_SHIFT);
+		__entry->size = (percpu_counter_sum_positive(&mm->rss_stat[member])
+							    << PAGE_SHIFT);
 	),
 
 	TP_printk("mm_id=%u curr=%d type=%s size=%ldB",
diff --git a/include/trace/events/vmalloc.h b/include/trace/events/vmalloc.h
new file mode 100644
index 000000000000..ad4e02191f35
--- /dev/null
+++ b/include/trace/events/vmalloc.h
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM vmalloc
+
+#if !defined(_TRACE_VMALLOC_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_VMALLOC_H
+
+#include <linux/tracepoint.h>
+
+/**
+ * alloc_vmap_area - called when a new vmap allocation occurs
+ * @addr:	an allocated address
+ * @size:	a requested size
+ * @align:	a requested alignment
+ * @vstart:	a requested start range
+ * @vend:	a requested end range
+ * @failed:	an allocation failed or not
+ *
+ * This event is used for a debug purpose, it can give an extra
+ * information for a developer about how often it occurs and which
+ * parameters are passed for further validation.
+ */
+TRACE_EVENT(alloc_vmap_area,
+
+	TP_PROTO(unsigned long addr, unsigned long size, unsigned long align,
+		unsigned long vstart, unsigned long vend, int failed),
+
+	TP_ARGS(addr, size, align, vstart, vend, failed),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, addr)
+		__field(unsigned long, size)
+		__field(unsigned long, align)
+		__field(unsigned long, vstart)
+		__field(unsigned long, vend)
+		__field(int, failed)
+	),
+
+	TP_fast_assign(
+		__entry->addr = addr;
+		__entry->size = size;
+		__entry->align = align;
+		__entry->vstart = vstart;
+		__entry->vend = vend;
+		__entry->failed = failed;
+	),
+
+	TP_printk("va_start: %lu size=%lu align=%lu vstart=0x%lx vend=0x%lx failed=%d",
+		__entry->addr, __entry->size, __entry->align,
+		__entry->vstart, __entry->vend, __entry->failed)
+);
+
+/**
+ * purge_vmap_area_lazy - called when vmap areas were lazily freed
+ * @start:		purging start address
+ * @end:		purging end address
+ * @npurged:	numbed of purged vmap areas
+ *
+ * This event is used for a debug purpose. It gives some
+ * indication about start:end range and how many objects
+ * are released.
+ */
+TRACE_EVENT(purge_vmap_area_lazy,
+
+	TP_PROTO(unsigned long start, unsigned long end,
+		unsigned int npurged),
+
+	TP_ARGS(start, end, npurged),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, start)
+		__field(unsigned long, end)
+		__field(unsigned int, npurged)
+	),
+
+	TP_fast_assign(
+		__entry->start = start;
+		__entry->end = end;
+		__entry->npurged = npurged;
+	),
+
+	TP_printk("start=0x%lx end=0x%lx num_purged=%u",
+		__entry->start, __entry->end, __entry->npurged)
+);
+
+/**
+ * free_vmap_area_noflush - called when a vmap area is freed
+ * @va_start:		a start address of VA
+ * @nr_lazy:		number of current lazy pages
+ * @nr_lazy_max:	number of maximum lazy pages
+ *
+ * This event is used for a debug purpose. It gives some
+ * indication about a VA that is released, number of current
+ * outstanding areas and a maximum allowed threshold before
+ * dropping all of them.
+ */
+TRACE_EVENT(free_vmap_area_noflush,
+
+	TP_PROTO(unsigned long va_start, unsigned long nr_lazy,
+		unsigned long nr_lazy_max),
+
+	TP_ARGS(va_start, nr_lazy, nr_lazy_max),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, va_start)
+		__field(unsigned long, nr_lazy)
+		__field(unsigned long, nr_lazy_max)
+	),
+
+	TP_fast_assign(
+		__entry->va_start = va_start;
+		__entry->nr_lazy = nr_lazy;
+		__entry->nr_lazy_max = nr_lazy_max;
+	),
+
+	TP_printk("va_start=0x%lx nr_lazy=%lu nr_lazy_max=%lu",
+		__entry->va_start, __entry->nr_lazy, __entry->nr_lazy_max)
+);
+
+#endif /*  _TRACE_VMALLOC_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>