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
  ...

1 files changed, 17 insertions, 3 deletions

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index ccaa461998f3..ca71de7c9d77 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -43,6 +43,9 @@
 #include <asm/tlbflush.h>
 #include <asm/shmparam.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/vmalloc.h>
+
 #include "internal.h"
 #include "pgalloc-track.h"
 
@@ -1620,6 +1623,8 @@ retry:
 		size, align, vstart, vend);
 	spin_unlock(&free_vmap_area_lock);
 
+	trace_alloc_vmap_area(addr, size, align, vstart, vend, addr == vend);
+
 	/*
 	 * If an allocation fails, the "vend" address is
 	 * returned. Therefore trigger the overflow path.
@@ -1725,6 +1730,7 @@ static void purge_fragmented_blocks_allcpus(void);
 static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
 {
 	unsigned long resched_threshold;
+	unsigned int num_purged_areas = 0;
 	struct list_head local_purge_list;
 	struct vmap_area *va, *n_va;
 
@@ -1736,7 +1742,7 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
 	spin_unlock(&purge_vmap_area_lock);
 
 	if (unlikely(list_empty(&local_purge_list)))
-		return false;
+		goto out;
 
 	start = min(start,
 		list_first_entry(&local_purge_list,
@@ -1771,12 +1777,16 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
 					      va->va_start, va->va_end);
 
 		atomic_long_sub(nr, &vmap_lazy_nr);
+		num_purged_areas++;
 
 		if (atomic_long_read(&vmap_lazy_nr) < resched_threshold)
 			cond_resched_lock(&free_vmap_area_lock);
 	}
 	spin_unlock(&free_vmap_area_lock);
-	return true;
+
+out:
+	trace_purge_vmap_area_lazy(start, end, num_purged_areas);
+	return num_purged_areas > 0;
 }
 
 /*
@@ -1811,6 +1821,8 @@ static void drain_vmap_area_work(struct work_struct *work)
  */
 static void free_vmap_area_noflush(struct vmap_area *va)
 {
+	unsigned long nr_lazy_max = lazy_max_pages();
+	unsigned long va_start = va->va_start;
 	unsigned long nr_lazy;
 
 	spin_lock(&vmap_area_lock);
@@ -1828,8 +1840,10 @@ static void free_vmap_area_noflush(struct vmap_area *va)
 		&purge_vmap_area_root, &purge_vmap_area_list);
 	spin_unlock(&purge_vmap_area_lock);
 
+	trace_free_vmap_area_noflush(va_start, nr_lazy, nr_lazy_max);
+
 	/* After this point, we may free va at any time */
-	if (unlikely(nr_lazy > lazy_max_pages()))
+	if (unlikely(nr_lazy > nr_lazy_max))
 		schedule_work(&drain_vmap_work);
 }