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, 32 insertions, 101 deletions

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 3f040c6e5d13..a190aae8ceaf 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1416,47 +1416,6 @@ void mark_rodata_ro(void)
 	debug_checkwx();
 }
 
-int kern_addr_valid(unsigned long addr)
-{
-	unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT;
-	pgd_t *pgd;
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-
-	if (above != 0 && above != -1UL)
-		return 0;
-
-	pgd = pgd_offset_k(addr);
-	if (pgd_none(*pgd))
-		return 0;
-
-	p4d = p4d_offset(pgd, addr);
-	if (!p4d_present(*p4d))
-		return 0;
-
-	pud = pud_offset(p4d, addr);
-	if (!pud_present(*pud))
-		return 0;
-
-	if (pud_large(*pud))
-		return pfn_valid(pud_pfn(*pud));
-
-	pmd = pmd_offset(pud, addr);
-	if (!pmd_present(*pmd))
-		return 0;
-
-	if (pmd_large(*pmd))
-		return pfn_valid(pmd_pfn(*pmd));
-
-	pte = pte_offset_kernel(pmd, addr);
-	if (pte_none(*pte))
-		return 0;
-
-	return pfn_valid(pte_pfn(*pte));
-}
-
 /*
  * Block size is the minimum amount of memory which can be hotplugged or
  * hotremoved. It must be power of two and must be equal or larger than
@@ -1533,72 +1492,44 @@ static long __meminitdata addr_start, addr_end;
 static void __meminitdata *p_start, *p_end;
 static int __meminitdata node_start;
 
-static int __meminit vmemmap_populate_hugepages(unsigned long start,
-		unsigned long end, int node, struct vmem_altmap *altmap)
+void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
+			       unsigned long addr, unsigned long next)
 {
-	unsigned long addr;
-	unsigned long next;
-	pgd_t *pgd;
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
-
-	for (addr = start; addr < end; addr = next) {
-		next = pmd_addr_end(addr, end);
-
-		pgd = vmemmap_pgd_populate(addr, node);
-		if (!pgd)
-			return -ENOMEM;
-
-		p4d = vmemmap_p4d_populate(pgd, addr, node);
-		if (!p4d)
-			return -ENOMEM;
-
-		pud = vmemmap_pud_populate(p4d, addr, node);
-		if (!pud)
-			return -ENOMEM;
-
-		pmd = pmd_offset(pud, addr);
-		if (pmd_none(*pmd)) {
-			void *p;
-
-			p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap);
-			if (p) {
-				pte_t entry;
-
-				entry = pfn_pte(__pa(p) >> PAGE_SHIFT,
-						PAGE_KERNEL_LARGE);
-				set_pmd(pmd, __pmd(pte_val(entry)));
+	pte_t entry;
+
+	entry = pfn_pte(__pa(p) >> PAGE_SHIFT,
+			PAGE_KERNEL_LARGE);
+	set_pmd(pmd, __pmd(pte_val(entry)));
+
+	/* check to see if we have contiguous blocks */
+	if (p_end != p || node_start != node) {
+		if (p_start)
+			pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+				addr_start, addr_end-1, p_start, p_end-1, node_start);
+		addr_start = addr;
+		node_start = node;
+		p_start = p;
+	}
 
-				/* check to see if we have contiguous blocks */
-				if (p_end != p || node_start != node) {
-					if (p_start)
-						pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n",
-						       addr_start, addr_end-1, p_start, p_end-1, node_start);
-					addr_start = addr;
-					node_start = node;
-					p_start = p;
-				}
+	addr_end = addr + PMD_SIZE;
+	p_end = p + PMD_SIZE;
 
-				addr_end = addr + PMD_SIZE;
-				p_end = p + PMD_SIZE;
+	if (!IS_ALIGNED(addr, PMD_SIZE) ||
+		!IS_ALIGNED(next, PMD_SIZE))
+		vmemmap_use_new_sub_pmd(addr, next);
+}
 
-				if (!IS_ALIGNED(addr, PMD_SIZE) ||
-				    !IS_ALIGNED(next, PMD_SIZE))
-					vmemmap_use_new_sub_pmd(addr, next);
+int __meminit vmemmap_check_pmd(pmd_t *pmd, int node,
+				unsigned long addr, unsigned long next)
+{
+	int large = pmd_large(*pmd);
 
-				continue;
-			} else if (altmap)
-				return -ENOMEM; /* no fallback */
-		} else if (pmd_large(*pmd)) {
-			vmemmap_verify((pte_t *)pmd, node, addr, next);
-			vmemmap_use_sub_pmd(addr, next);
-			continue;
-		}
-		if (vmemmap_populate_basepages(addr, next, node, NULL))
-			return -ENOMEM;
+	if (pmd_large(*pmd)) {
+		vmemmap_verify((pte_t *)pmd, node, addr, next);
+		vmemmap_use_sub_pmd(addr, next);
 	}
-	return 0;
+
+	return large;
 }
 
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,