Merge tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of
   switching from a user process to a kernel thread.

 - More folio conversions from Kefeng Wang, Zhang Peng and Pankaj
   Raghav.

 - zsmalloc performance improvements from Sergey Senozhatsky.

 - Yue Zhao has found and fixed some data race issues around the
   alteration of memcg userspace tunables.

 - VFS rationalizations from Christoph Hellwig:
     - removal of most of the callers of write_one_page()
     - make __filemap_get_folio()'s return value more useful

 - Luis Chamberlain has changed tmpfs so it no longer requires swap
   backing. Use `mount -o noswap'.

 - Qi Zheng has made the slab shrinkers operate locklessly, providing
   some scalability benefits.

 - Keith Busch has improved dmapool's performance, making part of its
   operations O(1) rather than O(n).

 - Peter Xu adds the UFFD_FEATURE_WP_UNPOPULATED feature to userfaultd,
   permitting userspace to wr-protect anon memory unpopulated ptes.

 - Kirill Shutemov has changed MAX_ORDER's meaning to be inclusive
   rather than exclusive, and has fixed a bunch of errors which were
   caused by its unintuitive meaning.

 - Axel Rasmussen give userfaultfd the UFFDIO_CONTINUE_MODE_WP feature,
   which causes minor faults to install a write-protected pte.

 - Vlastimil Babka has done some maintenance work on vma_merge():
   cleanups to the kernel code and improvements to our userspace test
   harness.

 - Cleanups to do_fault_around() by Lorenzo Stoakes.

 - Mike Rapoport has moved a lot of initialization code out of various
   mm/ files and into mm/mm_init.c.

 - Lorenzo Stoakes removd vmf_insert_mixed_prot(), which was added for
   DRM, but DRM doesn't use it any more.

 - Lorenzo has also coverted read_kcore() and vread() to use iterators
   and has thereby removed the use of bounce buffers in some cases.

 - Lorenzo has also contributed further cleanups of vma_merge().

 - Chaitanya Prakash provides some fixes to the mmap selftesting code.

 - Matthew Wilcox changes xfs and afs so they no longer take sleeping
   locks in ->map_page(), a step towards RCUification of pagefaults.

 - Suren Baghdasaryan has improved mmap_lock scalability by switching to
   per-VMA locking.

 - Frederic Weisbecker has reworked the percpu cache draining so that it
   no longer causes latency glitches on cpu isolated workloads.

 - Mike Rapoport cleans up and corrects the ARCH_FORCE_MAX_ORDER Kconfig
   logic.

 - Liu Shixin has changed zswap's initialization so we no longer waste a
   chunk of memory if zswap is not being used.

 - Yosry Ahmed has improved the performance of memcg statistics
   flushing.

 - David Stevens has fixed several issues involving khugepaged,
   userfaultfd and shmem.

 - Christoph Hellwig has provided some cleanup work to zram's IO-related
   code paths.

 - David Hildenbrand has fixed up some issues in the selftest code's
   testing of our pte state changing.

 - Pankaj Raghav has made page_endio() unneeded and has removed it.

 - Peter Xu contributed some rationalizations of the userfaultfd
   selftests.

 - Yosry Ahmed has fixed an issue around memcg's page recalim
   accounting.

 - Chaitanya Prakash has fixed some arm-related issues in the
   selftests/mm code.

 - Longlong Xia has improved the way in which KSM handles hwpoisoned
   pages.

 - Peter Xu fixes a few issues with uffd-wp at fork() time.

 - Stefan Roesch has changed KSM so that it may now be used on a
   per-process and per-cgroup basis.

* tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (369 commits)
  mm,unmap: avoid flushing TLB in batch if PTE is inaccessible
  shmem: restrict noswap option to initial user namespace
  mm/khugepaged: fix conflicting mods to collapse_file()
  sparse: remove unnecessary 0 values from rc
  mm: move 'mmap_min_addr' logic from callers into vm_unmapped_area()
  hugetlb: pte_alloc_huge() to replace huge pte_alloc_map()
  maple_tree: fix allocation in mas_sparse_area()
  mm: do not increment pgfault stats when page fault handler retries
  zsmalloc: allow only one active pool compaction context
  selftests/mm: add new selftests for KSM
  mm: add new KSM process and sysfs knobs
  mm: add new api to enable ksm per process
  mm: shrinkers: fix debugfs file permissions
  mm: don't check VMA write permissions if the PTE/PMD indicates write permissions
  migrate_pages_batch: fix statistics for longterm pin retry
  userfaultfd: use helper function range_in_vma()
  lib/show_mem.c: use for_each_populated_zone() simplify code
  mm: correct arg in reclaim_pages()/reclaim_clean_pages_from_list()
  fs/buffer: convert create_page_buffers to folio_create_buffers
  fs/buffer: add folio_create_empty_buffers helper
  ...

5 files changed, 53 insertions, 23 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 442eccc00960..f87590c3c382 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -27,6 +27,7 @@ config X86_64
 	# Options that are inherently 64-bit kernel only:
 	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
+	select ARCH_SUPPORTS_PER_VMA_LOCK
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select HAVE_ARCH_SOFT_DIRTY
 	select MODULES_USE_ELF_RELA
@@ -125,8 +126,8 @@ config X86
 	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANT_GENERAL_HUGETLB
 	select ARCH_WANT_HUGE_PMD_SHARE
-	select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP	if X86_64
 	select ARCH_WANT_LD_ORPHAN_WARN
+	select ARCH_WANT_OPTIMIZE_VMEMMAP	if X86_64
 	select ARCH_WANTS_THP_SWAP		if X86_64
 	select ARCH_HAS_PARANOID_L1D_FLUSH
 	select BUILDTIME_TABLE_SORT
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 7425f32e5293..15ae4d6ba476 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1097,7 +1097,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm,
 	clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte);
 }
 
-#define flush_tlb_fix_spurious_fault(vma, address) do { } while (0)
+#define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0)
 
 #define mk_pmd(page, pgprot)   pfn_pmd(page_to_pfn(page), (pgprot))
 
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index c1e14cee0722..857d364b9888 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -15,24 +15,18 @@
 #endif
 
 #define __HAVE_ARCH_MEMCPY 1
-#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
-#undef memcpy
-#define memcpy __msan_memcpy
-#else
 extern void *memcpy(void *to, const void *from, size_t len);
-#endif
 extern void *__memcpy(void *to, const void *from, size_t len);
 
 #define __HAVE_ARCH_MEMSET
-#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
-extern void *__msan_memset(void *s, int c, size_t n);
-#undef memset
-#define memset __msan_memset
-#else
 void *memset(void *s, int c, size_t n);
-#endif
 void *__memset(void *s, int c, size_t n);
 
+/*
+ * KMSAN needs to instrument as much code as possible. Use C versions of
+ * memsetXX() from lib/string.c under KMSAN.
+ */
+#if !defined(CONFIG_KMSAN)
 #define __HAVE_ARCH_MEMSET16
 static inline void *memset16(uint16_t *s, uint16_t v, size_t n)
 {
@@ -68,15 +62,10 @@ static inline void *memset64(uint64_t *s, uint64_t v, size_t n)
 		     : "memory");
 	return s;
 }
+#endif
 
 #define __HAVE_ARCH_MEMMOVE
-#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
-#undef memmove
-void *__msan_memmove(void *dest, const void *src, size_t len);
-#define memmove __msan_memmove
-#else
 void *memmove(void *dest, const void *src, size_t count);
-#endif
 void *__memmove(void *dest, const void *src, size_t count);
 
 int memcmp(const void *cs, const void *ct, size_t count);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index a498ae1fbe66..e4399983c50c 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -19,6 +19,7 @@
 #include <linux/uaccess.h>		/* faulthandler_disabled()	*/
 #include <linux/efi.h>			/* efi_crash_gracefully_on_page_fault()*/
 #include <linux/mm_types.h>
+#include <linux/mm.h>			/* find_and_lock_vma() */
 
 #include <asm/cpufeature.h>		/* boot_cpu_has, ...		*/
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
@@ -1333,6 +1334,38 @@ void do_user_addr_fault(struct pt_regs *regs,
 	}
 #endif
 
+#ifdef CONFIG_PER_VMA_LOCK
+	if (!(flags & FAULT_FLAG_USER))
+		goto lock_mmap;
+
+	vma = lock_vma_under_rcu(mm, address);
+	if (!vma)
+		goto lock_mmap;
+
+	if (unlikely(access_error(error_code, vma))) {
+		vma_end_read(vma);
+		goto lock_mmap;
+	}
+	fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
+	vma_end_read(vma);
+
+	if (!(fault & VM_FAULT_RETRY)) {
+		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+		goto done;
+	}
+	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+
+	/* Quick path to respond to signals */
+	if (fault_signal_pending(fault, regs)) {
+		if (!user_mode(regs))
+			kernelmode_fixup_or_oops(regs, error_code, address,
+						 SIGBUS, BUS_ADRERR,
+						 ARCH_DEFAULT_PKEY);
+		return;
+	}
+lock_mmap:
+#endif /* CONFIG_PER_VMA_LOCK */
+
 	/*
 	 * Kernel-mode access to the user address space should only occur
 	 * on well-defined single instructions listed in the exception
@@ -1433,6 +1466,9 @@ good_area:
 	}
 
 	mmap_read_unlock(mm);
+#ifdef CONFIG_PER_VMA_LOCK
+done:
+#endif
 	if (likely(!(fault & VM_FAULT_ERROR)))
 		return;
 
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 46a00aa858b6..de10800cd4dd 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -1073,11 +1073,15 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 }
 
 /*
- * untrack_pfn_moved is called, while mremapping a pfnmap for a new region,
- * with the old vma after its pfnmap page table has been removed.  The new
- * vma has a new pfnmap to the same pfn & cache type with VM_PAT set.
+ * untrack_pfn_clear is called if the following situation fits:
+ *
+ * 1) while mremapping a pfnmap for a new region,  with the old vma after
+ * its pfnmap page table has been removed.  The new vma has a new pfnmap
+ * to the same pfn & cache type with VM_PAT set.
+ * 2) while duplicating vm area, the new vma fails to copy the pgtable from
+ * old vma.
  */
-void untrack_pfn_moved(struct vm_area_struct *vma)
+void untrack_pfn_clear(struct vm_area_struct *vma)
 {
 	vm_flags_clear(vma, VM_PAT);
 }