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
  ...

init/main.c

@@ -62,7 +62,6 @@
 #include <linux/rmap.h>
 #include <linux/mempolicy.h>
 #include <linux/key.h>
-#include <linux/page_ext.h>
 #include <linux/debug_locks.h>
 #include <linux/debugobjects.h>
 #include <linux/lockdep.h>
@@ -807,69 +806,6 @@ static inline void initcall_debug_enable(void)
 }
 #endif
 
-/* Report memory auto-initialization states for this boot. */
-static void __init report_meminit(void)
-{
-	const char *stack;
-
-	if (IS_ENABLED(CONFIG_INIT_STACK_ALL_PATTERN))
-		stack = "all(pattern)";
-	else if (IS_ENABLED(CONFIG_INIT_STACK_ALL_ZERO))
-		stack = "all(zero)";
-	else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF_ALL))
-		stack = "byref_all(zero)";
-	else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF))
-		stack = "byref(zero)";
-	else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_USER))
-		stack = "__user(zero)";
-	else
-		stack = "off";
-
-	pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s\n",
-		stack, want_init_on_alloc(GFP_KERNEL) ? "on" : "off",
-		want_init_on_free() ? "on" : "off");
-	if (want_init_on_free())
-		pr_info("mem auto-init: clearing system memory may take some time...\n");
-}
-
-/*
- * Set up kernel memory allocators
- */
-static void __init mm_init(void)
-{
-	/*
-	 * page_ext requires contiguous pages,
-	 * bigger than MAX_ORDER unless SPARSEMEM.
-	 */
-	page_ext_init_flatmem();
-	init_mem_debugging_and_hardening();
-	kfence_alloc_pool();
-	report_meminit();
-	kmsan_init_shadow();
-	stack_depot_early_init();
-	mem_init();
-	mem_init_print_info();
-	kmem_cache_init();
-	/*
-	 * page_owner must be initialized after buddy is ready, and also after
-	 * slab is ready so that stack_depot_init() works properly
-	 */
-	page_ext_init_flatmem_late();
-	kmemleak_init();
-	pgtable_init();
-	debug_objects_mem_init();
-	vmalloc_init();
-	/* If no deferred init page_ext now, as vmap is fully initialized */
-	if (!deferred_struct_pages)
-		page_ext_init();
-	/* Should be run before the first non-init thread is created */
-	init_espfix_bsp();
-	/* Should be run after espfix64 is set up. */
-	pti_init();
-	kmsan_init_runtime();
-	mm_cache_init();
-}
-
 #ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET
 DEFINE_STATIC_KEY_MAYBE_RO(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT,
 			   randomize_kstack_offset);
@@ -972,9 +908,6 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void)
 	smp_prepare_boot_cpu();	/* arch-specific boot-cpu hooks */
 	boot_cpu_hotplug_init();
 
-	build_all_zonelists(NULL);
-	page_alloc_init();
-
 	pr_notice("Kernel command line: %s\n", saved_command_line);
 	/* parameters may set static keys */
 	jump_label_init();
@@ -996,13 +929,13 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void)
 
 	/*
 	 * These use large bootmem allocations and must precede
-	 * kmem_cache_init()
+	 * initalization of page allocator
 	 */
 	setup_log_buf(0);
 	vfs_caches_init_early();
 	sort_main_extable();
 	trap_init();
-	mm_init();
+	mm_core_init();
 	poking_init();
 	ftrace_init();
 
@@ -1634,9 +1567,6 @@ static noinline void __init kernel_init_freeable(void)
 
 	padata_init();
 	page_alloc_init_late();
-	/* Initialize page ext after all struct pages are initialized. */
-	if (deferred_struct_pages)
-		page_ext_init();
 
 	do_basic_setup();