Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - a few hot fixes

 - ocfs2 updates

 - almost all of -mm (slab-generic, slab, slub, kmemleak, kasan,
   cleanups, debug, pagecache, memcg, gup, pagemap, memory-hotplug,
   sparsemem, vmalloc, initialization, z3fold, compaction, mempolicy,
   oom-kill, hugetlb, migration, thp, mmap, madvise, shmem, zswap,
   zsmalloc)

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (132 commits)
  mm/zsmalloc.c: fix a -Wunused-function warning
  zswap: do not map same object twice
  zswap: use movable memory if zpool support allocate movable memory
  zpool: add malloc_support_movable to zpool_driver
  shmem: fix obsolete comment in shmem_getpage_gfp()
  mm/madvise: reduce code duplication in error handling paths
  mm: mmap: increase sockets maximum memory size pgoff for 32bits
  mm/mmap.c: refine find_vma_prev() with rb_last()
  riscv: make mmap allocation top-down by default
  mips: use generic mmap top-down layout and brk randomization
  mips: replace arch specific way to determine 32bit task with generic version
  mips: adjust brk randomization offset to fit generic version
  mips: use STACK_TOP when computing mmap base address
  mips: properly account for stack randomization and stack guard gap
  arm: use generic mmap top-down layout and brk randomization
  arm: use STACK_TOP when computing mmap base address
  arm: properly account for stack randomization and stack guard gap
  arm64, mm: make randomization selected by generic topdown mmap layout
  arm64, mm: move generic mmap layout functions to mm
  arm64: consider stack randomization for mmap base only when necessary
  ...

Documentation/ABI/testing/sysfs-kernel-slab

@@ -429,10 +429,15 @@ KernelVersion:	2.6.22
 Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 		Christoph Lameter <cl@linux-foundation.org>
 Description:
-		The shrink file is written when memory should be reclaimed from
+		The shrink file is used to reclaim unused slab cache
-		a cache.  Empty partial slabs are freed and the partial list is
+		memory from a cache.  Empty per-cpu or partial slabs
-		sorted so the slabs with the fewest available objects are used
+		are freed and the partial list is sorted so the slabs
-		first.
+		with the fewest available objects are used first.
+		It only accepts a value of "1" on write for shrinking
+		the cache. Other input values are considered invalid.
+		Shrinking slab caches might be expensive and can
+		adversely impact other running applications.  So it
+		should be used with care.
 
 What:		/sys/kernel/slab/cache/slab_size
 Date:		May 2007

Documentation/admin-guide/cgroup-v1/memory.rst

@@ -85,8 +85,10 @@ Brief summary of control files.
  memory.oom_control		     set/show oom controls.
  memory.numa_stat		     show the number of memory usage per numa
 				     node
-
  memory.kmem.limit_in_bytes          set/show hard limit for kernel memory
+                                     This knob is deprecated and shouldn't be
+                                     used. It is planned that this be removed in
+                                     the foreseeable future.
  memory.kmem.usage_in_bytes          show current kernel memory allocation
  memory.kmem.failcnt                 show the number of kernel memory usage
 				     hits limits

Documentation/admin-guide/kernel-parameters.txt

@@ -809,6 +809,8 @@
 			enables the feature at boot time. By default, it is
 			disabled and the system will work mostly the same as a
 			kernel built without CONFIG_DEBUG_PAGEALLOC.
+			Note: to get most of debug_pagealloc error reports, it's
+			useful to also enable the page_owner functionality.
 			on: enable the feature
 
 	debugpat	[X86] Enable PAT debugging

arch/Kconfig

@@ -706,6 +706,17 @@ config HAVE_ARCH_COMPAT_MMAP_BASES
 	  and vice-versa 32-bit applications to call 64-bit mmap().
 	  Required for applications doing different bitness syscalls.
 
+# This allows to use a set of generic functions to determine mmap base
+# address by giving priority to top-down scheme only if the process
+# is not in legacy mode (compat task, unlimited stack size or
+# sysctl_legacy_va_layout).
+# Architecture that selects this option can provide its own version of:
+# - STACK_RND_MASK
+config ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
+	bool
+	depends on MMU
+	select ARCH_HAS_ELF_RANDOMIZE
+
 config HAVE_COPY_THREAD_TLS
 	bool
 	help

arch/alpha/include/asm/pgalloc.h

@@ -53,6 +53,4 @@ pmd_free(struct mm_struct *mm, pmd_t *pmd)
 	free_page((unsigned long)pmd);
 }
 
-#define check_pgt_cache()	do { } while (0)
-
 #endif /* _ALPHA_PGALLOC_H */

arch/alpha/include/asm/pgtable.h

@@ -359,11 +359,6 @@ extern void paging_init(void);
 
 #include <asm-generic/pgtable.h>
 
-/*
- * No page table caches to initialise
- */
-#define pgtable_cache_init()	do { } while (0)
-
 /* We have our own get_unmapped_area to cope with ADDR_LIMIT_32BIT.  */
 #define HAVE_ARCH_UNMAPPED_AREA
 

arch/arc/include/asm/pgalloc.h

@@ -129,7 +129,6 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptep)
 
 #define __pte_free_tlb(tlb, pte, addr)  pte_free((tlb)->mm, pte)
 
-#define check_pgt_cache()   do { } while (0)
 #define pmd_pgtable(pmd)	((pgtable_t) pmd_page_vaddr(pmd))
 
 #endif /* _ASM_ARC_PGALLOC_H */

arch/arc/include/asm/pgtable.h

@@ -395,11 +395,6 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
 /* to cope with aliasing VIPT cache */
 #define HAVE_ARCH_UNMAPPED_AREA
 
-/*
- * No page table caches to initialise
- */
-#define pgtable_cache_init()   do { } while (0)
-
 #endif /* __ASSEMBLY__ */
 
 #endif

arch/arm/Kconfig

@@ -34,6 +34,7 @@ config ARM
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
+	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BINFMT_FLAT_ARGVP_ENVP_ON_STACK
 	select BUILDTIME_EXTABLE_SORT if MMU

arch/arm/include/asm/pgalloc.h

@@ -15,8 +15,6 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 
-#define check_pgt_cache()		do { } while (0)
-
 #ifdef CONFIG_MMU
 
 #define _PAGE_USER_TABLE	(PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_USER))

arch/arm/include/asm/pgtable-nommu.h

@@ -70,11 +70,6 @@ typedef pte_t *pte_addr_t;
  */
 extern unsigned int kobjsize(const void *objp);
 
-/*
- * No page table caches to initialise.
- */
-#define pgtable_cache_init()	do { } while (0)
-
 /*
  * All 32bit addresses are effectively valid for vmalloc...
  * Sort of meaningless for non-VM targets.

arch/arm/include/asm/pgtable.h

@@ -368,8 +368,6 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 #define HAVE_ARCH_UNMAPPED_AREA
 #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
 
-#define pgtable_cache_init() do { } while (0)
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* CONFIG_MMU */

arch/arm/include/asm/processor.h

@@ -140,8 +140,6 @@ static inline void prefetchw(const void *ptr)
 #endif
 #endif
 
-#define HAVE_ARCH_PICK_MMAP_LAYOUT
-
 #endif
 
 #endif /* __ASM_ARM_PROCESSOR_H */

arch/arm/kernel/process.c

@@ -319,11 +319,6 @@ unsigned long get_wchan(struct task_struct *p)
 	return 0;
 }
 
-unsigned long arch_randomize_brk(struct mm_struct *mm)
-{
-	return randomize_page(mm->brk, 0x02000000);
-}
-
 #ifdef CONFIG_MMU
 #ifdef CONFIG_KUSER_HELPERS
 /*

arch/arm/mm/flush.c

@@ -204,18 +204,17 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page)
 	 * coherent with the kernels mapping.
 	 */
 	if (!PageHighMem(page)) {
-		size_t page_size = PAGE_SIZE << compound_order(page);
+		__cpuc_flush_dcache_area(page_address(page), page_size(page));
-		__cpuc_flush_dcache_area(page_address(page), page_size);
 	} else {
 		unsigned long i;
 		if (cache_is_vipt_nonaliasing()) {
-			for (i = 0; i < (1 << compound_order(page)); i++) {
+			for (i = 0; i < compound_nr(page); i++) {
 				void *addr = kmap_atomic(page + i);
 				__cpuc_flush_dcache_area(addr, PAGE_SIZE);
 				kunmap_atomic(addr);
 			}
 		} else {
-			for (i = 0; i < (1 << compound_order(page)); i++) {
+			for (i = 0; i < compound_nr(page); i++) {
 				void *addr = kmap_high_get(page + i);
 				if (addr) {
 					__cpuc_flush_dcache_area(addr, PAGE_SIZE);

arch/arm/mm/mmap.c

@@ -17,33 +17,6 @@
 	((((addr)+SHMLBA-1)&~(SHMLBA-1)) +	\
 	 (((pgoff)<<PAGE_SHIFT) & (SHMLBA-1)))
 
-/* gap between mmap and stack */
-#define MIN_GAP (128*1024*1024UL)
-#define MAX_GAP ((TASK_SIZE)/6*5)
-
-static int mmap_is_legacy(struct rlimit *rlim_stack)
-{
-	if (current->personality & ADDR_COMPAT_LAYOUT)
-		return 1;
-
-	if (rlim_stack->rlim_cur == RLIM_INFINITY)
-		return 1;
-
-	return sysctl_legacy_va_layout;
-}
-
-static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
-{
-	unsigned long gap = rlim_stack->rlim_cur;
-
-	if (gap < MIN_GAP)
-		gap = MIN_GAP;
-	else if (gap > MAX_GAP)
-		gap = MAX_GAP;
-
-	return PAGE_ALIGN(TASK_SIZE - gap - rnd);
-}
-
 /*
  * We need to ensure that shared mappings are correctly aligned to
  * avoid aliasing issues with VIPT caches.  We need to ensure that
@@ -171,31 +144,6 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	return addr;
 }
 
-unsigned long arch_mmap_rnd(void)
-{
-	unsigned long rnd;
-
-	rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
-
-	return rnd << PAGE_SHIFT;
-}
-
-void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
-{
-	unsigned long random_factor = 0UL;
-
-	if (current->flags & PF_RANDOMIZE)
-		random_factor = arch_mmap_rnd();
-
-	if (mmap_is_legacy(rlim_stack)) {
-		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
-		mm->get_unmapped_area = arch_get_unmapped_area;
-	} else {
-		mm->mmap_base = mmap_base(random_factor, rlim_stack);
-		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
-	}
-}
-
 /*
  * You really shouldn't be using read() or write() on /dev/mem.  This
  * might go away in the future.

arch/arm64/Kconfig

@@ -15,7 +15,6 @@ config ARM64
 	select ARCH_HAS_DMA_COHERENT_TO_PFN
 	select ARCH_HAS_DMA_PREP_COHERENT
 	select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
-	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
@@ -71,6 +70,7 @@ config ARM64
 	select ARCH_SUPPORTS_INT128 if GCC_VERSION >= 50000 || CC_IS_CLANG
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT
+	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_HUGE_PMD_SHARE if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36)
 	select ARCH_HAS_UBSAN_SANITIZE_ALL

arch/arm64/include/asm/pgalloc.h

@@ -15,8 +15,6 @@
 
 #include <asm-generic/pgalloc.h>	/* for pte_{alloc,free}_one */
 
-#define check_pgt_cache()		do { } while (0)
-
 #define PGD_SIZE	(PTRS_PER_PGD * sizeof(pgd_t))
 
 #if CONFIG_PGTABLE_LEVELS > 2

arch/arm64/include/asm/pgtable.h

@@ -861,8 +861,6 @@ extern int kern_addr_valid(unsigned long addr);
 
 #include <asm-generic/pgtable.h>
 
-static inline void pgtable_cache_init(void) { }
-
 /*
  * On AArch64, the cache coherency is handled via the set_pte_at() function.
  */

arch/arm64/include/asm/processor.h

@@ -280,8 +280,6 @@ static inline void spin_lock_prefetch(const void *ptr)
 		     "nop") : : "p" (ptr));
 }
 
-#define HAVE_ARCH_PICK_MMAP_LAYOUT
-
 extern unsigned long __ro_after_init signal_minsigstksz; /* sigframe size */
 extern void __init minsigstksz_setup(void);
 

arch/arm64/kernel/process.c

@@ -557,14 +557,6 @@ unsigned long arch_align_stack(unsigned long sp)
 	return sp & ~0xf;
 }
 
-unsigned long arch_randomize_brk(struct mm_struct *mm)
-{
-	if (is_compat_task())
-		return randomize_page(mm->brk, SZ_32M);
-	else
-		return randomize_page(mm->brk, SZ_1G);
-}
-
 /*
  * Called from setup_new_exec() after (COMPAT_)SET_PERSONALITY.
  */

arch/arm64/mm/flush.c

@@ -56,8 +56,7 @@ void __sync_icache_dcache(pte_t pte)
 	struct page *page = pte_page(pte);
 
 	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
-		sync_icache_aliases(page_address(page),
+		sync_icache_aliases(page_address(page), page_size(page));
-				    PAGE_SIZE << compound_order(page));
 }
 EXPORT_SYMBOL_GPL(__sync_icache_dcache);
 

arch/arm64/mm/mmap.c

@@ -20,78 +20,6 @@
 
 #include <asm/cputype.h>
 
-/*
- * Leave enough space between the mmap area and the stack to honour ulimit in
- * the face of randomisation.
- */
-#define MIN_GAP (SZ_128M)
-#define MAX_GAP	(STACK_TOP/6*5)
-
-static int mmap_is_legacy(struct rlimit *rlim_stack)
-{
-	if (current->personality & ADDR_COMPAT_LAYOUT)
-		return 1;
-
-	if (rlim_stack->rlim_cur == RLIM_INFINITY)
-		return 1;
-
-	return sysctl_legacy_va_layout;
-}
-
-unsigned long arch_mmap_rnd(void)
-{
-	unsigned long rnd;
-
-#ifdef CONFIG_COMPAT
-	if (test_thread_flag(TIF_32BIT))
-		rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
-	else
-#endif
-		rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
-	return rnd << PAGE_SHIFT;
-}
-
-static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
-{
-	unsigned long gap = rlim_stack->rlim_cur;
-	unsigned long pad = (STACK_RND_MASK << PAGE_SHIFT) + stack_guard_gap;
-
-	/* Values close to RLIM_INFINITY can overflow. */
-	if (gap + pad > gap)
-		gap += pad;
-
-	if (gap < MIN_GAP)
-		gap = MIN_GAP;
-	else if (gap > MAX_GAP)
-		gap = MAX_GAP;
-
-	return PAGE_ALIGN(STACK_TOP - gap - rnd);
-}
-
-/*
- * This function, called very early during the creation of a new process VM
- * image, sets up which VM layout function to use:
- */
-void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
-{
-	unsigned long random_factor = 0UL;
-
-	if (current->flags & PF_RANDOMIZE)
-		random_factor = arch_mmap_rnd();
-
-	/*
-	 * Fall back to the standard layout if the personality bit is set, or
-	 * if the expected stack growth is unlimited:
-	 */
-	if (mmap_is_legacy(rlim_stack)) {
-		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
-		mm->get_unmapped_area = arch_get_unmapped_area;
-	} else {
-		mm->mmap_base = mmap_base(random_factor, rlim_stack);
-		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
-	}
-}
-
 /*
  * You really shouldn't be using read() or write() on /dev/mem.  This might go
  * away in the future.

arch/arm64/mm/pgd.c

@@ -35,7 +35,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 		kmem_cache_free(pgd_cache, pgd);
 }
 
-void __init pgd_cache_init(void)
+void __init pgtable_cache_init(void)
 {
 	if (PGD_SIZE == PAGE_SIZE)
 		return;

arch/c6x/include/asm/pgtable.h

@@ -59,11 +59,6 @@ extern unsigned long empty_zero_page;
 
 #define swapper_pg_dir ((pgd_t *) 0)
 
-/*
- * No page table caches to initialise
- */
-#define pgtable_cache_init()   do { } while (0)
-
 /*
  * c6x is !MMU, so define the simpliest implementation
  */

arch/csky/include/asm/pgalloc.h

@@ -75,8 +75,6 @@ do {							\
 	tlb_remove_page(tlb, pte);			\
 } while (0)
 
-#define check_pgt_cache()	do {} while (0)
-
 extern void pagetable_init(void);
 extern void pre_mmu_init(void);
 extern void pre_trap_init(void);

arch/csky/include/asm/pgtable.h

@@ -296,11 +296,6 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
 /* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
 #define kern_addr_valid(addr)	(1)
 
-/*
- * No page table caches to initialise
- */
-#define pgtable_cache_init()	do {} while (0)
-
 #define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \
 	remap_pfn_range(vma, vaddr, pfn, size, prot)
 

arch/h8300/include/asm/pgtable.h

@@ -4,7 +4,6 @@
 #define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 #include <asm-generic/pgtable.h>
-#define pgtable_cache_init()   do { } while (0)
 extern void paging_init(void);
 #define PAGE_NONE		__pgprot(0)    /* these mean nothing to NO_MM */
 #define PAGE_SHARED		__pgprot(0)    /* these mean nothing to NO_MM */
@@ -34,11 +33,6 @@ static inline int pte_file(pte_t pte) { return 0; }
 extern unsigned int kobjsize(const void *objp);
 extern int is_in_rom(unsigned long);
 
-/*
- * No page table caches to initialise
- */
-#define pgtable_cache_init()   do { } while (0)
-
 /*
  * All 32bit addresses are effectively valid for vmalloc...
  * Sort of meaningless for non-VM targets.

arch/hexagon/include/asm/pgalloc.h

@@ -13,8 +13,6 @@
 
 #include <asm-generic/pgalloc.h>	/* for pte_{alloc,free}_one */
 
-#define check_pgt_cache() do {} while (0)
-
 extern unsigned long long kmap_generation;
 
 /*

arch/hexagon/include/asm/pgtable.h

@@ -431,9 +431,6 @@ static inline int pte_exec(pte_t pte)
 
 #define __pte_offset(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
 
-/*  I think this is in case we have page table caches; needed by init/main.c  */
-#define pgtable_cache_init()    do { } while (0)
-
 /*
  * Swap/file PTE definitions.  If _PAGE_PRESENT is zero, the rest of the PTE is
  * interpreted as swap information.  The remaining free bits are interpreted as

arch/hexagon/mm/Makefile

@@ -3,5 +3,5 @@
 # Makefile for Hexagon memory management subsystem
 #
 
-obj-y := init.o pgalloc.o ioremap.o uaccess.o vm_fault.o cache.o
+obj-y := init.o ioremap.o uaccess.o vm_fault.o cache.o
 obj-y += copy_to_user.o copy_from_user.o strnlen_user.o vm_tlb.o

arch/hexagon/mm/pgalloc.c

@@ -1,10 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
- */
-
-#include <linux/init.h>
-
-void __init pgtable_cache_init(void)
-{
-}

arch/ia64/Kconfig

@@ -72,10 +72,6 @@ config 64BIT
 config ZONE_DMA32
 	def_bool y
 
-config QUICKLIST
-	bool
-	default y
-
 config MMU
 	bool
 	default y

arch/ia64/include/asm/pgalloc.h

@@ -19,18 +19,19 @@
 #include <linux/mm.h>
 #include <linux/page-flags.h>
 #include <linux/threads.h>
-#include <linux/quicklist.h>
+
+#include <asm-generic/pgalloc.h>
 
 #include <asm/mmu_context.h>
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	return quicklist_alloc(0, GFP_KERNEL, NULL);
+	return (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 }
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
-	quicklist_free(0, NULL, pgd);
+	free_page((unsigned long)pgd);
 }
 
 #if CONFIG_PGTABLE_LEVELS == 4
@@ -42,12 +43,12 @@ pgd_populate(struct mm_struct *mm, pgd_t * pgd_entry, pud_t * pud)
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return quicklist_alloc(0, GFP_KERNEL, NULL);
+	return (pud_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 {
-	quicklist_free(0, NULL, pud);
+	free_page((unsigned long)pud);
 }
 #define __pud_free_tlb(tlb, pud, address)	pud_free((tlb)->mm, pud)
 #endif /* CONFIG_PGTABLE_LEVELS == 4 */
@@ -60,12 +61,12 @@ pud_populate(struct mm_struct *mm, pud_t * pud_entry, pmd_t * pmd)
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return quicklist_alloc(0, GFP_KERNEL, NULL);
+	return (pmd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
-	quicklist_free(0, NULL, pmd);
+	free_page((unsigned long)pmd);
 }
 
 #define __pmd_free_tlb(tlb, pmd, address)	pmd_free((tlb)->mm, pmd)
@@ -83,43 +84,6 @@ pmd_populate_kernel(struct mm_struct *mm, pmd_t * pmd_entry, pte_t * pte)
 	pmd_val(*pmd_entry) = __pa(pte);
 }
 
-static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
-{
-	struct page *page;
-	void *pg;
-
-	pg = quicklist_alloc(0, GFP_KERNEL, NULL);
-	if (!pg)
-		return NULL;
-	page = virt_to_page(pg);
-	if (!pgtable_page_ctor(page)) {
-		quicklist_free(0, NULL, pg);
-		return NULL;
-	}
-	return page;
-}
-
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
-{
-	return quicklist_alloc(0, GFP_KERNEL, NULL);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
-{
-	pgtable_page_dtor(pte);
-	quicklist_free_page(0, NULL, pte);
-}
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-	quicklist_free(0, NULL, pte);
-}
-
-static inline void check_pgt_cache(void)
-{
-	quicklist_trim(0, NULL, 25, 16);
-}
-
 #define __pte_free_tlb(tlb, pte, address)	pte_free((tlb)->mm, pte)
 
 #endif				/* _ASM_IA64_PGALLOC_H */

arch/ia64/include/asm/pgtable.h

@@ -566,11 +566,6 @@ extern struct page *zero_page_memmap_ptr;
 #define KERNEL_TR_PAGE_SHIFT	_PAGE_SIZE_64M
 #define KERNEL_TR_PAGE_SIZE	(1 << KERNEL_TR_PAGE_SHIFT)
 
-/*
- * No page table caches to initialise
- */
-#define pgtable_cache_init()	do { } while (0)
-
 /* These tell get_user_pages() that the first gate page is accessible from user-level.  */
 #define FIXADDR_USER_START	GATE_ADDR
 #ifdef HAVE_BUGGY_SEGREL

arch/ia64/mm/init.c

@@ -64,7 +64,7 @@ __ia64_sync_icache_dcache (pte_t pte)
 	if (test_bit(PG_arch_1, &page->flags))
 		return;				/* i-cache is already coherent with d-cache */
 
-	flush_icache_range(addr, addr + (PAGE_SIZE << compound_order(page)));
+	flush_icache_range(addr, addr + page_size(page));
 	set_bit(PG_arch_1, &page->flags);	/* mark page as clean */
 }
 

arch/m68k/include/asm/pgtable_mm.h

@@ -176,11 +176,4 @@ pgprot_t pgprot_dmacoherent(pgprot_t prot);
 #include <asm-generic/pgtable.h>
 #endif /* !__ASSEMBLY__ */
 
-/*
- * No page table caches to initialise
- */
-#define pgtable_cache_init()	do { } while (0)
-
-#define check_pgt_cache()	do { } while (0)
-
 #endif /* _M68K_PGTABLE_H */

arch/m68k/include/asm/pgtable_no.h

@@ -44,11 +44,6 @@ extern void paging_init(void);
  */
 #define ZERO_PAGE(vaddr)	(virt_to_page(0))
 
-/*
- * No page table caches to initialise.
- */
-#define pgtable_cache_init()	do { } while (0)
-
 /*
  * All 32bit addresses are effectively valid for vmalloc...
  * Sort of meaningless for non-VM targets.
@@ -60,6 +55,4 @@ extern void paging_init(void);
 
 #include <asm-generic/pgtable.h>
 
-#define check_pgt_cache()	do { } while (0)
-
 #endif /* _M68KNOMMU_PGTABLE_H */

arch/microblaze/include/asm/pgalloc.h

@@ -21,83 +21,23 @@
 #include <asm/cache.h>
 #include <asm/pgtable.h>
 
-#define PGDIR_ORDER	0
+#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL
-
+#include <asm-generic/pgalloc.h>
-/*
- * This is handled very differently on MicroBlaze since out page tables
- * are all 0's and I want to be able to use these zero'd pages elsewhere
- * as well - it gives us quite a speedup.
- * -- Cort
- */
-extern struct pgtable_cache_struct {
-	unsigned long *pgd_cache;
-	unsigned long *pte_cache;
-	unsigned long pgtable_cache_sz;
-} quicklists;
-
-#define pgd_quicklist		(quicklists.pgd_cache)
-#define pmd_quicklist		((unsigned long *)0)
-#define pte_quicklist		(quicklists.pte_cache)
-#define pgtable_cache_size	(quicklists.pgtable_cache_sz)
-
-extern unsigned long *zero_cache; /* head linked list of pre-zero'd pages */
-extern atomic_t zero_sz; /* # currently pre-zero'd pages */
-extern atomic_t zeropage_hits; /* # zero'd pages request that we've done */
-extern atomic_t zeropage_calls; /* # zero'd pages request that've been made */
-extern atomic_t zerototal; /* # pages zero'd over time */
-
-#define zero_quicklist		(zero_cache)
-#define zero_cache_sz	 	(zero_sz)
-#define zero_cache_calls	(zeropage_calls)
-#define zero_cache_hits		(zeropage_hits)
-#define zero_cache_total	(zerototal)
-
-/*
- * return a pre-zero'd page from the list,
- * return NULL if none available -- Cort
- */
-extern unsigned long get_zero_page_fast(void);
 
 extern void __bad_pte(pmd_t *pmd);
 
-static inline pgd_t *get_pgd_slow(void)
+static inline pgd_t *get_pgd(void)
 {
-	pgd_t *ret;
+	return (pgd_t *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, 0);
-
-	ret = (pgd_t *)__get_free_pages(GFP_KERNEL, PGDIR_ORDER);
-	if (ret != NULL)
-		clear_page(ret);
-	return ret;
 }
 
-static inline pgd_t *get_pgd_fast(void)
+static inline void free_pgd(pgd_t *pgd)
-{
-	unsigned long *ret;
-
-	ret = pgd_quicklist;
-	if (ret != NULL) {
-		pgd_quicklist = (unsigned long *)(*ret);
-		ret[0] = 0;
-		pgtable_cache_size--;
-	} else
-		ret = (unsigned long *)get_pgd_slow();
-	return (pgd_t *)ret;
-}
-
-static inline void free_pgd_fast(pgd_t *pgd)
-{
-	*(unsigned long **)pgd = pgd_quicklist;
-	pgd_quicklist = (unsigned long *) pgd;
-	pgtable_cache_size++;
-}
-
-static inline void free_pgd_slow(pgd_t *pgd)
 {
 	free_page((unsigned long)pgd);
 }
 
-#define pgd_free(mm, pgd)        free_pgd_fast(pgd)
+#define pgd_free(mm, pgd)	free_pgd(pgd)
-#define pgd_alloc(mm)		get_pgd_fast()
+#define pgd_alloc(mm)		get_pgd()
 
 #define pmd_pgtable(pmd)	pmd_page(pmd)
 
@@ -110,50 +50,6 @@ static inline void free_pgd_slow(pgd_t *pgd)
 
 extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm);
 
-static inline struct page *pte_alloc_one(struct mm_struct *mm)
-{
-	struct page *ptepage;
-
-#ifdef CONFIG_HIGHPTE
-	int flags = GFP_KERNEL | __GFP_HIGHMEM;
-#else
-	int flags = GFP_KERNEL;
-#endif
-
-	ptepage = alloc_pages(flags, 0);
-	if (!ptepage)
-		return NULL;
-	clear_highpage(ptepage);
-	if (!pgtable_page_ctor(ptepage)) {
-		__free_page(ptepage);
-		return NULL;
-	}
-	return ptepage;
-}
-
-static inline void pte_free_fast(pte_t *pte)
-{
-	*(unsigned long **)pte = pte_quicklist;
-	pte_quicklist = (unsigned long *) pte;
-	pgtable_cache_size++;
-}
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-	free_page((unsigned long)pte);
-}
-
-static inline void pte_free_slow(struct page *ptepage)
-{
-	__free_page(ptepage);
-}
-
-static inline void pte_free(struct mm_struct *mm, struct page *ptepage)
-{
-	pgtable_page_dtor(ptepage);
-	__free_page(ptepage);
-}
-
 #define __pte_free_tlb(tlb, pte, addr)	pte_free((tlb)->mm, (pte))
 
 #define pmd_populate(mm, pmd, pte) \
@@ -171,10 +67,6 @@ static inline void pte_free(struct mm_struct *mm, struct page *ptepage)
 #define __pmd_free_tlb(tlb, x, addr)	pmd_free((tlb)->mm, x)
 #define pgd_populate(mm, pmd, pte)	BUG()
 
-extern int do_check_pgt_cache(int, int);
-
 #endif /* CONFIG_MMU */
 
-#define check_pgt_cache()		do { } while (0)
-
 #endif /* _ASM_MICROBLAZE_PGALLOC_H */

arch/microblaze/include/asm/pgtable.h

@@ -46,8 +46,6 @@ extern int mem_init_done;
 
 #define swapper_pg_dir ((pgd_t *) NULL)
 
-#define pgtable_cache_init()	do {} while (0)
-
 #define arch_enter_lazy_cpu_mode()	do {} while (0)
 
 #define pgprot_noncached_wc(prot)	prot
@@ -526,11 +524,6 @@ extern unsigned long iopa(unsigned long addr);
 /* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
 #define kern_addr_valid(addr)	(1)
 
-/*
- * No page table caches to initialise
- */
-#define pgtable_cache_init()	do { } while (0)
-
 void do_page_fault(struct pt_regs *regs, unsigned long address,
 		   unsigned long error_code);
 

arch/microblaze/mm/pgtable.c

@@ -44,10 +44,6 @@ unsigned long ioremap_base;
 unsigned long ioremap_bot;
 EXPORT_SYMBOL(ioremap_bot);
 
-#ifndef CONFIG_SMP
-struct pgtable_cache_struct quicklists;
-#endif
-
 static void __iomem *__ioremap(phys_addr_t addr, unsigned long size,
 		unsigned long flags)
 {

arch/mips/Kconfig

@@ -5,7 +5,6 @@ config MIPS
 	select ARCH_32BIT_OFF_T if !64BIT
 	select ARCH_BINFMT_ELF_STATE if MIPS_FP_SUPPORT
 	select ARCH_CLOCKSOURCE_DATA
-	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARCH_SUPPORTS_UPROBES
@@ -13,6 +12,7 @@ config MIPS
 	select ARCH_USE_CMPXCHG_LOCKREF if 64BIT
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
+	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS

arch/mips/include/asm/pgalloc.h

@@ -105,8 +105,6 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
 
 #endif /* __PAGETABLE_PUD_FOLDED */
 
-#define check_pgt_cache()	do { } while (0)
-
 extern void pagetable_init(void);
 
 #endif /* _ASM_PGALLOC_H */

arch/mips/include/asm/pgtable.h

@@ -661,9 +661,4 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 #define HAVE_ARCH_UNMAPPED_AREA
 #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
 
-/*
- * No page table caches to initialise
- */
-#define pgtable_cache_init()	do { } while (0)
-
 #endif /* _ASM_PGTABLE_H */

arch/mips/include/asm/processor.h

@@ -29,11 +29,6 @@
 
 extern unsigned int vced_count, vcei_count;
 
-/*
- * MIPS does have an arch_pick_mmap_layout()
- */
-#define HAVE_ARCH_PICK_MMAP_LAYOUT 1
-
 #ifdef CONFIG_32BIT
 #ifdef CONFIG_KVM_GUEST
 /* User space process size is limited to 1GB in KVM Guest Mode */

arch/mips/mm/mmap.c

@@ -20,33 +20,6 @@
 unsigned long shm_align_mask = PAGE_SIZE - 1;	/* Sane caches */
 EXPORT_SYMBOL(shm_align_mask);
 
-/* gap between mmap and stack */
-#define MIN_GAP (128*1024*1024UL)
-#define MAX_GAP ((TASK_SIZE)/6*5)
-
-static int mmap_is_legacy(struct rlimit *rlim_stack)
-{
-	if (current->personality & ADDR_COMPAT_LAYOUT)
-		return 1;
-
-	if (rlim_stack->rlim_cur == RLIM_INFINITY)
-		return 1;
-
-	return sysctl_legacy_va_layout;
-}
-
-static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
-{
-	unsigned long gap = rlim_stack->rlim_cur;
-
-	if (gap < MIN_GAP)
-		gap = MIN_GAP;
-	else if (gap > MAX_GAP)
-		gap = MAX_GAP;
-
-	return PAGE_ALIGN(TASK_SIZE - gap - rnd);
-}
-
 #define COLOUR_ALIGN(addr, pgoff)				\
 	((((addr) + shm_align_mask) & ~shm_align_mask) +	\
 	 (((pgoff) << PAGE_SHIFT) & shm_align_mask))
@@ -144,63 +117,6 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp,
 			addr0, len, pgoff, flags, DOWN);
 }
 
-unsigned long arch_mmap_rnd(void)
-{
-	unsigned long rnd;
-
-#ifdef CONFIG_COMPAT
-	if (TASK_IS_32BIT_ADDR)
-		rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
-	else
-#endif /* CONFIG_COMPAT */
-		rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
-
-	return rnd << PAGE_SHIFT;
-}
-
-void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
-{
-	unsigned long random_factor = 0UL;
-
-	if (current->flags & PF_RANDOMIZE)
-		random_factor = arch_mmap_rnd();
-
-	if (mmap_is_legacy(rlim_stack)) {
-		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
-		mm->get_unmapped_area = arch_get_unmapped_area;
-	} else {
-		mm->mmap_base = mmap_base(random_factor, rlim_stack);
-		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
-	}
-}
-
-static inline unsigned long brk_rnd(void)
-{
-	unsigned long rnd = get_random_long();
-
-	rnd = rnd << PAGE_SHIFT;
-	/* 8MB for 32bit, 256MB for 64bit */
-	if (TASK_IS_32BIT_ADDR)
-		rnd = rnd & 0x7ffffful;
-	else
-		rnd = rnd & 0xffffffful;
-
-	return rnd;
-}
-
-unsigned long arch_randomize_brk(struct mm_struct *mm)
-{
-	unsigned long base = mm->brk;
-	unsigned long ret;
-
-	ret = PAGE_ALIGN(base + brk_rnd());
-
-	if (ret < mm->brk)
-		return mm->brk;
-
-	return ret;
-}
-
 bool __virt_addr_valid(const volatile void *kaddr)
 {
 	unsigned long vaddr = (unsigned long)kaddr;

arch/nds32/include/asm/pgalloc.h

@@ -23,8 +23,6 @@
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
 extern void pgd_free(struct mm_struct *mm, pgd_t * pgd);
 
-#define check_pgt_cache()		do { } while (0)
-
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
 {
 	pgtable_t pte;

arch/nds32/include/asm/pgtable.h

@@ -403,8 +403,6 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
  * into virtual address `from'
  */
 
-#define pgtable_cache_init()       do { } while (0)
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASMNDS32_PGTABLE_H */

arch/nios2/include/asm/pgalloc.h

@@ -45,6 +45,4 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 		tlb_remove_page((tlb), (pte));			\
 	} while (0)
 
-#define check_pgt_cache()	do { } while (0)
-
 #endif /* _ASM_NIOS2_PGALLOC_H */

arch/nios2/include/asm/pgtable.h

@@ -291,8 +291,6 @@ static inline void pte_clear(struct mm_struct *mm,
 
 #include <asm-generic/pgtable.h>
 
-#define pgtable_cache_init()		do { } while (0)
-
 extern void __init paging_init(void);
 extern void __init mmu_init(void);
 

arch/openrisc/include/asm/pgalloc.h

@@ -101,6 +101,4 @@ do {					\
 
 #define pmd_pgtable(pmd) pmd_page(pmd)
 
-#define check_pgt_cache()          do { } while (0)
-
 #endif

arch/openrisc/include/asm/pgtable.h

@@ -443,11 +443,6 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 
 #include <asm-generic/pgtable.h>
 
-/*
- * No page table caches to initialise
- */
-#define pgtable_cache_init()		do { } while (0)
-
 typedef pte_t *pte_addr_t;
 
 #endif /* __ASSEMBLY__ */

arch/parisc/include/asm/pgalloc.h

@@ -124,6 +124,4 @@ pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
 	pmd_populate_kernel(mm, pmd, page_address(pte_page))
 #define pmd_pgtable(pmd) pmd_page(pmd)
 
-#define check_pgt_cache()	do { } while (0)
-
 #endif

arch/parisc/include/asm/pgtable.h

@@ -132,8 +132,6 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
 #define PTRS_PER_PTE    (1UL << BITS_PER_PTE)
 
 /* Definitions for 2nd level */
-#define pgtable_cache_init()	do { } while (0)
-
 #define PMD_SHIFT       (PLD_SHIFT + BITS_PER_PTE)
 #define PMD_SIZE	(1UL << PMD_SHIFT)
 #define PMD_MASK	(~(PMD_SIZE-1))

arch/powerpc/include/asm/pgalloc.h

@@ -64,8 +64,6 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 extern struct kmem_cache *pgtable_cache[];
 #define PGT_CACHE(shift) pgtable_cache[shift]
 
-static inline void check_pgt_cache(void) { }
-
 #ifdef CONFIG_PPC_BOOK3S
 #include <asm/book3s/pgalloc.h>
 #else

arch/powerpc/include/asm/pgtable.h

@@ -87,7 +87,6 @@ extern unsigned long ioremap_bot;
 unsigned long vmalloc_to_phys(void *vmalloc_addr);
 
 void pgtable_cache_add(unsigned int shift);
-void pgtable_cache_init(void);
 
 #if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_PPC32)
 void mark_initmem_nx(void);

arch/powerpc/mm/book3s64/hash_utils.c

@@ -1748,7 +1748,7 @@ void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
 	/*
 	 * IF we try to do a HUGE PTE update after a withdraw is done.
 	 * we will find the below NULL. This happens when we do
-	 * split_huge_page_pmd
+	 * split_huge_pmd
 	 */
 	if (!hpte_slot_array)
 		return;

arch/powerpc/mm/book3s64/iommu_api.c

@@ -129,11 +129,8 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 		 * Allow to use larger than 64k IOMMU pages. Only do that
 		 * if we are backed by hugetlb.
 		 */
-		if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page)) {
+		if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page))
-			struct page *head = compound_head(page);
+			pageshift = page_shift(compound_head(page));
-
-			pageshift = compound_order(head) + PAGE_SHIFT;
-		}
 		mem->pageshift = min(mem->pageshift, pageshift);
 		/*
 		 * We don't need struct page reference any more, switch

arch/powerpc/mm/hugetlbpage.c

@@ -667,7 +667,7 @@ void flush_dcache_icache_hugepage(struct page *page)
 
 	BUG_ON(!PageCompound(page));
 
-	for (i = 0; i < (1UL << compound_order(page)); i++) {
+	for (i = 0; i < compound_nr(page); i++) {
 		if (!PageHighMem(page)) {
 			__flush_dcache_icache(page_address(page+i));
 		} else {

arch/riscv/Kconfig

@@ -59,6 +59,18 @@ config RISCV
 	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
 	select SPARSEMEM_STATIC if 32BIT
+	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
+	select HAVE_ARCH_MMAP_RND_BITS
+
+config ARCH_MMAP_RND_BITS_MIN
+	default 18 if 64BIT
+	default 8
+
+# max bits determined by the following formula:
+#  VA_BITS - PAGE_SHIFT - 3
+config ARCH_MMAP_RND_BITS_MAX
+	default 24 if 64BIT # SV39 based
+	default 17
 
 config MMU
 	def_bool y

arch/riscv/include/asm/pgalloc.h

@@ -82,8 +82,4 @@ do {                                    \
 	tlb_remove_page((tlb), pte);    \
 } while (0)
 
-static inline void check_pgt_cache(void)
-{
-}
-
 #endif /* _ASM_RISCV_PGALLOC_H */

arch/riscv/include/asm/pgtable.h

@@ -424,11 +424,6 @@ extern void *dtb_early_va;
 extern void setup_bootmem(void);
 extern void paging_init(void);
 
-static inline void pgtable_cache_init(void)
-{
-	/* No page table caches to initialize */
-}
-
 #define VMALLOC_SIZE     (KERN_VIRT_SIZE >> 1)
 #define VMALLOC_END      (PAGE_OFFSET - 1)
 #define VMALLOC_START    (PAGE_OFFSET - VMALLOC_SIZE)

arch/s390/include/asm/pgtable.h

@@ -1682,12 +1682,6 @@ extern void s390_reset_cmma(struct mm_struct *mm);
 #define HAVE_ARCH_UNMAPPED_AREA
 #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
 
-/*
- * No page table caches to initialise
- */
-static inline void pgtable_cache_init(void) { }
-static inline void check_pgt_cache(void) { }
-
 #include <asm-generic/pgtable.h>
 
 #endif /* _S390_PAGE_H */

arch/sh/include/asm/pgalloc.h

@@ -2,10 +2,8 @@
 #ifndef __ASM_SH_PGALLOC_H
 #define __ASM_SH_PGALLOC_H
 
-#include <linux/quicklist.h>
 #include <asm/page.h>
-
+#include <asm-generic/pgalloc.h>
-#define QUICK_PT 0	/* Other page table pages that are zero on free */
 
 extern pgd_t *pgd_alloc(struct mm_struct *);
 extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
@@ -29,41 +27,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 }
 #define pmd_pgtable(pmd) pmd_page(pmd)
 
-/*
- * Allocate and free page tables.
- */
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
-{
-	return quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
-}
-
-static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
-{
-	struct page *page;
-	void *pg;
-
-	pg = quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
-	if (!pg)
-		return NULL;
-	page = virt_to_page(pg);
-	if (!pgtable_page_ctor(page)) {
-		quicklist_free(QUICK_PT, NULL, pg);
-		return NULL;
-	}
-	return page;
-}
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-	quicklist_free(QUICK_PT, NULL, pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
-{
-	pgtable_page_dtor(pte);
-	quicklist_free_page(QUICK_PT, NULL, pte);
-}
-
 #define __pte_free_tlb(tlb,pte,addr)			\
 do {							\
 	pgtable_page_dtor(pte);				\
@@ -79,9 +42,4 @@ do {							\
 } while (0);
 #endif
 
-static inline void check_pgt_cache(void)
-{
-	quicklist_trim(QUICK_PT, NULL, 25, 16);
-}
-
 #endif /* __ASM_SH_PGALLOC_H */

arch/sh/include/asm/pgtable.h

@@ -123,11 +123,6 @@ typedef pte_t *pte_addr_t;
 
 #define pte_pfn(x)		((unsigned long)(((x).pte_low >> PAGE_SHIFT)))
 
-/*
- * Initialise the page table caches
- */
-extern void pgtable_cache_init(void);
-
 struct vm_area_struct;
 struct mm_struct;
 

arch/sh/mm/Kconfig

@@ -1,9 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 menu "Memory management options"
 
-config QUICKLIST
-	def_bool y
-
 config MMU
         bool "Support for memory management hardware"
 	depends on !CPU_SH2

arch/sh/mm/nommu.c

@@ -97,7 +97,3 @@ void __init page_table_range_init(unsigned long start, unsigned long end,
 void __set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t prot)
 {
 }
-
-void pgtable_cache_init(void)
-{
-}

arch/sparc/include/asm/pgalloc_32.h

@@ -17,8 +17,6 @@ void srmmu_free_nocache(void *addr, int size);
 
 extern struct resource sparc_iomap;
 
-#define check_pgt_cache()	do { } while (0)
-
 pgd_t *get_pgd_fast(void);
 static inline void free_pgd_fast(pgd_t *pgd)
 {

arch/sparc/include/asm/pgalloc_64.h

@@ -69,8 +69,6 @@ void pte_free(struct mm_struct *mm, pgtable_t ptepage);
 #define pmd_populate(MM, PMD, PTE)		pmd_set(MM, PMD, PTE)
 #define pmd_pgtable(PMD)			((pte_t *)__pmd_page(PMD))
 
-#define check_pgt_cache()	do { } while (0)
-
 void pgtable_free(void *table, bool is_page);
 
 #ifdef CONFIG_SMP

arch/sparc/include/asm/pgtable_32.h

@@ -445,9 +445,4 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma,
 /* We provide our own get_unmapped_area to cope with VA holes for userland */
 #define HAVE_ARCH_UNMAPPED_AREA
 
-/*
- * No page table caches to initialise
- */
-#define pgtable_cache_init()	do { } while (0)
-
 #endif /* !(_SPARC_PGTABLE_H) */

arch/sparc/include/asm/pgtable_64.h

@@ -1135,7 +1135,6 @@ unsigned long get_fb_unmapped_area(struct file *filp, unsigned long,
 				   unsigned long);
 #define HAVE_ARCH_FB_UNMAPPED_AREA
 
-void pgtable_cache_init(void);
 void sun4v_register_fault_status(void);
 void sun4v_ktsb_register(void);
 void __init cheetah_ecache_flush_init(void);

arch/sparc/mm/init_32.c

@@ -31,7 +31,6 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/vaddrs.h>
-#include <asm/pgalloc.h>	/* bug in asm-generic/tlb.h: check_pgt_cache */
 #include <asm/setup.h>
 #include <asm/tlb.h>
 #include <asm/prom.h>

arch/um/include/asm/pgalloc.h

@@ -43,7 +43,5 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 #define __pmd_free_tlb(tlb,x, address)   tlb_remove_page((tlb),virt_to_page(x))
 #endif
 
-#define check_pgt_cache()	do { } while (0)
-
 #endif
 

arch/um/include/asm/pgtable.h

@@ -32,8 +32,6 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 /* zero page used for uninitialized stuff */
 extern unsigned long *empty_zero_page;
 
-#define pgtable_cache_init() do ; while (0)
-
 /* Just any arbitrary offset to the start of the vmalloc VM area: the
  * current 8MB value just means that there will be a 8MB "hole" after the
  * physical memory until the kernel virtual memory starts.  That means that

arch/unicore32/include/asm/pgalloc.h

@@ -18,8 +18,6 @@
 #define __HAVE_ARCH_PTE_ALLOC_ONE
 #include <asm-generic/pgalloc.h>
 
-#define check_pgt_cache()		do { } while (0)
-
 #define _PAGE_USER_TABLE	(PMD_TYPE_TABLE | PMD_PRESENT)
 #define _PAGE_KERNEL_TABLE	(PMD_TYPE_TABLE | PMD_PRESENT)
 

arch/unicore32/include/asm/pgtable.h

@@ -285,8 +285,6 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 
 #include <asm-generic/pgtable.h>
 
-#define pgtable_cache_init() do { } while (0)
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __UNICORE_PGTABLE_H__ */

arch/x86/include/asm/pgtable_32.h

@@ -29,8 +29,6 @@ extern pgd_t swapper_pg_dir[1024];
 extern pgd_t initial_page_table[1024];
 extern pmd_t initial_pg_pmd[];
 
-static inline void pgtable_cache_init(void) { }
-static inline void check_pgt_cache(void) { }
 void paging_init(void);
 void sync_initial_page_table(void);
 

arch/x86/include/asm/pgtable_64.h

@@ -241,9 +241,6 @@ extern void cleanup_highmap(void);
 #define HAVE_ARCH_UNMAPPED_AREA
 #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
 
-#define pgtable_cache_init()   do { } while (0)
-#define check_pgt_cache()      do { } while (0)
-
 #define PAGE_AGP    PAGE_KERNEL_NOCACHE
 #define HAVE_PAGE_AGP 1
 

arch/x86/mm/pgtable.c

@@ -357,7 +357,7 @@ static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
 
 static struct kmem_cache *pgd_cache;
 
-void __init pgd_cache_init(void)
+void __init pgtable_cache_init(void)
 {
 	/*
 	 * When PAE kernel is running as a Xen domain, it does not use
@@ -402,10 +402,6 @@ static inline void _pgd_free(pgd_t *pgd)
 }
 #else
 
-void __init pgd_cache_init(void)
-{
-}
-
 static inline pgd_t *_pgd_alloc(void)
 {
 	return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER,

arch/xtensa/include/asm/pgtable.h

@@ -238,7 +238,6 @@ extern void paging_init(void);
 # define swapper_pg_dir NULL
 static inline void paging_init(void) { }
 #endif
-static inline void pgtable_cache_init(void) { }
 
 /*
  * The pmd contains the kernel virtual address of the pte page.

arch/xtensa/include/asm/tlbflush.h

@@ -160,9 +160,6 @@ static inline void invalidate_dtlb_mapping (unsigned address)
 		invalidate_dtlb_entry(tlb_entry);
 }
 
-#define check_pgt_cache()	do { } while (0)
-
-
 /*
  * DO NOT USE THESE FUNCTIONS.  These instructions aren't part of the Xtensa
  * ISA and exist only for test purposes..

drivers/base/memory.c

@@ -100,26 +100,9 @@ unsigned long __weak memory_block_size_bytes(void)
 }
 EXPORT_SYMBOL_GPL(memory_block_size_bytes);
 
-static unsigned long get_memory_block_size(void)
-{
-	unsigned long block_sz;
-
-	block_sz = memory_block_size_bytes();
-
-	/* Validate blk_sz is a power of 2 and not less than section size */
-	if ((block_sz & (block_sz - 1)) || (block_sz < MIN_MEMORY_BLOCK_SIZE)) {
-		WARN_ON(1);
-		block_sz = MIN_MEMORY_BLOCK_SIZE;
-	}
-
-	return block_sz;
-}
-
 /*
- * use this as the physical section index that this memsection
+ * Show the first physical section index (number) of this memory block.
- * uses.
  */
-
 static ssize_t phys_index_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
@@ -131,7 +114,10 @@ static ssize_t phys_index_show(struct device *dev,
 }
 
 /*
- * Show whether the section of memory is likely to be hot-removable
+ * Show whether the memory block is likely to be offlineable (or is already
+ * offline). Once offline, the memory block could be removed. The return
+ * value does, however, not indicate that there is a way to remove the
+ * memory block.
  */
 static ssize_t removable_show(struct device *dev, struct device_attribute *attr,
 			      char *buf)
@@ -455,12 +441,12 @@ static DEVICE_ATTR_RO(phys_device);
 static DEVICE_ATTR_RO(removable);
 
 /*
- * Block size attribute stuff
+ * Show the memory block size (shared by all memory blocks).
  */
 static ssize_t block_size_bytes_show(struct device *dev,
 				     struct device_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%lx\n", get_memory_block_size());
+	return sprintf(buf, "%lx\n", memory_block_size_bytes());
 }
 
 static DEVICE_ATTR_RO(block_size_bytes);
@@ -670,10 +656,10 @@ static int init_memory_block(struct memory_block **memory,
 		return -ENOMEM;
 
 	mem->start_section_nr = block_id * sections_per_block;
-	mem->end_section_nr = mem->start_section_nr + sections_per_block - 1;
 	mem->state = state;
 	start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	mem->phys_device = arch_get_memory_phys_device(start_pfn);
+	mem->nid = NUMA_NO_NODE;
 
 	ret = register_memory(mem);
 
@@ -810,19 +796,22 @@ static const struct attribute_group *memory_root_attr_groups[] = {
 /*
  * Initialize the sysfs support for memory devices...
  */
-int __init memory_dev_init(void)
+void __init memory_dev_init(void)
 {
 	int ret;
 	int err;
 	unsigned long block_sz, nr;
 
+	/* Validate the configured memory block size */
+	block_sz = memory_block_size_bytes();
+	if (!is_power_of_2(block_sz) || block_sz < MIN_MEMORY_BLOCK_SIZE)
+		panic("Memory block size not suitable: 0x%lx\n", block_sz);
+	sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
+
 	ret = subsys_system_register(&memory_subsys, memory_root_attr_groups);
 	if (ret)
 		goto out;
 
-	block_sz = get_memory_block_size();
-	sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
-
 	/*
 	 * Create entries for memory sections that were found
 	 * during boot and have been initialized
@@ -838,8 +827,7 @@ int __init memory_dev_init(void)
 
 out:
 	if (ret)
-		printk(KERN_ERR "%s() failed: %d\n", __func__, ret);
+		panic("%s() failed: %d\n", __func__, ret);
-	return ret;
 }
 
 /**

drivers/base/node.c

@@ -427,6 +427,8 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       "Node %d AnonHugePages:  %8lu kB\n"
 		       "Node %d ShmemHugePages: %8lu kB\n"
 		       "Node %d ShmemPmdMapped: %8lu kB\n"
+		       "Node %d FileHugePages: %8lu kB\n"
+		       "Node %d FilePmdMapped: %8lu kB\n"
 #endif
 			,
 		       nid, K(node_page_state(pgdat, NR_FILE_DIRTY)),
@@ -452,6 +454,10 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       nid, K(node_page_state(pgdat, NR_SHMEM_THPS) *
 				       HPAGE_PMD_NR),
 		       nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) *
+				       HPAGE_PMD_NR),
+		       nid, K(node_page_state(pgdat, NR_FILE_THPS) *
+				       HPAGE_PMD_NR),
+		       nid, K(node_page_state(pgdat, NR_FILE_PMDMAPPED) *
 				       HPAGE_PMD_NR)
 #endif
 		       );
@@ -756,15 +762,13 @@ static int __ref get_nid_for_pfn(unsigned long pfn)
 static int register_mem_sect_under_node(struct memory_block *mem_blk,
 					 void *arg)
 {
+	unsigned long memory_block_pfns = memory_block_size_bytes() / PAGE_SIZE;
+	unsigned long start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
+	unsigned long end_pfn = start_pfn + memory_block_pfns - 1;
 	int ret, nid = *(int *)arg;
-	unsigned long pfn, sect_start_pfn, sect_end_pfn;
+	unsigned long pfn;
 
-	mem_blk->nid = nid;
+	for (pfn = start_pfn; pfn <= end_pfn; pfn++) {
-
-	sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
-	sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
-	sect_end_pfn += PAGES_PER_SECTION - 1;
-	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
 		int page_nid;
 
 		/*
@@ -789,6 +793,13 @@ static int register_mem_sect_under_node(struct memory_block *mem_blk,
 			if (page_nid != nid)
 				continue;
 		}
+
+		/*
+		 * If this memory block spans multiple nodes, we only indicate
+		 * the last processed node.
+		 */
+		mem_blk->nid = nid;
+
 		ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
 					&mem_blk->dev.kobj,
 					kobject_name(&mem_blk->dev.kobj));
@@ -804,32 +815,18 @@ static int register_mem_sect_under_node(struct memory_block *mem_blk,
 }
 
 /*
- * Unregister memory block device under all nodes that it spans.
+ * Unregister a memory block device under the node it spans. Memory blocks
- * Has to be called with mem_sysfs_mutex held (due to unlinked_nodes).
+ * with multiple nodes cannot be offlined and therefore also never be removed.
  */
 void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
 {
-	unsigned long pfn, sect_start_pfn, sect_end_pfn;
+	if (mem_blk->nid == NUMA_NO_NODE)
-	static nodemask_t unlinked_nodes;
+		return;
 
-	nodes_clear(unlinked_nodes);
+	sysfs_remove_link(&node_devices[mem_blk->nid]->dev.kobj,
-	sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
+			  kobject_name(&mem_blk->dev.kobj));
-	sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
+	sysfs_remove_link(&mem_blk->dev.kobj,
-	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
+			  kobject_name(&node_devices[mem_blk->nid]->dev.kobj));
-		int nid;
-
-		nid = get_nid_for_pfn(pfn);
-		if (nid < 0)
-			continue;
-		if (!node_online(nid))
-			continue;
-		if (node_test_and_set(nid, unlinked_nodes))
-			continue;
-		sysfs_remove_link(&node_devices[nid]->dev.kobj,
-			 kobject_name(&mem_blk->dev.kobj));
-		sysfs_remove_link(&mem_blk->dev.kobj,
-			 kobject_name(&node_devices[nid]->dev.kobj));
-	}
 }
 
 int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn)

drivers/crypto/chelsio/chtls/chtls_io.c

@@ -1078,7 +1078,7 @@ int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 			bool merge;
 
 			if (page)
-				pg_size <<= compound_order(page);
+				pg_size = page_size(page);
 			if (off < pg_size &&
 			    skb_can_coalesce(skb, i, page, off)) {
 				merge = 1;
@@ -1105,8 +1105,7 @@ int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 							   __GFP_NORETRY,
 							   order);
 					if (page)
-						pg_size <<=
+						pg_size <<= order;
-							compound_order(page);
 				}
 				if (!page) {
 					page = alloc_page(gfp);

drivers/gpu/drm/via/via_dmablit.c

@@ -174,7 +174,6 @@ via_map_blit_for_device(struct pci_dev *pdev,
 static void
 via_free_sg_info(struct pci_dev *pdev, drm_via_sg_info_t *vsg)
 {
-	struct page *page;
 	int i;
 
 	switch (vsg->state) {
@@ -189,13 +188,8 @@ via_free_sg_info(struct pci_dev *pdev, drm_via_sg_info_t *vsg)
 		kfree(vsg->desc_pages);
 		/* fall through */
 	case dr_via_pages_locked:
-		for (i = 0; i < vsg->num_pages; ++i) {
+		put_user_pages_dirty_lock(vsg->pages, vsg->num_pages,
-			if (NULL != (page = vsg->pages[i])) {
+					  (vsg->direction == DMA_FROM_DEVICE));
-				if (!PageReserved(page) && (DMA_FROM_DEVICE == vsg->direction))
-					SetPageDirty(page);
-				put_page(page);
-			}
-		}
 		/* fall through */
 	case dr_via_pages_alloc:
 		vfree(vsg->pages);

drivers/infiniband/core/umem.c

@@ -54,10 +54,7 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d
 
 	for_each_sg_page(umem->sg_head.sgl, &sg_iter, umem->sg_nents, 0) {
 		page = sg_page_iter_page(&sg_iter);
-		if (umem->writable && dirty)
+		put_user_pages_dirty_lock(&page, 1, umem->writable && dirty);
-			put_user_pages_dirty_lock(&page, 1);
-		else
-			put_user_page(page);
 	}
 
 	sg_free_table(&umem->sg_head);

drivers/infiniband/hw/hfi1/user_pages.c

@@ -118,10 +118,7 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t np
 void hfi1_release_user_pages(struct mm_struct *mm, struct page **p,
 			     size_t npages, bool dirty)
 {
-	if (dirty)
+	put_user_pages_dirty_lock(p, npages, dirty);
-		put_user_pages_dirty_lock(p, npages);
-	else
-		put_user_pages(p, npages);
 
 	if (mm) { /* during close after signal, mm can be NULL */
 		atomic64_sub(npages, &mm->pinned_vm);

drivers/infiniband/hw/qib/qib_user_pages.c

@@ -40,10 +40,7 @@
 static void __qib_release_user_pages(struct page **p, size_t num_pages,
 				     int dirty)
 {
-	if (dirty)
+	put_user_pages_dirty_lock(p, num_pages, dirty);
-		put_user_pages_dirty_lock(p, num_pages);
-	else
-		put_user_pages(p, num_pages);
 }
 
 /**

drivers/infiniband/hw/usnic/usnic_uiom.c

@@ -75,10 +75,7 @@ static void usnic_uiom_put_pages(struct list_head *chunk_list, int dirty)
 		for_each_sg(chunk->page_list, sg, chunk->nents, i) {
 			page = sg_page(sg);
 			pa = sg_phys(sg);
-			if (dirty)
+			put_user_pages_dirty_lock(&page, 1, dirty);
-				put_user_pages_dirty_lock(&page, 1);
-			else
-				put_user_page(page);
 			usnic_dbg("pa: %pa\n", &pa);
 		}
 		kfree(chunk);

drivers/infiniband/sw/siw/siw_mem.c

@@ -63,15 +63,7 @@ struct siw_mem *siw_mem_id2obj(struct siw_device *sdev, int stag_index)
 static void siw_free_plist(struct siw_page_chunk *chunk, int num_pages,
 			   bool dirty)
 {
-	struct page **p = chunk->plist;
+	put_user_pages_dirty_lock(chunk->plist, num_pages, dirty);
-
-	while (num_pages--) {
-		if (!PageDirty(*p) && dirty)
-			put_user_pages_dirty_lock(p, 1);
-		else
-			put_user_page(*p);
-		p++;
-	}
 }
 
 void siw_umem_release(struct siw_umem *umem, bool dirty)

drivers/staging/android/ion/ion_system_heap.c

@@ -120,7 +120,7 @@ static int ion_system_heap_allocate(struct ion_heap *heap,
 		if (!page)
 			goto free_pages;
 		list_add_tail(&page->lru, &pages);
-		size_remaining -= PAGE_SIZE << compound_order(page);
+		size_remaining -= page_size(page);
 		max_order = compound_order(page);
 		i++;
 	}
@@ -133,7 +133,7 @@ static int ion_system_heap_allocate(struct ion_heap *heap,
 
 	sg = table->sgl;
 	list_for_each_entry_safe(page, tmp_page, &pages, lru) {
-		sg_set_page(sg, page, PAGE_SIZE << compound_order(page), 0);
+		sg_set_page(sg, page, page_size(page), 0);
 		sg = sg_next(sg);
 		list_del(&page->lru);
 	}

drivers/target/tcm_fc/tfc_io.c

@@ -136,8 +136,7 @@ int ft_queue_data_in(struct se_cmd *se_cmd)
 					   page, off_in_page, tlen);
 			fr_len(fp) += tlen;
 			fp_skb(fp)->data_len += tlen;
-			fp_skb(fp)->truesize +=
+			fp_skb(fp)->truesize += page_size(page);
-					PAGE_SIZE << compound_order(page);
 		} else {
 			BUG_ON(!page);
 			from = kmap_atomic(page + (mem_off >> PAGE_SHIFT));

drivers/vfio/vfio_iommu_spapr_tce.c

@@ -176,13 +176,13 @@ static long tce_iommu_register_pages(struct tce_container *container,
 }
 
 static bool tce_page_is_contained(struct mm_struct *mm, unsigned long hpa,
-		unsigned int page_shift)
+		unsigned int it_page_shift)
 {
 	struct page *page;
 	unsigned long size = 0;
 
-	if (mm_iommu_is_devmem(mm, hpa, page_shift, &size))
+	if (mm_iommu_is_devmem(mm, hpa, it_page_shift, &size))
-		return size == (1UL << page_shift);
+		return size == (1UL << it_page_shift);
 
 	page = pfn_to_page(hpa >> PAGE_SHIFT);
 	/*
@@ -190,7 +190,7 @@ static bool tce_page_is_contained(struct mm_struct *mm, unsigned long hpa,
 	 * a page we just found. Otherwise the hardware can get access to
 	 * a bigger memory chunk that it should.
 	 */
-	return (PAGE_SHIFT + compound_order(compound_head(page))) >= page_shift;
+	return page_shift(compound_head(page)) >= it_page_shift;
 }
 
 static inline bool tce_groups_attached(struct tce_container *container)

fs/binfmt_elf.c

@@ -670,26 +670,6 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
  * libraries.  There is no binary dependent code anywhere else.
  */
 
-#ifndef STACK_RND_MASK
-#define STACK_RND_MASK (0x7ff >> (PAGE_SHIFT - 12))	/* 8MB of VA */
-#endif
-
-static unsigned long randomize_stack_top(unsigned long stack_top)
-{
-	unsigned long random_variable = 0;
-
-	if (current->flags & PF_RANDOMIZE) {
-		random_variable = get_random_long();
-		random_variable &= STACK_RND_MASK;
-		random_variable <<= PAGE_SHIFT;
-	}
-#ifdef CONFIG_STACK_GROWSUP
-	return PAGE_ALIGN(stack_top) + random_variable;
-#else
-	return PAGE_ALIGN(stack_top) - random_variable;
-#endif
-}
-
 static int load_elf_binary(struct linux_binprm *bprm)
 {
 	struct file *interpreter = NULL; /* to shut gcc up */

fs/fat/dir.c

@@ -1100,8 +1100,11 @@ static int fat_zeroed_cluster(struct inode *dir, sector_t blknr, int nr_used,
 			err = -ENOMEM;
 			goto error;
 		}
+		/* Avoid race with userspace read via bdev */
+		lock_buffer(bhs[n]);
 		memset(bhs[n]->b_data, 0, sb->s_blocksize);
 		set_buffer_uptodate(bhs[n]);
+		unlock_buffer(bhs[n]);
 		mark_buffer_dirty_inode(bhs[n], dir);
 
 		n++;
@@ -1158,6 +1161,8 @@ int fat_alloc_new_dir(struct inode *dir, struct timespec64 *ts)
 	fat_time_unix2fat(sbi, ts, &time, &date, &time_cs);
 
 	de = (struct msdos_dir_entry *)bhs[0]->b_data;
+	/* Avoid race with userspace read via bdev */
+	lock_buffer(bhs[0]);
 	/* filling the new directory slots ("." and ".." entries) */
 	memcpy(de[0].name, MSDOS_DOT, MSDOS_NAME);
 	memcpy(de[1].name, MSDOS_DOTDOT, MSDOS_NAME);
@@ -1180,6 +1185,7 @@ int fat_alloc_new_dir(struct inode *dir, struct timespec64 *ts)
 	de[0].size = de[1].size = 0;
 	memset(de + 2, 0, sb->s_blocksize - 2 * sizeof(*de));
 	set_buffer_uptodate(bhs[0]);
+	unlock_buffer(bhs[0]);
 	mark_buffer_dirty_inode(bhs[0], dir);
 
 	err = fat_zeroed_cluster(dir, blknr, 1, bhs, MAX_BUF_PER_PAGE);
@@ -1237,11 +1243,14 @@ static int fat_add_new_entries(struct inode *dir, void *slots, int nr_slots,
 
 			/* fill the directory entry */
 			copy = min(size, sb->s_blocksize);
+			/* Avoid race with userspace read via bdev */
+			lock_buffer(bhs[n]);
 			memcpy(bhs[n]->b_data, slots, copy);
+			set_buffer_uptodate(bhs[n]);
+			unlock_buffer(bhs[n]);
+			mark_buffer_dirty_inode(bhs[n], dir);
 			slots += copy;
 			size -= copy;
-			set_buffer_uptodate(bhs[n]);
-			mark_buffer_dirty_inode(bhs[n], dir);
 			if (!size)
 				break;
 			n++;

fs/fat/fatent.c

@@ -388,8 +388,11 @@ static int fat_mirror_bhs(struct super_block *sb, struct buffer_head **bhs,
 				err = -ENOMEM;
 				goto error;
 			}
+			/* Avoid race with userspace read via bdev */
+			lock_buffer(c_bh);
 			memcpy(c_bh->b_data, bhs[n]->b_data, sb->s_blocksize);
 			set_buffer_uptodate(c_bh);
+			unlock_buffer(c_bh);
 			mark_buffer_dirty_inode(c_bh, sbi->fat_inode);
 			if (sb->s_flags & SB_SYNCHRONOUS)
 				err = sync_dirty_buffer(c_bh);

fs/inode.c

@@ -181,6 +181,9 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	mapping->flags = 0;
 	mapping->wb_err = 0;
 	atomic_set(&mapping->i_mmap_writable, 0);
+#ifdef CONFIG_READ_ONLY_THP_FOR_FS
+	atomic_set(&mapping->nr_thps, 0);
+#endif
 	mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
 	mapping->private_data = NULL;
 	mapping->writeback_index = 0;

fs/io_uring.c

@@ -3319,7 +3319,7 @@ static int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
 	}
 
 	page = virt_to_head_page(ptr);
-	if (sz > (PAGE_SIZE << compound_order(page)))
+	if (sz > page_size(page))
 		return -EINVAL;
 
 	pfn = virt_to_phys(ptr) >> PAGE_SHIFT;

fs/jbd2/journal.c

@@ -89,8 +89,6 @@ EXPORT_SYMBOL(jbd2_journal_blocks_per_page);
 EXPORT_SYMBOL(jbd2_journal_invalidatepage);
 EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers);
 EXPORT_SYMBOL(jbd2_journal_force_commit);
-EXPORT_SYMBOL(jbd2_journal_inode_add_write);
-EXPORT_SYMBOL(jbd2_journal_inode_add_wait);
 EXPORT_SYMBOL(jbd2_journal_inode_ranged_write);
 EXPORT_SYMBOL(jbd2_journal_inode_ranged_wait);
 EXPORT_SYMBOL(jbd2_journal_init_jbd_inode);

fs/jbd2/transaction.c

@@ -2622,18 +2622,6 @@ static int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode,
 	return 0;
 }
 
-int jbd2_journal_inode_add_write(handle_t *handle, struct jbd2_inode *jinode)
-{
-	return jbd2_journal_file_inode(handle, jinode,
-			JI_WRITE_DATA | JI_WAIT_DATA, 0, LLONG_MAX);
-}
-
-int jbd2_journal_inode_add_wait(handle_t *handle, struct jbd2_inode *jinode)
-{
-	return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA, 0,
-			LLONG_MAX);
-}
-
 int jbd2_journal_inode_ranged_write(handle_t *handle,
 		struct jbd2_inode *jinode, loff_t start_byte, loff_t length)
 {