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 <[email protected]>: (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 ...
berg · Sep 24, 2019 · 9c9fa97 · 9c9fa97
2 parents 5184d44 + 2b38d01
commit 9c9fa97
Show file tree

Hide file tree

Showing 204 changed files with 2,273 additions and 2,444 deletions.
diff --git a/Documentation/ABI/testing/sysfs-kernel-slab b/Documentation/ABI/testing/sysfs-kernel-slab
@@ -429,10 +429,15 @@ KernelVersion:	2.6.22
 Contact:	Pekka Enberg <[email protected]>,
 		Christoph Lameter <[email protected]>
 Description:
-		The shrink file is written when memory should be reclaimed from
-		a cache.  Empty partial slabs are freed and the partial list is
-		sorted so the slabs with the fewest available objects are used
-		first.
+		The shrink file is used to reclaim unused slab cache
+		memory from a cache.  Empty per-cpu or partial slabs
+		are freed and the partial list is sorted so the slabs
+		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

diff --git a/Documentation/admin-guide/cgroup-v1/memory.rst b/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

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/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

diff --git a/arch/Kconfig b/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

diff --git a/arch/alpha/include/asm/pgalloc.h b/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 */
diff --git a/arch/alpha/include/asm/pgtable.h b/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
 

diff --git a/arch/arc/include/asm/pgalloc.h b/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 */
diff --git a/arch/arc/include/asm/pgtable.h b/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
diff --git a/arch/arm/Kconfig b/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

diff --git a/arch/arm/include/asm/pgalloc.h b/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))

diff --git a/arch/arm/include/asm/pgtable-nommu.h b/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.

diff --git a/arch/arm/include/asm/pgtable.h b/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 */

diff --git a/arch/arm/include/asm/processor.h b/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 */
diff --git a/arch/arm/kernel/process.c b/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
 /*

diff --git a/arch/arm/mm/flush.c b/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);
+		__cpuc_flush_dcache_area(page_address(page), page_size(page));
 	} 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);

diff --git a/arch/arm/mm/mmap.c b/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.

diff --git a/arch/arm64/Kconfig b/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

diff --git a/arch/arm64/include/asm/pgalloc.h b/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

diff --git a/arch/arm64/include/asm/pgtable.h b/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.
  */

diff --git a/arch/arm64/include/asm/processor.h b/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);
 

diff --git a/arch/arm64/kernel/process.c b/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.
  */

diff --git a/arch/arm64/mm/flush.c b/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),
-				    PAGE_SIZE << compound_order(page));
+		sync_icache_aliases(page_address(page), page_size(page));
 }
 EXPORT_SYMBOL_GPL(__sync_icache_dcache);
 

diff --git a/arch/arm64/mm/mmap.c b/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.
-Original file line number
+Diff line change
@@ Expand Up / @@ -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 */