Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton: - large KASAN update to use arm's "software tag-based mode" - a few misc things - sh updates - ocfs2 updates - just about all of MM * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (167 commits) kernel/fork.c: mark 'stack_vm_area' with __maybe_unused memcg, oom: notify on oom killer invocation from the charge path mm, swap: fix swapoff with KSM pages include/linux/gfp.h: fix typo mm/hmm: fix memremap.h, move dev_page_fault_t callback to hmm hugetlbfs: Use i_mmap_rwsem to fix page fault/truncate race hugetlbfs: use i_mmap_rwsem for more pmd sharing synchronization memory_hotplug: add missing newlines to debugging output mm: remove __hugepage_set_anon_rmap() include/linux/vmstat.h: remove unused page state adjustment macro mm/page_alloc.c: allow error injection mm: migrate: drop unused argument of migrate_page_move_mapping() blkdev: avoid migration stalls for blkdev pages mm: migrate: provide buffer_migrate_page_norefs() mm: migrate: move migrate_page_lock_buffers() mm: migrate: lock buffers before migrate_page_move_mapping() mm: migration: factor out code to compute expected number of page references mm, page_alloc: enable pcpu_drain with zone capability kmemleak: add config to select auto scan mm/page_alloc.c: don't call kasan_free_pages() at deferred mem init ...
2018-12-28 16:55:46 -08:00
parent 00d59fde85 0f4991e8fd
commit f346b0becb
585 changed files with 5038 additions and 4542 deletions
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -593,6 +593,21 @@ config DEBUG_KMEMLEAK_DEFAULT_OFF
 	  Say Y here to disable kmemleak by default. It can then be enabled
 	  on the command line via kmemleak=on.

+config DEBUG_KMEMLEAK_AUTO_SCAN
+	bool "Enable kmemleak auto scan thread on boot up"
+	default y
+	depends on DEBUG_KMEMLEAK
+	help
+	  Depending on the cpu, kmemleak scan may be cpu intensive and can
+	  stall user tasks at times. This option enables/disables automatic
+	  kmemleak scan at boot up.
+
+	  Say N here to disable kmemleak auto scan thread to stop automatic
+	  scanning. Disabling this option disables automatic reporting of
+	  memory leaks.
+
+	  If unsure, say Y.
+
 config DEBUG_STACK_USAGE
 	bool "Stack utilization instrumentation"
 	depends on DEBUG_KERNEL && !IA64
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -1,36 +1,92 @@
+# This config refers to the generic KASAN mode.
 config HAVE_ARCH_KASAN
 	bool

-if HAVE_ARCH_KASAN
+config HAVE_ARCH_KASAN_SW_TAGS
+	bool
+
+config CC_HAS_KASAN_GENERIC
+	def_bool $(cc-option, -fsanitize=kernel-address)
+
+config CC_HAS_KASAN_SW_TAGS
+	def_bool $(cc-option, -fsanitize=kernel-hwaddress)

 config KASAN
-	bool "KASan: runtime memory debugger"
+	bool "KASAN: runtime memory debugger"
+	depends on (HAVE_ARCH_KASAN && CC_HAS_KASAN_GENERIC) || \
+		   (HAVE_ARCH_KASAN_SW_TAGS && CC_HAS_KASAN_SW_TAGS)
+	depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB)
+	help
+	  Enables KASAN (KernelAddressSANitizer) - runtime memory debugger,
+	  designed to find out-of-bounds accesses and use-after-free bugs.
+	  See Documentation/dev-tools/kasan.rst for details.
+
+choice
+	prompt "KASAN mode"
+	depends on KASAN
+	default KASAN_GENERIC
+	help
+	  KASAN has two modes: generic KASAN (similar to userspace ASan,
+	  x86_64/arm64/xtensa, enabled with CONFIG_KASAN_GENERIC) and
+	  software tag-based KASAN (a version based on software memory
+	  tagging, arm64 only, similar to userspace HWASan, enabled with
+	  CONFIG_KASAN_SW_TAGS).
+	  Both generic and tag-based KASAN are strictly debugging features.
+
+config KASAN_GENERIC
+	bool "Generic mode"
+	depends on HAVE_ARCH_KASAN && CC_HAS_KASAN_GENERIC
 	depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB)
 	select SLUB_DEBUG if SLUB
 	select CONSTRUCTORS
 	select STACKDEPOT
 	help
-	  Enables kernel address sanitizer - runtime memory debugger,
-	  designed to find out-of-bounds accesses and use-after-free bugs.
-	  This is strictly a debugging feature and it requires a gcc version
-	  of 4.9.2 or later. Detection of out of bounds accesses to stack or
-	  global variables requires gcc 5.0 or later.
-	  This feature consumes about 1/8 of available memory and brings about
-	  ~x3 performance slowdown.
+	  Enables generic KASAN mode.
+	  Supported in both GCC and Clang. With GCC it requires version 4.9.2
+	  or later for basic support and version 5.0 or later for detection of
+	  out-of-bounds accesses for stack and global variables and for inline
+	  instrumentation mode (CONFIG_KASAN_INLINE). With Clang it requires
+	  version 3.7.0 or later and it doesn't support detection of
+	  out-of-bounds accesses for global variables yet.
+	  This mode consumes about 1/8th of available memory at kernel start
+	  and introduces an overhead of ~x1.5 for the rest of the allocations.
+	  The performance slowdown is ~x3.
 	  For better error detection enable CONFIG_STACKTRACE.
-	  Currently CONFIG_KASAN doesn't work with CONFIG_DEBUG_SLAB
+	  Currently CONFIG_KASAN_GENERIC doesn't work with CONFIG_DEBUG_SLAB
 	  (the resulting kernel does not boot).

-config KASAN_EXTRA
-	bool "KAsan: extra checks"
-	depends on KASAN && DEBUG_KERNEL && !COMPILE_TEST
+config KASAN_SW_TAGS
+	bool "Software tag-based mode"
+	depends on HAVE_ARCH_KASAN_SW_TAGS && CC_HAS_KASAN_SW_TAGS
+	depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB)
+	select SLUB_DEBUG if SLUB
+	select CONSTRUCTORS
+	select STACKDEPOT
 	help
-	  This enables further checks in the kernel address sanitizer, for now
-	  it only includes the address-use-after-scope check that can lead
-	  to excessive kernel stack usage, frame size warnings and longer
-	  compile time.
-	  https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 has more
+	  Enables software tag-based KASAN mode.
+	  This mode requires Top Byte Ignore support by the CPU and therefore
+	  is only supported for arm64.
+	  This mode requires Clang version 7.0.0 or later.
+	  This mode consumes about 1/16th of available memory at kernel start
+	  and introduces an overhead of ~20% for the rest of the allocations.
+	  This mode may potentially introduce problems relating to pointer
+	  casting and comparison, as it embeds tags into the top byte of each
+	  pointer.
+	  For better error detection enable CONFIG_STACKTRACE.
+	  Currently CONFIG_KASAN_SW_TAGS doesn't work with CONFIG_DEBUG_SLAB
+	  (the resulting kernel does not boot).

+endchoice
+
+config KASAN_EXTRA
+	bool "KASAN: extra checks"
+	depends on KASAN_GENERIC && DEBUG_KERNEL && !COMPILE_TEST
+	help
+	  This enables further checks in generic KASAN, for now it only
+	  includes the address-use-after-scope check that can lead to
+	  excessive kernel stack usage, frame size warnings and longer
+	  compile time.
+	  See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81715

 choice
 	prompt "Instrumentation type"
@@ -53,7 +109,7 @@ config KASAN_INLINE
 	  memory accesses. This is faster than outline (in some workloads
 	  it gives about x2 boost over outline instrumentation), but
 	  make kernel's .text size much bigger.
-	  This requires a gcc version of 5.0 or later.
+	  For CONFIG_KASAN_GENERIC this requires GCC 5.0 or later.

 endchoice

@@ -67,11 +123,9 @@ config KASAN_S390_4_LEVEL_PAGING
 	  4-level paging instead.

 config TEST_KASAN
-	tristate "Module for testing kasan for bug detection"
+	tristate "Module for testing KASAN for bug detection"
 	depends on m && KASAN
 	help
 	  This is a test module doing various nasty things like
 	  out of bounds accesses, use after free. It is useful for testing
-	  kernel debugging features like kernel address sanitizer.
-
-endif
+	  kernel debugging features like KASAN.
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -1131,11 +1131,10 @@ static int __init debug_objects_replace_static_objects(void)
 	}

 	/*
-	 * When debug_objects_mem_init() is called we know that only
-	 * one CPU is up, so disabling interrupts is enough
-	 * protection. This avoids the lockdep hell of lock ordering.
+	 * debug_objects_mem_init() is now called early that only one CPU is up
+	 * and interrupts have been disabled, so it is safe to replace the
+	 * active object references.
 	 */
-	local_irq_disable();

 	/* Remove the statically allocated objects from the pool */
 	hlist_for_each_entry_safe(obj, tmp, &obj_pool, node)
@@ -1156,7 +1155,6 @@ static int __init debug_objects_replace_static_objects(void)
 			cnt++;
 		}
 	}
-	local_irq_enable();

 	pr_debug("%d of %d active objects replaced\n",
 		 cnt, obj_pool_used);
--- a/lib/ioremap.c
+++ b/lib/ioremap.c
@@ -76,83 +76,123 @@ static int ioremap_pte_range(pmd_t *pmd, unsigned long addr,
 	return 0;
 }

+static int ioremap_try_huge_pmd(pmd_t *pmd, unsigned long addr,
+				unsigned long end, phys_addr_t phys_addr,
+				pgprot_t prot)
+{
+	if (!ioremap_pmd_enabled())
+		return 0;
+
+	if ((end - addr) != PMD_SIZE)
+		return 0;
+
+	if (!IS_ALIGNED(phys_addr, PMD_SIZE))
+		return 0;
+
+	if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr))
+		return 0;
+
+	return pmd_set_huge(pmd, phys_addr, prot);
+}
+
 static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
 		unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
 {
 	pmd_t *pmd;
 	unsigned long next;

-	phys_addr -= addr;
 	pmd = pmd_alloc(&init_mm, pud, addr);
 	if (!pmd)
 		return -ENOMEM;
 	do {
 		next = pmd_addr_end(addr, end);

-		if (ioremap_pmd_enabled() &&
-		    ((next - addr) == PMD_SIZE) &&
-		    IS_ALIGNED(phys_addr + addr, PMD_SIZE) &&
-		    pmd_free_pte_page(pmd, addr)) {
-			if (pmd_set_huge(pmd, phys_addr + addr, prot))
-				continue;
-		}
+		if (ioremap_try_huge_pmd(pmd, addr, next, phys_addr, prot))
+			continue;

-		if (ioremap_pte_range(pmd, addr, next, phys_addr + addr, prot))
+		if (ioremap_pte_range(pmd, addr, next, phys_addr, prot))
 			return -ENOMEM;
-	} while (pmd++, addr = next, addr != end);
+	} while (pmd++, phys_addr += (next - addr), addr = next, addr != end);
 	return 0;
 }

+static int ioremap_try_huge_pud(pud_t *pud, unsigned long addr,
+				unsigned long end, phys_addr_t phys_addr,
+				pgprot_t prot)
+{
+	if (!ioremap_pud_enabled())
+		return 0;
+
+	if ((end - addr) != PUD_SIZE)
+		return 0;
+
+	if (!IS_ALIGNED(phys_addr, PUD_SIZE))
+		return 0;
+
+	if (pud_present(*pud) && !pud_free_pmd_page(pud, addr))
+		return 0;
+
+	return pud_set_huge(pud, phys_addr, prot);
+}
+
 static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
 		unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
 {
 	pud_t *pud;
 	unsigned long next;

-	phys_addr -= addr;
 	pud = pud_alloc(&init_mm, p4d, addr);
 	if (!pud)
 		return -ENOMEM;
 	do {
 		next = pud_addr_end(addr, end);

-		if (ioremap_pud_enabled() &&
-		    ((next - addr) == PUD_SIZE) &&
-		    IS_ALIGNED(phys_addr + addr, PUD_SIZE) &&
-		    pud_free_pmd_page(pud, addr)) {
-			if (pud_set_huge(pud, phys_addr + addr, prot))
-				continue;
-		}
+		if (ioremap_try_huge_pud(pud, addr, next, phys_addr, prot))
+			continue;

-		if (ioremap_pmd_range(pud, addr, next, phys_addr + addr, prot))
+		if (ioremap_pmd_range(pud, addr, next, phys_addr, prot))
 			return -ENOMEM;
-	} while (pud++, addr = next, addr != end);
+	} while (pud++, phys_addr += (next - addr), addr = next, addr != end);
 	return 0;
 }

+static int ioremap_try_huge_p4d(p4d_t *p4d, unsigned long addr,
+				unsigned long end, phys_addr_t phys_addr,
+				pgprot_t prot)
+{
+	if (!ioremap_p4d_enabled())
+		return 0;
+
+	if ((end - addr) != P4D_SIZE)
+		return 0;
+
+	if (!IS_ALIGNED(phys_addr, P4D_SIZE))
+		return 0;
+
+	if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr))
+		return 0;
+
+	return p4d_set_huge(p4d, phys_addr, prot);
+}
+
 static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr,
 		unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
 {
 	p4d_t *p4d;
 	unsigned long next;

-	phys_addr -= addr;
 	p4d = p4d_alloc(&init_mm, pgd, addr);
 	if (!p4d)
 		return -ENOMEM;
 	do {
 		next = p4d_addr_end(addr, end);

-		if (ioremap_p4d_enabled() &&
-		    ((next - addr) == P4D_SIZE) &&
-		    IS_ALIGNED(phys_addr + addr, P4D_SIZE)) {
-			if (p4d_set_huge(p4d, phys_addr + addr, prot))
-				continue;
-		}
+		if (ioremap_try_huge_p4d(p4d, addr, next, phys_addr, prot))
+			continue;

-		if (ioremap_pud_range(p4d, addr, next, phys_addr + addr, prot))
+		if (ioremap_pud_range(p4d, addr, next, phys_addr, prot))
 			return -ENOMEM;
-	} while (p4d++, addr = next, addr != end);
+	} while (p4d++, phys_addr += (next - addr), addr = next, addr != end);
 	return 0;
 }

@@ -168,14 +208,13 @@ int ioremap_page_range(unsigned long addr,
 	BUG_ON(addr >= end);

 	start = addr;
-	phys_addr -= addr;
 	pgd = pgd_offset_k(addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		err = ioremap_p4d_range(pgd, addr, next, phys_addr+addr, prot);
+		err = ioremap_p4d_range(pgd, addr, next, phys_addr, prot);
 		if (err)
 			break;
-	} while (pgd++, addr = next, addr != end);
+	} while (pgd++, phys_addr += (next - addr), addr = next, addr != end);

 	flush_cache_vmap(start, end);

--- a/lib/show_mem.c
+++ b/lib/show_mem.c
@@ -18,22 +18,19 @@ void show_mem(unsigned int filter, nodemask_t *nodemask)
 	show_free_areas(filter, nodemask);

 	for_each_online_pgdat(pgdat) {
-		unsigned long flags;
 		int zoneid;

-		pgdat_resize_lock(pgdat, &flags);
 		for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
 			struct zone *zone = &pgdat->node_zones[zoneid];
 			if (!populated_zone(zone))
 				continue;

 			total += zone->present_pages;
-			reserved += zone->present_pages - zone->managed_pages;
+			reserved += zone->present_pages - zone_managed_pages(zone);

 			if (is_highmem_idx(zoneid))
 				highmem += zone->present_pages;
 		}
-		pgdat_resize_unlock(pgdat, &flags);
 	}

 	printk("%lu pages RAM\n", total);