Merge branch 'for-linus2' of git://git.kernel.org/pub/scm/linux/kernel/git/vegard/kmemcheck

* 'for-linus2' of git://git.kernel.org/pub/scm/linux/kernel/git/vegard/kmemcheck: (39 commits)
  signal: fix __send_signal() false positive kmemcheck warning
  fs: fix do_mount_root() false positive kmemcheck warning
  fs: introduce __getname_gfp()
  trace: annotate bitfields in struct ring_buffer_event
  net: annotate struct sock bitfield
  c2port: annotate bitfield for kmemcheck
  net: annotate inet_timewait_sock bitfields
  ieee1394/csr1212: fix false positive kmemcheck report
  ieee1394: annotate bitfield
  net: annotate bitfields in struct inet_sock
  net: use kmemcheck bitfields API for skbuff
  kmemcheck: introduce bitfield API
  kmemcheck: add opcode self-testing at boot
  x86: unify pte_hidden
  x86: make _PAGE_HIDDEN conditional
  kmemcheck: make kconfig accessible for other architectures
  kmemcheck: enable in the x86 Kconfig
  kmemcheck: add hooks for the page allocator
  kmemcheck: add hooks for page- and sg-dma-mappings
  kmemcheck: don't track page tables
  ...

6 files changed, 200 insertions, 88 deletions

diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index bb01e298f26..aa99fd1f710 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -2,6 +2,7 @@ config DEBUG_PAGEALLOC
 	bool "Debug page memory allocations"
 	depends on DEBUG_KERNEL && ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	depends on !HIBERNATION || !PPC && !SPARC
+	depends on !KMEMCHECK
 	---help---
 	  Unmap pages from the kernel linear mapping after free_pages().
 	  This results in a large slowdown, but helps to find certain types
diff --git a/mm/Makefile b/mm/Makefile
index e89acb090b4..c379ce08354 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -27,6 +27,7 @@ obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o
 obj-$(CONFIG_PAGE_POISONING) += debug-pagealloc.o
 obj-$(CONFIG_SLAB) += slab.o
 obj-$(CONFIG_SLUB) += slub.o
+obj-$(CONFIG_KMEMCHECK) += kmemcheck.o
 obj-$(CONFIG_FAILSLAB) += failslab.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
diff --git a/mm/kmemcheck.c b/mm/kmemcheck.c
new file mode 100644
index 00000000000..fd814fd6131
--- /dev/null
+++ b/mm/kmemcheck.c
@@ -0,0 +1,122 @@
+#include <linux/gfp.h>
+#include <linux/mm_types.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/kmemcheck.h>
+
+void kmemcheck_alloc_shadow(struct page *page, int order, gfp_t flags, int node)
+{
+	struct page *shadow;
+	int pages;
+	int i;
+
+	pages = 1 << order;
+
+	/*
+	 * With kmemcheck enabled, we need to allocate a memory area for the
+	 * shadow bits as well.
+	 */
+	shadow = alloc_pages_node(node, flags | __GFP_NOTRACK, order);
+	if (!shadow) {
+		if (printk_ratelimit())
+			printk(KERN_ERR "kmemcheck: failed to allocate "
+				"shadow bitmap\n");
+		return;
+	}
+
+	for(i = 0; i < pages; ++i)
+		page[i].shadow = page_address(&shadow[i]);
+
+	/*
+	 * Mark it as non-present for the MMU so that our accesses to
+	 * this memory will trigger a page fault and let us analyze
+	 * the memory accesses.
+	 */
+	kmemcheck_hide_pages(page, pages);
+}
+
+void kmemcheck_free_shadow(struct page *page, int order)
+{
+	struct page *shadow;
+	int pages;
+	int i;
+
+	if (!kmemcheck_page_is_tracked(page))
+		return;
+
+	pages = 1 << order;
+
+	kmemcheck_show_pages(page, pages);
+
+	shadow = virt_to_page(page[0].shadow);
+
+	for(i = 0; i < pages; ++i)
+		page[i].shadow = NULL;
+
+	__free_pages(shadow, order);
+}
+
+void kmemcheck_slab_alloc(struct kmem_cache *s, gfp_t gfpflags, void *object,
+			  size_t size)
+{
+	/*
+	 * Has already been memset(), which initializes the shadow for us
+	 * as well.
+	 */
+	if (gfpflags & __GFP_ZERO)
+		return;
+
+	/* No need to initialize the shadow of a non-tracked slab. */
+	if (s->flags & SLAB_NOTRACK)
+		return;
+
+	if (!kmemcheck_enabled || gfpflags & __GFP_NOTRACK) {
+		/*
+		 * Allow notracked objects to be allocated from
+		 * tracked caches. Note however that these objects
+		 * will still get page faults on access, they just
+		 * won't ever be flagged as uninitialized. If page
+		 * faults are not acceptable, the slab cache itself
+		 * should be marked NOTRACK.
+		 */
+		kmemcheck_mark_initialized(object, size);
+	} else if (!s->ctor) {
+		/*
+		 * New objects should be marked uninitialized before
+		 * they're returned to the called.
+		 */
+		kmemcheck_mark_uninitialized(object, size);
+	}
+}
+
+void kmemcheck_slab_free(struct kmem_cache *s, void *object, size_t size)
+{
+	/* TODO: RCU freeing is unsupported for now; hide false positives. */
+	if (!s->ctor && !(s->flags & SLAB_DESTROY_BY_RCU))
+		kmemcheck_mark_freed(object, size);
+}
+
+void kmemcheck_pagealloc_alloc(struct page *page, unsigned int order,
+			       gfp_t gfpflags)
+{
+	int pages;
+
+	if (gfpflags & (__GFP_HIGHMEM | __GFP_NOTRACK))
+		return;
+
+	pages = 1 << order;
+
+	/*
+	 * NOTE: We choose to track GFP_ZERO pages too; in fact, they
+	 * can become uninitialized by copying uninitialized memory
+	 * into them.
+	 */
+
+	/* XXX: Can use zone->node for node? */
+	kmemcheck_alloc_shadow(page, order, gfpflags, -1);
+
+	if (gfpflags & __GFP_ZERO)
+		kmemcheck_mark_initialized_pages(page, pages);
+	else
+		kmemcheck_mark_uninitialized_pages(page, pages);
+}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 17d5f539a9a..0727896a88a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -23,6 +23,7 @@
 #include <linux/bootmem.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
+#include <linux/kmemcheck.h>
 #include <linux/module.h>
 #include <linux/suspend.h>
 #include <linux/pagevec.h>
@@ -546,6 +547,8 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 	int i;
 	int bad = 0;
 
+	kmemcheck_free_shadow(page, order);
+
 	for (i = 0 ; i < (1 << order) ; ++i)
 		bad += free_pages_check(page + i);
 	if (bad)
@@ -994,6 +997,8 @@ static void free_hot_cold_page(struct page *page, int cold)
 	struct per_cpu_pages *pcp;
 	unsigned long flags;
 
+	kmemcheck_free_shadow(page, 0);
+
 	if (PageAnon(page))
 		page->mapping = NULL;
 	if (free_pages_check(page))
@@ -1047,6 +1052,16 @@ void split_page(struct page *page, unsigned int order)
 
 	VM_BUG_ON(PageCompound(page));
 	VM_BUG_ON(!page_count(page));
+
+#ifdef CONFIG_KMEMCHECK
+	/*
+	 * Split shadow pages too, because free(page[0]) would
+	 * otherwise free the whole shadow.
+	 */
+	if (kmemcheck_page_is_tracked(page))
+		split_page(virt_to_page(page[0].shadow), order);
+#endif
+
 	for (i = 1; i < (1 << order); i++)
 		set_page_refcounted(page + i);
 }
@@ -1667,7 +1682,10 @@ nopage:
 		dump_stack();
 		show_mem();
 	}
+	return page;
 got_pg:
+	if (kmemcheck_enabled)
+		kmemcheck_pagealloc_alloc(page, order, gfp_mask);
 	return page;
 }
 EXPORT_SYMBOL(__alloc_pages_internal);
diff --git a/mm/slab.c b/mm/slab.c
index 18e3164de09..af3376d0a83 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -114,6 +114,7 @@
 #include	<linux/rtmutex.h>
 #include	<linux/reciprocal_div.h>
 #include	<linux/debugobjects.h>
+#include	<linux/kmemcheck.h>
 
 #include	<asm/cacheflush.h>
 #include	<asm/tlbflush.h>
@@ -179,13 +180,13 @@
 			 SLAB_STORE_USER | \
 			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
 			 SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD | \
-			 SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE)
+			 SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE | SLAB_NOTRACK)
 #else
 # define CREATE_MASK	(SLAB_HWCACHE_ALIGN | \
 			 SLAB_CACHE_DMA | \
 			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
 			 SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD | \
-			 SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE)
+			 SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE | SLAB_NOTRACK)
 #endif
 
 /*
@@ -380,87 +381,6 @@ static void kmem_list3_init(struct kmem_list3 *parent)
 	MAKE_LIST((cachep), (&(ptr)->slabs_free), slabs_free, nodeid);	\
 	} while (0)
 
-/*
- * struct kmem_cache
- *
- * manages a cache.
- */
-
-struct kmem_cache {
-/* 1) per-cpu data, touched during every alloc/free */
-	struct array_cache *array[NR_CPUS];
-/* 2) Cache tunables. Protected by cache_chain_mutex */
-	unsigned int batchcount;
-	unsigned int limit;
-	unsigned int shared;
-
-	unsigned int buffer_size;
-	u32 reciprocal_buffer_size;
-/* 3) touched by every alloc & free from the backend */
-
-	unsigned int flags;		/* constant flags */
-	unsigned int num;		/* # of objs per slab */
-
-/* 4) cache_grow/shrink */
-	/* order of pgs per slab (2^n) */
-	unsigned int gfporder;
-
-	/* force GFP flags, e.g. GFP_DMA */
-	gfp_t gfpflags;
-
-	size_t colour;			/* cache colouring range */
-	unsigned int colour_off;	/* colour offset */
-	struct kmem_cache *slabp_cache;
-	unsigned int slab_size;
-	unsigned int dflags;		/* dynamic flags */
-
-	/* constructor func */
-	void (*ctor)(void *obj);
-
-/* 5) cache creation/removal */
-	const char *name;
-	struct list_head next;
-
-/* 6) statistics */
-#if STATS
-	unsigned long num_active;
-	unsigned long num_allocations;
-	unsigned long high_mark;
-	unsigned long grown;
-	unsigned long reaped;
-	unsigned long errors;
-	unsigned long max_freeable;
-	unsigned long node_allocs;
-	unsigned long node_frees;
-	unsigned long node_overflow;
-	atomic_t allochit;
-	atomic_t allocmiss;
-	atomic_t freehit;
-	atomic_t freemiss;
-#endif
-#if DEBUG
-	/*
-	 * If debugging is enabled, then the allocator can add additional
-	 * fields and/or padding to every object. buffer_size contains the total
-	 * object size including these internal fields, the following two
-	 * variables contain the offset to the user object and its size.
-	 */
-	int obj_offset;
-	int obj_size;
-#endif
-	/*
-	 * We put nodelists[] at the end of kmem_cache, because we want to size
-	 * this array to nr_node_ids slots instead of MAX_NUMNODES
-	 * (see kmem_cache_init())
-	 * We still use [MAX_NUMNODES] and not [1] or [0] because cache_cache
-	 * is statically defined, so we reserve the max number of nodes.
-	 */
-	struct kmem_list3 *nodelists[MAX_NUMNODES];
-	/*
-	 * Do not add fields after nodelists[]
-	 */
-};
-
 #define CFLGS_OFF_SLAB		(0x80000000UL)
 #define	OFF_SLAB(x)	((x)->flags & CFLGS_OFF_SLAB)
 
@@ -1707,7 +1627,7 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
 		flags |= __GFP_RECLAIMABLE;
 
-	page = alloc_pages_node(nodeid, flags, cachep->gfporder);
+	page = alloc_pages_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder);
 	if (!page)
 		return NULL;
 
@@ -1720,6 +1640,16 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 			NR_SLAB_UNRECLAIMABLE, nr_pages);
 	for (i = 0; i < nr_pages; i++)
 		__SetPageSlab(page + i);
+
+	if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) {
+		kmemcheck_alloc_shadow(page, cachep->gfporder, flags, nodeid);
+
+		if (cachep->ctor)
+			kmemcheck_mark_uninitialized_pages(page, nr_pages);
+		else
+			kmemcheck_mark_unallocated_pages(page, nr_pages);
+	}
+
 	return page_address(page);
 }
 
@@ -1732,6 +1662,8 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr)
 	struct page *page = virt_to_page(addr);
 	const unsigned long nr_freed = i;
 
+	kmemcheck_free_shadow(page, cachep->gfporder);
+
 	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
 		sub_zone_page_state(page_zone(page),
 				NR_SLAB_RECLAIMABLE, nr_freed);
@@ -3407,6 +3339,9 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
 	kmemleak_alloc_recursive(ptr, obj_size(cachep), 1, cachep->flags,
 				 flags);
 
+	if (likely(ptr))
+		kmemcheck_slab_alloc(cachep, flags, ptr, obj_size(cachep));
+
 	if (unlikely((flags & __GFP_ZERO) && ptr))
 		memset(ptr, 0, obj_size(cachep));
 
@@ -3467,6 +3402,9 @@ __cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller)
 				 flags);
 	prefetchw(objp);
 
+	if (likely(objp))
+		kmemcheck_slab_alloc(cachep, flags, objp, obj_size(cachep));
+
 	if (unlikely((flags & __GFP_ZERO) && objp))
 		memset(objp, 0, obj_size(cachep));
 
@@ -3583,6 +3521,8 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp)
 	kmemleak_free_recursive(objp, cachep->flags);
 	objp = cache_free_debugcheck(cachep, objp, __builtin_return_address(0));
 
+	kmemcheck_slab_free(cachep, objp, obj_size(cachep));
+
 	/*
 	 * Skip calling cache_free_alien() when the platform is not numa.
 	 * This will avoid cache misses that happen while accessing slabp (which
diff --git a/mm/slub.c b/mm/slub.c
index 30354bfeb43..15960a09abb 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -18,6 +18,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/kmemtrace.h>
+#include <linux/kmemcheck.h>
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
 #include <linux/kmemleak.h>
@@ -147,7 +148,7 @@
 		SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE)
 
 #define SLUB_MERGE_SAME (SLAB_DEBUG_FREE | SLAB_RECLAIM_ACCOUNT | \
-		SLAB_CACHE_DMA)
+		SLAB_CACHE_DMA | SLAB_NOTRACK)
 
 #ifndef ARCH_KMALLOC_MINALIGN
 #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long)
@@ -1071,6 +1072,8 @@ static inline struct page *alloc_slab_page(gfp_t flags, int node,
 {
 	int order = oo_order(oo);
 
+	flags |= __GFP_NOTRACK;
+
 	if (node == -1)
 		return alloc_pages(flags, order);
 	else
@@ -1098,6 +1101,24 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 
 		stat(get_cpu_slab(s, raw_smp_processor_id()), ORDER_FALLBACK);
 	}
+
+	if (kmemcheck_enabled
+		&& !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS)))
+	{
+		int pages = 1 << oo_order(oo);
+
+		kmemcheck_alloc_shadow(page, oo_order(oo), flags, node);
+
+		/*
+		 * Objects from caches that have a constructor don't get
+		 * cleared when they're allocated, so we need to do it here.
+		 */
+		if (s->ctor)
+			kmemcheck_mark_uninitialized_pages(page, pages);
+		else
+			kmemcheck_mark_unallocated_pages(page, pages);
+	}
+
 	page->objects = oo_objects(oo);
 	mod_zone_page_state(page_zone(page),
 		(s->flags & SLAB_RECLAIM_ACCOUNT) ?
@@ -1171,6 +1192,8 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
 		__ClearPageSlubDebug(page);
 	}
 
+	kmemcheck_free_shadow(page, compound_order(page));
+
 	mod_zone_page_state(page_zone(page),
 		(s->flags & SLAB_RECLAIM_ACCOUNT) ?
 		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
@@ -1626,7 +1649,9 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
 	if (unlikely((gfpflags & __GFP_ZERO) && object))
 		memset(object, 0, objsize);
 
+	kmemcheck_slab_alloc(s, gfpflags, object, c->objsize);
 	kmemleak_alloc_recursive(object, objsize, 1, s->flags, gfpflags);
+
 	return object;
 }
 
@@ -1759,6 +1784,7 @@ static __always_inline void slab_free(struct kmem_cache *s,
 	kmemleak_free_recursive(x, s->flags);
 	local_irq_save(flags);
 	c = get_cpu_slab(s, smp_processor_id());
+	kmemcheck_slab_free(s, object, c->objsize);
 	debug_check_no_locks_freed(object, c->objsize);
 	if (!(s->flags & SLAB_DEBUG_OBJECTS))
 		debug_check_no_obj_freed(object, c->objsize);
@@ -2633,7 +2659,8 @@ static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags)
 
 	if (!s || !text || !kmem_cache_open(s, flags, text,
 			realsize, ARCH_KMALLOC_MINALIGN,
-			SLAB_CACHE_DMA|__SYSFS_ADD_DEFERRED, NULL)) {
+			SLAB_CACHE_DMA|SLAB_NOTRACK|__SYSFS_ADD_DEFERRED,
+			NULL)) {
 		kfree(s);
 		kfree(text);
 		goto unlock_out;
@@ -2727,9 +2754,10 @@ EXPORT_SYMBOL(__kmalloc);
 
 static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
 {
-	struct page *page = alloc_pages_node(node, flags | __GFP_COMP,
-						get_order(size));
+	struct page *page;
 
+	flags |= __GFP_COMP | __GFP_NOTRACK;
+	page = alloc_pages_node(node, flags, get_order(size));
 	if (page)
 		return page_address(page);
 	else
@@ -4412,6 +4440,8 @@ static char *create_unique_id(struct kmem_cache *s)
 		*p++ = 'a';
 	if (s->flags & SLAB_DEBUG_FREE)
 		*p++ = 'F';
+	if (!(s->flags & SLAB_NOTRACK))
+		*p++ = 't';
 	if (p != name + 1)
 		*p++ = '-';
 	p += sprintf(p, "%07d", s->size);