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
  ...

11 files changed, 296 insertions, 3 deletions

diff --git a/include/linux/c2port.h b/include/linux/c2port.h
index 7b5a2388ba67..2a5cd867c365 100644
--- a/include/linux/c2port.h
+++ b/include/linux/c2port.h
@@ -10,6 +10,7 @@
  */
 
 #include <linux/device.h>
+#include <linux/kmemcheck.h>
 
 #define C2PORT_NAME_LEN                 32
 
@@ -20,8 +21,10 @@
 /* Main struct */
 struct c2port_ops;
 struct c2port_device {
+        kmemcheck_bitfield_begin(flags);
         unsigned int access:1;
         unsigned int flash_access:1;
+        kmemcheck_bitfield_end(flags);
 
         int id;
         char name[C2PORT_NAME_LEN];
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ede84fa7da5d..6d12174fbe11 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1919,8 +1919,9 @@ extern void __init vfs_caches_init(unsigned long);
 
 extern struct kmem_cache *names_cachep;
 
-#define __getname()     kmem_cache_alloc(names_cachep, GFP_KERNEL)
-#define __putname(name) kmem_cache_free(names_cachep, (void *)(name))
+#define __getname_gfp(gfp)      kmem_cache_alloc(names_cachep, (gfp))
+#define __getname()             __getname_gfp(GFP_KERNEL)
+#define __putname(name)         kmem_cache_free(names_cachep, (void *)(name))
 #ifndef CONFIG_AUDITSYSCALL
 #define putname(name)   __putname(name)
 #else
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 3760e7c5de02..80e14b8c2e78 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -52,7 +52,19 @@ struct vm_area_struct;
 #define __GFP_RECLAIMABLE ((__force gfp_t)0x80000u) /* Page is reclaimable */
 #define __GFP_MOVABLE   ((__force gfp_t)0x100000u)  /* Page is movable */
 
-#define __GFP_BITS_SHIFT 21     /* Room for 21 __GFP_FOO bits */
+#ifdef CONFIG_KMEMCHECK
+#define __GFP_NOTRACK   ((__force gfp_t)0x200000u)  /* Don't track with kmemcheck */
+#else
+#define __GFP_NOTRACK   ((__force gfp_t)0)
+#endif
+
+/*
+ * This may seem redundant, but it's a way of annotating false positives vs.
+ * allocations that simply cannot be supported (e.g. page tables).
+ */
+#define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK)
+
+#define __GFP_BITS_SHIFT 22     /* Room for 22 __GFP_FOO bits */
 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
 
 /* This equals 0, but use constants in case they ever change */
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index c41e812e9d5e..2721f07e9354 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -472,6 +472,20 @@ static inline void tasklet_hi_schedule(struct tasklet_struct *t)
                 __tasklet_hi_schedule(t);
 }
 
+extern void __tasklet_hi_schedule_first(struct tasklet_struct *t);
+
+/*
+ * This version avoids touching any other tasklets. Needed for kmemcheck
+ * in order not to take any page faults while enqueueing this tasklet;
+ * consider VERY carefully whether you really need this or
+ * tasklet_hi_schedule()...
+ */
+static inline void tasklet_hi_schedule_first(struct tasklet_struct *t)
+{
+        if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state))
+                __tasklet_hi_schedule_first(t);
+}
+
 
 static inline void tasklet_disable_nosync(struct tasklet_struct *t)
 {
diff --git a/include/linux/kmemcheck.h b/include/linux/kmemcheck.h
new file mode 100644
index 000000000000..47b39b7c7e84
--- /dev/null
+++ b/include/linux/kmemcheck.h
@@ -0,0 +1,153 @@
+#ifndef LINUX_KMEMCHECK_H
+#define LINUX_KMEMCHECK_H
+
+#include <linux/mm_types.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_KMEMCHECK
+extern int kmemcheck_enabled;
+
+/* The slab-related functions. */
+void kmemcheck_alloc_shadow(struct page *page, int order, gfp_t flags, int node);
+void kmemcheck_free_shadow(struct page *page, int order);
+void kmemcheck_slab_alloc(struct kmem_cache *s, gfp_t gfpflags, void *object,
+                          size_t size);
+void kmemcheck_slab_free(struct kmem_cache *s, void *object, size_t size);
+
+void kmemcheck_pagealloc_alloc(struct page *p, unsigned int order,
+                               gfp_t gfpflags);
+
+void kmemcheck_show_pages(struct page *p, unsigned int n);
+void kmemcheck_hide_pages(struct page *p, unsigned int n);
+
+bool kmemcheck_page_is_tracked(struct page *p);
+
+void kmemcheck_mark_unallocated(void *address, unsigned int n);
+void kmemcheck_mark_uninitialized(void *address, unsigned int n);
+void kmemcheck_mark_initialized(void *address, unsigned int n);
+void kmemcheck_mark_freed(void *address, unsigned int n);
+
+void kmemcheck_mark_unallocated_pages(struct page *p, unsigned int n);
+void kmemcheck_mark_uninitialized_pages(struct page *p, unsigned int n);
+void kmemcheck_mark_initialized_pages(struct page *p, unsigned int n);
+
+int kmemcheck_show_addr(unsigned long address);
+int kmemcheck_hide_addr(unsigned long address);
+
+#else
+#define kmemcheck_enabled 0
+
+static inline void
+kmemcheck_alloc_shadow(struct page *page, int order, gfp_t flags, int node)
+{
+}
+
+static inline void
+kmemcheck_free_shadow(struct page *page, int order)
+{
+}
+
+static inline void
+kmemcheck_slab_alloc(struct kmem_cache *s, gfp_t gfpflags, void *object,
+                     size_t size)
+{
+}
+
+static inline void kmemcheck_slab_free(struct kmem_cache *s, void *object,
+                                       size_t size)
+{
+}
+
+static inline void kmemcheck_pagealloc_alloc(struct page *p,
+        unsigned int order, gfp_t gfpflags)
+{
+}
+
+static inline bool kmemcheck_page_is_tracked(struct page *p)
+{
+        return false;
+}
+
+static inline void kmemcheck_mark_unallocated(void *address, unsigned int n)
+{
+}
+
+static inline void kmemcheck_mark_uninitialized(void *address, unsigned int n)
+{
+}
+
+static inline void kmemcheck_mark_initialized(void *address, unsigned int n)
+{
+}
+
+static inline void kmemcheck_mark_freed(void *address, unsigned int n)
+{
+}
+
+static inline void kmemcheck_mark_unallocated_pages(struct page *p,
+                                                    unsigned int n)
+{
+}
+
+static inline void kmemcheck_mark_uninitialized_pages(struct page *p,
+                                                      unsigned int n)
+{
+}
+
+static inline void kmemcheck_mark_initialized_pages(struct page *p,
+                                                    unsigned int n)
+{
+}
+
+#endif /* CONFIG_KMEMCHECK */
+
+/*
+ * Bitfield annotations
+ *
+ * How to use: If you have a struct using bitfields, for example
+ *
+ *     struct a {
+ *             int x:8, y:8;
+ *     };
+ *
+ * then this should be rewritten as
+ *
+ *     struct a {
+ *             kmemcheck_bitfield_begin(flags);
+ *             int x:8, y:8;
+ *             kmemcheck_bitfield_end(flags);
+ *     };
+ *
+ * Now the "flags_begin" and "flags_end" members may be used to refer to the
+ * beginning and end, respectively, of the bitfield (and things like
+ * &x.flags_begin is allowed). As soon as the struct is allocated, the bit-
+ * fields should be annotated:
+ *
+ *     struct a *a = kmalloc(sizeof(struct a), GFP_KERNEL);
+ *     kmemcheck_annotate_bitfield(a, flags);
+ *
+ * Note: We provide the same definitions for both kmemcheck and non-
+ * kmemcheck kernels. This makes it harder to introduce accidental errors. It
+ * is also allowed to pass NULL pointers to kmemcheck_annotate_bitfield().
+ */
+#define kmemcheck_bitfield_begin(name)  \
+        int name##_begin[0];
+
+#define kmemcheck_bitfield_end(name)    \
+        int name##_end[0];
+
+#define kmemcheck_annotate_bitfield(ptr, name)                          \
+        do if (ptr) {                                                   \
+                int _n = (long) &((ptr)->name##_end)                    \
+                        - (long) &((ptr)->name##_begin);                \
+                BUILD_BUG_ON(_n < 0);                                   \
+                                                                        \
+                kmemcheck_mark_initialized(&((ptr)->name##_begin), _n); \
+        } while (0)
+
+#define kmemcheck_annotate_variable(var)                                \
+        do {                                                            \
+                kmemcheck_mark_initialized(&(var), sizeof(var));        \
+        } while (0)                                                     \
+
+#endif /* LINUX_KMEMCHECK_H */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 0e80e26ecf21..0042090a4d70 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -98,6 +98,14 @@ struct page {
 #ifdef CONFIG_WANT_PAGE_DEBUG_FLAGS
         unsigned long debug_flags;      /* Use atomic bitops on this */
 #endif
+
+#ifdef CONFIG_KMEMCHECK
+        /*
+         * kmemcheck wants to track the status of each byte in a page; this
+         * is a pointer to such a status block. NULL if not tracked.
+         */
+        void *shadow;
+#endif
 };
 
 /*
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 8670f1575fe1..29f8599e6bea 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -1,6 +1,7 @@
 #ifndef _LINUX_RING_BUFFER_H
 #define _LINUX_RING_BUFFER_H
 
+#include <linux/kmemcheck.h>
 #include <linux/mm.h>
 #include <linux/seq_file.h>
 
@@ -11,7 +12,10 @@ struct ring_buffer_iter;
  * Don't refer to this struct directly, use functions below.
  */
 struct ring_buffer_event {
+        kmemcheck_bitfield_begin(bitfield);
         u32             type_len:5, time_delta:27;
+        kmemcheck_bitfield_end(bitfield);
+
         u32             array[];
 };
 
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index fa51293f2708..63ef24bc01d0 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -15,6 +15,7 @@
 #define _LINUX_SKBUFF_H
 
 #include <linux/kernel.h>
+#include <linux/kmemcheck.h>
 #include <linux/compiler.h>
 #include <linux/time.h>
 #include <linux/cache.h>
@@ -343,6 +344,7 @@ struct sk_buff {
                 };
         };
         __u32                   priority;
+        kmemcheck_bitfield_begin(flags1);
         __u8                    local_df:1,
                                 cloned:1,
                                 ip_summed:2,
@@ -353,6 +355,7 @@ struct sk_buff {
                                 ipvs_property:1,
                                 peeked:1,
                                 nf_trace:1;
+        kmemcheck_bitfield_end(flags1);
         __be16                  protocol;
 
         void                    (*destructor)(struct sk_buff *skb);
@@ -372,12 +375,16 @@ struct sk_buff {
         __u16                   tc_verd;        /* traffic control verdict */
 #endif
 #endif
+
+        kmemcheck_bitfield_begin(flags2);
 #ifdef CONFIG_IPV6_NDISC_NODETYPE
         __u8                    ndisc_nodetype:2;
 #endif
 #if defined(CONFIG_MAC80211) || defined(CONFIG_MAC80211_MODULE)
         __u8                    do_not_encrypt:1;
 #endif
+        kmemcheck_bitfield_end(flags2);
+
         /* 0/13/14 bit hole */
 
 #ifdef CONFIG_NET_DMA
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 219b8fb4651d..2da8372519f5 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -64,6 +64,13 @@
 
 #define SLAB_NOLEAKTRACE        0x00800000UL    /* Avoid kmemleak tracing */
 
+/* Don't track use of uninitialized memory */
+#ifdef CONFIG_KMEMCHECK
+# define SLAB_NOTRACK           0x01000000UL
+#else
+# define SLAB_NOTRACK           0x00000000UL
+#endif
+
 /* The following flags affect the page allocator grouping pages by mobility */
 #define SLAB_RECLAIM_ACCOUNT    0x00020000UL            /* Objects are reclaimable */
 #define SLAB_TEMPORARY          SLAB_RECLAIM_ACCOUNT    /* Objects are short-lived */
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index 713f841ecaa9..850d057500de 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -16,6 +16,87 @@
 #include <linux/compiler.h>
 #include <linux/kmemtrace.h>
 
+/*
+ * 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 */
+#ifdef CONFIG_DEBUG_SLAB
+        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;
+
+        /*
+         * 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 /* CONFIG_DEBUG_SLAB */
+
+        /*
+         * 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[]
+         */
+};
+
 /* Size description struct for general caches. */
 struct cache_sizes {
         size_t                  cs_size;
diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h
index 1a8cecc4f38c..51efbef38fb0 100644
--- a/include/linux/stacktrace.h
+++ b/include/linux/stacktrace.h
@@ -4,6 +4,8 @@
 struct task_struct;
 
 #ifdef CONFIG_STACKTRACE
+struct task_struct;
+
 struct stack_trace {
         unsigned int nr_entries, max_entries;
         unsigned long *entries;
@@ -11,6 +13,7 @@ struct stack_trace {
 };
 
 extern void save_stack_trace(struct stack_trace *trace);
+extern void save_stack_trace_bp(struct stack_trace *trace, unsigned long bp);
 extern void save_stack_trace_tsk(struct task_struct *tsk,
                                 struct stack_trace *trace);