[PATCH] slab: implement /proc/slab_allocators

Implement /proc/slab_allocators.   It produces output like:

idr_layer_cache: 80 idr_pre_get+0x33/0x4e
buffer_head: 2555 alloc_buffer_head+0x20/0x75
mm_struct: 9 mm_alloc+0x1e/0x42
mm_struct: 20 dup_mm+0x36/0x370
vm_area_struct: 384 dup_mm+0x18f/0x370
vm_area_struct: 151 do_mmap_pgoff+0x2e0/0x7c3
vm_area_struct: 1 split_vma+0x5a/0x10e
vm_area_struct: 11 do_brk+0x206/0x2e2
vm_area_struct: 2 copy_vma+0xda/0x142
vm_area_struct: 9 setup_arg_pages+0x99/0x214
fs_cache: 8 copy_fs_struct+0x21/0x133
fs_cache: 29 copy_process+0xf38/0x10e3
files_cache: 30 alloc_files+0x1b/0xcf
signal_cache: 81 copy_process+0xbaa/0x10e3
sighand_cache: 77 copy_process+0xe65/0x10e3
sighand_cache: 1 de_thread+0x4d/0x5f8
anon_vma: 241 anon_vma_prepare+0xd9/0xf3
size-2048: 1 add_sect_attrs+0x5f/0x145
size-2048: 2 journal_init_revoke+0x99/0x302
size-2048: 2 journal_init_revoke+0x137/0x302
size-2048: 2 journal_init_inode+0xf9/0x1c4

Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: Alexander Nyberg <alexn@telia.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Christoph Lameter <clameter@engr.sgi.com>
Cc: Ravikiran Thirumalai <kiran@scalex86.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
DESC
slab-leaks3-locking-fix
EDESC
From: Andrew Morton <akpm@osdl.org>

Update for slab-remove-cachep-spinlock.patch

Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: Alexander Nyberg <alexn@telia.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Christoph Lameter <clameter@engr.sgi.com>
Cc: Ravikiran Thirumalai <kiran@scalex86.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

6 files changed, 222 insertions, 11 deletions

diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 826c131994c3..1e9ea37d457e 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -485,6 +485,40 @@ static struct file_operations proc_slabinfo_operations = {
         .llseek         = seq_lseek,
         .release        = seq_release,
 };
+
+#ifdef CONFIG_DEBUG_SLAB_LEAK
+extern struct seq_operations slabstats_op;
+static int slabstats_open(struct inode *inode, struct file *file)
+{
+        unsigned long *n = kzalloc(PAGE_SIZE, GFP_KERNEL);
+        int ret = -ENOMEM;
+        if (n) {
+                ret = seq_open(file, &slabstats_op);
+                if (!ret) {
+                        struct seq_file *m = file->private_data;
+                        *n = PAGE_SIZE / (2 * sizeof(unsigned long));
+                        m->private = n;
+                        n = NULL;
+                }
+                kfree(n);
+        }
+        return ret;
+}
+
+static int slabstats_release(struct inode *inode, struct file *file)
+{
+        struct seq_file *m = file->private_data;
+        kfree(m->private);
+        return seq_release(inode, file);
+}
+
+static struct file_operations proc_slabstats_operations = {
+        .open           = slabstats_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = slabstats_release,
+};
+#endif
 #endif
 
 static int show_stat(struct seq_file *p, void *v)
@@ -744,6 +778,9 @@ void __init proc_misc_init(void)
         create_seq_entry("interrupts", 0, &proc_interrupts_operations);
 #ifdef CONFIG_SLAB
         create_seq_entry("slabinfo",S_IWUSR|S_IRUGO,&proc_slabinfo_operations);
+#ifdef CONFIG_DEBUG_SLAB_LEAK
+        create_seq_entry("slab_allocators", 0 ,&proc_slabstats_operations);
+#endif
 #endif
         create_seq_entry("buddyinfo",S_IRUGO, &fragmentation_file_operations);
         create_seq_entry("vmstat",S_IRUGO, &proc_vmstat_file_operations);
diff --git a/include/linux/slab.h b/include/linux/slab.h
index e2ee5b268797..f88e08a5802c 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -77,11 +77,12 @@ struct cache_sizes {
 };
 extern struct cache_sizes malloc_sizes[];
 
-#ifndef CONFIG_DEBUG_SLAB
 extern void *__kmalloc(size_t, gfp_t);
+#ifndef CONFIG_DEBUG_SLAB
+#define ____kmalloc(size, flags) __kmalloc(size, flags)
 #else
 extern void *__kmalloc_track_caller(size_t, gfp_t, void*);
-#define __kmalloc(size, flags) \
+#define ____kmalloc(size, flags) \
     __kmalloc_track_caller(size, flags, __builtin_return_address(0))
 #endif
 
@@ -173,6 +174,7 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags)
 #define kmem_ptr_validate(a, b) (0)
 #define kmem_cache_alloc_node(c, f, n) kmem_cache_alloc(c, f)
 #define kmalloc_node(s, f, n) kmalloc(s, f)
+#define ____kmalloc kmalloc
 
 #endif /* CONFIG_SLOB */
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index f2618e1c2b93..1fe3f897145f 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -85,6 +85,10 @@ config DEBUG_SLAB
           allocation as well as poisoning memory on free to catch use of freed
           memory. This can make kmalloc/kfree-intensive workloads much slower.
 
+config DEBUG_SLAB_LEAK
+        bool "Memory leak debugging"
+        depends on DEBUG_SLAB
+
 config DEBUG_PREEMPT
         bool "Debug preemptible kernel"
         depends on DEBUG_KERNEL && PREEMPT
diff --git a/mm/slab.c b/mm/slab.c
index 26138c9f8f00..a5047161084e 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -204,7 +204,8 @@
 typedef unsigned int kmem_bufctl_t;
 #define BUFCTL_END      (((kmem_bufctl_t)(~0U))-0)
 #define BUFCTL_FREE     (((kmem_bufctl_t)(~0U))-1)
-#define SLAB_LIMIT      (((kmem_bufctl_t)(~0U))-2)
+#define BUFCTL_ACTIVE   (((kmem_bufctl_t)(~0U))-2)
+#define SLAB_LIMIT      (((kmem_bufctl_t)(~0U))-3)
 
 /* Max number of objs-per-slab for caches which use off-slab slabs.
  * Needed to avoid a possible looping condition in cache_grow().
@@ -2399,7 +2400,7 @@ static void slab_put_obj(struct kmem_cache *cachep, struct slab *slabp,
         /* Verify that the slab belongs to the intended node */
         WARN_ON(slabp->nodeid != nodeid);
 
-        if (slab_bufctl(slabp)[objnr] != BUFCTL_FREE) {
+        if (slab_bufctl(slabp)[objnr] + 1 <= SLAB_LIMIT + 1) {
                 printk(KERN_ERR "slab: double free detected in cache "
                                 "'%s', objp %p\n", cachep->name, objp);
                 BUG();
@@ -2605,6 +2606,9 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
                  */
                 cachep->dtor(objp + obj_offset(cachep), cachep, 0);
         }
+#ifdef CONFIG_DEBUG_SLAB_LEAK
+        slab_bufctl(slabp)[objnr] = BUFCTL_FREE;
+#endif
         if (cachep->flags & SLAB_POISON) {
 #ifdef CONFIG_DEBUG_PAGEALLOC
                 if ((cachep->buffer_size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) {
@@ -2788,6 +2792,16 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
                 *dbg_redzone1(cachep, objp) = RED_ACTIVE;
                 *dbg_redzone2(cachep, objp) = RED_ACTIVE;
         }
+#ifdef CONFIG_DEBUG_SLAB_LEAK
+        {
+                struct slab *slabp;
+                unsigned objnr;
+
+                slabp = page_get_slab(virt_to_page(objp));
+                objnr = (unsigned)(objp - slabp->s_mem) / cachep->buffer_size;
+                slab_bufctl(slabp)[objnr] = BUFCTL_ACTIVE;
+        }
+#endif
         objp += obj_offset(cachep);
         if (cachep->ctor && cachep->flags & SLAB_POISON) {
                 unsigned long ctor_flags = SLAB_CTOR_CONSTRUCTOR;
@@ -3220,22 +3234,23 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
         return __cache_alloc(cachep, flags, caller);
 }
 
-#ifndef CONFIG_DEBUG_SLAB
 
 void *__kmalloc(size_t size, gfp_t flags)
 {
+#ifndef CONFIG_DEBUG_SLAB
         return __do_kmalloc(size, flags, NULL);
+#else
+        return __do_kmalloc(size, flags, __builtin_return_address(0));
+#endif
 }
 EXPORT_SYMBOL(__kmalloc);
 
-#else
-
+#ifdef CONFIG_DEBUG_SLAB
 void *__kmalloc_track_caller(size_t size, gfp_t flags, void *caller)
 {
         return __do_kmalloc(size, flags, caller);
 }
 EXPORT_SYMBOL(__kmalloc_track_caller);
-
 #endif
 
 #ifdef CONFIG_SMP
@@ -3899,6 +3914,159 @@ ssize_t slabinfo_write(struct file *file, const char __user * buffer,
                 res = count;
         return res;
 }
+
+#ifdef CONFIG_DEBUG_SLAB_LEAK
+
+static void *leaks_start(struct seq_file *m, loff_t *pos)
+{
+        loff_t n = *pos;
+        struct list_head *p;
+
+        mutex_lock(&cache_chain_mutex);
+        p = cache_chain.next;
+        while (n--) {
+                p = p->next;
+                if (p == &cache_chain)
+                        return NULL;
+        }
+        return list_entry(p, struct kmem_cache, next);
+}
+
+static inline int add_caller(unsigned long *n, unsigned long v)
+{
+        unsigned long *p;
+        int l;
+        if (!v)
+                return 1;
+        l = n[1];
+        p = n + 2;
+        while (l) {
+                int i = l/2;
+                unsigned long *q = p + 2 * i;
+                if (*q == v) {
+                        q[1]++;
+                        return 1;
+                }
+                if (*q > v) {
+                        l = i;
+                } else {
+                        p = q + 2;
+                        l -= i + 1;
+                }
+        }
+        if (++n[1] == n[0])
+                return 0;
+        memmove(p + 2, p, n[1] * 2 * sizeof(unsigned long) - ((void *)p - (void *)n));
+        p[0] = v;
+        p[1] = 1;
+        return 1;
+}
+
+static void handle_slab(unsigned long *n, struct kmem_cache *c, struct slab *s)
+{
+        void *p;
+        int i;
+        if (n[0] == n[1])
+                return;
+        for (i = 0, p = s->s_mem; i < c->num; i++, p += c->buffer_size) {
+                if (slab_bufctl(s)[i] != BUFCTL_ACTIVE)
+                        continue;
+                if (!add_caller(n, (unsigned long)*dbg_userword(c, p)))
+                        return;
+        }
+}
+
+static void show_symbol(struct seq_file *m, unsigned long address)
+{
+#ifdef CONFIG_KALLSYMS
+        char *modname;
+        const char *name;
+        unsigned long offset, size;
+        char namebuf[KSYM_NAME_LEN+1];
+
+        name = kallsyms_lookup(address, &size, &offset, &modname, namebuf);
+
+        if (name) {
+                seq_printf(m, "%s+%#lx/%#lx", name, offset, size);
+                if (modname)
+                        seq_printf(m, " [%s]", modname);
+                return;
+        }
+#endif
+        seq_printf(m, "%p", (void *)address);
+}
+
+static int leaks_show(struct seq_file *m, void *p)
+{
+        struct kmem_cache *cachep = p;
+        struct list_head *q;
+        struct slab *slabp;
+        struct kmem_list3 *l3;
+        const char *name;
+        unsigned long *n = m->private;
+        int node;
+        int i;
+
+        if (!(cachep->flags & SLAB_STORE_USER))
+                return 0;
+        if (!(cachep->flags & SLAB_RED_ZONE))
+                return 0;
+
+        /* OK, we can do it */
+
+        n[1] = 0;
+
+        for_each_online_node(node) {
+                l3 = cachep->nodelists[node];
+                if (!l3)
+                        continue;
+
+                check_irq_on();
+                spin_lock_irq(&l3->list_lock);
+
+                list_for_each(q, &l3->slabs_full) {
+                        slabp = list_entry(q, struct slab, list);
+                        handle_slab(n, cachep, slabp);
+                }
+                list_for_each(q, &l3->slabs_partial) {
+                        slabp = list_entry(q, struct slab, list);
+                        handle_slab(n, cachep, slabp);
+                }
+                spin_unlock_irq(&l3->list_lock);
+        }
+        name = cachep->name;
+        if (n[0] == n[1]) {
+                /* Increase the buffer size */
+                mutex_unlock(&cache_chain_mutex);
+                m->private = kzalloc(n[0] * 4 * sizeof(unsigned long), GFP_KERNEL);
+                if (!m->private) {
+                        /* Too bad, we are really out */
+                        m->private = n;
+                        mutex_lock(&cache_chain_mutex);
+                        return -ENOMEM;
+                }
+                *(unsigned long *)m->private = n[0] * 2;
+                kfree(n);
+                mutex_lock(&cache_chain_mutex);
+                /* Now make sure this entry will be retried */
+                m->count = m->size;
+                return 0;
+        }
+        for (i = 0; i < n[1]; i++) {
+                seq_printf(m, "%s: %lu ", name, n[2*i+3]);
+                show_symbol(m, n[2*i+2]);
+                seq_putc(m, '\n');
+        }
+        return 0;
+}
+
+struct seq_operations slabstats_op = {
+        .start = leaks_start,
+        .next = s_next,
+        .stop = s_stop,
+        .show = leaks_show,
+};
+#endif
 #endif
 
 /**
diff --git a/mm/util.c b/mm/util.c
index 49e29f751b50..b68d3d7d0359 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -11,7 +11,7 @@
  */
 void *kzalloc(size_t size, gfp_t flags)
 {
-        void *ret = kmalloc(size, flags);
+        void *ret = ____kmalloc(size, flags);
         if (ret)
                 memset(ret, 0, size);
         return ret;
@@ -33,7 +33,7 @@ char *kstrdup(const char *s, gfp_t gfp)
                 return NULL;
 
         len = strlen(s) + 1;
-        buf = kmalloc(len, gfp);
+        buf = ____kmalloc(len, gfp);
         if (buf)
                 memcpy(buf, s, len);
         return buf;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c9f878454531..09464fa8d72f 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -149,7 +149,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 
         /* Get the DATA. Size must match skb_add_mtu(). */
         size = SKB_DATA_ALIGN(size);
-        data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
+        data = ____kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
         if (!data)
                 goto nodata;