1 files changed, 61 insertions, 183 deletions

diff --git a/kernel/module.c b/kernel/module.c
index fe748a86d452..c968d3606dca 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -370,8 +370,6 @@ EXPORT_SYMBOL_GPL(find_module);
 
 #ifdef CONFIG_SMP
 
-#ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
-
 static void *percpu_modalloc(unsigned long size, unsigned long align,
                              const char *name)
 {
@@ -395,154 +393,6 @@ static void percpu_modfree(void *freeme)
         free_percpu(freeme);
 }
 
-#else /* ... CONFIG_HAVE_LEGACY_PER_CPU_AREA */
-
-/* Number of blocks used and allocated. */
-static unsigned int pcpu_num_used, pcpu_num_allocated;
-/* Size of each block.  -ve means used. */
-static int *pcpu_size;
-
-static int split_block(unsigned int i, unsigned short size)
-{
-        /* Reallocation required? */
-        if (pcpu_num_used + 1 > pcpu_num_allocated) {
-                int *new;
-
-                new = krealloc(pcpu_size, sizeof(new[0])*pcpu_num_allocated*2,
-                               GFP_KERNEL);
-                if (!new)
-                        return 0;
-
-                pcpu_num_allocated *= 2;
-                pcpu_size = new;
-        }
-
-        /* Insert a new subblock */
-        memmove(&pcpu_size[i+1], &pcpu_size[i],
-                sizeof(pcpu_size[0]) * (pcpu_num_used - i));
-        pcpu_num_used++;
-
-        pcpu_size[i+1] -= size;
-        pcpu_size[i] = size;
-        return 1;
-}
-
-static inline unsigned int block_size(int val)
-{
-        if (val < 0)
-                return -val;
-        return val;
-}
-
-static void *percpu_modalloc(unsigned long size, unsigned long align,
-                             const char *name)
-{
-        unsigned long extra;
-        unsigned int i;
-        void *ptr;
-        int cpu;
-
-        if (align > PAGE_SIZE) {
-                printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n",
-                       name, align, PAGE_SIZE);
-                align = PAGE_SIZE;
-        }
-
-        ptr = __per_cpu_start;
-        for (i = 0; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) {
-                /* Extra for alignment requirement. */
-                extra = ALIGN((unsigned long)ptr, align) - (unsigned long)ptr;
-                BUG_ON(i == 0 && extra != 0);
-
-                if (pcpu_size[i] < 0 || pcpu_size[i] < extra + size)
-                        continue;
-
-                /* Transfer extra to previous block. */
-                if (pcpu_size[i-1] < 0)
-                        pcpu_size[i-1] -= extra;
-                else
-                        pcpu_size[i-1] += extra;
-                pcpu_size[i] -= extra;
-                ptr += extra;
-
-                /* Split block if warranted */
-                if (pcpu_size[i] - size > sizeof(unsigned long))
-                        if (!split_block(i, size))
-                                return NULL;
-
-                /* add the per-cpu scanning areas */
-                for_each_possible_cpu(cpu)
-                        kmemleak_alloc(ptr + per_cpu_offset(cpu), size, 0,
-                                       GFP_KERNEL);
-
-                /* Mark allocated */
-                pcpu_size[i] = -pcpu_size[i];
-                return ptr;
-        }
-
-        printk(KERN_WARNING "Could not allocate %lu bytes percpu data\n",
-               size);
-        return NULL;
-}
-
-static void percpu_modfree(void *freeme)
-{
-        unsigned int i;
-        void *ptr = __per_cpu_start + block_size(pcpu_size[0]);
-        int cpu;
-
-        /* First entry is core kernel percpu data. */
-        for (i = 1; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) {
-                if (ptr == freeme) {
-                        pcpu_size[i] = -pcpu_size[i];
-                        goto free;
-                }
-        }
-        BUG();
-
- free:
-        /* remove the per-cpu scanning areas */
-        for_each_possible_cpu(cpu)
-                kmemleak_free(freeme + per_cpu_offset(cpu));
-
-        /* Merge with previous? */
-        if (pcpu_size[i-1] >= 0) {
-                pcpu_size[i-1] += pcpu_size[i];
-                pcpu_num_used--;
-                memmove(&pcpu_size[i], &pcpu_size[i+1],
-                        (pcpu_num_used - i) * sizeof(pcpu_size[0]));
-                i--;
-        }
-        /* Merge with next? */
-        if (i+1 < pcpu_num_used && pcpu_size[i+1] >= 0) {
-                pcpu_size[i] += pcpu_size[i+1];
-                pcpu_num_used--;
-                memmove(&pcpu_size[i+1], &pcpu_size[i+2],
-                        (pcpu_num_used - (i+1)) * sizeof(pcpu_size[0]));
-        }
-}
-
-static int percpu_modinit(void)
-{
-        pcpu_num_used = 2;
-        pcpu_num_allocated = 2;
-        pcpu_size = kmalloc(sizeof(pcpu_size[0]) * pcpu_num_allocated,
-                            GFP_KERNEL);
-        /* Static in-kernel percpu data (used). */
-        pcpu_size[0] = -(__per_cpu_end-__per_cpu_start);
-        /* Free room. */
-        pcpu_size[1] = PERCPU_ENOUGH_ROOM + pcpu_size[0];
-        if (pcpu_size[1] < 0) {
-                printk(KERN_ERR "No per-cpu room for modules.\n");
-                pcpu_num_used = 1;
-        }
-
-        return 0;
-}
-__initcall(percpu_modinit);
-
-#endif /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
-
 static unsigned int find_pcpusec(Elf_Ehdr *hdr,
                                  Elf_Shdr *sechdrs,
                                  const char *secstrings)
@@ -624,9 +474,10 @@ static void module_unload_init(struct module *mod)
 
         INIT_LIST_HEAD(&mod->modules_which_use_me);
         for_each_possible_cpu(cpu)
-                local_set(__module_ref_addr(mod, cpu), 0);
+                per_cpu_ptr(mod->refptr, cpu)->count = 0;
+
         /* Hold reference count during initialization. */
-        local_set(__module_ref_addr(mod, raw_smp_processor_id()), 1);
+        __this_cpu_write(mod->refptr->count, 1);
         /* Backwards compatibility macros put refcount during init. */
         mod->waiter = current;
 }
@@ -769,7 +620,7 @@ unsigned int module_refcount(struct module *mod)
         int cpu;
 
         for_each_possible_cpu(cpu)
-                total += local_read(__module_ref_addr(mod, cpu));
+                total += per_cpu_ptr(mod->refptr, cpu)->count;
         return total;
 }
 EXPORT_SYMBOL(module_refcount);
@@ -946,14 +797,15 @@ static struct module_attribute refcnt = {
 void module_put(struct module *module)
 {
         if (module) {
-                unsigned int cpu = get_cpu();
-                local_dec(__module_ref_addr(module, cpu));
+                preempt_disable();
+                __this_cpu_dec(module->refptr->count);
+
                 trace_module_put(module, _RET_IP_,
-                                 local_read(__module_ref_addr(module, cpu)));
+                                 __this_cpu_read(module->refptr->count));
                 /* Maybe they're waiting for us to drop reference? */
                 if (unlikely(!module_is_live(module)))
                         wake_up_process(module->waiter);
-                put_cpu();
+                preempt_enable();
         }
 }
 EXPORT_SYMBOL(module_put);
@@ -1030,11 +882,23 @@ static int try_to_force_load(struct module *mod, const char *reason)
 }
 
 #ifdef CONFIG_MODVERSIONS
+/* If the arch applies (non-zero) relocations to kernel kcrctab, unapply it. */
+static unsigned long maybe_relocated(unsigned long crc,
+                                     const struct module *crc_owner)
+{
+#ifdef ARCH_RELOCATES_KCRCTAB
+        if (crc_owner == NULL)
+                return crc - (unsigned long)reloc_start;
+#endif
+        return crc;
+}
+
 static int check_version(Elf_Shdr *sechdrs,
                          unsigned int versindex,
                          const char *symname,
                          struct module *mod, 
-                         const unsigned long *crc)
+                         const unsigned long *crc,
+                         const struct module *crc_owner)
 {
         unsigned int i, num_versions;
         struct modversion_info *versions;
@@ -1055,10 +919,10 @@ static int check_version(Elf_Shdr *sechdrs,
                 if (strcmp(versions[i].name, symname) != 0)
                         continue;
 
-                if (versions[i].crc == *crc)
+                if (versions[i].crc == maybe_relocated(*crc, crc_owner))
                         return 1;
                 DEBUGP("Found checksum %lX vs module %lX\n",
-                       *crc, versions[i].crc);
+                       maybe_relocated(*crc, crc_owner), versions[i].crc);
                 goto bad_version;
         }
 
@@ -1081,7 +945,8 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs,
         if (!find_symbol(MODULE_SYMBOL_PREFIX "module_layout", NULL,
                          &crc, true, false))
                 BUG();
-        return check_version(sechdrs, versindex, "module_layout", mod, crc);
+        return check_version(sechdrs, versindex, "module_layout", mod, crc,
+                             NULL);
 }
 
 /* First part is kernel version, which we ignore if module has crcs. */
@@ -1099,7 +964,8 @@ static inline int check_version(Elf_Shdr *sechdrs,
                                 unsigned int versindex,
                                 const char *symname,
                                 struct module *mod, 
-                                const unsigned long *crc)
+                                const unsigned long *crc,
+                                const struct module *crc_owner)
 {
         return 1;
 }
@@ -1134,8 +1000,8 @@ static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs,
         /* use_module can fail due to OOM,
            or module initialization or unloading */
         if (sym) {
-                if (!check_version(sechdrs, versindex, name, mod, crc) ||
-                    !use_module(mod, owner))
+                if (!check_version(sechdrs, versindex, name, mod, crc, owner)
+                    || !use_module(mod, owner))
                         sym = NULL;
         }
         return sym;
@@ -1146,6 +1012,12 @@ static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs,
  * J. Corbet <corbet@lwn.net>
  */
 #if defined(CONFIG_KALLSYMS) && defined(CONFIG_SYSFS)
+
+static inline bool sect_empty(const Elf_Shdr *sect)
+{
+        return !(sect->sh_flags & SHF_ALLOC) || sect->sh_size == 0;
+}
+
 struct module_sect_attr
 {
         struct module_attribute mattr;
@@ -1187,7 +1059,7 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect,
 
         /* Count loaded sections and allocate structures */
         for (i = 0; i < nsect; i++)
-                if (sechdrs[i].sh_flags & SHF_ALLOC)
+                if (!sect_empty(&sechdrs[i]))
                         nloaded++;
         size[0] = ALIGN(sizeof(*sect_attrs)
                         + nloaded * sizeof(sect_attrs->attrs[0]),
@@ -1205,7 +1077,7 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect,
         sattr = &sect_attrs->attrs[0];
         gattr = &sect_attrs->grp.attrs[0];
         for (i = 0; i < nsect; i++) {
-                if (! (sechdrs[i].sh_flags & SHF_ALLOC))
+                if (sect_empty(&sechdrs[i]))
                         continue;
                 sattr->address = sechdrs[i].sh_addr;
                 sattr->name = kstrdup(secstrings + sechdrs[i].sh_name,
@@ -1213,6 +1085,7 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect,
                 if (sattr->name == NULL)
                         goto out;
                 sect_attrs->nsections++;
+                sysfs_attr_init(&sattr->mattr.attr);
                 sattr->mattr.show = module_sect_show;
                 sattr->mattr.store = NULL;
                 sattr->mattr.attr.name = sattr->name;
@@ -1289,7 +1162,7 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect,
         /* Count notes sections and allocate structures.  */
         notes = 0;
         for (i = 0; i < nsect; i++)
-                if ((sechdrs[i].sh_flags & SHF_ALLOC) &&
+                if (!sect_empty(&sechdrs[i]) &&
                     (sechdrs[i].sh_type == SHT_NOTE))
                         ++notes;
 
@@ -1305,9 +1178,10 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect,
         notes_attrs->notes = notes;
         nattr = &notes_attrs->attrs[0];
         for (loaded = i = 0; i < nsect; ++i) {
-                if (!(sechdrs[i].sh_flags & SHF_ALLOC))
+                if (sect_empty(&sechdrs[i]))
                         continue;
                 if (sechdrs[i].sh_type == SHT_NOTE) {
+                        sysfs_bin_attr_init(nattr);
                         nattr->attr.name = mod->sect_attrs->attrs[loaded].name;
                         nattr->attr.mode = S_IRUGO;
                         nattr->size = sechdrs[i].sh_size;
@@ -1380,6 +1254,7 @@ int module_add_modinfo_attrs(struct module *mod)
                 if (!attr->test ||
                     (attr->test && attr->test(mod))) {
                         memcpy(temp_attr, attr, sizeof(*temp_attr));
+                        sysfs_attr_init(&temp_attr->attr);
                         error = sysfs_create_file(&mod->mkobj.kobj,&temp_attr->attr);
                         ++temp_attr;
                 }
@@ -1527,9 +1402,9 @@ static void free_module(struct module *mod)
         kfree(mod->args);
         if (mod->percpu)
                 percpu_modfree(mod->percpu);
-#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+#if defined(CONFIG_MODULE_UNLOAD)
         if (mod->refptr)
-                percpu_modfree(mod->refptr);
+                free_percpu(mod->refptr);
 #endif
         /* Free lock-classes: */
         lockdep_free_key_range(mod->module_core, mod->core_size);
@@ -1992,12 +1867,14 @@ static inline unsigned long layout_symtab(struct module *mod,
                                           Elf_Shdr *sechdrs,
                                           unsigned int symindex,
                                           unsigned int strindex,
-                                          const Elf_Hdr *hdr,
+                                          const Elf_Ehdr *hdr,
                                           const char *secstrings,
                                           unsigned long *pstroffs,
                                           unsigned long *strmap)
 {
+        return 0;
 }
+
 static inline void add_kallsyms(struct module *mod,
                                 Elf_Shdr *sechdrs,
                                 unsigned int shnum,
@@ -2041,9 +1918,7 @@ static void kmemleak_load_module(struct module *mod, Elf_Ehdr *hdr,
         unsigned int i;
 
         /* only scan the sections containing data */
-        kmemleak_scan_area(mod->module_core, (unsigned long)mod -
-                           (unsigned long)mod->module_core,
-                           sizeof(struct module), GFP_KERNEL);
+        kmemleak_scan_area(mod, sizeof(struct module), GFP_KERNEL);
 
         for (i = 1; i < hdr->e_shnum; i++) {
                 if (!(sechdrs[i].sh_flags & SHF_ALLOC))
@@ -2052,8 +1927,7 @@ static void kmemleak_load_module(struct module *mod, Elf_Ehdr *hdr,
                     && strncmp(secstrings + sechdrs[i].sh_name, ".bss", 4) != 0)
                         continue;
 
-                kmemleak_scan_area(mod->module_core, sechdrs[i].sh_addr -
-                                   (unsigned long)mod->module_core,
+                kmemleak_scan_area((void *)sechdrs[i].sh_addr,
                                    sechdrs[i].sh_size, GFP_KERNEL);
         }
 }
@@ -2081,9 +1955,8 @@ static noinline struct module *load_module(void __user *umod,
         struct module *mod;
         long err = 0;
         void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
-#ifdef CONFIG_KALLSYMS
         unsigned long symoffs, stroffs, *strmap;
-#endif
+
         mm_segment_t old_fs;
 
         DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n",
@@ -2294,9 +2167,8 @@ static noinline struct module *load_module(void __user *umod,
         mod = (void *)sechdrs[modindex].sh_addr;
         kmemleak_load_module(mod, hdr, sechdrs, secstrings);
 
-#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
-        mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t),
-                                      mod->name);
+#if defined(CONFIG_MODULE_UNLOAD)
+        mod->refptr = alloc_percpu(struct module_ref);
         if (!mod->refptr) {
                 err = -ENOMEM;
                 goto free_init;
@@ -2382,6 +2254,12 @@ static noinline struct module *load_module(void __user *umod,
                                          "_ftrace_events",
                                          sizeof(*mod->trace_events),
                                          &mod->num_trace_events);
+        /*
+         * This section contains pointers to allocated objects in the trace
+         * code and not scanning it leads to false positives.
+         */
+        kmemleak_scan_area(mod->trace_events, sizeof(*mod->trace_events) *
+                           mod->num_trace_events, GFP_KERNEL);
 #endif
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
         /* sechdrs[0].sh_size is always zero */
@@ -2522,8 +2400,8 @@ static noinline struct module *load_module(void __user *umod,
         kobject_put(&mod->mkobj.kobj);
  free_unload:
         module_unload_free(mod);
-#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
-        percpu_modfree(mod->refptr);
+#if defined(CONFIG_MODULE_UNLOAD)
+        free_percpu(mod->refptr);
  free_init:
 #endif
         module_free(mod, mod->module_init);