X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fmodule.c;h=e2564580f3f113ec9d391a7ad45beea842d39620;hb=fa9dc265ace9774e62f0e31108e5f47911124bda;hp=12afc5a3ddd3a73972604050695ff4ab4ef708f6;hpb=d0316554d3586cbea60592a41391b5def2553d6f;p=safe%2Fjmp%2Flinux-2.6

diff --git a/kernel/module.c b/kernel/module.c
index 12afc5a..e256458 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -59,8 +59,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/module.h>
 
-EXPORT_TRACEPOINT_SYMBOL(module_get);
-
 #if 0
 #define DEBUGP printk
 #else
@@ -370,27 +368,33 @@ EXPORT_SYMBOL_GPL(find_module);
 
 #ifdef CONFIG_SMP
 
-static void *percpu_modalloc(unsigned long size, unsigned long align,
-			     const char *name)
+static inline void __percpu *mod_percpu(struct module *mod)
 {
-	void *ptr;
+	return mod->percpu;
+}
 
+static int percpu_modalloc(struct module *mod,
+			   unsigned long size, unsigned long align)
+{
 	if (align > PAGE_SIZE) {
 		printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n",
-		       name, align, PAGE_SIZE);
+		       mod->name, align, PAGE_SIZE);
 		align = PAGE_SIZE;
 	}
 
-	ptr = __alloc_reserved_percpu(size, align);
-	if (!ptr)
+	mod->percpu = __alloc_reserved_percpu(size, align);
+	if (!mod->percpu) {
 		printk(KERN_WARNING
 		       "Could not allocate %lu bytes percpu data\n", size);
-	return ptr;
+		return -ENOMEM;
+	}
+	mod->percpu_size = size;
+	return 0;
 }
 
-static void percpu_modfree(void *freeme)
+static void percpu_modfree(struct module *mod)
 {
-	free_percpu(freeme);
+	free_percpu(mod->percpu);
 }
 
 static unsigned int find_pcpusec(Elf_Ehdr *hdr,
@@ -400,24 +404,62 @@ static unsigned int find_pcpusec(Elf_Ehdr *hdr,
 	return find_sec(hdr, sechdrs, secstrings, ".data.percpu");
 }
 
-static void percpu_modcopy(void *pcpudest, const void *from, unsigned long size)
+static void percpu_modcopy(struct module *mod,
+			   const void *from, unsigned long size)
 {
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		memcpy(pcpudest + per_cpu_offset(cpu), from, size);
+		memcpy(per_cpu_ptr(mod->percpu, cpu), from, size);
+}
+
+/**
+ * is_module_percpu_address - test whether address is from module static percpu
+ * @addr: address to test
+ *
+ * Test whether @addr belongs to module static percpu area.
+ *
+ * RETURNS:
+ * %true if @addr is from module static percpu area
+ */
+bool is_module_percpu_address(unsigned long addr)
+{
+	struct module *mod;
+	unsigned int cpu;
+
+	preempt_disable();
+
+	list_for_each_entry_rcu(mod, &modules, list) {
+		if (!mod->percpu_size)
+			continue;
+		for_each_possible_cpu(cpu) {
+			void *start = per_cpu_ptr(mod->percpu, cpu);
+
+			if ((void *)addr >= start &&
+			    (void *)addr < start + mod->percpu_size) {
+				preempt_enable();
+				return true;
+			}
+		}
+	}
+
+	preempt_enable();
+	return false;
 }
 
 #else /* ... !CONFIG_SMP */
 
-static inline void *percpu_modalloc(unsigned long size, unsigned long align,
-				    const char *name)
+static inline void __percpu *mod_percpu(struct module *mod)
 {
 	return NULL;
 }
-static inline void percpu_modfree(void *pcpuptr)
+static inline int percpu_modalloc(struct module *mod,
+				  unsigned long size, unsigned long align)
+{
+	return -ENOMEM;
+}
+static inline void percpu_modfree(struct module *mod)
 {
-	BUG();
 }
 static inline unsigned int find_pcpusec(Elf_Ehdr *hdr,
 					Elf_Shdr *sechdrs,
@@ -425,12 +467,16 @@ static inline unsigned int find_pcpusec(Elf_Ehdr *hdr,
 {
 	return 0;
 }
-static inline void percpu_modcopy(void *pcpudst, const void *src,
-				  unsigned long size)
+static inline void percpu_modcopy(struct module *mod,
+				  const void *from, unsigned long size)
 {
 	/* pcpusec should be 0, and size of that section should be 0. */
 	BUG_ON(size != 0);
 }
+bool is_module_percpu_address(unsigned long addr)
+{
+	return false;
+}
 
 #endif /* CONFIG_SMP */
 
@@ -467,16 +513,22 @@ MODINFO_ATTR(srcversion);
 static char last_unloaded_module[MODULE_NAME_LEN+1];
 
 #ifdef CONFIG_MODULE_UNLOAD
+
+EXPORT_TRACEPOINT_SYMBOL(module_get);
+
 /* Init the unload section of the module. */
 static void module_unload_init(struct module *mod)
 {
 	int cpu;
 
 	INIT_LIST_HEAD(&mod->modules_which_use_me);
-	for_each_possible_cpu(cpu)
-		local_set(__module_ref_addr(mod, cpu), 0);
+	for_each_possible_cpu(cpu) {
+		per_cpu_ptr(mod->refptr, cpu)->incs = 0;
+		per_cpu_ptr(mod->refptr, cpu)->decs = 0;
+	}
+
 	/* Hold reference count during initialization. */
-	local_set(__module_ref_addr(mod, raw_smp_processor_id()), 1);
+	__this_cpu_write(mod->refptr->incs, 1);
 	/* Backwards compatibility macros put refcount during init. */
 	mod->waiter = current;
 }
@@ -615,12 +667,28 @@ static int try_stop_module(struct module *mod, int flags, int *forced)
 
 unsigned int module_refcount(struct module *mod)
 {
-	unsigned int total = 0;
+	unsigned int incs = 0, decs = 0;
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		total += local_read(__module_ref_addr(mod, cpu));
-	return total;
+		decs += per_cpu_ptr(mod->refptr, cpu)->decs;
+	/*
+	 * ensure the incs are added up after the decs.
+	 * module_put ensures incs are visible before decs with smp_wmb.
+	 *
+	 * This 2-count scheme avoids the situation where the refcount
+	 * for CPU0 is read, then CPU0 increments the module refcount,
+	 * then CPU1 drops that refcount, then the refcount for CPU1 is
+	 * read. We would record a decrement but not its corresponding
+	 * increment so we would see a low count (disaster).
+	 *
+	 * Rare situation? But module_refcount can be preempted, and we
+	 * might be tallying up 4096+ CPUs. So it is not impossible.
+	 */
+	smp_rmb();
+	for_each_possible_cpu(cpu)
+		incs += per_cpu_ptr(mod->refptr, cpu)->incs;
+	return incs - decs;
 }
 EXPORT_SYMBOL(module_refcount);
 
@@ -656,16 +724,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 		return -EFAULT;
 	name[MODULE_NAME_LEN-1] = '\0';
 
-	/* Create stop_machine threads since free_module relies on
-	 * a non-failing stop_machine call. */
-	ret = stop_machine_create();
-	if (ret)
-		return ret;
-
-	if (mutex_lock_interruptible(&module_mutex) != 0) {
-		ret = -EINTR;
-		goto out_stop;
-	}
+	if (mutex_lock_interruptible(&module_mutex) != 0)
+		return -EINTR;
 
 	mod = find_module(name);
 	if (!mod) {
@@ -725,8 +785,6 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 
  out:
 	mutex_unlock(&module_mutex);
-out_stop:
-	stop_machine_destroy();
 	return ret;
 }
 
@@ -796,14 +854,15 @@ 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));
-		trace_module_put(module, _RET_IP_,
-				 local_read(__module_ref_addr(module, cpu)));
+		preempt_disable();
+		smp_wmb(); /* see comment in module_refcount */
+		__this_cpu_inc(module->refptr->decs);
+
+		trace_module_put(module, _RET_IP_);
 		/* 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);
@@ -880,11 +939,23 @@ 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;
@@ -905,10 +976,10 @@ 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;
 	}
 
@@ -931,7 +1002,8 @@ 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. */
@@ -949,7 +1021,8 @@ 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;
 }
@@ -984,8 +1057,8 @@ 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;
@@ -996,6 +1069,12 @@ 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;
@@ -1037,8 +1116,7 @@ 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
-		    && sechdrs[i].sh_size)
+		if (!sect_empty(&sechdrs[i]))
 			nloaded++;
 	size[0] = ALIGN(sizeof(*sect_attrs)
 			+ nloaded * sizeof(sect_attrs->attrs[0]),
@@ -1056,9 +1134,7 @@ 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))
-			continue;
-		if (!sechdrs[i].sh_size)
+		if (sect_empty(&sechdrs[i]))
 			continue;
 		sattr->address = sechdrs[i].sh_addr;
 		sattr->name = kstrdup(secstrings + sechdrs[i].sh_name,
@@ -1066,6 +1142,7 @@ 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;
@@ -1142,7 +1219,7 @@ 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;
 
@@ -1158,9 +1235,10 @@ 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;
@@ -1233,6 +1311,7 @@ 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;
 		}
@@ -1378,11 +1457,10 @@ static void free_module(struct module *mod)
 	/* This may be NULL, but that's OK */
 	module_free(mod, mod->module_init);
 	kfree(mod->args);
-	if (mod->percpu)
-		percpu_modfree(mod->percpu);
-#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+	percpu_modfree(mod);
+#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);
@@ -1498,7 +1576,7 @@ static int simplify_symbols(Elf_Shdr *sechdrs,
 		default:
 			/* Divert to percpu allocation if a percpu var. */
 			if (sym[i].st_shndx == pcpuindex)
-				secbase = (unsigned long)mod->percpu;
+				secbase = (unsigned long)mod_percpu(mod);
 			else
 				secbase = sechdrs[sym[i].st_shndx].sh_addr;
 			sym[i].st_value += secbase;
@@ -1896,9 +1974,7 @@ 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))
@@ -1907,8 +1983,7 @@ 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);
 	}
 }
@@ -1935,7 +2010,7 @@ static noinline struct module *load_module(void __user *umod,
 	unsigned int modindex, versindex, infoindex, pcpuindex;
 	struct module *mod;
 	long err = 0;
-	void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
+	void *ptr = NULL; /* Stops spurious gcc warning */
 	unsigned long symoffs, stroffs, *strmap;
 
 	mm_segment_t old_fs;
@@ -2075,15 +2150,11 @@ static noinline struct module *load_module(void __user *umod,
 
 	if (pcpuindex) {
 		/* We have a special allocation for this section. */
-		percpu = percpu_modalloc(sechdrs[pcpuindex].sh_size,
-					 sechdrs[pcpuindex].sh_addralign,
-					 mod->name);
-		if (!percpu) {
-			err = -ENOMEM;
+		err = percpu_modalloc(mod, sechdrs[pcpuindex].sh_size,
+				      sechdrs[pcpuindex].sh_addralign);
+		if (err)
 			goto free_mod;
-		}
 		sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
-		mod->percpu = percpu;
 	}
 
 	/* Determine total sizes, and put offsets in sh_entsize.  For now
@@ -2148,9 +2219,8 @@ 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;
@@ -2236,6 +2306,12 @@ 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 */
@@ -2293,7 +2369,7 @@ static noinline struct module *load_module(void __user *umod,
 	sort_extable(mod->extable, mod->extable + mod->num_exentries);
 
 	/* Finally, copy percpu area over. */
-	percpu_modcopy(mod->percpu, (void *)sechdrs[pcpuindex].sh_addr,
+	percpu_modcopy(mod, (void *)sechdrs[pcpuindex].sh_addr,
 		       sechdrs[pcpuindex].sh_size);
 
 	add_kallsyms(mod, sechdrs, hdr->e_shnum, symindex, strindex,
@@ -2376,8 +2452,8 @@ 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);
@@ -2385,8 +2461,7 @@ static noinline struct module *load_module(void __user *umod,
 	module_free(mod, mod->module_core);
 	/* mod will be freed with core. Don't access it beyond this line! */
  free_percpu:
-	if (percpu)
-		percpu_modfree(percpu);
+	percpu_modfree(mod);
  free_mod:
 	kfree(args);
 	kfree(strmap);