Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/livepatching

Pull livepatching updates from Jiri Kosina:

 - remove of our own implementation of architecture-specific relocation
   code and leveraging existing code in the module loader to perform
   arch-dependent work, from Jessica Yu.

   The relevant patches have been acked by Rusty (for module.c) and
   Heiko (for s390).

 - live patching support for ppc64le, which is a joint work of Michael
   Ellerman and Torsten Duwe.  This is coming from topic branch that is
   share between livepatching.git and ppc tree.

 - addition of livepatching documentation from Petr Mladek

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/livepatching:
  livepatch: make object/func-walking helpers more robust
  livepatch: Add some basic livepatch documentation
  powerpc/livepatch: Add live patching support on ppc64le
  powerpc/livepatch: Add livepatch stack to struct thread_info
  powerpc/livepatch: Add livepatch header
  livepatch: Allow architectures to specify an alternate ftrace location
  ftrace: Make ftrace_location_range() global
  livepatch: robustify klp_register_patch() API error checking
  Documentation: livepatch: outline Elf format and requirements for patch modules
  livepatch: reuse module loader code to write relocations
  module: s390: keep mod_arch_specific for livepatch modules
  module: preserve Elf information for livepatch modules
  Elf: add livepatch-specific Elf constants

3 files changed, 266 insertions, 64 deletions

diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index d68fbf6..5c2bc10 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -28,6 +28,8 @@
 #include <linux/list.h>
 #include <linux/kallsyms.h>
 #include <linux/livepatch.h>
+#include <linux/elf.h>
+#include <linux/moduleloader.h>
 #include <asm/cacheflush.h>
 
 /**
@@ -204,75 +206,109 @@ static int klp_find_object_symbol(const char *objname, const char *name,
 	return -EINVAL;
 }
 
-/*
- * external symbols are located outside the parent object (where the parent
- * object is either vmlinux or the kmod being patched).
- */
-static int klp_find_external_symbol(struct module *pmod, const char *name,
-				    unsigned long *addr)
+static int klp_resolve_symbols(Elf_Shdr *relasec, struct module *pmod)
 {
-	const struct kernel_symbol *sym;
-
-	/* first, check if it's an exported symbol */
-	preempt_disable();
-	sym = find_symbol(name, NULL, NULL, true, true);
-	if (sym) {
-		*addr = sym->value;
-		preempt_enable();
-		return 0;
-	}
-	preempt_enable();
+	int i, cnt, vmlinux, ret;
+	char objname[MODULE_NAME_LEN];
+	char symname[KSYM_NAME_LEN];
+	char *strtab = pmod->core_kallsyms.strtab;
+	Elf_Rela *relas;
+	Elf_Sym *sym;
+	unsigned long sympos, addr;
 
 	/*
-	 * Check if it's in another .o within the patch module. This also
-	 * checks that the external symbol is unique.
+	 * Since the field widths for objname and symname in the sscanf()
+	 * call are hard-coded and correspond to MODULE_NAME_LEN and
+	 * KSYM_NAME_LEN respectively, we must make sure that MODULE_NAME_LEN
+	 * and KSYM_NAME_LEN have the values we expect them to have.
+	 *
+	 * Because the value of MODULE_NAME_LEN can differ among architectures,
+	 * we use the smallest/strictest upper bound possible (56, based on
+	 * the current definition of MODULE_NAME_LEN) to prevent overflows.
 	 */
-	return klp_find_object_symbol(pmod->name, name, 0, addr);
+	BUILD_BUG_ON(MODULE_NAME_LEN < 56 || KSYM_NAME_LEN != 128);
+
+	relas = (Elf_Rela *) relasec->sh_addr;
+	/* For each rela in this klp relocation section */
+	for (i = 0; i < relasec->sh_size / sizeof(Elf_Rela); i++) {
+		sym = pmod->core_kallsyms.symtab + ELF_R_SYM(relas[i].r_info);
+		if (sym->st_shndx != SHN_LIVEPATCH) {
+			pr_err("symbol %s is not marked as a livepatch symbol",
+			       strtab + sym->st_name);
+			return -EINVAL;
+		}
+
+		/* Format: .klp.sym.objname.symname,sympos */
+		cnt = sscanf(strtab + sym->st_name,
+			     ".klp.sym.%55[^.].%127[^,],%lu",
+			     objname, symname, &sympos);
+		if (cnt != 3) {
+			pr_err("symbol %s has an incorrectly formatted name",
+			       strtab + sym->st_name);
+			return -EINVAL;
+		}
+
+		/* klp_find_object_symbol() treats a NULL objname as vmlinux */
+		vmlinux = !strcmp(objname, "vmlinux");
+		ret = klp_find_object_symbol(vmlinux ? NULL : objname,
+					     symname, sympos, &addr);
+		if (ret)
+			return ret;
+
+		sym->st_value = addr;
+	}
+
+	return 0;
 }
 
 static int klp_write_object_relocations(struct module *pmod,
 					struct klp_object *obj)
 {
-	int ret = 0;
-	unsigned long val;
-	struct klp_reloc *reloc;
+	int i, cnt, ret = 0;
+	const char *objname, *secname;
+	char sec_objname[MODULE_NAME_LEN];
+	Elf_Shdr *sec;
 
 	if (WARN_ON(!klp_is_object_loaded(obj)))
 		return -EINVAL;
 
-	if (WARN_ON(!obj->relocs))
-		return -EINVAL;
+	objname = klp_is_module(obj) ? obj->name : "vmlinux";
 
 	module_disable_ro(pmod);
+	/* For each klp relocation section */
+	for (i = 1; i < pmod->klp_info->hdr.e_shnum; i++) {
+		sec = pmod->klp_info->sechdrs + i;
+		secname = pmod->klp_info->secstrings + sec->sh_name;
+		if (!(sec->sh_flags & SHF_RELA_LIVEPATCH))
+			continue;
 
-	for (reloc = obj->relocs; reloc->name; reloc++) {
-		/* discover the address of the referenced symbol */
-		if (reloc->external) {
-			if (reloc->sympos > 0) {
-				pr_err("non-zero sympos for external reloc symbol '%s' is not supported\n",
-				       reloc->name);
-				ret = -EINVAL;
-				goto out;
-			}
-			ret = klp_find_external_symbol(pmod, reloc->name, &val);
-		} else
-			ret = klp_find_object_symbol(obj->name,
-						     reloc->name,
-						     reloc->sympos,
-						     &val);
+		/*
+		 * Format: .klp.rela.sec_objname.section_name
+		 * See comment in klp_resolve_symbols() for an explanation
+		 * of the selected field width value.
+		 */
+		cnt = sscanf(secname, ".klp.rela.%55[^.]", sec_objname);
+		if (cnt != 1) {
+			pr_err("section %s has an incorrectly formatted name",
+			       secname);
+			ret = -EINVAL;
+			break;
+		}
+
+		if (strcmp(objname, sec_objname))
+			continue;
+
+		ret = klp_resolve_symbols(sec, pmod);
 		if (ret)
-			goto out;
+			break;
 
-		ret = klp_write_module_reloc(pmod, reloc->type, reloc->loc,
-					     val + reloc->addend);
-		if (ret) {
-			pr_err("relocation failed for symbol '%s' at 0x%016lx (%d)\n",
-			       reloc->name, val, ret);
-			goto out;
-		}
+		ret = apply_relocate_add(pmod->klp_info->sechdrs,
+					 pmod->core_kallsyms.strtab,
+					 pmod->klp_info->symndx, i, pmod);
+		if (ret)
+			break;
 	}
 
-out:
 	module_enable_ro(pmod);
 	return ret;
 }
@@ -298,6 +334,19 @@ unlock:
 	rcu_read_unlock();
 }
 
+/*
+ * Convert a function address into the appropriate ftrace location.
+ *
+ * Usually this is just the address of the function, but on some architectures
+ * it's more complicated so allow them to provide a custom behaviour.
+ */
+#ifndef klp_get_ftrace_location
+static unsigned long klp_get_ftrace_location(unsigned long faddr)
+{
+	return faddr;
+}
+#endif
+
 static void klp_disable_func(struct klp_func *func)
 {
 	struct klp_ops *ops;
@@ -312,8 +361,14 @@ static void klp_disable_func(struct klp_func *func)
 		return;
 
 	if (list_is_singular(&ops->func_stack)) {
+		unsigned long ftrace_loc;
+
+		ftrace_loc = klp_get_ftrace_location(func->old_addr);
+		if (WARN_ON(!ftrace_loc))
+			return;
+
 		WARN_ON(unregister_ftrace_function(&ops->fops));
-		WARN_ON(ftrace_set_filter_ip(&ops->fops, func->old_addr, 1, 0));
+		WARN_ON(ftrace_set_filter_ip(&ops->fops, ftrace_loc, 1, 0));
 
 		list_del_rcu(&func->stack_node);
 		list_del(&ops->node);
@@ -338,6 +393,15 @@ static int klp_enable_func(struct klp_func *func)
 
 	ops = klp_find_ops(func->old_addr);
 	if (!ops) {
+		unsigned long ftrace_loc;
+
+		ftrace_loc = klp_get_ftrace_location(func->old_addr);
+		if (!ftrace_loc) {
+			pr_err("failed to find location for function '%s'\n",
+				func->old_name);
+			return -EINVAL;
+		}
+
 		ops = kzalloc(sizeof(*ops), GFP_KERNEL);
 		if (!ops)
 			return -ENOMEM;
@@ -352,7 +416,7 @@ static int klp_enable_func(struct klp_func *func)
 		INIT_LIST_HEAD(&ops->func_stack);
 		list_add_rcu(&func->stack_node, &ops->func_stack);
 
-		ret = ftrace_set_filter_ip(&ops->fops, func->old_addr, 0, 0);
+		ret = ftrace_set_filter_ip(&ops->fops, ftrace_loc, 0, 0);
 		if (ret) {
 			pr_err("failed to set ftrace filter for function '%s' (%d)\n",
 			       func->old_name, ret);
@@ -363,7 +427,7 @@ static int klp_enable_func(struct klp_func *func)
 		if (ret) {
 			pr_err("failed to register ftrace handler for function '%s' (%d)\n",
 			       func->old_name, ret);
-			ftrace_set_filter_ip(&ops->fops, func->old_addr, 1, 0);
+			ftrace_set_filter_ip(&ops->fops, ftrace_loc, 1, 0);
 			goto err;
 		}
 
@@ -683,6 +747,9 @@ static void klp_free_patch(struct klp_patch *patch)
 
 static int klp_init_func(struct klp_object *obj, struct klp_func *func)
 {
+	if (!func->old_name || !func->new_func)
+		return -EINVAL;
+
 	INIT_LIST_HEAD(&func->stack_node);
 	func->state = KLP_DISABLED;
 
@@ -703,11 +770,9 @@ static int klp_init_object_loaded(struct klp_patch *patch,
 	struct klp_func *func;
 	int ret;
 
-	if (obj->relocs) {
-		ret = klp_write_object_relocations(patch->mod, obj);
-		if (ret)
-			return ret;
-	}
+	ret = klp_write_object_relocations(patch->mod, obj);
+	if (ret)
+		return ret;
 
 	klp_for_each_func(obj, func) {
 		ret = klp_find_object_symbol(obj->name, func->old_name,
@@ -842,12 +907,18 @@ int klp_register_patch(struct klp_patch *patch)
 {
 	int ret;
 
-	if (!klp_initialized())
-		return -ENODEV;
-
 	if (!patch || !patch->mod)
 		return -EINVAL;
 
+	if (!is_livepatch_module(patch->mod)) {
+		pr_err("module %s is not marked as a livepatch module",
+		       patch->mod->name);
+		return -EINVAL;
+	}
+
+	if (!klp_initialized())
+		return -ENODEV;
+
 	/*
 	 * A reference is taken on the patch module to prevent it from being
 	 * unloaded.  Right now, we don't allow patch modules to unload since
diff --git a/kernel/module.c b/kernel/module.c
index 041200c..5f71aa6 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1973,6 +1973,83 @@ static void module_enable_nx(const struct module *mod) { }
 static void module_disable_nx(const struct module *mod) { }
 #endif
 
+#ifdef CONFIG_LIVEPATCH
+/*
+ * Persist Elf information about a module. Copy the Elf header,
+ * section header table, section string table, and symtab section
+ * index from info to mod->klp_info.
+ */
+static int copy_module_elf(struct module *mod, struct load_info *info)
+{
+	unsigned int size, symndx;
+	int ret;
+
+	size = sizeof(*mod->klp_info);
+	mod->klp_info = kmalloc(size, GFP_KERNEL);
+	if (mod->klp_info == NULL)
+		return -ENOMEM;
+
+	/* Elf header */
+	size = sizeof(mod->klp_info->hdr);
+	memcpy(&mod->klp_info->hdr, info->hdr, size);
+
+	/* Elf section header table */
+	size = sizeof(*info->sechdrs) * info->hdr->e_shnum;
+	mod->klp_info->sechdrs = kmalloc(size, GFP_KERNEL);
+	if (mod->klp_info->sechdrs == NULL) {
+		ret = -ENOMEM;
+		goto free_info;
+	}
+	memcpy(mod->klp_info->sechdrs, info->sechdrs, size);
+
+	/* Elf section name string table */
+	size = info->sechdrs[info->hdr->e_shstrndx].sh_size;
+	mod->klp_info->secstrings = kmalloc(size, GFP_KERNEL);
+	if (mod->klp_info->secstrings == NULL) {
+		ret = -ENOMEM;
+		goto free_sechdrs;
+	}
+	memcpy(mod->klp_info->secstrings, info->secstrings, size);
+
+	/* Elf symbol section index */
+	symndx = info->index.sym;
+	mod->klp_info->symndx = symndx;
+
+	/*
+	 * For livepatch modules, core_kallsyms.symtab is a complete
+	 * copy of the original symbol table. Adjust sh_addr to point
+	 * to core_kallsyms.symtab since the copy of the symtab in module
+	 * init memory is freed at the end of do_init_module().
+	 */
+	mod->klp_info->sechdrs[symndx].sh_addr = \
+		(unsigned long) mod->core_kallsyms.symtab;
+
+	return 0;
+
+free_sechdrs:
+	kfree(mod->klp_info->sechdrs);
+free_info:
+	kfree(mod->klp_info);
+	return ret;
+}
+
+static void free_module_elf(struct module *mod)
+{
+	kfree(mod->klp_info->sechdrs);
+	kfree(mod->klp_info->secstrings);
+	kfree(mod->klp_info);
+}
+#else /* !CONFIG_LIVEPATCH */
+static int copy_module_elf(struct module *mod, struct load_info *info)
+{
+	return 0;
+}
+
+static void free_module_elf(struct module *mod)
+{
+}
+#endif /* CONFIG_LIVEPATCH */
+
 void __weak module_memfree(void *module_region)
 {
 	vfree(module_region);
@@ -2011,6 +2088,9 @@ static void free_module(struct module *mod)
 	/* Free any allocated parameters. */
 	destroy_params(mod->kp, mod->num_kp);
 
+	if (is_livepatch_module(mod))
+		free_module_elf(mod);
+
 	/* Now we can delete it from the lists */
 	mutex_lock(&module_mutex);
 	/* Unlink carefully: kallsyms could be walking list. */
@@ -2126,6 +2206,10 @@ static int simplify_symbols(struct module *mod, const struct load_info *info)
 			       (long)sym[i].st_value);
 			break;
 
+		case SHN_LIVEPATCH:
+			/* Livepatch symbols are resolved by livepatch */
+			break;
+
 		case SHN_UNDEF:
 			ksym = resolve_symbol_wait(mod, info, name);
 			/* Ok if resolved.  */
@@ -2174,6 +2258,10 @@ static int apply_relocations(struct module *mod, const struct load_info *info)
 		if (!(info->sechdrs[infosec].sh_flags & SHF_ALLOC))
 			continue;
 
+		/* Livepatch relocation sections are applied by livepatch */
+		if (info->sechdrs[i].sh_flags & SHF_RELA_LIVEPATCH)
+			continue;
+
 		if (info->sechdrs[i].sh_type == SHT_REL)
 			err = apply_relocate(info->sechdrs, info->strtab,
 					     info->index.sym, i, mod);
@@ -2469,7 +2557,7 @@ static void layout_symtab(struct module *mod, struct load_info *info)
 
 	/* Compute total space required for the core symbols' strtab. */
 	for (ndst = i = 0; i < nsrc; i++) {
-		if (i == 0 ||
+		if (i == 0 || is_livepatch_module(mod) ||
 		    is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum,
 				   info->index.pcpu)) {
 			strtab_size += strlen(&info->strtab[src[i].st_name])+1;
@@ -2528,7 +2616,7 @@ static void add_kallsyms(struct module *mod, const struct load_info *info)
 	mod->core_kallsyms.strtab = s = mod->core_layout.base + info->stroffs;
 	src = mod->kallsyms->symtab;
 	for (ndst = i = 0; i < mod->kallsyms->num_symtab; i++) {
-		if (i == 0 ||
+		if (i == 0 || is_livepatch_module(mod) ||
 		    is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum,
 				   info->index.pcpu)) {
 			dst[ndst] = src[i];
@@ -2667,6 +2755,26 @@ static int copy_chunked_from_user(void *dst, const void __user *usrc, unsigned l
 	return 0;
 }
 
+#ifdef CONFIG_LIVEPATCH
+static int find_livepatch_modinfo(struct module *mod, struct load_info *info)
+{
+	mod->klp = get_modinfo(info, "livepatch") ? true : false;
+
+	return 0;
+}
+#else /* !CONFIG_LIVEPATCH */
+static int find_livepatch_modinfo(struct module *mod, struct load_info *info)
+{
+	if (get_modinfo(info, "livepatch")) {
+		pr_err("%s: module is marked as livepatch module, but livepatch support is disabled",
+		       mod->name);
+		return -ENOEXEC;
+	}
+
+	return 0;
+}
+#endif /* CONFIG_LIVEPATCH */
+
 /* Sets info->hdr and info->len. */
 static int copy_module_from_user(const void __user *umod, unsigned long len,
 				  struct load_info *info)
@@ -2821,6 +2929,10 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags)
 			"is unknown, you have been warned.\n", mod->name);
 	}
 
+	err = find_livepatch_modinfo(mod, info);
+	if (err)
+		return err;
+
 	/* Set up license info based on the info section */
 	set_license(mod, get_modinfo(info, "license"));
 
@@ -3494,6 +3606,12 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	if (err < 0)
 		goto coming_cleanup;
 
+	if (is_livepatch_module(mod)) {
+		err = copy_module_elf(mod, info);
+		if (err < 0)
+			goto sysfs_cleanup;
+	}
+
 	/* Get rid of temporary copy. */
 	free_copy(info);
 
@@ -3502,11 +3620,12 @@ static int load_module(struct load_info *info, const char __user *uargs,
 
 	return do_init_module(mod);
 
+ sysfs_cleanup:
+	mod_sysfs_teardown(mod);
  coming_cleanup:
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_GOING, mod);
 	klp_module_going(mod);
-
  bug_cleanup:
 	/* module_bug_cleanup needs module_mutex protection */
 	mutex_lock(&module_mutex);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index b1870fb..7e8d792 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1530,7 +1530,19 @@ static int ftrace_cmp_recs(const void *a, const void *b)
 	return 0;
 }
 
-static unsigned long ftrace_location_range(unsigned long start, unsigned long end)
+/**
+ * ftrace_location_range - return the first address of a traced location
+ *	if it touches the given ip range
+ * @start: start of range to search.
+ * @end: end of range to search (inclusive). @end points to the last byte
+ *	to check.
+ *
+ * Returns rec->ip if the related ftrace location is a least partly within
+ * the given address range. That is, the first address of the instruction
+ * that is either a NOP or call to the function tracer. It checks the ftrace
+ * internal tables to determine if the address belongs or not.
+ */
+unsigned long ftrace_location_range(unsigned long start, unsigned long end)
 {
 	struct ftrace_page *pg;
 	struct dyn_ftrace *rec;