Merging upstream version 6.10.3.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

4 files changed, 80 insertions, 86 deletions

diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig
index f3e0329337..4047b6d482 100644
--- a/kernel/module/Kconfig
+++ b/kernel/module/Kconfig
@@ -2,6 +2,7 @@
 menuconfig MODULES
 	bool "Enable loadable module support"
 	modules
+	select EXECMEM
 	help
 	  Kernel modules are small pieces of compiled code which can
 	  be inserted in the running kernel, rather than being
@@ -392,7 +393,7 @@ config UNUSED_KSYMS_WHITELIST
 	  exported at all times, even in absence of in-tree users. The value to
 	  set here is the path to a text file containing the list of symbols,
 	  one per line. The path can be absolute, or relative to the kernel
-	  source tree.
+	  source or obj tree.
 
 config MODULES_TREE_LOOKUP
 	def_bool y
diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c
index ef73ae7c89..bf65e0c3c8 100644
--- a/kernel/module/kallsyms.c
+++ b/kernel/module/kallsyms.c
@@ -321,14 +321,15 @@ void * __weak dereference_module_function_descriptor(struct module *mod,
  * For kallsyms to ask for address resolution.  NULL means not found.  Careful
  * not to lock to avoid deadlock on oopses, simply disable preemption.
  */
-const char *module_address_lookup(unsigned long addr,
-				  unsigned long *size,
-			    unsigned long *offset,
-			    char **modname,
-			    const unsigned char **modbuildid,
-			    char *namebuf)
+int module_address_lookup(unsigned long addr,
+			  unsigned long *size,
+			  unsigned long *offset,
+			  char **modname,
+			  const unsigned char **modbuildid,
+			  char *namebuf)
 {
-	const char *ret = NULL;
+	const char *sym;
+	int ret = 0;
 	struct module *mod;
 
 	preempt_disable();
@@ -344,12 +345,10 @@ const char *module_address_lookup(unsigned long addr,
 #endif
 		}
 
-		ret = find_kallsyms_symbol(mod, addr, size, offset);
-	}
-	/* Make a copy in here where it's safe */
-	if (ret) {
-		strncpy(namebuf, ret, KSYM_NAME_LEN - 1);
-		ret = namebuf;
+		sym = find_kallsyms_symbol(mod, addr, size, offset);
+
+		if (sym)
+			ret = strscpy(namebuf, sym, KSYM_NAME_LEN);
 	}
 	preempt_enable();
 
diff --git a/kernel/module/main.c b/kernel/module/main.c
index e1e8a7a9d6..d18a94b973 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -56,7 +56,9 @@
 #include <linux/dynamic_debug.h>
 #include <linux/audit.h>
 #include <linux/cfi.h>
+#include <linux/codetag.h>
 #include <linux/debugfs.h>
+#include <linux/execmem.h>
 #include <uapi/linux/module.h>
 #include "internal.h"
 
@@ -1179,16 +1181,6 @@ resolve_symbol_wait(struct module *mod,
 	return ksym;
 }
 
-void __weak module_memfree(void *module_region)
-{
-	/*
-	 * This memory may be RO, and freeing RO memory in an interrupt is not
-	 * supported by vmalloc.
-	 */
-	WARN_ON(in_interrupt());
-	vfree(module_region);
-}
-
 void __weak module_arch_cleanup(struct module *mod)
 {
 }
@@ -1197,28 +1189,54 @@ void __weak module_arch_freeing_init(struct module *mod)
 {
 }
 
-static bool mod_mem_use_vmalloc(enum mod_mem_type type)
+static int module_memory_alloc(struct module *mod, enum mod_mem_type type)
 {
-	return IS_ENABLED(CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC) &&
-		mod_mem_type_is_core_data(type);
-}
+	unsigned int size = PAGE_ALIGN(mod->mem[type].size);
+	enum execmem_type execmem_type;
+	void *ptr;
 
-static void *module_memory_alloc(unsigned int size, enum mod_mem_type type)
-{
-	if (mod_mem_use_vmalloc(type))
-		return vzalloc(size);
-	return module_alloc(size);
+	mod->mem[type].size = size;
+
+	if (mod_mem_type_is_data(type))
+		execmem_type = EXECMEM_MODULE_DATA;
+	else
+		execmem_type = EXECMEM_MODULE_TEXT;
+
+	ptr = execmem_alloc(execmem_type, size);
+	if (!ptr)
+		return -ENOMEM;
+
+	/*
+	 * The pointer to these blocks of memory are stored on the module
+	 * structure and we keep that around so long as the module is
+	 * around. We only free that memory when we unload the module.
+	 * Just mark them as not being a leak then. The .init* ELF
+	 * sections *do* get freed after boot so we *could* treat them
+	 * slightly differently with kmemleak_ignore() and only grey
+	 * them out as they work as typical memory allocations which
+	 * *do* eventually get freed, but let's just keep things simple
+	 * and avoid *any* false positives.
+	 */
+	kmemleak_not_leak(ptr);
+
+	memset(ptr, 0, size);
+	mod->mem[type].base = ptr;
+
+	return 0;
 }
 
-static void module_memory_free(void *ptr, enum mod_mem_type type)
+static void module_memory_free(struct module *mod, enum mod_mem_type type,
+			       bool unload_codetags)
 {
-	if (mod_mem_use_vmalloc(type))
-		vfree(ptr);
-	else
-		module_memfree(ptr);
+	void *ptr = mod->mem[type].base;
+
+	if (!unload_codetags && mod_mem_type_is_core_data(type))
+		return;
+
+	execmem_free(ptr);
 }
 
-static void free_mod_mem(struct module *mod)
+static void free_mod_mem(struct module *mod, bool unload_codetags)
 {
 	for_each_mod_mem_type(type) {
 		struct module_memory *mod_mem = &mod->mem[type];
@@ -1229,19 +1247,26 @@ static void free_mod_mem(struct module *mod)
 		/* Free lock-classes; relies on the preceding sync_rcu(). */
 		lockdep_free_key_range(mod_mem->base, mod_mem->size);
 		if (mod_mem->size)
-			module_memory_free(mod_mem->base, type);
+			module_memory_free(mod, type, unload_codetags);
 	}
 
 	/* MOD_DATA hosts mod, so free it at last */
 	lockdep_free_key_range(mod->mem[MOD_DATA].base, mod->mem[MOD_DATA].size);
-	module_memory_free(mod->mem[MOD_DATA].base, MOD_DATA);
+	module_memory_free(mod, MOD_DATA, unload_codetags);
 }
 
 /* Free a module, remove from lists, etc. */
 static void free_module(struct module *mod)
 {
+	bool unload_codetags;
+
 	trace_module_free(mod);
 
+	unload_codetags = codetag_unload_module(mod);
+	if (!unload_codetags)
+		pr_warn("%s: memory allocation(s) from the module still alive, cannot unload cleanly\n",
+			mod->name);
+
 	mod_sysfs_teardown(mod);
 
 	/*
@@ -1283,7 +1308,7 @@ static void free_module(struct module *mod)
 	kfree(mod->args);
 	percpu_modfree(mod);
 
-	free_mod_mem(mod);
+	free_mod_mem(mod, unload_codetags);
 }
 
 void *__symbol_get(const char *symbol)
@@ -1610,13 +1635,6 @@ static void free_modinfo(struct module *mod)
 	}
 }
 
-void * __weak module_alloc(unsigned long size)
-{
-	return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END,
-			GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS,
-			NUMA_NO_NODE, __builtin_return_address(0));
-}
-
 bool __weak module_init_section(const char *name)
 {
 	return strstarts(name, ".init");
@@ -2225,7 +2243,6 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 static int move_module(struct module *mod, struct load_info *info)
 {
 	int i;
-	void *ptr;
 	enum mod_mem_type t = 0;
 	int ret = -ENOMEM;
 
@@ -2234,26 +2251,12 @@ static int move_module(struct module *mod, struct load_info *info)
 			mod->mem[type].base = NULL;
 			continue;
 		}
-		mod->mem[type].size = PAGE_ALIGN(mod->mem[type].size);
-		ptr = module_memory_alloc(mod->mem[type].size, type);
-		/*
-                 * The pointer to these blocks of memory are stored on the module
-                 * structure and we keep that around so long as the module is
-                 * around. We only free that memory when we unload the module.
-                 * Just mark them as not being a leak then. The .init* ELF
-                 * sections *do* get freed after boot so we *could* treat them
-                 * slightly differently with kmemleak_ignore() and only grey
-                 * them out as they work as typical memory allocations which
-                 * *do* eventually get freed, but let's just keep things simple
-                 * and avoid *any* false positives.
-		 */
-		kmemleak_not_leak(ptr);
-		if (!ptr) {
+
+		ret = module_memory_alloc(mod, type);
+		if (ret) {
 			t = type;
 			goto out_enomem;
 		}
-		memset(ptr, 0, mod->mem[type].size);
-		mod->mem[type].base = ptr;
 	}
 
 	/* Transfer each section which specifies SHF_ALLOC */
@@ -2296,7 +2299,7 @@ static int move_module(struct module *mod, struct load_info *info)
 	return 0;
 out_enomem:
 	for (t--; t >= 0; t--)
-		module_memory_free(mod->mem[t].base, t);
+		module_memory_free(mod, t, true);
 	return ret;
 }
 
@@ -2426,7 +2429,7 @@ static void module_deallocate(struct module *mod, struct load_info *info)
 	percpu_modfree(mod);
 	module_arch_freeing_init(mod);
 
-	free_mod_mem(mod);
+	free_mod_mem(mod, true);
 }
 
 int __weak module_finalize(const Elf_Ehdr *hdr,
@@ -2482,9 +2485,9 @@ static void do_free_init(struct work_struct *w)
 
 	llist_for_each_safe(pos, n, list) {
 		initfree = container_of(pos, struct mod_initfree, node);
-		module_memfree(initfree->init_text);
-		module_memfree(initfree->init_data);
-		module_memfree(initfree->init_rodata);
+		execmem_free(initfree->init_text);
+		execmem_free(initfree->init_data);
+		execmem_free(initfree->init_rodata);
 		kfree(initfree);
 	}
 }
@@ -2594,10 +2597,10 @@ static noinline int do_init_module(struct module *mod)
 	 * We want to free module_init, but be aware that kallsyms may be
 	 * walking this with preempt disabled.  In all the failure paths, we
 	 * call synchronize_rcu(), but we don't want to slow down the success
-	 * path. module_memfree() cannot be called in an interrupt, so do the
+	 * path. execmem_free() cannot be called in an interrupt, so do the
 	 * work and call synchronize_rcu() in a work queue.
 	 *
-	 * Note that module_alloc() on most architectures creates W+X page
+	 * Note that execmem_alloc() on most architectures creates W+X page
 	 * mappings which won't be cleaned up until do_free_init() runs.  Any
 	 * code such as mark_rodata_ro() which depends on those mappings to
 	 * be cleaned up needs to sync with the queued work by invoking
@@ -2995,6 +2998,8 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	/* Get rid of temporary copy. */
 	free_copy(info, flags);
 
+	codetag_load_module(mod);
+
 	/* Done! */
 	trace_module_load(mod);
 
diff --git a/kernel/module/sysfs.c b/kernel/module/sysfs.c
index d964167c66..26efe1305c 100644
--- a/kernel/module/sysfs.c
+++ b/kernel/module/sysfs.c
@@ -146,17 +146,6 @@ struct module_notes_attrs {
 	struct bin_attribute attrs[] __counted_by(notes);
 };
 
-static ssize_t module_notes_read(struct file *filp, struct kobject *kobj,
-				 struct bin_attribute *bin_attr,
-				 char *buf, loff_t pos, size_t count)
-{
-	/*
-	 * The caller checked the pos and count against our size.
-	 */
-	memcpy(buf, bin_attr->private + pos, count);
-	return count;
-}
-
 static void free_notes_attrs(struct module_notes_attrs *notes_attrs,
 			     unsigned int i)
 {
@@ -205,7 +194,7 @@ static void add_notes_attrs(struct module *mod, const struct load_info *info)
 			nattr->attr.mode = 0444;
 			nattr->size = info->sechdrs[i].sh_size;
 			nattr->private = (void *)info->sechdrs[i].sh_addr;
-			nattr->read = module_notes_read;
+			nattr->read = sysfs_bin_attr_simple_read;
 			++nattr;
 		}
 		++loaded;