diff mbox series

[v3,4/8] module: prepare to handle ROX allocations for text

Message ID 20240909064730.3290724-5-rppt@kernel.org (mailing list archive)
State Not Applicable
Headers show
Series x86/module: use large ROX pages for text allocations | expand

Checks

Context Check Description
netdev/tree_selection success Not a local patch, async
bpf/vmtest-bpf-next-PR success PR summary
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-5 success Logs for aarch64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-2 success Logs for Unittests
bpf/vmtest-bpf-next-VM_Test-3 success Logs for Validate matrix.py
bpf/vmtest-bpf-next-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-next-VM_Test-12 success Logs for s390x-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-10 success Logs for aarch64-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-9 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-11 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-4 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-16 success Logs for s390x-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-17 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-18 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-19 success Logs for x86_64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-25 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-27 success Logs for x86_64-llvm-17 / build / build for x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-28 success Logs for x86_64-llvm-17 / build-release / build for x86_64 with llvm-17-O2
bpf/vmtest-bpf-next-VM_Test-32 success Logs for x86_64-llvm-17 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-33 success Logs for x86_64-llvm-17 / veristat
bpf/vmtest-bpf-next-VM_Test-34 success Logs for x86_64-llvm-18 / build / build for x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-35 success Logs for x86_64-llvm-18 / build-release / build for x86_64 with llvm-18-O2
bpf/vmtest-bpf-next-VM_Test-41 success Logs for x86_64-llvm-18 / veristat
bpf/vmtest-bpf-next-VM_Test-40 success Logs for x86_64-llvm-18 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-6 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-14 success Logs for s390x-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-20 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-15 success Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-21 success Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-22 success Logs for x86_64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-23 success Logs for x86_64-gcc / test (test_progs_no_alu32_parallel, true, 30) / test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-24 success Logs for x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-26 success Logs for x86_64-gcc / veristat / veristat on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-29 success Logs for x86_64-llvm-17 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-31 success Logs for x86_64-llvm-17 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-30 success Logs for x86_64-llvm-17 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-36 success Logs for x86_64-llvm-18 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-37 success Logs for x86_64-llvm-18 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-38 success Logs for x86_64-llvm-18 / test (test_progs_cpuv4, false, 360) / test_progs_cpuv4 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-39 success Logs for x86_64-llvm-18 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-13 success Logs for s390x-gcc / test (test_progs, false, 360) / test_progs on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-7 success Logs for aarch64-gcc / test (test_progs, false, 360) / test_progs on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-8 success Logs for aarch64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on aarch64 with gcc

Commit Message

Mike Rapoport Sept. 9, 2024, 6:47 a.m. UTC
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>

In order to support ROX allocations for module text, it is necessary to
handle modifications to the code, such as relocations and alternatives
patching, without write access to that memory.

One option is to use text patching, but this would make module loading
extremely slow and will expose executable code that is not finally formed.

A better way is to have memory allocated with ROX permissions contain
invalid instructions and keep a writable, but not executable copy of the
module text. The relocations and alternative patches would be done on the
writable copy using the addresses of the ROX memory.
Once the module is completely ready, the updated text will be copied to ROX
memory using text patching in one go and the writable copy will be freed.

Add support for that to module initialization code and provide necessary
interfaces in execmem.

Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
---
 include/linux/execmem.h      | 23 +++++++++++
 include/linux/module.h       | 11 ++++++
 include/linux/moduleloader.h |  4 ++
 kernel/module/main.c         | 77 ++++++++++++++++++++++++++++++++----
 kernel/module/strict_rwx.c   |  3 ++
 mm/execmem.c                 | 11 ++++++
 6 files changed, 122 insertions(+), 7 deletions(-)
diff mbox series

Patch

diff --git a/include/linux/execmem.h b/include/linux/execmem.h
index 32cef1144117..dfdf19f8a5e8 100644
--- a/include/linux/execmem.h
+++ b/include/linux/execmem.h
@@ -46,9 +46,11 @@  enum execmem_type {
 /**
  * enum execmem_range_flags - options for executable memory allocations
  * @EXECMEM_KASAN_SHADOW:	allocate kasan shadow
+ * @EXECMEM_ROX_CACHE:		allocations should use ROX cache of huge pages
  */
 enum execmem_range_flags {
 	EXECMEM_KASAN_SHADOW	= (1 << 0),
+	EXECMEM_ROX_CACHE	= (1 << 1),
 };
 
 /**
@@ -123,6 +125,27 @@  void *execmem_alloc(enum execmem_type type, size_t size);
  */
 void execmem_free(void *ptr);
 
+/**
+ * execmem_update_copy - copy an update to executable memory
+ * @dst:  destination address to update
+ * @src:  source address containing the data
+ * @size: how many bytes of memory shold be copied
+ *
+ * Copy @size bytes from @src to @dst using text poking if the memory at
+ * @dst is read-only.
+ *
+ * Return: a pointer to @dst or NULL on error
+ */
+void *execmem_update_copy(void *dst, const void *src, size_t size);
+
+/**
+ * execmem_is_rox - check if execmem is read-only
+ * @type - the execmem type to check
+ *
+ * Return: %true if the @type is read-only, %false if it's writable
+ */
+bool execmem_is_rox(enum execmem_type type);
+
 #if defined(CONFIG_EXECMEM) && !defined(CONFIG_ARCH_WANTS_EXECMEM_LATE)
 void execmem_init(void);
 #else
diff --git a/include/linux/module.h b/include/linux/module.h
index 88ecc5e9f523..7039f609c6ef 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -367,6 +367,8 @@  enum mod_mem_type {
 
 struct module_memory {
 	void *base;
+	void *rw_copy;
+	bool is_rox;
 	unsigned int size;
 
 #ifdef CONFIG_MODULES_TREE_LOOKUP
@@ -374,6 +376,15 @@  struct module_memory {
 #endif
 };
 
+#ifdef CONFIG_MODULES
+void *module_writable_address(struct module *mod, void *loc);
+#else
+static inline void *module_writable_address(struct module *mod, void *loc)
+{
+	return loc;
+}
+#endif
+
 #ifdef CONFIG_MODULES_TREE_LOOKUP
 /* Only touch one cacheline for common rbtree-for-core-layout case. */
 #define __module_memory_align ____cacheline_aligned
diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h
index e395461d59e5..1f5507ba5a12 100644
--- a/include/linux/moduleloader.h
+++ b/include/linux/moduleloader.h
@@ -108,6 +108,10 @@  int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *mod);
 
+int module_post_finalize(const Elf_Ehdr *hdr,
+			 const Elf_Shdr *sechdrs,
+			 struct module *mod);
+
 #ifdef CONFIG_MODULES
 void flush_module_init_free_work(void);
 #else
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 71396e297499..55f53f0095d4 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1189,6 +1189,21 @@  void __weak module_arch_freeing_init(struct module *mod)
 {
 }
 
+void *module_writable_address(struct module *mod, void *loc)
+{
+	if (!mod)
+		return loc;
+
+	for_class_mod_mem_type(type, text) {
+		struct module_memory *mem = &mod->mem[type];
+
+		if (loc >= mem->base && loc < mem->base + mem->size)
+			return loc + (mem->rw_copy - mem->base);
+	}
+
+	return loc;
+}
+
 static int module_memory_alloc(struct module *mod, enum mod_mem_type type)
 {
 	unsigned int size = PAGE_ALIGN(mod->mem[type].size);
@@ -1206,6 +1221,23 @@  static int module_memory_alloc(struct module *mod, enum mod_mem_type type)
 	if (!ptr)
 		return -ENOMEM;
 
+	mod->mem[type].base = ptr;
+
+	if (execmem_is_rox(execmem_type)) {
+		ptr = vzalloc(size);
+
+		if (!ptr) {
+			execmem_free(mod->mem[type].base);
+			return -ENOMEM;
+		}
+
+		mod->mem[type].rw_copy = ptr;
+		mod->mem[type].is_rox = true;
+	} else {
+		mod->mem[type].rw_copy = mod->mem[type].base;
+		memset(mod->mem[type].base, 0, size);
+	}
+
 	/*
 	 * The pointer to these blocks of memory are stored on the module
 	 * structure and we keep that around so long as the module is
@@ -1219,16 +1251,17 @@  static int module_memory_alloc(struct module *mod, enum mod_mem_type type)
 	 */
 	kmemleak_not_leak(ptr);
 
-	memset(ptr, 0, size);
-	mod->mem[type].base = ptr;
-
 	return 0;
 }
 
 static void module_memory_free(struct module *mod, enum mod_mem_type type,
 			       bool unload_codetags)
 {
-	void *ptr = mod->mem[type].base;
+	struct module_memory *mem = &mod->mem[type];
+	void *ptr = mem->base;
+
+	if (mem->is_rox)
+		vfree(mem->rw_copy);
 
 	if (!unload_codetags && mod_mem_type_is_core_data(type))
 		return;
@@ -2251,6 +2284,7 @@  static int move_module(struct module *mod, struct load_info *info)
 	for_each_mod_mem_type(type) {
 		if (!mod->mem[type].size) {
 			mod->mem[type].base = NULL;
+			mod->mem[type].rw_copy = NULL;
 			continue;
 		}
 
@@ -2267,11 +2301,14 @@  static int move_module(struct module *mod, struct load_info *info)
 		void *dest;
 		Elf_Shdr *shdr = &info->sechdrs[i];
 		enum mod_mem_type type = shdr->sh_entsize >> SH_ENTSIZE_TYPE_SHIFT;
+		unsigned long offset = shdr->sh_entsize & SH_ENTSIZE_OFFSET_MASK;
+		unsigned long addr;
 
 		if (!(shdr->sh_flags & SHF_ALLOC))
 			continue;
 
-		dest = mod->mem[type].base + (shdr->sh_entsize & SH_ENTSIZE_OFFSET_MASK);
+		addr = (unsigned long)mod->mem[type].base + offset;
+		dest = mod->mem[type].rw_copy + offset;
 
 		if (shdr->sh_type != SHT_NOBITS) {
 			/*
@@ -2293,7 +2330,7 @@  static int move_module(struct module *mod, struct load_info *info)
 		 * users of info can keep taking advantage and using the newly
 		 * minted official memory area.
 		 */
-		shdr->sh_addr = (unsigned long)dest;
+		shdr->sh_addr = addr;
 		pr_debug("\t0x%lx 0x%.8lx %s\n", (long)shdr->sh_addr,
 			 (long)shdr->sh_size, info->secstrings + shdr->sh_name);
 	}
@@ -2441,8 +2478,17 @@  int __weak module_finalize(const Elf_Ehdr *hdr,
 	return 0;
 }
 
+int __weak module_post_finalize(const Elf_Ehdr *hdr,
+				const Elf_Shdr *sechdrs,
+				struct module *me)
+{
+	return 0;
+}
+
 static int post_relocation(struct module *mod, const struct load_info *info)
 {
+	int ret;
+
 	/* Sort exception table now relocations are done. */
 	sort_extable(mod->extable, mod->extable + mod->num_exentries);
 
@@ -2454,7 +2500,24 @@  static int post_relocation(struct module *mod, const struct load_info *info)
 	add_kallsyms(mod, info);
 
 	/* Arch-specific module finalizing. */
-	return module_finalize(info->hdr, info->sechdrs, mod);
+	ret = module_finalize(info->hdr, info->sechdrs, mod);
+	if (ret)
+		return ret;
+
+	for_each_mod_mem_type(type) {
+		struct module_memory *mem = &mod->mem[type];
+
+		if (mem->is_rox) {
+			if (!execmem_update_copy(mem->base, mem->rw_copy,
+						 mem->size))
+				return -ENOMEM;
+
+			vfree(mem->rw_copy);
+			mem->rw_copy = NULL;
+		}
+	}
+
+	return module_post_finalize(info->hdr, info->sechdrs, mod);
 }
 
 /* Call module constructors. */
diff --git a/kernel/module/strict_rwx.c b/kernel/module/strict_rwx.c
index c45caa4690e5..239e5013359d 100644
--- a/kernel/module/strict_rwx.c
+++ b/kernel/module/strict_rwx.c
@@ -34,6 +34,9 @@  int module_enable_text_rox(const struct module *mod)
 	for_class_mod_mem_type(type, text) {
 		int ret;
 
+		if (mod->mem[type].is_rox)
+			continue;
+
 		if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
 			ret = module_set_memory(mod, type, set_memory_rox);
 		else
diff --git a/mm/execmem.c b/mm/execmem.c
index 0c4b36bc6d10..0f6691e9ffe6 100644
--- a/mm/execmem.c
+++ b/mm/execmem.c
@@ -10,6 +10,7 @@ 
 #include <linux/vmalloc.h>
 #include <linux/execmem.h>
 #include <linux/moduleloader.h>
+#include <linux/text-patching.h>
 
 static struct execmem_info *execmem_info __ro_after_init;
 static struct execmem_info default_execmem_info __ro_after_init;
@@ -69,6 +70,16 @@  void execmem_free(void *ptr)
 	vfree(ptr);
 }
 
+void *execmem_update_copy(void *dst, const void *src, size_t size)
+{
+	return text_poke_copy(dst, src, size);
+}
+
+bool execmem_is_rox(enum execmem_type type)
+{
+	return !!(execmem_info->ranges[type].flags & EXECMEM_ROX_CACHE);
+}
+
 static bool execmem_validate(struct execmem_info *info)
 {
 	struct execmem_range *r = &info->ranges[EXECMEM_DEFAULT];