mm: introduce execmem_alloc() and execmem_free()

module_alloc() is used everywhere as a mean to allocate memory for code.

Beside being semantically wrong, this unnecessarily ties all subsystems
that need to allocate code, such as ftrace, kprobes and BPF to modules and
puts the burden of code allocation to the modules code.

Several architectures override module_alloc() because of various
constraints where the executable memory can be located and this causes
additional obstacles for improvements of code allocation.

Start splitting code allocation from modules by introducing execmem_alloc()
and execmem_free() APIs.

Initially, execmem_alloc() is a wrapper for module_alloc() and
execmem_free() is a replacement of module_memfree() to allow updating all
call sites to use the new APIs.

Since architectures define different restrictions on placement,
permissions, alignment and other parameters for memory that can be used by
different subsystems that allocate executable memory, execmem_alloc() takes
a type argument, that will be used to identify the calling subsystem and to
allow architectures define parameters for ranges suitable for that
subsystem.

No functional changes.

Signed-off-by: Mike Rapoport (IBM) <[e-mail]>
Acked-by: Masami Hiramatsu (Google) <[e-mail]>
Acked-by: Song Liu <[e-mail]>
Acked-by: Steven Rostedt (Google) <[e-mail]>
Signed-off-by: Luis Chamberlain <[e-mail]>

arch/powerpc/kernel/kprobes.c

···
 #include <linux/extable.h>
 #include <linux/kdebug.h>
 #include <linux/slab.h>
-#include <linux/moduleloader.h>
 #include <linux/set_memory.h>
+#include <linux/execmem.h>
 #include <asm/code-patching.h>
 #include <asm/cacheflush.h>
 #include <asm/sstep.h>
···
 {
 	void *page;
 
-	page = module_alloc(PAGE_SIZE);
+	page = execmem_alloc(EXECMEM_KPROBES, PAGE_SIZE);
 	if (!page)
 		return NULL;
 
···
 	}
 	return page;
 error:
-	module_memfree(page);
+	execmem_free(page);
 	return NULL;
 }
 

arch/s390/kernel/ftrace.c

···
  *   Author(s): Martin Schwidefsky <[e-mail]>
  */
 
-#include <linux/moduleloader.h>
 #include <linux/hardirq.h>
 #include <linux/uaccess.h>
 #include <linux/ftrace.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/kprobes.h>
+#include <linux/execmem.h>
 #include <trace/syscall.h>
 #include <asm/asm-offsets.h>
 #include <asm/text-patching.h>
···
 {
 	const char *start, *end;
 
-	ftrace_plt = module_alloc(PAGE_SIZE);
+	ftrace_plt = execmem_alloc(EXECMEM_FTRACE, PAGE_SIZE);
 	if (!ftrace_plt)
 		panic("cannot allocate ftrace plt\n");
 

arch/s390/kernel/kprobes.c

···
 
 #define pr_fmt(fmt) "kprobes: " fmt
 
-#include <linux/moduleloader.h>
 #include <linux/kprobes.h>
 #include <linux/ptrace.h>
 #include <linux/preempt.h>
···
 #include <linux/slab.h>
 #include <linux/hardirq.h>
 #include <linux/ftrace.h>
+#include <linux/execmem.h>
 #include <asm/set_memory.h>
 #include <asm/sections.h>
 #include <asm/dis.h>
···
 {
 	void *page;
 
-	page = module_alloc(PAGE_SIZE);
+	page = execmem_alloc(EXECMEM_KPROBES, PAGE_SIZE);
 	if (!page)
 		return NULL;
 	set_memory_rox((unsigned long)page, 1);

arch/s390/kernel/module.c

···
 #include <linux/moduleloader.h>
 #include <linux/bug.h>
 #include <linux/memory.h>
+#include <linux/execmem.h>
 #include <asm/alternative.h>
 #include <asm/nospec-branch.h>
 #include <asm/facility.h>
···
 #ifdef CONFIG_FUNCTION_TRACER
 void module_arch_cleanup(struct module *mod)
 {
-	module_memfree(mod->arch.trampolines_start);
+	execmem_free(mod->arch.trampolines_start);
 }
 #endif
 
···
 
 	size = FTRACE_HOTPATCH_TRAMPOLINES_SIZE(s->sh_size);
 	numpages = DIV_ROUND_UP(size, PAGE_SIZE);
-	start = module_alloc(numpages * PAGE_SIZE);
+	start = execmem_alloc(EXECMEM_FTRACE, numpages * PAGE_SIZE);
 	if (!start)
 		return -ENOMEM;
 	set_memory_rox((unsigned long)start, numpages);

arch/sparc/net/bpf_jit_comp_32.c

···
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/moduleloader.h>
 #include <linux/workqueue.h>
 #include <linux/netdevice.h>
 #include <linux/filter.h>
 #include <linux/cache.h>
 #include <linux/if_vlan.h>
+#include <linux/execmem.h>
 
 #include <asm/cacheflush.h>
 #include <asm/ptrace.h>
···
 				if (unlikely(proglen + ilen > oldproglen)) {
 					pr_err("bpb_jit_compile fatal error\n");
 					kfree(addrs);
-					module_memfree(image);
+					execmem_free(image);
 					return;
 				}
 				memcpy(image + proglen, temp, ilen);
···
 			break;
 		}
 		if (proglen == oldproglen) {
-			image = module_alloc(proglen);
+			image = execmem_alloc(EXECMEM_BPF, proglen);
 			if (!image)
 				goto out;
 		}
···
 void bpf_jit_free(struct bpf_prog *fp)
 {
 	if (fp->jited)
-		module_memfree(fp->bpf_func);
+		execmem_free(fp->bpf_func);
 
 	bpf_prog_unlock_free(fp);
 }

arch/x86/kernel/ftrace.c

···
 #include <linux/memory.h>
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
+#include <linux/execmem.h>
 
 #include <trace/syscall.h>
 
···
 #ifdef CONFIG_X86_64
 
 #ifdef CONFIG_MODULES
-#include <linux/moduleloader.h>
 /* Module allocation simplifies allocating memory for code */
 static inline void *alloc_tramp(unsigned long size)
 {
-	return module_alloc(size);
+	return execmem_alloc(EXECMEM_FTRACE, size);
 }
 static inline void tramp_free(void *tramp)
 {
-	module_memfree(tramp);
+	execmem_free(tramp);
 }
 #else
 /* Trampolines can only be created if modules are supported */

arch/x86/kernel/kprobes/core.c

···
 #include <linux/kgdb.h>
 #include <linux/ftrace.h>
 #include <linux/kasan.h>
-#include <linux/moduleloader.h>
 #include <linux/objtool.h>
 #include <linux/vmalloc.h>
 #include <linux/pgtable.h>
 #include <linux/set_memory.h>
 #include <linux/cfi.h>
+#include <linux/execmem.h>
 
 #include <asm/text-patching.h>
 #include <asm/cacheflush.h>
···
 {
 	void *page;
 
-	page = module_alloc(PAGE_SIZE);
+	page = execmem_alloc(EXECMEM_KPROBES, PAGE_SIZE);
 	if (!page)
 		return NULL;
 

include/linux/execmem.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_EXECMEM_ALLOC_H
+#define _LINUX_EXECMEM_ALLOC_H
+
+#include <linux/types.h>
+#include <linux/moduleloader.h>
+
+/**
+ * enum execmem_type - types of executable memory ranges
+ *
+ * There are several subsystems that allocate executable memory.
+ * Architectures define different restrictions on placement,
+ * permissions, alignment and other parameters for memory that can be used
+ * by these subsystems.
+ * Types in this enum identify subsystems that allocate executable memory
+ * and let architectures define parameters for ranges suitable for
+ * allocations by each subsystem.
+ *
+ * @EXECMEM_DEFAULT: default parameters that would be used for types that
+ * are not explicitly defined.
+ * @EXECMEM_MODULE_TEXT: parameters for module text sections
+ * @EXECMEM_KPROBES: parameters for kprobes
+ * @EXECMEM_FTRACE: parameters for ftrace
+ * @EXECMEM_BPF: parameters for BPF
+ * @EXECMEM_TYPE_MAX:
+ */
+enum execmem_type {
+	EXECMEM_DEFAULT,
+	EXECMEM_MODULE_TEXT = EXECMEM_DEFAULT,
+	EXECMEM_KPROBES,
+	EXECMEM_FTRACE,
+	EXECMEM_BPF,
+	EXECMEM_TYPE_MAX,
+};
+
+/**
+ * execmem_alloc - allocate executable memory
+ * @type: type of the allocation
+ * @size: how many bytes of memory are required
+ *
+ * Allocates memory that will contain executable code, either generated or
+ * loaded from kernel modules.
+ *
+ * The memory will have protections defined by architecture for executable
+ * region of the @type.
+ *
+ * Return: a pointer to the allocated memory or %NULL
+ */
+void *execmem_alloc(enum execmem_type type, size_t size);
+
+/**
+ * execmem_free - free executable memory
+ * @ptr: pointer to the memory that should be freed
+ */
+void execmem_free(void *ptr);
+
+#endif /* _LINUX_EXECMEM_ALLOC_H */

include/linux/moduleloader.h

···
    sections.  Returns NULL on failure. */
 void *module_alloc(unsigned long size);
 
-/* Free memory returned from module_alloc. */
-void module_memfree(void *module_region);
-
 /* Determines if the section name is an init section (that is only used during
  * module loading).
  */

kernel/bpf/core.c

···
 #include <linux/skbuff.h>
 #include <linux/vmalloc.h>
 #include <linux/random.h>
-#include <linux/moduleloader.h>
 #include <linux/bpf.h>
 #include <linux/btf.h>
 #include <linux/objtool.h>
···
 #include <linux/nospec.h>
 #include <linux/bpf_mem_alloc.h>
 #include <linux/memcontrol.h>
+#include <linux/execmem.h>
 
 #include <asm/barrier.h>
 #include <asm/unaligned.h>
···
 
 void *__weak bpf_jit_alloc_exec(unsigned long size)
 {
-	return module_alloc(size);
+	return execmem_alloc(EXECMEM_BPF, size);
 }
 
 void __weak bpf_jit_free_exec(void *addr)
 {
-	module_memfree(addr);
+	execmem_free(addr);
 }
 
 struct bpf_binary_header *

kernel/kprobes.c

···
 #include <linux/slab.h>
 #include <linux/stddef.h>
 #include <linux/export.h>
-#include <linux/moduleloader.h>
 #include <linux/kallsyms.h>
 #include <linux/freezer.h>
 #include <linux/seq_file.h>
···
 #include <linux/jump_label.h>
 #include <linux/static_call.h>
 #include <linux/perf_event.h>
+#include <linux/execmem.h>
 
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
···
 void __weak *alloc_insn_page(void)
 {
 	/*
-	 * Use module_alloc() so this page is within +/- 2GB of where the
+	 * Use execmem_alloc() so this page is within +/- 2GB of where the
 	 * kernel image and loaded module images reside. This is required
 	 * for most of the architectures.
 	 * (e.g. x86-64 needs this to handle the %rip-relative fixups.)
 	 */
-	return module_alloc(PAGE_SIZE);
+	return execmem_alloc(EXECMEM_KPROBES, PAGE_SIZE);
 }
 
 static void free_insn_page(void *page)
 {
-	module_memfree(page);
+	execmem_free(page);
 }
 
 struct kprobe_insn_cache kprobe_insn_slots = {

kernel/module/Kconfig

···
 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

kernel/module/main.c

···
 #include <linux/audit.h>
 #include <linux/cfi.h>
 #include <linux/debugfs.h>
+#include <linux/execmem.h>
 #include <uapi/linux/module.h>
 #include "internal.h"
 
···
 	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)
 {
 }
···
 	if (mod_mem_use_vmalloc(type))
 		ptr = vmalloc(size);
 	else
-		ptr = module_alloc(size);
+		ptr = execmem_alloc(EXECMEM_MODULE_TEXT, size);
 
 	if (!ptr)
 		return -ENOMEM;
···
 	if (mod_mem_use_vmalloc(type))
 		vfree(ptr);
 	else
-		module_memfree(ptr);
+		execmem_free(ptr);
 }
 
 static void free_mod_mem(struct module *mod)
···
 
 	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);
 	}
 }
···
 	 * 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

mm/Kconfig

···
 config IOMMU_MM_DATA
 	bool
 
+config EXECMEM
+	bool
+
 source "mm/damon/Kconfig"
 
 endmenu

mm/Makefile

···
 obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o
 obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o
 obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o
+obj-$(CONFIG_EXECMEM) += execmem.o

mm/execmem.c

···
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2002 Richard Henderson
+ * Copyright (C) 2001 Rusty Russell, 2002, 2010 Rusty Russell IBM.
+ * Copyright (C) 2023 Luis Chamberlain <[e-mail]>
+ * Copyright (C) 2024 Mike Rapoport IBM.
+ */
+
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <linux/execmem.h>
+#include <linux/moduleloader.h>
+
+static void *__execmem_alloc(size_t size)
+{
+	return module_alloc(size);
+}
+
+void *execmem_alloc(enum execmem_type type, size_t size)
+{
+	return __execmem_alloc(size);
+}
+
+void execmem_free(void *ptr)
+{
+	/*
+	 * This memory may be RO, and freeing RO memory in an interrupt is not
+	 * supported by vmalloc.
+	 */
+	WARN_ON(in_interrupt());
+	vfree(ptr);
+}