mm/execmem, arch: convert remaining overrides of module_alloc to execmem

Extend execmem parameters to accommodate more complex overrides of
module_alloc() by architectures.

This includes specification of a fallback range required by arm, arm64
and powerpc, EXECMEM_MODULE_DATA type required by powerpc, support for
allocation of KASAN shadow required by s390 and x86 and support for
late initialization of execmem required by arm64.

The core implementation of execmem_alloc() takes care of suppressing
warnings when the initial allocation fails but there is a fallback range
defined.

Signed-off-by: Mike Rapoport (IBM) <[email protected]>
Acked-by: Will Deacon <[email protected]>
Acked-by: Song Liu <[email protected]>
Tested-by: Liviu Dudau <[email protected]>
Signed-off-by: Luis Chamberlain <[email protected]>

arch/Kconfig

@@ -977,6 +977,14 @@ config ARCH_WANTS_MODULES_DATA_IN_VMALLOC
 	  For architectures like powerpc/32 which have constraints on module
 	  allocation and need to allocate module data outside of module area.
 
+config ARCH_WANTS_EXECMEM_LATE
+	bool
+	help
+	  For architectures that do not allocate executable memory early on
+	  boot, but rather require its initialization late when there is
+	  enough entropy for module space randomization, for instance
+	  arm64.
+
 config HAVE_IRQ_EXIT_ON_IRQ_STACK
 	bool
 	help

arch/arm/kernel/module.c

@@ -16,6 +16,7 @@
 #include <linux/fs.h>
 #include <linux/string.h>
 #include <linux/gfp.h>
+#include <linux/execmem.h>
 
 #include <asm/sections.h>
 #include <asm/smp_plat.h>
@@ -34,23 +35,31 @@
 #endif
 
 #ifdef CONFIG_MMU
-void *module_alloc(unsigned long size)
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
 {
-	gfp_t gfp_mask = GFP_KERNEL;
-	void *p;
-
-	/* Silence the initial allocation */
-	if (IS_ENABLED(CONFIG_ARM_MODULE_PLTS))
-		gfp_mask |= __GFP_NOWARN;
-
-	p = __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
-				gfp_mask, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
-				__builtin_return_address(0));
-	if (!IS_ENABLED(CONFIG_ARM_MODULE_PLTS) || p)
-		return p;
-	return __vmalloc_node_range(size, 1,  VMALLOC_START, VMALLOC_END,
-				GFP_KERNEL, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
-				__builtin_return_address(0));
+	unsigned long fallback_start = 0, fallback_end = 0;
+
+	if (IS_ENABLED(CONFIG_ARM_MODULE_PLTS)) {
+		fallback_start = VMALLOC_START;
+		fallback_end = VMALLOC_END;
+	}
+
+	execmem_info = (struct execmem_info){
+		.ranges = {
+			[EXECMEM_DEFAULT] = {
+				.start	= MODULES_VADDR,
+				.end	= MODULES_END,
+				.pgprot	= PAGE_KERNEL_EXEC,
+				.alignment = 1,
+				.fallback_start	= fallback_start,
+				.fallback_end	= fallback_end,
+			},
+		},
+	};
+
+	return &execmem_info;
 }
 #endif
 

arch/arm64/Kconfig

@@ -105,6 +105,7 @@ config ARM64
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_HUGE_PMD_SHARE if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36)
 	select ARCH_WANT_LD_ORPHAN_WARN
+	select ARCH_WANTS_EXECMEM_LATE if EXECMEM
 	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANTS_THP_SWAP if ARM64_4K_PAGES
 	select ARCH_HAS_UBSAN

arch/arm64/kernel/module.c

@@ -20,6 +20,7 @@
 #include <linux/random.h>
 #include <linux/scs.h>
 #include <linux/vmalloc.h>
+#include <linux/execmem.h>
 
 #include <asm/alternative.h>
 #include <asm/insn.h>
@@ -108,41 +109,47 @@ static int __init module_init_limits(void)
 
 	return 0;
 }
-subsys_initcall(module_init_limits);
 
-void *module_alloc(unsigned long size)
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
 {
-	void *p = NULL;
+	unsigned long fallback_start = 0, fallback_end = 0;
+	unsigned long start = 0, end = 0;
+
+	module_init_limits();
 
 	/*
 	 * Where possible, prefer to allocate within direct branch range of the
 	 * kernel such that no PLTs are necessary.
 	 */
 	if (module_direct_base) {
-		p = __vmalloc_node_range(size, MODULE_ALIGN,
-					 module_direct_base,
-					 module_direct_base + SZ_128M,
-					 GFP_KERNEL | __GFP_NOWARN,
-					 PAGE_KERNEL, 0, NUMA_NO_NODE,
-					 __builtin_return_address(0));
-	}
+		start = module_direct_base;
+		end = module_direct_base + SZ_128M;
 
-	if (!p && module_plt_base) {
-		p = __vmalloc_node_range(size, MODULE_ALIGN,
-					 module_plt_base,
-					 module_plt_base + SZ_2G,
-					 GFP_KERNEL | __GFP_NOWARN,
-					 PAGE_KERNEL, 0, NUMA_NO_NODE,
-					 __builtin_return_address(0));
-	}
-
-	if (!p) {
-		pr_warn_ratelimited("%s: unable to allocate memory\n",
-				    __func__);
+		if (module_plt_base) {
+			fallback_start = module_plt_base;
+			fallback_end = module_plt_base + SZ_2G;
+		}
+	} else if (module_plt_base) {
+		start = module_plt_base;
+		end = module_plt_base + SZ_2G;
 	}
 
-	/* Memory is intended to be executable, reset the pointer tag. */
-	return kasan_reset_tag(p);
+	execmem_info = (struct execmem_info){
+		.ranges = {
+			[EXECMEM_DEFAULT] = {
+				.start	= start,
+				.end	= end,
+				.pgprot	= PAGE_KERNEL,
+				.alignment = 1,
+				.fallback_start	= fallback_start,
+				.fallback_end	= fallback_end,
+			},
+		},
+	};
+
+	return &execmem_info;
 }
 
 enum aarch64_reloc_op {

arch/powerpc/kernel/module.c

@@ -10,6 +10,7 @@
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
 #include <linux/bug.h>
+#include <linux/execmem.h>
 #include <asm/module.h>
 #include <linux/uaccess.h>
 #include <asm/firmware.h>
@@ -89,39 +90,56 @@ int module_finalize(const Elf_Ehdr *hdr,
 	return 0;
 }
 
-static __always_inline void *
-__module_alloc(unsigned long size, unsigned long start, unsigned long end, bool nowarn)
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
 {
 	pgprot_t prot = strict_module_rwx_enabled() ? PAGE_KERNEL : PAGE_KERNEL_EXEC;
-	gfp_t gfp = GFP_KERNEL | (nowarn ? __GFP_NOWARN : 0);
+	unsigned long fallback_start = 0, fallback_end = 0;
+	unsigned long start, end;
 
 	/*
-	 * Don't do huge page allocations for modules yet until more testing
-	 * is done. STRICT_MODULE_RWX may require extra work to support this
-	 * too.
+	 * BOOK3S_32 and 8xx define MODULES_VADDR for text allocations and
+	 * allow allocating data in the entire vmalloc space
 	 */
-	return __vmalloc_node_range(size, 1, start, end, gfp, prot,
-				    VM_FLUSH_RESET_PERMS,
-				    NUMA_NO_NODE, __builtin_return_address(0));
-}
-
-void *module_alloc(unsigned long size)
-{
 #ifdef MODULES_VADDR
 	unsigned long limit = (unsigned long)_etext - SZ_32M;
-	void *ptr = NULL;
 
 	BUILD_BUG_ON(TASK_SIZE > MODULES_VADDR);
 
 	/* First try within 32M limit from _etext to avoid branch trampolines */
-	if (MODULES_VADDR < PAGE_OFFSET && MODULES_END > limit)
-		ptr = __module_alloc(size, limit, MODULES_END, true);
-
-	if (!ptr)
-		ptr = __module_alloc(size, MODULES_VADDR, MODULES_END, false);
+	if (MODULES_VADDR < PAGE_OFFSET && MODULES_END > limit) {
+		start = limit;
+		fallback_start = MODULES_VADDR;
+		fallback_end = MODULES_END;
+	} else {
+		start = MODULES_VADDR;
+	}
 
-	return ptr;
+	end = MODULES_END;
 #else
-	return __module_alloc(size, VMALLOC_START, VMALLOC_END, false);
+	start = VMALLOC_START;
+	end = VMALLOC_END;
 #endif
+
+	execmem_info = (struct execmem_info){
+		.ranges = {
+			[EXECMEM_DEFAULT] = {
+				.start	= start,
+				.end	= end,
+				.pgprot	= prot,
+				.alignment = 1,
+				.fallback_start	= fallback_start,
+				.fallback_end	= fallback_end,
+			},
+			[EXECMEM_MODULE_DATA] = {
+				.start	= VMALLOC_START,
+				.end	= VMALLOC_END,
+				.pgprot	= PAGE_KERNEL,
+				.alignment = 1,
+			},
+		},
+	};
+
+	return &execmem_info;
 }

arch/s390/kernel/module.c

@@ -37,41 +37,31 @@
 
 #define PLT_ENTRY_SIZE 22
 
-static unsigned long get_module_load_offset(void)
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
 {
-	static DEFINE_MUTEX(module_kaslr_mutex);
-	static unsigned long module_load_offset;
-
-	if (!kaslr_enabled())
-		return 0;
-	/*
-	 * Calculate the module_load_offset the first time this code
-	 * is called. Once calculated it stays the same until reboot.
-	 */
-	mutex_lock(&module_kaslr_mutex);
-	if (!module_load_offset)
+	unsigned long module_load_offset = 0;
+	unsigned long start;
+
+	if (kaslr_enabled())
 		module_load_offset = get_random_u32_inclusive(1, 1024) * PAGE_SIZE;
-	mutex_unlock(&module_kaslr_mutex);
-	return module_load_offset;
-}
 
-void *module_alloc(unsigned long size)
-{
-	gfp_t gfp_mask = GFP_KERNEL;
-	void *p;
-
-	if (PAGE_ALIGN(size) > MODULES_LEN)
-		return NULL;
-	p = __vmalloc_node_range(size, MODULE_ALIGN,
-				 MODULES_VADDR + get_module_load_offset(),
-				 MODULES_END, gfp_mask, PAGE_KERNEL,
-				 VM_FLUSH_RESET_PERMS | VM_DEFER_KMEMLEAK,
-				 NUMA_NO_NODE, __builtin_return_address(0));
-	if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) {
-		vfree(p);
-		return NULL;
-	}
-	return p;
+	start = MODULES_VADDR + module_load_offset;
+
+	execmem_info = (struct execmem_info){
+		.ranges = {
+			[EXECMEM_DEFAULT] = {
+				.flags	= EXECMEM_KASAN_SHADOW,
+				.start	= start,
+				.end	= MODULES_END,
+				.pgprot	= PAGE_KERNEL,
+				.alignment = MODULE_ALIGN,
+			},
+		},
+	};
+
+	return &execmem_info;
 }
 
 #ifdef CONFIG_FUNCTION_TRACER

arch/x86/kernel/module.c

@@ -19,6 +19,7 @@
 #include <linux/jump_label.h>
 #include <linux/random.h>
 #include <linux/memory.h>
+#include <linux/execmem.h>
 
 #include <asm/text-patching.h>
 #include <asm/page.h>
@@ -36,55 +37,30 @@ do {							\
 } while (0)
 #endif
 
-#ifdef CONFIG_RANDOMIZE_BASE
-static unsigned long module_load_offset;
+static struct execmem_info execmem_info __ro_after_init;
 
-/* Mutex protects the module_load_offset. */
-static DEFINE_MUTEX(module_kaslr_mutex);
-
-static unsigned long int get_module_load_offset(void)
-{
-	if (kaslr_enabled()) {
-		mutex_lock(&module_kaslr_mutex);
-		/*
-		 * Calculate the module_load_offset the first time this
-		 * code is called. Once calculated it stays the same until
-		 * reboot.
-		 */
-		if (module_load_offset == 0)
-			module_load_offset =
-				get_random_u32_inclusive(1, 1024) * PAGE_SIZE;
-		mutex_unlock(&module_kaslr_mutex);
-	}
-	return module_load_offset;
-}
-#else
-static unsigned long int get_module_load_offset(void)
+struct execmem_info __init *execmem_arch_setup(void)
 {
-	return 0;
-}
-#endif
-
-void *module_alloc(unsigned long size)
-{
-	gfp_t gfp_mask = GFP_KERNEL;
-	void *p;
-
-	if (PAGE_ALIGN(size) > MODULES_LEN)
-		return NULL;
-
-	p = __vmalloc_node_range(size, MODULE_ALIGN,
-				 MODULES_VADDR + get_module_load_offset(),
-				 MODULES_END, gfp_mask, PAGE_KERNEL,
-				 VM_FLUSH_RESET_PERMS | VM_DEFER_KMEMLEAK,
-				 NUMA_NO_NODE, __builtin_return_address(0));
-
-	if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) {
-		vfree(p);
-		return NULL;
-	}
-
-	return p;
+	unsigned long start, offset = 0;
+
+	if (kaslr_enabled())
+		offset = get_random_u32_inclusive(1, 1024) * PAGE_SIZE;
+
+	start = MODULES_VADDR + offset;
+
+	execmem_info = (struct execmem_info){
+		.ranges = {
+			[EXECMEM_DEFAULT] = {
+				.flags	= EXECMEM_KASAN_SHADOW,
+				.start	= start,
+				.end	= MODULES_END,
+				.pgprot	= PAGE_KERNEL,
+				.alignment = MODULE_ALIGN,
+			},
+		},
+	};
+
+	return &execmem_info;
 }
 
 #ifdef CONFIG_X86_32