@@ -363,6 +363,7 @@ config ARM64_ERRATUM_843419
bool "Cortex-A53: 843419: A load or store might access an incorrect address"
depends on MODULES
default y
+ select ARM64_MODULE_CMODEL_LARGE
help
This option builds kernel modules using the large memory model in
order to avoid the use of the ADRP instruction, which can cause
@@ -702,6 +703,14 @@ config ARM64_LSE_ATOMICS
endmenu
+config ARM64_MODULE_CMODEL_LARGE
+ bool
+
+config ARM64_MODULE_PLTS
+ bool
+ select ARM64_MODULE_CMODEL_LARGE
+ select HAVE_MOD_ARCH_SPECIFIC
+
endmenu
menu "Boot options"
@@ -41,10 +41,14 @@ endif
CHECKFLAGS += -D__aarch64__
-ifeq ($(CONFIG_ARM64_ERRATUM_843419), y)
+ifeq ($(CONFIG_ARM64_MODULE_CMODEL_LARGE), y)
KBUILD_CFLAGS_MODULE += -mcmodel=large
endif
+ifeq ($(CONFIG_ARM64_MODULE_PLTS),y)
+KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/arm64/kernel/module.lds
+endif
+
# Default value
head-y := arch/arm64/kernel/head.o
@@ -20,4 +20,15 @@
#define MODULE_ARCH_VERMAGIC "aarch64"
+#ifdef CONFIG_ARM64_MODULE_PLTS
+struct mod_arch_specific {
+ struct elf64_shdr *core_plt;
+ struct elf64_shdr *init_plt;
+ int core_plt_count;
+ int init_plt_count;
+};
+#endif
+
+u64 get_module_plt(struct module *mod, void *loc, u64 val);
+
#endif /* __ASM_MODULE_H */
@@ -30,6 +30,7 @@ arm64-obj-$(CONFIG_COMPAT) += sys32.o kuser32.o signal32.o \
../../arm/kernel/opcodes.o
arm64-obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o
arm64-obj-$(CONFIG_MODULES) += arm64ksyms.o module.o
+arm64-obj-$(CONFIG_ARM64_MODULE_PLTS) += module-plts.o
arm64-obj-$(CONFIG_PERF_EVENTS) += perf_regs.o perf_callchain.o
arm64-obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o
arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
new file mode 100644
@@ -0,0 +1,137 @@
+/*
+ * Copyright (C) 2014-2015 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/elf.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+struct plt_entry {
+ __le32 mov0; /* movn x16, #0x.... */
+ __le32 mov1; /* movk x16, #0x...., lsl #16 */
+ __le32 mov2; /* movk x16, #0x...., lsl #32 */
+ __le32 br; /* br x16 */
+} __aligned(8);
+
+static bool in_init(const struct module *mod, void *addr)
+{
+ return (u64)addr - (u64)mod->module_init < mod->init_size;
+}
+
+u64 get_module_plt(struct module *mod, void *loc, u64 val)
+{
+ struct plt_entry entry = {
+ cpu_to_le32(0x92800010 | (((~val ) & 0xffff)) << 5),
+ cpu_to_le32(0xf2a00010 | ((( val >> 16) & 0xffff)) << 5),
+ cpu_to_le32(0xf2c00010 | ((( val >> 32) & 0xffff)) << 5),
+ cpu_to_le32(0xd61f0200)
+ }, *plt;
+ int i, *count;
+
+ if (in_init(mod, loc)) {
+ plt = (struct plt_entry *)mod->arch.init_plt->sh_addr;
+ count = &mod->arch.init_plt_count;
+ } else {
+ plt = (struct plt_entry *)mod->arch.core_plt->sh_addr;
+ count = &mod->arch.core_plt_count;
+ }
+
+ /* Look for an existing entry pointing to 'val' */
+ for (i = 0; i < *count; i++)
+ if (plt[i].mov0 == entry.mov0 &&
+ plt[i].mov1 == entry.mov1 &&
+ plt[i].mov2 == entry.mov2)
+ return (u64)&plt[i];
+
+ i = (*count)++;
+ plt[i] = entry;
+ return (u64)&plt[i];
+}
+
+static int duplicate_rel(Elf64_Addr base, const Elf64_Rela *rela, int num)
+{
+ int i;
+
+ for (i = 0; i < num; i++) {
+ if (rela[i].r_info == rela[num].r_info &&
+ rela[i].r_addend == rela[num].r_addend)
+ return 1;
+ }
+ return 0;
+}
+
+/* Count how many PLT entries we may need */
+static unsigned int count_plts(Elf64_Addr base, const Elf64_Rela *rela, int num)
+{
+ unsigned int ret = 0;
+ int i;
+
+ /*
+ * Sure, this is order(n^2), but it's usually short, and not
+ * time critical
+ */
+ for (i = 0; i < num; i++)
+ switch (ELF64_R_TYPE(rela[i].r_info)) {
+ case R_AARCH64_JUMP26:
+ case R_AARCH64_CALL26:
+ if (!duplicate_rel(base, rela, i))
+ ret++;
+ break;
+ }
+ return ret;
+}
+
+int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
+ char *secstrings, struct module *mod)
+{
+ unsigned long core_plts = 0, init_plts = 0;
+ Elf64_Shdr *s, *sechdrs_end = sechdrs + ehdr->e_shnum;
+
+ /*
+ * To store the PLTs, we expand the .text section for core module code
+ * and the .init.text section for initialization code.
+ */
+ for (s = sechdrs; s < sechdrs_end; ++s)
+ if (strcmp(".core.plt", secstrings + s->sh_name) == 0)
+ mod->arch.core_plt = s;
+ else if (strcmp(".init.plt", secstrings + s->sh_name) == 0)
+ mod->arch.init_plt = s;
+
+ if (!mod->arch.core_plt || !mod->arch.init_plt) {
+ pr_err("%s: sections missing\n", mod->name);
+ return -ENOEXEC;
+ }
+
+ for (s = sechdrs + 1; s < sechdrs_end; ++s) {
+ const Elf64_Rela *rels = (void *)ehdr + s->sh_offset;
+ int numrels = s->sh_size / sizeof(Elf64_Rela);
+ Elf64_Shdr *dstsec = sechdrs + s->sh_info;
+
+ if (s->sh_type != SHT_RELA)
+ continue;
+
+ if (strstr(secstrings + s->sh_name, ".init"))
+ init_plts += count_plts(dstsec->sh_addr, rels, numrels);
+ else
+ core_plts += count_plts(dstsec->sh_addr, rels, numrels);
+ }
+
+ mod->arch.core_plt->sh_type = SHT_NOBITS;
+ mod->arch.core_plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+ mod->arch.core_plt->sh_addralign = L1_CACHE_BYTES;
+ mod->arch.core_plt->sh_size = core_plts * sizeof(struct plt_entry);
+ mod->arch.core_plt_count = 0;
+
+ mod->arch.init_plt->sh_type = SHT_NOBITS;
+ mod->arch.init_plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+ mod->arch.init_plt->sh_addralign = L1_CACHE_BYTES;
+ mod->arch.init_plt->sh_size = init_plts * sizeof(struct plt_entry);
+ mod->arch.init_plt_count = 0;
+ pr_debug("%s: core.plt=%lld, init.plt=%lld\n", __func__,
+ mod->arch.core_plt->sh_size, mod->arch.init_plt->sh_size);
+ return 0;
+}
@@ -38,6 +38,11 @@ void *module_alloc(unsigned long size)
GFP_KERNEL, PAGE_KERNEL_EXEC, 0,
NUMA_NO_NODE, __builtin_return_address(0));
+ if (!p && IS_ENABLED(CONFIG_ARM64_MODULE_PLTS))
+ p = __vmalloc_node_range(size, MODULE_ALIGN, VMALLOC_START,
+ VMALLOC_END, GFP_KERNEL, PAGE_KERNEL_EXEC, 0,
+ NUMA_NO_NODE, __builtin_return_address(0));
+
if (p && (kasan_module_alloc(p, size) < 0)) {
vfree(p);
return NULL;
@@ -361,6 +366,13 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
case R_AARCH64_CALL26:
ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 26,
AARCH64_INSN_IMM_26);
+
+ if (IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) &&
+ ovf == -ERANGE) {
+ val = get_module_plt(me, loc, val);
+ ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2,
+ 26, AARCH64_INSN_IMM_26);
+ }
break;
default:
new file mode 100644
@@ -0,0 +1,4 @@
+SECTIONS {
+ .core.plt : { BYTE(0) }
+ .init.plt : { BYTE(0) }
+}
This adds support for emitting PLTs at module load time for relative branches that are out of range. This is a prerequisite for KASLR, which may place the kernel and the modules anywhere in the vmalloc area, making it more likely that branch target offsets exceed the maximum range of +/- 128 MB. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> --- arch/arm64/Kconfig | 9 ++ arch/arm64/Makefile | 6 +- arch/arm64/include/asm/module.h | 11 ++ arch/arm64/kernel/Makefile | 1 + arch/arm64/kernel/module-plts.c | 137 ++++++++++++++++++++ arch/arm64/kernel/module.c | 12 ++ arch/arm64/kernel/module.lds | 4 + 7 files changed, 179 insertions(+), 1 deletion(-) -- 2.5.0 _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel