summaryrefslogtreecommitdiff
path: root/arch/arm/kernel/module.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm/kernel/module.c')
-rw-r--r--arch/arm/kernel/module.c362
1 files changed, 262 insertions, 100 deletions
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index 85c3fb6c93c2..55ca3fcd37e8 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/arch/arm/kernel/module.c
*
* Copyright (C) 2002 Russell King.
* Modified for nommu by Hyok S. Choi
*
- * 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.
- *
* Module allocation method suggested by Andi Kleen.
*/
#include <linux/module.h>
@@ -15,33 +12,63 @@
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/elf.h>
-#include <linux/vmalloc.h>
#include <linux/fs.h>
#include <linux/string.h>
-#include <linux/gfp.h>
-#include <asm/pgtable.h>
#include <asm/sections.h>
#include <asm/smp_plat.h>
#include <asm/unwind.h>
+#include <asm/opcodes.h>
+
+bool module_init_section(const char *name)
+{
+ return strstarts(name, ".init") ||
+ strstarts(name, ".ARM.extab.init") ||
+ strstarts(name, ".ARM.exidx.init");
+}
-#ifdef CONFIG_XIP_KERNEL
+bool module_exit_section(const char *name)
+{
+ return strstarts(name, ".exit") ||
+ strstarts(name, ".ARM.extab.exit") ||
+ strstarts(name, ".ARM.exidx.exit");
+}
+
+#ifdef CONFIG_ARM_HAS_GROUP_RELOCS
/*
- * The XIP kernel text is mapped in the module area for modules and
- * some other stuff to work without any indirect relocations.
- * MODULES_VADDR is redefined here and not in asm/memory.h to avoid
- * recompiling the whole kernel when CONFIG_XIP_KERNEL is turned on/off.
+ * This implements the partitioning algorithm for group relocations as
+ * documented in the ARM AArch32 ELF psABI (IHI 0044).
+ *
+ * A single PC-relative symbol reference is divided in up to 3 add or subtract
+ * operations, where the final one could be incorporated into a load/store
+ * instruction with immediate offset. E.g.,
+ *
+ * ADD Rd, PC, #... or ADD Rd, PC, #...
+ * ADD Rd, Rd, #... ADD Rd, Rd, #...
+ * LDR Rd, [Rd, #...] ADD Rd, Rd, #...
+ *
+ * The latter has a guaranteed range of only 16 MiB (3x8 == 24 bits), so it is
+ * of limited use in the kernel. However, the ADD/ADD/LDR combo has a range of
+ * -/+ 256 MiB, (2x8 + 12 == 28 bits), which means it has sufficient range for
+ * any in-kernel symbol reference (unless module PLTs are being used).
+ *
+ * The main advantage of this approach over the typical pattern using a literal
+ * load is that literal loads may miss in the D-cache, and generally lead to
+ * lower cache efficiency for variables that are referenced often from many
+ * different places in the code.
*/
-#undef MODULES_VADDR
-#define MODULES_VADDR (((unsigned long)_etext + ~PMD_MASK) & PMD_MASK)
-#endif
-
-#ifdef CONFIG_MMU
-void *module_alloc(unsigned long size)
+static u32 get_group_rem(u32 group, u32 *offset)
{
- return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
- GFP_KERNEL, PAGE_KERNEL_EXEC, -1,
- __builtin_return_address(0));
+ u32 val = *offset;
+ u32 shift;
+ do {
+ shift = val ? (31 - __fls(val)) & ~1 : 32;
+ *offset = val;
+ if (!val)
+ break;
+ val &= 0xffffff >> shift;
+ } while (group--);
+ return shift;
}
#endif
@@ -59,7 +86,11 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
unsigned long loc;
Elf32_Sym *sym;
const char *symname;
+#ifdef CONFIG_ARM_HAS_GROUP_RELOCS
+ u32 shift, group = 1;
+#endif
s32 offset;
+ u32 tmp;
#ifdef CONFIG_THUMB2_KERNEL
u32 upper, lower, sign, j1, j2;
#endif
@@ -89,19 +120,39 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
break;
case R_ARM_ABS32:
+ case R_ARM_TARGET1:
*(u32 *)loc += sym->st_value;
break;
case R_ARM_PC24:
case R_ARM_CALL:
case R_ARM_JUMP24:
- offset = (*(u32 *)loc & 0x00ffffff) << 2;
- if (offset & 0x02000000)
- offset -= 0x04000000;
+ if (sym->st_value & 3) {
+ pr_err("%s: section %u reloc %u sym '%s': unsupported interworking call (ARM -> Thumb)\n",
+ module->name, relindex, i, symname);
+ return -ENOEXEC;
+ }
+
+ offset = __mem_to_opcode_arm(*(u32 *)loc);
+ offset = (offset & 0x00ffffff) << 2;
+ offset = sign_extend32(offset, 25);
offset += sym->st_value - loc;
- if (offset & 3 ||
- offset <= (s32)0xfe000000 ||
+
+ /*
+ * Route through a PLT entry if 'offset' exceeds the
+ * supported range. Note that 'offset + loc + 8'
+ * contains the absolute jump target, i.e.,
+ * @sym + addend, corrected for the +8 PC bias.
+ */
+ if (IS_ENABLED(CONFIG_ARM_MODULE_PLTS) &&
+ (offset <= (s32)0xfe000000 ||
+ offset >= (s32)0x02000000))
+ offset = get_module_plt(module, loc,
+ offset + loc + 8)
+ - loc - 8;
+
+ if (offset <= (s32)0xfe000000 ||
offset >= (s32)0x02000000) {
pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n",
module->name, relindex, i, symname,
@@ -111,9 +162,10 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
}
offset >>= 2;
+ offset &= 0x00ffffff;
- *(u32 *)loc &= 0xff000000;
- *(u32 *)loc |= offset & 0x00ffffff;
+ *(u32 *)loc &= __opcode_to_mem_arm(0xff000000);
+ *(u32 *)loc |= __opcode_to_mem_arm(offset);
break;
case R_ARM_V4BX:
@@ -121,35 +173,121 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
* other bits to re-code instruction as
* MOV PC,Rm.
*/
- *(u32 *)loc &= 0xf000000f;
- *(u32 *)loc |= 0x01a0f000;
+ *(u32 *)loc &= __opcode_to_mem_arm(0xf000000f);
+ *(u32 *)loc |= __opcode_to_mem_arm(0x01a0f000);
break;
case R_ARM_PREL31:
- offset = *(u32 *)loc + sym->st_value - loc;
- *(u32 *)loc = offset & 0x7fffffff;
+ offset = (*(s32 *)loc << 1) >> 1; /* sign extend */
+ offset += sym->st_value - loc;
+ if (offset >= 0x40000000 || offset < -0x40000000) {
+ pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n",
+ module->name, relindex, i, symname,
+ ELF32_R_TYPE(rel->r_info), loc,
+ sym->st_value);
+ return -ENOEXEC;
+ }
+ *(u32 *)loc &= 0x80000000;
+ *(u32 *)loc |= offset & 0x7fffffff;
+ break;
+
+ case R_ARM_REL32:
+ *(u32 *)loc += sym->st_value - loc;
break;
case R_ARM_MOVW_ABS_NC:
case R_ARM_MOVT_ABS:
- offset = *(u32 *)loc;
+ case R_ARM_MOVW_PREL_NC:
+ case R_ARM_MOVT_PREL:
+ offset = tmp = __mem_to_opcode_arm(*(u32 *)loc);
offset = ((offset & 0xf0000) >> 4) | (offset & 0xfff);
- offset = (offset ^ 0x8000) - 0x8000;
+ offset = sign_extend32(offset, 15);
offset += sym->st_value;
- if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_ABS)
+ if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_PREL ||
+ ELF32_R_TYPE(rel->r_info) == R_ARM_MOVW_PREL_NC)
+ offset -= loc;
+ if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_ABS ||
+ ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_PREL)
offset >>= 16;
- *(u32 *)loc &= 0xfff0f000;
- *(u32 *)loc |= ((offset & 0xf000) << 4) |
- (offset & 0x0fff);
+ tmp &= 0xfff0f000;
+ tmp |= ((offset & 0xf000) << 4) |
+ (offset & 0x0fff);
+
+ *(u32 *)loc = __opcode_to_mem_arm(tmp);
break;
+#ifdef CONFIG_ARM_HAS_GROUP_RELOCS
+ case R_ARM_ALU_PC_G0_NC:
+ group = 0;
+ fallthrough;
+ case R_ARM_ALU_PC_G1_NC:
+ tmp = __mem_to_opcode_arm(*(u32 *)loc);
+ offset = ror32(tmp & 0xff, (tmp & 0xf00) >> 7);
+ if (tmp & BIT(22))
+ offset = -offset;
+ offset += sym->st_value - loc;
+ if (offset < 0) {
+ offset = -offset;
+ tmp = (tmp & ~BIT(23)) | BIT(22); // SUB opcode
+ } else {
+ tmp = (tmp & ~BIT(22)) | BIT(23); // ADD opcode
+ }
+
+ shift = get_group_rem(group, &offset);
+ if (shift < 24) {
+ offset >>= 24 - shift;
+ offset |= (shift + 8) << 7;
+ }
+ *(u32 *)loc = __opcode_to_mem_arm((tmp & ~0xfff) | offset);
+ break;
+
+ case R_ARM_LDR_PC_G2:
+ tmp = __mem_to_opcode_arm(*(u32 *)loc);
+ offset = tmp & 0xfff;
+ if (~tmp & BIT(23)) // U bit cleared?
+ offset = -offset;
+ offset += sym->st_value - loc;
+ if (offset < 0) {
+ offset = -offset;
+ tmp &= ~BIT(23); // clear U bit
+ } else {
+ tmp |= BIT(23); // set U bit
+ }
+ get_group_rem(2, &offset);
+
+ if (offset > 0xfff) {
+ pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n",
+ module->name, relindex, i, symname,
+ ELF32_R_TYPE(rel->r_info), loc,
+ sym->st_value);
+ return -ENOEXEC;
+ }
+ *(u32 *)loc = __opcode_to_mem_arm((tmp & ~0xfff) | offset);
+ break;
+#endif
#ifdef CONFIG_THUMB2_KERNEL
case R_ARM_THM_CALL:
case R_ARM_THM_JUMP24:
- upper = *(u16 *)loc;
- lower = *(u16 *)(loc + 2);
+ /*
+ * For function symbols, only Thumb addresses are
+ * allowed (no interworking).
+ *
+ * For non-function symbols, the destination
+ * has no specific ARM/Thumb disposition, so
+ * the branch is resolved under the assumption
+ * that interworking is not required.
+ */
+ if (ELF32_ST_TYPE(sym->st_info) == STT_FUNC &&
+ !(sym->st_value & 1)) {
+ pr_err("%s: section %u reloc %u sym '%s': unsupported interworking call (Thumb -> ARM)\n",
+ module->name, relindex, i, symname);
+ return -ENOEXEC;
+ }
+
+ upper = __mem_to_opcode_thumb16(*(u16 *)loc);
+ lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2));
/*
* 25 bit signed address range (Thumb-2 BL and B.W
@@ -171,22 +309,21 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
((~(j2 ^ sign) & 1) << 22) |
((upper & 0x03ff) << 12) |
((lower & 0x07ff) << 1);
- if (offset & 0x01000000)
- offset -= 0x02000000;
+ offset = sign_extend32(offset, 24);
offset += sym->st_value - loc;
/*
- * For function symbols, only Thumb addresses are
- * allowed (no interworking).
- *
- * For non-function symbols, the destination
- * has no specific ARM/Thumb disposition, so
- * the branch is resolved under the assumption
- * that interworking is not required.
+ * Route through a PLT entry if 'offset' exceeds the
+ * supported range.
*/
- if ((ELF32_ST_TYPE(sym->st_info) == STT_FUNC &&
- !(offset & 1)) ||
- offset <= (s32)0xff000000 ||
+ if (IS_ENABLED(CONFIG_ARM_MODULE_PLTS) &&
+ (offset <= (s32)0xff000000 ||
+ offset >= (s32)0x01000000))
+ offset = get_module_plt(module, loc,
+ offset + loc + 4)
+ - loc - 4;
+
+ if (offset <= (s32)0xff000000 ||
offset >= (s32)0x01000000) {
pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n",
module->name, relindex, i, symname,
@@ -198,17 +335,22 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
sign = (offset >> 24) & 1;
j1 = sign ^ (~(offset >> 23) & 1);
j2 = sign ^ (~(offset >> 22) & 1);
- *(u16 *)loc = (u16)((upper & 0xf800) | (sign << 10) |
+ upper = (u16)((upper & 0xf800) | (sign << 10) |
((offset >> 12) & 0x03ff));
- *(u16 *)(loc + 2) = (u16)((lower & 0xd000) |
- (j1 << 13) | (j2 << 11) |
- ((offset >> 1) & 0x07ff));
+ lower = (u16)((lower & 0xd000) |
+ (j1 << 13) | (j2 << 11) |
+ ((offset >> 1) & 0x07ff));
+
+ *(u16 *)loc = __opcode_to_mem_thumb16(upper);
+ *(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower);
break;
case R_ARM_THM_MOVW_ABS_NC:
case R_ARM_THM_MOVT_ABS:
- upper = *(u16 *)loc;
- lower = *(u16 *)(loc + 2);
+ case R_ARM_THM_MOVW_PREL_NC:
+ case R_ARM_THM_MOVT_PREL:
+ upper = __mem_to_opcode_thumb16(*(u16 *)loc);
+ lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2));
/*
* MOVT/MOVW instructions encoding in Thumb-2:
@@ -223,23 +365,29 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
offset = ((upper & 0x000f) << 12) |
((upper & 0x0400) << 1) |
((lower & 0x7000) >> 4) | (lower & 0x00ff);
- offset = (offset ^ 0x8000) - 0x8000;
+ offset = sign_extend32(offset, 15);
offset += sym->st_value;
- if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_ABS)
+ if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_PREL ||
+ ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVW_PREL_NC)
+ offset -= loc;
+ if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_ABS ||
+ ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_PREL)
offset >>= 16;
- *(u16 *)loc = (u16)((upper & 0xfbf0) |
- ((offset & 0xf000) >> 12) |
- ((offset & 0x0800) >> 1));
- *(u16 *)(loc + 2) = (u16)((lower & 0x8f00) |
- ((offset & 0x0700) << 4) |
- (offset & 0x00ff));
+ upper = (u16)((upper & 0xfbf0) |
+ ((offset & 0xf000) >> 12) |
+ ((offset & 0x0800) >> 1));
+ lower = (u16)((lower & 0x8f00) |
+ ((offset & 0x0700) << 4) |
+ (offset & 0x00ff));
+ *(u16 *)loc = __opcode_to_mem_thumb16(upper);
+ *(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower);
break;
#endif
default:
- printk(KERN_ERR "%s: unknown relocation: %u\n",
+ pr_err("%s: unknown relocation: %u\n",
module->name, ELF32_R_TYPE(rel->r_info));
return -ENOEXEC;
}
@@ -247,11 +395,6 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
return 0;
}
-struct mod_unwind_map {
- const Elf_Shdr *unw_sec;
- const Elf_Shdr *txt_sec;
-};
-
static const Elf_Shdr *find_mod_section(const Elf32_Ehdr *hdr,
const Elf_Shdr *sechdrs, const char *name)
{
@@ -275,38 +418,40 @@ int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs,
#ifdef CONFIG_ARM_UNWIND
const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
const Elf_Shdr *sechdrs_end = sechdrs + hdr->e_shnum;
- struct mod_unwind_map maps[ARM_SEC_MAX];
- int i;
+ struct list_head *unwind_list = &mod->arch.unwind_list;
- memset(maps, 0, sizeof(maps));
+ INIT_LIST_HEAD(unwind_list);
+ mod->arch.init_table = NULL;
for (s = sechdrs; s < sechdrs_end; s++) {
const char *secname = secstrs + s->sh_name;
+ const char *txtname;
+ const Elf_Shdr *txt_sec;
- if (!(s->sh_flags & SHF_ALLOC))
+ if (!(s->sh_flags & SHF_ALLOC) ||
+ s->sh_type != ELF_SECTION_UNWIND)
continue;
- if (strcmp(".ARM.exidx.init.text", secname) == 0)
- maps[ARM_SEC_INIT].unw_sec = s;
- else if (strcmp(".ARM.exidx", secname) == 0)
- maps[ARM_SEC_CORE].unw_sec = s;
- else if (strcmp(".ARM.exidx.exit.text", secname) == 0)
- maps[ARM_SEC_EXIT].unw_sec = s;
- else if (strcmp(".init.text", secname) == 0)
- maps[ARM_SEC_INIT].txt_sec = s;
- else if (strcmp(".text", secname) == 0)
- maps[ARM_SEC_CORE].txt_sec = s;
- else if (strcmp(".exit.text", secname) == 0)
- maps[ARM_SEC_EXIT].txt_sec = s;
- }
+ if (!strcmp(".ARM.exidx", secname))
+ txtname = ".text";
+ else
+ txtname = secname + strlen(".ARM.exidx");
+ txt_sec = find_mod_section(hdr, sechdrs, txtname);
+
+ if (txt_sec) {
+ struct unwind_table *table =
+ unwind_table_add(s->sh_addr,
+ s->sh_size,
+ txt_sec->sh_addr,
+ txt_sec->sh_size);
+
+ list_add(&table->mod_list, unwind_list);
- for (i = 0; i < ARM_SEC_MAX; i++)
- if (maps[i].unw_sec && maps[i].txt_sec)
- mod->arch.unwind[i] =
- unwind_table_add(maps[i].unw_sec->sh_addr,
- maps[i].unw_sec->sh_size,
- maps[i].txt_sec->sh_addr,
- maps[i].txt_sec->sh_size);
+ /* save init table for module_arch_freeing_init */
+ if (strcmp(".ARM.exidx.init.text", secname) == 0)
+ mod->arch.init_table = table;
+ }
+ }
#endif
#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
s = find_mod_section(hdr, sechdrs, ".pv_table");
@@ -327,10 +472,27 @@ void
module_arch_cleanup(struct module *mod)
{
#ifdef CONFIG_ARM_UNWIND
- int i;
+ struct unwind_table *tmp;
+ struct unwind_table *n;
+
+ list_for_each_entry_safe(tmp, n,
+ &mod->arch.unwind_list, mod_list) {
+ list_del(&tmp->mod_list);
+ unwind_table_del(tmp);
+ }
+ mod->arch.init_table = NULL;
+#endif
+}
+
+void module_arch_freeing_init(struct module *mod)
+{
+#ifdef CONFIG_ARM_UNWIND
+ struct unwind_table *init = mod->arch.init_table;
- for (i = 0; i < ARM_SEC_MAX; i++)
- if (mod->arch.unwind[i])
- unwind_table_del(mod->arch.unwind[i]);
+ if (init) {
+ mod->arch.init_table = NULL;
+ list_del(&init->mod_list);
+ unwind_table_del(init);
+ }
#endif
}
generated by cgit (git 2.34.1) at 2025-12-21 21:14:41 +0000