mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-14 05:36:42 +07:00
f47671e2d8
Pull ARM updates from Russell King: "Included in this series are: 1. BE8 (modern big endian) changes for ARM from Ben Dooks 2. big.Little support from Nicolas Pitre and Dave Martin 3. support for LPAE systems with all system memory above 4GB 4. Perf updates from Will Deacon 5. Additional prefetching and other performance improvements from Will. 6. Neon-optimised AES implementation fro Ard. 7. A number of smaller fixes scattered around the place. There is a rather horrid merge conflict in tools/perf - I was never notified of the conflict because it originally occurred between Will's tree and other stuff. Consequently I have a resolution which Will forwarded me, which I'll forward on immediately after sending this mail. The other notable thing is I'm expecting some build breakage in the crypto stuff on ARM only with Ard's AES patches. These were merged into a stable git branch which others had already pulled, so there's little I can do about this. The problem is caused because these patches have a dependency on some code in the crypto git tree - I tried requesting a branch I can pull to resolve these, and all I got each time from the crypto people was "we'll revert our patches then" which would only make things worse since I still don't have the dependent patches. I've no idea what's going on there or how to resolve that, and since I can't split these patches from the rest of this pull request, I'm rather stuck with pushing this as-is or reverting Ard's patches. Since it should "come out in the wash" I've left them in - the only build problems they seem to cause at the moment are with randconfigs, and since it's a new feature anyway. However, if by -rc1 the dependencies aren't in, I think it'd be best to revert Ard's patches" I resolved the perf conflict roughly as per the patch sent by Russell, but there may be some differences. Any errors are likely mine. Let's see how the crypto issues work out.. * 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (110 commits) ARM: 7868/1: arm/arm64: remove atomic_clear_mask() in "include/asm/atomic.h" ARM: 7867/1: include: asm: use 'int' instead of 'unsigned long' for 'oldval' in atomic_cmpxchg(). ARM: 7866/1: include: asm: use 'long long' instead of 'u64' within atomic.h ARM: 7871/1: amba: Extend number of IRQS ARM: 7887/1: Don't smp_cross_call() on UP devices in arch_irq_work_raise() ARM: 7872/1: Support arch_irq_work_raise() via self IPIs ARM: 7880/1: Clear the IT state independent of the Thumb-2 mode ARM: 7878/1: nommu: Implement dummy early_paging_init() ARM: 7876/1: clear Thumb-2 IT state on exception handling ARM: 7874/2: bL_switcher: Remove cpu_hotplug_driver_{lock,unlock}() ARM: footbridge: fix build warnings for netwinder ARM: 7873/1: vfp: clear vfp_current_hw_state for dying cpu ARM: fix misplaced arch_virt_to_idmap() ARM: 7848/1: mcpm: Implement cpu_kill() to synchronise on powerdown ARM: 7847/1: mcpm: Factor out logical-to-physical CPU translation ARM: 7869/1: remove unused XSCALE_PMU Kconfig param ARM: 7864/1: Handle 64-bit memory in case of 32-bit phys_addr_t ARM: 7863/1: Let arm_add_memory() always use 64-bit arguments ARM: 7862/1: pcpu: replace __get_cpu_var_uses ARM: 7861/1: cacheflush: consolidate single-CPU ARMv7 cache disabling code ...
356 lines
9.8 KiB
C
356 lines
9.8 KiB
C
/*
|
|
* 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>
|
|
#include <linux/moduleloader.h>
|
|
#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>
|
|
|
|
#ifdef CONFIG_XIP_KERNEL
|
|
/*
|
|
* 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.
|
|
*/
|
|
#undef MODULES_VADDR
|
|
#define MODULES_VADDR (((unsigned long)_etext + ~PMD_MASK) & PMD_MASK)
|
|
#endif
|
|
|
|
#ifdef CONFIG_MMU
|
|
void *module_alloc(unsigned long size)
|
|
{
|
|
return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
|
|
GFP_KERNEL, PAGE_KERNEL_EXEC, NUMA_NO_NODE,
|
|
__builtin_return_address(0));
|
|
}
|
|
#endif
|
|
|
|
int
|
|
apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
|
|
unsigned int relindex, struct module *module)
|
|
{
|
|
Elf32_Shdr *symsec = sechdrs + symindex;
|
|
Elf32_Shdr *relsec = sechdrs + relindex;
|
|
Elf32_Shdr *dstsec = sechdrs + relsec->sh_info;
|
|
Elf32_Rel *rel = (void *)relsec->sh_addr;
|
|
unsigned int i;
|
|
|
|
for (i = 0; i < relsec->sh_size / sizeof(Elf32_Rel); i++, rel++) {
|
|
unsigned long loc;
|
|
Elf32_Sym *sym;
|
|
const char *symname;
|
|
s32 offset;
|
|
u32 tmp;
|
|
#ifdef CONFIG_THUMB2_KERNEL
|
|
u32 upper, lower, sign, j1, j2;
|
|
#endif
|
|
|
|
offset = ELF32_R_SYM(rel->r_info);
|
|
if (offset < 0 || offset > (symsec->sh_size / sizeof(Elf32_Sym))) {
|
|
pr_err("%s: section %u reloc %u: bad relocation sym offset\n",
|
|
module->name, relindex, i);
|
|
return -ENOEXEC;
|
|
}
|
|
|
|
sym = ((Elf32_Sym *)symsec->sh_addr) + offset;
|
|
symname = strtab + sym->st_name;
|
|
|
|
if (rel->r_offset < 0 || rel->r_offset > dstsec->sh_size - sizeof(u32)) {
|
|
pr_err("%s: section %u reloc %u sym '%s': out of bounds relocation, offset %d size %u\n",
|
|
module->name, relindex, i, symname,
|
|
rel->r_offset, dstsec->sh_size);
|
|
return -ENOEXEC;
|
|
}
|
|
|
|
loc = dstsec->sh_addr + rel->r_offset;
|
|
|
|
switch (ELF32_R_TYPE(rel->r_info)) {
|
|
case R_ARM_NONE:
|
|
/* ignore */
|
|
break;
|
|
|
|
case R_ARM_ABS32:
|
|
*(u32 *)loc += sym->st_value;
|
|
break;
|
|
|
|
case R_ARM_PC24:
|
|
case R_ARM_CALL:
|
|
case R_ARM_JUMP24:
|
|
offset = __mem_to_opcode_arm(*(u32 *)loc);
|
|
offset = (offset & 0x00ffffff) << 2;
|
|
if (offset & 0x02000000)
|
|
offset -= 0x04000000;
|
|
|
|
offset += sym->st_value - loc;
|
|
if (offset & 3 ||
|
|
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,
|
|
ELF32_R_TYPE(rel->r_info), loc,
|
|
sym->st_value);
|
|
return -ENOEXEC;
|
|
}
|
|
|
|
offset >>= 2;
|
|
offset &= 0x00ffffff;
|
|
|
|
*(u32 *)loc &= __opcode_to_mem_arm(0xff000000);
|
|
*(u32 *)loc |= __opcode_to_mem_arm(offset);
|
|
break;
|
|
|
|
case R_ARM_V4BX:
|
|
/* Preserve Rm and the condition code. Alter
|
|
* other bits to re-code instruction as
|
|
* MOV PC,Rm.
|
|
*/
|
|
*(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;
|
|
break;
|
|
|
|
case R_ARM_MOVW_ABS_NC:
|
|
case R_ARM_MOVT_ABS:
|
|
offset = tmp = __mem_to_opcode_arm(*(u32 *)loc);
|
|
offset = ((offset & 0xf0000) >> 4) | (offset & 0xfff);
|
|
offset = (offset ^ 0x8000) - 0x8000;
|
|
|
|
offset += sym->st_value;
|
|
if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_ABS)
|
|
offset >>= 16;
|
|
|
|
tmp &= 0xfff0f000;
|
|
tmp |= ((offset & 0xf000) << 4) |
|
|
(offset & 0x0fff);
|
|
|
|
*(u32 *)loc = __opcode_to_mem_arm(tmp);
|
|
break;
|
|
|
|
#ifdef CONFIG_THUMB2_KERNEL
|
|
case R_ARM_THM_CALL:
|
|
case R_ARM_THM_JUMP24:
|
|
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
|
|
* instructions):
|
|
* S:I1:I2:imm10:imm11:0
|
|
* where:
|
|
* S = upper[10] = offset[24]
|
|
* I1 = ~(J1 ^ S) = offset[23]
|
|
* I2 = ~(J2 ^ S) = offset[22]
|
|
* imm10 = upper[9:0] = offset[21:12]
|
|
* imm11 = lower[10:0] = offset[11:1]
|
|
* J1 = lower[13]
|
|
* J2 = lower[11]
|
|
*/
|
|
sign = (upper >> 10) & 1;
|
|
j1 = (lower >> 13) & 1;
|
|
j2 = (lower >> 11) & 1;
|
|
offset = (sign << 24) | ((~(j1 ^ sign) & 1) << 23) |
|
|
((~(j2 ^ sign) & 1) << 22) |
|
|
((upper & 0x03ff) << 12) |
|
|
((lower & 0x07ff) << 1);
|
|
if (offset & 0x01000000)
|
|
offset -= 0x02000000;
|
|
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.
|
|
*/
|
|
if ((ELF32_ST_TYPE(sym->st_info) == STT_FUNC &&
|
|
!(offset & 1)) ||
|
|
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,
|
|
ELF32_R_TYPE(rel->r_info), loc,
|
|
sym->st_value);
|
|
return -ENOEXEC;
|
|
}
|
|
|
|
sign = (offset >> 24) & 1;
|
|
j1 = sign ^ (~(offset >> 23) & 1);
|
|
j2 = sign ^ (~(offset >> 22) & 1);
|
|
upper = (u16)((upper & 0xf800) | (sign << 10) |
|
|
((offset >> 12) & 0x03ff));
|
|
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 = __mem_to_opcode_thumb16(*(u16 *)loc);
|
|
lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2));
|
|
|
|
/*
|
|
* MOVT/MOVW instructions encoding in Thumb-2:
|
|
*
|
|
* i = upper[10]
|
|
* imm4 = upper[3:0]
|
|
* imm3 = lower[14:12]
|
|
* imm8 = lower[7:0]
|
|
*
|
|
* imm16 = imm4:i:imm3:imm8
|
|
*/
|
|
offset = ((upper & 0x000f) << 12) |
|
|
((upper & 0x0400) << 1) |
|
|
((lower & 0x7000) >> 4) | (lower & 0x00ff);
|
|
offset = (offset ^ 0x8000) - 0x8000;
|
|
offset += sym->st_value;
|
|
|
|
if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_ABS)
|
|
offset >>= 16;
|
|
|
|
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",
|
|
module->name, ELF32_R_TYPE(rel->r_info));
|
|
return -ENOEXEC;
|
|
}
|
|
}
|
|
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)
|
|
{
|
|
const Elf_Shdr *s, *se;
|
|
const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
|
|
|
|
for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++)
|
|
if (strcmp(name, secstrs + s->sh_name) == 0)
|
|
return s;
|
|
|
|
return NULL;
|
|
}
|
|
|
|
extern void fixup_pv_table(const void *, unsigned long);
|
|
extern void fixup_smp(const void *, unsigned long);
|
|
|
|
int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs,
|
|
struct module *mod)
|
|
{
|
|
const Elf_Shdr *s = NULL;
|
|
#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;
|
|
|
|
memset(maps, 0, sizeof(maps));
|
|
|
|
for (s = sechdrs; s < sechdrs_end; s++) {
|
|
const char *secname = secstrs + s->sh_name;
|
|
|
|
if (!(s->sh_flags & SHF_ALLOC))
|
|
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(".ARM.exidx.text.unlikely", secname) == 0)
|
|
maps[ARM_SEC_UNLIKELY].unw_sec = s;
|
|
else if (strcmp(".ARM.exidx.text.hot", secname) == 0)
|
|
maps[ARM_SEC_HOT].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;
|
|
else if (strcmp(".text.unlikely", secname) == 0)
|
|
maps[ARM_SEC_UNLIKELY].txt_sec = s;
|
|
else if (strcmp(".text.hot", secname) == 0)
|
|
maps[ARM_SEC_HOT].txt_sec = s;
|
|
}
|
|
|
|
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);
|
|
#endif
|
|
#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
|
|
s = find_mod_section(hdr, sechdrs, ".pv_table");
|
|
if (s)
|
|
fixup_pv_table((void *)s->sh_addr, s->sh_size);
|
|
#endif
|
|
s = find_mod_section(hdr, sechdrs, ".alt.smp.init");
|
|
if (s && !is_smp())
|
|
#ifdef CONFIG_SMP_ON_UP
|
|
fixup_smp((void *)s->sh_addr, s->sh_size);
|
|
#else
|
|
return -EINVAL;
|
|
#endif
|
|
return 0;
|
|
}
|
|
|
|
void
|
|
module_arch_cleanup(struct module *mod)
|
|
{
|
|
#ifdef CONFIG_ARM_UNWIND
|
|
int i;
|
|
|
|
for (i = 0; i < ARM_SEC_MAX; i++)
|
|
if (mod->arch.unwind[i])
|
|
unwind_table_del(mod->arch.unwind[i]);
|
|
#endif
|
|
}
|