linux/arch/arm/kernel/module.c

337 lines
8.9 KiB
C
Raw Normal View History

/*
* 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>
2008-07-24 12:28:13 +08:00
#include <linux/mm.h>
#include <linux/elf.h>
#include <linux/vmalloc.h>
#include <linux/fs.h>
#include <linux/string.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/gfp.h>
#include <asm/pgtable.h>
#include <asm/sections.h>
#include <asm/smp_plat.h>
#include <asm/unwind.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, -1,
__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;
#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 = (*(u32 *)loc & 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;
*(u32 *)loc &= 0xff000000;
*(u32 *)loc |= offset & 0x00ffffff;
break;
case R_ARM_V4BX:
/* Preserve Rm and the condition code. Alter
* other bits to re-code instruction as
* MOV PC,Rm.
*/
*(u32 *)loc &= 0xf000000f;
*(u32 *)loc |= 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 = *(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;
*(u32 *)loc &= 0xfff0f000;
*(u32 *)loc |= ((offset & 0xf000) << 4) |
(offset & 0x0fff);
break;
#ifdef CONFIG_THUMB2_KERNEL
case R_ARM_THM_CALL:
case R_ARM_THM_JUMP24:
upper = *(u16 *)loc;
lower = *(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;
ARM: 6963/1: Thumb-2: Relax relocation requirements for non-function symbols The "Thumb bit" of a symbol is only really meaningful for function symbols (STT_FUNC). However, sometimes a branch is relocated against a non-function symbol; for example, PC-relative branches to anonymous assembler local symbols are typically fixed up against the start-of-section symbol, which is not a function symbol. Some inline assembler generates references of this type, such as fixup code generated by macros in <asm/uaccess.h>. The existing relocation code for R_ARM_THM_CALL/R_ARM_THM_JUMP24 interprets this case as an error, because the target symbol appears to be an ARM symbol; but this is really not the case, since the target symbol is just a base in these cases. The addend defines the precise offset to the target location, but since the addend is encoded in a non-interworking Thumb branch instruction, there is no explicit Thumb bit in the addend. Because these instructions never interwork, the implied Thumb bit in the addend is 1, and the destination is Thumb by definition. This patch removes the extraneous Thumb bit check for non-function symbols, enabling modules containing the affected relocation types to be loaded. No modification to the actual relocation code is required, since this code does not take bit[0] of the location->destination offset into account in any case. Function symbols are always checked for interworking conflicts, as before. Signed-off-by: Dave Martin <dave.martin@linaro.org> Acked-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2011-06-16 19:09:37 +08:00
/*
* 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);
*(u16 *)loc = (u16)((upper & 0xf800) | (sign << 10) |
((offset >> 12) & 0x03ff));
*(u16 *)(loc + 2) = (u16)((lower & 0xd000) |
(j1 << 13) | (j2 << 11) |
((offset >> 1) & 0x07ff));
break;
case R_ARM_THM_MOVW_ABS_NC:
case R_ARM_THM_MOVT_ABS:
upper = *(u16 *)loc;
lower = *(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;
*(u16 *)loc = (u16)((upper & 0xfbf0) |
((offset & 0xf000) >> 12) |
((offset & 0x0800) >> 1));
*(u16 *)(loc + 2) = (u16)((lower & 0x8f00) |
((offset & 0x0700) << 4) |
(offset & 0x00ff));
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;
}
ARM: P2V: introduce phys_to_virt/virt_to_phys runtime patching This idea came from Nicolas, Eric Miao produced an initial version, which was then rewritten into this. Patch the physical to virtual translations at runtime. As we modify the code, this makes it incompatible with XIP kernels, but allows us to achieve this with minimal loss of performance. As many translations are of the form: physical = virtual + (PHYS_OFFSET - PAGE_OFFSET) virtual = physical - (PHYS_OFFSET - PAGE_OFFSET) we generate an 'add' instruction for __virt_to_phys(), and a 'sub' instruction for __phys_to_virt(). We calculate at run time (PHYS_OFFSET - PAGE_OFFSET) by comparing the address prior to MMU initialization with where it should be once the MMU has been initialized, and place this constant into the above add/sub instructions. Once we have (PHYS_OFFSET - PAGE_OFFSET), we can calculate the real PHYS_OFFSET as PAGE_OFFSET is a build-time constant, and save this for the C-mode PHYS_OFFSET variable definition to use. At present, we are unable to support Realview with Sparsemem enabled as this uses a complex mapping function, and MSM as this requires a constant which will not fit in our math instruction. Add a module version magic string for this feature to prevent incompatible modules being loaded. Tested-by: Tony Lindgren <tony@atomide.com> Reviewed-by: Nicolas Pitre <nicolas.pitre@linaro.org> Tested-by: Nicolas Pitre <nicolas.pitre@linaro.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2011-01-05 03:09:43 +08:00
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)
{
ARM: P2V: introduce phys_to_virt/virt_to_phys runtime patching This idea came from Nicolas, Eric Miao produced an initial version, which was then rewritten into this. Patch the physical to virtual translations at runtime. As we modify the code, this makes it incompatible with XIP kernels, but allows us to achieve this with minimal loss of performance. As many translations are of the form: physical = virtual + (PHYS_OFFSET - PAGE_OFFSET) virtual = physical - (PHYS_OFFSET - PAGE_OFFSET) we generate an 'add' instruction for __virt_to_phys(), and a 'sub' instruction for __phys_to_virt(). We calculate at run time (PHYS_OFFSET - PAGE_OFFSET) by comparing the address prior to MMU initialization with where it should be once the MMU has been initialized, and place this constant into the above add/sub instructions. Once we have (PHYS_OFFSET - PAGE_OFFSET), we can calculate the real PHYS_OFFSET as PAGE_OFFSET is a build-time constant, and save this for the C-mode PHYS_OFFSET variable definition to use. At present, we are unable to support Realview with Sparsemem enabled as this uses a complex mapping function, and MSM as this requires a constant which will not fit in our math instruction. Add a module version magic string for this feature to prevent incompatible modules being loaded. Tested-by: Tony Lindgren <tony@atomide.com> Reviewed-by: Nicolas Pitre <nicolas.pitre@linaro.org> Tested-by: Nicolas Pitre <nicolas.pitre@linaro.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2011-01-05 03:09:43 +08:00
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(".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;
}
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);
ARM: P2V: introduce phys_to_virt/virt_to_phys runtime patching This idea came from Nicolas, Eric Miao produced an initial version, which was then rewritten into this. Patch the physical to virtual translations at runtime. As we modify the code, this makes it incompatible with XIP kernels, but allows us to achieve this with minimal loss of performance. As many translations are of the form: physical = virtual + (PHYS_OFFSET - PAGE_OFFSET) virtual = physical - (PHYS_OFFSET - PAGE_OFFSET) we generate an 'add' instruction for __virt_to_phys(), and a 'sub' instruction for __phys_to_virt(). We calculate at run time (PHYS_OFFSET - PAGE_OFFSET) by comparing the address prior to MMU initialization with where it should be once the MMU has been initialized, and place this constant into the above add/sub instructions. Once we have (PHYS_OFFSET - PAGE_OFFSET), we can calculate the real PHYS_OFFSET as PAGE_OFFSET is a build-time constant, and save this for the C-mode PHYS_OFFSET variable definition to use. At present, we are unable to support Realview with Sparsemem enabled as this uses a complex mapping function, and MSM as this requires a constant which will not fit in our math instruction. Add a module version magic string for this feature to prevent incompatible modules being loaded. Tested-by: Tony Lindgren <tony@atomide.com> Reviewed-by: Nicolas Pitre <nicolas.pitre@linaro.org> Tested-by: Nicolas Pitre <nicolas.pitre@linaro.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2011-01-05 03:09:43 +08:00
#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
}