vdso.c

linux 内核源代码

/*
 *    Copyright (C) 2004 Benjamin Herrenschmidt, IBM Corp.
 *			 <[e-mail]>
 *
 *  This program is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU General Public License
 *  as published by the Free Software Foundation; either version
 *  2 of the License, or (at your option) any later version.
 */

#include <linux/module.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/slab.h>
#include <linux/user.h>
#include <linux/elf.h>
#include <linux/security.h>
#include <linux/bootmem.h>

#include <asm/pgtable.h>
#include <asm/system.h>
#include <asm/processor.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
#include <asm/lmb.h>
#include <asm/machdep.h>
#include <asm/cputable.h>
#include <asm/sections.h>
#include <asm/firmware.h>
#include <asm/vdso.h>
#include <asm/vdso_datapage.h>

#include "setup.h"

#undef DEBUG

#ifdef DEBUG
#define DBG(fmt...) printk(fmt)
#else
#define DBG(fmt...)
#endif

/* Max supported size for symbol names */
#define MAX_SYMNAME	64

extern char vdso32_start, vdso32_end;
static void *vdso32_kbase = &vdso32_start;
static unsigned int vdso32_pages;
static struct page **vdso32_pagelist;
unsigned long vdso32_sigtramp;
unsigned long vdso32_rt_sigtramp;

#ifdef CONFIG_PPC64
extern char vdso64_start, vdso64_end;
static void *vdso64_kbase = &vdso64_start;
static unsigned int vdso64_pages;
static struct page **vdso64_pagelist;
unsigned long vdso64_rt_sigtramp;
#endif /* CONFIG_PPC64 */

static int vdso_ready;

/*
 * The vdso data page (aka. systemcfg for old ppc64 fans) is here.
 * Once the early boot kernel code no longer needs to muck around
 * with it, it will become dynamically allocated
 */
static union {
	struct vdso_data	data;
	u8			page[PAGE_SIZE];
} vdso_data_store __attribute__((__section__(".data.page_aligned")));
struct vdso_data *vdso_data = &vdso_data_store.data;

/* Format of the patch table */
struct vdso_patch_def
{
	unsigned long	ftr_mask, ftr_value;
	const char	*gen_name;
	const char	*fix_name;
};

/* Table of functions to patch based on the CPU type/revision
 *
 * Currently, we only change sync_dicache to do nothing on processors
 * with a coherent icache
 */
static struct vdso_patch_def vdso_patches[] = {
	{
		CPU_FTR_COHERENT_ICACHE, CPU_FTR_COHERENT_ICACHE,
		"__kernel_sync_dicache", "__kernel_sync_dicache_p5"
	},
	{
		CPU_FTR_USE_TB, 0,
		"__kernel_gettimeofday", NULL
	},
	{
		CPU_FTR_USE_TB, 0,
		"__kernel_clock_gettime", NULL
	},
	{
		CPU_FTR_USE_TB, 0,
		"__kernel_clock_getres", NULL
	},
	{
		CPU_FTR_USE_TB, 0,
		"__kernel_get_tbfreq", NULL
	},
};

/*
 * Some infos carried around for each of them during parsing at
 * boot time.
 */
struct lib32_elfinfo
{
	Elf32_Ehdr	*hdr;		/* ptr to ELF */
	Elf32_Sym	*dynsym;	/* ptr to .dynsym section */
	unsigned long	dynsymsize;	/* size of .dynsym section */
	char		*dynstr;	/* ptr to .dynstr section */
	unsigned long	text;		/* offset of .text section in .so */
};

struct lib64_elfinfo
{
	Elf64_Ehdr	*hdr;
	Elf64_Sym	*dynsym;
	unsigned long	dynsymsize;
	char		*dynstr;
	unsigned long	text;
};


#ifdef __DEBUG
static void dump_one_vdso_page(struct page *pg, struct page *upg)
{
	printk("kpg: %p (c:%d,f:%08lx)", __va(page_to_pfn(pg) << PAGE_SHIFT),
	       page_count(pg),
	       pg->flags);
	if (upg/* && pg != upg*/) {
		printk(" upg: %p (c:%d,f:%08lx)", __va(page_to_pfn(upg)
						       << PAGE_SHIFT),
		       page_count(upg),
		       upg->flags);
	}
	printk("\n");
}

static void dump_vdso_pages(struct vm_area_struct * vma)
{
	int i;

	if (!vma || test_thread_flag(TIF_32BIT)) {
		printk("vDSO32 @ %016lx:\n", (unsigned long)vdso32_kbase);
		for (i=0; i<vdso32_pages; i++) {
			struct page *pg = virt_to_page(vdso32_kbase +
						       i*PAGE_SIZE);
			struct page *upg = (vma && vma->vm_mm) ?
				follow_page(vma, vma->vm_start + i*PAGE_SIZE, 0)
				: NULL;
			dump_one_vdso_page(pg, upg);
		}
	}
	if (!vma || !test_thread_flag(TIF_32BIT)) {
		printk("vDSO64 @ %016lx:\n", (unsigned long)vdso64_kbase);
		for (i=0; i<vdso64_pages; i++) {
			struct page *pg = virt_to_page(vdso64_kbase +
						       i*PAGE_SIZE);
			struct page *upg = (vma && vma->vm_mm) ?
				follow_page(vma, vma->vm_start + i*PAGE_SIZE, 0)
				: NULL;
			dump_one_vdso_page(pg, upg);
		}
	}
}
#endif /* DEBUG */

/*
 * This is called from binfmt_elf, we create the special vma for the
 * vDSO and insert it into the mm struct tree
 */
int arch_setup_additional_pages(struct linux_binprm *bprm,
				int executable_stack)
{
	struct mm_struct *mm = current->mm;
	struct page **vdso_pagelist;
	unsigned long vdso_pages;
	unsigned long vdso_base;
	int rc;

	if (!vdso_ready)
		return 0;

#ifdef CONFIG_PPC64
	if (test_thread_flag(TIF_32BIT)) {
		vdso_pagelist = vdso32_pagelist;
		vdso_pages = vdso32_pages;
		vdso_base = VDSO32_MBASE;
	} else {
		vdso_pagelist = vdso64_pagelist;
		vdso_pages = vdso64_pages;
		vdso_base = VDSO64_MBASE;
	}
#else
	vdso_pagelist = vdso32_pagelist;
	vdso_pages = vdso32_pages;
	vdso_base = VDSO32_MBASE;
#endif

	current->mm->context.vdso_base = 0;

	/* vDSO has a problem and was disabled, just don't "enable" it for the
	 * process
	 */
	if (vdso_pages == 0)
		return 0;
	/* Add a page to the vdso size for the data page */
	vdso_pages ++;

	/*
	 * pick a base address for the vDSO in process space. We try to put it
	 * at vdso_base which is the "natural" base for it, but we might fail
	 * and end up putting it elsewhere.
	 */
	down_write(&mm->mmap_sem);
	vdso_base = get_unmapped_area(NULL, vdso_base,
				      vdso_pages << PAGE_SHIFT, 0, 0);
	if (IS_ERR_VALUE(vdso_base)) {
		rc = vdso_base;
		goto fail_mmapsem;
	}

	/*
	 * our vma flags don't have VM_WRITE so by default, the process isn't
	 * allowed to write those pages.
	 * gdb can break that with ptrace interface, and thus trigger COW on
	 * those pages but it's then your responsibility to never do that on
	 * the "data" page of the vDSO or you'll stop getting kernel updates
	 * and your nice userland gettimeofday will be totally dead.
	 * It's fine to use that for setting breakpoints in the vDSO code
	 * pages though
	 *
	 * Make sure the vDSO gets into every core dump.
	 * Dumping its contents makes post-mortem fully interpretable later
	 * without matching up the same kernel and hardware config to see
	 * what PC values meant.
	 */
	rc = install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
				     VM_READ|VM_EXEC|
				     VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
				     VM_ALWAYSDUMP,
				     vdso_pagelist);
	if (rc)
		goto fail_mmapsem;

	/* Put vDSO base into mm struct */
	current->mm->context.vdso_base = vdso_base;

	up_write(&mm->mmap_sem);
	return 0;

 fail_mmapsem:
	up_write(&mm->mmap_sem);
	return rc;
}

const char *arch_vma_name(struct vm_area_struct *vma)
{
	if (vma->vm_mm && vma->vm_start == vma->vm_mm->context.vdso_base)
		return "[vdso]";
	return NULL;
}



static void * __init find_section32(Elf32_Ehdr *ehdr, const char *secname,
				  unsigned long *size)
{
	Elf32_Shdr *sechdrs;
	unsigned int i;
	char *secnames;

	/* Grab section headers and strings so we can tell who is who */
	sechdrs = (void *)ehdr + ehdr->e_shoff;
	secnames = (void *)ehdr + sechdrs[ehdr->e_shstrndx].sh_offset;

	/* Find the section they want */
	for (i = 1; i < ehdr->e_shnum; i++) {
		if (strcmp(secnames+sechdrs[i].sh_name, secname) == 0) {
			if (size)
				*size = sechdrs[i].sh_size;
			return (void *)ehdr + sechdrs[i].sh_offset;
		}
	}
	*size = 0;
	return NULL;
}

static Elf32_Sym * __init find_symbol32(struct lib32_elfinfo *lib,
					const char *symname)
{
	unsigned int i;
	char name[MAX_SYMNAME], *c;

	for (i = 0; i < (lib->dynsymsize / sizeof(Elf32_Sym)); i++) {
		if (lib->dynsym[i].st_name == 0)
			continue;
		strlcpy(name, lib->dynstr + lib->dynsym[i].st_name,
			MAX_SYMNAME);
		c = strchr(name, '@');
		if (c)
			*c = 0;
		if (strcmp(symname, name) == 0)
			return &lib->dynsym[i];
	}
	return NULL;
}

/* Note that we assume the section is .text and the symbol is relative to
 * the library base
 */
static unsigned long __init find_function32(struct lib32_elfinfo *lib,
					    const char *symname)
{
	Elf32_Sym *sym = find_symbol32(lib, symname);

	if (sym == NULL) {
		printk(KERN_WARNING "vDSO32: function %s not found !\n",
		       symname);
		return 0;
	}
	return sym->st_value - VDSO32_LBASE;
}

static int vdso_do_func_patch32(struct lib32_elfinfo *v32,
				struct lib64_elfinfo *v64,
				const char *orig, const char *fix)
{
	Elf32_Sym *sym32_gen, *sym32_fix;

	sym32_gen = find_symbol32(v32, orig);
	if (sym32_gen == NULL) {
		printk(KERN_ERR "vDSO32: Can't find symbol %s !\n", orig);
		return -1;
	}
	if (fix == NULL) {
		sym32_gen->st_name = 0;
		return 0;
	}
	sym32_fix = find_symbol32(v32, fix);
	if (sym32_fix == NULL) {
		printk(KERN_ERR "vDSO32: Can't find symbol %s !\n", fix);
		return -1;
	}
	sym32_gen->st_value = sym32_fix->st_value;
	sym32_gen->st_size = sym32_fix->st_size;
	sym32_gen->st_info = sym32_fix->st_info;
	sym32_gen->st_other = sym32_fix->st_other;
	sym32_gen->st_shndx = sym32_fix->st_shndx;

	return 0;
}


#ifdef CONFIG_PPC64

static void * __init find_section64(Elf64_Ehdr *ehdr, const char *secname,
				  unsigned long *size)
{
	Elf64_Shdr *sechdrs;
	unsigned int i;
	char *secnames;

	/* Grab section headers and strings so we can tell who is who */
	sechdrs = (void *)ehdr + ehdr->e_shoff;
	secnames = (void *)ehdr + sechdrs[ehdr->e_shstrndx].sh_offset;

	/* Find the section they want */
	for (i = 1; i < ehdr->e_shnum; i++) {
		if (strcmp(secnames+sechdrs[i].sh_name, secname) == 0) {
			if (size)
				*size = sechdrs[i].sh_size;
			return (void *)ehdr + sechdrs[i].sh_offset;
		}
	}
	if (size)
		*size = 0;
	return NULL;
}

static Elf64_Sym * __init find_symbol64(struct lib64_elfinfo *lib,
					const char *symname)
{
	unsigned int i;
	char name[MAX_SYMNAME], *c;