binfmt_elf.c

linux下内存管理源代码。。。精、简、强!

	if (k > elf_bss)
		elf_bss = k;
	padzero(elf_bss);

	len = ELF_PAGESTART(elf_phdata->p_filesz + elf_phdata->p_vaddr + ELF_MIN_ALIGN - 1);
	bss = elf_phdata->p_memsz + elf_phdata->p_vaddr;
	if (bss > len)
		do_brk(len, bss - len);
	error = 0;

out_free_ph:
	kfree(elf_phdata);
out:
	return error;
}

/*
 * Note that some platforms still use traditional core dumps and not
 * the ELF core dump.  Each platform can select it as appropriate.
 */
#ifdef USE_ELF_CORE_DUMP

/*
 * ELF core dumper
 *
 * Modelled on fs/exec.c:aout_core_dump()
 * Jeremy Fitzhardinge <[e-mail]>
 */
/*
 * These are the only things you should do on a core-file: use only these
 * functions to write out all the necessary info.
 */
static int dump_write(struct file *file, const void *addr, int nr)
{
	return file->f_op->write(file, addr, nr, &file->f_pos) == nr;
}

static int dump_seek(struct file *file, off_t off)
{
	if (file->f_op->llseek) {
		if (file->f_op->llseek(file, off, 0) != off)
			return 0;
	} else
		file->f_pos = off;
	return 1;
}

/*
 * Decide whether a segment is worth dumping; default is yes to be
 * sure (missing info is worse than too much; etc).
 * Personally I'd include everything, and use the coredump limit...
 *
 * I think we should skip something. But I am not sure how. H.J.
 */
static inline int maydump(struct vm_area_struct *vma)
{
	if (!(vma->vm_flags & (VM_READ|VM_WRITE|VM_EXEC)))
		return 0;

	/* Do not dump I/O mapped devices! -DaveM */
	if(vma->vm_flags & VM_IO)
		return 0;
#if 1
	if (vma->vm_flags & (VM_WRITE|VM_GROWSUP|VM_GROWSDOWN))
		return 1;
	if (vma->vm_flags & (VM_READ|VM_EXEC|VM_EXECUTABLE|VM_SHARED))
		return 0;
#endif
	return 1;
}

#define roundup(x, y)  ((((x)+((y)-1))/(y))*(y))

/* An ELF note in memory */
struct memelfnote
{
	const char *name;
	int type;
	unsigned int datasz;
	void *data;
};

static int notesize(struct memelfnote *en)
{
	int sz;

	sz = sizeof(struct elf_note);
	sz += roundup(strlen(en->name), 4);
	sz += roundup(en->datasz, 4);

	return sz;
}

/* #define DEBUG */

#ifdef DEBUG
static void dump_regs(const char *str, elf_greg_t *r)
{
	int i;
	static const char *regs[] = { "ebx", "ecx", "edx", "esi", "edi", "ebp",
					      "eax", "ds", "es", "fs", "gs",
					      "orig_eax", "eip", "cs",
					      "efl", "uesp", "ss"};
	printk("Registers: %s\n", str);

	for(i = 0; i < ELF_NGREG; i++)
	{
		unsigned long val = r[i];
		printk("   %-2d %-5s=%08lx %lu\n", i, regs[i], val, val);
	}
}
#endif

#define DUMP_WRITE(addr, nr)	\
	do { if (!dump_write(file, (addr), (nr))) return 0; } while(0)
#define DUMP_SEEK(off)	\
	do { if (!dump_seek(file, (off))) return 0; } while(0)

static int writenote(struct memelfnote *men, struct file *file)
{
	struct elf_note en;

	en.n_namesz = strlen(men->name);
	en.n_descsz = men->datasz;
	en.n_type = men->type;

	DUMP_WRITE(&en, sizeof(en));
	DUMP_WRITE(men->name, en.n_namesz);
	/* XXX - cast from long long to long to avoid need for libgcc.a */
	DUMP_SEEK(roundup((unsigned long)file->f_pos, 4));	/* XXX */
	DUMP_WRITE(men->data, men->datasz);
	DUMP_SEEK(roundup((unsigned long)file->f_pos, 4));	/* XXX */

	return 1;
}
#undef DUMP_WRITE
#undef DUMP_SEEK

#define DUMP_WRITE(addr, nr)	\
	if ((size += (nr)) > limit || !dump_write(file, (addr), (nr))) \
		goto end_coredump;
#define DUMP_SEEK(off)	\
	if (!dump_seek(file, (off))) \
		goto end_coredump;
/*
 * Actual dumper
 *
 * This is a two-pass process; first we find the offsets of the bits,
 * and then they are actually written out.  If we run out of core limit
 * we just truncate.
 */
static int elf_core_dump(long signr, struct pt_regs * regs, struct file * file)
{
	int has_dumped = 0;
	mm_segment_t fs;
	int segs;
	size_t size = 0;
	int i;
	struct vm_area_struct *vma;
	struct elfhdr elf;
	off_t offset = 0, dataoff;
	unsigned long limit = current->rlim[RLIMIT_CORE].rlim_cur;
	int numnote = 4;
	struct memelfnote notes[4];
	struct elf_prstatus prstatus;	/* NT_PRSTATUS */
	elf_fpregset_t fpu;		/* NT_PRFPREG */
	struct elf_prpsinfo psinfo;	/* NT_PRPSINFO */

	segs = current->mm->map_count;

#ifdef DEBUG
	printk("elf_core_dump: %d segs %lu limit\n", segs, limit);
#endif

	/* Set up header */
	memcpy(elf.e_ident, ELFMAG, SELFMAG);
	elf.e_ident[EI_CLASS] = ELF_CLASS;
	elf.e_ident[EI_DATA] = ELF_DATA;
	elf.e_ident[EI_VERSION] = EV_CURRENT;
	memset(elf.e_ident+EI_PAD, 0, EI_NIDENT-EI_PAD);

	elf.e_type = ET_CORE;
	elf.e_machine = ELF_ARCH;
	elf.e_version = EV_CURRENT;
	elf.e_entry = 0;
	elf.e_phoff = sizeof(elf);
	elf.e_shoff = 0;
	elf.e_flags = 0;
	elf.e_ehsize = sizeof(elf);
	elf.e_phentsize = sizeof(struct elf_phdr);
	elf.e_phnum = segs+1;		/* Include notes */
	elf.e_shentsize = 0;
	elf.e_shnum = 0;
	elf.e_shstrndx = 0;

	fs = get_fs();
	set_fs(KERNEL_DS);

	has_dumped = 1;
	current->flags |= PF_DUMPCORE;

	DUMP_WRITE(&elf, sizeof(elf));
	offset += sizeof(elf);				/* Elf header */
	offset += (segs+1) * sizeof(struct elf_phdr);	/* Program headers */

	/*
	 * Set up the notes in similar form to SVR4 core dumps made
	 * with info from their /proc.
	 */
	memset(&psinfo, 0, sizeof(psinfo));
	memset(&prstatus, 0, sizeof(prstatus));

	notes[0].name = "CORE";
	notes[0].type = NT_PRSTATUS;
	notes[0].datasz = sizeof(prstatus);
	notes[0].data = &prstatus;
	prstatus.pr_info.si_signo = prstatus.pr_cursig = signr;
	prstatus.pr_sigpend = current->pending.signal.sig[0];
	prstatus.pr_sighold = current->blocked.sig[0];
	psinfo.pr_pid = prstatus.pr_pid = current->pid;
	psinfo.pr_ppid = prstatus.pr_ppid = current->p_pptr->pid;
	psinfo.pr_pgrp = prstatus.pr_pgrp = current->pgrp;
	psinfo.pr_sid = prstatus.pr_sid = current->session;
	prstatus.pr_utime.tv_sec = CT_TO_SECS(current->times.tms_utime);
	prstatus.pr_utime.tv_usec = CT_TO_USECS(current->times.tms_utime);
	prstatus.pr_stime.tv_sec = CT_TO_SECS(current->times.tms_stime);
	prstatus.pr_stime.tv_usec = CT_TO_USECS(current->times.tms_stime);
	prstatus.pr_cutime.tv_sec = CT_TO_SECS(current->times.tms_cutime);
	prstatus.pr_cutime.tv_usec = CT_TO_USECS(current->times.tms_cutime);
	prstatus.pr_cstime.tv_sec = CT_TO_SECS(current->times.tms_cstime);
	prstatus.pr_cstime.tv_usec = CT_TO_USECS(current->times.tms_cstime);

	/*
	 * This transfers the registers from regs into the standard
	 * coredump arrangement, whatever that is.
	 */
#ifdef ELF_CORE_COPY_REGS
	ELF_CORE_COPY_REGS(prstatus.pr_reg, regs)
#else
	if (sizeof(elf_gregset_t) != sizeof(struct pt_regs))
	{
		printk("sizeof(elf_gregset_t) (%ld) != sizeof(struct pt_regs) (%ld)\n",
			(long)sizeof(elf_gregset_t), (long)sizeof(struct pt_regs));
	}
	else
		*(struct pt_regs *)&prstatus.pr_reg = *regs;
#endif

#ifdef DEBUG
	dump_regs("Passed in regs", (elf_greg_t *)regs);
	dump_regs("prstatus regs", (elf_greg_t *)&prstatus.pr_reg);
#endif

	notes[1].name = "CORE";
	notes[1].type = NT_PRPSINFO;
	notes[1].datasz = sizeof(psinfo);
	notes[1].data = &psinfo;
	i = current->state ? ffz(~current->state) + 1 : 0;
	psinfo.pr_state = i;
	psinfo.pr_sname = (i < 0 || i > 5) ? '.' : "RSDZTD"[i];
	psinfo.pr_zomb = psinfo.pr_sname == 'Z';
	psinfo.pr_nice = current->nice;
	psinfo.pr_flag = current->flags;
	psinfo.pr_uid = NEW_TO_OLD_UID(current->uid);
	psinfo.pr_gid = NEW_TO_OLD_GID(current->gid);
	{
		int i, len;

		set_fs(fs);

		len = current->mm->arg_end - current->mm->arg_start;
		if (len >= ELF_PRARGSZ)
			len = ELF_PRARGSZ-1;
		copy_from_user(&psinfo.pr_psargs,
			      (const char *)current->mm->arg_start, len);
		for(i = 0; i < len; i++)
			if (psinfo.pr_psargs[i] == 0)
				psinfo.pr_psargs[i] = ' ';
		psinfo.pr_psargs[len] = 0;

		set_fs(KERNEL_DS);
	}
	strncpy(psinfo.pr_fname, current->comm, sizeof(psinfo.pr_fname));

	notes[2].name = "CORE";
	notes[2].type = NT_TASKSTRUCT;
	notes[2].datasz = sizeof(*current);
	notes[2].data = current;

	/* Try to dump the FPU. */
	prstatus.pr_fpvalid = dump_fpu (regs, &fpu);
	if (!prstatus.pr_fpvalid)
	{
		numnote--;
	}
	else
	{
		notes[3].name = "CORE";
		notes[3].type = NT_PRFPREG;
		notes[3].datasz = sizeof(fpu);
		notes[3].data = &fpu;
	}
	
	/* Write notes phdr entry */
	{
		struct elf_phdr phdr;
		int sz = 0;

		for(i = 0; i < numnote; i++)
			sz += notesize(&notes[i]);

		phdr.p_type = PT_NOTE;
		phdr.p_offset = offset;
		phdr.p_vaddr = 0;
		phdr.p_paddr = 0;
		phdr.p_filesz = sz;
		phdr.p_memsz = 0;
		phdr.p_flags = 0;
		phdr.p_align = 0;

		offset += phdr.p_filesz;
		DUMP_WRITE(&phdr, sizeof(phdr));
	}

	/* Page-align dumped data */
	dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);

	/* Write program headers for segments dump */
	for(vma = current->mm->mmap; vma != NULL; vma = vma->vm_next) {
		struct elf_phdr phdr;
		size_t sz;

		sz = vma->vm_end - vma->vm_start;

		phdr.p_type = PT_LOAD;
		phdr.p_offset = offset;
		phdr.p_vaddr = vma->vm_start;
		phdr.p_paddr = 0;
		phdr.p_filesz = maydump(vma) ? sz : 0;
		phdr.p_memsz = sz;
		offset += phdr.p_filesz;
		phdr.p_flags = vma->vm_flags & VM_READ ? PF_R : 0;
		if (vma->vm_flags & VM_WRITE) phdr.p_flags |= PF_W;
		if (vma->vm_flags & VM_EXEC) phdr.p_flags |= PF_X;
		phdr.p_align = ELF_EXEC_PAGESIZE;

		DUMP_WRITE(&phdr, sizeof(phdr));
	}

	for(i = 0; i < numnote; i++)
		if (!writenote(&notes[i], file))
			goto end_coredump;

	set_fs(fs);

	DUMP_SEEK(dataoff);

	for(vma = current->mm->mmap; vma != NULL; vma = vma->vm_next) {
		unsigned long addr;

		if (!maydump(vma))
			continue;
#ifdef DEBUG
		printk("elf_core_dump: writing %08lx %lx\n", addr, len);
#endif
		for (addr = vma->vm_start;
		     addr < vma->vm_end;
		     addr += PAGE_SIZE) {
			pgd_t *pgd;
			pmd_t *pmd;
			pte_t *pte;

			pgd = pgd_offset(vma->vm_mm, addr);
			pmd = pmd_alloc(pgd, addr);
	
			if (!pmd)
				goto end_coredump;
			pte = pte_alloc(pmd, addr);
			if (!pte)
				goto end_coredump;
			if (!pte_present(*pte) &&
			    pte_none(*pte)) {
				DUMP_SEEK (file->f_pos + PAGE_SIZE);
			} else {
				DUMP_WRITE((void*)addr, PAGE_SIZE);
			}
		}
	}

	if ((off_t) file->f_pos != offset) {
		/* Sanity check */
		printk("elf_core_dump: file->f_pos (%ld) != offset (%ld)\n",
		       (off_t) file->f_pos, offset);
	}

 end_coredump:
	set_fs(fs);
	return has_dumped;
}
#endif		/* USE_ELF_CORE_DUMP */

static int __init init_elf_binfmt(void)
{
	return register_binfmt(&elf_format);
}

static void __exit exit_elf_binfmt(void)
{
	/* Remove the COFF and ELF loaders. */
	unregister_binfmt(&elf_format);
}

module_init(init_elf_binfmt)
module_exit(exit_elf_binfmt)