kexec.c

Kernel code of linux kernel

		if (flags & KEXEC_PRESERVE_CONTEXT)
			image->preserve_context = 1;
		result = machine_kexec_prepare(image);
		if (result)
			goto out;

		for (i = 0; i < nr_segments; i++) {
			result = kimage_load_segment(image, &image->segment[i]);
			if (result)
				goto out;
		}
		kimage_terminate(image);
	}
	/* Install the new kernel, and  Uninstall the old */
	image = xchg(dest_image, image);

out:
	mutex_unlock(&kexec_mutex);
	kimage_free(image);

	return result;
}

#ifdef CONFIG_COMPAT
asmlinkage long compat_sys_kexec_load(unsigned long entry,
				unsigned long nr_segments,
				struct compat_kexec_segment __user *segments,
				unsigned long flags)
{
	struct compat_kexec_segment in;
	struct kexec_segment out, __user *ksegments;
	unsigned long i, result;

	/* Don't allow clients that don't understand the native
	 * architecture to do anything.
	 */
	if ((flags & KEXEC_ARCH_MASK) == KEXEC_ARCH_DEFAULT)
		return -EINVAL;

	if (nr_segments > KEXEC_SEGMENT_MAX)
		return -EINVAL;

	ksegments = compat_alloc_user_space(nr_segments * sizeof(out));
	for (i=0; i < nr_segments; i++) {
		result = copy_from_user(&in, &segments[i], sizeof(in));
		if (result)
			return -EFAULT;

		out.buf   = compat_ptr(in.buf);
		out.bufsz = in.bufsz;
		out.mem   = in.mem;
		out.memsz = in.memsz;

		result = copy_to_user(&ksegments[i], &out, sizeof(out));
		if (result)
			return -EFAULT;
	}

	return sys_kexec_load(entry, nr_segments, ksegments, flags);
}
#endif

void crash_kexec(struct pt_regs *regs)
{
	/* Take the kexec_mutex here to prevent sys_kexec_load
	 * running on one cpu from replacing the crash kernel
	 * we are using after a panic on a different cpu.
	 *
	 * If the crash kernel was not located in a fixed area
	 * of memory the xchg(&kexec_crash_image) would be
	 * sufficient.  But since I reuse the memory...
	 */
	if (mutex_trylock(&kexec_mutex)) {
		if (kexec_crash_image) {
			struct pt_regs fixed_regs;
			crash_setup_regs(&fixed_regs, regs);
			crash_save_vmcoreinfo();
			machine_crash_shutdown(&fixed_regs);
			machine_kexec(kexec_crash_image);
		}
		mutex_unlock(&kexec_mutex);
	}
}

static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data,
			    size_t data_len)
{
	struct elf_note note;

	note.n_namesz = strlen(name) + 1;
	note.n_descsz = data_len;
	note.n_type   = type;
	memcpy(buf, &note, sizeof(note));
	buf += (sizeof(note) + 3)/4;
	memcpy(buf, name, note.n_namesz);
	buf += (note.n_namesz + 3)/4;
	memcpy(buf, data, note.n_descsz);
	buf += (note.n_descsz + 3)/4;

	return buf;
}

static void final_note(u32 *buf)
{
	struct elf_note note;

	note.n_namesz = 0;
	note.n_descsz = 0;
	note.n_type   = 0;
	memcpy(buf, &note, sizeof(note));
}

void crash_save_cpu(struct pt_regs *regs, int cpu)
{
	struct elf_prstatus prstatus;
	u32 *buf;

	if ((cpu < 0) || (cpu >= NR_CPUS))
		return;

	/* Using ELF notes here is opportunistic.
	 * I need a well defined structure format
	 * for the data I pass, and I need tags
	 * on the data to indicate what information I have
	 * squirrelled away.  ELF notes happen to provide
	 * all of that, so there is no need to invent something new.
	 */
	buf = (u32*)per_cpu_ptr(crash_notes, cpu);
	if (!buf)
		return;
	memset(&prstatus, 0, sizeof(prstatus));
	prstatus.pr_pid = current->pid;
	elf_core_copy_regs(&prstatus.pr_reg, regs);
	buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
		      	      &prstatus, sizeof(prstatus));
	final_note(buf);
}

static int __init crash_notes_memory_init(void)
{
	/* Allocate memory for saving cpu registers. */
	crash_notes = alloc_percpu(note_buf_t);
	if (!crash_notes) {
		printk("Kexec: Memory allocation for saving cpu register"
		" states failed\n");
		return -ENOMEM;
	}
	return 0;
}
module_init(crash_notes_memory_init)


/*
 * parsing the "crashkernel" commandline
 *
 * this code is intended to be called from architecture specific code
 */


/*
 * This function parses command lines in the format
 *
 *   crashkernel=ramsize-range:size[,...][@offset]
 *
 * The function returns 0 on success and -EINVAL on failure.
 */
static int __init parse_crashkernel_mem(char 			*cmdline,
					unsigned long long	system_ram,
					unsigned long long	*crash_size,
					unsigned long long	*crash_base)
{
	char *cur = cmdline, *tmp;

	/* for each entry of the comma-separated list */
	do {
		unsigned long long start, end = ULLONG_MAX, size;

		/* get the start of the range */
		start = memparse(cur, &tmp);
		if (cur == tmp) {
			pr_warning("crashkernel: Memory value expected\n");
			return -EINVAL;
		}
		cur = tmp;
		if (*cur != '-') {
			pr_warning("crashkernel: '-' expected\n");
			return -EINVAL;
		}
		cur++;

		/* if no ':' is here, than we read the end */
		if (*cur != ':') {
			end = memparse(cur, &tmp);
			if (cur == tmp) {
				pr_warning("crashkernel: Memory "
						"value expected\n");
				return -EINVAL;
			}
			cur = tmp;
			if (end <= start) {
				pr_warning("crashkernel: end <= start\n");
				return -EINVAL;
			}
		}

		if (*cur != ':') {
			pr_warning("crashkernel: ':' expected\n");
			return -EINVAL;
		}
		cur++;

		size = memparse(cur, &tmp);
		if (cur == tmp) {
			pr_warning("Memory value expected\n");
			return -EINVAL;
		}
		cur = tmp;
		if (size >= system_ram) {
			pr_warning("crashkernel: invalid size\n");
			return -EINVAL;
		}

		/* match ? */
		if (system_ram >= start && system_ram < end) {
			*crash_size = size;
			break;
		}
	} while (*cur++ == ',');

	if (*crash_size > 0) {
		while (*cur != ' ' && *cur != '@')
			cur++;
		if (*cur == '@') {
			cur++;
			*crash_base = memparse(cur, &tmp);
			if (cur == tmp) {
				pr_warning("Memory value expected "
						"after '@'\n");
				return -EINVAL;
			}
		}
	}

	return 0;
}

/*
 * That function parses "simple" (old) crashkernel command lines like
 *
 * 	crashkernel=size[@offset]
 *
 * It returns 0 on success and -EINVAL on failure.
 */
static int __init parse_crashkernel_simple(char 		*cmdline,
					   unsigned long long 	*crash_size,
					   unsigned long long 	*crash_base)
{
	char *cur = cmdline;

	*crash_size = memparse(cmdline, &cur);
	if (cmdline == cur) {
		pr_warning("crashkernel: memory value expected\n");
		return -EINVAL;
	}

	if (*cur == '@')
		*crash_base = memparse(cur+1, &cur);

	return 0;
}

/*
 * That function is the entry point for command line parsing and should be
 * called from the arch-specific code.
 */
int __init parse_crashkernel(char 		 *cmdline,
			     unsigned long long system_ram,
			     unsigned long long *crash_size,
			     unsigned long long *crash_base)
{
	char 	*p = cmdline, *ck_cmdline = NULL;
	char	*first_colon, *first_space;

	BUG_ON(!crash_size || !crash_base);
	*crash_size = 0;
	*crash_base = 0;

	/* find crashkernel and use the last one if there are more */
	p = strstr(p, "crashkernel=");
	while (p) {
		ck_cmdline = p;
		p = strstr(p+1, "crashkernel=");
	}

	if (!ck_cmdline)
		return -EINVAL;

	ck_cmdline += 12; /* strlen("crashkernel=") */

	/*
	 * if the commandline contains a ':', then that's the extended
	 * syntax -- if not, it must be the classic syntax
	 */
	first_colon = strchr(ck_cmdline, ':');
	first_space = strchr(ck_cmdline, ' ');
	if (first_colon && (!first_space || first_colon < first_space))
		return parse_crashkernel_mem(ck_cmdline, system_ram,
				crash_size, crash_base);
	else
		return parse_crashkernel_simple(ck_cmdline, crash_size,
				crash_base);

	return 0;
}



void crash_save_vmcoreinfo(void)
{
	u32 *buf;

	if (!vmcoreinfo_size)
		return;

	vmcoreinfo_append_str("CRASHTIME=%ld", get_seconds());

	buf = (u32 *)vmcoreinfo_note;

	buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data,
			      vmcoreinfo_size);

	final_note(buf);
}

void vmcoreinfo_append_str(const char *fmt, ...)
{
	va_list args;
	char buf[0x50];
	int r;

	va_start(args, fmt);
	r = vsnprintf(buf, sizeof(buf), fmt, args);
	va_end(args);

	if (r + vmcoreinfo_size > vmcoreinfo_max_size)
		r = vmcoreinfo_max_size - vmcoreinfo_size;

	memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);

	vmcoreinfo_size += r;
}

/*
 * provide an empty default implementation here -- architecture
 * code may override this
 */
void __attribute__ ((weak)) arch_crash_save_vmcoreinfo(void)
{}

unsigned long __attribute__ ((weak)) paddr_vmcoreinfo_note(void)
{
	return __pa((unsigned long)(char *)&vmcoreinfo_note);
}

static int __init crash_save_vmcoreinfo_init(void)
{
	VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
	VMCOREINFO_PAGESIZE(PAGE_SIZE);

	VMCOREINFO_SYMBOL(init_uts_ns);
	VMCOREINFO_SYMBOL(node_online_map);
	VMCOREINFO_SYMBOL(swapper_pg_dir);
	VMCOREINFO_SYMBOL(_stext);

#ifndef CONFIG_NEED_MULTIPLE_NODES
	VMCOREINFO_SYMBOL(mem_map);
	VMCOREINFO_SYMBOL(contig_page_data);
#endif
#ifdef CONFIG_SPARSEMEM
	VMCOREINFO_SYMBOL(mem_section);
	VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
	VMCOREINFO_STRUCT_SIZE(mem_section);
	VMCOREINFO_OFFSET(mem_section, section_mem_map);
#endif
	VMCOREINFO_STRUCT_SIZE(page);
	VMCOREINFO_STRUCT_SIZE(pglist_data);
	VMCOREINFO_STRUCT_SIZE(zone);
	VMCOREINFO_STRUCT_SIZE(free_area);
	VMCOREINFO_STRUCT_SIZE(list_head);
	VMCOREINFO_SIZE(nodemask_t);
	VMCOREINFO_OFFSET(page, flags);
	VMCOREINFO_OFFSET(page, _count);
	VMCOREINFO_OFFSET(page, mapping);
	VMCOREINFO_OFFSET(page, lru);
	VMCOREINFO_OFFSET(pglist_data, node_zones);
	VMCOREINFO_OFFSET(pglist_data, nr_zones);
#ifdef CONFIG_FLAT_NODE_MEM_MAP
	VMCOREINFO_OFFSET(pglist_data, node_mem_map);
#endif
	VMCOREINFO_OFFSET(pglist_data, node_start_pfn);
	VMCOREINFO_OFFSET(pglist_data, node_spanned_pages);
	VMCOREINFO_OFFSET(pglist_data, node_id);
	VMCOREINFO_OFFSET(zone, free_area);
	VMCOREINFO_OFFSET(zone, vm_stat);
	VMCOREINFO_OFFSET(zone, spanned_pages);
	VMCOREINFO_OFFSET(free_area, free_list);
	VMCOREINFO_OFFSET(list_head, next);
	VMCOREINFO_OFFSET(list_head, prev);
	VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
	VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
	VMCOREINFO_NUMBER(NR_FREE_PAGES);
	VMCOREINFO_NUMBER(PG_lru);
	VMCOREINFO_NUMBER(PG_private);
	VMCOREINFO_NUMBER(PG_swapcache);

	arch_crash_save_vmcoreinfo();

	return 0;
}

module_init(crash_save_vmcoreinfo_init)

/*
 * Move into place and start executing a preloaded standalone
 * executable.  If nothing was preloaded return an error.
 */
int kernel_kexec(void)
{
	int error = 0;

	if (!mutex_trylock(&kexec_mutex))
		return -EBUSY;
	if (!kexec_image) {
		error = -EINVAL;
		goto Unlock;
	}

#ifdef CONFIG_KEXEC_JUMP
	if (kexec_image->preserve_context) {
		mutex_lock(&pm_mutex);
		pm_prepare_console();
		error = freeze_processes();
		if (error) {
			error = -EBUSY;
			goto Restore_console;
		}
		suspend_console();
		error = device_suspend(PMSG_FREEZE);
		if (error)
			goto Resume_console;
		error = disable_nonboot_cpus();
		if (error)
			goto Resume_devices;
		device_pm_lock();
		local_irq_disable();
		/* At this point, device_suspend() has been called,
		 * but *not* device_power_down(). We *must*
		 * device_power_down() now.  Otherwise, drivers for
		 * some devices (e.g. interrupt controllers) become
		 * desynchronized with the actual state of the
		 * hardware at resume time, and evil weirdness ensues.
		 */
		error = device_power_down(PMSG_FREEZE);
		if (error)
			goto Enable_irqs;
	} else
#endif
	{
		kernel_restart_prepare(NULL);
		printk(KERN_EMERG "Starting new kernel\n");
		machine_shutdown();
	}

	machine_kexec(kexec_image);

#ifdef CONFIG_KEXEC_JUMP
	if (kexec_image->preserve_context) {
		device_power_up(PMSG_RESTORE);
 Enable_irqs:
		local_irq_enable();
		device_pm_unlock();
		enable_nonboot_cpus();
 Resume_devices:
		device_resume(PMSG_RESTORE);
 Resume_console:
		resume_console();
		thaw_processes();
 Restore_console:
		pm_restore_console();
		mutex_unlock(&pm_mutex);
	}
#endif

 Unlock:
	mutex_unlock(&kexec_mutex);
	return error;
}