Revision 0ee931c4e31a5efb134c76440405e9219f896e33 authored by Michal Hocko on 13 September 2017, 23:28:29 UTC, committed by Linus Torvalds on 14 September 2017, 01:53:16 UTC
GFP_TEMPORARY was introduced by commit e12ba74d8ff3 ("Group short-lived
and reclaimable kernel allocations") along with __GFP_RECLAIMABLE.  It's
primary motivation was to allow users to tell that an allocation is
short lived and so the allocator can try to place such allocations close
together and prevent long term fragmentation.  As much as this sounds
like a reasonable semantic it becomes much less clear when to use the
highlevel GFP_TEMPORARY allocation flag.  How long is temporary? Can the
context holding that memory sleep? Can it take locks? It seems there is
no good answer for those questions.

The current implementation of GFP_TEMPORARY is basically GFP_KERNEL |
__GFP_RECLAIMABLE which in itself is tricky because basically none of
the existing caller provide a way to reclaim the allocated memory.  So
this is rather misleading and hard to evaluate for any benefits.

I have checked some random users and none of them has added the flag
with a specific justification.  I suspect most of them just copied from
other existing users and others just thought it might be a good idea to
use without any measuring.  This suggests that GFP_TEMPORARY just
motivates for cargo cult usage without any reasoning.

I believe that our gfp flags are quite complex already and especially
those with highlevel semantic should be clearly defined to prevent from
confusion and abuse.  Therefore I propose dropping GFP_TEMPORARY and
replace all existing users to simply use GFP_KERNEL.  Please note that
SLAB users with shrinkers will still get __GFP_RECLAIMABLE heuristic and
so they will be placed properly for memory fragmentation prevention.

I can see reasons we might want some gfp flag to reflect shorterm
allocations but I propose starting from a clear semantic definition and
only then add users with proper justification.

This was been brought up before LSF this year by Matthew [1] and it
turned out that GFP_TEMPORARY really doesn't have a clear semantic.  It
seems to be a heuristic without any measured advantage for most (if not
all) its current users.  The follow up discussion has revealed that
opinions on what might be temporary allocation differ a lot between
developers.  So rather than trying to tweak existing users into a
semantic which they haven't expected I propose to simply remove the flag
and start from scratch if we really need a semantic for short term
allocations.

[1] http://lkml.kernel.org/r/20170118054945.GD18349@bombadil.infradead.org

[akpm@linux-foundation.org: fix typo]
[akpm@linux-foundation.org: coding-style fixes]
[sfr@canb.auug.org.au: drm/i915: fix up]
  Link: http://lkml.kernel.org/r/20170816144703.378d4f4d@canb.auug.org.au
Link: http://lkml.kernel.org/r/20170728091904.14627-1-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Neil Brown <neilb@suse.de>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent d0dbf77
Raw File
reboot.c
/*
 *  linux/kernel/reboot.c
 *
 *  Copyright (C) 2013  Linus Torvalds
 */

#define pr_fmt(fmt)	"reboot: " fmt

#include <linux/ctype.h>
#include <linux/export.h>
#include <linux/kexec.h>
#include <linux/kmod.h>
#include <linux/kmsg_dump.h>
#include <linux/reboot.h>
#include <linux/suspend.h>
#include <linux/syscalls.h>
#include <linux/syscore_ops.h>
#include <linux/uaccess.h>

/*
 * this indicates whether you can reboot with ctrl-alt-del: the default is yes
 */

int C_A_D = 1;
struct pid *cad_pid;
EXPORT_SYMBOL(cad_pid);

#if defined(CONFIG_ARM) || defined(CONFIG_UNICORE32)
#define DEFAULT_REBOOT_MODE		= REBOOT_HARD
#else
#define DEFAULT_REBOOT_MODE
#endif
enum reboot_mode reboot_mode DEFAULT_REBOOT_MODE;

/*
 * This variable is used privately to keep track of whether or not
 * reboot_type is still set to its default value (i.e., reboot= hasn't
 * been set on the command line).  This is needed so that we can
 * suppress DMI scanning for reboot quirks.  Without it, it's
 * impossible to override a faulty reboot quirk without recompiling.
 */
int reboot_default = 1;
int reboot_cpu;
enum reboot_type reboot_type = BOOT_ACPI;
int reboot_force;

/*
 * If set, this is used for preparing the system to power off.
 */

void (*pm_power_off_prepare)(void);

/**
 *	emergency_restart - reboot the system
 *
 *	Without shutting down any hardware or taking any locks
 *	reboot the system.  This is called when we know we are in
 *	trouble so this is our best effort to reboot.  This is
 *	safe to call in interrupt context.
 */
void emergency_restart(void)
{
	kmsg_dump(KMSG_DUMP_EMERG);
	machine_emergency_restart();
}
EXPORT_SYMBOL_GPL(emergency_restart);

void kernel_restart_prepare(char *cmd)
{
	blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
	system_state = SYSTEM_RESTART;
	usermodehelper_disable();
	device_shutdown();
}

/**
 *	register_reboot_notifier - Register function to be called at reboot time
 *	@nb: Info about notifier function to be called
 *
 *	Registers a function with the list of functions
 *	to be called at reboot time.
 *
 *	Currently always returns zero, as blocking_notifier_chain_register()
 *	always returns zero.
 */
int register_reboot_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_register(&reboot_notifier_list, nb);
}
EXPORT_SYMBOL(register_reboot_notifier);

/**
 *	unregister_reboot_notifier - Unregister previously registered reboot notifier
 *	@nb: Hook to be unregistered
 *
 *	Unregisters a previously registered reboot
 *	notifier function.
 *
 *	Returns zero on success, or %-ENOENT on failure.
 */
int unregister_reboot_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_unregister(&reboot_notifier_list, nb);
}
EXPORT_SYMBOL(unregister_reboot_notifier);

/*
 *	Notifier list for kernel code which wants to be called
 *	to restart the system.
 */
static ATOMIC_NOTIFIER_HEAD(restart_handler_list);

/**
 *	register_restart_handler - Register function to be called to reset
 *				   the system
 *	@nb: Info about handler function to be called
 *	@nb->priority:	Handler priority. Handlers should follow the
 *			following guidelines for setting priorities.
 *			0:	Restart handler of last resort,
 *				with limited restart capabilities
 *			128:	Default restart handler; use if no other
 *				restart handler is expected to be available,
 *				and/or if restart functionality is
 *				sufficient to restart the entire system
 *			255:	Highest priority restart handler, will
 *				preempt all other restart handlers
 *
 *	Registers a function with code to be called to restart the
 *	system.
 *
 *	Registered functions will be called from machine_restart as last
 *	step of the restart sequence (if the architecture specific
 *	machine_restart function calls do_kernel_restart - see below
 *	for details).
 *	Registered functions are expected to restart the system immediately.
 *	If more than one function is registered, the restart handler priority
 *	selects which function will be called first.
 *
 *	Restart handlers are expected to be registered from non-architecture
 *	code, typically from drivers. A typical use case would be a system
 *	where restart functionality is provided through a watchdog. Multiple
 *	restart handlers may exist; for example, one restart handler might
 *	restart the entire system, while another only restarts the CPU.
 *	In such cases, the restart handler which only restarts part of the
 *	hardware is expected to register with low priority to ensure that
 *	it only runs if no other means to restart the system is available.
 *
 *	Currently always returns zero, as atomic_notifier_chain_register()
 *	always returns zero.
 */
int register_restart_handler(struct notifier_block *nb)
{
	return atomic_notifier_chain_register(&restart_handler_list, nb);
}
EXPORT_SYMBOL(register_restart_handler);

/**
 *	unregister_restart_handler - Unregister previously registered
 *				     restart handler
 *	@nb: Hook to be unregistered
 *
 *	Unregisters a previously registered restart handler function.
 *
 *	Returns zero on success, or %-ENOENT on failure.
 */
int unregister_restart_handler(struct notifier_block *nb)
{
	return atomic_notifier_chain_unregister(&restart_handler_list, nb);
}
EXPORT_SYMBOL(unregister_restart_handler);

/**
 *	do_kernel_restart - Execute kernel restart handler call chain
 *
 *	Calls functions registered with register_restart_handler.
 *
 *	Expected to be called from machine_restart as last step of the restart
 *	sequence.
 *
 *	Restarts the system immediately if a restart handler function has been
 *	registered. Otherwise does nothing.
 */
void do_kernel_restart(char *cmd)
{
	atomic_notifier_call_chain(&restart_handler_list, reboot_mode, cmd);
}

void migrate_to_reboot_cpu(void)
{
	/* The boot cpu is always logical cpu 0 */
	int cpu = reboot_cpu;

	cpu_hotplug_disable();

	/* Make certain the cpu I'm about to reboot on is online */
	if (!cpu_online(cpu))
		cpu = cpumask_first(cpu_online_mask);

	/* Prevent races with other tasks migrating this task */
	current->flags |= PF_NO_SETAFFINITY;

	/* Make certain I only run on the appropriate processor */
	set_cpus_allowed_ptr(current, cpumask_of(cpu));
}

/**
 *	kernel_restart - reboot the system
 *	@cmd: pointer to buffer containing command to execute for restart
 *		or %NULL
 *
 *	Shutdown everything and perform a clean reboot.
 *	This is not safe to call in interrupt context.
 */
void kernel_restart(char *cmd)
{
	kernel_restart_prepare(cmd);
	migrate_to_reboot_cpu();
	syscore_shutdown();
	if (!cmd)
		pr_emerg("Restarting system\n");
	else
		pr_emerg("Restarting system with command '%s'\n", cmd);
	kmsg_dump(KMSG_DUMP_RESTART);
	machine_restart(cmd);
}
EXPORT_SYMBOL_GPL(kernel_restart);

static void kernel_shutdown_prepare(enum system_states state)
{
	blocking_notifier_call_chain(&reboot_notifier_list,
		(state == SYSTEM_HALT) ? SYS_HALT : SYS_POWER_OFF, NULL);
	system_state = state;
	usermodehelper_disable();
	device_shutdown();
}
/**
 *	kernel_halt - halt the system
 *
 *	Shutdown everything and perform a clean system halt.
 */
void kernel_halt(void)
{
	kernel_shutdown_prepare(SYSTEM_HALT);
	migrate_to_reboot_cpu();
	syscore_shutdown();
	pr_emerg("System halted\n");
	kmsg_dump(KMSG_DUMP_HALT);
	machine_halt();
}
EXPORT_SYMBOL_GPL(kernel_halt);

/**
 *	kernel_power_off - power_off the system
 *
 *	Shutdown everything and perform a clean system power_off.
 */
void kernel_power_off(void)
{
	kernel_shutdown_prepare(SYSTEM_POWER_OFF);
	if (pm_power_off_prepare)
		pm_power_off_prepare();
	migrate_to_reboot_cpu();
	syscore_shutdown();
	pr_emerg("Power down\n");
	kmsg_dump(KMSG_DUMP_POWEROFF);
	machine_power_off();
}
EXPORT_SYMBOL_GPL(kernel_power_off);

static DEFINE_MUTEX(reboot_mutex);

/*
 * Reboot system call: for obvious reasons only root may call it,
 * and even root needs to set up some magic numbers in the registers
 * so that some mistake won't make this reboot the whole machine.
 * You can also set the meaning of the ctrl-alt-del-key here.
 *
 * reboot doesn't sync: do that yourself before calling this.
 */
SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
		void __user *, arg)
{
	struct pid_namespace *pid_ns = task_active_pid_ns(current);
	char buffer[256];
	int ret = 0;

	/* We only trust the superuser with rebooting the system. */
	if (!ns_capable(pid_ns->user_ns, CAP_SYS_BOOT))
		return -EPERM;

	/* For safety, we require "magic" arguments. */
	if (magic1 != LINUX_REBOOT_MAGIC1 ||
			(magic2 != LINUX_REBOOT_MAGIC2 &&
			magic2 != LINUX_REBOOT_MAGIC2A &&
			magic2 != LINUX_REBOOT_MAGIC2B &&
			magic2 != LINUX_REBOOT_MAGIC2C))
		return -EINVAL;

	/*
	 * If pid namespaces are enabled and the current task is in a child
	 * pid_namespace, the command is handled by reboot_pid_ns() which will
	 * call do_exit().
	 */
	ret = reboot_pid_ns(pid_ns, cmd);
	if (ret)
		return ret;

	/* Instead of trying to make the power_off code look like
	 * halt when pm_power_off is not set do it the easy way.
	 */
	if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
		cmd = LINUX_REBOOT_CMD_HALT;

	mutex_lock(&reboot_mutex);
	switch (cmd) {
	case LINUX_REBOOT_CMD_RESTART:
		kernel_restart(NULL);
		break;

	case LINUX_REBOOT_CMD_CAD_ON:
		C_A_D = 1;
		break;

	case LINUX_REBOOT_CMD_CAD_OFF:
		C_A_D = 0;
		break;

	case LINUX_REBOOT_CMD_HALT:
		kernel_halt();
		do_exit(0);
		panic("cannot halt");

	case LINUX_REBOOT_CMD_POWER_OFF:
		kernel_power_off();
		do_exit(0);
		break;

	case LINUX_REBOOT_CMD_RESTART2:
		ret = strncpy_from_user(&buffer[0], arg, sizeof(buffer) - 1);
		if (ret < 0) {
			ret = -EFAULT;
			break;
		}
		buffer[sizeof(buffer) - 1] = '\0';

		kernel_restart(buffer);
		break;

#ifdef CONFIG_KEXEC_CORE
	case LINUX_REBOOT_CMD_KEXEC:
		ret = kernel_kexec();
		break;
#endif

#ifdef CONFIG_HIBERNATION
	case LINUX_REBOOT_CMD_SW_SUSPEND:
		ret = hibernate();
		break;
#endif

	default:
		ret = -EINVAL;
		break;
	}
	mutex_unlock(&reboot_mutex);
	return ret;
}

static void deferred_cad(struct work_struct *dummy)
{
	kernel_restart(NULL);
}

/*
 * This function gets called by ctrl-alt-del - ie the keyboard interrupt.
 * As it's called within an interrupt, it may NOT sync: the only choice
 * is whether to reboot at once, or just ignore the ctrl-alt-del.
 */
void ctrl_alt_del(void)
{
	static DECLARE_WORK(cad_work, deferred_cad);

	if (C_A_D)
		schedule_work(&cad_work);
	else
		kill_cad_pid(SIGINT, 1);
}

char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff";
static const char reboot_cmd[] = "/sbin/reboot";

static int run_cmd(const char *cmd)
{
	char **argv;
	static char *envp[] = {
		"HOME=/",
		"PATH=/sbin:/bin:/usr/sbin:/usr/bin",
		NULL
	};
	int ret;
	argv = argv_split(GFP_KERNEL, cmd, NULL);
	if (argv) {
		ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
		argv_free(argv);
	} else {
		ret = -ENOMEM;
	}

	return ret;
}

static int __orderly_reboot(void)
{
	int ret;

	ret = run_cmd(reboot_cmd);

	if (ret) {
		pr_warn("Failed to start orderly reboot: forcing the issue\n");
		emergency_sync();
		kernel_restart(NULL);
	}

	return ret;
}

static int __orderly_poweroff(bool force)
{
	int ret;

	ret = run_cmd(poweroff_cmd);

	if (ret && force) {
		pr_warn("Failed to start orderly shutdown: forcing the issue\n");

		/*
		 * I guess this should try to kick off some daemon to sync and
		 * poweroff asap.  Or not even bother syncing if we're doing an
		 * emergency shutdown?
		 */
		emergency_sync();
		kernel_power_off();
	}

	return ret;
}

static bool poweroff_force;

static void poweroff_work_func(struct work_struct *work)
{
	__orderly_poweroff(poweroff_force);
}

static DECLARE_WORK(poweroff_work, poweroff_work_func);

/**
 * orderly_poweroff - Trigger an orderly system poweroff
 * @force: force poweroff if command execution fails
 *
 * This may be called from any context to trigger a system shutdown.
 * If the orderly shutdown fails, it will force an immediate shutdown.
 */
void orderly_poweroff(bool force)
{
	if (force) /* do not override the pending "true" */
		poweroff_force = true;
	schedule_work(&poweroff_work);
}
EXPORT_SYMBOL_GPL(orderly_poweroff);

static void reboot_work_func(struct work_struct *work)
{
	__orderly_reboot();
}

static DECLARE_WORK(reboot_work, reboot_work_func);

/**
 * orderly_reboot - Trigger an orderly system reboot
 *
 * This may be called from any context to trigger a system reboot.
 * If the orderly reboot fails, it will force an immediate reboot.
 */
void orderly_reboot(void)
{
	schedule_work(&reboot_work);
}
EXPORT_SYMBOL_GPL(orderly_reboot);

static int __init reboot_setup(char *str)
{
	for (;;) {
		/*
		 * Having anything passed on the command line via
		 * reboot= will cause us to disable DMI checking
		 * below.
		 */
		reboot_default = 0;

		switch (*str) {
		case 'w':
			reboot_mode = REBOOT_WARM;
			break;

		case 'c':
			reboot_mode = REBOOT_COLD;
			break;

		case 'h':
			reboot_mode = REBOOT_HARD;
			break;

		case 's':
		{
			int rc;

			if (isdigit(*(str+1))) {
				rc = kstrtoint(str+1, 0, &reboot_cpu);
				if (rc)
					return rc;
			} else if (str[1] == 'm' && str[2] == 'p' &&
				   isdigit(*(str+3))) {
				rc = kstrtoint(str+3, 0, &reboot_cpu);
				if (rc)
					return rc;
			} else
				reboot_mode = REBOOT_SOFT;
			break;
		}
		case 'g':
			reboot_mode = REBOOT_GPIO;
			break;

		case 'b':
		case 'a':
		case 'k':
		case 't':
		case 'e':
		case 'p':
			reboot_type = *str;
			break;

		case 'f':
			reboot_force = 1;
			break;
		}

		str = strchr(str, ',');
		if (str)
			str++;
		else
			break;
	}
	return 1;
}
__setup("reboot=", reboot_setup);
back to top