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
ksysfs.c
/*
 * kernel/ksysfs.c - sysfs attributes in /sys/kernel, which
 * 		     are not related to any other subsystem
 *
 * Copyright (C) 2004 Kay Sievers <kay.sievers@vrfy.org>
 * 
 * This file is release under the GPLv2
 *
 */

#include <linux/kobject.h>
#include <linux/string.h>
#include <linux/sysfs.h>
#include <linux/export.h>
#include <linux/init.h>
#include <linux/kexec.h>
#include <linux/profile.h>
#include <linux/stat.h>
#include <linux/sched.h>
#include <linux/capability.h>
#include <linux/compiler.h>

#include <linux/rcupdate.h>	/* rcu_expedited and rcu_normal */

#define KERNEL_ATTR_RO(_name) \
static struct kobj_attribute _name##_attr = __ATTR_RO(_name)

#define KERNEL_ATTR_RW(_name) \
static struct kobj_attribute _name##_attr = \
	__ATTR(_name, 0644, _name##_show, _name##_store)

/* current uevent sequence number */
static ssize_t uevent_seqnum_show(struct kobject *kobj,
				  struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%llu\n", (unsigned long long)uevent_seqnum);
}
KERNEL_ATTR_RO(uevent_seqnum);

#ifdef CONFIG_UEVENT_HELPER
/* uevent helper program, used during early boot */
static ssize_t uevent_helper_show(struct kobject *kobj,
				  struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%s\n", uevent_helper);
}
static ssize_t uevent_helper_store(struct kobject *kobj,
				   struct kobj_attribute *attr,
				   const char *buf, size_t count)
{
	if (count+1 > UEVENT_HELPER_PATH_LEN)
		return -ENOENT;
	memcpy(uevent_helper, buf, count);
	uevent_helper[count] = '\0';
	if (count && uevent_helper[count-1] == '\n')
		uevent_helper[count-1] = '\0';
	return count;
}
KERNEL_ATTR_RW(uevent_helper);
#endif

#ifdef CONFIG_PROFILING
static ssize_t profiling_show(struct kobject *kobj,
				  struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%d\n", prof_on);
}
static ssize_t profiling_store(struct kobject *kobj,
				   struct kobj_attribute *attr,
				   const char *buf, size_t count)
{
	int ret;

	if (prof_on)
		return -EEXIST;
	/*
	 * This eventually calls into get_option() which
	 * has a ton of callers and is not const.  It is
	 * easiest to cast it away here.
	 */
	profile_setup((char *)buf);
	ret = profile_init();
	if (ret)
		return ret;
	ret = create_proc_profile();
	if (ret)
		return ret;
	return count;
}
KERNEL_ATTR_RW(profiling);
#endif

#ifdef CONFIG_KEXEC_CORE
static ssize_t kexec_loaded_show(struct kobject *kobj,
				 struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%d\n", !!kexec_image);
}
KERNEL_ATTR_RO(kexec_loaded);

static ssize_t kexec_crash_loaded_show(struct kobject *kobj,
				       struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%d\n", kexec_crash_loaded());
}
KERNEL_ATTR_RO(kexec_crash_loaded);

static ssize_t kexec_crash_size_show(struct kobject *kobj,
				       struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%zu\n", crash_get_memory_size());
}
static ssize_t kexec_crash_size_store(struct kobject *kobj,
				   struct kobj_attribute *attr,
				   const char *buf, size_t count)
{
	unsigned long cnt;
	int ret;

	if (kstrtoul(buf, 0, &cnt))
		return -EINVAL;

	ret = crash_shrink_memory(cnt);
	return ret < 0 ? ret : count;
}
KERNEL_ATTR_RW(kexec_crash_size);

#endif /* CONFIG_KEXEC_CORE */

#ifdef CONFIG_CRASH_CORE

static ssize_t vmcoreinfo_show(struct kobject *kobj,
			       struct kobj_attribute *attr, char *buf)
{
	phys_addr_t vmcore_base = paddr_vmcoreinfo_note();
	return sprintf(buf, "%pa %x\n", &vmcore_base,
			(unsigned int)VMCOREINFO_NOTE_SIZE);
}
KERNEL_ATTR_RO(vmcoreinfo);

#endif /* CONFIG_CRASH_CORE */

/* whether file capabilities are enabled */
static ssize_t fscaps_show(struct kobject *kobj,
				  struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%d\n", file_caps_enabled);
}
KERNEL_ATTR_RO(fscaps);

#ifndef CONFIG_TINY_RCU
int rcu_expedited;
static ssize_t rcu_expedited_show(struct kobject *kobj,
				  struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%d\n", READ_ONCE(rcu_expedited));
}
static ssize_t rcu_expedited_store(struct kobject *kobj,
				   struct kobj_attribute *attr,
				   const char *buf, size_t count)
{
	if (kstrtoint(buf, 0, &rcu_expedited))
		return -EINVAL;

	return count;
}
KERNEL_ATTR_RW(rcu_expedited);

int rcu_normal;
static ssize_t rcu_normal_show(struct kobject *kobj,
			       struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%d\n", READ_ONCE(rcu_normal));
}
static ssize_t rcu_normal_store(struct kobject *kobj,
				struct kobj_attribute *attr,
				const char *buf, size_t count)
{
	if (kstrtoint(buf, 0, &rcu_normal))
		return -EINVAL;

	return count;
}
KERNEL_ATTR_RW(rcu_normal);
#endif /* #ifndef CONFIG_TINY_RCU */

/*
 * Make /sys/kernel/notes give the raw contents of our kernel .notes section.
 */
extern const void __start_notes __weak;
extern const void __stop_notes __weak;
#define	notes_size (&__stop_notes - &__start_notes)

static ssize_t notes_read(struct file *filp, struct kobject *kobj,
			  struct bin_attribute *bin_attr,
			  char *buf, loff_t off, size_t count)
{
	memcpy(buf, &__start_notes + off, count);
	return count;
}

static struct bin_attribute notes_attr __ro_after_init  = {
	.attr = {
		.name = "notes",
		.mode = S_IRUGO,
	},
	.read = &notes_read,
};

struct kobject *kernel_kobj;
EXPORT_SYMBOL_GPL(kernel_kobj);

static struct attribute * kernel_attrs[] = {
	&fscaps_attr.attr,
	&uevent_seqnum_attr.attr,
#ifdef CONFIG_UEVENT_HELPER
	&uevent_helper_attr.attr,
#endif
#ifdef CONFIG_PROFILING
	&profiling_attr.attr,
#endif
#ifdef CONFIG_KEXEC_CORE
	&kexec_loaded_attr.attr,
	&kexec_crash_loaded_attr.attr,
	&kexec_crash_size_attr.attr,
#endif
#ifdef CONFIG_CRASH_CORE
	&vmcoreinfo_attr.attr,
#endif
#ifndef CONFIG_TINY_RCU
	&rcu_expedited_attr.attr,
	&rcu_normal_attr.attr,
#endif
	NULL
};

static const struct attribute_group kernel_attr_group = {
	.attrs = kernel_attrs,
};

static int __init ksysfs_init(void)
{
	int error;

	kernel_kobj = kobject_create_and_add("kernel", NULL);
	if (!kernel_kobj) {
		error = -ENOMEM;
		goto exit;
	}
	error = sysfs_create_group(kernel_kobj, &kernel_attr_group);
	if (error)
		goto kset_exit;

	if (notes_size > 0) {
		notes_attr.size = notes_size;
		error = sysfs_create_bin_file(kernel_kobj, &notes_attr);
		if (error)
			goto group_exit;
	}

	return 0;

group_exit:
	sysfs_remove_group(kernel_kobj, &kernel_attr_group);
kset_exit:
	kobject_put(kernel_kobj);
exit:
	return error;
}

core_initcall(ksysfs_init);
back to top