Skip to main content

Browse the archive

Revision 7b6efc2bc4f19952b25ebf9b236e5ac43cd386c2 authored by Andrea Arcangeli on 01 November 2011, 00:08:26 UTC, committed by Linus Torvalds on 01 November 2011, 00:30:48 UTC 
mremap: avoid sending one IPI per page
 
This replaces ptep_clear_flush() with ptep_get_and_clear() and a single
flush_tlb_range() at the end of the loop, to avoid sending one IPI for
each page.

The mmu_notifier_invalidate_range_start/end section is enlarged
accordingly but this is not going to fundamentally change things.  It was
more by accident that the region under mremap was for the most part still
available for secondary MMUs: the primary MMU was never allowed to
reliably access that region for the duration of the mremap (modulo
trapping SIGSEGV on the old address range which sounds unpractical and
flakey).  If users wants secondary MMUs not to lose access to a large
region under mremap they should reduce the mremap size accordingly in
userland and run multiple calls.  Overall this will run faster so it's
actually going to reduce the time the region is under mremap for the
primary MMU which should provide a net benefit to apps.

For KVM this is a noop because the guest physical memory is never
mremapped, there's just no point it ever moving it while guest runs.  One
target of this optimization is JVM GC (so unrelated to the mmu notifier
logic).

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Johannes Weiner <jweiner@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent ebed484
Raw File
sort.c 
/*
 * A fast, small, non-recursive O(nlog n) sort for the Linux kernel
 *
 * Jan 23 2005  Matt Mackall <mpm@selenic.com>
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sort.h>
#include <linux/slab.h>

static void u32_swap(void *a, void *b, int size)
{
	u32 t = *(u32 *)a;
	*(u32 *)a = *(u32 *)b;
	*(u32 *)b = t;
}

static void generic_swap(void *a, void *b, int size)
{
	char t;

	do {
		t = *(char *)a;
		*(char *)a++ = *(char *)b;
		*(char *)b++ = t;
	} while (--size > 0);
}

/**
 * sort - sort an array of elements
 * @base: pointer to data to sort
 * @num: number of elements
 * @size: size of each element
 * @cmp_func: pointer to comparison function
 * @swap_func: pointer to swap function or NULL
 *
 * This function does a heapsort on the given array. You may provide a
 * swap_func function optimized to your element type.
 *
 * Sorting time is O(n log n) both on average and worst-case. While
 * qsort is about 20% faster on average, it suffers from exploitable
 * O(n*n) worst-case behavior and extra memory requirements that make
 * it less suitable for kernel use.
 */

void sort(void *base, size_t num, size_t size,
	  int (*cmp_func)(const void *, const void *),
	  void (*swap_func)(void *, void *, int size))
{
	/* pre-scale counters for performance */
	int i = (num/2 - 1) * size, n = num * size, c, r;

	if (!swap_func)
		swap_func = (size == 4 ? u32_swap : generic_swap);

	/* heapify */
	for ( ; i >= 0; i -= size) {
		for (r = i; r * 2 + size < n; r  = c) {
			c = r * 2 + size;
			if (c < n - size &&
					cmp_func(base + c, base + c + size) < 0)
				c += size;
			if (cmp_func(base + r, base + c) >= 0)
				break;
			swap_func(base + r, base + c, size);
		}
	}

	/* sort */
	for (i = n - size; i > 0; i -= size) {
		swap_func(base, base + i, size);
		for (r = 0; r * 2 + size < i; r = c) {
			c = r * 2 + size;
			if (c < i - size &&
					cmp_func(base + c, base + c + size) < 0)
				c += size;
			if (cmp_func(base + r, base + c) >= 0)
				break;
			swap_func(base + r, base + c, size);
		}
	}
}

EXPORT_SYMBOL(sort);

#if 0
/* a simple boot-time regression test */

int cmpint(const void *a, const void *b)
{
	return *(int *)a - *(int *)b;
}

static int sort_test(void)
{
	int *a, i, r = 1;

	a = kmalloc(1000 * sizeof(int), GFP_KERNEL);
	BUG_ON(!a);

	printk("testing sort()\n");

	for (i = 0; i < 1000; i++) {
		r = (r * 725861) % 6599;
		a[i] = r;
	}

	sort(a, 1000, sizeof(int), cmpint, NULL);

	for (i = 0; i < 999; i++)
		if (a[i] > a[i+1]) {
			printk("sort() failed!\n");
			break;
		}

	kfree(a);

	return 0;
}

module_init(sort_test);
#endif
back to top