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
gen_crc32table.c 
#include <stdio.h>
#include "crc32defs.h"
#include <inttypes.h>

#define ENTRIES_PER_LINE 4

#define LE_TABLE_SIZE (1 << CRC_LE_BITS)
#define BE_TABLE_SIZE (1 << CRC_BE_BITS)

static uint32_t crc32table_le[4][LE_TABLE_SIZE];
static uint32_t crc32table_be[4][BE_TABLE_SIZE];

/**
 * crc32init_le() - allocate and initialize LE table data
 *
 * crc is the crc of the byte i; other entries are filled in based on the
 * fact that crctable[i^j] = crctable[i] ^ crctable[j].
 *
 */
static void crc32init_le(void)
{
	unsigned i, j;
	uint32_t crc = 1;

	crc32table_le[0][0] = 0;

	for (i = 1 << (CRC_LE_BITS - 1); i; i >>= 1) {
		crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0);
		for (j = 0; j < LE_TABLE_SIZE; j += 2 * i)
			crc32table_le[0][i + j] = crc ^ crc32table_le[0][j];
	}
	for (i = 0; i < LE_TABLE_SIZE; i++) {
		crc = crc32table_le[0][i];
		for (j = 1; j < 4; j++) {
			crc = crc32table_le[0][crc & 0xff] ^ (crc >> 8);
			crc32table_le[j][i] = crc;
		}
	}
}

/**
 * crc32init_be() - allocate and initialize BE table data
 */
static void crc32init_be(void)
{
	unsigned i, j;
	uint32_t crc = 0x80000000;

	crc32table_be[0][0] = 0;

	for (i = 1; i < BE_TABLE_SIZE; i <<= 1) {
		crc = (crc << 1) ^ ((crc & 0x80000000) ? CRCPOLY_BE : 0);
		for (j = 0; j < i; j++)
			crc32table_be[0][i + j] = crc ^ crc32table_be[0][j];
	}
	for (i = 0; i < BE_TABLE_SIZE; i++) {
		crc = crc32table_be[0][i];
		for (j = 1; j < 4; j++) {
			crc = crc32table_be[0][(crc >> 24) & 0xff] ^ (crc << 8);
			crc32table_be[j][i] = crc;
		}
	}
}

static void output_table(uint32_t table[4][256], int len, char *trans)
{
	int i, j;

	for (j = 0 ; j < 4; j++) {
		printf("{");
		for (i = 0; i < len - 1; i++) {
			if (i % ENTRIES_PER_LINE == 0)
				printf("\n");
			printf("%s(0x%8.8xL), ", trans, table[j][i]);
		}
		printf("%s(0x%8.8xL)},\n", trans, table[j][len - 1]);
	}
}

int main(int argc, char** argv)
{
	printf("/* this file is generated - do not edit */\n\n");

	if (CRC_LE_BITS > 1) {
		crc32init_le();
		printf("static const u32 crc32table_le[4][256] = {");
		output_table(crc32table_le, LE_TABLE_SIZE, "tole");
		printf("};\n");
	}

	if (CRC_BE_BITS > 1) {
		crc32init_be();
		printf("static const u32 crc32table_be[4][256] = {");
		output_table(crc32table_be, BE_TABLE_SIZE, "tobe");
		printf("};\n");
	}

	return 0;
}
back to top