Revision 4a6cc4bd32e580722882115d4c8b964d732c11e4 authored by Jiri Kosina on 28 October 2009, 15:26:00 UTC, committed by Tejun Heo on 28 October 2009, 15:26:00 UTC
Commit 34d76c41 introduced percpu array update_shares_data, size of which
being proportional to NR_CPUS. Unfortunately this blows up ia64 for large
NR_CPUS configuration, as ia64 allows only 64k for .percpu section.

Fix this by allocating this array dynamically and keep only pointer to it
percpu.

The per-cpu handling doesn't impose significant performance penalty on
potentially contented path in tg_shares_up().

...
ffffffff8104337c:       65 48 8b 14 25 20 cd    mov    %gs:0xcd20,%rdx
ffffffff81043383:       00 00
ffffffff81043385:       48 c7 c0 00 e1 00 00    mov    $0xe100,%rax
ffffffff8104338c:       48 c7 45 a0 00 00 00    movq   $0x0,-0x60(%rbp)
ffffffff81043393:       00
ffffffff81043394:       48 c7 45 a8 00 00 00    movq   $0x0,-0x58(%rbp)
ffffffff8104339b:       00
ffffffff8104339c:       48 01 d0                add    %rdx,%rax
ffffffff8104339f:       49 8d 94 24 08 01 00    lea    0x108(%r12),%rdx
ffffffff810433a6:       00
ffffffff810433a7:       b9 ff ff ff ff          mov    $0xffffffff,%ecx
ffffffff810433ac:       48 89 45 b0             mov    %rax,-0x50(%rbp)
ffffffff810433b0:       bb 00 04 00 00          mov    $0x400,%ebx
ffffffff810433b5:       48 89 55 c0             mov    %rdx,-0x40(%rbp)
...

After:

...
ffffffff8104337c:       65 8b 04 25 28 cd 00    mov    %gs:0xcd28,%eax
ffffffff81043383:       00
ffffffff81043384:       48 98                   cltq
ffffffff81043386:       49 8d bc 24 08 01 00    lea    0x108(%r12),%rdi
ffffffff8104338d:       00
ffffffff8104338e:       48 8b 15 d3 7f 76 00    mov    0x767fd3(%rip),%rdx        # ffffffff817ab368 <update_shares_data>
ffffffff81043395:       48 8b 34 c5 00 ee 6d    mov    -0x7e921200(,%rax,8),%rsi
ffffffff8104339c:       81
ffffffff8104339d:       48 c7 45 a0 00 00 00    movq   $0x0,-0x60(%rbp)
ffffffff810433a4:       00
ffffffff810433a5:       b9 ff ff ff ff          mov    $0xffffffff,%ecx
ffffffff810433aa:       48 89 7d c0             mov    %rdi,-0x40(%rbp)
ffffffff810433ae:       48 c7 45 a8 00 00 00    movq   $0x0,-0x58(%rbp)
ffffffff810433b5:       00
ffffffff810433b6:       bb 00 04 00 00          mov    $0x400,%ebx
ffffffff810433bb:       48 01 f2                add    %rsi,%rdx
ffffffff810433be:       48 89 55 b0             mov    %rdx,-0x50(%rbp)
...

Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Tejun Heo <tj@kernel.org>
1 parent 403a91b
Raw File
michael_mic.c
/*
 * Cryptographic API
 *
 * Michael MIC (IEEE 802.11i/TKIP) keyed digest
 *
 * Copyright (c) 2004 Jouni Malinen <j@w1.fi>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */
#include <crypto/internal/hash.h>
#include <asm/byteorder.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/string.h>
#include <linux/types.h>


struct michael_mic_ctx {
	u32 l, r;
};

struct michael_mic_desc_ctx {
	u8 pending[4];
	size_t pending_len;

	u32 l, r;
};

static inline u32 xswap(u32 val)
{
	return ((val & 0x00ff00ff) << 8) | ((val & 0xff00ff00) >> 8);
}


#define michael_block(l, r)	\
do {				\
	r ^= rol32(l, 17);	\
	l += r;			\
	r ^= xswap(l);		\
	l += r;			\
	r ^= rol32(l, 3);	\
	l += r;			\
	r ^= ror32(l, 2);	\
	l += r;			\
} while (0)


static int michael_init(struct shash_desc *desc)
{
	struct michael_mic_desc_ctx *mctx = shash_desc_ctx(desc);
	struct michael_mic_ctx *ctx = crypto_shash_ctx(desc->tfm);
	mctx->pending_len = 0;
	mctx->l = ctx->l;
	mctx->r = ctx->r;

	return 0;
}


static int michael_update(struct shash_desc *desc, const u8 *data,
			   unsigned int len)
{
	struct michael_mic_desc_ctx *mctx = shash_desc_ctx(desc);
	const __le32 *src;

	if (mctx->pending_len) {
		int flen = 4 - mctx->pending_len;
		if (flen > len)
			flen = len;
		memcpy(&mctx->pending[mctx->pending_len], data, flen);
		mctx->pending_len += flen;
		data += flen;
		len -= flen;

		if (mctx->pending_len < 4)
			return 0;

		src = (const __le32 *)mctx->pending;
		mctx->l ^= le32_to_cpup(src);
		michael_block(mctx->l, mctx->r);
		mctx->pending_len = 0;
	}

	src = (const __le32 *)data;

	while (len >= 4) {
		mctx->l ^= le32_to_cpup(src++);
		michael_block(mctx->l, mctx->r);
		len -= 4;
	}

	if (len > 0) {
		mctx->pending_len = len;
		memcpy(mctx->pending, src, len);
	}

	return 0;
}


static int michael_final(struct shash_desc *desc, u8 *out)
{
	struct michael_mic_desc_ctx *mctx = shash_desc_ctx(desc);
	u8 *data = mctx->pending;
	__le32 *dst = (__le32 *)out;

	/* Last block and padding (0x5a, 4..7 x 0) */
	switch (mctx->pending_len) {
	case 0:
		mctx->l ^= 0x5a;
		break;
	case 1:
		mctx->l ^= data[0] | 0x5a00;
		break;
	case 2:
		mctx->l ^= data[0] | (data[1] << 8) | 0x5a0000;
		break;
	case 3:
		mctx->l ^= data[0] | (data[1] << 8) | (data[2] << 16) |
			0x5a000000;
		break;
	}
	michael_block(mctx->l, mctx->r);
	/* l ^= 0; */
	michael_block(mctx->l, mctx->r);

	dst[0] = cpu_to_le32(mctx->l);
	dst[1] = cpu_to_le32(mctx->r);

	return 0;
}


static int michael_setkey(struct crypto_shash *tfm, const u8 *key,
			  unsigned int keylen)
{
	struct michael_mic_ctx *mctx = crypto_shash_ctx(tfm);

	const __le32 *data = (const __le32 *)key;

	if (keylen != 8) {
		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
		return -EINVAL;
	}

	mctx->l = le32_to_cpu(data[0]);
	mctx->r = le32_to_cpu(data[1]);
	return 0;
}

static struct shash_alg alg = {
	.digestsize		=	8,
	.setkey			=	michael_setkey,
	.init			=	michael_init,
	.update			=	michael_update,
	.final			=	michael_final,
	.descsize		=	sizeof(struct michael_mic_desc_ctx),
	.base			=	{
		.cra_name		=	"michael_mic",
		.cra_blocksize		=	8,
		.cra_alignmask		=	3,
		.cra_ctxsize		=	sizeof(struct michael_mic_ctx),
		.cra_module		=	THIS_MODULE,
	}
};

static int __init michael_mic_init(void)
{
	return crypto_register_shash(&alg);
}


static void __exit michael_mic_exit(void)
{
	crypto_unregister_shash(&alg);
}


module_init(michael_mic_init);
module_exit(michael_mic_exit);

MODULE_LICENSE("GPL v2");
MODULE_DESCRIPTION("Michael MIC");
MODULE_AUTHOR("Jouni Malinen <j@w1.fi>");
back to top