https://github.com/torvalds/linux
Revision 4fca50d440cc5d4dc570ad5484cc0b70b381bc2a authored by Jan Kara on 08 September 2022, 09:21:24 UTC, committed by Theodore Ts'o on 22 September 2022, 02:11:34 UTC
One of the side-effects of mb_optimize_scan was that the optimized
functions to select next group to try were called even before we tried
the goal group. As a result we no longer allocate files close to
corresponding inodes as well as we don't try to expand currently
allocated extent in the same group. This results in reaim regression
with workfile.disk workload of upto 8% with many clients on my test
machine:

                     baseline               mb_optimize_scan
Hmean     disk-1       2114.16 (   0.00%)     2099.37 (  -0.70%)
Hmean     disk-41     87794.43 (   0.00%)    83787.47 *  -4.56%*
Hmean     disk-81    148170.73 (   0.00%)   135527.05 *  -8.53%*
Hmean     disk-121   177506.11 (   0.00%)   166284.93 *  -6.32%*
Hmean     disk-161   220951.51 (   0.00%)   207563.39 *  -6.06%*
Hmean     disk-201   208722.74 (   0.00%)   203235.59 (  -2.63%)
Hmean     disk-241   222051.60 (   0.00%)   217705.51 (  -1.96%)
Hmean     disk-281   252244.17 (   0.00%)   241132.72 *  -4.41%*
Hmean     disk-321   255844.84 (   0.00%)   245412.84 *  -4.08%*

Also this is causing huge regression (time increased by a factor of 5 or
so) when untarring archive with lots of small files on some eMMC storage
cards.

Fix the problem by making sure we try goal group first.

Fixes: 196e402adf2e ("ext4: improve cr 0 / cr 1 group scanning")
CC: stable@kernel.org
Reported-and-tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Tested-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Reviewed-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Link: https://lore.kernel.org/all/20220727105123.ckwrhbilzrxqpt24@quack3/
Link: https://lore.kernel.org/all/0d81a7c2-46b7-6010-62a4-3e6cfc1628d6@i2se.com/
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20220908092136.11770-1-jack@suse.cz
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
1 parent 7e18e42
Raw File
Tip revision: 4fca50d440cc5d4dc570ad5484cc0b70b381bc2a authored by Jan Kara on 08 September 2022, 09:21:24 UTC
ext4: make mballoc try target group first even with mb_optimize_scan
Tip revision: 4fca50d
cbc.c
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * CBC: Cipher Block Chaining mode
 *
 * Copyright (c) 2006-2016 Herbert Xu <herbert@gondor.apana.org.au>
 */

#include <crypto/algapi.h>
#include <crypto/internal/cipher.h>
#include <crypto/internal/skcipher.h>
#include <linux/err.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/log2.h>
#include <linux/module.h>

static int crypto_cbc_encrypt_segment(struct skcipher_walk *walk,
				      struct crypto_skcipher *skcipher)
{
	unsigned int bsize = crypto_skcipher_blocksize(skcipher);
	void (*fn)(struct crypto_tfm *, u8 *, const u8 *);
	unsigned int nbytes = walk->nbytes;
	u8 *src = walk->src.virt.addr;
	u8 *dst = walk->dst.virt.addr;
	struct crypto_cipher *cipher;
	struct crypto_tfm *tfm;
	u8 *iv = walk->iv;

	cipher = skcipher_cipher_simple(skcipher);
	tfm = crypto_cipher_tfm(cipher);
	fn = crypto_cipher_alg(cipher)->cia_encrypt;

	do {
		crypto_xor(iv, src, bsize);
		fn(tfm, dst, iv);
		memcpy(iv, dst, bsize);

		src += bsize;
		dst += bsize;
	} while ((nbytes -= bsize) >= bsize);

	return nbytes;
}

static int crypto_cbc_encrypt_inplace(struct skcipher_walk *walk,
				      struct crypto_skcipher *skcipher)
{
	unsigned int bsize = crypto_skcipher_blocksize(skcipher);
	void (*fn)(struct crypto_tfm *, u8 *, const u8 *);
	unsigned int nbytes = walk->nbytes;
	u8 *src = walk->src.virt.addr;
	struct crypto_cipher *cipher;
	struct crypto_tfm *tfm;
	u8 *iv = walk->iv;

	cipher = skcipher_cipher_simple(skcipher);
	tfm = crypto_cipher_tfm(cipher);
	fn = crypto_cipher_alg(cipher)->cia_encrypt;

	do {
		crypto_xor(src, iv, bsize);
		fn(tfm, src, src);
		iv = src;

		src += bsize;
	} while ((nbytes -= bsize) >= bsize);

	memcpy(walk->iv, iv, bsize);

	return nbytes;
}

static int crypto_cbc_encrypt(struct skcipher_request *req)
{
	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
	struct skcipher_walk walk;
	int err;

	err = skcipher_walk_virt(&walk, req, false);

	while (walk.nbytes) {
		if (walk.src.virt.addr == walk.dst.virt.addr)
			err = crypto_cbc_encrypt_inplace(&walk, skcipher);
		else
			err = crypto_cbc_encrypt_segment(&walk, skcipher);
		err = skcipher_walk_done(&walk, err);
	}

	return err;
}

static int crypto_cbc_decrypt_segment(struct skcipher_walk *walk,
				      struct crypto_skcipher *skcipher)
{
	unsigned int bsize = crypto_skcipher_blocksize(skcipher);
	void (*fn)(struct crypto_tfm *, u8 *, const u8 *);
	unsigned int nbytes = walk->nbytes;
	u8 *src = walk->src.virt.addr;
	u8 *dst = walk->dst.virt.addr;
	struct crypto_cipher *cipher;
	struct crypto_tfm *tfm;
	u8 *iv = walk->iv;

	cipher = skcipher_cipher_simple(skcipher);
	tfm = crypto_cipher_tfm(cipher);
	fn = crypto_cipher_alg(cipher)->cia_decrypt;

	do {
		fn(tfm, dst, src);
		crypto_xor(dst, iv, bsize);
		iv = src;

		src += bsize;
		dst += bsize;
	} while ((nbytes -= bsize) >= bsize);

	memcpy(walk->iv, iv, bsize);

	return nbytes;
}

static int crypto_cbc_decrypt_inplace(struct skcipher_walk *walk,
				      struct crypto_skcipher *skcipher)
{
	unsigned int bsize = crypto_skcipher_blocksize(skcipher);
	void (*fn)(struct crypto_tfm *, u8 *, const u8 *);
	unsigned int nbytes = walk->nbytes;
	u8 *src = walk->src.virt.addr;
	u8 last_iv[MAX_CIPHER_BLOCKSIZE];
	struct crypto_cipher *cipher;
	struct crypto_tfm *tfm;

	cipher = skcipher_cipher_simple(skcipher);
	tfm = crypto_cipher_tfm(cipher);
	fn = crypto_cipher_alg(cipher)->cia_decrypt;

	/* Start of the last block. */
	src += nbytes - (nbytes & (bsize - 1)) - bsize;
	memcpy(last_iv, src, bsize);

	for (;;) {
		fn(tfm, src, src);
		if ((nbytes -= bsize) < bsize)
			break;
		crypto_xor(src, src - bsize, bsize);
		src -= bsize;
	}

	crypto_xor(src, walk->iv, bsize);
	memcpy(walk->iv, last_iv, bsize);

	return nbytes;
}

static int crypto_cbc_decrypt(struct skcipher_request *req)
{
	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
	struct skcipher_walk walk;
	int err;

	err = skcipher_walk_virt(&walk, req, false);

	while (walk.nbytes) {
		if (walk.src.virt.addr == walk.dst.virt.addr)
			err = crypto_cbc_decrypt_inplace(&walk, skcipher);
		else
			err = crypto_cbc_decrypt_segment(&walk, skcipher);
		err = skcipher_walk_done(&walk, err);
	}

	return err;
}

static int crypto_cbc_create(struct crypto_template *tmpl, struct rtattr **tb)
{
	struct skcipher_instance *inst;
	struct crypto_alg *alg;
	int err;

	inst = skcipher_alloc_instance_simple(tmpl, tb);
	if (IS_ERR(inst))
		return PTR_ERR(inst);

	alg = skcipher_ialg_simple(inst);

	err = -EINVAL;
	if (!is_power_of_2(alg->cra_blocksize))
		goto out_free_inst;

	inst->alg.encrypt = crypto_cbc_encrypt;
	inst->alg.decrypt = crypto_cbc_decrypt;

	err = skcipher_register_instance(tmpl, inst);
	if (err) {
out_free_inst:
		inst->free(inst);
	}

	return err;
}

static struct crypto_template crypto_cbc_tmpl = {
	.name = "cbc",
	.create = crypto_cbc_create,
	.module = THIS_MODULE,
};

static int __init crypto_cbc_module_init(void)
{
	return crypto_register_template(&crypto_cbc_tmpl);
}

static void __exit crypto_cbc_module_exit(void)
{
	crypto_unregister_template(&crypto_cbc_tmpl);
}

subsys_initcall(crypto_cbc_module_init);
module_exit(crypto_cbc_module_exit);

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("CBC block cipher mode of operation");
MODULE_ALIAS_CRYPTO("cbc");
back to top