mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-12-28 20:09:35 +03:00
e5db313494
Restore the SIMD optimization for 4.19.38 LTS, 4.14.120 LTS,
and 5.0 and newer kernels. This is accomplished by leveraging
the fact that by definition dedicated kernel threads never need
to concern themselves with saving and restoring the user FPU state.
Therefore, they may use the FPU as long as we can guarantee user
tasks always restore their FPU state before context switching back
to user space.
For the 5.0 and 5.1 kernels disabling preemption and local
interrupts is sufficient to allow the FPU to be used. All non-kernel
threads will restore the preserved user FPU state.
For 5.2 and latter kernels the user FPU state restoration will be
skipped if the kernel determines the registers have not changed.
Therefore, for these kernels we need to perform the additional
step of saving and restoring the FPU registers. Invalidating the
per-cpu global tracking the FPU state would force a restore but
that functionality is private to the core x86 FPU implementation
and unavailable.
In practice, restricting SIMD to kernel threads is not a major
restriction for ZFS. The vast majority of SIMD operations are
already performed by the IO pipeline. The remaining cases are
relatively infrequent and can be handled by the generic code
without significant impact. The two most noteworthy cases are:
1) Decrypting the wrapping key for an encrypted dataset,
i.e. `zfs load-key`. All other encryption and decryption
operations will use the SIMD optimized implementations.
2) Generating the payload checksums for a `zfs send` stream.
In order to avoid making any changes to the higher layers of ZFS
all of the `*_get_ops()` functions were updated to take in to
consideration the calling context. This allows for the fastest
implementation to be used as appropriate (see kfpu_allowed()).
The only other notable instance of SIMD operations being used
outside a kernel thread was at module load time. This code
was moved in to a taskq in order to accommodate the new kernel
thread restriction.
Finally, a few other modifications were made in order to further
harden this code and facilitate testing. They include updating
each implementations operations structure to be declared as a
constant. And allowing "cycle" to be set when selecting the
preferred ops in the kernel as well as user space.
Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #8754
Closes #8793
Closes #8965
124 lines
3.7 KiB
C
124 lines
3.7 KiB
C
/*
|
|
* CDDL HEADER START
|
|
*
|
|
* The contents of this file are subject to the terms of the
|
|
* Common Development and Distribution License (the "License").
|
|
* You may not use this file except in compliance with the License.
|
|
*
|
|
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
|
|
* or http://www.opensolaris.org/os/licensing.
|
|
* See the License for the specific language governing permissions
|
|
* and limitations under the License.
|
|
*
|
|
* When distributing Covered Code, include this CDDL HEADER in each
|
|
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
|
|
* If applicable, add the following below this CDDL HEADER, with the
|
|
* fields enclosed by brackets "[]" replaced with your own identifying
|
|
* information: Portions Copyright [yyyy] [name of copyright owner]
|
|
*
|
|
* CDDL HEADER END
|
|
*/
|
|
/*
|
|
* Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved.
|
|
*/
|
|
|
|
#if defined(__x86_64) && defined(HAVE_AES)
|
|
|
|
#include <linux/simd_x86.h>
|
|
|
|
/* These functions are used to execute AES-NI instructions: */
|
|
extern int rijndael_key_setup_enc_intel(uint32_t rk[],
|
|
const uint32_t cipherKey[], uint64_t keyBits);
|
|
extern int rijndael_key_setup_dec_intel(uint32_t rk[],
|
|
const uint32_t cipherKey[], uint64_t keyBits);
|
|
extern void aes_encrypt_intel(const uint32_t rk[], int Nr,
|
|
const uint32_t pt[4], uint32_t ct[4]);
|
|
extern void aes_decrypt_intel(const uint32_t rk[], int Nr,
|
|
const uint32_t ct[4], uint32_t pt[4]);
|
|
|
|
|
|
#include <aes/aes_impl.h>
|
|
|
|
/*
|
|
* Expand the 32-bit AES cipher key array into the encryption and decryption
|
|
* key schedules.
|
|
*
|
|
* Parameters:
|
|
* key AES key schedule to be initialized
|
|
* keyarr32 User key
|
|
* keyBits AES key size (128, 192, or 256 bits)
|
|
*/
|
|
static void
|
|
aes_aesni_generate(aes_key_t *key, const uint32_t *keyarr32, int keybits)
|
|
{
|
|
kfpu_begin();
|
|
key->nr = rijndael_key_setup_enc_intel(&(key->encr_ks.ks32[0]),
|
|
keyarr32, keybits);
|
|
key->nr = rijndael_key_setup_dec_intel(&(key->decr_ks.ks32[0]),
|
|
keyarr32, keybits);
|
|
kfpu_end();
|
|
}
|
|
|
|
/*
|
|
* Encrypt one block of data. The block is assumed to be an array
|
|
* of four uint32_t values, so copy for alignment (and byte-order
|
|
* reversal for little endian systems might be necessary on the
|
|
* input and output byte streams.
|
|
* The size of the key schedule depends on the number of rounds
|
|
* (which can be computed from the size of the key), i.e. 4*(Nr + 1).
|
|
*
|
|
* Parameters:
|
|
* rk Key schedule, of aes_ks_t (60 32-bit integers)
|
|
* Nr Number of rounds
|
|
* pt Input block (plain text)
|
|
* ct Output block (crypto text). Can overlap with pt
|
|
*/
|
|
static void
|
|
aes_aesni_encrypt(const uint32_t rk[], int Nr, const uint32_t pt[4],
|
|
uint32_t ct[4])
|
|
{
|
|
kfpu_begin();
|
|
aes_encrypt_intel(rk, Nr, pt, ct);
|
|
kfpu_end();
|
|
}
|
|
|
|
/*
|
|
* Decrypt one block of data. The block is assumed to be an array
|
|
* of four uint32_t values, so copy for alignment (and byte-order
|
|
* reversal for little endian systems might be necessary on the
|
|
* input and output byte streams.
|
|
* The size of the key schedule depends on the number of rounds
|
|
* (which can be computed from the size of the key), i.e. 4*(Nr + 1).
|
|
*
|
|
* Parameters:
|
|
* rk Key schedule, of aes_ks_t (60 32-bit integers)
|
|
* Nr Number of rounds
|
|
* ct Input block (crypto text)
|
|
* pt Output block (plain text). Can overlap with pt
|
|
*/
|
|
static void
|
|
aes_aesni_decrypt(const uint32_t rk[], int Nr, const uint32_t ct[4],
|
|
uint32_t pt[4])
|
|
{
|
|
kfpu_begin();
|
|
aes_decrypt_intel(rk, Nr, ct, pt);
|
|
kfpu_end();
|
|
}
|
|
|
|
static boolean_t
|
|
aes_aesni_will_work(void)
|
|
{
|
|
return (kfpu_allowed() && zfs_aes_available());
|
|
}
|
|
|
|
const aes_impl_ops_t aes_aesni_impl = {
|
|
.generate = &aes_aesni_generate,
|
|
.encrypt = &aes_aesni_encrypt,
|
|
.decrypt = &aes_aesni_decrypt,
|
|
.is_supported = &aes_aesni_will_work,
|
|
.needs_byteswap = B_FALSE,
|
|
.name = "aesni"
|
|
};
|
|
|
|
#endif /* defined(__x86_64) && defined(HAVE_AES) */
|