Recent change in how get_user() handles pointers:
https://lore.kernel.org/all/20241024013214.129639-1-torvalds@linux-foundation.org/
has a specific case for LAM. It assigns a different bitmask that's
later used to check whether a pointer comes from userland in get_user().
Add test case to LAM that utilizes a ioctl (FIOASYNC) syscall which uses
get_user() in its implementation. Execute the syscall with differently
tagged pointers to verify that valid user pointers are passing through
and invalid kernel/non-canonical pointers are not.
Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/1624d9d1b9502517053a056652d50dc5d26884ac.1737990375.git.maciej.wieczor-retman@intel.com
Until LASS is merged into the kernel:
https://lore.kernel.org/all/20241028160917.1380714-1-alexander.shishkin@linux.intel.com/
LAM is left disabled in the config file. Running the LAM selftest with
disabled LAM only results in unhelpful output.
Use one of LAM syscalls() to determine whether the kernel was compiled
with LAM support (CONFIG_ADDRESS_MASKING) or not. Skip running the tests
in the latter case.
Merge CPUID checking function with the one mentioned above to achieve a
single function that shows LAM's availability from both CPU and the
kernel.
Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/251d0f45f6a768030115e8d04bc85458910cb0dc.1737990375.git.maciej.wieczor-retman@intel.com
In current form cpu_has_la57() reports platform's support for LA57
through reading the output of cpuid. A much more useful information is
whether 5-level paging is actually enabled on the running system.
Check whether 5-level paging is enabled by trying to map a page in the
high linear address space.
Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/8b1ca51b13e6d94b5a42b6930d81b692cbb0bcbb.1737990375.git.maciej.wieczor-retman@intel.com
Previously the e820_table_kexec[] was exported to sysfs since kexec-tools uses
the memmap entries to prepare the e820 table for the new kernel.
The following commit, ~8 years ago, introduced e820_table_firmware[] and changed
the behavior to export the firmware table instead:
12df216c61 ("x86/boot/e820: Introduce the bootloader provided e820_table_firmware[] table")
Originally the kexec_file_load and kexec_load syscalls both used e820_table_kexec[].
Since the sysfs exported entries are from e820_table_firmware[] people
now need to tune both tables for kexec.
Restore the old behavior so the kexec_load and kexec_file_load syscalls work with
only one table update. The e820_table_firmware[] is used by hibernation kernel
code and it works without the sysfs exporting. Also remove the SEV
e820_table_firmware[] updating code.
Also update the code comments here and drop the comments about setup_data
reservation since it is not needed any more after this change was made
a year ago:
fc7f27cda8 ("x86/kexec: Do not update E820 kexec table for setup_data")
[ mingo: Tidy up the changelog and comments. ]
Signed-off-by: Dave Young <dyoung@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Ashish Kalra <ashish.kalra@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Baoquan He <bhe@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Link: https://lore.kernel.org/r/Z5jcb1GKhLvH8kDc@darkstar.users.ipa.redhat.com
Replace bitmap array access with bitmap_write.
Accessing the bitmap array directly is not recommended and now there is
a helper function that can be used.
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David Lechner <dlechner@baylibre.com>
Link: https://patch.msgid.link/20250210-gpio-set-array-helper-v3-10-d6a673674da8@baylibre.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
The return values of some functions are of boolean type. Change the
type of these function to bool and adjust their return values.
No functional change intended.
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250129154920.6773-1-ubizjak@gmail.com
When CONFIG_PCI_P2PDMA=y (which is basically enabled on all
large x86 distros), it maps the PFN's via a ZONE_DEVICE
mapping using devm_memremap_pages(). The mapped virtual
address range corresponds to the pci_resource_start()
of the BAR address and size corresponding to the BAR length.
When KASLR is enabled, the direct map range of the kernel is
reduced to the size of physical memory plus additional padding.
If the BAR address is beyond this limit, PCI peer to peer DMA
mappings fail.
Fix this by not shrinking the size of the direct map when
CONFIG_PCI_P2PDMA=y.
This reduces the total available entropy, but it's better than
the current work around of having to disable KASLR completely.
[ mingo: Clarified the changelog to point out the broad impact ... ]
Signed-off-by: Balbir Singh <balbirs@nvidia.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kees Cook <kees@kernel.org>
Acked-by: Bjorn Helgaas <bhelgaas@google.com> # drivers/pci/Kconfig
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andy Lutomirski <luto@kernel.org>
Link: https://lore.kernel.org/lkml/20250206023201.1481957-1-balbirs@nvidia.com/
Link: https://lore.kernel.org/r/20250206234234.1912585-1-balbirs@nvidia.com
--
arch/x86/mm/kaslr.c | 10 ++++++++--
drivers/pci/Kconfig | 6 ++++++
2 files changed, 14 insertions(+), 2 deletions(-)
Load patches for which the driver carries a SHA256 checksum of the patch
blob.
This can be disabled by adding "microcode.amd_sha_check=off" on the
kernel cmdline. But it is highly NOT recommended.
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
If a B.A.T.M.A.N. IV aggregated OGM was prepared, it was always assumed
that 512 bytes (BATADV_MAX_AGGREGATION_BYTES) can be transmitted. But the
outgoing MTU might be too small for these 512 bytes and the aggregation
size must be adjusted in this case. Otherwise, the aggregates will cause
unnecessary packet loss.
For now, the non-aggregated packet length is not touched.
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
The batadv_forw_packet->num_packets didn't store the number of packets but
the the number of packets - 1. This didn't had any effects on the actual
handling of aggregates but can easily be a source of confusion when reading
the code.
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
The aggregation code duplicates code which already exists in the the bitops
and bitmap helper. By switching to the bitmap helpers, operating on larger
aggregations becomes possible without touching the different portions of
the code which read/modify direct_link_flags.
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
The currently selected size in BATADV_MAX_AGGREGATION_BYTES (512) is chosen
such that the number of possible aggregated packets is lower than 32. This
number must be limited so that the type of
batadv_forw_packet->direct_link_flags has enough bits to represent each
packet (with the size of at least 24 bytes).
This requirement is better implemented in code instead of having it inside
a comment.
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
The way how the virtual interface is called inside the batman-adv source
code is not consistent. The genl headers call it meshif and the rest of the
code calls is (mostly) softif.
The genl definitions cannot be touched because they are part of the UAPI.
But the rest of the batman-adv code can be touched to have a consistent
name again.
The bulk of the renaming was done using
sed -i -e 's/soft\(-\|\_\| \|\)i\([nf]\)/mesh\1i\2/g' \
-e 's/SOFT\(-\|\_\| \|\)I\([NF]\)/MESH\1I\2/g'
and then it was adjusted slightly when proofreading the changes.
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
Since batman-adv is not actually depending on hardware capabilities, it has
no limit on the MTU. Only the lower hard interfaces can limit it. In case
these have an high enough MTU or fragmentation is enabled, a higher MTU
than 1500 can be enabled.
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
Add a device tracker to struct batadv_hard_iface to help
debugging of network device refcount imbalances.
Signed-off-by: Eric Dumazet <edumazet@google.com>
[sven@narfation.org: fix kernel-doc, adopt for softif reference]
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
The support for the batman-adv ring buffer for debug logs was dropped with
the removal of the debugfs filesystem. The structure storing this ring
buffer is therefore no longer needed since commit aff6f5a68b
("batman-adv: Drop deprecated debugfs support")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
This version will contain all the (major or even only minor) changes for
Linux 6.15.
The version number isn't a semantic version number with major and minor
information. It is just encoding the year of the expected publishing as
Linux -rc1 and the number of published versions this year (starting at 0).
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
In allegro_probe(), the v4l2 device is not unregistered in the error
path, which results in a memory leak. Fix it by calling
v4l2_device_unregister() before returning error.
Fixes: d74d4e2359 ("media: allegro: move driver out of staging")
Signed-off-by: Joe Hattori <joe@pf.is.s.u-tokyo.ac.jp>
Reviewed-by: Michael Tretter <m.tretter@pengutronix.de>
Signed-off-by: Sebastian Fricke <sebastian.fricke@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil@xs4all.nl>
Change headres_size to headers_size.
Signed-off-by: Benjamin Gaignard <benjamin.gaignard@collabora.com>
Reviewed-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Signed-off-by: Sebastian Fricke <sebastian.fricke@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil@xs4all.nl>
The HEVC driver needs to set the start_bit field explicitly to avoid
causing corrupted frames when the VP9 decoder is used in parallel. The
reason for this problem is that the VP9 and the HEVC decoder share this
register.
Fixes: cb5dd5a0fa ("media: hantro: Introduce G2/HEVC decoder")
Signed-off-by: Benjamin Gaignard <benjamin.gaignard@collabora.com>
Tested-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Reviewed-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Signed-off-by: Sebastian Fricke <sebastian.fricke@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil@xs4all.nl>
drivers/i2c/i2c-core-base.c: In function ‘i2c_detect.isra’:
drivers/i2c/i2c-core-base.c:2544:1: warning: the frame size of 1312 bytes is larger than 1024 bytes [-Wframe-larger-than=]
2544 | }
| ^
Fix this by allocating the temporary client structure dynamically, as it
is a rather large structure (1216 bytes, depending on kernel config).
This is basically a revert of the to-be-fixed commit with some
checkpatch improvements.
Fixes: 735668f8e5 ("i2c: core: Allocate temp client on the stack in i2c_detect")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Su Hui <suhui@nfschina.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
[wsa: updated commit message, merged tags from similar patch]
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
The card name for ALSA is generated from the model name string and
is limited to 16 characters. Use a shorter name to prevent cutting the
name.
Since nearly all starter kit mainboards for i.MX based SoM by TQ-Systems
use the same codec with the same routing on board it is a good idea to
use the same mode name for the sound card. This allows sharing a default
asound.conf in BSP over all the kits.
Signed-off-by: Markus Niebel <Markus.Niebel@ew.tq-group.com>
Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
The card name for ALSA is generated from the model name string and
is limited to 16 characters. Use a shorter name to prevent cutting the
name.
Since nearly all starter kit mainboards for i.MX based SoM by TQ-Systems
use the same codec with the same routing on board it is a good idea to
use the same mode name for the sound card. This allows sharing a default
asound.conf in BSP over all the kits.
Signed-off-by: Markus Niebel <Markus.Niebel@ew.tq-group.com>
Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
The card name for ALSA is generated from the model name string and
is limited to 16 characters. Use a shorter name to prevent cutting the
name.
Since nearly all starter kit mainboards for i.MX based SoM by TQ-Systems
use the same codec with the same routing on board it is a good idea to
use the same mode name for the sound card. This allows sharing a default
asound.conf in BSP over all the kits.
Signed-off-by: Markus Niebel <Markus.Niebel@ew.tq-group.com>
Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
Add a reqsize field to struct ahash_alg and use it to set the
default reqsize so that algorithms with a static reqsize are
not forced to create an init_tfm function.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This patch adds virtual address support to ahash. Virtual addresses
were previously only supported through shash. The user may choose
to use virtual addresses with ahash by calling ahash_request_set_virt
instead of ahash_request_set_crypt.
The API will take care of translating this to an SG list if necessary,
unless the algorithm declares that it supports chaining. Therefore
in order for an ahash algorithm to support chaining, it must also
support virtual addresses directly.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The .get_power() and .set_power() function pointers in struct
cpci_hp_controller_ops were declared but never implemented by any
driver.
Thus, to improve code readability and reduce resource usage,
remove these pointers and the code that has never been used.
Link: https://lore.kernel.org/r/20250217185638.398925-1-trintaeoitogc@gmail.com
Signed-off-by: Guilherme Giacomo Simoes <trintaeoitogc@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
[kwilczynski: commit log]
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
This patch is a revert of commit 388ac25efc.
As multibuffer ahash is coming back in the form of request chaining,
restore the multibuffer ahash tests using the new interface.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This adds request chaining to the ahash interface. Request chaining
allows multiple requests to be submitted in one shot. An algorithm
can elect to receive chained requests by setting the flag
CRYPTO_ALG_REQ_CHAIN. If this bit is not set, the API will break
up chained requests and submit them one-by-one.
A new err field is added to struct crypto_async_request to record
the return value for each individual request.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Rather than copying a request by hand with memcpy, use the correct
API helpers to setup the new request. This will matter once the
API helpers start setting up chained requests as a simple memcpy
will break chaining.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
As unaligned operations are supported by the underlying algorithm,
ahash_save_req and ahash_restore_req can be greatly simplified to
only preserve the callback and data.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Fix smatch warning for sg_nents_for_len return value in Inside Secure
EIP93 driver.
The return value of sg_nents_for_len was assigned to an u32 and the
error was ignored and converted to a positive integer.
Rework the code to correctly handle the error from sg_nents_for_len to
mute smatch warning.
Fixes: 9739f5f93b ("crypto: eip93 - Add Inside Secure SafeXcel EIP-93 crypto engine support")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The type needs to be zeroed as otherwise the user could use it to
allocate an asynchronous sync skcipher.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The service parsing logic is used to parse the configuration string
provided by the user using the attribute qat/cfg_services in sysfs.
The logic relies on hard-coded strings. For example, the service
"sym;asym" is also replicated as "asym;sym".
This makes the addition of new services or service combinations
complex as it requires the addition of new hard-coded strings for all
possible combinations.
This commit addresses this issue by:
* reducing the number of internal service strings to only the basic
service representations.
* modifying the service parsing logic to analyze the service string
token by token instead of comparing a whole string with patterns.
* introducing the concept of a service mask where each service is
represented by a single bit.
* dividing the parsing logic into several functions to allow for code
reuse (e.g. by sysfs-related functions).
* introducing a new, device generation-specific function to verify
whether the requested service combination is supported by the
currently used device.
Signed-off-by: Małgorzata Mielnik <malgorzata.mielnik@intel.com>
Co-developed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The symbol `adf_cfg_services` is only used on the intel_qat module.
There is no need to export it.
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Set the request tfm directly in SYNC_SKCIPHER_REQUEST_ON_STACK since
the tfm is already available.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
When the lookup is retried after instance construction, it uses
the type and mask from the larval, which may not match the values
used by the caller. For example, if the caller is requesting for
a !NEEDS_FALLBACK algorithm, it may end up getting an algorithm
that needs fallbacks.
Fix this by making the caller supply the type/mask and using that
for the lookup.
Reported-by: Coiby Xu <coxu@redhat.com>
Fixes: 96ad595520 ("crypto: api - Remove instance larval fulfilment")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Document the crypto engine on the X1E80100 Platform.
Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
As the null algorithm may be freed in softirq context through
af_alg, use spin locks instead of mutexes to protect the default
null algorithm.
Reported-by: syzbot+b3e02953598f447d4d2a@syzkaller.appspotmail.com
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The HAVE_ARCH Kconfig options in lib/crypto try to solve the
modular versus built-in problem, but it still fails when the
the LIB option (e.g., CRYPTO_LIB_CURVE25519) is selected externally.
Fix this by introducing a level of indirection with ARCH_MAY_HAVE
Kconfig options, these then go on to select the ARCH_HAVE options
if the ARCH Kconfig options matches that of the LIB option.
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202501230223.ikroNDr1-lkp@intel.com/
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The objects in the qat_common Makefile are currently listed in a random
order.
Reorder the objects alphabetically to make it easier to find where to
add a new object.
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Ahsan Atta <ahsan.atta@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Align with kbuild documentation by using <module_name>-y instead of
<module_name>-objs, following the kernel convention for building modules
from multiple object files.
Link: https://docs.kernel.org/kbuild/makefiles.html#loadable-module-goals-obj-m
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Suggested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Remove hard-coded strings by using the str_yes_no() helper function.
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Use kmalloc_array() instead of kcalloc() because sg_init_table() already
sets the memory to zero. This avoids zeroing the memory twice.
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
As with the other AES modes I've implemented, I've received interest in
my AES-XTS assembly code being reused in other projects. Therefore,
change the license to Apache-2.0 OR BSD-2-Clause like what I used for
AES-GCM. Apache-2.0 is the license of OpenSSL and BoringSSL.
Note that it is difficult to *directly* share code between the kernel,
OpenSSL, and BoringSSL for various reasons such as perlasm vs. plain
asm, Windows ABI support, different divisions of responsibility between
C and asm in each project, etc. So whether that will happen instead of
just doing ports is still TBD. But this dual license should at least
make it possible to port changes between the projects.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Delete aes_ctrby8_avx-x86_64.S and add a new assembly file
aes-ctr-avx-x86_64.S which follows a similar approach to
aes-xts-avx-x86_64.S in that it uses a "template" to provide AESNI+AVX,
VAES+AVX2, VAES+AVX10/256, and VAES+AVX10/512 code, instead of just
AESNI+AVX. Wire it up to the crypto API accordingly.
This greatly improves the performance of AES-CTR and AES-XCTR on
VAES-capable CPUs, with the best case being AMD Zen 5 where an over 230%
increase in throughput is seen on long messages. Performance on
non-VAES-capable CPUs remains about the same, and the non-AVX AES-CTR
code (aesni_ctr_enc) is also kept as-is for now. There are some slight
regressions (less than 10%) on some short message lengths on some CPUs;
these are difficult to avoid, given how the previous code was so heavily
unrolled by message length, and they are not particularly important.
Detailed performance results are given in the tables below.
Both CTR and XCTR support is retained. The main loop remains
8-vector-wide, which differs from the 4-vector-wide main loops that are
used in the XTS and GCM code. A wider loop is appropriate for CTR and
XCTR since they have fewer other instructions (such as vpclmulqdq) to
interleave with the AES instructions.
Similar to what was the case for AES-GCM, the new assembly code also has
a much smaller binary size, as it fixes the excessive unrolling by data
length and key length present in the old code. Specifically, the new
assembly file compiles to about 9 KB of text vs. 28 KB for the old file.
This is despite 4x as many implementations being included.
The tables below show the detailed performance results. The tables show
percentage improvement in single-threaded throughput for repeated
encryption of the given message length; an increase from 6000 MB/s to
12000 MB/s would be listed as 100%. They were collected by directly
measuring the Linux crypto API performance using a custom kernel module.
The tested CPUs were all server processors from Google Compute Engine
except for Zen 5 which was a Ryzen 9 9950X desktop processor.
Table 1: AES-256-CTR throughput improvement,
CPU microarchitecture vs. message length in bytes:
| 16384 | 4096 | 4095 | 1420 | 512 | 500 |
---------------------+-------+-------+-------+-------+-------+-------+
AMD Zen 5 | 232% | 203% | 212% | 143% | 71% | 95% |
Intel Emerald Rapids | 116% | 116% | 117% | 91% | 78% | 79% |
Intel Ice Lake | 109% | 103% | 107% | 81% | 54% | 56% |
AMD Zen 4 | 109% | 91% | 100% | 70% | 43% | 59% |
AMD Zen 3 | 92% | 78% | 87% | 57% | 32% | 43% |
AMD Zen 2 | 9% | 8% | 14% | 12% | 8% | 21% |
Intel Skylake | 7% | 7% | 8% | 5% | 3% | 8% |
| 300 | 200 | 64 | 63 | 16 |
---------------------+-------+-------+-------+-------+-------+
AMD Zen 5 | 57% | 39% | -9% | 7% | -7% |
Intel Emerald Rapids | 37% | 42% | -0% | 13% | -8% |
Intel Ice Lake | 39% | 30% | -1% | 14% | -9% |
AMD Zen 4 | 42% | 38% | -0% | 18% | -3% |
AMD Zen 3 | 38% | 35% | 6% | 31% | 5% |
AMD Zen 2 | 24% | 23% | 5% | 30% | 3% |
Intel Skylake | 9% | 1% | -4% | 10% | -7% |
Table 2: AES-256-XCTR throughput improvement,
CPU microarchitecture vs. message length in bytes:
| 16384 | 4096 | 4095 | 1420 | 512 | 500 |
---------------------+-------+-------+-------+-------+-------+-------+
AMD Zen 5 | 240% | 201% | 216% | 151% | 75% | 108% |
Intel Emerald Rapids | 100% | 99% | 102% | 91% | 94% | 104% |
Intel Ice Lake | 93% | 89% | 92% | 74% | 50% | 64% |
AMD Zen 4 | 86% | 75% | 83% | 60% | 41% | 52% |
AMD Zen 3 | 73% | 63% | 69% | 45% | 21% | 33% |
AMD Zen 2 | -2% | -2% | 2% | 3% | -1% | 11% |
Intel Skylake | -1% | -1% | 1% | 2% | -1% | 9% |
| 300 | 200 | 64 | 63 | 16 |
---------------------+-------+-------+-------+-------+-------+
AMD Zen 5 | 78% | 56% | -4% | 38% | -2% |
Intel Emerald Rapids | 61% | 55% | 4% | 32% | -5% |
Intel Ice Lake | 57% | 42% | 3% | 44% | -4% |
AMD Zen 4 | 35% | 28% | -1% | 17% | -3% |
AMD Zen 3 | 26% | 23% | -3% | 11% | -6% |
AMD Zen 2 | 13% | 24% | -1% | 14% | -3% |
Intel Skylake | 16% | 8% | -4% | 35% | -3% |
Signed-off-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Tested-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Remove hard-coded strings by using the str_yes_no() helper function.
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Instead of having two entries for inside-secure in the top-level
Makefile, make it just a single one.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
PCI device 0x1134 shares same register features as PCI device 0x17E0.
Hence reuse same data for the new PCI device ID 0x1134.
Signed-off-by: Devaraj Rangasamy <Devaraj.Rangasamy@amd.com>
Acked-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
