Cryptographic Accelerator Unit (CPT) support different engine groups, one
for asymmetric algorithms (only AE engines in this group), one for the
most common symmetric algorithms (all SE and all IE engines in this group),
and one for other symmetric algorithms (only SE engines in this group).
For symmetric engine (SE), we obtain the group number using
"MBOX_MSG_GET_ENG_GRP_NUM" mailbox. Let's follow a similar approach to
determine the group number for asymmetric engine (AE).
Signed-off-by: Amit Singh Tomar <amitsinght@marvell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
By default, otx2_cpt_get_kcrypto_eng_grp_num() returns the engine group
number of SE engine type. Add an engine type parameter to support
retrieving the engine group number for different engine types.
Since otx2_cpt_get_kcrypto_eng_grp_num() always returns the kernel crypto
engine group number, rename it to otx2_cpt_get_eng_grp_num().
Signed-off-by: Amit Singh Tomar <amitsinght@marvell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Current driver uses static LMTST region allocated by firmware.
Firmware allocated memory for LMTST is available in PF/VF BAR2.
Using this memory have performance impact as this is mapped as
device memory. There is another option to allocate contiguous
memory at run time and map this in LMT MAP table with the
help of AF driver. With this patch dynamic allocated memory
is used for LMTST.
Also add myself as maintainer for crypto octeontx2 driver
Signed-off-by: Bharat Bhushan <bbhushan2@marvell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Function otx2_cptlf_set_dev_info() initializes common
fields of cptlfs data-struct. This function is called
every time a cptlf is initialized but this needs be done
once for a cptlf block. So this initialization is moved
to early device probe code to avoid redundant initialization.
Signed-off-by: Bharat Bhushan <bbhushan2@marvell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
pcim_iomap_table() and pcim_iomap_regions_request_all() have been
deprecated by the PCI subsystem in commit e354bb84a4 ("PCI: Deprecate
pcim_iomap_table(), pcim_iomap_regions_request_all()").
Replace these functions with their successors, pcim_iomap() and
pcim_request_all_regions().
Link: https://lore.kernel.org/r/20241030112743.104395-5-pstanner@redhat.com
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Bharat Bhushan <bbhushan2@marvell.com>
Register errors interrupts for inline cptlf attached to PF driver
so that SMMU faults and other errors can be reported.
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Scatter Gather input format for CPT has changed on CN10KB/CN10KA B0 HW
to make it compatible with NIX Scatter Gather format to support SG mode
for inline IPsec. This patch modifies the code to make the driver works
for the same. This patch also enables CPT firmware load for these chips.
Signed-off-by: Srujana Challa <schalla@marvell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This patch fixes following cleanup issues:
- Missing instruction queue free on cleanup. This
will lead to memory leak.
- lfs->lfs_num is set to zero before cleanup, which
will lead to improper cleanup.
Signed-off-by: Bharat Bhushan <bbhushan2@marvell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
There are limited number CPT LFs (example 64 LFs on cn10k) and
these LFs are allocated/attached to CPT VF on its creation.
cptpf sysfs parameter "kvf_limits" defines number of CPT LFs
per CPT VF. Default "kvf_limits" is initialized to zero and if
kvf_limits is zero then number of LF allocated are equal to
online cpus in system.
For example on 24 core system, 24 CPT LFs will be attached per VF.
That means no CPT LF available when creating more than 2 CPT VFs
on system which have total 64 LFs. Although VFs gets created but
no LF attached to it.
There seems no reason to default allocate as many LFs as many
online cpus in system. This patch initializes "kvf_limits" to
one to limit one LF allocated per CPT VF. "kvf_limits" can
be changed in range of 1 to number-of-online-cpus via sysfs.
Signed-off-by: Bharat Bhushan <bbhushan2@marvell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
API:
- Add linear akcipher/sig API.
- Add tfm cloning (hmac, cmac).
- Add statesize to crypto_ahash.
Algorithms:
- Allow only odd e and restrict value in FIPS mode for RSA.
- Replace LFSR with SHA3-256 in jitter.
- Add interface for gathering of raw entropy in jitter.
Drivers:
- Fix race on data_avail and actual data in hwrng/virtio.
- Add hash and HMAC support in starfive.
- Add RSA algo support in starfive.
- Add support for PCI device 0x156E in ccp.
-----BEGIN PGP SIGNATURE-----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=rOLu
-----END PGP SIGNATURE-----
Merge tag 'v6.5-p1' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6
Pull crypto updates from Herbert Xu:
"API:
- Add linear akcipher/sig API
- Add tfm cloning (hmac, cmac)
- Add statesize to crypto_ahash
Algorithms:
- Allow only odd e and restrict value in FIPS mode for RSA
- Replace LFSR with SHA3-256 in jitter
- Add interface for gathering of raw entropy in jitter
Drivers:
- Fix race on data_avail and actual data in hwrng/virtio
- Add hash and HMAC support in starfive
- Add RSA algo support in starfive
- Add support for PCI device 0x156E in ccp"
* tag 'v6.5-p1' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (85 commits)
crypto: akcipher - Do not copy dst if it is NULL
crypto: sig - Fix verify call
crypto: akcipher - Set request tfm on sync path
crypto: sm2 - Provide sm2_compute_z_digest when sm2 is disabled
hwrng: imx-rngc - switch to DEFINE_SIMPLE_DEV_PM_OPS
hwrng: st - keep clock enabled while hwrng is registered
hwrng: st - support compile-testing
hwrng: imx-rngc - fix the timeout for init and self check
KEYS: asymmetric: Use new crypto interface without scatterlists
KEYS: asymmetric: Move sm2 code into x509_public_key
KEYS: Add forward declaration in asymmetric-parser.h
crypto: sig - Add interface for sign/verify
crypto: akcipher - Add sync interface without SG lists
crypto: cipher - On clone do crypto_mod_get()
crypto: api - Add __crypto_alloc_tfmgfp
crypto: api - Remove crypto_init_ops()
crypto: rsa - allow only odd e and restrict value in FIPS mode
crypto: geniv - Split geniv out of AEAD Kconfig option
crypto: algboss - Add missing dependency on RNG2
crypto: starfive - Add RSA algo support
...
BACKGROUND
==========
When multiple work items are queued to a workqueue, their execution order
doesn't match the queueing order. They may get executed in any order and
simultaneously. When fully serialized execution - one by one in the queueing
order - is needed, an ordered workqueue should be used which can be created
with alloc_ordered_workqueue().
However, alloc_ordered_workqueue() was a later addition. Before it, an
ordered workqueue could be obtained by creating an UNBOUND workqueue with
@max_active==1. This originally was an implementation side-effect which was
broken by 4c16bd327c ("workqueue: restore WQ_UNBOUND/max_active==1 to be
ordered"). Because there were users that depended on the ordered execution,
5c0338c687 ("workqueue: restore WQ_UNBOUND/max_active==1 to be ordered")
made workqueue allocation path to implicitly promote UNBOUND workqueues w/
@max_active==1 to ordered workqueues.
While this has worked okay, overloading the UNBOUND allocation interface
this way creates other issues. It's difficult to tell whether a given
workqueue actually needs to be ordered and users that legitimately want a
min concurrency level wq unexpectedly gets an ordered one instead. With
planned UNBOUND workqueue updates to improve execution locality and more
prevalence of chiplet designs which can benefit from such improvements, this
isn't a state we wanna be in forever.
This patch series audits all callsites that create an UNBOUND workqueue w/
@max_active==1 and converts them to alloc_ordered_workqueue() as necessary.
WHAT TO LOOK FOR
================
The conversions are from
alloc_workqueue(WQ_UNBOUND | flags, 1, args..)
to
alloc_ordered_workqueue(flags, args...)
which don't cause any functional changes. If you know that fully ordered
execution is not ncessary, please let me know. I'll drop the conversion and
instead add a comment noting the fact to reduce confusion while conversion
is in progress.
If you aren't fully sure, it's completely fine to let the conversion
through. The behavior will stay exactly the same and we can always
reconsider later.
As there are follow-up workqueue core changes, I'd really appreciate if the
patch can be routed through the workqueue tree w/ your acks. Thanks.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Boris Brezillon <bbrezillon@kernel.org>
Cc: Arnaud Ebalard <arno@natisbad.org>
Cc: Srujana Challa <schalla@marvell.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Shijith Thotton <sthotton@marvell.com>
Cc: Vladis Dronov <vdronov@redhat.com>
Cc: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Cc: Wolfram Sang <wsa+renesas@sang-engineering.com>
Cc: Alexander Lobakin <alobakin@pm.me>
Cc: Minghao Chi <chi.minghao@zte.com.cn>
Cc: ye xingchen <ye.xingchen@zte.com.cn>
Cc: linux-crypto@vger.kernel.org
On OcteonTX2/OctoenTX3 variants of silicon, Admin function (AF)
handles resource allocation and configuration for PFs and their VFs.
PFs request the AF directly, via mailboxes.
Unlike PFs, VFs cannot send a mailbox request directly. A VF sends
mailbox messages to its parent PF, with which it shares a
mailbox region. The PF then forwards these messages to the AF.
This patch adds code to configure inline-IPsec HW resources for
CPT VFs as CPT VFs cannot send a mailbox request directly to AF.
Signed-off-by: Srujana Challa <schalla@marvell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
cn10k_cpt.o, otx2_cptlf.o and otx2_cpt_mbox_common.o are linked
into both rvu_cptpf and rvu_cptvf modules:
> scripts/Makefile.build:252: ./drivers/crypto/marvell/octeontx2/Makefile:
> cn10k_cpt.o is added to multiple modules: rvu_cptpf rvu_cptvf
> scripts/Makefile.build:252: ./drivers/crypto/marvell/octeontx2/Makefile:
> otx2_cptlf.o is added to multiple modules: rvu_cptpf rvu_cptvf
> scripts/Makefile.build:252: ./drivers/crypto/marvell/octeontx2/Makefile:
> otx2_cpt_mbox_common.o is added to multiple modules: rvu_cptpf rvu_cptvf
Despite they're build under the same Kconfig option
(CONFIG_CRYPTO_DEV_OCTEONTX2_CPT), it's better do link the common
code into a standalone module and export the shared functions. Under
certain circumstances, this can lead to the same situation as fixed
by commit 637a642f5c ("zstd: Fixing mixed module-builtin objects").
Plus, those three common object files are relatively big to duplicate
them several times.
Introduce the new module, rvu_cptcommon, to provide the common
functions to both modules.
Fixes: 19d8e8c7be ("crypto: octeontx2 - add virtual function driver support")
Suggested-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Alexander Lobakin <alobakin@pm.me>
Reviewed-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
On CN10K platform transmit/receive buffer alloc and free from/to
hardware had changed to support burst operation. Whereas pervious
silicon's only support single buffer free at a time.
To Support the same firmware allocates a DRAM region for each PF/VF for
storing LMTLINES. These LMTLINES are used to send CPT commands to HW.
PF/VF LMTST region is accessed via BAR4. PFs LMTST region is followed
by its VFs mbox memory. The size of region varies from 2KB to 256KB
based on number of LMTLINES configured.
This patch adds support for mapping of PF/VF LMTST region.
Signed-off-by: Srujana Challa <schalla@marvell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Mailbox region configuration has some changes on CN10K platform
from OcteonTX2(CN9XX) platform.
On CN10K platform:
The DRAM region allocated to PF is enumerated as PF BAR4 memory.
PF BAR4 contains AF-PF mbox region followed by its VFs mbox region.
AF-PF mbox region base address is configured at RVU_AF_PFX_BAR4_ADDR
PF-VF mailbox base address is configured at
RVU_PF(x)_VF_MBOX_ADDR = RVU_AF_PF()_BAR4_ADDR+64KB. PF access its
mbox region via BAR4, whereas VF accesses PF-VF DRAM mailboxes via
BAR2 indirect access.
On CN9XX platform:
Mailbox region in DRAM is divided into two parts AF-PF mbox region and
PF-VF mbox region i.e all PFs mbox region is contiguous similarly all
VFs.
The base address of the AF-PF mbox region is configured at
RVU_AF_PF_BAR4_ADDR.
AF-PF1 mbox address can be calculated as RVU_AF_PF_BAR4_ADDR * mbox
size.
This patch changes mbox initialization to support both CN9XX and CN10K
platform.
This patch also removes platform specific name from the PF/VF driver name
to make it appropriate for all supported platforms.
Signed-off-by: Srujana Challa <schalla@marvell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The "num_vec" has to be signed for the error handling to work.
Fixes: 19d8e8c7be ("crypto: octeontx2 - add virtual function driver support")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Attach LFs to CPT VF to process the crypto requests and register
LF interrupts.
Signed-off-by: Suheil Chandran <schandran@marvell.com>
Signed-off-by: Lukasz Bartosik <lbartosik@marvell.com>
Signed-off-by: Srujana Challa <schalla@marvell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Add support for the Marvell OcteonTX2 CPT virtual function
driver. This patch includes probe, PCI specific initialization
and interrupt handling.
Signed-off-by: Suheil Chandran <schandran@marvell.com>
Signed-off-by: Lukasz Bartosik <lbartosik@marvell.com>
Signed-off-by: Srujana Challa <schalla@marvell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
