The value of reqsize must only be changed through the helper.
Signed-off-by: Ovidiu Panait <ovidiu.panait@windriver.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Provide an option in Inline IPsec configure mailbox to configure the
CPT_AF_LFX_CTL:CTX_ILEN for inline CPT LF attached to CPT RVU PF.
This is needed to set the ctx ilen to size of inbound SA for
HW errata IPBUCPT-38756. Not setting this would lead to new context's
not being fetched.
Also set FLR_FLUSH in CPT_LF_CTX_CTL for CPT LF's as workaround
for same errata.
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
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>
HW has a errata that CPT HW may hit an issue, while processing CPT
instructions with CTX_VAL set and CTX_VAL not set. So, this patch
adds the code to always set the CTX_VAL as a workaround.
Signed-off-by: Srujana Challa <schalla@marvell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Updates CPT inbound inline IPsec configure mailbox to take
CPT credit threshold and bpid, which are introduced
in CN10KB.
Signed-off-by: Srujana Challa <schalla@marvell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
CPT LF must be reset and follow CPT LF disable sequence
suggested by HW team, when driver exits.
This patch adds code for the same.
Signed-off-by: Srujana Challa <schalla@marvell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Adds code to not execute CPT errata "when CPT_AF_DIAG[FLT_DIS] = 0 and a
CPT engine access to LLC/DRAM encounters a fault/poison, a rare case
may result in unpredictable data being delivered to a CPT engine"
workaround on CN10KA B0/CN10KB HW as it is fixed on these chips.
Signed-off-by: Srujana Challa <schalla@marvell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
On CN10KA B0/CN10KB, CPT scatter gather format has modified
to support multi-seg in inline IPsec. Due to this CPT requires
new firmware and doesn't work with CN10KA0/A1 firmware. To make
HW works in backward compatibility mode or works with CN10KA0/A1
firmware, a bit(T106_MODE) is introduced in HW CSR.
This patch adds devlink parameter for configuring T106_MODE.
This patch also documents the devlink parameter under
Documentation/crypto/device_drivers.
Signed-off-by: Srujana Challa <schalla@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>
CPT block reset in CPT PF erase all the CPT configuration which is
done in AF driver init. So, remove CPT block reset from CPT PF as
it is also being done in AF init and not required in PF.
Signed-off-by: Srujana Challa <schalla@marvell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
smatch warnings:
drivers/crypto/stm32/stm32-crc32.c:108 stm32_crc_get_next_crc() warn:
can 'crc' even be NULL?
Use list_first_entry_or_null instead of list_first_entry to retrieve
the first device registered.
The function list_first_entry always return a non NULL pointer even if
the list is empty. Hence checking if the pointer returned is NULL does
not tell if the list is empty or not.
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/r/202311281111.ou2oUL2i-lkp@intel.com/
Reported-by: Dan Carpenter <error27@gmail.com>
Closes: https://lore.kernel.org/r/202311281111.ou2oUL2i-lkp@intel.com/
Signed-off-by: Thomas Bourgoin <thomas.bourgoin@foss.st.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Add support for 420xx devices by including a new device driver that
supports such devices, updates to the firmware loader and capabilities.
Compared to 4xxx devices, 420xx devices have more acceleration engines
(16 service engines and 1 admin) and support the wireless cipher
algorithms ZUC and Snow 3G.
Signed-off-by: Jie Wang <jie.wang@intel.com>
Co-developed-by: Dong Xie <dong.xie@intel.com>
Signed-off-by: Dong Xie <dong.xie@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Relocate the structures adf_fw_objs and adf_fw_config from the file
adf_4xxx_hw_data.c to the newly created adf_fw_config.h.
These structures will be used by new device drivers.
This does not introduce any functional change.
Signed-off-by: Jie Wang <jie.wang@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Move logic that is common between QAT GEN4 accelerators to the
qat_common folder. This includes addresses of CSRs, setters and
configuration logic.
When moved, functions and defines have been renamed from 4XXX to GEN4.
Code specific to the device is moved to the file adf_gen4_hw_data.c.
Code related to configuration is moved to the newly created
adf_gen4_config.c.
This does not introduce any functional change.
Signed-off-by: Jie Wang <jie.wang@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Add accel_dev as parameter of the function uof_get_num_objs().
This is in preparation for the introduction of the QAT 420xx driver as
it will allow to reconfigure the ae_mask when a configuration that does
not require all AEs is loaded on the device.
This does not introduce any functional change.
Signed-off-by: Jie Wang <jie.wang@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Move the function get_service_enabled() from adf_4xxx_hw_data.c to
adf_cfg_services.c and rename it as adf_get_service_enabled().
This function is not specific to the 4xxx and will be used by
other QAT drivers.
This does not introduce any functional change.
Signed-off-by: Jie Wang <jie.wang@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The scheduled tasklet needs to be executed on device remove.
Fixes: fed93fb62e ("crypto: virtio - Handle dataq logic with tasklet")
Signed-off-by: wangyangxin <wangyangxin1@huawei.com>
Signed-off-by: Gonglei <arei.gonglei@huawei.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>
Add the printf of an error message and optimized the handling
process of ret.
Signed-off-by: Chenghai Huang <huangchenghai2@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Deleted a dbg function because this function has the risk of
address leakage. In addition, this function is only used for
debugging in the early stage and is not required in the future.
Signed-off-by: Chenghai Huang <huangchenghai2@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Add support for optional debugfs statistics support for the IAA
Compression Accelerator. This is enabled by the kernel config item:
CRYPTO_DEV_IAA_CRYPTO_STATS
When enabled, the IAA crypto driver will generate statistics which can
be accessed at /sys/kernel/debug/iaa-crypto/.
See Documentation/driver-api/crypto/iax/iax-crypto.rst for details.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The existing iaa crypto async support provides an implementation that
satisfies the interface but does so in a synchronous manner - it fills
and submits the IDXD descriptor and then waits for it to complete
before returning. This isn't a problem at the moment, since all
existing callers (e.g. zswap) wrap any asynchronous callees in a
synchronous wrapper anyway.
This change makes the iaa crypto async implementation truly
asynchronous: it fills and submits the IDXD descriptor, then returns
immediately with -EINPROGRESS. It also sets the descriptor's 'request
completion irq' bit and sets up a callback with the IDXD driver which
is called when the operation completes and the irq fires. The
existing callers such as zswap use synchronous wrappers to deal with
-EINPROGRESS and so work as expected without any changes.
This mode can be enabled by writing 'async_irq' to the sync_mode
iaa_crypto driver attribute:
echo async_irq > /sys/bus/dsa/drivers/crypto/sync_mode
Async mode without interrupts (caller must poll) can be enabled by
writing 'async' to it:
echo async > /sys/bus/dsa/drivers/crypto/sync_mode
The default sync mode can be enabled by writing 'sync' to it:
echo sync > /sys/bus/dsa/drivers/crypto/sync_mode
The sync_mode value setting at the time the IAA algorithms are
registered is captured in each algorithm's crypto_ctx and used for all
compresses and decompresses when using a given algorithm.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This patch registers the deflate-iaa deflate compression algorithm and
hooks it up to the IAA hardware using the 'fixed' compression mode
introduced in the previous patch.
Because the IAA hardware has a 4k history-window limitation, only
buffers <= 4k, or that have been compressed using a <= 4k history
window, are technically compliant with the deflate spec, which allows
for a window of up to 32k. Because of this limitation, the IAA fixed
mode deflate algorithm is given its own algorithm name, 'deflate-iaa'.
With this change, the deflate-iaa crypto algorithm is registered and
operational, and compression and decompression operations are fully
enabled following the successful binding of the first IAA workqueue
to the iaa_crypto sub-driver.
when there are no IAA workqueues bound to the driver, the IAA crypto
algorithm can be unregistered by removing the module.
A new iaa_crypto 'verify_compress' driver attribute is also added,
allowing the user to toggle compression verification. If set, each
compress will be internally decompressed and the contents verified,
returning error codes if unsuccessful. This can be toggled with 0/1:
echo 0 > /sys/bus/dsa/drivers/crypto/verify_compress
The default setting is '1' - verify all compresses.
The verify_compress value setting at the time the algorithm is
registered is captured in the algorithm's crypto_ctx and used for all
compresses when using the algorithm.
[ Based on work originally by George Powley, Jing Lin and Kyung Min
Park ]
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Define an in-kernel API for adding and removing compression modes,
which can be used by kernel modules or other kernel code that
implements IAA compression modes.
Also add a separate file, iaa_crypto_comp_fixed.c, containing huffman
tables generated for the IAA 'fixed' compression mode. Future
compression modes can be added in a similar fashion.
One or more crypto compression algorithms will be created for each
compression mode, each of which can be selected as the compression
algorithm to be used by a particular facility.
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The iaa compression/decompression algorithms in later patches need a
way to retrieve an appropriate IAA workqueue depending on how close
the associated IAA device is to the current cpu.
For this purpose, add a per-cpu array of workqueues such that an
appropriate workqueue can be retrieved by simply accessing the per-cpu
array.
Whenever a new workqueue is bound to or unbound from the iaa_crypto
driver, the available workqueues are 'rebalanced' such that work
submitted from a particular CPU is given to the most appropriate
workqueue available. There currently isn't any way for the user to
tweak the way this is done internally - if necessary, knobs can be
added later for that purpose. Current best practice is to configure
and bind at least one workqueue for each IAA device, but as long as
there is at least one workqueue configured and bound to any IAA device
in the system, the iaa_crypto driver will work, albeit most likely not
as efficiently.
[ Based on work originally by George Powley, Jing Lin and Kyung Min
Park ]
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The Intel Analytics Accelerator (IAA) is a hardware accelerator that
provides very high thoughput compression/decompression compatible with
the DEFLATE compression standard described in RFC 1951, which is the
compression/decompression algorithm exported by this module.
Users can select IAA compress/decompress acceleration by specifying
one of the deflate-iaa* algorithms as the compression algorithm to use
by whatever facility allows asynchronous compression algorithms to be
selected.
For example, zswap can select the IAA fixed deflate algorithm
'deflate-iaa' via:
# echo deflate-iaa > /sys/module/zswap/parameters/compressor
This patch adds iaa_crypto as an idxd sub-driver and tracks iaa
devices and workqueues as they are probed or removed.
[ Based on work originally by George Powley, Jing Lin and Kyung Min
Park ]
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Current dev_err_probe will return 0 instead of proper error code if
driver failed to get irq number. Fix the return code.
Signed-off-by: Jia Jie Ho <jiajie.ho@starfivetech.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
NULL check before kfree_sensitive function is not needed.
Signed-off-by: Jia Jie Ho <jiajie.ho@starfivetech.com>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202311301702.LxswfETY-lkp@intel.com/
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Pre-store the valid value of the zip alg support related capability
register in hisi_zip_qm_init(), which will be called by hisi_zip_probe().
It can reduce the number of capability register queries and avoid
obtaining incorrect values in abnormal scenarios, such as reset failed
and the memory space disabled.
Fixes: db700974b6 ("crypto: hisilicon/zip - support zip capability")
Signed-off-by: Zhiqi Song <songzhiqi1@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Pre-store the valid value of the sec alg support related capability
register in sec_qm_init(), which will be called by probe process.
It can reduce the number of capability register queries and avoid
obtaining incorrect values in abnormal scenarios, such as reset
failed and the memory space disabled.
Fixes: 921715b6b7 ("crypto: hisilicon/sec - get algorithm bitmap from registers")
Signed-off-by: Zhiqi Song <songzhiqi1@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Pre-store the valid value of hpre alg support related capability
register in hpre_qm_init(), which will be called by hpre_probe().
It can reduce the number of capability register queries and avoid
obtaining incorrect values in abnormal scenarios, such as reset
failed and the memory space disabled.
Fixes: f214d59a06 ("crypto: hisilicon/hpre - support hpre capability")
Signed-off-by: Zhiqi Song <songzhiqi1@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
In previous capability register implementation, qm irq related values
were read from capability registers dynamically when needed. But in
abnormal scenario, e.g. the core is timeout and the device needs to
soft reset and reset failed after disabling the MSE, the device can
not be removed normally, causing the following call trace:
| Call trace:
| pci_irq_vector+0xfc/0x140
| hisi_qm_uninit+0x278/0x3b0 [hisi_qm]
| hpre_remove+0x16c/0x1c0 [hisi_hpre]
| pci_device_remove+0x6c/0x264
| device_release_driver_internal+0x1ec/0x3e0
| device_release_driver+0x3c/0x60
| pci_stop_bus_device+0xfc/0x22c
| pci_stop_and_remove_bus_device+0x38/0x70
| pci_iov_remove_virtfn+0x108/0x1c0
| sriov_disable+0x7c/0x1e4
| pci_disable_sriov+0x4c/0x6c
| hisi_qm_sriov_disable+0x90/0x160 [hisi_qm]
| hpre_remove+0x1a8/0x1c0 [hisi_hpre]
| pci_device_remove+0x6c/0x264
| device_release_driver_internal+0x1ec/0x3e0
| driver_detach+0x168/0x2d0
| bus_remove_driver+0xc0/0x230
| driver_unregister+0x58/0xdc
| pci_unregister_driver+0x40/0x220
| hpre_exit+0x34/0x64 [hisi_hpre]
| __arm64_sys_delete_module+0x374/0x620
[...]
| Call trace:
| free_msi_irqs+0x25c/0x300
| pci_disable_msi+0x19c/0x264
| pci_free_irq_vectors+0x4c/0x70
| hisi_qm_pci_uninit+0x44/0x90 [hisi_qm]
| hisi_qm_uninit+0x28c/0x3b0 [hisi_qm]
| hpre_remove+0x16c/0x1c0 [hisi_hpre]
| pci_device_remove+0x6c/0x264
[...]
The reason for this call trace is that when the MSE is disabled, the value
of capability registers in the BAR space become invalid. This will make the
subsequent unregister process get the wrong irq vector through capability
registers and get the wrong irq number by pci_irq_vector().
So add a capability table structure to pre-store the valid value of the irq
information capability register in qm init process, avoid obtaining invalid
capability register value after the MSE is disabled.
Fixes: 3536cc55ca ("crypto: hisilicon/qm - support get device irq information from hardware registers")
Signed-off-by: Zhiqi Song <songzhiqi1@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Extract a public function to set qm algs and remove
the similar code for setting qm algs in each module.
Signed-off-by: Wenkai Lin <linwenkai6@hisilicon.com>
Signed-off-by: Hao Fang <fanghao11@huawei.com>
Signed-off-by: Zhiqi Song <songzhiqi1@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Factor out duplicated skcipher fallback handling code to a helper function
sahara_aes_fallback(). Also, keep a single check if fallback is required in
sahara_aes_crypt().
Signed-off-by: Ovidiu Panait <ovidiu.panait@windriver.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The "error" field in sahara_dev struct hasn't been needed/used since commit
c0c3c89ae3 ("crypto: sahara - replace tasklets with kthread"), so remove
the remaining references.
Signed-off-by: Ovidiu Panait <ovidiu.panait@windriver.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Do not call dma_unmap_sg() for scatterlists that were not mapped
successfully.
Fixes: 5de8875281 ("crypto: sahara - Add driver for SAHARA2 accelerator.")
Signed-off-by: Ovidiu Panait <ovidiu.panait@windriver.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
It's not always the case that the entire sg entry needs to be processed.
Currently, when cryptlen is less than sg->legth, "Descriptor length" errors
are encountered.
The error was noticed when testing xts(sahara-ecb-aes) with arbitrary sized
input data. To fix this, take the actual request size into account when
populating the hw links.
Fixes: 5de8875281 ("crypto: sahara - Add driver for SAHARA2 accelerator.")
Signed-off-by: Ovidiu Panait <ovidiu.panait@windriver.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
update() calls should not modify the result buffer, so add an additional
check for "rctx->last" to make sure that only the final hash value is
copied into the buffer.
Fixes the following selftest failure:
alg: ahash: sahara-sha256 update() used result buffer on test vector 3,
cfg="init+update+final aligned buffer"
Fixes: 5a2bb93f59 ("crypto: sahara - add support for SHA1/256")
Signed-off-by: Ovidiu Panait <ovidiu.panait@windriver.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The kernel crypto API requires that all CBC implementations update the IV
buffer to contain the last ciphertext block.
This fixes the following cbc selftest error:
alg: skcipher: sahara-cbc-aes encryption test failed (wrong output IV) on
test vector 0, cfg="in-place (one sglist)"
Fixes: 5de8875281 ("crypto: sahara - Add driver for SAHARA2 accelerator.")
Signed-off-by: Ovidiu Panait <ovidiu.panait@windriver.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Remove the FLAGS_NEW_KEY logic as it has the following issues:
- the wrong key may end up being used when there are multiple data streams:
t1 t2
setkey()
encrypt()
setkey()
encrypt()
encrypt() <--- key from t2 is used
- switching between encryption and decryption with the same key is not
possible, as the hdr flags are only updated when a new setkey() is
performed
With this change, the key is always sent along with the cryptdata when
performing encryption/decryption operations.
Fixes: 5de8875281 ("crypto: sahara - Add driver for SAHARA2 accelerator.")
Signed-off-by: Ovidiu Panait <ovidiu.panait@windriver.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Macro dma_map_sg() may return 0 on error. This patch enables
checks in case of the macro failure and ensures unmapping of
previously mapped buffers with dma_unmap_sg().
Found by Linux Verification Center (linuxtesting.org) with static
analysis tool SVACE.
Fixes: 49186a7d9e ("crypto: inside_secure - Avoid dma map if size is zero")
Signed-off-by: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Reviewed-by: Antoine Tenart <atenart@kernel.org>
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>
There is a possibility that the function adf_devmgr_pci_to_accel_dev()
might return a NULL pointer.
Add a NULL pointer check in the function rp2srv_show().
Fixes: dbc8876dd8 ("crypto: qat - add rp2svc sysfs attribute")
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Ahsan Atta <ahsan.atta@intel.com>
Reviewed-by: David Guckian <david.guckian@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
If the function validate_user_input() returns an error, the error path
attempts to unlock an unacquired mutex.
Acquire the mutex before calling validate_user_input(). This is not
strictly necessary but simplifies the code.
Fixes: d9fb840837 ("crypto: qat - add rate limiting feature to qat_4xxx")
Signed-off-by: Damian Muszynski <damian.muszynski@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The input argument `sla_in` is a pointer to a structure that contains
the parameters of the SLA which is being added or updated.
If this pointer is NULL, the function should return an error as
the data required for the algorithm is not available.
By mistake, the logic jumps to the error path which dereferences
the pointer.
This results in a warnings reported by the static analyzer Smatch when
executed without a database:
drivers/crypto/intel/qat/qat_common/adf_rl.c:871 add_update_sla()
error: we previously assumed 'sla_in' could be null (see line 812)
This issue was not found in internal testing as the pointer cannot be
NULL. The function add_update_sla() is only called (indirectly) by
the rate limiting sysfs interface implementation in adf_sysfs_rl.c
which ensures that the data structure is allocated and valid. This is
also proven by the fact that Smatch executed with a database does not
report such error.
Fix it by returning with error if the pointer `sla_in` is NULL.
Fixes: d9fb840837 ("crypto: qat - add rate limiting feature to qat_4xxx")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Damian Muszynski <damian.muszynski@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
When dma_map_single() fails, wa->address is supposed to be freed
by the callers of ccp_init_dm_workarea() through ccp_dm_free().
However, many of the call spots don't expect to have to call
ccp_dm_free() on failure of ccp_init_dm_workarea(), which may
lead to a memleak. Let's free wa->address in ccp_init_dm_workarea()
when dma_map_single() fails.
Fixes: 63b945091a ("crypto: ccp - CCP device driver and interface support")
Signed-off-by: Dinghao Liu <dinghao.liu@zju.edu.cn>
Acked-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Return crypto_aead_setkey() in order to transfer the error if
it fails.
Fixes: d2c8ac187f ("crypto: sa2ul - Add AEAD algorithm support")
Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
1. Remove redundant array element, prevent the size obtained by
ARRAY_SIZE() from qm_log_hw_error is greater than actual size.
2. Add comments in function qm_set_vf_mse() and qm_cq_ctx_cfg()
to make it easier to understand.
Signed-off-by: Weili Qian <qianweili@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The 'QM_INIT' and 'QM_CLOSE' status of qm and 'QP_INIT'
and 'QP_CLOSE' status of queue are not actually used. Currently,
driver only needs to switch status when the device or queue
is enabled or stopped, Therefore, remove unneeded status to
simplify driver. In addition, rename'QM_START to'QM_WORK' for
ease to understand.
Signed-off-by: Weili Qian <qianweili@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
1. Remove unnecessary brackets in function hisi_acc_create_sgl_pool().
2. Modify local variable type, ensure that the variable type is
consistent with the variable type to be compared.
3. Because the function clear_hw_sgl_sge() is in the task process,
obtain the value of le16_to_cpu(hw_sgl->entry_sum_in_sgl) before
loop execting to shorten the loop execution time.
Signed-off-by: Weili Qian <qianweili@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
To meet specific application scenarios, the function of switching between
the high performance mode and the high compression mode is added.
Use the perf_mode=0/1 configuration to set the compression high perf mode,
0(default, high compression mode), 1(high performance mode). These two
modes only apply to the compression direction and are compatible with
software algorithm in both directions.
Signed-off-by: Chenghai Huang <huangchenghai2@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The qat_rl sysfs attribute group is registered within the adf_dev_start()
function, alongside other driver components.
If any of the functions preceding the group registration fails,
the adf_dev_start() function returns, and the caller, to undo the
operation, invokes adf_dev_stop() followed by adf_dev_shutdown().
However, the current flow lacks information about whether the
registration of the qat_rl attribute group was successful or not.
In cases where this condition is encountered, an error similar to
the following might be reported:
4xxx 0000:6b:00.0: Starting device qat_dev0
4xxx 0000:6b:00.0: qat_dev0 started 9 acceleration engines
4xxx 0000:6b:00.0: Failed to send init message
4xxx 0000:6b:00.0: Failed to start device qat_dev0
sysfs group 'qat_rl' not found for kobject '0000:6b:00.0'
...
sysfs_remove_groups+0x2d/0x50
adf_sysfs_rl_rm+0x44/0x70 [intel_qat]
adf_rl_stop+0x2d/0xb0 [intel_qat]
adf_dev_stop+0x33/0x1d0 [intel_qat]
adf_dev_down+0xf1/0x150 [intel_qat]
...
4xxx 0000:6b:00.0: qat_dev0 stopped 9 acceleration engines
4xxx 0000:6b:00.0: Resetting device qat_dev0
To prevent attempting to remove attributes from a group that has not
been added yet, a flag named 'sysfs_added' is introduced. This flag
is set to true upon the successful registration of the attribute group.
Fixes: d9fb840837 ("crypto: qat - add rate limiting feature to qat_4xxx")
Signed-off-by: Damian Muszynski <damian.muszynski@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Ahsan Atta <ahsan.atta@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The qat_ras sysfs attribute group is registered within the
adf_dev_start() function, alongside other driver components.
If any of the functions preceding the group registration fails,
the adf_dev_start() function returns, and the caller, to undo the
operation, invokes adf_dev_stop() followed by adf_dev_shutdown().
However, the current flow lacks information about whether the
registration of the qat_ras attribute group was successful or not.
In cases where this condition is encountered, an error similar to
the following might be reported:
4xxx 0000:6b:00.0: Starting device qat_dev0
4xxx 0000:6b:00.0: qat_dev0 started 9 acceleration engines
4xxx 0000:6b:00.0: Failed to send init message
4xxx 0000:6b:00.0: Failed to start device qat_dev0
sysfs group 'qat_ras' not found for kobject '0000:6b:00.0'
...
sysfs_remove_groups+0x29/0x50
adf_sysfs_stop_ras+0x4b/0x80 [intel_qat]
adf_dev_stop+0x43/0x1d0 [intel_qat]
adf_dev_down+0x4b/0x150 [intel_qat]
...
4xxx 0000:6b:00.0: qat_dev0 stopped 9 acceleration engines
4xxx 0000:6b:00.0: Resetting device qat_dev0
To prevent attempting to remove attributes from a group that has not
been added yet, a flag named 'sysfs_added' is introduced. This flag
is set to true upon the successful registration of the attribute group.
Fixes: 532d7f6bc4 ("crypto: qat - add error counters")
Signed-off-by: Damian Muszynski <damian.muszynski@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Ahsan Atta <ahsan.atta@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Doing ipsec produces a spinlock recursion warning.
This is due to crypto_finalize_request() being called in the upper half.
Move virtual data queue processing of virtio-crypto driver to tasklet.
Fixes: dbaf0624ff ("crypto: add virtio-crypto driver")
Reported-by: Halil Pasic <pasic@linux.ibm.com>
Signed-off-by: wangyangxin <wangyangxin1@huawei.com>
Signed-off-by: Gonglei <arei.gonglei@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Aad requires padding with zeroes up to 15 bytes in some cases. This
patch increases the allocated buffer size for aad and prevents the
driver accessing uninitialized memory region.
v1->v2: Specify reason for alloc size change in descriptions.
Signed-off-by: Jia Jie Ho <jiajie.ho@starfivetech.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Hardware could not clear irq status without resetting the entire module.
Driver receives irq immediately when mask bit is cleared causing
intermittent errors in RSA calculations. Switch to use csr polling for
done status instead.
Signed-off-by: Jia Jie Ho <jiajie.ho@starfivetech.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Change AMBA_PL08X to required dependency as the hash ops depends on it
for data transfer.
Signed-off-by: Jia Jie Ho <jiajie.ho@starfivetech.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This fixes list_add corruption error when the driver is returned
with -EPROBE_DEFER. It is also required to roll back the previous
probe sequences in case of deferred_probe. So, this removes
'err_probe_defer" goto label and just use err_dma_init instead.
Fixes: 42ef0e944b ("crypto: starfive - Add crypto engine support")
Signed-off-by: Chanho Park <chanho61.park@samsung.com>
Reviewed-by: Jia Jie Ho <jiajie.ho@starfivetech.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The "ring" variable has an upper bounds check but nothing checks for
negatives. This code uses kstrtouint() already and it was obviously
intended to be declared as unsigned int. Make it so.
Fixes: dbc8876dd8 ("crypto: qat - add rp2svc sysfs attribute")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Acked-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Simplify sun8i_ss_hashkey() by using crypto_shash_tfm_digest() instead
of an alloc+init+update+final sequence. This should also improve
performance.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The 'offset' type is unsigned long in 'struct debugfs_reg32',
so type of values casts to unsigned long long is incorrect, and the
values do not require type cast, remove them.
Signed-off-by: Weili Qian <qianweili@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
When device is abnormal and reports abnormal interrupt event to driver,
the driver can print device information for error analysis. This patch
adds some device error-related information output after the device reports
an abnormal interrupt.
Signed-off-by: Weili Qian <qianweili@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The heuristics used by gcc triggers false positive truncation
warnings in hifn_alg_alloc.
Add checks on snprintf calls to silence these warnings, including
the one for cra_driver_name even though it does not currently trigger
a gcc warning.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The heuristics used by gcc triggers false positive truncation
warnings in hifn_alg_alloc. The warnings are false positives
because nengines is at most 2.
Make the buffer bigger and change the snprintf to use unsigned
integers to eliminate these warnings.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The heuristics used by gcc triggers false positive truncation
warnings in hifn_alg_alloc. The warning triggered by the strings
here are clearly false positives (see
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=95755).
Add checks on snprintf calls to silence these warnings, including
the one for cra_driver_name even though it does not currently trigger
a gcc warning.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The function pointer crypto_ahash::init is an internal implementation
detail of the ahash API that exists to help it support both ahash and
shash algorithms. With an upcoming refactoring of how the ahash API
supports shash algorithms, this field will be removed.
Some drivers are invoking crypto_ahash::init to call into their own
code, which is unnecessary and inefficient. The talitos driver is one
of those drivers. Make it just call its own code directly.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The function pointer crypto_ahash::init is an internal implementation
detail of the ahash API that exists to help it support both ahash and
shash algorithms. With an upcoming refactoring of how the ahash API
supports shash algorithms, this field will be removed.
Some drivers are invoking crypto_ahash::init to call into their own
code, which is unnecessary and inefficient. The chelsio driver is one
of those drivers. Make it just call its own code directly.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The crypto API's support for alignmasks for ahash algorithms is nearly
useless, as its only effect is to cause the API to align the key and
result buffers. The drivers that happen to be specifying an alignmask
for ahash rarely actually need it. When they do, it's easily fixable,
especially considering that these buffers cannot be used for DMA.
In preparation for removing alignmask support from ahash, this patch
makes the stm32 driver no longer use it. This driver didn't actually
rely on it; it only writes to the result buffer in stm32_hash_finish(),
simply using memcpy(). And stm32_hash_setkey() does not assume any
alignment for the key buffer.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The crypto API's support for alignmasks for ahash algorithms is nearly
useless, as its only effect is to cause the API to align the key and
result buffers. The drivers that happen to be specifying an alignmask
for ahash rarely actually need it. When they do, it's easily fixable,
especially considering that these buffers cannot be used for DMA.
In preparation for removing alignmask support from ahash, this patch
makes the starfive driver no longer use it. This driver did actually
rely on it, but only for storing to the result buffer using int stores
in starfive_hash_copy_hash(). This patch makes
starfive_hash_copy_hash() use put_unaligned() instead. (It really
should use a specific endianness, but that's an existing bug.)
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The crypto API's support for alignmasks for ahash algorithms is nearly
useless, as its only effect is to cause the API to align the key and
result buffers. The drivers that happen to be specifying an alignmask
for ahash rarely actually need it. When they do, it's easily fixable,
especially considering that these buffers cannot be used for DMA.
In preparation for removing alignmask support from ahash, this patch
makes the rockchip driver no longer use it. This driver didn't actually
rely on it; it only writes to the result buffer in rk_hash_run(),
already using put_unaligned_le32(). And this driver only supports
unkeyed hash algorithms, so the key buffer need not be considered.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The crypto API's support for alignmasks for ahash algorithms is nearly
useless, as its only effect is to cause the API to align the key and
result buffers. The drivers that happen to be specifying an alignmask
for ahash rarely actually need it. When they do, it's easily fixable,
especially considering that these buffers cannot be used for DMA.
In preparation for removing alignmask support from ahash, this patch
makes the omap-sham driver no longer use it. This driver did actually
rely on it, but only for storing to the result buffer using __u32 stores
in omap_sham_copy_ready_hash(). This patch makes
omap_sham_copy_ready_hash() use put_unaligned() instead. (It really
should use a specific endianness, but that's an existing bug.)
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The crypto API's support for alignmasks for ahash algorithms is nearly
useless, as its only effect is to cause the API to align the key and
result buffers. The drivers that happen to be specifying an alignmask
for ahash rarely actually need it. When they do, it's easily fixable,
especially considering that these buffers cannot be used for DMA.
In preparation for removing alignmask support from ahash, this patch
makes the talitos driver no longer use it. This driver didn't actually
rely on it; it only writes to the result buffer in
common_nonsnoop_hash_unmap(), simply using memcpy(). And this driver's
"ahash_setkey()" function does not assume any alignment for the key
buffer.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The crypto API's support for alignmasks for ahash algorithms is nearly
useless, as its only effect is to cause the API to align the key and
result buffers. The drivers that happen to be specifying an alignmask
for ahash rarely actually need it. When they do, it's easily fixable,
especially considering that these buffers cannot be used for DMA.
In preparation for removing alignmask support from ahash, this patch
makes the s5p-sss driver no longer use it. This driver didn't actually
rely on it; it only writes to the result buffer in
s5p_hash_copy_result(), simply using memcpy(). And this driver only
supports unkeyed hash algorithms, so the key buffer need not be
considered.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The crypto API's support for alignmasks for ahash algorithms is nearly
useless, as its only effect is to cause the API to align the key and
result buffers. The drivers that happen to be specifying an alignmask
for ahash rarely actually need it. When they do, it's easily fixable,
especially considering that these buffers cannot be used for DMA.
In preparation for removing alignmask support from ahash, this patch
makes the mxs-dcp driver no longer use it. This driver didn't actually
rely on it; it only writes to the result buffer in dcp_sha_req_to_buf(),
using a bytewise copy. And this driver only supports unkeyed hash
algorithms, so the key buffer need not be considered.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The crypto API's support for alignmasks for ahash algorithms is nearly
useless, as its only effect is to cause the API to align the key and
result buffers. The drivers that happen to be specifying an alignmask
for ahash rarely actually need it. When they do, it's easily fixable,
especially considering that these buffers cannot be used for DMA.
In preparation for removing alignmask support from ahash, this patch
makes the artpec6 driver no longer use it. This driver is unusual in
that it DMAs the digest directly to the result buffer. This is broken
because the crypto API provides the result buffer as an arbitrary
virtual address, which might not be valid for DMA, even after the crypto
API applies the alignmask. Maybe the alignmask (which this driver set
only to 3) made this code work in a few more cases than it otherwise
would have. But even if so, it doesn't make sense for this single
driver that is broken anyway to block removal of the alignmask support.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The crypto API's support for alignmasks for ahash algorithms is nearly
useless, as its only effect is to cause the API to align the key and
result buffers. The drivers that happen to be specifying an alignmask
for ahash rarely actually need it. When they do, it's easily fixable,
especially considering that these buffers cannot be used for DMA.
In preparation for removing alignmask support from ahash, this patch
makes the atmel driver no longer use it. This driver didn't actually
rely on it; it only writes to the result buffer in
atmel_sha_copy_ready_hash(), simply using memcpy(). And this driver
didn't set an alignmask for any keyed hash algorithms, so the key buffer
need not be considered.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The crypto API's support for alignmasks for ahash algorithms is nearly
useless, as its only effect is to cause the API to align the key and
result buffers. The drivers that happen to be specifying an alignmask
for ahash rarely actually need it. When they do, it's easily fixable,
especially considering that these buffers cannot be used for DMA.
In preparation for removing alignmask support from ahash, this patch
makes the sun8i-ss driver no longer use it. This driver didn't actually
rely on it; it only writes to the result buffer in sun8i_ss_hash_run(),
simply using memcpy(). And sun8i_ss_hmac_setkey() does not assume any
alignment for the key buffer.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Acked-by: Corentin Labbe <clabbe.montjoie@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The crypto API's support for alignmasks for ahash algorithms is nearly
useless, as its only effect is to cause the API to align the key and
result buffers. The drivers that happen to be specifying an alignmask
for ahash rarely actually need it. When they do, it's easily fixable,
especially considering that these buffers cannot be used for DMA.
In preparation for removing alignmask support from ahash, this patch
makes the sun8i-ce driver no longer use it. This driver didn't actually
rely on it; it only writes to the result buffer in sun8i_ce_hash_run(),
simply using memcpy(). And this driver only supports unkeyed hash
algorithms, so the key buffer need not be considered.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Acked-by: Corentin Labbe <clabbe.montjoie@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The crypto API's support for alignmasks for ahash algorithms is nearly
useless, as its only effect is to cause the API to align the key and
result buffers. The drivers that happen to be specifying an alignmask
for ahash rarely actually need it. When they do, it's easily fixable,
especially considering that these buffers cannot be used for DMA.
In preparation for removing alignmask support from ahash, this patch
makes the sun4i-ss driver no longer use it. This driver didn't actually
rely on it; it only writes to the result buffer in sun4i_hash(), already
using the unaligned access helpers. And this driver only supports
unkeyed hash algorithms, so the key buffer need not be considered.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Acked-by: Corentin Labbe <clabbe.montjoie@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
If a request has the flag CRYPTO_TFM_REQ_MAY_BACKLOG set, the function
qat_alg_send_message_maybacklog(), enqueues it in a backlog list if
either (1) there is already at least one request in the backlog list, or
(2) the HW ring is nearly full or (3) the enqueue to the HW ring fails.
If an interrupt occurs right before the lock in qat_alg_backlog_req() is
taken and the backlog queue is being emptied, then there is no request
in the HW queues that can trigger a subsequent interrupt that can clear
the backlog queue. In addition subsequent requests are enqueued to the
backlog list and not sent to the hardware.
Fix it by holding the lock while taking the decision if the request
needs to be included in the backlog queue or not. This synchronizes the
flow with the interrupt handler that drains the backlog queue.
For performance reasons, the logic has been changed to try to enqueue
first without holding the lock.
Fixes: 3868238397 ("crypto: qat - add backlog mechanism")
Reported-by: Mikulas Patocka <mpatocka@redhat.com>
Closes: https://lore.kernel.org/all/af9581e2-58f9-cc19-428f-6f18f1f83d54@redhat.com/T/
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The file adf_cfg_services.h cannot be included in header files since it
instantiates the structure adf_cfg_services. Move that structure to its
own file and export the symbol.
This does not introduce any functional change.
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Damian Muszynski <damian.muszynski@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Add the attribute `num_rps` to the `qat` attribute group. This returns
the number of ring pairs that a single device has. This allows to know
the maximum value that can be set to the attribute `rp2svc`.
Signed-off-by: Ciunas Bennett <ciunas.bennett@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Damian Muszynski <damian.muszynski@intel.com>
Reviewed-by: Tero Kristo <tero.kristo@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Add the attribute `rp2svc` to the `qat` attribute group. This provides a
way for a user to query a specific ring pair for the type of service
that is currently configured for.
When read, the service will be returned for the defined ring pair.
When written to this value will be stored as the ring pair to return
the service of.
Signed-off-by: Ciunas Bennett <ciunas.bennett@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Damian Muszynski <damian.muszynski@intel.com>
Reviewed-by: Tero Kristo <tero.kristo@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Add an interface for the rate limiting feature which allows to add,
remove and modify a QAT SLA (Service Level Agreement).
This adds a new sysfs attribute group, `qat_rl`, which can be accessed
from /sys/bus/pci/devices/<BUS:DEV:FUNCTION> with the following
hierarchy:
|-+ qat_rl
|---- id (RW) # SLA identifier
|---- cir (RW) # Committed Information Rate
|---- pir (RW) # Peak Information Rate
|---- srv (RW) # Service to be rate limited
|---- rp (RW) (HEX) # Ring pairs to be rate limited
|---- cap_rem (RW) # Remaining capability for a service
|---- sla_op (WO) # Allows to perform an operation on an SLA
The API works by setting the appropriate RW attributes and then
issuing a command through the `sla_op`. For example, to create an SLA, a
user needs to input the necessary data into the attributes cir, pir, srv
and rp and then write into `sla_op` the command `add` to execute the
operation.
The API also provides `cap_rem` attribute to get information about
the remaining device capability within a certain service which is
required when setting an SLA.
Signed-off-by: Ciunas Bennett <ciunas.bennett@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Damian Muszynski <damian.muszynski@intel.com>
Reviewed-by: Tero Kristo <tero.kristo@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The Rate Limiting (RL) feature allows to control the rate of requests
that can be submitted on a ring pair (RP). This allows sharing a QAT
device among multiple users while ensuring a guaranteed throughput.
The driver provides a mechanism that allows users to set policies, that
are programmed to the device. The device is then enforcing those policies.
Configuration of RL is accomplished through entities called SLAs
(Service Level Agreement). Each SLA object gets a unique identifier
and defines the limitations for a single service across up to four
ring pairs (RPs count allocated to a single VF).
The rate is determined using two fields:
* CIR (Committed Information Rate), i.e., the guaranteed rate.
* PIR (Peak Information Rate), i.e., the maximum rate achievable
when the device has available resources.
The rate values are expressed in permille scale i.e. 0-1000.
Ring pair selection is achieved by providing a 64-bit mask, where
each bit corresponds to one of the ring pairs.
This adds an interface and logic that allow to add, update, retrieve
and remove an SLA.
Signed-off-by: Damian Muszynski <damian.muszynski@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Tero Kristo <tero.kristo@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The QAT firmware provides a mechanism to retrieve its capabilities
through the init admin interface.
Add logic to retrieve the firmware capability mask from the firmware
through the init/admin channel. This mask reports if the
power management, telemetry and rate limiting features are supported.
The fw capabilities are stored in the accel_dev structure and are used
to detect if a certain feature is supported by the firmware loaded
in the device.
This is supported only by devices which have an admin AE.
Signed-off-by: Damian Muszynski <damian.muszynski@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Tero Kristo <tero.kristo@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>