linux-crypto.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH v2 00/15] crypto: Add Intel Analytics Accelerator (IAA) crypto compression driver
@ 2023-03-28 15:35 Tom Zanussi
  2023-03-28 15:35 ` [PATCH v2 01/15] dmaengine: idxd: add wq driver name support for accel-config user tool Tom Zanussi
                   ` (15 more replies)
  0 siblings, 16 replies; 25+ messages in thread
From: Tom Zanussi @ 2023-03-28 15:35 UTC (permalink / raw)
  To: herbert, davem, fenghua.yu, vkoul
  Cc: dave.jiang, tony.luck, wajdi.k.feghali, james.guilford,
	kanchana.p.sridhar, giovanni.cabiddu, linux-kernel, linux-crypto,
	dmaengine

Hi, this is v2 of the IAA crypto driver, incorporating feedback from
v1.

v2 changes:

  - Removed legacy interface and all related code; merged async
    interface into main deflate patch.

  - Added support for the null destination case.  Thanks to Giovanni
    Cabiddu for making me aware of this as well as the selftests for
    it.

  - Had to do some rearrangement of the code in order to pass all the
    selftests.  Also added a testcase for 'canned'.

  - Moved the iaa crypto driver to drivers/crypto/intel, and moved all
    the other intel drivers there as well (which will be posted as a
    separate series immediately following this one).

  - Added an iaa crypto section to MAINTAINERS.

  - Updated the documenation and commit messages to reflect the removal
    of the legacy interface.

  - Changed kernel version from 6.3.0 to 6.4.0 in patch 01/15 (wq
    driver name support)

v1:

This series adds Linux crypto algorithm support for Intel® In-memory
Analytics Accelerator (Intel IAA) [1] hardware compression and
decompression, which is available on Sapphire Rapids systems.

The IAA crypto support is implemented as an IDXD sub-driver.  The IDXD
driver already present in the kernel provides discovery and management
of the IAA devices on a system, as well as all the functionality
needed to manage, submit, and wait for completion of work executed on
them.  The first 7 patches (patches starting with dmaengine:) add
small bits of underlying IDXD plumbing needed to allow external
sub-drivers to take advantage of this support and claim ownership of
specific IAA devices and workqueues.

The remaining patches add the main support for this feature via the
crypto API, making it transparently accessible to kernel features that
can make use of it such as zswap and zram (patches starting with
crypto – iaa:).

These include both sync/async support for the deflate algorithm
implemented by the IAA hardware, as well as an additional option for
driver statistics and Documentation.

Patch 8 ('[PATCH 08/15] crypto: iaa - Add IAA Compression Accelerator
Documentation') describes the IAA crypto driver in detail; the
following is just a high-level synopsis meant to aid the following
discussion.

The IAA hardware is fairly complex and generally requires a
knowledgeable administrator with sufficiently detailed understanding
of the hardware to set it up before it can be used.  As mentioned in
the Documentation, this typically requires using a special tool called
accel-config to enumerate and configure IAA workqueues, engines, etc,
although this can also be done using only sysfs files.

The operation of the driver mirrors this requirement and only allows
the hardware to be accessed via the crypto layer once the hardware has
been configured and bound to the the IAA crypto driver.  As an IDXD
sub-driver, the IAA crypto driver essentially takes ownership of the
hardware until it is given up explicitly by the administrator.  This
occurs automatically when the administrator enables the first IAA
workqueue or disables the last one; the iaa_crypto (sync and async)
algorithms are registered when the first workqueue is enabled, and
deregistered when the last one is disabled.

The normal sequence of operations would normally be: 

  < configure the hardware using accel-config or sysfs > 

  < configure the iaa crypto driver (see below) > 

  < configure the subsystem e.g. zswap/zram to use the iaa_crypto algo >  

  < run the workload > 

There are a small number of iaa_crypto driver attributes that the
administrator can configure, and which also need to be configured
before the algorithm is enabled:

compression_mode: 

  The IAA crypto driver supports an extensible interface supporting
  any number of different compression modes that can be tailored to
  specific types of workloads.  These are implemented as tables and
  given arbitrary names describing their intent.

  There are currently only 2 compression modes, “canned” and “fixed”.
  In order to set a compression mode, echo the mode’s name to the
  compression_mode driver attribute:
 
    echo "canned" > /sys/bus/dsa/drivers/crypto/compression_mode

There are a few other available iaa_crypto driver attributes (see
Documentation for details) but the main one we want to consider in
detail for now is the ‘sync_mode’ attribute.

The ‘sync_mode’ attribute has 3 possible settings: ‘sync’, ‘async’,
and ‘async_irq’.

The context for these different modes is that although the iaa_crypto
driver implements the asynchronous crypto interface, the async
interface is currently only used in a synchronous way by facilities
like zswap that make use of it.

This is fine for software compress/decompress algorithms, since
there’s no real benefit in being able to use a truly asynchronous
interface with them.  This isn’t the case, though, for hardware
compress/decompress engines such as IAA, where truly asynchronous
behavior is beneficial if not completely necessary to make optimal use
of the hardware.

The IAA crypto driver ‘sync_mode’ support should allow facilities such
as zswap to ‘support async (de)compression in some way [2]’ once
they are modified to actually make use of it.

When the ‘async_irq’ sync_mode is specified, the driver sets the bits
in the IAA work descriptor to generate an irq when the work completes.
So for every compression or decompression, the IAA acomp_alg
implementations called by crypto_acomp_compress/decompress() simply
set up the descriptor, turn on the 'request irq' bit and return
immediately with -EINPROGRESS.  When the work completes, the irq fires
and the IDXD driver’s irq thread for that irq invokes the callback the
iaa_crypto module registered with IDXD.  When the irq thread gets
scheduled, it wakes up the caller, which could be for instance zswap,
waiting synchronously via crypto_wait_req().

Using the simple madvise test program in '[PATCH 08/15] crypto: iaa -
Add IAA Compression Accelerator Documentation' along with a set of
pages from the spec17 benchmark and tracepoint instrumentation
measuring the time taken between the start and end of each compress
and decompress, this case, async_irq, takes on average 6,847 ns for
compression and 5,840 ns for decompression. (See Table 1 below for a
summary of all the tests.)

When sync_mode is set to ‘sync’, the interrupt bit is not set and the
work descriptor is submitted in the same way it was for the previous
case.  In this case the call doesn’t return but rather loops around
waiting in the iaa_crypto driver’s check_completion() function which
continually checks the descriptor’s completion bit until it finds it
set to ‘completed’.  It then returns to the caller, again for example
zswap waiting in crypto_wait_req().  From the standpoint of zswap,
this case is exactly the same as the previous case, the difference
seen only in the crypto layer and the iaa_crypto driver internally;
from its standpoint they’re both synchronous calls.  There is however
a large performance difference: an average of 3,177 ns for compress
and 2,235 ns for decompress.

The final sync_mode is ‘async’.  In this case also the interrupt bit
is not set and the work descriptor is submitted, returning immediately
to the caller with -EINPROGRESS.  Because there’s no interrupt set to
notify anyone when the work completes, the caller needs to somehow
check for work completion.  Because core code like zswap can’t do this
directly by for example calling iaa_crypto’s check_completion(), there
would need to be some changes made to code like zswap and the crypto
layer in order to take advantage of this mode.  As such, there are no
numbers to share for this mode.

Finally, just a quick discussion of the remaining numbers in Table 1,
those comparing the iaa_crypto sync and async irq cases to software
deflate.  Software deflate took average of 108,978 ns for compress and
14,485 ns for decompress.

As can be seen from Table 1, the numbers using the iaa_crypto driver
for deflate as compared to software are so much better that merging it
would seem to make sense on its own merits.  The 'async' sync_mode
described above, however, offers the possibility of even greater gains
to be had against higher-performing algorithms such as lzo, via
parallelization, once the calling facilities are modified to take
advantage of it.  Follow-up patchsets to this one will demonstrate
concretely how that might be accomplished.

Thanks, 

Tom  


  Table 1. Zswap latency and compression numbers (in ns): 

  Algorithm                    compress      decompress
  ----------------------------------------------------------
  iaa sync			3,177		2,235
  iaa async irq   		6,847		5,840
  software deflate	      108,978	       14,485

[1] https://cdrdv2.intel.com/v1/dl/getContent/721858

[2] https://lore.kernel.org/lkml/20201107065332.26992-1-song.bao.hua@hisilicon.com/

Dave Jiang (2):
  dmaengine: idxd: add wq driver name support for accel-config user tool
  dmaengine: idxd: add external module driver support for dsa_bus_type

Tom Zanussi (13):
  dmaengine: idxd: Export drv_enable/disable and related functions
  dmaengine: idxd: Export descriptor management functions
  dmaengine: idxd: Export wq resource management functions
  dmaengine: idxd: Add private_data to struct idxd_wq
  dmaengine: idxd: add callback support for iaa crypto
  crypto: iaa - Add IAA Compression Accelerator Documentation
  crypto: iaa - Add Intel IAA Compression Accelerator crypto driver core
  crypto: iaa - Add per-cpu workqueue table with rebalancing
  crypto: iaa - Add compression mode management along with fixed mode
  crypto: iaa - Add support for iaa_crypto deflate compression algorithm
  crypto: iaa - Add support for default IAA 'canned' compression mode
  crypto: iaa - Add irq support for the crypto async interface
  crypto: iaa - Add IAA Compression Accelerator stats

 .../ABI/stable/sysfs-driver-dma-idxd          |    6 +
 .../driver-api/crypto/iaa/iaa-crypto.rst      |  581 +++++
 Documentation/driver-api/crypto/iaa/index.rst |   20 +
 Documentation/driver-api/crypto/index.rst     |   20 +
 Documentation/driver-api/index.rst            |    1 +
 MAINTAINERS                                   |    7 +
 crypto/testmgr.c                              |   10 +
 crypto/testmgr.h                              |   72 +
 drivers/crypto/Kconfig                        |    1 +
 drivers/crypto/Makefile                       |    1 +
 drivers/crypto/intel/Kconfig                  |    3 +
 drivers/crypto/intel/Makefile                 |    3 +
 drivers/crypto/intel/iaa/Kconfig              |   19 +
 drivers/crypto/intel/iaa/Makefile             |   12 +
 drivers/crypto/intel/iaa/iaa_crypto.h         |  172 ++
 .../crypto/intel/iaa/iaa_crypto_comp_canned.c |  110 +
 .../crypto/intel/iaa/iaa_crypto_comp_fixed.c  |   92 +
 drivers/crypto/intel/iaa/iaa_crypto_main.c    | 2041 +++++++++++++++++
 drivers/crypto/intel/iaa/iaa_crypto_stats.c   |  271 +++
 drivers/crypto/intel/iaa/iaa_crypto_stats.h   |   58 +
 drivers/dma/idxd/bus.c                        |    6 +
 drivers/dma/idxd/cdev.c                       |    8 +
 drivers/dma/idxd/device.c                     |    9 +-
 drivers/dma/idxd/dma.c                        |    9 +-
 drivers/dma/idxd/idxd.h                       |   74 +-
 drivers/dma/idxd/irq.c                        |   12 +-
 drivers/dma/idxd/submit.c                     |    9 +-
 drivers/dma/idxd/sysfs.c                      |   28 +
 include/uapi/linux/idxd.h                     |    1 +
 29 files changed, 3636 insertions(+), 20 deletions(-)
 create mode 100644 Documentation/driver-api/crypto/iaa/iaa-crypto.rst
 create mode 100644 Documentation/driver-api/crypto/iaa/index.rst
 create mode 100644 Documentation/driver-api/crypto/index.rst
 create mode 100644 drivers/crypto/intel/Kconfig
 create mode 100644 drivers/crypto/intel/Makefile
 create mode 100644 drivers/crypto/intel/iaa/Kconfig
 create mode 100644 drivers/crypto/intel/iaa/Makefile
 create mode 100644 drivers/crypto/intel/iaa/iaa_crypto.h
 create mode 100644 drivers/crypto/intel/iaa/iaa_crypto_comp_canned.c
 create mode 100644 drivers/crypto/intel/iaa/iaa_crypto_comp_fixed.c
 create mode 100644 drivers/crypto/intel/iaa/iaa_crypto_main.c
 create mode 100644 drivers/crypto/intel/iaa/iaa_crypto_stats.c
 create mode 100644 drivers/crypto/intel/iaa/iaa_crypto_stats.h

-- 
2.34.1


^ permalink raw reply	[flat|nested] 25+ messages in thread

* [PATCH v2 01/15] dmaengine: idxd: add wq driver name support for accel-config user tool
  2023-03-28 15:35 [PATCH v2 00/15] crypto: Add Intel Analytics Accelerator (IAA) crypto compression driver Tom Zanussi
@ 2023-03-28 15:35 ` Tom Zanussi
  2023-03-28 15:35 ` [PATCH v2 02/15] dmaengine: idxd: add external module driver support for dsa_bus_type Tom Zanussi
                   ` (14 subsequent siblings)
  15 siblings, 0 replies; 25+ messages in thread
From: Tom Zanussi @ 2023-03-28 15:35 UTC (permalink / raw)
  To: herbert, davem, fenghua.yu, vkoul
  Cc: dave.jiang, tony.luck, wajdi.k.feghali, james.guilford,
	kanchana.p.sridhar, giovanni.cabiddu, linux-kernel, linux-crypto,
	dmaengine

From: Dave Jiang <dave.jiang@intel.com>

With the possibility of multiple wq drivers that can be bound to the wq,
the user config tool accel-config needs a way to know which wq driver to
bind to the wq. Introduce per wq driver_name sysfs attribute where the user
can indicate the driver to be bound to the wq. This allows accel-config to
just bind to the driver using wq->driver_name.

Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
---
 .../ABI/stable/sysfs-driver-dma-idxd          |  6 ++++
 drivers/dma/idxd/cdev.c                       |  8 ++++++
 drivers/dma/idxd/dma.c                        |  6 ++++
 drivers/dma/idxd/idxd.h                       |  7 +++++
 drivers/dma/idxd/sysfs.c                      | 28 +++++++++++++++++++
 include/uapi/linux/idxd.h                     |  1 +
 6 files changed, 56 insertions(+)

diff --git a/Documentation/ABI/stable/sysfs-driver-dma-idxd b/Documentation/ABI/stable/sysfs-driver-dma-idxd
index 3becc9a82bdf..d5daae442fe7 100644
--- a/Documentation/ABI/stable/sysfs-driver-dma-idxd
+++ b/Documentation/ABI/stable/sysfs-driver-dma-idxd
@@ -244,6 +244,12 @@ Description:	Shows the operation capability bits displayed in bitmap format
 		correlates to the operations allowed. It's visible only
 		on platforms that support the capability.
 
+What:		/sys/bus/dsa/devices/wq<m>.<n>/driver_name
+Date:		Mar 27, 2023
+KernelVersion:	6.4.0
+Contact:	dmaengine@vger.kernel.org
+Description:	Name of driver to be bounded to the wq.
+
 What:           /sys/bus/dsa/devices/engine<m>.<n>/group_id
 Date:           Oct 25, 2019
 KernelVersion:  5.6.0
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index 674bfefca088..f3d1604e753d 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -304,6 +304,7 @@ void idxd_wq_del_cdev(struct idxd_wq *wq)
 
 static int idxd_user_drv_probe(struct idxd_dev *idxd_dev)
 {
+	struct device *dev = &idxd_dev->conf_dev;
 	struct idxd_wq *wq = idxd_dev_to_wq(idxd_dev);
 	struct idxd_device *idxd = wq->idxd;
 	int rc;
@@ -330,6 +331,13 @@ static int idxd_user_drv_probe(struct idxd_dev *idxd_dev)
 	}
 
 	mutex_lock(&wq->wq_lock);
+
+	if (!idxd_wq_driver_name_match(wq, dev)) {
+		idxd->cmd_status = IDXD_SCMD_WQ_NO_DRV_NAME;
+		rc = -ENODEV;
+		goto err;
+	}
+
 	wq->type = IDXD_WQT_USER;
 	rc = drv_enable_wq(wq);
 	if (rc < 0)
diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c
index eb35ca313684..8bb7e7ff8d6a 100644
--- a/drivers/dma/idxd/dma.c
+++ b/drivers/dma/idxd/dma.c
@@ -305,6 +305,12 @@ static int idxd_dmaengine_drv_probe(struct idxd_dev *idxd_dev)
 		return -ENXIO;
 
 	mutex_lock(&wq->wq_lock);
+	if (!idxd_wq_driver_name_match(wq, dev)) {
+		idxd->cmd_status = IDXD_SCMD_WQ_NO_DRV_NAME;
+		rc = -ENODEV;
+		goto err;
+	}
+
 	wq->type = IDXD_WQT_KERNEL;
 
 	rc = drv_enable_wq(wq);
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index 7ced8d283d98..505118fc19de 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -214,6 +214,8 @@ struct idxd_wq {
 	char name[WQ_NAME_SIZE + 1];
 	u64 max_xfer_bytes;
 	u32 max_batch_size;
+
+	char driver_name[WQ_NAME_SIZE + 1];
 };
 
 struct idxd_engine {
@@ -580,6 +582,11 @@ static inline void idxd_wqcfg_set_max_batch_shift(int idxd_type, union wqcfg *wq
 		wqcfg->max_batch_shift = max_batch_shift;
 }
 
+static inline int idxd_wq_driver_name_match(struct idxd_wq *wq, struct device *dev)
+{
+	return (strncmp(wq->driver_name, dev->driver->name, strlen(dev->driver->name)) == 0);
+}
+
 int __must_check __idxd_driver_register(struct idxd_device_driver *idxd_drv,
 					struct module *module, const char *mod_name);
 #define idxd_driver_register(driver) \
diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c
index 18cd8151dee0..cb5864c98d5a 100644
--- a/drivers/dma/idxd/sysfs.c
+++ b/drivers/dma/idxd/sysfs.c
@@ -1224,6 +1224,33 @@ static ssize_t wq_op_config_store(struct device *dev, struct device_attribute *a
 static struct device_attribute dev_attr_wq_op_config =
 		__ATTR(op_config, 0644, wq_op_config_show, wq_op_config_store);
 
+static ssize_t wq_driver_name_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct idxd_wq *wq = confdev_to_wq(dev);
+
+	return sysfs_emit(buf, "%s\n", wq->driver_name);
+}
+
+static ssize_t wq_driver_name_store(struct device *dev, struct device_attribute *attr,
+				    const char *buf, size_t count)
+{
+	struct idxd_wq *wq = confdev_to_wq(dev);
+
+	if (wq->state != IDXD_WQ_DISABLED)
+		return -EPERM;
+
+	if (strlen(buf) > WQ_NAME_SIZE || strlen(buf) == 0)
+		return -EINVAL;
+
+	memset(wq->driver_name, 0, WQ_NAME_SIZE + 1);
+	strncpy(wq->driver_name, buf, WQ_NAME_SIZE);
+	strreplace(wq->name, '\n', '\0');
+	return count;
+}
+
+static struct device_attribute dev_attr_wq_driver_name =
+		__ATTR(driver_name, 0644, wq_driver_name_show, wq_driver_name_store);
+
 static struct attribute *idxd_wq_attributes[] = {
 	&dev_attr_wq_clients.attr,
 	&dev_attr_wq_state.attr,
@@ -1242,6 +1269,7 @@ static struct attribute *idxd_wq_attributes[] = {
 	&dev_attr_wq_occupancy.attr,
 	&dev_attr_wq_enqcmds_retries.attr,
 	&dev_attr_wq_op_config.attr,
+	&dev_attr_wq_driver_name.attr,
 	NULL,
 };
 
diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h
index 1d553bedbdb5..2f85c8f59eb5 100644
--- a/include/uapi/linux/idxd.h
+++ b/include/uapi/linux/idxd.h
@@ -30,6 +30,7 @@ enum idxd_scmd_stat {
 	IDXD_SCMD_WQ_NO_PRIV = 0x800f0000,
 	IDXD_SCMD_WQ_IRQ_ERR = 0x80100000,
 	IDXD_SCMD_WQ_USER_NO_IOMMU = 0x80110000,
+	IDXD_SCMD_WQ_NO_DRV_NAME = 0x80200000,
 };
 
 #define IDXD_SCMD_SOFTERR_MASK	0x80000000
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH v2 02/15] dmaengine: idxd: add external module driver support for dsa_bus_type
  2023-03-28 15:35 [PATCH v2 00/15] crypto: Add Intel Analytics Accelerator (IAA) crypto compression driver Tom Zanussi
  2023-03-28 15:35 ` [PATCH v2 01/15] dmaengine: idxd: add wq driver name support for accel-config user tool Tom Zanussi
@ 2023-03-28 15:35 ` Tom Zanussi
  2023-03-28 15:35 ` [PATCH v2 03/15] dmaengine: idxd: Export drv_enable/disable and related functions Tom Zanussi
                   ` (13 subsequent siblings)
  15 siblings, 0 replies; 25+ messages in thread
From: Tom Zanussi @ 2023-03-28 15:35 UTC (permalink / raw)
  To: herbert, davem, fenghua.yu, vkoul
  Cc: dave.jiang, tony.luck, wajdi.k.feghali, james.guilford,
	kanchana.p.sridhar, giovanni.cabiddu, linux-kernel, linux-crypto,
	dmaengine

From: Dave Jiang <dave.jiang@intel.com>

Add support to allow an external driver to be registered to the
dsa_bus_type and also auto-loaded.

Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
---
 drivers/dma/idxd/bus.c  | 6 ++++++
 drivers/dma/idxd/idxd.h | 3 +++
 2 files changed, 9 insertions(+)

diff --git a/drivers/dma/idxd/bus.c b/drivers/dma/idxd/bus.c
index 6f84621053c6..0c9e689a2e77 100644
--- a/drivers/dma/idxd/bus.c
+++ b/drivers/dma/idxd/bus.c
@@ -67,11 +67,17 @@ static void idxd_config_bus_remove(struct device *dev)
 	idxd_drv->remove(idxd_dev);
 }
 
+static int idxd_bus_uevent(const struct device *dev, struct kobj_uevent_env *env)
+{
+	return add_uevent_var(env, "MODALIAS=" IDXD_DEVICES_MODALIAS_FMT, 0);
+}
+
 struct bus_type dsa_bus_type = {
 	.name = "dsa",
 	.match = idxd_config_bus_match,
 	.probe = idxd_config_bus_probe,
 	.remove = idxd_config_bus_remove,
+	.uevent = idxd_bus_uevent,
 };
 EXPORT_SYMBOL_GPL(dsa_bus_type);
 
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index 505118fc19de..719f9f1662ad 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -587,6 +587,9 @@ static inline int idxd_wq_driver_name_match(struct idxd_wq *wq, struct device *d
 	return (strncmp(wq->driver_name, dev->driver->name, strlen(dev->driver->name)) == 0);
 }
 
+#define MODULE_ALIAS_IDXD_DEVICE(type) MODULE_ALIAS("idxd:t" __stringify(type) "*")
+#define IDXD_DEVICES_MODALIAS_FMT "idxd:t%d"
+
 int __must_check __idxd_driver_register(struct idxd_device_driver *idxd_drv,
 					struct module *module, const char *mod_name);
 #define idxd_driver_register(driver) \
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH v2 03/15] dmaengine: idxd: Export drv_enable/disable and related functions
  2023-03-28 15:35 [PATCH v2 00/15] crypto: Add Intel Analytics Accelerator (IAA) crypto compression driver Tom Zanussi
  2023-03-28 15:35 ` [PATCH v2 01/15] dmaengine: idxd: add wq driver name support for accel-config user tool Tom Zanussi
  2023-03-28 15:35 ` [PATCH v2 02/15] dmaengine: idxd: add external module driver support for dsa_bus_type Tom Zanussi
@ 2023-03-28 15:35 ` Tom Zanussi
  2023-03-28 16:02   ` Dave Jiang
  2023-03-28 15:35 ` [PATCH v2 04/15] dmaengine: idxd: Export descriptor management functions Tom Zanussi
                   ` (12 subsequent siblings)
  15 siblings, 1 reply; 25+ messages in thread
From: Tom Zanussi @ 2023-03-28 15:35 UTC (permalink / raw)
  To: herbert, davem, fenghua.yu, vkoul
  Cc: dave.jiang, tony.luck, wajdi.k.feghali, james.guilford,
	kanchana.p.sridhar, giovanni.cabiddu, linux-kernel, linux-crypto,
	dmaengine

To allow idxd sub-drivers to enable and disable wqs, export them.

Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
---
 drivers/dma/idxd/device.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index 5f321f3b4242..af1aa88a66c1 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -1406,6 +1406,7 @@ int drv_enable_wq(struct idxd_wq *wq)
 err:
 	return rc;
 }
+EXPORT_SYMBOL_NS_GPL(drv_enable_wq, IDXD);
 
 void drv_disable_wq(struct idxd_wq *wq)
 {
@@ -1427,6 +1428,7 @@ void drv_disable_wq(struct idxd_wq *wq)
 	wq->type = IDXD_WQT_NONE;
 	wq->client_count = 0;
 }
+EXPORT_SYMBOL_NS_GPL(drv_disable_wq, IDXD);
 
 int idxd_device_drv_probe(struct idxd_dev *idxd_dev)
 {
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH v2 04/15] dmaengine: idxd: Export descriptor management functions
  2023-03-28 15:35 [PATCH v2 00/15] crypto: Add Intel Analytics Accelerator (IAA) crypto compression driver Tom Zanussi
                   ` (2 preceding siblings ...)
  2023-03-28 15:35 ` [PATCH v2 03/15] dmaengine: idxd: Export drv_enable/disable and related functions Tom Zanussi
@ 2023-03-28 15:35 ` Tom Zanussi
  2023-03-28 16:04   ` Dave Jiang
  2023-03-28 15:35 ` [PATCH v2 05/15] dmaengine: idxd: Export wq resource " Tom Zanussi
                   ` (11 subsequent siblings)
  15 siblings, 1 reply; 25+ messages in thread
From: Tom Zanussi @ 2023-03-28 15:35 UTC (permalink / raw)
  To: herbert, davem, fenghua.yu, vkoul
  Cc: dave.jiang, tony.luck, wajdi.k.feghali, james.guilford,
	kanchana.p.sridhar, giovanni.cabiddu, linux-kernel, linux-crypto,
	dmaengine

To allow idxd sub-drivers to access the descriptor management
functions, export them.

Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
---
 drivers/dma/idxd/submit.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c
index c01db23e3333..9d9ec0b76ccd 100644
--- a/drivers/dma/idxd/submit.c
+++ b/drivers/dma/idxd/submit.c
@@ -61,6 +61,7 @@ struct idxd_desc *idxd_alloc_desc(struct idxd_wq *wq, enum idxd_op_type optype)
 
 	return __get_desc(wq, idx, cpu);
 }
+EXPORT_SYMBOL_NS_GPL(idxd_alloc_desc, IDXD);
 
 void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 {
@@ -69,6 +70,7 @@ void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 	desc->cpu = -1;
 	sbitmap_queue_clear(&wq->sbq, desc->id, cpu);
 }
+EXPORT_SYMBOL_NS_GPL(idxd_free_desc, IDXD);
 
 static struct idxd_desc *list_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
 					 struct idxd_desc *desc)
@@ -215,3 +217,4 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 	percpu_ref_put(&wq->wq_active);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(idxd_submit_desc);
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH v2 05/15] dmaengine: idxd: Export wq resource management functions
  2023-03-28 15:35 [PATCH v2 00/15] crypto: Add Intel Analytics Accelerator (IAA) crypto compression driver Tom Zanussi
                   ` (3 preceding siblings ...)
  2023-03-28 15:35 ` [PATCH v2 04/15] dmaengine: idxd: Export descriptor management functions Tom Zanussi
@ 2023-03-28 15:35 ` Tom Zanussi
  2023-03-28 16:04   ` Dave Jiang
  2023-03-28 15:35 ` [PATCH v2 06/15] dmaengine: idxd: Add private_data to struct idxd_wq Tom Zanussi
                   ` (10 subsequent siblings)
  15 siblings, 1 reply; 25+ messages in thread
From: Tom Zanussi @ 2023-03-28 15:35 UTC (permalink / raw)
  To: herbert, davem, fenghua.yu, vkoul
  Cc: dave.jiang, tony.luck, wajdi.k.feghali, james.guilford,
	kanchana.p.sridhar, giovanni.cabiddu, linux-kernel, linux-crypto,
	dmaengine

To allow idxd sub-drivers to access the wq resource management
functions, export them.

Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
---
 drivers/dma/idxd/device.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index af1aa88a66c1..7837d0a56314 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -161,6 +161,7 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq)
 	free_hw_descs(wq);
 	return rc;
 }
+EXPORT_SYMBOL_NS_GPL(idxd_wq_alloc_resources, IDXD);
 
 void idxd_wq_free_resources(struct idxd_wq *wq)
 {
@@ -174,6 +175,7 @@ void idxd_wq_free_resources(struct idxd_wq *wq)
 	dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr);
 	sbitmap_queue_free(&wq->sbq);
 }
+EXPORT_SYMBOL_NS_GPL(idxd_wq_free_resources, IDXD);
 
 int idxd_wq_enable(struct idxd_wq *wq)
 {
@@ -422,6 +424,7 @@ int idxd_wq_init_percpu_ref(struct idxd_wq *wq)
 	reinit_completion(&wq->wq_resurrect);
 	return 0;
 }
+EXPORT_SYMBOL_NS_GPL(idxd_wq_init_percpu_ref, IDXD);
 
 void __idxd_wq_quiesce(struct idxd_wq *wq)
 {
@@ -431,6 +434,7 @@ void __idxd_wq_quiesce(struct idxd_wq *wq)
 	complete_all(&wq->wq_resurrect);
 	wait_for_completion(&wq->wq_dead);
 }
+EXPORT_SYMBOL_NS_GPL(__idxd_wq_quiesce, IDXD);
 
 void idxd_wq_quiesce(struct idxd_wq *wq)
 {
@@ -438,6 +442,7 @@ void idxd_wq_quiesce(struct idxd_wq *wq)
 	__idxd_wq_quiesce(wq);
 	mutex_unlock(&wq->wq_lock);
 }
+EXPORT_SYMBOL_NS_GPL(idxd_wq_quiesce, IDXD);
 
 /* Device control bits */
 static inline bool idxd_is_enabled(struct idxd_device *idxd)
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH v2 06/15] dmaengine: idxd: Add private_data to struct idxd_wq
  2023-03-28 15:35 [PATCH v2 00/15] crypto: Add Intel Analytics Accelerator (IAA) crypto compression driver Tom Zanussi
                   ` (4 preceding siblings ...)
  2023-03-28 15:35 ` [PATCH v2 05/15] dmaengine: idxd: Export wq resource " Tom Zanussi
@ 2023-03-28 15:35 ` Tom Zanussi
  2023-03-28 16:06   ` Dave Jiang
  2023-03-28 15:35 ` [PATCH v2 07/15] dmaengine: idxd: add callback support for iaa crypto Tom Zanussi
                   ` (9 subsequent siblings)
  15 siblings, 1 reply; 25+ messages in thread
From: Tom Zanussi @ 2023-03-28 15:35 UTC (permalink / raw)
  To: herbert, davem, fenghua.yu, vkoul
  Cc: dave.jiang, tony.luck, wajdi.k.feghali, james.guilford,
	kanchana.p.sridhar, giovanni.cabiddu, linux-kernel, linux-crypto,
	dmaengine

Add a void * to idxd_wqs for user-defined context data.

Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
---
 drivers/dma/idxd/idxd.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index 719f9f1662ad..e55213b5153e 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -216,6 +216,8 @@ struct idxd_wq {
 	u32 max_batch_size;
 
 	char driver_name[WQ_NAME_SIZE + 1];
+
+	void *private_data;
 };
 
 struct idxd_engine {
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH v2 07/15] dmaengine: idxd: add callback support for iaa crypto
  2023-03-28 15:35 [PATCH v2 00/15] crypto: Add Intel Analytics Accelerator (IAA) crypto compression driver Tom Zanussi
                   ` (5 preceding siblings ...)
  2023-03-28 15:35 ` [PATCH v2 06/15] dmaengine: idxd: Add private_data to struct idxd_wq Tom Zanussi
@ 2023-03-28 15:35 ` Tom Zanussi
  2023-03-28 15:35 ` [PATCH v2 08/15] crypto: iaa - Add IAA Compression Accelerator Documentation Tom Zanussi
                   ` (8 subsequent siblings)
  15 siblings, 0 replies; 25+ messages in thread
From: Tom Zanussi @ 2023-03-28 15:35 UTC (permalink / raw)
  To: herbert, davem, fenghua.yu, vkoul
  Cc: dave.jiang, tony.luck, wajdi.k.feghali, james.guilford,
	kanchana.p.sridhar, giovanni.cabiddu, linux-kernel, linux-crypto,
	dmaengine

Create a lightweight callback interface to allow idxd sub-drivers to
be notified when work sent to idxd wqs has completed.

For a sub-driver to be notified of work completion, it needs to:

  - Set the descriptor's 'Request Completion Interrupt'
    (IDXD_OP_FLAG_RCI)

  - Set the sub-driver desc_complete() callback when registering the
    sub-driver e.g.:

      struct idxd_device_driver my_drv = {
            .probe = my_probe,
            .desc_complete = my_complete,
      }

  - Set the sub-driver-specific context in the sub-driver's descriptor
    e.g:

      idxd_desc->crypto.req = req;
      idxd_desc->crypto.tfm = tfm;
      idxd_desc->crypto.src_addr = src_addr;
      idxd_desc->crypto.dst_addr = dst_addr;

When the work completes and the completion irq fires, idxd will invoke
the desc_complete() callback with pointers to the descriptor, context,
and completion_type.

Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
---
 drivers/dma/idxd/device.c |  2 +-
 drivers/dma/idxd/dma.c    |  3 +-
 drivers/dma/idxd/idxd.h   | 62 ++++++++++++++++++++++++++++++++-------
 drivers/dma/idxd/irq.c    | 12 ++++----
 drivers/dma/idxd/submit.c |  6 ++--
 5 files changed, 65 insertions(+), 20 deletions(-)

diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index 7837d0a56314..636451249046 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -1190,7 +1190,7 @@ static void idxd_flush_pending_descs(struct idxd_irq_entry *ie)
 		tx = &desc->txd;
 		tx->callback = NULL;
 		tx->callback_result = NULL;
-		idxd_dma_complete_txd(desc, ctype, true);
+		idxd_dma_complete_txd(desc, ctype, true, NULL, NULL);
 	}
 }
 
diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c
index 8bb7e7ff8d6a..9a12b02b0549 100644
--- a/drivers/dma/idxd/dma.c
+++ b/drivers/dma/idxd/dma.c
@@ -22,7 +22,7 @@ static inline struct idxd_wq *to_idxd_wq(struct dma_chan *c)
 
 void idxd_dma_complete_txd(struct idxd_desc *desc,
 			   enum idxd_complete_type comp_type,
-			   bool free_desc)
+			   bool free_desc, void *ctx, u32 *status)
 {
 	struct idxd_device *idxd = desc->wq->idxd;
 	struct dma_async_tx_descriptor *tx;
@@ -358,6 +358,7 @@ static enum idxd_dev_type dev_types[] = {
 struct idxd_device_driver idxd_dmaengine_drv = {
 	.probe = idxd_dmaengine_drv_probe,
 	.remove = idxd_dmaengine_drv_remove,
+	.desc_complete = idxd_dma_complete_txd,
 	.name = "dmaengine",
 	.type = dev_types,
 };
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index e55213b5153e..9b8d7043e79c 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -13,6 +13,7 @@
 #include <linux/ioasid.h>
 #include <linux/bitmap.h>
 #include <linux/perf_event.h>
+#include <linux/crypto.h>
 #include <uapi/linux/idxd.h>
 #include "registers.h"
 
@@ -56,11 +57,23 @@ enum idxd_type {
 #define IDXD_ENQCMDS_RETRIES		32
 #define IDXD_ENQCMDS_MAX_RETRIES	64
 
+enum idxd_complete_type {
+	IDXD_COMPLETE_NORMAL = 0,
+	IDXD_COMPLETE_ABORT,
+	IDXD_COMPLETE_DEV_FAIL,
+};
+
+struct idxd_desc;
+
 struct idxd_device_driver {
 	const char *name;
 	enum idxd_dev_type *type;
 	int (*probe)(struct idxd_dev *idxd_dev);
 	void (*remove)(struct idxd_dev *idxd_dev);
+	void (*desc_complete)(struct idxd_desc *desc,
+			      enum idxd_complete_type comp_type,
+			      bool free_desc,
+			      void *ctx, u32 *status);
 	struct device_driver drv;
 };
 
@@ -164,12 +177,6 @@ enum idxd_op_type {
 	IDXD_OP_NONBLOCK = 1,
 };
 
-enum idxd_complete_type {
-	IDXD_COMPLETE_NORMAL = 0,
-	IDXD_COMPLETE_ABORT,
-	IDXD_COMPLETE_DEV_FAIL,
-};
-
 struct idxd_dma_chan {
 	struct dma_chan chan;
 	struct idxd_wq *wq;
@@ -322,6 +329,14 @@ struct idxd_device {
 	unsigned long *opcap_bmap;
 };
 
+struct crypto_ctx {
+	struct acomp_req *req;
+	struct crypto_tfm *tfm;
+	dma_addr_t src_addr;
+	dma_addr_t dst_addr;
+	bool compress;
+};
+
 /* IDXD software descriptor */
 struct idxd_desc {
 	union {
@@ -334,7 +349,10 @@ struct idxd_desc {
 		struct iax_completion_record *iax_completion;
 	};
 	dma_addr_t compl_dma;
-	struct dma_async_tx_descriptor txd;
+	union {
+		struct dma_async_tx_descriptor txd;
+		struct crypto_ctx crypto;
+	};
 	struct llist_node llnode;
 	struct list_head list;
 	int id;
@@ -360,6 +378,15 @@ enum idxd_completion_status {
 #define idxd_dev_to_idxd(idxd_dev) container_of(idxd_dev, struct idxd_device, idxd_dev)
 #define idxd_dev_to_wq(idxd_dev) container_of(idxd_dev, struct idxd_wq, idxd_dev)
 
+static inline struct idxd_device_driver *wq_to_idxd_drv(struct idxd_wq *wq)
+{
+	struct device *dev = wq_confdev(wq);
+	struct idxd_device_driver *idxd_drv =
+		container_of(dev->driver, struct idxd_device_driver, drv);
+
+	return idxd_drv;
+}
+
 static inline struct idxd_device *confdev_to_idxd(struct device *dev)
 {
 	struct idxd_dev *idxd_dev = confdev_to_idxd_dev(dev);
@@ -602,6 +629,24 @@ void idxd_driver_unregister(struct idxd_device_driver *idxd_drv);
 #define module_idxd_driver(__idxd_driver) \
 	module_driver(__idxd_driver, idxd_driver_register, idxd_driver_unregister)
 
+void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc);
+void idxd_dma_complete_txd(struct idxd_desc *desc,
+			   enum idxd_complete_type comp_type,
+			   bool free_desc, void *ctx, u32 *status);
+
+static inline void idxd_desc_complete(struct idxd_desc *desc,
+				      enum idxd_complete_type comp_type,
+				      bool free_desc)
+{
+	struct idxd_device_driver *drv;
+	u32 status;
+
+	drv = wq_to_idxd_drv(desc->wq);
+	if (drv->desc_complete)
+		drv->desc_complete(desc, comp_type, free_desc,
+				   &desc->txd, &status);
+}
+
 int idxd_register_bus_type(void);
 void idxd_unregister_bus_type(void);
 int idxd_register_devices(struct idxd_device *idxd);
@@ -658,15 +703,12 @@ int idxd_wq_request_irq(struct idxd_wq *wq);
 /* submission */
 int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc);
 struct idxd_desc *idxd_alloc_desc(struct idxd_wq *wq, enum idxd_op_type optype);
-void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc);
 int idxd_enqcmds(struct idxd_wq *wq, void __iomem *portal, const void *desc);
 
 /* dmaengine */
 int idxd_register_dma_device(struct idxd_device *idxd);
 void idxd_unregister_dma_device(struct idxd_device *idxd);
 void idxd_parse_completion_status(u8 status, enum dmaengine_tx_result *res);
-void idxd_dma_complete_txd(struct idxd_desc *desc,
-			   enum idxd_complete_type comp_type, bool free_desc);
 
 /* cdev */
 int idxd_cdev_register(void);
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index aa314ebec587..3f89236c97c1 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -121,7 +121,7 @@ static void idxd_abort_invalid_int_handle_descs(struct idxd_irq_entry *ie)
 
 	list_for_each_entry_safe(d, t, &flist, list) {
 		list_del(&d->list);
-		idxd_dma_complete_txd(d, IDXD_COMPLETE_ABORT, true);
+		idxd_desc_complete(d, IDXD_COMPLETE_ABORT, true);
 	}
 }
 
@@ -376,7 +376,7 @@ static void idxd_int_handle_resubmit_work(struct work_struct *work)
 		 */
 		if (rc != -EAGAIN) {
 			desc->completion->status = IDXD_COMP_DESC_ABORT;
-			idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT, false);
+			idxd_desc_complete(desc, IDXD_COMPLETE_ABORT, false);
 		}
 		idxd_free_desc(wq, desc);
 	}
@@ -417,11 +417,11 @@ static void irq_process_pending_llist(struct idxd_irq_entry *irq_entry)
 			 * and 0xff, which DSA_COMP_STATUS_MASK can mask out.
 			 */
 			if (unlikely(desc->completion->status == IDXD_COMP_DESC_ABORT)) {
-				idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT, true);
+				idxd_desc_complete(desc, IDXD_COMPLETE_ABORT, true);
 				continue;
 			}
 
-			idxd_dma_complete_txd(desc, IDXD_COMPLETE_NORMAL, true);
+			idxd_desc_complete(desc, IDXD_COMPLETE_NORMAL, true);
 		} else {
 			spin_lock(&irq_entry->list_lock);
 			list_add_tail(&desc->list,
@@ -460,11 +460,11 @@ static void irq_process_work_list(struct idxd_irq_entry *irq_entry)
 		 * and 0xff, which DSA_COMP_STATUS_MASK can mask out.
 		 */
 		if (unlikely(desc->completion->status == IDXD_COMP_DESC_ABORT)) {
-			idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT, true);
+			idxd_desc_complete(desc, IDXD_COMPLETE_ABORT, true);
 			continue;
 		}
 
-		idxd_dma_complete_txd(desc, IDXD_COMPLETE_NORMAL, true);
+		idxd_desc_complete(desc, IDXD_COMPLETE_NORMAL, true);
 	}
 }
 
diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c
index 9d9ec0b76ccd..7ab37c349b2f 100644
--- a/drivers/dma/idxd/submit.c
+++ b/drivers/dma/idxd/submit.c
@@ -127,7 +127,8 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
 	spin_unlock(&ie->list_lock);
 
 	if (found)
-		idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, false);
+		idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, false,
+				      NULL, NULL);
 
 	/*
 	 * completing the descriptor will return desc to allocator and
@@ -137,7 +138,8 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
 	 */
 	list_for_each_entry_safe(d, t, &flist, list) {
 		list_del_init(&d->list);
-		idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, true);
+		idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, true,
+				      NULL, NULL);
 	}
 }
 
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH v2 08/15] crypto: iaa - Add IAA Compression Accelerator Documentation
  2023-03-28 15:35 [PATCH v2 00/15] crypto: Add Intel Analytics Accelerator (IAA) crypto compression driver Tom Zanussi
                   ` (6 preceding siblings ...)
  2023-03-28 15:35 ` [PATCH v2 07/15] dmaengine: idxd: add callback support for iaa crypto Tom Zanussi
@ 2023-03-28 15:35 ` Tom Zanussi
  2023-03-28 15:35 ` [PATCH v2 09/15] crypto: iaa - Add Intel IAA Compression Accelerator crypto driver core Tom Zanussi
                   ` (7 subsequent siblings)
  15 siblings, 0 replies; 25+ messages in thread
From: Tom Zanussi @ 2023-03-28 15:35 UTC (permalink / raw)
  To: herbert, davem, fenghua.yu, vkoul
  Cc: dave.jiang, tony.luck, wajdi.k.feghali, james.guilford,
	kanchana.p.sridhar, giovanni.cabiddu, linux-kernel, linux-crypto,
	dmaengine

Because the IAA Compression Accelerator requires significant user
setup in order to be used properly, this adds documentation on the
iaa_crypto driver including setup, usage, and examples.

Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
---
 .../driver-api/crypto/iaa/iaa-crypto.rst      | 581 ++++++++++++++++++
 Documentation/driver-api/crypto/iaa/index.rst |  20 +
 Documentation/driver-api/crypto/index.rst     |  20 +
 Documentation/driver-api/index.rst            |   1 +
 4 files changed, 622 insertions(+)
 create mode 100644 Documentation/driver-api/crypto/iaa/iaa-crypto.rst
 create mode 100644 Documentation/driver-api/crypto/iaa/index.rst
 create mode 100644 Documentation/driver-api/crypto/index.rst

diff --git a/Documentation/driver-api/crypto/iaa/iaa-crypto.rst b/Documentation/driver-api/crypto/iaa/iaa-crypto.rst
new file mode 100644
index 000000000000..442068778fb7
--- /dev/null
+++ b/Documentation/driver-api/crypto/iaa/iaa-crypto.rst
@@ -0,0 +1,581 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=========================================
+IAA Compression Accelerator Crypto Driver
+=========================================
+
+Tom Zanussi <tom.zanussi@linux.intel.com>
+
+The IAA crypto driver supports compression/decompression compatible
+with the DEFLATE compression standard described in RFC 1951, which is
+the compression/decompression algorithm exported by this module.
+
+The IAA hardware spec can be found here:
+
+  https://cdrdv2.intel.com/v1/dl/getContent/721858
+
+The iaa_crypto driver is designed to work as a layer underneath
+higher-level compression devices such as zswap.
+
+Users can select IAA compress/decompress acceleration by specifying
+'iaa_crypto' as the compression algorithm to use by whatever facility
+allows compression algorithms to be selected.
+
+For example, a zswap device can select iaa_crypto via::
+
+  # echo iaa_crypto > /sys/module/zswap/parameters/compressor
+
+
+Config options and other setup
+==============================
+
+The IAA crypto driver is available via menuconfig using the following
+path::
+
+  Cryptographic API -> Hardware crypto devices -> Support for Intel(R) IAA Compression Accelerator
+
+In the configuration file the option called CONFIG_CRYPTO_DEV_IAA_CRYPTO.
+
+The IAA crypto driver also supports statistics, which are available
+via menuconfig using the following path::
+
+  Cryptographic API -> Hardware crypto devices -> Support for Intel(R) IAA Compression -> Enable Intel(R) IAA Compression Accelerator Statistics
+
+In the configuration file the option called CONFIG_CRYPTO_DEV_IAA_CRYPTO_STATS.
+
+The following config options should also be enabled::
+
+  CONFIG_IRQ_REMAP=y
+  CONFIG_INTEL_IOMMU=y
+  CONFIG_INTEL_IOMMU_SVM=y
+  CONFIG_PCI_ATS=y
+  CONFIG_PCI_PRI=y
+  CONFIG_PCI_PASID=y
+  CONFIG_INTEL_IDXD=m
+  CONFIG_INTEL_IDXD_SVM=y
+
+IAA is one of the first Intel accelerator IPs that can work in
+conjunction with the Intel IOMMU.  There are multiple modes that exist
+for testing. Based on IOMMU configuration, there are 3 modes::
+
+  - Scalable
+  - Legacy
+  - No IOMMU
+
+
+Scalable mode
+-------------
+
+Scalable mode supports Shared Virtual Memory (SVM or SVA). It is
+entered when using the kernel boot commandline::
+
+  intel_iommu=on,sm_on
+
+with VT-d turned on in BIOS.
+
+With scalable mode, both shared and dedicated workqueues are available
+for use.
+
+For scalable mode, the following BIOS settings should be enabled::
+
+  Socket Configuration > IIO Configuration > Intel VT for Directed I/O (VT-d) > Intel VT for Directed I/O
+
+  Socket Configuration > IIO Configuration > PCIe ENQCMD > ENQCMDS
+
+
+Legacy mode
+-----------
+
+Legacy mode is entered when using the kernel boot commandline::
+
+  intel_iommu=off, intel_iommu=on
+
+or VT-d is not turned on in BIOS.
+
+If you have booted into Linux and not sure if VT-d is on, do a "dmesg
+| grep -i dmar". If you don't see a number of DMAR devices enumerated,
+most likely VT-d is not on.
+
+With legacy mode, only dedicated workqueues are available for use.
+
+
+No IOMMU mode
+-------------
+
+No IOMMU mode is entered when using the kernel boot commandline::
+
+  iommu=off.
+
+With no IOMMU mode, only dedicated workqueues are available for use.
+
+
+Usage
+=====
+
+accel-config
+------------
+
+Unlike typical drivers, the iaa_crypto driver does not enable the
+device on driver load.  Due to complexity and configurability of the
+accelerator devices, it was a design decision to have the user
+configure the device and manually enable the desired devices and
+workqueues.
+
+The userspace tool to help doing that is called accel-config.  Using
+accel-config to configure device or loading a previously saved config
+is highly recommended.  The device can be controlled via sysfs
+directly but comes with the warning that do this ONLY if you know
+exactly what you are doing.  This document will not cover the sysfs
+interface but assumes you will be using accel-config.
+
+The accel-config tool along with instructions for building it can be
+found here:
+
+  https://github.com/intel/idxd-config/#readme
+
+
+Typical usage
+-------------
+
+In order for the iaa_crypto module to actually do any
+compression/decompression work on behalf of a facility, one or more
+IAA workqueues need to be bound to the iaa_crypto driver.
+
+For instance, here's an example of configuring an IAA workqueue and
+binding it to the iaa_crypto driver (note that device names are
+specified as 'iax' rather than 'iaa' - this is because upstream still
+has the old 'iax' device naming in place) ::
+
+  # configure wq1.0
+
+  accel-config config-wq --group-id=0 --mode=dedicated --type=kernel --name="iaa_crypto" --device_name="crypto" iax1/wq1.0
+
+  # enable IAA device iax1
+
+  accel-config enable-device iax1
+
+  # enable wq1.0 on IAX device iax1
+
+  accel-config enable-wq iax1/wq1.0
+
+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.  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.
+
+The IAA crypto algorigthms is operational and compression and
+decompression operations are fully enabled following the successful
+binding of the first IAA workqueue to the iaa_crypto driver, and
+similarly, the IAA crypto algorithm is automatically unregistered when
+there are no IAA workqueues bound to the driver, following their
+removal.
+
+As a result, the iaa_crypto crypto algorithm and thus the IAA hardware
+are only available when one or more workques are bound to the
+iaa_crypto driver.
+
+Driver attributes
+-----------------
+
+There are a few user-configurable driver attributes that can be used
+to configure various modes of operation.  They're listed below, along
+with their default values.  To set any of these attributes, echo the
+appropriate values to the attribute file located under
+/sys/bus/dsa/drivers/crypto/
+
+  - verify_compress
+
+    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.
+
+  - compression_mode
+
+    Select compression mode to be used by all compresses and
+    decompresses.  There are a number ofcompression modes available,
+    each identified by a unique string.  These can be selected by
+    echoing the string to the 'compression_mode' driver attribute.
+    Currently, there are only two compression modes available,
+    'canned' and 'fixed' modes.
+
+    The 'fixed' compression mode implements the compression scheme
+    specified by RFC 1951.
+
+    The 'canned' compression mode implements a good general-purpose
+    compression scheme whose tables were generated from statistics
+    derived from a wide variety of SPEC17 workloads.  It provides much
+    better overall characteristics than the existing deflate-1951
+    tables implemented by 'fixed'.
+
+    Either 'fixed' or 'canned' modes can be chosen as the mode to be used
+    for compression/decompression via the iaa_crypto compression_mode
+    iaa_crypto driver attribute:
+
+      echo "canned" >  /sys/bus/dsa/drivers/crypto/compression_mode
+
+    The default setting is 'fixed'.
+
+  - sync_mode
+
+    Select mode to be used to wait for completion of each compresses
+    and decompress operation.
+
+    The crypto async interface support implemented by iaa_crypto
+    provides an implementation that satisfies the interface but does
+    so in a synchronous manner - it fills and submits the IDXD
+    descriptor and then loops around waiting 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.
+
+    The iaa_crypto driver does however provide true asynchronous
+    support for callers that can make use of it.  In this mode, it
+    fills and submits the IDXD descriptor, then returns immediately
+    with -EINPROGRESS.  The caller can then either poll for completion
+    itself, which requires specific code in the caller which currently
+    nothing in the upstream kernel implements, or go to sleep and wait
+    for an interrupt signaling completion.  This latter mode is
+    supported by current users in the kernel such as zswap via
+    synchronous wrappers.  Although it is supported this mode is
+    significantly slower than the synchronous mode that does the
+    polling in the iaa_crypto driver previously mentioned.
+
+    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 mode that does the polling in the iaa_crypto driver can be
+    enabled by writing 'sync' to it:
+
+      echo sync > /sys/bus/dsa/drivers/crypto/sync_mode
+
+    The default mode is 'sync'.
+
+
+Statistics
+==========
+
+If the optional debugfs statistics support is enabled, the IAA crypto
+driver will generate statistics which can be accessed in debugfs at::
+
+  # ls -al /sys/kernel/debug/iaa-crypto/
+  total 0
+  drwxr-xr-x  2 root root 0 Mar  3 09:35 .
+  drwx------ 47 root root 0 Mar  3 09:35 ..
+  -rw-r--r--  1 root root 0 Mar  3 09:35 max_acomp_delay_ns
+  -rw-r--r--  1 root root 0 Mar  3 09:35 max_adecomp_delay_ns
+  -rw-r--r--  1 root root 0 Mar  3 09:35 max_comp_delay_ns
+  -rw-r--r--  1 root root 0 Mar  3 09:35 max_decomp_delay_ns
+  -rw-r--r--  1 root root 0 Mar  3 09:35 stats_reset
+  -rw-r--r--  1 root root 0 Mar  3 09:35 total_comp_bytes_out
+  -rw-r--r--  1 root root 0 Mar  3 09:35 total_comp_calls
+  -rw-r--r--  1 root root 0 Mar  3 09:35 total_decomp_bytes_in
+  -rw-r--r--  1 root root 0 Mar  3 09:35 total_decomp_calls
+  -rw-r--r--  1 root root 0 Mar  3 09:35 wq_stats
+
+Most of the above statisticss are self-explanatory.  The wq_stats file
+shows per-wq stats, a set for each iaa device and wq in addition to
+some global stats::
+
+  # cat wq_stats
+  global stats:
+    total_comp_calls: 100
+    total_decomp_calls: 100
+    total_comp_bytes_out: 22800
+    total_decomp_bytes_in: 22800
+    total_completion_einval_errors: 0
+    total_completion_timeout_errors: 0
+    total_completion_comp_buf_overflow_errors: 0
+
+  iaa device:
+    id: 1
+    n_wqs: 1
+    comp_calls: 0
+    comp_bytes: 0
+    decomp_calls: 0
+    decomp_bytes: 0
+    wqs:
+      name: iaa_crypto
+      comp_calls: 0
+      comp_bytes: 0
+      decomp_calls: 0
+      decomp_bytes: 0
+
+  iaa device:
+    id: 3
+    n_wqs: 1
+    comp_calls: 0
+    comp_bytes: 0
+    decomp_calls: 0
+    decomp_bytes: 0
+    wqs:
+      name: iaa_crypto
+      comp_calls: 0
+      comp_bytes: 0
+      decomp_calls: 0
+      decomp_bytes: 0
+
+  iaa device:
+    id: 5
+    n_wqs: 1
+    comp_calls: 100
+    comp_bytes: 22800
+    decomp_calls: 100
+    decomp_bytes: 22800
+    wqs:
+      name: iaa_crypto
+      comp_calls: 100
+      comp_bytes: 22800
+      decomp_calls: 100
+      decomp_bytes: 22800
+
+Writing 0 to 'stats_reset' resets all the stats, including the
+per-device and per-wq stats::
+
+  # echo 0 > stats_reset
+  # cat wq_stats
+    global stats:
+    total_comp_calls: 0
+    total_decomp_calls: 0
+    total_comp_bytes_out: 0
+    total_decomp_bytes_in: 0
+    total_completion_einval_errors: 0
+    total_completion_timeout_errors: 0
+    total_completion_comp_buf_overflow_errors: 0
+    ...
+
+
+Use cases
+=========
+
+Simple zswap test
+-----------------
+
+For this example, the kernel should be configured according to the
+dedicated mode options described above, and zswap should be enabled as
+well::
+
+  CONFIG_ZSWAP=y
+
+This is a simple test that uses iaa_compress as the compressor for a
+swap (zswap) device.  It sets up the zswap device and then uses the
+memory_memadvise program listed below to forcibly swap out and in a
+specified number of pages, demonstrating both compress and decompress.
+
+The zswap test expects the work queues for each IAA device on the
+system to be configured properly as a kernel workqueue with a
+workqueue driver_name of "crypto".
+
+The first step is to make sure the iaa_crypto module is loaded::
+
+  modprobe iaa_crypto
+
+Following that the IAA device(s) should be configured and enabled.
+
+The zswap test expects the work queues for each IAA device on the
+system to be configured properly as a kernel workqueue with a
+workqueue driver_name of "crypto".
+
+The below script automatically does that::
+
+  #!/bin/bash
+
+  echo "IAA devices:"
+  lspci -d:0cfe
+  echo "# IAA devices:"
+  lspci -d:0cfe | wc -l
+
+  #
+  # count iaa instances
+  #
+  iaa_dev_id="0cfe"
+  num_iaa=$(lspci -d:${iaa_dev_id} | wc -l)
+  echo "Found ${num_iaa} IAA instances"
+
+  #
+  # disable iaa wqs and devices
+  #
+  echo "Disable IAA"
+
+  for ((i = 1; i < ${num_iaa} * 2; i += 2)); do
+      echo disable wq iax${i}/wq${i}.0
+      accel-config disable-wq iax${i}/wq${i}.0
+      echo disable iaa iax${i}
+      accel-config disable-device iax${i}
+  done
+
+  echo "End Disable IAA"
+
+  #
+  # configure iaa wqs and devices
+  #
+  echo "Configure IAA"
+  for ((i = 1; i < ${num_iaa} * 2; i += 2)); do
+      accel-config config-wq --group-id=0 --mode=dedicated --size=128 --priority=10 --type=kernel --name="iaa_crypto" --driver_name="crypto" iax${i}/wq${i}
+  done
+
+  echo "End Configure IAA"
+
+  #
+  # enable iaa wqs and devices
+  #
+  echo "Enable IAA"
+
+  for ((i = 1; i < ${num_iaa} * 2; i += 2)); do
+      echo enable iaa iaa${i}
+      accel-config enable-device iaa${i}
+      echo enable wq iaa${i}/wq${i}.0
+      accel-config enable-wq iaa${i}/wq${i}.0
+  done
+
+  echo "End Enable IAA"
+
+When the workqueues are bound to the iaa_crypto driver, you should
+see something similar to the following in dmesg output if you've
+enabled debug output (echo -n 'module iaa_crypto +p' >
+/sys/kernel/debug/dynamic_debug/control)::
+
+  [   60.752344] idxd 0000:f6:02.0: add_iaa_wq: added wq 000000004068d14d to iaa 00000000c9585ba2, n_wq 1
+  [   60.752346] iaa_crypto: rebalance_wq_table: nr_nodes=2, nr_cpus 160, nr_iaa 8, cpus_per_iaa 20
+  [   60.752347] iaa_crypto: rebalance_wq_table: iaa=0
+  [   60.752349] idxd 0000:6a:02.0: request_iaa_wq: getting wq from iaa_device 0000000042d7bc52 (0)
+  [   60.752350] idxd 0000:6a:02.0: request_iaa_wq: returning unused wq 00000000c8bb4452 (0) from iaa device 0000000042d7bc52 (0)
+  [   60.752352] iaa_crypto: rebalance_wq_table: assigned wq for cpu=0, node=0 = wq 00000000c8bb4452
+  [   60.752354] iaa_crypto: rebalance_wq_table: iaa=0
+  [   60.752355] idxd 0000:6a:02.0: request_iaa_wq: getting wq from iaa_device 0000000042d7bc52 (0)
+  [   60.752356] idxd 0000:6a:02.0: request_iaa_wq: returning unused wq 00000000c8bb4452 (0) from iaa device 0000000042d7bc52 (0)
+  [   60.752358] iaa_crypto: rebalance_wq_table: assigned wq for cpu=1, node=0 = wq 00000000c8bb4452
+  [   60.752359] iaa_crypto: rebalance_wq_table: iaa=0
+  [   60.752360] idxd 0000:6a:02.0: request_iaa_wq: getting wq from iaa_device 0000000042d7bc52 (0)
+  [   60.752361] idxd 0000:6a:02.0: request_iaa_wq: returning unused wq 00000000c8bb4452 (0) from iaa device 0000000042d7bc52 (0)
+  [   60.752362] iaa_crypto: rebalance_wq_table: assigned wq for cpu=2, node=0 = wq 00000000c8bb4452
+  [   60.752364] iaa_crypto: rebalance_wq_table: iaa=0
+  .
+  .
+  .
+
+Once the workqueues and devices have been enabled, the iaa_crypto
+algorithm is enabled and available.  When the iaa_crypto algorithm has
+been successfully enabled, you should see the following dmesg output::
+
+  [   64.893759] iaa_crypto: iaa_crypto_enable: iaa_crypto now ENABLED
+
+Now run the following zswap-specific setup commands::
+
+  echo 0 > /sys/module/zswap/parameters/enabled
+  echo 50 > /sys/module/zswap/parameters/max_pool_percent
+  echo iaa_crypto > /sys/module/zswap/parameters/compressor
+  echo zsmalloc > /sys/module/zswap/parameters/zpool
+  echo 1 > /sys/module/zswap/parameters/enabled
+  echo 0 > /sys/module/zswap/parameters/same_filled_pages_enabled
+
+  echo 100 > /proc/sys/vm/swappiness
+  echo never > /sys/kernel/mm/transparent_hugepage/enabled
+  echo 1 > /proc/sys/vm/overcommit_memory
+
+Finally, you can now run the zswap workload you want to measure. For
+example, using the code below, the following command will swap in and
+out 100 pages::
+
+  ./memory_madvise 100
+
+  Allocating 100 pages to swap in/out
+  Swapping out 100 pages
+  Swapping in 100 pages
+  Swapped out and in 100 pages
+
+You should see something like the following in the dmesg output if
+you've enabled debug output (echo -n 'module iaa_crypto +p' >
+/sys/kernel/debug/dynamic_debug/control)::
+
+  [  404.202972] idxd 0000:e7:02.0: iaa_comp_acompress: dma_map_sg, src_addr 223925c000, nr_sgs 1, req->src 00000000ee7cb5e6, req->slen 4096, sg_dma_len(sg) 4096
+  [  404.202973] idxd 0000:e7:02.0: iaa_comp_acompress: dma_map_sg, dst_addr 21dadf8000, nr_sgs 1, req->dst 000000008d6acea8, req->dlen 4096, sg_dma_len(sg) 8192
+  [  404.202975] idxd 0000:e7:02.0: iaa_compress: desc->src1_addr 223925c000, desc->src1_size 4096, desc->dst_addr 21dadf8000, desc->max_dst_size 4096, desc->src2_addr 2203543000, desc->src2_size 1568
+  [  404.202981] idxd 0000:e7:02.0: iaa_compress_verify: (verify) desc->src1_addr 21dadf8000, desc->src1_size 228, desc->dst_addr 223925c000, desc->max_dst_size 4096, desc->src2_addr 0, desc->src2_size 0
+  [  409.203227] idxd 0000:e7:02.0: iaa_comp_adecompress: dma_map_sg, src_addr 21ddd8b100, nr_sgs 1, req->src 0000000084adab64, req->slen 228, sg_dma_len(sg) 228
+  [  409.203235] idxd 0000:e7:02.0: iaa_comp_adecompress: dma_map_sg, dst_addr 21ee3dc000, nr_sgs 1, req->dst 000000004e2990d0, req->dlen 4096, sg_dma_len(sg) 4096
+  [  409.203239] idxd 0000:e7:02.0: iaa_decompress: desc->src1_addr 21ddd8b100, desc->src1_size 228, desc->dst_addr 21ee3dc000, desc->max_dst_size 4096, desc->src2_addr 0, desc->src2_size 0
+  [  409.203254] idxd 0000:e7:02.0: iaa_comp_adecompress: dma_map_sg, src_addr 21ddd8b100, nr_sgs 1, req->src 0000000084adab64, req->slen 228, sg_dma_len(sg) 228
+  [  409.203256] idxd 0000:e7:02.0: iaa_comp_adecompress: dma_map_sg, dst_addr 21f1551000, nr_sgs 1, req->dst 000000004e2990d0, req->dlen 4096, sg_dma_len(sg) 4096
+  [  409.203257] idxd 0000:e7:02.0: iaa_decompress: desc->src1_addr 21ddd8b100, desc->src1_size 228, desc->dst_addr 21f1551000, desc->max_dst_size 4096, desc->src2_addr 0, desc->src2_size 0
+
+memory_madvise.c (gcc -o memory_memadvise memory_madvise.c)::
+
+  #include <stdio.h>
+  #include <stdlib.h>
+  #include <string.h>
+  #include <unistd.h>
+  #include <sys/mman.h>
+  #include <linux/mman.h>
+
+  #ifndef MADV_PAGEOUT
+  #define MADV_PAGEOUT    21      /* force pages out immediately */
+  #endif
+
+  #define PG_SZ           4096
+
+  int main(int argc, char **argv)
+  {
+        int i, nr_pages = 1;
+        int64_t *dump_ptr;
+        char *addr, *a;
+        int loop = 1;
+
+        if (argc > 1)
+                nr_pages = atoi(argv[1]);
+
+        printf("Allocating %d pages to swap in/out\n", nr_pages);
+
+        /* allocate pages */
+        addr = mmap(NULL, nr_pages * PG_SZ, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+        *addr = 1;
+
+        /* initialize data in page to all '*' chars */
+        memset(addr, '*', nr_pages * PG_SZ);
+
+         printf("Swapping out %d pages\n", nr_pages);
+
+        /* Tell kernel to swap it out */
+        madvise(addr, nr_pages * PG_SZ, MADV_PAGEOUT);
+
+        while (loop > 0) {
+                /* Wait for swap out to finish */
+                sleep(5);
+
+                a = addr;
+
+                printf("Swapping in %d pages\n", nr_pages);
+
+                /* Access the page ... this will swap it back in again */
+                for (i = 0; i < nr_pages; i++) {
+                        if (a[0] != '*') {
+                                printf("Bad data from decompress!!!!!\n");
+
+                                dump_ptr = (int64_t *)a;
+                                 for (int j = 0; j < 100; j++) {
+                                        printf("  page %d data: %#llx\n", i, *dump_ptr);
+                                        dump_ptr++;
+                                }
+                        }
+
+                        a += PG_SZ;
+                }
+
+                loop --;
+        }
+
+       printf("Swapped out and in %d pages\n", nr_pages);
diff --git a/Documentation/driver-api/crypto/iaa/index.rst b/Documentation/driver-api/crypto/iaa/index.rst
new file mode 100644
index 000000000000..aa6837e27264
--- /dev/null
+++ b/Documentation/driver-api/crypto/iaa/index.rst
@@ -0,0 +1,20 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=================================
+IAA (Intel Analytics Accelerator)
+=================================
+
+IAA provides hardware compression and decompression via the crypto
+API.
+
+.. toctree::
+   :maxdepth: 1
+
+   iaa-crypto
+
+.. only::  subproject and html
+
+   Indices
+   =======
+
+   * :ref:`genindex`
diff --git a/Documentation/driver-api/crypto/index.rst b/Documentation/driver-api/crypto/index.rst
new file mode 100644
index 000000000000..fb9709b98bea
--- /dev/null
+++ b/Documentation/driver-api/crypto/index.rst
@@ -0,0 +1,20 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============
+Crypto Drivers
+==============
+
+Documentation for crypto drivers that may need more involved setup and
+configuration.
+
+.. toctree::
+   :maxdepth: 1
+
+   iaa/index
+
+.. only::  subproject and html
+
+   Indices
+   =======
+
+   * :ref:`genindex`
diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst
index ff9aa1afdc62..2ad1237d5d5f 100644
--- a/Documentation/driver-api/index.rst
+++ b/Documentation/driver-api/index.rst
@@ -113,6 +113,7 @@ available subsections can be seen below.
    xillybus
    zorro
    hte/index
+   crypto/index
 
 .. only::  subproject and html
 
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH v2 09/15] crypto: iaa - Add Intel IAA Compression Accelerator crypto driver core
  2023-03-28 15:35 [PATCH v2 00/15] crypto: Add Intel Analytics Accelerator (IAA) crypto compression driver Tom Zanussi
                   ` (7 preceding siblings ...)
  2023-03-28 15:35 ` [PATCH v2 08/15] crypto: iaa - Add IAA Compression Accelerator Documentation Tom Zanussi
@ 2023-03-28 15:35 ` Tom Zanussi
  2023-03-28 15:35 ` [PATCH v2 10/15] crypto: iaa - Add per-cpu workqueue table with rebalancing Tom Zanussi
                   ` (6 subsequent siblings)
  15 siblings, 0 replies; 25+ messages in thread
From: Tom Zanussi @ 2023-03-28 15:35 UTC (permalink / raw)
  To: herbert, davem, fenghua.yu, vkoul
  Cc: dave.jiang, tony.luck, wajdi.k.feghali, james.guilford,
	kanchana.p.sridhar, giovanni.cabiddu, linux-kernel, linux-crypto,
	dmaengine

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
'iaa_crypto' as the compression algorithm to use by whatever facility
allows asynchronous compression algorithms to be selected.

For example, zswap can select iaa_crypto via:

  # echo iaa_crypto > /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>
---
 MAINTAINERS                                |   7 +
 drivers/crypto/Kconfig                     |   1 +
 drivers/crypto/Makefile                    |   1 +
 drivers/crypto/intel/Kconfig               |   3 +
 drivers/crypto/intel/Makefile              |   3 +
 drivers/crypto/intel/iaa/Kconfig           |  10 +
 drivers/crypto/intel/iaa/Makefile          |  10 +
 drivers/crypto/intel/iaa/iaa_crypto.h      |  30 ++
 drivers/crypto/intel/iaa/iaa_crypto_main.c | 326 +++++++++++++++++++++
 9 files changed, 391 insertions(+)
 create mode 100644 drivers/crypto/intel/Kconfig
 create mode 100644 drivers/crypto/intel/Makefile
 create mode 100644 drivers/crypto/intel/iaa/Kconfig
 create mode 100644 drivers/crypto/intel/iaa/Makefile
 create mode 100644 drivers/crypto/intel/iaa/iaa_crypto.h
 create mode 100644 drivers/crypto/intel/iaa/iaa_crypto_main.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 1dc8bd26b6cf..2db8b4940de8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10313,6 +10313,13 @@ S:	Supported
 Q:	https://patchwork.kernel.org/project/linux-dmaengine/list/
 F:	drivers/dma/ioat*
 
+INTEL IAA CRYPTO DRIVER
+M:	Tom Zanussi <tom.zanussi@linux.intel.com>
+L:	linux-crypto@vger.kernel.org
+S:	Supported
+F:	Documentation/driver-api/crypto/iaa/iaa-crypto.rst
+F:	drivers/crypto/intel/iaa/*
+
 INTEL IDXD DRIVER
 M:	Fenghua Yu <fenghua.yu@intel.com>
 M:	Dave Jiang <dave.jiang@intel.com>
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 3b2516d1433f..56466eeb4eef 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -506,6 +506,7 @@ source "drivers/crypto/qat/Kconfig"
 source "drivers/crypto/cavium/cpt/Kconfig"
 source "drivers/crypto/cavium/nitrox/Kconfig"
 source "drivers/crypto/marvell/Kconfig"
+source "drivers/crypto/intel/Kconfig"
 
 config CRYPTO_DEV_CAVIUM_ZIP
 	tristate "Cavium ZIP driver"
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index 476f1a25ca32..34c1e60d9dd1 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -52,3 +52,4 @@ obj-y += xilinx/
 obj-y += hisilicon/
 obj-$(CONFIG_CRYPTO_DEV_AMLOGIC_GXL) += amlogic/
 obj-y += keembay/
+obj-y += intel/
diff --git a/drivers/crypto/intel/Kconfig b/drivers/crypto/intel/Kconfig
new file mode 100644
index 000000000000..7c9f51b873ea
--- /dev/null
+++ b/drivers/crypto/intel/Kconfig
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+
+source "drivers/crypto/intel/iaa/Kconfig"
diff --git a/drivers/crypto/intel/Makefile b/drivers/crypto/intel/Makefile
new file mode 100644
index 000000000000..b1263f1f90cc
--- /dev/null
+++ b/drivers/crypto/intel/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_CRYPTO_DEV_IAA_CRYPTO) += iaa/
diff --git a/drivers/crypto/intel/iaa/Kconfig b/drivers/crypto/intel/iaa/Kconfig
new file mode 100644
index 000000000000..fcccb6ff7e29
--- /dev/null
+++ b/drivers/crypto/intel/iaa/Kconfig
@@ -0,0 +1,10 @@
+config CRYPTO_DEV_IAA_CRYPTO
+	tristate "Support for Intel(R) IAA Compression Accelerator"
+	depends on CRYPTO_DEFLATE
+	depends on INTEL_IDXD
+	default n
+	help
+	  This driver supports acceleration for compression and
+	  decompression with the Intel Analytics Accelerator (IAA)
+	  hardware using the cryptographic API.  If you choose 'M'
+	  here, the module will be called iaa_crypto.
diff --git a/drivers/crypto/intel/iaa/Makefile b/drivers/crypto/intel/iaa/Makefile
new file mode 100644
index 000000000000..03859431c897
--- /dev/null
+++ b/drivers/crypto/intel/iaa/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for IAA crypto device drivers
+#
+
+ccflags-y += -I $(srctree)/drivers/dma/idxd -DDEFAULT_SYMBOL_NAMESPACE=IDXD
+
+obj-$(CONFIG_CRYPTO_DEV_IAA_CRYPTO) := iaa_crypto.o
+
+iaa_crypto-y := iaa_crypto_main.o
diff --git a/drivers/crypto/intel/iaa/iaa_crypto.h b/drivers/crypto/intel/iaa/iaa_crypto.h
new file mode 100644
index 000000000000..5d1fff7f4b8e
--- /dev/null
+++ b/drivers/crypto/intel/iaa/iaa_crypto.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2021 Intel Corporation. All rights rsvd. */
+
+#ifndef __IAA_CRYPTO_H__
+#define __IAA_CRYPTO_H__
+
+#include <linux/crypto.h>
+#include <linux/idxd.h>
+#include <uapi/linux/idxd.h>
+
+#define IDXD_SUBDRIVER_NAME		"crypto"
+
+/* Representation of IAA workqueue */
+struct iaa_wq {
+	struct list_head	list;
+	struct idxd_wq		*wq;
+
+	struct iaa_device	*iaa_device;
+};
+
+/* Representation of IAA device with wqs, populated by probe */
+struct iaa_device {
+	struct list_head		list;
+	struct idxd_device		*idxd;
+
+	int				n_wq;
+	struct list_head		wqs;
+};
+
+#endif
diff --git a/drivers/crypto/intel/iaa/iaa_crypto_main.c b/drivers/crypto/intel/iaa/iaa_crypto_main.c
new file mode 100644
index 000000000000..c35a778d53a6
--- /dev/null
+++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c
@@ -0,0 +1,326 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2021 Intel Corporation. All rights rsvd. */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/device.h>
+#include <linux/iommu.h>
+#include <uapi/linux/idxd.h>
+#include <linux/highmem.h>
+#include <linux/sched/smt.h>
+
+#include "idxd.h"
+#include "iaa_crypto.h"
+
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt)			"idxd: " IDXD_SUBDRIVER_NAME ": " fmt
+
+/* number of iaa instances probed */
+static unsigned int nr_iaa;
+
+static LIST_HEAD(iaa_devices);
+static DEFINE_MUTEX(iaa_devices_lock);
+
+static struct iaa_device *iaa_device_alloc(void)
+{
+	struct iaa_device *iaa_device;
+
+	iaa_device = kzalloc(sizeof(*iaa_device), GFP_KERNEL);
+	if (!iaa_device)
+		return NULL;
+
+	INIT_LIST_HEAD(&iaa_device->wqs);
+
+	return iaa_device;
+}
+
+static void iaa_device_free(struct iaa_device *iaa_device)
+{
+	struct iaa_wq *iaa_wq, *next;
+
+	list_for_each_entry_safe(iaa_wq, next, &iaa_device->wqs, list) {
+		list_del(&iaa_wq->list);
+		kfree(iaa_wq);
+	}
+
+	kfree(iaa_device);
+}
+
+static bool iaa_has_wq(struct iaa_device *iaa_device, struct idxd_wq *wq)
+{
+	struct iaa_wq *iaa_wq;
+
+	list_for_each_entry(iaa_wq, &iaa_device->wqs, list) {
+		if (iaa_wq->wq == wq)
+			return true;
+	}
+
+	return false;
+}
+
+static struct iaa_device *add_iaa_device(struct idxd_device *idxd)
+{
+	struct iaa_device *iaa_device;
+
+	iaa_device = iaa_device_alloc();
+	if (!iaa_device)
+		return NULL;
+
+	iaa_device->idxd = idxd;
+
+	list_add_tail(&iaa_device->list, &iaa_devices);
+
+	nr_iaa++;
+
+	return iaa_device;
+}
+
+static void del_iaa_device(struct iaa_device *iaa_device)
+{
+	list_del(&iaa_device->list);
+
+	iaa_device_free(iaa_device);
+
+	nr_iaa--;
+}
+
+static int add_iaa_wq(struct iaa_device *iaa_device, struct idxd_wq *wq,
+		      struct iaa_wq **new_wq)
+{
+	struct idxd_device *idxd = iaa_device->idxd;
+	struct pci_dev *pdev = idxd->pdev;
+	struct device *dev = &pdev->dev;
+	struct iaa_wq *iaa_wq;
+
+	iaa_wq = kzalloc(sizeof(*iaa_wq), GFP_KERNEL);
+	if (!iaa_wq)
+		return -ENOMEM;
+
+	iaa_wq->wq = wq;
+	iaa_wq->iaa_device = iaa_device;
+	wq->private_data = iaa_wq;
+
+	list_add_tail(&iaa_wq->list, &iaa_device->wqs);
+
+	iaa_device->n_wq++;
+
+	if (new_wq)
+		*new_wq = iaa_wq;
+
+	dev_dbg(dev, "added wq %d to iaa device %d, n_wq %d\n",
+		wq->id, iaa_device->idxd->id, iaa_device->n_wq);
+
+	return 0;
+}
+
+static void del_iaa_wq(struct iaa_device *iaa_device, struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = iaa_device->idxd;
+	struct pci_dev *pdev = idxd->pdev;
+	struct device *dev = &pdev->dev;
+	struct iaa_wq *iaa_wq;
+
+	list_for_each_entry(iaa_wq, &iaa_device->wqs, list) {
+		if (iaa_wq->wq == wq) {
+			list_del(&iaa_wq->list);
+			iaa_device->n_wq--;
+
+			dev_dbg(dev, "removed wq %d from iaa_device %d, n_wq %d, nr_iaa %d\n",
+				wq->id, iaa_device->idxd->id,
+				iaa_device->n_wq, nr_iaa);
+
+			if (iaa_device->n_wq == 0)
+				del_iaa_device(iaa_device);
+			break;
+		}
+	}
+}
+
+static int save_iaa_wq(struct idxd_wq *wq)
+{
+	struct iaa_device *iaa_device, *found = NULL;
+	struct idxd_device *idxd;
+	struct pci_dev *pdev;
+	struct device *dev;
+	int ret = 0;
+
+	list_for_each_entry(iaa_device, &iaa_devices, list) {
+		if (iaa_device->idxd == wq->idxd) {
+			idxd = iaa_device->idxd;
+			pdev = idxd->pdev;
+			dev = &pdev->dev;
+			/*
+			 * Check to see that we don't already have this wq.
+			 * Shouldn't happen but we don't control probing.
+			 */
+			if (iaa_has_wq(iaa_device, wq)) {
+				dev_dbg(dev, "same wq probed multiple times for iaa_device %p\n",
+					iaa_device);
+				goto out;
+			}
+
+			found = iaa_device;
+
+			ret = add_iaa_wq(iaa_device, wq, NULL);
+			if (ret)
+				goto out;
+
+			break;
+		}
+	}
+
+	if (!found) {
+		struct iaa_device *new_device;
+		struct iaa_wq *new_wq;
+
+		new_device = add_iaa_device(wq->idxd);
+		if (!new_device) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		ret = add_iaa_wq(new_device, wq, &new_wq);
+		if (ret) {
+			del_iaa_device(new_device);
+			goto out;
+		}
+	}
+
+	if (WARN_ON(nr_iaa == 0))
+		return -EINVAL;
+
+	idxd_wq_get(wq);
+out:
+	return 0;
+}
+
+static void remove_iaa_wq(struct idxd_wq *wq)
+{
+	struct iaa_device *iaa_device;
+
+	list_for_each_entry(iaa_device, &iaa_devices, list) {
+		if (iaa_has_wq(iaa_device, wq)) {
+			del_iaa_wq(iaa_device, wq);
+			idxd_wq_put(wq);
+			break;
+		}
+	}
+}
+
+static int iaa_crypto_probe(struct idxd_dev *idxd_dev)
+{
+	struct idxd_wq *wq = idxd_dev_to_wq(idxd_dev);
+	struct idxd_device *idxd = wq->idxd;
+	struct idxd_driver_data *data = idxd->data;
+	struct device *dev = &idxd_dev->conf_dev;
+	int ret = 0;
+
+	if (idxd->state != IDXD_DEV_ENABLED)
+		return -ENXIO;
+
+	if (data->type != IDXD_TYPE_IAX)
+		return -ENODEV;
+
+	mutex_lock(&wq->wq_lock);
+
+	if (!idxd_wq_driver_name_match(wq, dev)) {
+		dev_dbg(dev, "wq %d.%d driver_name match failed: wq driver_name %s, dev driver name %s\n",
+			idxd->id, wq->id, wq->driver_name, dev->driver->name);
+		idxd->cmd_status = IDXD_SCMD_WQ_NO_DRV_NAME;
+		ret = -ENODEV;
+		goto err;
+	}
+
+	wq->type = IDXD_WQT_KERNEL;
+
+	ret = drv_enable_wq(wq);
+	if (ret < 0) {
+		dev_dbg(dev, "enable wq %d.%d failed: %d\n",
+			idxd->id, wq->id, ret);
+		ret = -ENXIO;
+		goto err;
+	}
+
+	mutex_lock(&iaa_devices_lock);
+
+	ret = save_iaa_wq(wq);
+	if (ret)
+		goto err_save;
+
+	mutex_unlock(&iaa_devices_lock);
+out:
+	mutex_unlock(&wq->wq_lock);
+
+	return ret;
+
+err_save:
+	drv_disable_wq(wq);
+err:
+	wq->type = IDXD_WQT_NONE;
+
+	goto out;
+}
+
+static void iaa_crypto_remove(struct idxd_dev *idxd_dev)
+{
+	struct idxd_wq *wq = idxd_dev_to_wq(idxd_dev);
+
+	idxd_wq_quiesce(wq);
+
+	mutex_lock(&wq->wq_lock);
+	mutex_lock(&iaa_devices_lock);
+
+	remove_iaa_wq(wq);
+	drv_disable_wq(wq);
+
+	mutex_unlock(&iaa_devices_lock);
+	mutex_unlock(&wq->wq_lock);
+}
+
+static enum idxd_dev_type dev_types[] = {
+	IDXD_DEV_WQ,
+	IDXD_DEV_NONE,
+};
+
+static struct idxd_device_driver iaa_crypto_driver = {
+	.probe = iaa_crypto_probe,
+	.remove = iaa_crypto_remove,
+	.name = IDXD_SUBDRIVER_NAME,
+	.type = dev_types,
+};
+
+static int __init iaa_crypto_init_module(void)
+{
+	int ret = 0;
+
+	ret = idxd_driver_register(&iaa_crypto_driver);
+	if (ret) {
+		pr_debug("IAA wq sub-driver registration failed\n");
+		goto out;
+	}
+
+	pr_debug("initialized\n");
+out:
+	return ret;
+}
+
+static void __exit iaa_crypto_cleanup_module(void)
+{
+	idxd_driver_unregister(&iaa_crypto_driver);
+
+	pr_debug("cleaned up\n");
+}
+
+MODULE_IMPORT_NS(IDXD);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_IDXD_DEVICE(0);
+MODULE_AUTHOR("Intel Corporation");
+MODULE_DESCRIPTION("IAA Compression Accelerator Crypto Driver");
+
+module_init(iaa_crypto_init_module);
+module_exit(iaa_crypto_cleanup_module);
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH v2 10/15] crypto: iaa - Add per-cpu workqueue table with rebalancing
  2023-03-28 15:35 [PATCH v2 00/15] crypto: Add Intel Analytics Accelerator (IAA) crypto compression driver Tom Zanussi
                   ` (8 preceding siblings ...)
  2023-03-28 15:35 ` [PATCH v2 09/15] crypto: iaa - Add Intel IAA Compression Accelerator crypto driver core Tom Zanussi
@ 2023-03-28 15:35 ` Tom Zanussi
  2023-03-28 15:35 ` [PATCH v2 11/15] crypto: iaa - Add compression mode management along with fixed mode Tom Zanussi
                   ` (5 subsequent siblings)
  15 siblings, 0 replies; 25+ messages in thread
From: Tom Zanussi @ 2023-03-28 15:35 UTC (permalink / raw)
  To: herbert, davem, fenghua.yu, vkoul
  Cc: dave.jiang, tony.luck, wajdi.k.feghali, james.guilford,
	kanchana.p.sridhar, giovanni.cabiddu, linux-kernel, linux-crypto,
	dmaengine

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>
---
 drivers/crypto/intel/iaa/iaa_crypto.h      |   7 +
 drivers/crypto/intel/iaa/iaa_crypto_main.c | 244 +++++++++++++++++++++
 2 files changed, 251 insertions(+)

diff --git a/drivers/crypto/intel/iaa/iaa_crypto.h b/drivers/crypto/intel/iaa/iaa_crypto.h
index 5d1fff7f4b8e..c25546fa87f7 100644
--- a/drivers/crypto/intel/iaa/iaa_crypto.h
+++ b/drivers/crypto/intel/iaa/iaa_crypto.h
@@ -27,4 +27,11 @@ struct iaa_device {
 	struct list_head		wqs;
 };
 
+struct wq_table_entry {
+	struct idxd_wq **wqs;
+	int	max_wqs;
+	int	n_wqs;
+	int	cur_wq;
+};
+
 #endif
diff --git a/drivers/crypto/intel/iaa/iaa_crypto_main.c b/drivers/crypto/intel/iaa/iaa_crypto_main.c
index c35a778d53a6..cf728cf8798f 100644
--- a/drivers/crypto/intel/iaa/iaa_crypto_main.c
+++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c
@@ -22,10 +22,92 @@
 
 /* number of iaa instances probed */
 static unsigned int nr_iaa;
+static unsigned int nr_cpus;
+static unsigned int nr_nodes;
+static unsigned int nr_cpus_per_node;
+
+/* Number of physical cpus sharing each iaa instance */
+static unsigned int cpus_per_iaa;
+
+/* Per-cpu lookup table for balanced wqs */
+static struct wq_table_entry __percpu *wq_table;
+
+static void wq_table_add(int cpu, struct idxd_wq *wq)
+{
+	struct wq_table_entry *entry = per_cpu_ptr(wq_table, cpu);
+
+	if (WARN_ON(entry->n_wqs == entry->max_wqs))
+		return;
+
+	entry->wqs[entry->n_wqs++] = wq;
+
+	pr_debug("%s: added iaa wq %d.%d to idx %d of cpu %d\n", __func__,
+		 entry->wqs[entry->n_wqs - 1]->idxd->id,
+		 entry->wqs[entry->n_wqs - 1]->id, entry->n_wqs - 1, cpu);
+}
+
+static void wq_table_free_entry(int cpu)
+{
+	struct wq_table_entry *entry = per_cpu_ptr(wq_table, cpu);
+
+	kfree(entry->wqs);
+	memset(entry, 0, sizeof(*entry));
+}
+
+static void wq_table_clear_entry(int cpu)
+{
+	struct wq_table_entry *entry = per_cpu_ptr(wq_table, cpu);
+
+	entry->n_wqs = 0;
+	entry->cur_wq = 0;
+	memset(entry->wqs, 0, entry->max_wqs * sizeof(struct idxd_wq *));
+}
 
 static LIST_HEAD(iaa_devices);
 static DEFINE_MUTEX(iaa_devices_lock);
 
+/*
+ * Given a cpu, find the closest IAA instance.  The idea is to try to
+ * choose the most appropriate IAA instance for a caller and spread
+ * available workqueues around to clients.
+ */
+static inline int cpu_to_iaa(int cpu)
+{
+	int node, n_cpus = 0, test_cpu, iaa = 0;
+	int nr_iaa_per_node, nr_cores_per_iaa;
+	const struct cpumask *node_cpus;
+
+	if (!nr_nodes)
+		return 0;
+
+	nr_iaa_per_node = nr_iaa / nr_nodes;
+	if (!nr_iaa_per_node)
+		return 0;
+
+	nr_cores_per_iaa = nr_cpus_per_node / nr_iaa_per_node;
+
+	for_each_online_node(node) {
+		node_cpus = cpumask_of_node(node);
+		if (!cpumask_test_cpu(cpu, node_cpus))
+			continue;
+
+		for_each_cpu(test_cpu, node_cpus) {
+			if ((n_cpus % nr_cpus_per_node) == 0)
+				iaa = node * nr_iaa_per_node;
+
+			if (test_cpu == cpu)
+				return iaa;
+
+			n_cpus++;
+
+			if ((n_cpus % cpus_per_iaa) == 0)
+				iaa++;
+		}
+	}
+
+	return -1;
+}
+
 static struct iaa_device *iaa_device_alloc(void)
 {
 	struct iaa_device *iaa_device;
@@ -141,6 +223,53 @@ static void del_iaa_wq(struct iaa_device *iaa_device, struct idxd_wq *wq)
 	}
 }
 
+static void clear_wq_table(void)
+{
+	int cpu;
+
+	for (cpu = 0; cpu < nr_cpus; cpu++)
+		wq_table_clear_entry(cpu);
+
+	pr_debug("cleared wq table\n");
+}
+
+static void free_wq_table(void)
+{
+	int cpu;
+
+	for (cpu = 0; cpu < nr_cpus; cpu++)
+		wq_table_free_entry(cpu);
+
+	free_percpu(wq_table);
+
+	pr_debug("freed wq table\n");
+}
+
+static int alloc_wq_table(int max_wqs)
+{
+	struct wq_table_entry *entry;
+	int cpu;
+
+	wq_table = alloc_percpu(struct wq_table_entry);
+	if (!wq_table)
+		return -ENOMEM;
+
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		entry = per_cpu_ptr(wq_table, cpu);
+		entry->wqs = kzalloc(GFP_KERNEL, max_wqs * sizeof(struct wq *));
+		if (!entry->wqs) {
+			free_wq_table();
+			return -ENOMEM;
+		}
+
+		entry->max_wqs = max_wqs;
+	}
+
+	pr_debug("initialized wq table\n");
+
+	return 0;
+}
+
 static int save_iaa_wq(struct idxd_wq *wq)
 {
 	struct iaa_device *iaa_device, *found = NULL;
@@ -195,6 +324,8 @@ static int save_iaa_wq(struct idxd_wq *wq)
 		return -EINVAL;
 
 	idxd_wq_get(wq);
+
+	cpus_per_iaa = (nr_nodes * nr_cpus_per_node) / nr_iaa;
 out:
 	return 0;
 }
@@ -210,6 +341,97 @@ static void remove_iaa_wq(struct idxd_wq *wq)
 			break;
 		}
 	}
+
+	if (nr_iaa)
+		cpus_per_iaa = (nr_nodes * nr_cpus_per_node) / nr_iaa;
+	else
+		cpus_per_iaa = 0;
+}
+
+static int wq_table_add_wqs(int iaa, int cpu)
+{
+	struct iaa_device *iaa_device, *found_device = NULL;
+	int ret = 0, cur_iaa = 0, n_wqs_added = 0;
+	struct idxd_device *idxd;
+	struct iaa_wq *iaa_wq;
+	struct pci_dev *pdev;
+	struct device *dev;
+
+	list_for_each_entry(iaa_device, &iaa_devices, list) {
+		idxd = iaa_device->idxd;
+		pdev = idxd->pdev;
+		dev = &pdev->dev;
+
+		if (cur_iaa != iaa) {
+			cur_iaa++;
+			continue;
+		}
+
+		found_device = iaa_device;
+		dev_dbg(dev, "getting wq from iaa_device %d, cur_iaa %d\n",
+			found_device->idxd->id, cur_iaa);
+		break;
+	}
+
+	if (!found_device) {
+		found_device = list_first_entry_or_null(&iaa_devices,
+							struct iaa_device, list);
+		if (!found_device) {
+			pr_debug("couldn't find any iaa devices with wqs!\n");
+			ret = -EINVAL;
+			goto out;
+		}
+		cur_iaa = 0;
+
+		idxd = found_device->idxd;
+		pdev = idxd->pdev;
+		dev = &pdev->dev;
+		dev_dbg(dev, "getting wq from only iaa_device %d, cur_iaa %d\n",
+			found_device->idxd->id, cur_iaa);
+	}
+
+	list_for_each_entry(iaa_wq, &found_device->wqs, list) {
+		wq_table_add(cpu, iaa_wq->wq);
+		pr_debug("rebalance: added wq for cpu=%d: iaa wq %d.%d\n",
+			 cpu, iaa_wq->wq->idxd->id, iaa_wq->wq->id);
+		n_wqs_added++;
+	};
+
+	if (!n_wqs_added) {
+		pr_debug("couldn't find any iaa wqs!\n");
+		ret = -EINVAL;
+		goto out;
+	}
+out:
+	return ret;
+}
+
+static void rebalance_wq_table(void)
+{
+	int cpu, iaa;
+
+	if (nr_iaa == 0)
+		return;
+
+	clear_wq_table();
+
+	pr_debug("rebalance: nr_nodes=%d, nr_cpus %d, nr_iaa %d, cpus_per_iaa %d\n",
+		 nr_nodes, nr_cpus, nr_iaa, cpus_per_iaa);
+
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		iaa = cpu_to_iaa(cpu);
+		pr_debug("rebalance: cpu=%d iaa=%d\n", cpu, iaa);
+
+		if (WARN_ON(iaa == -1)) {
+			pr_debug("rebalance (cpu_to_iaa(%d)) failed!\n", cpu);
+			return;
+		}
+
+		if (WARN_ON(wq_table_add_wqs(iaa, cpu))) {
+			pr_debug("could not add any wqs for iaa %d to cpu %d!\n", iaa, cpu);
+			return;
+		}
+	}
 }
 
 static int iaa_crypto_probe(struct idxd_dev *idxd_dev)
@@ -218,6 +440,7 @@ static int iaa_crypto_probe(struct idxd_dev *idxd_dev)
 	struct idxd_device *idxd = wq->idxd;
 	struct idxd_driver_data *data = idxd->data;
 	struct device *dev = &idxd_dev->conf_dev;
+	bool first_wq = false;
 	int ret = 0;
 
 	if (idxd->state != IDXD_DEV_ENABLED)
@@ -248,10 +471,19 @@ static int iaa_crypto_probe(struct idxd_dev *idxd_dev)
 
 	mutex_lock(&iaa_devices_lock);
 
+	if (list_empty(&iaa_devices)) {
+		ret = alloc_wq_table(wq->idxd->max_wqs);
+		if (ret)
+			goto err_alloc;
+		first_wq = true;
+	}
+
 	ret = save_iaa_wq(wq);
 	if (ret)
 		goto err_save;
 
+	rebalance_wq_table();
+
 	mutex_unlock(&iaa_devices_lock);
 out:
 	mutex_unlock(&wq->wq_lock);
@@ -259,6 +491,10 @@ static int iaa_crypto_probe(struct idxd_dev *idxd_dev)
 	return ret;
 
 err_save:
+	if (first_wq)
+		free_wq_table();
+err_alloc:
+	mutex_unlock(&iaa_devices_lock);
 	drv_disable_wq(wq);
 err:
 	wq->type = IDXD_WQT_NONE;
@@ -277,6 +513,10 @@ static void iaa_crypto_remove(struct idxd_dev *idxd_dev)
 
 	remove_iaa_wq(wq);
 	drv_disable_wq(wq);
+	rebalance_wq_table();
+
+	if (nr_iaa == 0)
+		free_wq_table();
 
 	mutex_unlock(&iaa_devices_lock);
 	mutex_unlock(&wq->wq_lock);
@@ -298,6 +538,10 @@ static int __init iaa_crypto_init_module(void)
 {
 	int ret = 0;
 
+	nr_cpus = num_online_cpus();
+	nr_nodes = num_online_nodes();
+	nr_cpus_per_node = boot_cpu_data.x86_max_cores;
+
 	ret = idxd_driver_register(&iaa_crypto_driver);
 	if (ret) {
 		pr_debug("IAA wq sub-driver registration failed\n");
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH v2 11/15] crypto: iaa - Add compression mode management along with fixed mode
  2023-03-28 15:35 [PATCH v2 00/15] crypto: Add Intel Analytics Accelerator (IAA) crypto compression driver Tom Zanussi
                   ` (9 preceding siblings ...)
  2023-03-28 15:35 ` [PATCH v2 10/15] crypto: iaa - Add per-cpu workqueue table with rebalancing Tom Zanussi
@ 2023-03-28 15:35 ` Tom Zanussi
  2023-03-28 15:35 ` [PATCH v2 12/15] crypto: iaa - Add support for iaa_crypto deflate compression algorithm Tom Zanussi
                   ` (4 subsequent siblings)
  15 siblings, 0 replies; 25+ messages in thread
From: Tom Zanussi @ 2023-03-28 15:35 UTC (permalink / raw)
  To: herbert, davem, fenghua.yu, vkoul
  Cc: dave.jiang, tony.luck, wajdi.k.feghali, james.guilford,
	kanchana.p.sridhar, giovanni.cabiddu, linux-kernel, linux-crypto,
	dmaengine

Additionally, it defines an in-kernel API for adding, removing, and
setting compression schemes, which can be used by kernel modules or
other kernel code that implements IAA compression schemes.

It also adds a separate file, iaa_crypto_comp_fixed.c, containing
huffman tables generated for a compression scheme named 'fixed'.
Future compression schemes can be added in a similar fashion.

The compression mode in effect can be selected by the user via the new
iaa_crypto 'compression_mode' driver attribute.  Currently, there is
only one compression mode available, 'fixed' mode:

  echo "fixed" >  /sys/bus/dsa/drivers/crypto/compression_mode

Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
---
 drivers/crypto/intel/iaa/Makefile             |   2 +-
 drivers/crypto/intel/iaa/iaa_crypto.h         |  87 ++++
 .../crypto/intel/iaa/iaa_crypto_comp_fixed.c  |  92 ++++
 drivers/crypto/intel/iaa/iaa_crypto_main.c    | 421 ++++++++++++++++++
 4 files changed, 601 insertions(+), 1 deletion(-)
 create mode 100644 drivers/crypto/intel/iaa/iaa_crypto_comp_fixed.c

diff --git a/drivers/crypto/intel/iaa/Makefile b/drivers/crypto/intel/iaa/Makefile
index 03859431c897..cc87feffd059 100644
--- a/drivers/crypto/intel/iaa/Makefile
+++ b/drivers/crypto/intel/iaa/Makefile
@@ -7,4 +7,4 @@ ccflags-y += -I $(srctree)/drivers/dma/idxd -DDEFAULT_SYMBOL_NAMESPACE=IDXD
 
 obj-$(CONFIG_CRYPTO_DEV_IAA_CRYPTO) := iaa_crypto.o
 
-iaa_crypto-y := iaa_crypto_main.o
+iaa_crypto-y := iaa_crypto_main.o iaa_crypto_comp_fixed.o
diff --git a/drivers/crypto/intel/iaa/iaa_crypto.h b/drivers/crypto/intel/iaa/iaa_crypto.h
index c25546fa87f7..2daa3522e073 100644
--- a/drivers/crypto/intel/iaa/iaa_crypto.h
+++ b/drivers/crypto/intel/iaa/iaa_crypto.h
@@ -10,6 +10,11 @@
 
 #define IDXD_SUBDRIVER_NAME		"crypto"
 
+#define IAA_COMP_MODES_MAX		2
+
+#define FIXED_HDR			0x2
+#define FIXED_HDR_SIZE			3
+
 /* Representation of IAA workqueue */
 struct iaa_wq {
 	struct list_head	list;
@@ -18,11 +23,24 @@ struct iaa_wq {
 	struct iaa_device	*iaa_device;
 };
 
+struct iaa_device_compression_mode {
+	const char			*name;
+
+	struct aecs_comp_table_record	*aecs_comp_table;
+	struct aecs_decomp_table_record	*aecs_decomp_table;
+
+	dma_addr_t			aecs_comp_table_dma_addr;
+	dma_addr_t			aecs_decomp_table_dma_addr;
+};
+
 /* Representation of IAA device with wqs, populated by probe */
 struct iaa_device {
 	struct list_head		list;
 	struct idxd_device		*idxd;
 
+	struct iaa_device_compression_mode	*compression_modes[IAA_COMP_MODES_MAX];
+	struct iaa_device_compression_mode	*active_compression_mode;
+
 	int				n_wq;
 	struct list_head		wqs;
 };
@@ -34,4 +52,73 @@ struct wq_table_entry {
 	int	cur_wq;
 };
 
+#define IAA_AECS_ALIGN			32
+
+/*
+ * Analytics Engine Configuration and State (AECS) contains parameters and
+ * internal state of the analytics engine.
+ */
+struct aecs_comp_table_record {
+	u32 crc;
+	u32 xor_checksum;
+	u32 reserved0[5];
+	u32 num_output_accum_bits;
+	u8 output_accum[256];
+	u32 ll_sym[286];
+	u32 reserved1;
+	u32 reserved2;
+	u32 d_sym[30];
+	u32 reserved_padding[2];
+} __packed;
+
+/* AECS for decompress */
+struct aecs_decomp_table_record {
+	u32 crc;
+	u32 xor_checksum;
+	u32 low_filter_param;
+	u32 high_filter_param;
+	u32 output_mod_idx;
+	u32 drop_init_decomp_out_bytes;
+	u32 reserved[36];
+	u32 output_accum_data[2];
+	u32 out_bits_valid;
+	u32 bit_off_indexing;
+	u32 input_accum_data[64];
+	u8  size_qw[32];
+	u32 decomp_state[1220];
+} __packed;
+
+int iaa_aecs_init_fixed(void);
+void iaa_aecs_cleanup_fixed(void);
+
+typedef int (*iaa_dev_comp_init_fn_t) (struct iaa_device_compression_mode *mode);
+typedef int (*iaa_dev_comp_free_fn_t) (struct iaa_device_compression_mode *mode);
+
+struct iaa_compression_mode {
+	const char		*name;
+	u32			*ll_table;
+	int			ll_table_size;
+	u32			*d_table;
+	int			d_table_size;
+	u32			*header_table;
+	int			header_table_size;
+	u16			gen_decomp_table_flags;
+	iaa_dev_comp_init_fn_t	init;
+	iaa_dev_comp_free_fn_t	free;
+};
+
+int add_iaa_compression_mode(const char *name,
+			     const u32 *ll_table,
+			     int ll_table_size,
+			     const u32 *d_table,
+			     int d_table_size,
+			     const u8 *header_table,
+			     int header_table_size,
+			     u16 gen_decomp_table_flags,
+			     iaa_dev_comp_init_fn_t init,
+			     iaa_dev_comp_free_fn_t free);
+
+void remove_iaa_compression_mode(const char *name);
+int set_iaa_compression_mode(const char *name);
+
 #endif
diff --git a/drivers/crypto/intel/iaa/iaa_crypto_comp_fixed.c b/drivers/crypto/intel/iaa/iaa_crypto_comp_fixed.c
new file mode 100644
index 000000000000..e965da11b4d9
--- /dev/null
+++ b/drivers/crypto/intel/iaa/iaa_crypto_comp_fixed.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2021 Intel Corporation. All rights rsvd. */
+
+#include "idxd.h"
+#include "iaa_crypto.h"
+
+/*
+ * Fixed Huffman tables the IAA hardware requires to implement RFC-1951.
+ */
+const u32 fixed_ll_sym[286] = {
+	0x40030, 0x40031, 0x40032, 0x40033, 0x40034, 0x40035, 0x40036, 0x40037,
+	0x40038, 0x40039, 0x4003A, 0x4003B, 0x4003C, 0x4003D, 0x4003E, 0x4003F,
+	0x40040, 0x40041, 0x40042, 0x40043, 0x40044, 0x40045, 0x40046, 0x40047,
+	0x40048, 0x40049, 0x4004A, 0x4004B, 0x4004C, 0x4004D, 0x4004E, 0x4004F,
+	0x40050, 0x40051, 0x40052, 0x40053, 0x40054, 0x40055, 0x40056, 0x40057,
+	0x40058, 0x40059, 0x4005A, 0x4005B, 0x4005C, 0x4005D, 0x4005E, 0x4005F,
+	0x40060, 0x40061, 0x40062, 0x40063, 0x40064, 0x40065, 0x40066, 0x40067,
+	0x40068, 0x40069, 0x4006A, 0x4006B, 0x4006C, 0x4006D, 0x4006E, 0x4006F,
+	0x40070, 0x40071, 0x40072, 0x40073, 0x40074, 0x40075, 0x40076, 0x40077,
+	0x40078, 0x40079, 0x4007A, 0x4007B, 0x4007C, 0x4007D, 0x4007E, 0x4007F,
+	0x40080, 0x40081, 0x40082, 0x40083, 0x40084, 0x40085, 0x40086, 0x40087,
+	0x40088, 0x40089, 0x4008A, 0x4008B, 0x4008C, 0x4008D, 0x4008E, 0x4008F,
+	0x40090, 0x40091, 0x40092, 0x40093, 0x40094, 0x40095, 0x40096, 0x40097,
+	0x40098, 0x40099, 0x4009A, 0x4009B, 0x4009C, 0x4009D, 0x4009E, 0x4009F,
+	0x400A0, 0x400A1, 0x400A2, 0x400A3, 0x400A4, 0x400A5, 0x400A6, 0x400A7,
+	0x400A8, 0x400A9, 0x400AA, 0x400AB, 0x400AC, 0x400AD, 0x400AE, 0x400AF,
+	0x400B0, 0x400B1, 0x400B2, 0x400B3, 0x400B4, 0x400B5, 0x400B6, 0x400B7,
+	0x400B8, 0x400B9, 0x400BA, 0x400BB, 0x400BC, 0x400BD, 0x400BE, 0x400BF,
+	0x48190, 0x48191, 0x48192, 0x48193, 0x48194, 0x48195, 0x48196, 0x48197,
+	0x48198, 0x48199, 0x4819A, 0x4819B, 0x4819C, 0x4819D, 0x4819E, 0x4819F,
+	0x481A0, 0x481A1, 0x481A2, 0x481A3, 0x481A4, 0x481A5, 0x481A6, 0x481A7,
+	0x481A8, 0x481A9, 0x481AA, 0x481AB, 0x481AC, 0x481AD, 0x481AE, 0x481AF,
+	0x481B0, 0x481B1, 0x481B2, 0x481B3, 0x481B4, 0x481B5, 0x481B6, 0x481B7,
+	0x481B8, 0x481B9, 0x481BA, 0x481BB, 0x481BC, 0x481BD, 0x481BE, 0x481BF,
+	0x481C0, 0x481C1, 0x481C2, 0x481C3, 0x481C4, 0x481C5, 0x481C6, 0x481C7,
+	0x481C8, 0x481C9, 0x481CA, 0x481CB, 0x481CC, 0x481CD, 0x481CE, 0x481CF,
+	0x481D0, 0x481D1, 0x481D2, 0x481D3, 0x481D4, 0x481D5, 0x481D6, 0x481D7,
+	0x481D8, 0x481D9, 0x481DA, 0x481DB, 0x481DC, 0x481DD, 0x481DE, 0x481DF,
+	0x481E0, 0x481E1, 0x481E2, 0x481E3, 0x481E4, 0x481E5, 0x481E6, 0x481E7,
+	0x481E8, 0x481E9, 0x481EA, 0x481EB, 0x481EC, 0x481ED, 0x481EE, 0x481EF,
+	0x481F0, 0x481F1, 0x481F2, 0x481F3, 0x481F4, 0x481F5, 0x481F6, 0x481F7,
+	0x481F8, 0x481F9, 0x481FA, 0x481FB, 0x481FC, 0x481FD, 0x481FE, 0x481FF,
+	0x38000, 0x38001, 0x38002, 0x38003, 0x38004, 0x38005, 0x38006, 0x38007,
+	0x38008, 0x38009, 0x3800A, 0x3800B, 0x3800C, 0x3800D, 0x3800E, 0x3800F,
+	0x38010, 0x38011, 0x38012, 0x38013, 0x38014, 0x38015, 0x38016, 0x38017,
+	0x400C0, 0x400C1, 0x400C2, 0x400C3, 0x400C4, 0x400C5
+};
+
+const u32 fixed_d_sym[30] = {
+	0x28000, 0x28001, 0x28002, 0x28003, 0x28004, 0x28005, 0x28006, 0x28007,
+	0x28008, 0x28009, 0x2800A, 0x2800B, 0x2800C, 0x2800D, 0x2800E, 0x2800F,
+	0x28010, 0x28011, 0x28012, 0x28013, 0x28014, 0x28015, 0x28016, 0x28017,
+	0x28018, 0x28019, 0x2801A, 0x2801B, 0x2801C, 0x2801D
+};
+
+static int init_fixed_mode(struct iaa_device_compression_mode *mode)
+{
+	struct aecs_comp_table_record *comp_table = mode->aecs_comp_table;
+	u32 bfinal = 1;
+	u32 offset;
+
+	/* Configure aecs table using fixed Huffman table */
+	comp_table->crc = 0;
+	comp_table->xor_checksum = 0;
+	offset = comp_table->num_output_accum_bits / 8;
+	comp_table->output_accum[offset] = FIXED_HDR | bfinal;
+	comp_table->num_output_accum_bits = FIXED_HDR_SIZE;
+
+	return 0;
+}
+
+int iaa_aecs_init_fixed(void)
+{
+	int ret;
+
+	ret = add_iaa_compression_mode("fixed",
+				       fixed_ll_sym,
+				       sizeof(fixed_ll_sym),
+				       fixed_d_sym,
+				       sizeof(fixed_d_sym),
+				       NULL, 0, 0,
+				       init_fixed_mode, NULL);
+	if (!ret)
+		pr_debug("IAA fixed compression mode initialized\n");
+
+	return ret;
+}
+
+void iaa_aecs_cleanup_fixed(void)
+{
+	remove_iaa_compression_mode("fixed");
+}
diff --git a/drivers/crypto/intel/iaa/iaa_crypto_main.c b/drivers/crypto/intel/iaa/iaa_crypto_main.c
index cf728cf8798f..1ee7e3052177 100644
--- a/drivers/crypto/intel/iaa/iaa_crypto_main.c
+++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c
@@ -66,6 +66,381 @@ static void wq_table_clear_entry(int cpu)
 static LIST_HEAD(iaa_devices);
 static DEFINE_MUTEX(iaa_devices_lock);
 
+static struct iaa_compression_mode *iaa_compression_modes[IAA_COMP_MODES_MAX];
+static int active_compression_mode;
+
+static ssize_t compression_mode_show(struct device_driver *driver, char *buf)
+{
+	int ret = 0;
+
+	ret = sprintf(buf, "%s\n", "fixed");
+
+	return ret;
+}
+
+static ssize_t compression_mode_store(struct device_driver *driver,
+				      const char *buf, size_t count)
+{
+	int ret = -EBUSY;
+	char *mode_name;
+
+	mutex_lock(&iaa_devices_lock);
+
+	mode_name = kstrndup(buf, count, GFP_KERNEL);
+	if (!mode_name) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = set_iaa_compression_mode(strim(mode_name));
+	if (ret == 0)
+		ret = count;
+
+	kfree(mode_name);
+out:
+	mutex_unlock(&iaa_devices_lock);
+
+	return ret;
+}
+static DRIVER_ATTR_RW(compression_mode);
+
+static int find_empty_iaa_compression_mode(void)
+{
+	int i = -EINVAL;
+
+	for (i = 0; i < IAA_COMP_MODES_MAX; i++) {
+		if (iaa_compression_modes[i])
+			continue;
+		break;
+	}
+
+	return i;
+}
+
+static struct iaa_compression_mode *find_iaa_compression_mode(const char *name, int *idx)
+{
+	struct iaa_compression_mode *mode;
+	int i;
+
+	for (i = 0; i < IAA_COMP_MODES_MAX; i++) {
+		mode = iaa_compression_modes[i];
+		if (!mode)
+			continue;
+
+		if (!strcmp(mode->name, name)) {
+			*idx = i;
+			return iaa_compression_modes[i];
+		}
+	}
+
+	return NULL;
+}
+
+static void free_iaa_compression_mode(struct iaa_compression_mode *mode)
+{
+	kfree(mode->name);
+	kfree(mode->ll_table);
+	kfree(mode->d_table);
+	kfree(mode->header_table);
+
+	kfree(mode);
+}
+
+/*
+ * IAA Compression modes are defined by an ll_table, a d_table, and an
+ * optional header_table.  These tables are typically generated and
+ * captured using statistics collected from running actual
+ * compress/decompress workloads.
+ *
+ * A module or other kernel code can add and remove compression modes
+ * with a given name using the exported @add_iaa_compression_mode()
+ * and @remove_iaa_compression_mode functions.
+ *
+ * Successfully added compression modes can be selected using the
+ * function @set_iaa_compression_mode(), passing in the name of the
+ * compression mode.  Henceforth, all compressions and decompressions
+ * will use the given compression mode.  Any in-flight decompressions
+ * using the old mode will subsequently fail.
+ *
+ * When a new compression mode is added, the tables are saved in a
+ * global compression mode list.  When IAA devices are added, a
+ * per-IAA device dma mapping is created for each IAA device, for each
+ * compression mode.  These are the tables used to do the actual
+ * compression/deccompression and are unmapped if/when the devices are
+ * removed.  Currently, compression modes must be added before any
+ * device is added, and removed after all devices have been removed.
+ */
+
+/**
+ * remove_iaa_compression_mode - Remove an IAA compression mode
+ * @name: The name the compression mode will be known as
+ *
+ * Remove the IAA compression mode named @name.
+ */
+void remove_iaa_compression_mode(const char *name)
+{
+	struct iaa_compression_mode *mode;
+	int idx;
+
+	mutex_lock(&iaa_devices_lock);
+
+	if (!list_empty(&iaa_devices))
+		goto out;
+
+	mode = find_iaa_compression_mode(name, &idx);
+	if (mode) {
+		free_iaa_compression_mode(mode);
+		iaa_compression_modes[idx] = NULL;
+	}
+out:
+	mutex_unlock(&iaa_devices_lock);
+}
+EXPORT_SYMBOL_GPL(remove_iaa_compression_mode);
+
+/**
+ * add_iaa_compression_mode - Add an IAA compression mode
+ * @name: The name the compression mode will be known as
+ * @ll_table: The ll table
+ * @ll_table_size: The ll table size in bytes
+ * @d_table: The d table
+ * @d_table_size: The d table size in bytes
+ * @header_table: Optional header table
+ * @header_table_size: Optional header table size in bytes
+ * @gen_decomp_table_flags: Otional flags used to generate the decomp table
+ * @init: Optional callback function to init the compression mode data
+ * @free: Optional callback function to free the compression mode data
+ *
+ * Add a new IAA compression mode named @name.  If successful, @name
+ * can subsequently be given to @set_iaa_compression_mode() to make
+ * that mode the current mode for iaa compression/decompression.
+ *
+ * Returns 0 if successful, errcode otherwise.
+ */
+int add_iaa_compression_mode(const char *name,
+			     const u32 *ll_table,
+			     int ll_table_size,
+			     const u32 *d_table,
+			     int d_table_size,
+			     const u8 *header_table,
+			     int header_table_size,
+			     u16 gen_decomp_table_flags,
+			     iaa_dev_comp_init_fn_t init,
+			     iaa_dev_comp_free_fn_t free)
+{
+	struct iaa_compression_mode *mode;
+	int idx, ret = -ENOMEM;
+
+	mutex_lock(&iaa_devices_lock);
+
+	if (!list_empty(&iaa_devices)) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	mode = kzalloc(sizeof(*mode), GFP_KERNEL);
+	if (!mode)
+		goto out;
+
+	mode->name = kstrdup(name, GFP_KERNEL);
+	if (!mode->name)
+		goto free;
+
+	if (ll_table) {
+		mode->ll_table = kzalloc(ll_table_size, GFP_KERNEL);
+		if (!mode->ll_table)
+			goto free;
+		memcpy(mode->ll_table, ll_table, ll_table_size);
+		mode->ll_table_size = ll_table_size;
+	}
+
+	if (d_table) {
+		mode->d_table = kzalloc(d_table_size, GFP_KERNEL);
+		if (!mode->d_table)
+			goto free;
+		memcpy(mode->d_table, d_table, d_table_size);
+		mode->d_table_size = d_table_size;
+	}
+
+	if (header_table) {
+		mode->header_table = kzalloc(header_table_size, GFP_KERNEL);
+		if (!mode->header_table)
+			goto free;
+		memcpy(mode->header_table, header_table, header_table_size);
+		mode->header_table_size = header_table_size;
+	}
+
+	mode->gen_decomp_table_flags = gen_decomp_table_flags;
+
+	mode->init = init;
+	mode->free = free;
+
+	idx = find_empty_iaa_compression_mode();
+	if (idx < 0)
+		goto free;
+
+	pr_debug("IAA compression mode %s added at idx %d\n",
+		 mode->name, idx);
+
+	iaa_compression_modes[idx] = mode;
+
+	ret = 0;
+out:
+	mutex_unlock(&iaa_devices_lock);
+
+	return ret;
+free:
+	free_iaa_compression_mode(mode);
+	goto out;
+}
+EXPORT_SYMBOL_GPL(add_iaa_compression_mode);
+
+static void set_iaa_device_compression_mode(struct iaa_device *iaa_device, int idx)
+{
+	iaa_device->active_compression_mode = iaa_device->compression_modes[idx];
+}
+
+static void update_iaa_devices_compression_mode(void)
+{
+	struct iaa_device *iaa_device;
+
+	list_for_each_entry(iaa_device, &iaa_devices, list)
+		set_iaa_device_compression_mode(iaa_device, active_compression_mode);
+}
+
+/**
+ * set_iaa_compression_mode - Set an IAA compression mode
+ * @name: The name of the compression mode
+ *
+ * Make the IAA compression mode named @name the current compression
+ * mode used by compression/decompression.
+ */
+
+int set_iaa_compression_mode(const char *name)
+{
+	struct iaa_compression_mode *mode;
+	int ret = -EINVAL;
+	int idx;
+
+	mode = find_iaa_compression_mode(name, &idx);
+	if (mode) {
+		active_compression_mode = idx;
+		update_iaa_devices_compression_mode();
+		pr_debug("compression mode set to: %s\n", name);
+		ret = 0;
+	}
+
+	return ret;
+}
+
+static void free_device_compression_mode(struct iaa_device *iaa_device,
+					 struct iaa_device_compression_mode *device_mode)
+{
+	size_t size = sizeof(struct aecs_comp_table_record) + IAA_AECS_ALIGN;
+	struct device *dev = &iaa_device->idxd->pdev->dev;
+
+	kfree(device_mode->name);
+
+	if (device_mode->aecs_comp_table)
+		dma_free_coherent(dev, size, device_mode->aecs_comp_table,
+				  device_mode->aecs_comp_table_dma_addr);
+	if (device_mode->aecs_decomp_table)
+		dma_free_coherent(dev, size, device_mode->aecs_decomp_table,
+				  device_mode->aecs_decomp_table_dma_addr);
+
+	kfree(device_mode);
+}
+
+static int init_device_compression_mode(struct iaa_device *iaa_device,
+					struct iaa_compression_mode *mode,
+					int idx, struct idxd_wq *wq)
+{
+	size_t size = sizeof(struct aecs_comp_table_record) + IAA_AECS_ALIGN;
+	struct device *dev = &iaa_device->idxd->pdev->dev;
+	struct iaa_device_compression_mode *device_mode;
+	int ret = -ENOMEM;
+
+	device_mode = kzalloc(sizeof(*device_mode), GFP_KERNEL);
+	if (!device_mode)
+		return -ENOMEM;
+
+	device_mode->name = kstrdup(mode->name, GFP_KERNEL);
+	if (!device_mode->name)
+		goto free;
+
+	device_mode->aecs_comp_table = dma_alloc_coherent(dev, size,
+							  &device_mode->aecs_comp_table_dma_addr, GFP_KERNEL);
+	if (!device_mode->aecs_comp_table)
+		goto free;
+
+	device_mode->aecs_decomp_table = dma_alloc_coherent(dev, size,
+							    &device_mode->aecs_decomp_table_dma_addr, GFP_KERNEL);
+	if (!device_mode->aecs_decomp_table)
+		goto free;
+
+	/* Add Huffman table to aecs */
+	memset(device_mode->aecs_comp_table, 0, sizeof(*device_mode->aecs_comp_table));
+	memcpy(device_mode->aecs_comp_table->ll_sym, mode->ll_table, mode->ll_table_size);
+	memcpy(device_mode->aecs_comp_table->d_sym, mode->d_table, mode->d_table_size);
+
+	if (mode->init) {
+		ret = mode->init(device_mode);
+		if (ret)
+			goto free;
+	}
+
+	/* mode index should match iaa_compression_modes idx */
+	iaa_device->compression_modes[idx] = device_mode;
+
+	pr_debug("IAA %s compression mode initialized for iaa device %d\n",
+		 mode->name, iaa_device->idxd->id);
+
+	ret = 0;
+out:
+	return ret;
+free:
+	pr_debug("IAA %s compression mode initialization failed for iaa device %d\n",
+		 mode->name, iaa_device->idxd->id);
+
+	free_device_compression_mode(iaa_device, device_mode);
+	goto out;
+}
+
+static int init_device_compression_modes(struct iaa_device *iaa_device,
+					 struct idxd_wq *wq)
+{
+	struct iaa_compression_mode *mode;
+	int i, ret = 0;
+
+	for (i = 0; i < IAA_COMP_MODES_MAX; i++) {
+		mode = iaa_compression_modes[i];
+		if (!mode)
+			continue;
+
+		ret = init_device_compression_mode(iaa_device, mode, i, wq);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static void remove_device_compression_modes(struct iaa_device *iaa_device)
+{
+	struct iaa_device_compression_mode *device_mode;
+	int i;
+
+	for (i = 0; i < IAA_COMP_MODES_MAX; i++) {
+		device_mode = iaa_device->compression_modes[i];
+		if (!device_mode)
+			continue;
+
+		free_device_compression_mode(iaa_device, device_mode);
+		iaa_device->compression_modes[i] = NULL;
+		if (iaa_compression_modes[i]->free)
+			iaa_compression_modes[i]->free(device_mode);
+	}
+}
+
 /*
  * Given a cpu, find the closest IAA instance.  The idea is to try to
  * choose the most appropriate IAA instance for a caller and spread
@@ -162,8 +537,23 @@ static struct iaa_device *add_iaa_device(struct idxd_device *idxd)
 	return iaa_device;
 }
 
+static int init_iaa_device(struct iaa_device *iaa_device, struct iaa_wq *iaa_wq)
+{
+	int ret = 0;
+
+	ret = init_device_compression_modes(iaa_device, iaa_wq->wq);
+	if (ret)
+		return ret;
+
+	set_iaa_device_compression_mode(iaa_device, active_compression_mode);
+
+	return ret;
+}
+
 static void del_iaa_device(struct iaa_device *iaa_device)
 {
+	remove_device_compression_modes(iaa_device);
+
 	list_del(&iaa_device->list);
 
 	iaa_device_free(iaa_device);
@@ -318,6 +708,13 @@ static int save_iaa_wq(struct idxd_wq *wq)
 			del_iaa_device(new_device);
 			goto out;
 		}
+
+		ret = init_iaa_device(new_device, new_wq);
+		if (ret) {
+			del_iaa_wq(new_device, new_wq->wq);
+			del_iaa_device(new_device);
+			goto out;
+		}
 	}
 
 	if (WARN_ON(nr_iaa == 0))
@@ -548,14 +945,38 @@ static int __init iaa_crypto_init_module(void)
 		goto out;
 	}
 
+	ret = driver_create_file(&iaa_crypto_driver.drv,
+				 &driver_attr_compression_mode);
+	if (ret) {
+		pr_debug("IAA compression mode attr creation failed\n");
+		goto err_attr_create;
+	}
+
+	ret = iaa_aecs_init_fixed();
+	if (ret < 0) {
+		pr_debug("IAA fixed compression mode init failed\n");
+		goto err_compression_mode;
+	}
+
 	pr_debug("initialized\n");
 out:
 	return ret;
+
+err_compression_mode:
+	driver_remove_file(&iaa_crypto_driver.drv,
+			   &driver_attr_compression_mode);
+err_attr_create:
+	idxd_driver_unregister(&iaa_crypto_driver);
+
+	goto out;
 }
 
 static void __exit iaa_crypto_cleanup_module(void)
 {
+	driver_remove_file(&iaa_crypto_driver.drv,
+			   &driver_attr_compression_mode);
 	idxd_driver_unregister(&iaa_crypto_driver);
+	iaa_aecs_cleanup_fixed();
 
 	pr_debug("cleaned up\n");
 }
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH v2 12/15] crypto: iaa - Add support for iaa_crypto deflate compression algorithm
  2023-03-28 15:35 [PATCH v2 00/15] crypto: Add Intel Analytics Accelerator (IAA) crypto compression driver Tom Zanussi
                   ` (10 preceding siblings ...)
  2023-03-28 15:35 ` [PATCH v2 11/15] crypto: iaa - Add compression mode management along with fixed mode Tom Zanussi
@ 2023-03-28 15:35 ` Tom Zanussi
  2023-04-06  8:00   ` Herbert Xu
  2023-03-28 15:35 ` [PATCH v2 13/15] crypto: iaa - Add support for default IAA 'canned' compression mode Tom Zanussi
                   ` (3 subsequent siblings)
  15 siblings, 1 reply; 25+ messages in thread
From: Tom Zanussi @ 2023-03-28 15:35 UTC (permalink / raw)
  To: herbert, davem, fenghua.yu, vkoul
  Cc: dave.jiang, tony.luck, wajdi.k.feghali, james.guilford,
	kanchana.p.sridhar, giovanni.cabiddu, linux-kernel, linux-crypto,
	dmaengine

This patch registers the iaa_crypto deflate compression algorithm and
hooks it up to the IAA hardware.

With this change, the IAA crypto algorithm is operational and
compression and decompression operations are fully enabled following
the successful binding of the first IAA workqueue to the iaa_crypto
sub-driver, and similarly, the IAA crypto algorithm is automatically
unregistered when there are no IAA workqueues bound to the driver,
following their removal.

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.

[ Based on work originally by George Powley, Jing Lin and Kyung Min
Park ]

Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
---
 drivers/crypto/intel/iaa/iaa_crypto.h      |  24 +
 drivers/crypto/intel/iaa/iaa_crypto_main.c | 728 ++++++++++++++++++++-
 2 files changed, 751 insertions(+), 1 deletion(-)

diff --git a/drivers/crypto/intel/iaa/iaa_crypto.h b/drivers/crypto/intel/iaa/iaa_crypto.h
index 2daa3522e073..7ed3d8de250d 100644
--- a/drivers/crypto/intel/iaa/iaa_crypto.h
+++ b/drivers/crypto/intel/iaa/iaa_crypto.h
@@ -10,11 +10,35 @@
 
 #define IDXD_SUBDRIVER_NAME		"crypto"
 
+#define IAA_DECOMP_ENABLE		BIT(0)
+#define IAA_DECOMP_FLUSH_OUTPUT		BIT(1)
+#define IAA_DECOMP_CHECK_FOR_EOB	BIT(2)
+#define IAA_DECOMP_STOP_ON_EOB		BIT(3)
+#define IAA_DECOMP_SUPPRESS_OUTPUT	BIT(9)
+
+#define IAA_COMP_FLUSH_OUTPUT		BIT(1)
+#define IAA_COMP_APPEND_EOB		BIT(2)
+
+#define IAA_COMPLETION_TIMEOUT		1000000
+
+#define IAA_ANALYTICS_ERROR		0x0a
+#define IAA_ERROR_DECOMP_BUF_OVERFLOW	0x0b
+#define IAA_ERROR_COMP_BUF_OVERFLOW	0x19
+#define IAA_ERROR_WATCHDOG_EXPIRED	0x24
+
 #define IAA_COMP_MODES_MAX		2
 
 #define FIXED_HDR			0x2
 #define FIXED_HDR_SIZE			3
 
+#define IAA_COMP_FLAGS			(IAA_COMP_FLUSH_OUTPUT | \
+					 IAA_COMP_APPEND_EOB)
+
+#define IAA_DECOMP_FLAGS		(IAA_DECOMP_ENABLE |	   \
+					 IAA_DECOMP_FLUSH_OUTPUT | \
+					 IAA_DECOMP_CHECK_FOR_EOB | \
+					 IAA_DECOMP_STOP_ON_EOB)
+
 /* Representation of IAA workqueue */
 struct iaa_wq {
 	struct list_head	list;
diff --git a/drivers/crypto/intel/iaa/iaa_crypto_main.c b/drivers/crypto/intel/iaa/iaa_crypto_main.c
index 1ee7e3052177..d0b1ac45cc51 100644
--- a/drivers/crypto/intel/iaa/iaa_crypto_main.c
+++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c
@@ -10,6 +10,7 @@
 #include <uapi/linux/idxd.h>
 #include <linux/highmem.h>
 #include <linux/sched/smt.h>
+#include <crypto/internal/acompress.h>
 
 #include "idxd.h"
 #include "iaa_crypto.h"
@@ -20,6 +21,8 @@
 
 #define pr_fmt(fmt)			"idxd: " IDXD_SUBDRIVER_NAME ": " fmt
 
+#define IAA_ALG_PRIORITY		300
+
 /* number of iaa instances probed */
 static unsigned int nr_iaa;
 static unsigned int nr_cpus;
@@ -32,6 +35,20 @@ static unsigned int cpus_per_iaa;
 /* Per-cpu lookup table for balanced wqs */
 static struct wq_table_entry __percpu *wq_table;
 
+static struct idxd_wq *wq_table_next_wq(int cpu)
+{
+	struct wq_table_entry *entry = per_cpu_ptr(wq_table, cpu);
+
+	if (++entry->cur_wq >= entry->n_wqs)
+		entry->cur_wq = 0;
+
+	pr_debug("%s: returning wq at idx %d (iaa wq %d.%d) from cpu %d\n", __func__,
+		 entry->cur_wq, entry->wqs[entry->cur_wq]->idxd->id,
+		 entry->wqs[entry->cur_wq]->id, cpu);
+
+	return entry->wqs[entry->cur_wq];
+}
+
 static void wq_table_add(int cpu, struct idxd_wq *wq)
 {
 	struct wq_table_entry *entry = per_cpu_ptr(wq_table, cpu);
@@ -66,6 +83,39 @@ static void wq_table_clear_entry(int cpu)
 static LIST_HEAD(iaa_devices);
 static DEFINE_MUTEX(iaa_devices_lock);
 
+/* If enabled, IAA hw crypto algos are registered, unavailable otherwise */
+static bool iaa_crypto_enabled;
+
+/* Verify results of IAA compress or not */
+static bool iaa_verify_compress = true;
+
+static ssize_t verify_compress_show(struct device_driver *driver, char *buf)
+{
+	return sprintf(buf, "%d\n", iaa_verify_compress);
+}
+
+static ssize_t verify_compress_store(struct device_driver *driver,
+				     const char *buf, size_t count)
+{
+	int ret = -EBUSY;
+
+	mutex_lock(&iaa_devices_lock);
+
+	if (iaa_crypto_enabled)
+		goto out;
+
+	ret = kstrtobool(buf, &iaa_verify_compress);
+	if (ret)
+		goto out;
+
+	ret = count;
+out:
+	mutex_unlock(&iaa_devices_lock);
+
+	return ret;
+}
+static DRIVER_ATTR_RW(verify_compress);
+
 static struct iaa_compression_mode *iaa_compression_modes[IAA_COMP_MODES_MAX];
 static int active_compression_mode;
 
@@ -86,6 +136,9 @@ static ssize_t compression_mode_store(struct device_driver *driver,
 
 	mutex_lock(&iaa_devices_lock);
 
+	if (iaa_crypto_enabled)
+		goto out;
+
 	mode_name = kstrndup(buf, count, GFP_KERNEL);
 	if (!mode_name) {
 		ret = -ENOMEM;
@@ -350,6 +403,89 @@ static void free_device_compression_mode(struct iaa_device *iaa_device,
 	kfree(device_mode);
 }
 
+#define IDXD_OP_FLAG_AECS_RW_TGLS       0x400000
+#define IAX_AECS_DEFAULT_FLAG (IDXD_OP_FLAG_CRAV | IDXD_OP_FLAG_RCR | IDXD_OP_FLAG_CC)
+#define IAX_AECS_COMPRESS_FLAG	(IAX_AECS_DEFAULT_FLAG | IDXD_OP_FLAG_RD_SRC2_AECS)
+#define IAX_AECS_DECOMPRESS_FLAG (IAX_AECS_DEFAULT_FLAG | IDXD_OP_FLAG_RD_SRC2_AECS)
+#define IAX_AECS_GEN_FLAG (IAX_AECS_DEFAULT_FLAG | \
+						IDXD_OP_FLAG_WR_SRC2_AECS_COMP | \
+						IDXD_OP_FLAG_AECS_RW_TGLS)
+
+static int check_completion(struct device *dev,
+			    struct iax_completion_record *comp,
+			    bool compress,
+			    bool only_once);
+
+static int decompress_header(struct iaa_device_compression_mode *device_mode,
+			     struct iaa_compression_mode *mode,
+			     struct idxd_wq *wq)
+{
+	dma_addr_t src_addr, src2_addr;
+	struct idxd_desc *idxd_desc;
+	struct iax_hw_desc *desc;
+	struct device *dev;
+	int ret = 0;
+
+	idxd_desc = idxd_alloc_desc(wq, IDXD_OP_BLOCK);
+	if (IS_ERR(idxd_desc))
+		return PTR_ERR(idxd_desc);
+
+	desc = idxd_desc->iax_hw;
+
+	dev = &wq->idxd->pdev->dev;
+
+	src_addr = dma_map_single(dev, (void *)mode->header_table,
+				  mode->header_table_size, DMA_TO_DEVICE);
+	dev_dbg(dev, "%s: mode->name %s, src_addr %llx, dev %p, src %p, slen %d\n",
+		__func__, mode->name, src_addr,	dev,
+		mode->header_table, mode->header_table_size);
+	if (unlikely(dma_mapping_error(dev, src_addr))) {
+		dev_dbg(dev, "dma_map_single err, exiting\n");
+		ret = -ENOMEM;
+		return ret;
+	}
+
+	desc->flags = IAX_AECS_GEN_FLAG;
+	desc->opcode = IAX_OPCODE_DECOMPRESS;
+
+	desc->src1_addr = (u64)src_addr;
+	desc->src1_size = mode->header_table_size;
+
+	src2_addr = device_mode->aecs_decomp_table_dma_addr;
+	desc->src2_addr = (u64)src2_addr;
+	desc->src2_size = 1088;
+	dev_dbg(dev, "%s: mode->name %s, src2_addr %llx, dev %p, src2_size %d\n",
+		__func__, mode->name, desc->src2_addr, dev, desc->src2_size);
+	desc->max_dst_size = 0; // suppressed output
+
+	desc->decompr_flags = mode->gen_decomp_table_flags;
+
+#ifdef SPR_E0
+	desc->priv = 1;
+#else
+	desc->priv = 0;
+#endif
+	desc->completion_addr = idxd_desc->compl_dma;
+
+	ret = idxd_submit_desc(wq, idxd_desc);
+	if (ret) {
+		pr_err("%s: submit_desc failed ret=0x%x\n", __func__, ret);
+		goto out;
+	}
+
+	ret = check_completion(dev, idxd_desc->iax_completion, false, false);
+	if (ret)
+		dev_dbg(dev, "%s: mode->name %s check_completion failed ret=%d\n",
+			__func__, mode->name, ret);
+	else
+		dev_dbg(dev, "%s: mode->name %s succeeded\n", __func__,
+			mode->name);
+out:
+	dma_unmap_single(dev, src2_addr, 1088, DMA_TO_DEVICE);
+
+	return ret;
+}
+
 static int init_device_compression_mode(struct iaa_device *iaa_device,
 					struct iaa_compression_mode *mode,
 					int idx, struct idxd_wq *wq)
@@ -382,6 +518,14 @@ static int init_device_compression_mode(struct iaa_device *iaa_device,
 	memcpy(device_mode->aecs_comp_table->ll_sym, mode->ll_table, mode->ll_table_size);
 	memcpy(device_mode->aecs_comp_table->d_sym, mode->d_table, mode->d_table_size);
 
+	if (mode->header_table) {
+		ret = decompress_header(device_mode, mode, wq);
+		if (ret) {
+			pr_debug("iaa header decompression failed: ret=%d\n", ret);
+			goto free;
+		}
+	}
+
 	if (mode->init) {
 		ret = mode->init(device_mode);
 		if (ret)
@@ -831,6 +975,555 @@ static void rebalance_wq_table(void)
 	}
 }
 
+static inline int check_completion(struct device *dev,
+				   struct iax_completion_record *comp,
+				   bool compress,
+				   bool only_once)
+{
+	char *op_str = compress ? "compress" : "decompress";
+	int ret = 0;
+
+	while (!comp->status) {
+		if (only_once)
+			return -EAGAIN;
+		cpu_relax();
+	}
+
+	if (comp->status != IAX_COMP_SUCCESS) {
+		if (comp->status == IAA_ERROR_WATCHDOG_EXPIRED) {
+			ret = -ETIMEDOUT;
+			dev_dbg(dev, "%s timed out, size=0x%x\n",
+				op_str, comp->output_size);
+			goto out;
+		}
+
+		if (comp->status == IAA_ANALYTICS_ERROR &&
+		    comp->error_code == IAA_ERROR_COMP_BUF_OVERFLOW && compress) {
+			ret = -E2BIG;
+			dev_dbg(dev, "compressed > uncompressed size,"
+				" not compressing, size=0x%x\n",
+				comp->output_size);
+			goto out;
+		}
+
+		if (comp->status == IAA_ERROR_DECOMP_BUF_OVERFLOW) {
+			ret = -EOVERFLOW;
+			goto out;
+		}
+
+		ret = -EINVAL;
+		dev_dbg(dev, "iaa %s status=0x%x, error=0x%x, size=0x%x\n",
+			op_str, comp->status, comp->error_code, comp->output_size);
+		print_hex_dump(KERN_INFO, "cmp-rec: ", DUMP_PREFIX_OFFSET, 8, 1, comp, 64, 0);
+
+		goto out;
+	}
+out:
+	return ret;
+}
+
+static int iaa_compress(struct crypto_tfm *tfm,	struct acomp_req *req,
+			struct idxd_wq *wq,
+			dma_addr_t src_addr, unsigned int slen,
+			dma_addr_t dst_addr, unsigned int *dlen,
+			u32 *compression_crc,
+			bool disable_async)
+{
+	struct idxd_desc *idxd_desc;
+	struct iax_hw_desc *desc;
+	struct idxd_device *idxd;
+	struct iaa_wq *iaa_wq;
+	struct pci_dev *pdev;
+	struct device *dev;
+	int ret = 0;
+
+	iaa_wq = wq->private_data;
+	idxd = iaa_wq->iaa_device->idxd;
+	pdev = idxd->pdev;
+	dev = &pdev->dev;
+
+	idxd_desc = idxd_alloc_desc(wq, IDXD_OP_BLOCK);
+	if (IS_ERR(idxd_desc)) {
+		dev_dbg(dev, "idxd descriptor allocation failed\n");
+		dev_dbg(dev, "iaa compress failed: ret=%ld\n", PTR_ERR(idxd_desc));
+		return PTR_ERR(idxd_desc);
+	}
+	desc = idxd_desc->iax_hw;
+
+	desc->flags = IDXD_OP_FLAG_CRAV | IDXD_OP_FLAG_RCR |
+		IDXD_OP_FLAG_RD_SRC2_AECS | IDXD_OP_FLAG_CC;
+	desc->opcode = IAX_OPCODE_COMPRESS;
+	desc->compr_flags = IAA_COMP_FLAGS;
+	desc->priv = 1;
+
+	desc->src1_addr = (u64)src_addr;
+	desc->src1_size = slen;
+	desc->dst_addr = (u64)dst_addr;
+	desc->max_dst_size = *dlen;
+	desc->src2_addr = iaa_wq->iaa_device->active_compression_mode->aecs_comp_table_dma_addr;
+	desc->src2_size = sizeof(struct aecs_comp_table_record);
+	desc->completion_addr = idxd_desc->compl_dma;
+
+	dev_dbg(dev, "%s: compression mode %s,"
+		" desc->src1_addr %llx, desc->src1_size %d,"
+		" desc->dst_addr %llx, desc->max_dst_size %d,"
+		" desc->src2_addr %llx, desc->src2_size %d\n", __func__,
+		iaa_wq->iaa_device->active_compression_mode->name,
+		desc->src1_addr, desc->src1_size, desc->dst_addr,
+		desc->max_dst_size, desc->src2_addr, desc->src2_size);
+
+	ret = idxd_submit_desc(wq, idxd_desc);
+	if (ret) {
+		dev_dbg(dev, "submit_desc failed ret=%d\n", ret);
+		goto err;
+	}
+
+	ret = check_completion(dev, idxd_desc->iax_completion, true, false);
+	if (ret) {
+		dev_dbg(dev, "check_completion failed ret=%d\n", ret);
+		goto err;
+	}
+
+	*dlen = idxd_desc->iax_completion->output_size;
+
+	*compression_crc = idxd_desc->iax_completion->crc;
+
+	idxd_free_desc(wq, idxd_desc);
+out:
+	return ret;
+err:
+	idxd_free_desc(wq, idxd_desc);
+	dev_dbg(dev, "iaa compress failed: ret=%d\n", ret);
+
+	goto out;
+}
+
+static int iaa_compress_verify(struct crypto_tfm *tfm, struct acomp_req *req,
+			       struct idxd_wq *wq,
+			       dma_addr_t src_addr, unsigned int slen,
+			       dma_addr_t dst_addr, unsigned int *dlen,
+			       u32 compression_crc)
+{
+	struct idxd_desc *idxd_desc;
+	struct iax_hw_desc *desc;
+	struct idxd_device *idxd;
+	struct iaa_wq *iaa_wq;
+	struct pci_dev *pdev;
+	struct device *dev;
+	int ret = 0;
+
+	iaa_wq = wq->private_data;
+	idxd = iaa_wq->iaa_device->idxd;
+	pdev = idxd->pdev;
+	dev = &pdev->dev;
+
+	idxd_desc = idxd_alloc_desc(wq, IDXD_OP_BLOCK);
+	if (IS_ERR(idxd_desc)) {
+		dev_dbg(dev, "idxd descriptor allocation failed\n");
+		dev_dbg(dev, "iaa compress failed: ret=%ld\n",
+			PTR_ERR(idxd_desc));
+		return PTR_ERR(idxd_desc);
+	}
+	desc = idxd_desc->iax_hw;
+
+	/* Verify (optional) - decompress and check crc, suppress dest write */
+
+	desc->flags = IDXD_OP_FLAG_CRAV | IDXD_OP_FLAG_RCR | IDXD_OP_FLAG_CC;
+	desc->opcode = IAX_OPCODE_DECOMPRESS;
+	desc->decompr_flags = IAA_DECOMP_FLAGS | IAA_DECOMP_SUPPRESS_OUTPUT;
+	desc->priv = 1;
+
+	desc->src1_addr = (u64)dst_addr;
+	desc->src1_size = *dlen;
+	desc->dst_addr = (u64)src_addr;
+	desc->max_dst_size = slen;
+	desc->completion_addr = idxd_desc->compl_dma;
+
+	dev_dbg(dev, "(verify) compression mode %s,"
+		" desc->src1_addr %llx, desc->src1_size %d,"
+		" desc->dst_addr %llx, desc->max_dst_size %d,"
+		" desc->src2_addr %llx, desc->src2_size %d\n",
+		iaa_wq->iaa_device->active_compression_mode->name,
+		desc->src1_addr, desc->src1_size, desc->dst_addr,
+		desc->max_dst_size, desc->src2_addr, desc->src2_size);
+
+	ret = idxd_submit_desc(wq, idxd_desc);
+	if (ret) {
+		dev_dbg(dev, "submit_desc (verify) failed ret=%d\n", ret);
+		goto err;
+	}
+
+	ret = check_completion(dev, idxd_desc->iax_completion, false, false);
+	if (ret) {
+		dev_dbg(dev, "(verify) check_completion failed ret=%d\n", ret);
+		goto err;
+	}
+
+	if (compression_crc != idxd_desc->iax_completion->crc) {
+		ret = -EINVAL;
+		dev_dbg(dev, "(verify) iaa comp/decomp crc mismatch:"
+			" comp=0x%x, decomp=0x%x\n", compression_crc,
+			idxd_desc->iax_completion->crc);
+		print_hex_dump(KERN_INFO, "cmp-rec: ", DUMP_PREFIX_OFFSET,
+			       8, 1, idxd_desc->iax_completion, 64, 0);
+		goto err;
+	}
+
+	idxd_free_desc(wq, idxd_desc);
+out:
+	return ret;
+err:
+	idxd_free_desc(wq, idxd_desc);
+	dev_dbg(dev, "iaa compress failed: ret=%d\n", ret);
+
+	goto out;
+}
+
+static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
+			  struct idxd_wq *wq,
+			  dma_addr_t src_addr, unsigned int slen,
+			  dma_addr_t dst_addr, unsigned int *dlen,
+			  bool disable_async)
+{
+	struct idxd_desc *idxd_desc;
+	struct iax_hw_desc *desc;
+	struct idxd_device *idxd;
+	struct iaa_wq *iaa_wq;
+	struct pci_dev *pdev;
+	struct device *dev;
+	int ret = 0;
+
+	iaa_wq = wq->private_data;
+	idxd = iaa_wq->iaa_device->idxd;
+	pdev = idxd->pdev;
+	dev = &pdev->dev;
+
+	idxd_desc = idxd_alloc_desc(wq, IDXD_OP_BLOCK);
+	if (IS_ERR(idxd_desc)) {
+		dev_dbg(dev, "idxd descriptor allocation failed\n");
+		dev_dbg(dev, "iaa decompress failed: ret=%ld\n",
+			PTR_ERR(idxd_desc));
+		return PTR_ERR(idxd_desc);
+	}
+	desc = idxd_desc->iax_hw;
+
+	desc->flags = IDXD_OP_FLAG_CRAV | IDXD_OP_FLAG_RCR | IDXD_OP_FLAG_CC;
+	desc->opcode = IAX_OPCODE_DECOMPRESS;
+	desc->max_dst_size = PAGE_SIZE;
+	desc->decompr_flags = IAA_DECOMP_FLAGS;
+	desc->priv = 1;
+
+	desc->src1_addr = (u64)src_addr;
+	desc->dst_addr = (u64)dst_addr;
+	desc->max_dst_size = *dlen;
+	desc->src1_size = slen;
+	desc->completion_addr = idxd_desc->compl_dma;
+
+	dev_dbg(dev, "%s: decompression mode %s,"
+		" desc->src1_addr %llx, desc->src1_size %d,"
+		" desc->dst_addr %llx, desc->max_dst_size %d,"
+		" desc->src2_addr %llx, desc->src2_size %d\n", __func__,
+		iaa_wq->iaa_device->active_compression_mode->name,
+		desc->src1_addr, desc->src1_size, desc->dst_addr,
+		desc->max_dst_size, desc->src2_addr, desc->src2_size);
+
+	ret = idxd_submit_desc(wq, idxd_desc);
+	if (ret) {
+		dev_dbg(dev, "submit_desc failed ret=%d\n", ret);
+		goto err;
+	}
+
+	ret = check_completion(dev, idxd_desc->iax_completion, false, false);
+	if (ret) {
+		dev_dbg(dev, "check_completion failed ret=%d\n", ret);
+		goto err;
+	}
+
+	*dlen = idxd_desc->iax_completion->output_size;
+
+	idxd_free_desc(wq, idxd_desc);
+out:
+	return ret;
+err:
+	idxd_free_desc(wq, idxd_desc);
+	dev_dbg(dev, "iaa decompress failed: ret=%d\n", ret);
+
+	goto out;
+}
+
+static int iaa_comp_acompress(struct acomp_req *req)
+{
+	struct crypto_tfm *tfm = req->base.tfm;
+	dma_addr_t src_addr, dst_addr;
+	int nr_sgs, cpu, ret = 0;
+	struct iaa_wq *iaa_wq;
+	u32 compression_crc;
+	struct idxd_wq *wq;
+	struct device *dev;
+
+	if (!iaa_crypto_enabled) {
+		pr_debug("iaa_crypto disabled, not compressing\n");
+		return -ENODEV;
+	}
+
+	if (!req->src || !req->slen) {
+		pr_debug("invalid src, not compressing\n");
+		return -EINVAL;
+	}
+
+	if (!req->dst) {
+		gfp_t flags = req->flags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL : GFP_ATOMIC;
+		/* incompressible data will always be < 2 * slen */
+		req->dlen = 2 * req->slen;
+		req->dst = sgl_alloc(req->dlen, flags, NULL);
+		if (!req->dst)
+			return -ENOMEM;
+	}
+
+	cpu = get_cpu();
+	wq = wq_table_next_wq(cpu);
+	put_cpu();
+	if (!wq) {
+		pr_debug("no wq configured for cpu=%d\n", cpu);
+		ret = -ENODEV;
+		goto out;
+	}
+	iaa_wq = wq->private_data;
+
+	dev = &wq->idxd->pdev->dev;
+
+	nr_sgs = dma_map_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
+	if (nr_sgs <= 0 || nr_sgs > 1) {
+		dev_dbg(dev, "couldn't map src sg for iaa device %d,"
+			" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
+			iaa_wq->wq->id, ret);
+		ret = -EIO;
+		goto out;
+	}
+	src_addr = sg_dma_address(req->src);
+	dev_dbg(dev, "dma_map_sg, src_addr %llx, nr_sgs %d, req->src %p,"
+		" req->slen %d, sg_dma_len(sg) %d\n", src_addr, nr_sgs,
+		req->src, req->slen, sg_dma_len(req->src));
+
+	nr_sgs = dma_map_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
+	if (nr_sgs <= 0 || nr_sgs > 1) {
+		dev_dbg(dev, "couldn't map dst sg for iaa device %d,"
+			" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
+			iaa_wq->wq->id, ret);
+		ret = -EIO;
+		goto err_map_dst;
+	}
+	dst_addr = sg_dma_address(req->dst);
+	dev_dbg(dev, "dma_map_sg, dst_addr %llx, nr_sgs %d, req->dst %p,"
+		" req->dlen %d, sg_dma_len(sg) %d\n", dst_addr, nr_sgs,
+		req->dst, req->dlen, sg_dma_len(req->dst));
+
+	ret = iaa_compress(tfm, req, wq, src_addr, req->slen, dst_addr,
+			   &req->dlen, &compression_crc, false);
+	if (ret == -EINPROGRESS)
+		goto out;
+
+	if (!ret && iaa_verify_compress) {
+		dma_sync_sg_for_device(dev, req->dst, 1, DMA_FROM_DEVICE);
+		dma_sync_sg_for_device(dev, req->src, 1, DMA_TO_DEVICE);
+		ret = iaa_compress_verify(tfm, req, wq, src_addr, req->slen,
+					  dst_addr, &req->dlen, compression_crc);
+	}
+
+	if (ret)
+		dev_dbg(dev, "asynchronous compress failed ret=%d\n", ret);
+
+	dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
+err_map_dst:
+	dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
+out:
+	return ret;
+}
+
+static int iaa_comp_adecompress_alloc_dest(struct acomp_req *req)
+{
+	gfp_t flags = req->flags & CRYPTO_TFM_REQ_MAY_SLEEP ?
+		GFP_KERNEL : GFP_ATOMIC;
+	struct crypto_tfm *tfm = req->base.tfm;
+	dma_addr_t src_addr, dst_addr;
+	int nr_sgs, cpu, ret = 0;
+	struct iaa_wq *iaa_wq;
+	struct device *dev;
+	struct idxd_wq *wq;
+
+	cpu = get_cpu();
+	wq = wq_table_next_wq(cpu);
+	put_cpu();
+	if (!wq) {
+		pr_debug("no wq configured for cpu=%d\n", cpu);
+		ret = -ENODEV;
+		goto out;
+	}
+	iaa_wq = wq->private_data;
+
+	dev = &wq->idxd->pdev->dev;
+
+	nr_sgs = dma_map_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
+	if (nr_sgs <= 0 || nr_sgs > 1) {
+		dev_dbg(dev, "couldn't map src sg for iaa device %d,"
+			" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
+			iaa_wq->wq->id, ret);
+		ret = -EIO;
+		goto out;
+	}
+	src_addr = sg_dma_address(req->src);
+	dev_dbg(dev, "dma_map_sg, src_addr %llx, nr_sgs %d, req->src %p,"
+		" req->slen %d, sg_dma_len(sg) %d\n", src_addr, nr_sgs,
+		req->src, req->slen, sg_dma_len(req->src));
+
+	req->dlen = 4 * req->slen; /* start with ~avg comp rato */
+alloc_dest:
+	req->dst = sgl_alloc(req->dlen, flags, NULL);
+	if (!req->dst)
+		return -ENOMEM;
+
+	nr_sgs = dma_map_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
+	if (nr_sgs <= 0 || nr_sgs > 1) {
+		dev_dbg(dev, "couldn't map dst sg for iaa device %d,"
+			" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
+			iaa_wq->wq->id, ret);
+		ret = -EIO;
+		goto err_map_dst;
+	}
+
+	dst_addr = sg_dma_address(req->dst);
+	dev_dbg(dev, "dma_map_sg, dst_addr %llx, nr_sgs %d, req->dst %p,"
+		" req->dlen %d, sg_dma_len(sg) %d\n", dst_addr, nr_sgs,
+		req->dst, req->dlen, sg_dma_len(req->dst));
+	ret = iaa_decompress(tfm, req, wq, src_addr, req->slen,
+			     dst_addr, &req->dlen, true);
+	if (ret == -EOVERFLOW) {
+		dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
+		sgl_free(req->dst);
+		req->dlen *= 2;
+		if (req->dlen > CRYPTO_ACOMP_DST_MAX)
+			goto err_map_dst;
+		goto alloc_dest;
+	}
+
+	if (ret != 0)
+		dev_dbg(dev, "asynchronous decompress failed ret=%d\n", ret);
+
+	dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
+err_map_dst:
+	dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
+out:
+	return ret;
+}
+
+static int iaa_comp_adecompress(struct acomp_req *req)
+{
+	struct crypto_tfm *tfm = req->base.tfm;
+	dma_addr_t src_addr, dst_addr;
+	int nr_sgs, cpu, ret = 0;
+	struct iaa_wq *iaa_wq;
+	struct device *dev;
+	struct idxd_wq *wq;
+
+	if (!iaa_crypto_enabled) {
+		pr_debug("iaa_crypto disabled, not decompressing\n");
+		return -ENODEV;
+	}
+
+	if (!req->src || !req->slen) {
+		pr_debug("invalid src, not decompressing\n");
+		return -EINVAL;
+	}
+
+	if (!req->dst)
+		return iaa_comp_adecompress_alloc_dest(req);
+
+	cpu = get_cpu();
+	wq = wq_table_next_wq(cpu);
+	put_cpu();
+	if (!wq) {
+		pr_debug("no wq configured for cpu=%d\n", cpu);
+		ret = -ENODEV;
+		goto out;
+	}
+	iaa_wq = wq->private_data;
+
+	dev = &wq->idxd->pdev->dev;
+
+	nr_sgs = dma_map_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
+	if (nr_sgs <= 0 || nr_sgs > 1) {
+		dev_dbg(dev, "couldn't map src sg for iaa device %d,"
+			" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
+			iaa_wq->wq->id, ret);
+		ret = -EIO;
+		goto out;
+	}
+	src_addr = sg_dma_address(req->src);
+	dev_dbg(dev, "dma_map_sg, src_addr %llx, nr_sgs %d, req->src %p,"
+		" req->slen %d, sg_dma_len(sg) %d\n", src_addr, nr_sgs,
+		req->src, req->slen, sg_dma_len(req->src));
+
+	nr_sgs = dma_map_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
+	if (nr_sgs <= 0 || nr_sgs > 1) {
+		dev_dbg(dev, "couldn't map dst sg for iaa device %d,"
+			" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
+			iaa_wq->wq->id, ret);
+		ret = -EIO;
+		goto err_map_dst;
+	}
+	dst_addr = sg_dma_address(req->dst);
+	dev_dbg(dev, "dma_map_sg, dst_addr %llx, nr_sgs %d, req->dst %p,"
+		" req->dlen %d, sg_dma_len(sg) %d\n", dst_addr, nr_sgs,
+		req->dst, req->dlen, sg_dma_len(req->dst));
+
+	ret = iaa_decompress(tfm, req, wq, src_addr, req->slen,
+			     dst_addr, &req->dlen, false);
+	if (ret == -EINPROGRESS)
+		goto out;
+
+	if (ret != 0)
+		dev_dbg(dev, "asynchronous decompress failed ret=%d\n", ret);
+
+	dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
+err_map_dst:
+	dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
+out:
+	return ret;
+}
+
+static struct acomp_alg iaa_acomp_deflate = {
+	.compress		= iaa_comp_acompress,
+	.decompress		= iaa_comp_adecompress,
+	.dst_free		= sgl_free,
+	.base			= {
+		.cra_name		= "deflate",
+		.cra_driver_name	= "iaa_crypto",
+		.cra_module		= THIS_MODULE,
+		.cra_priority           = IAA_ALG_PRIORITY,
+	}
+};
+
+static int iaa_register_compression_device(void)
+{
+	int ret;
+
+	ret = crypto_register_acomp(&iaa_acomp_deflate);
+	if (ret)
+		pr_err("deflate algorithm acomp registration failed (%d)\n", ret);
+
+	return ret;
+}
+
+static int iaa_unregister_compression_device(void)
+{
+	if (refcount_read(&iaa_acomp_deflate.base.cra_refcnt) > 1)
+		return -EBUSY;
+
+	crypto_unregister_acomp(&iaa_acomp_deflate);
+
+	return 0;
+}
+
 static int iaa_crypto_probe(struct idxd_dev *idxd_dev)
 {
 	struct idxd_wq *wq = idxd_dev_to_wq(idxd_dev);
@@ -881,12 +1574,26 @@ static int iaa_crypto_probe(struct idxd_dev *idxd_dev)
 
 	rebalance_wq_table();
 
+	if (first_wq) {
+		iaa_crypto_enabled = true;
+		ret = iaa_register_compression_device();
+		if (ret != 0) {
+			iaa_crypto_enabled = false;
+			dev_dbg(dev, "IAA compression device registration failed\n");
+			goto err_register;
+		}
+
+		pr_info("iaa_crypto now ENABLED\n");
+	}
+
 	mutex_unlock(&iaa_devices_lock);
 out:
 	mutex_unlock(&wq->wq_lock);
 
 	return ret;
 
+err_register:
+	remove_iaa_wq(wq);
 err_save:
 	if (first_wq)
 		free_wq_table();
@@ -902,6 +1609,7 @@ static int iaa_crypto_probe(struct idxd_dev *idxd_dev)
 static void iaa_crypto_remove(struct idxd_dev *idxd_dev)
 {
 	struct idxd_wq *wq = idxd_dev_to_wq(idxd_dev);
+	struct device *dev = &idxd_dev->conf_dev;
 
 	idxd_wq_quiesce(wq);
 
@@ -912,9 +1620,16 @@ static void iaa_crypto_remove(struct idxd_dev *idxd_dev)
 	drv_disable_wq(wq);
 	rebalance_wq_table();
 
-	if (nr_iaa == 0)
+	if (nr_iaa == 0) {
+		iaa_crypto_enabled = false;
 		free_wq_table();
 
+		if (iaa_unregister_compression_device())
+			dev_dbg(dev, "IAA compression device unregister failed\n");
+
+		pr_info("iaa_crypto now DISABLED\n");
+	}
+
 	mutex_unlock(&iaa_devices_lock);
 	mutex_unlock(&wq->wq_lock);
 }
@@ -952,6 +1667,13 @@ static int __init iaa_crypto_init_module(void)
 		goto err_attr_create;
 	}
 
+	ret = driver_create_file(&iaa_crypto_driver.drv,
+				 &driver_attr_verify_compress);
+	if (ret) {
+		pr_debug("IAA verify_compress attr creation failed\n");
+		goto err_attr_create;
+	}
+
 	ret = iaa_aecs_init_fixed();
 	if (ret < 0) {
 		pr_debug("IAA fixed compression mode init failed\n");
@@ -965,6 +1687,8 @@ static int __init iaa_crypto_init_module(void)
 err_compression_mode:
 	driver_remove_file(&iaa_crypto_driver.drv,
 			   &driver_attr_compression_mode);
+	driver_remove_file(&iaa_crypto_driver.drv,
+			   &driver_attr_verify_compress);
 err_attr_create:
 	idxd_driver_unregister(&iaa_crypto_driver);
 
@@ -975,6 +1699,8 @@ static void __exit iaa_crypto_cleanup_module(void)
 {
 	driver_remove_file(&iaa_crypto_driver.drv,
 			   &driver_attr_compression_mode);
+	driver_remove_file(&iaa_crypto_driver.drv,
+			   &driver_attr_verify_compress);
 	idxd_driver_unregister(&iaa_crypto_driver);
 	iaa_aecs_cleanup_fixed();
 
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH v2 13/15] crypto: iaa - Add support for default IAA 'canned' compression mode
  2023-03-28 15:35 [PATCH v2 00/15] crypto: Add Intel Analytics Accelerator (IAA) crypto compression driver Tom Zanussi
                   ` (11 preceding siblings ...)
  2023-03-28 15:35 ` [PATCH v2 12/15] crypto: iaa - Add support for iaa_crypto deflate compression algorithm Tom Zanussi
@ 2023-03-28 15:35 ` Tom Zanussi
  2023-03-28 15:35 ` [PATCH v2 14/15] crypto: iaa - Add irq support for the crypto async interface Tom Zanussi
                   ` (2 subsequent siblings)
  15 siblings, 0 replies; 25+ messages in thread
From: Tom Zanussi @ 2023-03-28 15:35 UTC (permalink / raw)
  To: herbert, davem, fenghua.yu, vkoul
  Cc: dave.jiang, tony.luck, wajdi.k.feghali, james.guilford,
	kanchana.p.sridhar, giovanni.cabiddu, linux-kernel, linux-crypto,
	dmaengine

Add support for a 'canned' compression mode using the IAA compression
mode in-kernel API.

The IAA 'canned' compression mode is added alongside the existing
'fixed' compression mode and is named simply 'canned'.  It implements
a good general-purpose compression scheme whose tables were generated
from statistics derived from a wide variety of SPEC17 workloads.

It provides much better overall characteristics than the existing
deflate-1951 tables implemented by 'fixed'.

Either 'fixed' or 'canned' modes can be chosen as the mode to be used
for compression/decompression via the iaa_crypto compression_mode
iaa_crypto driver attribute:

To choose 'fixed' mode:

  echo "fixed" >  /sys/bus/dsa/drivers/crypto/compression_mode

To choose 'canned' mode:

  echo "canned" >  /sys/bus/dsa/drivers/crypto/compression_mode

[ Based on work originally by George Powley, Jing Lin and Kyung Min
Park ]

Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
---
 crypto/testmgr.c                              |  10 ++
 crypto/testmgr.h                              |  72 ++++++++++++
 drivers/crypto/intel/iaa/Makefile             |   2 +-
 drivers/crypto/intel/iaa/iaa_crypto.h         |   2 +
 .../crypto/intel/iaa/iaa_crypto_comp_canned.c | 110 ++++++++++++++++++
 drivers/crypto/intel/iaa/iaa_crypto_main.c    |  43 ++++++-
 6 files changed, 236 insertions(+), 3 deletions(-)
 create mode 100644 drivers/crypto/intel/iaa/iaa_crypto_comp_canned.c

diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index c91e93ece20b..e10bc9581d86 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -5235,6 +5235,16 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.suite = {
 			.hash = __VECS(hmac_streebog512_tv_template)
 		}
+	}, {
+		.alg = "iaa-canned-deflate",
+		.test = alg_test_comp,
+		.fips_allowed = 1,
+		.suite = {
+			.comp = {
+				.comp = __VECS(iaa_canned_deflate_comp_tv_template),
+				.decomp = __VECS(iaa_canned_deflate_decomp_tv_template)
+			}
+		}
 	}, {
 		.alg = "jitterentropy_rng",
 		.fips_allowed = 1,
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index f10bfb9d9973..9a26fcc3364f 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -35782,6 +35782,78 @@ static const struct comp_testvec zlib_deflate_decomp_tv_template[] = {
 	},
 };
 
+static const struct comp_testvec iaa_canned_deflate_comp_tv_template[] = {
+	{
+		.inlen	= 70,
+		.outlen	= 37,
+		.input	= "Join us now and share the software "
+			"Join us now and share the software ",
+		.output	= "\x6d\x23\x43\x23\xa4\x71\x31\xd2"
+			  "\x88\xc8\x61\x52\x75\x84\x56\x1a"
+			  "\x13\xa2\x8e\xd6\x49\x63\x43\x74"
+			  "\xd2\x98\xc8\xe0\xd8\x61\x58\x69"
+			  "\xcb\x71\x01\xe5\x7f",
+	}, {
+		.inlen	= 191,
+		.outlen	= 128,
+		.input	= "This document describes a compression method based on the DEFLATE"
+			"compression algorithm.  This document defines the application of "
+			"the DEFLATE algorithm to the IP Payload Compression Protocol.",
+		.output	= "\xdd\x42\x42\x63\xa4\xda\x48\x4d"
+			  "\x5c\xb8\x2e\x22\x56\xaa\xd5\xc5"
+			  "\x68\xa2\x43\x83\x74\x31\x52\xb5"
+			  "\x54\x13\x19\x1e\x15\xad\x8b\x89"
+			  "\x09\x8d\x8c\x90\x86\xeb\x62\x43"
+			  "\x22\xb5\xd2\x20\x75\x8c\x4e\x2b"
+			  "\x05\x3d\x36\x44\x27\xf5\x69\xe5"
+			  "\xdb\xde\xbb\x5b\x2b\x7d\x37\x75"
+			  "\xd8\xc0\xc8\xe8\xd0\xd8\x90\x70"
+			  "\x7b\xa9\x54\x1c\x38\x38\x34\x02"
+			  "\xc2\xe2\x8e\xea\xa8\xa8\xb0\x50"
+			  "\x8d\x3a\x16\xf7\x88\x0c\xd6\x8f"
+			  "\x95\x1f\x40\x1a\x1b\x29\x34\xb4"
+			  "\xf1\x97\xfa\xab\x87\x87\x45\xaa"
+			  "\xb5\xd2\x96\x7a\x03\xf9\x47\x47"
+			  "\xc6\x46\x6a\x22\xc3\xec\xff\x07",
+	},
+};
+
+static const struct comp_testvec iaa_canned_deflate_decomp_tv_template[] = {
+	{
+		.inlen	= 128,
+		.outlen	= 191,
+		.input	= "\xdd\x42\x42\x63\xa4\xda\x48\x4d"
+			  "\x5c\xb8\x2e\x22\x56\xaa\xd5\xc5"
+			  "\x68\xa2\x43\x83\x74\x31\x52\xb5"
+			  "\x54\x13\x19\x1e\x15\xad\x8b\x89"
+			  "\x09\x8d\x8c\x90\x86\xeb\x62\x43"
+			  "\x22\xb5\xd2\x20\x75\x8c\x4e\x2b"
+			  "\x05\x3d\x36\x44\x27\xf5\x69\xe5"
+			  "\xdb\xde\xbb\x5b\x2b\x7d\x37\x75"
+			  "\xd8\xc0\xc8\xe8\xd0\xd8\x90\x70"
+			  "\x7b\xa9\x54\x1c\x38\x38\x34\x02"
+			  "\xc2\xe2\x8e\xea\xa8\xa8\xb0\x50"
+			  "\x8d\x3a\x16\xf7\x88\x0c\xd6\x8f"
+			  "\x95\x1f\x40\x1a\x1b\x29\x34\xb4"
+			  "\xf1\x97\xfa\xab\x87\x87\x45\xaa"
+			  "\xb5\xd2\x96\x7a\x03\xf9\x47\x47"
+			  "\xc6\x46\x6a\x22\xc3\xec\xff\x07",
+		.output	= "This document describes a compression method based on the DEFLATE"
+			"compression algorithm.  This document defines the application of "
+			"the DEFLATE algorithm to the IP Payload Compression Protocol.",
+	}, {
+		.inlen	= 37,
+		.outlen	= 70,
+		.input	= "\x6d\x23\x43\x23\xa4\x71\x31\xd2"
+			  "\x88\xc8\x61\x52\x75\x84\x56\x1a"
+			  "\x13\xa2\x8e\xd6\x49\x63\x43\x74"
+			  "\xd2\x98\xc8\xe0\xd8\x61\x58\x69"
+			  "\xcb\x71\x01\xe5\x7f",
+		.output	= "Join us now and share the software "
+			"Join us now and share the software ",
+	},
+};
+
 /*
  * LZO test vectors (null-terminated strings).
  */
diff --git a/drivers/crypto/intel/iaa/Makefile b/drivers/crypto/intel/iaa/Makefile
index cc87feffd059..ff6ab1d0bc13 100644
--- a/drivers/crypto/intel/iaa/Makefile
+++ b/drivers/crypto/intel/iaa/Makefile
@@ -7,4 +7,4 @@ ccflags-y += -I $(srctree)/drivers/dma/idxd -DDEFAULT_SYMBOL_NAMESPACE=IDXD
 
 obj-$(CONFIG_CRYPTO_DEV_IAA_CRYPTO) := iaa_crypto.o
 
-iaa_crypto-y := iaa_crypto_main.o iaa_crypto_comp_fixed.o
+iaa_crypto-y := iaa_crypto_main.o iaa_crypto_comp_canned.o iaa_crypto_comp_fixed.o
diff --git a/drivers/crypto/intel/iaa/iaa_crypto.h b/drivers/crypto/intel/iaa/iaa_crypto.h
index 7ed3d8de250d..3a04a7bdea8e 100644
--- a/drivers/crypto/intel/iaa/iaa_crypto.h
+++ b/drivers/crypto/intel/iaa/iaa_crypto.h
@@ -112,6 +112,8 @@ struct aecs_decomp_table_record {
 	u32 decomp_state[1220];
 } __packed;
 
+int iaa_aecs_init_canned(void);
+void iaa_aecs_cleanup_canned(void);
 int iaa_aecs_init_fixed(void);
 void iaa_aecs_cleanup_fixed(void);
 
diff --git a/drivers/crypto/intel/iaa/iaa_crypto_comp_canned.c b/drivers/crypto/intel/iaa/iaa_crypto_comp_canned.c
new file mode 100644
index 000000000000..aff0899ffb9e
--- /dev/null
+++ b/drivers/crypto/intel/iaa/iaa_crypto_comp_canned.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2021 Intel Corporation. All rights rsvd. */
+
+#include "idxd.h"
+#include "iaa_crypto.h"
+
+#define IAA_AECS_ALIGN			32
+
+/*
+ * These tables were generated from statistics derived from a wide
+ * variety of SPEC17 workloads and implement a good general-purpose
+ * compression scheme called simply 'canned'.
+ */
+
+static const u32 canned_ll_iaa[286] = {
+0x28002,  0x38024,  0x40066,  0x40067,  0x40068,  0x48144,  0x40069,  0x48145,
+0x4006a,  0x48146,  0x4006b,  0x48147,  0x48148,  0x48149,  0x4814a,  0x4814b,
+0x4006c,  0x4814c,  0x4814d,  0x4814e,  0x4814f,  0x48150,  0x48151,  0x48152,
+0x4006d,  0x48153,  0x48154,  0x48155,  0x48156,  0x48157,  0x48158,  0x48159,
+0x38025,  0x4815a,  0x4815b,  0x4815c,  0x4815d,  0x4815e,  0x4815f,  0x48160,
+0x4006e,  0x48161,  0x48162,  0x48163,  0x48164,  0x48165,  0x4006f,  0x48166,
+0x38026,  0x38027,  0x40070,  0x40071,  0x40072,  0x40073,  0x40074,  0x40075,
+0x38028,  0x40076,  0x40077,  0x48167,  0x40078,  0x40079,  0x4007a,  0x38029,
+0x3802a,  0x4007b,  0x48168,  0x48169,  0x4007c,  0x4816a,  0x4007d,  0x4816b,
+0x4007e,  0x4816c,  0x4816d,  0x4816e,  0x4816f,  0x48170,  0x48171,  0x48172,
+0x4007f,  0x48173,  0x48174,  0x48175,  0x48176,  0x48177,  0x48178,  0x48179,
+0x40080,  0x4817a,  0x4817b,  0x4817c,  0x4817d,  0x4817e,  0x4817f,  0x48180,
+0x40081,  0x3802b,  0x40082,  0x3802c,  0x3802d,  0x3802e,  0x40083,  0x48181,
+0x40084,  0x40085,  0x48182,  0x48183,  0x40086,  0x40087,  0x40088,  0x40089,
+0x4008a,  0x48184,  0x4008b,  0x4008c,  0x4008d,  0x4008e,  0x48185,  0x48186,
+0x4008f,  0x48187,  0x48188,  0x48189,  0x4818a,  0x4818b,  0x4818c,  0x4818d,
+0x40090,  0x4818e,  0x4818f,  0x48190,  0x48191,  0x48192,  0x48193,  0x48194,
+0x40091,  0x48195,  0x48196,  0x48197,  0x48198,  0x48199,  0x4819a,  0x4819b,
+0x40092,  0x4819c,  0x4819d,  0x4819e,  0x4819f,  0x481a0,  0x481a1,  0x481a2,
+0x40093,  0x481a3,  0x481a4,  0x481a5,  0x481a6,  0x481a7,  0x481a8,  0x481a9,
+0x40094,  0x481aa,  0x481ab,  0x481ac,  0x481ad,  0x481ae,  0x481af,  0x481b0,
+0x481b1,  0x481b2,  0x481b3,  0x481b4,  0x481b5,  0x481b6,  0x481b7,  0x481b8,
+0x40095,  0x481b9,  0x481ba,  0x481bb,  0x481bc,  0x481bd,  0x481be,  0x481bf,
+0x40096,  0x481c0,  0x481c1,  0x481c2,  0x481c3,  0x481c4,  0x481c5,  0x40097,
+0x40098,  0x481c6,  0x481c7,  0x481c8,  0x481c9,  0x481ca,  0x481cb,  0x481cc,
+0x40099,  0x481cd,  0x481ce,  0x481cf,  0x481d0,  0x481d1,  0x481d2,  0x481d3,
+0x4009a,  0x481d4,  0x481d5,  0x481d6,  0x481d7,  0x481d8,  0x481d9,  0x481da,
+0x481db,  0x481dc,  0x481dd,  0x481de,  0x481df,  0x481e0,  0x481e1,  0x481e2,
+0x4009b,  0x481e3,  0x481e4,  0x481e5,  0x481e6,  0x481e7,  0x481e8,  0x481e9,
+0x481ea,  0x481eb,  0x481ec,  0x481ed,  0x481ee,  0x481ef,  0x481f0,  0x481f1,
+0x4009c,  0x481f2,  0x481f3,  0x481f4,  0x481f5,  0x481f6,  0x481f7,  0x481f8,
+0x481f9,  0x481fa,  0x481fb,  0x503fe,  0x481fc,  0x481fd,  0x481fe,  0x4009d,
+0x503ff,  0x20000,  0x28003,  0x30010,  0x28004,  0x28005,  0x28006,  0x4009e,
+0x4009f,  0x3802f,  0x38030,  0x30011,  0x400a0,  0x38031,  0x38032,  0x400a1,
+0x28007,  0x0,  0x0,  0x0,  0x0,  0x0,  0x0,  0x0,
+0x0,  0x0,  0x0,  0x0,  0x0,  0x0,
+};
+
+static const u32 canned_d_iaa[30] = {
+0x3807e,  0x20004,  0x481fe,  0x18000,  0x400fe,  0x18001,  0x3003c,  0x20005,
+0x20006,  0x28016,  0x20007,  0x28017,  0x20008,  0x28018,  0x28019,  0x20009,
+0x2000a,  0x2801a,  0x2801b,  0x2801c,  0x2801d,  0x3003d,  0x3003e,  0x481ff,
+0x0,  0x0,  0x0,  0x0,  0x0,  0x0,
+};
+
+#define CANNED_HEADER_SIZE (71)
+
+static const u8 canned_header[] = {
+0x85, 0xd7, 0x05, 0x40, 0x54, 0x4d, 0x10, 0x06,
+0x80, 0x3d, 0x40, 0x44, 0x2c, 0x6c, 0xec, 0xb3,
+0xb1, 0xf0, 0x8e, 0x3c, 0x10, 0xb8, 0x43, 0x11,
+0xb1, 0xb1, 0xb1, 0x39, 0xee, 0x0e, 0x41, 0x29,
+0x09, 0xc5, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x6e,
+0xc5, 0xc6, 0x04, 0x1b, 0x1b, 0xbb, 0x15, 0xbb,
+0x15, 0x3b, 0x7e, 0x95, 0x7f, 0xf6, 0xed, 0x2e,
+0xdc, 0x3d, 0xee, 0xd8, 0x1b, 0x3f, 0xbe, 0x37,
+0xb3, 0xb3, 0xb3, 0x3b, 0xb3, 0xf1, 0x9e,
+};
+
+#define HEADER_SIZE_IN_BITS 568
+
+#define CEIL(a, b)     (((a) + ((b) - 1)) / (b))
+
+int iaa_aecs_init_canned(void)
+{
+	u16 gen_decomp_table_flags;
+	unsigned int slen;
+	int ret;
+
+	slen = CEIL(HEADER_SIZE_IN_BITS, 8);
+
+	gen_decomp_table_flags = 0x1;
+	gen_decomp_table_flags |= 1 << 9; // suppress output
+	gen_decomp_table_flags |= (((slen * 8) - HEADER_SIZE_IN_BITS) << 6);
+
+	ret = add_iaa_compression_mode("canned",
+				       canned_ll_iaa,
+				       sizeof(canned_ll_iaa),
+				       canned_d_iaa,
+				       sizeof(canned_d_iaa),
+				       canned_header,
+				       sizeof(canned_header),
+				       gen_decomp_table_flags,
+				       NULL, NULL);
+
+	if (!ret)
+		pr_debug("IAA canned compression mode initialized\n");
+
+	return ret;
+}
+
+void iaa_aecs_cleanup_canned(void)
+{
+	remove_iaa_compression_mode("canned");
+}
diff --git a/drivers/crypto/intel/iaa/iaa_crypto_main.c b/drivers/crypto/intel/iaa/iaa_crypto_main.c
index d0b1ac45cc51..b6d41642f0dd 100644
--- a/drivers/crypto/intel/iaa/iaa_crypto_main.c
+++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c
@@ -119,11 +119,16 @@ static DRIVER_ATTR_RW(verify_compress);
 static struct iaa_compression_mode *iaa_compression_modes[IAA_COMP_MODES_MAX];
 static int active_compression_mode;
 
+static bool canned_mode = true;
+
 static ssize_t compression_mode_show(struct device_driver *driver, char *buf)
 {
 	int ret = 0;
 
-	ret = sprintf(buf, "%s\n", "fixed");
+	if (canned_mode)
+		ret = sprintf(buf, "%s\n", "canned");
+	else
+		ret = sprintf(buf, "%s\n", "fixed");
 
 	return ret;
 }
@@ -382,6 +387,12 @@ int set_iaa_compression_mode(const char *name)
 		ret = 0;
 	}
 
+	if (ret == 0 && !strcmp(name, "canned"))
+		canned_mode = true;
+
+	if (ret == 0 && !strcmp(name, "fixed"))
+		canned_mode = false;
+
 	return ret;
 }
 
@@ -1109,6 +1120,7 @@ static int iaa_compress_verify(struct crypto_tfm *tfm, struct acomp_req *req,
 	struct idxd_device *idxd;
 	struct iaa_wq *iaa_wq;
 	struct pci_dev *pdev;
+	dma_addr_t src2_addr;
 	struct device *dev;
 	int ret = 0;
 
@@ -1139,6 +1151,13 @@ static int iaa_compress_verify(struct crypto_tfm *tfm, struct acomp_req *req,
 	desc->max_dst_size = slen;
 	desc->completion_addr = idxd_desc->compl_dma;
 
+	if (canned_mode) {
+		src2_addr = iaa_wq->iaa_device->active_compression_mode->aecs_decomp_table_dma_addr;
+		desc->src2_addr = (u64)src2_addr;
+		desc->src2_size = 1088;
+		desc->flags |= IDXD_OP_FLAG_RD_SRC2_AECS;
+	}
+
 	dev_dbg(dev, "(verify) compression mode %s,"
 		" desc->src1_addr %llx, desc->src1_size %d,"
 		" desc->dst_addr %llx, desc->max_dst_size %d,"
@@ -1190,6 +1209,7 @@ static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
 	struct idxd_device *idxd;
 	struct iaa_wq *iaa_wq;
 	struct pci_dev *pdev;
+	dma_addr_t src2_addr;
 	struct device *dev;
 	int ret = 0;
 
@@ -1219,6 +1239,13 @@ static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
 	desc->src1_size = slen;
 	desc->completion_addr = idxd_desc->compl_dma;
 
+	if (canned_mode) {
+		src2_addr = iaa_wq->iaa_device->active_compression_mode->aecs_decomp_table_dma_addr;
+		desc->src2_addr = (u64)src2_addr;
+		desc->src2_size = 1088;
+		desc->flags |= IDXD_OP_FLAG_RD_SRC2_AECS;
+	}
+
 	dev_dbg(dev, "%s: decompression mode %s,"
 		" desc->src1_addr %llx, desc->src1_size %d,"
 		" desc->dst_addr %llx, desc->max_dst_size %d,"
@@ -1496,7 +1523,6 @@ static struct acomp_alg iaa_acomp_deflate = {
 	.decompress		= iaa_comp_adecompress,
 	.dst_free		= sgl_free,
 	.base			= {
-		.cra_name		= "deflate",
 		.cra_driver_name	= "iaa_crypto",
 		.cra_module		= THIS_MODULE,
 		.cra_priority           = IAA_ALG_PRIORITY,
@@ -1507,6 +1533,11 @@ static int iaa_register_compression_device(void)
 {
 	int ret;
 
+	if (canned_mode)
+		strcpy(iaa_acomp_deflate.base.cra_name, "iaa-canned-deflate");
+	else
+		strcpy(iaa_acomp_deflate.base.cra_name, "deflate");
+
 	ret = crypto_register_acomp(&iaa_acomp_deflate);
 	if (ret)
 		pr_err("deflate algorithm acomp registration failed (%d)\n", ret);
@@ -1674,8 +1705,15 @@ static int __init iaa_crypto_init_module(void)
 		goto err_attr_create;
 	}
 
+	ret = iaa_aecs_init_canned();
+	if (ret < 0) {
+		pr_debug("IAA canned compression mode init failed\n");
+		goto err_compression_mode;
+	}
+
 	ret = iaa_aecs_init_fixed();
 	if (ret < 0) {
+		iaa_aecs_cleanup_canned();
 		pr_debug("IAA fixed compression mode init failed\n");
 		goto err_compression_mode;
 	}
@@ -1702,6 +1740,7 @@ static void __exit iaa_crypto_cleanup_module(void)
 	driver_remove_file(&iaa_crypto_driver.drv,
 			   &driver_attr_verify_compress);
 	idxd_driver_unregister(&iaa_crypto_driver);
+	iaa_aecs_cleanup_canned();
 	iaa_aecs_cleanup_fixed();
 
 	pr_debug("cleaned up\n");
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH v2 14/15] crypto: iaa - Add irq support for the crypto async interface
  2023-03-28 15:35 [PATCH v2 00/15] crypto: Add Intel Analytics Accelerator (IAA) crypto compression driver Tom Zanussi
                   ` (12 preceding siblings ...)
  2023-03-28 15:35 ` [PATCH v2 13/15] crypto: iaa - Add support for default IAA 'canned' compression mode Tom Zanussi
@ 2023-03-28 15:35 ` Tom Zanussi
  2023-03-28 15:35 ` [PATCH v2 15/15] crypto: iaa - Add IAA Compression Accelerator stats Tom Zanussi
       [not found] ` <20230329075149.2736-1-hdanton@sina.com>
  15 siblings, 0 replies; 25+ messages in thread
From: Tom Zanussi @ 2023-03-28 15:35 UTC (permalink / raw)
  To: herbert, davem, fenghua.yu, vkoul
  Cc: dave.jiang, tony.luck, wajdi.k.feghali, james.guilford,
	kanchana.p.sridhar, giovanni.cabiddu, linux-kernel, linux-crypto,
	dmaengine

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

Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
---
 drivers/crypto/intel/iaa/iaa_crypto_main.c | 224 ++++++++++++++++++++-
 1 file changed, 222 insertions(+), 2 deletions(-)

diff --git a/drivers/crypto/intel/iaa/iaa_crypto_main.c b/drivers/crypto/intel/iaa/iaa_crypto_main.c
index b6d41642f0dd..7a2c0ed80108 100644
--- a/drivers/crypto/intel/iaa/iaa_crypto_main.c
+++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c
@@ -116,6 +116,102 @@ static ssize_t verify_compress_store(struct device_driver *driver,
 }
 static DRIVER_ATTR_RW(verify_compress);
 
+/*
+ * The iaa crypto driver supports three 'sync' methods determining how
+ * compressions and decompressions are performed:
+ *
+ * - sync:      the compression or decompression completes before
+ *              returning.  This is the mode used by the async crypto
+ *              interface when the sync mode is set to 'sync' and by
+ *              the sync crypto interface regardless of setting.
+ *
+ * - async:     the compression or decompression is submitted and returns
+ *              immediately.  Completion interrupts are not used so
+ *              the caller is responsible for polling the descriptor
+ *              for completion.  This mode is applicable to only the
+ *              async crypto interface and is ignored for anything
+ *              else.
+ *
+ * - async_irq: the compression or decompression is submitted and
+ *              returns immediately.  Completion interrupts are
+ *              enabled so the caller can wait for the completion and
+ *              yield to other threads.  When the compression or
+ *              decompression completes, the completion is signaled
+ *              and the caller awakened.  This mode is applicable to
+ *              only the async crypto interface and is ignored for
+ *              anything else.
+ *
+ * These modes can be set using the iaa_crypto sync_mode driver
+ * attribute.
+ */
+
+/* Use async mode */
+static bool async_mode;
+/* Use interrupts */
+static bool use_irq;
+
+/**
+ * set_iaa_sync_mode - Set IAA sync mode
+ * @name: The name of the sync mode
+ *
+ * Make the IAA sync mode named @name the current sync mode used by
+ * compression/decompression.
+ */
+
+static int set_iaa_sync_mode(const char *name)
+{
+	int ret = 0;
+
+	if (sysfs_streq(name, "sync")) {
+		async_mode = false;
+		use_irq = false;
+	} else if (sysfs_streq(name, "async")) {
+		async_mode = true;
+		use_irq = false;
+	} else if (sysfs_streq(name, "async_irq")) {
+		async_mode = true;
+		use_irq = true;
+	} else {
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static ssize_t sync_mode_show(struct device_driver *driver, char *buf)
+{
+	int ret = 0;
+
+	if (!async_mode && !use_irq)
+		ret = sprintf(buf, "%s\n", "sync");
+	else if (async_mode && !use_irq)
+		ret = sprintf(buf, "%s\n", "async");
+	else if (async_mode && use_irq)
+		ret = sprintf(buf, "%s\n", "async_irq");
+
+	return ret;
+}
+
+static ssize_t sync_mode_store(struct device_driver *driver,
+			       const char *buf, size_t count)
+{
+	int ret = -EBUSY;
+
+	mutex_lock(&iaa_devices_lock);
+
+	if (iaa_crypto_enabled)
+		goto out;
+
+	ret = set_iaa_sync_mode(buf);
+	if (ret == 0)
+		ret = count;
+out:
+	mutex_unlock(&iaa_devices_lock);
+
+	return ret;
+}
+static DRIVER_ATTR_RW(sync_mode);
+
 static struct iaa_compression_mode *iaa_compression_modes[IAA_COMP_MODES_MAX];
 static int active_compression_mode;
 
@@ -1033,6 +1129,72 @@ static inline int check_completion(struct device *dev,
 	return ret;
 }
 
+static int iaa_compress_verify(struct crypto_tfm *tfm, struct acomp_req *req,
+			       struct idxd_wq *wq,
+			       dma_addr_t src_addr, unsigned int slen,
+			       dma_addr_t dst_addr, unsigned int *dlen,
+			       u32 compression_crc);
+
+static void iaa_desc_complete(struct idxd_desc *idxd_desc,
+			      enum idxd_complete_type comp_type,
+			      bool free_desc, void *__ctx,
+			      u32 *status)
+{
+	struct crypto_ctx *ctx = __ctx;
+	struct idxd_device *idxd;
+	struct iaa_wq *iaa_wq;
+	struct pci_dev *pdev;
+	struct device *dev;
+	int ret, err = 0;
+
+	iaa_wq = idxd_desc->wq->private_data;
+	idxd = iaa_wq->iaa_device->idxd;
+	pdev = idxd->pdev;
+	dev = &pdev->dev;
+
+	dev_dbg(dev, "%s: compression mode %s,"
+		" ctx->src_addr %llx, ctx->dst_addr %llx\n", __func__,
+		iaa_wq->iaa_device->active_compression_mode->name,
+		ctx->src_addr, ctx->dst_addr);
+
+	ret = check_completion(dev, idxd_desc->iax_completion,
+			       ctx->compress, false);
+	if (ret) {
+		dev_dbg(dev, "%s: check_completion failed ret=%d\n", __func__, ret);
+		err = -EIO;
+		goto err;
+	}
+
+	ctx->req->dlen = idxd_desc->iax_completion->output_size;
+
+	if (ctx->compress && iaa_verify_compress) {
+		u32 compression_crc;
+
+		compression_crc = idxd_desc->iax_completion->crc;
+		dma_sync_sg_for_device(dev, ctx->req->dst, 1, DMA_FROM_DEVICE);
+		dma_sync_sg_for_device(dev, ctx->req->src, 1, DMA_TO_DEVICE);
+		ret = iaa_compress_verify(ctx->tfm, ctx->req, iaa_wq->wq, ctx->src_addr,
+					  ctx->req->slen, ctx->dst_addr, &ctx->req->dlen,
+					  compression_crc);
+		if (ret) {
+			dev_dbg(dev, "%s: compress verify failed ret=%d\n", __func__, ret);
+			err = -EIO;
+		}
+	}
+err:
+	if (ctx->req->base.complete)
+		acomp_request_complete(ctx->req, err);
+
+	dma_unmap_sg(dev, ctx->req->dst, sg_nents(ctx->req->dst), DMA_FROM_DEVICE);
+	dma_unmap_sg(dev, ctx->req->src, sg_nents(ctx->req->src), DMA_TO_DEVICE);
+
+	if (ret != 0)
+		dev_dbg(dev, "asynchronous compress failed ret=%d\n", ret);
+
+	if (free_desc)
+		idxd_free_desc(idxd_desc->wq, idxd_desc);
+}
+
 static int iaa_compress(struct crypto_tfm *tfm,	struct acomp_req *req,
 			struct idxd_wq *wq,
 			dma_addr_t src_addr, unsigned int slen,
@@ -1075,6 +1237,22 @@ static int iaa_compress(struct crypto_tfm *tfm,	struct acomp_req *req,
 	desc->src2_size = sizeof(struct aecs_comp_table_record);
 	desc->completion_addr = idxd_desc->compl_dma;
 
+	if (use_irq) {
+		desc->flags |= IDXD_OP_FLAG_RCI;
+
+		idxd_desc->crypto.req = req;
+		idxd_desc->crypto.tfm = tfm;
+		idxd_desc->crypto.src_addr = src_addr;
+		idxd_desc->crypto.dst_addr = dst_addr;
+		idxd_desc->crypto.compress = true;
+
+		dev_dbg(dev, "%s use_async_irq: compression mode %s,"
+			" src_addr %llx, dst_addr %llx\n", __func__,
+			iaa_wq->iaa_device->active_compression_mode->name,
+			src_addr, dst_addr);
+	} else if (async_mode && !disable_async)
+		req->base.data = idxd_desc;
+
 	dev_dbg(dev, "%s: compression mode %s,"
 		" desc->src1_addr %llx, desc->src1_size %d,"
 		" desc->dst_addr %llx, desc->max_dst_size %d,"
@@ -1089,6 +1267,12 @@ static int iaa_compress(struct crypto_tfm *tfm,	struct acomp_req *req,
 		goto err;
 	}
 
+	if (async_mode && !disable_async) {
+		ret = -EINPROGRESS;
+		dev_dbg(dev, "%s: returning -EINPROGRESS\n", __func__);
+		goto out;
+	}
+
 	ret = check_completion(dev, idxd_desc->iax_completion, true, false);
 	if (ret) {
 		dev_dbg(dev, "check_completion failed ret=%d\n", ret);
@@ -1099,7 +1283,8 @@ static int iaa_compress(struct crypto_tfm *tfm,	struct acomp_req *req,
 
 	*compression_crc = idxd_desc->iax_completion->crc;
 
-	idxd_free_desc(wq, idxd_desc);
+	if (!async_mode)
+		idxd_free_desc(wq, idxd_desc);
 out:
 	return ret;
 err:
@@ -1246,6 +1431,22 @@ static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
 		desc->flags |= IDXD_OP_FLAG_RD_SRC2_AECS;
 	}
 
+	if (use_irq && !disable_async) {
+		desc->flags |= IDXD_OP_FLAG_RCI;
+
+		idxd_desc->crypto.req = req;
+		idxd_desc->crypto.tfm = tfm;
+		idxd_desc->crypto.src_addr = src_addr;
+		idxd_desc->crypto.dst_addr = dst_addr;
+		idxd_desc->crypto.compress = false;
+
+		dev_dbg(dev, "%s: use_async_irq compression mode %s,"
+			" src_addr %llx, dst_addr %llx\n", __func__,
+			iaa_wq->iaa_device->active_compression_mode->name,
+			src_addr, dst_addr);
+	} else if (async_mode && !disable_async)
+		req->base.data = idxd_desc;
+
 	dev_dbg(dev, "%s: decompression mode %s,"
 		" desc->src1_addr %llx, desc->src1_size %d,"
 		" desc->dst_addr %llx, desc->max_dst_size %d,"
@@ -1260,6 +1461,12 @@ static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
 		goto err;
 	}
 
+	if (async_mode && !disable_async) {
+		ret = -EINPROGRESS;
+		dev_dbg(dev, "%s: returning -EINPROGRESS\n", __func__);
+		goto out;
+	}
+
 	ret = check_completion(dev, idxd_desc->iax_completion, false, false);
 	if (ret) {
 		dev_dbg(dev, "check_completion failed ret=%d\n", ret);
@@ -1268,7 +1475,8 @@ static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
 
 	*dlen = idxd_desc->iax_completion->output_size;
 
-	idxd_free_desc(wq, idxd_desc);
+	if (!async_mode)
+		idxd_free_desc(wq, idxd_desc);
 out:
 	return ret;
 err:
@@ -1675,6 +1883,7 @@ static struct idxd_device_driver iaa_crypto_driver = {
 	.remove = iaa_crypto_remove,
 	.name = IDXD_SUBDRIVER_NAME,
 	.type = dev_types,
+	.desc_complete = iaa_desc_complete,
 };
 
 static int __init iaa_crypto_init_module(void)
@@ -1691,6 +1900,13 @@ static int __init iaa_crypto_init_module(void)
 		goto out;
 	}
 
+	ret = driver_create_file(&iaa_crypto_driver.drv,
+				 &driver_attr_sync_mode);
+	if (ret) {
+		pr_debug("IAA sync mode attr creation failed\n");
+		goto err_attr_create;
+	}
+
 	ret = driver_create_file(&iaa_crypto_driver.drv,
 				 &driver_attr_compression_mode);
 	if (ret) {
@@ -1723,6 +1939,8 @@ static int __init iaa_crypto_init_module(void)
 	return ret;
 
 err_compression_mode:
+	driver_remove_file(&iaa_crypto_driver.drv,
+			   &driver_attr_sync_mode);
 	driver_remove_file(&iaa_crypto_driver.drv,
 			   &driver_attr_compression_mode);
 	driver_remove_file(&iaa_crypto_driver.drv,
@@ -1735,6 +1953,8 @@ static int __init iaa_crypto_init_module(void)
 
 static void __exit iaa_crypto_cleanup_module(void)
 {
+	driver_remove_file(&iaa_crypto_driver.drv,
+			   &driver_attr_sync_mode);
 	driver_remove_file(&iaa_crypto_driver.drv,
 			   &driver_attr_compression_mode);
 	driver_remove_file(&iaa_crypto_driver.drv,
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH v2 15/15] crypto: iaa - Add IAA Compression Accelerator stats
  2023-03-28 15:35 [PATCH v2 00/15] crypto: Add Intel Analytics Accelerator (IAA) crypto compression driver Tom Zanussi
                   ` (13 preceding siblings ...)
  2023-03-28 15:35 ` [PATCH v2 14/15] crypto: iaa - Add irq support for the crypto async interface Tom Zanussi
@ 2023-03-28 15:35 ` Tom Zanussi
       [not found] ` <20230329075149.2736-1-hdanton@sina.com>
  15 siblings, 0 replies; 25+ messages in thread
From: Tom Zanussi @ 2023-03-28 15:35 UTC (permalink / raw)
  To: herbert, davem, fenghua.yu, vkoul
  Cc: dave.jiang, tony.luck, wajdi.k.feghali, james.guilford,
	kanchana.p.sridhar, giovanni.cabiddu, linux-kernel, linux-crypto,
	dmaengine

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>
---
 drivers/crypto/intel/iaa/Kconfig            |   9 +
 drivers/crypto/intel/iaa/Makefile           |   2 +
 drivers/crypto/intel/iaa/iaa_crypto.h       |  22 ++
 drivers/crypto/intel/iaa/iaa_crypto_main.c  |  65 +++++
 drivers/crypto/intel/iaa/iaa_crypto_stats.c | 271 ++++++++++++++++++++
 drivers/crypto/intel/iaa/iaa_crypto_stats.h |  58 +++++
 6 files changed, 427 insertions(+)
 create mode 100644 drivers/crypto/intel/iaa/iaa_crypto_stats.c
 create mode 100644 drivers/crypto/intel/iaa/iaa_crypto_stats.h

diff --git a/drivers/crypto/intel/iaa/Kconfig b/drivers/crypto/intel/iaa/Kconfig
index fcccb6ff7e29..cffb3a4359fc 100644
--- a/drivers/crypto/intel/iaa/Kconfig
+++ b/drivers/crypto/intel/iaa/Kconfig
@@ -8,3 +8,12 @@ config CRYPTO_DEV_IAA_CRYPTO
 	  decompression with the Intel Analytics Accelerator (IAA)
 	  hardware using the cryptographic API.  If you choose 'M'
 	  here, the module will be called iaa_crypto.
+
+config CRYPTO_DEV_IAA_CRYPTO_STATS
+	bool "Enable Intel(R) IAA Compression Accelerator Statistics"
+	depends on CRYPTO_DEV_IAA_CRYPTO
+	default n
+	help
+          Enable statistics for the IAA compression accelerator.
+	  These include per-device and per-workqueue statistics in
+	  addition to global driver statistics.
diff --git a/drivers/crypto/intel/iaa/Makefile b/drivers/crypto/intel/iaa/Makefile
index ff6ab1d0bc13..2a1bee385932 100644
--- a/drivers/crypto/intel/iaa/Makefile
+++ b/drivers/crypto/intel/iaa/Makefile
@@ -8,3 +8,5 @@ ccflags-y += -I $(srctree)/drivers/dma/idxd -DDEFAULT_SYMBOL_NAMESPACE=IDXD
 obj-$(CONFIG_CRYPTO_DEV_IAA_CRYPTO) := iaa_crypto.o
 
 iaa_crypto-y := iaa_crypto_main.o iaa_crypto_comp_canned.o iaa_crypto_comp_fixed.o
+
+iaa_crypto-$(CONFIG_CRYPTO_DEV_IAA_CRYPTO_STATS) += iaa_crypto_stats.o
diff --git a/drivers/crypto/intel/iaa/iaa_crypto.h b/drivers/crypto/intel/iaa/iaa_crypto.h
index 3a04a7bdea8e..ced10742e00b 100644
--- a/drivers/crypto/intel/iaa/iaa_crypto.h
+++ b/drivers/crypto/intel/iaa/iaa_crypto.h
@@ -45,6 +45,11 @@ struct iaa_wq {
 	struct idxd_wq		*wq;
 
 	struct iaa_device	*iaa_device;
+
+	u64			comp_calls;
+	u64			comp_bytes;
+	u64			decomp_calls;
+	u64			decomp_bytes;
 };
 
 struct iaa_device_compression_mode {
@@ -67,6 +72,11 @@ struct iaa_device {
 
 	int				n_wq;
 	struct list_head		wqs;
+
+	u64				comp_calls;
+	u64				comp_bytes;
+	u64				decomp_calls;
+	u64				decomp_bytes;
 };
 
 struct wq_table_entry {
@@ -147,4 +157,16 @@ int add_iaa_compression_mode(const char *name,
 void remove_iaa_compression_mode(const char *name);
 int set_iaa_compression_mode(const char *name);
 
+#if defined(CONFIG_CRYPTO_DEV_IAA_CRYPTO_STATS)
+void	global_stats_show(struct seq_file *m);
+void	device_stats_show(struct seq_file *m, struct iaa_device *iaa_device);
+void	reset_iaa_crypto_stats(void);
+void	reset_device_stats(struct iaa_device *iaa_device);
+#else
+static inline void	global_stats_show(struct seq_file *m) {}
+static inline void	device_stats_show(struct seq_file *m, struct iaa_device *iaa_device) {}
+static inline void	reset_iaa_crypto_stats(void) {}
+static inline void	reset_device_stats(struct iaa_device *iaa_device) {}
+#endif
+
 #endif
diff --git a/drivers/crypto/intel/iaa/iaa_crypto_main.c b/drivers/crypto/intel/iaa/iaa_crypto_main.c
index 7a2c0ed80108..7172aba3588c 100644
--- a/drivers/crypto/intel/iaa/iaa_crypto_main.c
+++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c
@@ -14,6 +14,7 @@
 
 #include "idxd.h"
 #include "iaa_crypto.h"
+#include "iaa_crypto_stats.h"
 
 #ifdef pr_fmt
 #undef pr_fmt
@@ -1101,6 +1102,7 @@ static inline int check_completion(struct device *dev,
 			ret = -ETIMEDOUT;
 			dev_dbg(dev, "%s timed out, size=0x%x\n",
 				op_str, comp->output_size);
+			update_completion_timeout_errs();
 			goto out;
 		}
 
@@ -1110,6 +1112,7 @@ static inline int check_completion(struct device *dev,
 			dev_dbg(dev, "compressed > uncompressed size,"
 				" not compressing, size=0x%x\n",
 				comp->output_size);
+			update_completion_comp_buf_overflow_errs();
 			goto out;
 		}
 
@@ -1122,6 +1125,7 @@ static inline int check_completion(struct device *dev,
 		dev_dbg(dev, "iaa %s status=0x%x, error=0x%x, size=0x%x\n",
 			op_str, comp->status, comp->error_code, comp->output_size);
 		print_hex_dump(KERN_INFO, "cmp-rec: ", DUMP_PREFIX_OFFSET, 8, 1, comp, 64, 0);
+		update_completion_einval_errs();
 
 		goto out;
 	}
@@ -1167,6 +1171,15 @@ static void iaa_desc_complete(struct idxd_desc *idxd_desc,
 
 	ctx->req->dlen = idxd_desc->iax_completion->output_size;
 
+	/* Update stats */
+	if (ctx->compress) {
+		update_total_comp_bytes_out(ctx->req->dlen);
+		update_wq_comp_bytes(iaa_wq->wq, ctx->req->dlen);
+	} else {
+		update_total_decomp_bytes_in(ctx->req->dlen);
+		update_wq_decomp_bytes(iaa_wq->wq, ctx->req->dlen);
+	}
+
 	if (ctx->compress && iaa_verify_compress) {
 		u32 compression_crc;
 
@@ -1267,6 +1280,10 @@ static int iaa_compress(struct crypto_tfm *tfm,	struct acomp_req *req,
 		goto err;
 	}
 
+	/* Update stats */
+	update_total_comp_calls();
+	update_wq_comp_calls(wq);
+
 	if (async_mode && !disable_async) {
 		ret = -EINPROGRESS;
 		dev_dbg(dev, "%s: returning -EINPROGRESS\n", __func__);
@@ -1281,6 +1298,10 @@ static int iaa_compress(struct crypto_tfm *tfm,	struct acomp_req *req,
 
 	*dlen = idxd_desc->iax_completion->output_size;
 
+	/* Update stats */
+	update_total_comp_bytes_out(*dlen);
+	update_wq_comp_bytes(wq, *dlen);
+
 	*compression_crc = idxd_desc->iax_completion->crc;
 
 	if (!async_mode)
@@ -1461,6 +1482,10 @@ static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
 		goto err;
 	}
 
+	/* Update stats */
+	update_total_decomp_calls();
+	update_wq_decomp_calls(wq);
+
 	if (async_mode && !disable_async) {
 		ret = -EINPROGRESS;
 		dev_dbg(dev, "%s: returning -EINPROGRESS\n", __func__);
@@ -1477,6 +1502,10 @@ static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
 
 	if (!async_mode)
 		idxd_free_desc(wq, idxd_desc);
+
+	/* Update stats */
+	update_total_decomp_bytes_in(slen);
+	update_wq_decomp_bytes(wq, slen);
 out:
 	return ret;
 err:
@@ -1886,6 +1915,38 @@ static struct idxd_device_driver iaa_crypto_driver = {
 	.desc_complete = iaa_desc_complete,
 };
 
+int wq_stats_show(struct seq_file *m, void *v)
+{
+	struct iaa_device *iaa_device;
+
+	mutex_lock(&iaa_devices_lock);
+
+	global_stats_show(m);
+
+	list_for_each_entry(iaa_device, &iaa_devices, list)
+		device_stats_show(m, iaa_device);
+
+	mutex_unlock(&iaa_devices_lock);
+
+	return 0;
+}
+
+int iaa_crypto_stats_reset(void *data, u64 value)
+{
+	struct iaa_device *iaa_device;
+
+	reset_iaa_crypto_stats();
+
+	mutex_lock(&iaa_devices_lock);
+
+	list_for_each_entry(iaa_device, &iaa_devices, list)
+		reset_device_stats(iaa_device);
+
+	mutex_unlock(&iaa_devices_lock);
+
+	return 0;
+}
+
 static int __init iaa_crypto_init_module(void)
 {
 	int ret = 0;
@@ -1934,6 +1995,9 @@ static int __init iaa_crypto_init_module(void)
 		goto err_compression_mode;
 	}
 
+	if (iaa_crypto_debugfs_init())
+		pr_warn("debugfs init failed, stats not available\n");
+
 	pr_debug("initialized\n");
 out:
 	return ret;
@@ -1953,6 +2017,7 @@ static int __init iaa_crypto_init_module(void)
 
 static void __exit iaa_crypto_cleanup_module(void)
 {
+	iaa_crypto_debugfs_cleanup();
 	driver_remove_file(&iaa_crypto_driver.drv,
 			   &driver_attr_sync_mode);
 	driver_remove_file(&iaa_crypto_driver.drv,
diff --git a/drivers/crypto/intel/iaa/iaa_crypto_stats.c b/drivers/crypto/intel/iaa/iaa_crypto_stats.c
new file mode 100644
index 000000000000..336847b83085
--- /dev/null
+++ b/drivers/crypto/intel/iaa/iaa_crypto_stats.c
@@ -0,0 +1,271 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2021 Intel Corporation. All rights rsvd. */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/highmem.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/smp.h>
+#include <uapi/linux/idxd.h>
+#include <linux/idxd.h>
+#include <linux/dmaengine.h>
+#include "../../dma/idxd/idxd.h"
+#include <linux/debugfs.h>
+#include <crypto/internal/acompress.h>
+#include "iaa_crypto.h"
+#include "iaa_crypto_stats.h"
+
+static u64 total_comp_calls;
+static u64 total_decomp_calls;
+static u64 max_comp_delay_ns;
+static u64 max_decomp_delay_ns;
+static u64 max_acomp_delay_ns;
+static u64 max_adecomp_delay_ns;
+static u64 total_comp_bytes_out;
+static u64 total_decomp_bytes_in;
+static u64 total_completion_einval_errors;
+static u64 total_completion_timeout_errors;
+static u64 total_completion_comp_buf_overflow_errors;
+
+static struct dentry *iaa_crypto_debugfs_root;
+
+void update_total_comp_calls(void)
+{
+	total_comp_calls++;
+}
+
+void update_total_comp_bytes_out(int n)
+{
+	total_comp_bytes_out += n;
+}
+
+void update_total_decomp_calls(void)
+{
+	total_decomp_calls++;
+}
+
+void update_total_decomp_bytes_in(int n)
+{
+	total_decomp_bytes_in += n;
+}
+
+void update_completion_einval_errs(void)
+{
+	total_completion_einval_errors++;
+}
+
+void update_completion_timeout_errs(void)
+{
+	total_completion_timeout_errors++;
+}
+
+void update_completion_comp_buf_overflow_errs(void)
+{
+	total_completion_comp_buf_overflow_errors++;
+}
+
+void update_max_comp_delay_ns(u64 start_time_ns)
+{
+	u64 time_diff;
+
+	time_diff = ktime_get_ns() - start_time_ns;
+
+	if (time_diff > max_comp_delay_ns)
+		max_comp_delay_ns = time_diff;
+}
+
+void update_max_decomp_delay_ns(u64 start_time_ns)
+{
+	u64 time_diff;
+
+	time_diff = ktime_get_ns() - start_time_ns;
+
+	if (time_diff > max_decomp_delay_ns)
+		max_decomp_delay_ns = time_diff;
+}
+
+void update_max_acomp_delay_ns(u64 start_time_ns)
+{
+	u64 time_diff;
+
+	time_diff = ktime_get_ns() - start_time_ns;
+
+	if (time_diff > max_acomp_delay_ns)
+		max_acomp_delay_ns = time_diff;
+}
+
+void update_max_adecomp_delay_ns(u64 start_time_ns)
+{
+	u64 time_diff;
+
+	time_diff = ktime_get_ns() - start_time_ns;
+
+	if (time_diff > max_adecomp_delay_ns)
+
+		max_adecomp_delay_ns = time_diff;
+}
+
+void update_wq_comp_calls(struct idxd_wq *idxd_wq)
+{
+	struct iaa_wq *wq = idxd_wq->private_data;
+
+	wq->comp_calls++;
+	wq->iaa_device->comp_calls++;
+}
+
+void update_wq_comp_bytes(struct idxd_wq *idxd_wq, int n)
+{
+	struct iaa_wq *wq = idxd_wq->private_data;
+
+	wq->comp_bytes += n;
+	wq->iaa_device->comp_bytes += n;
+}
+
+void update_wq_decomp_calls(struct idxd_wq *idxd_wq)
+{
+	struct iaa_wq *wq = idxd_wq->private_data;
+
+	wq->decomp_calls++;
+	wq->iaa_device->decomp_calls++;
+}
+
+void update_wq_decomp_bytes(struct idxd_wq *idxd_wq, int n)
+{
+	struct iaa_wq *wq = idxd_wq->private_data;
+
+	wq->decomp_bytes += n;
+	wq->iaa_device->decomp_bytes += n;
+}
+
+void reset_iaa_crypto_stats(void)
+{
+	total_comp_calls = 0;
+	total_decomp_calls = 0;
+	max_comp_delay_ns = 0;
+	max_decomp_delay_ns = 0;
+	max_acomp_delay_ns = 0;
+	max_adecomp_delay_ns = 0;
+	total_comp_bytes_out = 0;
+	total_decomp_bytes_in = 0;
+	total_completion_einval_errors = 0;
+	total_completion_timeout_errors = 0;
+	total_completion_comp_buf_overflow_errors = 0;
+}
+
+static void reset_wq_stats(struct iaa_wq *wq)
+{
+	wq->comp_calls = 0;
+	wq->comp_bytes = 0;
+	wq->decomp_calls = 0;
+	wq->decomp_bytes = 0;
+}
+
+void reset_device_stats(struct iaa_device *iaa_device)
+{
+	struct iaa_wq *iaa_wq;
+
+	iaa_device->comp_calls = 0;
+	iaa_device->comp_bytes = 0;
+	iaa_device->decomp_calls = 0;
+	iaa_device->decomp_bytes = 0;
+
+	list_for_each_entry(iaa_wq, &iaa_device->wqs, list)
+		reset_wq_stats(iaa_wq);
+}
+
+static void wq_show(struct seq_file *m, struct iaa_wq *iaa_wq)
+{
+	seq_printf(m, "    name: %s\n", iaa_wq->wq->name);
+	seq_printf(m, "    comp_calls: %llu\n", iaa_wq->comp_calls);
+	seq_printf(m, "    comp_bytes: %llu\n", iaa_wq->comp_bytes);
+	seq_printf(m, "    decomp_calls: %llu\n", iaa_wq->decomp_calls);
+	seq_printf(m, "    decomp_bytes: %llu\n\n", iaa_wq->decomp_bytes);
+}
+
+void device_stats_show(struct seq_file *m, struct iaa_device *iaa_device)
+{
+	struct iaa_wq *iaa_wq;
+
+	seq_puts(m, "iaa device:\n");
+	seq_printf(m, "  id: %d\n", iaa_device->idxd->id);
+	seq_printf(m, "  n_wqs: %d\n", iaa_device->n_wq);
+	seq_printf(m, "  comp_calls: %llu\n", iaa_device->comp_calls);
+	seq_printf(m, "  comp_bytes: %llu\n", iaa_device->comp_bytes);
+	seq_printf(m, "  decomp_calls: %llu\n", iaa_device->decomp_calls);
+	seq_printf(m, "  decomp_bytes: %llu\n", iaa_device->decomp_bytes);
+	seq_puts(m, "  wqs:\n");
+
+	list_for_each_entry(iaa_wq, &iaa_device->wqs, list)
+		wq_show(m, iaa_wq);
+}
+
+void global_stats_show(struct seq_file *m)
+{
+	seq_puts(m, "global stats:\n");
+	seq_printf(m, "  total_comp_calls: %llu\n", total_comp_calls);
+	seq_printf(m, "  total_decomp_calls: %llu\n", total_decomp_calls);
+	seq_printf(m, "  total_comp_bytes_out: %llu\n", total_comp_bytes_out);
+	seq_printf(m, "  total_decomp_bytes_in: %llu\n", total_decomp_bytes_in);
+	seq_printf(m, "  total_completion_einval_errors: %llu\n",
+		   total_completion_einval_errors);
+	seq_printf(m, "  total_completion_timeout_errors: %llu\n",
+		   total_completion_timeout_errors);
+	seq_printf(m, "  total_completion_comp_buf_overflow_errors: %llu\n\n",
+		   total_completion_comp_buf_overflow_errors);
+}
+
+static int wq_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wq_stats_show, file);
+}
+
+const struct file_operations wq_stats_fops = {
+	.open = wq_stats_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+DEFINE_DEBUGFS_ATTRIBUTE(wq_stats_reset_fops, NULL, iaa_crypto_stats_reset, "%llu\n");
+
+int __init iaa_crypto_debugfs_init(void)
+{
+	if (!debugfs_initialized())
+		return -ENODEV;
+
+	iaa_crypto_debugfs_root = debugfs_create_dir("iaa_crypto", NULL);
+	if (!iaa_crypto_debugfs_root)
+		return -ENOMEM;
+
+	debugfs_create_u64("max_comp_delay_ns", 0644,
+			   iaa_crypto_debugfs_root, &max_comp_delay_ns);
+	debugfs_create_u64("max_decomp_delay_ns", 0644,
+			   iaa_crypto_debugfs_root, &max_decomp_delay_ns);
+	debugfs_create_u64("max_acomp_delay_ns", 0644,
+			   iaa_crypto_debugfs_root, &max_comp_delay_ns);
+	debugfs_create_u64("max_adecomp_delay_ns", 0644,
+			   iaa_crypto_debugfs_root, &max_decomp_delay_ns);
+	debugfs_create_u64("total_comp_calls", 0644,
+			   iaa_crypto_debugfs_root, &total_comp_calls);
+	debugfs_create_u64("total_decomp_calls", 0644,
+			   iaa_crypto_debugfs_root, &total_decomp_calls);
+	debugfs_create_u64("total_comp_bytes_out", 0644,
+			   iaa_crypto_debugfs_root, &total_comp_bytes_out);
+	debugfs_create_u64("total_decomp_bytes_in", 0644,
+			   iaa_crypto_debugfs_root, &total_decomp_bytes_in);
+	debugfs_create_file("wq_stats", 0644, iaa_crypto_debugfs_root, NULL,
+			    &wq_stats_fops);
+	debugfs_create_file("stats_reset", 0644, iaa_crypto_debugfs_root, NULL,
+			    &wq_stats_reset_fops);
+
+	return 0;
+}
+
+void __exit iaa_crypto_debugfs_cleanup(void)
+{
+	debugfs_remove_recursive(iaa_crypto_debugfs_root);
+}
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/crypto/intel/iaa/iaa_crypto_stats.h b/drivers/crypto/intel/iaa/iaa_crypto_stats.h
new file mode 100644
index 000000000000..ad8333329fa6
--- /dev/null
+++ b/drivers/crypto/intel/iaa/iaa_crypto_stats.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2021 Intel Corporation. All rights rsvd. */
+
+#ifndef __CRYPTO_DEV_IAA_CRYPTO_STATS_H__
+#define __CRYPTO_DEV_IAA_CRYPTO_STATS_H__
+
+#if defined(CONFIG_CRYPTO_DEV_IAA_CRYPTO_STATS)
+int	iaa_crypto_debugfs_init(void);
+void	iaa_crypto_debugfs_cleanup(void);
+
+void	update_total_comp_calls(void);
+void	update_total_comp_bytes_out(int n);
+void	update_total_decomp_calls(void);
+void	update_total_decomp_bytes_in(int n);
+void	update_max_comp_delay_ns(u64 start_time_ns);
+void	update_max_decomp_delay_ns(u64 start_time_ns);
+void	update_max_acomp_delay_ns(u64 start_time_ns);
+void	update_max_adecomp_delay_ns(u64 start_time_ns);
+void	update_completion_einval_errs(void);
+void	update_completion_timeout_errs(void);
+void	update_completion_comp_buf_overflow_errs(void);
+
+void	update_wq_comp_calls(struct idxd_wq *idxd_wq);
+void	update_wq_comp_bytes(struct idxd_wq *idxd_wq, int n);
+void	update_wq_decomp_calls(struct idxd_wq *idxd_wq);
+void	update_wq_decomp_bytes(struct idxd_wq *idxd_wq, int n);
+
+int	wq_stats_show(struct seq_file *m, void *v);
+int	iaa_crypto_stats_reset(void *data, u64 value);
+
+static inline u64	iaa_get_ts(void) { return ktime_get_ns(); }
+
+#else
+static inline int	iaa_crypto_debugfs_init(void) { return 0; }
+static inline void	iaa_crypto_debugfs_cleanup(void) {}
+
+static inline void	update_total_comp_calls(void) {}
+static inline void	update_total_comp_bytes_out(int n) {}
+static inline void	update_total_decomp_calls(void) {}
+static inline void	update_total_decomp_bytes_in(int n) {}
+static inline void	update_max_comp_delay_ns(u64 start_time_ns) {}
+static inline void	update_max_decomp_delay_ns(u64 start_time_ns) {}
+static inline void	update_max_acomp_delay_ns(u64 start_time_ns) {}
+static inline void	update_max_adecomp_delay_ns(u64 start_time_ns) {}
+static inline void	update_completion_einval_errs(void) {}
+static inline void	update_completion_timeout_errs(void) {}
+static inline void	update_completion_comp_buf_overflow_errs(void) {}
+
+static inline void	update_wq_comp_calls(struct idxd_wq *idxd_wq) {}
+static inline void	update_wq_comp_bytes(struct idxd_wq *idxd_wq, int n) {}
+static inline void	update_wq_decomp_calls(struct idxd_wq *idxd_wq) {}
+static inline void	update_wq_decomp_bytes(struct idxd_wq *idxd_wq, int n) {}
+
+static inline u64	iaa_get_ts(void) { return 0; }
+
+#endif // CONFIG_CRYPTO_DEV_IAA_CRYPTO_STATS
+
+#endif
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 25+ messages in thread

* Re: [PATCH v2 03/15] dmaengine: idxd: Export drv_enable/disable and related functions
  2023-03-28 15:35 ` [PATCH v2 03/15] dmaengine: idxd: Export drv_enable/disable and related functions Tom Zanussi
@ 2023-03-28 16:02   ` Dave Jiang
  0 siblings, 0 replies; 25+ messages in thread
From: Dave Jiang @ 2023-03-28 16:02 UTC (permalink / raw)
  To: Tom Zanussi, herbert, davem, fenghua.yu, vkoul
  Cc: tony.luck, wajdi.k.feghali, james.guilford, kanchana.p.sridhar,
	giovanni.cabiddu, linux-kernel, linux-crypto, dmaengine



On 3/28/23 8:35 AM, Tom Zanussi wrote:
> To allow idxd sub-drivers to enable and disable wqs, export them.
> 
> Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>

Reviewed-by: Dave Jiang <dave.jiang@intel.com>

> ---
>   drivers/dma/idxd/device.c | 2 ++
>   1 file changed, 2 insertions(+)
> 
> diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
> index 5f321f3b4242..af1aa88a66c1 100644
> --- a/drivers/dma/idxd/device.c
> +++ b/drivers/dma/idxd/device.c
> @@ -1406,6 +1406,7 @@ int drv_enable_wq(struct idxd_wq *wq)
>   err:
>   	return rc;
>   }
> +EXPORT_SYMBOL_NS_GPL(drv_enable_wq, IDXD);
>   
>   void drv_disable_wq(struct idxd_wq *wq)
>   {
> @@ -1427,6 +1428,7 @@ void drv_disable_wq(struct idxd_wq *wq)
>   	wq->type = IDXD_WQT_NONE;
>   	wq->client_count = 0;
>   }
> +EXPORT_SYMBOL_NS_GPL(drv_disable_wq, IDXD);
>   
>   int idxd_device_drv_probe(struct idxd_dev *idxd_dev)
>   {

^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH v2 04/15] dmaengine: idxd: Export descriptor management functions
  2023-03-28 15:35 ` [PATCH v2 04/15] dmaengine: idxd: Export descriptor management functions Tom Zanussi
@ 2023-03-28 16:04   ` Dave Jiang
  2023-03-28 16:12     ` Tom Zanussi
  0 siblings, 1 reply; 25+ messages in thread
From: Dave Jiang @ 2023-03-28 16:04 UTC (permalink / raw)
  To: Tom Zanussi, herbert, davem, fenghua.yu, vkoul
  Cc: tony.luck, wajdi.k.feghali, james.guilford, kanchana.p.sridhar,
	giovanni.cabiddu, linux-kernel, linux-crypto, dmaengine



On 3/28/23 8:35 AM, Tom Zanussi wrote:
> To allow idxd sub-drivers to access the descriptor management
> functions, export them.
> 
> Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
> ---
>   drivers/dma/idxd/submit.c | 3 +++
>   1 file changed, 3 insertions(+)
> 
> diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c
> index c01db23e3333..9d9ec0b76ccd 100644
> --- a/drivers/dma/idxd/submit.c
> +++ b/drivers/dma/idxd/submit.c
> @@ -61,6 +61,7 @@ struct idxd_desc *idxd_alloc_desc(struct idxd_wq *wq, enum idxd_op_type optype)
>   
>   	return __get_desc(wq, idx, cpu);
>   }
> +EXPORT_SYMBOL_NS_GPL(idxd_alloc_desc, IDXD);
>   
>   void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc)
>   {
> @@ -69,6 +70,7 @@ void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc)
>   	desc->cpu = -1;
>   	sbitmap_queue_clear(&wq->sbq, desc->id, cpu);
>   }
> +EXPORT_SYMBOL_NS_GPL(idxd_free_desc, IDXD);
>   
>   static struct idxd_desc *list_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
>   					 struct idxd_desc *desc)
> @@ -215,3 +217,4 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
>   	percpu_ref_put(&wq->wq_active);
>   	return 0;
>   }
> +EXPORT_SYMBOL_GPL(idxd_submit_desc);

This one should use the EXPORT_SYMBOL_NS_GPL() as above?

^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH v2 05/15] dmaengine: idxd: Export wq resource management functions
  2023-03-28 15:35 ` [PATCH v2 05/15] dmaengine: idxd: Export wq resource " Tom Zanussi
@ 2023-03-28 16:04   ` Dave Jiang
  0 siblings, 0 replies; 25+ messages in thread
From: Dave Jiang @ 2023-03-28 16:04 UTC (permalink / raw)
  To: Tom Zanussi, herbert, davem, fenghua.yu, vkoul
  Cc: tony.luck, wajdi.k.feghali, james.guilford, kanchana.p.sridhar,
	giovanni.cabiddu, linux-kernel, linux-crypto, dmaengine



On 3/28/23 8:35 AM, Tom Zanussi wrote:
> To allow idxd sub-drivers to access the wq resource management
> functions, export them.
> 
> Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>

> ---
>   drivers/dma/idxd/device.c | 5 +++++
>   1 file changed, 5 insertions(+)
> 
> diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
> index af1aa88a66c1..7837d0a56314 100644
> --- a/drivers/dma/idxd/device.c
> +++ b/drivers/dma/idxd/device.c
> @@ -161,6 +161,7 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq)
>   	free_hw_descs(wq);
>   	return rc;
>   }
> +EXPORT_SYMBOL_NS_GPL(idxd_wq_alloc_resources, IDXD);
>   
>   void idxd_wq_free_resources(struct idxd_wq *wq)
>   {
> @@ -174,6 +175,7 @@ void idxd_wq_free_resources(struct idxd_wq *wq)
>   	dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr);
>   	sbitmap_queue_free(&wq->sbq);
>   }
> +EXPORT_SYMBOL_NS_GPL(idxd_wq_free_resources, IDXD);
>   
>   int idxd_wq_enable(struct idxd_wq *wq)
>   {
> @@ -422,6 +424,7 @@ int idxd_wq_init_percpu_ref(struct idxd_wq *wq)
>   	reinit_completion(&wq->wq_resurrect);
>   	return 0;
>   }
> +EXPORT_SYMBOL_NS_GPL(idxd_wq_init_percpu_ref, IDXD);
>   
>   void __idxd_wq_quiesce(struct idxd_wq *wq)
>   {
> @@ -431,6 +434,7 @@ void __idxd_wq_quiesce(struct idxd_wq *wq)
>   	complete_all(&wq->wq_resurrect);
>   	wait_for_completion(&wq->wq_dead);
>   }
> +EXPORT_SYMBOL_NS_GPL(__idxd_wq_quiesce, IDXD);
>   
>   void idxd_wq_quiesce(struct idxd_wq *wq)
>   {
> @@ -438,6 +442,7 @@ void idxd_wq_quiesce(struct idxd_wq *wq)
>   	__idxd_wq_quiesce(wq);
>   	mutex_unlock(&wq->wq_lock);
>   }
> +EXPORT_SYMBOL_NS_GPL(idxd_wq_quiesce, IDXD);
>   
>   /* Device control bits */
>   static inline bool idxd_is_enabled(struct idxd_device *idxd)

^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH v2 06/15] dmaengine: idxd: Add private_data to struct idxd_wq
  2023-03-28 15:35 ` [PATCH v2 06/15] dmaengine: idxd: Add private_data to struct idxd_wq Tom Zanussi
@ 2023-03-28 16:06   ` Dave Jiang
  2023-03-28 16:13     ` Tom Zanussi
  0 siblings, 1 reply; 25+ messages in thread
From: Dave Jiang @ 2023-03-28 16:06 UTC (permalink / raw)
  To: Tom Zanussi, herbert, davem, fenghua.yu, vkoul
  Cc: tony.luck, wajdi.k.feghali, james.guilford, kanchana.p.sridhar,
	giovanni.cabiddu, linux-kernel, linux-crypto, dmaengine



On 3/28/23 8:35 AM, Tom Zanussi wrote:
> Add a void * to idxd_wqs for user-defined context data.

I wonder if we should add accessor functions like get and set private 
data for the wq.
> 
> Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
> ---
>   drivers/dma/idxd/idxd.h | 2 ++
>   1 file changed, 2 insertions(+)
> 
> diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
> index 719f9f1662ad..e55213b5153e 100644
> --- a/drivers/dma/idxd/idxd.h
> +++ b/drivers/dma/idxd/idxd.h
> @@ -216,6 +216,8 @@ struct idxd_wq {
>   	u32 max_batch_size;
>   
>   	char driver_name[WQ_NAME_SIZE + 1];
> +
> +	void *private_data;
>   };
>   
>   struct idxd_engine {

^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH v2 04/15] dmaengine: idxd: Export descriptor management functions
  2023-03-28 16:04   ` Dave Jiang
@ 2023-03-28 16:12     ` Tom Zanussi
  0 siblings, 0 replies; 25+ messages in thread
From: Tom Zanussi @ 2023-03-28 16:12 UTC (permalink / raw)
  To: Dave Jiang, herbert, davem, fenghua.yu, vkoul
  Cc: tony.luck, wajdi.k.feghali, james.guilford, kanchana.p.sridhar,
	giovanni.cabiddu, linux-kernel, linux-crypto, dmaengine

Hi Dave,

On Tue, 2023-03-28 at 09:04 -0700, Dave Jiang wrote:
> 
> 
> On 3/28/23 8:35 AM, Tom Zanussi wrote:
> > To allow idxd sub-drivers to access the descriptor management
> > functions, export them.
> > 
> > Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
> > ---
> >   drivers/dma/idxd/submit.c | 3 +++
> >   1 file changed, 3 insertions(+)
> > 
> > diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c
> > index c01db23e3333..9d9ec0b76ccd 100644
> > --- a/drivers/dma/idxd/submit.c
> > +++ b/drivers/dma/idxd/submit.c
> > @@ -61,6 +61,7 @@ struct idxd_desc *idxd_alloc_desc(struct idxd_wq
> > *wq, enum idxd_op_type optype)
> >   
> >         return __get_desc(wq, idx, cpu);
> >   }
> > +EXPORT_SYMBOL_NS_GPL(idxd_alloc_desc, IDXD);
> >   
> >   void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc)
> >   {
> > @@ -69,6 +70,7 @@ void idxd_free_desc(struct idxd_wq *wq, struct
> > idxd_desc *desc)
> >         desc->cpu = -1;
> >         sbitmap_queue_clear(&wq->sbq, desc->id, cpu);
> >   }
> > +EXPORT_SYMBOL_NS_GPL(idxd_free_desc, IDXD);
> >   
> >   static struct idxd_desc *list_abort_desc(struct idxd_wq *wq,
> > struct idxd_irq_entry *ie,
> >                                          struct idxd_desc *desc)
> > @@ -215,3 +217,4 @@ int idxd_submit_desc(struct idxd_wq *wq, struct
> > idxd_desc *desc)
> >         percpu_ref_put(&wq->wq_active);
> >         return 0;
> >   }
> > +EXPORT_SYMBOL_GPL(idxd_submit_desc);
> 
> This one should use the EXPORT_SYMBOL_NS_GPL() as above?

Yeah, not sure how I missed that one ;-/

Thanks for pointing it out.

Tom


^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH v2 06/15] dmaengine: idxd: Add private_data to struct idxd_wq
  2023-03-28 16:06   ` Dave Jiang
@ 2023-03-28 16:13     ` Tom Zanussi
  0 siblings, 0 replies; 25+ messages in thread
From: Tom Zanussi @ 2023-03-28 16:13 UTC (permalink / raw)
  To: Dave Jiang, herbert, davem, fenghua.yu, vkoul
  Cc: tony.luck, wajdi.k.feghali, james.guilford, kanchana.p.sridhar,
	giovanni.cabiddu, linux-kernel, linux-crypto, dmaengine

On Tue, 2023-03-28 at 09:06 -0700, Dave Jiang wrote:
> 
> 
> On 3/28/23 8:35 AM, Tom Zanussi wrote:
> > Add a void * to idxd_wqs for user-defined context data.
> 
> I wonder if we should add accessor functions like get and set private
> data for the wq.
> > 

Yeah, makes sense, will do that in v3.

Tom

> > Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
> > ---
> >   drivers/dma/idxd/idxd.h | 2 ++
> >   1 file changed, 2 insertions(+)
> > 
> > diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
> > index 719f9f1662ad..e55213b5153e 100644
> > --- a/drivers/dma/idxd/idxd.h
> > +++ b/drivers/dma/idxd/idxd.h
> > @@ -216,6 +216,8 @@ struct idxd_wq {
> >         u32 max_batch_size;
> >   
> >         char driver_name[WQ_NAME_SIZE + 1];
> > +
> > +       void *private_data;
> >   };
> >   
> >   struct idxd_engine {


^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH v2 10/15] crypto: iaa - Add per-cpu workqueue table with rebalancing
       [not found] ` <20230329075149.2736-1-hdanton@sina.com>
@ 2023-03-29 14:58   ` Tom Zanussi
  0 siblings, 0 replies; 25+ messages in thread
From: Tom Zanussi @ 2023-03-29 14:58 UTC (permalink / raw)
  To: Hillf Danton
  Cc: herbert, fenghua.yu, vkoul, linux-kernel, linux-crypto, dmaengine

Hi Hillf,

On Wed, 2023-03-29 at 15:51 +0800, Hillf Danton wrote:
> On 28 Mar 2023 10:35:30 -0500 Tom Zanussi
> <tom.zanussi@linux.intel.com>
> > +/*
> > + * Given a cpu, find the closest IAA instance.  The idea is to try
> > to
> > + * choose the most appropriate IAA instance for a caller and
> > spread
> > + * available workqueues around to clients.
> > + */
> > +static inline int cpu_to_iaa(int cpu)
> > +{
> > +       int node, n_cpus = 0, test_cpu, iaa = 0;
> > +       int nr_iaa_per_node, nr_cores_per_iaa;
> > +       const struct cpumask *node_cpus;
> > +
> > +       if (!nr_nodes)
> > +               return 0;
> > +
> > +       nr_iaa_per_node = nr_iaa / nr_nodes;
> > +       if (!nr_iaa_per_node)
> > +               return 0;
> > +
> > +       nr_cores_per_iaa = nr_cpus_per_node / nr_iaa_per_node;
> > +
> > +       for_each_online_node(node) {
> > +               node_cpus = cpumask_of_node(node);
> > +               if (!cpumask_test_cpu(cpu, node_cpus))
> > +                       continue;
> 
> cpu_to_node(cpu) works for you.

Yes, thanks for pointing that out.

> > +
> > +               for_each_cpu(test_cpu, node_cpus) {
> > +                       if ((n_cpus % nr_cpus_per_node) == 0)
> > +                               iaa = node * nr_iaa_per_node;
> > +
> > +                       if (test_cpu == cpu)
> > +                               return iaa;
> 
> Given nr_iaa_per_node, why round robin-ing every iaa in the node not
> work?

True, we should be able to simplify this, will do for the next version.

Thanks,

Tom


> > +
> > +                       n_cpus++;
> > +
> > +                       if ((n_cpus % cpus_per_iaa) == 0)
> > +                               iaa++;
> > +               }
> > +       }
> > +
> > +       return -1;
> > +}


^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH v2 12/15] crypto: iaa - Add support for iaa_crypto deflate compression algorithm
  2023-03-28 15:35 ` [PATCH v2 12/15] crypto: iaa - Add support for iaa_crypto deflate compression algorithm Tom Zanussi
@ 2023-04-06  8:00   ` Herbert Xu
  2023-04-06 14:43     ` Tom Zanussi
  0 siblings, 1 reply; 25+ messages in thread
From: Herbert Xu @ 2023-04-06  8:00 UTC (permalink / raw)
  To: Tom Zanussi
  Cc: davem, fenghua.yu, vkoul, dave.jiang, tony.luck, wajdi.k.feghali,
	james.guilford, kanchana.p.sridhar, giovanni.cabiddu,
	linux-kernel, linux-crypto, dmaengine

On Tue, Mar 28, 2023 at 10:35:32AM -0500, Tom Zanussi wrote:
>
> @@ -881,12 +1574,26 @@ static int iaa_crypto_probe(struct idxd_dev *idxd_dev)
>  
>  	rebalance_wq_table();
>  
> +	if (first_wq) {
> +		iaa_crypto_enabled = true;
> +		ret = iaa_register_compression_device();
> +		if (ret != 0) {
> +			iaa_crypto_enabled = false;
> +			dev_dbg(dev, "IAA compression device registration failed\n");
> +			goto err_register;
> +		}
> +
> +		pr_info("iaa_crypto now ENABLED\n");
> +	}
> +

Sorry for picking on your driver but I've got to start somewhere :)

A long standing problem shared by almost all crypto drivers is that
the hardware removal handling is completely broken.

This is because hardware can be removed at any time, including during
a crypto operatin.  So drivers must work carefully around that fact.

Here is a recipe for dealing with this safely:

1) Never unregister your crypto algorithms, even after the last
piece of hardware has been unplugged.  The algorithms should only
be unregistered (if they have been registered through the first
successful probe call) in the module unload function.

2) Never free any software state for your hardware without some form
of synchronisation with oustanding operations.

Any mechanism would do, for example, you could use a spinlock if the
critical path isn't very long.  The operational path would take the
lock, check the hardware state, and if present proceed with the
operation (but still being prepared to cope if the hardware goes
AWAL because even if the driver state is still present the actual
hardware may be gone already).

Then the removal path would simply take the spinlock, set a flag
indicating the hardware is gone and then you could safely unlock
and free your driver states.

Thanks,
-- 
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt

^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH v2 12/15] crypto: iaa - Add support for iaa_crypto deflate compression algorithm
  2023-04-06  8:00   ` Herbert Xu
@ 2023-04-06 14:43     ` Tom Zanussi
  0 siblings, 0 replies; 25+ messages in thread
From: Tom Zanussi @ 2023-04-06 14:43 UTC (permalink / raw)
  To: Herbert Xu
  Cc: davem, fenghua.yu, vkoul, dave.jiang, tony.luck, wajdi.k.feghali,
	james.guilford, kanchana.p.sridhar, giovanni.cabiddu,
	linux-kernel, linux-crypto, dmaengine

Hi Herbert,

On Thu, 2023-04-06 at 16:00 +0800, Herbert Xu wrote:
> On Tue, Mar 28, 2023 at 10:35:32AM -0500, Tom Zanussi wrote:
> > 
> > @@ -881,12 +1574,26 @@ static int iaa_crypto_probe(struct idxd_dev
> > *idxd_dev)
> >  
> >         rebalance_wq_table();
> >  
> > +       if (first_wq) {
> > +               iaa_crypto_enabled = true;
> > +               ret = iaa_register_compression_device();
> > +               if (ret != 0) {
> > +                       iaa_crypto_enabled = false;
> > +                       dev_dbg(dev, "IAA compression device
> > registration failed\n");
> > +                       goto err_register;
> > +               }
> > +
> > +               pr_info("iaa_crypto now ENABLED\n");
> > +       }
> > +
> 
> Sorry for picking on your driver but I've got to start somewhere :)

No problem, thanks for reviewing the code. ;-)

> 
> A long standing problem shared by almost all crypto drivers is that
> the hardware removal handling is completely broken.
> 
> This is because hardware can be removed at any time, including during
> a crypto operatin.  So drivers must work carefully around that fact.
> 
> Here is a recipe for dealing with this safely:
> 
> 1) Never unregister your crypto algorithms, even after the last
> piece of hardware has been unplugged.  The algorithms should only
> be unregistered (if they have been registered through the first
> successful probe call) in the module unload function.
> 
> 2) Never free any software state for your hardware without some form
> of synchronisation with oustanding operations.
> 
> Any mechanism would do, for example, you could use a spinlock if the
> critical path isn't very long.  The operational path would take the
> lock, check the hardware state, and if present proceed with the
> operation (but still being prepared to cope if the hardware goes
> AWAL because even if the driver state is still present the actual
> hardware may be gone already).
> 
> Then the removal path would simply take the spinlock, set a flag
> indicating the hardware is gone and then you could safely unlock
> and free your driver states.
> 

OK, yeah, thanks for pointing this out along with the detailed
explanation and remedy.  Will take care of this in the next version.

Tom

> Thanks,


^ permalink raw reply	[flat|nested] 25+ messages in thread

end of thread, other threads:[~2023-04-06 14:47 UTC | newest]

Thread overview: 25+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2023-03-28 15:35 [PATCH v2 00/15] crypto: Add Intel Analytics Accelerator (IAA) crypto compression driver Tom Zanussi
2023-03-28 15:35 ` [PATCH v2 01/15] dmaengine: idxd: add wq driver name support for accel-config user tool Tom Zanussi
2023-03-28 15:35 ` [PATCH v2 02/15] dmaengine: idxd: add external module driver support for dsa_bus_type Tom Zanussi
2023-03-28 15:35 ` [PATCH v2 03/15] dmaengine: idxd: Export drv_enable/disable and related functions Tom Zanussi
2023-03-28 16:02   ` Dave Jiang
2023-03-28 15:35 ` [PATCH v2 04/15] dmaengine: idxd: Export descriptor management functions Tom Zanussi
2023-03-28 16:04   ` Dave Jiang
2023-03-28 16:12     ` Tom Zanussi
2023-03-28 15:35 ` [PATCH v2 05/15] dmaengine: idxd: Export wq resource " Tom Zanussi
2023-03-28 16:04   ` Dave Jiang
2023-03-28 15:35 ` [PATCH v2 06/15] dmaengine: idxd: Add private_data to struct idxd_wq Tom Zanussi
2023-03-28 16:06   ` Dave Jiang
2023-03-28 16:13     ` Tom Zanussi
2023-03-28 15:35 ` [PATCH v2 07/15] dmaengine: idxd: add callback support for iaa crypto Tom Zanussi
2023-03-28 15:35 ` [PATCH v2 08/15] crypto: iaa - Add IAA Compression Accelerator Documentation Tom Zanussi
2023-03-28 15:35 ` [PATCH v2 09/15] crypto: iaa - Add Intel IAA Compression Accelerator crypto driver core Tom Zanussi
2023-03-28 15:35 ` [PATCH v2 10/15] crypto: iaa - Add per-cpu workqueue table with rebalancing Tom Zanussi
2023-03-28 15:35 ` [PATCH v2 11/15] crypto: iaa - Add compression mode management along with fixed mode Tom Zanussi
2023-03-28 15:35 ` [PATCH v2 12/15] crypto: iaa - Add support for iaa_crypto deflate compression algorithm Tom Zanussi
2023-04-06  8:00   ` Herbert Xu
2023-04-06 14:43     ` Tom Zanussi
2023-03-28 15:35 ` [PATCH v2 13/15] crypto: iaa - Add support for default IAA 'canned' compression mode Tom Zanussi
2023-03-28 15:35 ` [PATCH v2 14/15] crypto: iaa - Add irq support for the crypto async interface Tom Zanussi
2023-03-28 15:35 ` [PATCH v2 15/15] crypto: iaa - Add IAA Compression Accelerator stats Tom Zanussi
     [not found] ` <20230329075149.2736-1-hdanton@sina.com>
2023-03-29 14:58   ` [PATCH v2 10/15] crypto: iaa - Add per-cpu workqueue table with rebalancing Tom Zanussi

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).