diff mbox series

[v2,01/13] crypto: acomp - Define two new interfaces for compress/decompress batching.

Message ID 20241103032111.333282-2-kanchana.p.sridhar@intel.com (mailing list archive)
State New
Headers show
Series zswap IAA compress batching | expand

Commit Message

Kanchana P Sridhar Nov. 3, 2024, 3:20 a.m. UTC 
This commit adds batch_compress() and batch_decompress() interfaces to:

  struct acomp_alg
  struct crypto_acomp

This allows the iaa_crypto Intel IAA driver to register implementation for
batch_compress() and batch_decompress() API, that can subsequently be
invoked from the kernel zswap/zram swap modules to compress/decompress
up to CRYPTO_BATCH_SIZE (i.e. 8) pages in parallel in the IAA hardware
accelerator to improve swapout/swapin performance.

Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@intel.com>
---
 crypto/acompress.c                  |  2 +
 include/crypto/acompress.h          | 82 +++++++++++++++++++++++++++++
 include/crypto/internal/acompress.h | 16 ++++++
 3 files changed, 100 insertions(+)

Comments

Herbert Xu Nov. 15, 2024, 11:32 a.m. UTC | #1 
On Sat, Nov 02, 2024 at 08:20:59PM -0700, Kanchana P Sridhar wrote:
> This commit adds batch_compress() and batch_decompress() interfaces to:
> 
>   struct acomp_alg
>   struct crypto_acomp
> 
> This allows the iaa_crypto Intel IAA driver to register implementation for
> batch_compress() and batch_decompress() API, that can subsequently be
> invoked from the kernel zswap/zram swap modules to compress/decompress
> up to CRYPTO_BATCH_SIZE (i.e. 8) pages in parallel in the IAA hardware
> accelerator to improve swapout/swapin performance.
> 
> Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@intel.com>
> ---
>  crypto/acompress.c                  |  2 +
>  include/crypto/acompress.h          | 82 +++++++++++++++++++++++++++++
>  include/crypto/internal/acompress.h | 16 ++++++
>  3 files changed, 100 insertions(+)

Please take a look at the request chaining patch that I created
for crypto_ahash.  It should be applicable to acomp as well.

https://lore.kernel.org/all/677614fbdc70b31df2e26483c8d2cd1510c8af91.1730021644.git.herbert@gondor.apana.org.au/

Thanks,
Kanchana P Sridhar Nov. 15, 2024, 9:16 p.m. UTC | #2 
> -----Original Message-----
> From: Herbert Xu <herbert@gondor.apana.org.au>
> Sent: Friday, November 15, 2024 3:33 AM
> To: Sridhar, Kanchana P <kanchana.p.sridhar@intel.com>
> Cc: linux-kernel@vger.kernel.org; linux-mm@kvack.org;
> hannes@cmpxchg.org; yosryahmed@google.com; nphamcs@gmail.com;
> chengming.zhou@linux.dev; usamaarif642@gmail.com;
> ryan.roberts@arm.com; Huang, Ying <ying.huang@intel.com>;
> 21cnbao@gmail.com; akpm@linux-foundation.org; linux-
> crypto@vger.kernel.org; davem@davemloft.net; clabbe@baylibre.com;
> ardb@kernel.org; ebiggers@google.com; surenb@google.com; Accardi,
> Kristen C <kristen.c.accardi@intel.com>; zanussi@kernel.org; Feghali, Wajdi K
> <wajdi.k.feghali@intel.com>; Gopal, Vinodh <vinodh.gopal@intel.com>
> Subject: Re: [PATCH v2 01/13] crypto: acomp - Define two new interfaces for
> compress/decompress batching.
> 
> On Sat, Nov 02, 2024 at 08:20:59PM -0700, Kanchana P Sridhar wrote:
> > This commit adds batch_compress() and batch_decompress() interfaces to:
> >
> >   struct acomp_alg
> >   struct crypto_acomp
> >
> > This allows the iaa_crypto Intel IAA driver to register implementation for
> > batch_compress() and batch_decompress() API, that can subsequently be
> > invoked from the kernel zswap/zram swap modules to
> compress/decompress
> > up to CRYPTO_BATCH_SIZE (i.e. 8) pages in parallel in the IAA hardware
> > accelerator to improve swapout/swapin performance.
> >
> > Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@intel.com>
> > ---
> >  crypto/acompress.c                  |  2 +
> >  include/crypto/acompress.h          | 82 +++++++++++++++++++++++++++++
> >  include/crypto/internal/acompress.h | 16 ++++++
> >  3 files changed, 100 insertions(+)
> 
> Please take a look at the request chaining patch that I created
> for crypto_ahash.  It should be applicable to acomp as well.
> 
> https://lore.kernel.org/all/677614fbdc70b31df2e26483c8d2cd1510c8af91.1
> 730021644.git.herbert@gondor.apana.org.au/

Thanks for sharing this, Herbert. I will take a look at this as I work on
updates to the IAA compress batching series.

Thanks,
Kanchana

> 
> 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
diff mbox series

Patch

diff --git a/crypto/acompress.c b/crypto/acompress.c
index 6fdf0ff9f3c0..a506db499a37 100644
--- a/crypto/acompress.c
+++ b/crypto/acompress.c
@@ -71,6 +71,8 @@  static int crypto_acomp_init_tfm(struct crypto_tfm *tfm)
 
 	acomp->compress = alg->compress;
 	acomp->decompress = alg->decompress;
+	acomp->batch_compress = alg->batch_compress;
+	acomp->batch_decompress = alg->batch_decompress;
 	acomp->dst_free = alg->dst_free;
 	acomp->reqsize = alg->reqsize;
 
diff --git a/include/crypto/acompress.h b/include/crypto/acompress.h
index 54937b615239..ab0d9987bde1 100644
--- a/include/crypto/acompress.h
+++ b/include/crypto/acompress.h
@@ -37,12 +37,20 @@  struct acomp_req {
 	void *__ctx[] CRYPTO_MINALIGN_ATTR;
 };
 
+/*
+ * The max compress/decompress batch size, for crypto algorithms
+ * that support batch_compress and batch_decompress API.
+ */
+#define CRYPTO_BATCH_SIZE 8UL
+
 /**
  * struct crypto_acomp - user-instantiated objects which encapsulate
  * algorithms and core processing logic
  *
  * @compress:		Function performs a compress operation
  * @decompress:		Function performs a de-compress operation
+ * @batch_compress:	Function performs a batch compress operation
+ * @batch_decompress:	Function performs a batch decompress operation
  * @dst_free:		Frees destination buffer if allocated inside the
  *			algorithm
  * @reqsize:		Context size for (de)compression requests
@@ -51,6 +59,20 @@  struct acomp_req {
 struct crypto_acomp {
 	int (*compress)(struct acomp_req *req);
 	int (*decompress)(struct acomp_req *req);
+	void (*batch_compress)(struct acomp_req *reqs[],
+			       struct crypto_wait *wait,
+			       struct page *pages[],
+			       u8 *dsts[],
+			       unsigned int dlens[],
+			       int errors[],
+			       int nr_pages);
+	void (*batch_decompress)(struct acomp_req *reqs[],
+				 struct crypto_wait *wait,
+				 u8 *srcs[],
+				 struct page *pages[],
+				 unsigned int slens[],
+				 int errors[],
+				 int nr_pages);
 	void (*dst_free)(struct scatterlist *dst);
 	unsigned int reqsize;
 	struct crypto_tfm base;
@@ -265,4 +287,64 @@  static inline int crypto_acomp_decompress(struct acomp_req *req)
 	return crypto_acomp_reqtfm(req)->decompress(req);
 }
 
+/**
+ * crypto_acomp_batch_compress() -- compress a batch of requests
+ *
+ * Function invokes the batch compress operation
+ *
+ * @reqs: @nr_pages asynchronous compress requests.
+ * @wait: crypto_wait for synchronous acomp batch compress. If NULL, the
+ *        driver must provide a way to process completions asynchronously.
+ * @pages: Pages to be compressed.
+ * @dsts: Pre-allocated destination buffers to store results of compression.
+ * @dlens: Will contain the compressed lengths.
+ * @errors: zero on successful compression of the corresponding
+ *          req, or error code in case of error.
+ * @nr_pages: The number of pages, up to CRYPTO_BATCH_SIZE,
+ *            to be compressed.
+ */
+static inline void crypto_acomp_batch_compress(struct acomp_req *reqs[],
+					       struct crypto_wait *wait,
+					       struct page *pages[],
+					       u8 *dsts[],
+					       unsigned int dlens[],
+					       int errors[],
+					       int nr_pages)
+{
+	struct crypto_acomp *tfm = crypto_acomp_reqtfm(reqs[0]);
+
+	return tfm->batch_compress(reqs, wait, pages, dsts,
+				   dlens, errors, nr_pages);
+}
+
+/**
+ * crypto_acomp_batch_decompress() -- decompress a batch of requests
+ *
+ * Function invokes the batch decompress operation
+ *
+ * @reqs: @nr_pages asynchronous decompress requests.
+ * @wait: crypto_wait for synchronous acomp batch decompress. If NULL, the
+ *        driver must provide a way to process completions asynchronously.
+ * @srcs: The src buffers to be decompressed.
+ * @pages: The pages to store the decompressed buffers.
+ * @slens: Compressed lengths of @srcs.
+ * @errors: zero on successful compression of the corresponding
+ *          req, or error code in case of error.
+ * @nr_pages: The number of pages, up to CRYPTO_BATCH_SIZE,
+ *            to be decompressed.
+ */
+static inline void crypto_acomp_batch_decompress(struct acomp_req *reqs[],
+						 struct crypto_wait *wait,
+						 u8 *srcs[],
+						 struct page *pages[],
+						 unsigned int slens[],
+						 int errors[],
+						 int nr_pages)
+{
+	struct crypto_acomp *tfm = crypto_acomp_reqtfm(reqs[0]);
+
+	return tfm->batch_decompress(reqs, wait, srcs, pages,
+				     slens, errors, nr_pages);
+}
+
 #endif
diff --git a/include/crypto/internal/acompress.h b/include/crypto/internal/acompress.h
index 8831edaafc05..acfe2d9d5a83 100644
--- a/include/crypto/internal/acompress.h
+++ b/include/crypto/internal/acompress.h
@@ -17,6 +17,8 @@ 
  *
  * @compress:	Function performs a compress operation
  * @decompress:	Function performs a de-compress operation
+ * @batch_compress:	Function performs a batch compress operation
+ * @batch_decompress:	Function performs a batch decompress operation
  * @dst_free:	Frees destination buffer if allocated inside the algorithm
  * @init:	Initialize the cryptographic transformation object.
  *		This function is used to initialize the cryptographic
@@ -37,6 +39,20 @@ 
 struct acomp_alg {
 	int (*compress)(struct acomp_req *req);
 	int (*decompress)(struct acomp_req *req);
+	void (*batch_compress)(struct acomp_req *reqs[],
+			       struct crypto_wait *wait,
+			       struct page *pages[],
+			       u8 *dsts[],
+			       unsigned int dlens[],
+			       int errors[],
+			       int nr_pages);
+	void (*batch_decompress)(struct acomp_req *reqs[],
+				 struct crypto_wait *wait,
+				 u8 *srcs[],
+				 struct page *pages[],
+				 unsigned int slens[],
+				 int errors[],
+				 int nr_pages);
 	void (*dst_free)(struct scatterlist *dst);
 	int (*init)(struct crypto_acomp *tfm);
 	void (*exit)(struct crypto_acomp *tfm);