linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Kanchana P Sridhar <kanchana.p.sridhar@intel.com>
To: 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, ying.huang@intel.com, 21cnbao@gmail.com,
	akpm@linux-foundation.org, linux-crypto@vger.kernel.org,
	herbert@gondor.apana.org.au, davem@davemloft.net,
	clabbe@baylibre.com, ardb@kernel.org, ebiggers@google.com,
	surenb@google.com, kristen.c.accardi@intel.com
Cc: wajdi.k.feghali@intel.com, vinodh.gopal@intel.com,
	kanchana.p.sridhar@intel.com
Subject: [PATCH v4 01/10] crypto: acomp - Define two new interfaces for compress/decompress batching.
Date: Fri, 22 Nov 2024 23:01:18 -0800	[thread overview]
Message-ID: <20241123070127.332773-2-kanchana.p.sridhar@intel.com> (raw)
In-Reply-To: <20241123070127.332773-1-kanchana.p.sridhar@intel.com>

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 implementations for
the 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.

A new helper function acomp_has_async_batching() can be invoked to query
if a crypto_acomp has registered these batch_compress and batch_decompress
interfaces.

Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@intel.com>
---
 crypto/acompress.c                  |  2 +
 include/crypto/acompress.h          | 91 +++++++++++++++++++++++++++++
 include/crypto/internal/acompress.h | 16 +++++
 3 files changed, 109 insertions(+)

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..4252bab3d0e1 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;
@@ -142,6 +164,13 @@ static inline bool acomp_is_async(struct crypto_acomp *tfm)
 	       CRYPTO_ALG_ASYNC;
 }
 
+static inline bool acomp_has_async_batching(struct crypto_acomp *tfm)
+{
+	return (acomp_is_async(tfm) &&
+		(crypto_comp_alg_common(tfm)->base.cra_flags & CRYPTO_ALG_TYPE_ACOMPRESS) &&
+		tfm->batch_compress && tfm->batch_decompress);
+}
+
 static inline struct crypto_acomp *crypto_acomp_reqtfm(struct acomp_req *req)
 {
 	return __crypto_acomp_tfm(req->base.tfm);
@@ -265,4 +294,66 @@ static inline int crypto_acomp_decompress(struct acomp_req *req)
 	return crypto_acomp_reqtfm(req)->decompress(req);
 }
 
+/**
+ * crypto_acomp_batch_compress() -- Invoke asynchronous compress of
+ *                                  a batch of requests
+ *
+ * Function invokes the asynchronous 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() -- Invoke asynchronous decompress of
+ *                                    a batch of requests
+ *
+ * Function invokes the asynchronous 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);
-- 
2.27.0



  reply	other threads:[~2024-11-23  7:01 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-11-23  7:01 [PATCH v4 00/10] zswap IAA compress batching Kanchana P Sridhar
2024-11-23  7:01 ` Kanchana P Sridhar [this message]
2024-11-25  9:35   ` [PATCH v4 01/10] crypto: acomp - Define two new interfaces for compress/decompress batching Herbert Xu
2024-11-25 20:03     ` Sridhar, Kanchana P
2024-11-26  2:13       ` Sridhar, Kanchana P
2024-11-26  2:14         ` Herbert Xu
2024-11-26  2:37           ` Sridhar, Kanchana P
2024-11-27  1:22             ` Sridhar, Kanchana P
2024-11-27  5:04               ` Herbert Xu
2024-11-23  7:01 ` [PATCH v4 02/10] crypto: iaa - Add an acomp_req flag CRYPTO_ACOMP_REQ_POLL to enable async mode Kanchana P Sridhar
2024-11-23  7:01 ` [PATCH v4 03/10] crypto: iaa - Implement batch_compress(), batch_decompress() API in iaa_crypto Kanchana P Sridhar
2024-11-26  7:05   ` kernel test robot
2024-11-23  7:01 ` [PATCH v4 04/10] crypto: iaa - Make async mode the default Kanchana P Sridhar
2024-11-23  7:01 ` [PATCH v4 05/10] crypto: iaa - Disable iaa_verify_compress by default Kanchana P Sridhar
2024-11-23  7:01 ` [PATCH v4 06/10] crypto: iaa - Re-organize the iaa_crypto driver code Kanchana P Sridhar
2024-11-23  7:01 ` [PATCH v4 07/10] crypto: iaa - Map IAA devices/wqs to cores based on packages instead of NUMA Kanchana P Sridhar
2024-11-23  7:01 ` [PATCH v4 08/10] crypto: iaa - Distribute compress jobs from all cores to all IAAs on a package Kanchana P Sridhar
2024-11-23  7:01 ` [PATCH v4 09/10] mm: zswap: Allocate pool batching resources if the crypto_alg supports batching Kanchana P Sridhar
2024-12-02 19:15   ` Nhat Pham
2024-12-03  0:30     ` Sridhar, Kanchana P
2024-12-03  8:00       ` Herbert Xu
2024-12-03 21:37         ` Sridhar, Kanchana P
2024-12-03 21:44           ` Yosry Ahmed
2024-12-03 22:17             ` Sridhar, Kanchana P
2024-12-03 22:24               ` Sridhar, Kanchana P
2024-12-04  1:42             ` Herbert Xu
2024-12-04 22:35               ` Yosry Ahmed
2024-12-04 22:49                 ` Sridhar, Kanchana P
2024-12-04 22:55                   ` Yosry Ahmed
2024-12-04 23:12                     ` Sridhar, Kanchana P
2024-12-21  6:30       ` Sridhar, Kanchana P
2024-11-23  7:01 ` [PATCH v4 10/10] mm: zswap: Compress batching with Intel IAA in zswap_batch_store() of large folios Kanchana P Sridhar
2024-11-25  8:00   ` kernel test robot
2024-11-25 20:20   ` Yosry Ahmed
2024-11-25 21:47     ` Johannes Weiner
2024-11-25 21:54     ` Sridhar, Kanchana P
2024-11-25 22:08       ` Yosry Ahmed
2024-12-02 19:26       ` Nhat Pham
2024-12-03  0:34         ` Sridhar, Kanchana P

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20241123070127.332773-2-kanchana.p.sridhar@intel.com \
    --to=kanchana.p.sridhar@intel.com \
    --cc=21cnbao@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=ardb@kernel.org \
    --cc=chengming.zhou@linux.dev \
    --cc=clabbe@baylibre.com \
    --cc=davem@davemloft.net \
    --cc=ebiggers@google.com \
    --cc=hannes@cmpxchg.org \
    --cc=herbert@gondor.apana.org.au \
    --cc=kristen.c.accardi@intel.com \
    --cc=linux-crypto@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=nphamcs@gmail.com \
    --cc=ryan.roberts@arm.com \
    --cc=surenb@google.com \
    --cc=usamaarif642@gmail.com \
    --cc=vinodh.gopal@intel.com \
    --cc=wajdi.k.feghali@intel.com \
    --cc=ying.huang@intel.com \
    --cc=yosryahmed@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox