diff mbox series

[v5,04/12] crypto: iaa - Implement batch_compress(), batch_decompress() API in iaa_crypto.

Message ID 20241221063119.29140-5-kanchana.p.sridhar@intel.com (mailing list archive)
State New
Headers show
Series zswap IAA compress batching | expand

Commit Message

Kanchana P Sridhar Dec. 21, 2024, 6:31 a.m. UTC
This patch provides iaa_crypto driver implementations for the newly added
crypto_acomp batch_compress() and batch_decompress() interfaces using
acomp request chaining.

iaa_crypto also implements the new crypto_acomp get_batch_size() interface
that returns an iaa_driver specific constant, IAA_CRYPTO_MAX_BATCH_SIZE
(set to 8U currently).

This allows swap modules such as zswap/zram to allocate required batching
resources and then invoke fully asynchronous batch parallel
compression/decompression of pages on systems with Intel IAA, by invoking
these API, respectively:

 crypto_acomp_batch_size(...);
 crypto_acomp_batch_compress(...);
 crypto_acomp_batch_decompress(...);

This enables zswap compress batching code to be developed in
a manner similar to the current single-page synchronous calls to:

 crypto_acomp_compress(...);
 crypto_acomp_decompress(...);

thereby, facilitating encapsulated and modular hand-off between the kernel
zswap/zram code and the crypto_acomp layer.

Since iaa_crypto supports the use of acomp request chaining, this patch
also adds CRYPTO_ALG_REQ_CHAIN to the iaa_acomp_fixed_deflate algorithm's
cra_flags.

Suggested-by: Yosry Ahmed <yosryahmed@google.com>
Suggested-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@intel.com>
---
 drivers/crypto/intel/iaa/iaa_crypto.h      |   9 +
 drivers/crypto/intel/iaa/iaa_crypto_main.c | 395 ++++++++++++++++++++-
 2 files changed, 403 insertions(+), 1 deletion(-)

Comments

kernel test robot Dec. 22, 2024, 4:07 a.m. UTC | #1
Hi Kanchana,

kernel test robot noticed the following build warnings:

[auto build test WARNING on 5555a83c82d66729e4abaf16ae28d6bd81f9a64a]

url:    https://github.com/intel-lab-lkp/linux/commits/Kanchana-P-Sridhar/crypto-acomp-Add-synchronous-asynchronous-acomp-request-chaining/20241221-143254
base:   5555a83c82d66729e4abaf16ae28d6bd81f9a64a
patch link:    https://lore.kernel.org/r/20241221063119.29140-5-kanchana.p.sridhar%40intel.com
patch subject: [PATCH v5 04/12] crypto: iaa - Implement batch_compress(), batch_decompress() API in iaa_crypto.
config: x86_64-allyesconfig (https://download.01.org/0day-ci/archive/20241222/202412221117.i9BKx0mV-lkp@intel.com/config)
compiler: clang version 19.1.3 (https://github.com/llvm/llvm-project ab51eccf88f5321e7c60591c5546b254b6afab99)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20241222/202412221117.i9BKx0mV-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202412221117.i9BKx0mV-lkp@intel.com/

All warnings (new ones prefixed by >>):

>> drivers/crypto/intel/iaa/iaa_crypto_main.c:1897: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
    * This API provides IAA compress batching functionality for use by swap
   drivers/crypto/intel/iaa/iaa_crypto_main.c:2050: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
    * This API provides IAA decompress batching functionality for use by swap


vim +1897 drivers/crypto/intel/iaa/iaa_crypto_main.c

  1895	
  1896	/**
> 1897	 * This API provides IAA compress batching functionality for use by swap
  1898	 * modules.
  1899	 *
  1900	 * @reqs: @nr_pages asynchronous compress requests.
  1901	 * @wait: crypto_wait for acomp batch compress implemented using request
  1902	 *        chaining. Required if async_mode is "false". If async_mode is "true",
  1903	 *        and @wait is NULL, the completions will be processed using
  1904	 *        asynchronous polling of the requests' completion statuses.
  1905	 * @pages: Pages to be compressed by IAA.
  1906	 * @dsts: Pre-allocated destination buffers to store results of IAA
  1907	 *        compression. Each element of @dsts must be of size "PAGE_SIZE * 2".
  1908	 * @dlens: Will contain the compressed lengths.
  1909	 * @errors: zero on successful compression of the corresponding
  1910	 *          req, or error code in case of error.
  1911	 * @nr_pages: The number of pages, up to IAA_CRYPTO_MAX_BATCH_SIZE,
  1912	 *            to be compressed.
  1913	 *
  1914	 * Returns true if all compress requests complete successfully,
  1915	 * false otherwise.
  1916	 */
  1917	static bool iaa_comp_acompress_batch(
  1918		struct acomp_req *reqs[],
  1919		struct crypto_wait *wait,
  1920		struct page *pages[],
  1921		u8 *dsts[],
  1922		unsigned int dlens[],
  1923		int errors[],
  1924		int nr_pages)
  1925	{
  1926		struct scatterlist inputs[IAA_CRYPTO_MAX_BATCH_SIZE];
  1927		struct scatterlist outputs[IAA_CRYPTO_MAX_BATCH_SIZE];
  1928		bool compressions_done = false;
  1929		bool async = (async_mode && !use_irq);
  1930		bool async_poll = (async && !wait);
  1931		int i, err = 0;
  1932	
  1933		BUG_ON(nr_pages > IAA_CRYPTO_MAX_BATCH_SIZE);
  1934		BUG_ON(!async && !wait);
  1935	
  1936		if (async)
  1937			iaa_set_req_poll(reqs, nr_pages, true);
  1938		else
  1939			iaa_set_req_poll(reqs, nr_pages, false);
  1940	
  1941		/*
  1942		 * Prepare and submit acomp_reqs to IAA. IAA will process these
  1943		 * compress jobs in parallel if async_mode is true.
  1944		 */
  1945		for (i = 0; i < nr_pages; ++i) {
  1946			sg_init_table(&inputs[i], 1);
  1947			sg_set_page(&inputs[i], pages[i], PAGE_SIZE, 0);
  1948	
  1949			/*
  1950			 * Each dst buffer should be of size (PAGE_SIZE * 2).
  1951			 * Reflect same in sg_list.
  1952			 */
  1953			sg_init_one(&outputs[i], dsts[i], PAGE_SIZE * 2);
  1954			acomp_request_set_params(reqs[i], &inputs[i],
  1955						 &outputs[i], PAGE_SIZE, dlens[i]);
  1956	
  1957			/*
  1958			 * As long as the API is called with a valid "wait", chain the
  1959			 * requests for synchronous/asynchronous compress ops.
  1960			 * If async_mode is in effect, but the API is called with a
  1961			 * NULL "wait", submit the requests first, and poll for
  1962			 * their completion status later, after all descriptors have
  1963			 * been submitted.
  1964			 */
  1965			if (!async_poll) {
  1966				/* acomp request chaining. */
  1967				if (i)
  1968					acomp_request_chain(reqs[i], reqs[0]);
  1969				else
  1970					acomp_reqchain_init(reqs[0], 0, crypto_req_done,
  1971							    wait);
  1972			} else {
  1973				errors[i] = iaa_comp_acompress(reqs[i]);
  1974	
  1975				if (errors[i] != -EINPROGRESS) {
  1976					errors[i] = -EINVAL;
  1977					err = -EINVAL;
  1978				} else {
  1979					errors[i] = -EAGAIN;
  1980				}
  1981			}
  1982		}
  1983	
  1984		if (!async_poll) {
  1985			if (async)
  1986				/* Process the request chain in parallel. */
  1987				err = crypto_wait_req(acomp_do_async_req_chain(reqs[0],
  1988						      iaa_comp_acompress, iaa_comp_poll),
  1989						      wait);
  1990			else
  1991				/* Process the request chain in series. */
  1992				err = crypto_wait_req(acomp_do_req_chain(reqs[0],
  1993						      iaa_comp_acompress), wait);
  1994	
  1995			for (i = 0; i < nr_pages; ++i) {
  1996				errors[i] = acomp_request_err(reqs[i]);
  1997				if (errors[i]) {
  1998					err = -EINVAL;
  1999					pr_debug("Request chaining req %d compress error %d\n", i, errors[i]);
  2000				} else {
  2001					dlens[i] = reqs[i]->dlen;
  2002				}
  2003			}
  2004	
  2005			goto reset_reqs;
  2006		}
  2007	
  2008		/*
  2009		 * Asynchronously poll for and process IAA compress job completions.
  2010		 */
  2011		while (!compressions_done) {
  2012			compressions_done = true;
  2013	
  2014			for (i = 0; i < nr_pages; ++i) {
  2015				/*
  2016				 * Skip, if the compression has already completed
  2017				 * successfully or with an error.
  2018				 */
  2019				if (errors[i] != -EAGAIN)
  2020					continue;
  2021	
  2022				errors[i] = iaa_comp_poll(reqs[i]);
  2023	
  2024				if (errors[i]) {
  2025					if (errors[i] == -EAGAIN)
  2026						compressions_done = false;
  2027					else
  2028						err = -EINVAL;
  2029				} else {
  2030					dlens[i] = reqs[i]->dlen;
  2031				}
  2032			}
  2033		}
  2034	
  2035	reset_reqs:
  2036		/*
  2037		 * For the same 'reqs[]' to be usable by
  2038		 * iaa_comp_acompress()/iaa_comp_deacompress(),
  2039		 * clear the CRYPTO_ACOMP_REQ_POLL bit on all acomp_reqs, and the
  2040		 * CRYPTO_TFM_REQ_CHAIN bit on the reqs[0].
  2041		 */
  2042		iaa_set_req_poll(reqs, nr_pages, false);
  2043		if (!async_poll)
  2044			acomp_reqchain_clear(reqs[0], wait);
  2045	
  2046		return !err;
  2047	}
  2048
diff mbox series

Patch

diff --git a/drivers/crypto/intel/iaa/iaa_crypto.h b/drivers/crypto/intel/iaa/iaa_crypto.h
index 56985e395263..b3b67c44ec8a 100644
--- a/drivers/crypto/intel/iaa/iaa_crypto.h
+++ b/drivers/crypto/intel/iaa/iaa_crypto.h
@@ -39,6 +39,15 @@ 
 					 IAA_DECOMP_CHECK_FOR_EOB | \
 					 IAA_DECOMP_STOP_ON_EOB)
 
+/*
+ * The maximum compress/decompress batch size for IAA's implementation of
+ * the crypto_acomp batch_compress() and batch_decompress() interfaces.
+ * The IAA compression algorithms should provide the crypto_acomp
+ * get_batch_size() interface through a function that returns this
+ * constant.
+ */
+#define IAA_CRYPTO_MAX_BATCH_SIZE 8U
+
 /* 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 29d03df39fab..b51b0b4b9ac3 100644
--- a/drivers/crypto/intel/iaa/iaa_crypto_main.c
+++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c
@@ -1807,6 +1807,396 @@  static void compression_ctx_init(struct iaa_compression_ctx *ctx)
 	ctx->use_irq = use_irq;
 }
 
+static int iaa_comp_poll(struct acomp_req *req)
+{
+	struct idxd_desc *idxd_desc;
+	struct idxd_device *idxd;
+	struct iaa_wq *iaa_wq;
+	struct pci_dev *pdev;
+	struct device *dev;
+	struct idxd_wq *wq;
+	bool compress_op;
+	int ret;
+
+	idxd_desc = req->base.data;
+	if (!idxd_desc)
+		return -EAGAIN;
+
+	compress_op = (idxd_desc->iax_hw->opcode == IAX_OPCODE_COMPRESS);
+	wq = idxd_desc->wq;
+	iaa_wq = idxd_wq_get_private(wq);
+	idxd = iaa_wq->iaa_device->idxd;
+	pdev = idxd->pdev;
+	dev = &pdev->dev;
+
+	ret = check_completion(dev, idxd_desc->iax_completion, true, true);
+	if (ret == -EAGAIN)
+		return ret;
+	if (ret)
+		goto out;
+
+	req->dlen = idxd_desc->iax_completion->output_size;
+
+	/* Update stats */
+	if (compress_op) {
+		update_total_comp_bytes_out(req->dlen);
+		update_wq_comp_bytes(wq, req->dlen);
+	} else {
+		update_total_decomp_bytes_in(req->slen);
+		update_wq_decomp_bytes(wq, req->slen);
+	}
+
+	if (iaa_verify_compress && (idxd_desc->iax_hw->opcode == IAX_OPCODE_COMPRESS)) {
+		struct crypto_tfm *tfm = req->base.tfm;
+		dma_addr_t src_addr, dst_addr;
+		u32 compression_crc;
+
+		compression_crc = idxd_desc->iax_completion->crc;
+
+		dma_sync_sg_for_device(dev, req->dst, 1, DMA_FROM_DEVICE);
+		dma_sync_sg_for_device(dev, req->src, 1, DMA_TO_DEVICE);
+
+		src_addr = sg_dma_address(req->src);
+		dst_addr = sg_dma_address(req->dst);
+
+		ret = iaa_compress_verify(tfm, req, wq, src_addr, req->slen,
+					  dst_addr, &req->dlen, compression_crc);
+	}
+out:
+	/* caller doesn't call crypto_wait_req, so no acomp_request_complete() */
+
+	dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
+	dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
+
+	idxd_free_desc(idxd_desc->wq, idxd_desc);
+
+	dev_dbg(dev, "%s: returning ret=%d\n", __func__, ret);
+
+	return ret;
+}
+
+static unsigned int iaa_comp_get_batch_size(void)
+{
+	return IAA_CRYPTO_MAX_BATCH_SIZE;
+}
+
+static void iaa_set_req_poll(
+	struct acomp_req *reqs[],
+	int nr_reqs,
+	bool set_flag)
+{
+	int i;
+
+	for (i = 0; i < nr_reqs; ++i) {
+		set_flag ? (reqs[i]->flags |= CRYPTO_ACOMP_REQ_POLL) :
+			   (reqs[i]->flags &= ~CRYPTO_ACOMP_REQ_POLL);
+	}
+}
+
+/**
+ * This API provides IAA compress batching functionality for use by swap
+ * modules.
+ *
+ * @reqs: @nr_pages asynchronous compress requests.
+ * @wait: crypto_wait for acomp batch compress implemented using request
+ *        chaining. Required if async_mode is "false". If async_mode is "true",
+ *        and @wait is NULL, the completions will be processed using
+ *        asynchronous polling of the requests' completion statuses.
+ * @pages: Pages to be compressed by IAA.
+ * @dsts: Pre-allocated destination buffers to store results of IAA
+ *        compression. Each element of @dsts must be of size "PAGE_SIZE * 2".
+ * @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 IAA_CRYPTO_MAX_BATCH_SIZE,
+ *            to be compressed.
+ *
+ * Returns true if all compress requests complete successfully,
+ * false otherwise.
+ */
+static bool iaa_comp_acompress_batch(
+	struct acomp_req *reqs[],
+	struct crypto_wait *wait,
+	struct page *pages[],
+	u8 *dsts[],
+	unsigned int dlens[],
+	int errors[],
+	int nr_pages)
+{
+	struct scatterlist inputs[IAA_CRYPTO_MAX_BATCH_SIZE];
+	struct scatterlist outputs[IAA_CRYPTO_MAX_BATCH_SIZE];
+	bool compressions_done = false;
+	bool async = (async_mode && !use_irq);
+	bool async_poll = (async && !wait);
+	int i, err = 0;
+
+	BUG_ON(nr_pages > IAA_CRYPTO_MAX_BATCH_SIZE);
+	BUG_ON(!async && !wait);
+
+	if (async)
+		iaa_set_req_poll(reqs, nr_pages, true);
+	else
+		iaa_set_req_poll(reqs, nr_pages, false);
+
+	/*
+	 * Prepare and submit acomp_reqs to IAA. IAA will process these
+	 * compress jobs in parallel if async_mode is true.
+	 */
+	for (i = 0; i < nr_pages; ++i) {
+		sg_init_table(&inputs[i], 1);
+		sg_set_page(&inputs[i], pages[i], PAGE_SIZE, 0);
+
+		/*
+		 * Each dst buffer should be of size (PAGE_SIZE * 2).
+		 * Reflect same in sg_list.
+		 */
+		sg_init_one(&outputs[i], dsts[i], PAGE_SIZE * 2);
+		acomp_request_set_params(reqs[i], &inputs[i],
+					 &outputs[i], PAGE_SIZE, dlens[i]);
+
+		/*
+		 * As long as the API is called with a valid "wait", chain the
+		 * requests for synchronous/asynchronous compress ops.
+		 * If async_mode is in effect, but the API is called with a
+		 * NULL "wait", submit the requests first, and poll for
+		 * their completion status later, after all descriptors have
+		 * been submitted.
+		 */
+		if (!async_poll) {
+			/* acomp request chaining. */
+			if (i)
+				acomp_request_chain(reqs[i], reqs[0]);
+			else
+				acomp_reqchain_init(reqs[0], 0, crypto_req_done,
+						    wait);
+		} else {
+			errors[i] = iaa_comp_acompress(reqs[i]);
+
+			if (errors[i] != -EINPROGRESS) {
+				errors[i] = -EINVAL;
+				err = -EINVAL;
+			} else {
+				errors[i] = -EAGAIN;
+			}
+		}
+	}
+
+	if (!async_poll) {
+		if (async)
+			/* Process the request chain in parallel. */
+			err = crypto_wait_req(acomp_do_async_req_chain(reqs[0],
+					      iaa_comp_acompress, iaa_comp_poll),
+					      wait);
+		else
+			/* Process the request chain in series. */
+			err = crypto_wait_req(acomp_do_req_chain(reqs[0],
+					      iaa_comp_acompress), wait);
+
+		for (i = 0; i < nr_pages; ++i) {
+			errors[i] = acomp_request_err(reqs[i]);
+			if (errors[i]) {
+				err = -EINVAL;
+				pr_debug("Request chaining req %d compress error %d\n", i, errors[i]);
+			} else {
+				dlens[i] = reqs[i]->dlen;
+			}
+		}
+
+		goto reset_reqs;
+	}
+
+	/*
+	 * Asynchronously poll for and process IAA compress job completions.
+	 */
+	while (!compressions_done) {
+		compressions_done = true;
+
+		for (i = 0; i < nr_pages; ++i) {
+			/*
+			 * Skip, if the compression has already completed
+			 * successfully or with an error.
+			 */
+			if (errors[i] != -EAGAIN)
+				continue;
+
+			errors[i] = iaa_comp_poll(reqs[i]);
+
+			if (errors[i]) {
+				if (errors[i] == -EAGAIN)
+					compressions_done = false;
+				else
+					err = -EINVAL;
+			} else {
+				dlens[i] = reqs[i]->dlen;
+			}
+		}
+	}
+
+reset_reqs:
+	/*
+	 * For the same 'reqs[]' to be usable by
+	 * iaa_comp_acompress()/iaa_comp_deacompress(),
+	 * clear the CRYPTO_ACOMP_REQ_POLL bit on all acomp_reqs, and the
+	 * CRYPTO_TFM_REQ_CHAIN bit on the reqs[0].
+	 */
+	iaa_set_req_poll(reqs, nr_pages, false);
+	if (!async_poll)
+		acomp_reqchain_clear(reqs[0], wait);
+
+	return !err;
+}
+
+/**
+ * This API provides IAA decompress batching functionality for use by swap
+ * modules.
+ *
+ * @reqs: @nr_pages asynchronous decompress requests.
+ * @wait: crypto_wait for acomp batch decompress implemented using request
+ *        chaining. Required if async_mode is "false". If async_mode is "true",
+ *        and @wait is NULL, the completions will be processed using
+ *        asynchronous polling of the requests' completion statuses.
+ * @srcs: The src buffers to be decompressed by IAA.
+ * @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 IAA_CRYPTO_MAX_BATCH_SIZE,
+ *            to be decompressed.
+ *
+ * Returns true if all decompress requests complete successfully,
+ * false otherwise.
+ */
+static bool iaa_comp_adecompress_batch(
+	struct acomp_req *reqs[],
+	struct crypto_wait *wait,
+	u8 *srcs[],
+	struct page *pages[],
+	unsigned int slens[],
+	int errors[],
+	int nr_pages)
+{
+	struct scatterlist inputs[IAA_CRYPTO_MAX_BATCH_SIZE];
+	struct scatterlist outputs[IAA_CRYPTO_MAX_BATCH_SIZE];
+	unsigned int dlens[IAA_CRYPTO_MAX_BATCH_SIZE];
+	bool decompressions_done = false;
+	bool async = (async_mode && !use_irq);
+	bool async_poll = (async && !wait);
+	int i, err = 0;
+
+	BUG_ON(nr_pages > IAA_CRYPTO_MAX_BATCH_SIZE);
+	BUG_ON(!async && !wait);
+
+	if (async)
+		iaa_set_req_poll(reqs, nr_pages, true);
+	else
+		iaa_set_req_poll(reqs, nr_pages, false);
+
+	/*
+	 * Prepare and submit acomp_reqs to IAA. IAA will process these
+	 * decompress jobs in parallel if async_mode is true.
+	 */
+	for (i = 0; i < nr_pages; ++i) {
+		dlens[i] = PAGE_SIZE;
+		sg_init_one(&inputs[i], srcs[i], slens[i]);
+		sg_init_table(&outputs[i], 1);
+		sg_set_page(&outputs[i], pages[i], PAGE_SIZE, 0);
+		acomp_request_set_params(reqs[i], &inputs[i],
+					&outputs[i], slens[i], dlens[i]);
+
+		/*
+		 * As long as the API is called with a valid "wait", chain the
+		 * requests for synchronous/asynchronous decompress ops.
+		 * If async_mode is in effect, but the API is called with a
+		 * NULL "wait", submit the requests first, and poll for
+		 * their completion status later, after all descriptors have
+		 * been submitted.
+		 */
+		if (!async_poll) {
+			/* acomp request chaining. */
+			if (i)
+				acomp_request_chain(reqs[i], reqs[0]);
+			else
+				acomp_reqchain_init(reqs[0], 0, crypto_req_done,
+						    wait);
+		} else {
+			errors[i] = iaa_comp_adecompress(reqs[i]);
+
+			if (errors[i] != -EINPROGRESS) {
+				errors[i] = -EINVAL;
+				err = -EINVAL;
+			} else {
+				errors[i] = -EAGAIN;
+			}
+		}
+	}
+
+	if (!async_poll) {
+		if (async)
+			/* Process the request chain in parallel. */
+			err = crypto_wait_req(acomp_do_async_req_chain(reqs[0],
+					      iaa_comp_adecompress, iaa_comp_poll),
+					      wait);
+		else
+			/* Process the request chain in series. */
+			err = crypto_wait_req(acomp_do_req_chain(reqs[0],
+					      iaa_comp_adecompress), wait);
+
+		for (i = 0; i < nr_pages; ++i) {
+			errors[i] = acomp_request_err(reqs[i]);
+			if (errors[i]) {
+				err = -EINVAL;
+				pr_debug("Request chaining req %d decompress error %d\n", i, errors[i]);
+			} else {
+				dlens[i] = reqs[i]->dlen;
+				BUG_ON(dlens[i] != PAGE_SIZE);
+			}
+		}
+
+		goto reset_reqs;
+	}
+
+	/*
+	 * Asynchronously poll for and process IAA decompress job completions.
+	 */
+	while (!decompressions_done) {
+		decompressions_done = true;
+
+		for (i = 0; i < nr_pages; ++i) {
+			/*
+			 * Skip, if the decompression has already completed
+			 * successfully or with an error.
+			 */
+			if (errors[i] != -EAGAIN)
+				continue;
+
+			errors[i] = iaa_comp_poll(reqs[i]);
+
+			if (errors[i]) {
+				if (errors[i] == -EAGAIN)
+					decompressions_done = false;
+				else
+					err = -EINVAL;
+			} else {
+				dlens[i] = reqs[i]->dlen;
+				BUG_ON(dlens[i] != PAGE_SIZE);
+			}
+		}
+	}
+
+reset_reqs:
+	/*
+	 * For the same 'reqs[]' to be usable by
+	 * iaa_comp_acompress()/iaa_comp_deacompress(),
+	 * clear the CRYPTO_ACOMP_REQ_POLL bit on all acomp_reqs, and the
+	 * CRYPTO_TFM_REQ_CHAIN bit on the reqs[0].
+	 */
+	iaa_set_req_poll(reqs, nr_pages, false);
+	if (!async_poll)
+		acomp_reqchain_clear(reqs[0], wait);
+
+	return !err;
+}
+
 static int iaa_comp_init_fixed(struct crypto_acomp *acomp_tfm)
 {
 	struct crypto_tfm *tfm = crypto_acomp_tfm(acomp_tfm);
@@ -1832,10 +2222,13 @@  static struct acomp_alg iaa_acomp_fixed_deflate = {
 	.compress		= iaa_comp_acompress,
 	.decompress		= iaa_comp_adecompress,
 	.dst_free               = dst_free,
+	.get_batch_size		= iaa_comp_get_batch_size,
+	.batch_compress		= iaa_comp_acompress_batch,
+	.batch_decompress	= iaa_comp_adecompress_batch,
 	.base			= {
 		.cra_name		= "deflate",
 		.cra_driver_name	= "deflate-iaa",
-		.cra_flags		= CRYPTO_ALG_ASYNC,
+		.cra_flags		= CRYPTO_ALG_ASYNC | CRYPTO_ALG_REQ_CHAIN,
 		.cra_ctxsize		= sizeof(struct iaa_compression_ctx),
 		.cra_module		= THIS_MODULE,
 		.cra_priority		= IAA_ALG_PRIORITY,