Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Kenneth Lee <nek.in.cn@gmail.com>
To:     Jonathan Corbet <corbet@lwn.net>,
        Herbert Xu <herbert@gondor.apana.org.au>,
        "David S . Miller" <davem@davemloft.net>,
        Joerg Roedel <joro@8bytes.org>,
        Alex Williamson <alex.williamson@redhat.com>,
        Kenneth Lee <liguozhu@hisilicon.com>,
        Hao Fang <fanghao11@huawei.com>,
        Zhou Wang <wangzhou1@hisilicon.com>,
        Zaibo Xu <xuzaibo@huawei.com>,
        Philippe Ombredanne <pombredanne@nexb.com>,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
        linux-crypto@vger.kernel.org, iommu@lists.linux-foundation.org,
        kvm@vger.kernel.org, linux-accelerators@lists.ozlabs.org,
        Lu Baolu <baolu.lu@linux.intel.com>,
        Sanjay Kumar <sanjay.k.kumar@intel.com>
Cc:     linuxarm@huawei.com
Subject: [PATCH 5/7] crypto: Add Hisilicon Zip driver
Date:   Mon,  3 Sep 2018 08:52:02 +0800
Message-Id: <20180903005204.26041-6-nek.in.cn@gmail.com>
In-Reply-To: <20180903005204.26041-1-nek.in.cn@gmail.com>
References: <20180903005204.26041-1-nek.in.cn@gmail.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: Kenneth Lee <liguozhu@hisilicon.com>

The Hisilicon ZIP accelerator implements zlib and gzip algorithm support
for the software. It uses Hisilicon QM as the interface to the CPU, so it
is shown up as a PCIE device to the CPU with a group of queues.

This commit provides PCIE driver to the accelerator and register it to
the crypto subsystem.

Signed-off-by: Kenneth Lee <liguozhu@hisilicon.com>
Signed-off-by: Zhou Wang <wangzhou1@hisilicon.com>
Signed-off-by: Hao Fang <fanghao11@huawei.com>
---
 drivers/crypto/hisilicon/Kconfig          |   7 +
 drivers/crypto/hisilicon/Makefile         |   1 +
 drivers/crypto/hisilicon/zip/Makefile     |   2 +
 drivers/crypto/hisilicon/zip/zip.h        |  57 ++++
 drivers/crypto/hisilicon/zip/zip_crypto.c | 353 ++++++++++++++++++++++
 drivers/crypto/hisilicon/zip/zip_crypto.h |   8 +
 drivers/crypto/hisilicon/zip/zip_main.c   | 195 ++++++++++++
 7 files changed, 623 insertions(+)
 create mode 100644 drivers/crypto/hisilicon/zip/Makefile
 create mode 100644 drivers/crypto/hisilicon/zip/zip.h
 create mode 100644 drivers/crypto/hisilicon/zip/zip_crypto.c
 create mode 100644 drivers/crypto/hisilicon/zip/zip_crypto.h
 create mode 100644 drivers/crypto/hisilicon/zip/zip_main.c

diff --git a/drivers/crypto/hisilicon/Kconfig b/drivers/crypto/hisilicon/Kconfig
index 02a6eef84101..1d155708cd69 100644
--- a/drivers/crypto/hisilicon/Kconfig
+++ b/drivers/crypto/hisilicon/Kconfig
@@ -20,3 +20,10 @@ config CRYPTO_DEV_HISI_SEC
 config CRYPTO_DEV_HISI_QM
 	tristate
 	depends on ARM64 && PCI
+
+config CRYPTO_DEV_HISI_ZIP
+	tristate "Support for HISI ZIP Driver"
+	depends on ARM64 && CRYPTO_DEV_HISILICON
+	select CRYPTO_DEV_HISI_QM
+	help
+	  Support for HiSilicon HIP08 ZIP Driver
diff --git a/drivers/crypto/hisilicon/Makefile b/drivers/crypto/hisilicon/Makefile
index 05e9052e0f52..c97c5b27c3cb 100644
--- a/drivers/crypto/hisilicon/Makefile
+++ b/drivers/crypto/hisilicon/Makefile
@@ -1,3 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_CRYPTO_DEV_HISI_SEC) += sec/
 obj-$(CONFIG_CRYPTO_DEV_HISI_QM) += qm.o
+obj-$(CONFIG_CRYPTO_DEV_HISI_ZIP) += zip/
diff --git a/drivers/crypto/hisilicon/zip/Makefile b/drivers/crypto/hisilicon/zip/Makefile
new file mode 100644
index 000000000000..a936f099ee22
--- /dev/null
+++ b/drivers/crypto/hisilicon/zip/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_CRYPTO_DEV_HISI_ZIP) += hisi_zip.o
+hisi_zip-objs = zip_main.o zip_crypto.o
diff --git a/drivers/crypto/hisilicon/zip/zip.h b/drivers/crypto/hisilicon/zip/zip.h
new file mode 100644
index 000000000000..87515e158b17
--- /dev/null
+++ b/drivers/crypto/hisilicon/zip/zip.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+#ifndef HISI_ZIP_H
+#define HISI_ZIP_H
+
+#include <linux/list.h>
+#include "../qm.h"
+
+#define HZIP_SQE_SIZE			128
+#define HZIP_SQ_SIZE			(HZIP_SQE_SIZE * QM_Q_DEPTH)
+#define QM_CQ_SIZE			(QM_CQE_SIZE * QM_Q_DEPTH)
+#define HZIP_PF_DEF_Q_NUM		64
+#define HZIP_PF_DEF_Q_BASE		0
+
+struct hisi_zip {
+	struct qm_info qm;
+	struct list_head list;
+
+#ifdef CONFIG_CRYPTO_DEV_HISI_SPIMDEV
+	struct vfio_spimdev *spimdev;
+#endif
+};
+
+struct hisi_zip_sqe {
+	__u32 consumed;
+	__u32 produced;
+	__u32 comp_data_length;
+	__u32 dw3;
+	__u32 input_data_length;
+	__u32 lba_l;
+	__u32 lba_h;
+	__u32 dw7;
+	__u32 dw8;
+	__u32 dw9;
+	__u32 dw10;
+	__u32 priv_info;
+	__u32 dw12;
+	__u32 tag;
+	__u32 dest_avail_out;
+	__u32 rsvd0;
+	__u32 comp_head_addr_l;
+	__u32 comp_head_addr_h;
+	__u32 source_addr_l;
+	__u32 source_addr_h;
+	__u32 dest_addr_l;
+	__u32 dest_addr_h;
+	__u32 stream_ctx_addr_l;
+	__u32 stream_ctx_addr_h;
+	__u32 cipher_key1_addr_l;
+	__u32 cipher_key1_addr_h;
+	__u32 cipher_key2_addr_l;
+	__u32 cipher_key2_addr_h;
+	__u32 rsvd1[4];
+};
+
+extern struct list_head hisi_zip_list;
+
+#endif
diff --git a/drivers/crypto/hisilicon/zip/zip_crypto.c b/drivers/crypto/hisilicon/zip/zip_crypto.c
new file mode 100644
index 000000000000..0a0e3de8e1d6
--- /dev/null
+++ b/drivers/crypto/hisilicon/zip/zip_crypto.c
@@ -0,0 +1,353 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+#include <linux/crypto.h>
+#include <linux/dma-mapping.h>
+#include <linux/pci.h>
+#include <linux/topology.h>
+#include "../qm.h"
+#include "zip.h"
+
+#define INPUT_BUFFER_SIZE	(64 * 1024)
+#define OUTPUT_BUFFER_SIZE	(64 * 1024)
+
+#define COMP_NAME_TO_TYPE(alg_name)			\
+	(!strcmp((alg_name), "zlib-deflate") ? 0x02 :	\
+	 !strcmp((alg_name), "gzip") ? 0x03 : 0)	\
+
+struct hisi_zip_buffer {
+	u8 *input;
+	dma_addr_t input_dma;
+	u8 *output;
+	dma_addr_t output_dma;
+};
+
+struct hisi_zip_qp_ctx {
+	struct hisi_zip_buffer buffer;
+	struct hisi_qp *qp;
+	struct hisi_zip_sqe zip_sqe;
+};
+
+struct hisi_zip_ctx {
+#define QPC_COMP	0
+#define QPC_DECOMP	1
+	struct hisi_zip_qp_ctx qp_ctx[2];
+};
+
+static struct hisi_zip *find_zip_device(int node)
+{
+	struct hisi_zip *hisi_zip, *ret = NULL;
+	struct device *dev;
+	int min_distance = 100;
+
+	list_for_each_entry(hisi_zip, &hisi_zip_list, list) {
+		dev = &hisi_zip->qm.pdev->dev;
+		if (node_distance(dev->numa_node, node) < min_distance) {
+			ret = hisi_zip;
+			min_distance = node_distance(dev->numa_node, node);
+		}
+	}
+
+	return ret;
+}
+
+static void hisi_zip_qp_event_notifier(struct hisi_qp *qp)
+{
+	complete(&qp->completion);
+}
+
+static int hisi_zip_fill_sqe_v1(void *sqe, void *q_parm, u32 len)
+{
+	struct hisi_zip_sqe *zip_sqe = (struct hisi_zip_sqe *)sqe;
+	struct hisi_zip_qp_ctx *qp_ctx = (struct hisi_zip_qp_ctx *)q_parm;
+	struct hisi_zip_buffer *buffer = &qp_ctx->buffer;
+
+	memset(zip_sqe, 0, sizeof(struct hisi_zip_sqe));
+
+	zip_sqe->input_data_length = len;
+	zip_sqe->dw9 = qp_ctx->qp->req_type;
+	zip_sqe->dest_avail_out = OUTPUT_BUFFER_SIZE;
+	zip_sqe->source_addr_l = lower_32_bits(buffer->input_dma);
+	zip_sqe->source_addr_h = upper_32_bits(buffer->input_dma);
+	zip_sqe->dest_addr_l = lower_32_bits(buffer->output_dma);
+	zip_sqe->dest_addr_h = upper_32_bits(buffer->output_dma);
+
+	return 0;
+}
+
+/* let's allocate one buffer now, may have problem in async case */
+static int hisi_zip_alloc_qp_buffer(struct hisi_zip_qp_ctx *hisi_zip_qp_ctx)
+{
+	struct hisi_zip_buffer *buffer = &hisi_zip_qp_ctx->buffer;
+	struct hisi_qp *qp = hisi_zip_qp_ctx->qp;
+	struct device *dev = &qp->qm->pdev->dev;
+	int ret;
+
+	buffer->input = dma_alloc_coherent(dev, INPUT_BUFFER_SIZE,
+					   &buffer->input_dma, GFP_KERNEL);
+	if (!buffer->input)
+		return -ENOMEM;
+
+	buffer->output = dma_alloc_coherent(dev, OUTPUT_BUFFER_SIZE,
+					    &buffer->output_dma, GFP_KERNEL);
+	if (!buffer->output) {
+		ret = -ENOMEM;
+		goto err_alloc_output_buffer;
+	}
+
+	return 0;
+
+err_alloc_output_buffer:
+	dma_free_coherent(dev, INPUT_BUFFER_SIZE, buffer->input,
+			  buffer->input_dma);
+	return ret;
+}
+
+static void hisi_zip_free_qp_buffer(struct hisi_zip_qp_ctx *hisi_zip_qp_ctx)
+{
+	struct hisi_zip_buffer *buffer = &hisi_zip_qp_ctx->buffer;
+	struct hisi_qp *qp = hisi_zip_qp_ctx->qp;
+	struct device *dev = &qp->qm->pdev->dev;
+
+	dma_free_coherent(dev, INPUT_BUFFER_SIZE, buffer->input,
+			  buffer->input_dma);
+	dma_free_coherent(dev, OUTPUT_BUFFER_SIZE, buffer->output,
+			  buffer->output_dma);
+}
+
+static int hisi_zip_create_qp(struct qm_info *qm, struct hisi_zip_qp_ctx *ctx,
+			      int alg_type, int req_type)
+{
+	struct hisi_qp *qp;
+	int ret;
+
+	qp = hisi_qm_create_qp(qm, alg_type);
+
+	if (IS_ERR(qp))
+		return PTR_ERR(qp);
+
+	qp->event_cb = hisi_zip_qp_event_notifier;
+	qp->req_type = req_type;
+
+	qp->qp_ctx = ctx;
+	ctx->qp = qp;
+
+	ret = hisi_zip_alloc_qp_buffer(ctx);
+	if (ret)
+		goto err_with_qp;
+
+	ret = hisi_qm_start_qp(qp, 0);
+	if (ret < 0)
+		goto err_with_qp_buffer;
+
+	return 0;
+err_with_qp_buffer:
+	hisi_zip_free_qp_buffer(ctx);
+err_with_qp:
+	hisi_qm_release_qp(qp);
+	return ret;
+}
+
+static void hisi_zip_release_qp(struct hisi_zip_qp_ctx *ctx)
+{
+	hisi_qm_release_qp(ctx->qp);
+	hisi_zip_free_qp_buffer(ctx);
+}
+
+static int hisi_zip_alloc_comp_ctx(struct crypto_tfm *tfm)
+{
+	struct hisi_zip_ctx *hisi_zip_ctx = crypto_tfm_ctx(tfm);
+	const char *alg_name = crypto_tfm_alg_name(tfm);
+	struct hisi_zip *hisi_zip;
+	struct qm_info *qm;
+	int ret, i, j;
+
+	u8 req_type = COMP_NAME_TO_TYPE(alg_name);
+
+	/* find the proper zip device */
+	hisi_zip = find_zip_device(cpu_to_node(smp_processor_id()));
+	if (!hisi_zip) {
+		pr_err("Can not find proper ZIP device!\n");
+		return -ENODEV;
+	}
+	qm = &hisi_zip->qm;
+
+	for (i = 0; i < 2; i++) {
+	/* it is just happen that 0 is compress, 1 is decompress on alg_type */
+		ret = hisi_zip_create_qp(qm, &hisi_zip_ctx->qp_ctx[i], i,
+					 req_type);
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+err:
+	for (j = i-1; j >= 0; j--)
+		hisi_zip_release_qp(&hisi_zip_ctx->qp_ctx[j]);
+
+	return ret;
+}
+
+static void hisi_zip_free_comp_ctx(struct crypto_tfm *tfm)
+{
+	struct hisi_zip_ctx *hisi_zip_ctx = crypto_tfm_ctx(tfm);
+	int i;
+
+	/* release the qp */
+	for (i = 1; i >= 0; i--)
+		hisi_zip_release_qp(&hisi_zip_ctx->qp_ctx[i]);
+}
+
+static int hisi_zip_copy_data_to_buffer(struct hisi_zip_qp_ctx *qp_ctx,
+					const u8 *src, unsigned int slen)
+{
+	struct hisi_zip_buffer *buffer = &qp_ctx->buffer;
+
+	if (slen > INPUT_BUFFER_SIZE)
+		return -EINVAL;
+
+	memcpy(buffer->input, src, slen);
+
+	return 0;
+}
+
+static struct hisi_zip_sqe *hisi_zip_get_writeback_sqe(struct hisi_qp *qp)
+{
+	struct hisi_acc_qp_status *qp_status = &qp->qp_status;
+	struct hisi_zip_sqe *sq_base = QP_SQE_ADDR(qp);
+	u16 sq_head = qp_status->sq_head;
+
+	return sq_base + sq_head;
+}
+
+static int hisi_zip_copy_data_from_buffer(struct hisi_zip_qp_ctx *qp_ctx,
+					  u8 *dst, unsigned int *dlen)
+{
+	struct hisi_zip_buffer *buffer = &qp_ctx->buffer;
+	struct hisi_qp *qp = qp_ctx->qp;
+	struct hisi_zip_sqe *zip_sqe = hisi_zip_get_writeback_sqe(qp);
+	u32 status = zip_sqe->dw3 & 0xff;
+	u16 sq_head;
+
+	if (status != 0) {
+		pr_err("hisi zip: %s fail!\n", (qp->alg_type == 0) ?
+		       "compression" : "decompression");
+		return status;
+	}
+
+	if (zip_sqe->produced > OUTPUT_BUFFER_SIZE)
+		return -ENOMEM;
+
+	memcpy(dst, buffer->output, zip_sqe->produced);
+	*dlen = zip_sqe->produced;
+
+	sq_head = qp->qp_status.sq_head;
+	if (sq_head == QM_Q_DEPTH - 1)
+		qp->qp_status.sq_head = 0;
+	else
+		qp->qp_status.sq_head++;
+
+	return 0;
+}
+
+static int hisi_zip_compress(struct crypto_tfm *tfm, const u8 *src,
+			     unsigned int slen, u8 *dst, unsigned int *dlen)
+{
+	struct hisi_zip_ctx *hisi_zip_ctx = crypto_tfm_ctx(tfm);
+	struct hisi_zip_qp_ctx *qp_ctx = &hisi_zip_ctx->qp_ctx[QPC_COMP];
+	struct hisi_qp *qp = qp_ctx->qp;
+	struct hisi_zip_sqe *zip_sqe = &qp_ctx->zip_sqe;
+	int ret;
+
+	ret = hisi_zip_copy_data_to_buffer(qp_ctx, src, slen);
+	if (ret < 0)
+		return ret;
+
+	hisi_zip_fill_sqe_v1(zip_sqe, qp_ctx, slen);
+
+	/* send command to start the compress job */
+	hisi_qp_send(qp, zip_sqe);
+
+	return hisi_zip_copy_data_from_buffer(qp_ctx, dst, dlen);
+}
+
+static int hisi_zip_decompress(struct crypto_tfm *tfm, const u8 *src,
+			       unsigned int slen, u8 *dst, unsigned int *dlen)
+{
+	struct hisi_zip_ctx *hisi_zip_ctx = crypto_tfm_ctx(tfm);
+	struct hisi_zip_qp_ctx *qp_ctx = &hisi_zip_ctx->qp_ctx[QPC_DECOMP];
+	struct hisi_qp *qp = qp_ctx->qp;
+	struct hisi_zip_sqe *zip_sqe = &qp_ctx->zip_sqe;
+	int ret;
+
+	ret = hisi_zip_copy_data_to_buffer(qp_ctx, src, slen);
+	if (ret < 0)
+		return ret;
+
+	hisi_zip_fill_sqe_v1(zip_sqe, qp_ctx, slen);
+
+	/* send command to start the decompress job */
+	hisi_qp_send(qp, zip_sqe);
+
+	return hisi_zip_copy_data_from_buffer(qp_ctx, dst, dlen);
+}
+
+static struct crypto_alg hisi_zip_zlib = {
+	.cra_name		= "zlib-deflate",
+	.cra_flags		= CRYPTO_ALG_TYPE_COMPRESS,
+	.cra_ctxsize		= sizeof(struct hisi_zip_ctx),
+	.cra_priority           = 300,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= hisi_zip_alloc_comp_ctx,
+	.cra_exit		= hisi_zip_free_comp_ctx,
+	.cra_u			= {
+		.compress = {
+			.coa_compress	= hisi_zip_compress,
+			.coa_decompress	= hisi_zip_decompress
+		}
+	}
+};
+
+static struct crypto_alg hisi_zip_gzip = {
+	.cra_name		= "gzip",
+	.cra_flags		= CRYPTO_ALG_TYPE_COMPRESS,
+	.cra_ctxsize		= sizeof(struct hisi_zip_ctx),
+	.cra_priority           = 300,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= hisi_zip_alloc_comp_ctx,
+	.cra_exit		= hisi_zip_free_comp_ctx,
+	.cra_u			= {
+		.compress = {
+			.coa_compress	= hisi_zip_compress,
+			.coa_decompress	= hisi_zip_decompress
+		}
+	}
+};
+
+int hisi_zip_register_to_crypto(void)
+{
+	int ret;
+
+	ret = crypto_register_alg(&hisi_zip_zlib);
+	if (ret < 0) {
+		pr_err("Zlib algorithm registration failed\n");
+		return ret;
+	}
+
+	ret = crypto_register_alg(&hisi_zip_gzip);
+	if (ret < 0) {
+		pr_err("Gzip algorithm registration failed\n");
+		goto err_unregister_zlib;
+	}
+
+	return 0;
+
+err_unregister_zlib:
+	crypto_unregister_alg(&hisi_zip_zlib);
+
+	return ret;
+}
+
+void hisi_zip_unregister_from_crypto(void)
+{
+	crypto_unregister_alg(&hisi_zip_zlib);
+	crypto_unregister_alg(&hisi_zip_gzip);
+}
diff --git a/drivers/crypto/hisilicon/zip/zip_crypto.h b/drivers/crypto/hisilicon/zip/zip_crypto.h
new file mode 100644
index 000000000000..84eefd74c9c4
--- /dev/null
+++ b/drivers/crypto/hisilicon/zip/zip_crypto.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+#ifndef HISI_ZIP_CRYPTO_H
+#define HISI_ZIP_CRYPTO_H
+
+int hisi_zip_register_to_crypto(void);
+void hisi_zip_unregister_from_crypto(void);
+
+#endif
diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c
new file mode 100644
index 000000000000..cad4c97f4826
--- /dev/null
+++ b/drivers/crypto/hisilicon/zip/zip_main.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0+
+#include <linux/bitops.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include "zip.h"
+#include "zip_crypto.h"
+
+#define HZIP_VF_NUM			63
+#define HZIP_QUEUE_NUM_V1		4096
+#define HZIP_QUEUE_NUM_V2		1024
+
+#define HZIP_FSM_MAX_CNT		0x301008
+
+#define HZIP_PORT_ARCA_CHE_0		0x301040
+#define HZIP_PORT_ARCA_CHE_1		0x301044
+#define HZIP_PORT_AWCA_CHE_0		0x301060
+#define HZIP_PORT_AWCA_CHE_1		0x301064
+
+#define HZIP_BD_RUSER_32_63		0x301110
+#define HZIP_SGL_RUSER_32_63		0x30111c
+#define HZIP_DATA_RUSER_32_63		0x301128
+#define HZIP_DATA_WUSER_32_63		0x301134
+#define HZIP_BD_WUSER_32_63		0x301140
+
+LIST_HEAD(hisi_zip_list);
+DEFINE_MUTEX(hisi_zip_list_lock);
+
+static const char hisi_zip_name[] = "hisi_zip";
+
+static const struct pci_device_id hisi_zip_dev_ids[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, 0xa250) },
+	{ 0, }
+};
+
+static inline void hisi_zip_add_to_list(struct hisi_zip *hisi_zip)
+{
+	mutex_lock(&hisi_zip_list_lock);
+	list_add_tail(&hisi_zip->list, &hisi_zip_list);
+	mutex_unlock(&hisi_zip_list_lock);
+}
+
+static inline void hisi_zip_remove_from_list(struct hisi_zip *hisi_zip)
+{
+	mutex_lock(&hisi_zip_list_lock);
+	list_del(&hisi_zip->list);
+	mutex_unlock(&hisi_zip_list_lock);
+}
+
+static void hisi_zip_set_user_domain_and_cache(struct hisi_zip *hisi_zip)
+{
+	u32 val;
+
+	/* qm user domain */
+	writel(0x40001070, hisi_zip->qm.io_base + QM_ARUSER_M_CFG_1);
+	writel(0xfffffffe, hisi_zip->qm.io_base + QM_ARUSER_M_CFG_ENABLE);
+	writel(0x40001070, hisi_zip->qm.io_base + QM_AWUSER_M_CFG_1);
+	writel(0xfffffffe, hisi_zip->qm.io_base + QM_AWUSER_M_CFG_ENABLE);
+	writel(0xffffffff, hisi_zip->qm.io_base + QM_WUSER_M_CFG_ENABLE);
+	writel(0x4893,     hisi_zip->qm.io_base + QM_CACHE_CTL);
+
+	val = readl(hisi_zip->qm.io_base + QM_PEH_AXUSER_CFG);
+	val |= (1 << 11);
+	writel(val, hisi_zip->qm.io_base + QM_PEH_AXUSER_CFG);
+
+	/* qm cache */
+	writel(0xffff,     hisi_zip->qm.io_base + QM_AXI_M_CFG);
+	writel(0xffffffff, hisi_zip->qm.io_base + QM_AXI_M_CFG_ENABLE);
+	writel(0xffffffff, hisi_zip->qm.io_base + QM_PEH_AXUSER_CFG_ENABLE);
+
+	/* cache */
+	writel(0xffffffff, hisi_zip->qm.io_base + HZIP_PORT_ARCA_CHE_0);
+	writel(0xffffffff, hisi_zip->qm.io_base + HZIP_PORT_ARCA_CHE_1);
+	writel(0xffffffff, hisi_zip->qm.io_base + HZIP_PORT_AWCA_CHE_0);
+	writel(0xffffffff, hisi_zip->qm.io_base + HZIP_PORT_AWCA_CHE_1);
+	/* user domain configurations */
+	writel(0x40001070, hisi_zip->qm.io_base + HZIP_BD_RUSER_32_63);
+	writel(0x40001070, hisi_zip->qm.io_base + HZIP_SGL_RUSER_32_63);
+#ifdef CONFIG_IOMMU_SVA
+	writel(0x40001071, hisi_zip->qm.io_base + HZIP_DATA_RUSER_32_63);
+	writel(0x40001071, hisi_zip->qm.io_base + HZIP_DATA_WUSER_32_63);
+#else
+	writel(0x40001070, hisi_zip->qm.io_base + HZIP_DATA_RUSER_32_63);
+	writel(0x40001070, hisi_zip->qm.io_base + HZIP_DATA_WUSER_32_63);
+#endif
+	writel(0x40001070, hisi_zip->qm.io_base + HZIP_BD_WUSER_32_63);
+
+	/* fsm count */
+	writel(0xfffffff, hisi_zip->qm.io_base + HZIP_FSM_MAX_CNT);
+
+	/* clock gating, core, decompress verify enable */
+	writel(0x10005, hisi_zip->qm.io_base + 0x301004);
+}
+
+static int hisi_zip_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct hisi_zip *hisi_zip;
+	struct qm_info *qm;
+	int ret;
+	u8 rev_id;
+
+	hisi_zip = devm_kzalloc(&pdev->dev, sizeof(*hisi_zip), GFP_KERNEL);
+	if (!hisi_zip)
+		return -ENOMEM;
+	hisi_zip_add_to_list(hisi_zip);
+	pci_set_drvdata(pdev, hisi_zip);
+
+	qm = &hisi_zip->qm;
+	qm->pdev = pdev;
+
+	pci_read_config_byte(pdev, PCI_REVISION_ID, &rev_id);
+	if (rev_id == 0x20)
+		qm->ver = 1;
+	qm->sqe_size = HZIP_SQE_SIZE;
+	ret = hisi_qm_init(hisi_zip_name, qm);
+	if (ret)
+		goto err_with_hisi_zip;
+
+	if (pdev->is_physfn) {
+		ret = hisi_qm_mem_start(qm);
+		if (ret)
+			goto err_with_qm_init;
+
+		hisi_zip_set_user_domain_and_cache(hisi_zip);
+
+		qm->qp_base = HZIP_PF_DEF_Q_BASE;
+		qm->qp_num = HZIP_PF_DEF_Q_NUM;
+	}
+
+	ret = hisi_qm_start(qm);
+	if (ret)
+		goto err_with_qm_init;
+
+	return 0;
+
+err_with_qm_init:
+	hisi_qm_uninit(qm);
+err_with_hisi_zip:
+	kfree(hisi_zip);
+	return ret;
+}
+
+static void hisi_zip_remove(struct pci_dev *pdev)
+{
+	struct hisi_zip *hisi_zip = pci_get_drvdata(pdev);
+	struct qm_info *qm = &hisi_zip->qm;
+
+	hisi_qm_stop(qm);
+	hisi_qm_uninit(qm);
+	hisi_zip_remove_from_list(hisi_zip);
+	kfree(hisi_zip);
+}
+
+static struct pci_driver hisi_zip_pci_driver = {
+	.name		= "hisi_zip",
+	.id_table	= hisi_zip_dev_ids,
+	.probe		= hisi_zip_probe,
+	.remove		= hisi_zip_remove,
+};
+
+static int __init hisi_zip_init(void)
+{
+	int ret;
+
+	ret = pci_register_driver(&hisi_zip_pci_driver);
+	if (ret < 0) {
+		pr_err("zip: can't register hisi zip driver.\n");
+		return ret;
+	}
+
+	ret = hisi_zip_register_to_crypto();
+	if (ret < 0) {
+		pr_err("zip: can't register hisi zip to crypto.\n");
+		pci_unregister_driver(&hisi_zip_pci_driver);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void __exit hisi_zip_exit(void)
+{
+	hisi_zip_unregister_from_crypto();
+	pci_unregister_driver(&hisi_zip_pci_driver);
+}
+
+module_init(hisi_zip_init);
+module_exit(hisi_zip_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Zhou Wang <wangzhou1@hisilicon.com>");
+MODULE_DESCRIPTION("Driver for HiSilicon ZIP accelerator");
+MODULE_DEVICE_TABLE(pci, hisi_zip_dev_ids);
-- 
2.17.1