[PATCH 4/7] crypto: add hisilicon Queue Manager driver

[Kenneth Lee <nek.in.cn@gmail.com>]

From: Kenneth Lee <liguozhu@hisilicon.com>

Hisilicon QM is a general IP used by some Hisilicon accelerators. It
provides a general PCIE interface for the CPU and the accelerator to share
a group of queues.

This commit includes a library used by the accelerator driver to access
the QM hardware.

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/Makefile           |   2 +-
 drivers/crypto/hisilicon/Kconfig  |   8 +
 drivers/crypto/hisilicon/Makefile |   1 +
 drivers/crypto/hisilicon/qm.c     | 820 ++++++++++++++++++++++++++++++
 drivers/crypto/hisilicon/qm.h     | 110 ++++
 5 files changed, 940 insertions(+), 1 deletion(-)
 create mode 100644 drivers/crypto/hisilicon/qm.c
 create mode 100644 drivers/crypto/hisilicon/qm.h

diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index c23396f32c8a..f3a7abe42424 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -46,4 +46,4 @@ obj-$(CONFIG_CRYPTO_DEV_VMX) += vmx/
 obj-$(CONFIG_CRYPTO_DEV_BCM_SPU) += bcm/
 obj-$(CONFIG_CRYPTO_DEV_SAFEXCEL) += inside-secure/
 obj-$(CONFIG_CRYPTO_DEV_ARTPEC6) += axis/
-obj-y += hisilicon/
+obj-$(CONFIG_CRYPTO_DEV_HISILICON) += hisilicon/
diff --git a/drivers/crypto/hisilicon/Kconfig b/drivers/crypto/hisilicon/Kconfig
index 8ca9c503bcb0..02a6eef84101 100644
--- a/drivers/crypto/hisilicon/Kconfig
+++ b/drivers/crypto/hisilicon/Kconfig
@@ -1,4 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
+config CRYPTO_DEV_HISILICON
+	tristate "Support for HISILICON CRYPTO ACCELERATOR"
+	help
+	  Enable this to use Hisilicon Hardware Accelerators
 
 config CRYPTO_DEV_HISI_SEC
 	tristate "Support for Hisilicon SEC crypto block cipher accelerator"
@@ -12,3 +16,7 @@ config CRYPTO_DEV_HISI_SEC
 
 	  To compile this as a module, choose M here: the module
 	  will be called hisi_sec.
+
+config CRYPTO_DEV_HISI_QM
+	tristate
+	depends on ARM64 && PCI
diff --git a/drivers/crypto/hisilicon/Makefile b/drivers/crypto/hisilicon/Makefile
index 463f46ace182..05e9052e0f52 100644
--- a/drivers/crypto/hisilicon/Makefile
+++ b/drivers/crypto/hisilicon/Makefile
@@ -1,2 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_CRYPTO_DEV_HISI_SEC) += sec/
+obj-$(CONFIG_CRYPTO_DEV_HISI_QM) += qm.o
diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c
new file mode 100644
index 000000000000..ea618b4d0929
--- /dev/null
+++ b/drivers/crypto/hisilicon/qm.c
@@ -0,0 +1,820 @@
+// SPDX-License-Identifier: GPL-2.0+
+#include <asm/page.h>
+#include <linux/bitmap.h>
+#include <linux/dma-mapping.h>
+#include <linux/io.h>
+#include <linux/irqreturn.h>
+#include <linux/log2.h>
+#include "qm.h"
+
+#define QM_DEF_Q_NUM			128
+
+/* eq/aeq irq enable */
+#define QM_VF_AEQ_INT_SOURCE		0x0
+#define QM_VF_AEQ_INT_MASK		0x4
+#define QM_VF_EQ_INT_SOURCE		0x8
+#define QM_VF_EQ_INT_MASK		0xc
+
+/* mailbox */
+#define MAILBOX_CMD_SQC			0x0
+#define MAILBOX_CMD_CQC			0x1
+#define MAILBOX_CMD_EQC			0x2
+#define MAILBOX_CMD_SQC_BT		0x4
+#define MAILBOX_CMD_CQC_BT		0x5
+
+#define MAILBOX_CMD_SEND_BASE		0x300
+#define MAILBOX_EVENT_SHIFT		8
+#define MAILBOX_STATUS_SHIFT		9
+#define MAILBOX_BUSY_SHIFT		13
+#define MAILBOX_OP_SHIFT		14
+#define MAILBOX_QUEUE_SHIFT		16
+
+/* sqc shift */
+#define SQ_HEAD_SHIFT			0
+#define SQ_TAIL_SHIFI			16
+#define SQ_HOP_NUM_SHIFT		0
+#define SQ_PAGE_SIZE_SHIFT		4
+#define SQ_BUF_SIZE_SHIFT		8
+#define SQ_SQE_SIZE_SHIFT		12
+#define SQ_HEAD_IDX_SIG_SHIFT		0
+#define SQ_TAIL_IDX_SIG_SHIFT		0
+#define SQ_CQN_SHIFT			0
+#define SQ_PRIORITY_SHIFT		0
+#define SQ_ORDERS_SHIFT			4
+#define SQ_TYPE_SHIFT			8
+
+#define SQ_TYPE_MASK			0xf
+
+/* cqc shift */
+#define CQ_HEAD_SHIFT			0
+#define CQ_TAIL_SHIFI			16
+#define CQ_HOP_NUM_SHIFT		0
+#define CQ_PAGE_SIZE_SHIFT		4
+#define CQ_BUF_SIZE_SHIFT		8
+#define CQ_SQE_SIZE_SHIFT		12
+#define CQ_PASID			0
+#define CQ_HEAD_IDX_SIG_SHIFT		0
+#define CQ_TAIL_IDX_SIG_SHIFT		0
+#define CQ_CQN_SHIFT			0
+#define CQ_PRIORITY_SHIFT		16
+#define CQ_ORDERS_SHIFT			0
+#define CQ_TYPE_SHIFT			0
+#define CQ_PHASE_SHIFT			0
+#define CQ_FLAG_SHIFT			1
+
+#define CQC_HEAD_INDEX(cqc)		((cqc)->cq_head)
+#define CQC_PHASE(cqc)			(((cqc)->dw6) & 0x1)
+#define CQC_CQ_ADDRESS(cqc)		(((u64)((cqc)->cq_base_h) << 32) | \
+					 ((cqc)->cq_base_l))
+#define CQC_PHASE_BIT			0x1
+
+/* eqc shift */
+#define MB_EQC_EQE_SHIFT		12
+#define MB_EQC_PHASE_SHIFT		16
+
+#define EQC_HEAD_INDEX(eqc)		((eqc)->eq_head)
+#define EQC_TAIL_INDEX(eqc)		((eqc)->eq_tail)
+#define EQC_PHASE(eqc)			((((eqc)->dw6) >> 16) & 0x1)
+
+#define EQC_PHASE_BIT			0x00010000
+
+/* cqe shift */
+#define CQE_PHASE(cqe)			((cqe)->w7 & 0x1)
+#define CQE_SQ_NUM(cqe)			((cqe)->sq_num)
+#define CQE_SQ_HEAD_INDEX(cqe)		((cqe)->sq_head)
+
+/* eqe shift */
+#define EQE_PHASE(eqe)			(((eqe)->dw0 >> 16) & 0x1)
+#define EQE_CQN(eqe)			(((eqe)->dw0) & 0xffff)
+
+#define QM_EQE_CQN_MASK			0xffff
+
+/* doorbell */
+#define DOORBELL_CMD_SQ			0
+#define DOORBELL_CMD_CQ			1
+#define DOORBELL_CMD_EQ			2
+#define DOORBELL_CMD_AEQ		3
+
+#define DOORBELL_CMD_SEND_BASE		0x340
+
+#define QM_MEM_START_INIT		0x100040
+#define QM_MEM_INIT_DONE		0x100044
+#define QM_VFT_CFG_RDY			0x10006c
+#define QM_VFT_CFG_OP_WR		0x100058
+#define QM_VFT_CFG_TYPE			0x10005c
+#define QM_SQC_VFT			0x0
+#define QM_CQC_VFT			0x1
+#define QM_VFT_CFG_ADDRESS		0x100060
+#define QM_VFT_CFG_OP_ENABLE		0x100054
+
+#define QM_VFT_CFG_DATA_L		0x100064
+#define QM_VFT_CFG_DATA_H		0x100068
+#define QM_SQC_VFT_BUF_SIZE		(7ULL << 8)
+#define QM_SQC_VFT_SQC_SIZE		(5ULL << 12)
+#define QM_SQC_VFT_INDEX_NUMBER		(1ULL << 16)
+#define QM_SQC_VFT_BT_INDEX_SHIFT	22
+#define QM_SQC_VFT_START_SQN_SHIFT	28
+#define QM_SQC_VFT_VALID		(1ULL << 44)
+#define QM_CQC_VFT_BUF_SIZE		(7ULL << 8)
+#define QM_CQC_VFT_SQC_SIZE		(5ULL << 12)
+#define QM_CQC_VFT_INDEX_NUMBER		(1ULL << 16)
+#define QM_CQC_VFT_BT_INDEX_SHIFT	22
+#define QM_CQC_VFT_VALID		(1ULL << 28)
+
+struct cqe {
+	__le32 rsvd0;
+	__le16 cmd_id;
+	__le16 rsvd1;
+	__le16 sq_head;
+	__le16 sq_num;
+	__le16 rsvd2;
+	__le16 w7;
+};
+
+struct eqe {
+	__le32 dw0;
+};
+
+struct sqc {
+	__le16 head;
+	__le16 tail;
+	__le32 base_l;
+	__le32 base_h;
+	__le32 dw3;
+	__le16 qes;
+	__le16 rsvd0;
+	__le16 pasid;
+	__le16 w11;
+	__le16 cq_num;
+	__le16 w13;
+	__le32 rsvd1;
+};
+
+struct cqc {
+	__le16 head;
+	__le16 tail;
+	__le32 base_l;
+	__le32 base_h;
+	__le32 dw3;
+	__le16 qes;
+	__le16 rsvd0;
+	__le16 pasid;
+	__le16 w11;
+	__le32 dw6;
+	__le32 rsvd1;
+};
+
+#define INIT_QC(qc, base) do { \
+	(qc)->head = 0; \
+	(qc)->tail = 0; \
+	(qc)->base_l = lower_32_bits(base); \
+	(qc)->base_h = upper_32_bits(base); \
+	(qc)->pasid = 0; \
+	(qc)->w11 = 0; \
+	(qc)->rsvd1 = 0; \
+	(qc)->qes = QM_Q_DEPTH - 1; \
+} while (0)
+
+struct eqc {
+	__le16 head;
+	__le16 tail;
+	__le32 base_l;
+	__le32 base_h;
+	__le32 dw3;
+	__le32 rsvd[2];
+	__le32 dw6;
+};
+
+struct mailbox {
+	__le16 w0;
+	__le16 queue_num;
+	__le32 base_l;
+	__le32 base_h;
+	__le32 rsvd;
+};
+
+struct doorbell {
+	__le16 queue_num;
+	__le16 cmd;
+	__le16 index;
+	__le16 priority;
+};
+
+#define QM_DMA_BUF(p, buf) ((struct buf *)(p)->buf.addr)
+#define QM_SQC(p) QM_DMA_BUF(p, sqc)
+#define QM_CQC(p) QM_DMA_BUF(p, cqc)
+#define QM_EQC(p) QM_DMA_BUF(p, eqc)
+#define QM_EQE(p) QM_DMA_BUF(p, eqe)
+
+#define QP_SQE_DMA(qp) ((qp)->scqe.dma)
+#define QP_CQE(qp) ((struct cqe *)((qp)->scqe.addr + \
+				   qp->qm->sqe_size * QM_Q_DEPTH))
+#define QP_CQE_DMA(qp) ((qp)->scqe.dma + qp->qm->sqe_size * QM_Q_DEPTH)
+
+static inline void qm_writel(struct qm_info *qm, u32 val, u32 offset)
+{
+	writel(val, qm->io_base + offset);
+}
+
+struct qm_info;
+
+struct hisi_acc_qm_hw_ops {
+	int (*vft_config)(struct qm_info *qm, u16 base, u32 number);
+};
+
+static inline int hacc_qm_mb_is_busy(struct qm_info *qm)
+{
+	u32 val;
+
+	return readl_relaxed_poll_timeout(QM_ADDR(qm, MAILBOX_CMD_SEND_BASE),
+		val, !((val >> MAILBOX_BUSY_SHIFT) & 0x1), 10, 1000);
+}
+
+static inline void qm_mb_write(struct qm_info *qm, void *src)
+{
+	void __iomem *fun_base = QM_ADDR(qm, MAILBOX_CMD_SEND_BASE);
+	unsigned long tmp0 = 0, tmp1 = 0;
+
+	asm volatile("ldp %0, %1, %3\n"
+		     "stp %0, %1, %2\n"
+		     "dsb sy\n"
+		     : "=&r" (tmp0),
+		       "=&r" (tmp1),
+		       "+Q" (*((char *)fun_base))
+		     : "Q" (*((char *)src))
+		     : "memory");
+}
+
+static int qm_mb(struct qm_info *qm, u8 cmd, dma_addr_t dma_addr, u16 queue,
+		 bool op, bool event)
+{
+	struct mailbox mailbox;
+	int i = 0;
+	int ret = 0;
+
+	memset(&mailbox, 0, sizeof(struct mailbox));
+
+	mailbox.w0 = cmd |
+		     (event ? 0x1 << MAILBOX_EVENT_SHIFT : 0) |
+		     (op ? 0x1 << MAILBOX_OP_SHIFT : 0) |
+		     (0x1 << MAILBOX_BUSY_SHIFT);
+	mailbox.queue_num = queue;
+	mailbox.base_l = lower_32_bits(dma_addr);
+	mailbox.base_h = upper_32_bits(dma_addr);
+	mailbox.rsvd = 0;
+
+	mutex_lock(&qm->mailbox_lock);
+
+	while (hacc_qm_mb_is_busy(qm) && i < 10)
+		i++;
+	if (i >= 10) {
+		ret = -EBUSY;
+		dev_err(&qm->pdev->dev, "QM mail box is busy!");
+		goto busy_unlock;
+	}
+	qm_mb_write(qm, &mailbox);
+	i = 0;
+	while (hacc_qm_mb_is_busy(qm) && i < 10)
+		i++;
+	if (i >= 10) {
+		ret = -EBUSY;
+		dev_err(&qm->pdev->dev, "QM mail box is still busy!");
+		goto busy_unlock;
+	}
+
+busy_unlock:
+	mutex_unlock(&qm->mailbox_lock);
+
+	return ret;
+}
+
+static void qm_db(struct qm_info *qm, u16 qn, u8 cmd, u16 index, u8 priority)
+{
+	u64 doorbell = 0;
+
+	doorbell = (u64)qn | ((u64)cmd << 16);
+	doorbell |= ((u64)index | ((u64)priority << 16)) << 32;
+
+	writeq(doorbell, QM_ADDR(qm, DOORBELL_CMD_SEND_BASE));
+}
+
+/* @return 0 - cq/eq event, 1 - async event, 2 - abnormal error */
+static u32 qm_get_irq_source(struct qm_info *qm)
+{
+	return readl(QM_ADDR(qm, QM_VF_EQ_INT_SOURCE));
+}
+
+static inline struct hisi_qp *to_hisi_qp(struct qm_info *qm, struct eqe *eqe)
+{
+	u16 cqn = eqe->dw0 & QM_EQE_CQN_MASK;
+	struct hisi_qp *qp;
+
+	read_lock(&qm->qps_lock);
+	qp = qm->qp_array[cqn];
+	read_unlock(&qm->qps_lock);
+
+	return qp;
+}
+
+static inline void qm_cq_head_update(struct hisi_qp *qp)
+{
+	if (qp->qp_status.cq_head == QM_Q_DEPTH - 1) {
+		QM_CQC(qp)->dw6 = QM_CQC(qp)->dw6 ^ CQC_PHASE_BIT;
+		qp->qp_status.cq_head = 0;
+	} else {
+		qp->qp_status.cq_head++;
+	}
+}
+
+static inline void qm_poll_qp(struct hisi_qp *qp, struct qm_info *qm)
+{
+	struct cqe *cqe;
+
+	cqe = QP_CQE(qp) + qp->qp_status.cq_head;
+
+	if (qp->req_cb) {
+		while (CQE_PHASE(cqe) == CQC_PHASE(QM_CQC(qp))) {
+			dma_rmb();
+			qp->req_cb(qp, QP_SQE_ADDR(qp) +
+				   qm->sqe_size *
+				   CQE_SQ_HEAD_INDEX(cqe));
+			qm_cq_head_update(qp);
+			cqe = QP_CQE(qp) + qp->qp_status.cq_head;
+		}
+	} else if (qp->event_cb) {
+		qp->event_cb(qp);
+		qm_cq_head_update(qp);
+		cqe = QP_CQE(qp) + qp->qp_status.cq_head;
+	}
+
+	qm_db(qm, qp->queue_id, DOORBELL_CMD_CQ, qp->qp_status.cq_head, 0);
+
+	/* set c_flag */
+	qm_db(qm, qp->queue_id, DOORBELL_CMD_CQ, qp->qp_status.cq_head, 1);
+}
+
+static irqreturn_t qm_irq_thread(int irq, void *data)
+{
+	struct qm_info *qm = data;
+	struct eqe *eqe = QM_EQE(qm) + qm->eq_head;
+	struct eqc *eqc = QM_EQC(qm);
+	struct hisi_qp *qp;
+
+	while (EQE_PHASE(eqe) == EQC_PHASE(eqc)) {
+		qp = to_hisi_qp(qm, eqe);
+		if (qp)
+			qm_poll_qp(qp, qm);
+
+		if (qm->eq_head == QM_Q_DEPTH - 1) {
+			eqc->dw6 = eqc->dw6 ^ EQC_PHASE_BIT;
+			eqe = QM_EQE(qm);
+			qm->eq_head = 0;
+		} else {
+			eqe++;
+			qm->eq_head++;
+		}
+
+		qm_db(qm, 0, DOORBELL_CMD_EQ, qm->eq_head, 0);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void qm_init_qp_status(struct hisi_qp *qp)
+{
+	struct hisi_acc_qp_status *qp_status = &qp->qp_status;
+
+	qp_status->sq_tail = 0;
+	qp_status->sq_head = 0;
+	qp_status->cq_head = 0;
+	qp_status->cqc_phase = 1;
+	qp_status->is_sq_full = 0;
+}
+
+/* check if bit in regs is 1 */
+static inline int qm_acc_check(struct qm_info *qm, u32 offset, u32 bit)
+{
+	int val;
+
+	return readl_relaxed_poll_timeout(QM_ADDR(qm, offset), val,
+					  val & BIT(bit), 10, 1000);
+}
+
+static inline int qm_init_q_buffer(struct device *dev, size_t size,
+				   struct qm_dma_buffer *db)
+{
+	db->size = size;
+	db->addr = dma_zalloc_coherent(dev, size, &db->dma, GFP_KERNEL);
+	if (!db->addr)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static inline void qm_uninit_q_buffer(struct device *dev,
+				      struct qm_dma_buffer *db)
+{
+	dma_free_coherent(dev, db->size, db->addr, db->dma);
+}
+
+static inline int qm_init_bt(struct qm_info *qm, struct device *dev,
+			     size_t size, struct qm_dma_buffer *db, int mb_cmd)
+{
+	int ret;
+
+	ret = qm_init_q_buffer(dev, size, db);
+	if (ret)
+		return -ENOMEM;
+
+	ret = qm_mb(qm, mb_cmd, db->dma, 0, 0, 0);
+	if (ret) {
+		qm_uninit_q_buffer(dev, db);
+		return ret;
+	}
+
+	return 0;
+}
+
+/* the config should be conducted after hisi_acc_init_qm_mem() */
+static int qm_vft_common_config(struct qm_info *qm, u16 base, u32 number)
+{
+	u64 tmp;
+	int ret;
+
+	ret = qm_acc_check(qm, QM_VFT_CFG_RDY, 0);
+	if (ret)
+		return ret;
+	qm_writel(qm, 0x0, QM_VFT_CFG_OP_WR);
+	qm_writel(qm, QM_SQC_VFT, QM_VFT_CFG_TYPE);
+	qm_writel(qm, qm->pdev->devfn, QM_VFT_CFG_ADDRESS);
+
+	tmp = QM_SQC_VFT_BUF_SIZE			|
+	      QM_SQC_VFT_SQC_SIZE			|
+	      QM_SQC_VFT_INDEX_NUMBER			|
+	      QM_SQC_VFT_VALID				|
+	      (u64)base << QM_SQC_VFT_START_SQN_SHIFT;
+
+	qm_writel(qm, tmp & 0xffffffff, QM_VFT_CFG_DATA_L);
+	qm_writel(qm, tmp >> 32, QM_VFT_CFG_DATA_H);
+
+	qm_writel(qm, 0x0, QM_VFT_CFG_RDY);
+	qm_writel(qm, 0x1, QM_VFT_CFG_OP_ENABLE);
+	ret = qm_acc_check(qm, QM_VFT_CFG_RDY, 0);
+	if (ret)
+		return ret;
+	tmp = 0;
+
+	qm_writel(qm, 0x0, QM_VFT_CFG_OP_WR);
+	qm_writel(qm, QM_CQC_VFT, QM_VFT_CFG_TYPE);
+	qm_writel(qm, qm->pdev->devfn, QM_VFT_CFG_ADDRESS);
+
+	tmp = QM_CQC_VFT_BUF_SIZE			|
+	      QM_CQC_VFT_SQC_SIZE			|
+	      QM_CQC_VFT_INDEX_NUMBER			|
+	      QM_CQC_VFT_VALID;
+
+	qm_writel(qm, tmp & 0xffffffff, QM_VFT_CFG_DATA_L);
+	qm_writel(qm, tmp >> 32, QM_VFT_CFG_DATA_H);
+
+	qm_writel(qm, 0x0, QM_VFT_CFG_RDY);
+	qm_writel(qm, 0x1, QM_VFT_CFG_OP_ENABLE);
+	ret = qm_acc_check(qm, QM_VFT_CFG_RDY, 0);
+	if (ret)
+		return ret;
+	return 0;
+}
+
+static struct hisi_acc_qm_hw_ops qm_hw_ops_v1 = {
+	.vft_config = qm_vft_common_config,
+};
+
+struct hisi_qp *hisi_qm_create_qp(struct qm_info *qm, u8 alg_type)
+{
+	struct hisi_qp *qp;
+	int qp_index;
+	int ret;
+
+	write_lock(&qm->qps_lock);
+	qp_index = find_first_zero_bit(qm->qp_bitmap, qm->qp_num);
+	if (qp_index >= qm->qp_num) {
+		write_unlock(&qm->qps_lock);
+		return ERR_PTR(-EBUSY);
+	}
+	set_bit(qp_index, qm->qp_bitmap);
+
+	qp = kzalloc(sizeof(*qp), GFP_KERNEL);
+	if (!qp) {
+		ret = -ENOMEM;
+		write_unlock(&qm->qps_lock);
+		goto err_with_bitset;
+	}
+
+	qp->queue_id = qp_index;
+	qp->qm = qm;
+	qp->alg_type = alg_type;
+	qm_init_qp_status(qp);
+
+	write_unlock(&qm->qps_lock);
+	return qp;
+
+err_with_bitset:
+	clear_bit(qp_index, qm->qp_bitmap);
+
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(hisi_qm_create_qp);
+
+int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg)
+{
+	struct qm_info *qm = qp->qm;
+	struct device *dev = &qm->pdev->dev;
+	struct sqc *sqc;
+	struct cqc *cqc;
+	int qp_index = qp->queue_id;
+	int pasid = arg;
+	int ret;
+
+	/* set sq and cq context */
+	qp->sqc.addr = QM_SQC(qm) + qp_index;
+	qp->sqc.dma = qm->sqc.dma + qp_index * sizeof(struct sqc);
+	sqc = QM_SQC(qp);
+
+	qp->cqc.addr = QM_CQC(qm) + qp_index;
+	qp->cqc.dma = qm->cqc.dma + qp_index * sizeof(struct cqc);
+	cqc = QM_CQC(qp);
+
+	/* allocate sq and cq */
+	ret = qm_init_q_buffer(dev,
+		qm->sqe_size * QM_Q_DEPTH + sizeof(struct cqe) * QM_Q_DEPTH,
+		&qp->scqe);
+	if (ret)
+		return ret;
+
+	INIT_QC(sqc, qp->scqe.dma);
+	sqc->pasid = pasid;
+	sqc->dw3 = (0 << SQ_HOP_NUM_SHIFT)      |
+		   (0 << SQ_PAGE_SIZE_SHIFT)    |
+		   (0 << SQ_BUF_SIZE_SHIFT)     |
+		   (ilog2(qm->sqe_size) << SQ_SQE_SIZE_SHIFT);
+	sqc->cq_num = qp_index;
+	sqc->w13 = 0 << SQ_PRIORITY_SHIFT	|
+		   1 << SQ_ORDERS_SHIFT		|
+		   (qp->alg_type & SQ_TYPE_MASK) << SQ_TYPE_SHIFT;
+
+	ret = qm_mb(qm, MAILBOX_CMD_SQC, qp->sqc.dma, qp_index, 0, 0);
+	if (ret)
+		return ret;
+
+	INIT_QC(cqc, qp->scqe.dma + qm->sqe_size * QM_Q_DEPTH);
+	cqc->dw3 = (0 << CQ_HOP_NUM_SHIFT)	|
+		   (0 << CQ_PAGE_SIZE_SHIFT)	|
+		   (0 << CQ_BUF_SIZE_SHIFT)	|
+		   (4 << CQ_SQE_SIZE_SHIFT);
+	cqc->dw6 = 1 << CQ_PHASE_SHIFT | 1 << CQ_FLAG_SHIFT;
+
+	ret = qm_mb(qm, MAILBOX_CMD_CQC, qp->cqc.dma, qp_index, 0, 0);
+	if (ret)
+		return ret;
+
+	write_lock(&qm->qps_lock);
+	qm->qp_array[qp_index] = qp;
+	init_completion(&qp->completion);
+	write_unlock(&qm->qps_lock);
+
+	return qp_index;
+}
+EXPORT_SYMBOL_GPL(hisi_qm_start_qp);
+
+void hisi_qm_release_qp(struct hisi_qp *qp)
+{
+	struct qm_info *qm = qp->qm;
+	struct device *dev = &qm->pdev->dev;
+
+	write_lock(&qm->qps_lock);
+	qm->qp_array[qp->queue_id] = NULL;
+	bitmap_clear(qm->qp_bitmap, qp->queue_id, 1);
+	write_unlock(&qm->qps_lock);
+
+	qm_uninit_q_buffer(dev, &qp->scqe);
+	kfree(qp);
+}
+EXPORT_SYMBOL_GPL(hisi_qm_release_qp);
+
+static void *qm_get_avail_sqe(struct hisi_qp *qp)
+{
+	struct hisi_acc_qp_status *qp_status = &qp->qp_status;
+	void *sq_base = QP_SQE_ADDR(qp);
+	u16 sq_tail = qp_status->sq_tail;
+
+	if (qp_status->is_sq_full == 1)
+		return NULL;
+
+	return sq_base + sq_tail * qp->qm->sqe_size;
+}
+
+int hisi_qp_send(struct hisi_qp *qp, void *msg)
+{
+	struct hisi_acc_qp_status *qp_status = &qp->qp_status;
+	u16 sq_tail = qp_status->sq_tail;
+	u16 sq_tail_next = (sq_tail + 1) % QM_Q_DEPTH;
+	unsigned long timeout = 100;
+	void *sqe = qm_get_avail_sqe(qp);
+
+	if (!sqe)
+		return -ENOSPC;
+
+	memcpy(sqe, msg, qp->qm->sqe_size);
+
+	qm_db(qp->qm, qp->queue_id, DOORBELL_CMD_SQ, sq_tail_next, 0);
+
+	qp_status->sq_tail = sq_tail_next;
+
+	if (qp_status->sq_tail == qp_status->sq_head)
+		qp_status->is_sq_full = 1;
+
+	/* wait until job finished */
+	wait_for_completion_timeout(&qp->completion, timeout);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(hisi_qp_send);
+
+int hisi_qm_init(const char *dev_name, struct qm_info *qm)
+{
+	struct pci_dev *pdev = qm->pdev;
+	int ret;
+
+	ret = pci_enable_device_mem(pdev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Can't enable device mem!\n");
+		return ret;
+	}
+
+	ret = pci_request_mem_regions(pdev, dev_name);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Can't request mem regions!\n");
+		goto err_with_pcidev;
+	}
+
+	qm->dev_name = dev_name;
+	qm->phys_base = pci_resource_start(pdev, 2);
+	qm->size = pci_resource_len(qm->pdev, 2);
+	qm->io_base = devm_ioremap(&pdev->dev, qm->phys_base, qm->size);
+	if (!qm->io_base) {
+		ret = -EIO;
+		goto err_with_mem_regions;
+	}
+
+	dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	pci_set_master(pdev);
+
+	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Enable MSI vectors fail!\n");
+		goto err_with_mem_regions;
+	}
+
+	qm->eq_head = 0;
+	mutex_init(&qm->mailbox_lock);
+	rwlock_init(&qm->qps_lock);
+
+	if (qm->ver)
+		qm->ops = &qm_hw_ops_v1;
+
+	return 0;
+
+err_with_mem_regions:
+	pci_release_mem_regions(pdev);
+err_with_pcidev:
+	pci_disable_device(pdev);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hisi_qm_init);
+
+void hisi_qm_uninit(struct qm_info *qm)
+{
+	struct pci_dev *pdev = qm->pdev;
+
+	pci_free_irq_vectors(pdev);
+	pci_release_mem_regions(pdev);
+	pci_disable_device(pdev);
+}
+EXPORT_SYMBOL_GPL(hisi_qm_uninit);
+
+static irqreturn_t qm_irq(int irq, void *data)
+{
+	struct qm_info *qm = data;
+	u32 int_source;
+
+	int_source = qm_get_irq_source(qm);
+	if (int_source)
+		return IRQ_WAKE_THREAD;
+
+	dev_err(&qm->pdev->dev, "invalid int source %d\n", int_source);
+
+	return IRQ_HANDLED;
+}
+
+int hisi_qm_start(struct qm_info *qm)
+{
+	struct pci_dev *pdev = qm->pdev;
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	if (qm->pdev->is_physfn)
+		qm->ops->vft_config(qm, qm->qp_base, qm->qp_num);
+
+	ret = qm_init_q_buffer(dev, sizeof(struct eqc), &qm->eqc);
+	if (ret)
+		goto err_out;
+
+	ret = qm_init_q_buffer(dev, sizeof(struct eqe) * QM_Q_DEPTH, &qm->eqe);
+	if (ret)
+		goto err_with_eqc;
+
+	QM_EQC(qm)->base_l = lower_32_bits(qm->eqe.dma);
+	QM_EQC(qm)->base_h = upper_32_bits(qm->eqe.dma);
+	QM_EQC(qm)->dw3 = 2 << MB_EQC_EQE_SHIFT;
+	QM_EQC(qm)->dw6 = (QM_Q_DEPTH - 1) | (1 << MB_EQC_PHASE_SHIFT);
+	ret = qm_mb(qm, MAILBOX_CMD_EQC, qm->eqc.dma, 0, 0, 0);
+	if (ret)
+		goto err_with_eqe;
+
+	qm->qp_bitmap = kcalloc(BITS_TO_LONGS(qm->qp_num), sizeof(long),
+				GFP_KERNEL);
+	if (!qm->qp_bitmap)
+		goto err_with_eqe;
+
+	qm->qp_array = kcalloc(qm->qp_num, sizeof(struct hisi_qp *),
+			       GFP_KERNEL);
+	if (!qm->qp_array)
+		goto err_with_bitmap;
+
+	/* Init sqc_bt */
+	ret = qm_init_bt(qm, dev, sizeof(struct sqc) * qm->qp_num, &qm->sqc,
+			 MAILBOX_CMD_SQC_BT);
+	if (ret)
+		goto err_with_qp_array;
+
+	/* Init cqc_bt */
+	ret = qm_init_bt(qm, dev, sizeof(struct cqc) * qm->qp_num, &qm->cqc,
+			 MAILBOX_CMD_CQC_BT);
+	if (ret)
+		goto err_with_sqc;
+
+	ret = request_threaded_irq(pci_irq_vector(pdev, 0), qm_irq,
+				   qm_irq_thread, IRQF_SHARED, qm->dev_name,
+				   qm);
+	if (ret)
+		goto err_with_cqc;
+
+	writel(0x0, QM_ADDR(qm, QM_VF_EQ_INT_MASK));
+
+	return 0;
+
+err_with_cqc:
+	qm_uninit_q_buffer(dev, &qm->cqc);
+err_with_sqc:
+	qm_uninit_q_buffer(dev, &qm->sqc);
+err_with_qp_array:
+	kfree(qm->qp_array);
+err_with_bitmap:
+	kfree(qm->qp_bitmap);
+err_with_eqe:
+	qm_uninit_q_buffer(dev, &qm->eqe);
+err_with_eqc:
+	qm_uninit_q_buffer(dev, &qm->eqc);
+err_out:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hisi_qm_start);
+
+void hisi_qm_stop(struct qm_info *qm)
+{
+	struct pci_dev *pdev = qm->pdev;
+	struct device *dev = &pdev->dev;
+
+	free_irq(pci_irq_vector(pdev, 0), qm);
+	qm_uninit_q_buffer(dev, &qm->cqc);
+	kfree(qm->qp_array);
+	kfree(qm->qp_bitmap);
+	qm_uninit_q_buffer(dev, &qm->eqe);
+	qm_uninit_q_buffer(dev, &qm->eqc);
+}
+EXPORT_SYMBOL_GPL(hisi_qm_stop);
+
+/* put qm into init state, so the acce config become available */
+int hisi_qm_mem_start(struct qm_info *qm)
+{
+	u32 val;
+
+	qm_writel(qm, 0x1, QM_MEM_START_INIT);
+	return readl_relaxed_poll_timeout(QM_ADDR(qm, QM_MEM_INIT_DONE), val,
+					  val & BIT(0), 10, 1000);
+}
+EXPORT_SYMBOL_GPL(hisi_qm_mem_start);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Zhou Wang <wangzhou1@hisilicon.com>");
+MODULE_DESCRIPTION("HiSilicon Accelerator queue manager driver");
diff --git a/drivers/crypto/hisilicon/qm.h b/drivers/crypto/hisilicon/qm.h
new file mode 100644
index 000000000000..0e81182ac6a8
--- /dev/null
+++ b/drivers/crypto/hisilicon/qm.h
@@ -0,0 +1,110 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+#ifndef HISI_ACC_QM_H
+#define HISI_ACC_QM_H
+
+#include <linux/dmapool.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+
+#define QM_CQE_SIZE			16
+/* default queue depth for sq/cq/eq */
+#define QM_Q_DEPTH			1024
+
+/* qm user domain */
+#define QM_ARUSER_M_CFG_1		0x100088
+#define QM_ARUSER_M_CFG_ENABLE		0x100090
+#define QM_AWUSER_M_CFG_1		0x100098
+#define QM_AWUSER_M_CFG_ENABLE		0x1000a0
+#define QM_WUSER_M_CFG_ENABLE		0x1000a8
+
+/* qm cache */
+#define QM_CACHE_CTL			0x100050
+#define QM_AXI_M_CFG			0x1000ac
+#define QM_AXI_M_CFG_ENABLE		0x1000b0
+#define QM_PEH_AXUSER_CFG		0x1000cc
+#define QM_PEH_AXUSER_CFG_ENABLE	0x1000d0
+
+#define QP_SQE_ADDR(qp) ((qp)->scqe.addr)
+
+struct qm_dma_buffer {
+	int size;
+	void *addr;
+	dma_addr_t dma;
+};
+
+struct qm_info {
+	int ver;
+	const char *dev_name;
+	struct pci_dev *pdev;
+
+	resource_size_t phys_base;
+	resource_size_t size;
+	void __iomem *io_base;
+
+	u32 sqe_size;
+	u32 qp_base;
+	u32 qp_num;
+
+	struct qm_dma_buffer sqc, cqc, eqc, eqe;
+
+	u32 eq_head;
+
+	rwlock_t qps_lock;
+	unsigned long *qp_bitmap;
+	struct hisi_qp **qp_array;
+
+	struct mutex mailbox_lock;
+
+	struct hisi_acc_qm_hw_ops *ops;
+
+};
+#define QM_ADDR(qm, off) ((qm)->io_base + off)
+
+struct hisi_acc_qp_status {
+	u16 sq_tail;
+	u16 sq_head;
+	u16 cq_head;
+	bool cqc_phase;
+	int is_sq_full;
+};
+
+struct hisi_qp;
+
+struct hisi_qp_ops {
+	int (*fill_sqe)(void *sqe, void *q_parm, void *d_parm);
+};
+
+struct hisi_qp {
+	/* sq number in this function */
+	u32 queue_id;
+	u8 alg_type;
+	u8 req_type;
+
+	struct qm_dma_buffer sqc, cqc;
+	struct qm_dma_buffer scqe;
+
+	struct hisi_acc_qp_status qp_status;
+
+	struct qm_info *qm;
+
+	/* for crypto sync API */
+	struct completion completion;
+
+	struct hisi_qp_ops *hw_ops;
+	void *qp_ctx;
+	void (*event_cb)(struct hisi_qp *qp);
+	void (*req_cb)(struct hisi_qp *qp, void *data);
+};
+
+extern int hisi_qm_init(const char *dev_name, struct qm_info *qm);
+extern void hisi_qm_uninit(struct qm_info *qm);
+extern int hisi_qm_start(struct qm_info *qm);
+extern void hisi_qm_stop(struct qm_info *qm);
+extern int hisi_qm_mem_start(struct qm_info *qm);
+extern struct hisi_qp *hisi_qm_create_qp(struct qm_info *qm, u8 alg_type);
+extern int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg);
+extern void hisi_qm_release_qp(struct hisi_qp *qp);
+extern int hisi_qp_send(struct hisi_qp *qp, void *msg);
+#endif
-- 
2.17.1