diff options
Diffstat (limited to 'drivers/crypto/hisilicon')
| -rw-r--r-- | drivers/crypto/hisilicon/Kconfig | 25 | ||||
| -rw-r--r-- | drivers/crypto/hisilicon/Makefile | 3 | ||||
| -rw-r--r-- | drivers/crypto/hisilicon/qm.c | 1913 | ||||
| -rw-r--r-- | drivers/crypto/hisilicon/qm.h | 215 | ||||
| -rw-r--r-- | drivers/crypto/hisilicon/sec/sec_algs.c | 18 | ||||
| -rw-r--r-- | drivers/crypto/hisilicon/sgl.c | 214 | ||||
| -rw-r--r-- | drivers/crypto/hisilicon/sgl.h | 24 | ||||
| -rw-r--r-- | drivers/crypto/hisilicon/zip/Makefile | 2 | ||||
| -rw-r--r-- | drivers/crypto/hisilicon/zip/zip.h | 71 | ||||
| -rw-r--r-- | drivers/crypto/hisilicon/zip/zip_crypto.c | 653 | ||||
| -rw-r--r-- | drivers/crypto/hisilicon/zip/zip_main.c | 1013 |
11 files changed, 4140 insertions, 11 deletions
diff --git a/drivers/crypto/hisilicon/Kconfig b/drivers/crypto/hisilicon/Kconfig index 8ca9c503bcb0..ebaf91e0146d 100644 --- a/drivers/crypto/hisilicon/Kconfig +++ b/drivers/crypto/hisilicon/Kconfig @@ -4,6 +4,7 @@ config CRYPTO_DEV_HISI_SEC tristate "Support for Hisilicon SEC crypto block cipher accelerator" select CRYPTO_BLKCIPHER select CRYPTO_ALGAPI + select CRYPTO_LIB_DES select SG_SPLIT depends on ARM64 || COMPILE_TEST depends on HAS_IOMEM @@ -12,3 +13,27 @@ 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 && PCI_MSI + help + HiSilicon accelerator engines use a common queue management + interface. Specific engine driver may use this module. + +config CRYPTO_HISI_SGL + tristate + depends on ARM64 + help + HiSilicon accelerator engines use a common hardware scatterlist + interface for data format. Specific engine driver may use this + module. + +config CRYPTO_DEV_HISI_ZIP + tristate "Support for HiSilicon ZIP accelerator" + depends on ARM64 && PCI && PCI_MSI + select CRYPTO_DEV_HISI_QM + select CRYPTO_HISI_SGL + select SG_SPLIT + help + Support for HiSilicon ZIP Driver diff --git a/drivers/crypto/hisilicon/Makefile b/drivers/crypto/hisilicon/Makefile index 463f46ace182..45a279741126 100644 --- a/drivers/crypto/hisilicon/Makefile +++ b/drivers/crypto/hisilicon/Makefile @@ -1,2 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_CRYPTO_DEV_HISI_SEC) += sec/ +obj-$(CONFIG_CRYPTO_DEV_HISI_QM) += qm.o +obj-$(CONFIG_CRYPTO_HISI_SGL) += sgl.o +obj-$(CONFIG_CRYPTO_DEV_HISI_ZIP) += zip/ diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c new file mode 100644 index 000000000000..f975c393a603 --- /dev/null +++ b/drivers/crypto/hisilicon/qm.c @@ -0,0 +1,1913 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 HiSilicon Limited. */ +#include <asm/page.h> +#include <linux/bitmap.h> +#include <linux/debugfs.h> +#include <linux/dma-mapping.h> +#include <linux/io.h> +#include <linux/irqreturn.h> +#include <linux/log2.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include "qm.h" + +/* 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 +#define QM_IRQ_NUM_V1 1 +#define QM_IRQ_NUM_PF_V2 4 +#define QM_IRQ_NUM_VF_V2 2 + +#define QM_EQ_EVENT_IRQ_VECTOR 0 +#define QM_AEQ_EVENT_IRQ_VECTOR 1 +#define QM_ABNORMAL_EVENT_IRQ_VECTOR 3 + +/* mailbox */ +#define QM_MB_CMD_SQC 0x0 +#define QM_MB_CMD_CQC 0x1 +#define QM_MB_CMD_EQC 0x2 +#define QM_MB_CMD_AEQC 0x3 +#define QM_MB_CMD_SQC_BT 0x4 +#define QM_MB_CMD_CQC_BT 0x5 +#define QM_MB_CMD_SQC_VFT_V2 0x6 + +#define QM_MB_CMD_SEND_BASE 0x300 +#define QM_MB_EVENT_SHIFT 8 +#define QM_MB_BUSY_SHIFT 13 +#define QM_MB_OP_SHIFT 14 +#define QM_MB_CMD_DATA_ADDR_L 0x304 +#define QM_MB_CMD_DATA_ADDR_H 0x308 + +/* sqc shift */ +#define QM_SQ_HOP_NUM_SHIFT 0 +#define QM_SQ_PAGE_SIZE_SHIFT 4 +#define QM_SQ_BUF_SIZE_SHIFT 8 +#define QM_SQ_SQE_SIZE_SHIFT 12 +#define QM_SQ_PRIORITY_SHIFT 0 +#define QM_SQ_ORDERS_SHIFT 4 +#define QM_SQ_TYPE_SHIFT 8 + +#define QM_SQ_TYPE_MASK GENMASK(3, 0) + +/* cqc shift */ +#define QM_CQ_HOP_NUM_SHIFT 0 +#define QM_CQ_PAGE_SIZE_SHIFT 4 +#define QM_CQ_BUF_SIZE_SHIFT 8 +#define QM_CQ_CQE_SIZE_SHIFT 12 +#define QM_CQ_PHASE_SHIFT 0 +#define QM_CQ_FLAG_SHIFT 1 + +#define QM_CQE_PHASE(cqe) ((cqe)->w7 & 0x1) +#define QM_QC_CQE_SIZE 4 + +/* eqc shift */ +#define QM_EQE_AEQE_SIZE (2UL << 12) +#define QM_EQC_PHASE_SHIFT 16 + +#define QM_EQE_PHASE(eqe) (((eqe)->dw0 >> 16) & 0x1) +#define QM_EQE_CQN_MASK GENMASK(15, 0) + +#define QM_AEQE_PHASE(aeqe) (((aeqe)->dw0 >> 16) & 0x1) +#define QM_AEQE_TYPE_SHIFT 17 + +#define QM_DOORBELL_CMD_SQ 0 +#define QM_DOORBELL_CMD_CQ 1 +#define QM_DOORBELL_CMD_EQ 2 +#define QM_DOORBELL_CMD_AEQ 3 + +#define QM_DOORBELL_BASE_V1 0x340 +#define QM_DB_CMD_SHIFT_V1 16 +#define QM_DB_INDEX_SHIFT_V1 32 +#define QM_DB_PRIORITY_SHIFT_V1 48 +#define QM_DOORBELL_SQ_CQ_BASE_V2 0x1000 +#define QM_DOORBELL_EQ_AEQ_BASE_V2 0x2000 +#define QM_DB_CMD_SHIFT_V2 12 +#define QM_DB_RAND_SHIFT_V2 16 +#define QM_DB_INDEX_SHIFT_V2 32 +#define QM_DB_PRIORITY_SHIFT_V2 48 + +#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 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_START_SQN_SHIFT 28 +#define QM_SQC_VFT_VALID (1ULL << 44) +#define QM_SQC_VFT_SQN_SHIFT 45 +#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_VALID (1ULL << 28) + +#define QM_SQC_VFT_BASE_SHIFT_V2 28 +#define QM_SQC_VFT_BASE_MASK_V2 GENMASK(5, 0) +#define QM_SQC_VFT_NUM_SHIFT_V2 45 +#define QM_SQC_VFT_NUM_MASK_v2 GENMASK(9, 0) + +#define QM_DFX_CNT_CLR_CE 0x100118 + +#define QM_ABNORMAL_INT_SOURCE 0x100000 +#define QM_ABNORMAL_INT_MASK 0x100004 +#define QM_ABNORMAL_INT_MASK_VALUE 0x1fff +#define QM_ABNORMAL_INT_STATUS 0x100008 +#define QM_ABNORMAL_INF00 0x100010 +#define QM_FIFO_OVERFLOW_TYPE 0xc0 +#define QM_FIFO_OVERFLOW_TYPE_SHIFT 6 +#define QM_FIFO_OVERFLOW_VF 0x3f +#define QM_ABNORMAL_INF01 0x100014 +#define QM_DB_TIMEOUT_TYPE 0xc0 +#define QM_DB_TIMEOUT_TYPE_SHIFT 6 +#define QM_DB_TIMEOUT_VF 0x3f +#define QM_RAS_CE_ENABLE 0x1000ec +#define QM_RAS_FE_ENABLE 0x1000f0 +#define QM_RAS_NFE_ENABLE 0x1000f4 +#define QM_RAS_CE_THRESHOLD 0x1000f8 +#define QM_RAS_CE_TIMES_PER_IRQ 1 +#define QM_RAS_MSI_INT_SEL 0x1040f4 + +#define QM_CACHE_WB_START 0x204 +#define QM_CACHE_WB_DONE 0x208 + +#define PCI_BAR_2 2 +#define QM_SQE_DATA_ALIGN_MASK GENMASK(6, 0) +#define QMC_ALIGN(sz) ALIGN(sz, 32) + +#define QM_DBG_TMP_BUF_LEN 22 + +#define QM_MK_CQC_DW3_V1(hop_num, pg_sz, buf_sz, cqe_sz) \ + (((hop_num) << QM_CQ_HOP_NUM_SHIFT) | \ + ((pg_sz) << QM_CQ_PAGE_SIZE_SHIFT) | \ + ((buf_sz) << QM_CQ_BUF_SIZE_SHIFT) | \ + ((cqe_sz) << QM_CQ_CQE_SIZE_SHIFT)) + +#define QM_MK_CQC_DW3_V2(cqe_sz) \ + ((QM_Q_DEPTH - 1) | ((cqe_sz) << QM_CQ_CQE_SIZE_SHIFT)) + +#define QM_MK_SQC_W13(priority, orders, alg_type) \ + (((priority) << QM_SQ_PRIORITY_SHIFT) | \ + ((orders) << QM_SQ_ORDERS_SHIFT) | \ + (((alg_type) & QM_SQ_TYPE_MASK) << QM_SQ_TYPE_SHIFT)) + +#define QM_MK_SQC_DW3_V1(hop_num, pg_sz, buf_sz, sqe_sz) \ + (((hop_num) << QM_SQ_HOP_NUM_SHIFT) | \ + ((pg_sz) << QM_SQ_PAGE_SIZE_SHIFT) | \ + ((buf_sz) << QM_SQ_BUF_SIZE_SHIFT) | \ + ((u32)ilog2(sqe_sz) << QM_SQ_SQE_SIZE_SHIFT)) + +#define QM_MK_SQC_DW3_V2(sqe_sz) \ + ((QM_Q_DEPTH - 1) | ((u32)ilog2(sqe_sz) << QM_SQ_SQE_SIZE_SHIFT)) + +#define INIT_QC_COMMON(qc, base, pasid) do { \ + (qc)->head = 0; \ + (qc)->tail = 0; \ + (qc)->base_l = lower_32_bits(base); \ + (qc)->base_h = upper_32_bits(base); \ + (qc)->dw3 = 0; \ + (qc)->w8 = 0; \ + (qc)->rsvd0 = 0; \ + (qc)->pasid = pasid; \ + (qc)->w11 = 0; \ + (qc)->rsvd1 = 0; \ +} while (0) + +enum vft_type { + SQC_VFT = 0, + CQC_VFT, +}; + +struct qm_cqe { + __le32 rsvd0; + __le16 cmd_id; + __le16 rsvd1; + __le16 sq_head; + __le16 sq_num; + __le16 rsvd2; + __le16 w7; +}; + +struct qm_eqe { + __le32 dw0; +}; + +struct qm_aeqe { + __le32 dw0; +}; + +struct qm_sqc { + __le16 head; + __le16 tail; + __le32 base_l; + __le32 base_h; + __le32 dw3; + __le16 w8; + __le16 rsvd0; + __le16 pasid; + __le16 w11; + __le16 cq_num; + __le16 w13; + __le32 rsvd1; +}; + +struct qm_cqc { + __le16 head; + __le16 tail; + __le32 base_l; + __le32 base_h; + __le32 dw3; + __le16 w8; + __le16 rsvd0; + __le16 pasid; + __le16 w11; + __le32 dw6; + __le32 rsvd1; +}; + +struct qm_eqc { + __le16 head; + __le16 tail; + __le32 base_l; + __le32 base_h; + __le32 dw3; + __le32 rsvd[2]; + __le32 dw6; +}; + +struct qm_aeqc { + __le16 head; + __le16 tail; + __le32 base_l; + __le32 base_h; + __le32 dw3; + __le32 rsvd[2]; + __le32 dw6; +}; + +struct qm_mailbox { + __le16 w0; + __le16 queue_num; + __le32 base_l; + __le32 base_h; + __le32 rsvd; +}; + +struct qm_doorbell { + __le16 queue_num; + __le16 cmd; + __le16 index; + __le16 priority; +}; + +struct hisi_qm_hw_ops { + int (*get_vft)(struct hisi_qm *qm, u32 *base, u32 *number); + void (*qm_db)(struct hisi_qm *qm, u16 qn, + u8 cmd, u16 index, u8 priority); + u32 (*get_irq_num)(struct hisi_qm *qm); + int (*debug_init)(struct hisi_qm *qm); + void (*hw_error_init)(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe, + u32 msi); + pci_ers_result_t (*hw_error_handle)(struct hisi_qm *qm); +}; + +static const char * const qm_debug_file_name[] = { + [CURRENT_Q] = "current_q", + [CLEAR_ENABLE] = "clear_enable", +}; + +struct hisi_qm_hw_error { + u32 int_msk; + const char *msg; +}; + +static const struct hisi_qm_hw_error qm_hw_error[] = { + { .int_msk = BIT(0), .msg = "qm_axi_rresp" }, + { .int_msk = BIT(1), .msg = "qm_axi_bresp" }, + { .int_msk = BIT(2), .msg = "qm_ecc_mbit" }, + { .int_msk = BIT(3), .msg = "qm_ecc_1bit" }, + { .int_msk = BIT(4), .msg = "qm_acc_get_task_timeout" }, + { .int_msk = BIT(5), .msg = "qm_acc_do_task_timeout" }, + { .int_msk = BIT(6), .msg = "qm_acc_wb_not_ready_timeout" }, + { .int_msk = BIT(7), .msg = "qm_sq_cq_vf_invalid" }, + { .int_msk = BIT(8), .msg = "qm_cq_vf_invalid" }, + { .int_msk = BIT(9), .msg = "qm_sq_vf_invalid" }, + { .int_msk = BIT(10), .msg = "qm_db_timeout" }, + { .int_msk = BIT(11), .msg = "qm_of_fifo_of" }, + { .int_msk = BIT(12), .msg = "qm_db_random_invalid" }, + { /* sentinel */ } +}; + +static const char * const qm_db_timeout[] = { + "sq", "cq", "eq", "aeq", +}; + +static const char * const qm_fifo_overflow[] = { + "cq", "eq", "aeq", +}; + +/* return 0 mailbox ready, -ETIMEDOUT hardware timeout */ +static int qm_wait_mb_ready(struct hisi_qm *qm) +{ + u32 val; + + return readl_relaxed_poll_timeout(qm->io_base + QM_MB_CMD_SEND_BASE, + val, !((val >> QM_MB_BUSY_SHIFT) & + 0x1), 10, 1000); +} + +/* 128 bit should be written to hardware at one time to trigger a mailbox */ +static void qm_mb_write(struct hisi_qm *qm, const void *src) +{ + void __iomem *fun_base = qm->io_base + QM_MB_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 hisi_qm *qm, u8 cmd, dma_addr_t dma_addr, u16 queue, + bool op) +{ + struct qm_mailbox mailbox; + int ret = 0; + + dev_dbg(&qm->pdev->dev, "QM mailbox request to q%u: %u-%llx\n", + queue, cmd, (unsigned long long)dma_addr); + + mailbox.w0 = cmd | + (op ? 0x1 << QM_MB_OP_SHIFT : 0) | + (0x1 << QM_MB_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); + + if (unlikely(qm_wait_mb_ready(qm))) { + ret = -EBUSY; + dev_err(&qm->pdev->dev, "QM mailbox is busy to start!\n"); + goto busy_unlock; + } + + qm_mb_write(qm, &mailbox); + + if (unlikely(qm_wait_mb_ready(qm))) { + ret = -EBUSY; + dev_err(&qm->pdev->dev, "QM mailbox operation timeout!\n"); + goto busy_unlock; + } + +busy_unlock: + mutex_unlock(&qm->mailbox_lock); + + return ret; +} + +static void qm_db_v1(struct hisi_qm *qm, u16 qn, u8 cmd, u16 index, u8 priority) +{ + u64 doorbell; + + doorbell = qn | ((u64)cmd << QM_DB_CMD_SHIFT_V1) | + ((u64)index << QM_DB_INDEX_SHIFT_V1) | + ((u64)priority << QM_DB_PRIORITY_SHIFT_V1); + + writeq(doorbell, qm->io_base + QM_DOORBELL_BASE_V1); +} + +static void qm_db_v2(struct hisi_qm *qm, u16 qn, u8 cmd, u16 index, u8 priority) +{ + u64 doorbell; + u64 dbase; + u16 randata = 0; + + if (cmd == QM_DOORBELL_CMD_SQ || cmd == QM_DOORBELL_CMD_CQ) + dbase = QM_DOORBELL_SQ_CQ_BASE_V2; + else + dbase = QM_DOORBELL_EQ_AEQ_BASE_V2; + + doorbell = qn | ((u64)cmd << QM_DB_CMD_SHIFT_V2) | + ((u64)randata << QM_DB_RAND_SHIFT_V2) | + ((u64)index << QM_DB_INDEX_SHIFT_V2) | + ((u64)priority << QM_DB_PRIORITY_SHIFT_V2); + + writeq(doorbell, qm->io_base + dbase); +} + +static void qm_db(struct hisi_qm *qm, u16 qn, u8 cmd, u16 index, u8 priority) +{ + dev_dbg(&qm->pdev->dev, "QM doorbell request: qn=%u, cmd=%u, index=%u\n", + qn, cmd, index); + + qm->ops->qm_db(qm, qn, cmd, index, priority); +} + +static int qm_dev_mem_reset(struct hisi_qm *qm) +{ + u32 val; + + writel(0x1, qm->io_base + QM_MEM_START_INIT); + return readl_relaxed_poll_timeout(qm->io_base + QM_MEM_INIT_DONE, val, + val & BIT(0), 10, 1000); +} + +static u32 qm_get_irq_num_v1(struct hisi_qm *qm) +{ + return QM_IRQ_NUM_V1; +} + +static u32 qm_get_irq_num_v2(struct hisi_qm *qm) +{ + if (qm->fun_type == QM_HW_PF) + return QM_IRQ_NUM_PF_V2; + else + return QM_IRQ_NUM_VF_V2; +} + +static struct hisi_qp *qm_to_hisi_qp(struct hisi_qm *qm, struct qm_eqe *eqe) +{ + u16 cqn = eqe->dw0 & QM_EQE_CQN_MASK; + + return qm->qp_array[cqn]; +} + +static void qm_cq_head_update(struct hisi_qp *qp) +{ + if (qp->qp_status.cq_head == QM_Q_DEPTH - 1) { + qp->qp_status.cqc_phase = !qp->qp_status.cqc_phase; + qp->qp_status.cq_head = 0; + } else { + qp->qp_status.cq_head++; + } +} + +static void qm_poll_qp(struct hisi_qp *qp, struct hisi_qm *qm) +{ + struct qm_cqe *cqe = qp->cqe + qp->qp_status.cq_head; + + if (qp->req_cb) { + while (QM_CQE_PHASE(cqe) == qp->qp_status.cqc_phase) { + dma_rmb(); + qp->req_cb(qp, qp->sqe + qm->sqe_size * cqe->sq_head); + qm_cq_head_update(qp); + cqe = qp->cqe + qp->qp_status.cq_head; + qm_db(qm, qp->qp_id, QM_DOORBELL_CMD_CQ, + qp->qp_status.cq_head, 0); + atomic_dec(&qp->qp_status.used); + } + + /* set c_flag */ + qm_db(qm, qp->qp_id, QM_DOORBELL_CMD_CQ, + qp->qp_status.cq_head, 1); + } +} + +static void qm_qp_work_func(struct work_struct *work) +{ + struct hisi_qp *qp; + + qp = container_of(work, struct hisi_qp, work); + qm_poll_qp(qp, qp->qm); +} + +static irqreturn_t qm_irq_handler(int irq, void *data) +{ + struct hisi_qm *qm = data; + struct qm_eqe *eqe = qm->eqe + qm->status.eq_head; + struct hisi_qp *qp; + int eqe_num = 0; + + while (QM_EQE_PHASE(eqe) == qm->status.eqc_phase) { + eqe_num++; + qp = qm_to_hisi_qp(qm, eqe); + if (qp) + queue_work(qp->wq, &qp->work); + + if (qm->status.eq_head == QM_Q_DEPTH - 1) { + qm->status.eqc_phase = !qm->status.eqc_phase; + eqe = qm->eqe; + qm->status.eq_head = 0; + } else { + eqe++; + qm->status.eq_head++; + } + + if (eqe_num == QM_Q_DEPTH / 2 - 1) { + eqe_num = 0; + qm_db(qm, 0, QM_DOORBELL_CMD_EQ, qm->status.eq_head, 0); + } + } + + qm_db(qm, 0, QM_DOORBELL_CMD_EQ, qm->status.eq_head, 0); + + return IRQ_HANDLED; +} + +static irqreturn_t qm_irq(int irq, void *data) +{ + struct hisi_qm *qm = data; + + if (readl(qm->io_base + QM_VF_EQ_INT_SOURCE)) + return qm_irq_handler(irq, data); + + dev_err(&qm->pdev->dev, "invalid int source\n"); + qm_db(qm, 0, QM_DOORBELL_CMD_EQ, qm->status.eq_head, 0); + + return IRQ_NONE; +} + +static irqreturn_t qm_aeq_irq(int irq, void *data) +{ + struct hisi_qm *qm = data; + struct qm_aeqe *aeqe = qm->aeqe + qm->status.aeq_head; + u32 type; + + if (!readl(qm->io_base + QM_VF_AEQ_INT_SOURCE)) + return IRQ_NONE; + + while (QM_AEQE_PHASE(aeqe) == qm->status.aeqc_phase) { + type = aeqe->dw0 >> QM_AEQE_TYPE_SHIFT; + if (type < ARRAY_SIZE(qm_fifo_overflow)) + dev_err(&qm->pdev->dev, "%s overflow\n", + qm_fifo_overflow[type]); + else + dev_err(&qm->pdev->dev, "unknown error type %d\n", + type); + + if (qm->status.aeq_head == QM_Q_DEPTH - 1) { + qm->status.aeqc_phase = !qm->status.aeqc_phase; + aeqe = qm->aeqe; + qm->status.aeq_head = 0; + } else { + aeqe++; + qm->status.aeq_head++; + } + + qm_db(qm, 0, QM_DOORBELL_CMD_AEQ, qm->status.aeq_head, 0); + } + + return IRQ_HANDLED; +} + +static irqreturn_t qm_abnormal_irq(int irq, void *data) +{ + const struct hisi_qm_hw_error *err = qm_hw_error; + struct hisi_qm *qm = data; + struct device *dev = &qm->pdev->dev; + u32 error_status, tmp; + + /* read err sts */ + tmp = readl(qm->io_base + QM_ABNORMAL_INT_STATUS); + error_status = qm->msi_mask & tmp; + + while (err->msg) { + if (err->int_msk & error_status) + dev_err(dev, "%s [error status=0x%x] found\n", + err->msg, err->int_msk); + + err++; + } + + /* clear err sts */ + writel(error_status, qm->io_base + QM_ABNORMAL_INT_SOURCE); + + return IRQ_HANDLED; +} + +static int qm_irq_register(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + int ret; + + ret = request_irq(pci_irq_vector(pdev, QM_EQ_EVENT_IRQ_VECTOR), + qm_irq, IRQF_SHARED, qm->dev_name, qm); + if (ret) + return ret; + + if (qm->ver == QM_HW_V2) { + ret = request_irq(pci_irq_vector(pdev, QM_AEQ_EVENT_IRQ_VECTOR), + qm_aeq_irq, IRQF_SHARED, qm->dev_name, qm); + if (ret) + goto err_aeq_irq; + + if (qm->fun_type == QM_HW_PF) { + ret = request_irq(pci_irq_vector(pdev, + QM_ABNORMAL_EVENT_IRQ_VECTOR), + qm_abnormal_irq, IRQF_SHARED, + qm->dev_name, qm); + if (ret) + goto err_abonormal_irq; + } + } + + return 0; + +err_abonormal_irq: + free_irq(pci_irq_vector(pdev, QM_AEQ_EVENT_IRQ_VECTOR), qm); +err_aeq_irq: + free_irq(pci_irq_vector(pdev, QM_EQ_EVENT_IRQ_VECTOR), qm); + return ret; +} + +static void qm_irq_unregister(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + + free_irq(pci_irq_vector(pdev, QM_EQ_EVENT_IRQ_VECTOR), qm); + + if (qm->ver == QM_HW_V2) { + free_irq(pci_irq_vector(pdev, QM_AEQ_EVENT_IRQ_VECTOR), qm); + + if (qm->fun_type == QM_HW_PF) + free_irq(pci_irq_vector(pdev, + QM_ABNORMAL_EVENT_IRQ_VECTOR), qm); + } +} + +static void qm_init_qp_status(struct hisi_qp *qp) +{ + struct hisi_qp_status *qp_status = &qp->qp_status; + + qp_status->sq_tail = 0; + qp_status->cq_head = 0; + qp_status->cqc_phase = 1; + qp_status->flags = 0; +} + +static void qm_vft_data_cfg(struct hisi_qm *qm, enum vft_type type, u32 base, + u32 number) +{ + u64 tmp = 0; + + if (number > 0) { + switch (type) { + case SQC_VFT: + switch (qm->ver) { + case QM_HW_V1: + 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; + break; + case QM_HW_V2: + tmp = (u64)base << QM_SQC_VFT_START_SQN_SHIFT | + QM_SQC_VFT_VALID | + (u64)(number - 1) << QM_SQC_VFT_SQN_SHIFT; + break; + case QM_HW_UNKNOWN: + break; + } + break; + case CQC_VFT: + switch (qm->ver) { + case QM_HW_V1: + tmp = QM_CQC_VFT_BUF_SIZE | + QM_CQC_VFT_SQC_SIZE | + QM_CQC_VFT_INDEX_NUMBER | + QM_CQC_VFT_VALID; + break; + case QM_HW_V2: + tmp = QM_CQC_VFT_VALID; + break; + case QM_HW_UNKNOWN: + break; + } + break; + } + } + + writel(lower_32_bits(tmp), qm->io_base + QM_VFT_CFG_DATA_L); + writel(upper_32_bits(tmp), qm->io_base + QM_VFT_CFG_DATA_H); +} + +static int qm_set_vft_common(struct hisi_qm *qm, enum vft_type type, + u32 fun_num, u32 base, u32 number) +{ + unsigned int val; + int ret; + + ret = readl_relaxed_poll_timeout(qm->io_base + QM_VFT_CFG_RDY, val, + val & BIT(0), 10, 1000); + if (ret) + return ret; + + writel(0x0, qm->io_base + QM_VFT_CFG_OP_WR); + writel(type, qm->io_base + QM_VFT_CFG_TYPE); + writel(fun_num, qm->io_base + QM_VFT_CFG); + + qm_vft_data_cfg(qm, type, base, number); + + writel(0x0, qm->io_base + QM_VFT_CFG_RDY); + writel(0x1, qm->io_base + QM_VFT_CFG_OP_ENABLE); + + return readl_relaxed_poll_timeout(qm->io_base + QM_VFT_CFG_RDY, val, + val & BIT(0), 10, 1000); +} + +/* The config should be conducted after qm_dev_mem_reset() */ +static int qm_set_sqc_cqc_vft(struct hisi_qm *qm, u32 fun_num, u32 base, + u32 number) +{ + int ret, i; + + for (i = SQC_VFT; i <= CQC_VFT; i++) { + ret = qm_set_vft_common(qm, i, fun_num, base, number); + if (ret) + return ret; + } + + return 0; +} + +static int qm_get_vft_v2(struct hisi_qm *qm, u32 *base, u32 *number) +{ + u64 sqc_vft; + int ret; + + ret = qm_mb(qm, QM_MB_CMD_SQC_VFT_V2, 0, 0, 1); + if (ret) + return ret; + + sqc_vft = readl(qm->io_base + QM_MB_CMD_DATA_ADDR_L) | + ((u64)readl(qm->io_base + QM_MB_CMD_DATA_ADDR_H) << 32); + *base = QM_SQC_VFT_BASE_MASK_V2 & (sqc_vft >> QM_SQC_VFT_BASE_SHIFT_V2); + *number = (QM_SQC_VFT_NUM_MASK_v2 & + (sqc_vft >> QM_SQC_VFT_NUM_SHIFT_V2)) + 1; + + return 0; +} + +static struct hisi_qm *file_to_qm(struct debugfs_file *file) +{ + struct qm_debug *debug = file->debug; + + return container_of(debug, struct hisi_qm, debug); +} + +static u32 current_q_read(struct debugfs_file *file) +{ + struct hisi_qm *qm = file_to_qm(file); + + return readl(qm->io_base + QM_DFX_SQE_CNT_VF_SQN) >> QM_DFX_QN_SHIFT; +} + +static int current_q_write(struct debugfs_file *file, u32 val) +{ + struct hisi_qm *qm = file_to_qm(file); + u32 tmp; + + if (val >= qm->debug.curr_qm_qp_num) + return -EINVAL; + + tmp = val << QM_DFX_QN_SHIFT | + (readl(qm->io_base + QM_DFX_SQE_CNT_VF_SQN) & CURRENT_FUN_MASK); + writel(tmp, qm->io_base + QM_DFX_SQE_CNT_VF_SQN); + + tmp = val << QM_DFX_QN_SHIFT | + (readl(qm->io_base + QM_DFX_CQE_CNT_VF_CQN) & CURRENT_FUN_MASK); + writel(tmp, qm->io_base + QM_DFX_CQE_CNT_VF_CQN); + + return 0; +} + +static u32 clear_enable_read(struct debugfs_file *file) +{ + struct hisi_qm *qm = file_to_qm(file); + + return readl(qm->io_base + QM_DFX_CNT_CLR_CE); +} + +/* rd_clr_ctrl 1 enable read clear, otherwise 0 disable it */ +static int clear_enable_write(struct debugfs_file *file, u32 rd_clr_ctrl) +{ + struct hisi_qm *qm = file_to_qm(file); + + if (rd_clr_ctrl > 1) + return -EINVAL; + + writel(rd_clr_ctrl, qm->io_base + QM_DFX_CNT_CLR_CE); + + return 0; +} + +static ssize_t qm_debug_read(struct file *filp, char __user *buf, + size_t count, loff_t *pos) +{ + struct debugfs_file *file = filp->private_data; + enum qm_debug_file index = file->index; + char tbuf[QM_DBG_TMP_BUF_LEN]; + u32 val; + int ret; + + mutex_lock(&file->lock); + switch (index) { + case CURRENT_Q: + val = current_q_read(file); + break; + case CLEAR_ENABLE: + val = clear_enable_read(file); + break; + default: + mutex_unlock(&file->lock); + return -EINVAL; + } + mutex_unlock(&file->lock); + ret = sprintf(tbuf, "%u\n", val); + return simple_read_from_buffer(buf, count, pos, tbuf, ret); +} + +static ssize_t qm_debug_write(struct file *filp, const char __user *buf, + size_t count, loff_t *pos) +{ + struct debugfs_file *file = filp->private_data; + enum qm_debug_file index = file->index; + unsigned long val; + char tbuf[QM_DBG_TMP_BUF_LEN]; + int len, ret; + + if (*pos != 0) + return 0; + + if (count >= QM_DBG_TMP_BUF_LEN) + return -ENOSPC; + + len = simple_write_to_buffer(tbuf, QM_DBG_TMP_BUF_LEN - 1, pos, buf, + count); + if (len < 0) + return len; + + tbuf[len] = '\0'; + if (kstrtoul(tbuf, 0, &val)) + return -EFAULT; + + mutex_lock(&file->lock); + switch (index) { + case CURRENT_Q: + ret = current_q_write(file, val); + if (ret) + goto err_input; + break; + case CLEAR_ENABLE: + ret = clear_enable_write(file, val); + if (ret) + goto err_input; + break; + default: + ret = -EINVAL; + goto err_input; + } + mutex_unlock(&file->lock); + + return count; + +err_input: + mutex_unlock(&file->lock); + return ret; +} + +static const struct file_operations qm_debug_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = qm_debug_read, + .write = qm_debug_write, +}; + +struct qm_dfx_registers { + char *reg_name; + u64 reg_offset; +}; + +#define CNT_CYC_REGS_NUM 10 +static struct qm_dfx_registers qm_dfx_regs[] = { + /* XXX_CNT are reading clear register */ + {"QM_ECC_1BIT_CNT ", 0x104000ull}, + {"QM_ECC_MBIT_CNT ", 0x104008ull}, + {"QM_DFX_MB_CNT ", 0x104018ull}, + {"QM_DFX_DB_CNT ", 0x104028ull}, + {"QM_DFX_SQE_CNT ", 0x104038ull}, + {"QM_DFX_CQE_CNT ", 0x104048ull}, + {"QM_DFX_SEND_SQE_TO_ACC_CNT ", 0x104050ull}, + {"QM_DFX_WB_SQE_FROM_ACC_CNT ", 0x104058ull}, + {"QM_DFX_ACC_FINISH_CNT ", 0x104060ull}, + {"QM_DFX_CQE_ERR_CNT ", 0x1040b4ull}, + {"QM_DFX_FUNS_ACTIVE_ST ", 0x200ull}, + {"QM_ECC_1BIT_INF ", 0x104004ull}, + {"QM_ECC_MBIT_INF ", 0x10400cull}, + {"QM_DFX_ACC_RDY_VLD0 ", 0x1040a0ull}, + {"QM_DFX_ACC_RDY_VLD1 ", 0x1040a4ull}, + {"QM_DFX_AXI_RDY_VLD ", 0x1040a8ull}, + {"QM_DFX_FF_ST0 ", 0x1040c8ull}, + {"QM_DFX_FF_ST1 ", 0x1040ccull}, + {"QM_DFX_FF_ST2 ", 0x1040d0ull}, + {"QM_DFX_FF_ST3 ", 0x1040d4ull}, + {"QM_DFX_FF_ST4 ", 0x1040d8ull}, + {"QM_DFX_FF_ST5 ", 0x1040dcull}, + {"QM_DFX_FF_ST6 ", 0x1040e0ull}, + {"QM_IN_IDLE_ST ", 0x1040e4ull}, + { NULL, 0} +}; + +static struct qm_dfx_registers qm_vf_dfx_regs[] = { + {"QM_DFX_FUNS_ACTIVE_ST ", 0x200ull}, + { NULL, 0} +}; + +static int qm_regs_show(struct seq_file *s, void *unused) +{ + struct hisi_qm *qm = s->private; + struct qm_dfx_registers *regs; + u32 val; + + if (qm->fun_type == QM_HW_PF) + regs = qm_dfx_regs; + else + regs = qm_vf_dfx_regs; + + while (regs->reg_name) { + val = readl(qm->io_base + regs->reg_offset); + seq_printf(s, "%s= 0x%08x\n", regs->reg_name, val); + regs++; + } + + return 0; +} + +static int qm_regs_open(struct inode *inode, struct file *file) +{ + return single_open(file, qm_regs_show, inode->i_private); +} + +static const struct file_operations qm_regs_fops = { + .owner = THIS_MODULE, + .open = qm_regs_open, + .read = seq_read, + .release = single_release, +}; + +static int qm_create_debugfs_file(struct hisi_qm *qm, enum qm_debug_file index) +{ + struct dentry *qm_d = qm->debug.qm_d, *tmp; + struct debugfs_file *file = qm->debug.files + index; + + tmp = debugfs_create_file(qm_debug_file_name[index], 0600, qm_d, file, + &qm_debug_fops); + if (IS_ERR(tmp)) + return -ENOENT; + + file->index = index; + mutex_init(&file->lock); + file->debug = &qm->debug; + + return 0; +} + +static void qm_hw_error_init_v1(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe, + u32 msi) +{ + dev_info(&qm->pdev->dev, + "QM v%d does not support hw error handle\n", qm->ver); + + writel(QM_ABNORMAL_INT_MASK_VALUE, qm->io_base + QM_ABNORMAL_INT_MASK); +} + +static void qm_hw_error_init_v2(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe, + u32 msi) +{ + u32 irq_enable = ce | nfe | fe | msi; + u32 irq_unmask = ~irq_enable; + + qm->error_mask = ce | nfe | fe; + qm->msi_mask = msi; + + /* configure error type */ + writel(ce, qm->io_base + QM_RAS_CE_ENABLE); + writel(QM_RAS_CE_TIMES_PER_IRQ, qm->io_base + QM_RAS_CE_THRESHOLD); + writel(nfe, qm->io_base + QM_RAS_NFE_ENABLE); + writel(fe, qm->io_base + QM_RAS_FE_ENABLE); + + /* use RAS irq default, so only set QM_RAS_MSI_INT_SEL for MSI */ + writel(msi, qm->io_base + QM_RAS_MSI_INT_SEL); + + irq_unmask &= readl(qm->io_base + QM_ABNORMAL_INT_MASK); + writel(irq_unmask, qm->io_base + QM_ABNORMAL_INT_MASK); +} + +static void qm_log_hw_error(struct hisi_qm *qm, u32 error_status) +{ + const struct hisi_qm_hw_error *err = qm_hw_error; + struct device *dev = &qm->pdev->dev; + u32 reg_val, type, vf_num; + + while (err->msg) { + if (err->int_msk & error_status) { + dev_err(dev, "%s [error status=0x%x] found\n", + err->msg, err->int_msk); + + if (error_status & QM_DB_TIMEOUT) { + reg_val = readl(qm->io_base + + QM_ABNORMAL_INF01); + type = (reg_val & QM_DB_TIMEOUT_TYPE) >> + QM_DB_TIMEOUT_TYPE_SHIFT; + vf_num = reg_val & QM_DB_TIMEOUT_VF; + dev_err(dev, "qm %s doorbell timeout in function %u\n", + qm_db_timeout[type], vf_num); + } + + if (error_status & QM_OF_FIFO_OF) { + reg_val = readl(qm->io_base + + QM_ABNORMAL_INF00); + type = (reg_val & QM_FIFO_OVERFLOW_TYPE) >> + QM_FIFO_OVERFLOW_TYPE_SHIFT; + vf_num = reg_val & QM_FIFO_OVERFLOW_VF; + + if (type < ARRAY_SIZE(qm_fifo_overflow)) + dev_err(dev, "qm %s fifo overflow in function %u\n", + qm_fifo_overflow[type], + vf_num); + else + dev_err(dev, "unknown error type\n"); + } + } + err++; + } +} + +static pci_ers_result_t qm_hw_error_handle_v2(struct hisi_qm *qm) +{ + u32 error_status, tmp; + + /* read err sts */ + tmp = readl(qm->io_base + QM_ABNORMAL_INT_STATUS); + error_status = qm->error_mask & tmp; + + if (error_status) { + qm_log_hw_error(qm, error_status); + + /* clear err sts */ + writel(error_status, qm->io_base + QM_ABNORMAL_INT_SOURCE); + + return PCI_ERS_RESULT_NEED_RESET; + } + + return PCI_ERS_RESULT_RECOVERED; +} + +static const struct hisi_qm_hw_ops qm_hw_ops_v1 = { + .qm_db = qm_db_v1, + .get_irq_num = qm_get_irq_num_v1, + .hw_error_init = qm_hw_error_init_v1, +}; + +static const struct hisi_qm_hw_ops qm_hw_ops_v2 = { + .get_vft = qm_get_vft_v2, + .qm_db = qm_db_v2, + .get_irq_num = qm_get_irq_num_v2, + .hw_error_init = qm_hw_error_init_v2, + .hw_error_handle = qm_hw_error_handle_v2, +}; + +static void *qm_get_avail_sqe(struct hisi_qp *qp) +{ + struct hisi_qp_status *qp_status = &qp->qp_status; + u16 sq_tail = qp_status->sq_tail; + + if (unlikely(atomic_read(&qp->qp_status.used) == QM_Q_DEPTH)) + return NULL; + + return qp->sqe + sq_tail * qp->qm->sqe_size; +} + +/** + * hisi_qm_create_qp() - Create a queue pair from qm. + * @qm: The qm we create a qp from. + * @alg_type: Accelerator specific algorithm type in sqc. + * + * return created qp, -EBUSY if all qps in qm allocated, -ENOMEM if allocating + * qp memory fails. + */ +struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type) +{ + struct device *dev = &qm->pdev->dev; + struct hisi_qp *qp; + int qp_id, ret; + + qp = kzalloc(sizeof(*qp), GFP_KERNEL); + if (!qp) + return ERR_PTR(-ENOMEM); + + write_lock(&qm->qps_lock); + + qp_id = find_first_zero_bit(qm->qp_bitmap, qm->qp_num); + if (qp_id >= qm->qp_num) { + write_unlock(&qm->qps_lock); + dev_info(&qm->pdev->dev, "QM all queues are busy!\n"); + ret = -EBUSY; + goto err_free_qp; + } + set_bit(qp_id, qm->qp_bitmap); + qm->qp_array[qp_id] = qp; + + write_unlock(&qm->qps_lock); + + qp->qm = qm; + + if (qm->use_dma_api) { + qp->qdma.size = qm->sqe_size * QM_Q_DEPTH + + sizeof(struct qm_cqe) * QM_Q_DEPTH; + qp->qdma.va = dma_alloc_coherent(dev, qp->qdma.size, + &qp->qdma.dma, GFP_KERNEL); + if (!qp->qdma.va) { + ret = -ENOMEM; + goto err_clear_bit; + } + + dev_dbg(dev, "allocate qp dma buf(va=%pK, dma=%pad, size=%zx)\n", + qp->qdma.va, &qp->qdma.dma, qp->qdma.size); + } + + qp->qp_id = qp_id; + qp->alg_type = alg_type; + INIT_WORK(&qp->work, qm_qp_work_func); + qp->wq = alloc_workqueue("hisi_qm", WQ_UNBOUND | WQ_HIGHPRI | + WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 0); + if (!qp->wq) { + ret = -EFAULT; + goto err_free_qp_mem; + } + + return qp; + +err_free_qp_mem: + if (qm->use_dma_api) + dma_free_coherent(dev, qp->qdma.size, qp->qdma.va, + qp->qdma.dma); +err_clear_bit: + write_lock(&qm->qps_lock); + qm->qp_array[qp_id] = NULL; + clear_bit(qp_id, qm->qp_bitmap); + write_unlock(&qm->qps_lock); +err_free_qp: + kfree(qp); + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(hisi_qm_create_qp); + +/** + * hisi_qm_release_qp() - Release a qp back to its qm. + * @qp: The qp we want to release. + * + * This function releases the resource of a qp. + */ +void hisi_qm_release_qp(struct hisi_qp *qp) +{ + struct hisi_qm *qm = qp->qm; + struct qm_dma *qdma = &qp->qdma; + struct device *dev = &qm->pdev->dev; + + if (qm->use_dma_api && qdma->va) + dma_free_coherent(dev, qdma->size, qdma->va, qdma->dma); + + write_lock(&qm->qps_lock); + qm->qp_array[qp->qp_id] = NULL; + clear_bit(qp->qp_id, qm->qp_bitmap); + write_unlock(&qm->qps_lock); + + kfree(qp); +} +EXPORT_SYMBOL_GPL(hisi_qm_release_qp); + +static int qm_qp_ctx_cfg(struct hisi_qp *qp, int qp_id, int pasid) +{ + struct hisi_qm *qm = qp->qm; + struct device *dev = &qm->pdev->dev; + enum qm_hw_ver ver = qm->ver; + struct qm_sqc *sqc; + struct qm_cqc *cqc; + dma_addr_t sqc_dma; + dma_addr_t cqc_dma; + int ret; + + qm_init_qp_status(qp); + + sqc = kzalloc(sizeof(struct qm_sqc), GFP_KERNEL); + if (!sqc) + return -ENOMEM; + sqc_dma = dma_map_single(dev, sqc, sizeof(struct qm_sqc), + DMA_TO_DEVICE); + if (dma_mapping_error(dev, sqc_dma)) { + kfree(sqc); + return -ENOMEM; + } + + INIT_QC_COMMON(sqc, qp->sqe_dma, pasid); + if (ver == QM_HW_V1) { + sqc->dw3 = QM_MK_SQC_DW3_V1(0, 0, 0, qm->sqe_size); + sqc->w8 = QM_Q_DEPTH - 1; + } else if (ver == QM_HW_V2) { + sqc->dw3 = QM_MK_SQC_DW3_V2(qm->sqe_size); + sqc->w8 = 0; /* rand_qc */ + } + sqc->cq_num = qp_id; + sqc->w13 = QM_MK_SQC_W13(0, 1, qp->alg_type); + + ret = qm_mb(qm, QM_MB_CMD_SQC, sqc_dma, qp_id, 0); + dma_unmap_single(dev, sqc_dma, sizeof(struct qm_sqc), DMA_TO_DEVICE); + kfree(sqc); + if (ret) + return ret; + + cqc = kzalloc(sizeof(struct qm_cqc), GFP_KERNEL); + if (!cqc) + return -ENOMEM; + cqc_dma = dma_map_single(dev, cqc, sizeof(struct qm_cqc), + DMA_TO_DEVICE); + if (dma_mapping_error(dev, cqc_dma)) { + kfree(cqc); + return -ENOMEM; + } + + INIT_QC_COMMON(cqc, qp->cqe_dma, pasid); + if (ver == QM_HW_V1) { + cqc->dw3 = QM_MK_CQC_DW3_V1(0, 0, 0, 4); + cqc->w8 = QM_Q_DEPTH - 1; + } else if (ver == QM_HW_V2) { + cqc->dw3 = QM_MK_CQC_DW3_V2(4); + cqc->w8 = 0; + } + cqc->dw6 = 1 << QM_CQ_PHASE_SHIFT | 1 << QM_CQ_FLAG_SHIFT; + + ret = qm_mb(qm, QM_MB_CMD_CQC, cqc_dma, qp_id, 0); + dma_unmap_single(dev, cqc_dma, sizeof(struct qm_cqc), DMA_TO_DEVICE); + kfree(cqc); + + return ret; +} + +/** + * hisi_qm_start_qp() - Start a qp into running. + * @qp: The qp we want to start to run. + * @arg: Accelerator specific argument. + * + * After this function, qp can receive request from user. Return qp_id if + * successful, Return -EBUSY if failed. + */ +int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg) +{ + struct hisi_qm *qm = qp->qm; + struct device *dev = &qm->pdev->dev; + enum qm_hw_ver ver = qm->ver; + int qp_id = qp->qp_id; + int pasid = arg; + size_t off = 0; + int ret; + +#define QP_INIT_BUF(qp, type, size) do { \ + (qp)->type = ((qp)->qdma.va + (off)); \ + (qp)->type##_dma = (qp)->qdma.dma + (off); \ + off += (size); \ +} while (0) + + if (!qp->qdma.dma) { + dev_err(dev, "cannot get qm dma buffer\n"); + return -EINVAL; + } + + /* sq need 128 bytes alignment */ + if (qp->qdma.dma & QM_SQE_DATA_ALIGN_MASK) { + dev_err(dev, "qm sq is not aligned to 128 byte\n"); + return -EINVAL; + } + + QP_INIT_BUF(qp, sqe, qm->sqe_size * QM_Q_DEPTH); + QP_INIT_BUF(qp, cqe, sizeof(struct qm_cqe) * QM_Q_DEPTH); + + dev_dbg(dev, "init qp buffer(v%d):\n" + " sqe (%pK, %lx)\n" + " cqe (%pK, %lx)\n", + ver, qp->sqe, (unsigned long)qp->sqe_dma, + qp->cqe, (unsigned long)qp->cqe_dma); + + ret = qm_qp_ctx_cfg(qp, qp_id, pasid); + if (ret) + return ret; + + dev_dbg(dev, "queue %d started\n", qp_id); + + return qp_id; +} +EXPORT_SYMBOL_GPL(hisi_qm_start_qp); + +/** + * hisi_qm_stop_qp() - Stop a qp in qm. + * @qp: The qp we want to stop. + * + * This function is reverse of hisi_qm_start_qp. Return 0 if successful. + */ +int hisi_qm_stop_qp(struct hisi_qp *qp) +{ + struct device *dev = &qp->qm->pdev->dev; + int i = 0; + + /* it is stopped */ + if (test_bit(QP_STOP, &qp->qp_status.flags)) + return 0; + + while (atomic_read(&qp->qp_status.used)) { + i++; + msleep(20); + if (i == 10) { + dev_err(dev, "Cannot drain out data for stopping, Force to stop!\n"); + return 0; + } + } + + set_bit(QP_STOP, &qp->qp_status.flags); + + dev_dbg(dev, "stop queue %u!", qp->qp_id); + + return 0; +} +EXPORT_SYMBOL_GPL(hisi_qm_stop_qp); + +/** + * hisi_qp_send() - Queue up a task in the hardware queue. + * @qp: The qp in which to put the message. + * @msg: The message. + * + * This function will return -EBUSY if qp is currently full, and -EAGAIN + * if qp related qm is resetting. + */ +int hisi_qp_send(struct hisi_qp *qp, const void *msg) +{ + struct hisi_qp_status *qp_status = &qp->qp_status; + u16 sq_tail = qp_status->sq_tail; + u16 sq_tail_next = (sq_tail + 1) % QM_Q_DEPTH; + void *sqe = qm_get_avail_sqe(qp); + + if (unlikely(test_bit(QP_STOP, &qp->qp_status.flags))) { + dev_info(&qp->qm->pdev->dev, "QP is stopped or resetting\n"); + return -EAGAIN; + } + + if (!sqe) + return -EBUSY; + + memcpy(sqe, msg, qp->qm->sqe_size); + + qm_db(qp->qm, qp->qp_id, QM_DOORBELL_CMD_SQ, sq_tail_next, 0); + atomic_inc(&qp->qp_status.used); + qp_status->sq_tail = sq_tail_next; + + return 0; +} +EXPORT_SYMBOL_GPL(hisi_qp_send); + +static void hisi_qm_cache_wb(struct hisi_qm *qm) +{ + unsigned int val; + + if (qm->ver == QM_HW_V2) { + writel(0x1, qm->io_base + QM_CACHE_WB_START); + if (readl_relaxed_poll_timeout(qm->io_base + QM_CACHE_WB_DONE, + val, val & BIT(0), 10, 1000)) + dev_err(&qm->pdev->dev, "QM writeback sqc cache fail!\n"); + } +} + +/** + * hisi_qm_init() - Initialize configures about qm. + * @qm: The qm needing init. + * + * This function init qm, then we can call hisi_qm_start to put qm into work. + */ +int hisi_qm_init(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + struct device *dev = &pdev->dev; + unsigned int num_vec; + int ret; + + switch (qm->ver) { + case QM_HW_V1: + qm->ops = &qm_hw_ops_v1; + break; + case QM_HW_V2: + qm->ops = &qm_hw_ops_v2; + break; + default: + return -EINVAL; + } + + ret = pci_enable_device_mem(pdev); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to enable device mem!\n"); + return ret; + } + + ret = pci_request_mem_regions(pdev, qm->dev_name); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to request mem regions!\n"); + goto err_disable_pcidev; + } + + qm->io_base = ioremap(pci_resource_start(pdev, PCI_BAR_2), + pci_resource_len(qm->pdev, PCI_BAR_2)); + if (!qm->io_base) { + ret = -EIO; + goto err_release_mem_regions; + } + + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); + if (ret < 0) + goto err_iounmap; + pci_set_master(pdev); + + if (!qm->ops->get_irq_num) { + ret = -EOPNOTSUPP; + goto err_iounmap; + } + num_vec = qm->ops->get_irq_num(qm); + ret = pci_alloc_irq_vectors(pdev, num_vec, num_vec, PCI_IRQ_MSI); + if (ret < 0) { + dev_err(dev, "Failed to enable MSI vectors!\n"); + goto err_iounmap; + } + + ret = qm_irq_register(qm); + if (ret) + goto err_free_irq_vectors; + + mutex_init(&qm->mailbox_lock); + rwlock_init(&qm->qps_lock); + + dev_dbg(dev, "init qm %s with %s\n", pdev->is_physfn ? "pf" : "vf", + qm->use_dma_api ? "dma api" : "iommu api"); + + return 0; + +err_free_irq_vectors: + pci_free_irq_vectors(pdev); +err_iounmap: + iounmap(qm->io_base); +err_release_mem_regions: + pci_release_mem_regions(pdev); +err_disable_pcidev: + pci_disable_device(pdev); + + return ret; +} +EXPORT_SYMBOL_GPL(hisi_qm_init); + +/** + * hisi_qm_uninit() - Uninitialize qm. + * @qm: The qm needed uninit. + * + * This function uninits qm related device resources. + */ +void hisi_qm_uninit(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + struct device *dev = &pdev->dev; + + if (qm->use_dma_api && qm->qdma.va) { + hisi_qm_cache_wb(qm); + dma_free_coherent(dev, qm->qdma.size, + qm->qdma.va, qm->qdma.dma); + memset(&qm->qdma, 0, sizeof(qm->qdma)); + } + + qm_irq_unregister(qm); + pci_free_irq_vectors(pdev); + iounmap(qm->io_base); + pci_release_mem_regions(pdev); + pci_disable_device(pdev); +} +EXPORT_SYMBOL_GPL(hisi_qm_uninit); + +/** + * hisi_qm_get_vft() - Get vft from a qm. + * @qm: The qm we want to get its vft. + * @base: The base number of queue in vft. + * @number: The number of queues in vft. + * + * We can allocate multiple queues to a qm by configuring virtual function + * table. We get related configures by this function. Normally, we call this + * function in VF driver to get the queue information. + * + * qm hw v1 does not support this interface. + */ +int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number) +{ + if (!base || !number) + return -EINVAL; + + if (!qm->ops->get_vft) { + dev_err(&qm->pdev->dev, "Don't support vft read!\n"); + return -EINVAL; + } + + return qm->ops->get_vft(qm, base, number); +} +EXPORT_SYMBOL_GPL(hisi_qm_get_vft); + +/** + * hisi_qm_set_vft() - Set "virtual function table" for a qm. + * @fun_num: Number of operated function. + * @qm: The qm in which to set vft, alway in a PF. + * @base: The base number of queue in vft. + * @number: The number of queues in vft. 0 means invalid vft. + * + * This function is alway called in PF driver, it is used to assign queues + * among PF and VFs. + * + * Assign queues A~B to PF: hisi_qm_set_vft(qm, 0, A, B - A + 1) + * Assign queues A~B to VF: hisi_qm_set_vft(qm, 2, A, B - A + 1) + * (VF function number 0x2) + */ +int hisi_qm_set_vft(struct hisi_qm *qm, u32 fun_num, u32 base, + u32 number) +{ + u32 max_q_num = qm->ctrl_qp_num; + + if (base >= max_q_num || number > max_q_num || + (base + number) > max_q_num) + return -EINVAL; + + return qm_set_sqc_cqc_vft(qm, fun_num, base, number); +} +EXPORT_SYMBOL_GPL(hisi_qm_set_vft); + +static void qm_init_eq_aeq_status(struct hisi_qm *qm) +{ + struct hisi_qm_status *status = &qm->status; + + status->eq_head = 0; + status->aeq_head = 0; + status->eqc_phase = 1; + status->aeqc_phase = 1; +} + +static int qm_eq_ctx_cfg(struct hisi_qm *qm) +{ + struct device *dev = &qm->pdev->dev; + struct qm_eqc *eqc; + struct qm_aeqc *aeqc; + dma_addr_t eqc_dma; + dma_addr_t aeqc_dma; + int ret; + + qm_init_eq_aeq_status(qm); + + eqc = kzalloc(sizeof(struct qm_eqc), GFP_KERNEL); + if (!eqc) + return -ENOMEM; + eqc_dma = dma_map_single(dev, eqc, sizeof(struct qm_eqc), + DMA_TO_DEVICE); + if (dma_mapping_error(dev, eqc_dma)) { + kfree(eqc); + return -ENOMEM; + } + + eqc->base_l = lower_32_bits(qm->eqe_dma); + eqc->base_h = upper_32_bits(qm->eqe_dma); + if (qm->ver == QM_HW_V1) + eqc->dw3 = QM_EQE_AEQE_SIZE; + eqc->dw6 = (QM_Q_DEPTH - 1) | (1 << QM_EQC_PHASE_SHIFT); + ret = qm_mb(qm, QM_MB_CMD_EQC, eqc_dma, 0, 0); + dma_unmap_single(dev, eqc_dma, sizeof(struct qm_eqc), DMA_TO_DEVICE); + kfree(eqc); + if (ret) + return ret; + + aeqc = kzalloc(sizeof(struct qm_aeqc), GFP_KERNEL); + if (!aeqc) + return -ENOMEM; + aeqc_dma = dma_map_single(dev, aeqc, sizeof(struct qm_aeqc), + DMA_TO_DEVICE); + if (dma_mapping_error(dev, aeqc_dma)) { + kfree(aeqc); + return -ENOMEM; + } + + aeqc->base_l = lower_32_bits(qm->aeqe_dma); + aeqc->base_h = upper_32_bits(qm->aeqe_dma); + aeqc->dw6 = (QM_Q_DEPTH - 1) | (1 << QM_EQC_PHASE_SHIFT); + + ret = qm_mb(qm, QM_MB_CMD_AEQC, aeqc_dma, 0, 0); + dma_unmap_single(dev, aeqc_dma, sizeof(struct qm_aeqc), DMA_TO_DEVICE); + kfree(aeqc); + + return ret; +} + +static int __hisi_qm_start(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + struct device *dev = &pdev->dev; + size_t off = 0; + int ret; + +#define QM_INIT_BUF(qm, type, num) do { \ + (qm)->type = ((qm)->qdma.va + (off)); \ + (qm)->type##_dma = (qm)->qdma.dma + (off); \ + off += QMC_ALIGN(sizeof(struct qm_##type) * (num)); \ +} while (0) + + WARN_ON(!qm->qdma.dma); + + if (qm->qp_num == 0) + return -EINVAL; + + if (qm->fun_type == QM_HW_PF) { + ret = qm_dev_mem_reset(qm); + if (ret) + return ret; + + ret = hisi_qm_set_vft(qm, 0, qm->qp_base, qm->qp_num); + if (ret) + return ret; + } + + QM_INIT_BUF(qm, eqe, QM_Q_DEPTH); + QM_INIT_BUF(qm, aeqe, QM_Q_DEPTH); + QM_INIT_BUF(qm, sqc, qm->qp_num); + QM_INIT_BUF(qm, cqc, qm->qp_num); + + dev_dbg(dev, "init qm buffer:\n" + " eqe (%pK, %lx)\n" + " aeqe (%pK, %lx)\n" + " sqc (%pK, %lx)\n" + " cqc (%pK, %lx)\n", + qm->eqe, (unsigned long)qm->eqe_dma, + qm->aeqe, (unsigned long)qm->aeqe_dma, + qm->sqc, (unsigned long)qm->sqc_dma, + qm->cqc, (unsigned long)qm->cqc_dma); + + ret = qm_eq_ctx_cfg(qm); + if (ret) + return ret; + + ret = qm_mb(qm, QM_MB_CMD_SQC_BT, qm->sqc_dma, 0, 0); + if (ret) + return ret; + + ret = qm_mb(qm, QM_MB_CMD_CQC_BT, qm->cqc_dma, 0, 0); + if (ret) + return ret; + + writel(0x0, qm->io_base + QM_VF_EQ_INT_MASK); + writel(0x0, qm->io_base + QM_VF_AEQ_INT_MASK); + + return 0; +} + +/** + * hisi_qm_start() - start qm + * @qm: The qm to be started. + * + * This function starts a qm, then we can allocate qp from this qm. + */ +int hisi_qm_start(struct hisi_qm *qm) +{ + struct device *dev = &qm->pdev->dev; + + dev_dbg(dev, "qm start with %d queue pairs\n", qm->qp_num); + + if (!qm->qp_num) { + dev_err(dev, "qp_num should not be 0\n"); + return -EINVAL; + } + + if (!qm->qp_bitmap) { + qm->qp_bitmap = devm_kcalloc(dev, BITS_TO_LONGS(qm->qp_num), + sizeof(long), GFP_KERNEL); + qm->qp_array = devm_kcalloc(dev, qm->qp_num, + sizeof(struct hisi_qp *), + GFP_KERNEL); + if (!qm->qp_bitmap || !qm->qp_array) + return -ENOMEM; + } + + if (!qm->use_dma_api) { + dev_dbg(&qm->pdev->dev, "qm delay start\n"); + return 0; + } else if (!qm->qdma.va) { + qm->qdma.size = QMC_ALIGN(sizeof(struct qm_eqe) * QM_Q_DEPTH) + + QMC_ALIGN(sizeof(struct qm_aeqe) * QM_Q_DEPTH) + + QMC_ALIGN(sizeof(struct qm_sqc) * qm->qp_num) + + QMC_ALIGN(sizeof(struct qm_cqc) * qm->qp_num); + qm->qdma.va = dma_alloc_coherent(dev, qm->qdma.size, + &qm->qdma.dma, GFP_KERNEL); + dev_dbg(dev, "allocate qm dma buf(va=%pK, dma=%pad, size=%zx)\n", + qm->qdma.va, &qm->qdma.dma, qm->qdma.size); + if (!qm->qdma.va) + return -ENOMEM; + } + + return __hisi_qm_start(qm); +} +EXPORT_SYMBOL_GPL(hisi_qm_start); + +/** + * hisi_qm_stop() - Stop a qm. + * @qm: The qm which will be stopped. + * + * This function stops qm and its qps, then qm can not accept request. + * Related resources are not released at this state, we can use hisi_qm_start + * to let qm start again. + */ +int hisi_qm_stop(struct hisi_qm *qm) +{ + struct device *dev; + struct hisi_qp *qp; + int ret = 0, i; + + if (!qm || !qm->pdev) { + WARN_ON(1); + return -EINVAL; + } + + dev = &qm->pdev->dev; + + /* Mask eq and aeq irq */ + writel(0x1, qm->io_base + QM_VF_EQ_INT_MASK); + writel(0x1, qm->io_base + QM_VF_AEQ_INT_MASK); + + /* Stop all qps belong to this qm */ + for (i = 0; i < qm->qp_num; i++) { + qp = qm->qp_array[i]; + if (qp) { + ret = hisi_qm_stop_qp(qp); + if (ret < 0) { + dev_err(dev, "Failed to stop qp%d!\n", i); + return -EBUSY; + } + } + } + + if (qm->fun_type == QM_HW_PF) { + ret = hisi_qm_set_vft(qm, 0, 0, 0); + if (ret < 0) + dev_err(dev, "Failed to set vft!\n"); + } + + return ret; +} +EXPORT_SYMBOL_GPL(hisi_qm_stop); + +/** + * hisi_qm_debug_init() - Initialize qm related debugfs files. + * @qm: The qm for which we want to add debugfs files. + * + * Create qm related debugfs files. + */ +int hisi_qm_debug_init(struct hisi_qm *qm) +{ + struct dentry *qm_d, *qm_regs; + int i, ret; + + qm_d = debugfs_create_dir("qm", qm->debug.debug_root); + if (IS_ERR(qm_d)) + return -ENOENT; + qm->debug.qm_d = qm_d; + + /* only show this in PF */ + if (qm->fun_type == QM_HW_PF) + for (i = CURRENT_Q; i < DEBUG_FILE_NUM; i++) + if (qm_create_debugfs_file(qm, i)) { + ret = -ENOENT; + goto failed_to_create; + } + + qm_regs = debugfs_create_file("qm_regs", 0444, qm->debug.qm_d, qm, + &qm_regs_fops); + if (IS_ERR(qm_regs)) { + ret = -ENOENT; + goto failed_to_create; + } + + return 0; + +failed_to_create: + debugfs_remove_recursive(qm_d); + return ret; +} +EXPORT_SYMBOL_GPL(hisi_qm_debug_init); + +/** + * hisi_qm_debug_regs_clear() - clear qm debug related registers. + * @qm: The qm for which we want to clear its debug registers. + */ +void hisi_qm_debug_regs_clear(struct hisi_qm *qm) +{ + struct qm_dfx_registers *regs; + int i; + + /* clear current_q */ + writel(0x0, qm->io_base + QM_DFX_SQE_CNT_VF_SQN); + writel(0x0, qm->io_base + QM_DFX_CQE_CNT_VF_CQN); + + /* + * these registers are reading and clearing, so clear them after + * reading them. + */ + writel(0x1, qm->io_base + QM_DFX_CNT_CLR_CE); + + regs = qm_dfx_regs; + for (i = 0; i < CNT_CYC_REGS_NUM; i++) { + readl(qm->io_base + regs->reg_offset); + regs++; + } + + writel(0x0, qm->io_base + QM_DFX_CNT_CLR_CE); +} +EXPORT_SYMBOL_GPL(hisi_qm_debug_regs_clear); + +/** + * hisi_qm_hw_error_init() - Configure qm hardware error report method. + * @qm: The qm which we want to configure. + * @ce: Bit mask of correctable error configure. + * @nfe: Bit mask of non-fatal error configure. + * @fe: Bit mask of fatal error configure. + * @msi: Bit mask of error reported by message signal interrupt. + * + * Hardware errors of qm can be reported either by RAS interrupts which will + * be handled by UEFI and then PCIe AER or by device MSI. User can configure + * each error to use either of above two methods. For RAS interrupts, we can + * configure an error as one of correctable error, non-fatal error or + * fatal error. + * + * Bits indicating errors can be configured to ce, nfe, fe and msi to enable + * related report methods. Error report will be masked if related error bit + * does not configure. + */ +void hisi_qm_hw_error_init(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe, + u32 msi) +{ + if (!qm->ops->hw_error_init) { + dev_err(&qm->pdev->dev, "QM version %d doesn't support hw error handling!\n", + qm->ver); + return; + } + + qm->ops->hw_error_init(qm, ce, nfe, fe, msi); +} +EXPORT_SYMBOL_GPL(hisi_qm_hw_error_init); + +/** + * hisi_qm_hw_error_handle() - Handle qm non-fatal hardware errors. + * @qm: The qm which has non-fatal hardware errors. + * + * Accelerators use this function to handle qm non-fatal hardware errors. + */ +int hisi_qm_hw_error_handle(struct hisi_qm *qm) +{ + if (!qm->ops->hw_error_handle) { + dev_err(&qm->pdev->dev, "QM version %d doesn't support hw error report!\n", + qm->ver); + return PCI_ERS_RESULT_NONE; + } + + return qm->ops->hw_error_handle(qm); +} +EXPORT_SYMBOL_GPL(hisi_qm_hw_error_handle); + +/** + * hisi_qm_get_hw_version() - Get hardware version of a qm. + * @pdev: The device which hardware version we want to get. + * + * This function gets the hardware version of a qm. Return QM_HW_UNKNOWN + * if the hardware version is not supported. + */ +enum qm_hw_ver hisi_qm_get_hw_version(struct pci_dev *pdev) +{ + switch (pdev->revision) { + case QM_HW_V1: + case QM_HW_V2: + return pdev->revision; + default: + return QM_HW_UNKNOWN; + } +} +EXPORT_SYMBOL_GPL(hisi_qm_get_hw_version); + +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..70e672ae86bf --- /dev/null +++ b/drivers/crypto/hisilicon/qm.h @@ -0,0 +1,215 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 HiSilicon Limited. */ +#ifndef HISI_ACC_QM_H +#define HISI_ACC_QM_H + +#include <linux/bitfield.h> +#include <linux/iopoll.h> +#include <linux/module.h> +#include <linux/pci.h> + +/* qm user domain */ +#define QM_ARUSER_M_CFG_1 0x100088 +#define AXUSER_SNOOP_ENABLE BIT(30) +#define AXUSER_CMD_TYPE GENMASK(14, 12) +#define AXUSER_CMD_SMMU_NORMAL 1 +#define AXUSER_NS BIT(6) +#define AXUSER_NO BIT(5) +#define AXUSER_FP BIT(4) +#define AXUSER_SSV BIT(0) +#define AXUSER_BASE (AXUSER_SNOOP_ENABLE | \ + FIELD_PREP(AXUSER_CMD_TYPE, \ + AXUSER_CMD_SMMU_NORMAL) | \ + AXUSER_NS | AXUSER_NO | AXUSER_FP) +#define QM_ARUSER_M_CFG_ENABLE 0x100090 +#define ARUSER_M_CFG_ENABLE 0xfffffffe +#define QM_AWUSER_M_CFG_1 0x100098 +#define QM_AWUSER_M_CFG_ENABLE 0x1000a0 +#define AWUSER_M_CFG_ENABLE 0xfffffffe +#define QM_WUSER_M_CFG_ENABLE 0x1000a8 +#define WUSER_M_CFG_ENABLE 0xffffffff + +/* qm cache */ +#define QM_CACHE_CTL 0x100050 +#define SQC_CACHE_ENABLE BIT(0) +#define CQC_CACHE_ENABLE BIT(1) +#define SQC_CACHE_WB_ENABLE BIT(4) +#define SQC_CACHE_WB_THRD GENMASK(10, 5) +#define CQC_CACHE_WB_ENABLE BIT(11) +#define CQC_CACHE_WB_THRD GENMASK(17, 12) +#define QM_AXI_M_CFG 0x1000ac +#define AXI_M_CFG 0xffff +#define QM_AXI_M_CFG_ENABLE 0x1000b0 +#define AXI_M_CFG_ENABLE 0xffffffff +#define QM_PEH_AXUSER_CFG 0x1000cc +#define QM_PEH_AXUSER_CFG_ENABLE 0x1000d0 +#define PEH_AXUSER_CFG 0x401001 +#define PEH_AXUSER_CFG_ENABLE 0xffffffff + +#define QM_DFX_MB_CNT_VF 0x104010 +#define QM_DFX_DB_CNT_VF 0x104020 +#define QM_DFX_SQE_CNT_VF_SQN 0x104030 +#define QM_DFX_CQE_CNT_VF_CQN 0x104040 +#define QM_DFX_QN_SHIFT 16 +#define CURRENT_FUN_MASK GENMASK(5, 0) +#define CURRENT_Q_MASK GENMASK(31, 16) + +#define QM_AXI_RRESP BIT(0) +#define QM_AXI_BRESP BIT(1) +#define QM_ECC_MBIT BIT(2) +#define QM_ECC_1BIT BIT(3) +#define QM_ACC_GET_TASK_TIMEOUT BIT(4) +#define QM_ACC_DO_TASK_TIMEOUT BIT(5) +#define QM_ACC_WB_NOT_READY_TIMEOUT BIT(6) +#define QM_SQ_CQ_VF_INVALID BIT(7) +#define QM_CQ_VF_INVALID BIT(8) +#define QM_SQ_VF_INVALID BIT(9) +#define QM_DB_TIMEOUT BIT(10) +#define QM_OF_FIFO_OF BIT(11) +#define QM_DB_RANDOM_INVALID BIT(12) + +#define QM_BASE_NFE (QM_AXI_RRESP | QM_AXI_BRESP | QM_ECC_MBIT | \ + QM_ACC_GET_TASK_TIMEOUT | QM_DB_TIMEOUT | \ + QM_OF_FIFO_OF) +#define QM_BASE_CE QM_ECC_1BIT + +#define QM_Q_DEPTH 1024 + +enum qp_state { + QP_STOP, +}; + +enum qm_hw_ver { + QM_HW_UNKNOWN = -1, + QM_HW_V1 = 0x20, + QM_HW_V2 = 0x21, +}; + +enum qm_fun_type { + QM_HW_PF, + QM_HW_VF, +}; + +enum qm_debug_file { + CURRENT_Q, + CLEAR_ENABLE, + DEBUG_FILE_NUM, +}; + +struct debugfs_file { + enum qm_debug_file index; + struct mutex lock; + struct qm_debug *debug; +}; + +struct qm_debug { + u32 curr_qm_qp_num; + struct dentry *debug_root; + struct dentry *qm_d; + struct debugfs_file files[DEBUG_FILE_NUM]; +}; + +struct qm_dma { + void *va; + dma_addr_t dma; + size_t size; +}; + +struct hisi_qm_status { + u32 eq_head; + bool eqc_phase; + u32 aeq_head; + bool aeqc_phase; + unsigned long flags; +}; + +struct hisi_qm { + enum qm_hw_ver ver; + enum qm_fun_type fun_type; + const char *dev_name; + struct pci_dev *pdev; + void __iomem *io_base; + u32 sqe_size; + u32 qp_base; + u32 qp_num; + u32 ctrl_qp_num; + + struct qm_dma qdma; + struct qm_sqc *sqc; + struct qm_cqc *cqc; + struct qm_eqe *eqe; + struct qm_aeqe *aeqe; + dma_addr_t sqc_dma; + dma_addr_t cqc_dma; + dma_addr_t eqe_dma; + dma_addr_t aeqe_dma; + + struct hisi_qm_status status; + + rwlock_t qps_lock; + unsigned long *qp_bitmap; + struct hisi_qp **qp_array; + + struct mutex mailbox_lock; + + const struct hisi_qm_hw_ops *ops; + + struct qm_debug debug; + + u32 error_mask; + u32 msi_mask; + + bool use_dma_api; +}; + +struct hisi_qp_status { + atomic_t used; + u16 sq_tail; + u16 cq_head; + bool cqc_phase; + unsigned long flags; +}; + +struct hisi_qp_ops { + int (*fill_sqe)(void *sqe, void *q_parm, void *d_parm); +}; + +struct hisi_qp { + u32 qp_id; + u8 alg_type; + u8 req_type; + + struct qm_dma qdma; + void *sqe; + struct qm_cqe *cqe; + dma_addr_t sqe_dma; + dma_addr_t cqe_dma; + + struct hisi_qp_status qp_status; + struct hisi_qp_ops *hw_ops; + void *qp_ctx; + void (*req_cb)(struct hisi_qp *qp, void *data); + struct work_struct work; + struct workqueue_struct *wq; + + struct hisi_qm *qm; +}; + +int hisi_qm_init(struct hisi_qm *qm); +void hisi_qm_uninit(struct hisi_qm *qm); +int hisi_qm_start(struct hisi_qm *qm); +int hisi_qm_stop(struct hisi_qm *qm); +struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type); +int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg); +int hisi_qm_stop_qp(struct hisi_qp *qp); +void hisi_qm_release_qp(struct hisi_qp *qp); +int hisi_qp_send(struct hisi_qp *qp, const void *msg); +int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number); +int hisi_qm_set_vft(struct hisi_qm *qm, u32 fun_num, u32 base, u32 number); +int hisi_qm_debug_init(struct hisi_qm *qm); +void hisi_qm_hw_error_init(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe, + u32 msi); +int hisi_qm_hw_error_handle(struct hisi_qm *qm); +enum qm_hw_ver hisi_qm_get_hw_version(struct pci_dev *pdev); +void hisi_qm_debug_regs_clear(struct hisi_qm *qm); +#endif diff --git a/drivers/crypto/hisilicon/sec/sec_algs.c b/drivers/crypto/hisilicon/sec/sec_algs.c index 02768af0dccd..e0508ea160f1 100644 --- a/drivers/crypto/hisilicon/sec/sec_algs.c +++ b/drivers/crypto/hisilicon/sec/sec_algs.c @@ -9,7 +9,7 @@ #include <crypto/aes.h> #include <crypto/algapi.h> -#include <crypto/des.h> +#include <crypto/internal/des.h> #include <crypto/skcipher.h> #include <crypto/xts.h> #include <crypto/internal/skcipher.h> @@ -347,25 +347,21 @@ static int sec_alg_skcipher_setkey_aes_xts(struct crypto_skcipher *tfm, static int sec_alg_skcipher_setkey_des_ecb(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { - if (keylen != DES_KEY_SIZE) - return -EINVAL; - - return sec_alg_skcipher_setkey(tfm, key, keylen, SEC_C_DES_ECB_64); + return verify_skcipher_des_key(tfm, key) ?: + sec_alg_skcipher_setkey(tfm, key, keylen, SEC_C_DES_ECB_64); } static int sec_alg_skcipher_setkey_des_cbc(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { - if (keylen != DES_KEY_SIZE) - return -EINVAL; - - return sec_alg_skcipher_setkey(tfm, key, keylen, SEC_C_DES_CBC_64); + return verify_skcipher_des_key(tfm, key) ?: + sec_alg_skcipher_setkey(tfm, key, keylen, SEC_C_DES_CBC_64); } static int sec_alg_skcipher_setkey_3des_ecb(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { - return unlikely(des3_verify_key(tfm, key)) ?: + return verify_skcipher_des3_key(tfm, key) ?: sec_alg_skcipher_setkey(tfm, key, keylen, SEC_C_3DES_ECB_192_3KEY); } @@ -373,7 +369,7 @@ static int sec_alg_skcipher_setkey_3des_ecb(struct crypto_skcipher *tfm, static int sec_alg_skcipher_setkey_3des_cbc(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { - return unlikely(des3_verify_key(tfm, key)) ?: + return verify_skcipher_des3_key(tfm, key) ?: sec_alg_skcipher_setkey(tfm, key, keylen, SEC_C_3DES_CBC_192_3KEY); } diff --git a/drivers/crypto/hisilicon/sgl.c b/drivers/crypto/hisilicon/sgl.c new file mode 100644 index 000000000000..e083d172b618 --- /dev/null +++ b/drivers/crypto/hisilicon/sgl.c @@ -0,0 +1,214 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 HiSilicon Limited. */ +#include <linux/dma-mapping.h> +#include <linux/module.h> +#include "./sgl.h" + +#define HISI_ACC_SGL_SGE_NR_MIN 1 +#define HISI_ACC_SGL_SGE_NR_MAX 255 +#define HISI_ACC_SGL_SGE_NR_DEF 10 +#define HISI_ACC_SGL_NR_MAX 256 +#define HISI_ACC_SGL_ALIGN_SIZE 64 + +static int acc_sgl_sge_set(const char *val, const struct kernel_param *kp) +{ + int ret; + u32 n; + + if (!val) + return -EINVAL; + + ret = kstrtou32(val, 10, &n); + if (ret != 0 || n > HISI_ACC_SGL_SGE_NR_MAX || n == 0) + return -EINVAL; + + return param_set_int(val, kp); +} + +static const struct kernel_param_ops acc_sgl_sge_ops = { + .set = acc_sgl_sge_set, + .get = param_get_int, +}; + +static u32 acc_sgl_sge_nr = HISI_ACC_SGL_SGE_NR_DEF; +module_param_cb(acc_sgl_sge_nr, &acc_sgl_sge_ops, &acc_sgl_sge_nr, 0444); +MODULE_PARM_DESC(acc_sgl_sge_nr, "Number of sge in sgl(1-255)"); + +struct acc_hw_sge { + dma_addr_t buf; + void *page_ctrl; + __le32 len; + __le32 pad; + __le32 pad0; + __le32 pad1; +}; + +/* use default sgl head size 64B */ +struct hisi_acc_hw_sgl { + dma_addr_t next_dma; + __le16 entry_sum_in_chain; + __le16 entry_sum_in_sgl; + __le16 entry_length_in_sgl; + __le16 pad0; + __le64 pad1[5]; + struct hisi_acc_hw_sgl *next; + struct acc_hw_sge sge_entries[]; +} __aligned(1); + +/** + * hisi_acc_create_sgl_pool() - Create a hw sgl pool. + * @dev: The device which hw sgl pool belongs to. + * @pool: Pointer of pool. + * @count: Count of hisi_acc_hw_sgl in pool. + * + * This function creates a hw sgl pool, after this user can get hw sgl memory + * from it. + */ +int hisi_acc_create_sgl_pool(struct device *dev, + struct hisi_acc_sgl_pool *pool, u32 count) +{ + u32 sgl_size; + u32 size; + + if (!dev || !pool || !count) + return -EINVAL; + + sgl_size = sizeof(struct acc_hw_sge) * acc_sgl_sge_nr + + sizeof(struct hisi_acc_hw_sgl); + size = sgl_size * count; + + pool->sgl = dma_alloc_coherent(dev, size, &pool->sgl_dma, GFP_KERNEL); + if (!pool->sgl) + return -ENOMEM; + + pool->size = size; + pool->count = count; + pool->sgl_size = sgl_size; + + return 0; +} +EXPORT_SYMBOL_GPL(hisi_acc_create_sgl_pool); + +/** + * hisi_acc_free_sgl_pool() - Free a hw sgl pool. + * @dev: The device which hw sgl pool belongs to. + * @pool: Pointer of pool. + * + * This function frees memory of a hw sgl pool. + */ +void hisi_acc_free_sgl_pool(struct device *dev, struct hisi_acc_sgl_pool *pool) +{ + dma_free_coherent(dev, pool->size, pool->sgl, pool->sgl_dma); + memset(pool, 0, sizeof(struct hisi_acc_sgl_pool)); +} +EXPORT_SYMBOL_GPL(hisi_acc_free_sgl_pool); + +struct hisi_acc_hw_sgl *acc_get_sgl(struct hisi_acc_sgl_pool *pool, u32 index, + dma_addr_t *hw_sgl_dma) +{ + if (!pool || !hw_sgl_dma || index >= pool->count || !pool->sgl) + return ERR_PTR(-EINVAL); + + *hw_sgl_dma = pool->sgl_dma + pool->sgl_size * index; + return (void *)pool->sgl + pool->sgl_size * index; +} + +void acc_put_sgl(struct hisi_acc_sgl_pool *pool, u32 index) {} + +static void sg_map_to_hw_sg(struct scatterlist *sgl, + struct acc_hw_sge *hw_sge) +{ + hw_sge->buf = sgl->dma_address; + hw_sge->len = sgl->dma_length; +} + +static void inc_hw_sgl_sge(struct hisi_acc_hw_sgl *hw_sgl) +{ + hw_sgl->entry_sum_in_sgl++; +} + +static void update_hw_sgl_sum_sge(struct hisi_acc_hw_sgl *hw_sgl, u16 sum) +{ + hw_sgl->entry_sum_in_chain = sum; +} + +/** + * hisi_acc_sg_buf_map_to_hw_sgl - Map a scatterlist to a hw sgl. + * @dev: The device which hw sgl belongs to. + * @sgl: Scatterlist which will be mapped to hw sgl. + * @pool: Pool which hw sgl memory will be allocated in. + * @index: Index of hisi_acc_hw_sgl in pool. + * @hw_sgl_dma: The dma address of allocated hw sgl. + * + * This function builds hw sgl according input sgl, user can use hw_sgl_dma + * as src/dst in its BD. Only support single hw sgl currently. + */ +struct hisi_acc_hw_sgl * +hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev, + struct scatterlist *sgl, + struct hisi_acc_sgl_pool *pool, + u32 index, dma_addr_t *hw_sgl_dma) +{ + struct hisi_acc_hw_sgl *curr_hw_sgl; + dma_addr_t curr_sgl_dma = 0; + struct acc_hw_sge *curr_hw_sge; + struct scatterlist *sg; + int sg_n = sg_nents(sgl); + int i, ret; + + if (!dev || !sgl || !pool || !hw_sgl_dma || sg_n > acc_sgl_sge_nr) + return ERR_PTR(-EINVAL); + + ret = dma_map_sg(dev, sgl, sg_n, DMA_BIDIRECTIONAL); + if (!ret) + return ERR_PTR(-EINVAL); + + curr_hw_sgl = acc_get_sgl(pool, index, &curr_sgl_dma); + if (!curr_hw_sgl) { + ret = -ENOMEM; + goto err_unmap_sg; + } + curr_hw_sgl->entry_length_in_sgl = acc_sgl_sge_nr; + curr_hw_sge = curr_hw_sgl->sge_entries; + + for_each_sg(sgl, sg, sg_n, i) { + sg_map_to_hw_sg(sg, curr_hw_sge); + inc_hw_sgl_sge(curr_hw_sgl); + curr_hw_sge++; + } + + update_hw_sgl_sum_sge(curr_hw_sgl, acc_sgl_sge_nr); + *hw_sgl_dma = curr_sgl_dma; + + return curr_hw_sgl; + +err_unmap_sg: + dma_unmap_sg(dev, sgl, sg_n, DMA_BIDIRECTIONAL); + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(hisi_acc_sg_buf_map_to_hw_sgl); + +/** + * hisi_acc_sg_buf_unmap() - Unmap allocated hw sgl. + * @dev: The device which hw sgl belongs to. + * @sgl: Related scatterlist. + * @hw_sgl: Virtual address of hw sgl. + * @hw_sgl_dma: DMA address of hw sgl. + * @pool: Pool which hw sgl is allocated in. + * + * This function unmaps allocated hw sgl. + */ +void hisi_acc_sg_buf_unmap(struct device *dev, struct scatterlist *sgl, + struct hisi_acc_hw_sgl *hw_sgl) +{ + dma_unmap_sg(dev, sgl, sg_nents(sgl), DMA_BIDIRECTIONAL); + + hw_sgl->entry_sum_in_chain = 0; + hw_sgl->entry_sum_in_sgl = 0; + hw_sgl->entry_length_in_sgl = 0; +} +EXPORT_SYMBOL_GPL(hisi_acc_sg_buf_unmap); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Zhou Wang <wangzhou1@hisilicon.com>"); +MODULE_DESCRIPTION("HiSilicon Accelerator SGL support"); diff --git a/drivers/crypto/hisilicon/sgl.h b/drivers/crypto/hisilicon/sgl.h new file mode 100644 index 000000000000..3ac8871c7acf --- /dev/null +++ b/drivers/crypto/hisilicon/sgl.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 HiSilicon Limited. */ +#ifndef HISI_ACC_SGL_H +#define HISI_ACC_SGL_H + +struct hisi_acc_sgl_pool { + struct hisi_acc_hw_sgl *sgl; + dma_addr_t sgl_dma; + size_t size; + u32 count; + size_t sgl_size; +}; + +struct hisi_acc_hw_sgl * +hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev, + struct scatterlist *sgl, + struct hisi_acc_sgl_pool *pool, + u32 index, dma_addr_t *hw_sgl_dma); +void hisi_acc_sg_buf_unmap(struct device *dev, struct scatterlist *sgl, + struct hisi_acc_hw_sgl *hw_sgl); +int hisi_acc_create_sgl_pool(struct device *dev, struct hisi_acc_sgl_pool *pool, + u32 count); +void hisi_acc_free_sgl_pool(struct device *dev, struct hisi_acc_sgl_pool *pool); +#endif 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..ffb00d987d02 --- /dev/null +++ b/drivers/crypto/hisilicon/zip/zip.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 HiSilicon Limited. */ +#ifndef HISI_ZIP_H +#define HISI_ZIP_H + +#undef pr_fmt +#define pr_fmt(fmt) "hisi_zip: " fmt + +#include <linux/list.h> +#include "../qm.h" +#include "../sgl.h" + +/* hisi_zip_sqe dw3 */ +#define HZIP_BD_STATUS_M GENMASK(7, 0) +/* hisi_zip_sqe dw9 */ +#define HZIP_REQ_TYPE_M GENMASK(7, 0) +#define HZIP_ALG_TYPE_ZLIB 0x02 +#define HZIP_ALG_TYPE_GZIP 0x03 +#define HZIP_BUF_TYPE_M GENMASK(11, 8) +#define HZIP_PBUFFER 0x0 +#define HZIP_SGL 0x1 + +enum hisi_zip_error_type { + /* negative compression */ + HZIP_NC_ERR = 0x0d, +}; + +struct hisi_zip_ctrl; + +struct hisi_zip { + struct hisi_qm qm; + struct list_head list; + struct hisi_zip_ctrl *ctrl; +}; + +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]; +}; + +struct hisi_zip *find_zip_device(int node); +int hisi_zip_register_to_crypto(void); +void hisi_zip_unregister_from_crypto(void); +#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..5a3f84dcdcde --- /dev/null +++ b/drivers/crypto/hisilicon/zip/zip_crypto.c @@ -0,0 +1,653 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 HiSilicon Limited. */ +#include <crypto/internal/acompress.h> +#include <linux/bitfield.h> +#include <linux/dma-mapping.h> +#include <linux/scatterlist.h> +#include "zip.h" + +#define HZIP_ZLIB_HEAD_SIZE 2 +#define HZIP_GZIP_HEAD_SIZE 10 + +#define GZIP_HEAD_FHCRC_BIT BIT(1) +#define GZIP_HEAD_FEXTRA_BIT BIT(2) +#define GZIP_HEAD_FNAME_BIT BIT(3) +#define GZIP_HEAD_FCOMMENT_BIT BIT(4) + +#define GZIP_HEAD_FLG_SHIFT 3 +#define GZIP_HEAD_FEXTRA_SHIFT 10 +#define GZIP_HEAD_FEXTRA_XLEN 2 +#define GZIP_HEAD_FHCRC_SIZE 2 + +#define HZIP_CTX_Q_NUM 2 +#define HZIP_GZIP_HEAD_BUF 256 +#define HZIP_ALG_PRIORITY 300 + +static const u8 zlib_head[HZIP_ZLIB_HEAD_SIZE] = {0x78, 0x9c}; +static const u8 gzip_head[HZIP_GZIP_HEAD_SIZE] = {0x1f, 0x8b, 0x08, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, 0x03}; +enum hisi_zip_alg_type { + HZIP_ALG_TYPE_COMP = 0, + HZIP_ALG_TYPE_DECOMP = 1, +}; + +#define COMP_NAME_TO_TYPE(alg_name) \ + (!strcmp((alg_name), "zlib-deflate") ? HZIP_ALG_TYPE_ZLIB : \ + !strcmp((alg_name), "gzip") ? HZIP_ALG_TYPE_GZIP : 0) \ + +#define TO_HEAD_SIZE(req_type) \ + (((req_type) == HZIP_ALG_TYPE_ZLIB) ? sizeof(zlib_head) : \ + ((req_type) == HZIP_ALG_TYPE_GZIP) ? sizeof(gzip_head) : 0) \ + +#define TO_HEAD(req_type) \ + (((req_type) == HZIP_ALG_TYPE_ZLIB) ? zlib_head : \ + ((req_type) == HZIP_ALG_TYPE_GZIP) ? gzip_head : 0) \ + +struct hisi_zip_req { + struct acomp_req *req; + struct scatterlist *src; + struct scatterlist *dst; + size_t slen; + size_t dlen; + struct hisi_acc_hw_sgl *hw_src; + struct hisi_acc_hw_sgl *hw_dst; + dma_addr_t dma_src; + dma_addr_t dma_dst; + int req_id; +}; + +struct hisi_zip_req_q { + struct hisi_zip_req *q; + unsigned long *req_bitmap; + rwlock_t req_lock; + u16 size; +}; + +struct hisi_zip_qp_ctx { + struct hisi_qp *qp; + struct hisi_zip_sqe zip_sqe; + struct hisi_zip_req_q req_q; + struct hisi_acc_sgl_pool sgl_pool; + struct hisi_zip *zip_dev; + struct hisi_zip_ctx *ctx; +}; + +struct hisi_zip_ctx { +#define QPC_COMP 0 +#define QPC_DECOMP 1 + struct hisi_zip_qp_ctx qp_ctx[HZIP_CTX_Q_NUM]; +}; + +static void hisi_zip_config_buf_type(struct hisi_zip_sqe *sqe, u8 buf_type) +{ + u32 val; + + val = (sqe->dw9) & ~HZIP_BUF_TYPE_M; + val |= FIELD_PREP(HZIP_BUF_TYPE_M, buf_type); + sqe->dw9 = val; +} + +static void hisi_zip_config_tag(struct hisi_zip_sqe *sqe, u32 tag) +{ + sqe->tag = tag; +} + +static void hisi_zip_fill_sqe(struct hisi_zip_sqe *sqe, u8 req_type, + dma_addr_t s_addr, dma_addr_t d_addr, u32 slen, + u32 dlen) +{ + memset(sqe, 0, sizeof(struct hisi_zip_sqe)); + + sqe->input_data_length = slen; + sqe->dw9 = FIELD_PREP(HZIP_REQ_TYPE_M, req_type); + sqe->dest_avail_out = dlen; + sqe->source_addr_l = lower_32_bits(s_addr); + sqe->source_addr_h = upper_32_bits(s_addr); + sqe->dest_addr_l = lower_32_bits(d_addr); + sqe->dest_addr_h = upper_32_bits(d_addr); +} + +static int hisi_zip_create_qp(struct hisi_qm *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->req_type = req_type; + qp->qp_ctx = ctx; + ctx->qp = qp; + + ret = hisi_qm_start_qp(qp, 0); + if (ret < 0) + goto err_release_qp; + + return 0; + +err_release_qp: + hisi_qm_release_qp(qp); + return ret; +} + +static void hisi_zip_release_qp(struct hisi_zip_qp_ctx *ctx) +{ + hisi_qm_stop_qp(ctx->qp); + hisi_qm_release_qp(ctx->qp); +} + +static int hisi_zip_ctx_init(struct hisi_zip_ctx *hisi_zip_ctx, u8 req_type) +{ + struct hisi_zip *hisi_zip; + struct hisi_qm *qm; + int ret, i, j; + + /* find the proper zip device */ + hisi_zip = find_zip_device(cpu_to_node(smp_processor_id())); + if (!hisi_zip) { + pr_err("Failed to find a proper ZIP device!\n"); + return -ENODEV; + } + qm = &hisi_zip->qm; + + for (i = 0; i < HZIP_CTX_Q_NUM; i++) { + /* alg_type = 0 for compress, 1 for decompress in hw sqe */ + ret = hisi_zip_create_qp(qm, &hisi_zip_ctx->qp_ctx[i], i, + req_type); + if (ret) + goto err; + + hisi_zip_ctx->qp_ctx[i].zip_dev = hisi_zip; + } + + 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_ctx_exit(struct hisi_zip_ctx *hisi_zip_ctx) +{ + int i; + + for (i = 1; i >= 0; i--) + hisi_zip_release_qp(&hisi_zip_ctx->qp_ctx[i]); +} + +static u16 get_extra_field_size(const u8 *start) +{ + return *((u16 *)start) + GZIP_HEAD_FEXTRA_XLEN; +} + +static u32 get_name_field_size(const u8 *start) +{ + return strlen(start) + 1; +} + +static u32 get_comment_field_size(const u8 *start) +{ + return strlen(start) + 1; +} + +static u32 __get_gzip_head_size(const u8 *src) +{ + u8 head_flg = *(src + GZIP_HEAD_FLG_SHIFT); + u32 size = GZIP_HEAD_FEXTRA_SHIFT; + + if (head_flg & GZIP_HEAD_FEXTRA_BIT) + size += get_extra_field_size(src + size); + if (head_flg & GZIP_HEAD_FNAME_BIT) + size += get_name_field_size(src + size); + if (head_flg & GZIP_HEAD_FCOMMENT_BIT) + size += get_comment_field_size(src + size); + if (head_flg & GZIP_HEAD_FHCRC_BIT) + size += GZIP_HEAD_FHCRC_SIZE; + + return size; +} + +static int hisi_zip_create_req_q(struct hisi_zip_ctx *ctx) +{ + struct hisi_zip_req_q *req_q; + int i, ret; + + for (i = 0; i < HZIP_CTX_Q_NUM; i++) { + req_q = &ctx->qp_ctx[i].req_q; + req_q->size = QM_Q_DEPTH; + + req_q->req_bitmap = kcalloc(BITS_TO_LONGS(req_q->size), + sizeof(long), GFP_KERNEL); + if (!req_q->req_bitmap) { + ret = -ENOMEM; + if (i == 0) + return ret; + + goto err_free_loop0; + } + rwlock_init(&req_q->req_lock); + + req_q->q = kcalloc(req_q->size, sizeof(struct hisi_zip_req), + GFP_KERNEL); + if (!req_q->q) { + ret = -ENOMEM; + if (i == 0) + goto err_free_bitmap; + else + goto err_free_loop1; + } + } + + return 0; + +err_free_loop1: + kfree(ctx->qp_ctx[QPC_DECOMP].req_q.req_bitmap); +err_free_loop0: + kfree(ctx->qp_ctx[QPC_COMP].req_q.q); +err_free_bitmap: + kfree(ctx->qp_ctx[QPC_COMP].req_q.req_bitmap); + return ret; +} + +static void hisi_zip_release_req_q(struct hisi_zip_ctx *ctx) +{ + int i; + + for (i = 0; i < HZIP_CTX_Q_NUM; i++) { + kfree(ctx->qp_ctx[i].req_q.q); + kfree(ctx->qp_ctx[i].req_q.req_bitmap); + } +} + +static int hisi_zip_create_sgl_pool(struct hisi_zip_ctx *ctx) +{ + struct hisi_zip_qp_ctx *tmp; + int i, ret; + + for (i = 0; i < HZIP_CTX_Q_NUM; i++) { + tmp = &ctx->qp_ctx[i]; + ret = hisi_acc_create_sgl_pool(&tmp->qp->qm->pdev->dev, + &tmp->sgl_pool, + QM_Q_DEPTH << 1); + if (ret < 0) { + if (i == 1) + goto err_free_sgl_pool0; + return -ENOMEM; + } + } + + return 0; + +err_free_sgl_pool0: + hisi_acc_free_sgl_pool(&ctx->qp_ctx[QPC_COMP].qp->qm->pdev->dev, + &ctx->qp_ctx[QPC_COMP].sgl_pool); + return -ENOMEM; +} + +static void hisi_zip_release_sgl_pool(struct hisi_zip_ctx *ctx) +{ + int i; + + for (i = 0; i < HZIP_CTX_Q_NUM; i++) + hisi_acc_free_sgl_pool(&ctx->qp_ctx[i].qp->qm->pdev->dev, + &ctx->qp_ctx[i].sgl_pool); +} + +static void hisi_zip_remove_req(struct hisi_zip_qp_ctx *qp_ctx, + struct hisi_zip_req *req) +{ + struct hisi_zip_req_q *req_q = &qp_ctx->req_q; + + if (qp_ctx->qp->alg_type == HZIP_ALG_TYPE_COMP) + kfree(req->dst); + else + kfree(req->src); + + write_lock(&req_q->req_lock); + clear_bit(req->req_id, req_q->req_bitmap); + memset(req, 0, sizeof(struct hisi_zip_req)); + write_unlock(&req_q->req_lock); +} + +static void hisi_zip_acomp_cb(struct hisi_qp *qp, void *data) +{ + struct hisi_zip_sqe *sqe = data; + struct hisi_zip_qp_ctx *qp_ctx = qp->qp_ctx; + struct hisi_zip_req_q *req_q = &qp_ctx->req_q; + struct hisi_zip_req *req = req_q->q + sqe->tag; + struct acomp_req *acomp_req = req->req; + struct device *dev = &qp->qm->pdev->dev; + u32 status, dlen, head_size; + int err = 0; + + status = sqe->dw3 & HZIP_BD_STATUS_M; + + if (status != 0 && status != HZIP_NC_ERR) { + dev_err(dev, "%scompress fail in qp%u: %u, output: %u\n", + (qp->alg_type == 0) ? "" : "de", qp->qp_id, status, + sqe->produced); + err = -EIO; + } + dlen = sqe->produced; + + hisi_acc_sg_buf_unmap(dev, req->src, req->hw_src); + hisi_acc_sg_buf_unmap(dev, req->dst, req->hw_dst); + + head_size = (qp->alg_type == 0) ? TO_HEAD_SIZE(qp->req_type) : 0; + acomp_req->dlen = dlen + head_size; + + if (acomp_req->base.complete) + acomp_request_complete(acomp_req, err); + + hisi_zip_remove_req(qp_ctx, req); +} + +static void hisi_zip_set_acomp_cb(struct hisi_zip_ctx *ctx, + void (*fn)(struct hisi_qp *, void *)) +{ + int i; + + for (i = 0; i < HZIP_CTX_Q_NUM; i++) + ctx->qp_ctx[i].qp->req_cb = fn; +} + +static int hisi_zip_acomp_init(struct crypto_acomp *tfm) +{ + const char *alg_name = crypto_tfm_alg_name(&tfm->base); + struct hisi_zip_ctx *ctx = crypto_tfm_ctx(&tfm->base); + int ret; + + ret = hisi_zip_ctx_init(ctx, COMP_NAME_TO_TYPE(alg_name)); + if (ret) + return ret; + + ret = hisi_zip_create_req_q(ctx); + if (ret) + goto err_ctx_exit; + + ret = hisi_zip_create_sgl_pool(ctx); + if (ret) + goto err_release_req_q; + + hisi_zip_set_acomp_cb(ctx, hisi_zip_acomp_cb); + + return 0; + +err_release_req_q: + hisi_zip_release_req_q(ctx); +err_ctx_exit: + hisi_zip_ctx_exit(ctx); + return ret; +} + +static void hisi_zip_acomp_exit(struct crypto_acomp *tfm) +{ + struct hisi_zip_ctx *ctx = crypto_tfm_ctx(&tfm->base); + + hisi_zip_set_acomp_cb(ctx, NULL); + hisi_zip_release_sgl_pool(ctx); + hisi_zip_release_req_q(ctx); + hisi_zip_ctx_exit(ctx); +} + +static int add_comp_head(struct scatterlist *dst, u8 req_type) +{ + int head_size = TO_HEAD_SIZE(req_type); + const u8 *head = TO_HEAD(req_type); + int ret; + + ret = sg_copy_from_buffer(dst, sg_nents(dst), head, head_size); + if (ret != head_size) + return -ENOMEM; + + return head_size; +} + +static size_t get_gzip_head_size(struct scatterlist *sgl) +{ + char buf[HZIP_GZIP_HEAD_BUF]; + + sg_copy_to_buffer(sgl, sg_nents(sgl), buf, sizeof(buf)); + + return __get_gzip_head_size(buf); +} + +static size_t get_comp_head_size(struct scatterlist *src, u8 req_type) +{ + switch (req_type) { + case HZIP_ALG_TYPE_ZLIB: + return TO_HEAD_SIZE(HZIP_ALG_TYPE_ZLIB); + case HZIP_ALG_TYPE_GZIP: + return get_gzip_head_size(src); + default: + pr_err("request type does not support!\n"); + return -EINVAL; + } +} + +static int get_sg_skip_bytes(struct scatterlist *sgl, size_t bytes, + size_t remains, struct scatterlist **out) +{ +#define SPLIT_NUM 2 + size_t split_sizes[SPLIT_NUM]; + int out_mapped_nents[SPLIT_NUM]; + + split_sizes[0] = bytes; + split_sizes[1] = remains; + + return sg_split(sgl, 0, 0, SPLIT_NUM, split_sizes, out, + out_mapped_nents, GFP_KERNEL); +} + +static struct hisi_zip_req *hisi_zip_create_req(struct acomp_req *req, + struct hisi_zip_qp_ctx *qp_ctx, + size_t head_size, bool is_comp) +{ + struct hisi_zip_req_q *req_q = &qp_ctx->req_q; + struct hisi_zip_req *q = req_q->q; + struct hisi_zip_req *req_cache; + struct scatterlist *out[2]; + struct scatterlist *sgl; + size_t len; + int ret, req_id; + + /* + * remove/add zlib/gzip head, as hardware operations do not include + * comp head. so split req->src to get sgl without heads in acomp, or + * add comp head to req->dst ahead of that hardware output compressed + * data in sgl splited from req->dst without comp head. + */ + if (is_comp) { + sgl = req->dst; + len = req->dlen - head_size; + } else { + sgl = req->src; + len = req->slen - head_size; + } + + ret = get_sg_skip_bytes(sgl, head_size, len, out); + if (ret) + return ERR_PTR(ret); + + /* sgl for comp head is useless, so free it now */ + kfree(out[0]); + + write_lock(&req_q->req_lock); + + req_id = find_first_zero_bit(req_q->req_bitmap, req_q->size); + if (req_id >= req_q->size) { + write_unlock(&req_q->req_lock); + dev_dbg(&qp_ctx->qp->qm->pdev->dev, "req cache is full!\n"); + kfree(out[1]); + return ERR_PTR(-EBUSY); + } + set_bit(req_id, req_q->req_bitmap); + + req_cache = q + req_id; + req_cache->req_id = req_id; + req_cache->req = req; + if (is_comp) { + req_cache->src = req->src; + req_cache->dst = out[1]; + req_cache->slen = req->slen; + req_cache->dlen = req->dlen - head_size; + } else { + req_cache->src = out[1]; + req_cache->dst = req->dst; + req_cache->slen = req->slen - head_size; + req_cache->dlen = req->dlen; + } + + write_unlock(&req_q->req_lock); + + return req_cache; +} + +static int hisi_zip_do_work(struct hisi_zip_req *req, + struct hisi_zip_qp_ctx *qp_ctx) +{ + struct hisi_zip_sqe *zip_sqe = &qp_ctx->zip_sqe; + struct hisi_qp *qp = qp_ctx->qp; + struct device *dev = &qp->qm->pdev->dev; + struct hisi_acc_sgl_pool *pool = &qp_ctx->sgl_pool; + dma_addr_t input; + dma_addr_t output; + int ret; + + if (!req->src || !req->slen || !req->dst || !req->dlen) + return -EINVAL; + + req->hw_src = hisi_acc_sg_buf_map_to_hw_sgl(dev, req->src, pool, + req->req_id << 1, &input); + if (IS_ERR(req->hw_src)) + return PTR_ERR(req->hw_src); + req->dma_src = input; + + req->hw_dst = hisi_acc_sg_buf_map_to_hw_sgl(dev, req->dst, pool, + (req->req_id << 1) + 1, + &output); + if (IS_ERR(req->hw_dst)) { + ret = PTR_ERR(req->hw_dst); + goto err_unmap_input; + } + req->dma_dst = output; + + hisi_zip_fill_sqe(zip_sqe, qp->req_type, input, output, req->slen, + req->dlen); + hisi_zip_config_buf_type(zip_sqe, HZIP_SGL); + hisi_zip_config_tag(zip_sqe, req->req_id); + + /* send command to start a task */ + ret = hisi_qp_send(qp, zip_sqe); + if (ret < 0) + goto err_unmap_output; + + return -EINPROGRESS; + +err_unmap_output: + hisi_acc_sg_buf_unmap(dev, req->dst, req->hw_dst); +err_unmap_input: + hisi_acc_sg_buf_unmap(dev, req->src, req->hw_src); + return ret; +} + +static int hisi_zip_acompress(struct acomp_req *acomp_req) +{ + struct hisi_zip_ctx *ctx = crypto_tfm_ctx(acomp_req->base.tfm); + struct hisi_zip_qp_ctx *qp_ctx = &ctx->qp_ctx[QPC_COMP]; + struct hisi_zip_req *req; + size_t head_size; + int ret; + + /* let's output compression head now */ + head_size = add_comp_head(acomp_req->dst, qp_ctx->qp->req_type); + if (head_size < 0) + return -ENOMEM; + + req = hisi_zip_create_req(acomp_req, qp_ctx, head_size, true); + if (IS_ERR(req)) + return PTR_ERR(req); + + ret = hisi_zip_do_work(req, qp_ctx); + if (ret != -EINPROGRESS) + hisi_zip_remove_req(qp_ctx, req); + + return ret; +} + +static int hisi_zip_adecompress(struct acomp_req *acomp_req) +{ + struct hisi_zip_ctx *ctx = crypto_tfm_ctx(acomp_req->base.tfm); + struct hisi_zip_qp_ctx *qp_ctx = &ctx->qp_ctx[QPC_DECOMP]; + struct hisi_zip_req *req; + size_t head_size; + int ret; + + head_size = get_comp_head_size(acomp_req->src, qp_ctx->qp->req_type); + + req = hisi_zip_create_req(acomp_req, qp_ctx, head_size, false); + if (IS_ERR(req)) + return PTR_ERR(req); + + ret = hisi_zip_do_work(req, qp_ctx); + if (ret != -EINPROGRESS) + hisi_zip_remove_req(qp_ctx, req); + + return ret; +} + +static struct acomp_alg hisi_zip_acomp_zlib = { + .init = hisi_zip_acomp_init, + .exit = hisi_zip_acomp_exit, + .compress = hisi_zip_acompress, + .decompress = hisi_zip_adecompress, + .base = { + .cra_name = "zlib-deflate", + .cra_driver_name = "hisi-zlib-acomp", + .cra_module = THIS_MODULE, + .cra_priority = HZIP_ALG_PRIORITY, + .cra_ctxsize = sizeof(struct hisi_zip_ctx), + } +}; + +static struct acomp_alg hisi_zip_acomp_gzip = { + .init = hisi_zip_acomp_init, + .exit = hisi_zip_acomp_exit, + .compress = hisi_zip_acompress, + .decompress = hisi_zip_adecompress, + .base = { + .cra_name = "gzip", + .cra_driver_name = "hisi-gzip-acomp", + .cra_module = THIS_MODULE, + .cra_priority = HZIP_ALG_PRIORITY, + .cra_ctxsize = sizeof(struct hisi_zip_ctx), + } +}; + +int hisi_zip_register_to_crypto(void) +{ + int ret = 0; + + ret = crypto_register_acomp(&hisi_zip_acomp_zlib); + if (ret) { + pr_err("Zlib acomp algorithm registration failed\n"); + return ret; + } + + ret = crypto_register_acomp(&hisi_zip_acomp_gzip); + if (ret) { + pr_err("Gzip acomp algorithm registration failed\n"); + crypto_unregister_acomp(&hisi_zip_acomp_zlib); + } + + return ret; +} + +void hisi_zip_unregister_from_crypto(void) +{ + crypto_unregister_acomp(&hisi_zip_acomp_gzip); + crypto_unregister_acomp(&hisi_zip_acomp_zlib); +} diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c new file mode 100644 index 000000000000..6e0ca75585d4 --- /dev/null +++ b/drivers/crypto/hisilicon/zip/zip_main.c @@ -0,0 +1,1013 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 HiSilicon Limited. */ +#include <linux/acpi.h> +#include <linux/aer.h> +#include <linux/bitops.h> +#include <linux/debugfs.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/seq_file.h> +#include <linux/topology.h> +#include "zip.h" + +#define PCI_DEVICE_ID_ZIP_PF 0xa250 +#define PCI_DEVICE_ID_ZIP_VF 0xa251 + +#define HZIP_VF_NUM 63 +#define HZIP_QUEUE_NUM_V1 4096 +#define HZIP_QUEUE_NUM_V2 1024 + +#define HZIP_CLOCK_GATE_CTRL 0x301004 +#define COMP0_ENABLE BIT(0) +#define COMP1_ENABLE BIT(1) +#define DECOMP0_ENABLE BIT(2) +#define DECOMP1_ENABLE BIT(3) +#define DECOMP2_ENABLE BIT(4) +#define DECOMP3_ENABLE BIT(5) +#define DECOMP4_ENABLE BIT(6) +#define DECOMP5_ENABLE BIT(7) +#define ALL_COMP_DECOMP_EN (COMP0_ENABLE | COMP1_ENABLE | \ + DECOMP0_ENABLE | DECOMP1_ENABLE | \ + DECOMP2_ENABLE | DECOMP3_ENABLE | \ + DECOMP4_ENABLE | DECOMP5_ENABLE) +#define DECOMP_CHECK_ENABLE BIT(16) +#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 CACHE_ALL_EN 0xffffffff + +#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 + +#define HZIP_QM_IDEL_STATUS 0x3040e4 + +#define HZIP_CORE_DEBUG_COMP_0 0x302000 +#define HZIP_CORE_DEBUG_COMP_1 0x303000 +#define HZIP_CORE_DEBUG_DECOMP_0 0x304000 +#define HZIP_CORE_DEBUG_DECOMP_1 0x305000 +#define HZIP_CORE_DEBUG_DECOMP_2 0x306000 +#define HZIP_CORE_DEBUG_DECOMP_3 0x307000 +#define HZIP_CORE_DEBUG_DECOMP_4 0x308000 +#define HZIP_CORE_DEBUG_DECOMP_5 0x309000 + +#define HZIP_CORE_INT_SOURCE 0x3010A0 +#define HZIP_CORE_INT_MASK 0x3010A4 +#define HZIP_CORE_INT_STATUS 0x3010AC +#define HZIP_CORE_INT_STATUS_M_ECC BIT(1) +#define HZIP_CORE_SRAM_ECC_ERR_INFO 0x301148 +#define SRAM_ECC_ERR_NUM_SHIFT 16 +#define SRAM_ECC_ERR_ADDR_SHIFT 24 +#define HZIP_CORE_INT_DISABLE 0x000007FF +#define HZIP_COMP_CORE_NUM 2 +#define HZIP_DECOMP_CORE_NUM 6 +#define HZIP_CORE_NUM (HZIP_COMP_CORE_NUM + \ + HZIP_DECOMP_CORE_NUM) +#define HZIP_SQE_SIZE 128 +#define HZIP_SQ_SIZE (HZIP_SQE_SIZE * QM_Q_DEPTH) +#define HZIP_PF_DEF_Q_NUM 64 +#define HZIP_PF_DEF_Q_BASE 0 + +#define HZIP_SOFT_CTRL_CNT_CLR_CE 0x301000 +#define SOFT_CTRL_CNT_CLR_CE_BIT BIT(0) + +#define HZIP_NUMA_DISTANCE 100 +#define HZIP_BUF_SIZE 22 + +static const char hisi_zip_name[] = "hisi_zip"; +static struct dentry *hzip_debugfs_root; +LIST_HEAD(hisi_zip_list); +DEFINE_MUTEX(hisi_zip_list_lock); + +#ifdef CONFIG_NUMA +static struct hisi_zip *find_zip_device_numa(int node) +{ + struct hisi_zip *zip = NULL; + struct hisi_zip *hisi_zip; + int min_distance = HZIP_NUMA_DISTANCE; + struct device *dev; + + 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) { + zip = hisi_zip; + min_distance = node_distance(dev->numa_node, node); + } + } + + return zip; +} +#endif + +struct hisi_zip *find_zip_device(int node) +{ + struct hisi_zip *zip = NULL; + + mutex_lock(&hisi_zip_list_lock); +#ifdef CONFIG_NUMA + zip = find_zip_device_numa(node); +#else + zip = list_first_entry(&hisi_zip_list, struct hisi_zip, list); +#endif + mutex_unlock(&hisi_zip_list_lock); + + return zip; +} + +struct hisi_zip_hw_error { + u32 int_msk; + const char *msg; +}; + +static const struct hisi_zip_hw_error zip_hw_error[] = { + { .int_msk = BIT(0), .msg = "zip_ecc_1bitt_err" }, + { .int_msk = BIT(1), .msg = "zip_ecc_2bit_err" }, + { .int_msk = BIT(2), .msg = "zip_axi_rresp_err" }, + { .int_msk = BIT(3), .msg = "zip_axi_bresp_err" }, + { .int_msk = BIT(4), .msg = "zip_src_addr_parse_err" }, + { .int_msk = BIT(5), .msg = "zip_dst_addr_parse_err" }, + { .int_msk = BIT(6), .msg = "zip_pre_in_addr_err" }, + { .int_msk = BIT(7), .msg = "zip_pre_in_data_err" }, + { .int_msk = BIT(8), .msg = "zip_com_inf_err" }, + { .int_msk = BIT(9), .msg = "zip_enc_inf_err" }, + { .int_msk = BIT(10), .msg = "zip_pre_out_err" }, + { /* sentinel */ } +}; + +enum ctrl_debug_file_index { + HZIP_CURRENT_QM, + HZIP_CLEAR_ENABLE, + HZIP_DEBUG_FILE_NUM, +}; + +static const char * const ctrl_debug_file_name[] = { + [HZIP_CURRENT_QM] = "current_qm", + [HZIP_CLEAR_ENABLE] = "clear_enable", +}; + +struct ctrl_debug_file { + enum ctrl_debug_file_index index; + spinlock_t lock; + struct hisi_zip_ctrl *ctrl; +}; + +/* + * One ZIP controller has one PF and multiple VFs, some global configurations + * which PF has need this structure. + * + * Just relevant for PF. + */ +struct hisi_zip_ctrl { + u32 num_vfs; + struct hisi_zip *hisi_zip; + struct dentry *debug_root; + struct ctrl_debug_file files[HZIP_DEBUG_FILE_NUM]; +}; + +enum { + HZIP_COMP_CORE0, + HZIP_COMP_CORE1, + HZIP_DECOMP_CORE0, + HZIP_DECOMP_CORE1, + HZIP_DECOMP_CORE2, + HZIP_DECOMP_CORE3, + HZIP_DECOMP_CORE4, + HZIP_DECOMP_CORE5, +}; + +static const u64 core_offsets[] = { + [HZIP_COMP_CORE0] = 0x302000, + [HZIP_COMP_CORE1] = 0x303000, + [HZIP_DECOMP_CORE0] = 0x304000, + [HZIP_DECOMP_CORE1] = 0x305000, + [HZIP_DECOMP_CORE2] = 0x306000, + [HZIP_DECOMP_CORE3] = 0x307000, + [HZIP_DECOMP_CORE4] = 0x308000, + [HZIP_DECOMP_CORE5] = 0x309000, +}; + +static struct debugfs_reg32 hzip_dfx_regs[] = { + {"HZIP_GET_BD_NUM ", 0x00ull}, + {"HZIP_GET_RIGHT_BD ", 0x04ull}, + {"HZIP_GET_ERROR_BD ", 0x08ull}, + {"HZIP_DONE_BD_NUM ", 0x0cull}, + {"HZIP_WORK_CYCLE ", 0x10ull}, + {"HZIP_IDLE_CYCLE ", 0x18ull}, + {"HZIP_MAX_DELAY ", 0x20ull}, + {"HZIP_MIN_DELAY ", 0x24ull}, + {"HZIP_AVG_DELAY ", 0x28ull}, + {"HZIP_MEM_VISIBLE_DATA ", 0x30ull}, + {"HZIP_MEM_VISIBLE_ADDR ", 0x34ull}, + {"HZIP_COMSUMED_BYTE ", 0x38ull}, + {"HZIP_PRODUCED_BYTE ", 0x40ull}, + {"HZIP_COMP_INF ", 0x70ull}, + {"HZIP_PRE_OUT ", 0x78ull}, + {"HZIP_BD_RD ", 0x7cull}, + {"HZIP_BD_WR ", 0x80ull}, + {"HZIP_GET_BD_AXI_ERR_NUM ", 0x84ull}, + {"HZIP_GET_BD_PARSE_ERR_NUM ", 0x88ull}, + {"HZIP_ADD_BD_AXI_ERR_NUM ", 0x8cull}, + {"HZIP_DECOMP_STF_RELOAD_CURR_ST ", 0x94ull}, + {"HZIP_DECOMP_LZ77_CURR_ST ", 0x9cull}, +}; + +static int pf_q_num_set(const char *val, const struct kernel_param *kp) +{ + struct pci_dev *pdev = pci_get_device(PCI_VENDOR_ID_HUAWEI, + PCI_DEVICE_ID_ZIP_PF, NULL); + u32 n, q_num; + u8 rev_id; + int ret; + + if (!val) + return -EINVAL; + + if (!pdev) { + q_num = min_t(u32, HZIP_QUEUE_NUM_V1, HZIP_QUEUE_NUM_V2); + pr_info("No device found currently, suppose queue number is %d\n", + q_num); + } else { + rev_id = pdev->revision; + switch (rev_id) { + case QM_HW_V1: + q_num = HZIP_QUEUE_NUM_V1; + break; + case QM_HW_V2: + q_num = HZIP_QUEUE_NUM_V2; + break; + default: + return -EINVAL; + } + } + + ret = kstrtou32(val, 10, &n); + if (ret != 0 || n > q_num || n == 0) + return -EINVAL; + + return param_set_int(val, kp); +} + +static const struct kernel_param_ops pf_q_num_ops = { + .set = pf_q_num_set, + .get = param_get_int, +}; + +static u32 pf_q_num = HZIP_PF_DEF_Q_NUM; +module_param_cb(pf_q_num, &pf_q_num_ops, &pf_q_num, 0444); +MODULE_PARM_DESC(pf_q_num, "Number of queues in PF(v1 1-4096, v2 1-1024)"); + +static int uacce_mode; +module_param(uacce_mode, int, 0); + +static const struct pci_device_id hisi_zip_dev_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_ZIP_PF) }, + { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_ZIP_VF) }, + { 0, } +}; +MODULE_DEVICE_TABLE(pci, hisi_zip_dev_ids); + +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) +{ + void __iomem *base = hisi_zip->qm.io_base; + + /* qm user domain */ + writel(AXUSER_BASE, base + QM_ARUSER_M_CFG_1); + writel(ARUSER_M_CFG_ENABLE, base + QM_ARUSER_M_CFG_ENABLE); + writel(AXUSER_BASE, base + QM_AWUSER_M_CFG_1); + writel(AWUSER_M_CFG_ENABLE, base + QM_AWUSER_M_CFG_ENABLE); + writel(WUSER_M_CFG_ENABLE, base + QM_WUSER_M_CFG_ENABLE); + + /* qm cache */ + writel(AXI_M_CFG, base + QM_AXI_M_CFG); + writel(AXI_M_CFG_ENABLE, base + QM_AXI_M_CFG_ENABLE); + /* disable FLR triggered by BME(bus master enable) */ + writel(PEH_AXUSER_CFG, base + QM_PEH_AXUSER_CFG); + writel(PEH_AXUSER_CFG_ENABLE, base + QM_PEH_AXUSER_CFG_ENABLE); + + /* cache */ + writel(CACHE_ALL_EN, base + HZIP_PORT_ARCA_CHE_0); + writel(CACHE_ALL_EN, base + HZIP_PORT_ARCA_CHE_1); + writel(CACHE_ALL_EN, base + HZIP_PORT_AWCA_CHE_0); + writel(CACHE_ALL_EN, base + HZIP_PORT_AWCA_CHE_1); + + /* user domain configurations */ + writel(AXUSER_BASE, base + HZIP_BD_RUSER_32_63); + writel(AXUSER_BASE, base + HZIP_SGL_RUSER_32_63); + writel(AXUSER_BASE, base + HZIP_BD_WUSER_32_63); + writel(AXUSER_BASE, base + HZIP_DATA_RUSER_32_63); + writel(AXUSER_BASE, base + HZIP_DATA_WUSER_32_63); + + /* let's open all compression/decompression cores */ + writel(DECOMP_CHECK_ENABLE | ALL_COMP_DECOMP_EN, + base + HZIP_CLOCK_GATE_CTRL); + + /* enable sqc writeback */ + writel(SQC_CACHE_ENABLE | CQC_CACHE_ENABLE | SQC_CACHE_WB_ENABLE | + CQC_CACHE_WB_ENABLE | FIELD_PREP(SQC_CACHE_WB_THRD, 1) | + FIELD_PREP(CQC_CACHE_WB_THRD, 1), base + QM_CACHE_CTL); +} + +static void hisi_zip_hw_error_set_state(struct hisi_zip *hisi_zip, bool state) +{ + struct hisi_qm *qm = &hisi_zip->qm; + + if (qm->ver == QM_HW_V1) { + writel(HZIP_CORE_INT_DISABLE, qm->io_base + HZIP_CORE_INT_MASK); + dev_info(&qm->pdev->dev, "ZIP v%d does not support hw error handle\n", + qm->ver); + return; + } + + if (state) { + /* clear ZIP hw error source if having */ + writel(HZIP_CORE_INT_DISABLE, hisi_zip->qm.io_base + + HZIP_CORE_INT_SOURCE); + /* enable ZIP hw error interrupts */ + writel(0, hisi_zip->qm.io_base + HZIP_CORE_INT_MASK); + } else { + /* disable ZIP hw error interrupts */ + writel(HZIP_CORE_INT_DISABLE, + hisi_zip->qm.io_base + HZIP_CORE_INT_MASK); + } +} + +static inline struct hisi_qm *file_to_qm(struct ctrl_debug_file *file) +{ + struct hisi_zip *hisi_zip = file->ctrl->hisi_zip; + + return &hisi_zip->qm; +} + +static u32 current_qm_read(struct ctrl_debug_file *file) +{ + struct hisi_qm *qm = file_to_qm(file); + + return readl(qm->io_base + QM_DFX_MB_CNT_VF); +} + +static int current_qm_write(struct ctrl_debug_file *file, u32 val) +{ + struct hisi_qm *qm = file_to_qm(file); + struct hisi_zip_ctrl *ctrl = file->ctrl; + u32 vfq_num; + u32 tmp; + + if (val > ctrl->num_vfs) + return -EINVAL; + + /* Calculate curr_qm_qp_num and store */ + if (val == 0) { + qm->debug.curr_qm_qp_num = qm->qp_num; + } else { + vfq_num = (qm->ctrl_qp_num - qm->qp_num) / ctrl->num_vfs; + if (val == ctrl->num_vfs) + qm->debug.curr_qm_qp_num = qm->ctrl_qp_num - + qm->qp_num - (ctrl->num_vfs - 1) * vfq_num; + else + qm->debug.curr_qm_qp_num = vfq_num; + } + + writel(val, qm->io_base + QM_DFX_MB_CNT_VF); + writel(val, qm->io_base + QM_DFX_DB_CNT_VF); + + tmp = val | + (readl(qm->io_base + QM_DFX_SQE_CNT_VF_SQN) & CURRENT_Q_MASK); + writel(tmp, qm->io_base + QM_DFX_SQE_CNT_VF_SQN); + + tmp = val | + (readl(qm->io_base + QM_DFX_CQE_CNT_VF_CQN) & CURRENT_Q_MASK); + writel(tmp, qm->io_base + QM_DFX_CQE_CNT_VF_CQN); + + return 0; +} + +static u32 clear_enable_read(struct ctrl_debug_file *file) +{ + struct hisi_qm *qm = file_to_qm(file); + + return readl(qm->io_base + HZIP_SOFT_CTRL_CNT_CLR_CE) & + SOFT_CTRL_CNT_CLR_CE_BIT; +} + +static int clear_enable_write(struct ctrl_debug_file *file, u32 val) +{ + struct hisi_qm *qm = file_to_qm(file); + u32 tmp; + + if (val != 1 && val != 0) + return -EINVAL; + + tmp = (readl(qm->io_base + HZIP_SOFT_CTRL_CNT_CLR_CE) & + ~SOFT_CTRL_CNT_CLR_CE_BIT) | val; + writel(tmp, qm->io_base + HZIP_SOFT_CTRL_CNT_CLR_CE); + + return 0; +} + +static ssize_t ctrl_debug_read(struct file *filp, char __user *buf, + size_t count, loff_t *pos) +{ + struct ctrl_debug_file *file = filp->private_data; + char tbuf[HZIP_BUF_SIZE]; + u32 val; + int ret; + + spin_lock_irq(&file->lock); + switch (file->index) { + case HZIP_CURRENT_QM: + val = current_qm_read(file); + break; + case HZIP_CLEAR_ENABLE: + val = clear_enable_read(file); + break; + default: + spin_unlock_irq(&file->lock); + return -EINVAL; + } + spin_unlock_irq(&file->lock); + ret = sprintf(tbuf, "%u\n", val); + return simple_read_from_buffer(buf, count, pos, tbuf, ret); +} + +static ssize_t ctrl_debug_write(struct file *filp, const char __user *buf, + size_t count, loff_t *pos) +{ + struct ctrl_debug_file *file = filp->private_data; + char tbuf[HZIP_BUF_SIZE]; + unsigned long val; + int len, ret; + + if (*pos != 0) + return 0; + + if (count >= HZIP_BUF_SIZE) + return -ENOSPC; + + len = simple_write_to_buffer(tbuf, HZIP_BUF_SIZE - 1, pos, buf, count); + if (len < 0) + return len; + + tbuf[len] = '\0'; + if (kstrtoul(tbuf, 0, &val)) + return -EFAULT; + + spin_lock_irq(&file->lock); + switch (file->index) { + case HZIP_CURRENT_QM: + ret = current_qm_write(file, val); + if (ret) + goto err_input; + break; + case HZIP_CLEAR_ENABLE: + ret = clear_enable_write(file, val); + if (ret) + goto err_input; + break; + default: + ret = -EINVAL; + goto err_input; + } + spin_unlock_irq(&file->lock); + + return count; + +err_input: + spin_unlock_irq(&file->lock); + return ret; +} + +static const struct file_operations ctrl_debug_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = ctrl_debug_read, + .write = ctrl_debug_write, +}; + +static int hisi_zip_core_debug_init(struct hisi_zip_ctrl *ctrl) +{ + struct hisi_zip *hisi_zip = ctrl->hisi_zip; + struct hisi_qm *qm = &hisi_zip->qm; + struct device *dev = &qm->pdev->dev; + struct debugfs_regset32 *regset; + struct dentry *tmp_d, *tmp; + char buf[HZIP_BUF_SIZE]; + int i; + + for (i = 0; i < HZIP_CORE_NUM; i++) { + if (i < HZIP_COMP_CORE_NUM) + sprintf(buf, "comp_core%d", i); + else + sprintf(buf, "decomp_core%d", i - HZIP_COMP_CORE_NUM); + + tmp_d = debugfs_create_dir(buf, ctrl->debug_root); + if (!tmp_d) + return -ENOENT; + + regset = devm_kzalloc(dev, sizeof(*regset), GFP_KERNEL); + if (!regset) + return -ENOENT; + + regset->regs = hzip_dfx_regs; + regset->nregs = ARRAY_SIZE(hzip_dfx_regs); + regset->base = qm->io_base + core_offsets[i]; + + tmp = debugfs_create_regset32("regs", 0444, tmp_d, regset); + if (!tmp) + return -ENOENT; + } + + return 0; +} + +static int hisi_zip_ctrl_debug_init(struct hisi_zip_ctrl *ctrl) +{ + struct dentry *tmp; + int i; + + for (i = HZIP_CURRENT_QM; i < HZIP_DEBUG_FILE_NUM; i++) { + spin_lock_init(&ctrl->files[i].lock); + ctrl->files[i].ctrl = ctrl; + ctrl->files[i].index = i; + + tmp = debugfs_create_file(ctrl_debug_file_name[i], 0600, + ctrl->debug_root, ctrl->files + i, + &ctrl_debug_fops); + if (!tmp) + return -ENOENT; + } + + return hisi_zip_core_debug_init(ctrl); +} + +static int hisi_zip_debugfs_init(struct hisi_zip *hisi_zip) +{ + struct hisi_qm *qm = &hisi_zip->qm; + struct device *dev = &qm->pdev->dev; + struct dentry *dev_d; + int ret; + + dev_d = debugfs_create_dir(dev_name(dev), hzip_debugfs_root); + if (!dev_d) + return -ENOENT; + + qm->debug.debug_root = dev_d; + ret = hisi_qm_debug_init(qm); + if (ret) + goto failed_to_create; + + if (qm->fun_type == QM_HW_PF) { + hisi_zip->ctrl->debug_root = dev_d; + ret = hisi_zip_ctrl_debug_init(hisi_zip->ctrl); + if (ret) + goto failed_to_create; + } + + return 0; + +failed_to_create: + debugfs_remove_recursive(hzip_debugfs_root); + return ret; +} + +static void hisi_zip_debug_regs_clear(struct hisi_zip *hisi_zip) +{ + struct hisi_qm *qm = &hisi_zip->qm; + + writel(0x0, qm->io_base + QM_DFX_MB_CNT_VF); + writel(0x0, qm->io_base + QM_DFX_DB_CNT_VF); + writel(0x0, qm->io_base + HZIP_SOFT_CTRL_CNT_CLR_CE); + + hisi_qm_debug_regs_clear(qm); +} + +static void hisi_zip_debugfs_exit(struct hisi_zip *hisi_zip) +{ + struct hisi_qm *qm = &hisi_zip->qm; + + debugfs_remove_recursive(qm->debug.debug_root); + + if (qm->fun_type == QM_HW_PF) + hisi_zip_debug_regs_clear(hisi_zip); +} + +static void hisi_zip_hw_error_init(struct hisi_zip *hisi_zip) +{ + hisi_qm_hw_error_init(&hisi_zip->qm, QM_BASE_CE, + QM_BASE_NFE | QM_ACC_WB_NOT_READY_TIMEOUT, 0, + QM_DB_RANDOM_INVALID); + hisi_zip_hw_error_set_state(hisi_zip, true); +} + +static int hisi_zip_pf_probe_init(struct hisi_zip *hisi_zip) +{ + struct hisi_qm *qm = &hisi_zip->qm; + struct hisi_zip_ctrl *ctrl; + + ctrl = devm_kzalloc(&qm->pdev->dev, sizeof(*ctrl), GFP_KERNEL); + if (!ctrl) + return -ENOMEM; + + hisi_zip->ctrl = ctrl; + ctrl->hisi_zip = hisi_zip; + + switch (qm->ver) { + case QM_HW_V1: + qm->ctrl_qp_num = HZIP_QUEUE_NUM_V1; + break; + + case QM_HW_V2: + qm->ctrl_qp_num = HZIP_QUEUE_NUM_V2; + break; + + default: + return -EINVAL; + } + + hisi_zip_set_user_domain_and_cache(hisi_zip); + hisi_zip_hw_error_init(hisi_zip); + hisi_zip_debug_regs_clear(hisi_zip); + + return 0; +} + +static int hisi_zip_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct hisi_zip *hisi_zip; + enum qm_hw_ver rev_id; + struct hisi_qm *qm; + int ret; + + rev_id = hisi_qm_get_hw_version(pdev); + if (rev_id == QM_HW_UNKNOWN) + return -EINVAL; + + hisi_zip = devm_kzalloc(&pdev->dev, sizeof(*hisi_zip), GFP_KERNEL); + if (!hisi_zip) + return -ENOMEM; + pci_set_drvdata(pdev, hisi_zip); + + qm = &hisi_zip->qm; + qm->pdev = pdev; + qm->ver = rev_id; + + qm->sqe_size = HZIP_SQE_SIZE; + qm->dev_name = hisi_zip_name; + qm->fun_type = (pdev->device == PCI_DEVICE_ID_ZIP_PF) ? QM_HW_PF : + QM_HW_VF; + switch (uacce_mode) { + case 0: + qm->use_dma_api = true; + break; + case 1: + qm->use_dma_api = false; + break; + case 2: + qm->use_dma_api = true; + break; + default: + return -EINVAL; + } + + ret = hisi_qm_init(qm); + if (ret) { + dev_err(&pdev->dev, "Failed to init qm!\n"); + return ret; + } + + if (qm->fun_type == QM_HW_PF) { + ret = hisi_zip_pf_probe_init(hisi_zip); + if (ret) + return ret; + + qm->qp_base = HZIP_PF_DEF_Q_BASE; + qm->qp_num = pf_q_num; + } else if (qm->fun_type == QM_HW_VF) { + /* + * have no way to get qm configure in VM in v1 hardware, + * so currently force PF to uses HZIP_PF_DEF_Q_NUM, and force + * to trigger only one VF in v1 hardware. + * + * v2 hardware has no such problem. + */ + if (qm->ver == QM_HW_V1) { + qm->qp_base = HZIP_PF_DEF_Q_NUM; + qm->qp_num = HZIP_QUEUE_NUM_V1 - HZIP_PF_DEF_Q_NUM; + } else if (qm->ver == QM_HW_V2) + /* v2 starts to support get vft by mailbox */ + hisi_qm_get_vft(qm, &qm->qp_base, &qm->qp_num); + } + + ret = hisi_qm_start(qm); + if (ret) + goto err_qm_uninit; + + ret = hisi_zip_debugfs_init(hisi_zip); + if (ret) + dev_err(&pdev->dev, "Failed to init debugfs (%d)!\n", ret); + + hisi_zip_add_to_list(hisi_zip); + + return 0; + +err_qm_uninit: + hisi_qm_uninit(qm); + return ret; +} + +/* Currently we only support equal assignment */ +static int hisi_zip_vf_q_assign(struct hisi_zip *hisi_zip, int num_vfs) +{ + struct hisi_qm *qm = &hisi_zip->qm; + u32 qp_num = qm->qp_num; + u32 q_base = qp_num; + u32 q_num, remain_q_num, i; + int ret; + + if (!num_vfs) + return -EINVAL; + + remain_q_num = qm->ctrl_qp_num - qp_num; + if (remain_q_num < num_vfs) + return -EINVAL; + + q_num = remain_q_num / num_vfs; + for (i = 1; i <= num_vfs; i++) { + if (i == num_vfs) + q_num += remain_q_num % num_vfs; + ret = hisi_qm_set_vft(qm, i, q_base, q_num); + if (ret) + return ret; + q_base += q_num; + } + + return 0; +} + +static int hisi_zip_clear_vft_config(struct hisi_zip *hisi_zip) +{ + struct hisi_zip_ctrl *ctrl = hisi_zip->ctrl; + struct hisi_qm *qm = &hisi_zip->qm; + u32 i, num_vfs = ctrl->num_vfs; + int ret; + + for (i = 1; i <= num_vfs; i++) { + ret = hisi_qm_set_vft(qm, i, 0, 0); + if (ret) + return ret; + } + + ctrl->num_vfs = 0; + + return 0; +} + +static int hisi_zip_sriov_enable(struct pci_dev *pdev, int max_vfs) +{ +#ifdef CONFIG_PCI_IOV + struct hisi_zip *hisi_zip = pci_get_drvdata(pdev); + int pre_existing_vfs, num_vfs, ret; + + pre_existing_vfs = pci_num_vf(pdev); + + if (pre_existing_vfs) { + dev_err(&pdev->dev, + "Can't enable VF. Please disable pre-enabled VFs!\n"); + return 0; + } + + num_vfs = min_t(int, max_vfs, HZIP_VF_NUM); + + ret = hisi_zip_vf_q_assign(hisi_zip, num_vfs); + if (ret) { + dev_err(&pdev->dev, "Can't assign queues for VF!\n"); + return ret; + } + + hisi_zip->ctrl->num_vfs = num_vfs; + + ret = pci_enable_sriov(pdev, num_vfs); + if (ret) { + dev_err(&pdev->dev, "Can't enable VF!\n"); + hisi_zip_clear_vft_config(hisi_zip); + return ret; + } + + return num_vfs; +#else + return 0; +#endif +} + +static int hisi_zip_sriov_disable(struct pci_dev *pdev) +{ + struct hisi_zip *hisi_zip = pci_get_drvdata(pdev); + + if (pci_vfs_assigned(pdev)) { + dev_err(&pdev->dev, + "Can't disable VFs while VFs are assigned!\n"); + return -EPERM; + } + + /* remove in hisi_zip_pci_driver will be called to free VF resources */ + pci_disable_sriov(pdev); + + return hisi_zip_clear_vft_config(hisi_zip); +} + +static int hisi_zip_sriov_configure(struct pci_dev *pdev, int num_vfs) +{ + if (num_vfs == 0) + return hisi_zip_sriov_disable(pdev); + else + return hisi_zip_sriov_enable(pdev, num_vfs); +} + +static void hisi_zip_remove(struct pci_dev *pdev) +{ + struct hisi_zip *hisi_zip = pci_get_drvdata(pdev); + struct hisi_qm *qm = &hisi_zip->qm; + + if (qm->fun_type == QM_HW_PF && hisi_zip->ctrl->num_vfs != 0) + hisi_zip_sriov_disable(pdev); + + hisi_zip_debugfs_exit(hisi_zip); + hisi_qm_stop(qm); + + if (qm->fun_type == QM_HW_PF) + hisi_zip_hw_error_set_state(hisi_zip, false); + + hisi_qm_uninit(qm); + hisi_zip_remove_from_list(hisi_zip); +} + +static void hisi_zip_log_hw_error(struct hisi_zip *hisi_zip, u32 err_sts) +{ + const struct hisi_zip_hw_error *err = zip_hw_error; + struct device *dev = &hisi_zip->qm.pdev->dev; + u32 err_val; + + while (err->msg) { + if (err->int_msk & err_sts) { + dev_warn(dev, "%s [error status=0x%x] found\n", + err->msg, err->int_msk); + + if (HZIP_CORE_INT_STATUS_M_ECC & err->int_msk) { + err_val = readl(hisi_zip->qm.io_base + + HZIP_CORE_SRAM_ECC_ERR_INFO); + dev_warn(dev, "hisi-zip multi ecc sram num=0x%x\n", + ((err_val >> SRAM_ECC_ERR_NUM_SHIFT) & + 0xFF)); + dev_warn(dev, "hisi-zip multi ecc sram addr=0x%x\n", + (err_val >> SRAM_ECC_ERR_ADDR_SHIFT)); + } + } + err++; + } +} + +static pci_ers_result_t hisi_zip_hw_error_handle(struct hisi_zip *hisi_zip) +{ + u32 err_sts; + + /* read err sts */ + err_sts = readl(hisi_zip->qm.io_base + HZIP_CORE_INT_STATUS); + + if (err_sts) { + hisi_zip_log_hw_error(hisi_zip, err_sts); + /* clear error interrupts */ + writel(err_sts, hisi_zip->qm.io_base + HZIP_CORE_INT_SOURCE); + + return PCI_ERS_RESULT_NEED_RESET; + } + + return PCI_ERS_RESULT_RECOVERED; +} + +static pci_ers_result_t hisi_zip_process_hw_error(struct pci_dev *pdev) +{ + struct hisi_zip *hisi_zip = pci_get_drvdata(pdev); + struct device *dev = &pdev->dev; + pci_ers_result_t qm_ret, zip_ret; + + if (!hisi_zip) { + dev_err(dev, + "Can't recover ZIP-error occurred during device init\n"); + return PCI_ERS_RESULT_NONE; + } + + qm_ret = hisi_qm_hw_error_handle(&hisi_zip->qm); + + zip_ret = hisi_zip_hw_error_handle(hisi_zip); + + return (qm_ret == PCI_ERS_RESULT_NEED_RESET || + zip_ret == PCI_ERS_RESULT_NEED_RESET) ? + PCI_ERS_RESULT_NEED_RESET : PCI_ERS_RESULT_RECOVERED; +} + +static pci_ers_result_t hisi_zip_error_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + if (pdev->is_virtfn) + return PCI_ERS_RESULT_NONE; + + dev_info(&pdev->dev, "PCI error detected, state(=%d)!!\n", state); + if (state == pci_channel_io_perm_failure) + return PCI_ERS_RESULT_DISCONNECT; + + return hisi_zip_process_hw_error(pdev); +} + +static const struct pci_error_handlers hisi_zip_err_handler = { + .error_detected = hisi_zip_error_detected, +}; + +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, + .sriov_configure = hisi_zip_sriov_configure, + .err_handler = &hisi_zip_err_handler, +}; + +static void hisi_zip_register_debugfs(void) +{ + if (!debugfs_initialized()) + return; + + hzip_debugfs_root = debugfs_create_dir("hisi_zip", NULL); + if (IS_ERR_OR_NULL(hzip_debugfs_root)) + hzip_debugfs_root = NULL; +} + +static void hisi_zip_unregister_debugfs(void) +{ + debugfs_remove_recursive(hzip_debugfs_root); +} + +static int __init hisi_zip_init(void) +{ + int ret; + + hisi_zip_register_debugfs(); + + ret = pci_register_driver(&hisi_zip_pci_driver); + if (ret < 0) { + pr_err("Failed to register pci driver.\n"); + goto err_pci; + } + + if (uacce_mode == 0 || uacce_mode == 2) { + ret = hisi_zip_register_to_crypto(); + if (ret < 0) { + pr_err("Failed to register driver to crypto.\n"); + goto err_crypto; + } + } + + return 0; + +err_crypto: + pci_unregister_driver(&hisi_zip_pci_driver); +err_pci: + hisi_zip_unregister_debugfs(); + + return ret; +} + +static void __exit hisi_zip_exit(void) +{ + if (uacce_mode == 0 || uacce_mode == 2) + hisi_zip_unregister_from_crypto(); + pci_unregister_driver(&hisi_zip_pci_driver); + hisi_zip_unregister_debugfs(); +} + +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"); |