Resguardo inicial

linux-7.2.3/drivers/crypto/marvell/octeontx2/Makefile

@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_CRYPTO_DEV_OCTEONTX2_CPT) += rvu_cptcommon.o rvu_cptpf.o rvu_cptvf.o
+
+rvu_cptcommon-objs := cn10k_cpt.o otx2_cptlf.o otx2_cpt_mbox_common.o
+rvu_cptpf-objs := otx2_cptpf_main.o otx2_cptpf_mbox.o \
+		  otx2_cptpf_ucode.o otx2_cpt_devlink.o
+rvu_cptvf-objs := otx2_cptvf_main.o otx2_cptvf_mbox.o \
+		  otx2_cptvf_reqmgr.o otx2_cptvf_algs.o
+
+ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af

linux-7.2.3/drivers/crypto/marvell/octeontx2/cn10k_cpt.c

@@ -0,0 +1,223 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2021 Marvell. */
+
+#include <linux/soc/marvell/octeontx2/asm.h>
+#include "otx2_cptpf.h"
+#include "otx2_cptvf.h"
+#include "otx2_cptlf.h"
+#include "cn10k_cpt.h"
+#include "otx2_cpt_common.h"
+
+static void cn10k_cpt_send_cmd(union otx2_cpt_inst_s *cptinst, u32 insts_num,
+			       struct otx2_cptlf_info *lf);
+
+static struct cpt_hw_ops otx2_hw_ops = {
+	.send_cmd = otx2_cpt_send_cmd,
+	.cpt_get_compcode = otx2_cpt_get_compcode,
+	.cpt_get_uc_compcode = otx2_cpt_get_uc_compcode,
+	.cpt_sg_info_create = otx2_sg_info_create,
+};
+
+static struct cpt_hw_ops cn10k_hw_ops = {
+	.send_cmd = cn10k_cpt_send_cmd,
+	.cpt_get_compcode = cn10k_cpt_get_compcode,
+	.cpt_get_uc_compcode = cn10k_cpt_get_uc_compcode,
+	.cpt_sg_info_create = otx2_sg_info_create,
+};
+
+static void cn10k_cpt_send_cmd(union otx2_cpt_inst_s *cptinst, u32 insts_num,
+			       struct otx2_cptlf_info *lf)
+{
+	void *lmtline = lf->lfs->lmt_info.base + (lf->slot * LMTLINE_SIZE);
+	u64 val = (lf->slot & 0x7FF);
+	u64 tar_addr = 0;
+
+	/* tar_addr<6:4> = Size of first LMTST - 1 in units of 128b. */
+	tar_addr |= (__force u64)lf->ioreg |
+		    (((OTX2_CPT_INST_SIZE/16) - 1) & 0x7) << 4;
+	/*
+	 * Make sure memory areas pointed in CPT_INST_S
+	 * are flushed before the instruction is sent to CPT
+	 */
+	dma_wmb();
+
+	/* Copy CPT command to LMTLINE */
+	memcpy(lmtline, cptinst, insts_num * OTX2_CPT_INST_SIZE);
+	cn10k_lmt_flush(val, tar_addr);
+}
+
+void cn10k_cpt_lmtst_free(struct pci_dev *pdev, struct otx2_cptlfs_info *lfs)
+{
+	struct otx2_lmt_info *lmt_info = &lfs->lmt_info;
+
+	if (!lmt_info->base)
+		return;
+
+	dma_free_attrs(&pdev->dev, lmt_info->size,
+		       lmt_info->base - lmt_info->align,
+		       lmt_info->iova - lmt_info->align,
+		       DMA_ATTR_FORCE_CONTIGUOUS);
+}
+EXPORT_SYMBOL_NS_GPL(cn10k_cpt_lmtst_free, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+static int cn10k_cpt_lmtst_alloc(struct pci_dev *pdev,
+				 struct otx2_cptlfs_info *lfs, u32 size)
+{
+	struct otx2_lmt_info *lmt_info = &lfs->lmt_info;
+	dma_addr_t align_iova;
+	dma_addr_t iova;
+
+	lmt_info->base = dma_alloc_attrs(&pdev->dev, size, &iova, GFP_KERNEL,
+					 DMA_ATTR_FORCE_CONTIGUOUS);
+	if (!lmt_info->base)
+		return -ENOMEM;
+
+	align_iova = ALIGN((u64)iova, LMTLINE_ALIGN);
+	lmt_info->iova = align_iova;
+	lmt_info->align = align_iova - iova;
+	lmt_info->size = size;
+	lmt_info->base += lmt_info->align;
+	return 0;
+}
+
+int cn10k_cptpf_lmtst_init(struct otx2_cptpf_dev *cptpf)
+{
+	struct pci_dev *pdev = cptpf->pdev;
+	u32 size;
+	int ret;
+
+	if (!test_bit(CN10K_LMTST, &cptpf->cap_flag)) {
+		cptpf->lfs.ops = &otx2_hw_ops;
+		return 0;
+	}
+
+	cptpf->lfs.ops = &cn10k_hw_ops;
+	size = OTX2_CPT_MAX_VFS_NUM * LMTLINE_SIZE + LMTLINE_ALIGN;
+	ret = cn10k_cpt_lmtst_alloc(pdev, &cptpf->lfs, size);
+	if (ret) {
+		dev_err(&pdev->dev, "PF-%d LMTLINE memory allocation failed\n",
+			cptpf->pf_id);
+		return ret;
+	}
+
+	ret = otx2_cpt_lmtst_tbl_setup_msg(&cptpf->lfs);
+	if (ret) {
+		dev_err(&pdev->dev, "PF-%d: LMTST Table setup failed\n",
+		cptpf->pf_id);
+		cn10k_cpt_lmtst_free(pdev, &cptpf->lfs);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cn10k_cptpf_lmtst_init, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+int cn10k_cptvf_lmtst_init(struct otx2_cptvf_dev *cptvf)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+	u32 size;
+	int ret;
+
+	if (!test_bit(CN10K_LMTST, &cptvf->cap_flag))
+		return 0;
+
+	size = cptvf->lfs.lfs_num * LMTLINE_SIZE + LMTLINE_ALIGN;
+	ret = cn10k_cpt_lmtst_alloc(pdev, &cptvf->lfs, size);
+	if (ret) {
+		dev_err(&pdev->dev, "VF-%d LMTLINE memory allocation failed\n",
+			cptvf->vf_id);
+		return ret;
+	}
+
+	ret = otx2_cpt_lmtst_tbl_setup_msg(&cptvf->lfs);
+	if (ret) {
+		dev_err(&pdev->dev, "VF-%d: LMTST Table setup failed\n",
+			cptvf->vf_id);
+		cn10k_cpt_lmtst_free(pdev, &cptvf->lfs);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cn10k_cptvf_lmtst_init, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+void cn10k_cpt_hw_ctx_clear(struct pci_dev *pdev,
+			    struct cn10k_cpt_errata_ctx *er_ctx)
+{
+	u64 cptr_dma;
+
+	if (!is_dev_cn10ka_ax(pdev))
+		return;
+
+	cptr_dma = er_ctx->cptr_dma & ~(BIT_ULL(60));
+	cn10k_cpt_ctx_flush(pdev, cptr_dma, true);
+	dma_unmap_single(&pdev->dev, cptr_dma, CN10K_CPT_HW_CTX_SIZE,
+			 DMA_BIDIRECTIONAL);
+	kfree(er_ctx->hw_ctx);
+}
+EXPORT_SYMBOL_NS_GPL(cn10k_cpt_hw_ctx_clear, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+void cn10k_cpt_hw_ctx_set(union cn10k_cpt_hw_ctx *hctx, u16 ctx_sz)
+{
+	hctx->w0.aop_valid = 1;
+	hctx->w0.ctx_hdr_sz = 0;
+	hctx->w0.ctx_sz = ctx_sz;
+	hctx->w0.ctx_push_sz = 1;
+}
+EXPORT_SYMBOL_NS_GPL(cn10k_cpt_hw_ctx_set, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+int cn10k_cpt_hw_ctx_init(struct pci_dev *pdev,
+			  struct cn10k_cpt_errata_ctx *er_ctx)
+{
+	union cn10k_cpt_hw_ctx *hctx;
+	u64 cptr_dma;
+
+	er_ctx->cptr_dma = 0;
+	er_ctx->hw_ctx = NULL;
+
+	if (!is_dev_cn10ka_ax(pdev))
+		return 0;
+
+	hctx = kmalloc(CN10K_CPT_HW_CTX_SIZE, GFP_KERNEL);
+	if (unlikely(!hctx))
+		return -ENOMEM;
+	cptr_dma = dma_map_single(&pdev->dev, hctx, CN10K_CPT_HW_CTX_SIZE,
+				  DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(&pdev->dev, cptr_dma)) {
+		kfree(hctx);
+		return -ENOMEM;
+	}
+
+	cn10k_cpt_hw_ctx_set(hctx, 1);
+	er_ctx->hw_ctx = hctx;
+	er_ctx->cptr_dma = cptr_dma | BIT_ULL(60);
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cn10k_cpt_hw_ctx_init, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+void cn10k_cpt_ctx_flush(struct pci_dev *pdev, u64 cptr, bool inval)
+{
+	struct otx2_cptvf_dev *cptvf = pci_get_drvdata(pdev);
+	struct otx2_cptlfs_info *lfs = &cptvf->lfs;
+	u64 reg;
+
+	reg = (uintptr_t)cptr >> 7;
+	if (inval)
+		reg = reg | BIT_ULL(46);
+
+	otx2_cpt_write64(lfs->reg_base, lfs->blkaddr, lfs->lf[0].slot,
+			 OTX2_CPT_LF_CTX_FLUSH, reg);
+	/* Make sure that the FLUSH operation is complete */
+	wmb();
+	otx2_cpt_read64(lfs->reg_base, lfs->blkaddr, lfs->lf[0].slot,
+			OTX2_CPT_LF_CTX_ERR);
+}
+EXPORT_SYMBOL_NS_GPL(cn10k_cpt_ctx_flush, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+void cptvf_hw_ops_get(struct otx2_cptvf_dev *cptvf)
+{
+	if (test_bit(CN10K_LMTST, &cptvf->cap_flag))
+		cptvf->lfs.ops = &cn10k_hw_ops;
+	else
+		cptvf->lfs.ops = &otx2_hw_ops;
+}
+EXPORT_SYMBOL_NS_GPL(cptvf_hw_ops_get, "CRYPTO_DEV_OCTEONTX2_CPT");

linux-7.2.3/drivers/crypto/marvell/octeontx2/cn10k_cpt.h

@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2021 Marvell.
+ */
+#ifndef __CN10K_CPT_H
+#define __CN10K_CPT_H
+
+#include "otx2_cpt_common.h"
+#include "otx2_cptpf.h"
+#include "otx2_cptvf.h"
+
+#define CN10K_CPT_HW_CTX_SIZE  256
+
+union cn10k_cpt_hw_ctx {
+	u64 u;
+	struct {
+		u64 reserved_0_47:48;
+		u64 ctx_push_sz:7;
+		u64 reserved_55:1;
+		u64 ctx_hdr_sz:2;
+		u64 aop_valid:1;
+		u64 reserved_59:1;
+		u64 ctx_sz:4;
+	} w0;
+};
+
+struct cn10k_cpt_errata_ctx {
+	union cn10k_cpt_hw_ctx *hw_ctx;
+	u64 cptr_dma;
+};
+
+static inline u8 cn10k_cpt_get_compcode(union otx2_cpt_res_s *result)
+{
+	return ((struct cn10k_cpt_res_s *)result)->compcode;
+}
+
+static inline u8 cn10k_cpt_get_uc_compcode(union otx2_cpt_res_s *result)
+{
+	return ((struct cn10k_cpt_res_s *)result)->uc_compcode;
+}
+
+static inline u8 otx2_cpt_get_compcode(union otx2_cpt_res_s *result)
+{
+	return ((struct cn9k_cpt_res_s *)result)->compcode;
+}
+
+static inline u8 otx2_cpt_get_uc_compcode(union otx2_cpt_res_s *result)
+{
+	return ((struct cn9k_cpt_res_s *)result)->uc_compcode;
+}
+
+int cn10k_cptpf_lmtst_init(struct otx2_cptpf_dev *cptpf);
+int cn10k_cptvf_lmtst_init(struct otx2_cptvf_dev *cptvf);
+void cn10k_cpt_lmtst_free(struct pci_dev *pdev, struct otx2_cptlfs_info *lfs);
+void cn10k_cpt_ctx_flush(struct pci_dev *pdev, u64 cptr, bool inval);
+int cn10k_cpt_hw_ctx_init(struct pci_dev *pdev,
+			  struct cn10k_cpt_errata_ctx *er_ctx);
+void cn10k_cpt_hw_ctx_clear(struct pci_dev *pdev,
+			    struct cn10k_cpt_errata_ctx *er_ctx);
+void cn10k_cpt_hw_ctx_set(union cn10k_cpt_hw_ctx *hctx, u16 ctx_sz);
+void cptvf_hw_ops_get(struct otx2_cptvf_dev *cptvf);
+
+#endif /* __CN10K_CPTLF_H */

linux-7.2.3/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h

@@ -0,0 +1,213 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2020 Marvell.
+ */
+
+#ifndef __OTX2_CPT_COMMON_H
+#define __OTX2_CPT_COMMON_H
+
+#include <linux/pci.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/crypto.h>
+#include <net/devlink.h>
+#include "otx2_cpt_hw_types.h"
+#include "rvu.h"
+#include "mbox.h"
+
+#define OTX2_CPT_MAX_VFS_NUM 128
+#define OTX2_CPT_RVU_FUNC_ADDR_S(blk, slot, offs) \
+		(((blk) << 20) | ((slot) << 12) | (offs))
+
+#define OTX2_CPT_RVU_PFFUNC(pdev, pf, func) rvu_make_pcifunc(pdev, pf, func)
+
+#define OTX2_CPT_INVALID_CRYPTO_ENG_GRP 0xFF
+#define OTX2_CPT_NAME_LENGTH 64
+#define OTX2_CPT_DMA_MINALIGN 128
+
+/* HW capability flags */
+#define CN10K_MBOX  0
+#define CN10K_LMTST 1
+
+#define BAD_OTX2_CPT_ENG_TYPE OTX2_CPT_MAX_ENG_TYPES
+
+enum otx2_cpt_eng_type {
+	OTX2_CPT_AE_TYPES = 1,
+	OTX2_CPT_SE_TYPES = 2,
+	OTX2_CPT_IE_TYPES = 3,
+	OTX2_CPT_MAX_ENG_TYPES,
+};
+
+/* Take mbox id from end of CPT mbox range in AF (range 0xA00 - 0xBFF) */
+#define MBOX_MSG_RX_INLINE_IPSEC_LF_CFG 0xBFE
+#define MBOX_MSG_GET_ENG_GRP_NUM        0xBFF
+#define MBOX_MSG_GET_CAPS               0xBFD
+#define MBOX_MSG_GET_KVF_LIMITS         0xBFC
+
+/*
+ * Message request to config cpt lf for inline inbound ipsec.
+ * This message is only used between CPT PF <-> CPT VF
+ */
+struct otx2_cpt_rx_inline_lf_cfg {
+	struct mbox_msghdr hdr;
+	u16 sso_pf_func;
+	u16 param1;
+	u16 param2;
+	u16 opcode;
+	u32 credit;
+	u32 credit_th;
+	u16 bpid;
+	u32 reserved;
+	u8 ctx_ilen_valid : 1;
+	u8 ctx_ilen : 7;
+};
+
+/*
+ * Message request and response to get engine group number
+ * which has attached a given type of engines (SE, AE, IE)
+ * This messages are only used between CPT PF <=> CPT VF
+ */
+struct otx2_cpt_egrp_num_msg {
+	struct mbox_msghdr hdr;
+	u8 eng_type;
+};
+
+struct otx2_cpt_egrp_num_rsp {
+	struct mbox_msghdr hdr;
+	u8 eng_type;
+	u8 eng_grp_num;
+};
+
+/*
+ * Message request and response to get kernel crypto limits
+ * This messages are only used between CPT PF <-> CPT VF
+ */
+struct otx2_cpt_kvf_limits_msg {
+	struct mbox_msghdr hdr;
+};
+
+struct otx2_cpt_kvf_limits_rsp {
+	struct mbox_msghdr hdr;
+	u8 kvf_limits;
+};
+
+/* CPT HW capabilities */
+union otx2_cpt_eng_caps {
+	u64 u;
+	struct {
+		u64 reserved_0_4:5;
+		u64 mul:1;
+		u64 sha1_sha2:1;
+		u64 chacha20:1;
+		u64 zuc_snow3g:1;
+		u64 sha3:1;
+		u64 aes:1;
+		u64 kasumi:1;
+		u64 des:1;
+		u64 crc:1;
+		u64 mmul:1;
+		u64 reserved_15_33:19;
+		u64 pdcp_chain:1;
+		u64 reserved_35_63:29;
+	};
+};
+
+/*
+ * Message request and response to get HW capabilities for each
+ * engine type (SE, IE, AE).
+ * This messages are only used between CPT PF <=> CPT VF
+ */
+struct otx2_cpt_caps_msg {
+	struct mbox_msghdr hdr;
+};
+
+struct otx2_cpt_caps_rsp {
+	struct mbox_msghdr hdr;
+	u16 cpt_pf_drv_version;
+	u8 cpt_revision;
+	union otx2_cpt_eng_caps eng_caps[OTX2_CPT_MAX_ENG_TYPES];
+};
+
+static inline void otx2_cpt_write64(void __iomem *reg_base, u64 blk, u64 slot,
+				    u64 offs, u64 val)
+{
+	writeq_relaxed(val, reg_base +
+		       OTX2_CPT_RVU_FUNC_ADDR_S(blk, slot, offs));
+}
+
+static inline u64 otx2_cpt_read64(void __iomem *reg_base, u64 blk, u64 slot,
+				  u64 offs)
+{
+	return readq_relaxed(reg_base +
+			     OTX2_CPT_RVU_FUNC_ADDR_S(blk, slot, offs));
+}
+
+static inline bool is_dev_otx2(struct pci_dev *pdev)
+{
+	return pdev->device == OTX2_CPT_PCI_PF_DEVICE_ID ||
+	       pdev->device == OTX2_CPT_PCI_VF_DEVICE_ID;
+}
+
+static inline bool is_dev_cn10ka(struct pci_dev *pdev)
+{
+	return pdev->subsystem_device == CPT_PCI_SUBSYS_DEVID_CN10K_A;
+}
+
+static inline bool is_dev_cn10ka_ax(struct pci_dev *pdev)
+{
+	return pdev->subsystem_device == CPT_PCI_SUBSYS_DEVID_CN10K_A &&
+	       ((pdev->revision & 0xFF) == 4 ||
+		(pdev->revision & 0xFF) == 0x50 ||
+		(pdev->revision & 0xFF) == 0x51);
+}
+
+static inline bool is_dev_cn10kb(struct pci_dev *pdev)
+{
+	return pdev->subsystem_device == CPT_PCI_SUBSYS_DEVID_CN10K_B;
+}
+
+static inline bool is_dev_cn10ka_b0(struct pci_dev *pdev)
+{
+	return pdev->subsystem_device == CPT_PCI_SUBSYS_DEVID_CN10K_A &&
+	       (pdev->revision & 0xFF) == 0x54;
+}
+
+static inline void otx2_cpt_set_hw_caps(struct pci_dev *pdev,
+					unsigned long *cap_flag)
+{
+	if (!is_dev_otx2(pdev)) {
+		__set_bit(CN10K_MBOX, cap_flag);
+		__set_bit(CN10K_LMTST, cap_flag);
+	}
+}
+
+static inline bool cpt_is_errata_38550_exists(struct pci_dev *pdev)
+{
+	return is_dev_otx2(pdev) || is_dev_cn10ka_ax(pdev);
+}
+
+static inline bool cpt_feature_sgv2(struct pci_dev *pdev)
+{
+	return !is_dev_otx2(pdev) && !is_dev_cn10ka_ax(pdev);
+}
+
+int otx2_cpt_send_ready_msg(struct otx2_mbox *mbox, struct pci_dev *pdev);
+int otx2_cpt_send_mbox_msg(struct otx2_mbox *mbox, struct pci_dev *pdev);
+
+int otx2_cpt_send_af_reg_requests(struct otx2_mbox *mbox,
+				  struct pci_dev *pdev);
+int otx2_cpt_add_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
+			      u64 reg, u64 val, int blkaddr);
+int otx2_cpt_read_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
+			 u64 reg, u64 *val, int blkaddr);
+int otx2_cpt_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
+			  u64 reg, u64 val, int blkaddr);
+struct otx2_cptlfs_info;
+int otx2_cpt_attach_rscrs_msg(struct otx2_cptlfs_info *lfs);
+int otx2_cpt_detach_rsrcs_msg(struct otx2_cptlfs_info *lfs);
+int otx2_cpt_msix_offset_msg(struct otx2_cptlfs_info *lfs);
+int otx2_cpt_sync_mbox_msg(struct otx2_mbox *mbox);
+int otx2_cpt_lf_reset_msg(struct otx2_cptlfs_info *lfs, int slot);
+int otx2_cpt_lmtst_tbl_setup_msg(struct otx2_cptlfs_info *lfs);
+
+#endif /* __OTX2_CPT_COMMON_H */

linux-7.2.3/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c

@@ -0,0 +1,185 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2021 Marvell. */
+
+#include "otx2_cpt_devlink.h"
+
+static int otx2_cpt_dl_egrp_create(struct devlink *dl, u32 id,
+				   struct devlink_param_gset_ctx *ctx,
+				   struct netlink_ext_ack *extack)
+{
+	struct otx2_cpt_devlink *cpt_dl = devlink_priv(dl);
+	struct otx2_cptpf_dev *cptpf = cpt_dl->cptpf;
+
+	return otx2_cpt_dl_custom_egrp_create(cptpf, ctx);
+}
+
+static int otx2_cpt_dl_egrp_delete(struct devlink *dl, u32 id,
+				   struct devlink_param_gset_ctx *ctx,
+				   struct netlink_ext_ack *extack)
+{
+	struct otx2_cpt_devlink *cpt_dl = devlink_priv(dl);
+	struct otx2_cptpf_dev *cptpf = cpt_dl->cptpf;
+
+	return otx2_cpt_dl_custom_egrp_delete(cptpf, ctx);
+}
+
+static int otx2_cpt_dl_uc_info(struct devlink *dl, u32 id,
+			       struct devlink_param_gset_ctx *ctx,
+			       struct netlink_ext_ack *extack)
+{
+	ctx->val.vstr[0] = '\0';
+
+	return 0;
+}
+
+static int otx2_cpt_dl_t106_mode_get(struct devlink *dl, u32 id,
+				     struct devlink_param_gset_ctx *ctx,
+				     struct netlink_ext_ack *extack)
+{
+	struct otx2_cpt_devlink *cpt_dl = devlink_priv(dl);
+	struct otx2_cptpf_dev *cptpf = cpt_dl->cptpf;
+	struct pci_dev *pdev = cptpf->pdev;
+	u64 reg_val = 0;
+
+	otx2_cpt_read_af_reg(&cptpf->afpf_mbox, pdev, CPT_AF_CTL, &reg_val,
+			     BLKADDR_CPT0);
+	ctx->val.vu8 = (reg_val >> 18) & 0x1;
+
+	return 0;
+}
+
+static int otx2_cpt_dl_t106_mode_set(struct devlink *dl, u32 id,
+				     struct devlink_param_gset_ctx *ctx,
+				     struct netlink_ext_ack *extack)
+{
+	struct otx2_cpt_devlink *cpt_dl = devlink_priv(dl);
+	struct otx2_cptpf_dev *cptpf = cpt_dl->cptpf;
+	struct pci_dev *pdev = cptpf->pdev;
+	u64 reg_val = 0;
+
+	if (cptpf->enabled_vfs != 0 || cptpf->eng_grps.is_grps_created)
+		return -EPERM;
+
+	if (cpt_feature_sgv2(pdev)) {
+		otx2_cpt_read_af_reg(&cptpf->afpf_mbox, pdev, CPT_AF_CTL,
+				     &reg_val, BLKADDR_CPT0);
+		reg_val &= ~(0x1ULL << 18);
+		reg_val |= ((u64)ctx->val.vu8 & 0x1) << 18;
+		return otx2_cpt_write_af_reg(&cptpf->afpf_mbox, pdev,
+					     CPT_AF_CTL, reg_val, BLKADDR_CPT0);
+	}
+
+	return 0;
+}
+
+enum otx2_cpt_dl_param_id {
+	OTX2_CPT_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
+	OTX2_CPT_DEVLINK_PARAM_ID_EGRP_CREATE,
+	OTX2_CPT_DEVLINK_PARAM_ID_EGRP_DELETE,
+	OTX2_CPT_DEVLINK_PARAM_ID_T106_MODE,
+};
+
+static const struct devlink_param otx2_cpt_dl_params[] = {
+	DEVLINK_PARAM_DRIVER(OTX2_CPT_DEVLINK_PARAM_ID_EGRP_CREATE,
+			     "egrp_create", DEVLINK_PARAM_TYPE_STRING,
+			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+			     otx2_cpt_dl_uc_info, otx2_cpt_dl_egrp_create,
+			     NULL),
+	DEVLINK_PARAM_DRIVER(OTX2_CPT_DEVLINK_PARAM_ID_EGRP_DELETE,
+			     "egrp_delete", DEVLINK_PARAM_TYPE_STRING,
+			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+			     otx2_cpt_dl_uc_info, otx2_cpt_dl_egrp_delete,
+			     NULL),
+	DEVLINK_PARAM_DRIVER(OTX2_CPT_DEVLINK_PARAM_ID_T106_MODE,
+			     "t106_mode", DEVLINK_PARAM_TYPE_U8,
+			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+			     otx2_cpt_dl_t106_mode_get, otx2_cpt_dl_t106_mode_set,
+			     NULL),
+};
+
+static int otx2_cpt_dl_info_firmware_version_put(struct devlink_info_req *req,
+						 struct otx2_cpt_eng_grp_info grp[],
+						 const char *ver_name, int eng_type)
+{
+	struct otx2_cpt_engs_rsvd *eng;
+	int i;
+
+	for (i = 0; i < OTX2_CPT_MAX_ENGINE_GROUPS; i++) {
+		eng = find_engines_by_type(&grp[i], eng_type);
+		if (eng)
+			return devlink_info_version_running_put(req, ver_name,
+								eng->ucode->ver_str);
+	}
+
+	return 0;
+}
+
+static int otx2_cpt_devlink_info_get(struct devlink *dl,
+				     struct devlink_info_req *req,
+				     struct netlink_ext_ack *extack)
+{
+	struct otx2_cpt_devlink *cpt_dl = devlink_priv(dl);
+	struct otx2_cptpf_dev *cptpf = cpt_dl->cptpf;
+	int err;
+
+	err = otx2_cpt_dl_info_firmware_version_put(req, cptpf->eng_grps.grp,
+						    "fw.ae", OTX2_CPT_AE_TYPES);
+	if (err)
+		return err;
+
+	err = otx2_cpt_dl_info_firmware_version_put(req, cptpf->eng_grps.grp,
+						    "fw.se", OTX2_CPT_SE_TYPES);
+	if (err)
+		return err;
+
+	return otx2_cpt_dl_info_firmware_version_put(req, cptpf->eng_grps.grp,
+						    "fw.ie", OTX2_CPT_IE_TYPES);
+}
+
+static const struct devlink_ops otx2_cpt_devlink_ops = {
+	.info_get = otx2_cpt_devlink_info_get,
+};
+
+int otx2_cpt_register_dl(struct otx2_cptpf_dev *cptpf)
+{
+	struct device *dev = &cptpf->pdev->dev;
+	struct otx2_cpt_devlink *cpt_dl;
+	struct devlink *dl;
+	int ret;
+
+	dl = devlink_alloc(&otx2_cpt_devlink_ops,
+			   sizeof(struct otx2_cpt_devlink), dev);
+	if (!dl) {
+		dev_warn(dev, "devlink_alloc failed\n");
+		return -ENOMEM;
+	}
+
+	cpt_dl = devlink_priv(dl);
+	cpt_dl->dl = dl;
+	cpt_dl->cptpf = cptpf;
+	cptpf->dl = dl;
+	ret = devlink_params_register(dl, otx2_cpt_dl_params,
+				      ARRAY_SIZE(otx2_cpt_dl_params));
+	if (ret) {
+		dev_err(dev, "devlink params register failed with error %d",
+			ret);
+		devlink_free(dl);
+		return ret;
+	}
+	devlink_register(dl);
+
+	return 0;
+}
+
+void otx2_cpt_unregister_dl(struct otx2_cptpf_dev *cptpf)
+{
+	struct devlink *dl = cptpf->dl;
+
+	if (!dl)
+		return;
+
+	devlink_unregister(dl);
+	devlink_params_unregister(dl, otx2_cpt_dl_params,
+				  ARRAY_SIZE(otx2_cpt_dl_params));
+	devlink_free(dl);
+}

linux-7.2.3/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.h

@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2021 Marvell.
+ */
+
+#ifndef __OTX2_CPT_DEVLINK_H
+#define __OTX2_CPT_DEVLINK_H
+
+#include "otx2_cpt_common.h"
+#include "otx2_cptpf.h"
+
+struct otx2_cpt_devlink {
+	struct devlink *dl;
+	struct otx2_cptpf_dev *cptpf;
+};
+
+/* Devlink APIs */
+int otx2_cpt_register_dl(struct otx2_cptpf_dev *cptpf);
+void otx2_cpt_unregister_dl(struct otx2_cptpf_dev *cptpf);
+
+#endif /* __OTX2_CPT_DEVLINK_H */

linux-7.2.3/drivers/crypto/marvell/octeontx2/otx2_cpt_hw_types.h

@@ -0,0 +1,483 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2020 Marvell.
+ */
+
+#ifndef __OTX2_CPT_HW_TYPES_H
+#define __OTX2_CPT_HW_TYPES_H
+
+#include <linux/types.h>
+
+/* Device IDs */
+#define OTX2_CPT_PCI_PF_DEVICE_ID 0xA0FD
+#define OTX2_CPT_PCI_VF_DEVICE_ID 0xA0FE
+#define CN10K_CPT_PCI_PF_DEVICE_ID 0xA0F2
+#define CN10K_CPT_PCI_VF_DEVICE_ID 0xA0F3
+
+#define CPT_PCI_SUBSYS_DEVID_CN10K_A 0xB900
+#define CPT_PCI_SUBSYS_DEVID_CN10K_B 0xBD00
+
+/* Mailbox interrupts offset */
+#define OTX2_CPT_PF_MBOX_INT	6
+#define OTX2_CPT_PF_INT_VEC_E_MBOXX(x, a) ((x) + (a))
+
+/* Maximum supported microcode groups */
+#define OTX2_CPT_MAX_ENGINE_GROUPS 8
+
+/* CPT instruction size in bytes */
+#define OTX2_CPT_INST_SIZE	64
+/*
+ * CPT VF MSIX vectors and their offsets
+ */
+#define OTX2_CPT_VF_MSIX_VECTORS 1
+#define OTX2_CPT_VF_INTR_MBOX_MASK BIT(0)
+#define CN10K_CPT_VF_MBOX_REGION  (0xC0000)
+
+/* CPT LF MSIX vectors */
+#define OTX2_CPT_LF_MSIX_VECTORS 2
+
+/* OcteonTX2 CPT PF registers */
+#define OTX2_CPT_PF_CONSTANTS           (0x0)
+#define OTX2_CPT_PF_RESET               (0x100)
+#define OTX2_CPT_PF_DIAG                (0x120)
+#define OTX2_CPT_PF_BIST_STATUS         (0x160)
+#define OTX2_CPT_PF_ECC0_CTL            (0x200)
+#define OTX2_CPT_PF_ECC0_FLIP           (0x210)
+#define OTX2_CPT_PF_ECC0_INT            (0x220)
+#define OTX2_CPT_PF_ECC0_INT_W1S        (0x230)
+#define OTX2_CPT_PF_ECC0_ENA_W1S        (0x240)
+#define OTX2_CPT_PF_ECC0_ENA_W1C        (0x250)
+#define OTX2_CPT_PF_MBOX_INTX(b)        (0x400 | (b) << 3)
+#define OTX2_CPT_PF_MBOX_INT_W1SX(b)    (0x420 | (b) << 3)
+#define OTX2_CPT_PF_MBOX_ENA_W1CX(b)    (0x440 | (b) << 3)
+#define OTX2_CPT_PF_MBOX_ENA_W1SX(b)    (0x460 | (b) << 3)
+#define OTX2_CPT_PF_EXEC_INT            (0x500)
+#define OTX2_CPT_PF_EXEC_INT_W1S        (0x520)
+#define OTX2_CPT_PF_EXEC_ENA_W1C        (0x540)
+#define OTX2_CPT_PF_EXEC_ENA_W1S        (0x560)
+#define OTX2_CPT_PF_GX_EN(b)            (0x600 | (b) << 3)
+#define OTX2_CPT_PF_EXEC_INFO           (0x700)
+#define OTX2_CPT_PF_EXEC_BUSY           (0x800)
+#define OTX2_CPT_PF_EXEC_INFO0          (0x900)
+#define OTX2_CPT_PF_EXEC_INFO1          (0x910)
+#define OTX2_CPT_PF_INST_REQ_PC         (0x10000)
+#define OTX2_CPT_PF_INST_LATENCY_PC     (0x10020)
+#define OTX2_CPT_PF_RD_REQ_PC           (0x10040)
+#define OTX2_CPT_PF_RD_LATENCY_PC       (0x10060)
+#define OTX2_CPT_PF_RD_UC_PC            (0x10080)
+#define OTX2_CPT_PF_ACTIVE_CYCLES_PC    (0x10100)
+#define OTX2_CPT_PF_EXE_CTL             (0x4000000)
+#define OTX2_CPT_PF_EXE_STATUS          (0x4000008)
+#define OTX2_CPT_PF_EXE_CLK             (0x4000010)
+#define OTX2_CPT_PF_EXE_DBG_CTL         (0x4000018)
+#define OTX2_CPT_PF_EXE_DBG_DATA        (0x4000020)
+#define OTX2_CPT_PF_EXE_BIST_STATUS     (0x4000028)
+#define OTX2_CPT_PF_EXE_REQ_TIMER       (0x4000030)
+#define OTX2_CPT_PF_EXE_MEM_CTL         (0x4000038)
+#define OTX2_CPT_PF_EXE_PERF_CTL        (0x4001000)
+#define OTX2_CPT_PF_EXE_DBG_CNTX(b)     (0x4001100 | (b) << 3)
+#define OTX2_CPT_PF_EXE_PERF_EVENT_CNT  (0x4001180)
+#define OTX2_CPT_PF_EXE_EPCI_INBX_CNT(b)  (0x4001200 | (b) << 3)
+#define OTX2_CPT_PF_EXE_EPCI_OUTBX_CNT(b) (0x4001240 | (b) << 3)
+#define OTX2_CPT_PF_ENGX_UCODE_BASE(b)  (0x4002000 | (b) << 3)
+#define OTX2_CPT_PF_QX_CTL(b)           (0x8000000 | (b) << 20)
+#define OTX2_CPT_PF_QX_GMCTL(b)         (0x8000020 | (b) << 20)
+#define OTX2_CPT_PF_QX_CTL2(b)          (0x8000100 | (b) << 20)
+#define OTX2_CPT_PF_VFX_MBOXX(b, c)     (0x8001000 | (b) << 20 | \
+					 (c) << 8)
+
+/* OcteonTX2 CPT LF registers */
+#define OTX2_CPT_LF_CTL                 (0x10)
+#define OTX2_CPT_LF_DONE_WAIT           (0x30)
+#define OTX2_CPT_LF_INPROG              (0x40)
+#define OTX2_CPT_LF_DONE                (0x50)
+#define OTX2_CPT_LF_DONE_ACK            (0x60)
+#define OTX2_CPT_LF_DONE_INT_ENA_W1S    (0x90)
+#define OTX2_CPT_LF_DONE_INT_ENA_W1C    (0xa0)
+#define OTX2_CPT_LF_MISC_INT            (0xb0)
+#define OTX2_CPT_LF_MISC_INT_W1S        (0xc0)
+#define OTX2_CPT_LF_MISC_INT_ENA_W1S    (0xd0)
+#define OTX2_CPT_LF_MISC_INT_ENA_W1C    (0xe0)
+#define OTX2_CPT_LF_Q_BASE              (0xf0)
+#define OTX2_CPT_LF_Q_SIZE              (0x100)
+#define OTX2_CPT_LF_Q_INST_PTR          (0x110)
+#define OTX2_CPT_LF_Q_GRP_PTR           (0x120)
+#define OTX2_CPT_LF_NQX(a)              (0x400 | (a) << 3)
+#define OTX2_CPT_LF_CTX_CTL             (0x500)
+#define OTX2_CPT_LF_CTX_FLUSH           (0x510)
+#define OTX2_CPT_LF_CTX_ERR             (0x520)
+#define OTX2_CPT_RVU_FUNC_BLKADDR_SHIFT 20
+/* LMT LF registers */
+#define OTX2_CPT_LMT_LFBASE             BIT_ULL(OTX2_CPT_RVU_FUNC_BLKADDR_SHIFT)
+#define OTX2_CPT_LMT_LF_LMTLINEX(a)     (OTX2_CPT_LMT_LFBASE | 0x000 | \
+					 (a) << 12)
+/* RVU VF registers */
+#define OTX2_RVU_VF_INT                 (0x20)
+#define OTX2_RVU_VF_INT_W1S             (0x28)
+#define OTX2_RVU_VF_INT_ENA_W1S         (0x30)
+#define OTX2_RVU_VF_INT_ENA_W1C         (0x38)
+
+/*
+ * Enumeration otx2_cpt_ucode_error_code_e
+ *
+ * Enumerates ucode errors
+ */
+enum otx2_cpt_ucode_comp_code_e {
+	OTX2_CPT_UCC_SUCCESS = 0x00,
+	OTX2_CPT_UCC_INVALID_OPCODE = 0x01,
+
+	/* Scatter gather */
+	OTX2_CPT_UCC_SG_WRITE_LENGTH = 0x02,
+	OTX2_CPT_UCC_SG_LIST = 0x03,
+	OTX2_CPT_UCC_SG_NOT_SUPPORTED = 0x04,
+
+};
+
+/*
+ * Enumeration otx2_cpt_comp_e
+ *
+ * OcteonTX2 CPT Completion Enumeration
+ * Enumerates the values of CPT_RES_S[COMPCODE].
+ */
+enum otx2_cpt_comp_e {
+	OTX2_CPT_COMP_E_NOTDONE = 0x00,
+	OTX2_CPT_COMP_E_GOOD = 0x01,
+	OTX2_CPT_COMP_E_FAULT = 0x02,
+	OTX2_CPT_COMP_E_HWERR = 0x04,
+	OTX2_CPT_COMP_E_INSTERR = 0x05,
+	OTX2_CPT_COMP_E_WARN = 0x06
+};
+
+/*
+ * Enumeration otx2_cpt_vf_int_vec_e
+ *
+ * OcteonTX2 CPT VF MSI-X Vector Enumeration
+ * Enumerates the MSI-X interrupt vectors.
+ */
+enum otx2_cpt_vf_int_vec_e {
+	OTX2_CPT_VF_INT_VEC_E_MBOX = 0x00
+};
+
+/*
+ * Enumeration otx2_cpt_lf_int_vec_e
+ *
+ * OcteonTX2 CPT LF MSI-X Vector Enumeration
+ * Enumerates the MSI-X interrupt vectors.
+ */
+enum otx2_cpt_lf_int_vec_e {
+	OTX2_CPT_LF_INT_VEC_E_MISC = 0x00,
+	OTX2_CPT_LF_INT_VEC_E_DONE = 0x01
+};
+
+/*
+ * Structure otx2_cpt_inst_s
+ *
+ * CPT Instruction Structure
+ * This structure specifies the instruction layout. Instructions are
+ * stored in memory as little-endian unless CPT()_PF_Q()_CTL[INST_BE] is set.
+ * cpt_inst_s_s
+ * Word 0
+ * doneint:1 Done interrupt.
+ *	0 = No interrupts related to this instruction.
+ *	1 = When the instruction completes, CPT()_VQ()_DONE[DONE] will be
+ *	incremented,and based on the rules described there an interrupt may
+ *	occur.
+ * Word 1
+ * res_addr [127: 64] Result IOVA.
+ *	If nonzero, specifies where to write CPT_RES_S.
+ *	If zero, no result structure will be written.
+ *	Address must be 16-byte aligned.
+ *	Bits <63:49> are ignored by hardware; software should use a
+ *	sign-extended bit <48> for forward compatibility.
+ * Word 2
+ *  grp:10 [171:162] If [WQ_PTR] is nonzero, the SSO guest-group to use when
+ *	CPT submits work SSO.
+ *	For the SSO to not discard the add-work request, FPA_PF_MAP() must map
+ *	[GRP] and CPT()_PF_Q()_GMCTL[GMID] as valid.
+ *  tt:2 [161:160] If [WQ_PTR] is nonzero, the SSO tag type to use when CPT
+ *	submits work to SSO
+ *  tag:32 [159:128] If [WQ_PTR] is nonzero, the SSO tag to use when CPT
+ *	submits work to SSO.
+ * Word 3
+ *  wq_ptr [255:192] If [WQ_PTR] is nonzero, it is a pointer to a
+ *	work-queue entry that CPT submits work to SSO after all context,
+ *	output data, and result write operations are visible to other
+ *	CNXXXX units and the cores. Bits <2:0> must be zero.
+ *	Bits <63:49> are ignored by hardware; software should
+ *	use a sign-extended bit <48> for forward compatibility.
+ *	Internal:
+ *	Bits <63:49>, <2:0> are ignored by hardware, treated as always 0x0.
+ * Word 4
+ *  ei0; [319:256] Engine instruction word 0. Passed to the AE/SE.
+ * Word 5
+ *  ei1; [383:320] Engine instruction word 1. Passed to the AE/SE.
+ * Word 6
+ *  ei2; [447:384] Engine instruction word 1. Passed to the AE/SE.
+ * Word 7
+ *  ei3; [511:448] Engine instruction word 1. Passed to the AE/SE.
+ *
+ */
+union otx2_cpt_inst_s {
+	u64 u[8];
+
+	struct {
+		/* Word 0 */
+		u64 nixtxl:3;
+		u64 doneint:1;
+		u64 nixtx_addr:60;
+		/* Word 1 */
+		u64 res_addr;
+		/* Word 2 */
+		u64 tag:32;
+		u64 tt:2;
+		u64 grp:10;
+		u64 reserved_172_175:4;
+		u64 rvu_pf_func:16;
+		/* Word 3 */
+		u64 qord:1;
+		u64 reserved_194_193:2;
+		u64 wq_ptr:61;
+		/* Word 4 */
+		u64 ei0;
+		/* Word 5 */
+		u64 ei1;
+		/* Word 6 */
+		u64 ei2;
+		/* Word 7 */
+		u64 ei3;
+	} s;
+};
+
+/*
+ * Structure otx2_cpt_res_s
+ *
+ * CPT Result Structure
+ * The CPT coprocessor writes the result structure after it completes a
+ * CPT_INST_S instruction. The result structure is exactly 16 bytes, and
+ * each instruction completion produces exactly one result structure.
+ *
+ * This structure is stored in memory as little-endian unless
+ * CPT()_PF_Q()_CTL[INST_BE] is set.
+ * cpt_res_s_s
+ * Word 0
+ *  doneint:1 [16:16] Done interrupt. This bit is copied from the
+ *	corresponding instruction's CPT_INST_S[DONEINT].
+ *  compcode:8 [7:0] Indicates completion/error status of the CPT coprocessor
+ *	for the	associated instruction, as enumerated by CPT_COMP_E.
+ *	Core software may write the memory location containing [COMPCODE] to
+ *	0x0 before ringing the doorbell, and then poll for completion by
+ *	checking for a nonzero value.
+ *	Once the core observes a nonzero [COMPCODE] value in this case,the CPT
+ *	coprocessor will have also completed L2/DRAM write operations.
+ * Word 1
+ *  reserved
+ *
+ */
+union otx2_cpt_res_s {
+	u64 u[2];
+
+	struct cn9k_cpt_res_s {
+		u64 compcode:8;
+		u64 uc_compcode:8;
+		u64 doneint:1;
+		u64 reserved_17_63:47;
+		u64 reserved_64_127;
+	} s;
+
+	struct cn10k_cpt_res_s {
+		u64 compcode:7;
+		u64 doneint:1;
+		u64 uc_compcode:8;
+		u64 rlen:16;
+		u64 spi:32;
+		u64 esn;
+	} cn10k;
+};
+
+/*
+ * Register (RVU_PF_BAR0) cpt#_af_constants1
+ *
+ * CPT AF Constants Register
+ * This register contains implementation-related parameters of CPT.
+ */
+union otx2_cptx_af_constants1 {
+	u64 u;
+	struct otx2_cptx_af_constants1_s {
+		u64 se:16;
+		u64 ie:16;
+		u64 ae:16;
+		u64 reserved_48_63:16;
+	} s;
+};
+
+/*
+ * RVU_PFVF_BAR2 - cpt_lf_misc_int
+ *
+ * This register contain the per-queue miscellaneous interrupts.
+ *
+ */
+union otx2_cptx_lf_misc_int {
+	u64 u;
+	struct otx2_cptx_lf_misc_int_s {
+		u64 reserved_0:1;
+		u64 nqerr:1;
+		u64 irde:1;
+		u64 nwrp:1;
+		u64 reserved_4:1;
+		u64 hwerr:1;
+		u64 fault:1;
+		u64 reserved_7_63:57;
+	} s;
+};
+
+/*
+ * RVU_PFVF_BAR2 - cpt_lf_misc_int_ena_w1s
+ *
+ * This register sets interrupt enable bits.
+ *
+ */
+union otx2_cptx_lf_misc_int_ena_w1s {
+	u64 u;
+	struct otx2_cptx_lf_misc_int_ena_w1s_s {
+		u64 reserved_0:1;
+		u64 nqerr:1;
+		u64 irde:1;
+		u64 nwrp:1;
+		u64 reserved_4:1;
+		u64 hwerr:1;
+		u64 fault:1;
+		u64 reserved_7_63:57;
+	} s;
+};
+
+/*
+ * RVU_PFVF_BAR2 - cpt_lf_ctl
+ *
+ * This register configures the queue.
+ *
+ * When the queue is not execution-quiescent (see CPT_LF_INPROG[EENA,INFLIGHT]),
+ * software must only write this register with [ENA]=0.
+ */
+union otx2_cptx_lf_ctl {
+	u64 u;
+	struct otx2_cptx_lf_ctl_s {
+		u64 ena:1;
+		u64 fc_ena:1;
+		u64 fc_up_crossing:1;
+		u64 reserved_3:1;
+		u64 fc_hyst_bits:4;
+		u64 reserved_8_63:56;
+	} s;
+};
+
+/*
+ * RVU_PFVF_BAR2 - cpt_lf_done_wait
+ *
+ * This register specifies the per-queue interrupt coalescing settings.
+ */
+union otx2_cptx_lf_done_wait {
+	u64 u;
+	struct otx2_cptx_lf_done_wait_s {
+		u64 num_wait:20;
+		u64 reserved_20_31:12;
+		u64 time_wait:16;
+		u64 reserved_48_63:16;
+	} s;
+};
+
+/*
+ * RVU_PFVF_BAR2 - cpt_lf_done
+ *
+ * This register contain the per-queue instruction done count.
+ */
+union otx2_cptx_lf_done {
+	u64 u;
+	struct otx2_cptx_lf_done_s {
+		u64 done:20;
+		u64 reserved_20_63:44;
+	} s;
+};
+
+/*
+ * RVU_PFVF_BAR2 - cpt_lf_inprog
+ *
+ * These registers contain the per-queue instruction in flight registers.
+ *
+ */
+union otx2_cptx_lf_inprog {
+	u64 u;
+	struct otx2_cptx_lf_inprog_s {
+		u64 inflight:9;
+		u64 reserved_9_15:7;
+		u64 eena:1;
+		u64 grp_drp:1;
+		u64 reserved_18_30:13;
+		u64 grb_partial:1;
+		u64 grb_cnt:8;
+		u64 gwb_cnt:8;
+		u64 reserved_48_63:16;
+	} s;
+};
+
+/*
+ * RVU_PFVF_BAR2 - cpt_lf_q_base
+ *
+ * CPT initializes these CSR fields to these values on any CPT_LF_Q_BASE write:
+ * _ CPT_LF_Q_INST_PTR[XQ_XOR]=0.
+ * _ CPT_LF_Q_INST_PTR[NQ_PTR]=2.
+ * _ CPT_LF_Q_INST_PTR[DQ_PTR]=2.
+ * _ CPT_LF_Q_GRP_PTR[XQ_XOR]=0.
+ * _ CPT_LF_Q_GRP_PTR[NQ_PTR]=1.
+ * _ CPT_LF_Q_GRP_PTR[DQ_PTR]=1.
+ */
+union otx2_cptx_lf_q_base {
+	u64 u;
+	struct otx2_cptx_lf_q_base_s {
+		u64 fault:1;
+		u64 reserved_1_6:6;
+		u64 addr:46;
+		u64 reserved_53_63:11;
+	} s;
+};
+
+/*
+ * RVU_PFVF_BAR2 - cpt_lf_q_size
+ *
+ * CPT initializes these CSR fields to these values on any CPT_LF_Q_SIZE write:
+ * _ CPT_LF_Q_INST_PTR[XQ_XOR]=0.
+ * _ CPT_LF_Q_INST_PTR[NQ_PTR]=2.
+ * _ CPT_LF_Q_INST_PTR[DQ_PTR]=2.
+ * _ CPT_LF_Q_GRP_PTR[XQ_XOR]=0.
+ * _ CPT_LF_Q_GRP_PTR[NQ_PTR]=1.
+ * _ CPT_LF_Q_GRP_PTR[DQ_PTR]=1.
+ */
+union otx2_cptx_lf_q_size {
+	u64 u;
+	struct otx2_cptx_lf_q_size_s {
+		u64 size_div40:15;
+		u64 reserved_15_63:49;
+	} s;
+};
+
+/*
+ * RVU_PF_BAR0 - cpt_af_lf_ctl
+ *
+ * This register configures queues. This register should be written only
+ * when the queue is execution-quiescent (see CPT_LF_INPROG[INFLIGHT]).
+ */
+union otx2_cptx_af_lf_ctrl {
+	u64 u;
+	struct otx2_cptx_af_lf_ctrl_s {
+		u64 pri:1;
+		u64 reserved_1_8:8;
+		u64 pf_func_inst:1;
+		u64 cont_err:1;
+		u64 reserved_11_15:5;
+		u64 nixtx_en:1;
+		u64 ctx_ilen:3;
+		u64 reserved_17_47:28;
+		u64 grp:8;
+		u64 reserved_56_63:8;
+	} s;
+};
+
+#endif /* __OTX2_CPT_HW_TYPES_H */

linux-7.2.3/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c

@@ -0,0 +1,282 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Marvell. */
+
+#include "otx2_cpt_common.h"
+#include "otx2_cptlf.h"
+
+int otx2_cpt_send_mbox_msg(struct otx2_mbox *mbox, struct pci_dev *pdev)
+{
+	int ret;
+
+	otx2_mbox_msg_send(mbox, 0);
+	ret = otx2_mbox_wait_for_rsp(mbox, 0);
+	if (ret == -EIO) {
+		dev_err(&pdev->dev, "RVU MBOX timeout.\n");
+		return ret;
+	} else if (ret) {
+		dev_err(&pdev->dev, "RVU MBOX error: %d.\n", ret);
+		return -EFAULT;
+	}
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cpt_send_mbox_msg, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+int otx2_cpt_send_ready_msg(struct otx2_mbox *mbox, struct pci_dev *pdev)
+{
+	struct mbox_msghdr *req;
+
+	req = otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req),
+				      sizeof(struct ready_msg_rsp));
+	if (req == NULL) {
+		dev_err(&pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+	req->id = MBOX_MSG_READY;
+	req->sig = OTX2_MBOX_REQ_SIG;
+	req->pcifunc = 0;
+
+	return otx2_cpt_send_mbox_msg(mbox, pdev);
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cpt_send_ready_msg, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+int otx2_cpt_send_af_reg_requests(struct otx2_mbox *mbox, struct pci_dev *pdev)
+{
+	return otx2_cpt_send_mbox_msg(mbox, pdev);
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cpt_send_af_reg_requests, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+static int otx2_cpt_add_read_af_reg(struct otx2_mbox *mbox,
+				    struct pci_dev *pdev, u64 reg,
+				    u64 *val, int blkaddr)
+{
+	struct cpt_rd_wr_reg_msg *reg_msg;
+
+	reg_msg = (struct cpt_rd_wr_reg_msg *)
+			otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*reg_msg),
+						sizeof(*reg_msg));
+	if (reg_msg == NULL) {
+		dev_err(&pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+
+	reg_msg->hdr.id = MBOX_MSG_CPT_RD_WR_REGISTER;
+	reg_msg->hdr.sig = OTX2_MBOX_REQ_SIG;
+	reg_msg->hdr.pcifunc = 0;
+
+	reg_msg->is_write = 0;
+	reg_msg->reg_offset = reg;
+	reg_msg->ret_val = val;
+	reg_msg->blkaddr = blkaddr;
+
+	return 0;
+}
+
+int otx2_cpt_add_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
+			      u64 reg, u64 val, int blkaddr)
+{
+	struct cpt_rd_wr_reg_msg *reg_msg;
+
+	reg_msg = (struct cpt_rd_wr_reg_msg *)
+			otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*reg_msg),
+						sizeof(*reg_msg));
+	if (reg_msg == NULL) {
+		dev_err(&pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+
+	reg_msg->hdr.id = MBOX_MSG_CPT_RD_WR_REGISTER;
+	reg_msg->hdr.sig = OTX2_MBOX_REQ_SIG;
+	reg_msg->hdr.pcifunc = 0;
+
+	reg_msg->is_write = 1;
+	reg_msg->reg_offset = reg;
+	reg_msg->val = val;
+	reg_msg->blkaddr = blkaddr;
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cpt_add_write_af_reg, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+int otx2_cpt_read_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
+			 u64 reg, u64 *val, int blkaddr)
+{
+	int ret;
+
+	ret = otx2_cpt_add_read_af_reg(mbox, pdev, reg, val, blkaddr);
+	if (ret)
+		return ret;
+
+	return otx2_cpt_send_mbox_msg(mbox, pdev);
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cpt_read_af_reg, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+int otx2_cpt_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
+			  u64 reg, u64 val, int blkaddr)
+{
+	int ret;
+
+	ret = otx2_cpt_add_write_af_reg(mbox, pdev, reg, val, blkaddr);
+	if (ret)
+		return ret;
+
+	return otx2_cpt_send_mbox_msg(mbox, pdev);
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cpt_write_af_reg, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+int otx2_cpt_attach_rscrs_msg(struct otx2_cptlfs_info *lfs)
+{
+	struct otx2_mbox *mbox = lfs->mbox;
+	struct rsrc_attach *req;
+	int ret;
+
+	req = (struct rsrc_attach *)
+			otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req),
+						sizeof(struct msg_rsp));
+	if (req == NULL) {
+		dev_err(&lfs->pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+
+	req->hdr.id = MBOX_MSG_ATTACH_RESOURCES;
+	req->hdr.sig = OTX2_MBOX_REQ_SIG;
+	req->hdr.pcifunc = 0;
+	req->cptlfs = lfs->lfs_num;
+	req->cpt_blkaddr = lfs->blkaddr;
+	req->modify = 1;
+	ret = otx2_cpt_send_mbox_msg(mbox, lfs->pdev);
+	if (ret)
+		return ret;
+
+	if (!lfs->are_lfs_attached)
+		ret = -EINVAL;
+
+	return ret;
+}
+
+int otx2_cpt_detach_rsrcs_msg(struct otx2_cptlfs_info *lfs)
+{
+	struct otx2_mbox *mbox = lfs->mbox;
+	struct rsrc_detach *req;
+	int ret;
+
+	req = (struct rsrc_detach *)
+				otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req),
+							sizeof(struct msg_rsp));
+	if (req == NULL) {
+		dev_err(&lfs->pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+
+	req->hdr.id = MBOX_MSG_DETACH_RESOURCES;
+	req->hdr.sig = OTX2_MBOX_REQ_SIG;
+	req->hdr.pcifunc = 0;
+	req->cptlfs = 1;
+	ret = otx2_cpt_send_mbox_msg(mbox, lfs->pdev);
+	if (ret)
+		return ret;
+
+	if (lfs->are_lfs_attached)
+		ret = -EINVAL;
+
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cpt_detach_rsrcs_msg, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+int otx2_cpt_msix_offset_msg(struct otx2_cptlfs_info *lfs)
+{
+	struct otx2_mbox *mbox = lfs->mbox;
+	struct pci_dev *pdev = lfs->pdev;
+	struct mbox_msghdr *req;
+	int ret, i;
+
+	req = otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req),
+				      sizeof(struct msix_offset_rsp));
+	if (req == NULL) {
+		dev_err(&pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+
+	req->id = MBOX_MSG_MSIX_OFFSET;
+	req->sig = OTX2_MBOX_REQ_SIG;
+	req->pcifunc = 0;
+	ret = otx2_cpt_send_mbox_msg(mbox, pdev);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < lfs->lfs_num; i++) {
+		if (lfs->lf[i].msix_offset == MSIX_VECTOR_INVALID) {
+			dev_err(&pdev->dev,
+				"Invalid msix offset %d for LF %d\n",
+				lfs->lf[i].msix_offset, i);
+			return -EINVAL;
+		}
+	}
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cpt_msix_offset_msg, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+int otx2_cpt_sync_mbox_msg(struct otx2_mbox *mbox)
+{
+	int err;
+
+	if (!otx2_mbox_nonempty(mbox, 0))
+		return 0;
+	otx2_mbox_msg_send(mbox, 0);
+	err = otx2_mbox_wait_for_rsp(mbox, 0);
+	if (err)
+		return err;
+
+	return otx2_mbox_check_rsp_msgs(mbox, 0);
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cpt_sync_mbox_msg, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+int otx2_cpt_lf_reset_msg(struct otx2_cptlfs_info *lfs, int slot)
+{
+	struct otx2_mbox *mbox = lfs->mbox;
+	struct pci_dev *pdev = lfs->pdev;
+	struct cpt_lf_rst_req *req;
+	int ret;
+
+	req = (struct cpt_lf_rst_req *)otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req),
+							       sizeof(struct msg_rsp));
+	if (!req) {
+		dev_err(&pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+
+	req->hdr.id = MBOX_MSG_CPT_LF_RESET;
+	req->hdr.sig = OTX2_MBOX_REQ_SIG;
+	req->hdr.pcifunc = 0;
+	req->slot = slot;
+	ret = otx2_cpt_send_mbox_msg(mbox, pdev);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cpt_lf_reset_msg, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+int otx2_cpt_lmtst_tbl_setup_msg(struct otx2_cptlfs_info *lfs)
+{
+	struct otx2_mbox *mbox = lfs->mbox;
+	struct pci_dev *pdev = lfs->pdev;
+	struct lmtst_tbl_setup_req *req;
+
+	req = (struct lmtst_tbl_setup_req *)
+	       otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req),
+				       sizeof(struct msg_rsp));
+	if (!req) {
+		dev_err(&pdev->dev, "RVU MBOX failed to alloc message.\n");
+		return -EFAULT;
+	}
+
+	req->hdr.id = MBOX_MSG_LMTST_TBL_SETUP;
+	req->hdr.sig = OTX2_MBOX_REQ_SIG;
+	req->hdr.pcifunc = 0;
+
+	req->use_local_lmt_region = true;
+	req->lmt_iova = lfs->lmt_info.iova;
+
+	return otx2_cpt_send_mbox_msg(mbox, pdev);
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cpt_lmtst_tbl_setup_msg, "CRYPTO_DEV_OCTEONTX2_CPT");

linux-7.2.3/drivers/crypto/marvell/octeontx2/otx2_cpt_reqmgr.h

@@ -0,0 +1,561 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2020 Marvell.
+ */
+
+#ifndef __OTX2_CPT_REQMGR_H
+#define __OTX2_CPT_REQMGR_H
+
+#include "otx2_cpt_common.h"
+
+/* Completion code size and initial value */
+#define OTX2_CPT_COMPLETION_CODE_SIZE 8
+#define OTX2_CPT_COMPLETION_CODE_INIT OTX2_CPT_COMP_E_NOTDONE
+/*
+ * Maximum total number of SG buffers is 100, we divide it equally
+ * between input and output
+ */
+#define OTX2_CPT_MAX_SG_IN_CNT  50
+#define OTX2_CPT_MAX_SG_OUT_CNT 50
+
+/* DMA mode direct or SG */
+#define OTX2_CPT_DMA_MODE_DIRECT 0
+#define OTX2_CPT_DMA_MODE_SG     1
+
+/* Context source CPTR or DPTR */
+#define OTX2_CPT_FROM_CPTR 0
+#define OTX2_CPT_FROM_DPTR 1
+
+#define OTX2_CPT_MAX_REQ_SIZE 65535
+
+#define SG_COMPS_MAX    4
+#define SGV2_COMPS_MAX  3
+
+#define SG_COMP_3    3
+#define SG_COMP_2    2
+#define SG_COMP_1    1
+
+#define OTX2_CPT_DPTR_RPTR_ALIGN	8
+#define OTX2_CPT_RES_ADDR_ALIGN		32
+
+union otx2_cpt_opcode {
+	u16 flags;
+	struct {
+		u8 major;
+		u8 minor;
+	} s;
+};
+
+struct otx2_cptvf_request {
+	u32 param1;
+	u32 param2;
+	u16 dlen;
+	union otx2_cpt_opcode opcode;
+	dma_addr_t cptr_dma;
+	void *cptr;
+};
+
+/*
+ * CPT_INST_S software command definitions
+ * Words EI (0-3)
+ */
+union otx2_cpt_iq_cmd_word0 {
+	u64 u;
+	struct {
+		__be16 opcode;
+		__be16 param1;
+		__be16 param2;
+		__be16 dlen;
+	} s;
+};
+
+union otx2_cpt_iq_cmd_word3 {
+	u64 u;
+	struct {
+		u64 cptr:61;
+		u64 grp:3;
+	} s;
+};
+
+struct otx2_cpt_iq_command {
+	union otx2_cpt_iq_cmd_word0 cmd;
+	u64 dptr;
+	u64 rptr;
+	union otx2_cpt_iq_cmd_word3 cptr;
+};
+
+struct otx2_cpt_pending_entry {
+	void *completion_addr;	/* Completion address */
+	void *info;
+	/* Kernel async request callback */
+	void (*callback)(int status, void *arg1, void *arg2);
+	struct crypto_async_request *areq; /* Async request callback arg */
+	u8 resume_sender;	/* Notify sender to resume sending requests */
+	u8 busy;		/* Entry status (free/busy) */
+};
+
+struct otx2_cpt_pending_queue {
+	struct otx2_cpt_pending_entry *head; /* Head of the queue */
+	u32 front;		/* Process work from here */
+	u32 rear;		/* Append new work here */
+	u32 pending_count;	/* Pending requests count */
+	u32 qlen;		/* Queue length */
+	spinlock_t lock;	/* Queue lock */
+};
+
+struct otx2_cpt_buf_ptr {
+	u8 *vptr;
+	dma_addr_t dma_addr;
+	u16 size;
+};
+
+union otx2_cpt_ctrl_info {
+	u32 flags;
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u32 reserved_6_31:26;
+		u32 grp:3;	/* Group bits */
+		u32 dma_mode:2;	/* DMA mode */
+		u32 se_req:1;	/* To SE core */
+#else
+		u32 se_req:1;	/* To SE core */
+		u32 dma_mode:2;	/* DMA mode */
+		u32 grp:3;	/* Group bits */
+		u32 reserved_6_31:26;
+#endif
+	} s;
+};
+
+struct otx2_cpt_req_info {
+	/* Kernel async request callback */
+	void (*callback)(int status, void *arg1, void *arg2);
+	struct crypto_async_request *areq; /* Async request callback arg */
+	struct otx2_cptvf_request req;/* Request information (core specific) */
+	union otx2_cpt_ctrl_info ctrl;/* User control information */
+	struct otx2_cpt_buf_ptr in[OTX2_CPT_MAX_SG_IN_CNT];
+	struct otx2_cpt_buf_ptr out[OTX2_CPT_MAX_SG_OUT_CNT];
+	u8 *iv_out;     /* IV to send back */
+	u16 rlen;	/* Output length */
+	u8 in_cnt;	/* Number of input buffers */
+	u8 out_cnt;	/* Number of output buffers */
+	u8 req_type;	/* Type of request */
+	u8 is_enc;	/* Is a request an encryption request */
+	u8 is_trunc_hmac;/* Is truncated hmac used */
+};
+
+struct otx2_cpt_inst_info {
+	struct otx2_cpt_pending_entry *pentry;
+	struct otx2_cpt_req_info *req;
+	struct pci_dev *pdev;
+	void *completion_addr;
+	u8 *out_buffer;
+	u8 *in_buffer;
+	dma_addr_t dptr_baddr;
+	dma_addr_t rptr_baddr;
+	dma_addr_t comp_baddr;
+	unsigned long time_in;
+	u32 dlen;
+	u32 dma_len;
+	u64 gthr_sz;
+	u64 sctr_sz;
+	u8 extra_time;
+};
+
+struct otx2_cpt_sglist_component {
+	__be16 len0;
+	__be16 len1;
+	__be16 len2;
+	__be16 len3;
+	__be64 ptr0;
+	__be64 ptr1;
+	__be64 ptr2;
+	__be64 ptr3;
+};
+
+struct cn10kb_cpt_sglist_component {
+	u16 len0;
+	u16 len1;
+	u16 len2;
+	u16 valid_segs;
+	u64 ptr0;
+	u64 ptr1;
+	u64 ptr2;
+};
+
+static inline void otx2_cpt_info_destroy(struct pci_dev *pdev,
+					 struct otx2_cpt_inst_info *info)
+{
+	struct otx2_cpt_req_info *req;
+	int i;
+
+	if (info->dptr_baddr)
+		dma_unmap_single(&pdev->dev, info->dptr_baddr,
+				 info->dma_len, DMA_BIDIRECTIONAL);
+
+	if (info->req) {
+		req = info->req;
+		for (i = 0; i < req->out_cnt; i++) {
+			if (req->out[i].dma_addr)
+				dma_unmap_single(&pdev->dev,
+						 req->out[i].dma_addr,
+						 req->out[i].size,
+						 DMA_BIDIRECTIONAL);
+		}
+
+		for (i = 0; i < req->in_cnt; i++) {
+			if (req->in[i].dma_addr)
+				dma_unmap_single(&pdev->dev,
+						 req->in[i].dma_addr,
+						 req->in[i].size,
+						 DMA_BIDIRECTIONAL);
+		}
+	}
+	kfree(info);
+}
+
+static inline int setup_sgio_components(struct pci_dev *pdev,
+					struct otx2_cpt_buf_ptr *list,
+					int buf_count, u8 *buffer)
+{
+	struct otx2_cpt_sglist_component *sg_ptr;
+	int components;
+	int i, j;
+
+	if (unlikely(!list)) {
+		dev_err(&pdev->dev, "Input list pointer is NULL\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < buf_count; i++) {
+		if (unlikely(!list[i].vptr))
+			continue;
+		list[i].dma_addr = dma_map_single(&pdev->dev, list[i].vptr,
+						  list[i].size,
+						  DMA_BIDIRECTIONAL);
+		if (unlikely(dma_mapping_error(&pdev->dev, list[i].dma_addr))) {
+			dev_err(&pdev->dev, "Dma mapping failed\n");
+			goto sg_cleanup;
+		}
+	}
+	components = buf_count / SG_COMPS_MAX;
+	sg_ptr = (struct otx2_cpt_sglist_component *)buffer;
+	for (i = 0; i < components; i++) {
+		sg_ptr->len0 = cpu_to_be16(list[i * SG_COMPS_MAX + 0].size);
+		sg_ptr->len1 = cpu_to_be16(list[i * SG_COMPS_MAX + 1].size);
+		sg_ptr->len2 = cpu_to_be16(list[i * SG_COMPS_MAX + 2].size);
+		sg_ptr->len3 = cpu_to_be16(list[i * SG_COMPS_MAX + 3].size);
+		sg_ptr->ptr0 = cpu_to_be64(list[i * SG_COMPS_MAX + 0].dma_addr);
+		sg_ptr->ptr1 = cpu_to_be64(list[i * SG_COMPS_MAX + 1].dma_addr);
+		sg_ptr->ptr2 = cpu_to_be64(list[i * SG_COMPS_MAX + 2].dma_addr);
+		sg_ptr->ptr3 = cpu_to_be64(list[i * SG_COMPS_MAX + 3].dma_addr);
+		sg_ptr++;
+	}
+	components = buf_count % SG_COMPS_MAX;
+
+	switch (components) {
+	case SG_COMP_3:
+		sg_ptr->len2 = cpu_to_be16(list[i * SG_COMPS_MAX + 2].size);
+		sg_ptr->ptr2 = cpu_to_be64(list[i * SG_COMPS_MAX + 2].dma_addr);
+		fallthrough;
+	case SG_COMP_2:
+		sg_ptr->len1 = cpu_to_be16(list[i * SG_COMPS_MAX + 1].size);
+		sg_ptr->ptr1 = cpu_to_be64(list[i * SG_COMPS_MAX + 1].dma_addr);
+		fallthrough;
+	case SG_COMP_1:
+		sg_ptr->len0 = cpu_to_be16(list[i * SG_COMPS_MAX + 0].size);
+		sg_ptr->ptr0 = cpu_to_be64(list[i * SG_COMPS_MAX + 0].dma_addr);
+		break;
+	default:
+		break;
+	}
+	return 0;
+
+sg_cleanup:
+	for (j = 0; j < i; j++) {
+		if (list[j].dma_addr) {
+			dma_unmap_single(&pdev->dev, list[j].dma_addr,
+					 list[j].size, DMA_BIDIRECTIONAL);
+		}
+
+		list[j].dma_addr = 0;
+	}
+	return -EIO;
+}
+
+static inline int sgv2io_components_setup(struct pci_dev *pdev,
+					  struct otx2_cpt_buf_ptr *list,
+					  int buf_count, u8 *buffer)
+{
+	struct cn10kb_cpt_sglist_component *sg_ptr;
+	int components;
+	int i, j;
+
+	if (unlikely(!list)) {
+		dev_err(&pdev->dev, "Input list pointer is NULL\n");
+		return -EFAULT;
+	}
+
+	for (i = 0; i < buf_count; i++) {
+		if (unlikely(!list[i].vptr))
+			continue;
+		list[i].dma_addr = dma_map_single(&pdev->dev, list[i].vptr,
+						  list[i].size,
+						  DMA_BIDIRECTIONAL);
+		if (unlikely(dma_mapping_error(&pdev->dev, list[i].dma_addr))) {
+			dev_err(&pdev->dev, "Dma mapping failed\n");
+			goto sg_cleanup;
+		}
+	}
+	components = buf_count / SGV2_COMPS_MAX;
+	sg_ptr = (struct cn10kb_cpt_sglist_component *)buffer;
+	for (i = 0; i < components; i++) {
+		sg_ptr->len0 = list[i * SGV2_COMPS_MAX + 0].size;
+		sg_ptr->len1 = list[i * SGV2_COMPS_MAX + 1].size;
+		sg_ptr->len2 = list[i * SGV2_COMPS_MAX + 2].size;
+		sg_ptr->ptr0 = list[i * SGV2_COMPS_MAX + 0].dma_addr;
+		sg_ptr->ptr1 = list[i * SGV2_COMPS_MAX + 1].dma_addr;
+		sg_ptr->ptr2 = list[i * SGV2_COMPS_MAX + 2].dma_addr;
+		sg_ptr->valid_segs = SGV2_COMPS_MAX;
+		sg_ptr++;
+	}
+	components = buf_count % SGV2_COMPS_MAX;
+
+	sg_ptr->valid_segs = components;
+	switch (components) {
+	case SG_COMP_2:
+		sg_ptr->len1 = list[i * SGV2_COMPS_MAX + 1].size;
+		sg_ptr->ptr1 = list[i * SGV2_COMPS_MAX + 1].dma_addr;
+		fallthrough;
+	case SG_COMP_1:
+		sg_ptr->len0 = list[i * SGV2_COMPS_MAX + 0].size;
+		sg_ptr->ptr0 = list[i * SGV2_COMPS_MAX + 0].dma_addr;
+		break;
+	default:
+		break;
+	}
+	return 0;
+
+sg_cleanup:
+	for (j = 0; j < i; j++) {
+		if (list[j].dma_addr) {
+			dma_unmap_single(&pdev->dev, list[j].dma_addr,
+					 list[j].size, DMA_BIDIRECTIONAL);
+		}
+
+		list[j].dma_addr = 0;
+	}
+	return -EIO;
+}
+
+static inline struct otx2_cpt_inst_info *
+cn10k_sgv2_info_create(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
+		       gfp_t gfp)
+{
+	u32 dlen = 0, g_len, s_len, sg_len, info_len;
+	struct otx2_cpt_inst_info *info;
+	u32 total_mem_len;
+	int i;
+
+	/* Allocate memory to meet below alignment requirement:
+	 *  ------------------------------------
+	 * |    struct otx2_cpt_inst_info       |
+	 * |    (No alignment required)         |
+	 * |    --------------------------------|
+	 * |   | padding for ARCH_DMA_MINALIGN  |
+	 * |   | alignment                      |
+	 * |------------------------------------|
+	 * |    SG List Gather/Input memory     |
+	 * |    Length = multiple of 32Bytes    |
+	 * |    Alignment = 8Byte               |
+	 * |----------------------------------  |
+	 * |    SG List Scatter/Output memory   |
+	 * |    Length = multiple of 32Bytes    |
+	 * |    Alignment = 8Byte               |
+	 * |     -------------------------------|
+	 * |    | padding for 32B alignment     |
+	 * |------------------------------------|
+	 * |    Result response memory          |
+	 * |    Alignment = 32Byte              |
+	 *  ------------------------------------
+	 */
+
+	info_len = sizeof(*info);
+
+	g_len = ((req->in_cnt + 2) / 3) *
+		 sizeof(struct cn10kb_cpt_sglist_component);
+	s_len = ((req->out_cnt + 2) / 3) *
+		 sizeof(struct cn10kb_cpt_sglist_component);
+	sg_len = g_len + s_len;
+
+	/* Allocate extra memory for SG and response address alignment */
+	total_mem_len = ALIGN(info_len, OTX2_CPT_DPTR_RPTR_ALIGN);
+	total_mem_len += (ARCH_DMA_MINALIGN - 1) &
+			  ~(OTX2_CPT_DPTR_RPTR_ALIGN - 1);
+	total_mem_len += ALIGN(sg_len, OTX2_CPT_RES_ADDR_ALIGN);
+	total_mem_len += sizeof(union otx2_cpt_res_s);
+
+	info = kzalloc(total_mem_len, gfp);
+	if (unlikely(!info))
+		return NULL;
+
+	for (i = 0; i < req->in_cnt; i++)
+		dlen += req->in[i].size;
+
+	info->dlen = dlen;
+	info->in_buffer = PTR_ALIGN((u8 *)info + info_len, ARCH_DMA_MINALIGN);
+	info->out_buffer = info->in_buffer + g_len;
+	info->gthr_sz = req->in_cnt;
+	info->sctr_sz = req->out_cnt;
+
+	/* Setup gather (input) components */
+	if (sgv2io_components_setup(pdev, req->in, req->in_cnt,
+				    info->in_buffer)) {
+		dev_err(&pdev->dev, "Failed to setup gather list\n");
+		goto destroy_info;
+	}
+
+	if (sgv2io_components_setup(pdev, req->out, req->out_cnt,
+				    info->out_buffer)) {
+		dev_err(&pdev->dev, "Failed to setup scatter list\n");
+		goto destroy_info;
+	}
+
+	info->dma_len = total_mem_len - info_len;
+	info->dptr_baddr = dma_map_single(&pdev->dev, info->in_buffer,
+					  info->dma_len, DMA_BIDIRECTIONAL);
+	if (unlikely(dma_mapping_error(&pdev->dev, info->dptr_baddr))) {
+		dev_err(&pdev->dev, "DMA Mapping failed for cpt req\n");
+		goto destroy_info;
+	}
+	info->rptr_baddr = info->dptr_baddr + g_len;
+	/*
+	 * Get buffer for union otx2_cpt_res_s response
+	 * structure and its physical address
+	 */
+	info->completion_addr = PTR_ALIGN((info->in_buffer + sg_len),
+					  OTX2_CPT_RES_ADDR_ALIGN);
+	info->comp_baddr = ALIGN((info->dptr_baddr + sg_len),
+				 OTX2_CPT_RES_ADDR_ALIGN);
+
+	return info;
+
+destroy_info:
+	otx2_cpt_info_destroy(pdev, info);
+	return NULL;
+}
+
+/* SG list header size in bytes */
+#define SG_LIST_HDR_SIZE	8
+static inline struct otx2_cpt_inst_info *
+otx2_sg_info_create(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
+		    gfp_t gfp)
+{
+	struct otx2_cpt_inst_info *info;
+	u32 dlen, info_len;
+	u16 g_len, s_len;
+	u32 total_mem_len;
+
+	if (unlikely(req->in_cnt > OTX2_CPT_MAX_SG_IN_CNT ||
+		     req->out_cnt > OTX2_CPT_MAX_SG_OUT_CNT)) {
+		dev_err(&pdev->dev, "Error too many sg components\n");
+		return NULL;
+	}
+
+	/* Allocate memory to meet below alignment requirement:
+	 *  ------------------------------------
+	 * |    struct otx2_cpt_inst_info       |
+	 * |    (No alignment required)         |
+	 * |    --------------------------------|
+	 * |   | padding for ARCH_DMA_MINALIGN  |
+	 * |   | alignment                      |
+	 * |------------------------------------|
+	 * |    SG List Header of 8 Byte        |
+	 * |------------------------------------|
+	 * |    SG List Gather/Input memory     |
+	 * |    Length = multiple of 32Bytes    |
+	 * |    Alignment = 8Byte               |
+	 * |----------------------------------  |
+	 * |    SG List Scatter/Output memory   |
+	 * |    Length = multiple of 32Bytes    |
+	 * |    Alignment = 8Byte               |
+	 * |     -------------------------------|
+	 * |    | padding for 32B alignment     |
+	 * |------------------------------------|
+	 * |    Result response memory          |
+	 * |    Alignment = 32Byte              |
+	 *  ------------------------------------
+	 */
+
+	info_len = sizeof(*info);
+
+	g_len = ((req->in_cnt + 3) / 4) *
+		 sizeof(struct otx2_cpt_sglist_component);
+	s_len = ((req->out_cnt + 3) / 4) *
+		 sizeof(struct otx2_cpt_sglist_component);
+
+	dlen = g_len + s_len + SG_LIST_HDR_SIZE;
+
+	/* Allocate extra memory for SG and response address alignment */
+	total_mem_len = ALIGN(info_len, OTX2_CPT_DPTR_RPTR_ALIGN);
+	total_mem_len += (ARCH_DMA_MINALIGN - 1) &
+			  ~(OTX2_CPT_DPTR_RPTR_ALIGN - 1);
+	total_mem_len += ALIGN(dlen, OTX2_CPT_RES_ADDR_ALIGN);
+	total_mem_len += sizeof(union otx2_cpt_res_s);
+
+	info = kzalloc(total_mem_len, gfp);
+	if (unlikely(!info))
+		return NULL;
+
+	info->dlen = dlen;
+	info->in_buffer = PTR_ALIGN((u8 *)info + info_len, ARCH_DMA_MINALIGN);
+	info->out_buffer = info->in_buffer + SG_LIST_HDR_SIZE + g_len;
+
+	((u16 *)info->in_buffer)[0] = req->out_cnt;
+	((u16 *)info->in_buffer)[1] = req->in_cnt;
+	((u16 *)info->in_buffer)[2] = 0;
+	((u16 *)info->in_buffer)[3] = 0;
+	cpu_to_be64s((u64 *)info->in_buffer);
+
+	/* Setup gather (input) components */
+	if (setup_sgio_components(pdev, req->in, req->in_cnt,
+				  &info->in_buffer[8])) {
+		dev_err(&pdev->dev, "Failed to setup gather list\n");
+		goto destroy_info;
+	}
+
+	if (setup_sgio_components(pdev, req->out, req->out_cnt,
+				  info->out_buffer)) {
+		dev_err(&pdev->dev, "Failed to setup scatter list\n");
+		goto destroy_info;
+	}
+
+	info->dma_len = total_mem_len - info_len;
+	info->dptr_baddr = dma_map_single(&pdev->dev, info->in_buffer,
+					  info->dma_len, DMA_BIDIRECTIONAL);
+	if (unlikely(dma_mapping_error(&pdev->dev, info->dptr_baddr))) {
+		dev_err(&pdev->dev, "DMA Mapping failed for cpt req\n");
+		goto destroy_info;
+	}
+	/*
+	 * Get buffer for union otx2_cpt_res_s response
+	 * structure and its physical address
+	 */
+	info->completion_addr = PTR_ALIGN((info->in_buffer + dlen),
+					  OTX2_CPT_RES_ADDR_ALIGN);
+	info->comp_baddr = ALIGN((info->dptr_baddr + dlen),
+				 OTX2_CPT_RES_ADDR_ALIGN);
+
+	return info;
+
+destroy_info:
+	otx2_cpt_info_destroy(pdev, info);
+	return NULL;
+}
+
+struct otx2_cptlf_wqe;
+int otx2_cpt_do_request(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
+			int cpu_num);
+void otx2_cpt_post_process(struct otx2_cptlf_wqe *wqe);
+int otx2_cpt_get_eng_grp_num(struct pci_dev *pdev,
+			     enum otx2_cpt_eng_type);
+
+#endif /* __OTX2_CPT_REQMGR_H */

linux-7.2.3/drivers/crypto/marvell/octeontx2/otx2_cptlf.c

@@ -0,0 +1,498 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Marvell. */
+
+#include "otx2_cpt_common.h"
+#include "otx2_cptlf.h"
+#include "rvu_reg.h"
+
+#define CPT_TIMER_HOLD 0x03F
+#define CPT_COUNT_HOLD 32
+
+static void cptlf_do_set_done_time_wait(struct otx2_cptlf_info *lf,
+					int time_wait)
+{
+	union otx2_cptx_lf_done_wait done_wait;
+
+	done_wait.u = otx2_cpt_read64(lf->lfs->reg_base, lf->lfs->blkaddr,
+				      lf->slot, OTX2_CPT_LF_DONE_WAIT);
+	done_wait.s.time_wait = time_wait;
+	otx2_cpt_write64(lf->lfs->reg_base, lf->lfs->blkaddr, lf->slot,
+			 OTX2_CPT_LF_DONE_WAIT, done_wait.u);
+}
+
+static void cptlf_do_set_done_num_wait(struct otx2_cptlf_info *lf, int num_wait)
+{
+	union otx2_cptx_lf_done_wait done_wait;
+
+	done_wait.u = otx2_cpt_read64(lf->lfs->reg_base, lf->lfs->blkaddr,
+				      lf->slot, OTX2_CPT_LF_DONE_WAIT);
+	done_wait.s.num_wait = num_wait;
+	otx2_cpt_write64(lf->lfs->reg_base, lf->lfs->blkaddr, lf->slot,
+			 OTX2_CPT_LF_DONE_WAIT, done_wait.u);
+}
+
+static void cptlf_set_done_time_wait(struct otx2_cptlfs_info *lfs,
+				     int time_wait)
+{
+	int slot;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++)
+		cptlf_do_set_done_time_wait(&lfs->lf[slot], time_wait);
+}
+
+static void cptlf_set_done_num_wait(struct otx2_cptlfs_info *lfs, int num_wait)
+{
+	int slot;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++)
+		cptlf_do_set_done_num_wait(&lfs->lf[slot], num_wait);
+}
+
+static int cptlf_set_pri(struct otx2_cptlf_info *lf, int pri)
+{
+	struct otx2_cptlfs_info *lfs = lf->lfs;
+	union otx2_cptx_af_lf_ctrl lf_ctrl;
+	int ret;
+
+	ret = otx2_cpt_read_af_reg(lfs->mbox, lfs->pdev,
+				   CPT_AF_LFX_CTL(lf->slot),
+				   &lf_ctrl.u, lfs->blkaddr);
+	if (ret)
+		return ret;
+
+	lf_ctrl.s.pri = pri ? 1 : 0;
+
+	ret = otx2_cpt_write_af_reg(lfs->mbox, lfs->pdev,
+				    CPT_AF_LFX_CTL(lf->slot),
+				    lf_ctrl.u, lfs->blkaddr);
+	return ret;
+}
+
+static int cptlf_set_eng_grps_mask(struct otx2_cptlf_info *lf,
+				   int eng_grps_mask)
+{
+	struct otx2_cptlfs_info *lfs = lf->lfs;
+	union otx2_cptx_af_lf_ctrl lf_ctrl;
+	int ret;
+
+	ret = otx2_cpt_read_af_reg(lfs->mbox, lfs->pdev,
+				   CPT_AF_LFX_CTL(lf->slot),
+				   &lf_ctrl.u, lfs->blkaddr);
+	if (ret)
+		return ret;
+
+	lf_ctrl.s.grp = eng_grps_mask;
+
+	ret = otx2_cpt_write_af_reg(lfs->mbox, lfs->pdev,
+				    CPT_AF_LFX_CTL(lf->slot),
+				    lf_ctrl.u, lfs->blkaddr);
+	return ret;
+}
+
+static int cptlf_set_grp_and_pri(struct otx2_cptlfs_info *lfs,
+				 int eng_grp_mask, int pri)
+{
+	int slot, ret = 0;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		ret = cptlf_set_pri(&lfs->lf[slot], pri);
+		if (ret)
+			return ret;
+
+		ret = cptlf_set_eng_grps_mask(&lfs->lf[slot], eng_grp_mask);
+		if (ret)
+			return ret;
+	}
+	return ret;
+}
+
+static int cptlf_set_ctx_ilen(struct otx2_cptlfs_info *lfs, int ctx_ilen)
+{
+	union otx2_cptx_af_lf_ctrl lf_ctrl;
+	struct otx2_cptlf_info *lf;
+	int slot, ret = 0;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		lf = &lfs->lf[slot];
+
+		ret = otx2_cpt_read_af_reg(lfs->mbox, lfs->pdev,
+					   CPT_AF_LFX_CTL(lf->slot),
+					   &lf_ctrl.u, lfs->blkaddr);
+		if (ret)
+			return ret;
+
+		lf_ctrl.s.ctx_ilen = ctx_ilen;
+
+		ret = otx2_cpt_write_af_reg(lfs->mbox, lfs->pdev,
+					    CPT_AF_LFX_CTL(lf->slot),
+					    lf_ctrl.u, lfs->blkaddr);
+		if (ret)
+			return ret;
+	}
+	return ret;
+}
+
+static void cptlf_hw_init(struct otx2_cptlfs_info *lfs)
+{
+	/* Disable instruction queues */
+	otx2_cptlf_disable_iqueues(lfs);
+
+	/* Set instruction queues base addresses */
+	otx2_cptlf_set_iqueues_base_addr(lfs);
+
+	/* Set instruction queues sizes */
+	otx2_cptlf_set_iqueues_size(lfs);
+
+	/* Set done interrupts time wait */
+	cptlf_set_done_time_wait(lfs, CPT_TIMER_HOLD);
+
+	/* Set done interrupts num wait */
+	cptlf_set_done_num_wait(lfs, CPT_COUNT_HOLD);
+
+	/* Enable instruction queues */
+	otx2_cptlf_enable_iqueues(lfs);
+}
+
+static void cptlf_hw_cleanup(struct otx2_cptlfs_info *lfs)
+{
+	/* Disable instruction queues */
+	otx2_cptlf_disable_iqueues(lfs);
+}
+
+static void cptlf_set_misc_intrs(struct otx2_cptlfs_info *lfs, u8 enable)
+{
+	union otx2_cptx_lf_misc_int_ena_w1s irq_misc = { .u = 0x0 };
+	u64 reg = enable ? OTX2_CPT_LF_MISC_INT_ENA_W1S :
+			   OTX2_CPT_LF_MISC_INT_ENA_W1C;
+	int slot;
+
+	irq_misc.s.fault = 0x1;
+	irq_misc.s.hwerr = 0x1;
+	irq_misc.s.irde = 0x1;
+	irq_misc.s.nqerr = 0x1;
+	irq_misc.s.nwrp = 0x1;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++)
+		otx2_cpt_write64(lfs->reg_base, lfs->blkaddr, slot, reg,
+				 irq_misc.u);
+}
+
+static void cptlf_set_done_intrs(struct otx2_cptlfs_info *lfs, u8 enable)
+{
+	u64 reg = enable ? OTX2_CPT_LF_DONE_INT_ENA_W1S :
+			   OTX2_CPT_LF_DONE_INT_ENA_W1C;
+	int slot;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++)
+		otx2_cpt_write64(lfs->reg_base, lfs->blkaddr, slot, reg, 0x1);
+}
+
+static inline int cptlf_read_done_cnt(struct otx2_cptlf_info *lf)
+{
+	union otx2_cptx_lf_done irq_cnt;
+
+	irq_cnt.u = otx2_cpt_read64(lf->lfs->reg_base, lf->lfs->blkaddr, lf->slot,
+				    OTX2_CPT_LF_DONE);
+	return irq_cnt.s.done;
+}
+
+static irqreturn_t cptlf_misc_intr_handler(int __always_unused irq, void *arg)
+{
+	union otx2_cptx_lf_misc_int irq_misc, irq_misc_ack;
+	struct otx2_cptlf_info *lf = arg;
+	struct device *dev;
+
+	dev = &lf->lfs->pdev->dev;
+	irq_misc.u = otx2_cpt_read64(lf->lfs->reg_base, lf->lfs->blkaddr,
+				     lf->slot, OTX2_CPT_LF_MISC_INT);
+	irq_misc_ack.u = 0x0;
+
+	if (irq_misc.s.fault) {
+		dev_err(dev, "Memory error detected while executing CPT_INST_S, LF %d.\n",
+			lf->slot);
+		irq_misc_ack.s.fault = 0x1;
+
+	} else if (irq_misc.s.hwerr) {
+		dev_err(dev, "HW error from an engine executing CPT_INST_S, LF %d.",
+			lf->slot);
+		irq_misc_ack.s.hwerr = 0x1;
+
+	} else if (irq_misc.s.nwrp) {
+		dev_err(dev, "SMMU fault while writing CPT_RES_S to CPT_INST_S[RES_ADDR], LF %d.\n",
+			lf->slot);
+		irq_misc_ack.s.nwrp = 0x1;
+
+	} else if (irq_misc.s.irde) {
+		dev_err(dev, "Memory error when accessing instruction memory queue CPT_LF_Q_BASE[ADDR].\n");
+		irq_misc_ack.s.irde = 0x1;
+
+	} else if (irq_misc.s.nqerr) {
+		dev_err(dev, "Error enqueuing an instruction received at CPT_LF_NQ.\n");
+		irq_misc_ack.s.nqerr = 0x1;
+
+	} else {
+		dev_err(dev, "Unhandled interrupt in CPT LF %d\n", lf->slot);
+		return IRQ_NONE;
+	}
+
+	/* Acknowledge interrupts */
+	otx2_cpt_write64(lf->lfs->reg_base, lf->lfs->blkaddr, lf->slot,
+			 OTX2_CPT_LF_MISC_INT, irq_misc_ack.u);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t cptlf_done_intr_handler(int irq, void *arg)
+{
+	union otx2_cptx_lf_done_wait done_wait;
+	struct otx2_cptlf_info *lf = arg;
+	int irq_cnt;
+
+	/* Read the number of completed requests */
+	irq_cnt = cptlf_read_done_cnt(lf);
+	if (irq_cnt) {
+		done_wait.u = otx2_cpt_read64(lf->lfs->reg_base, lf->lfs->blkaddr,
+					      lf->slot, OTX2_CPT_LF_DONE_WAIT);
+		/* Acknowledge the number of completed requests */
+		otx2_cpt_write64(lf->lfs->reg_base, lf->lfs->blkaddr, lf->slot,
+				 OTX2_CPT_LF_DONE_ACK, irq_cnt);
+
+		otx2_cpt_write64(lf->lfs->reg_base, lf->lfs->blkaddr, lf->slot,
+				 OTX2_CPT_LF_DONE_WAIT, done_wait.u);
+		if (unlikely(!lf->wqe)) {
+			dev_err(&lf->lfs->pdev->dev, "No work for LF %d\n",
+				lf->slot);
+			return IRQ_NONE;
+		}
+
+		/* Schedule processing of completed requests */
+		tasklet_hi_schedule(&lf->wqe->work);
+	}
+	return IRQ_HANDLED;
+}
+
+void otx2_cptlf_unregister_misc_interrupts(struct otx2_cptlfs_info *lfs)
+{
+	int i, irq_offs, vector;
+
+	irq_offs = OTX2_CPT_LF_INT_VEC_E_MISC;
+	for (i = 0; i < lfs->lfs_num; i++) {
+		if (!lfs->lf[i].is_irq_reg[irq_offs])
+			continue;
+
+		vector = pci_irq_vector(lfs->pdev,
+					lfs->lf[i].msix_offset + irq_offs);
+		free_irq(vector, &lfs->lf[i]);
+		lfs->lf[i].is_irq_reg[irq_offs] = false;
+	}
+
+	cptlf_set_misc_intrs(lfs, false);
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cptlf_unregister_misc_interrupts, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+void otx2_cptlf_unregister_done_interrupts(struct otx2_cptlfs_info *lfs)
+{
+	int i, irq_offs, vector;
+
+	irq_offs = OTX2_CPT_LF_INT_VEC_E_DONE;
+	for (i = 0; i < lfs->lfs_num; i++) {
+		if (!lfs->lf[i].is_irq_reg[irq_offs])
+			continue;
+
+		vector = pci_irq_vector(lfs->pdev,
+					lfs->lf[i].msix_offset + irq_offs);
+		free_irq(vector, &lfs->lf[i]);
+		lfs->lf[i].is_irq_reg[irq_offs] = false;
+	}
+
+	cptlf_set_done_intrs(lfs, false);
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cptlf_unregister_done_interrupts, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+static int cptlf_do_register_interrrupts(struct otx2_cptlfs_info *lfs,
+					 int lf_num, int irq_offset,
+					 irq_handler_t handler)
+{
+	int ret, vector;
+
+	vector = pci_irq_vector(lfs->pdev, lfs->lf[lf_num].msix_offset +
+				irq_offset);
+	ret = request_irq(vector, handler, 0,
+			  lfs->lf[lf_num].irq_name[irq_offset],
+			  &lfs->lf[lf_num]);
+	if (ret)
+		return ret;
+
+	lfs->lf[lf_num].is_irq_reg[irq_offset] = true;
+
+	return ret;
+}
+
+int otx2_cptlf_register_misc_interrupts(struct otx2_cptlfs_info *lfs)
+{
+	bool is_cpt1 = (lfs->blkaddr == BLKADDR_CPT1);
+	int irq_offs, ret, i;
+
+	irq_offs = OTX2_CPT_LF_INT_VEC_E_MISC;
+	for (i = 0; i < lfs->lfs_num; i++) {
+		snprintf(lfs->lf[i].irq_name[irq_offs], 32, "CPT%dLF Misc%d",
+			 is_cpt1, i);
+		ret = cptlf_do_register_interrrupts(lfs, i, irq_offs,
+						    cptlf_misc_intr_handler);
+		if (ret)
+			goto free_irq;
+	}
+	cptlf_set_misc_intrs(lfs, true);
+	return 0;
+
+free_irq:
+	otx2_cptlf_unregister_misc_interrupts(lfs);
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cptlf_register_misc_interrupts, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+int otx2_cptlf_register_done_interrupts(struct otx2_cptlfs_info *lfs)
+{
+	bool is_cpt1 = (lfs->blkaddr == BLKADDR_CPT1);
+	int irq_offs, ret, i;
+
+	irq_offs = OTX2_CPT_LF_INT_VEC_E_DONE;
+	for (i = 0; i < lfs->lfs_num; i++) {
+		snprintf(lfs->lf[i].irq_name[irq_offs], 32,
+			 "OTX2_CPT%dLF Done%d", is_cpt1, i);
+		ret = cptlf_do_register_interrrupts(lfs, i, irq_offs,
+						    cptlf_done_intr_handler);
+		if (ret)
+			goto free_irq;
+	}
+	cptlf_set_done_intrs(lfs, true);
+	return 0;
+
+free_irq:
+	otx2_cptlf_unregister_done_interrupts(lfs);
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cptlf_register_done_interrupts, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+void otx2_cptlf_free_irqs_affinity(struct otx2_cptlfs_info *lfs)
+{
+	int slot, offs;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		for (offs = 0; offs < OTX2_CPT_LF_MSIX_VECTORS; offs++)
+			irq_set_affinity_hint(pci_irq_vector(lfs->pdev,
+					      lfs->lf[slot].msix_offset +
+					      offs), NULL);
+		free_cpumask_var(lfs->lf[slot].affinity_mask);
+	}
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cptlf_free_irqs_affinity, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+int otx2_cptlf_set_irqs_affinity(struct otx2_cptlfs_info *lfs)
+{
+	struct otx2_cptlf_info *lf = lfs->lf;
+	int slot, offs, ret;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		if (!zalloc_cpumask_var(&lf[slot].affinity_mask, GFP_KERNEL)) {
+			dev_err(&lfs->pdev->dev,
+				"cpumask allocation failed for LF %d", slot);
+			ret = -ENOMEM;
+			goto free_affinity_mask;
+		}
+
+		cpumask_set_cpu(cpumask_local_spread(slot,
+				dev_to_node(&lfs->pdev->dev)),
+				lf[slot].affinity_mask);
+
+		for (offs = 0; offs < OTX2_CPT_LF_MSIX_VECTORS; offs++) {
+			ret = irq_set_affinity_hint(pci_irq_vector(lfs->pdev,
+						lf[slot].msix_offset + offs),
+						lf[slot].affinity_mask);
+			if (ret)
+				goto free_affinity_mask;
+		}
+	}
+	return 0;
+
+free_affinity_mask:
+	otx2_cptlf_free_irqs_affinity(lfs);
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cptlf_set_irqs_affinity, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+int otx2_cptlf_init(struct otx2_cptlfs_info *lfs, u8 eng_grp_mask, int pri,
+		    int lfs_num)
+{
+	int slot, ret;
+
+	if (!lfs->pdev || !lfs->reg_base)
+		return -EINVAL;
+
+	lfs->lfs_num = lfs_num;
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		lfs->lf[slot].lfs = lfs;
+		lfs->lf[slot].slot = slot;
+		if (!lfs->lmt_info.base)
+			lfs->lf[slot].lmtline = lfs->reg_base +
+				OTX2_CPT_RVU_FUNC_ADDR_S(BLKADDR_LMT, slot,
+						 OTX2_CPT_LMT_LF_LMTLINEX(0));
+
+		lfs->lf[slot].ioreg = lfs->reg_base +
+			OTX2_CPT_RVU_FUNC_ADDR_S(lfs->blkaddr, slot,
+						 OTX2_CPT_LF_NQX(0));
+	}
+	/* Send request to attach LFs */
+	ret = otx2_cpt_attach_rscrs_msg(lfs);
+	if (ret)
+		goto clear_lfs_num;
+
+	ret = otx2_cpt_alloc_instruction_queues(lfs);
+	if (ret) {
+		dev_err(&lfs->pdev->dev,
+			"Allocating instruction queues failed\n");
+		goto detach_rsrcs;
+	}
+	cptlf_hw_init(lfs);
+	/*
+	 * Allow each LF to execute requests destined to any of 8 engine
+	 * groups and set queue priority of each LF to high
+	 */
+	ret = cptlf_set_grp_and_pri(lfs, eng_grp_mask, pri);
+	if (ret)
+		goto free_iq;
+
+	if (lfs->ctx_ilen_ovrd) {
+		ret = cptlf_set_ctx_ilen(lfs, lfs->ctx_ilen);
+		if (ret)
+			goto free_iq;
+	}
+
+	return 0;
+
+free_iq:
+	cptlf_hw_cleanup(lfs);
+	otx2_cpt_free_instruction_queues(lfs);
+detach_rsrcs:
+	otx2_cpt_detach_rsrcs_msg(lfs);
+clear_lfs_num:
+	lfs->lfs_num = 0;
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cptlf_init, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+void otx2_cptlf_shutdown(struct otx2_cptlfs_info *lfs)
+{
+	/* Cleanup LFs hardware side */
+	cptlf_hw_cleanup(lfs);
+	/* Free instruction queues */
+	otx2_cpt_free_instruction_queues(lfs);
+	/* Send request to detach LFs */
+	otx2_cpt_detach_rsrcs_msg(lfs);
+	lfs->lfs_num = 0;
+}
+EXPORT_SYMBOL_NS_GPL(otx2_cptlf_shutdown, "CRYPTO_DEV_OCTEONTX2_CPT");
+
+MODULE_AUTHOR("Marvell");
+MODULE_DESCRIPTION("Marvell RVU CPT Common module");
+MODULE_LICENSE("GPL");

linux-7.2.3/drivers/crypto/marvell/octeontx2/otx2_cptlf.h

@@ -0,0 +1,448 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2020 Marvell.
+ */
+#ifndef __OTX2_CPTLF_H
+#define __OTX2_CPTLF_H
+
+#include <linux/soc/marvell/octeontx2/asm.h>
+#include <linux/bitfield.h>
+#include <mbox.h>
+#include <rvu.h>
+#include "otx2_cpt_common.h"
+#include "otx2_cpt_reqmgr.h"
+
+/*
+ * CPT instruction and pending queues user requested length in CPT_INST_S msgs
+ */
+#define OTX2_CPT_USER_REQUESTED_QLEN_MSGS 8200
+
+/*
+ * CPT instruction queue size passed to HW is in units of 40*CPT_INST_S
+ * messages.
+ */
+#define OTX2_CPT_SIZE_DIV40 (OTX2_CPT_USER_REQUESTED_QLEN_MSGS/40)
+
+/*
+ * CPT instruction and pending queues length in CPT_INST_S messages
+ */
+#define OTX2_CPT_INST_QLEN_MSGS	((OTX2_CPT_SIZE_DIV40 - 1) * 40)
+
+/*
+ * LDWB is getting incorrectly used when IQB_LDWB = 1 and CPT instruction
+ * queue has less than 320 free entries. So, increase HW instruction queue
+ * size by 320 and give 320 entries less for SW/NIX RX as a workaround.
+ */
+#define OTX2_CPT_INST_QLEN_EXTRA_BYTES  (320 * OTX2_CPT_INST_SIZE)
+#define OTX2_CPT_EXTRA_SIZE_DIV40       (320/40)
+
+/* CPT instruction queue length in bytes */
+#define OTX2_CPT_INST_QLEN_BYTES                                               \
+		((OTX2_CPT_SIZE_DIV40 * 40 * OTX2_CPT_INST_SIZE) +             \
+		OTX2_CPT_INST_QLEN_EXTRA_BYTES)
+
+/* CPT instruction group queue length in bytes */
+#define OTX2_CPT_INST_GRP_QLEN_BYTES                                           \
+		((OTX2_CPT_SIZE_DIV40 + OTX2_CPT_EXTRA_SIZE_DIV40) * 16)
+
+/* CPT FC length in bytes */
+#define OTX2_CPT_Q_FC_LEN 128
+
+/* CPT instruction queue alignment */
+#define OTX2_CPT_INST_Q_ALIGNMENT  128
+
+/* Mask which selects all engine groups */
+#define OTX2_CPT_ALL_ENG_GRPS_MASK 0xFF
+
+/* Maximum LFs supported in OcteonTX2 for CPT */
+#define OTX2_CPT_MAX_LFS_NUM    64
+
+/* Queue priority */
+#define OTX2_CPT_QUEUE_HI_PRIO  0x1
+#define OTX2_CPT_QUEUE_LOW_PRIO 0x0
+
+enum otx2_cptlf_state {
+	OTX2_CPTLF_IN_RESET,
+	OTX2_CPTLF_STARTED,
+};
+
+struct otx2_cpt_inst_queue {
+	u8 *vaddr;
+	u8 *real_vaddr;
+	dma_addr_t dma_addr;
+	dma_addr_t real_dma_addr;
+	u32 size;
+};
+
+struct otx2_cptlfs_info;
+struct otx2_cptlf_wqe {
+	struct tasklet_struct work;
+	struct otx2_cptlfs_info *lfs;
+	u8 lf_num;
+};
+
+struct otx2_cptlf_info {
+	struct otx2_cptlfs_info *lfs;           /* Ptr to cptlfs_info struct */
+	void __iomem *lmtline;                  /* Address of LMTLINE */
+	void __iomem *ioreg;                    /* LMTLINE send register */
+	int msix_offset;                        /* MSI-X interrupts offset */
+	cpumask_var_t affinity_mask;            /* IRQs affinity mask */
+	u8 irq_name[OTX2_CPT_LF_MSIX_VECTORS][32];/* Interrupts name */
+	u8 is_irq_reg[OTX2_CPT_LF_MSIX_VECTORS];  /* Is interrupt registered */
+	u8 slot;                                /* Slot number of this LF */
+
+	struct otx2_cpt_inst_queue iqueue;/* Instruction queue */
+	struct otx2_cpt_pending_queue pqueue; /* Pending queue */
+	struct otx2_cptlf_wqe *wqe;       /* Tasklet work info */
+};
+
+struct cpt_hw_ops {
+	void (*send_cmd)(union otx2_cpt_inst_s *cptinst, u32 insts_num,
+			 struct otx2_cptlf_info *lf);
+	u8 (*cpt_get_compcode)(union otx2_cpt_res_s *result);
+	u8 (*cpt_get_uc_compcode)(union otx2_cpt_res_s *result);
+	struct otx2_cpt_inst_info *
+	(*cpt_sg_info_create)(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
+			      gfp_t gfp);
+};
+
+#define LMTLINE_SIZE  128
+#define LMTLINE_ALIGN 128
+struct otx2_lmt_info {
+	void *base;
+	dma_addr_t iova;
+	u32 size;
+	u8 align;
+};
+
+struct otx2_cptlfs_info {
+	/* Registers start address of VF/PF LFs are attached to */
+	void __iomem *reg_base;
+	struct otx2_lmt_info lmt_info;
+	struct pci_dev *pdev;   /* Device LFs are attached to */
+	struct otx2_cptlf_info lf[OTX2_CPT_MAX_LFS_NUM];
+	struct otx2_mbox *mbox;
+	struct cpt_hw_ops *ops;
+	u8 are_lfs_attached;	/* Whether CPT LFs are attached */
+	u8 lfs_num;		/* Number of CPT LFs */
+	u8 kcrypto_se_eng_grp_num; /* Crypto symmetric engine group number */
+	u8 kcrypto_ae_eng_grp_num; /* Crypto asymmetric engine group number */
+	u8 kvf_limits;          /* Kernel crypto limits */
+	atomic_t state;         /* LF's state. started/reset */
+	int blkaddr;            /* CPT blkaddr: BLKADDR_CPT0/BLKADDR_CPT1 */
+	int global_slot;        /* Global slot across the blocks */
+	u8 ctx_ilen;
+	u8 ctx_ilen_ovrd;
+};
+
+static inline void otx2_cpt_free_instruction_queues(
+					struct otx2_cptlfs_info *lfs)
+{
+	struct otx2_cpt_inst_queue *iq;
+	int i;
+
+	for (i = 0; i < lfs->lfs_num; i++) {
+		iq = &lfs->lf[i].iqueue;
+		if (iq->real_vaddr)
+			dma_free_coherent(&lfs->pdev->dev,
+					  iq->size,
+					  iq->real_vaddr,
+					  iq->real_dma_addr);
+		iq->real_vaddr = NULL;
+		iq->vaddr = NULL;
+	}
+}
+
+static inline int otx2_cpt_alloc_instruction_queues(
+					struct otx2_cptlfs_info *lfs)
+{
+	struct otx2_cpt_inst_queue *iq;
+	int ret = 0, i;
+
+	if (!lfs->lfs_num)
+		return -EINVAL;
+
+	for (i = 0; i < lfs->lfs_num; i++) {
+		iq = &lfs->lf[i].iqueue;
+		iq->size = OTX2_CPT_INST_QLEN_BYTES +
+			   OTX2_CPT_Q_FC_LEN +
+			   OTX2_CPT_INST_GRP_QLEN_BYTES +
+			   OTX2_CPT_INST_Q_ALIGNMENT;
+		iq->real_vaddr = dma_alloc_coherent(&lfs->pdev->dev, iq->size,
+					&iq->real_dma_addr, GFP_KERNEL);
+		if (!iq->real_vaddr) {
+			ret = -ENOMEM;
+			goto error;
+		}
+		iq->vaddr = iq->real_vaddr + OTX2_CPT_INST_GRP_QLEN_BYTES;
+		iq->dma_addr = iq->real_dma_addr + OTX2_CPT_INST_GRP_QLEN_BYTES;
+
+		/* Align pointers */
+		iq->vaddr = PTR_ALIGN(iq->vaddr, OTX2_CPT_INST_Q_ALIGNMENT);
+		iq->dma_addr = PTR_ALIGN(iq->dma_addr,
+					 OTX2_CPT_INST_Q_ALIGNMENT);
+	}
+	return 0;
+
+error:
+	otx2_cpt_free_instruction_queues(lfs);
+	return ret;
+}
+
+static inline void otx2_cptlf_set_iqueues_base_addr(
+					struct otx2_cptlfs_info *lfs)
+{
+	union otx2_cptx_lf_q_base lf_q_base;
+	int slot;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		lf_q_base.u = lfs->lf[slot].iqueue.dma_addr;
+		otx2_cpt_write64(lfs->reg_base, lfs->blkaddr, slot,
+				 OTX2_CPT_LF_Q_BASE, lf_q_base.u);
+	}
+}
+
+static inline void otx2_cptlf_do_set_iqueue_size(struct otx2_cptlf_info *lf)
+{
+	union otx2_cptx_lf_q_size lf_q_size = { .u = 0x0 };
+
+	lf_q_size.s.size_div40 = OTX2_CPT_SIZE_DIV40 +
+				 OTX2_CPT_EXTRA_SIZE_DIV40;
+	otx2_cpt_write64(lf->lfs->reg_base, lf->lfs->blkaddr, lf->slot,
+			 OTX2_CPT_LF_Q_SIZE, lf_q_size.u);
+}
+
+static inline void otx2_cptlf_set_iqueues_size(struct otx2_cptlfs_info *lfs)
+{
+	int slot;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++)
+		otx2_cptlf_do_set_iqueue_size(&lfs->lf[slot]);
+}
+
+#define INFLIGHT   GENMASK_ULL(8, 0)
+#define GRB_CNT    GENMASK_ULL(39, 32)
+#define GWB_CNT    GENMASK_ULL(47, 40)
+#define XQ_XOR     GENMASK_ULL(63, 63)
+#define DQPTR      GENMASK_ULL(19, 0)
+#define NQPTR      GENMASK_ULL(51, 32)
+
+static inline void otx2_cptlf_do_disable_iqueue(struct otx2_cptlf_info *lf)
+{
+	void __iomem *reg_base = lf->lfs->reg_base;
+	struct pci_dev *pdev = lf->lfs->pdev;
+	u8 blkaddr = lf->lfs->blkaddr;
+	int timeout = 1000000;
+	u64 inprog, inst_ptr;
+	u64 slot = lf->slot;
+	u64 qsize, pending;
+	int i = 0;
+
+	/* Disable instructions enqueuing */
+	otx2_cpt_write64(reg_base, blkaddr, slot, OTX2_CPT_LF_CTL, 0x0);
+
+	inprog = otx2_cpt_read64(reg_base, blkaddr, slot, OTX2_CPT_LF_INPROG);
+	inprog |= BIT_ULL(16);
+	otx2_cpt_write64(reg_base, blkaddr, slot, OTX2_CPT_LF_INPROG, inprog);
+
+	qsize = otx2_cpt_read64(reg_base, blkaddr, slot, OTX2_CPT_LF_Q_SIZE) & 0x7FFF;
+	do {
+		inst_ptr = otx2_cpt_read64(reg_base, blkaddr, slot, OTX2_CPT_LF_Q_INST_PTR);
+		pending = (FIELD_GET(XQ_XOR, inst_ptr) * qsize * 40) +
+			  FIELD_GET(NQPTR, inst_ptr) - FIELD_GET(DQPTR, inst_ptr);
+		udelay(1);
+		timeout--;
+	} while ((pending != 0) && (timeout != 0));
+
+	if (timeout == 0)
+		dev_warn(&pdev->dev, "TIMEOUT: CPT poll on pending instructions\n");
+
+	timeout = 1000000;
+	/* Wait for CPT queue to become execution-quiescent */
+	do {
+		inprog = otx2_cpt_read64(reg_base, blkaddr, slot, OTX2_CPT_LF_INPROG);
+
+		if ((FIELD_GET(INFLIGHT, inprog) == 0) &&
+		    (FIELD_GET(GRB_CNT, inprog) == 0)) {
+			i++;
+		} else {
+			i = 0;
+			timeout--;
+		}
+	} while ((timeout != 0) && (i < 10));
+
+	if (timeout == 0)
+		dev_warn(&pdev->dev, "TIMEOUT: CPT poll on inflight count\n");
+	/* Wait for 2 us to flush all queue writes to memory */
+	udelay(2);
+}
+
+static inline void otx2_cptlf_disable_iqueues(struct otx2_cptlfs_info *lfs)
+{
+	int slot;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		otx2_cptlf_do_disable_iqueue(&lfs->lf[slot]);
+		otx2_cpt_lf_reset_msg(lfs, lfs->global_slot + slot);
+	}
+}
+
+static inline void otx2_cptlf_set_iqueue_enq(struct otx2_cptlf_info *lf,
+					     bool enable)
+{
+	u8 blkaddr = lf->lfs->blkaddr;
+	union otx2_cptx_lf_ctl lf_ctl;
+
+	lf_ctl.u = otx2_cpt_read64(lf->lfs->reg_base, blkaddr, lf->slot,
+				   OTX2_CPT_LF_CTL);
+
+	/* Set iqueue's enqueuing */
+	lf_ctl.s.ena = enable ? 0x1 : 0x0;
+	otx2_cpt_write64(lf->lfs->reg_base, blkaddr, lf->slot,
+			 OTX2_CPT_LF_CTL, lf_ctl.u);
+}
+
+static inline void otx2_cptlf_enable_iqueue_enq(struct otx2_cptlf_info *lf)
+{
+	otx2_cptlf_set_iqueue_enq(lf, true);
+}
+
+static inline void otx2_cptlf_set_iqueue_exec(struct otx2_cptlf_info *lf,
+					      bool enable)
+{
+	union otx2_cptx_lf_inprog lf_inprog;
+	u8 blkaddr = lf->lfs->blkaddr;
+
+	lf_inprog.u = otx2_cpt_read64(lf->lfs->reg_base, blkaddr, lf->slot,
+				      OTX2_CPT_LF_INPROG);
+
+	/* Set iqueue's execution */
+	lf_inprog.s.eena = enable ? 0x1 : 0x0;
+	otx2_cpt_write64(lf->lfs->reg_base, blkaddr, lf->slot,
+			 OTX2_CPT_LF_INPROG, lf_inprog.u);
+}
+
+static inline void otx2_cptlf_set_ctx_flr_flush(struct otx2_cptlf_info *lf)
+{
+	u8 blkaddr = lf->lfs->blkaddr;
+	u64 val;
+
+	val = otx2_cpt_read64(lf->lfs->reg_base, blkaddr, lf->slot,
+			      OTX2_CPT_LF_CTX_CTL);
+	val |= BIT_ULL(0);
+
+	otx2_cpt_write64(lf->lfs->reg_base, blkaddr, lf->slot,
+			 OTX2_CPT_LF_CTX_CTL, val);
+}
+
+static inline void otx2_cptlf_enable_iqueue_exec(struct otx2_cptlf_info *lf)
+{
+	otx2_cptlf_set_iqueue_exec(lf, true);
+}
+
+static inline void otx2_cptlf_disable_iqueue_exec(struct otx2_cptlf_info *lf)
+{
+	otx2_cptlf_set_iqueue_exec(lf, false);
+}
+
+static inline void otx2_cptlf_enable_iqueues(struct otx2_cptlfs_info *lfs)
+{
+	int slot;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		/* Enable flush on FLR for Errata */
+		if (is_dev_cn10kb(lfs->pdev))
+			otx2_cptlf_set_ctx_flr_flush(&lfs->lf[slot]);
+
+		otx2_cptlf_enable_iqueue_exec(&lfs->lf[slot]);
+		otx2_cptlf_enable_iqueue_enq(&lfs->lf[slot]);
+	}
+}
+
+static inline void otx2_cpt_fill_inst(union otx2_cpt_inst_s *cptinst,
+				      struct otx2_cpt_iq_command *iq_cmd,
+				      u64 comp_baddr)
+{
+	cptinst->u[0] = 0x0;
+	cptinst->s.doneint = true;
+	cptinst->s.res_addr = comp_baddr;
+	cptinst->u[2] = 0x0;
+	cptinst->u[3] = 0x0;
+	cptinst->s.ei0 = iq_cmd->cmd.u;
+	cptinst->s.ei1 = iq_cmd->dptr;
+	cptinst->s.ei2 = iq_cmd->rptr;
+	cptinst->s.ei3 = iq_cmd->cptr.u;
+}
+
+/*
+ * On OcteonTX2 platform the parameter insts_num is used as a count of
+ * instructions to be enqueued. The valid values for insts_num are:
+ * 1 - 1 CPT instruction will be enqueued during LMTST operation
+ * 2 - 2 CPT instructions will be enqueued during LMTST operation
+ */
+static inline void otx2_cpt_send_cmd(union otx2_cpt_inst_s *cptinst,
+				     u32 insts_num, struct otx2_cptlf_info *lf)
+{
+	void __iomem *lmtline = lf->lmtline;
+	long ret;
+
+	/*
+	 * Make sure memory areas pointed in CPT_INST_S
+	 * are flushed before the instruction is sent to CPT
+	 */
+	dma_wmb();
+
+	do {
+		/* Copy CPT command to LMTLINE */
+		memcpy_toio(lmtline, cptinst, insts_num * OTX2_CPT_INST_SIZE);
+
+		/*
+		 * LDEOR initiates atomic transfer to I/O device
+		 * The following will cause the LMTST to fail (the LDEOR
+		 * returns zero):
+		 * - No stores have been performed to the LMTLINE since it was
+		 * last invalidated.
+		 * - The bytes which have been stored to LMTLINE since it was
+		 * last invalidated form a pattern that is non-contiguous, does
+		 * not start at byte 0, or does not end on a 8-byte boundary.
+		 * (i.e.comprises a formation of other than 1–16 8-byte
+		 * words.)
+		 *
+		 * These rules are designed such that an operating system
+		 * context switch or hypervisor guest switch need have no
+		 * knowledge of the LMTST operations; the switch code does not
+		 * need to store to LMTCANCEL. Also note as LMTLINE data cannot
+		 * be read, there is no information leakage between processes.
+		 */
+		ret = otx2_lmt_flush(lf->ioreg);
+
+	} while (!ret);
+}
+
+static inline bool otx2_cptlf_started(struct otx2_cptlfs_info *lfs)
+{
+	return atomic_read(&lfs->state) == OTX2_CPTLF_STARTED;
+}
+
+static inline void otx2_cptlf_set_dev_info(struct otx2_cptlfs_info *lfs,
+					   struct pci_dev *pdev,
+					   void __iomem *reg_base,
+					   struct otx2_mbox *mbox,
+					   int blkaddr)
+{
+	lfs->pdev = pdev;
+	lfs->reg_base = reg_base;
+	lfs->mbox = mbox;
+	lfs->blkaddr = blkaddr;
+}
+
+int otx2_cptlf_init(struct otx2_cptlfs_info *lfs, u8 eng_grp_msk, int pri,
+		    int lfs_num);
+void otx2_cptlf_shutdown(struct otx2_cptlfs_info *lfs);
+int otx2_cptlf_register_misc_interrupts(struct otx2_cptlfs_info *lfs);
+int otx2_cptlf_register_done_interrupts(struct otx2_cptlfs_info *lfs);
+void otx2_cptlf_unregister_misc_interrupts(struct otx2_cptlfs_info *lfs);
+void otx2_cptlf_unregister_done_interrupts(struct otx2_cptlfs_info *lfs);
+void otx2_cptlf_free_irqs_affinity(struct otx2_cptlfs_info *lfs);
+int otx2_cptlf_set_irqs_affinity(struct otx2_cptlfs_info *lfs);
+
+#endif /* __OTX2_CPTLF_H */

linux-7.2.3/drivers/crypto/marvell/octeontx2/otx2_cptpf.h

@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2020 Marvell.
+ */
+
+#ifndef __OTX2_CPTPF_H
+#define __OTX2_CPTPF_H
+
+#include "otx2_cpt_common.h"
+#include "otx2_cptpf_ucode.h"
+#include "otx2_cptlf.h"
+
+struct otx2_cptpf_dev;
+struct otx2_cptvf_info {
+	struct otx2_cptpf_dev *cptpf;	/* PF pointer this VF belongs to */
+	struct work_struct vfpf_mbox_work;
+	struct pci_dev *vf_dev;
+	int vf_id;
+	int intr_idx;
+};
+
+struct cptpf_flr_work {
+	struct work_struct work;
+	struct otx2_cptpf_dev *pf;
+};
+
+struct otx2_cptpf_dev {
+	void __iomem *reg_base;		/* CPT PF registers start address */
+	void __iomem *afpf_mbox_base;	/* PF-AF mbox start address */
+	void __iomem *vfpf_mbox_base;   /* VF-PF mbox start address */
+	struct pci_dev *pdev;		/* PCI device handle */
+	struct otx2_cptvf_info vf[OTX2_CPT_MAX_VFS_NUM];
+	struct otx2_cpt_eng_grps eng_grps;/* Engine groups information */
+	struct otx2_cptlfs_info lfs;      /* CPT LFs attached to this PF */
+	struct otx2_cptlfs_info cpt1_lfs; /* CPT1 LFs attached to this PF */
+	/* HW capabilities for each engine type */
+	union otx2_cpt_eng_caps eng_caps[OTX2_CPT_MAX_ENG_TYPES];
+	bool is_eng_caps_discovered;
+
+	/* AF <=> PF mbox */
+	struct otx2_mbox	afpf_mbox;
+	struct work_struct	afpf_mbox_work;
+	struct workqueue_struct *afpf_mbox_wq;
+
+	struct otx2_mbox	afpf_mbox_up;
+	struct work_struct	afpf_mbox_up_work;
+
+	/* VF <=> PF mbox */
+	struct otx2_mbox	vfpf_mbox;
+	struct workqueue_struct *vfpf_mbox_wq;
+
+	struct workqueue_struct	*flr_wq;
+	struct cptpf_flr_work   *flr_work;
+	struct mutex            lock;   /* serialize mailbox access */
+
+	unsigned long cap_flag;
+	u8 pf_id;               /* RVU PF number */
+	u8 max_vfs;		/* Maximum number of VFs supported by CPT */
+	u8 enabled_vfs;		/* Number of enabled VFs */
+	u8 sso_pf_func_ovrd;	/* SSO PF_FUNC override bit */
+	u8 kvf_limits;		/* Kernel crypto limits */
+	bool has_cpt1;
+	u8 rsrc_req_blkaddr;
+
+	/* Devlink */
+	struct devlink *dl;
+};
+
+irqreturn_t otx2_cptpf_afpf_mbox_intr(int irq, void *arg);
+void otx2_cptpf_afpf_mbox_handler(struct work_struct *work);
+void otx2_cptpf_afpf_mbox_up_handler(struct work_struct *work);
+irqreturn_t otx2_cptpf_vfpf_mbox_intr(int irq, void *arg);
+void otx2_cptpf_vfpf_mbox_handler(struct work_struct *work);
+
+int otx2_inline_cptlf_setup(struct otx2_cptpf_dev *cptpf,
+			    struct otx2_cptlfs_info *lfs, u8 egrp, int num_lfs);
+void otx2_inline_cptlf_cleanup(struct otx2_cptlfs_info *lfs);
+
+#endif /* __OTX2_CPTPF_H */

linux-7.2.3/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c

@@ -0,0 +1,886 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Marvell. */
+
+#include <linux/firmware.h>
+#include <linux/sysfs.h>
+#include "otx2_cpt_hw_types.h"
+#include "otx2_cpt_common.h"
+#include "otx2_cpt_devlink.h"
+#include "otx2_cptpf_ucode.h"
+#include "otx2_cptpf.h"
+#include "cn10k_cpt.h"
+#include "rvu_reg.h"
+
+#define OTX2_CPT_DRV_NAME    "rvu_cptpf"
+#define OTX2_CPT_DRV_STRING  "Marvell RVU CPT Physical Function Driver"
+
+#define CPT_UC_RID_CN9K_B0   1
+#define CPT_UC_RID_CN10K_A   4
+#define CPT_UC_RID_CN10K_B   5
+
+static void cptpf_enable_vfpf_mbox_intr(struct otx2_cptpf_dev *cptpf,
+					int num_vfs)
+{
+	int ena_bits;
+
+	/* Clear any pending interrupts */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFPF_MBOX_INTX(0), ~0x0ULL);
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFPF_MBOX_INTX(1), ~0x0ULL);
+
+	/* Enable VF interrupts for VFs from 0 to 63 */
+	ena_bits = ((num_vfs - 1) % 64);
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFPF_MBOX_INT_ENA_W1SX(0),
+			 GENMASK_ULL(ena_bits, 0));
+
+	if (num_vfs > 64) {
+		/* Enable VF interrupts for VFs from 64 to 127 */
+		ena_bits = num_vfs - 64 - 1;
+		otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+				RVU_PF_VFPF_MBOX_INT_ENA_W1SX(1),
+				GENMASK_ULL(ena_bits, 0));
+	}
+}
+
+static void cptpf_disable_vfpf_mbox_intr(struct otx2_cptpf_dev *cptpf,
+					 int num_vfs)
+{
+	int vector;
+
+	/* Disable VF-PF interrupts */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFPF_MBOX_INT_ENA_W1CX(0), ~0ULL);
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFPF_MBOX_INT_ENA_W1CX(1), ~0ULL);
+	/* Clear any pending interrupts */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFPF_MBOX_INTX(0), ~0ULL);
+
+	vector = pci_irq_vector(cptpf->pdev, RVU_PF_INT_VEC_VFPF_MBOX0);
+	free_irq(vector, cptpf);
+
+	if (num_vfs > 64) {
+		otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+				 RVU_PF_VFPF_MBOX_INTX(1), ~0ULL);
+		vector = pci_irq_vector(cptpf->pdev, RVU_PF_INT_VEC_VFPF_MBOX1);
+		free_irq(vector, cptpf);
+	}
+}
+
+static void cptpf_enable_vf_flr_me_intrs(struct otx2_cptpf_dev *cptpf,
+					 int num_vfs)
+{
+	/* Clear FLR interrupt if any */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_VFFLR_INTX(0),
+			 INTR_MASK(num_vfs));
+
+	/* Enable VF FLR interrupts */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFFLR_INT_ENA_W1SX(0), INTR_MASK(num_vfs));
+	/* Clear ME interrupt if any */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_VFME_INTX(0),
+			 INTR_MASK(num_vfs));
+	/* Enable VF ME interrupts */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFME_INT_ENA_W1SX(0), INTR_MASK(num_vfs));
+
+	if (num_vfs <= 64)
+		return;
+
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_VFFLR_INTX(1),
+			 INTR_MASK(num_vfs - 64));
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFFLR_INT_ENA_W1SX(1), INTR_MASK(num_vfs - 64));
+
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_VFME_INTX(1),
+			 INTR_MASK(num_vfs - 64));
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFME_INT_ENA_W1SX(1), INTR_MASK(num_vfs - 64));
+}
+
+static void cptpf_disable_vf_flr_me_intrs(struct otx2_cptpf_dev *cptpf,
+				       int num_vfs)
+{
+	int vector;
+
+	/* Disable VF FLR interrupts */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFFLR_INT_ENA_W1CX(0), INTR_MASK(num_vfs));
+	vector = pci_irq_vector(cptpf->pdev, RVU_PF_INT_VEC_VFFLR0);
+	free_irq(vector, cptpf);
+
+	/* Disable VF ME interrupts */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFME_INT_ENA_W1CX(0), INTR_MASK(num_vfs));
+	vector = pci_irq_vector(cptpf->pdev, RVU_PF_INT_VEC_VFME0);
+	free_irq(vector, cptpf);
+
+	if (num_vfs <= 64)
+		return;
+
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFFLR_INT_ENA_W1CX(1), INTR_MASK(num_vfs - 64));
+	vector = pci_irq_vector(cptpf->pdev, RVU_PF_INT_VEC_VFFLR1);
+	free_irq(vector, cptpf);
+
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFME_INT_ENA_W1CX(1), INTR_MASK(num_vfs - 64));
+	vector = pci_irq_vector(cptpf->pdev, RVU_PF_INT_VEC_VFME1);
+	free_irq(vector, cptpf);
+}
+
+static void cptpf_flr_wq_handler(struct work_struct *work)
+{
+	struct cptpf_flr_work *flr_work;
+	struct otx2_cptpf_dev *pf;
+	struct mbox_msghdr *req;
+	struct otx2_mbox *mbox;
+	int vf, reg = 0;
+
+	flr_work = container_of(work, struct cptpf_flr_work, work);
+	pf = flr_work->pf;
+	mbox = &pf->afpf_mbox;
+
+	vf = flr_work - pf->flr_work;
+
+	mutex_lock(&pf->lock);
+	req = otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req),
+				      sizeof(struct msg_rsp));
+	if (!req) {
+		mutex_unlock(&pf->lock);
+		return;
+	}
+
+	req->sig = OTX2_MBOX_REQ_SIG;
+	req->id = MBOX_MSG_VF_FLR;
+	req->pcifunc &= RVU_PFVF_FUNC_MASK;
+	req->pcifunc |= (vf + 1) & RVU_PFVF_FUNC_MASK;
+
+	otx2_cpt_send_mbox_msg(mbox, pf->pdev);
+	if (!otx2_cpt_sync_mbox_msg(&pf->afpf_mbox)) {
+
+		if (vf >= 64) {
+			reg = 1;
+			vf = vf - 64;
+		}
+		/* Clear transaction pending register */
+		otx2_cpt_write64(pf->reg_base, BLKADDR_RVUM, 0,
+				 RVU_PF_VFTRPENDX(reg), BIT_ULL(vf));
+		otx2_cpt_write64(pf->reg_base, BLKADDR_RVUM, 0,
+				 RVU_PF_VFFLR_INT_ENA_W1SX(reg), BIT_ULL(vf));
+	}
+	mutex_unlock(&pf->lock);
+}
+
+static irqreturn_t cptpf_vf_flr_intr(int __always_unused irq, void *arg)
+{
+	int reg, dev, vf, start_vf, num_reg = 1;
+	struct otx2_cptpf_dev *cptpf = arg;
+	u64 intr;
+
+	if (cptpf->max_vfs > 64)
+		num_reg = 2;
+
+	for (reg = 0; reg < num_reg; reg++) {
+		intr = otx2_cpt_read64(cptpf->reg_base, BLKADDR_RVUM, 0,
+				       RVU_PF_VFFLR_INTX(reg));
+		if (!intr)
+			continue;
+		start_vf = 64 * reg;
+		for (vf = 0; vf < 64; vf++) {
+			if (!(intr & BIT_ULL(vf)))
+				continue;
+			dev = vf + start_vf;
+			queue_work(cptpf->flr_wq, &cptpf->flr_work[dev].work);
+			/* Clear interrupt */
+			otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+					 RVU_PF_VFFLR_INTX(reg), BIT_ULL(vf));
+			/* Disable the interrupt */
+			otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+					 RVU_PF_VFFLR_INT_ENA_W1CX(reg),
+					 BIT_ULL(vf));
+		}
+	}
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t cptpf_vf_me_intr(int __always_unused irq, void *arg)
+{
+	struct otx2_cptpf_dev *cptpf = arg;
+	int reg, vf, num_reg = 1;
+	u64 intr;
+
+	if (cptpf->max_vfs > 64)
+		num_reg = 2;
+
+	for (reg = 0; reg < num_reg; reg++) {
+		intr = otx2_cpt_read64(cptpf->reg_base, BLKADDR_RVUM, 0,
+				       RVU_PF_VFME_INTX(reg));
+		if (!intr)
+			continue;
+		for (vf = 0; vf < 64; vf++) {
+			if (!(intr & BIT_ULL(vf)))
+				continue;
+			otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+					 RVU_PF_VFTRPENDX(reg), BIT_ULL(vf));
+			/* Clear interrupt */
+			otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+					 RVU_PF_VFME_INTX(reg), BIT_ULL(vf));
+		}
+	}
+	return IRQ_HANDLED;
+}
+
+static void cptpf_unregister_vfpf_intr(struct otx2_cptpf_dev *cptpf,
+				       int num_vfs)
+{
+	cptpf_disable_vfpf_mbox_intr(cptpf, num_vfs);
+	cptpf_disable_vf_flr_me_intrs(cptpf, num_vfs);
+}
+
+static int cptpf_register_vfpf_intr(struct otx2_cptpf_dev *cptpf, int num_vfs)
+{
+	struct pci_dev *pdev = cptpf->pdev;
+	struct device *dev = &pdev->dev;
+	int ret, vector;
+
+	vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFPF_MBOX0);
+	/* Register VF-PF mailbox interrupt handler */
+	ret = request_irq(vector, otx2_cptpf_vfpf_mbox_intr, 0, "CPTVFPF Mbox0",
+			  cptpf);
+	if (ret) {
+		dev_err(dev,
+			"IRQ registration failed for PFVF mbox0 irq\n");
+		return ret;
+	}
+	vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFFLR0);
+	/* Register VF FLR interrupt handler */
+	ret = request_irq(vector, cptpf_vf_flr_intr, 0, "CPTPF FLR0", cptpf);
+	if (ret) {
+		dev_err(dev,
+			"IRQ registration failed for VFFLR0 irq\n");
+		goto free_mbox0_irq;
+	}
+	vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFME0);
+	/* Register VF ME interrupt handler */
+	ret = request_irq(vector, cptpf_vf_me_intr, 0, "CPTPF ME0", cptpf);
+	if (ret) {
+		dev_err(dev,
+			"IRQ registration failed for PFVF mbox0 irq\n");
+		goto free_flr0_irq;
+	}
+
+	if (num_vfs > 64) {
+		vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFPF_MBOX1);
+		ret = request_irq(vector, otx2_cptpf_vfpf_mbox_intr, 0,
+				  "CPTVFPF Mbox1", cptpf);
+		if (ret) {
+			dev_err(dev,
+				"IRQ registration failed for PFVF mbox1 irq\n");
+			goto free_me0_irq;
+		}
+		vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFFLR1);
+		/* Register VF FLR interrupt handler */
+		ret = request_irq(vector, cptpf_vf_flr_intr, 0, "CPTPF FLR1",
+				  cptpf);
+		if (ret) {
+			dev_err(dev,
+				"IRQ registration failed for VFFLR1 irq\n");
+			goto free_mbox1_irq;
+		}
+		vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFME1);
+		/* Register VF FLR interrupt handler */
+		ret = request_irq(vector, cptpf_vf_me_intr, 0, "CPTPF ME1",
+				  cptpf);
+		if (ret) {
+			dev_err(dev,
+				"IRQ registration failed for VFFLR1 irq\n");
+			goto free_flr1_irq;
+		}
+	}
+	cptpf_enable_vfpf_mbox_intr(cptpf, num_vfs);
+	cptpf_enable_vf_flr_me_intrs(cptpf, num_vfs);
+
+	return 0;
+
+free_flr1_irq:
+	vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFFLR1);
+	free_irq(vector, cptpf);
+free_mbox1_irq:
+	vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFPF_MBOX1);
+	free_irq(vector, cptpf);
+free_me0_irq:
+	vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFME0);
+	free_irq(vector, cptpf);
+free_flr0_irq:
+	vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFFLR0);
+	free_irq(vector, cptpf);
+free_mbox0_irq:
+	vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFPF_MBOX0);
+	free_irq(vector, cptpf);
+	return ret;
+}
+
+static void cptpf_flr_wq_destroy(struct otx2_cptpf_dev *pf)
+{
+	if (!pf->flr_wq)
+		return;
+	destroy_workqueue(pf->flr_wq);
+	pf->flr_wq = NULL;
+	kfree(pf->flr_work);
+}
+
+static int cptpf_flr_wq_init(struct otx2_cptpf_dev *cptpf, int num_vfs)
+{
+	int vf;
+
+	cptpf->flr_wq = alloc_ordered_workqueue("cptpf_flr_wq", 0);
+	if (!cptpf->flr_wq)
+		return -ENOMEM;
+
+	cptpf->flr_work = kzalloc_objs(struct cptpf_flr_work, num_vfs);
+	if (!cptpf->flr_work)
+		goto destroy_wq;
+
+	for (vf = 0; vf < num_vfs; vf++) {
+		cptpf->flr_work[vf].pf = cptpf;
+		INIT_WORK(&cptpf->flr_work[vf].work, cptpf_flr_wq_handler);
+	}
+	return 0;
+
+destroy_wq:
+	destroy_workqueue(cptpf->flr_wq);
+	return -ENOMEM;
+}
+
+static int cptpf_vfpf_mbox_init(struct otx2_cptpf_dev *cptpf, int num_vfs)
+{
+	struct device *dev = &cptpf->pdev->dev;
+	u64 vfpf_mbox_base;
+	int err, i;
+
+	cptpf->vfpf_mbox_wq =
+		alloc_ordered_workqueue("cpt_vfpf_mailbox",
+					WQ_HIGHPRI | WQ_MEM_RECLAIM);
+	if (!cptpf->vfpf_mbox_wq)
+		return -ENOMEM;
+
+	/* Map VF-PF mailbox memory */
+	if (test_bit(CN10K_MBOX, &cptpf->cap_flag))
+		vfpf_mbox_base = readq(cptpf->reg_base + RVU_PF_VF_MBOX_ADDR);
+	else
+		vfpf_mbox_base = readq(cptpf->reg_base + RVU_PF_VF_BAR4_ADDR);
+
+	if (!vfpf_mbox_base) {
+		dev_err(dev, "VF-PF mailbox address not configured\n");
+		err = -ENOMEM;
+		goto free_wqe;
+	}
+	cptpf->vfpf_mbox_base = devm_ioremap_wc(dev, vfpf_mbox_base,
+						MBOX_SIZE * cptpf->max_vfs);
+	if (!cptpf->vfpf_mbox_base) {
+		dev_err(dev, "Mapping of VF-PF mailbox address failed\n");
+		err = -ENOMEM;
+		goto free_wqe;
+	}
+	err = otx2_mbox_init(&cptpf->vfpf_mbox, cptpf->vfpf_mbox_base,
+			     cptpf->pdev, cptpf->reg_base, MBOX_DIR_PFVF,
+			     num_vfs);
+	if (err)
+		goto free_wqe;
+
+	for (i = 0; i < num_vfs; i++) {
+		cptpf->vf[i].vf_id = i;
+		cptpf->vf[i].cptpf = cptpf;
+		cptpf->vf[i].intr_idx = i % 64;
+		INIT_WORK(&cptpf->vf[i].vfpf_mbox_work,
+			  otx2_cptpf_vfpf_mbox_handler);
+	}
+	return 0;
+
+free_wqe:
+	destroy_workqueue(cptpf->vfpf_mbox_wq);
+	return err;
+}
+
+static void cptpf_vfpf_mbox_destroy(struct otx2_cptpf_dev *cptpf)
+{
+	destroy_workqueue(cptpf->vfpf_mbox_wq);
+	otx2_mbox_destroy(&cptpf->vfpf_mbox);
+}
+
+static void cptpf_disable_afpf_mbox_intr(struct otx2_cptpf_dev *cptpf)
+{
+	/* Disable AF-PF interrupt */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_INT_ENA_W1C,
+			 0x1ULL);
+	/* Clear interrupt if any */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_INT, 0x1ULL);
+}
+
+static int cptpf_register_afpf_mbox_intr(struct otx2_cptpf_dev *cptpf)
+{
+	struct pci_dev *pdev = cptpf->pdev;
+	struct device *dev = &pdev->dev;
+	int ret, irq;
+
+	irq = pci_irq_vector(pdev, RVU_PF_INT_VEC_AFPF_MBOX);
+	/* Register AF-PF mailbox interrupt handler */
+	ret = devm_request_irq(dev, irq, otx2_cptpf_afpf_mbox_intr, 0,
+			       "CPTAFPF Mbox", cptpf);
+	if (ret) {
+		dev_err(dev,
+			"IRQ registration failed for PFAF mbox irq\n");
+		return ret;
+	}
+	/* Clear interrupt if any, to avoid spurious interrupts */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_INT, 0x1ULL);
+	/* Enable AF-PF interrupt */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_INT_ENA_W1S,
+			 0x1ULL);
+
+	ret = otx2_cpt_send_ready_msg(&cptpf->afpf_mbox, cptpf->pdev);
+	if (ret) {
+		dev_warn(dev,
+			 "AF not responding to mailbox, deferring probe\n");
+		cptpf_disable_afpf_mbox_intr(cptpf);
+		return -EPROBE_DEFER;
+	}
+	return 0;
+}
+
+static int cptpf_afpf_mbox_init(struct otx2_cptpf_dev *cptpf)
+{
+	struct pci_dev *pdev = cptpf->pdev;
+	resource_size_t offset;
+	int err;
+
+	cptpf->afpf_mbox_wq =
+		alloc_ordered_workqueue("cpt_afpf_mailbox",
+					WQ_HIGHPRI | WQ_MEM_RECLAIM);
+	if (!cptpf->afpf_mbox_wq)
+		return -ENOMEM;
+
+	offset = pci_resource_start(pdev, PCI_MBOX_BAR_NUM);
+	/* Map AF-PF mailbox memory */
+	cptpf->afpf_mbox_base = devm_ioremap_wc(&pdev->dev, offset, MBOX_SIZE);
+	if (!cptpf->afpf_mbox_base) {
+		dev_err(&pdev->dev, "Unable to map BAR4\n");
+		err = -ENOMEM;
+		goto error;
+	}
+
+	err = otx2_mbox_init(&cptpf->afpf_mbox, cptpf->afpf_mbox_base,
+			     pdev, cptpf->reg_base, MBOX_DIR_PFAF, 1);
+	if (err)
+		goto error;
+
+	err = otx2_mbox_init(&cptpf->afpf_mbox_up, cptpf->afpf_mbox_base,
+			     pdev, cptpf->reg_base, MBOX_DIR_PFAF_UP, 1);
+	if (err)
+		goto mbox_cleanup;
+
+	INIT_WORK(&cptpf->afpf_mbox_work, otx2_cptpf_afpf_mbox_handler);
+	INIT_WORK(&cptpf->afpf_mbox_up_work, otx2_cptpf_afpf_mbox_up_handler);
+	mutex_init(&cptpf->lock);
+
+	return 0;
+
+mbox_cleanup:
+	otx2_mbox_destroy(&cptpf->afpf_mbox);
+error:
+	destroy_workqueue(cptpf->afpf_mbox_wq);
+	return err;
+}
+
+static void cptpf_afpf_mbox_destroy(struct otx2_cptpf_dev *cptpf)
+{
+	destroy_workqueue(cptpf->afpf_mbox_wq);
+	otx2_mbox_destroy(&cptpf->afpf_mbox);
+	otx2_mbox_destroy(&cptpf->afpf_mbox_up);
+}
+
+static ssize_t sso_pf_func_ovrd_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	struct otx2_cptpf_dev *cptpf = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%d\n", cptpf->sso_pf_func_ovrd);
+}
+
+static ssize_t sso_pf_func_ovrd_store(struct device *dev,
+				      struct device_attribute *attr,
+				      const char *buf, size_t count)
+{
+	struct otx2_cptpf_dev *cptpf = dev_get_drvdata(dev);
+	u8 sso_pf_func_ovrd;
+
+	if (!(cptpf->pdev->revision == CPT_UC_RID_CN9K_B0))
+		return count;
+
+	if (kstrtou8(buf, 0, &sso_pf_func_ovrd))
+		return -EINVAL;
+
+	cptpf->sso_pf_func_ovrd = sso_pf_func_ovrd;
+
+	return count;
+}
+
+static ssize_t kvf_limits_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct otx2_cptpf_dev *cptpf = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%d\n", cptpf->kvf_limits);
+}
+
+static ssize_t kvf_limits_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
+{
+	struct otx2_cptpf_dev *cptpf = dev_get_drvdata(dev);
+	int lfs_num;
+	int ret;
+
+	ret = kstrtoint(buf, 0, &lfs_num);
+	if (ret)
+		return ret;
+	if (lfs_num < 1 || lfs_num > num_online_cpus()) {
+		dev_err(dev, "lfs count %d must be in range [1 - %d]\n",
+			lfs_num, num_online_cpus());
+		return -EINVAL;
+	}
+	cptpf->kvf_limits = lfs_num;
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(kvf_limits);
+static DEVICE_ATTR_RW(sso_pf_func_ovrd);
+
+static struct attribute *cptpf_attrs[] = {
+	&dev_attr_kvf_limits.attr,
+	&dev_attr_sso_pf_func_ovrd.attr,
+	NULL
+};
+
+static const struct attribute_group cptpf_sysfs_group = {
+	.attrs = cptpf_attrs,
+};
+
+static int cpt_is_pf_usable(struct otx2_cptpf_dev *cptpf)
+{
+	u64 rev;
+
+	rev = otx2_cpt_read64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			      RVU_PF_BLOCK_ADDRX_DISC(BLKADDR_RVUM));
+	rev = (rev >> 12) & 0xFF;
+	/*
+	 * Check if AF has setup revision for RVUM block, otherwise
+	 * driver probe should be deferred until AF driver comes up
+	 */
+	if (!rev) {
+		dev_warn(&cptpf->pdev->dev,
+			 "AF is not initialized, deferring probe\n");
+		return -EPROBE_DEFER;
+	}
+	return 0;
+}
+
+static void cptpf_get_rid(struct pci_dev *pdev, struct otx2_cptpf_dev *cptpf)
+{
+	struct otx2_cpt_eng_grps *eng_grps = &cptpf->eng_grps;
+	u64 reg_val = 0x0;
+
+	if (is_dev_otx2(pdev)) {
+		eng_grps->rid = pdev->revision;
+		return;
+	}
+	otx2_cpt_read_af_reg(&cptpf->afpf_mbox, pdev, CPT_AF_CTL, &reg_val,
+			     BLKADDR_CPT0);
+	if ((cpt_feature_sgv2(pdev) && (reg_val & BIT_ULL(18))) ||
+	    is_dev_cn10ka_ax(pdev))
+		eng_grps->rid = CPT_UC_RID_CN10K_A;
+	else if (cpt_feature_sgv2(pdev))
+		eng_grps->rid = CPT_UC_RID_CN10K_B;
+}
+
+static void cptpf_check_block_implemented(struct otx2_cptpf_dev *cptpf)
+{
+	u64 cfg;
+
+	cfg = otx2_cpt_read64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			      RVU_PF_BLOCK_ADDRX_DISC(BLKADDR_CPT1));
+	if (cfg & BIT_ULL(11))
+		cptpf->has_cpt1 = true;
+}
+
+static int cptpf_device_init(struct otx2_cptpf_dev *cptpf)
+{
+	union otx2_cptx_af_constants1 af_cnsts1 = {0};
+	int ret = 0;
+
+	/* check if 'implemented' bit is set for block BLKADDR_CPT1 */
+	cptpf_check_block_implemented(cptpf);
+
+	/* Get number of SE, IE and AE engines */
+	ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
+				   CPT_AF_CONSTANTS1, &af_cnsts1.u,
+				   BLKADDR_CPT0);
+	if (ret)
+		return ret;
+
+	cptpf->eng_grps.avail.max_se_cnt = af_cnsts1.s.se;
+	cptpf->eng_grps.avail.max_ie_cnt = af_cnsts1.s.ie;
+	cptpf->eng_grps.avail.max_ae_cnt = af_cnsts1.s.ae;
+
+	/* Disable all cores */
+	ret = otx2_cpt_disable_all_cores(cptpf);
+
+	otx2_cptlf_set_dev_info(&cptpf->lfs, cptpf->pdev, cptpf->reg_base,
+				&cptpf->afpf_mbox, BLKADDR_CPT0);
+	if (cptpf->has_cpt1)
+		otx2_cptlf_set_dev_info(&cptpf->cpt1_lfs, cptpf->pdev,
+					cptpf->reg_base, &cptpf->afpf_mbox,
+					BLKADDR_CPT1);
+	return ret;
+}
+
+static int cptpf_sriov_disable(struct pci_dev *pdev)
+{
+	struct otx2_cptpf_dev *cptpf = pci_get_drvdata(pdev);
+	int num_vfs = pci_num_vf(pdev);
+
+	if (!num_vfs)
+		return 0;
+
+	pci_disable_sriov(pdev);
+	cptpf_unregister_vfpf_intr(cptpf, num_vfs);
+	cptpf_flr_wq_destroy(cptpf);
+	cptpf_vfpf_mbox_destroy(cptpf);
+	module_put(THIS_MODULE);
+	cptpf->enabled_vfs = 0;
+
+	return 0;
+}
+
+static int cptpf_sriov_enable(struct pci_dev *pdev, int num_vfs)
+{
+	struct otx2_cptpf_dev *cptpf = pci_get_drvdata(pdev);
+	int ret;
+
+	/* Initialize VF<=>PF mailbox */
+	ret = cptpf_vfpf_mbox_init(cptpf, num_vfs);
+	if (ret)
+		return ret;
+
+	ret = cptpf_flr_wq_init(cptpf, num_vfs);
+	if (ret)
+		goto destroy_mbox;
+	/* Register VF<=>PF mailbox interrupt */
+	ret = cptpf_register_vfpf_intr(cptpf, num_vfs);
+	if (ret)
+		goto destroy_flr;
+
+	cptpf_get_rid(pdev, cptpf);
+	/* Get CPT HW capabilities using LOAD_FVC operation. */
+	ret = otx2_cpt_discover_eng_capabilities(cptpf);
+	if (ret)
+		goto disable_intr;
+
+	ret = otx2_cpt_create_eng_grps(cptpf, &cptpf->eng_grps);
+	if (ret)
+		goto disable_intr;
+
+	cptpf->enabled_vfs = num_vfs;
+	ret = pci_enable_sriov(pdev, num_vfs);
+	if (ret)
+		goto disable_intr;
+
+	dev_notice(&cptpf->pdev->dev, "VFs enabled: %d\n", num_vfs);
+
+	try_module_get(THIS_MODULE);
+	return num_vfs;
+
+disable_intr:
+	cptpf_unregister_vfpf_intr(cptpf, num_vfs);
+	cptpf->enabled_vfs = 0;
+destroy_flr:
+	cptpf_flr_wq_destroy(cptpf);
+destroy_mbox:
+	cptpf_vfpf_mbox_destroy(cptpf);
+	return ret;
+}
+
+static int otx2_cptpf_sriov_configure(struct pci_dev *pdev, int num_vfs)
+{
+	if (num_vfs > 0) {
+		return cptpf_sriov_enable(pdev, num_vfs);
+	} else {
+		return cptpf_sriov_disable(pdev);
+	}
+}
+
+static int otx2_cptpf_probe(struct pci_dev *pdev,
+			    const struct pci_device_id *ent)
+{
+	struct device *dev = &pdev->dev;
+	struct otx2_cptpf_dev *cptpf;
+	int err, num_vec;
+
+	cptpf = devm_kzalloc(dev, sizeof(*cptpf), GFP_KERNEL);
+	if (!cptpf)
+		return -ENOMEM;
+
+	err = pcim_enable_device(pdev);
+	if (err) {
+		dev_err(dev, "Failed to enable PCI device\n");
+		goto clear_drvdata;
+	}
+
+	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
+	if (err) {
+		dev_err(dev, "Unable to get usable DMA configuration\n");
+		goto clear_drvdata;
+	}
+	err = pcim_request_all_regions(pdev, OTX2_CPT_DRV_NAME);
+	if (err) {
+		dev_err(dev, "Couldn't request PCI resources 0x%x\n", err);
+		goto clear_drvdata;
+	}
+	pci_set_master(pdev);
+	pci_set_drvdata(pdev, cptpf);
+	cptpf->pdev = pdev;
+
+	/* Map PF's configuration registers */
+	cptpf->reg_base = pcim_iomap(pdev, PCI_PF_REG_BAR_NUM, 0);
+	if (!cptpf->reg_base) {
+		err = -ENOMEM;
+		dev_err(dev, "Couldn't ioremap PCI resource 0x%x\n", err);
+		goto clear_drvdata;
+	}
+
+	/* Check if AF driver is up, otherwise defer probe */
+	err = cpt_is_pf_usable(cptpf);
+	if (err)
+		goto clear_drvdata;
+
+	num_vec = pci_msix_vec_count(cptpf->pdev);
+	if (num_vec <= 0) {
+		err = -EINVAL;
+		goto clear_drvdata;
+	}
+
+	err = pci_alloc_irq_vectors(pdev, num_vec, num_vec, PCI_IRQ_MSIX);
+	if (err < 0) {
+		dev_err(dev, "Request for %d msix vectors failed\n",
+			RVU_PF_INT_VEC_CNT);
+		goto clear_drvdata;
+	}
+	otx2_cpt_set_hw_caps(pdev, &cptpf->cap_flag);
+	/* Initialize AF-PF mailbox */
+	err = cptpf_afpf_mbox_init(cptpf);
+	if (err)
+		goto clear_drvdata;
+	/* Register mailbox interrupt */
+	err = cptpf_register_afpf_mbox_intr(cptpf);
+	if (err)
+		goto destroy_afpf_mbox;
+
+	cptpf->max_vfs = pci_sriov_get_totalvfs(pdev);
+	cptpf->kvf_limits = 1;
+
+	/* Initialize CPT PF device */
+	err = cptpf_device_init(cptpf);
+	if (err)
+		goto unregister_intr;
+
+	err = cn10k_cptpf_lmtst_init(cptpf);
+	if (err)
+		goto unregister_intr;
+
+	/* Initialize engine groups */
+	err = otx2_cpt_init_eng_grps(pdev, &cptpf->eng_grps);
+	if (err)
+		goto free_lmtst;
+
+	err = sysfs_create_group(&dev->kobj, &cptpf_sysfs_group);
+	if (err)
+		goto cleanup_eng_grps;
+
+	err = otx2_cpt_register_dl(cptpf);
+	if (err)
+		goto sysfs_grp_del;
+
+	return 0;
+
+sysfs_grp_del:
+	sysfs_remove_group(&dev->kobj, &cptpf_sysfs_group);
+cleanup_eng_grps:
+	otx2_cpt_cleanup_eng_grps(pdev, &cptpf->eng_grps);
+free_lmtst:
+	cn10k_cpt_lmtst_free(pdev, &cptpf->lfs);
+unregister_intr:
+	cptpf_disable_afpf_mbox_intr(cptpf);
+destroy_afpf_mbox:
+	cptpf_afpf_mbox_destroy(cptpf);
+clear_drvdata:
+	pci_set_drvdata(pdev, NULL);
+	return err;
+}
+
+static void otx2_cptpf_remove(struct pci_dev *pdev)
+{
+	struct otx2_cptpf_dev *cptpf = pci_get_drvdata(pdev);
+
+	if (!cptpf)
+		return;
+
+	cptpf_sriov_disable(pdev);
+	otx2_cpt_unregister_dl(cptpf);
+
+	/* Cleanup Inline CPT LF's if attached */
+	if (cptpf->lfs.lfs_num)
+		otx2_inline_cptlf_cleanup(&cptpf->lfs);
+
+	if (cptpf->cpt1_lfs.lfs_num)
+		otx2_inline_cptlf_cleanup(&cptpf->cpt1_lfs);
+
+	/* Delete sysfs entry created for kernel VF limits */
+	sysfs_remove_group(&pdev->dev.kobj, &cptpf_sysfs_group);
+	/* Cleanup engine groups */
+	otx2_cpt_cleanup_eng_grps(pdev, &cptpf->eng_grps);
+	/* Disable AF-PF mailbox interrupt */
+	cptpf_disable_afpf_mbox_intr(cptpf);
+	/* Destroy AF-PF mbox */
+	cptpf_afpf_mbox_destroy(cptpf);
+	/* Free LMTST memory */
+	cn10k_cpt_lmtst_free(pdev, &cptpf->lfs);
+	pci_set_drvdata(pdev, NULL);
+}
+
+/* Supported devices */
+static const struct pci_device_id otx2_cpt_id_table[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, OTX2_CPT_PCI_PF_DEVICE_ID) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, CN10K_CPT_PCI_PF_DEVICE_ID) },
+	{ 0, }  /* end of table */
+};
+MODULE_DEVICE_TABLE(pci, otx2_cpt_id_table);
+
+static struct pci_driver otx2_cpt_pci_driver = {
+	.name = OTX2_CPT_DRV_NAME,
+	.id_table = otx2_cpt_id_table,
+	.probe = otx2_cptpf_probe,
+	.remove = otx2_cptpf_remove,
+	.sriov_configure = otx2_cptpf_sriov_configure
+};
+
+module_pci_driver(otx2_cpt_pci_driver);
+
+MODULE_IMPORT_NS("CRYPTO_DEV_OCTEONTX2_CPT");
+
+MODULE_AUTHOR("Marvell");
+MODULE_DESCRIPTION(OTX2_CPT_DRV_STRING);
+MODULE_LICENSE("GPL v2");

linux-7.2.3/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c

@@ -0,0 +1,661 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Marvell. */
+
+#include "otx2_cpt_common.h"
+#include "otx2_cptpf.h"
+#include "rvu_reg.h"
+
+/* Fastpath ipsec opcode with inplace processing */
+#define CPT_INLINE_RX_OPCODE (0x26 | (1 << 6))
+#define CN10K_CPT_INLINE_RX_OPCODE (0x29 | (1 << 6))
+
+#define cpt_inline_rx_opcode(pdev)                      \
+({                                                      \
+	u8 opcode;                                      \
+	if (is_dev_otx2(pdev))                          \
+		opcode = CPT_INLINE_RX_OPCODE;          \
+	else                                            \
+		opcode = CN10K_CPT_INLINE_RX_OPCODE;    \
+	(opcode);                                       \
+})
+
+/*
+ * CPT PF driver version, It will be incremented by 1 for every feature
+ * addition in CPT mailbox messages.
+ */
+#define OTX2_CPT_PF_DRV_VERSION 0x1
+
+static int forward_to_af(struct otx2_cptpf_dev *cptpf,
+			 struct otx2_cptvf_info *vf,
+			 struct mbox_msghdr *req, int size)
+{
+	struct mbox_msghdr *msg;
+	int ret;
+
+	mutex_lock(&cptpf->lock);
+	msg = otx2_mbox_alloc_msg(&cptpf->afpf_mbox, 0, size);
+	if (msg == NULL) {
+		mutex_unlock(&cptpf->lock);
+		return -ENOMEM;
+	}
+
+	memcpy((uint8_t *)msg + sizeof(struct mbox_msghdr),
+	       (uint8_t *)req + sizeof(struct mbox_msghdr), size);
+	msg->id = req->id;
+	msg->pcifunc = req->pcifunc;
+	msg->sig = req->sig;
+	msg->ver = req->ver;
+
+	ret = otx2_cpt_sync_mbox_msg(&cptpf->afpf_mbox);
+	/* Error code -EIO indicate there is a communication failure
+	 * to the AF. Rest of the error codes indicate that AF processed
+	 * VF messages and set the error codes in response messages
+	 * (if any) so simply forward responses to VF.
+	 */
+	if (ret == -EIO) {
+		dev_warn(&cptpf->pdev->dev,
+			 "AF not responding to VF%d messages\n", vf->vf_id);
+		mutex_unlock(&cptpf->lock);
+		return ret;
+	}
+	mutex_unlock(&cptpf->lock);
+	return 0;
+}
+
+static int handle_msg_get_caps(struct otx2_cptpf_dev *cptpf,
+			       struct otx2_cptvf_info *vf,
+			       struct mbox_msghdr *req)
+{
+	struct otx2_cpt_caps_rsp *rsp;
+
+	rsp = (struct otx2_cpt_caps_rsp *)
+	      otx2_mbox_alloc_msg(&cptpf->vfpf_mbox, vf->vf_id,
+				  sizeof(*rsp));
+	if (!rsp)
+		return -ENOMEM;
+
+	rsp->hdr.id = MBOX_MSG_GET_CAPS;
+	rsp->hdr.sig = OTX2_MBOX_RSP_SIG;
+	rsp->hdr.pcifunc = req->pcifunc;
+	rsp->cpt_pf_drv_version = OTX2_CPT_PF_DRV_VERSION;
+	rsp->cpt_revision = cptpf->eng_grps.rid;
+	memcpy(&rsp->eng_caps, &cptpf->eng_caps, sizeof(rsp->eng_caps));
+
+	return 0;
+}
+
+static int handle_msg_get_eng_grp_num(struct otx2_cptpf_dev *cptpf,
+				      struct otx2_cptvf_info *vf,
+				      struct mbox_msghdr *req)
+{
+	struct otx2_cpt_egrp_num_msg *grp_req;
+	struct otx2_cpt_egrp_num_rsp *rsp;
+
+	grp_req = (struct otx2_cpt_egrp_num_msg *)req;
+	rsp = (struct otx2_cpt_egrp_num_rsp *)
+	       otx2_mbox_alloc_msg(&cptpf->vfpf_mbox, vf->vf_id, sizeof(*rsp));
+	if (!rsp)
+		return -ENOMEM;
+
+	rsp->hdr.id = MBOX_MSG_GET_ENG_GRP_NUM;
+	rsp->hdr.sig = OTX2_MBOX_RSP_SIG;
+	rsp->hdr.pcifunc = req->pcifunc;
+	rsp->eng_type = grp_req->eng_type;
+	rsp->eng_grp_num = otx2_cpt_get_eng_grp(&cptpf->eng_grps,
+						grp_req->eng_type);
+
+	return 0;
+}
+
+static int handle_msg_kvf_limits(struct otx2_cptpf_dev *cptpf,
+				 struct otx2_cptvf_info *vf,
+				 struct mbox_msghdr *req)
+{
+	struct otx2_cpt_kvf_limits_rsp *rsp;
+
+	rsp = (struct otx2_cpt_kvf_limits_rsp *)
+	      otx2_mbox_alloc_msg(&cptpf->vfpf_mbox, vf->vf_id, sizeof(*rsp));
+	if (!rsp)
+		return -ENOMEM;
+
+	rsp->hdr.id = MBOX_MSG_GET_KVF_LIMITS;
+	rsp->hdr.sig = OTX2_MBOX_RSP_SIG;
+	rsp->hdr.pcifunc = req->pcifunc;
+	rsp->kvf_limits = cptpf->kvf_limits;
+
+	return 0;
+}
+
+static int send_inline_ipsec_inbound_msg(struct otx2_cptpf_dev *cptpf,
+					 int sso_pf_func, u8 slot)
+{
+	struct cpt_inline_ipsec_cfg_msg *req;
+	struct pci_dev *pdev = cptpf->pdev;
+
+	req = (struct cpt_inline_ipsec_cfg_msg *)
+	      otx2_mbox_alloc_msg_rsp(&cptpf->afpf_mbox, 0,
+				      sizeof(*req), sizeof(struct msg_rsp));
+	if (req == NULL) {
+		dev_err(&pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+	memset(req, 0, sizeof(*req));
+	req->hdr.id = MBOX_MSG_CPT_INLINE_IPSEC_CFG;
+	req->hdr.sig = OTX2_MBOX_REQ_SIG;
+	req->hdr.pcifunc = OTX2_CPT_RVU_PFFUNC(cptpf->pdev, cptpf->pf_id, 0);
+	req->dir = CPT_INLINE_INBOUND;
+	req->slot = slot;
+	req->sso_pf_func_ovrd = cptpf->sso_pf_func_ovrd;
+	req->sso_pf_func = sso_pf_func;
+	req->enable = 1;
+
+	return otx2_cpt_send_mbox_msg(&cptpf->afpf_mbox, pdev);
+}
+
+static int rx_inline_ipsec_lf_cfg(struct otx2_cptpf_dev *cptpf, u8 egrp,
+				  struct otx2_cpt_rx_inline_lf_cfg *req)
+{
+	struct nix_inline_ipsec_cfg *nix_req;
+	struct pci_dev *pdev = cptpf->pdev;
+	int ret;
+
+	nix_req = (struct nix_inline_ipsec_cfg *)
+		   otx2_mbox_alloc_msg_rsp(&cptpf->afpf_mbox, 0,
+					   sizeof(*nix_req),
+					   sizeof(struct msg_rsp));
+	if (nix_req == NULL) {
+		dev_err(&pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+	memset(nix_req, 0, sizeof(*nix_req));
+	nix_req->hdr.id = MBOX_MSG_NIX_INLINE_IPSEC_CFG;
+	nix_req->hdr.sig = OTX2_MBOX_REQ_SIG;
+	nix_req->enable = 1;
+	nix_req->credit_th = req->credit_th;
+	nix_req->bpid = req->bpid;
+	if (!req->credit || req->credit > OTX2_CPT_INST_QLEN_MSGS)
+		nix_req->cpt_credit = OTX2_CPT_INST_QLEN_MSGS - 1;
+	else
+		nix_req->cpt_credit = req->credit - 1;
+	nix_req->gen_cfg.egrp = egrp;
+	if (req->opcode)
+		nix_req->gen_cfg.opcode = req->opcode;
+	else
+		nix_req->gen_cfg.opcode = cpt_inline_rx_opcode(pdev);
+	nix_req->gen_cfg.param1 = req->param1;
+	nix_req->gen_cfg.param2 = req->param2;
+	nix_req->inst_qsel.cpt_pf_func =
+		OTX2_CPT_RVU_PFFUNC(cptpf->pdev, cptpf->pf_id, 0);
+	nix_req->inst_qsel.cpt_slot = 0;
+	ret = otx2_cpt_send_mbox_msg(&cptpf->afpf_mbox, pdev);
+	if (ret)
+		return ret;
+
+	if (cptpf->has_cpt1) {
+		ret = send_inline_ipsec_inbound_msg(cptpf, req->sso_pf_func, 1);
+		if (ret)
+			return ret;
+	}
+
+	return send_inline_ipsec_inbound_msg(cptpf, req->sso_pf_func, 0);
+}
+
+int
+otx2_inline_cptlf_setup(struct otx2_cptpf_dev *cptpf,
+			struct otx2_cptlfs_info *lfs, u8 egrp, int num_lfs)
+{
+	int ret;
+
+	ret = otx2_cptlf_init(lfs, 1 << egrp, OTX2_CPT_QUEUE_HI_PRIO, 1);
+	if (ret) {
+		dev_err(&cptpf->pdev->dev,
+			"LF configuration failed for RX inline ipsec.\n");
+		return ret;
+	}
+
+	/* Get msix offsets for attached LFs */
+	ret = otx2_cpt_msix_offset_msg(lfs);
+	if (ret)
+		goto cleanup_lf;
+
+	/* Register for CPT LF Misc interrupts */
+	ret = otx2_cptlf_register_misc_interrupts(lfs);
+	if (ret)
+		goto free_irq;
+
+	return 0;
+free_irq:
+	otx2_cptlf_unregister_misc_interrupts(lfs);
+cleanup_lf:
+	otx2_cptlf_shutdown(lfs);
+	return ret;
+}
+
+void
+otx2_inline_cptlf_cleanup(struct otx2_cptlfs_info *lfs)
+{
+	/* Unregister misc interrupt */
+	otx2_cptlf_unregister_misc_interrupts(lfs);
+
+	/* Cleanup LFs */
+	otx2_cptlf_shutdown(lfs);
+}
+
+static int handle_msg_rx_inline_ipsec_lf_cfg(struct otx2_cptpf_dev *cptpf,
+					     struct mbox_msghdr *req)
+{
+	struct otx2_cpt_rx_inline_lf_cfg *cfg_req;
+	int num_lfs = 1, ret;
+	u8 egrp;
+
+	cfg_req = (struct otx2_cpt_rx_inline_lf_cfg *)req;
+	if (cptpf->lfs.lfs_num) {
+		dev_err(&cptpf->pdev->dev,
+			"LF is already configured for RX inline ipsec.\n");
+		return -EEXIST;
+	}
+	/*
+	 * Allow LFs to execute requests destined to only grp IE_TYPES and
+	 * set queue priority of each LF to high
+	 */
+	egrp = otx2_cpt_get_eng_grp(&cptpf->eng_grps, OTX2_CPT_IE_TYPES);
+	if (egrp == OTX2_CPT_INVALID_CRYPTO_ENG_GRP) {
+		dev_err(&cptpf->pdev->dev,
+			"Engine group for inline ipsec is not available\n");
+		return -ENOENT;
+	}
+
+	cptpf->lfs.global_slot = 0;
+	cptpf->lfs.ctx_ilen_ovrd = cfg_req->ctx_ilen_valid;
+	cptpf->lfs.ctx_ilen = cfg_req->ctx_ilen;
+
+	ret = otx2_inline_cptlf_setup(cptpf, &cptpf->lfs, egrp, num_lfs);
+	if (ret) {
+		dev_err(&cptpf->pdev->dev, "Inline-Ipsec CPT0 LF setup failed.\n");
+		return ret;
+	}
+
+	if (cptpf->has_cpt1) {
+		cptpf->rsrc_req_blkaddr = BLKADDR_CPT1;
+		cptpf->cpt1_lfs.global_slot = num_lfs;
+		cptpf->cpt1_lfs.ctx_ilen_ovrd = cfg_req->ctx_ilen_valid;
+		cptpf->cpt1_lfs.ctx_ilen = cfg_req->ctx_ilen;
+		ret = otx2_inline_cptlf_setup(cptpf, &cptpf->cpt1_lfs, egrp,
+					      num_lfs);
+		if (ret) {
+			dev_err(&cptpf->pdev->dev, "Inline CPT1 LF setup failed.\n");
+			goto lf_cleanup;
+		}
+		cptpf->rsrc_req_blkaddr = 0;
+	}
+
+	ret = rx_inline_ipsec_lf_cfg(cptpf, egrp, cfg_req);
+	if (ret)
+		goto lf1_cleanup;
+
+	return 0;
+
+lf1_cleanup:
+	otx2_inline_cptlf_cleanup(&cptpf->cpt1_lfs);
+lf_cleanup:
+	otx2_inline_cptlf_cleanup(&cptpf->lfs);
+	return ret;
+}
+
+static int cptpf_handle_vf_req(struct otx2_cptpf_dev *cptpf,
+			       struct otx2_cptvf_info *vf,
+			       struct mbox_msghdr *req, int size)
+{
+	int err = 0;
+
+	/* Check if msg is valid, if not reply with an invalid msg */
+	if (req->sig != OTX2_MBOX_REQ_SIG)
+		goto inval_msg;
+
+	switch (req->id) {
+	case MBOX_MSG_GET_ENG_GRP_NUM:
+		err = handle_msg_get_eng_grp_num(cptpf, vf, req);
+		break;
+	case MBOX_MSG_GET_CAPS:
+		err = handle_msg_get_caps(cptpf, vf, req);
+		break;
+	case MBOX_MSG_GET_KVF_LIMITS:
+		err = handle_msg_kvf_limits(cptpf, vf, req);
+		break;
+	case MBOX_MSG_RX_INLINE_IPSEC_LF_CFG:
+		err = handle_msg_rx_inline_ipsec_lf_cfg(cptpf, req);
+		break;
+
+	default:
+		err = forward_to_af(cptpf, vf, req, size);
+		break;
+	}
+	return err;
+
+inval_msg:
+	otx2_reply_invalid_msg(&cptpf->vfpf_mbox, vf->vf_id, 0, req->id);
+	otx2_mbox_msg_send(&cptpf->vfpf_mbox, vf->vf_id);
+	return err;
+}
+
+irqreturn_t otx2_cptpf_vfpf_mbox_intr(int __always_unused irq, void *arg)
+{
+	struct otx2_cptpf_dev *cptpf = arg;
+	struct otx2_cptvf_info *vf;
+	int i, vf_idx;
+	u64 intr;
+
+	/*
+	 * Check which VF has raised an interrupt and schedule
+	 * corresponding work queue to process the messages
+	 */
+	for (i = 0; i < 2; i++) {
+		/* Read the interrupt bits */
+		intr = otx2_cpt_read64(cptpf->reg_base, BLKADDR_RVUM, 0,
+				       RVU_PF_VFPF_MBOX_INTX(i));
+
+		for (vf_idx = i * 64; vf_idx < cptpf->enabled_vfs; vf_idx++) {
+			vf = &cptpf->vf[vf_idx];
+			if (intr & (1ULL << vf->intr_idx)) {
+				queue_work(cptpf->vfpf_mbox_wq,
+					   &vf->vfpf_mbox_work);
+				/* Clear the interrupt */
+				otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM,
+						 0, RVU_PF_VFPF_MBOX_INTX(i),
+						 BIT_ULL(vf->intr_idx));
+			}
+		}
+	}
+	return IRQ_HANDLED;
+}
+
+void otx2_cptpf_vfpf_mbox_handler(struct work_struct *work)
+{
+	struct otx2_cptpf_dev *cptpf;
+	struct otx2_cptvf_info *vf;
+	struct otx2_mbox_dev *mdev;
+	struct mbox_hdr *req_hdr;
+	struct mbox_msghdr *msg;
+	struct otx2_mbox *mbox;
+	int offset, i, err;
+
+	vf = container_of(work, struct otx2_cptvf_info, vfpf_mbox_work);
+	cptpf = vf->cptpf;
+	mbox = &cptpf->vfpf_mbox;
+	/* sync with mbox memory region */
+	smp_rmb();
+	mdev = &mbox->dev[vf->vf_id];
+	/* Process received mbox messages */
+	req_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
+	offset = mbox->rx_start + ALIGN(sizeof(*req_hdr), MBOX_MSG_ALIGN);
+
+	for (i = 0; i < req_hdr->num_msgs; i++) {
+		msg = (struct mbox_msghdr *)(mdev->mbase + offset);
+
+		/* Set which VF sent this message based on mbox IRQ */
+		msg->pcifunc = rvu_make_pcifunc(cptpf->pdev, cptpf->pf_id,
+						(vf->vf_id + 1));
+		err = cptpf_handle_vf_req(cptpf, vf, msg,
+					  msg->next_msgoff - offset);
+		/*
+		 * Behave as the AF, drop the msg if there is
+		 * no memory, timeout handling also goes here
+		 */
+		if (err == -ENOMEM || err == -EIO)
+			break;
+		offset = msg->next_msgoff;
+		/* Write barrier required for VF responses which are handled by
+		 * PF driver and not forwarded to AF.
+		 */
+		smp_wmb();
+	}
+	/* Send mbox responses to VF */
+	if (mdev->num_msgs)
+		otx2_mbox_msg_send(mbox, vf->vf_id);
+}
+
+irqreturn_t otx2_cptpf_afpf_mbox_intr(int __always_unused irq, void *arg)
+{
+	struct otx2_cptpf_dev *cptpf = arg;
+	struct otx2_mbox_dev *mdev;
+	struct otx2_mbox *mbox;
+	struct mbox_hdr *hdr;
+	u64 intr;
+
+	/* Read the interrupt bits */
+	intr = otx2_cpt_read64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_INT);
+
+	if (intr & 0x1ULL) {
+		mbox = &cptpf->afpf_mbox;
+		mdev = &mbox->dev[0];
+		hdr = mdev->mbase + mbox->rx_start;
+		if (hdr->num_msgs)
+			/* Schedule work queue function to process the MBOX request */
+			queue_work(cptpf->afpf_mbox_wq, &cptpf->afpf_mbox_work);
+
+		mbox = &cptpf->afpf_mbox_up;
+		mdev = &mbox->dev[0];
+		hdr = mdev->mbase + mbox->rx_start;
+		if (hdr->num_msgs)
+			/* Schedule work queue function to process the MBOX request */
+			queue_work(cptpf->afpf_mbox_wq, &cptpf->afpf_mbox_up_work);
+		/* Clear and ack the interrupt */
+		otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_INT,
+				 0x1ULL);
+	}
+	return IRQ_HANDLED;
+}
+
+static void process_afpf_mbox_msg(struct otx2_cptpf_dev *cptpf,
+				  struct mbox_msghdr *msg)
+{
+	struct otx2_cptlfs_info *lfs = &cptpf->lfs;
+	struct device *dev = &cptpf->pdev->dev;
+	struct cpt_rd_wr_reg_msg *rsp_rd_wr;
+	struct msix_offset_rsp *rsp_msix;
+	int i;
+
+	if (msg->id >= MBOX_MSG_MAX) {
+		dev_err(dev, "MBOX msg with unknown ID %d\n", msg->id);
+		return;
+	}
+	if (msg->sig != OTX2_MBOX_RSP_SIG) {
+		dev_err(dev, "MBOX msg with wrong signature %x, ID %d\n",
+			msg->sig, msg->id);
+		return;
+	}
+	if (cptpf->rsrc_req_blkaddr == BLKADDR_CPT1)
+		lfs = &cptpf->cpt1_lfs;
+
+	switch (msg->id) {
+	case MBOX_MSG_READY:
+		cptpf->pf_id = rvu_get_pf(cptpf->pdev, msg->pcifunc);
+		break;
+	case MBOX_MSG_MSIX_OFFSET:
+		rsp_msix = (struct msix_offset_rsp *) msg;
+		for (i = 0; i < rsp_msix->cptlfs; i++)
+			lfs->lf[i].msix_offset = rsp_msix->cptlf_msixoff[i];
+
+		for (i = 0; i < rsp_msix->cpt1_lfs; i++)
+			lfs->lf[i].msix_offset = rsp_msix->cpt1_lf_msixoff[i];
+		break;
+	case MBOX_MSG_CPT_RD_WR_REGISTER:
+		rsp_rd_wr = (struct cpt_rd_wr_reg_msg *)msg;
+		if (msg->rc) {
+			dev_err(dev, "Reg %llx rd/wr(%d) failed %d\n",
+				rsp_rd_wr->reg_offset, rsp_rd_wr->is_write,
+				msg->rc);
+			return;
+		}
+		if (!rsp_rd_wr->is_write)
+			*rsp_rd_wr->ret_val = rsp_rd_wr->val;
+		break;
+	case MBOX_MSG_ATTACH_RESOURCES:
+		if (!msg->rc)
+			lfs->are_lfs_attached = 1;
+		break;
+	case MBOX_MSG_DETACH_RESOURCES:
+		if (!msg->rc)
+			lfs->are_lfs_attached = 0;
+		break;
+	case MBOX_MSG_CPT_INLINE_IPSEC_CFG:
+	case MBOX_MSG_NIX_INLINE_IPSEC_CFG:
+	case MBOX_MSG_CPT_LF_RESET:
+	case MBOX_MSG_LMTST_TBL_SETUP:
+		break;
+
+	default:
+		dev_err(dev,
+			"Unsupported msg %d received.\n", msg->id);
+		break;
+	}
+}
+
+static void forward_to_vf(struct otx2_cptpf_dev *cptpf, struct mbox_msghdr *msg,
+			  int vf_id, int size)
+{
+	struct otx2_mbox *vfpf_mbox;
+	struct mbox_msghdr *fwd;
+
+	if (msg->id >= MBOX_MSG_MAX) {
+		dev_err(&cptpf->pdev->dev,
+			"MBOX msg with unknown ID %d\n", msg->id);
+		return;
+	}
+	if (msg->sig != OTX2_MBOX_RSP_SIG) {
+		dev_err(&cptpf->pdev->dev,
+			"MBOX msg with wrong signature %x, ID %d\n",
+			msg->sig, msg->id);
+		return;
+	}
+	vfpf_mbox = &cptpf->vfpf_mbox;
+	vf_id--;
+	if (vf_id >= cptpf->enabled_vfs) {
+		dev_err(&cptpf->pdev->dev,
+			"MBOX msg to unknown VF: %d >= %d\n",
+			vf_id, cptpf->enabled_vfs);
+		return;
+	}
+	if (msg->id == MBOX_MSG_VF_FLR)
+		return;
+
+	fwd = otx2_mbox_alloc_msg(vfpf_mbox, vf_id, size);
+	if (!fwd) {
+		dev_err(&cptpf->pdev->dev,
+			"Forwarding to VF%d failed.\n", vf_id);
+		return;
+	}
+	memcpy((uint8_t *)fwd + sizeof(struct mbox_msghdr),
+		(uint8_t *)msg + sizeof(struct mbox_msghdr), size);
+	fwd->id = msg->id;
+	fwd->pcifunc = msg->pcifunc;
+	fwd->sig = msg->sig;
+	fwd->ver = msg->ver;
+	fwd->rc = msg->rc;
+}
+
+/* Handle mailbox messages received from AF */
+void otx2_cptpf_afpf_mbox_handler(struct work_struct *work)
+{
+	struct otx2_cptpf_dev *cptpf;
+	struct otx2_mbox *afpf_mbox;
+	struct otx2_mbox_dev *mdev;
+	struct mbox_hdr *rsp_hdr;
+	struct mbox_msghdr *msg;
+	int offset, vf_id, i;
+
+	cptpf = container_of(work, struct otx2_cptpf_dev, afpf_mbox_work);
+	afpf_mbox = &cptpf->afpf_mbox;
+	mdev = &afpf_mbox->dev[0];
+	/* Sync mbox data into memory */
+	smp_wmb();
+
+	rsp_hdr = (struct mbox_hdr *)(mdev->mbase + afpf_mbox->rx_start);
+	offset = ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN);
+
+	for (i = 0; i < rsp_hdr->num_msgs; i++) {
+		msg = (struct mbox_msghdr *)(mdev->mbase + afpf_mbox->rx_start +
+					     offset);
+		vf_id = (msg->pcifunc >> RVU_PFVF_FUNC_SHIFT) &
+			 RVU_PFVF_FUNC_MASK;
+		if (vf_id > 0)
+			forward_to_vf(cptpf, msg, vf_id,
+				      msg->next_msgoff - offset);
+		else
+			process_afpf_mbox_msg(cptpf, msg);
+
+		offset = msg->next_msgoff;
+		/* Sync VF response ready to be sent */
+		smp_wmb();
+		mdev->msgs_acked++;
+	}
+	otx2_mbox_reset(afpf_mbox, 0);
+}
+
+static void handle_msg_cpt_inst_lmtst(struct otx2_cptpf_dev *cptpf,
+				      struct mbox_msghdr *msg)
+{
+	struct cpt_inst_lmtst_req *req = (struct cpt_inst_lmtst_req *)msg;
+	struct otx2_cptlfs_info *lfs = &cptpf->lfs;
+	struct msg_rsp *rsp;
+
+	if (cptpf->lfs.lfs_num)
+		lfs->ops->send_cmd((union otx2_cpt_inst_s *)req->inst, 1,
+				   &lfs->lf[0]);
+
+	rsp = (struct msg_rsp *)otx2_mbox_alloc_msg(&cptpf->afpf_mbox_up, 0,
+						    sizeof(*rsp));
+	if (!rsp)
+		return;
+
+	rsp->hdr.id = msg->id;
+	rsp->hdr.sig = OTX2_MBOX_RSP_SIG;
+	rsp->hdr.pcifunc = 0;
+	rsp->hdr.rc = 0;
+}
+
+static void process_afpf_mbox_up_msg(struct otx2_cptpf_dev *cptpf,
+				     struct mbox_msghdr *msg)
+{
+	if (msg->id >= MBOX_MSG_MAX) {
+		dev_err(&cptpf->pdev->dev,
+			"MBOX msg with unknown ID %d\n", msg->id);
+		return;
+	}
+
+	switch (msg->id) {
+	case MBOX_MSG_CPT_INST_LMTST:
+		handle_msg_cpt_inst_lmtst(cptpf, msg);
+		break;
+	default:
+		otx2_reply_invalid_msg(&cptpf->afpf_mbox_up, 0, 0, msg->id);
+	}
+}
+
+void otx2_cptpf_afpf_mbox_up_handler(struct work_struct *work)
+{
+	struct otx2_cptpf_dev *cptpf;
+	struct otx2_mbox_dev *mdev;
+	struct mbox_hdr *rsp_hdr;
+	struct mbox_msghdr *msg;
+	struct otx2_mbox *mbox;
+	int offset, i;
+
+	cptpf = container_of(work, struct otx2_cptpf_dev, afpf_mbox_up_work);
+	mbox = &cptpf->afpf_mbox_up;
+	mdev = &mbox->dev[0];
+	/* Sync mbox data into memory */
+	smp_wmb();
+
+	rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
+	offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN);
+
+	for (i = 0; i < rsp_hdr->num_msgs; i++) {
+		msg = (struct mbox_msghdr *)(mdev->mbase + offset);
+
+		process_afpf_mbox_up_msg(cptpf, msg);
+
+		offset = mbox->rx_start + msg->next_msgoff;
+	}
+	otx2_mbox_msg_send(mbox, 0);
+}

linux-7.2.3/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.h

@@ -0,0 +1,172 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2020 Marvell.
+ */
+
+#ifndef __OTX2_CPTPF_UCODE_H
+#define __OTX2_CPTPF_UCODE_H
+
+#include <linux/pci.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include "otx2_cpt_hw_types.h"
+#include "otx2_cpt_common.h"
+
+/*
+ * On OcteonTX2 platform IPSec ucode can use both IE and SE engines therefore
+ * IE and SE engines can be attached to the same engine group.
+ */
+#define OTX2_CPT_MAX_ETYPES_PER_GRP 2
+
+/* CPT ucode signature size */
+#define OTX2_CPT_UCODE_SIGN_LEN     256
+
+/* Microcode version string length */
+#define OTX2_CPT_UCODE_VER_STR_SZ   44
+
+/* Maximum number of supported engines/cores on OcteonTX2/CN10K platform */
+#define OTX2_CPT_MAX_ENGINES        144
+
+#define OTX2_CPT_ENGS_BITMASK_LEN   BITS_TO_LONGS(OTX2_CPT_MAX_ENGINES)
+
+#define OTX2_CPT_UCODE_SZ           (64 * 1024)
+
+/* Microcode types */
+enum otx2_cpt_ucode_type {
+	OTX2_CPT_AE_UC_TYPE = 1,  /* AE-MAIN */
+	OTX2_CPT_SE_UC_TYPE1 = 20,/* SE-MAIN - combination of 21 and 22 */
+	OTX2_CPT_SE_UC_TYPE2 = 21,/* Fast Path IPSec + AirCrypto */
+	OTX2_CPT_SE_UC_TYPE3 = 22,/*
+				   * Hash + HMAC + FlexiCrypto + RNG +
+				   * Full Feature IPSec + AirCrypto + Kasumi
+				   */
+	OTX2_CPT_IE_UC_TYPE1 = 30, /* IE-MAIN - combination of 31 and 32 */
+	OTX2_CPT_IE_UC_TYPE2 = 31, /* Fast Path IPSec */
+	OTX2_CPT_IE_UC_TYPE3 = 32, /*
+				    * Hash + HMAC + FlexiCrypto + RNG +
+				    * Full Future IPSec
+				    */
+};
+
+struct otx2_cpt_bitmap {
+	unsigned long bits[OTX2_CPT_ENGS_BITMASK_LEN];
+	int size;
+};
+
+struct otx2_cpt_engines {
+	int type;
+	int count;
+};
+
+/* Microcode version number */
+struct otx2_cpt_ucode_ver_num {
+	u8 nn;
+	u8 xx;
+	u8 yy;
+	u8 zz;
+};
+
+struct otx2_cpt_ucode_hdr {
+	struct otx2_cpt_ucode_ver_num ver_num;
+	u8 ver_str[OTX2_CPT_UCODE_VER_STR_SZ];
+	__be32 code_length;
+	u32 padding[3];
+};
+
+struct otx2_cpt_ucode {
+	u8 ver_str[OTX2_CPT_UCODE_VER_STR_SZ + 1];/*
+					       * ucode version in readable
+					       * format
+					       */
+	struct otx2_cpt_ucode_ver_num ver_num;/* ucode version number */
+	char filename[OTX2_CPT_NAME_LENGTH];/* ucode filename */
+	dma_addr_t dma;		/* phys address of ucode image */
+	void *va;		/* virt address of ucode image */
+	u32 size;		/* ucode image size */
+	int type;		/* ucode image type SE, IE, AE or SE+IE */
+};
+
+struct otx2_cpt_uc_info_t {
+	struct list_head list;
+	struct otx2_cpt_ucode ucode;/* microcode information */
+	const struct firmware *fw;
+};
+
+/* Maximum and current number of engines available for all engine groups */
+struct otx2_cpt_engs_available {
+	int max_se_cnt;
+	int max_ie_cnt;
+	int max_ae_cnt;
+	int se_cnt;
+	int ie_cnt;
+	int ae_cnt;
+};
+
+/* Engines reserved to an engine group */
+struct otx2_cpt_engs_rsvd {
+	int type;	/* engine type */
+	int count;	/* number of engines attached */
+	int offset;     /* constant offset of engine type in the bitmap */
+	unsigned long *bmap;		/* attached engines bitmap */
+	struct otx2_cpt_ucode *ucode;	/* ucode used by these engines */
+};
+
+struct otx2_cpt_mirror_info {
+	int is_ena;	/*
+			 * is mirroring enabled, it is set only for engine
+			 * group which mirrors another engine group
+			 */
+	int idx;	/*
+			 * index of engine group which is mirrored by this
+			 * group, set only for engine group which mirrors
+			 * another group
+			 */
+	int ref_count;	/*
+			 * number of times this engine group is mirrored by
+			 * other groups, this is set only for engine group
+			 * which is mirrored by other group(s)
+			 */
+};
+
+struct otx2_cpt_eng_grp_info {
+	struct otx2_cpt_eng_grps *g; /* pointer to engine_groups structure */
+	/* engines attached */
+	struct otx2_cpt_engs_rsvd engs[OTX2_CPT_MAX_ETYPES_PER_GRP];
+	/* ucodes information */
+	struct otx2_cpt_ucode ucode[OTX2_CPT_MAX_ETYPES_PER_GRP];
+	/* engine group mirroring information */
+	struct otx2_cpt_mirror_info mirror;
+	int idx;	 /* engine group index */
+	bool is_enabled; /*
+			  * is engine group enabled, engine group is enabled
+			  * when it has engines attached and ucode loaded
+			  */
+};
+
+struct otx2_cpt_eng_grps {
+	struct mutex lock;
+	struct otx2_cpt_eng_grp_info grp[OTX2_CPT_MAX_ENGINE_GROUPS];
+	struct otx2_cpt_engs_available avail;
+	void *obj;			/* device specific data */
+	int engs_num;			/* total number of engines supported */
+	u8 eng_ref_cnt[OTX2_CPT_MAX_ENGINES];/* engines reference count */
+	bool is_grps_created; /* Is the engine groups are already created */
+	u16 rid;
+};
+struct otx2_cptpf_dev;
+int otx2_cpt_init_eng_grps(struct pci_dev *pdev,
+			   struct otx2_cpt_eng_grps *eng_grps);
+void otx2_cpt_cleanup_eng_grps(struct pci_dev *pdev,
+			       struct otx2_cpt_eng_grps *eng_grps);
+int otx2_cpt_create_eng_grps(struct otx2_cptpf_dev *cptpf,
+			     struct otx2_cpt_eng_grps *eng_grps);
+int otx2_cpt_disable_all_cores(struct otx2_cptpf_dev *cptpf);
+int otx2_cpt_get_eng_grp(struct otx2_cpt_eng_grps *eng_grps, int eng_type);
+int otx2_cpt_discover_eng_capabilities(struct otx2_cptpf_dev *cptpf);
+int otx2_cpt_dl_custom_egrp_create(struct otx2_cptpf_dev *cptpf,
+				   struct devlink_param_gset_ctx *ctx);
+int otx2_cpt_dl_custom_egrp_delete(struct otx2_cptpf_dev *cptpf,
+				   struct devlink_param_gset_ctx *ctx);
+struct otx2_cpt_engs_rsvd *find_engines_by_type(
+					struct otx2_cpt_eng_grp_info *eng_grp,
+					int eng_type);
+#endif /* __OTX2_CPTPF_UCODE_H */

linux-7.2.3/drivers/crypto/marvell/octeontx2/otx2_cptvf.h

@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2020 Marvell.
+ */
+
+#ifndef __OTX2_CPTVF_H
+#define __OTX2_CPTVF_H
+
+#include "mbox.h"
+#include "otx2_cptlf.h"
+
+struct otx2_cptvf_dev {
+	void __iomem *reg_base;		/* Register start address */
+	void __iomem *pfvf_mbox_base;	/* PF-VF mbox start address */
+	struct pci_dev *pdev;		/* PCI device handle */
+	struct otx2_cptlfs_info lfs;	/* CPT LFs attached to this VF */
+	u8 vf_id;			/* Virtual function index */
+
+	/* PF <=> VF mbox */
+	struct otx2_mbox	pfvf_mbox;
+	struct work_struct	pfvf_mbox_work;
+	struct workqueue_struct *pfvf_mbox_wq;
+	int blkaddr;
+	void *bbuf_base;
+	unsigned long cap_flag;
+	u64 eng_caps[OTX2_CPT_MAX_ENG_TYPES];
+};
+
+irqreturn_t otx2_cptvf_pfvf_mbox_intr(int irq, void *arg);
+void otx2_cptvf_pfvf_mbox_handler(struct work_struct *work);
+int otx2_cptvf_send_eng_grp_num_msg(struct otx2_cptvf_dev *cptvf, int eng_type);
+int otx2_cptvf_send_kvf_limits_msg(struct otx2_cptvf_dev *cptvf);
+int otx2_cpt_mbox_bbuf_init(struct otx2_cptvf_dev *cptvf, struct pci_dev *pdev);
+int otx2_cptvf_send_caps_msg(struct otx2_cptvf_dev *cptvf);
+
+#endif /* __OTX2_CPTVF_H */

linux-7.2.3/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.h

@@ -0,0 +1,183 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2020 Marvell.
+ */
+
+#ifndef __OTX2_CPT_ALGS_H
+#define __OTX2_CPT_ALGS_H
+
+#include <crypto/hash.h>
+#include <crypto/skcipher.h>
+#include <crypto/aead.h>
+#include "otx2_cpt_common.h"
+#include "cn10k_cpt.h"
+
+#define OTX2_CPT_MAX_ENC_KEY_SIZE    32
+#define OTX2_CPT_MAX_HASH_KEY_SIZE   64
+#define OTX2_CPT_MAX_KEY_SIZE (OTX2_CPT_MAX_ENC_KEY_SIZE + \
+			       OTX2_CPT_MAX_HASH_KEY_SIZE)
+enum otx2_cpt_request_type {
+	OTX2_CPT_ENC_DEC_REQ            = 0x1,
+	OTX2_CPT_AEAD_ENC_DEC_REQ       = 0x2,
+	OTX2_CPT_AEAD_ENC_DEC_NULL_REQ  = 0x3,
+	OTX2_CPT_PASSTHROUGH_REQ	= 0x4
+};
+
+enum otx2_cpt_major_opcodes {
+	OTX2_CPT_MAJOR_OP_MISC = 0x01,
+	OTX2_CPT_MAJOR_OP_FC   = 0x33,
+	OTX2_CPT_MAJOR_OP_HMAC = 0x35,
+};
+
+enum otx2_cpt_cipher_type {
+	OTX2_CPT_CIPHER_NULL = 0x0,
+	OTX2_CPT_DES3_CBC = 0x1,
+	OTX2_CPT_DES3_ECB = 0x2,
+	OTX2_CPT_AES_CBC  = 0x3,
+	OTX2_CPT_AES_ECB  = 0x4,
+	OTX2_CPT_AES_CFB  = 0x5,
+	OTX2_CPT_AES_CTR  = 0x6,
+	OTX2_CPT_AES_GCM  = 0x7,
+	OTX2_CPT_AES_XTS  = 0x8
+};
+
+enum otx2_cpt_mac_type {
+	OTX2_CPT_MAC_NULL = 0x0,
+	OTX2_CPT_MD5      = 0x1,
+	OTX2_CPT_SHA1     = 0x2,
+	OTX2_CPT_SHA224   = 0x3,
+	OTX2_CPT_SHA256   = 0x4,
+	OTX2_CPT_SHA384   = 0x5,
+	OTX2_CPT_SHA512   = 0x6,
+	OTX2_CPT_GMAC     = 0x7
+};
+
+enum otx2_cpt_aes_key_len {
+	OTX2_CPT_AES_128_BIT = 0x1,
+	OTX2_CPT_AES_192_BIT = 0x2,
+	OTX2_CPT_AES_256_BIT = 0x3
+};
+
+union otx2_cpt_encr_ctrl {
+	u64 u;
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 enc_cipher:4;
+		u64 reserved_59:1;
+		u64 aes_key:2;
+		u64 iv_source:1;
+		u64 mac_type:4;
+		u64 reserved_49_51:3;
+		u64 auth_input_type:1;
+		u64 mac_len:8;
+		u64 reserved_32_39:8;
+		u64 encr_offset:16;
+		u64 iv_offset:8;
+		u64 auth_offset:8;
+#else
+		u64 auth_offset:8;
+		u64 iv_offset:8;
+		u64 encr_offset:16;
+		u64 reserved_32_39:8;
+		u64 mac_len:8;
+		u64 auth_input_type:1;
+		u64 reserved_49_51:3;
+		u64 mac_type:4;
+		u64 iv_source:1;
+		u64 aes_key:2;
+		u64 reserved_59:1;
+		u64 enc_cipher:4;
+#endif
+	} e;
+};
+
+struct otx2_cpt_cipher {
+	const char *name;
+	u8 value;
+};
+
+struct otx2_cpt_fc_enc_ctx {
+	union otx2_cpt_encr_ctrl enc_ctrl;
+	u8 encr_key[32];
+	u8 encr_iv[16];
+};
+
+union otx2_cpt_fc_hmac_ctx {
+	struct {
+		u8 ipad[64];
+		u8 opad[64];
+	} e;
+	struct {
+		u8 hmac_calc[64]; /* HMAC calculated */
+		u8 hmac_recv[64]; /* HMAC received */
+	} s;
+};
+
+struct otx2_cpt_fc_ctx {
+	struct otx2_cpt_fc_enc_ctx enc;
+	union otx2_cpt_fc_hmac_ctx hmac;
+};
+
+struct otx2_cpt_enc_ctx {
+	u32 key_len;
+	u8 enc_key[OTX2_CPT_MAX_KEY_SIZE];
+	u8 cipher_type;
+	u8 key_type;
+	u8 enc_align_len;
+	struct crypto_skcipher *fbk_cipher;
+	struct pci_dev *pdev;
+	struct cn10k_cpt_errata_ctx er_ctx;
+};
+
+union otx2_cpt_offset_ctrl {
+	u64 flags;
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved:32;
+		u64 enc_data_offset:16;
+		u64 iv_offset:8;
+		u64 auth_offset:8;
+#else
+		u64 auth_offset:8;
+		u64 iv_offset:8;
+		u64 enc_data_offset:16;
+		u64 reserved:32;
+#endif
+	} e;
+};
+
+struct otx2_cpt_req_ctx {
+	struct otx2_cpt_req_info cpt_req;
+	union otx2_cpt_offset_ctrl ctrl_word;
+	struct otx2_cpt_fc_ctx fctx;
+	union {
+		struct skcipher_request sk_fbk_req;
+		struct aead_request fbk_req;
+	};
+};
+
+struct otx2_cpt_sdesc {
+	struct shash_desc shash;
+};
+
+struct otx2_cpt_aead_ctx {
+	u8 key[OTX2_CPT_MAX_KEY_SIZE];
+	struct crypto_shash *hashalg;
+	struct otx2_cpt_sdesc *sdesc;
+	struct crypto_aead *fbk_cipher;
+	struct cn10k_cpt_errata_ctx er_ctx;
+	struct pci_dev *pdev;
+	u8 *ipad;
+	u8 *opad;
+	u32 enc_key_len;
+	u32 auth_key_len;
+	u8 cipher_type;
+	u8 mac_type;
+	u8 key_type;
+	u8 is_trunc_hmac;
+	u8 enc_align_len;
+};
+int otx2_cpt_crypto_init(struct pci_dev *pdev, struct module *mod,
+			 int num_queues, int num_devices);
+void otx2_cpt_crypto_exit(struct pci_dev *pdev, struct module *mod);
+
+#endif /* __OTX2_CPT_ALGS_H */

linux-7.2.3/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c

@@ -0,0 +1,482 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Marvell. */
+
+#include "otx2_cpt_common.h"
+#include "otx2_cptvf.h"
+#include "otx2_cptlf.h"
+#include "otx2_cptvf_algs.h"
+#include "cn10k_cpt.h"
+#include <rvu_reg.h>
+
+#define OTX2_CPTVF_DRV_NAME "rvu_cptvf"
+
+static void cptvf_enable_pfvf_mbox_intrs(struct otx2_cptvf_dev *cptvf)
+{
+	/* Clear interrupt if any */
+	otx2_cpt_write64(cptvf->reg_base, BLKADDR_RVUM, 0, OTX2_RVU_VF_INT,
+			 0x1ULL);
+
+	/* Enable PF-VF interrupt */
+	otx2_cpt_write64(cptvf->reg_base, BLKADDR_RVUM, 0,
+			 OTX2_RVU_VF_INT_ENA_W1S, 0x1ULL);
+}
+
+static void cptvf_disable_pfvf_mbox_intrs(struct otx2_cptvf_dev *cptvf)
+{
+	/* Disable PF-VF interrupt */
+	otx2_cpt_write64(cptvf->reg_base, BLKADDR_RVUM, 0,
+			 OTX2_RVU_VF_INT_ENA_W1C, 0x1ULL);
+
+	/* Clear interrupt if any */
+	otx2_cpt_write64(cptvf->reg_base, BLKADDR_RVUM, 0, OTX2_RVU_VF_INT,
+			 0x1ULL);
+}
+
+static int cptvf_register_interrupts(struct otx2_cptvf_dev *cptvf)
+{
+	int ret, irq;
+	int num_vec;
+
+	num_vec = pci_msix_vec_count(cptvf->pdev);
+	if (num_vec <= 0)
+		return -EINVAL;
+
+	/* Enable MSI-X */
+	ret = pci_alloc_irq_vectors(cptvf->pdev, num_vec, num_vec,
+				    PCI_IRQ_MSIX);
+	if (ret < 0) {
+		dev_err(&cptvf->pdev->dev,
+			"Request for %d msix vectors failed\n", num_vec);
+		return ret;
+	}
+	irq = pci_irq_vector(cptvf->pdev, OTX2_CPT_VF_INT_VEC_E_MBOX);
+	/* Register VF<=>PF mailbox interrupt handler */
+	ret = devm_request_irq(&cptvf->pdev->dev, irq,
+			       otx2_cptvf_pfvf_mbox_intr, 0,
+			       "CPTPFVF Mbox", cptvf);
+	if (ret)
+		return ret;
+	/* Enable PF-VF mailbox interrupts */
+	cptvf_enable_pfvf_mbox_intrs(cptvf);
+
+	ret = otx2_cpt_send_ready_msg(&cptvf->pfvf_mbox, cptvf->pdev);
+	if (ret) {
+		dev_warn(&cptvf->pdev->dev,
+			 "PF not responding to mailbox, deferring probe\n");
+		cptvf_disable_pfvf_mbox_intrs(cptvf);
+		return -EPROBE_DEFER;
+	}
+	return 0;
+}
+
+static int cptvf_pfvf_mbox_init(struct otx2_cptvf_dev *cptvf)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+	resource_size_t offset, size;
+	int ret;
+
+	cptvf->pfvf_mbox_wq =
+		alloc_ordered_workqueue("cpt_pfvf_mailbox",
+					WQ_HIGHPRI | WQ_MEM_RECLAIM);
+	if (!cptvf->pfvf_mbox_wq)
+		return -ENOMEM;
+
+	if (test_bit(CN10K_MBOX, &cptvf->cap_flag)) {
+		/* For cn10k platform, VF mailbox region is in its BAR2
+		 * register space
+		 */
+		cptvf->pfvf_mbox_base = cptvf->reg_base +
+					CN10K_CPT_VF_MBOX_REGION;
+	} else {
+		offset = pci_resource_start(pdev, PCI_MBOX_BAR_NUM);
+		size = pci_resource_len(pdev, PCI_MBOX_BAR_NUM);
+		/* Map PF-VF mailbox memory */
+		cptvf->pfvf_mbox_base = devm_ioremap_wc(&pdev->dev, offset,
+							size);
+		if (!cptvf->pfvf_mbox_base) {
+			dev_err(&pdev->dev, "Unable to map BAR4\n");
+			ret = -ENOMEM;
+			goto free_wqe;
+		}
+	}
+
+	ret = otx2_mbox_init(&cptvf->pfvf_mbox, cptvf->pfvf_mbox_base,
+			     pdev, cptvf->reg_base, MBOX_DIR_VFPF, 1);
+	if (ret)
+		goto free_wqe;
+
+	ret = otx2_cpt_mbox_bbuf_init(cptvf, pdev);
+	if (ret)
+		goto destroy_mbox;
+
+	INIT_WORK(&cptvf->pfvf_mbox_work, otx2_cptvf_pfvf_mbox_handler);
+	return 0;
+
+destroy_mbox:
+	otx2_mbox_destroy(&cptvf->pfvf_mbox);
+free_wqe:
+	destroy_workqueue(cptvf->pfvf_mbox_wq);
+	return ret;
+}
+
+static void cptvf_pfvf_mbox_destroy(struct otx2_cptvf_dev *cptvf)
+{
+	destroy_workqueue(cptvf->pfvf_mbox_wq);
+	otx2_mbox_destroy(&cptvf->pfvf_mbox);
+}
+
+static void cptlf_work_handler(unsigned long data)
+{
+	otx2_cpt_post_process((struct otx2_cptlf_wqe *) data);
+}
+
+static void cleanup_tasklet_work(struct otx2_cptlfs_info *lfs)
+{
+	int i;
+
+	for (i = 0; i <  lfs->lfs_num; i++) {
+		if (!lfs->lf[i].wqe)
+			continue;
+
+		tasklet_kill(&lfs->lf[i].wqe->work);
+		kfree(lfs->lf[i].wqe);
+		lfs->lf[i].wqe = NULL;
+	}
+}
+
+static int init_tasklet_work(struct otx2_cptlfs_info *lfs)
+{
+	struct otx2_cptlf_wqe *wqe;
+	int i, ret = 0;
+
+	for (i = 0; i < lfs->lfs_num; i++) {
+		wqe = kzalloc_obj(struct otx2_cptlf_wqe);
+		if (!wqe) {
+			ret = -ENOMEM;
+			goto cleanup_tasklet;
+		}
+
+		tasklet_init(&wqe->work, cptlf_work_handler, (u64) wqe);
+		wqe->lfs = lfs;
+		wqe->lf_num = i;
+		lfs->lf[i].wqe = wqe;
+	}
+	return 0;
+
+cleanup_tasklet:
+	cleanup_tasklet_work(lfs);
+	return ret;
+}
+
+static void free_pending_queues(struct otx2_cptlfs_info *lfs)
+{
+	int i;
+
+	for (i = 0; i < lfs->lfs_num; i++) {
+		kfree(lfs->lf[i].pqueue.head);
+		lfs->lf[i].pqueue.head = NULL;
+	}
+}
+
+static int alloc_pending_queues(struct otx2_cptlfs_info *lfs)
+{
+	int size, ret, i;
+
+	if (!lfs->lfs_num)
+		return -EINVAL;
+
+	for (i = 0; i < lfs->lfs_num; i++) {
+		lfs->lf[i].pqueue.qlen = OTX2_CPT_INST_QLEN_MSGS;
+		size = lfs->lf[i].pqueue.qlen *
+		       sizeof(struct otx2_cpt_pending_entry);
+
+		lfs->lf[i].pqueue.head = kzalloc(size, GFP_KERNEL);
+		if (!lfs->lf[i].pqueue.head) {
+			ret = -ENOMEM;
+			goto error;
+		}
+
+		/* Initialize spin lock */
+		spin_lock_init(&lfs->lf[i].pqueue.lock);
+	}
+	return 0;
+
+error:
+	free_pending_queues(lfs);
+	return ret;
+}
+
+static void lf_sw_cleanup(struct otx2_cptlfs_info *lfs)
+{
+	cleanup_tasklet_work(lfs);
+	free_pending_queues(lfs);
+}
+
+static int lf_sw_init(struct otx2_cptlfs_info *lfs)
+{
+	int ret;
+
+	ret = alloc_pending_queues(lfs);
+	if (ret) {
+		dev_err(&lfs->pdev->dev,
+			"Allocating pending queues failed\n");
+		return ret;
+	}
+	ret = init_tasklet_work(lfs);
+	if (ret) {
+		dev_err(&lfs->pdev->dev,
+			"Tasklet work init failed\n");
+		goto pending_queues_free;
+	}
+	return 0;
+
+pending_queues_free:
+	free_pending_queues(lfs);
+	return ret;
+}
+
+static void cptvf_lf_shutdown(struct otx2_cptlfs_info *lfs)
+{
+	atomic_set(&lfs->state, OTX2_CPTLF_IN_RESET);
+
+	/* Remove interrupts affinity */
+	otx2_cptlf_free_irqs_affinity(lfs);
+	/* Disable instruction queue */
+	otx2_cptlf_disable_iqueues(lfs);
+	/* Unregister crypto algorithms */
+	otx2_cpt_crypto_exit(lfs->pdev, THIS_MODULE);
+	/* Unregister LFs interrupts */
+	otx2_cptlf_unregister_misc_interrupts(lfs);
+	otx2_cptlf_unregister_done_interrupts(lfs);
+	/* Cleanup LFs software side */
+	lf_sw_cleanup(lfs);
+	/* Free instruction queues */
+	otx2_cpt_free_instruction_queues(lfs);
+	/* Send request to detach LFs */
+	otx2_cpt_detach_rsrcs_msg(lfs);
+	lfs->lfs_num = 0;
+}
+
+static int cptvf_lf_init(struct otx2_cptvf_dev *cptvf)
+{
+	struct otx2_cptlfs_info *lfs = &cptvf->lfs;
+	struct device *dev = &cptvf->pdev->dev;
+	int ret, lfs_num;
+	u8 eng_grp_msk;
+
+	/* Get engine group number for symmetric crypto */
+	cptvf->lfs.kcrypto_se_eng_grp_num = OTX2_CPT_INVALID_CRYPTO_ENG_GRP;
+	ret = otx2_cptvf_send_eng_grp_num_msg(cptvf, OTX2_CPT_SE_TYPES);
+	if (ret)
+		return ret;
+
+	if (cptvf->lfs.kcrypto_se_eng_grp_num ==
+		OTX2_CPT_INVALID_CRYPTO_ENG_GRP) {
+		dev_err(dev,
+			"Symmetric Engine group for crypto not available\n");
+		return -ENOENT;
+	}
+
+	/* Get engine group number for asymmetric crypto */
+	cptvf->lfs.kcrypto_ae_eng_grp_num = OTX2_CPT_INVALID_CRYPTO_ENG_GRP;
+	ret = otx2_cptvf_send_eng_grp_num_msg(cptvf, OTX2_CPT_AE_TYPES);
+	if (ret)
+		return ret;
+
+	if (cptvf->lfs.kcrypto_ae_eng_grp_num ==
+		OTX2_CPT_INVALID_CRYPTO_ENG_GRP) {
+		dev_err(dev,
+			"Asymmetric Engine group for crypto not available\n");
+		return -ENOENT;
+	}
+
+	eng_grp_msk = BIT(cptvf->lfs.kcrypto_se_eng_grp_num) |
+		      BIT(cptvf->lfs.kcrypto_ae_eng_grp_num);
+
+	ret = otx2_cptvf_send_kvf_limits_msg(cptvf);
+	if (ret)
+		return ret;
+
+	lfs_num = cptvf->lfs.kvf_limits;
+
+	ret = otx2_cptlf_init(lfs, eng_grp_msk, OTX2_CPT_QUEUE_HI_PRIO,
+			      lfs_num);
+	if (ret)
+		return ret;
+
+	/* Get msix offsets for attached LFs */
+	ret = otx2_cpt_msix_offset_msg(lfs);
+	if (ret)
+		goto cleanup_lf;
+
+	/* Initialize LFs software side */
+	ret = lf_sw_init(lfs);
+	if (ret)
+		goto cleanup_lf;
+
+	/* Register LFs interrupts */
+	ret = otx2_cptlf_register_misc_interrupts(lfs);
+	if (ret)
+		goto cleanup_lf_sw;
+
+	ret = otx2_cptlf_register_done_interrupts(lfs);
+	if (ret)
+		goto cleanup_lf_sw;
+
+	/* Set interrupts affinity */
+	ret = otx2_cptlf_set_irqs_affinity(lfs);
+	if (ret)
+		goto unregister_intr;
+
+	atomic_set(&lfs->state, OTX2_CPTLF_STARTED);
+	/* Register crypto algorithms */
+	ret = otx2_cpt_crypto_init(lfs->pdev, THIS_MODULE, lfs_num, 1);
+	if (ret) {
+		dev_err(&lfs->pdev->dev, "algorithms registration failed\n");
+		goto disable_irqs;
+	}
+	return 0;
+
+disable_irqs:
+	otx2_cptlf_free_irqs_affinity(lfs);
+unregister_intr:
+	otx2_cptlf_unregister_misc_interrupts(lfs);
+	otx2_cptlf_unregister_done_interrupts(lfs);
+cleanup_lf_sw:
+	lf_sw_cleanup(lfs);
+cleanup_lf:
+	otx2_cptlf_shutdown(lfs);
+
+	return ret;
+}
+
+static int otx2_cptvf_probe(struct pci_dev *pdev,
+			    const struct pci_device_id *ent)
+{
+	struct device *dev = &pdev->dev;
+	struct otx2_cptvf_dev *cptvf;
+	int ret;
+
+	cptvf = devm_kzalloc(dev, sizeof(*cptvf), GFP_KERNEL);
+	if (!cptvf)
+		return -ENOMEM;
+
+	ret = pcim_enable_device(pdev);
+	if (ret) {
+		dev_err(dev, "Failed to enable PCI device\n");
+		goto clear_drvdata;
+	}
+
+	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
+	if (ret) {
+		dev_err(dev, "Unable to get usable DMA configuration\n");
+		goto clear_drvdata;
+	}
+
+	ret = pcim_request_all_regions(pdev, OTX2_CPTVF_DRV_NAME);
+	if (ret) {
+		dev_err(dev, "Couldn't get PCI resources 0x%x\n", ret);
+		goto clear_drvdata;
+	}
+	pci_set_master(pdev);
+	pci_set_drvdata(pdev, cptvf);
+	cptvf->pdev = pdev;
+
+	/* Map VF's configuration registers */
+	cptvf->reg_base = pcim_iomap(pdev, PCI_PF_REG_BAR_NUM, 0);
+	if (!cptvf->reg_base) {
+		ret = -ENOMEM;
+		dev_err(dev, "Couldn't ioremap PCI resource 0x%x\n", ret);
+		goto clear_drvdata;
+	}
+
+	otx2_cpt_set_hw_caps(pdev, &cptvf->cap_flag);
+
+	/* Initialize PF<=>VF mailbox */
+	ret = cptvf_pfvf_mbox_init(cptvf);
+	if (ret)
+		goto clear_drvdata;
+
+	/* Register interrupts */
+	ret = cptvf_register_interrupts(cptvf);
+	if (ret)
+		goto destroy_pfvf_mbox;
+
+	cptvf->blkaddr = BLKADDR_CPT0;
+
+	cptvf_hw_ops_get(cptvf);
+
+	otx2_cptlf_set_dev_info(&cptvf->lfs, cptvf->pdev, cptvf->reg_base,
+				&cptvf->pfvf_mbox, cptvf->blkaddr);
+
+	ret = otx2_cptvf_send_caps_msg(cptvf);
+	if (ret) {
+		dev_err(&pdev->dev, "Couldn't get CPT engine capabilities.\n");
+		goto unregister_interrupts;
+	}
+	if (cptvf->eng_caps[OTX2_CPT_SE_TYPES] & BIT_ULL(35))
+		cptvf->lfs.ops->cpt_sg_info_create = cn10k_sgv2_info_create;
+
+	ret = cn10k_cptvf_lmtst_init(cptvf);
+	if (ret)
+		goto unregister_interrupts;
+
+	/* Initialize CPT LFs */
+	ret = cptvf_lf_init(cptvf);
+	if (ret)
+		goto free_lmtst;
+
+	return 0;
+
+free_lmtst:
+	cn10k_cpt_lmtst_free(pdev, &cptvf->lfs);
+unregister_interrupts:
+	cptvf_disable_pfvf_mbox_intrs(cptvf);
+destroy_pfvf_mbox:
+	cptvf_pfvf_mbox_destroy(cptvf);
+clear_drvdata:
+	pci_set_drvdata(pdev, NULL);
+
+	return ret;
+}
+
+static void otx2_cptvf_remove(struct pci_dev *pdev)
+{
+	struct otx2_cptvf_dev *cptvf = pci_get_drvdata(pdev);
+
+	if (!cptvf) {
+		dev_err(&pdev->dev, "Invalid CPT VF device.\n");
+		return;
+	}
+	cptvf_lf_shutdown(&cptvf->lfs);
+	/* Disable PF-VF mailbox interrupt */
+	cptvf_disable_pfvf_mbox_intrs(cptvf);
+	/* Destroy PF-VF mbox */
+	cptvf_pfvf_mbox_destroy(cptvf);
+	/* Free LMTST memory */
+	cn10k_cpt_lmtst_free(pdev, &cptvf->lfs);
+	pci_set_drvdata(pdev, NULL);
+}
+
+/* Supported devices */
+static const struct pci_device_id otx2_cptvf_id_table[] = {
+	{ PCI_VDEVICE(CAVIUM, OTX2_CPT_PCI_VF_DEVICE_ID) },
+	{ PCI_VDEVICE(CAVIUM, CN10K_CPT_PCI_VF_DEVICE_ID) },
+	{ }  /* end of table */
+};
+MODULE_DEVICE_TABLE(pci, otx2_cptvf_id_table);
+
+static struct pci_driver otx2_cptvf_pci_driver = {
+	.name = OTX2_CPTVF_DRV_NAME,
+	.id_table = otx2_cptvf_id_table,
+	.probe = otx2_cptvf_probe,
+	.remove = otx2_cptvf_remove,
+};
+
+module_pci_driver(otx2_cptvf_pci_driver);
+
+MODULE_IMPORT_NS("CRYPTO_DEV_OCTEONTX2_CPT");
+
+MODULE_AUTHOR("Marvell");
+MODULE_DESCRIPTION("Marvell RVU CPT Virtual Function Driver");
+MODULE_LICENSE("GPL v2");

linux-7.2.3/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c

@@ -0,0 +1,241 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Marvell. */
+
+#include "otx2_cpt_common.h"
+#include "otx2_cptvf.h"
+#include <rvu_reg.h>
+
+int otx2_cpt_mbox_bbuf_init(struct otx2_cptvf_dev *cptvf, struct pci_dev *pdev)
+{
+	struct otx2_mbox_dev *mdev;
+	struct otx2_mbox *otx2_mbox;
+
+	cptvf->bbuf_base = devm_kmalloc(&pdev->dev, MBOX_SIZE, GFP_KERNEL);
+	if (!cptvf->bbuf_base)
+		return -ENOMEM;
+	/*
+	 * Overwrite mbox mbase to point to bounce buffer, so that PF/VF
+	 * prepare all mbox messages in bounce buffer instead of directly
+	 * in hw mbox memory.
+	 */
+	otx2_mbox = &cptvf->pfvf_mbox;
+	mdev = &otx2_mbox->dev[0];
+	mdev->mbase = cptvf->bbuf_base;
+
+	return 0;
+}
+
+static void otx2_cpt_sync_mbox_bbuf(struct otx2_mbox *mbox, int devid)
+{
+	u16 msgs_offset = ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN);
+	void *hw_mbase = mbox->hwbase + (devid * MBOX_SIZE);
+	struct otx2_mbox_dev *mdev = &mbox->dev[devid];
+	struct mbox_hdr *hdr;
+	u64 msg_size;
+
+	if (mdev->mbase == hw_mbase)
+		return;
+
+	hdr = hw_mbase + mbox->rx_start;
+	msg_size = hdr->msg_size;
+
+	if (msg_size > mbox->rx_size - msgs_offset)
+		msg_size = mbox->rx_size - msgs_offset;
+
+	/* Copy mbox messages from mbox memory to bounce buffer */
+	memcpy(mdev->mbase + mbox->rx_start,
+	       hw_mbase + mbox->rx_start, msg_size + msgs_offset);
+}
+
+irqreturn_t otx2_cptvf_pfvf_mbox_intr(int __always_unused irq, void *arg)
+{
+	struct otx2_cptvf_dev *cptvf = arg;
+	u64 intr;
+
+	/* Read the interrupt bits */
+	intr = otx2_cpt_read64(cptvf->reg_base, BLKADDR_RVUM, 0,
+			       OTX2_RVU_VF_INT);
+
+	if (intr & 0x1ULL) {
+		/* Schedule work queue function to process the MBOX request */
+		queue_work(cptvf->pfvf_mbox_wq, &cptvf->pfvf_mbox_work);
+		/* Clear and ack the interrupt */
+		otx2_cpt_write64(cptvf->reg_base, BLKADDR_RVUM, 0,
+				 OTX2_RVU_VF_INT, 0x1ULL);
+	}
+	return IRQ_HANDLED;
+}
+
+static void process_pfvf_mbox_mbox_msg(struct otx2_cptvf_dev *cptvf,
+				       struct mbox_msghdr *msg)
+{
+	struct otx2_cptlfs_info *lfs = &cptvf->lfs;
+	struct otx2_cpt_kvf_limits_rsp *rsp_limits;
+	struct otx2_cpt_egrp_num_rsp *rsp_grp;
+	struct otx2_cpt_caps_rsp *eng_caps;
+	struct cpt_rd_wr_reg_msg *rsp_reg;
+	struct msix_offset_rsp *rsp_msix;
+	u8 grp_num;
+	int i;
+
+	if (msg->id >= MBOX_MSG_MAX) {
+		dev_err(&cptvf->pdev->dev,
+			"MBOX msg with unknown ID %d\n", msg->id);
+		return;
+	}
+	if (msg->sig != OTX2_MBOX_RSP_SIG) {
+		dev_err(&cptvf->pdev->dev,
+			"MBOX msg with wrong signature %x, ID %d\n",
+			msg->sig, msg->id);
+		return;
+	}
+	switch (msg->id) {
+	case MBOX_MSG_READY:
+		cptvf->vf_id = ((msg->pcifunc >> RVU_PFVF_FUNC_SHIFT)
+				& RVU_PFVF_FUNC_MASK) - 1;
+		break;
+	case MBOX_MSG_ATTACH_RESOURCES:
+		/* Check if resources were successfully attached */
+		if (!msg->rc)
+			lfs->are_lfs_attached = 1;
+		break;
+	case MBOX_MSG_DETACH_RESOURCES:
+		/* Check if resources were successfully detached */
+		if (!msg->rc)
+			lfs->are_lfs_attached = 0;
+		break;
+	case MBOX_MSG_MSIX_OFFSET:
+		rsp_msix = (struct msix_offset_rsp *) msg;
+		for (i = 0; i < rsp_msix->cptlfs; i++)
+			lfs->lf[i].msix_offset = rsp_msix->cptlf_msixoff[i];
+		break;
+	case MBOX_MSG_CPT_RD_WR_REGISTER:
+		rsp_reg = (struct cpt_rd_wr_reg_msg *) msg;
+		if (msg->rc) {
+			dev_err(&cptvf->pdev->dev,
+				"Reg %llx rd/wr(%d) failed %d\n",
+				rsp_reg->reg_offset, rsp_reg->is_write,
+				msg->rc);
+			return;
+		}
+		if (!rsp_reg->is_write)
+			*rsp_reg->ret_val = rsp_reg->val;
+		break;
+	case MBOX_MSG_GET_ENG_GRP_NUM:
+		rsp_grp = (struct otx2_cpt_egrp_num_rsp *) msg;
+		grp_num = rsp_grp->eng_grp_num;
+		if (rsp_grp->eng_type == OTX2_CPT_SE_TYPES)
+			cptvf->lfs.kcrypto_se_eng_grp_num = grp_num;
+		else if (rsp_grp->eng_type == OTX2_CPT_AE_TYPES)
+			cptvf->lfs.kcrypto_ae_eng_grp_num = grp_num;
+		break;
+	case MBOX_MSG_GET_KVF_LIMITS:
+		rsp_limits = (struct otx2_cpt_kvf_limits_rsp *) msg;
+		cptvf->lfs.kvf_limits = rsp_limits->kvf_limits;
+		break;
+	case MBOX_MSG_GET_CAPS:
+		eng_caps = (struct otx2_cpt_caps_rsp *)msg;
+		memcpy(cptvf->eng_caps, eng_caps->eng_caps,
+		       sizeof(cptvf->eng_caps));
+		break;
+	case MBOX_MSG_CPT_LF_RESET:
+	case MBOX_MSG_LMTST_TBL_SETUP:
+		break;
+	default:
+		dev_err(&cptvf->pdev->dev, "Unsupported msg %d received.\n",
+			msg->id);
+		break;
+	}
+}
+
+void otx2_cptvf_pfvf_mbox_handler(struct work_struct *work)
+{
+	struct otx2_cptvf_dev *cptvf;
+	struct otx2_mbox *pfvf_mbox;
+	struct otx2_mbox_dev *mdev;
+	struct mbox_hdr *rsp_hdr;
+	struct mbox_msghdr *msg;
+	int offset, i;
+
+	/* sync with mbox memory region */
+	smp_rmb();
+
+	cptvf = container_of(work, struct otx2_cptvf_dev, pfvf_mbox_work);
+	pfvf_mbox = &cptvf->pfvf_mbox;
+	otx2_cpt_sync_mbox_bbuf(pfvf_mbox, 0);
+	mdev = &pfvf_mbox->dev[0];
+	rsp_hdr = (struct mbox_hdr *)(mdev->mbase + pfvf_mbox->rx_start);
+	if (rsp_hdr->num_msgs == 0)
+		return;
+	offset = ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN);
+
+	for (i = 0; i < rsp_hdr->num_msgs; i++) {
+		msg = (struct mbox_msghdr *)(mdev->mbase + pfvf_mbox->rx_start +
+					     offset);
+		process_pfvf_mbox_mbox_msg(cptvf, msg);
+		offset = msg->next_msgoff;
+		mdev->msgs_acked++;
+	}
+	otx2_mbox_reset(pfvf_mbox, 0);
+}
+
+int otx2_cptvf_send_eng_grp_num_msg(struct otx2_cptvf_dev *cptvf, int eng_type)
+{
+	struct otx2_mbox *mbox = &cptvf->pfvf_mbox;
+	struct pci_dev *pdev = cptvf->pdev;
+	struct otx2_cpt_egrp_num_msg *req;
+
+	req = (struct otx2_cpt_egrp_num_msg *)
+	      otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req),
+				      sizeof(struct otx2_cpt_egrp_num_rsp));
+	if (req == NULL) {
+		dev_err(&pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+	req->hdr.id = MBOX_MSG_GET_ENG_GRP_NUM;
+	req->hdr.sig = OTX2_MBOX_REQ_SIG;
+	req->hdr.pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->pdev, cptvf->vf_id, 0);
+	req->eng_type = eng_type;
+
+	return otx2_cpt_send_mbox_msg(mbox, pdev);
+}
+
+int otx2_cptvf_send_kvf_limits_msg(struct otx2_cptvf_dev *cptvf)
+{
+	struct otx2_mbox *mbox = &cptvf->pfvf_mbox;
+	struct pci_dev *pdev = cptvf->pdev;
+	struct mbox_msghdr *req;
+
+	req = (struct mbox_msghdr *)
+	      otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req),
+				      sizeof(struct otx2_cpt_kvf_limits_rsp));
+	if (req == NULL) {
+		dev_err(&pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+	req->id = MBOX_MSG_GET_KVF_LIMITS;
+	req->sig = OTX2_MBOX_REQ_SIG;
+	req->pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->pdev, cptvf->vf_id, 0);
+
+	return otx2_cpt_send_mbox_msg(mbox, pdev);
+}
+
+int otx2_cptvf_send_caps_msg(struct otx2_cptvf_dev *cptvf)
+{
+	struct otx2_mbox *mbox = &cptvf->pfvf_mbox;
+	struct pci_dev *pdev = cptvf->pdev;
+	struct mbox_msghdr *req;
+
+	req = (struct mbox_msghdr *)
+	      otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req),
+				      sizeof(struct otx2_cpt_caps_rsp));
+	if (!req) {
+		dev_err(&pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+	req->id = MBOX_MSG_GET_CAPS;
+	req->sig = OTX2_MBOX_REQ_SIG;
+	req->pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->pdev, cptvf->vf_id, 0);
+
+	return otx2_cpt_send_mbox_msg(mbox, pdev);
+}

linux-7.2.3/drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c

@@ -0,0 +1,409 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Marvell. */
+
+#include "otx2_cptvf.h"
+#include "otx2_cpt_common.h"
+
+/* Default timeout when waiting for free pending entry in us */
+#define CPT_PENTRY_TIMEOUT	1000
+#define CPT_PENTRY_STEP		50
+
+/* Default threshold for stopping and resuming sender requests */
+#define CPT_IQ_STOP_MARGIN	128
+#define CPT_IQ_RESUME_MARGIN	512
+
+/* Default command timeout in seconds */
+#define CPT_COMMAND_TIMEOUT	4
+#define CPT_TIME_IN_RESET_COUNT 5
+
+static void otx2_cpt_dump_sg_list(struct pci_dev *pdev,
+				  struct otx2_cpt_req_info *req)
+{
+	int i;
+
+	pr_debug("Gather list size %d\n", req->in_cnt);
+	for (i = 0; i < req->in_cnt; i++) {
+		pr_debug("Buffer %d size %d, vptr 0x%p, dmaptr 0x%llx\n", i,
+			 req->in[i].size, req->in[i].vptr,
+			 req->in[i].dma_addr);
+		pr_debug("Buffer hexdump (%d bytes)\n",
+			 req->in[i].size);
+		print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1,
+				     req->in[i].vptr, req->in[i].size, false);
+	}
+	pr_debug("Scatter list size %d\n", req->out_cnt);
+	for (i = 0; i < req->out_cnt; i++) {
+		pr_debug("Buffer %d size %d, vptr 0x%p, dmaptr 0x%llx\n", i,
+			 req->out[i].size, req->out[i].vptr,
+			 req->out[i].dma_addr);
+		pr_debug("Buffer hexdump (%d bytes)\n", req->out[i].size);
+		print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1,
+				     req->out[i].vptr, req->out[i].size, false);
+	}
+}
+
+static inline struct otx2_cpt_pending_entry *get_free_pending_entry(
+					struct otx2_cpt_pending_queue *q,
+					int qlen)
+{
+	struct otx2_cpt_pending_entry *ent = NULL;
+
+	ent = &q->head[q->rear];
+	if (unlikely(ent->busy))
+		return NULL;
+
+	q->rear++;
+	if (unlikely(q->rear == qlen))
+		q->rear = 0;
+
+	return ent;
+}
+
+static inline u32 modulo_inc(u32 index, u32 length, u32 inc)
+{
+	if (WARN_ON(inc > length))
+		inc = length;
+
+	index += inc;
+	if (unlikely(index >= length))
+		index -= length;
+
+	return index;
+}
+
+static inline void free_pentry(struct otx2_cpt_pending_entry *pentry)
+{
+	pentry->completion_addr = NULL;
+	pentry->info = NULL;
+	pentry->callback = NULL;
+	pentry->areq = NULL;
+	pentry->resume_sender = false;
+	pentry->busy = false;
+}
+
+static int process_request(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
+			   struct otx2_cpt_pending_queue *pqueue,
+			   struct otx2_cptlf_info *lf)
+{
+	struct otx2_cptvf_request *cpt_req = &req->req;
+	struct otx2_cpt_pending_entry *pentry = NULL;
+	union otx2_cpt_ctrl_info *ctrl = &req->ctrl;
+	struct otx2_cpt_inst_info *info = NULL;
+	union otx2_cpt_res_s *result = NULL;
+	struct otx2_cpt_iq_command iq_cmd;
+	union otx2_cpt_inst_s cptinst;
+	int retry, ret = 0;
+	u8 resume_sender;
+	gfp_t gfp;
+
+	gfp = (req->areq->flags & CRYPTO_TFM_REQ_MAY_SLEEP) ? GFP_KERNEL :
+							      GFP_ATOMIC;
+	if (unlikely(!otx2_cptlf_started(lf->lfs)))
+		return -ENODEV;
+
+	info = lf->lfs->ops->cpt_sg_info_create(pdev, req, gfp);
+	if (unlikely(!info)) {
+		dev_err(&pdev->dev, "Setting up cpt inst info failed");
+		return -ENOMEM;
+	}
+	cpt_req->dlen = info->dlen;
+
+	result = info->completion_addr;
+	result->s.compcode = OTX2_CPT_COMPLETION_CODE_INIT;
+
+	spin_lock_bh(&pqueue->lock);
+	pentry = get_free_pending_entry(pqueue, pqueue->qlen);
+	retry = CPT_PENTRY_TIMEOUT / CPT_PENTRY_STEP;
+	while (unlikely(!pentry) && retry--) {
+		spin_unlock_bh(&pqueue->lock);
+		udelay(CPT_PENTRY_STEP);
+		spin_lock_bh(&pqueue->lock);
+		pentry = get_free_pending_entry(pqueue, pqueue->qlen);
+	}
+
+	if (unlikely(!pentry)) {
+		ret = -ENOSPC;
+		goto destroy_info;
+	}
+
+	/*
+	 * Check if we are close to filling in entire pending queue,
+	 * if so then tell the sender to stop/sleep by returning -EBUSY
+	 * We do it only for context which can sleep (GFP_KERNEL)
+	 */
+	if (gfp == GFP_KERNEL &&
+	    pqueue->pending_count > (pqueue->qlen - CPT_IQ_STOP_MARGIN)) {
+		pentry->resume_sender = true;
+	} else
+		pentry->resume_sender = false;
+	resume_sender = pentry->resume_sender;
+	pqueue->pending_count++;
+
+	pentry->completion_addr = info->completion_addr;
+	pentry->info = info;
+	pentry->callback = req->callback;
+	pentry->areq = req->areq;
+	pentry->busy = true;
+	info->pentry = pentry;
+	info->time_in = jiffies;
+	info->req = req;
+
+	/* Fill in the command */
+	iq_cmd.cmd.u = 0;
+	iq_cmd.cmd.s.opcode = cpu_to_be16(cpt_req->opcode.flags);
+	iq_cmd.cmd.s.param1 = cpu_to_be16(cpt_req->param1);
+	iq_cmd.cmd.s.param2 = cpu_to_be16(cpt_req->param2);
+	iq_cmd.cmd.s.dlen   = cpu_to_be16(cpt_req->dlen);
+
+	/* 64-bit swap for microcode data reads, not needed for addresses*/
+	cpu_to_be64s(&iq_cmd.cmd.u);
+	iq_cmd.dptr = info->dptr_baddr | info->gthr_sz << 60;
+	iq_cmd.rptr = info->rptr_baddr | info->sctr_sz << 60;
+	iq_cmd.cptr.s.cptr = cpt_req->cptr_dma;
+	iq_cmd.cptr.s.grp = ctrl->s.grp;
+
+	/* Fill in the CPT_INST_S type command for HW interpretation */
+	otx2_cpt_fill_inst(&cptinst, &iq_cmd, info->comp_baddr);
+
+	/* Print debug info if enabled */
+	otx2_cpt_dump_sg_list(pdev, req);
+	pr_debug("Cpt_inst_s hexdump (%d bytes)\n", OTX2_CPT_INST_SIZE);
+	print_hex_dump_debug("", 0, 16, 1, &cptinst, OTX2_CPT_INST_SIZE, false);
+	pr_debug("Dptr hexdump (%d bytes)\n", cpt_req->dlen);
+	print_hex_dump_debug("", 0, 16, 1, info->in_buffer,
+			     cpt_req->dlen, false);
+
+	/* Send CPT command */
+	lf->lfs->ops->send_cmd(&cptinst, 1, lf);
+
+	/*
+	 * We allocate and prepare pending queue entry in critical section
+	 * together with submitting CPT instruction to CPT instruction queue
+	 * to make sure that order of CPT requests is the same in both
+	 * pending and instruction queues
+	 */
+	spin_unlock_bh(&pqueue->lock);
+
+	ret = resume_sender ? -EBUSY : -EINPROGRESS;
+	return ret;
+
+destroy_info:
+	spin_unlock_bh(&pqueue->lock);
+	otx2_cpt_info_destroy(pdev, info);
+	return ret;
+}
+
+int otx2_cpt_do_request(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
+			int cpu_num)
+{
+	struct otx2_cptvf_dev *cptvf = pci_get_drvdata(pdev);
+	struct otx2_cptlfs_info *lfs = &cptvf->lfs;
+
+	return process_request(lfs->pdev, req, &lfs->lf[cpu_num].pqueue,
+			       &lfs->lf[cpu_num]);
+}
+
+static int cpt_process_ccode(struct otx2_cptlfs_info *lfs,
+			     union otx2_cpt_res_s *cpt_status,
+			     struct otx2_cpt_inst_info *info,
+			     u32 *res_code)
+{
+	u8 uc_ccode = lfs->ops->cpt_get_uc_compcode(cpt_status);
+	u8 ccode = lfs->ops->cpt_get_compcode(cpt_status);
+	struct pci_dev *pdev = lfs->pdev;
+
+	switch (ccode) {
+	case OTX2_CPT_COMP_E_FAULT:
+		dev_err(&pdev->dev,
+			"Request failed with DMA fault\n");
+		otx2_cpt_dump_sg_list(pdev, info->req);
+		break;
+
+	case OTX2_CPT_COMP_E_HWERR:
+		dev_err(&pdev->dev,
+			"Request failed with hardware error\n");
+		otx2_cpt_dump_sg_list(pdev, info->req);
+		break;
+
+	case OTX2_CPT_COMP_E_INSTERR:
+		dev_err(&pdev->dev,
+			"Request failed with instruction error\n");
+		otx2_cpt_dump_sg_list(pdev, info->req);
+		break;
+
+	case OTX2_CPT_COMP_E_NOTDONE:
+		/* check for timeout */
+		if (time_after_eq(jiffies, info->time_in +
+				  CPT_COMMAND_TIMEOUT * HZ))
+			dev_warn(&pdev->dev,
+				 "Request timed out 0x%p", info->req);
+		else if (info->extra_time < CPT_TIME_IN_RESET_COUNT) {
+			info->time_in = jiffies;
+			info->extra_time++;
+		}
+		return 1;
+
+	case OTX2_CPT_COMP_E_GOOD:
+	case OTX2_CPT_COMP_E_WARN:
+		/*
+		 * Check microcode completion code, it is only valid
+		 * when completion code is CPT_COMP_E::GOOD
+		 */
+		if (uc_ccode != OTX2_CPT_UCC_SUCCESS) {
+			/*
+			 * If requested hmac is truncated and ucode returns
+			 * s/g write length error then we report success
+			 * because ucode writes as many bytes of calculated
+			 * hmac as available in gather buffer and reports
+			 * s/g write length error if number of bytes in gather
+			 * buffer is less than full hmac size.
+			 */
+			if (info->req->is_trunc_hmac &&
+			    uc_ccode == OTX2_CPT_UCC_SG_WRITE_LENGTH) {
+				*res_code = 0;
+				break;
+			}
+
+			pr_debug("Request failed with software error code 0x%x: algo = %s driver = %s\n",
+				 cpt_status->s.uc_compcode,
+				 info->req->areq->tfm->__crt_alg->cra_name,
+				 info->req->areq->tfm->__crt_alg->cra_driver_name);
+			otx2_cpt_dump_sg_list(pdev, info->req);
+			break;
+		}
+		/* Request has been processed with success */
+		*res_code = 0;
+		break;
+
+	default:
+		dev_err(&pdev->dev,
+			"Request returned invalid status %d\n", ccode);
+		break;
+	}
+	return 0;
+}
+
+static inline void process_pending_queue(struct otx2_cptlfs_info *lfs,
+					 struct otx2_cpt_pending_queue *pqueue)
+{
+	struct otx2_cpt_pending_entry *resume_pentry = NULL;
+	void (*callback)(int status, void *arg, void *req);
+	struct otx2_cpt_pending_entry *pentry = NULL;
+	union otx2_cpt_res_s *cpt_status = NULL;
+	struct otx2_cpt_inst_info *info = NULL;
+	struct otx2_cpt_req_info *req = NULL;
+	struct crypto_async_request *areq;
+	struct pci_dev *pdev = lfs->pdev;
+	u32 res_code, resume_index;
+
+	while (1) {
+		spin_lock_bh(&pqueue->lock);
+		pentry = &pqueue->head[pqueue->front];
+
+		if (WARN_ON(!pentry)) {
+			spin_unlock_bh(&pqueue->lock);
+			break;
+		}
+
+		res_code = -EINVAL;
+		if (unlikely(!pentry->busy)) {
+			spin_unlock_bh(&pqueue->lock);
+			break;
+		}
+
+		if (unlikely(!pentry->callback)) {
+			dev_err(&pdev->dev, "Callback NULL\n");
+			goto process_pentry;
+		}
+
+		info = pentry->info;
+		if (unlikely(!info)) {
+			dev_err(&pdev->dev, "Pending entry post arg NULL\n");
+			goto process_pentry;
+		}
+
+		req = info->req;
+		if (unlikely(!req)) {
+			dev_err(&pdev->dev, "Request NULL\n");
+			goto process_pentry;
+		}
+
+		cpt_status = pentry->completion_addr;
+		if (unlikely(!cpt_status)) {
+			dev_err(&pdev->dev, "Completion address NULL\n");
+			goto process_pentry;
+		}
+
+		if (cpt_process_ccode(lfs, cpt_status, info, &res_code)) {
+			spin_unlock_bh(&pqueue->lock);
+			return;
+		}
+		info->pdev = pdev;
+
+process_pentry:
+		/*
+		 * Check if we should inform sending side to resume
+		 * We do it CPT_IQ_RESUME_MARGIN elements in advance before
+		 * pending queue becomes empty
+		 */
+		resume_index = modulo_inc(pqueue->front, pqueue->qlen,
+					  CPT_IQ_RESUME_MARGIN);
+		resume_pentry = &pqueue->head[resume_index];
+		if (resume_pentry &&
+		    resume_pentry->resume_sender) {
+			resume_pentry->resume_sender = false;
+			callback = resume_pentry->callback;
+			areq = resume_pentry->areq;
+
+			if (callback) {
+				spin_unlock_bh(&pqueue->lock);
+
+				/*
+				 * EINPROGRESS is an indication for sending
+				 * side that it can resume sending requests
+				 */
+				callback(-EINPROGRESS, areq, info);
+				spin_lock_bh(&pqueue->lock);
+			}
+		}
+
+		callback = pentry->callback;
+		areq = pentry->areq;
+		free_pentry(pentry);
+
+		pqueue->pending_count--;
+		pqueue->front = modulo_inc(pqueue->front, pqueue->qlen, 1);
+		spin_unlock_bh(&pqueue->lock);
+
+		/*
+		 * Call callback after current pending entry has been
+		 * processed, we don't do it if the callback pointer is
+		 * invalid.
+		 */
+		if (callback)
+			callback(res_code, areq, info);
+	}
+}
+
+void otx2_cpt_post_process(struct otx2_cptlf_wqe *wqe)
+{
+	process_pending_queue(wqe->lfs,
+			      &wqe->lfs->lf[wqe->lf_num].pqueue);
+}
+
+int otx2_cpt_get_eng_grp_num(struct pci_dev *pdev,
+			     enum otx2_cpt_eng_type eng_type)
+{
+	struct otx2_cptvf_dev *cptvf = pci_get_drvdata(pdev);
+
+	switch (eng_type) {
+	case OTX2_CPT_SE_TYPES:
+		return cptvf->lfs.kcrypto_se_eng_grp_num;
+	case OTX2_CPT_AE_TYPES:
+		return cptvf->lfs.kcrypto_ae_eng_grp_num;
+	default:
+		dev_err(&cptvf->pdev->dev, "Unsupported engine type");
+		break;
+	}
+	return -ENXIO;
+}