KVM: Don't pre-reserve xarray entries when storing empty/NULL attributesgrafted

Skip the xarray reservation loop when clearing all memory attributes, as
storing NULL only erases the entry and never needs to allocate, so no
reservation (and no cleanup of a failed one) is required in that case.

Suggested-by: Sean Christopherson <seanjc@google.com>
Cc: David Ballesteros <davimaba.v@proton.me>
Signed-off-by: Zeng Chi <zengchi@kylinos.cn>
Link: https://patch.msgid.link/20260921102442.1232375-1-zeng_chi911@163.com
[sean: split to separate patch]
Signed-off-by: Sean Christopherson <seanjc@google.com>

36 files changed, 11086 insertions, 0 deletions

diff --git a/drivers/crypto/cavium/Makefile b/drivers/crypto/cavium/Makefile
new file mode 100644
index 000000000..75227c587
--- /dev/null
+++ b/drivers/crypto/cavium/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for Cavium crypto device drivers
+#
+obj-$(CONFIG_CRYPTO_DEV_CPT) += cpt/
+obj-$(CONFIG_CRYPTO_DEV_NITROX) += nitrox/
diff --git a/drivers/crypto/cavium/cpt/Kconfig b/drivers/crypto/cavium/cpt/Kconfig
new file mode 100644
index 000000000..b9874058d
--- /dev/null
+++ b/drivers/crypto/cavium/cpt/Kconfig
@@ -0,0 +1,18 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Cavium crypto device configuration
+#
+
+config CRYPTO_DEV_CPT
+	tristate
+
+config CAVIUM_CPT
+	tristate "Cavium Cryptographic Accelerator driver"
+	depends on ARCH_THUNDER || COMPILE_TEST
+	depends on PCI_MSI && 64BIT
+	select CRYPTO_DEV_CPT
+	help
+	  Support for Cavium CPT block found in octeon-tx series of
+	  processors.
+
+	  To compile this as a module, choose M here.
diff --git a/drivers/crypto/cavium/cpt/Makefile b/drivers/crypto/cavium/cpt/Makefile
new file mode 100644
index 000000000..0f04f1b5c
--- /dev/null
+++ b/drivers/crypto/cavium/cpt/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_CAVIUM_CPT) += cptpf.o cptvf.o
+cptpf-objs := cptpf_main.o cptpf_mbox.o
+cptvf-objs := cptvf_main.o cptvf_reqmanager.o cptvf_mbox.o cptvf_algs.o
diff --git a/drivers/crypto/cavium/cpt/cpt_common.h b/drivers/crypto/cavium/cpt/cpt_common.h
new file mode 100644
index 000000000..eb3361518
--- /dev/null
+++ b/drivers/crypto/cavium/cpt/cpt_common.h
@@ -0,0 +1,153 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2016 Cavium, Inc.
+ */
+
+#ifndef __CPT_COMMON_H
+#define __CPT_COMMON_H
+
+#include <asm/byteorder.h>
+#include <linux/delay.h>
+#include <linux/pci.h>
+
+#include "cpt_hw_types.h"
+
+/* Device ID */
+#define CPT_81XX_PCI_PF_DEVICE_ID 0xa040
+#define CPT_81XX_PCI_VF_DEVICE_ID 0xa041
+
+/* flags to indicate the features supported */
+#define CPT_FLAG_SRIOV_ENABLED BIT(1)
+#define CPT_FLAG_VF_DRIVER BIT(2)
+#define CPT_FLAG_DEVICE_READY BIT(3)
+
+#define cpt_sriov_enabled(cpt) ((cpt)->flags & CPT_FLAG_SRIOV_ENABLED)
+#define cpt_vf_driver(cpt) ((cpt)->flags & CPT_FLAG_VF_DRIVER)
+#define cpt_device_ready(cpt) ((cpt)->flags & CPT_FLAG_DEVICE_READY)
+
+#define CPT_MBOX_MSG_TYPE_ACK 1
+#define CPT_MBOX_MSG_TYPE_NACK 2
+#define CPT_MBOX_MSG_TIMEOUT 2000
+#define VF_STATE_DOWN 0
+#define VF_STATE_UP 1
+
+/*
+ * CPT Registers map for 81xx
+ */
+
+/* PF registers */
+#define CPTX_PF_CONSTANTS(a) (0x0ll + ((u64)(a) << 36))
+#define CPTX_PF_RESET(a) (0x100ll + ((u64)(a) << 36))
+#define CPTX_PF_DIAG(a) (0x120ll + ((u64)(a) << 36))
+#define CPTX_PF_BIST_STATUS(a) (0x160ll + ((u64)(a) << 36))
+#define CPTX_PF_ECC0_CTL(a) (0x200ll + ((u64)(a) << 36))
+#define CPTX_PF_ECC0_FLIP(a) (0x210ll + ((u64)(a) << 36))
+#define CPTX_PF_ECC0_INT(a) (0x220ll + ((u64)(a) << 36))
+#define CPTX_PF_ECC0_INT_W1S(a) (0x230ll + ((u64)(a) << 36))
+#define CPTX_PF_ECC0_ENA_W1S(a)	(0x240ll + ((u64)(a) << 36))
+#define CPTX_PF_ECC0_ENA_W1C(a)	(0x250ll + ((u64)(a) << 36))
+#define CPTX_PF_MBOX_INTX(a, b)	\
+	(0x400ll + ((u64)(a) << 36) + ((b) << 3))
+#define CPTX_PF_MBOX_INT_W1SX(a, b) \
+	(0x420ll + ((u64)(a) << 36) + ((b) << 3))
+#define CPTX_PF_MBOX_ENA_W1CX(a, b) \
+	(0x440ll + ((u64)(a) << 36) + ((b) << 3))
+#define CPTX_PF_MBOX_ENA_W1SX(a, b) \
+	(0x460ll + ((u64)(a) << 36) + ((b) << 3))
+#define CPTX_PF_EXEC_INT(a) (0x500ll + 0x1000000000ll * ((a) & 0x1))
+#define CPTX_PF_EXEC_INT_W1S(a)	(0x520ll + ((u64)(a) << 36))
+#define CPTX_PF_EXEC_ENA_W1C(a)	(0x540ll + ((u64)(a) << 36))
+#define CPTX_PF_EXEC_ENA_W1S(a)	(0x560ll + ((u64)(a) << 36))
+#define CPTX_PF_GX_EN(a, b) \
+	(0x600ll + ((u64)(a) << 36) + ((b) << 3))
+#define CPTX_PF_EXEC_INFO(a) (0x700ll + ((u64)(a) << 36))
+#define CPTX_PF_EXEC_BUSY(a) (0x800ll + ((u64)(a) << 36))
+#define CPTX_PF_EXEC_INFO0(a) (0x900ll + ((u64)(a) << 36))
+#define CPTX_PF_EXEC_INFO1(a) (0x910ll + ((u64)(a) << 36))
+#define CPTX_PF_INST_REQ_PC(a) (0x10000ll + ((u64)(a) << 36))
+#define CPTX_PF_INST_LATENCY_PC(a) \
+	(0x10020ll + ((u64)(a) << 36))
+#define CPTX_PF_RD_REQ_PC(a) (0x10040ll + ((u64)(a) << 36))
+#define CPTX_PF_RD_LATENCY_PC(a) (0x10060ll + ((u64)(a) << 36))
+#define CPTX_PF_RD_UC_PC(a) (0x10080ll + ((u64)(a) << 36))
+#define CPTX_PF_ACTIVE_CYCLES_PC(a) (0x10100ll + ((u64)(a) << 36))
+#define CPTX_PF_EXE_CTL(a) (0x4000000ll + ((u64)(a) << 36))
+#define CPTX_PF_EXE_STATUS(a) (0x4000008ll + ((u64)(a) << 36))
+#define CPTX_PF_EXE_CLK(a) (0x4000010ll + ((u64)(a) << 36))
+#define CPTX_PF_EXE_DBG_CTL(a) (0x4000018ll + ((u64)(a) << 36))
+#define CPTX_PF_EXE_DBG_DATA(a)	(0x4000020ll + ((u64)(a) << 36))
+#define CPTX_PF_EXE_BIST_STATUS(a) (0x4000028ll + ((u64)(a) << 36))
+#define CPTX_PF_EXE_REQ_TIMER(a) (0x4000030ll + ((u64)(a) << 36))
+#define CPTX_PF_EXE_MEM_CTL(a) (0x4000038ll + ((u64)(a) << 36))
+#define CPTX_PF_EXE_PERF_CTL(a)	(0x4001000ll + ((u64)(a) << 36))
+#define CPTX_PF_EXE_DBG_CNTX(a, b) \
+	(0x4001100ll + ((u64)(a) << 36) + ((b) << 3))
+#define CPTX_PF_EXE_PERF_EVENT_CNT(a) (0x4001180ll + ((u64)(a) << 36))
+#define CPTX_PF_EXE_EPCI_INBX_CNT(a, b) \
+	(0x4001200ll + ((u64)(a) << 36) + ((b) << 3))
+#define CPTX_PF_EXE_EPCI_OUTBX_CNT(a, b) \
+	(0x4001240ll + ((u64)(a) << 36) + ((b) << 3))
+#define CPTX_PF_ENGX_UCODE_BASE(a, b) \
+	(0x4002000ll + ((u64)(a) << 36) + ((b) << 3))
+#define CPTX_PF_QX_CTL(a, b) \
+	(0x8000000ll + ((u64)(a) << 36) + ((b) << 20))
+#define CPTX_PF_QX_GMCTL(a, b) \
+	(0x8000020ll + ((u64)(a) << 36) + ((b) << 20))
+#define CPTX_PF_QX_CTL2(a, b) \
+	(0x8000100ll + ((u64)(a) << 36) + ((b) << 20))
+#define CPTX_PF_VFX_MBOXX(a, b, c) \
+	(0x8001000ll + ((u64)(a) << 36) + ((b) << 20) + ((c) << 8))
+
+/* VF registers */
+#define CPTX_VQX_CTL(a, b) (0x100ll + ((u64)(a) << 36) + ((b) << 20))
+#define CPTX_VQX_SADDR(a, b) (0x200ll + ((u64)(a) << 36) + ((b) << 20))
+#define CPTX_VQX_DONE_WAIT(a, b) (0x400ll + ((u64)(a) << 36) + ((b) << 20))
+#define CPTX_VQX_INPROG(a, b) (0x410ll + ((u64)(a) << 36) + ((b) << 20))
+#define CPTX_VQX_DONE(a, b) (0x420ll + ((u64)(a) << 36) + ((b) << 20))
+#define CPTX_VQX_DONE_ACK(a, b) (0x440ll + ((u64)(a) << 36) + ((b) << 20))
+#define CPTX_VQX_DONE_INT_W1S(a, b) (0x460ll + ((u64)(a) << 36) + ((b) << 20))
+#define CPTX_VQX_DONE_INT_W1C(a, b) (0x468ll + ((u64)(a) << 36) + ((b) << 20))
+#define CPTX_VQX_DONE_ENA_W1S(a, b) (0x470ll + ((u64)(a) << 36) + ((b) << 20))
+#define CPTX_VQX_DONE_ENA_W1C(a, b) (0x478ll + ((u64)(a) << 36) + ((b) << 20))
+#define CPTX_VQX_MISC_INT(a, b)	(0x500ll + ((u64)(a) << 36) + ((b) << 20))
+#define CPTX_VQX_MISC_INT_W1S(a, b) (0x508ll + ((u64)(a) << 36) + ((b) << 20))
+#define CPTX_VQX_MISC_ENA_W1S(a, b) (0x510ll + ((u64)(a) << 36) + ((b) << 20))
+#define CPTX_VQX_MISC_ENA_W1C(a, b) (0x518ll + ((u64)(a) << 36) + ((b) << 20))
+#define CPTX_VQX_DOORBELL(a, b) (0x600ll + ((u64)(a) << 36) + ((b) << 20))
+#define CPTX_VFX_PF_MBOXX(a, b, c) \
+	(0x1000ll + ((u64)(a) << 36) + ((b) << 20) + ((c) << 3))
+
+enum vftype {
+	AE_TYPES = 1,
+	SE_TYPES = 2,
+	BAD_CPT_TYPES,
+};
+
+/* Max CPT devices supported */
+enum cpt_mbox_opcode {
+	CPT_MSG_VF_UP = 1,
+	CPT_MSG_VF_DOWN,
+	CPT_MSG_READY,
+	CPT_MSG_QLEN,
+	CPT_MSG_QBIND_GRP,
+	CPT_MSG_VQ_PRIORITY,
+};
+
+/* CPT mailbox structure */
+struct cpt_mbox {
+	u64 msg; /* Message type MBOX[0] */
+	u64 data;/* Data         MBOX[1] */
+};
+
+/* Register read/write APIs */
+static inline void cpt_write_csr64(u8 __iomem *hw_addr, u64 offset,
+				   u64 val)
+{
+	writeq(val, hw_addr + offset);
+}
+
+static inline u64 cpt_read_csr64(u8 __iomem *hw_addr, u64 offset)
+{
+	return readq(hw_addr + offset);
+}
+#endif /* __CPT_COMMON_H */
diff --git a/drivers/crypto/cavium/cpt/cpt_hw_types.h b/drivers/crypto/cavium/cpt/cpt_hw_types.h
new file mode 100644
index 000000000..ae4791a8e
--- /dev/null
+++ b/drivers/crypto/cavium/cpt/cpt_hw_types.h
@@ -0,0 +1,655 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2016 Cavium, Inc.
+ */
+
+#ifndef __CPT_HW_TYPES_H
+#define __CPT_HW_TYPES_H
+
+#include "cpt_common.h"
+
+/**
+ * Enumeration cpt_comp_e
+ *
+ * CPT Completion Enumeration
+ * Enumerates the values of CPT_RES_S[COMPCODE].
+ */
+enum cpt_comp_e {
+	CPT_COMP_E_NOTDONE = 0x00,
+	CPT_COMP_E_GOOD = 0x01,
+	CPT_COMP_E_FAULT = 0x02,
+	CPT_COMP_E_SWERR = 0x03,
+	CPT_COMP_E_LAST_ENTRY = 0xFF
+};
+
+/**
+ * Structure 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 cpt_inst_s {
+	u64 u[8];
+	struct cpt_inst_s_s {
+#if defined(__BIG_ENDIAN_BITFIELD) /* Word 0 - Big Endian */
+		u64 reserved_17_63:47;
+		u64 doneint:1;
+		u64 reserved_0_1:16;
+#else /* Word 0 - Little Endian */
+		u64 reserved_0_15:16;
+		u64 doneint:1;
+		u64 reserved_17_63:47;
+#endif /* Word 0 - End */
+		u64 res_addr;
+#if defined(__BIG_ENDIAN_BITFIELD) /* Word 2 - Big Endian */
+		u64 reserved_172_19:20;
+		u64 grp:10;
+		u64 tt:2;
+		u64 tag:32;
+#else /* Word 2 - Little Endian */
+		u64 tag:32;
+		u64 tt:2;
+		u64 grp:10;
+		u64 reserved_172_191:20;
+#endif /* Word 2 - End */
+		u64 wq_ptr;
+		u64 ei0;
+		u64 ei1;
+		u64 ei2;
+		u64 ei3;
+	} s;
+};
+
+/**
+ * Structure 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 cpt_res_s {
+	u64 u[2];
+	struct cpt_res_s_s {
+#if defined(__BIG_ENDIAN_BITFIELD) /* Word 0 - Big Endian */
+		u64 reserved_17_63:47;
+		u64 doneint:1;
+		u64 reserved_8_15:8;
+		u64 compcode:8;
+#else /* Word 0 - Little Endian */
+		u64 compcode:8;
+		u64 reserved_8_15:8;
+		u64 doneint:1;
+		u64 reserved_17_63:47;
+#endif /* Word 0 - End */
+		u64 reserved_64_127;
+	} s;
+};
+
+/**
+ * Register (NCB) cpt#_pf_bist_status
+ *
+ * CPT PF Control Bist Status Register
+ * This register has the BIST status of memories. Each bit is the BIST result
+ * of an individual memory (per bit, 0 = pass and 1 = fail).
+ * cptx_pf_bist_status_s
+ * Word0
+ *  bstatus [29:0](RO/H) BIST status. One bit per memory, enumerated by
+ *	CPT_RAMS_E.
+ */
+union cptx_pf_bist_status {
+	u64 u;
+	struct cptx_pf_bist_status_s {
+#if defined(__BIG_ENDIAN_BITFIELD) /* Word 0 - Big Endian */
+		u64 reserved_30_63:34;
+		u64 bstatus:30;
+#else /* Word 0 - Little Endian */
+		u64 bstatus:30;
+		u64 reserved_30_63:34;
+#endif /* Word 0 - End */
+	} s;
+};
+
+/**
+ * Register (NCB) cpt#_pf_constants
+ *
+ * CPT PF Constants Register
+ * This register contains implementation-related parameters of CPT in CNXXXX.
+ * cptx_pf_constants_s
+ * Word 0
+ *  reserved_40_63:24 [63:40] Reserved.
+ *  epcis:8 [39:32](RO) Number of EPCI busses.
+ *  grps:8 [31:24](RO) Number of engine groups implemented.
+ *  ae:8 [23:16](RO/H) Number of AEs. In CNXXXX, for CPT0 returns 0x0,
+ *	for CPT1 returns 0x18, or less if there are fuse-disables.
+ *  se:8 [15:8](RO/H) Number of SEs. In CNXXXX, for CPT0 returns 0x30,
+ *	or less if there are fuse-disables, for CPT1 returns 0x0.
+ *  vq:8 [7:0](RO) Number of VQs.
+ */
+union cptx_pf_constants {
+	u64 u;
+	struct cptx_pf_constants_s {
+#if defined(__BIG_ENDIAN_BITFIELD) /* Word 0 - Big Endian */
+		u64 reserved_40_63:24;
+		u64 epcis:8;
+		u64 grps:8;
+		u64 ae:8;
+		u64 se:8;
+		u64 vq:8;
+#else /* Word 0 - Little Endian */
+		u64 vq:8;
+		u64 se:8;
+		u64 ae:8;
+		u64 grps:8;
+		u64 epcis:8;
+		u64 reserved_40_63:24;
+#endif /* Word 0 - End */
+	} s;
+};
+
+/**
+ * Register (NCB) cpt#_pf_exe_bist_status
+ *
+ * CPT PF Engine Bist Status Register
+ * This register has the BIST status of each engine.  Each bit is the
+ * BIST result of an individual engine (per bit, 0 = pass and 1 = fail).
+ * cptx_pf_exe_bist_status_s
+ * Word0
+ *  reserved_48_63:16 [63:48] reserved
+ *  bstatus:48 [47:0](RO/H) BIST status. One bit per engine.
+ *
+ */
+union cptx_pf_exe_bist_status {
+	u64 u;
+	struct cptx_pf_exe_bist_status_s {
+#if defined(__BIG_ENDIAN_BITFIELD) /* Word 0 - Big Endian */
+		u64 reserved_48_63:16;
+		u64 bstatus:48;
+#else /* Word 0 - Little Endian */
+		u64 bstatus:48;
+		u64 reserved_48_63:16;
+#endif /* Word 0 - End */
+	} s;
+};
+
+/**
+ * Register (NCB) cpt#_pf_q#_ctl
+ *
+ * CPT Queue Control Register
+ * This register configures queues. This register should be changed only
+ * when quiescent (see CPT()_VQ()_INPROG[INFLIGHT]).
+ * cptx_pf_qx_ctl_s
+ * Word0
+ *  reserved_60_63:4 [63:60] reserved.
+ *  aura:12; [59:48](R/W) Guest-aura for returning this queue's
+ *	instruction-chunk buffers to FPA. Only used when [INST_FREE] is set.
+ *	For the FPA to not discard the request, FPA_PF_MAP() must map
+ *	[AURA] and CPT()_PF_Q()_GMCTL[GMID] as valid.
+ *  reserved_45_47:3 [47:45] reserved.
+ *  size:13 [44:32](R/W) Command-buffer size, in number of 64-bit words per
+ *	command buffer segment. Must be 8*n + 1, where n is the number of
+ *	instructions per buffer segment.
+ *  reserved_11_31:21 [31:11] Reserved.
+ *  cont_err:1 [10:10](R/W) Continue on error.
+ *	0 = When CPT()_VQ()_MISC_INT[NWRP], CPT()_VQ()_MISC_INT[IRDE] or
+ *	CPT()_VQ()_MISC_INT[DOVF] are set by hardware or software via
+ *	CPT()_VQ()_MISC_INT_W1S, then CPT()_VQ()_CTL[ENA] is cleared.  Due to
+ *	pipelining, additional instructions may have been processed between the
+ *	instruction causing the error and the next instruction in the disabled
+ *	queue (the instruction at CPT()_VQ()_SADDR).
+ *	1 = Ignore errors and continue processing instructions.
+ *	For diagnostic use only.
+ *  inst_free:1 [9:9](R/W) Instruction FPA free. When set, when CPT reaches the
+ *	end of an instruction chunk, that chunk will be freed to the FPA.
+ *  inst_be:1 [8:8](R/W) Instruction big-endian control. When set, instructions,
+ *	instruction next chunk pointers, and result structures are stored in
+ *	big-endian format in memory.
+ *  iqb_ldwb:1 [7:7](R/W) Instruction load don't write back.
+ *	0 = The hardware issues NCB transient load (LDT) towards the cache,
+ *	which if the line hits and it is dirty will cause the line to be
+ *	written back before being replaced.
+ *	1 = The hardware issues NCB LDWB read-and-invalidate command towards
+ *	the cache when fetching the last word of instructions; as a result the
+ *	line will not be written back when replaced.  This improves
+ *	performance, but software must not read the instructions after they are
+ *	posted to the hardware.	Reads that do not consume the last word of a
+ *	cache line always use LDI.
+ *  reserved_4_6:3 [6:4] Reserved.
+ *  grp:3; [3:1](R/W) Engine group.
+ *  pri:1; [0:0](R/W) Queue priority.
+ *	1 = This queue has higher priority. Round-robin between higher
+ *	priority queues.
+ *	0 = This queue has lower priority. Round-robin between lower
+ *	priority queues.
+ */
+union cptx_pf_qx_ctl {
+	u64 u;
+	struct cptx_pf_qx_ctl_s {
+#if defined(__BIG_ENDIAN_BITFIELD) /* Word 0 - Big Endian */
+		u64 reserved_60_63:4;
+		u64 aura:12;
+		u64 reserved_45_47:3;
+		u64 size:13;
+		u64 reserved_11_31:21;
+		u64 cont_err:1;
+		u64 inst_free:1;
+		u64 inst_be:1;
+		u64 iqb_ldwb:1;
+		u64 reserved_4_6:3;
+		u64 grp:3;
+		u64 pri:1;
+#else /* Word 0 - Little Endian */
+		u64 pri:1;
+		u64 grp:3;
+		u64 reserved_4_6:3;
+		u64 iqb_ldwb:1;
+		u64 inst_be:1;
+		u64 inst_free:1;
+		u64 cont_err:1;
+		u64 reserved_11_31:21;
+		u64 size:13;
+		u64 reserved_45_47:3;
+		u64 aura:12;
+		u64 reserved_60_63:4;
+#endif /* Word 0 - End */
+	} s;
+};
+
+/**
+ * Register (NCB) cpt#_vq#_saddr
+ *
+ * CPT Queue Starting Buffer Address Registers
+ * These registers set the instruction buffer starting address.
+ * cptx_vqx_saddr_s
+ * Word0
+ *  reserved_49_63:15 [63:49] Reserved.
+ *  ptr:43 [48:6](R/W/H) Instruction buffer IOVA <48:6> (64-byte aligned).
+ *	When written, it is the initial buffer starting address; when read,
+ *	it is the next read pointer to be requested from L2C. The PTR field
+ *	is overwritten with the next pointer each time that the command buffer
+ *	segment is exhausted. New commands will then be read from the newly
+ *	specified command buffer pointer.
+ *  reserved_0_5:6 [5:0] Reserved.
+ *
+ */
+union cptx_vqx_saddr {
+	u64 u;
+	struct cptx_vqx_saddr_s {
+#if defined(__BIG_ENDIAN_BITFIELD) /* Word 0 - Big Endian */
+		u64 reserved_49_63:15;
+		u64 ptr:43;
+		u64 reserved_0_5:6;
+#else /* Word 0 - Little Endian */
+		u64 reserved_0_5:6;
+		u64 ptr:43;
+		u64 reserved_49_63:15;
+#endif /* Word 0 - End */
+	} s;
+};
+
+/**
+ * Register (NCB) cpt#_vq#_misc_ena_w1s
+ *
+ * CPT Queue Misc Interrupt Enable Set Register
+ * This register sets interrupt enable bits.
+ * cptx_vqx_misc_ena_w1s_s
+ * Word0
+ * reserved_5_63:59 [63:5] Reserved.
+ * swerr:1 [4:4](R/W1S/H) Reads or sets enable for
+ *	CPT(0..1)_VQ(0..63)_MISC_INT[SWERR].
+ * nwrp:1 [3:3](R/W1S/H) Reads or sets enable for
+ *	CPT(0..1)_VQ(0..63)_MISC_INT[NWRP].
+ * irde:1 [2:2](R/W1S/H) Reads or sets enable for
+ *	CPT(0..1)_VQ(0..63)_MISC_INT[IRDE].
+ * dovf:1 [1:1](R/W1S/H) Reads or sets enable for
+ *	CPT(0..1)_VQ(0..63)_MISC_INT[DOVF].
+ * mbox:1 [0:0](R/W1S/H) Reads or sets enable for
+ *	CPT(0..1)_VQ(0..63)_MISC_INT[MBOX].
+ *
+ */
+union cptx_vqx_misc_ena_w1s {
+	u64 u;
+	struct cptx_vqx_misc_ena_w1s_s {
+#if defined(__BIG_ENDIAN_BITFIELD) /* Word 0 - Big Endian */
+		u64 reserved_5_63:59;
+		u64 swerr:1;
+		u64 nwrp:1;
+		u64 irde:1;
+		u64 dovf:1;
+		u64 mbox:1;
+#else /* Word 0 - Little Endian */
+		u64 mbox:1;
+		u64 dovf:1;
+		u64 irde:1;
+		u64 nwrp:1;
+		u64 swerr:1;
+		u64 reserved_5_63:59;
+#endif /* Word 0 - End */
+	} s;
+};
+
+/**
+ * Register (NCB) cpt#_vq#_doorbell
+ *
+ * CPT Queue Doorbell Registers
+ * Doorbells for the CPT instruction queues.
+ * cptx_vqx_doorbell_s
+ * Word0
+ *  reserved_20_63:44 [63:20] Reserved.
+ *  dbell_cnt:20 [19:0](R/W/H) Number of instruction queue 64-bit words to add
+ *	to the CPT instruction doorbell count. Readback value is the
+ *	current number of pending doorbell requests. If counter overflows
+ *	CPT()_VQ()_MISC_INT[DBELL_DOVF] is set. To reset the count back to
+ *	zero, write one to clear CPT()_VQ()_MISC_INT_ENA_W1C[DBELL_DOVF],
+ *	then write a value of 2^20 minus the read [DBELL_CNT], then write one
+ *	to CPT()_VQ()_MISC_INT_W1C[DBELL_DOVF] and
+ *	CPT()_VQ()_MISC_INT_ENA_W1S[DBELL_DOVF]. Must be a multiple of 8.
+ *	All CPT instructions are 8 words and require a doorbell count of
+ *	multiple of 8.
+ */
+union cptx_vqx_doorbell {
+	u64 u;
+	struct cptx_vqx_doorbell_s {
+#if defined(__BIG_ENDIAN_BITFIELD) /* Word 0 - Big Endian */
+		u64 reserved_20_63:44;
+		u64 dbell_cnt:20;
+#else /* Word 0 - Little Endian */
+		u64 dbell_cnt:20;
+		u64 reserved_20_63:44;
+#endif /* Word 0 - End */
+	} s;
+};
+
+/**
+ * Register (NCB) cpt#_vq#_inprog
+ *
+ * CPT Queue In Progress Count Registers
+ * These registers contain the per-queue instruction in flight registers.
+ * cptx_vqx_inprog_s
+ * Word0
+ *  reserved_8_63:56 [63:8] Reserved.
+ *  inflight:8 [7:0](RO/H) Inflight count. Counts the number of instructions
+ *	for the VF for which CPT is fetching, executing or responding to
+ *	instructions. However this does not include any interrupts that are
+ *	awaiting software handling (CPT()_VQ()_DONE[DONE] != 0x0).
+ *	A queue may not be reconfigured until:
+ *	1. CPT()_VQ()_CTL[ENA] is cleared by software.
+ *	2. [INFLIGHT] is polled until equals to zero.
+ */
+union cptx_vqx_inprog {
+	u64 u;
+	struct cptx_vqx_inprog_s {
+#if defined(__BIG_ENDIAN_BITFIELD) /* Word 0 - Big Endian */
+		u64 reserved_8_63:56;
+		u64 inflight:8;
+#else /* Word 0 - Little Endian */
+		u64 inflight:8;
+		u64 reserved_8_63:56;
+#endif /* Word 0 - End */
+	} s;
+};
+
+/**
+ * Register (NCB) cpt#_vq#_misc_int
+ *
+ * CPT Queue Misc Interrupt Register
+ * These registers contain the per-queue miscellaneous interrupts.
+ * cptx_vqx_misc_int_s
+ * Word 0
+ *  reserved_5_63:59 [63:5] Reserved.
+ *  swerr:1 [4:4](R/W1C/H) Software error from engines.
+ *  nwrp:1  [3:3](R/W1C/H) NCB result write response error.
+ *  irde:1  [2:2](R/W1C/H) Instruction NCB read response error.
+ *  dovf:1 [1:1](R/W1C/H) Doorbell overflow.
+ *  mbox:1 [0:0](R/W1C/H) PF to VF mailbox interrupt. Set when
+ *	CPT()_VF()_PF_MBOX(0) is written.
+ *
+ */
+union cptx_vqx_misc_int {
+	u64 u;
+	struct cptx_vqx_misc_int_s {
+#if defined(__BIG_ENDIAN_BITFIELD) /* Word 0 - Big Endian */
+		u64 reserved_5_63:59;
+		u64 swerr:1;
+		u64 nwrp:1;
+		u64 irde:1;
+		u64 dovf:1;
+		u64 mbox:1;
+#else /* Word 0 - Little Endian */
+		u64 mbox:1;
+		u64 dovf:1;
+		u64 irde:1;
+		u64 nwrp:1;
+		u64 swerr:1;
+		u64 reserved_5_63:59;
+#endif /* Word 0 - End */
+	} s;
+};
+
+/**
+ * Register (NCB) cpt#_vq#_done_ack
+ *
+ * CPT Queue Done Count Ack Registers
+ * This register is written by software to acknowledge interrupts.
+ * cptx_vqx_done_ack_s
+ * Word0
+ *  reserved_20_63:44 [63:20] Reserved.
+ *  done_ack:20 [19:0](R/W/H) Number of decrements to CPT()_VQ()_DONE[DONE].
+ *	Reads CPT()_VQ()_DONE[DONE]. Written by software to acknowledge
+ *	interrupts. If CPT()_VQ()_DONE[DONE] is still nonzero the interrupt
+ *	will be re-sent if the conditions described in CPT()_VQ()_DONE[DONE]
+ *	are satisfied.
+ *
+ */
+union cptx_vqx_done_ack {
+	u64 u;
+	struct cptx_vqx_done_ack_s {
+#if defined(__BIG_ENDIAN_BITFIELD) /* Word 0 - Big Endian */
+		u64 reserved_20_63:44;
+		u64 done_ack:20;
+#else /* Word 0 - Little Endian */
+		u64 done_ack:20;
+		u64 reserved_20_63:44;
+#endif /* Word 0 - End */
+	} s;
+};
+
+/**
+ * Register (NCB) cpt#_vq#_done
+ *
+ * CPT Queue Done Count Registers
+ * These registers contain the per-queue instruction done count.
+ * cptx_vqx_done_s
+ * Word0
+ *  reserved_20_63:44 [63:20] Reserved.
+ *  done:20 [19:0](R/W/H) Done count. When CPT_INST_S[DONEINT] set and that
+ *	instruction completes, CPT()_VQ()_DONE[DONE] is incremented when the
+ *	instruction finishes. Write to this field are for diagnostic use only;
+ *	instead software writes CPT()_VQ()_DONE_ACK with the number of
+ *	decrements for this field.
+ *	Interrupts are sent as follows:
+ *	* When CPT()_VQ()_DONE[DONE] = 0, then no results are pending, the
+ *	interrupt coalescing timer is held to zero, and an interrupt is not
+ *	sent.
+ *	* When CPT()_VQ()_DONE[DONE] != 0, then the interrupt coalescing timer
+ *	counts. If the counter is >= CPT()_VQ()_DONE_WAIT[TIME_WAIT]*1024, or
+ *	CPT()_VQ()_DONE[DONE] >= CPT()_VQ()_DONE_WAIT[NUM_WAIT], i.e. enough
+ *	time has passed or enough results have arrived, then the interrupt is
+ *	sent.
+ *	* When CPT()_VQ()_DONE_ACK is written (or CPT()_VQ()_DONE is written
+ *	but this is not typical), the interrupt coalescing timer restarts.
+ *	Note after decrementing this interrupt equation is recomputed,
+ *	for example if CPT()_VQ()_DONE[DONE] >= CPT()_VQ()_DONE_WAIT[NUM_WAIT]
+ *	and because the timer is zero, the interrupt will be resent immediately.
+ *	(This covers the race case between software acknowledging an interrupt
+ *	and a result returning.)
+ *	* When CPT()_VQ()_DONE_ENA_W1S[DONE] = 0, interrupts are not sent,
+ *	but the counting described above still occurs.
+ *	Since CPT instructions complete out-of-order, if software is using
+ *	completion interrupts the suggested scheme is to request a DONEINT on
+ *	each request, and when an interrupt arrives perform a "greedy" scan for
+ *	completions; even if a later command is acknowledged first this will
+ *	not result in missing a completion.
+ *	Software is responsible for making sure [DONE] does not overflow;
+ *	for example by insuring there are not more than 2^20-1 instructions in
+ *	flight that may request interrupts.
+ *
+ */
+union cptx_vqx_done {
+	u64 u;
+	struct cptx_vqx_done_s {
+#if defined(__BIG_ENDIAN_BITFIELD) /* Word 0 - Big Endian */
+		u64 reserved_20_63:44;
+		u64 done:20;
+#else /* Word 0 - Little Endian */
+		u64 done:20;
+		u64 reserved_20_63:44;
+#endif /* Word 0 - End */
+	} s;
+};
+
+/**
+ * Register (NCB) cpt#_vq#_done_wait
+ *
+ * CPT Queue Done Interrupt Coalescing Wait Registers
+ * Specifies the per queue interrupt coalescing settings.
+ * cptx_vqx_done_wait_s
+ * Word0
+ *  reserved_48_63:16 [63:48] Reserved.
+ *  time_wait:16; [47:32](R/W) Time hold-off. When CPT()_VQ()_DONE[DONE] = 0
+ *	or CPT()_VQ()_DONE_ACK is written a timer is cleared. When the timer
+ *	reaches [TIME_WAIT]*1024 then interrupt coalescing ends.
+ *	see CPT()_VQ()_DONE[DONE]. If 0x0, time coalescing is disabled.
+ *  reserved_20_31:12 [31:20] Reserved.
+ *  num_wait:20 [19:0](R/W) Number of messages hold-off.
+ *	When CPT()_VQ()_DONE[DONE] >= [NUM_WAIT] then interrupt coalescing ends
+ *	see CPT()_VQ()_DONE[DONE]. If 0x0, same behavior as 0x1.
+ *
+ */
+union cptx_vqx_done_wait {
+	u64 u;
+	struct cptx_vqx_done_wait_s {
+#if defined(__BIG_ENDIAN_BITFIELD) /* Word 0 - Big Endian */
+		u64 reserved_48_63:16;
+		u64 time_wait:16;
+		u64 reserved_20_31:12;
+		u64 num_wait:20;
+#else /* Word 0 - Little Endian */
+		u64 num_wait:20;
+		u64 reserved_20_31:12;
+		u64 time_wait:16;
+		u64 reserved_48_63:16;
+#endif /* Word 0 - End */
+	} s;
+};
+
+/**
+ * Register (NCB) cpt#_vq#_done_ena_w1s
+ *
+ * CPT Queue Done Interrupt Enable Set Registers
+ * Write 1 to these registers will enable the DONEINT interrupt for the queue.
+ * cptx_vqx_done_ena_w1s_s
+ * Word0
+ *  reserved_1_63:63 [63:1] Reserved.
+ *  done:1 [0:0](R/W1S/H) Write 1 will enable DONEINT for this queue.
+ *	Write 0 has no effect. Read will return the enable bit.
+ */
+union cptx_vqx_done_ena_w1s {
+	u64 u;
+	struct cptx_vqx_done_ena_w1s_s {
+#if defined(__BIG_ENDIAN_BITFIELD) /* Word 0 - Big Endian */
+		u64 reserved_1_63:63;
+		u64 done:1;
+#else /* Word 0 - Little Endian */
+		u64 done:1;
+		u64 reserved_1_63:63;
+#endif /* Word 0 - End */
+	} s;
+};
+
+/**
+ * Register (NCB) cpt#_vq#_ctl
+ *
+ * CPT VF Queue Control Registers
+ * This register configures queues. This register should be changed (other than
+ * clearing [ENA]) only when quiescent (see CPT()_VQ()_INPROG[INFLIGHT]).
+ * cptx_vqx_ctl_s
+ * Word0
+ *  reserved_1_63:63 [63:1] Reserved.
+ *  ena:1 [0:0](R/W/H) Enables the logical instruction queue.
+ *	See also CPT()_PF_Q()_CTL[CONT_ERR] and	CPT()_VQ()_INPROG[INFLIGHT].
+ *	1 = Queue is enabled.
+ *	0 = Queue is disabled.
+ */
+union cptx_vqx_ctl {
+	u64 u;
+	struct cptx_vqx_ctl_s {
+#if defined(__BIG_ENDIAN_BITFIELD) /* Word 0 - Big Endian */
+		u64 reserved_1_63:63;
+		u64 ena:1;
+#else /* Word 0 - Little Endian */
+		u64 ena:1;
+		u64 reserved_1_63:63;
+#endif /* Word 0 - End */
+	} s;
+};
+#endif /*__CPT_HW_TYPES_H*/
diff --git a/drivers/crypto/cavium/cpt/cptpf.h b/drivers/crypto/cavium/cpt/cptpf.h
new file mode 100644
index 000000000..c88e177a3
--- /dev/null
+++ b/drivers/crypto/cavium/cpt/cptpf.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2016 Cavium, Inc.
+ */
+
+#ifndef __CPTPF_H
+#define __CPTPF_H
+
+#include "cpt_common.h"
+
+#define CSR_DELAY 30
+#define CPT_MAX_CORE_GROUPS 8
+#define CPT_MAX_SE_CORES 10
+#define CPT_MAX_AE_CORES 6
+#define CPT_MAX_TOTAL_CORES (CPT_MAX_SE_CORES + CPT_MAX_AE_CORES)
+#define CPT_MAX_VF_NUM 16
+#define	CPT_PF_MSIX_VECTORS 3
+#define CPT_PF_INT_VEC_E_MBOXX(a) (0x02 + (a))
+#define CPT_UCODE_VERSION_SZ 32
+struct cpt_device;
+
+struct microcode {
+	u8 is_mc_valid;
+	u8 is_ae;
+	u8 group;
+	u8 num_cores;
+	u32 code_size;
+	u64 core_mask;
+	u8 version[CPT_UCODE_VERSION_SZ];
+	/* Base info */
+	dma_addr_t phys_base;
+	void *code;
+};
+
+struct cpt_vf_info {
+	u8 state;
+	u8 priority;
+	u8 id;
+	u32 qlen;
+};
+
+/**
+ * cpt device structure
+ */
+struct cpt_device {
+	u16 flags;	/* Flags to hold device status bits */
+	u8 num_vf_en; /* Number of VFs enabled (0...CPT_MAX_VF_NUM) */
+	struct cpt_vf_info vfinfo[CPT_MAX_VF_NUM]; /* Per VF info */
+
+	void __iomem *reg_base; /* Register start address */
+	struct pci_dev *pdev; /* pci device handle */
+
+	struct microcode mcode[CPT_MAX_CORE_GROUPS];
+	u8 next_mc_idx; /* next microcode index */
+	u8 next_group;
+	u8 max_se_cores;
+	u8 max_ae_cores;
+};
+
+void cpt_mbox_intr_handler(struct cpt_device *cpt, int mbx);
+#endif /* __CPTPF_H */
diff --git a/drivers/crypto/cavium/cpt/cptpf_main.c b/drivers/crypto/cavium/cpt/cptpf_main.c
new file mode 100644
index 000000000..9358c1c04
--- /dev/null
+++ b/drivers/crypto/cavium/cpt/cptpf_main.c
@@ -0,0 +1,669 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2016 Cavium, Inc.
+ */
+
+#include <linux/device.h>
+#include <linux/firmware.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/pci.h>
+#include <linux/printk.h>
+
+#include "cptpf.h"
+
+#define DRV_NAME	"thunder-cpt"
+#define DRV_VERSION	"1.0"
+
+static u32 num_vfs = 4; /* Default 4 VF enabled */
+module_param(num_vfs, uint, 0444);
+MODULE_PARM_DESC(num_vfs, "Number of VFs to enable(1-16)");
+
+/*
+ * Disable cores specified by coremask
+ */
+static void cpt_disable_cores(struct cpt_device *cpt, u64 coremask,
+			      u8 type, u8 grp)
+{
+	u64 pf_exe_ctl;
+	u32 timeout = 100;
+	u64 grpmask = 0;
+	struct device *dev = &cpt->pdev->dev;
+
+	if (type == AE_TYPES)
+		coremask = (coremask << cpt->max_se_cores);
+
+	/* Disengage the cores from groups */
+	grpmask = cpt_read_csr64(cpt->reg_base, CPTX_PF_GX_EN(0, grp));
+	cpt_write_csr64(cpt->reg_base, CPTX_PF_GX_EN(0, grp),
+			(grpmask & ~coremask));
+	udelay(CSR_DELAY);
+	grp = cpt_read_csr64(cpt->reg_base, CPTX_PF_EXEC_BUSY(0));
+	while (grp & coremask) {
+		dev_err(dev, "Cores still busy %llx", coremask);
+		grp = cpt_read_csr64(cpt->reg_base,
+				     CPTX_PF_EXEC_BUSY(0));
+		if (!timeout--)
+			break;
+
+		udelay(CSR_DELAY);
+	}
+
+	/* Disable the cores */
+	pf_exe_ctl = cpt_read_csr64(cpt->reg_base, CPTX_PF_EXE_CTL(0));
+	cpt_write_csr64(cpt->reg_base, CPTX_PF_EXE_CTL(0),
+			(pf_exe_ctl & ~coremask));
+	udelay(CSR_DELAY);
+}
+
+/*
+ * Enable cores specified by coremask
+ */
+static void cpt_enable_cores(struct cpt_device *cpt, u64 coremask,
+			     u8 type)
+{
+	u64 pf_exe_ctl;
+
+	if (type == AE_TYPES)
+		coremask = (coremask << cpt->max_se_cores);
+
+	pf_exe_ctl = cpt_read_csr64(cpt->reg_base, CPTX_PF_EXE_CTL(0));
+	cpt_write_csr64(cpt->reg_base, CPTX_PF_EXE_CTL(0),
+			(pf_exe_ctl | coremask));
+	udelay(CSR_DELAY);
+}
+
+static void cpt_configure_group(struct cpt_device *cpt, u8 grp,
+				u64 coremask, u8 type)
+{
+	u64 pf_gx_en = 0;
+
+	if (type == AE_TYPES)
+		coremask = (coremask << cpt->max_se_cores);
+
+	pf_gx_en = cpt_read_csr64(cpt->reg_base, CPTX_PF_GX_EN(0, grp));
+	cpt_write_csr64(cpt->reg_base, CPTX_PF_GX_EN(0, grp),
+			(pf_gx_en | coremask));
+	udelay(CSR_DELAY);
+}
+
+static void cpt_disable_mbox_interrupts(struct cpt_device *cpt)
+{
+	/* Clear mbox(0) interupts for all vfs */
+	cpt_write_csr64(cpt->reg_base, CPTX_PF_MBOX_ENA_W1CX(0, 0), ~0ull);
+}
+
+static void cpt_disable_ecc_interrupts(struct cpt_device *cpt)
+{
+	/* Clear ecc(0) interupts for all vfs */
+	cpt_write_csr64(cpt->reg_base, CPTX_PF_ECC0_ENA_W1C(0), ~0ull);
+}
+
+static void cpt_disable_exec_interrupts(struct cpt_device *cpt)
+{
+	/* Clear exec interupts for all vfs */
+	cpt_write_csr64(cpt->reg_base, CPTX_PF_EXEC_ENA_W1C(0), ~0ull);
+}
+
+static void cpt_disable_all_interrupts(struct cpt_device *cpt)
+{
+	cpt_disable_mbox_interrupts(cpt);
+	cpt_disable_ecc_interrupts(cpt);
+	cpt_disable_exec_interrupts(cpt);
+}
+
+static void cpt_enable_mbox_interrupts(struct cpt_device *cpt)
+{
+	/* Set mbox(0) interupts for all vfs */
+	cpt_write_csr64(cpt->reg_base, CPTX_PF_MBOX_ENA_W1SX(0, 0), ~0ull);
+}
+
+static int cpt_load_microcode(struct cpt_device *cpt, struct microcode *mcode)
+{
+	int ret = 0, core = 0, shift = 0;
+	u32 total_cores = 0;
+	struct device *dev = &cpt->pdev->dev;
+
+	if (!mcode || !mcode->code) {
+		dev_err(dev, "Either the mcode is null or data is NULL\n");
+		return -EINVAL;
+	}
+
+	if (mcode->code_size == 0) {
+		dev_err(dev, "microcode size is 0\n");
+		return -EINVAL;
+	}
+
+	/* Assumes 0-9 are SE cores for UCODE_BASE registers and
+	 * AE core bases follow
+	 */
+	if (mcode->is_ae) {
+		core = CPT_MAX_SE_CORES; /* start couting from 10 */
+		total_cores = CPT_MAX_TOTAL_CORES; /* upto 15 */
+	} else {
+		core = 0; /* start couting from 0 */
+		total_cores = CPT_MAX_SE_CORES; /* upto 9 */
+	}
+
+	/* Point to microcode for each core of the group */
+	for (; core < total_cores ; core++, shift++) {
+		if (mcode->core_mask & (1 << shift)) {
+			cpt_write_csr64(cpt->reg_base,
+					CPTX_PF_ENGX_UCODE_BASE(0, core),
+					(u64)mcode->phys_base);
+		}
+	}
+	return ret;
+}
+
+static int do_cpt_init(struct cpt_device *cpt, struct microcode *mcode)
+{
+	int ret = 0;
+	struct device *dev = &cpt->pdev->dev;
+
+	/* Make device not ready */
+	cpt->flags &= ~CPT_FLAG_DEVICE_READY;
+	/* Disable All PF interrupts */
+	cpt_disable_all_interrupts(cpt);
+	/* Calculate mcode group and coremasks */
+	if (mcode->is_ae) {
+		if (mcode->num_cores > cpt->max_ae_cores) {
+			dev_err(dev, "Requested for more cores than available AE cores\n");
+			ret = -EINVAL;
+			goto cpt_init_fail;
+		}
+
+		if (cpt->next_group >= CPT_MAX_CORE_GROUPS) {
+			dev_err(dev, "Can't load, all eight microcode groups in use");
+			return -ENFILE;
+		}
+
+		mcode->group = cpt->next_group;
+		/* Convert requested cores to mask */
+		mcode->core_mask = GENMASK(mcode->num_cores, 0);
+		cpt_disable_cores(cpt, mcode->core_mask, AE_TYPES,
+				  mcode->group);
+		/* Load microcode for AE engines */
+		ret = cpt_load_microcode(cpt, mcode);
+		if (ret) {
+			dev_err(dev, "Microcode load Failed for %s\n",
+				mcode->version);
+			goto cpt_init_fail;
+		}
+		cpt->next_group++;
+		/* Configure group mask for the mcode */
+		cpt_configure_group(cpt, mcode->group, mcode->core_mask,
+				    AE_TYPES);
+		/* Enable AE cores for the group mask */
+		cpt_enable_cores(cpt, mcode->core_mask, AE_TYPES);
+	} else {
+		if (mcode->num_cores > cpt->max_se_cores) {
+			dev_err(dev, "Requested for more cores than available SE cores\n");
+			ret = -EINVAL;
+			goto cpt_init_fail;
+		}
+		if (cpt->next_group >= CPT_MAX_CORE_GROUPS) {
+			dev_err(dev, "Can't load, all eight microcode groups in use");
+			return -ENFILE;
+		}
+
+		mcode->group = cpt->next_group;
+		/* Covert requested cores to mask */
+		mcode->core_mask = GENMASK(mcode->num_cores, 0);
+		cpt_disable_cores(cpt, mcode->core_mask, SE_TYPES,
+				  mcode->group);
+		/* Load microcode for SE engines */
+		ret = cpt_load_microcode(cpt, mcode);
+		if (ret) {
+			dev_err(dev, "Microcode load Failed for %s\n",
+				mcode->version);
+			goto cpt_init_fail;
+		}
+		cpt->next_group++;
+		/* Configure group mask for the mcode */
+		cpt_configure_group(cpt, mcode->group, mcode->core_mask,
+				    SE_TYPES);
+		/* Enable SE cores for the group mask */
+		cpt_enable_cores(cpt, mcode->core_mask, SE_TYPES);
+	}
+
+	/* Enabled PF mailbox interrupts */
+	cpt_enable_mbox_interrupts(cpt);
+	cpt->flags |= CPT_FLAG_DEVICE_READY;
+
+	return ret;
+
+cpt_init_fail:
+	/* Enabled PF mailbox interrupts */
+	cpt_enable_mbox_interrupts(cpt);
+
+	return ret;
+}
+
+struct ucode_header {
+	u8 version[CPT_UCODE_VERSION_SZ];
+	__be32 code_length;
+	u32 data_length;
+	u64 sram_address;
+};
+
+static int cpt_ucode_load_fw(struct cpt_device *cpt, const u8 *fw, bool is_ae)
+{
+	const struct firmware *fw_entry;
+	struct device *dev = &cpt->pdev->dev;
+	struct ucode_header *ucode;
+	unsigned int code_length;
+	struct microcode *mcode;
+	int j, ret = 0;
+
+	ret = request_firmware(&fw_entry, fw, dev);
+	if (ret)
+		return ret;
+
+	ucode = (struct ucode_header *)fw_entry->data;
+	mcode = &cpt->mcode[cpt->next_mc_idx];
+	memcpy(mcode->version, (u8 *)fw_entry->data, CPT_UCODE_VERSION_SZ);
+	code_length = ntohl(ucode->code_length);
+	if (code_length == 0 || code_length >= INT_MAX / 2) {
+		ret = -EINVAL;
+		goto fw_release;
+	}
+	mcode->code_size = code_length * 2;
+
+	mcode->is_ae = is_ae;
+	mcode->core_mask = 0ULL;
+	mcode->num_cores = is_ae ? 6 : 10;
+
+	/*  Allocate DMAable space */
+	mcode->code = dma_alloc_coherent(&cpt->pdev->dev, mcode->code_size,
+					 &mcode->phys_base, GFP_KERNEL);
+	if (!mcode->code) {
+		dev_err(dev, "Unable to allocate space for microcode");
+		ret = -ENOMEM;
+		goto fw_release;
+	}
+
+	memcpy((void *)mcode->code, (void *)(fw_entry->data + sizeof(*ucode)),
+	       mcode->code_size);
+
+	/* Byte swap 64-bit */
+	for (j = 0; j < (mcode->code_size / 8); j++)
+		((__be64 *)mcode->code)[j] = cpu_to_be64(((u64 *)mcode->code)[j]);
+	/*  MC needs 16-bit swap */
+	for (j = 0; j < (mcode->code_size / 2); j++)
+		((__be16 *)mcode->code)[j] = cpu_to_be16(((u16 *)mcode->code)[j]);
+
+	dev_dbg(dev, "mcode->code_size = %u\n", mcode->code_size);
+	dev_dbg(dev, "mcode->is_ae = %u\n", mcode->is_ae);
+	dev_dbg(dev, "mcode->num_cores = %u\n", mcode->num_cores);
+	dev_dbg(dev, "mcode->code = %llx\n", (u64)mcode->code);
+	dev_dbg(dev, "mcode->phys_base = %llx\n", mcode->phys_base);
+
+	ret = do_cpt_init(cpt, mcode);
+	if (ret) {
+		dma_free_coherent(&cpt->pdev->dev, mcode->code_size,
+				  mcode->code, mcode->phys_base);
+		dev_err(dev, "do_cpt_init failed with ret: %d\n", ret);
+		goto fw_release;
+	}
+
+	dev_info(dev, "Microcode Loaded %s\n", mcode->version);
+	mcode->is_mc_valid = 1;
+	cpt->next_mc_idx++;
+
+fw_release:
+	release_firmware(fw_entry);
+
+	return ret;
+}
+
+static int cpt_ucode_load(struct cpt_device *cpt)
+{
+	int ret = 0;
+	struct device *dev = &cpt->pdev->dev;
+
+	ret = cpt_ucode_load_fw(cpt, "cpt8x-mc-ae.out", true);
+	if (ret) {
+		dev_err(dev, "ae:cpt_ucode_load failed with ret: %d\n", ret);
+		return ret;
+	}
+	ret = cpt_ucode_load_fw(cpt, "cpt8x-mc-se.out", false);
+	if (ret) {
+		dev_err(dev, "se:cpt_ucode_load failed with ret: %d\n", ret);
+		return ret;
+	}
+
+	return ret;
+}
+
+static irqreturn_t cpt_mbx0_intr_handler(int irq, void *cpt_irq)
+{
+	struct cpt_device *cpt = (struct cpt_device *)cpt_irq;
+
+	cpt_mbox_intr_handler(cpt, 0);
+
+	return IRQ_HANDLED;
+}
+
+static void cpt_reset(struct cpt_device *cpt)
+{
+	cpt_write_csr64(cpt->reg_base, CPTX_PF_RESET(0), 1);
+}
+
+static void cpt_find_max_enabled_cores(struct cpt_device *cpt)
+{
+	union cptx_pf_constants pf_cnsts = {0};
+
+	pf_cnsts.u = cpt_read_csr64(cpt->reg_base, CPTX_PF_CONSTANTS(0));
+	cpt->max_se_cores = pf_cnsts.s.se;
+	cpt->max_ae_cores = pf_cnsts.s.ae;
+}
+
+static u32 cpt_check_bist_status(struct cpt_device *cpt)
+{
+	union cptx_pf_bist_status bist_sts = {0};
+
+	bist_sts.u = cpt_read_csr64(cpt->reg_base,
+				    CPTX_PF_BIST_STATUS(0));
+
+	return bist_sts.u;
+}
+
+static u64 cpt_check_exe_bist_status(struct cpt_device *cpt)
+{
+	union cptx_pf_exe_bist_status bist_sts = {0};
+
+	bist_sts.u = cpt_read_csr64(cpt->reg_base,
+				    CPTX_PF_EXE_BIST_STATUS(0));
+
+	return bist_sts.u;
+}
+
+static void cpt_disable_all_cores(struct cpt_device *cpt)
+{
+	u32 grp, timeout = 100;
+	struct device *dev = &cpt->pdev->dev;
+
+	/* Disengage the cores from groups */
+	for (grp = 0; grp < CPT_MAX_CORE_GROUPS; grp++) {
+		cpt_write_csr64(cpt->reg_base, CPTX_PF_GX_EN(0, grp), 0);
+		udelay(CSR_DELAY);
+	}
+
+	grp = cpt_read_csr64(cpt->reg_base, CPTX_PF_EXEC_BUSY(0));
+	while (grp) {
+		dev_err(dev, "Cores still busy");
+		grp = cpt_read_csr64(cpt->reg_base,
+				     CPTX_PF_EXEC_BUSY(0));
+		if (!timeout--)
+			break;
+
+		udelay(CSR_DELAY);
+	}
+	/* Disable the cores */
+	cpt_write_csr64(cpt->reg_base, CPTX_PF_EXE_CTL(0), 0);
+}
+
+/*
+ * Ensure all cores are disengaged from all groups by
+ * calling cpt_disable_all_cores() before calling this
+ * function.
+ */
+static void cpt_unload_microcode(struct cpt_device *cpt)
+{
+	u32 grp = 0, core;
+
+	/* Free microcode bases and reset group masks */
+	for (grp = 0; grp < CPT_MAX_CORE_GROUPS; grp++) {
+		struct microcode *mcode = &cpt->mcode[grp];
+
+		if (cpt->mcode[grp].code)
+			dma_free_coherent(&cpt->pdev->dev, mcode->code_size,
+					  mcode->code, mcode->phys_base);
+		mcode->code = NULL;
+	}
+	/* Clear UCODE_BASE registers for all engines */
+	for (core = 0; core < CPT_MAX_TOTAL_CORES; core++)
+		cpt_write_csr64(cpt->reg_base,
+				CPTX_PF_ENGX_UCODE_BASE(0, core), 0ull);
+}
+
+static int cpt_device_init(struct cpt_device *cpt)
+{
+	u64 bist;
+	struct device *dev = &cpt->pdev->dev;
+
+	/* Reset the PF when probed first */
+	cpt_reset(cpt);
+	msleep(100);
+
+	/*Check BIST status*/
+	bist = (u64)cpt_check_bist_status(cpt);
+	if (bist) {
+		dev_err(dev, "RAM BIST failed with code 0x%llx", bist);
+		return -ENODEV;
+	}
+
+	bist = cpt_check_exe_bist_status(cpt);
+	if (bist) {
+		dev_err(dev, "Engine BIST failed with code 0x%llx", bist);
+		return -ENODEV;
+	}
+
+	/*Get CLK frequency*/
+	/*Get max enabled cores */
+	cpt_find_max_enabled_cores(cpt);
+	/*Disable all cores*/
+	cpt_disable_all_cores(cpt);
+	/*Reset device parameters*/
+	cpt->next_mc_idx   = 0;
+	cpt->next_group = 0;
+	/* PF is ready */
+	cpt->flags |= CPT_FLAG_DEVICE_READY;
+
+	return 0;
+}
+
+static int cpt_register_interrupts(struct cpt_device *cpt)
+{
+	int ret;
+	struct device *dev = &cpt->pdev->dev;
+
+	/* Enable MSI-X */
+	ret = pci_alloc_irq_vectors(cpt->pdev, CPT_PF_MSIX_VECTORS,
+			CPT_PF_MSIX_VECTORS, PCI_IRQ_MSIX);
+	if (ret < 0) {
+		dev_err(&cpt->pdev->dev, "Request for #%d msix vectors failed\n",
+			CPT_PF_MSIX_VECTORS);
+		return ret;
+	}
+
+	/* Register mailbox interrupt handlers */
+	ret = request_irq(pci_irq_vector(cpt->pdev, CPT_PF_INT_VEC_E_MBOXX(0)),
+			  cpt_mbx0_intr_handler, 0, "CPT Mbox0", cpt);
+	if (ret)
+		goto fail;
+
+	/* Enable mailbox interrupt */
+	cpt_enable_mbox_interrupts(cpt);
+	return 0;
+
+fail:
+	dev_err(dev, "Request irq failed\n");
+	pci_disable_msix(cpt->pdev);
+	return ret;
+}
+
+static void cpt_unregister_interrupts(struct cpt_device *cpt)
+{
+	free_irq(pci_irq_vector(cpt->pdev, CPT_PF_INT_VEC_E_MBOXX(0)), cpt);
+	pci_disable_msix(cpt->pdev);
+}
+
+static int cpt_sriov_init(struct cpt_device *cpt, int num_vfs)
+{
+	int pos = 0;
+	int err;
+	u16 total_vf_cnt;
+	struct pci_dev *pdev = cpt->pdev;
+
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV);
+	if (!pos) {
+		dev_err(&pdev->dev, "SRIOV capability is not found in PCIe config space\n");
+		return -ENODEV;
+	}
+
+	cpt->num_vf_en = num_vfs; /* User requested VFs */
+	pci_read_config_word(pdev, (pos + PCI_SRIOV_TOTAL_VF), &total_vf_cnt);
+	if (total_vf_cnt < cpt->num_vf_en)
+		cpt->num_vf_en = total_vf_cnt;
+
+	if (!total_vf_cnt)
+		return 0;
+
+	/*Enabled the available VFs */
+	err = pci_enable_sriov(pdev, cpt->num_vf_en);
+	if (err) {
+		dev_err(&pdev->dev, "SRIOV enable failed, num VF is %d\n",
+			cpt->num_vf_en);
+		cpt->num_vf_en = 0;
+		return err;
+	}
+
+	/* TODO: Optionally enable static VQ priorities feature */
+
+	dev_info(&pdev->dev, "SRIOV enabled, number of VF available %d\n",
+		 cpt->num_vf_en);
+
+	cpt->flags |= CPT_FLAG_SRIOV_ENABLED;
+
+	return 0;
+}
+
+static int cpt_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	struct device *dev = &pdev->dev;
+	struct cpt_device *cpt;
+	int err;
+
+	if (num_vfs > 16 || num_vfs < 4) {
+		dev_warn(dev, "Invalid vf count %d, Resetting it to 4(default)\n",
+			 num_vfs);
+		num_vfs = 4;
+	}
+
+	cpt = devm_kzalloc(dev, sizeof(*cpt), GFP_KERNEL);
+	if (!cpt)
+		return -ENOMEM;
+
+	pci_set_drvdata(pdev, cpt);
+	cpt->pdev = pdev;
+	err = pci_enable_device(pdev);
+	if (err) {
+		dev_err(dev, "Failed to enable PCI device\n");
+		pci_set_drvdata(pdev, NULL);
+		return err;
+	}
+
+	err = pci_request_regions(pdev, DRV_NAME);
+	if (err) {
+		dev_err(dev, "PCI request regions failed 0x%x\n", err);
+		goto cpt_err_disable_device;
+	}
+
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(48));
+	if (err) {
+		dev_err(dev, "Unable to get usable 48-bit DMA configuration\n");
+		goto cpt_err_release_regions;
+	}
+
+	/* MAP PF's configuration registers */
+	cpt->reg_base = pcim_iomap(pdev, 0, 0);
+	if (!cpt->reg_base) {
+		dev_err(dev, "Cannot map config register space, aborting\n");
+		err = -ENOMEM;
+		goto cpt_err_release_regions;
+	}
+
+	/* CPT device HW initialization */
+	cpt_device_init(cpt);
+
+	/* Register interrupts */
+	err = cpt_register_interrupts(cpt);
+	if (err)
+		goto cpt_err_release_regions;
+
+	err = cpt_ucode_load(cpt);
+	if (err)
+		goto cpt_err_unregister_interrupts;
+
+	/* Configure SRIOV */
+	err = cpt_sriov_init(cpt, num_vfs);
+	if (err)
+		goto cpt_err_unregister_interrupts;
+
+	return 0;
+
+cpt_err_unregister_interrupts:
+	cpt_unregister_interrupts(cpt);
+cpt_err_release_regions:
+	pci_release_regions(pdev);
+cpt_err_disable_device:
+	pci_disable_device(pdev);
+	pci_set_drvdata(pdev, NULL);
+	return err;
+}
+
+static void cpt_remove(struct pci_dev *pdev)
+{
+	struct cpt_device *cpt = pci_get_drvdata(pdev);
+
+	/* Disengage SE and AE cores from all groups*/
+	cpt_disable_all_cores(cpt);
+	/* Unload microcodes */
+	cpt_unload_microcode(cpt);
+	cpt_unregister_interrupts(cpt);
+	pci_disable_sriov(pdev);
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+	pci_set_drvdata(pdev, NULL);
+}
+
+static void cpt_shutdown(struct pci_dev *pdev)
+{
+	struct cpt_device *cpt = pci_get_drvdata(pdev);
+
+	if (!cpt)
+		return;
+
+	dev_info(&pdev->dev, "Shutdown device %x:%x.\n",
+		 (u32)pdev->vendor, (u32)pdev->device);
+
+	cpt_unregister_interrupts(cpt);
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+	pci_set_drvdata(pdev, NULL);
+}
+
+/* Supported devices */
+static const struct pci_device_id cpt_id_table[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, CPT_81XX_PCI_PF_DEVICE_ID) },
+	{ 0, }  /* end of table */
+};
+MODULE_DEVICE_TABLE(pci, cpt_id_table);
+
+static struct pci_driver cpt_pci_driver = {
+	.name = DRV_NAME,
+	.id_table = cpt_id_table,
+	.probe = cpt_probe,
+	.remove = cpt_remove,
+	.shutdown = cpt_shutdown,
+};
+
+module_pci_driver(cpt_pci_driver);
+
+MODULE_AUTHOR("George Cherian <george.cherian@cavium.com>");
+MODULE_DESCRIPTION("Cavium Thunder CPT Physical Function Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_VERSION(DRV_VERSION);
diff --git a/drivers/crypto/cavium/cpt/cptpf_mbox.c b/drivers/crypto/cavium/cpt/cptpf_mbox.c
new file mode 100644
index 000000000..f01b863d6
--- /dev/null
+++ b/drivers/crypto/cavium/cpt/cptpf_mbox.c
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2016 Cavium, Inc.
+ */
+#include <linux/module.h>
+#include "cptpf.h"
+
+static void cpt_send_msg_to_vf(struct cpt_device *cpt, int vf,
+			       struct cpt_mbox *mbx)
+{
+	/* Writing mbox(0) causes interrupt */
+	cpt_write_csr64(cpt->reg_base, CPTX_PF_VFX_MBOXX(0, vf, 1),
+			mbx->data);
+	cpt_write_csr64(cpt->reg_base, CPTX_PF_VFX_MBOXX(0, vf, 0), mbx->msg);
+}
+
+/* ACKs VF's mailbox message
+ * @vf: VF to which ACK to be sent
+ */
+static void cpt_mbox_send_ack(struct cpt_device *cpt, int vf,
+			      struct cpt_mbox *mbx)
+{
+	mbx->data = 0ull;
+	mbx->msg = CPT_MBOX_MSG_TYPE_ACK;
+	cpt_send_msg_to_vf(cpt, vf, mbx);
+}
+
+static void cpt_clear_mbox_intr(struct cpt_device *cpt, u32 vf)
+{
+	/* W1C for the VF */
+	cpt_write_csr64(cpt->reg_base, CPTX_PF_MBOX_INTX(0, 0), (1 << vf));
+}
+
+/*
+ *  Configure QLEN/Chunk sizes for VF
+ */
+static void cpt_cfg_qlen_for_vf(struct cpt_device *cpt, int vf, u32 size)
+{
+	union cptx_pf_qx_ctl pf_qx_ctl;
+
+	pf_qx_ctl.u = cpt_read_csr64(cpt->reg_base, CPTX_PF_QX_CTL(0, vf));
+	pf_qx_ctl.s.size = size;
+	pf_qx_ctl.s.cont_err = true;
+	cpt_write_csr64(cpt->reg_base, CPTX_PF_QX_CTL(0, vf), pf_qx_ctl.u);
+}
+
+/*
+ * Configure VQ priority
+ */
+static void cpt_cfg_vq_priority(struct cpt_device *cpt, int vf, u32 pri)
+{
+	union cptx_pf_qx_ctl pf_qx_ctl;
+
+	pf_qx_ctl.u = cpt_read_csr64(cpt->reg_base, CPTX_PF_QX_CTL(0, vf));
+	pf_qx_ctl.s.pri = pri;
+	cpt_write_csr64(cpt->reg_base, CPTX_PF_QX_CTL(0, vf), pf_qx_ctl.u);
+}
+
+static int cpt_bind_vq_to_grp(struct cpt_device *cpt, u8 q, u8 grp)
+{
+	struct microcode *mcode = cpt->mcode;
+	union cptx_pf_qx_ctl pf_qx_ctl;
+	struct device *dev = &cpt->pdev->dev;
+
+	if (q >= CPT_MAX_VF_NUM) {
+		dev_err(dev, "Queues are more than cores in the group");
+		return -EINVAL;
+	}
+	if (grp >= CPT_MAX_CORE_GROUPS) {
+		dev_err(dev, "Request group is more than possible groups");
+		return -EINVAL;
+	}
+	if (grp >= cpt->next_mc_idx) {
+		dev_err(dev, "Request group is higher than available functional groups");
+		return -EINVAL;
+	}
+	pf_qx_ctl.u = cpt_read_csr64(cpt->reg_base, CPTX_PF_QX_CTL(0, q));
+	pf_qx_ctl.s.grp = mcode[grp].group;
+	cpt_write_csr64(cpt->reg_base, CPTX_PF_QX_CTL(0, q), pf_qx_ctl.u);
+	dev_dbg(dev, "VF %d TYPE %s", q, (mcode[grp].is_ae ? "AE" : "SE"));
+
+	return mcode[grp].is_ae ? AE_TYPES : SE_TYPES;
+}
+
+/* Interrupt handler to handle mailbox messages from VFs */
+static void cpt_handle_mbox_intr(struct cpt_device *cpt, int vf)
+{
+	struct cpt_vf_info *vfx = &cpt->vfinfo[vf];
+	struct cpt_mbox mbx = {};
+	int vftype;
+	struct device *dev = &cpt->pdev->dev;
+	/*
+	 * MBOX[0] contains msg
+	 * MBOX[1] contains data
+	 */
+	mbx.msg  = cpt_read_csr64(cpt->reg_base, CPTX_PF_VFX_MBOXX(0, vf, 0));
+	mbx.data = cpt_read_csr64(cpt->reg_base, CPTX_PF_VFX_MBOXX(0, vf, 1));
+	dev_dbg(dev, "%s: Mailbox msg 0x%llx from VF%d", __func__, mbx.msg, vf);
+	switch (mbx.msg) {
+	case CPT_MSG_VF_UP:
+		vfx->state = VF_STATE_UP;
+		try_module_get(THIS_MODULE);
+		cpt_mbox_send_ack(cpt, vf, &mbx);
+		break;
+	case CPT_MSG_READY:
+		mbx.msg  = CPT_MSG_READY;
+		mbx.data = vf;
+		cpt_send_msg_to_vf(cpt, vf, &mbx);
+		break;
+	case CPT_MSG_VF_DOWN:
+		/* First msg in VF teardown sequence */
+		vfx->state = VF_STATE_DOWN;
+		module_put(THIS_MODULE);
+		cpt_mbox_send_ack(cpt, vf, &mbx);
+		break;
+	case CPT_MSG_QLEN:
+		vfx->qlen = mbx.data;
+		cpt_cfg_qlen_for_vf(cpt, vf, vfx->qlen);
+		cpt_mbox_send_ack(cpt, vf, &mbx);
+		break;
+	case CPT_MSG_QBIND_GRP:
+		vftype = cpt_bind_vq_to_grp(cpt, vf, (u8)mbx.data);
+		if ((vftype != AE_TYPES) && (vftype != SE_TYPES))
+			dev_err(dev, "Queue %d binding to group %llu failed",
+				vf, mbx.data);
+		else {
+			dev_dbg(dev, "Queue %d binding to group %llu successful",
+				vf, mbx.data);
+			mbx.msg = CPT_MSG_QBIND_GRP;
+			mbx.data = vftype;
+			cpt_send_msg_to_vf(cpt, vf, &mbx);
+		}
+		break;
+	case CPT_MSG_VQ_PRIORITY:
+		vfx->priority = mbx.data;
+		cpt_cfg_vq_priority(cpt, vf, vfx->priority);
+		cpt_mbox_send_ack(cpt, vf, &mbx);
+		break;
+	default:
+		dev_err(&cpt->pdev->dev, "Invalid msg from VF%d, msg 0x%llx\n",
+			vf, mbx.msg);
+		break;
+	}
+}
+
+void cpt_mbox_intr_handler (struct cpt_device *cpt, int mbx)
+{
+	u64 intr;
+	u8  vf;
+
+	intr = cpt_read_csr64(cpt->reg_base, CPTX_PF_MBOX_INTX(0, 0));
+	dev_dbg(&cpt->pdev->dev, "PF interrupt Mbox%d 0x%llx\n", mbx, intr);
+	for (vf = 0; vf < CPT_MAX_VF_NUM; vf++) {
+		if (intr & (1ULL << vf)) {
+			dev_dbg(&cpt->pdev->dev, "Intr from VF %d\n", vf);
+			cpt_handle_mbox_intr(cpt, vf);
+			cpt_clear_mbox_intr(cpt, vf);
+		}
+	}
+}
diff --git a/drivers/crypto/cavium/cpt/cptvf.h b/drivers/crypto/cavium/cpt/cptvf.h
new file mode 100644
index 000000000..c695676ad
--- /dev/null
+++ b/drivers/crypto/cavium/cpt/cptvf.h
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2016 Cavium, Inc.
+ */
+
+#ifndef __CPTVF_H
+#define __CPTVF_H
+
+#include <linux/list.h>
+#include "cpt_common.h"
+
+/* Default command queue length */
+#define CPT_CMD_QLEN 2046
+#define CPT_CMD_QCHUNK_SIZE 1023
+
+/* Default command timeout in seconds */
+#define CPT_COMMAND_TIMEOUT 4
+#define CPT_TIMER_THOLD	0xFFFF
+#define CPT_NUM_QS_PER_VF 1
+#define CPT_INST_SIZE 64
+#define CPT_NEXT_CHUNK_PTR_SIZE 8
+
+#define	CPT_VF_MSIX_VECTORS 2
+#define CPT_VF_INTR_MBOX_MASK BIT(0)
+#define CPT_VF_INTR_DOVF_MASK BIT(1)
+#define CPT_VF_INTR_IRDE_MASK BIT(2)
+#define CPT_VF_INTR_NWRP_MASK BIT(3)
+#define CPT_VF_INTR_SERR_MASK BIT(4)
+#define DMA_DIRECT_DIRECT 0 /* Input DIRECT, Output DIRECT */
+#define DMA_GATHER_SCATTER 1
+#define FROM_DPTR 1
+
+/**
+ * Enumeration cpt_vf_int_vec_e
+ *
+ * CPT VF MSI-X Vector Enumeration
+ * Enumerates the MSI-X interrupt vectors.
+ */
+enum cpt_vf_int_vec_e {
+	CPT_VF_INT_VEC_E_MISC = 0x00,
+	CPT_VF_INT_VEC_E_DONE = 0x01
+};
+
+struct command_chunk {
+	u8 *head;
+	dma_addr_t dma_addr;
+	u32 size; /* Chunk size, max CPT_INST_CHUNK_MAX_SIZE */
+	struct hlist_node nextchunk;
+};
+
+struct command_queue {
+	spinlock_t lock; /* command queue lock */
+	u32 idx; /* Command queue host write idx */
+	u32 nchunks; /* Number of command chunks */
+	struct command_chunk *qhead;	/* Command queue head, instructions
+					 * are inserted here
+					 */
+	struct hlist_head chead;
+};
+
+struct command_qinfo {
+	u32 cmd_size;
+	u32 qchunksize; /* Command queue chunk size */
+	struct command_queue queue[CPT_NUM_QS_PER_VF];
+};
+
+struct pending_entry {
+	u8 busy; /* Entry status (free/busy) */
+
+	volatile u64 *completion_addr; /* Completion address */
+	void *post_arg;
+	void (*callback)(int, void *); /* Kernel ASYNC request callabck */
+	void *callback_arg; /* Kernel ASYNC request callabck arg */
+};
+
+struct pending_queue {
+	struct pending_entry *head;	/* head of the queue */
+	u32 front; /* Process work from here */
+	u32 rear; /* Append new work here */
+	atomic64_t pending_count;
+	spinlock_t lock; /* Queue lock */
+};
+
+struct pending_qinfo {
+	u32 nr_queues;	/* Number of queues supported */
+	u32 qlen; /* Queue length */
+	struct pending_queue queue[CPT_NUM_QS_PER_VF];
+};
+
+#define for_each_pending_queue(qinfo, q, i)	\
+	for (i = 0, q = &qinfo->queue[i]; i < qinfo->nr_queues; i++, \
+	     q = &qinfo->queue[i])
+
+struct cpt_vf {
+	u16 flags; /* Flags to hold device status bits */
+	u8 vfid; /* Device Index 0...CPT_MAX_VF_NUM */
+	u8 vftype; /* VF type of SE_TYPE(1) or AE_TYPE(1) */
+	u8 vfgrp; /* VF group (0 - 8) */
+	u8 node; /* Operating node: Bits (46:44) in BAR0 address */
+	u8 priority; /* VF priority ring: 1-High proirity round
+		      * robin ring;0-Low priority round robin ring;
+		      */
+	struct pci_dev *pdev; /* pci device handle */
+	void __iomem *reg_base; /* Register start address */
+	void *wqe_info;	/* BH worker info */
+	/* MSI-X */
+	cpumask_var_t affinity_mask[CPT_VF_MSIX_VECTORS];
+	/* Command and Pending queues */
+	u32 qsize;
+	u32 nr_queues;
+	struct command_qinfo cqinfo; /* Command queue information */
+	struct pending_qinfo pqinfo; /* Pending queue information */
+	/* VF-PF mailbox communication */
+	bool pf_acked;
+	bool pf_nacked;
+};
+
+int cptvf_send_vf_up(struct cpt_vf *cptvf);
+int cptvf_send_vf_down(struct cpt_vf *cptvf);
+int cptvf_send_vf_to_grp_msg(struct cpt_vf *cptvf);
+int cptvf_send_vf_priority_msg(struct cpt_vf *cptvf);
+int cptvf_send_vq_size_msg(struct cpt_vf *cptvf);
+int cptvf_check_pf_ready(struct cpt_vf *cptvf);
+void cptvf_handle_mbox_intr(struct cpt_vf *cptvf);
+void cvm_crypto_exit(void);
+int cvm_crypto_init(struct cpt_vf *cptvf);
+void vq_post_process(struct cpt_vf *cptvf, u32 qno);
+void cptvf_write_vq_doorbell(struct cpt_vf *cptvf, u32 val);
+#endif /* __CPTVF_H */
diff --git a/drivers/crypto/cavium/cpt/cptvf_algs.c b/drivers/crypto/cavium/cpt/cptvf_algs.c
new file mode 100644
index 000000000..219fe9be7
--- /dev/null
+++ b/drivers/crypto/cavium/cpt/cptvf_algs.c
@@ -0,0 +1,462 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/*
+ * Copyright (C) 2016 Cavium, Inc.
+ */
+
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <crypto/authenc.h>
+#include <crypto/internal/des.h>
+#include <crypto/xts.h>
+#include <linux/crypto.h>
+#include <linux/err.h>
+#include <linux/list.h>
+#include <linux/scatterlist.h>
+
+#include "cptvf.h"
+#include "cptvf_algs.h"
+
+struct cpt_device_handle {
+	void *cdev[MAX_DEVICES];
+	u32 dev_count;
+};
+
+static struct cpt_device_handle dev_handle;
+
+static void cvm_callback(u32 status, void *arg)
+{
+	struct crypto_async_request *req = (struct crypto_async_request *)arg;
+
+	crypto_request_complete(req, !status);
+}
+
+static inline void update_input_iv(struct cpt_request_info *req_info,
+				   u8 *iv, u32 enc_iv_len,
+				   u32 *argcnt)
+{
+	/* Setting the iv information */
+	req_info->in[*argcnt].vptr = (void *)iv;
+	req_info->in[*argcnt].size = enc_iv_len;
+	req_info->req.dlen += enc_iv_len;
+
+	++(*argcnt);
+}
+
+static inline void update_output_iv(struct cpt_request_info *req_info,
+				    u8 *iv, u32 enc_iv_len,
+				    u32 *argcnt)
+{
+	/* Setting the iv information */
+	req_info->out[*argcnt].vptr = (void *)iv;
+	req_info->out[*argcnt].size = enc_iv_len;
+	req_info->rlen += enc_iv_len;
+
+	++(*argcnt);
+}
+
+static inline void update_input_data(struct cpt_request_info *req_info,
+				     struct scatterlist *inp_sg,
+				     u32 nbytes, u32 *argcnt)
+{
+	req_info->req.dlen += nbytes;
+
+	while (nbytes) {
+		u32 len = min(nbytes, inp_sg->length);
+		u8 *ptr = sg_virt(inp_sg);
+
+		req_info->in[*argcnt].vptr = (void *)ptr;
+		req_info->in[*argcnt].size = len;
+		nbytes -= len;
+
+		++(*argcnt);
+		++inp_sg;
+	}
+}
+
+static inline void update_output_data(struct cpt_request_info *req_info,
+				      struct scatterlist *outp_sg,
+				      u32 nbytes, u32 *argcnt)
+{
+	req_info->rlen += nbytes;
+
+	while (nbytes) {
+		u32 len = min(nbytes, outp_sg->length);
+		u8 *ptr = sg_virt(outp_sg);
+
+		req_info->out[*argcnt].vptr = (void *)ptr;
+		req_info->out[*argcnt].size = len;
+		nbytes -= len;
+		++(*argcnt);
+		++outp_sg;
+	}
+}
+
+static inline u32 create_ctx_hdr(struct skcipher_request *req, u32 enc,
+				 u32 *argcnt)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct cvm_enc_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct cvm_req_ctx *rctx = skcipher_request_ctx_dma(req);
+	struct fc_context *fctx = &rctx->fctx;
+	u32 enc_iv_len = crypto_skcipher_ivsize(tfm);
+	struct cpt_request_info *req_info = &rctx->cpt_req;
+	__be64 *ctrl_flags = NULL;
+	__be64 *offset_control;
+
+	req_info->ctrl.s.grp = 0;
+	req_info->ctrl.s.dma_mode = DMA_GATHER_SCATTER;
+	req_info->ctrl.s.se_req = SE_CORE_REQ;
+
+	req_info->req.opcode.s.major = MAJOR_OP_FC |
+					DMA_MODE_FLAG(DMA_GATHER_SCATTER);
+	if (enc)
+		req_info->req.opcode.s.minor = 2;
+	else
+		req_info->req.opcode.s.minor = 3;
+
+	req_info->req.param1 = req->cryptlen; /* Encryption Data length */
+	req_info->req.param2 = 0; /*Auth data length */
+
+	fctx->enc.enc_ctrl.e.enc_cipher = ctx->cipher_type;
+	fctx->enc.enc_ctrl.e.aes_key = ctx->key_type;
+	fctx->enc.enc_ctrl.e.iv_source = FROM_DPTR;
+
+	if (ctx->cipher_type == AES_XTS)
+		memcpy(fctx->enc.encr_key, ctx->enc_key, ctx->key_len * 2);
+	else
+		memcpy(fctx->enc.encr_key, ctx->enc_key, ctx->key_len);
+	ctrl_flags = (__be64 *)&fctx->enc.enc_ctrl.flags;
+	*ctrl_flags = cpu_to_be64(fctx->enc.enc_ctrl.flags);
+
+	offset_control = (__be64 *)&rctx->control_word;
+	*offset_control = cpu_to_be64(((u64)(enc_iv_len) << 16));
+	/* Storing  Packet Data Information in offset
+	 * Control Word First 8 bytes
+	 */
+	req_info->in[*argcnt].vptr = (u8 *)offset_control;
+	req_info->in[*argcnt].size = CONTROL_WORD_LEN;
+	req_info->req.dlen += CONTROL_WORD_LEN;
+	++(*argcnt);
+
+	req_info->in[*argcnt].vptr = (u8 *)fctx;
+	req_info->in[*argcnt].size = sizeof(struct fc_context);
+	req_info->req.dlen += sizeof(struct fc_context);
+
+	++(*argcnt);
+
+	return 0;
+}
+
+static inline u32 create_input_list(struct skcipher_request  *req, u32 enc,
+				    u32 enc_iv_len)
+{
+	struct cvm_req_ctx *rctx = skcipher_request_ctx_dma(req);
+	struct cpt_request_info *req_info = &rctx->cpt_req;
+	u32 argcnt =  0;
+
+	create_ctx_hdr(req, enc, &argcnt);
+	update_input_iv(req_info, req->iv, enc_iv_len, &argcnt);
+	update_input_data(req_info, req->src, req->cryptlen, &argcnt);
+	req_info->incnt = argcnt;
+
+	return 0;
+}
+
+static inline void store_cb_info(struct skcipher_request *req,
+				 struct cpt_request_info *req_info)
+{
+	req_info->callback = (void *)cvm_callback;
+	req_info->callback_arg = (void *)&req->base;
+}
+
+static inline void create_output_list(struct skcipher_request *req,
+				      u32 enc_iv_len)
+{
+	struct cvm_req_ctx *rctx = skcipher_request_ctx_dma(req);
+	struct cpt_request_info *req_info = &rctx->cpt_req;
+	u32 argcnt = 0;
+
+	/* OUTPUT Buffer Processing
+	 * AES encryption/decryption output would be
+	 * received in the following format
+	 *
+	 * ------IV--------|------ENCRYPTED/DECRYPTED DATA-----|
+	 * [ 16 Bytes/     [   Request Enc/Dec/ DATA Len AES CBC ]
+	 */
+	/* Reading IV information */
+	update_output_iv(req_info, req->iv, enc_iv_len, &argcnt);
+	update_output_data(req_info, req->dst, req->cryptlen, &argcnt);
+	req_info->outcnt = argcnt;
+}
+
+static inline int cvm_enc_dec(struct skcipher_request *req, u32 enc)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct cvm_req_ctx *rctx = skcipher_request_ctx_dma(req);
+	u32 enc_iv_len = crypto_skcipher_ivsize(tfm);
+	struct fc_context *fctx = &rctx->fctx;
+	struct cpt_request_info *req_info = &rctx->cpt_req;
+	void *cdev = NULL;
+	int status;
+
+	memset(req_info, 0, sizeof(struct cpt_request_info));
+	req_info->may_sleep = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) != 0;
+	memset(fctx, 0, sizeof(struct fc_context));
+	create_input_list(req, enc, enc_iv_len);
+	create_output_list(req, enc_iv_len);
+	store_cb_info(req, req_info);
+	cdev = dev_handle.cdev[smp_processor_id()];
+	status = cptvf_do_request(cdev, req_info);
+	/* We perform an asynchronous send and once
+	 * the request is completed the driver would
+	 * intimate through  registered call back functions
+	 */
+
+	if (status)
+		return status;
+	else
+		return -EINPROGRESS;
+}
+
+static int cvm_encrypt(struct skcipher_request *req)
+{
+	return cvm_enc_dec(req, true);
+}
+
+static int cvm_decrypt(struct skcipher_request *req)
+{
+	return cvm_enc_dec(req, false);
+}
+
+static int cvm_xts_setkey(struct crypto_skcipher *cipher, const u8 *key,
+		   u32 keylen)
+{
+	struct cvm_enc_ctx *ctx = crypto_skcipher_ctx(cipher);
+	int err;
+	const u8 *key1 = key;
+	const u8 *key2 = key + (keylen / 2);
+
+	err = xts_verify_key(cipher, key, keylen);
+	if (err)
+		return err;
+	ctx->key_len = keylen;
+	memcpy(ctx->enc_key, key1, keylen / 2);
+	memcpy(ctx->enc_key + KEY2_OFFSET, key2, keylen / 2);
+	ctx->cipher_type = AES_XTS;
+	switch (ctx->key_len) {
+	case 32:
+		ctx->key_type = AES_128_BIT;
+		break;
+	case 64:
+		ctx->key_type = AES_256_BIT;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int cvm_validate_keylen(struct cvm_enc_ctx *ctx, u32 keylen)
+{
+	if ((keylen == 16) || (keylen == 24) || (keylen == 32)) {
+		ctx->key_len = keylen;
+		switch (ctx->key_len) {
+		case 16:
+			ctx->key_type = AES_128_BIT;
+			break;
+		case 24:
+			ctx->key_type = AES_192_BIT;
+			break;
+		case 32:
+			ctx->key_type = AES_256_BIT;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		if (ctx->cipher_type == DES3_CBC)
+			ctx->key_type = 0;
+
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int cvm_setkey(struct crypto_skcipher *cipher, const u8 *key,
+		      u32 keylen, u8 cipher_type)
+{
+	struct cvm_enc_ctx *ctx = crypto_skcipher_ctx(cipher);
+
+	ctx->cipher_type = cipher_type;
+	if (!cvm_validate_keylen(ctx, keylen)) {
+		memcpy(ctx->enc_key, key, keylen);
+		return 0;
+	} else {
+		return -EINVAL;
+	}
+}
+
+static int cvm_cbc_aes_setkey(struct crypto_skcipher *cipher, const u8 *key,
+			      u32 keylen)
+{
+	return cvm_setkey(cipher, key, keylen, AES_CBC);
+}
+
+static int cvm_ecb_aes_setkey(struct crypto_skcipher *cipher, const u8 *key,
+			      u32 keylen)
+{
+	return cvm_setkey(cipher, key, keylen, AES_ECB);
+}
+
+static int cvm_cbc_des3_setkey(struct crypto_skcipher *cipher, const u8 *key,
+			       u32 keylen)
+{
+	return verify_skcipher_des3_key(cipher, key) ?:
+	       cvm_setkey(cipher, key, keylen, DES3_CBC);
+}
+
+static int cvm_ecb_des3_setkey(struct crypto_skcipher *cipher, const u8 *key,
+			       u32 keylen)
+{
+	return verify_skcipher_des3_key(cipher, key) ?:
+	       cvm_setkey(cipher, key, keylen, DES3_ECB);
+}
+
+static int cvm_enc_dec_init(struct crypto_skcipher *tfm)
+{
+	crypto_skcipher_set_reqsize_dma(tfm, sizeof(struct cvm_req_ctx));
+
+	return 0;
+}
+
+static struct skcipher_alg algs[] = { {
+	.base.cra_flags		= CRYPTO_ALG_ASYNC |
+				  CRYPTO_ALG_ALLOCATES_MEMORY,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct cvm_enc_ctx),
+	.base.cra_alignmask	= 7,
+	.base.cra_priority	= 4001,
+	.base.cra_name		= "xts(aes)",
+	.base.cra_driver_name	= "cavium-xts-aes",
+	.base.cra_module	= THIS_MODULE,
+
+	.ivsize			= AES_BLOCK_SIZE,
+	.min_keysize		= 2 * AES_MIN_KEY_SIZE,
+	.max_keysize		= 2 * AES_MAX_KEY_SIZE,
+	.setkey			= cvm_xts_setkey,
+	.encrypt		= cvm_encrypt,
+	.decrypt		= cvm_decrypt,
+	.init			= cvm_enc_dec_init,
+}, {
+	.base.cra_flags		= CRYPTO_ALG_ASYNC |
+				  CRYPTO_ALG_ALLOCATES_MEMORY,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct cvm_enc_ctx),
+	.base.cra_alignmask	= 7,
+	.base.cra_priority	= 4001,
+	.base.cra_name		= "cbc(aes)",
+	.base.cra_driver_name	= "cavium-cbc-aes",
+	.base.cra_module	= THIS_MODULE,
+
+	.ivsize			= AES_BLOCK_SIZE,
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= cvm_cbc_aes_setkey,
+	.encrypt		= cvm_encrypt,
+	.decrypt		= cvm_decrypt,
+	.init			= cvm_enc_dec_init,
+}, {
+	.base.cra_flags		= CRYPTO_ALG_ASYNC |
+				  CRYPTO_ALG_ALLOCATES_MEMORY,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct cvm_enc_ctx),
+	.base.cra_alignmask	= 7,
+	.base.cra_priority	= 4001,
+	.base.cra_name		= "ecb(aes)",
+	.base.cra_driver_name	= "cavium-ecb-aes",
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= cvm_ecb_aes_setkey,
+	.encrypt		= cvm_encrypt,
+	.decrypt		= cvm_decrypt,
+	.init			= cvm_enc_dec_init,
+}, {
+	.base.cra_flags		= CRYPTO_ALG_ASYNC |
+				  CRYPTO_ALG_ALLOCATES_MEMORY,
+	.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct cvm_des3_ctx),
+	.base.cra_alignmask	= 7,
+	.base.cra_priority	= 4001,
+	.base.cra_name		= "cbc(des3_ede)",
+	.base.cra_driver_name	= "cavium-cbc-des3_ede",
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= DES3_EDE_KEY_SIZE,
+	.max_keysize		= DES3_EDE_KEY_SIZE,
+	.ivsize			= DES_BLOCK_SIZE,
+	.setkey			= cvm_cbc_des3_setkey,
+	.encrypt		= cvm_encrypt,
+	.decrypt		= cvm_decrypt,
+	.init			= cvm_enc_dec_init,
+}, {
+	.base.cra_flags		= CRYPTO_ALG_ASYNC |
+				  CRYPTO_ALG_ALLOCATES_MEMORY,
+	.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct cvm_des3_ctx),
+	.base.cra_alignmask	= 7,
+	.base.cra_priority	= 4001,
+	.base.cra_name		= "ecb(des3_ede)",
+	.base.cra_driver_name	= "cavium-ecb-des3_ede",
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= DES3_EDE_KEY_SIZE,
+	.max_keysize		= DES3_EDE_KEY_SIZE,
+	.ivsize			= DES_BLOCK_SIZE,
+	.setkey			= cvm_ecb_des3_setkey,
+	.encrypt		= cvm_encrypt,
+	.decrypt		= cvm_decrypt,
+	.init			= cvm_enc_dec_init,
+} };
+
+static inline int cav_register_algs(void)
+{
+	return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
+}
+
+static inline void cav_unregister_algs(void)
+{
+	crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
+}
+
+int cvm_crypto_init(struct cpt_vf *cptvf)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+	u32 dev_count;
+
+	dev_count = dev_handle.dev_count;
+	dev_handle.cdev[dev_count] = cptvf;
+	dev_handle.dev_count++;
+
+	if (dev_count == 3) {
+		if (cav_register_algs()) {
+			dev_err(&pdev->dev, "Error in registering crypto algorithms\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+void cvm_crypto_exit(void)
+{
+	u32 dev_count;
+
+	dev_count = --dev_handle.dev_count;
+	if (!dev_count)
+		cav_unregister_algs();
+}
diff --git a/drivers/crypto/cavium/cpt/cptvf_algs.h b/drivers/crypto/cavium/cpt/cptvf_algs.h
new file mode 100644
index 000000000..61a149fe8
--- /dev/null
+++ b/drivers/crypto/cavium/cpt/cptvf_algs.h
@@ -0,0 +1,117 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2016 Cavium, Inc.
+ */
+
+#ifndef _CPTVF_ALGS_H_
+#define _CPTVF_ALGS_H_
+
+#include "request_manager.h"
+
+#define MAX_DEVICES 16
+#define MAJOR_OP_FC 0x33
+#define MAX_ENC_KEY_SIZE 32
+#define MAX_HASH_KEY_SIZE 64
+#define MAX_KEY_SIZE (MAX_ENC_KEY_SIZE + MAX_HASH_KEY_SIZE)
+#define CONTROL_WORD_LEN 8
+#define KEY2_OFFSET 48
+
+#define DMA_MODE_FLAG(dma_mode) \
+	(((dma_mode) == DMA_GATHER_SCATTER) ? (1 << 7) : 0)
+
+enum req_type {
+	AE_CORE_REQ,
+	SE_CORE_REQ,
+};
+
+enum cipher_type {
+	DES3_CBC = 0x1,
+	DES3_ECB = 0x2,
+	AES_CBC = 0x3,
+	AES_ECB = 0x4,
+	AES_CFB = 0x5,
+	AES_CTR = 0x6,
+	AES_GCM = 0x7,
+	AES_XTS = 0x8
+};
+
+enum aes_type {
+	AES_128_BIT = 0x1,
+	AES_192_BIT = 0x2,
+	AES_256_BIT = 0x3
+};
+
+union encr_ctrl {
+	u64 flags;
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 enc_cipher:4;
+		u64 reserved1:1;
+		u64 aes_key:2;
+		u64 iv_source:1;
+		u64 hash_type:4;
+		u64 reserved2:3;
+		u64 auth_input_type:1;
+		u64 mac_len:8;
+		u64 reserved3:8;
+		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 reserved3:8;
+		u64 mac_len:8;
+		u64 auth_input_type:1;
+		u64 reserved2:3;
+		u64 hash_type:4;
+		u64 iv_source:1;
+		u64 aes_key:2;
+		u64 reserved1:1;
+		u64 enc_cipher:4;
+#endif
+	} e;
+};
+
+struct cvm_cipher {
+	const char *name;
+	u8 value;
+};
+
+struct enc_context {
+	union encr_ctrl enc_ctrl;
+	u8 encr_key[32];
+	u8 encr_iv[16];
+};
+
+struct fchmac_context {
+	u8 ipad[64];
+	u8 opad[64]; /* or OPAD */
+};
+
+struct fc_context {
+	struct enc_context enc;
+	struct fchmac_context hmac;
+};
+
+struct cvm_enc_ctx {
+	u32 key_len;
+	u8 enc_key[MAX_KEY_SIZE];
+	u8 cipher_type:4;
+	u8 key_type:2;
+};
+
+struct cvm_des3_ctx {
+	u32 key_len;
+	u8 des3_key[MAX_KEY_SIZE];
+};
+
+struct cvm_req_ctx {
+	struct cpt_request_info cpt_req;
+	u64 control_word;
+	struct fc_context fctx;
+};
+
+int cptvf_do_request(void *cptvf, struct cpt_request_info *req);
+#endif /*_CPTVF_ALGS_H_*/
diff --git a/drivers/crypto/cavium/cpt/cptvf_main.c b/drivers/crypto/cavium/cpt/cptvf_main.c
new file mode 100644
index 000000000..db76df14c
--- /dev/null
+++ b/drivers/crypto/cavium/cpt/cptvf_main.c
@@ -0,0 +1,856 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2016 Cavium, Inc.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/module.h>
+
+#include "cptvf.h"
+
+#define DRV_NAME	"thunder-cptvf"
+#define DRV_VERSION	"1.0"
+
+struct cptvf_wqe {
+	struct tasklet_struct twork;
+	void *cptvf;
+	u32 qno;
+};
+
+struct cptvf_wqe_info {
+	struct cptvf_wqe vq_wqe[CPT_NUM_QS_PER_VF];
+};
+
+static void vq_work_handler(unsigned long data)
+{
+	struct cptvf_wqe_info *cwqe_info = (struct cptvf_wqe_info *)data;
+	struct cptvf_wqe *cwqe = &cwqe_info->vq_wqe[0];
+
+	vq_post_process(cwqe->cptvf, cwqe->qno);
+}
+
+static int init_worker_threads(struct cpt_vf *cptvf)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+	struct cptvf_wqe_info *cwqe_info;
+	int i;
+
+	cwqe_info = kzalloc_obj(*cwqe_info);
+	if (!cwqe_info)
+		return -ENOMEM;
+
+	if (cptvf->nr_queues) {
+		dev_info(&pdev->dev, "Creating VQ worker threads (%d)\n",
+			 cptvf->nr_queues);
+	}
+
+	for (i = 0; i < cptvf->nr_queues; i++) {
+		tasklet_init(&cwqe_info->vq_wqe[i].twork, vq_work_handler,
+			     (u64)cwqe_info);
+		cwqe_info->vq_wqe[i].qno = i;
+		cwqe_info->vq_wqe[i].cptvf = cptvf;
+	}
+
+	cptvf->wqe_info = cwqe_info;
+
+	return 0;
+}
+
+static void cleanup_worker_threads(struct cpt_vf *cptvf)
+{
+	struct cptvf_wqe_info *cwqe_info;
+	struct pci_dev *pdev = cptvf->pdev;
+	int i;
+
+	cwqe_info = (struct cptvf_wqe_info *)cptvf->wqe_info;
+	if (!cwqe_info)
+		return;
+
+	if (cptvf->nr_queues) {
+		dev_info(&pdev->dev, "Cleaning VQ worker threads (%u)\n",
+			 cptvf->nr_queues);
+	}
+
+	for (i = 0; i < cptvf->nr_queues; i++)
+		tasklet_kill(&cwqe_info->vq_wqe[i].twork);
+
+	kfree_sensitive(cwqe_info);
+	cptvf->wqe_info = NULL;
+}
+
+static void free_pending_queues(struct pending_qinfo *pqinfo)
+{
+	int i;
+	struct pending_queue *queue;
+
+	for_each_pending_queue(pqinfo, queue, i) {
+		if (!queue->head)
+			continue;
+
+		/* free single queue */
+		kfree_sensitive((queue->head));
+
+		queue->front = 0;
+		queue->rear = 0;
+
+		return;
+	}
+
+	pqinfo->qlen = 0;
+	pqinfo->nr_queues = 0;
+}
+
+static int alloc_pending_queues(struct pending_qinfo *pqinfo, u32 qlen,
+				u32 nr_queues)
+{
+	u32 i;
+	int ret;
+	struct pending_queue *queue = NULL;
+
+	pqinfo->nr_queues = nr_queues;
+	pqinfo->qlen = qlen;
+
+	for_each_pending_queue(pqinfo, queue, i) {
+		queue->head = kzalloc_objs(*queue->head, qlen);
+		if (!queue->head) {
+			ret = -ENOMEM;
+			goto pending_qfail;
+		}
+
+		queue->front = 0;
+		queue->rear = 0;
+		atomic64_set((&queue->pending_count), (0));
+
+		/* init queue spin lock */
+		spin_lock_init(&queue->lock);
+	}
+
+	return 0;
+
+pending_qfail:
+	free_pending_queues(pqinfo);
+
+	return ret;
+}
+
+static int init_pending_queues(struct cpt_vf *cptvf, u32 qlen, u32 nr_queues)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+	int ret;
+
+	if (!nr_queues)
+		return 0;
+
+	ret = alloc_pending_queues(&cptvf->pqinfo, qlen, nr_queues);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to setup pending queues (%u)\n",
+			nr_queues);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void cleanup_pending_queues(struct cpt_vf *cptvf)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+
+	if (!cptvf->nr_queues)
+		return;
+
+	dev_info(&pdev->dev, "Cleaning VQ pending queue (%u)\n",
+		 cptvf->nr_queues);
+	free_pending_queues(&cptvf->pqinfo);
+}
+
+static void free_command_queues(struct cpt_vf *cptvf,
+				struct command_qinfo *cqinfo)
+{
+	int i;
+	struct command_queue *queue = NULL;
+	struct command_chunk *chunk = NULL;
+	struct pci_dev *pdev = cptvf->pdev;
+	struct hlist_node *node;
+
+	/* clean up for each queue */
+	for (i = 0; i < cptvf->nr_queues; i++) {
+		queue = &cqinfo->queue[i];
+		if (hlist_empty(&cqinfo->queue[i].chead))
+			continue;
+
+		hlist_for_each_entry_safe(chunk, node, &cqinfo->queue[i].chead,
+					  nextchunk) {
+			dma_free_coherent(&pdev->dev,
+					  chunk->size + CPT_NEXT_CHUNK_PTR_SIZE,
+					  chunk->head,
+					  chunk->dma_addr);
+			chunk->head = NULL;
+			chunk->dma_addr = 0;
+			hlist_del(&chunk->nextchunk);
+			kfree_sensitive(chunk);
+		}
+
+		queue->nchunks = 0;
+		queue->idx = 0;
+	}
+
+	/* common cleanup */
+	cqinfo->cmd_size = 0;
+}
+
+static int alloc_command_queues(struct cpt_vf *cptvf,
+				struct command_qinfo *cqinfo, size_t cmd_size,
+				u32 qlen)
+{
+	int i;
+	size_t q_size;
+	struct command_queue *queue = NULL;
+	struct pci_dev *pdev = cptvf->pdev;
+
+	/* common init */
+	cqinfo->cmd_size = cmd_size;
+	/* Qsize in dwords, needed for SADDR config, 1-next chunk pointer */
+	cptvf->qsize = min(qlen, cqinfo->qchunksize) *
+			CPT_NEXT_CHUNK_PTR_SIZE + 1;
+	/* Qsize in bytes to create space for alignment */
+	q_size = qlen * cqinfo->cmd_size;
+
+	/* per queue initialization */
+	for (i = 0; i < cptvf->nr_queues; i++) {
+		size_t c_size = 0;
+		size_t rem_q_size = q_size;
+		struct command_chunk *curr = NULL, *first = NULL, *last = NULL;
+		u32 qcsize_bytes = cqinfo->qchunksize * cqinfo->cmd_size;
+
+		queue = &cqinfo->queue[i];
+		INIT_HLIST_HEAD(&cqinfo->queue[i].chead);
+		do {
+			curr = kzalloc_obj(*curr);
+			if (!curr)
+				goto cmd_qfail;
+
+			c_size = (rem_q_size > qcsize_bytes) ? qcsize_bytes :
+					rem_q_size;
+			curr->head = dma_alloc_coherent(&pdev->dev,
+							c_size + CPT_NEXT_CHUNK_PTR_SIZE,
+							&curr->dma_addr,
+							GFP_KERNEL);
+			if (!curr->head) {
+				dev_err(&pdev->dev, "Command Q (%d) chunk (%d) allocation failed\n",
+					i, queue->nchunks);
+				kfree(curr);
+				goto cmd_qfail;
+			}
+
+			curr->size = c_size;
+			if (queue->nchunks == 0) {
+				hlist_add_head(&curr->nextchunk,
+					       &cqinfo->queue[i].chead);
+				first = curr;
+			} else {
+				hlist_add_behind(&curr->nextchunk,
+						 &last->nextchunk);
+			}
+
+			queue->nchunks++;
+			rem_q_size -= c_size;
+			if (last)
+				*((u64 *)(&last->head[last->size])) = (u64)curr->dma_addr;
+
+			last = curr;
+		} while (rem_q_size);
+
+		/* Make the queue circular */
+		/* Tie back last chunk entry to head */
+		curr = first;
+		*((u64 *)(&last->head[last->size])) = (u64)curr->dma_addr;
+		queue->qhead = curr;
+		spin_lock_init(&queue->lock);
+	}
+	return 0;
+
+cmd_qfail:
+	free_command_queues(cptvf, cqinfo);
+	return -ENOMEM;
+}
+
+static int init_command_queues(struct cpt_vf *cptvf, u32 qlen)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+	int ret;
+
+	/* setup AE command queues */
+	ret = alloc_command_queues(cptvf, &cptvf->cqinfo, CPT_INST_SIZE,
+				   qlen);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to allocate AE command queues (%u)\n",
+			cptvf->nr_queues);
+		return ret;
+	}
+
+	return ret;
+}
+
+static void cleanup_command_queues(struct cpt_vf *cptvf)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+
+	if (!cptvf->nr_queues)
+		return;
+
+	dev_info(&pdev->dev, "Cleaning VQ command queue (%u)\n",
+		 cptvf->nr_queues);
+	free_command_queues(cptvf, &cptvf->cqinfo);
+}
+
+static void cptvf_sw_cleanup(struct cpt_vf *cptvf)
+{
+	cleanup_worker_threads(cptvf);
+	cleanup_pending_queues(cptvf);
+	cleanup_command_queues(cptvf);
+}
+
+static int cptvf_sw_init(struct cpt_vf *cptvf, u32 qlen, u32 nr_queues)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+	int ret = 0;
+	u32 max_dev_queues = 0;
+
+	max_dev_queues = CPT_NUM_QS_PER_VF;
+	/* possible cpus */
+	nr_queues = min_t(u32, nr_queues, max_dev_queues);
+	cptvf->nr_queues = nr_queues;
+
+	ret = init_command_queues(cptvf, qlen);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to setup command queues (%u)\n",
+			nr_queues);
+		return ret;
+	}
+
+	ret = init_pending_queues(cptvf, qlen, nr_queues);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to setup pending queues (%u)\n",
+			nr_queues);
+		goto setup_pqfail;
+	}
+
+	/* Create worker threads for BH processing */
+	ret = init_worker_threads(cptvf);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to setup worker threads\n");
+		goto init_work_fail;
+	}
+
+	return 0;
+
+init_work_fail:
+	cleanup_worker_threads(cptvf);
+	cleanup_pending_queues(cptvf);
+
+setup_pqfail:
+	cleanup_command_queues(cptvf);
+
+	return ret;
+}
+
+static void cptvf_free_irq_affinity(struct cpt_vf *cptvf, int vec)
+{
+	irq_set_affinity_hint(pci_irq_vector(cptvf->pdev, vec), NULL);
+	free_cpumask_var(cptvf->affinity_mask[vec]);
+}
+
+static void cptvf_write_vq_ctl(struct cpt_vf *cptvf, bool val)
+{
+	union cptx_vqx_ctl vqx_ctl;
+
+	vqx_ctl.u = cpt_read_csr64(cptvf->reg_base, CPTX_VQX_CTL(0, 0));
+	vqx_ctl.s.ena = val;
+	cpt_write_csr64(cptvf->reg_base, CPTX_VQX_CTL(0, 0), vqx_ctl.u);
+}
+
+void cptvf_write_vq_doorbell(struct cpt_vf *cptvf, u32 val)
+{
+	union cptx_vqx_doorbell vqx_dbell;
+
+	vqx_dbell.u = cpt_read_csr64(cptvf->reg_base,
+				     CPTX_VQX_DOORBELL(0, 0));
+	vqx_dbell.s.dbell_cnt = val * 8; /* Num of Instructions * 8 words */
+	cpt_write_csr64(cptvf->reg_base, CPTX_VQX_DOORBELL(0, 0),
+			vqx_dbell.u);
+}
+
+static void cptvf_write_vq_inprog(struct cpt_vf *cptvf, u8 val)
+{
+	union cptx_vqx_inprog vqx_inprg;
+
+	vqx_inprg.u = cpt_read_csr64(cptvf->reg_base, CPTX_VQX_INPROG(0, 0));
+	vqx_inprg.s.inflight = val;
+	cpt_write_csr64(cptvf->reg_base, CPTX_VQX_INPROG(0, 0), vqx_inprg.u);
+}
+
+static void cptvf_write_vq_done_numwait(struct cpt_vf *cptvf, u32 val)
+{
+	union cptx_vqx_done_wait vqx_dwait;
+
+	vqx_dwait.u = cpt_read_csr64(cptvf->reg_base,
+				     CPTX_VQX_DONE_WAIT(0, 0));
+	vqx_dwait.s.num_wait = val;
+	cpt_write_csr64(cptvf->reg_base, CPTX_VQX_DONE_WAIT(0, 0),
+			vqx_dwait.u);
+}
+
+static void cptvf_write_vq_done_timewait(struct cpt_vf *cptvf, u16 time)
+{
+	union cptx_vqx_done_wait vqx_dwait;
+
+	vqx_dwait.u = cpt_read_csr64(cptvf->reg_base,
+				     CPTX_VQX_DONE_WAIT(0, 0));
+	vqx_dwait.s.time_wait = time;
+	cpt_write_csr64(cptvf->reg_base, CPTX_VQX_DONE_WAIT(0, 0),
+			vqx_dwait.u);
+}
+
+static void cptvf_enable_swerr_interrupts(struct cpt_vf *cptvf)
+{
+	union cptx_vqx_misc_ena_w1s vqx_misc_ena;
+
+	vqx_misc_ena.u = cpt_read_csr64(cptvf->reg_base,
+					CPTX_VQX_MISC_ENA_W1S(0, 0));
+	/* Set mbox(0) interupts for the requested vf */
+	vqx_misc_ena.s.swerr = 1;
+	cpt_write_csr64(cptvf->reg_base, CPTX_VQX_MISC_ENA_W1S(0, 0),
+			vqx_misc_ena.u);
+}
+
+static void cptvf_enable_mbox_interrupts(struct cpt_vf *cptvf)
+{
+	union cptx_vqx_misc_ena_w1s vqx_misc_ena;
+
+	vqx_misc_ena.u = cpt_read_csr64(cptvf->reg_base,
+					CPTX_VQX_MISC_ENA_W1S(0, 0));
+	/* Set mbox(0) interupts for the requested vf */
+	vqx_misc_ena.s.mbox = 1;
+	cpt_write_csr64(cptvf->reg_base, CPTX_VQX_MISC_ENA_W1S(0, 0),
+			vqx_misc_ena.u);
+}
+
+static void cptvf_enable_done_interrupts(struct cpt_vf *cptvf)
+{
+	union cptx_vqx_done_ena_w1s vqx_done_ena;
+
+	vqx_done_ena.u = cpt_read_csr64(cptvf->reg_base,
+					CPTX_VQX_DONE_ENA_W1S(0, 0));
+	/* Set DONE interrupt for the requested vf */
+	vqx_done_ena.s.done = 1;
+	cpt_write_csr64(cptvf->reg_base, CPTX_VQX_DONE_ENA_W1S(0, 0),
+			vqx_done_ena.u);
+}
+
+static void cptvf_clear_dovf_intr(struct cpt_vf *cptvf)
+{
+	union cptx_vqx_misc_int vqx_misc_int;
+
+	vqx_misc_int.u = cpt_read_csr64(cptvf->reg_base,
+					CPTX_VQX_MISC_INT(0, 0));
+	/* W1C for the VF */
+	vqx_misc_int.s.dovf = 1;
+	cpt_write_csr64(cptvf->reg_base, CPTX_VQX_MISC_INT(0, 0),
+			vqx_misc_int.u);
+}
+
+static void cptvf_clear_irde_intr(struct cpt_vf *cptvf)
+{
+	union cptx_vqx_misc_int vqx_misc_int;
+
+	vqx_misc_int.u = cpt_read_csr64(cptvf->reg_base,
+					CPTX_VQX_MISC_INT(0, 0));
+	/* W1C for the VF */
+	vqx_misc_int.s.irde = 1;
+	cpt_write_csr64(cptvf->reg_base, CPTX_VQX_MISC_INT(0, 0),
+			vqx_misc_int.u);
+}
+
+static void cptvf_clear_nwrp_intr(struct cpt_vf *cptvf)
+{
+	union cptx_vqx_misc_int vqx_misc_int;
+
+	vqx_misc_int.u = cpt_read_csr64(cptvf->reg_base,
+					CPTX_VQX_MISC_INT(0, 0));
+	/* W1C for the VF */
+	vqx_misc_int.s.nwrp = 1;
+	cpt_write_csr64(cptvf->reg_base,
+			CPTX_VQX_MISC_INT(0, 0), vqx_misc_int.u);
+}
+
+static void cptvf_clear_mbox_intr(struct cpt_vf *cptvf)
+{
+	union cptx_vqx_misc_int vqx_misc_int;
+
+	vqx_misc_int.u = cpt_read_csr64(cptvf->reg_base,
+					CPTX_VQX_MISC_INT(0, 0));
+	/* W1C for the VF */
+	vqx_misc_int.s.mbox = 1;
+	cpt_write_csr64(cptvf->reg_base, CPTX_VQX_MISC_INT(0, 0),
+			vqx_misc_int.u);
+}
+
+static void cptvf_clear_swerr_intr(struct cpt_vf *cptvf)
+{
+	union cptx_vqx_misc_int vqx_misc_int;
+
+	vqx_misc_int.u = cpt_read_csr64(cptvf->reg_base,
+					CPTX_VQX_MISC_INT(0, 0));
+	/* W1C for the VF */
+	vqx_misc_int.s.swerr = 1;
+	cpt_write_csr64(cptvf->reg_base, CPTX_VQX_MISC_INT(0, 0),
+			vqx_misc_int.u);
+}
+
+static u64 cptvf_read_vf_misc_intr_status(struct cpt_vf *cptvf)
+{
+	return cpt_read_csr64(cptvf->reg_base, CPTX_VQX_MISC_INT(0, 0));
+}
+
+static irqreturn_t cptvf_misc_intr_handler(int irq, void *cptvf_irq)
+{
+	struct cpt_vf *cptvf = (struct cpt_vf *)cptvf_irq;
+	struct pci_dev *pdev = cptvf->pdev;
+	u64 intr;
+
+	intr = cptvf_read_vf_misc_intr_status(cptvf);
+	/*Check for MISC interrupt types*/
+	if (likely(intr & CPT_VF_INTR_MBOX_MASK)) {
+		dev_dbg(&pdev->dev, "Mailbox interrupt 0x%llx on CPT VF %d\n",
+			intr, cptvf->vfid);
+		cptvf_handle_mbox_intr(cptvf);
+		cptvf_clear_mbox_intr(cptvf);
+	} else if (unlikely(intr & CPT_VF_INTR_DOVF_MASK)) {
+		cptvf_clear_dovf_intr(cptvf);
+		/*Clear doorbell count*/
+		cptvf_write_vq_doorbell(cptvf, 0);
+		dev_err(&pdev->dev, "Doorbell overflow error interrupt 0x%llx on CPT VF %d\n",
+			intr, cptvf->vfid);
+	} else if (unlikely(intr & CPT_VF_INTR_IRDE_MASK)) {
+		cptvf_clear_irde_intr(cptvf);
+		dev_err(&pdev->dev, "Instruction NCB read error interrupt 0x%llx on CPT VF %d\n",
+			intr, cptvf->vfid);
+	} else if (unlikely(intr & CPT_VF_INTR_NWRP_MASK)) {
+		cptvf_clear_nwrp_intr(cptvf);
+		dev_err(&pdev->dev, "NCB response write error interrupt 0x%llx on CPT VF %d\n",
+			intr, cptvf->vfid);
+	} else if (unlikely(intr & CPT_VF_INTR_SERR_MASK)) {
+		cptvf_clear_swerr_intr(cptvf);
+		dev_err(&pdev->dev, "Software error interrupt 0x%llx on CPT VF %d\n",
+			intr, cptvf->vfid);
+	} else {
+		dev_err(&pdev->dev, "Unhandled interrupt in CPT VF %d\n",
+			cptvf->vfid);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static inline struct cptvf_wqe *get_cptvf_vq_wqe(struct cpt_vf *cptvf,
+						 int qno)
+{
+	struct cptvf_wqe_info *nwqe_info;
+
+	if (unlikely(qno >= cptvf->nr_queues))
+		return NULL;
+	nwqe_info = (struct cptvf_wqe_info *)cptvf->wqe_info;
+
+	return &nwqe_info->vq_wqe[qno];
+}
+
+static inline u32 cptvf_read_vq_done_count(struct cpt_vf *cptvf)
+{
+	union cptx_vqx_done vqx_done;
+
+	vqx_done.u = cpt_read_csr64(cptvf->reg_base, CPTX_VQX_DONE(0, 0));
+	return vqx_done.s.done;
+}
+
+static inline void cptvf_write_vq_done_ack(struct cpt_vf *cptvf,
+					   u32 ackcnt)
+{
+	union cptx_vqx_done_ack vqx_dack_cnt;
+
+	vqx_dack_cnt.u = cpt_read_csr64(cptvf->reg_base,
+					CPTX_VQX_DONE_ACK(0, 0));
+	vqx_dack_cnt.s.done_ack = ackcnt;
+	cpt_write_csr64(cptvf->reg_base, CPTX_VQX_DONE_ACK(0, 0),
+			vqx_dack_cnt.u);
+}
+
+static irqreturn_t cptvf_done_intr_handler(int irq, void *cptvf_irq)
+{
+	struct cpt_vf *cptvf = (struct cpt_vf *)cptvf_irq;
+	struct pci_dev *pdev = cptvf->pdev;
+	/* Read the number of completions */
+	u32 intr = cptvf_read_vq_done_count(cptvf);
+
+	if (intr) {
+		struct cptvf_wqe *wqe;
+
+		/* Acknowledge the number of
+		 * scheduled completions for processing
+		 */
+		cptvf_write_vq_done_ack(cptvf, intr);
+		wqe = get_cptvf_vq_wqe(cptvf, 0);
+		if (unlikely(!wqe)) {
+			dev_err(&pdev->dev, "No work to schedule for VF (%d)",
+				cptvf->vfid);
+			return IRQ_NONE;
+		}
+		tasklet_hi_schedule(&wqe->twork);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void cptvf_set_irq_affinity(struct cpt_vf *cptvf, int vec)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+	int cpu;
+
+	if (!zalloc_cpumask_var(&cptvf->affinity_mask[vec],
+				GFP_KERNEL)) {
+		dev_err(&pdev->dev, "Allocation failed for affinity_mask for VF %d",
+			cptvf->vfid);
+		return;
+	}
+
+	cpu = cptvf->vfid % num_online_cpus();
+	cpumask_set_cpu(cpumask_local_spread(cpu, cptvf->node),
+			cptvf->affinity_mask[vec]);
+	irq_set_affinity_hint(pci_irq_vector(pdev, vec),
+			cptvf->affinity_mask[vec]);
+}
+
+static void cptvf_write_vq_saddr(struct cpt_vf *cptvf, u64 val)
+{
+	union cptx_vqx_saddr vqx_saddr;
+
+	vqx_saddr.u = val;
+	cpt_write_csr64(cptvf->reg_base, CPTX_VQX_SADDR(0, 0), vqx_saddr.u);
+}
+
+static void cptvf_device_init(struct cpt_vf *cptvf)
+{
+	u64 base_addr = 0;
+
+	/* Disable the VQ */
+	cptvf_write_vq_ctl(cptvf, 0);
+	/* Reset the doorbell */
+	cptvf_write_vq_doorbell(cptvf, 0);
+	/* Clear inflight */
+	cptvf_write_vq_inprog(cptvf, 0);
+	/* Write VQ SADDR */
+	/* TODO: for now only one queue, so hard coded */
+	base_addr = (u64)(cptvf->cqinfo.queue[0].qhead->dma_addr);
+	cptvf_write_vq_saddr(cptvf, base_addr);
+	/* Configure timerhold / coalescence */
+	cptvf_write_vq_done_timewait(cptvf, CPT_TIMER_THOLD);
+	cptvf_write_vq_done_numwait(cptvf, 1);
+	/* Enable the VQ */
+	cptvf_write_vq_ctl(cptvf, 1);
+	/* Flag the VF ready */
+	cptvf->flags |= CPT_FLAG_DEVICE_READY;
+}
+
+static int cptvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	struct device *dev = &pdev->dev;
+	struct cpt_vf *cptvf;
+	int    err;
+
+	cptvf = devm_kzalloc(dev, sizeof(*cptvf), GFP_KERNEL);
+	if (!cptvf)
+		return -ENOMEM;
+
+	pci_set_drvdata(pdev, cptvf);
+	cptvf->pdev = pdev;
+	err = pci_enable_device(pdev);
+	if (err) {
+		dev_err(dev, "Failed to enable PCI device\n");
+		pci_set_drvdata(pdev, NULL);
+		return err;
+	}
+
+	err = pci_request_regions(pdev, DRV_NAME);
+	if (err) {
+		dev_err(dev, "PCI request regions failed 0x%x\n", err);
+		goto cptvf_err_disable_device;
+	}
+	/* Mark as VF driver */
+	cptvf->flags |= CPT_FLAG_VF_DRIVER;
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(48));
+	if (err) {
+		dev_err(dev, "Unable to get usable 48-bit DMA configuration\n");
+		goto cptvf_err_release_regions;
+	}
+
+	/* MAP PF's configuration registers */
+	cptvf->reg_base = pcim_iomap(pdev, 0, 0);
+	if (!cptvf->reg_base) {
+		dev_err(dev, "Cannot map config register space, aborting\n");
+		err = -ENOMEM;
+		goto cptvf_err_release_regions;
+	}
+
+	cptvf->node = dev_to_node(&pdev->dev);
+	err = pci_alloc_irq_vectors(pdev, CPT_VF_MSIX_VECTORS,
+			CPT_VF_MSIX_VECTORS, PCI_IRQ_MSIX);
+	if (err < 0) {
+		dev_err(dev, "Request for #%d msix vectors failed\n",
+			CPT_VF_MSIX_VECTORS);
+		goto cptvf_err_release_regions;
+	}
+
+	err = request_irq(pci_irq_vector(pdev, CPT_VF_INT_VEC_E_MISC),
+			  cptvf_misc_intr_handler, 0, "CPT VF misc intr",
+			  cptvf);
+	if (err) {
+		dev_err(dev, "Request misc irq failed");
+		goto cptvf_free_vectors;
+	}
+
+	/* Enable mailbox interrupt */
+	cptvf_enable_mbox_interrupts(cptvf);
+	cptvf_enable_swerr_interrupts(cptvf);
+
+	/* Check ready with PF */
+	/* Gets chip ID / device Id from PF if ready */
+	err = cptvf_check_pf_ready(cptvf);
+	if (err) {
+		dev_err(dev, "PF not responding to READY msg");
+		goto cptvf_free_misc_irq;
+	}
+
+	/* CPT VF software resources initialization */
+	cptvf->cqinfo.qchunksize = CPT_CMD_QCHUNK_SIZE;
+	err = cptvf_sw_init(cptvf, CPT_CMD_QLEN, CPT_NUM_QS_PER_VF);
+	if (err) {
+		dev_err(dev, "cptvf_sw_init() failed");
+		goto cptvf_free_misc_irq;
+	}
+	/* Convey VQ LEN to PF */
+	err = cptvf_send_vq_size_msg(cptvf);
+	if (err) {
+		dev_err(dev, "PF not responding to QLEN msg");
+		goto cptvf_free_misc_irq;
+	}
+
+	/* CPT VF device initialization */
+	cptvf_device_init(cptvf);
+	/* Send msg to PF to assign currnet Q to required group */
+	cptvf->vfgrp = 1;
+	err = cptvf_send_vf_to_grp_msg(cptvf);
+	if (err) {
+		dev_err(dev, "PF not responding to VF_GRP msg");
+		goto cptvf_free_misc_irq;
+	}
+
+	cptvf->priority = 1;
+	err = cptvf_send_vf_priority_msg(cptvf);
+	if (err) {
+		dev_err(dev, "PF not responding to VF_PRIO msg");
+		goto cptvf_free_misc_irq;
+	}
+
+	err = request_irq(pci_irq_vector(pdev, CPT_VF_INT_VEC_E_DONE),
+			  cptvf_done_intr_handler, 0, "CPT VF done intr",
+			  cptvf);
+	if (err) {
+		dev_err(dev, "Request done irq failed\n");
+		goto cptvf_free_misc_irq;
+	}
+
+	/* Enable mailbox interrupt */
+	cptvf_enable_done_interrupts(cptvf);
+
+	/* Set irq affinity masks */
+	cptvf_set_irq_affinity(cptvf, CPT_VF_INT_VEC_E_MISC);
+	cptvf_set_irq_affinity(cptvf, CPT_VF_INT_VEC_E_DONE);
+
+	err = cptvf_send_vf_up(cptvf);
+	if (err) {
+		dev_err(dev, "PF not responding to UP msg");
+		goto cptvf_free_irq_affinity;
+	}
+	err = cvm_crypto_init(cptvf);
+	if (err) {
+		dev_err(dev, "Algorithm register failed\n");
+		goto cptvf_free_irq_affinity;
+	}
+	return 0;
+
+cptvf_free_irq_affinity:
+	cptvf_free_irq_affinity(cptvf, CPT_VF_INT_VEC_E_DONE);
+	cptvf_free_irq_affinity(cptvf, CPT_VF_INT_VEC_E_MISC);
+cptvf_free_misc_irq:
+	free_irq(pci_irq_vector(pdev, CPT_VF_INT_VEC_E_MISC), cptvf);
+cptvf_free_vectors:
+	pci_free_irq_vectors(cptvf->pdev);
+cptvf_err_release_regions:
+	pci_release_regions(pdev);
+cptvf_err_disable_device:
+	pci_disable_device(pdev);
+	pci_set_drvdata(pdev, NULL);
+
+	return err;
+}
+
+static void cptvf_remove(struct pci_dev *pdev)
+{
+	struct cpt_vf *cptvf = pci_get_drvdata(pdev);
+
+	if (!cptvf) {
+		dev_err(&pdev->dev, "Invalid CPT-VF device\n");
+		return;
+	}
+
+	/* Convey DOWN to PF */
+	if (cptvf_send_vf_down(cptvf)) {
+		dev_err(&pdev->dev, "PF not responding to DOWN msg");
+	} else {
+		cptvf_free_irq_affinity(cptvf, CPT_VF_INT_VEC_E_DONE);
+		cptvf_free_irq_affinity(cptvf, CPT_VF_INT_VEC_E_MISC);
+		free_irq(pci_irq_vector(pdev, CPT_VF_INT_VEC_E_DONE), cptvf);
+		free_irq(pci_irq_vector(pdev, CPT_VF_INT_VEC_E_MISC), cptvf);
+		pci_free_irq_vectors(cptvf->pdev);
+		cptvf_sw_cleanup(cptvf);
+		pci_set_drvdata(pdev, NULL);
+		pci_release_regions(pdev);
+		pci_disable_device(pdev);
+		cvm_crypto_exit();
+	}
+}
+
+static void cptvf_shutdown(struct pci_dev *pdev)
+{
+	cptvf_remove(pdev);
+}
+
+/* Supported devices */
+static const struct pci_device_id cptvf_id_table[] = {
+	{ PCI_VDEVICE(CAVIUM, CPT_81XX_PCI_VF_DEVICE_ID) },
+	{ }  /* end of table */
+};
+MODULE_DEVICE_TABLE(pci, cptvf_id_table);
+
+static struct pci_driver cptvf_pci_driver = {
+	.name = DRV_NAME,
+	.id_table = cptvf_id_table,
+	.probe = cptvf_probe,
+	.remove = cptvf_remove,
+	.shutdown = cptvf_shutdown,
+};
+
+module_pci_driver(cptvf_pci_driver);
+
+MODULE_AUTHOR("George Cherian <george.cherian@cavium.com>");
+MODULE_DESCRIPTION("Cavium Thunder CPT Virtual Function Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_VERSION(DRV_VERSION);
diff --git a/drivers/crypto/cavium/cpt/cptvf_mbox.c b/drivers/crypto/cavium/cpt/cptvf_mbox.c
new file mode 100644
index 000000000..1267e1eba
--- /dev/null
+++ b/drivers/crypto/cavium/cpt/cptvf_mbox.c
@@ -0,0 +1,191 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2016 Cavium, Inc.
+ */
+
+#include "cptvf.h"
+
+static void cptvf_send_msg_to_pf(struct cpt_vf *cptvf, struct cpt_mbox *mbx)
+{
+	/* Writing mbox(1) causes interrupt */
+	cpt_write_csr64(cptvf->reg_base, CPTX_VFX_PF_MBOXX(0, 0, 0),
+			mbx->msg);
+	cpt_write_csr64(cptvf->reg_base, CPTX_VFX_PF_MBOXX(0, 0, 1),
+			mbx->data);
+}
+
+/* Interrupt handler to handle mailbox messages from VFs */
+void cptvf_handle_mbox_intr(struct cpt_vf *cptvf)
+{
+	struct cpt_mbox mbx = {};
+
+	/*
+	 * MBOX[0] contains msg
+	 * MBOX[1] contains data
+	 */
+	mbx.msg  = cpt_read_csr64(cptvf->reg_base, CPTX_VFX_PF_MBOXX(0, 0, 0));
+	mbx.data = cpt_read_csr64(cptvf->reg_base, CPTX_VFX_PF_MBOXX(0, 0, 1));
+	dev_dbg(&cptvf->pdev->dev, "%s: Mailbox msg 0x%llx from PF\n",
+		__func__, mbx.msg);
+	switch (mbx.msg) {
+	case CPT_MSG_READY:
+	{
+		cptvf->pf_acked = true;
+		cptvf->vfid = mbx.data;
+		dev_dbg(&cptvf->pdev->dev, "Received VFID %d\n", cptvf->vfid);
+		break;
+	}
+	case CPT_MSG_QBIND_GRP:
+		cptvf->pf_acked = true;
+		cptvf->vftype = mbx.data;
+		dev_dbg(&cptvf->pdev->dev, "VF %d type %s group %d\n",
+			cptvf->vfid, ((mbx.data == SE_TYPES) ? "SE" : "AE"),
+			cptvf->vfgrp);
+		break;
+	case CPT_MBOX_MSG_TYPE_ACK:
+		cptvf->pf_acked = true;
+		break;
+	case CPT_MBOX_MSG_TYPE_NACK:
+		cptvf->pf_nacked = true;
+		break;
+	default:
+		dev_err(&cptvf->pdev->dev, "Invalid msg from PF, msg 0x%llx\n",
+			mbx.msg);
+		break;
+	}
+}
+
+static int cptvf_send_msg_to_pf_timeout(struct cpt_vf *cptvf,
+					struct cpt_mbox *mbx)
+{
+	int timeout = CPT_MBOX_MSG_TIMEOUT;
+	int sleep = 10;
+
+	cptvf->pf_acked = false;
+	cptvf->pf_nacked = false;
+	cptvf_send_msg_to_pf(cptvf, mbx);
+	/* Wait for previous message to be acked, timeout 2sec */
+	while (!cptvf->pf_acked) {
+		if (cptvf->pf_nacked)
+			return -EINVAL;
+		msleep(sleep);
+		if (cptvf->pf_acked)
+			break;
+		timeout -= sleep;
+		if (!timeout) {
+			dev_err(&cptvf->pdev->dev, "PF didn't ack to mbox msg %llx from VF%u\n",
+				(mbx->msg & 0xFF), cptvf->vfid);
+			return -EBUSY;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Checks if VF is able to comminicate with PF
+ * and also gets the CPT number this VF is associated to.
+ */
+int cptvf_check_pf_ready(struct cpt_vf *cptvf)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+	struct cpt_mbox mbx = {};
+
+	mbx.msg = CPT_MSG_READY;
+	if (cptvf_send_msg_to_pf_timeout(cptvf, &mbx)) {
+		dev_err(&pdev->dev, "PF didn't respond to READY msg\n");
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+/*
+ * Communicate VQs size to PF to program CPT(0)_PF_Q(0-15)_CTL of the VF.
+ * Must be ACKed.
+ */
+int cptvf_send_vq_size_msg(struct cpt_vf *cptvf)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+	struct cpt_mbox mbx = {};
+
+	mbx.msg = CPT_MSG_QLEN;
+	mbx.data = cptvf->qsize;
+	if (cptvf_send_msg_to_pf_timeout(cptvf, &mbx)) {
+		dev_err(&pdev->dev, "PF didn't respond to vq_size msg\n");
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+/*
+ * Communicate VF group required to PF and get the VQ binded to that group
+ */
+int cptvf_send_vf_to_grp_msg(struct cpt_vf *cptvf)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+	struct cpt_mbox mbx = {};
+
+	mbx.msg = CPT_MSG_QBIND_GRP;
+	/* Convey group of the VF */
+	mbx.data = cptvf->vfgrp;
+	if (cptvf_send_msg_to_pf_timeout(cptvf, &mbx)) {
+		dev_err(&pdev->dev, "PF didn't respond to vf_type msg\n");
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+/*
+ * Communicate VF group required to PF and get the VQ binded to that group
+ */
+int cptvf_send_vf_priority_msg(struct cpt_vf *cptvf)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+	struct cpt_mbox mbx = {};
+
+	mbx.msg = CPT_MSG_VQ_PRIORITY;
+	/* Convey group of the VF */
+	mbx.data = cptvf->priority;
+	if (cptvf_send_msg_to_pf_timeout(cptvf, &mbx)) {
+		dev_err(&pdev->dev, "PF didn't respond to vf_type msg\n");
+		return -EBUSY;
+	}
+	return 0;
+}
+
+/*
+ * Communicate to PF that VF is UP and running
+ */
+int cptvf_send_vf_up(struct cpt_vf *cptvf)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+	struct cpt_mbox mbx = {};
+
+	mbx.msg = CPT_MSG_VF_UP;
+	if (cptvf_send_msg_to_pf_timeout(cptvf, &mbx)) {
+		dev_err(&pdev->dev, "PF didn't respond to UP msg\n");
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+/*
+ * Communicate to PF that VF is DOWN and running
+ */
+int cptvf_send_vf_down(struct cpt_vf *cptvf)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+	struct cpt_mbox mbx = {};
+
+	mbx.msg = CPT_MSG_VF_DOWN;
+	if (cptvf_send_msg_to_pf_timeout(cptvf, &mbx)) {
+		dev_err(&pdev->dev, "PF didn't respond to DOWN msg\n");
+		return -EBUSY;
+	}
+
+	return 0;
+}
diff --git a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
new file mode 100644
index 000000000..de305cbec
--- /dev/null
+++ b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
@@ -0,0 +1,575 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2016 Cavium, Inc.
+ */
+
+#include "cptvf.h"
+#include "cptvf_algs.h"
+#include "request_manager.h"
+
+/**
+ * get_free_pending_entry - get free entry from pending queue
+ * @q: pending queue
+ * @qlen: queue length
+ */
+static struct pending_entry *get_free_pending_entry(struct pending_queue *q,
+						    int qlen)
+{
+	struct pending_entry *ent = NULL;
+
+	ent = &q->head[q->rear];
+	if (unlikely(ent->busy)) {
+		ent = NULL;
+		goto no_free_entry;
+	}
+
+	q->rear++;
+	if (unlikely(q->rear == qlen))
+		q->rear = 0;
+
+no_free_entry:
+	return ent;
+}
+
+static inline void pending_queue_inc_front(struct pending_qinfo *pqinfo,
+					   int qno)
+{
+	struct pending_queue *queue = &pqinfo->queue[qno];
+
+	queue->front++;
+	if (unlikely(queue->front == pqinfo->qlen))
+		queue->front = 0;
+}
+
+static int setup_sgio_components(struct cpt_vf *cptvf, struct buf_ptr *list,
+				 int buf_count, u8 *buffer)
+{
+	int ret = 0, i, j;
+	int components;
+	struct sglist_component *sg_ptr = NULL;
+	struct pci_dev *pdev = cptvf->pdev;
+
+	if (unlikely(!list)) {
+		dev_err(&pdev->dev, "Input List pointer is NULL\n");
+		return -EFAULT;
+	}
+
+	for (i = 0; i < buf_count; i++) {
+		if (likely(list[i].vptr)) {
+			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 map kernel buffer failed for component: %d\n",
+					i);
+				ret = -EIO;
+				goto sg_cleanup;
+			}
+		}
+	}
+
+	components = buf_count / 4;
+	sg_ptr = (struct sglist_component *)buffer;
+	for (i = 0; i < components; i++) {
+		sg_ptr->u.s.len0 = cpu_to_be16(list[i * 4 + 0].size);
+		sg_ptr->u.s.len1 = cpu_to_be16(list[i * 4 + 1].size);
+		sg_ptr->u.s.len2 = cpu_to_be16(list[i * 4 + 2].size);
+		sg_ptr->u.s.len3 = cpu_to_be16(list[i * 4 + 3].size);
+		sg_ptr->ptr0 = cpu_to_be64(list[i * 4 + 0].dma_addr);
+		sg_ptr->ptr1 = cpu_to_be64(list[i * 4 + 1].dma_addr);
+		sg_ptr->ptr2 = cpu_to_be64(list[i * 4 + 2].dma_addr);
+		sg_ptr->ptr3 = cpu_to_be64(list[i * 4 + 3].dma_addr);
+		sg_ptr++;
+	}
+
+	components = buf_count % 4;
+
+	switch (components) {
+	case 3:
+		sg_ptr->u.s.len2 = cpu_to_be16(list[i * 4 + 2].size);
+		sg_ptr->ptr2 = cpu_to_be64(list[i * 4 + 2].dma_addr);
+		fallthrough;
+	case 2:
+		sg_ptr->u.s.len1 = cpu_to_be16(list[i * 4 + 1].size);
+		sg_ptr->ptr1 = cpu_to_be64(list[i * 4 + 1].dma_addr);
+		fallthrough;
+	case 1:
+		sg_ptr->u.s.len0 = cpu_to_be16(list[i * 4 + 0].size);
+		sg_ptr->ptr0 = cpu_to_be64(list[i * 4 + 0].dma_addr);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+
+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 ret;
+}
+
+static inline int setup_sgio_list(struct cpt_vf *cptvf,
+				  struct cpt_info_buffer *info,
+				  struct cpt_request_info *req)
+{
+	u16 g_sz_bytes = 0, s_sz_bytes = 0;
+	int ret = 0;
+	struct pci_dev *pdev = cptvf->pdev;
+
+	if (req->incnt > MAX_SG_IN_CNT || req->outcnt > MAX_SG_OUT_CNT) {
+		dev_err(&pdev->dev, "Request SG components are higher than supported\n");
+		ret = -EINVAL;
+		goto  scatter_gather_clean;
+	}
+
+	/* Setup gather (input) components */
+	g_sz_bytes = ((req->incnt + 3) / 4) * sizeof(struct sglist_component);
+	info->gather_components = kzalloc(g_sz_bytes, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC);
+	if (!info->gather_components) {
+		ret = -ENOMEM;
+		goto  scatter_gather_clean;
+	}
+
+	ret = setup_sgio_components(cptvf, req->in,
+				    req->incnt,
+				    info->gather_components);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to setup gather list\n");
+		ret = -EFAULT;
+		goto  scatter_gather_clean;
+	}
+
+	/* Setup scatter (output) components */
+	s_sz_bytes = ((req->outcnt + 3) / 4) * sizeof(struct sglist_component);
+	info->scatter_components = kzalloc(s_sz_bytes, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC);
+	if (!info->scatter_components) {
+		ret = -ENOMEM;
+		goto  scatter_gather_clean;
+	}
+
+	ret = setup_sgio_components(cptvf, req->out,
+				    req->outcnt,
+				    info->scatter_components);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to setup gather list\n");
+		ret = -EFAULT;
+		goto  scatter_gather_clean;
+	}
+
+	/* Create and initialize DPTR */
+	info->dlen = g_sz_bytes + s_sz_bytes + SG_LIST_HDR_SIZE;
+	info->in_buffer = kzalloc(info->dlen, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC);
+	if (!info->in_buffer) {
+		ret = -ENOMEM;
+		goto  scatter_gather_clean;
+	}
+
+	((__be16 *)info->in_buffer)[0] = cpu_to_be16(req->outcnt);
+	((__be16 *)info->in_buffer)[1] = cpu_to_be16(req->incnt);
+	((__be16 *)info->in_buffer)[2] = 0;
+	((__be16 *)info->in_buffer)[3] = 0;
+
+	memcpy(&info->in_buffer[8], info->gather_components,
+	       g_sz_bytes);
+	memcpy(&info->in_buffer[8 + g_sz_bytes],
+	       info->scatter_components, s_sz_bytes);
+
+	info->dptr_baddr = dma_map_single(&pdev->dev,
+					  (void *)info->in_buffer,
+					  info->dlen,
+					  DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(&pdev->dev, info->dptr_baddr)) {
+		dev_err(&pdev->dev, "Mapping DPTR Failed %d\n", info->dlen);
+		ret = -EIO;
+		goto  scatter_gather_clean;
+	}
+
+	/* Create and initialize RPTR */
+	info->out_buffer = kzalloc(COMPLETION_CODE_SIZE, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC);
+	if (!info->out_buffer) {
+		ret = -ENOMEM;
+		goto scatter_gather_clean;
+	}
+
+	*((u64 *)info->out_buffer) = ~((u64)COMPLETION_CODE_INIT);
+	info->alternate_caddr = (u64 *)info->out_buffer;
+	info->rptr_baddr = dma_map_single(&pdev->dev,
+					  (void *)info->out_buffer,
+					  COMPLETION_CODE_SIZE,
+					  DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(&pdev->dev, info->rptr_baddr)) {
+		dev_err(&pdev->dev, "Mapping RPTR Failed %d\n",
+			COMPLETION_CODE_SIZE);
+		ret = -EIO;
+		goto  scatter_gather_clean;
+	}
+
+	return 0;
+
+scatter_gather_clean:
+	return ret;
+}
+
+static int send_cpt_command(struct cpt_vf *cptvf, union cpt_inst_s *cmd,
+		     u32 qno)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+	struct command_qinfo *qinfo = NULL;
+	struct command_queue *queue;
+	struct command_chunk *chunk;
+	u8 *ent;
+	int ret = 0;
+
+	if (unlikely(qno >= cptvf->nr_queues)) {
+		dev_err(&pdev->dev, "Invalid queue (qno: %d, nr_queues: %d)\n",
+			qno, cptvf->nr_queues);
+		return -EINVAL;
+	}
+
+	qinfo = &cptvf->cqinfo;
+	queue = &qinfo->queue[qno];
+	/* lock command queue */
+	spin_lock(&queue->lock);
+	ent = &queue->qhead->head[queue->idx * qinfo->cmd_size];
+	memcpy(ent, (void *)cmd, qinfo->cmd_size);
+
+	if (++queue->idx >= queue->qhead->size / 64) {
+		hlist_for_each_entry(chunk, &queue->chead, nextchunk) {
+			if (chunk == queue->qhead) {
+				continue;
+			} else {
+				queue->qhead = chunk;
+				break;
+			}
+		}
+		queue->idx = 0;
+	}
+	/* make sure all memory stores are done before ringing doorbell */
+	smp_wmb();
+	cptvf_write_vq_doorbell(cptvf, 1);
+	/* unlock command queue */
+	spin_unlock(&queue->lock);
+
+	return ret;
+}
+
+static void do_request_cleanup(struct cpt_vf *cptvf,
+			struct cpt_info_buffer *info)
+{
+	int i;
+	struct pci_dev *pdev = cptvf->pdev;
+	struct cpt_request_info *req;
+
+	if (info->dptr_baddr)
+		dma_unmap_single(&pdev->dev, info->dptr_baddr,
+				 info->dlen, DMA_BIDIRECTIONAL);
+
+	if (info->rptr_baddr)
+		dma_unmap_single(&pdev->dev, info->rptr_baddr,
+				 COMPLETION_CODE_SIZE, DMA_BIDIRECTIONAL);
+
+	if (info->comp_baddr)
+		dma_unmap_single(&pdev->dev, info->comp_baddr,
+				 sizeof(union cpt_res_s), DMA_BIDIRECTIONAL);
+
+	if (info->req) {
+		req = info->req;
+		for (i = 0; i < req->outcnt; 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->incnt; i++) {
+			if (req->in[i].dma_addr)
+				dma_unmap_single(&pdev->dev,
+						 req->in[i].dma_addr,
+						 req->in[i].size,
+						 DMA_BIDIRECTIONAL);
+		}
+	}
+
+	kfree_sensitive(info->scatter_components);
+	kfree_sensitive(info->gather_components);
+	kfree_sensitive(info->out_buffer);
+	kfree_sensitive(info->in_buffer);
+	kfree_sensitive((void *)info->completion_addr);
+	kfree_sensitive(info);
+}
+
+static void do_post_process(struct cpt_vf *cptvf, struct cpt_info_buffer *info)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+
+	if (!info) {
+		dev_err(&pdev->dev, "incorrect cpt_info_buffer for post processing\n");
+		return;
+	}
+
+	do_request_cleanup(cptvf, info);
+}
+
+static inline void process_pending_queue(struct cpt_vf *cptvf,
+					 struct pending_qinfo *pqinfo,
+					 int qno)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+	struct pending_queue *pqueue = &pqinfo->queue[qno];
+	struct pending_entry *pentry = NULL;
+	struct cpt_info_buffer *info = NULL;
+	union cpt_res_s *status = NULL;
+	unsigned char ccode;
+
+	while (1) {
+		spin_lock_bh(&pqueue->lock);
+		pentry = &pqueue->head[pqueue->front];
+		if (unlikely(!pentry->busy)) {
+			spin_unlock_bh(&pqueue->lock);
+			break;
+		}
+
+		info = (struct cpt_info_buffer *)pentry->post_arg;
+		if (unlikely(!info)) {
+			dev_err(&pdev->dev, "Pending Entry post arg NULL\n");
+			pending_queue_inc_front(pqinfo, qno);
+			spin_unlock_bh(&pqueue->lock);
+			continue;
+		}
+
+		status = (union cpt_res_s *)pentry->completion_addr;
+		ccode = status->s.compcode;
+		if ((status->s.compcode == CPT_COMP_E_FAULT) ||
+		    (status->s.compcode == CPT_COMP_E_SWERR)) {
+			dev_err(&pdev->dev, "Request failed with %s\n",
+				(status->s.compcode == CPT_COMP_E_FAULT) ?
+				"DMA Fault" : "Software error");
+			pentry->completion_addr = NULL;
+			pentry->busy = false;
+			atomic64_dec((&pqueue->pending_count));
+			pentry->post_arg = NULL;
+			pending_queue_inc_front(pqinfo, qno);
+			do_request_cleanup(cptvf, info);
+			spin_unlock_bh(&pqueue->lock);
+			break;
+		} else if (status->s.compcode == COMPLETION_CODE_INIT) {
+			/* check for timeout */
+			if (time_after_eq(jiffies,
+					  (info->time_in +
+					  (CPT_COMMAND_TIMEOUT * HZ)))) {
+				dev_err(&pdev->dev, "Request timed out");
+				pentry->completion_addr = NULL;
+				pentry->busy = false;
+				atomic64_dec((&pqueue->pending_count));
+				pentry->post_arg = NULL;
+				pending_queue_inc_front(pqinfo, qno);
+				do_request_cleanup(cptvf, info);
+				spin_unlock_bh(&pqueue->lock);
+				break;
+			} else if ((*info->alternate_caddr ==
+				(~COMPLETION_CODE_INIT)) &&
+				(info->extra_time < TIME_IN_RESET_COUNT)) {
+				info->time_in = jiffies;
+				info->extra_time++;
+				spin_unlock_bh(&pqueue->lock);
+				break;
+			}
+		}
+
+		pentry->completion_addr = NULL;
+		pentry->busy = false;
+		pentry->post_arg = NULL;
+		atomic64_dec((&pqueue->pending_count));
+		pending_queue_inc_front(pqinfo, qno);
+		spin_unlock_bh(&pqueue->lock);
+
+		do_post_process(info->cptvf, info);
+		/*
+		 * Calling callback after we find
+		 * that the request has been serviced
+		 */
+		pentry->callback(ccode, pentry->callback_arg);
+	}
+}
+
+int process_request(struct cpt_vf *cptvf, struct cpt_request_info *req)
+{
+	int ret = 0, clear = 0, queue = 0;
+	struct cpt_info_buffer *info = NULL;
+	struct cptvf_request *cpt_req = NULL;
+	union ctrl_info *ctrl = NULL;
+	union cpt_res_s *result = NULL;
+	struct pending_entry *pentry = NULL;
+	struct pending_queue *pqueue = NULL;
+	struct pci_dev *pdev = cptvf->pdev;
+	u8 group = 0;
+	struct cpt_vq_command vq_cmd;
+	union cpt_inst_s cptinst;
+
+	info = kzalloc_obj(*info, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC);
+	if (unlikely(!info)) {
+		dev_err(&pdev->dev, "Unable to allocate memory for info_buffer\n");
+		return -ENOMEM;
+	}
+
+	cpt_req = (struct cptvf_request *)&req->req;
+	ctrl = (union ctrl_info *)&req->ctrl;
+
+	info->cptvf = cptvf;
+	group = ctrl->s.grp;
+	ret = setup_sgio_list(cptvf, info, req);
+	if (ret) {
+		dev_err(&pdev->dev, "Setting up SG list failed");
+		goto request_cleanup;
+	}
+
+	cpt_req->dlen = info->dlen;
+	/*
+	 * Get buffer for union cpt_res_s response
+	 * structure and its physical address
+	 */
+	info->completion_addr = kzalloc(sizeof(union cpt_res_s), req->may_sleep ? GFP_KERNEL : GFP_ATOMIC);
+	if (unlikely(!info->completion_addr)) {
+		dev_err(&pdev->dev, "Unable to allocate memory for completion_addr\n");
+		ret = -ENOMEM;
+		goto request_cleanup;
+	}
+
+	result = (union cpt_res_s *)info->completion_addr;
+	result->s.compcode = COMPLETION_CODE_INIT;
+	info->comp_baddr = dma_map_single(&pdev->dev,
+					       (void *)info->completion_addr,
+					       sizeof(union cpt_res_s),
+					       DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(&pdev->dev, info->comp_baddr)) {
+		dev_err(&pdev->dev, "mapping compptr Failed %lu\n",
+			sizeof(union cpt_res_s));
+		ret = -EFAULT;
+		goto  request_cleanup;
+	}
+
+	/* Fill the VQ command */
+	vq_cmd.cmd.u64 = 0;
+	vq_cmd.cmd.s.opcode = cpu_to_be16(cpt_req->opcode.flags);
+	vq_cmd.cmd.s.param1 = cpu_to_be16(cpt_req->param1);
+	vq_cmd.cmd.s.param2 = cpu_to_be16(cpt_req->param2);
+	vq_cmd.cmd.s.dlen   = cpu_to_be16(cpt_req->dlen);
+
+	vq_cmd.dptr = info->dptr_baddr;
+	vq_cmd.rptr = info->rptr_baddr;
+	vq_cmd.cptr.u64 = 0;
+	vq_cmd.cptr.s.grp = group;
+	/* Get Pending Entry to submit command */
+	/* Always queue 0, because 1 queue per VF */
+	queue = 0;
+	pqueue = &cptvf->pqinfo.queue[queue];
+
+	if (atomic64_read(&pqueue->pending_count) > PENDING_THOLD) {
+		dev_err(&pdev->dev, "pending threshold reached\n");
+		process_pending_queue(cptvf, &cptvf->pqinfo, queue);
+	}
+
+get_pending_entry:
+	spin_lock_bh(&pqueue->lock);
+	pentry = get_free_pending_entry(pqueue, cptvf->pqinfo.qlen);
+	if (unlikely(!pentry)) {
+		spin_unlock_bh(&pqueue->lock);
+		if (clear == 0) {
+			process_pending_queue(cptvf, &cptvf->pqinfo, queue);
+			clear = 1;
+			goto get_pending_entry;
+		}
+		dev_err(&pdev->dev, "Get free entry failed\n");
+		dev_err(&pdev->dev, "queue: %d, rear: %d, front: %d\n",
+			queue, pqueue->rear, pqueue->front);
+		ret = -EFAULT;
+		goto request_cleanup;
+	}
+
+	pentry->completion_addr = info->completion_addr;
+	pentry->post_arg = (void *)info;
+	pentry->callback = req->callback;
+	pentry->callback_arg = req->callback_arg;
+	info->pentry = pentry;
+	pentry->busy = true;
+	atomic64_inc(&pqueue->pending_count);
+
+	/* Send CPT command */
+	info->pentry = pentry;
+	info->time_in = jiffies;
+	info->req = req;
+
+	/* Create the CPT_INST_S type command for HW interpretation */
+	cptinst.s.doneint = true;
+	cptinst.s.res_addr = (u64)info->comp_baddr;
+	cptinst.s.tag = 0;
+	cptinst.s.grp = 0;
+	cptinst.s.wq_ptr = 0;
+	cptinst.s.ei0 = vq_cmd.cmd.u64;
+	cptinst.s.ei1 = vq_cmd.dptr;
+	cptinst.s.ei2 = vq_cmd.rptr;
+	cptinst.s.ei3 = vq_cmd.cptr.u64;
+
+	ret = send_cpt_command(cptvf, &cptinst, queue);
+	spin_unlock_bh(&pqueue->lock);
+	if (unlikely(ret)) {
+		dev_err(&pdev->dev, "Send command failed for AE\n");
+		ret = -EFAULT;
+		goto request_cleanup;
+	}
+
+	return 0;
+
+request_cleanup:
+	dev_dbg(&pdev->dev, "Failed to submit CPT command\n");
+	do_request_cleanup(cptvf, info);
+
+	return ret;
+}
+
+void vq_post_process(struct cpt_vf *cptvf, u32 qno)
+{
+	struct pci_dev *pdev = cptvf->pdev;
+
+	if (unlikely(qno > cptvf->nr_queues)) {
+		dev_err(&pdev->dev, "Request for post processing on invalid pending queue: %u\n",
+			qno);
+		return;
+	}
+
+	process_pending_queue(cptvf, &cptvf->pqinfo, qno);
+}
+
+int cptvf_do_request(void *vfdev, struct cpt_request_info *req)
+{
+	struct cpt_vf *cptvf = (struct cpt_vf *)vfdev;
+	struct pci_dev *pdev = cptvf->pdev;
+
+	if (!cpt_device_ready(cptvf)) {
+		dev_err(&pdev->dev, "CPT Device is not ready");
+		return -ENODEV;
+	}
+
+	if ((cptvf->vftype == SE_TYPES) && (!req->ctrl.s.se_req)) {
+		dev_err(&pdev->dev, "CPTVF-%d of SE TYPE got AE request",
+			cptvf->vfid);
+		return -EINVAL;
+	} else if ((cptvf->vftype == AE_TYPES) && (req->ctrl.s.se_req)) {
+		dev_err(&pdev->dev, "CPTVF-%d of AE TYPE got SE request",
+			cptvf->vfid);
+		return -EINVAL;
+	}
+
+	return process_request(cptvf, req);
+}
diff --git a/drivers/crypto/cavium/cpt/request_manager.h b/drivers/crypto/cavium/cpt/request_manager.h
new file mode 100644
index 000000000..8d40e4ba3
--- /dev/null
+++ b/drivers/crypto/cavium/cpt/request_manager.h
@@ -0,0 +1,146 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2016 Cavium, Inc.
+ */
+
+#ifndef __REQUEST_MANAGER_H
+#define __REQUEST_MANAGER_H
+
+#include "cpt_common.h"
+
+#define TIME_IN_RESET_COUNT  5
+#define COMPLETION_CODE_SIZE 8
+#define COMPLETION_CODE_INIT 0
+#define PENDING_THOLD  100
+#define MAX_SG_IN_CNT 12
+#define MAX_SG_OUT_CNT 13
+#define SG_LIST_HDR_SIZE  8
+#define MAX_BUF_CNT	16
+
+union ctrl_info {
+	u32 flags;
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u32 reserved0:26;
+		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 reserved0:26;
+#endif
+	} s;
+};
+
+union opcode_info {
+	u16 flags;
+	struct {
+		u8 major;
+		u8 minor;
+	} s;
+};
+
+struct cptvf_request {
+	union opcode_info opcode;
+	u16 param1;
+	u16 param2;
+	u16 dlen;
+};
+
+struct buf_ptr {
+	u8 *vptr;
+	dma_addr_t dma_addr;
+	u16 size;
+};
+
+struct cpt_request_info {
+	u8 incnt; /* Number of input buffers */
+	u8 outcnt; /* Number of output buffers */
+	u16 rlen; /* Output length */
+	union ctrl_info ctrl; /* User control information */
+	struct cptvf_request req; /* Request Information (Core specific) */
+
+	bool may_sleep;
+
+	struct buf_ptr in[MAX_BUF_CNT];
+	struct buf_ptr out[MAX_BUF_CNT];
+
+	void (*callback)(int, void *); /* Kernel ASYNC request callabck */
+	void *callback_arg; /* Kernel ASYNC request callabck arg */
+};
+
+struct sglist_component {
+	union {
+		u64 len;
+		struct {
+			__be16 len0;
+			__be16 len1;
+			__be16 len2;
+			__be16 len3;
+		} s;
+	} u;
+	__be64 ptr0;
+	__be64 ptr1;
+	__be64 ptr2;
+	__be64 ptr3;
+};
+
+struct cpt_info_buffer {
+	struct cpt_vf *cptvf;
+	unsigned long time_in;
+	u8 extra_time;
+
+	struct cpt_request_info *req;
+	dma_addr_t dptr_baddr;
+	u32 dlen;
+	dma_addr_t rptr_baddr;
+	dma_addr_t comp_baddr;
+	u8 *in_buffer;
+	u8 *out_buffer;
+	u8 *gather_components;
+	u8 *scatter_components;
+
+	struct pending_entry *pentry;
+	volatile u64 *completion_addr;
+	volatile u64 *alternate_caddr;
+};
+
+/*
+ * CPT_INST_S software command definitions
+ * Words EI (0-3)
+ */
+union vq_cmd_word0 {
+	u64 u64;
+	struct {
+		__be16 opcode;
+		__be16 param1;
+		__be16 param2;
+		__be16 dlen;
+	} s;
+};
+
+union vq_cmd_word3 {
+	u64 u64;
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 grp:3;
+		u64 cptr:61;
+#else
+		u64 cptr:61;
+		u64 grp:3;
+#endif
+	} s;
+};
+
+struct cpt_vq_command {
+	union vq_cmd_word0 cmd;
+	u64 dptr;
+	u64 rptr;
+	union vq_cmd_word3 cptr;
+};
+
+void vq_post_process(struct cpt_vf *cptvf, u32 qno);
+int process_request(struct cpt_vf *cptvf, struct cpt_request_info *req);
+#endif /* __REQUEST_MANAGER_H */
diff --git a/drivers/crypto/cavium/nitrox/Kconfig b/drivers/crypto/cavium/nitrox/Kconfig
new file mode 100644
index 000000000..7dc008332
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/Kconfig
@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Cavium NITROX Crypto Device configuration
+#
+config CRYPTO_DEV_NITROX
+	tristate
+	select CRYPTO_SKCIPHER
+	select CRYPTO_AES
+	select CRYPTO_LIB_DES
+	select FW_LOADER
+
+config CRYPTO_DEV_NITROX_CNN55XX
+	tristate "Support for Cavium CNN55XX driver"
+	depends on PCI_MSI && 64BIT
+	select CRYPTO_DEV_NITROX
+	help
+	  Support for Cavium NITROX family CNN55XX driver
+	  for accelerating crypto workloads.
+
+	  To compile this as a module, choose M here: the module
+	  will be called n5pf.
diff --git a/drivers/crypto/cavium/nitrox/Makefile b/drivers/crypto/cavium/nitrox/Makefile
new file mode 100644
index 000000000..f83991aaf
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/Makefile
@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_CRYPTO_DEV_NITROX_CNN55XX) += n5pf.o
+
+n5pf-objs := nitrox_main.o \
+	nitrox_isr.o \
+	nitrox_lib.o \
+	nitrox_hal.o \
+	nitrox_reqmgr.o \
+	nitrox_algs.o	\
+	nitrox_mbx.o	\
+	nitrox_skcipher.o \
+	nitrox_aead.o
+
+n5pf-$(CONFIG_PCI_IOV) += nitrox_sriov.o
+n5pf-$(CONFIG_DEBUG_FS) += nitrox_debugfs.o
diff --git a/drivers/crypto/cavium/nitrox/nitrox_aead.c b/drivers/crypto/cavium/nitrox/nitrox_aead.c
new file mode 100644
index 000000000..b0e530341
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/nitrox_aead.c
@@ -0,0 +1,567 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/printk.h>
+#include <linux/crypto.h>
+#include <linux/rtnetlink.h>
+
+#include <crypto/aead.h>
+#include <crypto/authenc.h>
+#include <crypto/des.h>
+#include <crypto/internal/aead.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/gcm.h>
+
+#include "nitrox_dev.h"
+#include "nitrox_common.h"
+#include "nitrox_req.h"
+
+#define GCM_AES_SALT_SIZE	4
+
+union gph_p3 {
+	struct {
+#ifdef __BIG_ENDIAN_BITFIELD
+		u16 iv_offset : 8;
+		u16 auth_offset	: 8;
+#else
+		u16 auth_offset	: 8;
+		u16 iv_offset : 8;
+#endif
+	};
+	u16 param;
+};
+
+static int nitrox_aes_gcm_setkey(struct crypto_aead *aead, const u8 *key,
+				 unsigned int keylen)
+{
+	int aes_keylen;
+	struct nitrox_crypto_ctx *nctx = crypto_aead_ctx(aead);
+	struct flexi_crypto_context *fctx;
+	union fc_ctx_flags flags;
+
+	aes_keylen = flexi_aes_keylen(keylen);
+	if (aes_keylen < 0)
+		return -EINVAL;
+
+	/* fill crypto context */
+	fctx = nctx->u.fctx;
+	flags.fu = be64_to_cpu(fctx->flags.f);
+	flags.w0.aes_keylen = aes_keylen;
+	fctx->flags.f = cpu_to_be64(flags.fu);
+
+	/* copy enc key to context */
+	memset(&fctx->crypto, 0, sizeof(fctx->crypto));
+	memcpy(fctx->crypto.u.key, key, keylen);
+
+	return 0;
+}
+
+static int nitrox_aead_setauthsize(struct crypto_aead *aead,
+				   unsigned int authsize)
+{
+	struct nitrox_crypto_ctx *nctx = crypto_aead_ctx(aead);
+	struct flexi_crypto_context *fctx = nctx->u.fctx;
+	union fc_ctx_flags flags;
+
+	flags.fu = be64_to_cpu(fctx->flags.f);
+	flags.w0.mac_len = authsize;
+	fctx->flags.f = cpu_to_be64(flags.fu);
+
+	aead->authsize = authsize;
+
+	return 0;
+}
+
+static int nitrox_aes_gcm_setauthsize(struct crypto_aead *aead,
+				      unsigned int authsize)
+{
+	switch (authsize) {
+	case 4:
+	case 8:
+	case 12:
+	case 13:
+	case 14:
+	case 15:
+	case 16:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return nitrox_aead_setauthsize(aead, authsize);
+}
+
+static int alloc_src_sglist(struct nitrox_kcrypt_request *nkreq,
+			    struct scatterlist *src, char *iv, int ivsize,
+			    int buflen)
+{
+	int nents = sg_nents_for_len(src, buflen);
+	int ret;
+
+	if (nents < 0)
+		return nents;
+
+	/* IV entry */
+	nents += 1;
+	/* Allocate buffer to hold IV and input scatterlist array */
+	ret = alloc_src_req_buf(nkreq, nents, ivsize);
+	if (ret)
+		return ret;
+
+	nitrox_creq_copy_iv(nkreq->src, iv, ivsize);
+	nitrox_creq_set_src_sg(nkreq, nents, ivsize, src, buflen);
+
+	return 0;
+}
+
+static int alloc_dst_sglist(struct nitrox_kcrypt_request *nkreq,
+			    struct scatterlist *dst, int ivsize, int buflen)
+{
+	int nents = sg_nents_for_len(dst, buflen);
+	int ret;
+
+	if (nents < 0)
+		return nents;
+
+	/* IV, ORH, COMPLETION entries */
+	nents += 3;
+	/* Allocate buffer to hold ORH, COMPLETION and output scatterlist
+	 * array
+	 */
+	ret = alloc_dst_req_buf(nkreq, nents);
+	if (ret)
+		return ret;
+
+	nitrox_creq_set_orh(nkreq);
+	nitrox_creq_set_comp(nkreq);
+	nitrox_creq_set_dst_sg(nkreq, nents, ivsize, dst, buflen);
+
+	return 0;
+}
+
+static void free_src_sglist(struct nitrox_kcrypt_request *nkreq)
+{
+	kfree(nkreq->src);
+}
+
+static void free_dst_sglist(struct nitrox_kcrypt_request *nkreq)
+{
+	kfree(nkreq->dst);
+}
+
+static int nitrox_set_creq(struct nitrox_aead_rctx *rctx)
+{
+	struct se_crypto_request *creq = &rctx->nkreq.creq;
+	union gph_p3 param3;
+	int ret;
+
+	creq->flags = rctx->flags;
+	creq->gfp = (rctx->flags & CRYPTO_TFM_REQ_MAY_SLEEP) ? GFP_KERNEL :
+							       GFP_ATOMIC;
+
+	creq->ctrl.value = 0;
+	creq->opcode = FLEXI_CRYPTO_ENCRYPT_HMAC;
+	creq->ctrl.s.arg = rctx->ctrl_arg;
+
+	creq->gph.param0 = cpu_to_be16(rctx->cryptlen);
+	creq->gph.param1 = cpu_to_be16(rctx->cryptlen + rctx->assoclen);
+	creq->gph.param2 = cpu_to_be16(rctx->ivsize + rctx->assoclen);
+	param3.iv_offset = 0;
+	param3.auth_offset = rctx->ivsize;
+	creq->gph.param3 = cpu_to_be16(param3.param);
+
+	creq->ctx_handle = rctx->ctx_handle;
+	creq->ctrl.s.ctxl = sizeof(struct flexi_crypto_context);
+
+	ret = alloc_src_sglist(&rctx->nkreq, rctx->src, rctx->iv, rctx->ivsize,
+			       rctx->srclen);
+	if (ret)
+		return ret;
+
+	ret = alloc_dst_sglist(&rctx->nkreq, rctx->dst, rctx->ivsize,
+			       rctx->dstlen);
+	if (ret) {
+		free_src_sglist(&rctx->nkreq);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void nitrox_aead_callback(void *arg, int err)
+{
+	struct aead_request *areq = arg;
+	struct nitrox_aead_rctx *rctx = aead_request_ctx(areq);
+
+	free_src_sglist(&rctx->nkreq);
+	free_dst_sglist(&rctx->nkreq);
+	if (err) {
+		pr_err_ratelimited("request failed status 0x%0x\n", err);
+		err = -EINVAL;
+	}
+
+	aead_request_complete(areq, err);
+}
+
+static inline bool nitrox_aes_gcm_assoclen_supported(unsigned int assoclen)
+{
+	if (assoclen <= 512)
+		return true;
+
+	return false;
+}
+
+static int nitrox_aes_gcm_enc(struct aead_request *areq)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(areq);
+	struct nitrox_crypto_ctx *nctx = crypto_aead_ctx(aead);
+	struct nitrox_aead_rctx *rctx = aead_request_ctx(areq);
+	struct se_crypto_request *creq = &rctx->nkreq.creq;
+	struct flexi_crypto_context *fctx = nctx->u.fctx;
+	int ret;
+
+	if (!nitrox_aes_gcm_assoclen_supported(areq->assoclen))
+		return -EINVAL;
+
+	memcpy(fctx->crypto.iv, areq->iv, GCM_AES_SALT_SIZE);
+
+	rctx->cryptlen = areq->cryptlen;
+	rctx->assoclen = areq->assoclen;
+	rctx->srclen = areq->assoclen + areq->cryptlen;
+	rctx->dstlen = rctx->srclen + aead->authsize;
+	rctx->iv = &areq->iv[GCM_AES_SALT_SIZE];
+	rctx->ivsize = GCM_AES_IV_SIZE - GCM_AES_SALT_SIZE;
+	rctx->flags = areq->base.flags;
+	rctx->ctx_handle = nctx->u.ctx_handle;
+	rctx->src = areq->src;
+	rctx->dst = areq->dst;
+	rctx->ctrl_arg = ENCRYPT;
+	ret = nitrox_set_creq(rctx);
+	if (ret)
+		return ret;
+
+	/* send the crypto request */
+	return nitrox_process_se_request(nctx->ndev, creq, nitrox_aead_callback,
+					 areq);
+}
+
+static int nitrox_aes_gcm_dec(struct aead_request *areq)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(areq);
+	struct nitrox_crypto_ctx *nctx = crypto_aead_ctx(aead);
+	struct nitrox_aead_rctx *rctx = aead_request_ctx(areq);
+	struct se_crypto_request *creq = &rctx->nkreq.creq;
+	struct flexi_crypto_context *fctx = nctx->u.fctx;
+	int ret;
+
+	if (!nitrox_aes_gcm_assoclen_supported(areq->assoclen))
+		return -EINVAL;
+
+	memcpy(fctx->crypto.iv, areq->iv, GCM_AES_SALT_SIZE);
+
+	rctx->cryptlen = areq->cryptlen - aead->authsize;
+	rctx->assoclen = areq->assoclen;
+	rctx->srclen = areq->cryptlen + areq->assoclen;
+	rctx->dstlen = rctx->srclen - aead->authsize;
+	rctx->iv = &areq->iv[GCM_AES_SALT_SIZE];
+	rctx->ivsize = GCM_AES_IV_SIZE - GCM_AES_SALT_SIZE;
+	rctx->flags = areq->base.flags;
+	rctx->ctx_handle = nctx->u.ctx_handle;
+	rctx->src = areq->src;
+	rctx->dst = areq->dst;
+	rctx->ctrl_arg = DECRYPT;
+	ret = nitrox_set_creq(rctx);
+	if (ret)
+		return ret;
+
+	/* send the crypto request */
+	return nitrox_process_se_request(nctx->ndev, creq, nitrox_aead_callback,
+					 areq);
+}
+
+static int nitrox_aead_init(struct crypto_aead *aead)
+{
+	struct nitrox_crypto_ctx *nctx = crypto_aead_ctx(aead);
+	struct crypto_ctx_hdr *chdr;
+
+	/* get the first device */
+	nctx->ndev = nitrox_get_first_device();
+	if (!nctx->ndev)
+		return -ENODEV;
+
+	/* allocate nitrox crypto context */
+	chdr = crypto_alloc_context(nctx->ndev);
+	if (!chdr) {
+		nitrox_put_device(nctx->ndev);
+		return -ENOMEM;
+	}
+	nctx->chdr = chdr;
+	nctx->u.ctx_handle = (uintptr_t)((u8 *)chdr->vaddr +
+					 sizeof(struct ctx_hdr));
+	nctx->u.fctx->flags.f = 0;
+
+	return 0;
+}
+
+static int nitrox_gcm_common_init(struct crypto_aead *aead)
+{
+	int ret;
+	struct nitrox_crypto_ctx *nctx = crypto_aead_ctx(aead);
+	union fc_ctx_flags *flags;
+
+	ret = nitrox_aead_init(aead);
+	if (ret)
+		return ret;
+
+	flags = &nctx->u.fctx->flags;
+	flags->w0.cipher_type = CIPHER_AES_GCM;
+	flags->w0.hash_type = AUTH_NULL;
+	flags->w0.iv_source = IV_FROM_DPTR;
+	/* ask microcode to calculate ipad/opad */
+	flags->w0.auth_input_type = 1;
+	flags->f = cpu_to_be64(flags->fu);
+
+	return 0;
+}
+
+static int nitrox_aes_gcm_init(struct crypto_aead *aead)
+{
+	int ret;
+
+	ret = nitrox_gcm_common_init(aead);
+	if (ret)
+		return ret;
+
+	crypto_aead_set_reqsize(aead,
+				sizeof(struct aead_request) +
+					sizeof(struct nitrox_aead_rctx));
+
+	return 0;
+}
+
+static void nitrox_aead_exit(struct crypto_aead *aead)
+{
+	struct nitrox_crypto_ctx *nctx = crypto_aead_ctx(aead);
+
+	/* free the nitrox crypto context */
+	if (nctx->u.ctx_handle) {
+		struct flexi_crypto_context *fctx = nctx->u.fctx;
+
+		memzero_explicit(&fctx->crypto, sizeof(struct crypto_keys));
+		memzero_explicit(&fctx->auth, sizeof(struct auth_keys));
+		crypto_free_context((void *)nctx->chdr);
+	}
+	nitrox_put_device(nctx->ndev);
+
+	nctx->u.ctx_handle = 0;
+	nctx->ndev = NULL;
+}
+
+static int nitrox_rfc4106_setkey(struct crypto_aead *aead, const u8 *key,
+				 unsigned int keylen)
+{
+	struct nitrox_crypto_ctx *nctx = crypto_aead_ctx(aead);
+	struct flexi_crypto_context *fctx = nctx->u.fctx;
+	int ret;
+
+	if (keylen < GCM_AES_SALT_SIZE)
+		return -EINVAL;
+
+	keylen -= GCM_AES_SALT_SIZE;
+	ret = nitrox_aes_gcm_setkey(aead, key, keylen);
+	if (ret)
+		return ret;
+
+	memcpy(fctx->crypto.iv, key + keylen, GCM_AES_SALT_SIZE);
+	return 0;
+}
+
+static int nitrox_rfc4106_setauthsize(struct crypto_aead *aead,
+				      unsigned int authsize)
+{
+	switch (authsize) {
+	case 8:
+	case 12:
+	case 16:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return nitrox_aead_setauthsize(aead, authsize);
+}
+
+static int nitrox_rfc4106_set_aead_rctx_sglist(struct aead_request *areq)
+{
+	struct nitrox_rfc4106_rctx *rctx = aead_request_ctx_dma(areq);
+	struct nitrox_aead_rctx *aead_rctx = &rctx->base;
+	unsigned int assoclen = areq->assoclen - GCM_RFC4106_IV_SIZE;
+	struct scatterlist *sg;
+
+	if (areq->assoclen != 16 && areq->assoclen != 20)
+		return -EINVAL;
+
+	scatterwalk_map_and_copy(rctx->assoc, areq->src, 0, assoclen, 0);
+	sg_init_table(rctx->src, 3);
+	sg_set_buf(rctx->src, rctx->assoc, assoclen);
+	sg = scatterwalk_ffwd(rctx->src + 1, areq->src, areq->assoclen);
+	if (sg != rctx->src + 1)
+		sg_chain(rctx->src, 2, sg);
+
+	if (areq->src != areq->dst) {
+		sg_init_table(rctx->dst, 3);
+		sg_set_buf(rctx->dst, rctx->assoc, assoclen);
+		sg = scatterwalk_ffwd(rctx->dst + 1, areq->dst, areq->assoclen);
+		if (sg != rctx->dst + 1)
+			sg_chain(rctx->dst, 2, sg);
+	}
+
+	aead_rctx->src = rctx->src;
+	aead_rctx->dst = (areq->src == areq->dst) ? rctx->src : rctx->dst;
+
+	return 0;
+}
+
+static void nitrox_rfc4106_callback(void *arg, int err)
+{
+	struct aead_request *areq = arg;
+	struct nitrox_rfc4106_rctx *rctx = aead_request_ctx_dma(areq);
+	struct nitrox_kcrypt_request *nkreq = &rctx->base.nkreq;
+
+	free_src_sglist(nkreq);
+	free_dst_sglist(nkreq);
+	if (err) {
+		pr_err_ratelimited("request failed status 0x%0x\n", err);
+		err = -EINVAL;
+	}
+
+	aead_request_complete(areq, err);
+}
+
+static int nitrox_rfc4106_enc(struct aead_request *areq)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(areq);
+	struct nitrox_crypto_ctx *nctx = crypto_aead_ctx(aead);
+	struct nitrox_rfc4106_rctx *rctx = aead_request_ctx_dma(areq);
+	struct nitrox_aead_rctx *aead_rctx = &rctx->base;
+	struct se_crypto_request *creq = &aead_rctx->nkreq.creq;
+	int ret;
+
+	aead_rctx->cryptlen = areq->cryptlen;
+	aead_rctx->assoclen = areq->assoclen - GCM_RFC4106_IV_SIZE;
+	aead_rctx->srclen = aead_rctx->assoclen + aead_rctx->cryptlen;
+	aead_rctx->dstlen = aead_rctx->srclen + aead->authsize;
+	aead_rctx->iv = areq->iv;
+	aead_rctx->ivsize = GCM_RFC4106_IV_SIZE;
+	aead_rctx->flags = areq->base.flags;
+	aead_rctx->ctx_handle = nctx->u.ctx_handle;
+	aead_rctx->ctrl_arg = ENCRYPT;
+
+	ret = nitrox_rfc4106_set_aead_rctx_sglist(areq);
+	if (ret)
+		return ret;
+
+	ret = nitrox_set_creq(aead_rctx);
+	if (ret)
+		return ret;
+
+	/* send the crypto request */
+	return nitrox_process_se_request(nctx->ndev, creq,
+					 nitrox_rfc4106_callback, areq);
+}
+
+static int nitrox_rfc4106_dec(struct aead_request *areq)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(areq);
+	struct nitrox_crypto_ctx *nctx = crypto_aead_ctx_dma(aead);
+	struct nitrox_rfc4106_rctx *rctx = aead_request_ctx(areq);
+	struct nitrox_aead_rctx *aead_rctx = &rctx->base;
+	struct se_crypto_request *creq = &aead_rctx->nkreq.creq;
+	int ret;
+
+	aead_rctx->cryptlen = areq->cryptlen - aead->authsize;
+	aead_rctx->assoclen = areq->assoclen - GCM_RFC4106_IV_SIZE;
+	aead_rctx->srclen =
+		areq->cryptlen - GCM_RFC4106_IV_SIZE + areq->assoclen;
+	aead_rctx->dstlen = aead_rctx->srclen - aead->authsize;
+	aead_rctx->iv = areq->iv;
+	aead_rctx->ivsize = GCM_RFC4106_IV_SIZE;
+	aead_rctx->flags = areq->base.flags;
+	aead_rctx->ctx_handle = nctx->u.ctx_handle;
+	aead_rctx->ctrl_arg = DECRYPT;
+
+	ret = nitrox_rfc4106_set_aead_rctx_sglist(areq);
+	if (ret)
+		return ret;
+
+	ret = nitrox_set_creq(aead_rctx);
+	if (ret)
+		return ret;
+
+	/* send the crypto request */
+	return nitrox_process_se_request(nctx->ndev, creq,
+					 nitrox_rfc4106_callback, areq);
+}
+
+static int nitrox_rfc4106_init(struct crypto_aead *aead)
+{
+	int ret;
+
+	ret = nitrox_gcm_common_init(aead);
+	if (ret)
+		return ret;
+
+	crypto_aead_set_reqsize_dma(aead, sizeof(struct aead_request) +
+					  sizeof(struct nitrox_rfc4106_rctx));
+
+	return 0;
+}
+
+static struct aead_alg nitrox_aeads[] = { {
+	.base = {
+		.cra_name = "gcm(aes)",
+		.cra_driver_name = "n5_aes_gcm",
+		.cra_priority = PRIO,
+		.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY,
+		.cra_blocksize = 1,
+		.cra_ctxsize = sizeof(struct nitrox_crypto_ctx),
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+	},
+	.setkey = nitrox_aes_gcm_setkey,
+	.setauthsize = nitrox_aes_gcm_setauthsize,
+	.encrypt = nitrox_aes_gcm_enc,
+	.decrypt = nitrox_aes_gcm_dec,
+	.init = nitrox_aes_gcm_init,
+	.exit = nitrox_aead_exit,
+	.ivsize = GCM_AES_IV_SIZE,
+	.maxauthsize = AES_BLOCK_SIZE,
+}, {
+	.base = {
+		.cra_name = "rfc4106(gcm(aes))",
+		.cra_driver_name = "n5_rfc4106",
+		.cra_priority = PRIO,
+		.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY,
+		.cra_blocksize = 1,
+		.cra_ctxsize = sizeof(struct nitrox_crypto_ctx),
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+	},
+	.setkey = nitrox_rfc4106_setkey,
+	.setauthsize = nitrox_rfc4106_setauthsize,
+	.encrypt = nitrox_rfc4106_enc,
+	.decrypt = nitrox_rfc4106_dec,
+	.init = nitrox_rfc4106_init,
+	.exit = nitrox_aead_exit,
+	.ivsize = GCM_RFC4106_IV_SIZE,
+	.maxauthsize = AES_BLOCK_SIZE,
+} };
+
+int nitrox_register_aeads(void)
+{
+	return crypto_register_aeads(nitrox_aeads, ARRAY_SIZE(nitrox_aeads));
+}
+
+void nitrox_unregister_aeads(void)
+{
+	crypto_unregister_aeads(nitrox_aeads, ARRAY_SIZE(nitrox_aeads));
+}
diff --git a/drivers/crypto/cavium/nitrox/nitrox_algs.c b/drivers/crypto/cavium/nitrox/nitrox_algs.c
new file mode 100644
index 000000000..d646ae5f2
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/nitrox_algs.c
@@ -0,0 +1,24 @@
+#include "nitrox_common.h"
+
+int nitrox_crypto_register(void)
+{
+	int err;
+
+	err = nitrox_register_skciphers();
+	if (err)
+		return err;
+
+	err = nitrox_register_aeads();
+	if (err) {
+		nitrox_unregister_skciphers();
+		return err;
+	}
+
+	return 0;
+}
+
+void nitrox_crypto_unregister(void)
+{
+	nitrox_unregister_aeads();
+	nitrox_unregister_skciphers();
+}
diff --git a/drivers/crypto/cavium/nitrox/nitrox_common.h b/drivers/crypto/cavium/nitrox/nitrox_common.h
new file mode 100644
index 000000000..e4be69d7e
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/nitrox_common.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NITROX_COMMON_H
+#define __NITROX_COMMON_H
+
+#include "nitrox_dev.h"
+#include "nitrox_req.h"
+
+int nitrox_crypto_register(void);
+void nitrox_crypto_unregister(void);
+int nitrox_register_aeads(void);
+void nitrox_unregister_aeads(void);
+int nitrox_register_skciphers(void);
+void nitrox_unregister_skciphers(void);
+void *crypto_alloc_context(struct nitrox_device *ndev);
+void crypto_free_context(void *ctx);
+struct nitrox_device *nitrox_get_first_device(void);
+void nitrox_put_device(struct nitrox_device *ndev);
+
+int nitrox_common_sw_init(struct nitrox_device *ndev);
+void nitrox_common_sw_cleanup(struct nitrox_device *ndev);
+
+void pkt_slc_resp_tasklet(unsigned long data);
+int nitrox_process_se_request(struct nitrox_device *ndev,
+			      struct se_crypto_request *req,
+			      completion_t cb,
+			      void *cb_arg);
+void backlog_qflush_work(struct work_struct *work);
+
+
+#endif /* __NITROX_COMMON_H */
diff --git a/drivers/crypto/cavium/nitrox/nitrox_csr.h b/drivers/crypto/cavium/nitrox/nitrox_csr.h
new file mode 100644
index 000000000..1c8715ae0
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/nitrox_csr.h
@@ -0,0 +1,1439 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NITROX_CSR_H
+#define __NITROX_CSR_H
+
+#include <asm/byteorder.h>
+#include <linux/types.h>
+
+/* EMU clusters */
+#define NR_CLUSTERS		4
+/* Maximum cores per cluster,
+ * varies based on partname
+ */
+#define AE_CORES_PER_CLUSTER	20
+#define SE_CORES_PER_CLUSTER	16
+
+#define AE_MAX_CORES	(AE_CORES_PER_CLUSTER * NR_CLUSTERS)
+#define SE_MAX_CORES	(SE_CORES_PER_CLUSTER * NR_CLUSTERS)
+#define ZIP_MAX_CORES	5
+
+/* BIST registers */
+#define EMU_BIST_STATUSX(_i)	(0x1402700 + ((_i) * 0x40000))
+#define UCD_BIST_STATUS		0x12C0070
+#define NPS_CORE_BIST_REG	0x10000E8
+#define NPS_CORE_NPC_BIST_REG	0x1000128
+#define NPS_PKT_SLC_BIST_REG	0x1040088
+#define NPS_PKT_IN_BIST_REG	0x1040100
+#define POM_BIST_REG		0x11C0100
+#define BMI_BIST_REG		0x1140080
+#define EFL_CORE_BIST_REGX(_i)	(0x1240100 + ((_i) * 0x400))
+#define EFL_TOP_BIST_STAT	0x1241090
+#define BMO_BIST_REG		0x1180080
+#define LBC_BIST_STATUS		0x1200020
+#define PEM_BIST_STATUSX(_i)	(0x1080468 | ((_i) << 18))
+
+/* EMU registers */
+#define EMU_SE_ENABLEX(_i)	(0x1400000 + ((_i) * 0x40000))
+#define EMU_AE_ENABLEX(_i)	(0x1400008 + ((_i) * 0x40000))
+#define EMU_WD_INT_ENA_W1SX(_i)	(0x1402318 + ((_i) * 0x40000))
+#define EMU_GE_INT_ENA_W1SX(_i)	(0x1402518 + ((_i) * 0x40000))
+#define EMU_FUSE_MAPX(_i)	(0x1402708 + ((_i) * 0x40000))
+
+/* UCD registers */
+#define UCD_SE_EID_UCODE_BLOCK_NUMX(_i)	(0x12C0000 + ((_i) * 0x1000))
+#define UCD_AE_EID_UCODE_BLOCK_NUMX(_i)	(0x12C0008 + ((_i) * 0x800))
+#define UCD_UCODE_LOAD_BLOCK_NUM	0x12C0010
+#define UCD_UCODE_LOAD_IDX_DATAX(_i)	(0x12C0018 + ((_i) * 0x20))
+#define UCD_SE_CNTX(_i)			(0x12C0040 + ((_i) * 0x1000))
+#define UCD_AE_CNTX(_i)			(0x12C0048 + ((_i) * 0x800))
+
+/* AQM registers */
+#define AQM_CTL                         0x1300000
+#define AQM_INT                         0x1300008
+#define AQM_DBELL_OVF_LO                0x1300010
+#define AQM_DBELL_OVF_HI                0x1300018
+#define AQM_DBELL_OVF_LO_W1S            0x1300020
+#define AQM_DBELL_OVF_LO_ENA_W1C        0x1300028
+#define AQM_DBELL_OVF_LO_ENA_W1S        0x1300030
+#define AQM_DBELL_OVF_HI_W1S            0x1300038
+#define AQM_DBELL_OVF_HI_ENA_W1C        0x1300040
+#define AQM_DBELL_OVF_HI_ENA_W1S        0x1300048
+#define AQM_DMA_RD_ERR_LO               0x1300050
+#define AQM_DMA_RD_ERR_HI               0x1300058
+#define AQM_DMA_RD_ERR_LO_W1S           0x1300060
+#define AQM_DMA_RD_ERR_LO_ENA_W1C       0x1300068
+#define AQM_DMA_RD_ERR_LO_ENA_W1S       0x1300070
+#define AQM_DMA_RD_ERR_HI_W1S           0x1300078
+#define AQM_DMA_RD_ERR_HI_ENA_W1C       0x1300080
+#define AQM_DMA_RD_ERR_HI_ENA_W1S       0x1300088
+#define AQM_EXEC_NA_LO                  0x1300090
+#define AQM_EXEC_NA_HI                  0x1300098
+#define AQM_EXEC_NA_LO_W1S              0x13000A0
+#define AQM_EXEC_NA_LO_ENA_W1C          0x13000A8
+#define AQM_EXEC_NA_LO_ENA_W1S          0x13000B0
+#define AQM_EXEC_NA_HI_W1S              0x13000B8
+#define AQM_EXEC_NA_HI_ENA_W1C          0x13000C0
+#define AQM_EXEC_NA_HI_ENA_W1S          0x13000C8
+#define AQM_EXEC_ERR_LO                 0x13000D0
+#define AQM_EXEC_ERR_HI                 0x13000D8
+#define AQM_EXEC_ERR_LO_W1S             0x13000E0
+#define AQM_EXEC_ERR_LO_ENA_W1C         0x13000E8
+#define AQM_EXEC_ERR_LO_ENA_W1S         0x13000F0
+#define AQM_EXEC_ERR_HI_W1S             0x13000F8
+#define AQM_EXEC_ERR_HI_ENA_W1C         0x1300100
+#define AQM_EXEC_ERR_HI_ENA_W1S         0x1300108
+#define AQM_ECC_INT                     0x1300110
+#define AQM_ECC_INT_W1S                 0x1300118
+#define AQM_ECC_INT_ENA_W1C             0x1300120
+#define AQM_ECC_INT_ENA_W1S             0x1300128
+#define AQM_ECC_CTL                     0x1300130
+#define AQM_BIST_STATUS                 0x1300138
+#define AQM_CMD_INF_THRX(x)             (0x1300400 + ((x) * 0x8))
+#define AQM_CMD_INFX(x)                 (0x1300800 + ((x) * 0x8))
+#define AQM_GRP_EXECMSK_LOX(x)          (0x1300C00 + ((x) * 0x10))
+#define AQM_GRP_EXECMSK_HIX(x)          (0x1300C08 + ((x) * 0x10))
+#define AQM_ACTIVITY_STAT_LO            0x1300C80
+#define AQM_ACTIVITY_STAT_HI            0x1300C88
+#define AQM_Q_CMD_PROCX(x)              (0x1301000 + ((x) * 0x8))
+#define AQM_PERF_CTL_LO                 0x1301400
+#define AQM_PERF_CTL_HI                 0x1301408
+#define AQM_PERF_CNT                    0x1301410
+
+#define AQMQ_DRBLX(x)                   (0x20000 + ((x) * 0x40000))
+#define AQMQ_QSZX(x)                    (0x20008 + ((x) * 0x40000))
+#define AQMQ_BADRX(x)                   (0x20010 + ((x) * 0x40000))
+#define AQMQ_NXT_CMDX(x)                (0x20018 + ((x) * 0x40000))
+#define AQMQ_CMD_CNTX(x)                (0x20020 + ((x) * 0x40000))
+#define AQMQ_CMP_THRX(x)                (0x20028 + ((x) * 0x40000))
+#define AQMQ_CMP_CNTX(x)                (0x20030 + ((x) * 0x40000))
+#define AQMQ_TIM_LDX(x)                 (0x20038 + ((x) * 0x40000))
+#define AQMQ_TIMERX(x)                  (0x20040 + ((x) * 0x40000))
+#define AQMQ_ENX(x)                     (0x20048 + ((x) * 0x40000))
+#define AQMQ_ACTIVITY_STATX(x)          (0x20050 + ((x) * 0x40000))
+#define AQM_VF_CMP_STATX(x)             (0x28000 + ((x) * 0x40000))
+
+/* NPS core registers */
+#define NPS_CORE_GBL_VFCFG	0x1000000
+#define NPS_CORE_CONTROL	0x1000008
+#define NPS_CORE_INT_ACTIVE	0x1000080
+#define NPS_CORE_INT		0x10000A0
+#define NPS_CORE_INT_ENA_W1S	0x10000B8
+#define NPS_STATS_PKT_DMA_RD_CNT	0x1000180
+#define NPS_STATS_PKT_DMA_WR_CNT	0x1000190
+
+/* NPS packet registers */
+#define NPS_PKT_INT			0x1040018
+#define NPS_PKT_MBOX_INT_LO		0x1040020
+#define NPS_PKT_MBOX_INT_LO_ENA_W1C	0x1040030
+#define NPS_PKT_MBOX_INT_LO_ENA_W1S	0x1040038
+#define NPS_PKT_MBOX_INT_HI		0x1040040
+#define NPS_PKT_MBOX_INT_HI_ENA_W1C	0x1040050
+#define NPS_PKT_MBOX_INT_HI_ENA_W1S	0x1040058
+#define NPS_PKT_IN_RERR_HI		0x1040108
+#define NPS_PKT_IN_RERR_HI_ENA_W1S	0x1040120
+#define NPS_PKT_IN_RERR_LO		0x1040128
+#define NPS_PKT_IN_RERR_LO_ENA_W1S	0x1040140
+#define NPS_PKT_IN_ERR_TYPE		0x1040148
+#define NPS_PKT_IN_ERR_TYPE_ENA_W1S	0x1040160
+#define NPS_PKT_IN_INSTR_CTLX(_i)	(0x10060 + ((_i) * 0x40000))
+#define NPS_PKT_IN_INSTR_BADDRX(_i)	(0x10068 + ((_i) * 0x40000))
+#define NPS_PKT_IN_INSTR_RSIZEX(_i)	(0x10070 + ((_i) * 0x40000))
+#define NPS_PKT_IN_DONE_CNTSX(_i)	(0x10080 + ((_i) * 0x40000))
+#define NPS_PKT_IN_INSTR_BAOFF_DBELLX(_i)	(0x10078 + ((_i) * 0x40000))
+#define NPS_PKT_IN_INT_LEVELSX(_i)		(0x10088 + ((_i) * 0x40000))
+
+#define NPS_PKT_SLC_RERR_HI		0x1040208
+#define NPS_PKT_SLC_RERR_HI_ENA_W1S	0x1040220
+#define NPS_PKT_SLC_RERR_LO		0x1040228
+#define NPS_PKT_SLC_RERR_LO_ENA_W1S	0x1040240
+#define NPS_PKT_SLC_ERR_TYPE		0x1040248
+#define NPS_PKT_SLC_ERR_TYPE_ENA_W1S	0x1040260
+/* Mailbox PF->VF PF Accessible Data registers */
+#define NPS_PKT_MBOX_PF_VF_PFDATAX(_i)	(0x1040800 + ((_i) * 0x8))
+#define NPS_PKT_MBOX_VF_PF_PFDATAX(_i)	(0x1040C00 + ((_i) * 0x8))
+
+#define NPS_PKT_SLC_CTLX(_i)		(0x10000 + ((_i) * 0x40000))
+#define NPS_PKT_SLC_CNTSX(_i)		(0x10008 + ((_i) * 0x40000))
+#define NPS_PKT_SLC_INT_LEVELSX(_i)	(0x10010 + ((_i) * 0x40000))
+
+/* POM registers */
+#define POM_INT_ENA_W1S		0x11C0018
+#define POM_GRP_EXECMASKX(_i)	(0x11C1100 | ((_i) * 8))
+#define POM_INT		0x11C0000
+#define POM_PERF_CTL	0x11CC400
+
+/* BMI registers */
+#define BMI_INT		0x1140000
+#define BMI_CTL		0x1140020
+#define BMI_INT_ENA_W1S	0x1140018
+#define BMI_NPS_PKT_CNT	0x1140070
+
+/* EFL registers */
+#define EFL_CORE_INT_ENA_W1SX(_i)		(0x1240018 + ((_i) * 0x400))
+#define EFL_CORE_VF_ERR_INT0X(_i)		(0x1240050 + ((_i) * 0x400))
+#define EFL_CORE_VF_ERR_INT0_ENA_W1SX(_i)	(0x1240068 + ((_i) * 0x400))
+#define EFL_CORE_VF_ERR_INT1X(_i)		(0x1240070 + ((_i) * 0x400))
+#define EFL_CORE_VF_ERR_INT1_ENA_W1SX(_i)	(0x1240088 + ((_i) * 0x400))
+#define EFL_CORE_SE_ERR_INTX(_i)		(0x12400A0 + ((_i) * 0x400))
+#define EFL_RNM_CTL_STATUS			0x1241800
+#define EFL_CORE_INTX(_i)			(0x1240000 + ((_i) * 0x400))
+
+/* BMO registers */
+#define BMO_CTL2		0x1180028
+#define BMO_NPS_SLC_PKT_CNT	0x1180078
+
+/* LBC registers */
+#define LBC_INT			0x1200000
+#define LBC_INVAL_CTL		0x1201010
+#define LBC_PLM_VF1_64_INT	0x1202008
+#define LBC_INVAL_STATUS	0x1202010
+#define LBC_INT_ENA_W1S		0x1203000
+#define LBC_PLM_VF1_64_INT_ENA_W1S	0x1205008
+#define LBC_PLM_VF65_128_INT		0x1206008
+#define LBC_ELM_VF1_64_INT		0x1208000
+#define LBC_PLM_VF65_128_INT_ENA_W1S	0x1209008
+#define LBC_ELM_VF1_64_INT_ENA_W1S	0x120B000
+#define LBC_ELM_VF65_128_INT		0x120C000
+#define LBC_ELM_VF65_128_INT_ENA_W1S	0x120F000
+
+#define RST_BOOT	0x10C1600
+#define FUS_DAT1	0x10C1408
+
+/* PEM registers */
+#define PEM0_INT 0x1080428
+
+/**
+ * struct ucd_core_eid_ucode_block_num - Core Eid to Ucode Blk Mapping Registers
+ * @ucode_len: Ucode length identifier 32KB or 64KB
+ * @ucode_blk: Ucode Block Number
+ */
+union ucd_core_eid_ucode_block_num {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz_4_63 : 60;
+		u64 ucode_len : 1;
+		u64 ucode_blk : 3;
+#else
+		u64 ucode_blk : 3;
+		u64 ucode_len : 1;
+		u64 raz_4_63 : 60;
+#endif
+	};
+};
+
+/**
+ * struct aqm_grp_execmsk_lo - Available AE engines for the group
+ * @exec_0_to_39: AE engines 0 to 39 status
+ */
+union aqm_grp_execmsk_lo {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz_40_63 : 24;
+		u64 exec_0_to_39 : 40;
+#else
+		u64 exec_0_to_39 : 40;
+		u64 raz_40_63 : 24;
+#endif
+	};
+};
+
+/**
+ * struct aqm_grp_execmsk_hi - Available AE engines for the group
+ * @exec_40_to_79: AE engines 40 to 79 status
+ */
+union aqm_grp_execmsk_hi {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz_40_63 : 24;
+		u64 exec_40_to_79 : 40;
+#else
+		u64 exec_40_to_79 : 40;
+		u64 raz_40_63 : 24;
+#endif
+	};
+};
+
+/**
+ * struct aqmq_drbl - AQM Queue Doorbell Counter Registers
+ * @dbell_count: Doorbell Counter
+ */
+union aqmq_drbl {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz_32_63 : 32;
+		u64 dbell_count : 32;
+#else
+		u64 dbell_count : 32;
+		u64 raz_32_63 : 32;
+#endif
+	};
+};
+
+/**
+ * struct aqmq_qsz - AQM Queue Host Queue Size Registers
+ * @host_queue_size: Size, in numbers of 'aqmq_command_s' command
+ * of the Host Ring.
+ */
+union aqmq_qsz {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz_32_63 : 32;
+		u64 host_queue_size : 32;
+#else
+		u64 host_queue_size : 32;
+		u64 raz_32_63 : 32;
+#endif
+	};
+};
+
+/**
+ * struct aqmq_cmp_thr - AQM Queue Commands Completed Threshold Registers
+ * @commands_completed_threshold: Count of 'aqmq_command_s' commands executed
+ * by AE engines for which completion interrupt is asserted.
+ */
+union aqmq_cmp_thr {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz_32_63 : 32;
+		u64 commands_completed_threshold : 32;
+#else
+		u64 commands_completed_threshold : 32;
+		u64 raz_32_63 : 32;
+#endif
+	};
+};
+
+/**
+ * struct aqmq_cmp_cnt - AQM Queue Commands Completed Count Registers
+ * @resend: Bit to request completion interrupt Resend.
+ * @completion_status: Command completion status of the ring.
+ * @commands_completed_count: Count of 'aqmq_command_s' commands executed by
+ * AE engines.
+ */
+union aqmq_cmp_cnt {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz_34_63 : 30;
+		u64 resend : 1;
+		u64 completion_status : 1;
+		u64 commands_completed_count : 32;
+#else
+		u64 commands_completed_count : 32;
+		u64 completion_status : 1;
+		u64 resend : 1;
+		u64 raz_34_63 : 30;
+#endif
+	};
+};
+
+/**
+ * struct aqmq_en - AQM Queue Enable Registers
+ * @queue_status: 1 = AQMQ is enabled, 0 = AQMQ is disabled
+ */
+union aqmq_en {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz_1_63 : 63;
+		u64 queue_enable : 1;
+#else
+		u64 queue_enable : 1;
+		u64 raz_1_63 : 63;
+#endif
+	};
+};
+
+/**
+ * struct aqmq_activity_stat - AQM Queue Activity Status Registers
+ * @queue_active: 1 = AQMQ is active, 0 = AQMQ is quiescent
+ */
+union aqmq_activity_stat {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz_1_63 : 63;
+		u64 queue_active : 1;
+#else
+		u64 queue_active : 1;
+		u64 raz_1_63 : 63;
+#endif
+	};
+};
+
+/**
+ * struct emu_fuse_map - EMU Fuse Map Registers
+ * @ae_fuse: Fuse settings for AE 19..0
+ * @se_fuse: Fuse settings for SE 15..0
+ *
+ * A set bit indicates the unit is fuse disabled.
+ */
+union emu_fuse_map {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 valid : 1;
+		u64 raz_52_62 : 11;
+		u64 ae_fuse : 20;
+		u64 raz_16_31 : 16;
+		u64 se_fuse : 16;
+#else
+		u64 se_fuse : 16;
+		u64 raz_16_31 : 16;
+		u64 ae_fuse : 20;
+		u64 raz_52_62 : 11;
+		u64 valid : 1;
+#endif
+	} s;
+};
+
+/**
+ * struct emu_se_enable - Symmetric Engine Enable Registers
+ * @enable: Individual enables for each of the clusters
+ *   16 symmetric engines.
+ */
+union emu_se_enable {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz	: 48;
+		u64 enable : 16;
+#else
+		u64 enable : 16;
+		u64 raz	: 48;
+#endif
+	} s;
+};
+
+/**
+ * struct emu_ae_enable - EMU Asymmetric engines.
+ * @enable: Individual enables for each of the cluster's
+ *   20 Asymmetric Engines.
+ */
+union emu_ae_enable {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz	: 44;
+		u64 enable : 20;
+#else
+		u64 enable : 20;
+		u64 raz	: 44;
+#endif
+	} s;
+};
+
+/**
+ * struct emu_wd_int_ena_w1s - EMU Interrupt Enable Registers
+ * @ae_wd: Reads or sets enable for EMU(0..3)_WD_INT[AE_WD]
+ * @se_wd: Reads or sets enable for EMU(0..3)_WD_INT[SE_WD]
+ */
+union emu_wd_int_ena_w1s {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz2 : 12;
+		u64 ae_wd : 20;
+		u64 raz1 : 16;
+		u64 se_wd : 16;
+#else
+		u64 se_wd : 16;
+		u64 raz1 : 16;
+		u64 ae_wd : 20;
+		u64 raz2 : 12;
+#endif
+	} s;
+};
+
+/**
+ * struct emu_ge_int_ena_w1s - EMU Interrupt Enable set registers
+ * @ae_ge: Reads or sets enable for EMU(0..3)_GE_INT[AE_GE]
+ * @se_ge: Reads or sets enable for EMU(0..3)_GE_INT[SE_GE]
+ */
+union emu_ge_int_ena_w1s {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz_52_63 : 12;
+		u64 ae_ge : 20;
+		u64 raz_16_31: 16;
+		u64 se_ge : 16;
+#else
+		u64 se_ge : 16;
+		u64 raz_16_31: 16;
+		u64 ae_ge : 20;
+		u64 raz_52_63 : 12;
+#endif
+	} s;
+};
+
+/**
+ * struct nps_pkt_slc_ctl - Solicited Packet Out Control Registers
+ * @rh: Indicates whether to remove or include the response header
+ *   1 = Include, 0 = Remove
+ * @z: If set, 8 trailing 0x00 bytes will be added to the end of the
+ *   outgoing packet.
+ * @enb: Enable for this port.
+ */
+union nps_pkt_slc_ctl {
+	u64 value;
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 raz : 61;
+		u64 rh : 1;
+		u64 z : 1;
+		u64 enb : 1;
+#else
+		u64 enb : 1;
+		u64 z : 1;
+		u64 rh : 1;
+		u64 raz : 61;
+#endif
+	} s;
+};
+
+/**
+ * struct nps_pkt_slc_cnts - Solicited Packet Out Count Registers
+ * @slc_int: Returns a 1 when:
+ *   NPS_PKT_SLC(i)_CNTS[CNT] > NPS_PKT_SLC(i)_INT_LEVELS[CNT], or
+ *   NPS_PKT_SLC(i)_CNTS[TIMER] > NPS_PKT_SLC(i)_INT_LEVELS[TIMET].
+ *   To clear the bit, the CNTS register must be written to clear.
+ * @in_int: Returns a 1 when:
+ *   NPS_PKT_IN(i)_DONE_CNTS[CNT] > NPS_PKT_IN(i)_INT_LEVELS[CNT].
+ *   To clear the bit, the DONE_CNTS register must be written to clear.
+ * @mbox_int: Returns a 1 when:
+ *   NPS_PKT_MBOX_PF_VF(i)_INT[INTR] is set. To clear the bit,
+ *   write NPS_PKT_MBOX_PF_VF(i)_INT[INTR] with 1.
+ * @timer: Timer, incremented every 2048 coprocessor clock cycles
+ *   when [CNT] is not zero. The hardware clears both [TIMER] and
+ *   [INT] when [CNT] goes to 0.
+ * @cnt: Packet counter. Hardware adds to [CNT] as it sends packets out.
+ *   On a write to this CSR, hardware subtracts the amount written to the
+ *   [CNT] field from [CNT].
+ */
+union nps_pkt_slc_cnts {
+	u64 value;
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 slc_int : 1;
+		u64 uns_int : 1;
+		u64 in_int : 1;
+		u64 mbox_int : 1;
+		u64 resend : 1;
+		u64 raz : 5;
+		u64 timer : 22;
+		u64 cnt : 32;
+#else
+		u64 cnt	: 32;
+		u64 timer : 22;
+		u64 raz	: 5;
+		u64 resend : 1;
+		u64 mbox_int : 1;
+		u64 in_int : 1;
+		u64 uns_int : 1;
+		u64 slc_int : 1;
+#endif
+	} s;
+};
+
+/**
+ * struct nps_pkt_slc_int_levels - Solicited Packet Out Interrupt Levels
+ *   Registers.
+ * @bmode: Determines whether NPS_PKT_SLC_CNTS[CNT] is a byte or
+ *   packet counter.
+ * @timet: Output port counter time interrupt threshold.
+ * @cnt: Output port counter interrupt threshold.
+ */
+union nps_pkt_slc_int_levels {
+	u64 value;
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 bmode : 1;
+		u64 raz	: 9;
+		u64 timet : 22;
+		u64 cnt	: 32;
+#else
+		u64 cnt : 32;
+		u64 timet : 22;
+		u64 raz : 9;
+		u64 bmode : 1;
+#endif
+	} s;
+};
+
+/**
+ * struct nps_pkt_inst - NPS Packet Interrupt Register
+ * @in_err: Set when any NPS_PKT_IN_RERR_HI/LO bit and
+ *    corresponding NPS_PKT_IN_RERR_*_ENA_* bit are bot set.
+ * @uns_err: Set when any NSP_PKT_UNS_RERR_HI/LO bit and
+ *    corresponding NPS_PKT_UNS_RERR_*_ENA_* bit are both set.
+ * @slc_er: Set when any NSP_PKT_SLC_RERR_HI/LO bit and
+ *    corresponding NPS_PKT_SLC_RERR_*_ENA_* bit are both set.
+ */
+union nps_pkt_int {
+	u64 value;
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 raz	: 54;
+		u64 uns_wto : 1;
+		u64 in_err : 1;
+		u64 uns_err : 1;
+		u64 slc_err : 1;
+		u64 in_dbe : 1;
+		u64 in_sbe : 1;
+		u64 uns_dbe : 1;
+		u64 uns_sbe : 1;
+		u64 slc_dbe : 1;
+		u64 slc_sbe : 1;
+#else
+		u64 slc_sbe : 1;
+		u64 slc_dbe : 1;
+		u64 uns_sbe : 1;
+		u64 uns_dbe : 1;
+		u64 in_sbe : 1;
+		u64 in_dbe : 1;
+		u64 slc_err : 1;
+		u64 uns_err : 1;
+		u64 in_err : 1;
+		u64 uns_wto : 1;
+		u64 raz	: 54;
+#endif
+	} s;
+};
+
+/**
+ * struct nps_pkt_in_done_cnts - Input instruction ring counts registers
+ * @slc_cnt: Returns a 1 when:
+ *    NPS_PKT_SLC(i)_CNTS[CNT] > NPS_PKT_SLC(i)_INT_LEVELS[CNT], or
+ *    NPS_PKT_SLC(i)_CNTS[TIMER] > NPS_PKT_SCL(i)_INT_LEVELS[TIMET]
+ *    To clear the bit, the CNTS register must be
+ *    written to clear the underlying condition
+ * @uns_int: Return a 1 when:
+ *    NPS_PKT_UNS(i)_CNTS[CNT] > NPS_PKT_UNS(i)_INT_LEVELS[CNT], or
+ *    NPS_PKT_UNS(i)_CNTS[TIMER] > NPS_PKT_UNS(i)_INT_LEVELS[TIMET]
+ *    To clear the bit, the CNTS register must be
+ *    written to clear the underlying condition
+ * @in_int: Returns a 1 when:
+ *    NPS_PKT_IN(i)_DONE_CNTS[CNT] > NPS_PKT_IN(i)_INT_LEVELS[CNT]
+ *    To clear the bit, the DONE_CNTS register
+ *    must be written to clear the underlying condition
+ * @mbox_int: Returns a 1 when:
+ *    NPS_PKT_MBOX_PF_VF(i)_INT[INTR] is set.
+ *    To clear the bit, write NPS_PKT_MBOX_PF_VF(i)_INT[INTR]
+ *    with 1.
+ * @resend: A write of 1 will resend an MSI-X interrupt message if any
+ *    of the following conditions are true for this ring "i".
+ *    NPS_PKT_SLC(i)_CNTS[CNT] > NPS_PKT_SLC(i)_INT_LEVELS[CNT]
+ *    NPS_PKT_SLC(i)_CNTS[TIMER] > NPS_PKT_SLC(i)_INT_LEVELS[TIMET]
+ *    NPS_PKT_UNS(i)_CNTS[CNT] > NPS_PKT_UNS(i)_INT_LEVELS[CNT]
+ *    NPS_PKT_UNS(i)_CNTS[TIMER] > NPS_PKT_UNS(i)_INT_LEVELS[TIMET]
+ *    NPS_PKT_IN(i)_DONE_CNTS[CNT] > NPS_PKT_IN(i)_INT_LEVELS[CNT]
+ *    NPS_PKT_MBOX_PF_VF(i)_INT[INTR] is set
+ * @cnt: Packet counter. Hardware adds to [CNT] as it reads
+ *    packets. On a write to this CSR, hardware substracts the
+ *    amount written to the [CNT] field from [CNT], which will
+ *    clear PKT_IN(i)_INT_STATUS[INTR] if [CNT] becomes <=
+ *    NPS_PKT_IN(i)_INT_LEVELS[CNT]. This register should be
+ *    cleared before enabling a ring by reading the current
+ *    value and writing it back.
+ */
+union nps_pkt_in_done_cnts {
+	u64 value;
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 slc_int : 1;
+		u64 uns_int : 1;
+		u64 in_int : 1;
+		u64 mbox_int : 1;
+		u64 resend : 1;
+		u64 raz : 27;
+		u64 cnt	: 32;
+#else
+		u64 cnt	: 32;
+		u64 raz	: 27;
+		u64 resend : 1;
+		u64 mbox_int : 1;
+		u64 in_int : 1;
+		u64 uns_int : 1;
+		u64 slc_int : 1;
+#endif
+	} s;
+};
+
+/**
+ * struct nps_pkt_in_instr_ctl - Input Instruction Ring Control Registers.
+ * @is64b: If 1, the ring uses 64-byte instructions. If 0, the
+ *   ring uses 32-byte instructions.
+ * @enb: Enable for the input ring.
+ */
+union nps_pkt_in_instr_ctl {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz	: 62;
+		u64 is64b : 1;
+		u64 enb	: 1;
+#else
+		u64 enb	: 1;
+		u64 is64b : 1;
+		u64 raz : 62;
+#endif
+	} s;
+};
+
+/**
+ * struct nps_pkt_in_instr_rsize - Input instruction ring size registers
+ * @rsize: Ring size (number of instructions)
+ */
+union nps_pkt_in_instr_rsize {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz	: 32;
+		u64 rsize : 32;
+#else
+		u64 rsize : 32;
+		u64 raz	: 32;
+#endif
+	} s;
+};
+
+/**
+ * struct nps_pkt_in_instr_baoff_dbell - Input instruction ring
+ *   base address offset and doorbell registers
+ * @aoff: Address offset. The offset from the NPS_PKT_IN_INSTR_BADDR
+ *   where the next pointer is read.
+ * @dbell: Pointer list doorbell count. Write operations to this field
+ *   increments the present value here. Read operations return the
+ *   present value.
+ */
+union nps_pkt_in_instr_baoff_dbell {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 aoff : 32;
+		u64 dbell : 32;
+#else
+		u64 dbell : 32;
+		u64 aoff : 32;
+#endif
+	} s;
+};
+
+/**
+ * struct nps_core_int_ena_w1s - NPS core interrupt enable set register
+ * @host_nps_wr_err: Reads or sets enable for
+ *   NPS_CORE_INT[HOST_NPS_WR_ERR].
+ * @npco_dma_malform: Reads or sets enable for
+ *   NPS_CORE_INT[NPCO_DMA_MALFORM].
+ * @exec_wr_timeout: Reads or sets enable for
+ *   NPS_CORE_INT[EXEC_WR_TIMEOUT].
+ * @host_wr_timeout: Reads or sets enable for
+ *   NPS_CORE_INT[HOST_WR_TIMEOUT].
+ * @host_wr_err: Reads or sets enable for
+ *   NPS_CORE_INT[HOST_WR_ERR]
+ */
+union nps_core_int_ena_w1s {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz4 : 55;
+		u64 host_nps_wr_err : 1;
+		u64 npco_dma_malform : 1;
+		u64 exec_wr_timeout : 1;
+		u64 host_wr_timeout : 1;
+		u64 host_wr_err : 1;
+		u64 raz3 : 1;
+		u64 raz2 : 1;
+		u64 raz1 : 1;
+		u64 raz0 : 1;
+#else
+		u64 raz0 : 1;
+		u64 raz1 : 1;
+		u64 raz2 : 1;
+		u64 raz3 : 1;
+		u64 host_wr_err	: 1;
+		u64 host_wr_timeout : 1;
+		u64 exec_wr_timeout : 1;
+		u64 npco_dma_malform : 1;
+		u64 host_nps_wr_err : 1;
+		u64 raz4 : 55;
+#endif
+	} s;
+};
+
+/**
+ * struct nps_core_gbl_vfcfg - Global VF Configuration Register.
+ * @ilk_disable: When set, this bit indicates that the ILK interface has
+ *    been disabled.
+ * @obaf: BMO allocation control
+ *    0 = allocate per queue
+ *    1 = allocate per VF
+ * @ibaf: BMI allocation control
+ *    0 = allocate per queue
+ *    1 = allocate per VF
+ * @zaf: ZIP allocation control
+ *    0 = allocate per queue
+ *    1 = allocate per VF
+ * @aeaf: AE allocation control
+ *    0 = allocate per queue
+ *    1 = allocate per VF
+ * @seaf: SE allocation control
+ *    0 = allocation per queue
+ *    1 = allocate per VF
+ * @cfg: VF/PF mode.
+ */
+union nps_core_gbl_vfcfg {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64  raz :55;
+		u64  ilk_disable :1;
+		u64  obaf :1;
+		u64  ibaf :1;
+		u64  zaf :1;
+		u64  aeaf :1;
+		u64  seaf :1;
+		u64  cfg :3;
+#else
+		u64  cfg :3;
+		u64  seaf :1;
+		u64  aeaf :1;
+		u64  zaf :1;
+		u64  ibaf :1;
+		u64  obaf :1;
+		u64  ilk_disable :1;
+		u64  raz :55;
+#endif
+	} s;
+};
+
+/**
+ * struct nps_core_int_active - NPS Core Interrupt Active Register
+ * @resend: Resend MSI-X interrupt if needs to handle interrupts
+ *    Sofware can set this bit and then exit the ISR.
+ * @ocla: Set when any OCLA(0)_INT and corresponding OCLA(0_INT_ENA_W1C
+ *    bit are set
+ * @mbox: Set when any NPS_PKT_MBOX_INT_LO/HI and corresponding
+ *    NPS_PKT_MBOX_INT_LO_ENA_W1C/HI_ENA_W1C bits are set
+ * @emu: bit i is set in [EMU] when any EMU(i)_INT bit is set
+ * @bmo: Set when any BMO_INT bit is set
+ * @bmi: Set when any BMI_INT bit is set or when any non-RO
+ *    BMI_INT and corresponding BMI_INT_ENA_W1C bits are both set
+ * @aqm: Set when any AQM_INT bit is set
+ * @zqm: Set when any ZQM_INT bit is set
+ * @efl: Set when any EFL_INT RO bit is set or when any non-RO EFL_INT
+ *    and corresponding EFL_INT_ENA_W1C bits are both set
+ * @ilk: Set when any ILK_INT bit is set
+ * @lbc: Set when any LBC_INT RO bit is set or when any non-RO LBC_INT
+ *    and corresponding LBC_INT_ENA_W1C bits are bot set
+ * @pem: Set when any PEM(0)_INT RO bit is set or when any non-RO
+ *    PEM(0)_INT and corresponding PEM(0)_INT_ENA_W1C bit are both set
+ * @ucd: Set when any UCD_INT bit is set
+ * @zctl: Set when any ZIP_INT RO bit is set or when any non-RO ZIP_INT
+ *    and corresponding ZIP_INT_ENA_W1C bits are both set
+ * @lbm: Set when any LBM_INT bit is set
+ * @nps_pkt: Set when any NPS_PKT_INT bit is set
+ * @nps_core: Set when any NPS_CORE_INT RO bit is set or when non-RO
+ *    NPS_CORE_INT and corresponding NSP_CORE_INT_ENA_W1C bits are both set
+ */
+union nps_core_int_active {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 resend : 1;
+		u64 raz	: 43;
+		u64 ocla : 1;
+		u64 mbox : 1;
+		u64 emu	: 4;
+		u64 bmo	: 1;
+		u64 bmi	: 1;
+		u64 aqm	: 1;
+		u64 zqm	: 1;
+		u64 efl	: 1;
+		u64 ilk	: 1;
+		u64 lbc	: 1;
+		u64 pem	: 1;
+		u64 pom	: 1;
+		u64 ucd	: 1;
+		u64 zctl : 1;
+		u64 lbm	: 1;
+		u64 nps_pkt : 1;
+		u64 nps_core : 1;
+#else
+		u64 nps_core : 1;
+		u64 nps_pkt : 1;
+		u64 lbm	: 1;
+		u64 zctl: 1;
+		u64 ucd	: 1;
+		u64 pom	: 1;
+		u64 pem	: 1;
+		u64 lbc	: 1;
+		u64 ilk	: 1;
+		u64 efl	: 1;
+		u64 zqm	: 1;
+		u64 aqm	: 1;
+		u64 bmi	: 1;
+		u64 bmo	: 1;
+		u64 emu	: 4;
+		u64 mbox : 1;
+		u64 ocla : 1;
+		u64 raz	: 43;
+		u64 resend : 1;
+#endif
+	} s;
+};
+
+/**
+ * struct efl_core_int - EFL Interrupt Registers
+ * @epci_decode_err: EPCI decoded a transacation that was unknown
+ *    This error should only occurred when there is a micrcode/SE error
+ *    and should be considered fatal
+ * @ae_err: An AE uncorrectable error occurred.
+ *    See EFL_CORE(0..3)_AE_ERR_INT
+ * @se_err: An SE uncorrectable error occurred.
+ *    See EFL_CORE(0..3)_SE_ERR_INT
+ * @dbe: Double-bit error occurred in EFL
+ * @sbe: Single-bit error occurred in EFL
+ * @d_left: Asserted when new POM-Header-BMI-data is
+ *    being sent to an Exec, and that Exec has Not read all BMI
+ *    data associated with the previous POM header
+ * @len_ovr: Asserted when an Exec-Read is issued that is more than
+ *    14 greater in length that the BMI data left to be read
+ */
+union efl_core_int {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz	: 57;
+		u64 epci_decode_err : 1;
+		u64 ae_err : 1;
+		u64 se_err : 1;
+		u64 dbe	: 1;
+		u64 sbe	: 1;
+		u64 d_left : 1;
+		u64 len_ovr : 1;
+#else
+		u64 len_ovr : 1;
+		u64 d_left : 1;
+		u64 sbe	: 1;
+		u64 dbe	: 1;
+		u64 se_err : 1;
+		u64 ae_err : 1;
+		u64 epci_decode_err  : 1;
+		u64 raz	: 57;
+#endif
+	} s;
+};
+
+/**
+ * struct efl_core_int_ena_w1s - EFL core interrupt enable set register
+ * @epci_decode_err: Reads or sets enable for
+ *   EFL_CORE(0..3)_INT[EPCI_DECODE_ERR].
+ * @d_left: Reads or sets enable for
+ *   EFL_CORE(0..3)_INT[D_LEFT].
+ * @len_ovr: Reads or sets enable for
+ *   EFL_CORE(0..3)_INT[LEN_OVR].
+ */
+union efl_core_int_ena_w1s {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz_7_63 : 57;
+		u64 epci_decode_err : 1;
+		u64 raz_2_5 : 4;
+		u64 d_left : 1;
+		u64 len_ovr : 1;
+#else
+		u64 len_ovr : 1;
+		u64 d_left : 1;
+		u64 raz_2_5 : 4;
+		u64 epci_decode_err : 1;
+		u64 raz_7_63 : 57;
+#endif
+	} s;
+};
+
+/**
+ * struct efl_rnm_ctl_status - RNM Control and Status Register
+ * @ent_sel: Select input to RNM FIFO
+ * @exp_ent: Exported entropy enable for random number generator
+ * @rng_rst: Reset to RNG. Setting this bit to 1 cancels the generation
+ *    of the current random number.
+ * @rnm_rst: Reset the RNM. Setting this bit to 1 clears all sorted numbers
+ *    in the random number memory.
+ * @rng_en: Enabled the output of the RNG.
+ * @ent_en: Entropy enable for random number generator.
+ */
+union efl_rnm_ctl_status {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz_9_63 : 55;
+		u64 ent_sel : 4;
+		u64 exp_ent : 1;
+		u64 rng_rst : 1;
+		u64 rnm_rst : 1;
+		u64 rng_en : 1;
+		u64 ent_en : 1;
+#else
+		u64 ent_en : 1;
+		u64 rng_en : 1;
+		u64 rnm_rst : 1;
+		u64 rng_rst : 1;
+		u64 exp_ent : 1;
+		u64 ent_sel : 4;
+		u64 raz_9_63 : 55;
+#endif
+	} s;
+};
+
+/**
+ * struct bmi_ctl - BMI control register
+ * @ilk_hdrq_thrsh: Maximum number of header queue locations
+ *   that ILK packets may consume. When the threshold is
+ *   exceeded ILK_XOFF is sent to the BMI_X2P_ARB.
+ * @nps_hdrq_thrsh: Maximum number of header queue locations
+ *   that NPS packets may consume. When the threshold is
+ *   exceeded NPS_XOFF is sent to the BMI_X2P_ARB.
+ * @totl_hdrq_thrsh: Maximum number of header queue locations
+ *   that the sum of ILK and NPS packets may consume.
+ * @ilk_free_thrsh: Maximum number of buffers that ILK packet
+ *   flows may consume before ILK_XOFF is sent to the BMI_X2P_ARB.
+ * @nps_free_thrsh: Maximum number of buffers that NPS packet
+ *   flows may consume before NPS XOFF is sent to the BMI_X2p_ARB.
+ * @totl_free_thrsh: Maximum number of buffers that bot ILK and NPS
+ *   packet flows may consume before both NPS_XOFF and ILK_XOFF
+ *   are asserted to the BMI_X2P_ARB.
+ * @max_pkt_len: Maximum packet length, integral number of 256B
+ *   buffers.
+ */
+union bmi_ctl {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz_56_63 : 8;
+		u64 ilk_hdrq_thrsh : 8;
+		u64 nps_hdrq_thrsh : 8;
+		u64 totl_hdrq_thrsh : 8;
+		u64 ilk_free_thrsh : 8;
+		u64 nps_free_thrsh : 8;
+		u64 totl_free_thrsh : 8;
+		u64 max_pkt_len : 8;
+#else
+		u64 max_pkt_len : 8;
+		u64 totl_free_thrsh : 8;
+		u64 nps_free_thrsh : 8;
+		u64 ilk_free_thrsh : 8;
+		u64 totl_hdrq_thrsh : 8;
+		u64 nps_hdrq_thrsh : 8;
+		u64 ilk_hdrq_thrsh : 8;
+		u64 raz_56_63 : 8;
+#endif
+	} s;
+};
+
+/**
+ * struct bmi_int_ena_w1s - BMI interrupt enable set register
+ * @ilk_req_oflw: Reads or sets enable for
+ *   BMI_INT[ILK_REQ_OFLW].
+ * @nps_req_oflw: Reads or sets enable for
+ *   BMI_INT[NPS_REQ_OFLW].
+ * @fpf_undrrn: Reads or sets enable for
+ *   BMI_INT[FPF_UNDRRN].
+ * @eop_err_ilk: Reads or sets enable for
+ *   BMI_INT[EOP_ERR_ILK].
+ * @eop_err_nps: Reads or sets enable for
+ *   BMI_INT[EOP_ERR_NPS].
+ * @sop_err_ilk: Reads or sets enable for
+ *   BMI_INT[SOP_ERR_ILK].
+ * @sop_err_nps: Reads or sets enable for
+ *   BMI_INT[SOP_ERR_NPS].
+ * @pkt_rcv_err_ilk: Reads or sets enable for
+ *   BMI_INT[PKT_RCV_ERR_ILK].
+ * @pkt_rcv_err_nps: Reads or sets enable for
+ *   BMI_INT[PKT_RCV_ERR_NPS].
+ * @max_len_err_ilk: Reads or sets enable for
+ *   BMI_INT[MAX_LEN_ERR_ILK].
+ * @max_len_err_nps: Reads or sets enable for
+ *   BMI_INT[MAX_LEN_ERR_NPS].
+ */
+union bmi_int_ena_w1s {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz_13_63	: 51;
+		u64 ilk_req_oflw : 1;
+		u64 nps_req_oflw : 1;
+		u64 raz_10 : 1;
+		u64 raz_9 : 1;
+		u64 fpf_undrrn	: 1;
+		u64 eop_err_ilk	: 1;
+		u64 eop_err_nps	: 1;
+		u64 sop_err_ilk	: 1;
+		u64 sop_err_nps	: 1;
+		u64 pkt_rcv_err_ilk : 1;
+		u64 pkt_rcv_err_nps : 1;
+		u64 max_len_err_ilk : 1;
+		u64 max_len_err_nps : 1;
+#else
+		u64 max_len_err_nps : 1;
+		u64 max_len_err_ilk : 1;
+		u64 pkt_rcv_err_nps : 1;
+		u64 pkt_rcv_err_ilk : 1;
+		u64 sop_err_nps	: 1;
+		u64 sop_err_ilk	: 1;
+		u64 eop_err_nps	: 1;
+		u64 eop_err_ilk	: 1;
+		u64 fpf_undrrn	: 1;
+		u64 raz_9 : 1;
+		u64 raz_10 : 1;
+		u64 nps_req_oflw : 1;
+		u64 ilk_req_oflw : 1;
+		u64 raz_13_63 : 51;
+#endif
+	} s;
+};
+
+/**
+ * struct bmo_ctl2 - BMO Control2 Register
+ * @arb_sel: Determines P2X Arbitration
+ * @ilk_buf_thrsh: Maximum number of buffers that the
+ *    ILK packet flows may consume before ILK XOFF is
+ *    asserted to the POM.
+ * @nps_slc_buf_thrsh: Maximum number of buffers that the
+ *    NPS_SLC packet flow may consume before NPS_SLC XOFF is
+ *    asserted to the POM.
+ * @nps_uns_buf_thrsh: Maximum number of buffers that the
+ *    NPS_UNS packet flow may consume before NPS_UNS XOFF is
+ *    asserted to the POM.
+ * @totl_buf_thrsh: Maximum number of buffers that ILK, NPS_UNS and
+ *    NPS_SLC packet flows may consume before NPS_UNS XOFF, NSP_SLC and
+ *    ILK_XOFF are all asserted POM.
+ */
+union bmo_ctl2 {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 arb_sel : 1;
+		u64 raz_32_62 : 31;
+		u64 ilk_buf_thrsh : 8;
+		u64 nps_slc_buf_thrsh : 8;
+		u64 nps_uns_buf_thrsh : 8;
+		u64 totl_buf_thrsh : 8;
+#else
+		u64 totl_buf_thrsh : 8;
+		u64 nps_uns_buf_thrsh : 8;
+		u64 nps_slc_buf_thrsh : 8;
+		u64 ilk_buf_thrsh : 8;
+		u64 raz_32_62 : 31;
+		u64 arb_sel : 1;
+#endif
+	} s;
+};
+
+/**
+ * struct pom_int_ena_w1s - POM interrupt enable set register
+ * @illegal_intf: Reads or sets enable for POM_INT[ILLEGAL_INTF].
+ * @illegal_dport: Reads or sets enable for POM_INT[ILLEGAL_DPORT].
+ */
+union pom_int_ena_w1s {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz2 : 60;
+		u64 illegal_intf : 1;
+		u64 illegal_dport : 1;
+		u64 raz1 : 1;
+		u64 raz0 : 1;
+#else
+		u64 raz0 : 1;
+		u64 raz1 : 1;
+		u64 illegal_dport : 1;
+		u64 illegal_intf : 1;
+		u64 raz2 : 60;
+#endif
+	} s;
+};
+
+/**
+ * struct lbc_inval_ctl - LBC invalidation control register
+ * @wait_timer: Wait timer for wait state. [WAIT_TIMER] must
+ *   always be written with its reset value.
+ * @cam_inval_start: Software should write [CAM_INVAL_START]=1
+ *   to initiate an LBC cache invalidation. After this, software
+ *   should read LBC_INVAL_STATUS until LBC_INVAL_STATUS[DONE] is set.
+ *   LBC hardware clears [CAVM_INVAL_START] before software can
+ *   observed LBC_INVAL_STATUS[DONE] to be set
+ */
+union lbc_inval_ctl {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz2 : 48;
+		u64 wait_timer : 8;
+		u64 raz1 : 6;
+		u64 cam_inval_start : 1;
+		u64 raz0 : 1;
+#else
+		u64 raz0 : 1;
+		u64 cam_inval_start : 1;
+		u64 raz1 : 6;
+		u64 wait_timer : 8;
+		u64 raz2 : 48;
+#endif
+	} s;
+};
+
+/**
+ * struct lbc_int_ena_w1s - LBC interrupt enable set register
+ * @cam_hard_err: Reads or sets enable for LBC_INT[CAM_HARD_ERR].
+ * @cam_inval_abort: Reads or sets enable for LBC_INT[CAM_INVAL_ABORT].
+ * @over_fetch_err: Reads or sets enable for LBC_INT[OVER_FETCH_ERR].
+ * @cache_line_to_err: Reads or sets enable for
+ *   LBC_INT[CACHE_LINE_TO_ERR].
+ * @cam_soft_err: Reads or sets enable for
+ *   LBC_INT[CAM_SOFT_ERR].
+ * @dma_rd_err: Reads or sets enable for
+ *   LBC_INT[DMA_RD_ERR].
+ */
+union lbc_int_ena_w1s {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz_10_63 : 54;
+		u64 cam_hard_err : 1;
+		u64 cam_inval_abort : 1;
+		u64 over_fetch_err : 1;
+		u64 cache_line_to_err : 1;
+		u64 raz_2_5 : 4;
+		u64 cam_soft_err : 1;
+		u64 dma_rd_err : 1;
+#else
+		u64 dma_rd_err : 1;
+		u64 cam_soft_err : 1;
+		u64 raz_2_5 : 4;
+		u64 cache_line_to_err : 1;
+		u64 over_fetch_err : 1;
+		u64 cam_inval_abort : 1;
+		u64 cam_hard_err : 1;
+		u64 raz_10_63 : 54;
+#endif
+	} s;
+};
+
+/**
+ * struct lbc_int - LBC interrupt summary register
+ * @cam_hard_err: indicates a fatal hardware error.
+ *   It requires system reset.
+ *   When [CAM_HARD_ERR] is set, LBC stops logging any new information in
+ *   LBC_POM_MISS_INFO_LOG,
+ *   LBC_POM_MISS_ADDR_LOG,
+ *   LBC_EFL_MISS_INFO_LOG, and
+ *   LBC_EFL_MISS_ADDR_LOG.
+ *   Software should sample them.
+ * @cam_inval_abort: indicates a fatal hardware error.
+ *   System reset is required.
+ * @over_fetch_err: indicates a fatal hardware error
+ *   System reset is required
+ * @cache_line_to_err: is a debug feature.
+ *   This timeout interrupt bit tells the software that
+ *   a cacheline in LBC has non-zero usage and the context
+ *   has not been used for greater than the
+ *   LBC_TO_CNT[TO_CNT] time interval.
+ * @sbe: Memory SBE error. This is recoverable via ECC.
+ *   See LBC_ECC_INT for more details.
+ * @dbe: Memory DBE error. This is a fatal and requires a
+ *   system reset.
+ * @pref_dat_len_mismatch_err: Summary bit for context length
+ *   mismatch errors.
+ * @rd_dat_len_mismatch_err: Summary bit for SE read data length
+ *   greater than data prefect length errors.
+ * @cam_soft_err: is recoverable. Software must complete a
+ *   LBC_INVAL_CTL[CAM_INVAL_START] invalidation sequence and
+ *   then clear [CAM_SOFT_ERR].
+ * @dma_rd_err: A context prefect read of host memory returned with
+ *   a read error.
+ */
+union lbc_int {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz_10_63 : 54;
+		u64 cam_hard_err : 1;
+		u64 cam_inval_abort : 1;
+		u64 over_fetch_err : 1;
+		u64 cache_line_to_err : 1;
+		u64 sbe : 1;
+		u64 dbe	: 1;
+		u64 pref_dat_len_mismatch_err : 1;
+		u64 rd_dat_len_mismatch_err : 1;
+		u64 cam_soft_err : 1;
+		u64 dma_rd_err : 1;
+#else
+		u64 dma_rd_err : 1;
+		u64 cam_soft_err : 1;
+		u64 rd_dat_len_mismatch_err : 1;
+		u64 pref_dat_len_mismatch_err : 1;
+		u64 dbe	: 1;
+		u64 sbe	: 1;
+		u64 cache_line_to_err : 1;
+		u64 over_fetch_err : 1;
+		u64 cam_inval_abort : 1;
+		u64 cam_hard_err : 1;
+		u64 raz_10_63 : 54;
+#endif
+	} s;
+};
+
+/**
+ * struct lbc_inval_status: LBC Invalidation status register
+ * @cam_clean_entry_complete_cnt: The number of entries that are
+ *   cleaned up successfully.
+ * @cam_clean_entry_cnt: The number of entries that have the CAM
+ *   inval command issued.
+ * @cam_inval_state: cam invalidation FSM state
+ * @cam_inval_abort: cam invalidation abort
+ * @cam_rst_rdy: lbc_cam reset ready
+ * @done: LBC clears [DONE] when
+ *   LBC_INVAL_CTL[CAM_INVAL_START] is written with a one,
+ *   and sets [DONE] when it completes the invalidation
+ *   sequence.
+ */
+union lbc_inval_status {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz3 : 23;
+		u64 cam_clean_entry_complete_cnt : 9;
+		u64 raz2 : 7;
+		u64 cam_clean_entry_cnt : 9;
+		u64 raz1 : 5;
+		u64 cam_inval_state : 3;
+		u64 raz0 : 5;
+		u64 cam_inval_abort : 1;
+		u64 cam_rst_rdy	: 1;
+		u64 done : 1;
+#else
+		u64 done : 1;
+		u64 cam_rst_rdy : 1;
+		u64 cam_inval_abort : 1;
+		u64 raz0 : 5;
+		u64 cam_inval_state : 3;
+		u64 raz1 : 5;
+		u64 cam_clean_entry_cnt : 9;
+		u64 raz2 : 7;
+		u64 cam_clean_entry_complete_cnt : 9;
+		u64 raz3 : 23;
+#endif
+	} s;
+};
+
+/**
+ * struct rst_boot: RST Boot Register
+ * @jtcsrdis: when set, internal CSR access via JTAG TAP controller
+ *   is disabled
+ * @jt_tst_mode: JTAG test mode
+ * @io_supply: I/O power supply setting based on IO_VDD_SELECT pin:
+ *    0x1 = 1.8V
+ *    0x2 = 2.5V
+ *    0x4 = 3.3V
+ *    All other values are reserved
+ * @pnr_mul: clock multiplier
+ * @lboot: last boot cause mask, resets only with PLL_DC_OK
+ * @rboot: determines whether core 0 remains in reset after
+ *    chip cold or warm or soft reset
+ * @rboot_pin: read only access to REMOTE_BOOT pin
+ */
+union rst_boot {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz_63 : 1;
+		u64 jtcsrdis : 1;
+		u64 raz_59_61 : 3;
+		u64 jt_tst_mode : 1;
+		u64 raz_40_57 : 18;
+		u64 io_supply : 3;
+		u64 raz_30_36 : 7;
+		u64 pnr_mul : 6;
+		u64 raz_12_23 : 12;
+		u64 lboot : 10;
+		u64 rboot : 1;
+		u64 rboot_pin : 1;
+#else
+		u64 rboot_pin : 1;
+		u64 rboot : 1;
+		u64 lboot : 10;
+		u64 raz_12_23 : 12;
+		u64 pnr_mul : 6;
+		u64 raz_30_36 : 7;
+		u64 io_supply : 3;
+		u64 raz_40_57 : 18;
+		u64 jt_tst_mode : 1;
+		u64 raz_59_61 : 3;
+		u64 jtcsrdis : 1;
+		u64 raz_63 : 1;
+#endif
+	};
+};
+
+/**
+ * struct fus_dat1: Fuse Data 1 Register
+ * @pll_mul: main clock PLL multiplier hardware limit
+ * @pll_half_dis: main clock PLL control
+ * @efus_lck: efuse lockdown
+ * @zip_info: ZIP information
+ * @bar2_sz_conf: when zero, BAR2 size conforms to
+ *    PCIe specification
+ * @efus_ign: efuse ignore
+ * @nozip: ZIP disable
+ * @pll_alt_matrix: select alternate PLL matrix
+ * @pll_bwadj_denom: select CLKF denominator for
+ *    BWADJ value
+ * @chip_id: chip ID
+ */
+union fus_dat1 {
+	u64 value;
+	struct {
+#if (defined(__BIG_ENDIAN_BITFIELD))
+		u64 raz_57_63 : 7;
+		u64 pll_mul : 3;
+		u64 pll_half_dis : 1;
+		u64 raz_43_52 : 10;
+		u64 efus_lck : 3;
+		u64 raz_26_39 : 14;
+		u64 zip_info : 5;
+		u64 bar2_sz_conf : 1;
+		u64 efus_ign : 1;
+		u64 nozip : 1;
+		u64 raz_11_17 : 7;
+		u64 pll_alt_matrix : 1;
+		u64 pll_bwadj_denom : 2;
+		u64 chip_id : 8;
+#else
+		u64 chip_id : 8;
+		u64 pll_bwadj_denom : 2;
+		u64 pll_alt_matrix : 1;
+		u64 raz_11_17 : 7;
+		u64 nozip : 1;
+		u64 efus_ign : 1;
+		u64 bar2_sz_conf : 1;
+		u64 zip_info : 5;
+		u64 raz_26_39 : 14;
+		u64 efus_lck : 3;
+		u64 raz_43_52 : 10;
+		u64 pll_half_dis : 1;
+		u64 pll_mul : 3;
+		u64 raz_57_63 : 7;
+#endif
+	};
+};
+
+#endif /* __NITROX_CSR_H */
diff --git a/drivers/crypto/cavium/nitrox/nitrox_debugfs.c b/drivers/crypto/cavium/nitrox/nitrox_debugfs.c
new file mode 100644
index 000000000..741572a01
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/nitrox_debugfs.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+
+#include "nitrox_csr.h"
+#include "nitrox_debugfs.h"
+#include "nitrox_dev.h"
+
+static int firmware_show(struct seq_file *s, void *v)
+{
+	struct nitrox_device *ndev = s->private;
+
+	seq_printf(s, "Version: %s\n", ndev->hw.fw_name[0]);
+	seq_printf(s, "Version: %s\n", ndev->hw.fw_name[1]);
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(firmware);
+
+static int device_show(struct seq_file *s, void *v)
+{
+	struct nitrox_device *ndev = s->private;
+
+	seq_printf(s, "NITROX [%d]\n", ndev->idx);
+	seq_printf(s, "  Part Name: %s\n", ndev->hw.partname);
+	seq_printf(s, "  Frequency: %d MHz\n", ndev->hw.freq);
+	seq_printf(s, "  Device ID: 0x%0x\n", ndev->hw.device_id);
+	seq_printf(s, "  Revision ID: 0x%0x\n", ndev->hw.revision_id);
+	seq_printf(s, "  Cores: [AE=%u  SE=%u  ZIP=%u]\n",
+		   ndev->hw.ae_cores, ndev->hw.se_cores, ndev->hw.zip_cores);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(device);
+
+static int stats_show(struct seq_file *s, void *v)
+{
+	struct nitrox_device *ndev = s->private;
+
+	seq_printf(s, "NITROX [%d] Request Statistics\n", ndev->idx);
+	seq_printf(s, "  Posted: %llu\n",
+		   (u64)atomic64_read(&ndev->stats.posted));
+	seq_printf(s, "  Completed: %llu\n",
+		   (u64)atomic64_read(&ndev->stats.completed));
+	seq_printf(s, "  Dropped: %llu\n",
+		   (u64)atomic64_read(&ndev->stats.dropped));
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(stats);
+
+void nitrox_debugfs_exit(struct nitrox_device *ndev)
+{
+	debugfs_remove_recursive(ndev->debugfs_dir);
+	ndev->debugfs_dir = NULL;
+}
+
+void nitrox_debugfs_init(struct nitrox_device *ndev)
+{
+	struct dentry *dir;
+
+	dir = debugfs_create_dir(KBUILD_MODNAME, NULL);
+
+	ndev->debugfs_dir = dir;
+	debugfs_create_file("firmware", 0400, dir, ndev, &firmware_fops);
+	debugfs_create_file("device", 0400, dir, ndev, &device_fops);
+	debugfs_create_file("stats", 0400, dir, ndev, &stats_fops);
+}
diff --git a/drivers/crypto/cavium/nitrox/nitrox_debugfs.h b/drivers/crypto/cavium/nitrox/nitrox_debugfs.h
new file mode 100644
index 000000000..09c4cf251
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/nitrox_debugfs.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NITROX_DEBUGFS_H
+#define __NITROX_DEBUGFS_H
+
+#include "nitrox_dev.h"
+
+#ifdef CONFIG_DEBUG_FS
+void nitrox_debugfs_init(struct nitrox_device *ndev);
+void nitrox_debugfs_exit(struct nitrox_device *ndev);
+#else
+static inline void nitrox_debugfs_init(struct nitrox_device *ndev)
+{
+}
+
+static inline void nitrox_debugfs_exit(struct nitrox_device *ndev)
+{
+}
+#endif /* !CONFIG_DEBUG_FS */
+
+#endif /* __NITROX_DEBUGFS_H */
diff --git a/drivers/crypto/cavium/nitrox/nitrox_dev.h b/drivers/crypto/cavium/nitrox/nitrox_dev.h
new file mode 100644
index 000000000..c2d0c23fb
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/nitrox_dev.h
@@ -0,0 +1,302 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NITROX_DEV_H
+#define __NITROX_DEV_H
+
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/if.h>
+
+#define VERSION_LEN 32
+/* Maximum queues in PF mode */
+#define MAX_PF_QUEUES	64
+/* Maximum device queues */
+#define MAX_DEV_QUEUES (MAX_PF_QUEUES)
+/* Maximum UCD Blocks */
+#define CNN55XX_MAX_UCD_BLOCKS	8
+
+/**
+ * struct nitrox_cmdq - NITROX command queue
+ * @cmd_qlock: command queue lock
+ * @resp_qlock: response queue lock
+ * @backlog_qlock: backlog queue lock
+ * @ndev: NITROX device
+ * @response_head: submitted request list
+ * @backlog_head: backlog queue
+ * @dbell_csr_addr: doorbell register address for this queue
+ * @compl_cnt_csr_addr: completion count register address of the slc port
+ * @base: command queue base address
+ * @dma: dma address of the base
+ * @pending_count: request pending at device
+ * @backlog_count: backlog request count
+ * @write_idx: next write index for the command
+ * @instr_size: command size
+ * @qno: command queue number
+ * @qsize: command queue size
+ * @unalign_base: unaligned base address
+ * @unalign_dma: unaligned dma address
+ */
+struct nitrox_cmdq {
+	spinlock_t cmd_qlock;
+	spinlock_t resp_qlock;
+	spinlock_t backlog_qlock;
+
+	struct nitrox_device *ndev;
+	struct list_head response_head;
+	struct list_head backlog_head;
+
+	u8 __iomem *dbell_csr_addr;
+	u8 __iomem *compl_cnt_csr_addr;
+	u8 *base;
+	dma_addr_t dma;
+
+	struct work_struct backlog_qflush;
+
+	atomic_t pending_count;
+	atomic_t backlog_count;
+
+	int write_idx;
+	u8 instr_size;
+	u8 qno;
+	u32 qsize;
+
+	u8 *unalign_base;
+	dma_addr_t unalign_dma;
+};
+
+/**
+ * struct nitrox_hw - NITROX hardware information
+ * @partname: partname ex: CNN55xxx-xxx
+ * @fw_name: firmware version
+ * @freq: NITROX frequency
+ * @vendor_id: vendor ID
+ * @device_id: device ID
+ * @revision_id: revision ID
+ * @se_cores: number of symmetric cores
+ * @ae_cores: number of asymmetric cores
+ * @zip_cores: number of zip cores
+ */
+struct nitrox_hw {
+	char partname[IFNAMSIZ * 2];
+	char fw_name[CNN55XX_MAX_UCD_BLOCKS][VERSION_LEN];
+
+	int freq;
+	u16 vendor_id;
+	u16 device_id;
+	u8 revision_id;
+
+	u8 se_cores;
+	u8 ae_cores;
+	u8 zip_cores;
+};
+
+struct nitrox_stats {
+	atomic64_t posted;
+	atomic64_t completed;
+	atomic64_t dropped;
+};
+
+#define IRQ_NAMESZ	32
+
+struct nitrox_q_vector {
+	char name[IRQ_NAMESZ];
+	bool valid;
+	int ring;
+	struct tasklet_struct resp_tasklet;
+	union {
+		struct nitrox_cmdq *cmdq;
+		struct nitrox_device *ndev;
+	};
+};
+
+enum mcode_type {
+	MCODE_TYPE_INVALID,
+	MCODE_TYPE_AE,
+	MCODE_TYPE_SE_SSL,
+	MCODE_TYPE_SE_IPSEC,
+};
+
+/**
+ * mbox_msg - Mailbox message data
+ * @type: message type
+ * @opcode: message opcode
+ * @data: message data
+ */
+union mbox_msg {
+	u64 value;
+	struct {
+		u64 type: 2;
+		u64 opcode: 6;
+		u64 data: 58;
+	};
+	struct {
+		u64 type: 2;
+		u64 opcode: 6;
+		u64 chipid: 8;
+		u64 vfid: 8;
+	} id;
+	struct {
+		u64 type: 2;
+		u64 opcode: 6;
+		u64 count: 4;
+		u64 info: 40;
+		u64 next_se_grp: 3;
+		u64 next_ae_grp: 3;
+	} mcode_info;
+};
+
+/**
+ * nitrox_vfdev - NITROX VF device instance in PF
+ * @state: VF device state
+ * @vfno: VF number
+ * @nr_queues: number of queues enabled in VF
+ * @ring: ring to communicate with VF
+ * @msg: Mailbox message data from VF
+ * @mbx_resp: Mailbox counters
+ */
+struct nitrox_vfdev {
+	atomic_t state;
+	int vfno;
+	int nr_queues;
+	int ring;
+	union mbox_msg msg;
+	atomic64_t mbx_resp;
+};
+
+/**
+ * struct nitrox_iov - SR-IOV information
+ * @num_vfs: number of VF(s) enabled
+ * @max_vf_queues: Maximum number of queues allowed for VF
+ * @vfdev: VF(s) devices
+ * @pf2vf_wq: workqueue for PF2VF communication
+ * @msix: MSI-X entry for PF in SR-IOV case
+ */
+struct nitrox_iov {
+	int num_vfs;
+	int max_vf_queues;
+	struct nitrox_vfdev *vfdev;
+	struct workqueue_struct *pf2vf_wq;
+	struct msix_entry msix;
+};
+
+/*
+ * NITROX Device states
+ */
+enum ndev_state {
+	__NDEV_NOT_READY,
+	__NDEV_READY,
+	__NDEV_IN_RESET,
+};
+
+/* NITROX support modes for VF(s) */
+enum vf_mode {
+	__NDEV_MODE_PF,
+	__NDEV_MODE_VF16,
+	__NDEV_MODE_VF32,
+	__NDEV_MODE_VF64,
+	__NDEV_MODE_VF128,
+};
+
+#define __NDEV_SRIOV_BIT 0
+
+/* command queue size */
+#define DEFAULT_CMD_QLEN 2048
+/* command timeout in milliseconds */
+#define CMD_TIMEOUT 2000
+
+#define DEV(ndev) ((struct device *)(&(ndev)->pdev->dev))
+
+#define NITROX_CSR_ADDR(ndev, offset) \
+	((ndev)->bar_addr + (offset))
+
+/**
+ * struct nitrox_device - NITROX Device Information.
+ * @list: pointer to linked list of devices
+ * @bar_addr: iomap address
+ * @pdev: PCI device information
+ * @state: NITROX device state
+ * @flags: flags to indicate device the features
+ * @timeout: Request timeout in jiffies
+ * @refcnt: Device usage count
+ * @idx: device index (0..N)
+ * @node: NUMA node id attached
+ * @qlen: Command queue length
+ * @nr_queues: Number of command queues
+ * @mode: Device mode PF/VF
+ * @ctx_pool: DMA pool for crypto context
+ * @pkt_inq: Packet input rings
+ * @aqmq: AQM command queues
+ * @qvec: MSI-X queue vectors information
+ * @iov: SR-IOV informatin
+ * @num_vecs: number of MSI-X vectors
+ * @stats: request statistics
+ * @hw: hardware information
+ * @debugfs_dir: debugfs directory
+ */
+struct nitrox_device {
+	struct list_head list;
+
+	u8 __iomem *bar_addr;
+	struct pci_dev *pdev;
+
+	atomic_t state;
+	unsigned long flags;
+	unsigned long timeout;
+	refcount_t refcnt;
+
+	u8 idx;
+	int node;
+	u16 qlen;
+	u16 nr_queues;
+	enum vf_mode mode;
+
+	struct dma_pool *ctx_pool;
+	struct nitrox_cmdq *pkt_inq;
+	struct nitrox_cmdq *aqmq[MAX_DEV_QUEUES] ____cacheline_aligned_in_smp;
+
+	struct nitrox_q_vector *qvec;
+	struct nitrox_iov iov;
+	int num_vecs;
+
+	struct nitrox_stats stats;
+	struct nitrox_hw hw;
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+	struct dentry *debugfs_dir;
+#endif
+};
+
+/**
+ * nitrox_read_csr - Read from device register
+ * @ndev: NITROX device
+ * @offset: offset of the register to read
+ *
+ * Returns: value read
+ */
+static inline u64 nitrox_read_csr(struct nitrox_device *ndev, u64 offset)
+{
+	return readq(ndev->bar_addr + offset);
+}
+
+/**
+ * nitrox_write_csr - Write to device register
+ * @ndev: NITROX device
+ * @offset: offset of the register to write
+ * @value: value to write
+ */
+static inline void nitrox_write_csr(struct nitrox_device *ndev, u64 offset,
+				    u64 value)
+{
+	writeq(value, (ndev->bar_addr + offset));
+}
+
+static inline bool nitrox_ready(struct nitrox_device *ndev)
+{
+	return atomic_read(&ndev->state) == __NDEV_READY;
+}
+
+static inline bool nitrox_vfdev_ready(struct nitrox_vfdev *vfdev)
+{
+	return atomic_read(&vfdev->state) == __NDEV_READY;
+}
+
+#endif /* __NITROX_DEV_H */
diff --git a/drivers/crypto/cavium/nitrox/nitrox_hal.c b/drivers/crypto/cavium/nitrox/nitrox_hal.c
new file mode 100644
index 000000000..e36c1741b
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/nitrox_hal.c
@@ -0,0 +1,680 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/delay.h>
+#include <linux/string.h>
+
+#include "nitrox_dev.h"
+#include "nitrox_csr.h"
+#include "nitrox_hal.h"
+
+#define PLL_REF_CLK 50
+#define MAX_CSR_RETRIES 10
+
+/**
+ * emu_enable_cores - Enable EMU cluster cores.
+ * @ndev: NITROX device
+ */
+static void emu_enable_cores(struct nitrox_device *ndev)
+{
+	union emu_se_enable emu_se;
+	union emu_ae_enable emu_ae;
+	int i;
+
+	/* AE cores 20 per cluster */
+	emu_ae.value = 0;
+	emu_ae.s.enable = 0xfffff;
+
+	/* SE cores 16 per cluster */
+	emu_se.value = 0;
+	emu_se.s.enable = 0xffff;
+
+	/* enable per cluster cores */
+	for (i = 0; i < NR_CLUSTERS; i++) {
+		nitrox_write_csr(ndev, EMU_AE_ENABLEX(i), emu_ae.value);
+		nitrox_write_csr(ndev, EMU_SE_ENABLEX(i), emu_se.value);
+	}
+}
+
+/**
+ * nitrox_config_emu_unit - configure EMU unit.
+ * @ndev: NITROX device
+ */
+void nitrox_config_emu_unit(struct nitrox_device *ndev)
+{
+	union emu_wd_int_ena_w1s emu_wd_int;
+	union emu_ge_int_ena_w1s emu_ge_int;
+	u64 offset;
+	int i;
+
+	/* enable cores */
+	emu_enable_cores(ndev);
+
+	/* enable general error and watch dog interrupts */
+	emu_ge_int.value = 0;
+	emu_ge_int.s.se_ge = 0xffff;
+	emu_ge_int.s.ae_ge = 0xfffff;
+	emu_wd_int.value = 0;
+	emu_wd_int.s.se_wd = 1;
+
+	for (i = 0; i < NR_CLUSTERS; i++) {
+		offset = EMU_WD_INT_ENA_W1SX(i);
+		nitrox_write_csr(ndev, offset, emu_wd_int.value);
+		offset = EMU_GE_INT_ENA_W1SX(i);
+		nitrox_write_csr(ndev, offset, emu_ge_int.value);
+	}
+}
+
+static void reset_pkt_input_ring(struct nitrox_device *ndev, int ring)
+{
+	union nps_pkt_in_instr_ctl pkt_in_ctl;
+	union nps_pkt_in_done_cnts pkt_in_cnts;
+	int max_retries = MAX_CSR_RETRIES;
+	u64 offset;
+
+	/* step 1: disable the ring, clear enable bit */
+	offset = NPS_PKT_IN_INSTR_CTLX(ring);
+	pkt_in_ctl.value = nitrox_read_csr(ndev, offset);
+	pkt_in_ctl.s.enb = 0;
+	nitrox_write_csr(ndev, offset, pkt_in_ctl.value);
+
+	/* step 2: wait to clear [ENB] */
+	usleep_range(100, 150);
+	do {
+		pkt_in_ctl.value = nitrox_read_csr(ndev, offset);
+		if (!pkt_in_ctl.s.enb)
+			break;
+		udelay(50);
+	} while (max_retries--);
+
+	/* step 3: clear done counts */
+	offset = NPS_PKT_IN_DONE_CNTSX(ring);
+	pkt_in_cnts.value = nitrox_read_csr(ndev, offset);
+	nitrox_write_csr(ndev, offset, pkt_in_cnts.value);
+	usleep_range(50, 100);
+}
+
+void enable_pkt_input_ring(struct nitrox_device *ndev, int ring)
+{
+	union nps_pkt_in_instr_ctl pkt_in_ctl;
+	int max_retries = MAX_CSR_RETRIES;
+	u64 offset;
+
+	/* 64-byte instruction size */
+	offset = NPS_PKT_IN_INSTR_CTLX(ring);
+	pkt_in_ctl.value = nitrox_read_csr(ndev, offset);
+	pkt_in_ctl.s.is64b = 1;
+	pkt_in_ctl.s.enb = 1;
+	nitrox_write_csr(ndev, offset, pkt_in_ctl.value);
+
+	/* wait for set [ENB] */
+	do {
+		pkt_in_ctl.value = nitrox_read_csr(ndev, offset);
+		if (pkt_in_ctl.s.enb)
+			break;
+		udelay(50);
+	} while (max_retries--);
+}
+
+/**
+ * nitrox_config_pkt_input_rings - configure Packet Input Rings
+ * @ndev: NITROX device
+ */
+void nitrox_config_pkt_input_rings(struct nitrox_device *ndev)
+{
+	int i;
+
+	for (i = 0; i < ndev->nr_queues; i++) {
+		struct nitrox_cmdq *cmdq = &ndev->pkt_inq[i];
+		union nps_pkt_in_instr_rsize pkt_in_rsize;
+		union nps_pkt_in_instr_baoff_dbell pkt_in_dbell;
+		u64 offset;
+
+		reset_pkt_input_ring(ndev, i);
+
+		/**
+		 * step 4:
+		 * configure ring base address 16-byte aligned,
+		 * size and interrupt threshold.
+		 */
+		offset = NPS_PKT_IN_INSTR_BADDRX(i);
+		nitrox_write_csr(ndev, offset, cmdq->dma);
+
+		/* configure ring size */
+		offset = NPS_PKT_IN_INSTR_RSIZEX(i);
+		pkt_in_rsize.value = 0;
+		pkt_in_rsize.s.rsize = ndev->qlen;
+		nitrox_write_csr(ndev, offset, pkt_in_rsize.value);
+
+		/* set high threshold for pkt input ring interrupts */
+		offset = NPS_PKT_IN_INT_LEVELSX(i);
+		nitrox_write_csr(ndev, offset, 0xffffffff);
+
+		/* step 5: clear off door bell counts */
+		offset = NPS_PKT_IN_INSTR_BAOFF_DBELLX(i);
+		pkt_in_dbell.value = 0;
+		pkt_in_dbell.s.dbell = 0xffffffff;
+		nitrox_write_csr(ndev, offset, pkt_in_dbell.value);
+
+		/* enable the ring */
+		enable_pkt_input_ring(ndev, i);
+	}
+}
+
+static void reset_pkt_solicit_port(struct nitrox_device *ndev, int port)
+{
+	union nps_pkt_slc_ctl pkt_slc_ctl;
+	union nps_pkt_slc_cnts pkt_slc_cnts;
+	int max_retries = MAX_CSR_RETRIES;
+	u64 offset;
+
+	/* step 1: disable slc port */
+	offset = NPS_PKT_SLC_CTLX(port);
+	pkt_slc_ctl.value = nitrox_read_csr(ndev, offset);
+	pkt_slc_ctl.s.enb = 0;
+	nitrox_write_csr(ndev, offset, pkt_slc_ctl.value);
+
+	/* step 2 */
+	usleep_range(100, 150);
+	/* wait to clear [ENB] */
+	do {
+		pkt_slc_ctl.value = nitrox_read_csr(ndev, offset);
+		if (!pkt_slc_ctl.s.enb)
+			break;
+		udelay(50);
+	} while (max_retries--);
+
+	/* step 3: clear slc counters */
+	offset = NPS_PKT_SLC_CNTSX(port);
+	pkt_slc_cnts.value = nitrox_read_csr(ndev, offset);
+	nitrox_write_csr(ndev, offset, pkt_slc_cnts.value);
+	usleep_range(50, 100);
+}
+
+void enable_pkt_solicit_port(struct nitrox_device *ndev, int port)
+{
+	union nps_pkt_slc_ctl pkt_slc_ctl;
+	int max_retries = MAX_CSR_RETRIES;
+	u64 offset;
+
+	offset = NPS_PKT_SLC_CTLX(port);
+	pkt_slc_ctl.value = 0;
+	pkt_slc_ctl.s.enb = 1;
+	/*
+	 * 8 trailing 0x00 bytes will be added
+	 * to the end of the outgoing packet.
+	 */
+	pkt_slc_ctl.s.z = 1;
+	/* enable response header */
+	pkt_slc_ctl.s.rh = 1;
+	nitrox_write_csr(ndev, offset, pkt_slc_ctl.value);
+
+	/* wait to set [ENB] */
+	do {
+		pkt_slc_ctl.value = nitrox_read_csr(ndev, offset);
+		if (pkt_slc_ctl.s.enb)
+			break;
+		udelay(50);
+	} while (max_retries--);
+}
+
+static void config_pkt_solicit_port(struct nitrox_device *ndev, int port)
+{
+	union nps_pkt_slc_int_levels pkt_slc_int;
+	u64 offset;
+
+	reset_pkt_solicit_port(ndev, port);
+
+	/* step 4: configure interrupt levels */
+	offset = NPS_PKT_SLC_INT_LEVELSX(port);
+	pkt_slc_int.value = 0;
+	/* time interrupt threshold */
+	pkt_slc_int.s.timet = 0x3fffff;
+	nitrox_write_csr(ndev, offset, pkt_slc_int.value);
+
+	/* enable the solicit port */
+	enable_pkt_solicit_port(ndev, port);
+}
+
+void nitrox_config_pkt_solicit_ports(struct nitrox_device *ndev)
+{
+	int i;
+
+	for (i = 0; i < ndev->nr_queues; i++)
+		config_pkt_solicit_port(ndev, i);
+}
+
+/**
+ * enable_nps_core_interrupts - enable NPS core interrutps
+ * @ndev: NITROX device.
+ *
+ * This includes NPS core interrupts.
+ */
+static void enable_nps_core_interrupts(struct nitrox_device *ndev)
+{
+	union nps_core_int_ena_w1s core_int;
+
+	/* NPS core interrutps */
+	core_int.value = 0;
+	core_int.s.host_wr_err = 1;
+	core_int.s.host_wr_timeout = 1;
+	core_int.s.exec_wr_timeout = 1;
+	core_int.s.npco_dma_malform = 1;
+	core_int.s.host_nps_wr_err = 1;
+	nitrox_write_csr(ndev, NPS_CORE_INT_ENA_W1S, core_int.value);
+}
+
+void nitrox_config_nps_core_unit(struct nitrox_device *ndev)
+{
+	union nps_core_gbl_vfcfg core_gbl_vfcfg;
+
+	/* endian control information */
+	nitrox_write_csr(ndev, NPS_CORE_CONTROL, 1ULL);
+
+	/* disable ILK interface */
+	core_gbl_vfcfg.value = 0;
+	core_gbl_vfcfg.s.ilk_disable = 1;
+	core_gbl_vfcfg.s.cfg = __NDEV_MODE_PF;
+	nitrox_write_csr(ndev, NPS_CORE_GBL_VFCFG, core_gbl_vfcfg.value);
+
+	/* enable nps core interrupts */
+	enable_nps_core_interrupts(ndev);
+}
+
+/**
+ * enable_nps_pkt_interrupts - enable NPS packet interrutps
+ * @ndev: NITROX device.
+ *
+ * This includes NPS packet in and slc interrupts.
+ */
+static void enable_nps_pkt_interrupts(struct nitrox_device *ndev)
+{
+	/* NPS packet in ring interrupts */
+	nitrox_write_csr(ndev, NPS_PKT_IN_RERR_LO_ENA_W1S, (~0ULL));
+	nitrox_write_csr(ndev, NPS_PKT_IN_RERR_HI_ENA_W1S, (~0ULL));
+	nitrox_write_csr(ndev, NPS_PKT_IN_ERR_TYPE_ENA_W1S, (~0ULL));
+	/* NPS packet slc port interrupts */
+	nitrox_write_csr(ndev, NPS_PKT_SLC_RERR_HI_ENA_W1S, (~0ULL));
+	nitrox_write_csr(ndev, NPS_PKT_SLC_RERR_LO_ENA_W1S, (~0ULL));
+	nitrox_write_csr(ndev, NPS_PKT_SLC_ERR_TYPE_ENA_W1S, (~0uLL));
+}
+
+void nitrox_config_nps_pkt_unit(struct nitrox_device *ndev)
+{
+	/* config input and solicit ports */
+	nitrox_config_pkt_input_rings(ndev);
+	nitrox_config_pkt_solicit_ports(ndev);
+
+	/* enable nps packet interrupts */
+	enable_nps_pkt_interrupts(ndev);
+}
+
+static void reset_aqm_ring(struct nitrox_device *ndev, int ring)
+{
+	union aqmq_en aqmq_en_reg;
+	union aqmq_activity_stat activity_stat;
+	union aqmq_cmp_cnt cmp_cnt;
+	int max_retries = MAX_CSR_RETRIES;
+	u64 offset;
+
+	/* step 1: disable the queue */
+	offset = AQMQ_ENX(ring);
+	aqmq_en_reg.value = 0;
+	aqmq_en_reg.queue_enable = 0;
+	nitrox_write_csr(ndev, offset, aqmq_en_reg.value);
+
+	/* step 2: wait for AQMQ_ACTIVITY_STATX[QUEUE_ACTIVE] to clear */
+	usleep_range(100, 150);
+	offset = AQMQ_ACTIVITY_STATX(ring);
+	do {
+		activity_stat.value = nitrox_read_csr(ndev, offset);
+		if (!activity_stat.queue_active)
+			break;
+		udelay(50);
+	} while (max_retries--);
+
+	/* step 3: clear commands completed count */
+	offset = AQMQ_CMP_CNTX(ring);
+	cmp_cnt.value = nitrox_read_csr(ndev, offset);
+	nitrox_write_csr(ndev, offset, cmp_cnt.value);
+	usleep_range(50, 100);
+}
+
+void enable_aqm_ring(struct nitrox_device *ndev, int ring)
+{
+	union aqmq_en aqmq_en_reg;
+	u64 offset;
+
+	offset = AQMQ_ENX(ring);
+	aqmq_en_reg.value = 0;
+	aqmq_en_reg.queue_enable = 1;
+	nitrox_write_csr(ndev, offset, aqmq_en_reg.value);
+	usleep_range(50, 100);
+}
+
+void nitrox_config_aqm_rings(struct nitrox_device *ndev)
+{
+	int ring;
+
+	for (ring = 0; ring < ndev->nr_queues; ring++) {
+		struct nitrox_cmdq *cmdq = ndev->aqmq[ring];
+		union aqmq_drbl drbl;
+		union aqmq_qsz qsize;
+		union aqmq_cmp_thr cmp_thr;
+		u64 offset;
+
+		/* steps 1 - 3 */
+		reset_aqm_ring(ndev, ring);
+
+		/* step 4: clear doorbell count of ring */
+		offset = AQMQ_DRBLX(ring);
+		drbl.value = 0;
+		drbl.dbell_count = 0xFFFFFFFF;
+		nitrox_write_csr(ndev, offset, drbl.value);
+
+		/* step 5: configure host ring details */
+
+		/* set host address for next command of ring */
+		offset = AQMQ_NXT_CMDX(ring);
+		nitrox_write_csr(ndev, offset, 0ULL);
+
+		/* set host address of ring base */
+		offset = AQMQ_BADRX(ring);
+		nitrox_write_csr(ndev, offset, cmdq->dma);
+
+		/* set ring size */
+		offset = AQMQ_QSZX(ring);
+		qsize.value = 0;
+		qsize.host_queue_size = ndev->qlen;
+		nitrox_write_csr(ndev, offset, qsize.value);
+
+		/* set command completion threshold */
+		offset = AQMQ_CMP_THRX(ring);
+		cmp_thr.value = 0;
+		cmp_thr.commands_completed_threshold = 1;
+		nitrox_write_csr(ndev, offset, cmp_thr.value);
+
+		/* step 6: enable the queue */
+		enable_aqm_ring(ndev, ring);
+	}
+}
+
+static void enable_aqm_interrupts(struct nitrox_device *ndev)
+{
+	/* clear interrupt enable bits */
+	nitrox_write_csr(ndev, AQM_DBELL_OVF_LO_ENA_W1S, (~0ULL));
+	nitrox_write_csr(ndev, AQM_DBELL_OVF_HI_ENA_W1S, (~0ULL));
+	nitrox_write_csr(ndev, AQM_DMA_RD_ERR_LO_ENA_W1S, (~0ULL));
+	nitrox_write_csr(ndev, AQM_DMA_RD_ERR_HI_ENA_W1S, (~0ULL));
+	nitrox_write_csr(ndev, AQM_EXEC_NA_LO_ENA_W1S, (~0ULL));
+	nitrox_write_csr(ndev, AQM_EXEC_NA_HI_ENA_W1S, (~0ULL));
+	nitrox_write_csr(ndev, AQM_EXEC_ERR_LO_ENA_W1S, (~0ULL));
+	nitrox_write_csr(ndev, AQM_EXEC_ERR_HI_ENA_W1S, (~0ULL));
+}
+
+void nitrox_config_aqm_unit(struct nitrox_device *ndev)
+{
+	/* config aqm command queues */
+	nitrox_config_aqm_rings(ndev);
+
+	/* enable aqm interrupts */
+	enable_aqm_interrupts(ndev);
+}
+
+void nitrox_config_pom_unit(struct nitrox_device *ndev)
+{
+	union pom_int_ena_w1s pom_int;
+	int i;
+
+	/* enable pom interrupts */
+	pom_int.value = 0;
+	pom_int.s.illegal_dport = 1;
+	nitrox_write_csr(ndev, POM_INT_ENA_W1S, pom_int.value);
+
+	/* enable perf counters */
+	for (i = 0; i < ndev->hw.se_cores; i++)
+		nitrox_write_csr(ndev, POM_PERF_CTL, BIT_ULL(i));
+}
+
+/**
+ * nitrox_config_rand_unit - enable NITROX random number unit
+ * @ndev: NITROX device
+ */
+void nitrox_config_rand_unit(struct nitrox_device *ndev)
+{
+	union efl_rnm_ctl_status efl_rnm_ctl;
+	u64 offset;
+
+	offset = EFL_RNM_CTL_STATUS;
+	efl_rnm_ctl.value = nitrox_read_csr(ndev, offset);
+	efl_rnm_ctl.s.ent_en = 1;
+	efl_rnm_ctl.s.rng_en = 1;
+	nitrox_write_csr(ndev, offset, efl_rnm_ctl.value);
+}
+
+void nitrox_config_efl_unit(struct nitrox_device *ndev)
+{
+	int i;
+
+	for (i = 0; i < NR_CLUSTERS; i++) {
+		union efl_core_int_ena_w1s efl_core_int;
+		u64 offset;
+
+		/* EFL core interrupts */
+		offset = EFL_CORE_INT_ENA_W1SX(i);
+		efl_core_int.value = 0;
+		efl_core_int.s.len_ovr = 1;
+		efl_core_int.s.d_left = 1;
+		efl_core_int.s.epci_decode_err = 1;
+		nitrox_write_csr(ndev, offset, efl_core_int.value);
+
+		offset = EFL_CORE_VF_ERR_INT0_ENA_W1SX(i);
+		nitrox_write_csr(ndev, offset, (~0ULL));
+		offset = EFL_CORE_VF_ERR_INT1_ENA_W1SX(i);
+		nitrox_write_csr(ndev, offset, (~0ULL));
+	}
+}
+
+void nitrox_config_bmi_unit(struct nitrox_device *ndev)
+{
+	union bmi_ctl bmi_ctl;
+	union bmi_int_ena_w1s bmi_int_ena;
+	u64 offset;
+
+	/* no threshold limits for PCIe */
+	offset = BMI_CTL;
+	bmi_ctl.value = nitrox_read_csr(ndev, offset);
+	bmi_ctl.s.max_pkt_len = 0xff;
+	bmi_ctl.s.nps_free_thrsh = 0xff;
+	bmi_ctl.s.nps_hdrq_thrsh = 0x7a;
+	nitrox_write_csr(ndev, offset, bmi_ctl.value);
+
+	/* enable interrupts */
+	offset = BMI_INT_ENA_W1S;
+	bmi_int_ena.value = 0;
+	bmi_int_ena.s.max_len_err_nps = 1;
+	bmi_int_ena.s.pkt_rcv_err_nps = 1;
+	bmi_int_ena.s.fpf_undrrn = 1;
+	nitrox_write_csr(ndev, offset, bmi_int_ena.value);
+}
+
+void nitrox_config_bmo_unit(struct nitrox_device *ndev)
+{
+	union bmo_ctl2 bmo_ctl2;
+	u64 offset;
+
+	/* no threshold limits for PCIe */
+	offset = BMO_CTL2;
+	bmo_ctl2.value = nitrox_read_csr(ndev, offset);
+	bmo_ctl2.s.nps_slc_buf_thrsh = 0xff;
+	nitrox_write_csr(ndev, offset, bmo_ctl2.value);
+}
+
+void invalidate_lbc(struct nitrox_device *ndev)
+{
+	union lbc_inval_ctl lbc_ctl;
+	union lbc_inval_status lbc_stat;
+	int max_retries = MAX_CSR_RETRIES;
+	u64 offset;
+
+	/* invalidate LBC */
+	offset = LBC_INVAL_CTL;
+	lbc_ctl.value = nitrox_read_csr(ndev, offset);
+	lbc_ctl.s.cam_inval_start = 1;
+	nitrox_write_csr(ndev, offset, lbc_ctl.value);
+
+	offset = LBC_INVAL_STATUS;
+	do {
+		lbc_stat.value = nitrox_read_csr(ndev, offset);
+		if (lbc_stat.s.done)
+			break;
+		udelay(50);
+	} while (max_retries--);
+}
+
+void nitrox_config_lbc_unit(struct nitrox_device *ndev)
+{
+	union lbc_int_ena_w1s lbc_int_ena;
+	u64 offset;
+
+	invalidate_lbc(ndev);
+
+	/* enable interrupts */
+	offset = LBC_INT_ENA_W1S;
+	lbc_int_ena.value = 0;
+	lbc_int_ena.s.dma_rd_err = 1;
+	lbc_int_ena.s.over_fetch_err = 1;
+	lbc_int_ena.s.cam_inval_abort = 1;
+	lbc_int_ena.s.cam_hard_err = 1;
+	nitrox_write_csr(ndev, offset, lbc_int_ena.value);
+
+	offset = LBC_PLM_VF1_64_INT_ENA_W1S;
+	nitrox_write_csr(ndev, offset, (~0ULL));
+	offset = LBC_PLM_VF65_128_INT_ENA_W1S;
+	nitrox_write_csr(ndev, offset, (~0ULL));
+
+	offset = LBC_ELM_VF1_64_INT_ENA_W1S;
+	nitrox_write_csr(ndev, offset, (~0ULL));
+	offset = LBC_ELM_VF65_128_INT_ENA_W1S;
+	nitrox_write_csr(ndev, offset, (~0ULL));
+}
+
+void config_nps_core_vfcfg_mode(struct nitrox_device *ndev, enum vf_mode mode)
+{
+	union nps_core_gbl_vfcfg vfcfg;
+
+	vfcfg.value = nitrox_read_csr(ndev, NPS_CORE_GBL_VFCFG);
+	vfcfg.s.cfg = mode & 0x7;
+
+	nitrox_write_csr(ndev, NPS_CORE_GBL_VFCFG, vfcfg.value);
+}
+
+static const char *get_core_option(u8 se_cores, u8 ae_cores)
+{
+	const char *option = "";
+
+	if (ae_cores == AE_MAX_CORES) {
+		switch (se_cores) {
+		case SE_MAX_CORES:
+			option = "60";
+			break;
+		case 40:
+			option = "60s";
+			break;
+		}
+	} else if (ae_cores == (AE_MAX_CORES / 2)) {
+		option = "30";
+	} else {
+		option = "60i";
+	}
+
+	return option;
+}
+
+static const char *get_feature_option(u8 zip_cores, int core_freq)
+{
+	if (zip_cores == 0)
+		return "";
+	else if (zip_cores < ZIP_MAX_CORES)
+		return "-C15";
+
+	if (core_freq >= 850)
+		return "-C45";
+	else if (core_freq >= 750)
+		return "-C35";
+	else if (core_freq >= 550)
+		return "-C25";
+
+	return "";
+}
+
+void nitrox_get_hwinfo(struct nitrox_device *ndev)
+{
+	union emu_fuse_map emu_fuse;
+	union rst_boot rst_boot;
+	union fus_dat1 fus_dat1;
+	unsigned char name[IFNAMSIZ * 2] = {};
+	int i, dead_cores;
+	u64 offset;
+
+	/* get core frequency */
+	offset = RST_BOOT;
+	rst_boot.value = nitrox_read_csr(ndev, offset);
+	ndev->hw.freq = (rst_boot.pnr_mul + 3) * PLL_REF_CLK;
+
+	for (i = 0; i < NR_CLUSTERS; i++) {
+		offset = EMU_FUSE_MAPX(i);
+		emu_fuse.value = nitrox_read_csr(ndev, offset);
+		if (emu_fuse.s.valid) {
+			dead_cores = hweight32(emu_fuse.s.ae_fuse);
+			ndev->hw.ae_cores += AE_CORES_PER_CLUSTER - dead_cores;
+			dead_cores = hweight16(emu_fuse.s.se_fuse);
+			ndev->hw.se_cores += SE_CORES_PER_CLUSTER - dead_cores;
+		}
+	}
+	/* find zip hardware availability */
+	offset = FUS_DAT1;
+	fus_dat1.value = nitrox_read_csr(ndev, offset);
+	if (!fus_dat1.nozip) {
+		dead_cores = hweight8(fus_dat1.zip_info);
+		ndev->hw.zip_cores = ZIP_MAX_CORES - dead_cores;
+	}
+
+	/* determine the partname
+	 * CNN55<core option>-<freq><pincount>-<feature option>-<rev>
+	 */
+	snprintf(name, sizeof(name), "CNN55%s-%3dBG676%s-1.%u",
+		 get_core_option(ndev->hw.se_cores, ndev->hw.ae_cores),
+		 ndev->hw.freq,
+		 get_feature_option(ndev->hw.zip_cores, ndev->hw.freq),
+		 ndev->hw.revision_id);
+
+	/* copy partname */
+	strscpy(ndev->hw.partname, name);
+}
+
+void enable_pf2vf_mbox_interrupts(struct nitrox_device *ndev)
+{
+	u64 value = ~0ULL;
+	u64 reg_addr;
+
+	/* Mailbox interrupt low enable set register */
+	reg_addr = NPS_PKT_MBOX_INT_LO_ENA_W1S;
+	nitrox_write_csr(ndev, reg_addr, value);
+
+	/* Mailbox interrupt high enable set register */
+	reg_addr = NPS_PKT_MBOX_INT_HI_ENA_W1S;
+	nitrox_write_csr(ndev, reg_addr, value);
+}
+
+void disable_pf2vf_mbox_interrupts(struct nitrox_device *ndev)
+{
+	u64 value = ~0ULL;
+	u64 reg_addr;
+
+	/* Mailbox interrupt low enable clear register */
+	reg_addr = NPS_PKT_MBOX_INT_LO_ENA_W1C;
+	nitrox_write_csr(ndev, reg_addr, value);
+
+	/* Mailbox interrupt high enable clear register */
+	reg_addr = NPS_PKT_MBOX_INT_HI_ENA_W1C;
+	nitrox_write_csr(ndev, reg_addr, value);
+}
diff --git a/drivers/crypto/cavium/nitrox/nitrox_hal.h b/drivers/crypto/cavium/nitrox/nitrox_hal.h
new file mode 100644
index 000000000..48b0af039
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/nitrox_hal.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NITROX_HAL_H
+#define __NITROX_HAL_H
+
+#include "nitrox_dev.h"
+
+void nitrox_config_aqm_rings(struct nitrox_device *ndev);
+void nitrox_config_aqm_unit(struct nitrox_device *ndev);
+void nitrox_config_emu_unit(struct nitrox_device *ndev);
+void nitrox_config_pkt_input_rings(struct nitrox_device *ndev);
+void nitrox_config_pkt_solicit_ports(struct nitrox_device *ndev);
+void nitrox_config_nps_core_unit(struct nitrox_device *ndev);
+void nitrox_config_nps_pkt_unit(struct nitrox_device *ndev);
+void nitrox_config_pom_unit(struct nitrox_device *ndev);
+void nitrox_config_rand_unit(struct nitrox_device *ndev);
+void nitrox_config_efl_unit(struct nitrox_device *ndev);
+void nitrox_config_bmi_unit(struct nitrox_device *ndev);
+void nitrox_config_bmo_unit(struct nitrox_device *ndev);
+void nitrox_config_lbc_unit(struct nitrox_device *ndev);
+void invalidate_lbc(struct nitrox_device *ndev);
+void enable_aqm_ring(struct nitrox_device *ndev, int qno);
+void enable_pkt_input_ring(struct nitrox_device *ndev, int ring);
+void enable_pkt_solicit_port(struct nitrox_device *ndev, int port);
+void config_nps_core_vfcfg_mode(struct nitrox_device *ndev, enum vf_mode mode);
+void nitrox_get_hwinfo(struct nitrox_device *ndev);
+void enable_pf2vf_mbox_interrupts(struct nitrox_device *ndev);
+void disable_pf2vf_mbox_interrupts(struct nitrox_device *ndev);
+
+#endif /* __NITROX_HAL_H */
diff --git a/drivers/crypto/cavium/nitrox/nitrox_isr.c b/drivers/crypto/cavium/nitrox/nitrox_isr.c
new file mode 100644
index 000000000..cf09f7451
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/nitrox_isr.c
@@ -0,0 +1,458 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/pci.h>
+#include <linux/printk.h>
+#include <linux/slab.h>
+
+#include "nitrox_dev.h"
+#include "nitrox_csr.h"
+#include "nitrox_common.h"
+#include "nitrox_hal.h"
+#include "nitrox_isr.h"
+#include "nitrox_mbx.h"
+
+/*
+ * One vector for each type of ring
+ *  - NPS packet ring, AQMQ ring and ZQMQ ring
+ */
+#define NR_RING_VECTORS 3
+#define NR_NON_RING_VECTORS 1
+/* base entry for packet ring/port */
+#define PKT_RING_MSIX_BASE 0
+#define NON_RING_MSIX_BASE 192
+
+/**
+ * nps_pkt_slc_isr - IRQ handler for NPS solicit port
+ * @irq: irq number
+ * @data: argument
+ */
+static irqreturn_t nps_pkt_slc_isr(int irq, void *data)
+{
+	struct nitrox_q_vector *qvec = data;
+	union nps_pkt_slc_cnts slc_cnts;
+	struct nitrox_cmdq *cmdq = qvec->cmdq;
+
+	slc_cnts.value = readq(cmdq->compl_cnt_csr_addr);
+	/* New packet on SLC output port */
+	if (slc_cnts.s.slc_int)
+		tasklet_hi_schedule(&qvec->resp_tasklet);
+
+	return IRQ_HANDLED;
+}
+
+static void clear_nps_core_err_intr(struct nitrox_device *ndev)
+{
+	u64 value;
+
+	/* Write 1 to clear */
+	value = nitrox_read_csr(ndev, NPS_CORE_INT);
+	nitrox_write_csr(ndev, NPS_CORE_INT, value);
+
+	dev_err_ratelimited(DEV(ndev), "NSP_CORE_INT  0x%016llx\n", value);
+}
+
+static void clear_nps_pkt_err_intr(struct nitrox_device *ndev)
+{
+	union nps_pkt_int pkt_int;
+	unsigned long value, offset;
+	int i;
+
+	pkt_int.value = nitrox_read_csr(ndev, NPS_PKT_INT);
+	dev_err_ratelimited(DEV(ndev), "NPS_PKT_INT  0x%016llx\n",
+			    pkt_int.value);
+
+	if (pkt_int.s.slc_err) {
+		offset = NPS_PKT_SLC_ERR_TYPE;
+		value = nitrox_read_csr(ndev, offset);
+		nitrox_write_csr(ndev, offset, value);
+		dev_err_ratelimited(DEV(ndev),
+				    "NPS_PKT_SLC_ERR_TYPE  0x%016lx\n", value);
+
+		offset = NPS_PKT_SLC_RERR_LO;
+		value = nitrox_read_csr(ndev, offset);
+		nitrox_write_csr(ndev, offset, value);
+		/* enable the solicit ports */
+		for_each_set_bit(i, &value, BITS_PER_LONG)
+			enable_pkt_solicit_port(ndev, i);
+
+		dev_err_ratelimited(DEV(ndev),
+				    "NPS_PKT_SLC_RERR_LO  0x%016lx\n", value);
+
+		offset = NPS_PKT_SLC_RERR_HI;
+		value = nitrox_read_csr(ndev, offset);
+		nitrox_write_csr(ndev, offset, value);
+		dev_err_ratelimited(DEV(ndev),
+				    "NPS_PKT_SLC_RERR_HI  0x%016lx\n", value);
+	}
+
+	if (pkt_int.s.in_err) {
+		offset = NPS_PKT_IN_ERR_TYPE;
+		value = nitrox_read_csr(ndev, offset);
+		nitrox_write_csr(ndev, offset, value);
+		dev_err_ratelimited(DEV(ndev),
+				    "NPS_PKT_IN_ERR_TYPE  0x%016lx\n", value);
+		offset = NPS_PKT_IN_RERR_LO;
+		value = nitrox_read_csr(ndev, offset);
+		nitrox_write_csr(ndev, offset, value);
+		/* enable the input ring */
+		for_each_set_bit(i, &value, BITS_PER_LONG)
+			enable_pkt_input_ring(ndev, i);
+
+		dev_err_ratelimited(DEV(ndev),
+				    "NPS_PKT_IN_RERR_LO  0x%016lx\n", value);
+
+		offset = NPS_PKT_IN_RERR_HI;
+		value = nitrox_read_csr(ndev, offset);
+		nitrox_write_csr(ndev, offset, value);
+		dev_err_ratelimited(DEV(ndev),
+				    "NPS_PKT_IN_RERR_HI  0x%016lx\n", value);
+	}
+}
+
+static void clear_pom_err_intr(struct nitrox_device *ndev)
+{
+	u64 value;
+
+	value = nitrox_read_csr(ndev, POM_INT);
+	nitrox_write_csr(ndev, POM_INT, value);
+	dev_err_ratelimited(DEV(ndev), "POM_INT  0x%016llx\n", value);
+}
+
+static void clear_pem_err_intr(struct nitrox_device *ndev)
+{
+	u64 value;
+
+	value = nitrox_read_csr(ndev, PEM0_INT);
+	nitrox_write_csr(ndev, PEM0_INT, value);
+	dev_err_ratelimited(DEV(ndev), "PEM(0)_INT  0x%016llx\n", value);
+}
+
+static void clear_lbc_err_intr(struct nitrox_device *ndev)
+{
+	union lbc_int lbc_int;
+	u64 value, offset;
+	int i;
+
+	lbc_int.value = nitrox_read_csr(ndev, LBC_INT);
+	dev_err_ratelimited(DEV(ndev), "LBC_INT  0x%016llx\n", lbc_int.value);
+
+	if (lbc_int.s.dma_rd_err) {
+		for (i = 0; i < NR_CLUSTERS; i++) {
+			offset = EFL_CORE_VF_ERR_INT0X(i);
+			value = nitrox_read_csr(ndev, offset);
+			nitrox_write_csr(ndev, offset, value);
+			offset = EFL_CORE_VF_ERR_INT1X(i);
+			value = nitrox_read_csr(ndev, offset);
+			nitrox_write_csr(ndev, offset, value);
+		}
+	}
+
+	if (lbc_int.s.cam_soft_err) {
+		dev_err_ratelimited(DEV(ndev), "CAM_SOFT_ERR, invalidating LBC\n");
+		invalidate_lbc(ndev);
+	}
+
+	if (lbc_int.s.pref_dat_len_mismatch_err) {
+		offset = LBC_PLM_VF1_64_INT;
+		value = nitrox_read_csr(ndev, offset);
+		nitrox_write_csr(ndev, offset, value);
+		offset = LBC_PLM_VF65_128_INT;
+		value = nitrox_read_csr(ndev, offset);
+		nitrox_write_csr(ndev, offset, value);
+	}
+
+	if (lbc_int.s.rd_dat_len_mismatch_err) {
+		offset = LBC_ELM_VF1_64_INT;
+		value = nitrox_read_csr(ndev, offset);
+		nitrox_write_csr(ndev, offset, value);
+		offset = LBC_ELM_VF65_128_INT;
+		value = nitrox_read_csr(ndev, offset);
+		nitrox_write_csr(ndev, offset, value);
+	}
+	nitrox_write_csr(ndev, LBC_INT, lbc_int.value);
+}
+
+static void clear_efl_err_intr(struct nitrox_device *ndev)
+{
+	int i;
+
+	for (i = 0; i < NR_CLUSTERS; i++) {
+		union efl_core_int core_int;
+		u64 value, offset;
+
+		offset = EFL_CORE_INTX(i);
+		core_int.value = nitrox_read_csr(ndev, offset);
+		nitrox_write_csr(ndev, offset, core_int.value);
+		dev_err_ratelimited(DEV(ndev), "ELF_CORE(%d)_INT  0x%016llx\n",
+				    i, core_int.value);
+		if (core_int.s.se_err) {
+			offset = EFL_CORE_SE_ERR_INTX(i);
+			value = nitrox_read_csr(ndev, offset);
+			nitrox_write_csr(ndev, offset, value);
+		}
+	}
+}
+
+static void clear_bmi_err_intr(struct nitrox_device *ndev)
+{
+	u64 value;
+
+	value = nitrox_read_csr(ndev, BMI_INT);
+	nitrox_write_csr(ndev, BMI_INT, value);
+	dev_err_ratelimited(DEV(ndev), "BMI_INT  0x%016llx\n", value);
+}
+
+static void nps_core_int_tasklet(unsigned long data)
+{
+	struct nitrox_q_vector *qvec = (void *)(uintptr_t)(data);
+	struct nitrox_device *ndev = qvec->ndev;
+
+	/* if pf mode do queue recovery */
+	if (ndev->mode == __NDEV_MODE_PF) {
+	} else {
+		/**
+		 * if VF(s) enabled communicate the error information
+		 * to VF(s)
+		 */
+	}
+}
+
+/*
+ * nps_core_int_isr - interrupt handler for NITROX errors and
+ *   mailbox communication
+ */
+static irqreturn_t nps_core_int_isr(int irq, void *data)
+{
+	struct nitrox_q_vector *qvec = data;
+	struct nitrox_device *ndev = qvec->ndev;
+	union nps_core_int_active core_int;
+
+	core_int.value = nitrox_read_csr(ndev, NPS_CORE_INT_ACTIVE);
+
+	if (core_int.s.nps_core)
+		clear_nps_core_err_intr(ndev);
+
+	if (core_int.s.nps_pkt)
+		clear_nps_pkt_err_intr(ndev);
+
+	if (core_int.s.pom)
+		clear_pom_err_intr(ndev);
+
+	if (core_int.s.pem)
+		clear_pem_err_intr(ndev);
+
+	if (core_int.s.lbc)
+		clear_lbc_err_intr(ndev);
+
+	if (core_int.s.efl)
+		clear_efl_err_intr(ndev);
+
+	if (core_int.s.bmi)
+		clear_bmi_err_intr(ndev);
+
+	/* Mailbox interrupt */
+	if (core_int.s.mbox)
+		nitrox_pf2vf_mbox_handler(ndev);
+
+	/* If more work callback the ISR, set resend */
+	core_int.s.resend = 1;
+	nitrox_write_csr(ndev, NPS_CORE_INT_ACTIVE, core_int.value);
+
+	return IRQ_HANDLED;
+}
+
+void nitrox_unregister_interrupts(struct nitrox_device *ndev)
+{
+	struct pci_dev *pdev = ndev->pdev;
+	int i;
+
+	for (i = 0; i < ndev->num_vecs; i++) {
+		struct nitrox_q_vector *qvec;
+		int vec;
+
+		qvec = ndev->qvec + i;
+		if (!qvec->valid)
+			continue;
+
+		/* get the vector number */
+		vec = pci_irq_vector(pdev, i);
+		irq_set_affinity_hint(vec, NULL);
+		free_irq(vec, qvec);
+
+		tasklet_disable(&qvec->resp_tasklet);
+		tasklet_kill(&qvec->resp_tasklet);
+		qvec->valid = false;
+	}
+	kfree(ndev->qvec);
+	ndev->qvec = NULL;
+	pci_free_irq_vectors(pdev);
+}
+
+int nitrox_register_interrupts(struct nitrox_device *ndev)
+{
+	struct pci_dev *pdev = ndev->pdev;
+	struct nitrox_q_vector *qvec;
+	int nr_vecs, vec, cpu;
+	int ret, i;
+
+	/*
+	 * PF MSI-X vectors
+	 *
+	 * Entry 0: NPS PKT ring 0
+	 * Entry 1: AQMQ ring 0
+	 * Entry 2: ZQM ring 0
+	 * Entry 3: NPS PKT ring 1
+	 * Entry 4: AQMQ ring 1
+	 * Entry 5: ZQM ring 1
+	 * ....
+	 * Entry 192: NPS_CORE_INT_ACTIVE
+	 */
+	nr_vecs = pci_msix_vec_count(pdev);
+	if (nr_vecs < 0) {
+		dev_err(DEV(ndev), "Error in getting vec count %d\n", nr_vecs);
+		return nr_vecs;
+	}
+
+	/* Enable MSI-X */
+	ret = pci_alloc_irq_vectors(pdev, nr_vecs, nr_vecs, PCI_IRQ_MSIX);
+	if (ret < 0) {
+		dev_err(DEV(ndev), "msix vectors %d alloc failed\n", nr_vecs);
+		return ret;
+	}
+	ndev->num_vecs = nr_vecs;
+
+	ndev->qvec = kzalloc_objs(*qvec, nr_vecs);
+	if (!ndev->qvec) {
+		pci_free_irq_vectors(pdev);
+		return -ENOMEM;
+	}
+
+	/* request irqs for packet rings/ports */
+	for (i = PKT_RING_MSIX_BASE; i < (nr_vecs - 1); i += NR_RING_VECTORS) {
+		qvec = &ndev->qvec[i];
+
+		qvec->ring = i / NR_RING_VECTORS;
+		if (qvec->ring >= ndev->nr_queues)
+			break;
+
+		qvec->cmdq = &ndev->pkt_inq[qvec->ring];
+		snprintf(qvec->name, IRQ_NAMESZ, "nitrox-pkt%d", qvec->ring);
+		/* get the vector number */
+		vec = pci_irq_vector(pdev, i);
+		ret = request_irq(vec, nps_pkt_slc_isr, 0, qvec->name, qvec);
+		if (ret) {
+			dev_err(DEV(ndev), "irq failed for pkt ring/port%d\n",
+				qvec->ring);
+			goto irq_fail;
+		}
+		cpu = qvec->ring % num_online_cpus();
+		irq_set_affinity_hint(vec, get_cpu_mask(cpu));
+
+		tasklet_init(&qvec->resp_tasklet, pkt_slc_resp_tasklet,
+			     (unsigned long)qvec);
+		qvec->valid = true;
+	}
+
+	/* request irqs for non ring vectors */
+	i = NON_RING_MSIX_BASE;
+	qvec = &ndev->qvec[i];
+	qvec->ndev = ndev;
+
+	snprintf(qvec->name, IRQ_NAMESZ, "nitrox-core-int%d", i);
+	/* get the vector number */
+	vec = pci_irq_vector(pdev, i);
+	ret = request_irq(vec, nps_core_int_isr, 0, qvec->name, qvec);
+	if (ret) {
+		dev_err(DEV(ndev), "irq failed for nitrox-core-int%d\n", i);
+		goto irq_fail;
+	}
+	cpu = num_online_cpus();
+	irq_set_affinity_hint(vec, get_cpu_mask(cpu));
+
+	tasklet_init(&qvec->resp_tasklet, nps_core_int_tasklet,
+		     (unsigned long)qvec);
+	qvec->valid = true;
+
+	return 0;
+
+irq_fail:
+	nitrox_unregister_interrupts(ndev);
+	return ret;
+}
+
+void nitrox_sriov_unregister_interrupts(struct nitrox_device *ndev)
+{
+	struct pci_dev *pdev = ndev->pdev;
+	int i;
+
+	for (i = 0; i < ndev->num_vecs; i++) {
+		struct nitrox_q_vector *qvec;
+		int vec;
+
+		qvec = ndev->qvec + i;
+		if (!qvec->valid)
+			continue;
+
+		vec = ndev->iov.msix.vector;
+		irq_set_affinity_hint(vec, NULL);
+		free_irq(vec, qvec);
+
+		tasklet_disable(&qvec->resp_tasklet);
+		tasklet_kill(&qvec->resp_tasklet);
+		qvec->valid = false;
+	}
+	kfree(ndev->qvec);
+	ndev->qvec = NULL;
+	pci_disable_msix(pdev);
+}
+
+int nitrox_sriov_register_interupts(struct nitrox_device *ndev)
+{
+	struct pci_dev *pdev = ndev->pdev;
+	struct nitrox_q_vector *qvec;
+	int vec, cpu;
+	int ret;
+
+	/**
+	 * only non ring vectors i.e Entry 192 is available
+	 * for PF in SR-IOV mode.
+	 */
+	ndev->iov.msix.entry = NON_RING_MSIX_BASE;
+	ret = pci_enable_msix_exact(pdev, &ndev->iov.msix, NR_NON_RING_VECTORS);
+	if (ret) {
+		dev_err(DEV(ndev), "failed to allocate nps-core-int%d\n",
+			NON_RING_MSIX_BASE);
+		return ret;
+	}
+
+	qvec = kzalloc_objs(*qvec, NR_NON_RING_VECTORS);
+	if (!qvec) {
+		pci_disable_msix(pdev);
+		return -ENOMEM;
+	}
+	qvec->ndev = ndev;
+
+	ndev->qvec = qvec;
+	ndev->num_vecs = NR_NON_RING_VECTORS;
+	snprintf(qvec->name, IRQ_NAMESZ, "nitrox-core-int%d",
+		 NON_RING_MSIX_BASE);
+
+	vec = ndev->iov.msix.vector;
+	ret = request_irq(vec, nps_core_int_isr, 0, qvec->name, qvec);
+	if (ret) {
+		dev_err(DEV(ndev), "irq failed for nitrox-core-int%d\n",
+			NON_RING_MSIX_BASE);
+		goto iov_irq_fail;
+	}
+	cpu = num_online_cpus();
+	irq_set_affinity_hint(vec, get_cpu_mask(cpu));
+
+	tasklet_init(&qvec->resp_tasklet, nps_core_int_tasklet,
+		     (unsigned long)qvec);
+	qvec->valid = true;
+
+	return 0;
+
+iov_irq_fail:
+	nitrox_sriov_unregister_interrupts(ndev);
+	return ret;
+}
diff --git a/drivers/crypto/cavium/nitrox/nitrox_isr.h b/drivers/crypto/cavium/nitrox/nitrox_isr.h
new file mode 100644
index 000000000..2bb123cd2
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/nitrox_isr.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NITROX_ISR_H
+#define __NITROX_ISR_H
+
+#include "nitrox_dev.h"
+
+int nitrox_register_interrupts(struct nitrox_device *ndev);
+void nitrox_unregister_interrupts(struct nitrox_device *ndev);
+int nitrox_sriov_register_interupts(struct nitrox_device *ndev);
+void nitrox_sriov_unregister_interrupts(struct nitrox_device *ndev);
+
+#ifdef CONFIG_PCI_IOV
+int nitrox_sriov_configure(struct pci_dev *pdev, int num_vfs);
+#else
+static inline int nitrox_sriov_configure(struct pci_dev *pdev, int num_vfs)
+{
+	return 0;
+}
+#endif
+
+#endif /* __NITROX_ISR_H */
diff --git a/drivers/crypto/cavium/nitrox/nitrox_lib.c b/drivers/crypto/cavium/nitrox/nitrox_lib.c
new file mode 100644
index 000000000..d35303857
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/nitrox_lib.c
@@ -0,0 +1,300 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/cpumask.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/delay.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci_regs.h>
+#include <linux/vmalloc.h>
+#include <linux/pci.h>
+
+#include "nitrox_dev.h"
+#include "nitrox_common.h"
+#include "nitrox_req.h"
+#include "nitrox_csr.h"
+
+#define CRYPTO_CTX_SIZE	256
+
+/* packet input ring alignments */
+#define PKTIN_Q_ALIGN_BYTES 16
+/* AQM Queue input alignments */
+#define AQM_Q_ALIGN_BYTES 32
+
+static int nitrox_cmdq_init(struct nitrox_cmdq *cmdq, int align_bytes)
+{
+	struct nitrox_device *ndev = cmdq->ndev;
+
+	cmdq->qsize = (ndev->qlen * cmdq->instr_size) + align_bytes;
+	cmdq->unalign_base = dma_alloc_coherent(DEV(ndev), cmdq->qsize,
+						&cmdq->unalign_dma,
+						GFP_KERNEL);
+	if (!cmdq->unalign_base)
+		return -ENOMEM;
+
+	cmdq->dma = PTR_ALIGN(cmdq->unalign_dma, align_bytes);
+	cmdq->base = cmdq->unalign_base + (cmdq->dma - cmdq->unalign_dma);
+	cmdq->write_idx = 0;
+
+	spin_lock_init(&cmdq->cmd_qlock);
+	spin_lock_init(&cmdq->resp_qlock);
+	spin_lock_init(&cmdq->backlog_qlock);
+
+	INIT_LIST_HEAD(&cmdq->response_head);
+	INIT_LIST_HEAD(&cmdq->backlog_head);
+	INIT_WORK(&cmdq->backlog_qflush, backlog_qflush_work);
+
+	atomic_set(&cmdq->pending_count, 0);
+	atomic_set(&cmdq->backlog_count, 0);
+	return 0;
+}
+
+static void nitrox_cmdq_reset(struct nitrox_cmdq *cmdq)
+{
+	cmdq->write_idx = 0;
+	atomic_set(&cmdq->pending_count, 0);
+	atomic_set(&cmdq->backlog_count, 0);
+}
+
+static void nitrox_cmdq_cleanup(struct nitrox_cmdq *cmdq)
+{
+	struct nitrox_device *ndev;
+
+	if (!cmdq)
+		return;
+
+	if (!cmdq->unalign_base)
+		return;
+
+	ndev = cmdq->ndev;
+	cancel_work_sync(&cmdq->backlog_qflush);
+
+	dma_free_coherent(DEV(ndev), cmdq->qsize,
+			  cmdq->unalign_base, cmdq->unalign_dma);
+	nitrox_cmdq_reset(cmdq);
+
+	cmdq->dbell_csr_addr = NULL;
+	cmdq->compl_cnt_csr_addr = NULL;
+	cmdq->unalign_base = NULL;
+	cmdq->base = NULL;
+	cmdq->unalign_dma = 0;
+	cmdq->dma = 0;
+	cmdq->qsize = 0;
+	cmdq->instr_size = 0;
+}
+
+static void nitrox_free_aqm_queues(struct nitrox_device *ndev)
+{
+	int i;
+
+	for (i = 0; i < ndev->nr_queues; i++) {
+		nitrox_cmdq_cleanup(ndev->aqmq[i]);
+		kfree_sensitive(ndev->aqmq[i]);
+		ndev->aqmq[i] = NULL;
+	}
+}
+
+static int nitrox_alloc_aqm_queues(struct nitrox_device *ndev)
+{
+	int i, err;
+
+	for (i = 0; i < ndev->nr_queues; i++) {
+		struct nitrox_cmdq *cmdq;
+		u64 offset;
+
+		cmdq = kzalloc_node(sizeof(*cmdq), GFP_KERNEL, ndev->node);
+		if (!cmdq) {
+			err = -ENOMEM;
+			goto aqmq_fail;
+		}
+
+		cmdq->ndev = ndev;
+		cmdq->qno = i;
+		cmdq->instr_size = sizeof(struct aqmq_command_s);
+
+		/* AQM Queue Doorbell Counter Register Address */
+		offset = AQMQ_DRBLX(i);
+		cmdq->dbell_csr_addr = NITROX_CSR_ADDR(ndev, offset);
+		/* AQM Queue Commands Completed Count Register Address */
+		offset = AQMQ_CMD_CNTX(i);
+		cmdq->compl_cnt_csr_addr = NITROX_CSR_ADDR(ndev, offset);
+
+		err = nitrox_cmdq_init(cmdq, AQM_Q_ALIGN_BYTES);
+		if (err) {
+			kfree_sensitive(cmdq);
+			goto aqmq_fail;
+		}
+		ndev->aqmq[i] = cmdq;
+	}
+
+	return 0;
+
+aqmq_fail:
+	nitrox_free_aqm_queues(ndev);
+	return err;
+}
+
+static void nitrox_free_pktin_queues(struct nitrox_device *ndev)
+{
+	int i;
+
+	for (i = 0; i < ndev->nr_queues; i++) {
+		struct nitrox_cmdq *cmdq = &ndev->pkt_inq[i];
+
+		nitrox_cmdq_cleanup(cmdq);
+	}
+	kfree(ndev->pkt_inq);
+	ndev->pkt_inq = NULL;
+}
+
+static int nitrox_alloc_pktin_queues(struct nitrox_device *ndev)
+{
+	int i, err;
+
+	ndev->pkt_inq = kcalloc_node(ndev->nr_queues,
+				     sizeof(struct nitrox_cmdq),
+				     GFP_KERNEL, ndev->node);
+	if (!ndev->pkt_inq)
+		return -ENOMEM;
+
+	for (i = 0; i < ndev->nr_queues; i++) {
+		struct nitrox_cmdq *cmdq;
+		u64 offset;
+
+		cmdq = &ndev->pkt_inq[i];
+		cmdq->ndev = ndev;
+		cmdq->qno = i;
+		cmdq->instr_size = sizeof(struct nps_pkt_instr);
+
+		/* packet input ring doorbell address */
+		offset = NPS_PKT_IN_INSTR_BAOFF_DBELLX(i);
+		cmdq->dbell_csr_addr = NITROX_CSR_ADDR(ndev, offset);
+		/* packet solicit port completion count address */
+		offset = NPS_PKT_SLC_CNTSX(i);
+		cmdq->compl_cnt_csr_addr = NITROX_CSR_ADDR(ndev, offset);
+
+		err = nitrox_cmdq_init(cmdq, PKTIN_Q_ALIGN_BYTES);
+		if (err)
+			goto pktq_fail;
+	}
+	return 0;
+
+pktq_fail:
+	nitrox_free_pktin_queues(ndev);
+	return err;
+}
+
+static int create_crypto_dma_pool(struct nitrox_device *ndev)
+{
+	size_t size;
+
+	/* Crypto context pool, 16 byte aligned */
+	size = CRYPTO_CTX_SIZE + sizeof(struct ctx_hdr);
+	ndev->ctx_pool = dma_pool_create("nitrox-context",
+					 DEV(ndev), size, 16, 0);
+	if (!ndev->ctx_pool)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void destroy_crypto_dma_pool(struct nitrox_device *ndev)
+{
+	if (!ndev->ctx_pool)
+		return;
+
+	dma_pool_destroy(ndev->ctx_pool);
+	ndev->ctx_pool = NULL;
+}
+
+/*
+ * crypto_alloc_context - Allocate crypto context from pool
+ * @ndev: NITROX Device
+ */
+void *crypto_alloc_context(struct nitrox_device *ndev)
+{
+	struct ctx_hdr *ctx;
+	struct crypto_ctx_hdr *chdr;
+	void *vaddr;
+	dma_addr_t dma;
+
+	chdr = kmalloc_obj(*chdr);
+	if (!chdr)
+		return NULL;
+
+	vaddr = dma_pool_zalloc(ndev->ctx_pool, GFP_KERNEL, &dma);
+	if (!vaddr) {
+		kfree(chdr);
+		return NULL;
+	}
+
+	/* fill meta data */
+	ctx = vaddr;
+	ctx->pool = ndev->ctx_pool;
+	ctx->dma = dma;
+	ctx->ctx_dma = dma + sizeof(struct ctx_hdr);
+
+	chdr->pool = ndev->ctx_pool;
+	chdr->dma = dma;
+	chdr->vaddr = vaddr;
+
+	return chdr;
+}
+
+/**
+ * crypto_free_context - Free crypto context to pool
+ * @ctx: context to free
+ */
+void crypto_free_context(void *ctx)
+{
+	struct crypto_ctx_hdr *ctxp;
+
+	if (!ctx)
+		return;
+
+	ctxp = ctx;
+	dma_pool_free(ctxp->pool, ctxp->vaddr, ctxp->dma);
+	kfree(ctxp);
+}
+
+/**
+ * nitrox_common_sw_init - allocate software resources.
+ * @ndev: NITROX device
+ *
+ * Allocates crypto context pools and command queues etc.
+ *
+ * Return: 0 on success, or a negative error code on error.
+ */
+int nitrox_common_sw_init(struct nitrox_device *ndev)
+{
+	int err = 0;
+
+	/* per device crypto context pool */
+	err = create_crypto_dma_pool(ndev);
+	if (err)
+		return err;
+
+	err = nitrox_alloc_pktin_queues(ndev);
+	if (err)
+		destroy_crypto_dma_pool(ndev);
+
+	err = nitrox_alloc_aqm_queues(ndev);
+	if (err) {
+		nitrox_free_pktin_queues(ndev);
+		destroy_crypto_dma_pool(ndev);
+	}
+
+	return err;
+}
+
+/**
+ * nitrox_common_sw_cleanup - free software resources.
+ * @ndev: NITROX device
+ */
+void nitrox_common_sw_cleanup(struct nitrox_device *ndev)
+{
+	nitrox_free_aqm_queues(ndev);
+	nitrox_free_pktin_queues(ndev);
+	destroy_crypto_dma_pool(ndev);
+}
diff --git a/drivers/crypto/cavium/nitrox/nitrox_main.c b/drivers/crypto/cavium/nitrox/nitrox_main.c
new file mode 100644
index 000000000..e474c84d8
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/nitrox_main.c
@@ -0,0 +1,582 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/delay.h>
+#include <linux/firmware.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/pci_ids.h>
+
+#include "nitrox_dev.h"
+#include "nitrox_common.h"
+#include "nitrox_csr.h"
+#include "nitrox_hal.h"
+#include "nitrox_isr.h"
+#include "nitrox_debugfs.h"
+
+#define CNN55XX_DEV_ID	0x12
+#define UCODE_HLEN 48
+#define DEFAULT_SE_GROUP 0
+#define DEFAULT_AE_GROUP 0
+
+#define DRIVER_VERSION "1.2"
+#define CNN55XX_UCD_BLOCK_SIZE 32768
+#define CNN55XX_MAX_UCODE_SIZE (CNN55XX_UCD_BLOCK_SIZE * 2)
+#define FW_DIR "cavium/"
+/* SE microcode */
+#define SE_FW	FW_DIR "cnn55xx_se.fw"
+/* AE microcode */
+#define AE_FW	FW_DIR "cnn55xx_ae.fw"
+
+static const char nitrox_driver_name[] = "CNN55XX";
+
+static LIST_HEAD(ndevlist);
+static DEFINE_MUTEX(devlist_lock);
+static unsigned int num_devices;
+
+/*
+ * nitrox_pci_tbl - PCI Device ID Table
+ */
+static const struct pci_device_id nitrox_pci_tbl[] = {
+	{ PCI_VDEVICE(CAVIUM, CNN55XX_DEV_ID) },
+	/* required last entry */
+	{ }
+};
+MODULE_DEVICE_TABLE(pci, nitrox_pci_tbl);
+
+static unsigned int qlen = DEFAULT_CMD_QLEN;
+module_param(qlen, uint, 0644);
+MODULE_PARM_DESC(qlen, "Command queue length - default 2048");
+
+/**
+ * struct ucode - Firmware Header
+ * @id: microcode ID
+ * @version: firmware version
+ * @code_size: code section size
+ * @raz: alignment
+ * @code: code section
+ */
+struct ucode {
+	u8 id;
+	char version[VERSION_LEN - 1];
+	__be32 code_size;
+	u8 raz[12];
+	u64 code[];
+};
+
+/*
+ * write_to_ucd_unit - Write Firmware to NITROX UCD unit
+ */
+static void write_to_ucd_unit(struct nitrox_device *ndev, u32 ucode_size,
+			      u64 *ucode_data, int block_num)
+{
+	u32 code_size;
+	u64 offset, data;
+	int i = 0;
+
+	/*
+	 * UCD structure
+	 *
+	 *  -------------
+	 *  |    BLK 7  |
+	 *  -------------
+	 *  |    BLK 6  |
+	 *  -------------
+	 *  |    ...    |
+	 *  -------------
+	 *  |    BLK 0  |
+	 *  -------------
+	 *  Total of 8 blocks, each size 32KB
+	 */
+
+	/* set the block number */
+	offset = UCD_UCODE_LOAD_BLOCK_NUM;
+	nitrox_write_csr(ndev, offset, block_num);
+
+	code_size = roundup(ucode_size, 16);
+	while (code_size) {
+		data = ucode_data[i];
+		/* write 8 bytes at a time */
+		offset = UCD_UCODE_LOAD_IDX_DATAX(i);
+		nitrox_write_csr(ndev, offset, data);
+		code_size -= 8;
+		i++;
+	}
+
+	usleep_range(300, 400);
+}
+
+static int nitrox_load_fw(struct nitrox_device *ndev)
+{
+	const struct firmware *fw;
+	const char *fw_name;
+	struct ucode *ucode;
+	u64 *ucode_data;
+	u64 offset;
+	union ucd_core_eid_ucode_block_num core_2_eid_val;
+	union aqm_grp_execmsk_lo aqm_grp_execmask_lo;
+	union aqm_grp_execmsk_hi aqm_grp_execmask_hi;
+	u32 ucode_size;
+	int ret, i = 0;
+
+	fw_name = SE_FW;
+	dev_info(DEV(ndev), "Loading firmware \"%s\"\n", fw_name);
+
+	ret = request_firmware(&fw, fw_name, DEV(ndev));
+	if (ret < 0) {
+		dev_err(DEV(ndev), "failed to get firmware %s\n", fw_name);
+		return ret;
+	}
+
+	ucode = (struct ucode *)fw->data;
+
+	ucode_size = be32_to_cpu(ucode->code_size) * 2;
+	if (!ucode_size || ucode_size > CNN55XX_MAX_UCODE_SIZE) {
+		dev_err(DEV(ndev), "Invalid ucode size: %u for firmware %s\n",
+			ucode_size, fw_name);
+		release_firmware(fw);
+		return -EINVAL;
+	}
+	ucode_data = ucode->code;
+
+	/* copy the firmware version */
+	memcpy(&ndev->hw.fw_name[0][0], ucode->version, (VERSION_LEN - 2));
+	ndev->hw.fw_name[0][VERSION_LEN - 1] = '\0';
+
+	/* Load SE Firmware on UCD Block 0 */
+	write_to_ucd_unit(ndev, ucode_size, ucode_data, 0);
+
+	release_firmware(fw);
+
+	/* put all SE cores in DEFAULT_SE_GROUP */
+	offset = POM_GRP_EXECMASKX(DEFAULT_SE_GROUP);
+	nitrox_write_csr(ndev, offset, (~0ULL));
+
+	/* write block number and firmware length
+	 * bit:<2:0> block number
+	 * bit:3 is set SE uses 32KB microcode
+	 * bit:3 is clear SE uses 64KB microcode
+	 */
+	core_2_eid_val.value = 0ULL;
+	core_2_eid_val.ucode_blk = 0;
+	if (ucode_size <= CNN55XX_UCD_BLOCK_SIZE)
+		core_2_eid_val.ucode_len = 1;
+	else
+		core_2_eid_val.ucode_len = 0;
+
+	for (i = 0; i < ndev->hw.se_cores; i++) {
+		offset = UCD_SE_EID_UCODE_BLOCK_NUMX(i);
+		nitrox_write_csr(ndev, offset, core_2_eid_val.value);
+	}
+
+
+	fw_name = AE_FW;
+	dev_info(DEV(ndev), "Loading firmware \"%s\"\n", fw_name);
+
+	ret = request_firmware(&fw, fw_name, DEV(ndev));
+	if (ret < 0) {
+		dev_err(DEV(ndev), "failed to get firmware %s\n", fw_name);
+		return ret;
+	}
+
+	ucode = (struct ucode *)fw->data;
+
+	ucode_size = be32_to_cpu(ucode->code_size) * 2;
+	if (!ucode_size || ucode_size > CNN55XX_MAX_UCODE_SIZE) {
+		dev_err(DEV(ndev), "Invalid ucode size: %u for firmware %s\n",
+			ucode_size, fw_name);
+		release_firmware(fw);
+		return -EINVAL;
+	}
+	ucode_data = ucode->code;
+
+	/* copy the firmware version */
+	memcpy(&ndev->hw.fw_name[1][0], ucode->version, (VERSION_LEN - 2));
+	ndev->hw.fw_name[1][VERSION_LEN - 1] = '\0';
+
+	/* Load AE Firmware on UCD Block 2 */
+	write_to_ucd_unit(ndev, ucode_size, ucode_data, 2);
+
+	release_firmware(fw);
+
+	/* put all AE cores in DEFAULT_AE_GROUP */
+	offset = AQM_GRP_EXECMSK_LOX(DEFAULT_AE_GROUP);
+	aqm_grp_execmask_lo.exec_0_to_39 = 0xFFFFFFFFFFULL;
+	nitrox_write_csr(ndev, offset, aqm_grp_execmask_lo.value);
+	offset = AQM_GRP_EXECMSK_HIX(DEFAULT_AE_GROUP);
+	aqm_grp_execmask_hi.exec_40_to_79 = 0xFFFFFFFFFFULL;
+	nitrox_write_csr(ndev, offset, aqm_grp_execmask_hi.value);
+
+	/* write block number and firmware length
+	 * bit:<2:0> block number
+	 * bit:3 is set AE uses 32KB microcode
+	 * bit:3 is clear AE uses 64KB microcode
+	 */
+	core_2_eid_val.value = 0ULL;
+	core_2_eid_val.ucode_blk = 2;
+	if (ucode_size <= CNN55XX_UCD_BLOCK_SIZE)
+		core_2_eid_val.ucode_len = 1;
+	else
+		core_2_eid_val.ucode_len = 0;
+
+	for (i = 0; i < ndev->hw.ae_cores; i++) {
+		offset = UCD_AE_EID_UCODE_BLOCK_NUMX(i);
+		nitrox_write_csr(ndev, offset, core_2_eid_val.value);
+	}
+
+	return 0;
+}
+
+/**
+ * nitrox_add_to_devlist - add NITROX device to global device list
+ * @ndev: NITROX device
+ */
+static int nitrox_add_to_devlist(struct nitrox_device *ndev)
+{
+	struct nitrox_device *dev;
+	int ret = 0;
+
+	INIT_LIST_HEAD(&ndev->list);
+	refcount_set(&ndev->refcnt, 1);
+
+	mutex_lock(&devlist_lock);
+	list_for_each_entry(dev, &ndevlist, list) {
+		if (dev == ndev) {
+			ret = -EEXIST;
+			goto unlock;
+		}
+	}
+	ndev->idx = num_devices++;
+	list_add_tail(&ndev->list, &ndevlist);
+unlock:
+	mutex_unlock(&devlist_lock);
+	return ret;
+}
+
+/**
+ * nitrox_remove_from_devlist - remove NITROX device from
+ *   global device list
+ * @ndev: NITROX device
+ */
+static void nitrox_remove_from_devlist(struct nitrox_device *ndev)
+{
+	mutex_lock(&devlist_lock);
+	list_del(&ndev->list);
+	num_devices--;
+	mutex_unlock(&devlist_lock);
+}
+
+struct nitrox_device *nitrox_get_first_device(void)
+{
+	struct nitrox_device *ndev = NULL, *iter;
+
+	mutex_lock(&devlist_lock);
+	list_for_each_entry(iter, &ndevlist, list) {
+		if (nitrox_ready(iter)) {
+			ndev = iter;
+			break;
+		}
+	}
+	mutex_unlock(&devlist_lock);
+	if (!ndev)
+		return NULL;
+
+	refcount_inc(&ndev->refcnt);
+	/* barrier to sync with other cpus */
+	smp_mb__after_atomic();
+	return ndev;
+}
+
+void nitrox_put_device(struct nitrox_device *ndev)
+{
+	if (!ndev)
+		return;
+
+	refcount_dec(&ndev->refcnt);
+	/* barrier to sync with other cpus */
+	smp_mb__after_atomic();
+}
+
+static int nitrox_device_flr(struct pci_dev *pdev)
+{
+	int pos = 0;
+
+	pos = pci_save_state(pdev);
+	if (pos) {
+		dev_err(&pdev->dev, "Failed to save pci state\n");
+		return -ENOMEM;
+	}
+
+	pcie_reset_flr(pdev, PCI_RESET_DO_RESET);
+
+	pci_restore_state(pdev);
+
+	return 0;
+}
+
+static int nitrox_pf_sw_init(struct nitrox_device *ndev)
+{
+	int err;
+
+	err = nitrox_common_sw_init(ndev);
+	if (err)
+		return err;
+
+	err = nitrox_register_interrupts(ndev);
+	if (err)
+		nitrox_common_sw_cleanup(ndev);
+
+	return err;
+}
+
+static void nitrox_pf_sw_cleanup(struct nitrox_device *ndev)
+{
+	nitrox_unregister_interrupts(ndev);
+	nitrox_common_sw_cleanup(ndev);
+}
+
+/**
+ * nitrox_bist_check - Check NITROX BIST registers status
+ * @ndev: NITROX device
+ */
+static int nitrox_bist_check(struct nitrox_device *ndev)
+{
+	u64 value = 0;
+	int i;
+
+	for (i = 0; i < NR_CLUSTERS; i++) {
+		value += nitrox_read_csr(ndev, EMU_BIST_STATUSX(i));
+		value += nitrox_read_csr(ndev, EFL_CORE_BIST_REGX(i));
+	}
+	value += nitrox_read_csr(ndev, UCD_BIST_STATUS);
+	value += nitrox_read_csr(ndev, NPS_CORE_BIST_REG);
+	value += nitrox_read_csr(ndev, NPS_CORE_NPC_BIST_REG);
+	value += nitrox_read_csr(ndev, NPS_PKT_SLC_BIST_REG);
+	value += nitrox_read_csr(ndev, NPS_PKT_IN_BIST_REG);
+	value += nitrox_read_csr(ndev, POM_BIST_REG);
+	value += nitrox_read_csr(ndev, BMI_BIST_REG);
+	value += nitrox_read_csr(ndev, EFL_TOP_BIST_STAT);
+	value += nitrox_read_csr(ndev, BMO_BIST_REG);
+	value += nitrox_read_csr(ndev, LBC_BIST_STATUS);
+	value += nitrox_read_csr(ndev, PEM_BIST_STATUSX(0));
+	if (value)
+		return -EIO;
+	return 0;
+}
+
+static int nitrox_pf_hw_init(struct nitrox_device *ndev)
+{
+	int err;
+
+	err = nitrox_bist_check(ndev);
+	if (err) {
+		dev_err(&ndev->pdev->dev, "BIST check failed\n");
+		return err;
+	}
+	/* get cores information */
+	nitrox_get_hwinfo(ndev);
+
+	nitrox_config_nps_core_unit(ndev);
+	nitrox_config_aqm_unit(ndev);
+	nitrox_config_nps_pkt_unit(ndev);
+	nitrox_config_pom_unit(ndev);
+	nitrox_config_efl_unit(ndev);
+	/* configure IO units */
+	nitrox_config_bmi_unit(ndev);
+	nitrox_config_bmo_unit(ndev);
+	/* configure Local Buffer Cache */
+	nitrox_config_lbc_unit(ndev);
+	nitrox_config_rand_unit(ndev);
+
+	/* load firmware on cores */
+	err = nitrox_load_fw(ndev);
+	if (err)
+		return err;
+
+	nitrox_config_emu_unit(ndev);
+
+	return 0;
+}
+
+/**
+ * nitrox_probe - NITROX Initialization function.
+ * @pdev: PCI device information struct
+ * @id: entry in nitrox_pci_tbl
+ *
+ * Return: 0, if the driver is bound to the device, or
+ *         a negative error if there is failure.
+ */
+static int nitrox_probe(struct pci_dev *pdev,
+			const struct pci_device_id *id)
+{
+	struct nitrox_device *ndev;
+	int err;
+
+	dev_info_once(&pdev->dev, "%s driver version %s\n",
+		      nitrox_driver_name, DRIVER_VERSION);
+
+	err = pci_enable_device_mem(pdev);
+	if (err)
+		return err;
+
+	/* do FLR */
+	err = nitrox_device_flr(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "FLR failed\n");
+		goto flr_fail;
+	}
+
+	if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) {
+		dev_dbg(&pdev->dev, "DMA to 64-BIT address\n");
+	} else {
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+		if (err) {
+			dev_err(&pdev->dev, "DMA configuration failed\n");
+			goto flr_fail;
+		}
+	}
+
+	err = pci_request_mem_regions(pdev, nitrox_driver_name);
+	if (err)
+		goto flr_fail;
+	pci_set_master(pdev);
+
+	ndev = kzalloc_obj(*ndev);
+	if (!ndev) {
+		err = -ENOMEM;
+		goto ndev_fail;
+	}
+
+	pci_set_drvdata(pdev, ndev);
+	ndev->pdev = pdev;
+
+	/* add to device list */
+	nitrox_add_to_devlist(ndev);
+
+	ndev->hw.vendor_id = pdev->vendor;
+	ndev->hw.device_id = pdev->device;
+	ndev->hw.revision_id = pdev->revision;
+	/* command timeout in jiffies */
+	ndev->timeout = msecs_to_jiffies(CMD_TIMEOUT);
+	ndev->node = dev_to_node(&pdev->dev);
+	if (ndev->node == NUMA_NO_NODE)
+		ndev->node = 0;
+
+	ndev->bar_addr = ioremap(pci_resource_start(pdev, 0),
+				 pci_resource_len(pdev, 0));
+	if (!ndev->bar_addr) {
+		err = -EIO;
+		goto ioremap_err;
+	}
+	/* allocate command queus based on cpus, max queues are 64 */
+	ndev->nr_queues = min_t(u32, MAX_PF_QUEUES, num_online_cpus());
+	ndev->qlen = qlen;
+
+	err = nitrox_pf_sw_init(ndev);
+	if (err)
+		goto pf_sw_fail;
+
+	err = nitrox_pf_hw_init(ndev);
+	if (err)
+		goto pf_hw_fail;
+
+	nitrox_debugfs_init(ndev);
+
+	/* clear the statistics */
+	atomic64_set(&ndev->stats.posted, 0);
+	atomic64_set(&ndev->stats.completed, 0);
+	atomic64_set(&ndev->stats.dropped, 0);
+
+	atomic_set(&ndev->state, __NDEV_READY);
+	/* barrier to sync with other cpus */
+	smp_mb__after_atomic();
+
+	err = nitrox_crypto_register();
+	if (err)
+		goto crypto_fail;
+
+	return 0;
+
+crypto_fail:
+	nitrox_debugfs_exit(ndev);
+	atomic_set(&ndev->state, __NDEV_NOT_READY);
+	/* barrier to sync with other cpus */
+	smp_mb__after_atomic();
+pf_hw_fail:
+	nitrox_pf_sw_cleanup(ndev);
+pf_sw_fail:
+	iounmap(ndev->bar_addr);
+ioremap_err:
+	nitrox_remove_from_devlist(ndev);
+	kfree(ndev);
+	pci_set_drvdata(pdev, NULL);
+ndev_fail:
+	pci_release_mem_regions(pdev);
+flr_fail:
+	pci_disable_device(pdev);
+	return err;
+}
+
+/**
+ * nitrox_remove - Unbind the driver from the device.
+ * @pdev: PCI device information struct
+ */
+static void nitrox_remove(struct pci_dev *pdev)
+{
+	struct nitrox_device *ndev = pci_get_drvdata(pdev);
+
+	if (!ndev)
+		return;
+
+	if (!refcount_dec_and_test(&ndev->refcnt)) {
+		dev_err(DEV(ndev), "Device refcnt not zero (%d)\n",
+			refcount_read(&ndev->refcnt));
+		return;
+	}
+
+	dev_info(DEV(ndev), "Removing Device %x:%x\n",
+		 ndev->hw.vendor_id, ndev->hw.device_id);
+
+	atomic_set(&ndev->state, __NDEV_NOT_READY);
+	/* barrier to sync with other cpus */
+	smp_mb__after_atomic();
+
+	nitrox_remove_from_devlist(ndev);
+
+	/* disable SR-IOV */
+	nitrox_sriov_configure(pdev, 0);
+	nitrox_crypto_unregister();
+	nitrox_debugfs_exit(ndev);
+	nitrox_pf_sw_cleanup(ndev);
+
+	iounmap(ndev->bar_addr);
+	kfree(ndev);
+
+	pci_set_drvdata(pdev, NULL);
+	pci_release_mem_regions(pdev);
+	pci_disable_device(pdev);
+}
+
+static void nitrox_shutdown(struct pci_dev *pdev)
+{
+	pci_set_drvdata(pdev, NULL);
+	pci_release_mem_regions(pdev);
+	pci_disable_device(pdev);
+}
+
+static struct pci_driver nitrox_driver = {
+	.name = nitrox_driver_name,
+	.id_table = nitrox_pci_tbl,
+	.probe = nitrox_probe,
+	.remove	= nitrox_remove,
+	.shutdown = nitrox_shutdown,
+	.sriov_configure = nitrox_sriov_configure,
+};
+
+module_pci_driver(nitrox_driver);
+
+MODULE_AUTHOR("Srikanth Jampala <Jampala.Srikanth@cavium.com>");
+MODULE_DESCRIPTION("Cavium CNN55XX PF Driver" DRIVER_VERSION " ");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_FIRMWARE(SE_FW);
diff --git a/drivers/crypto/cavium/nitrox/nitrox_mbx.c b/drivers/crypto/cavium/nitrox/nitrox_mbx.c
new file mode 100644
index 000000000..944d8b882
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/nitrox_mbx.c
@@ -0,0 +1,217 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bitmap.h>
+#include <linux/workqueue.h>
+
+#include "nitrox_csr.h"
+#include "nitrox_hal.h"
+#include "nitrox_dev.h"
+#include "nitrox_mbx.h"
+
+#define RING_TO_VFNO(_x, _y)	((_x) / (_y))
+
+/*
+ * mbx_msg_type - Mailbox message types
+ */
+enum mbx_msg_type {
+	MBX_MSG_TYPE_NOP,
+	MBX_MSG_TYPE_REQ,
+	MBX_MSG_TYPE_ACK,
+	MBX_MSG_TYPE_NACK,
+};
+
+/*
+ * mbx_msg_opcode - Mailbox message opcodes
+ */
+enum mbx_msg_opcode {
+	MSG_OP_VF_MODE = 1,
+	MSG_OP_VF_UP,
+	MSG_OP_VF_DOWN,
+	MSG_OP_CHIPID_VFID,
+	MSG_OP_MCODE_INFO = 11,
+};
+
+struct pf2vf_work {
+	struct nitrox_vfdev *vfdev;
+	struct nitrox_device *ndev;
+	struct work_struct pf2vf_resp;
+};
+
+static inline u64 pf2vf_read_mbox(struct nitrox_device *ndev, int ring)
+{
+	u64 reg_addr;
+
+	reg_addr = NPS_PKT_MBOX_VF_PF_PFDATAX(ring);
+	return nitrox_read_csr(ndev, reg_addr);
+}
+
+static inline void pf2vf_write_mbox(struct nitrox_device *ndev, u64 value,
+				    int ring)
+{
+	u64 reg_addr;
+
+	reg_addr = NPS_PKT_MBOX_PF_VF_PFDATAX(ring);
+	nitrox_write_csr(ndev, reg_addr, value);
+}
+
+static void pf2vf_send_response(struct nitrox_device *ndev,
+				struct nitrox_vfdev *vfdev)
+{
+	union mbox_msg msg;
+
+	msg.value = vfdev->msg.value;
+
+	switch (vfdev->msg.opcode) {
+	case MSG_OP_VF_MODE:
+		msg.data = ndev->mode;
+		break;
+	case MSG_OP_VF_UP:
+		vfdev->nr_queues = vfdev->msg.data;
+		atomic_set(&vfdev->state, __NDEV_READY);
+		break;
+	case MSG_OP_CHIPID_VFID:
+		msg.id.chipid = ndev->idx;
+		msg.id.vfid = vfdev->vfno;
+		break;
+	case MSG_OP_VF_DOWN:
+		vfdev->nr_queues = 0;
+		atomic_set(&vfdev->state, __NDEV_NOT_READY);
+		break;
+	case MSG_OP_MCODE_INFO:
+		msg.data = 0;
+		msg.mcode_info.count = 2;
+		msg.mcode_info.info = MCODE_TYPE_SE_SSL | (MCODE_TYPE_AE << 5);
+		msg.mcode_info.next_se_grp = 1;
+		msg.mcode_info.next_ae_grp = 1;
+		break;
+	default:
+		msg.type = MBX_MSG_TYPE_NOP;
+		break;
+	}
+
+	if (msg.type == MBX_MSG_TYPE_NOP)
+		return;
+
+	/* send ACK to VF */
+	msg.type = MBX_MSG_TYPE_ACK;
+	pf2vf_write_mbox(ndev, msg.value, vfdev->ring);
+
+	vfdev->msg.value = 0;
+	atomic64_inc(&vfdev->mbx_resp);
+}
+
+static void pf2vf_resp_handler(struct work_struct *work)
+{
+	struct pf2vf_work *pf2vf_resp = container_of(work, struct pf2vf_work,
+						     pf2vf_resp);
+	struct nitrox_vfdev *vfdev = pf2vf_resp->vfdev;
+	struct nitrox_device *ndev = pf2vf_resp->ndev;
+
+	switch (vfdev->msg.type) {
+	case MBX_MSG_TYPE_REQ:
+		/* process the request from VF */
+		pf2vf_send_response(ndev, vfdev);
+		break;
+	case MBX_MSG_TYPE_ACK:
+	case MBX_MSG_TYPE_NACK:
+		break;
+	}
+
+	kfree(pf2vf_resp);
+}
+
+void nitrox_pf2vf_mbox_handler(struct nitrox_device *ndev)
+{
+	DECLARE_BITMAP(csr, BITS_PER_TYPE(u64));
+	struct nitrox_vfdev *vfdev;
+	struct pf2vf_work *pfwork;
+	u64 value, reg_addr;
+	u32 i;
+	int vfno;
+
+	/* loop for VF(0..63) */
+	reg_addr = NPS_PKT_MBOX_INT_LO;
+	value = nitrox_read_csr(ndev, reg_addr);
+	bitmap_from_u64(csr, value);
+	for_each_set_bit(i, csr, BITS_PER_TYPE(csr)) {
+		/* get the vfno from ring */
+		vfno = RING_TO_VFNO(i, ndev->iov.max_vf_queues);
+		vfdev = ndev->iov.vfdev + vfno;
+		vfdev->ring = i;
+		/* fill the vf mailbox data */
+		vfdev->msg.value = pf2vf_read_mbox(ndev, vfdev->ring);
+		pfwork = kzalloc_obj(*pfwork, GFP_ATOMIC);
+		if (!pfwork)
+			continue;
+
+		pfwork->vfdev = vfdev;
+		pfwork->ndev = ndev;
+		INIT_WORK(&pfwork->pf2vf_resp, pf2vf_resp_handler);
+		queue_work(ndev->iov.pf2vf_wq, &pfwork->pf2vf_resp);
+		/* clear the corresponding vf bit */
+		nitrox_write_csr(ndev, reg_addr, BIT_ULL(i));
+	}
+
+	/* loop for VF(64..127) */
+	reg_addr = NPS_PKT_MBOX_INT_HI;
+	value = nitrox_read_csr(ndev, reg_addr);
+	bitmap_from_u64(csr, value);
+	for_each_set_bit(i, csr, BITS_PER_TYPE(csr)) {
+		/* get the vfno from ring */
+		vfno = RING_TO_VFNO(i + 64, ndev->iov.max_vf_queues);
+		vfdev = ndev->iov.vfdev + vfno;
+		vfdev->ring = (i + 64);
+		/* fill the vf mailbox data */
+		vfdev->msg.value = pf2vf_read_mbox(ndev, vfdev->ring);
+
+		pfwork = kzalloc_obj(*pfwork, GFP_ATOMIC);
+		if (!pfwork)
+			continue;
+
+		pfwork->vfdev = vfdev;
+		pfwork->ndev = ndev;
+		INIT_WORK(&pfwork->pf2vf_resp, pf2vf_resp_handler);
+		queue_work(ndev->iov.pf2vf_wq, &pfwork->pf2vf_resp);
+		/* clear the corresponding vf bit */
+		nitrox_write_csr(ndev, reg_addr, BIT_ULL(i));
+	}
+}
+
+int nitrox_mbox_init(struct nitrox_device *ndev)
+{
+	struct nitrox_vfdev *vfdev;
+	int i;
+
+	ndev->iov.vfdev = kzalloc_objs(struct nitrox_vfdev, ndev->iov.num_vfs);
+	if (!ndev->iov.vfdev)
+		return -ENOMEM;
+
+	for (i = 0; i < ndev->iov.num_vfs; i++) {
+		vfdev = ndev->iov.vfdev + i;
+		vfdev->vfno = i;
+	}
+
+	/* allocate pf2vf response workqueue */
+	ndev->iov.pf2vf_wq = alloc_workqueue("nitrox_pf2vf", WQ_PERCPU, 0);
+	if (!ndev->iov.pf2vf_wq) {
+		kfree(ndev->iov.vfdev);
+		ndev->iov.vfdev = NULL;
+		return -ENOMEM;
+	}
+	/* enable pf2vf mailbox interrupts */
+	enable_pf2vf_mbox_interrupts(ndev);
+
+	return 0;
+}
+
+void nitrox_mbox_cleanup(struct nitrox_device *ndev)
+{
+	/* disable pf2vf mailbox interrupts */
+	disable_pf2vf_mbox_interrupts(ndev);
+	/* destroy workqueue */
+	if (ndev->iov.pf2vf_wq)
+		destroy_workqueue(ndev->iov.pf2vf_wq);
+
+	kfree(ndev->iov.vfdev);
+	ndev->iov.pf2vf_wq = NULL;
+	ndev->iov.vfdev = NULL;
+}
diff --git a/drivers/crypto/cavium/nitrox/nitrox_mbx.h b/drivers/crypto/cavium/nitrox/nitrox_mbx.h
new file mode 100644
index 000000000..7c93d0282
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/nitrox_mbx.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NITROX_MBX_H
+#define __NITROX_MBX_H
+
+int nitrox_mbox_init(struct nitrox_device *ndev);
+void nitrox_mbox_cleanup(struct nitrox_device *ndev);
+void nitrox_pf2vf_mbox_handler(struct nitrox_device *ndev);
+
+#endif /* __NITROX_MBX_H */
diff --git a/drivers/crypto/cavium/nitrox/nitrox_req.h b/drivers/crypto/cavium/nitrox/nitrox_req.h
new file mode 100644
index 000000000..6bf088bcd
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/nitrox_req.h
@@ -0,0 +1,728 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NITROX_REQ_H
+#define __NITROX_REQ_H
+
+#include <linux/dma-mapping.h>
+#include <crypto/aes.h>
+
+#include "nitrox_dev.h"
+
+#define PENDING_SIG	0xFFFFFFFFFFFFFFFFUL
+#define PRIO 4001
+
+typedef void (*sereq_completion_t)(void *req, int err);
+
+/**
+ * struct gphdr - General purpose Header
+ * @param0: first parameter.
+ * @param1: second parameter.
+ * @param2: third parameter.
+ * @param3: fourth parameter.
+ *
+ * Params tell the iv and enc/dec data offsets.
+ */
+struct gphdr {
+	__be16 param0;
+	__be16 param1;
+	__be16 param2;
+	__be16 param3;
+};
+
+/**
+ * struct se_req_ctrl - SE request information.
+ * @arg: Minor number of the opcode
+ * @ctxc: Context control.
+ * @unca: Uncertainity enabled.
+ * @info: Additional information for SE cores.
+ * @ctxl: Context length in bytes.
+ * @uddl: User defined data length
+ */
+union se_req_ctrl {
+	u64 value;
+	struct {
+		u64 raz	: 22;
+		u64 arg	: 8;
+		u64 ctxc : 2;
+		u64 unca : 1;
+		u64 info : 3;
+		u64 unc : 8;
+		u64 ctxl : 12;
+		u64 uddl : 8;
+	} s;
+};
+
+#define MAX_IV_LEN 16
+
+/**
+ * struct se_crypto_request - SE crypto request structure.
+ * @opcode: Request opcode (enc/dec)
+ * @flags: flags from crypto subsystem
+ * @ctx_handle: Crypto context handle.
+ * @gph: GP Header
+ * @ctrl: Request Information.
+ * @orh: ORH address
+ * @comp: completion address
+ * @src: Input sglist
+ * @dst: Output sglist
+ */
+struct se_crypto_request {
+	u8 opcode;
+	gfp_t gfp;
+	u32 flags;
+	u64 ctx_handle;
+
+	struct gphdr gph;
+	union se_req_ctrl ctrl;
+	u64 *orh;
+	u64 *comp;
+
+	struct scatterlist *src;
+	struct scatterlist *dst;
+};
+
+/* Crypto opcodes */
+#define FLEXI_CRYPTO_ENCRYPT_HMAC	0x33
+#define ENCRYPT	0
+#define DECRYPT 1
+
+/* IV from context */
+#define IV_FROM_CTX	0
+/* IV from Input data */
+#define IV_FROM_DPTR	1
+
+/**
+ * cipher opcodes for firmware
+ */
+enum flexi_cipher {
+	CIPHER_NULL = 0,
+	CIPHER_3DES_CBC,
+	CIPHER_3DES_ECB,
+	CIPHER_AES_CBC,
+	CIPHER_AES_ECB,
+	CIPHER_AES_CFB,
+	CIPHER_AES_CTR,
+	CIPHER_AES_GCM,
+	CIPHER_AES_XTS,
+	CIPHER_AES_CCM,
+	CIPHER_AES_CBC_CTS,
+	CIPHER_AES_ECB_CTS,
+	CIPHER_INVALID
+};
+
+enum flexi_auth {
+	AUTH_NULL = 0,
+	AUTH_MD5,
+	AUTH_SHA1,
+	AUTH_SHA2_SHA224,
+	AUTH_SHA2_SHA256,
+	AUTH_SHA2_SHA384,
+	AUTH_SHA2_SHA512,
+	AUTH_GMAC,
+	AUTH_INVALID
+};
+
+/**
+ * struct crypto_keys - Crypto keys
+ * @key: Encryption key or KEY1 for AES-XTS
+ * @iv: Encryption IV or Tweak for AES-XTS
+ */
+struct crypto_keys {
+	union {
+		u8 key[AES_MAX_KEY_SIZE];
+		u8 key1[AES_MAX_KEY_SIZE];
+	} u;
+	u8 iv[AES_BLOCK_SIZE];
+};
+
+/**
+ * struct auth_keys - Authentication keys
+ * @ipad: IPAD or KEY2 for AES-XTS
+ * @opad: OPAD or AUTH KEY if auth_input_type = 1
+ */
+struct auth_keys {
+	union {
+		u8 ipad[64];
+		u8 key2[64];
+	} u;
+	u8 opad[64];
+};
+
+union fc_ctx_flags {
+	__be64 f;
+	u64 fu;
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 cipher_type	: 4;
+		u64 reserved_59	: 1;
+		u64 aes_keylen : 2;
+		u64 iv_source : 1;
+		u64 hash_type : 4;
+		u64 reserved_49_51 : 3;
+		u64 auth_input_type: 1;
+		u64 mac_len : 8;
+		u64 reserved_0_39 : 40;
+#else
+		u64 reserved_0_39 : 40;
+		u64 mac_len : 8;
+		u64 auth_input_type: 1;
+		u64 reserved_49_51 : 3;
+		u64 hash_type : 4;
+		u64 iv_source : 1;
+		u64 aes_keylen : 2;
+		u64 reserved_59	: 1;
+		u64 cipher_type	: 4;
+#endif
+	} w0;
+};
+/**
+ * struct flexi_crypto_context - Crypto context
+ * @cipher_type: Encryption cipher type
+ * @aes_keylen: AES key length
+ * @iv_source: Encryption IV source
+ * @hash_type: Authentication type
+ * @auth_input_type: Authentication input type
+ *   1 - Authentication IV and KEY, microcode calculates OPAD/IPAD
+ *   0 - Authentication OPAD/IPAD
+ * @mac_len: mac length
+ * @crypto: Crypto keys
+ * @auth: Authentication keys
+ */
+struct flexi_crypto_context {
+	union fc_ctx_flags flags;
+	struct crypto_keys crypto;
+	struct auth_keys auth;
+};
+
+struct crypto_ctx_hdr {
+	struct dma_pool *pool;
+	dma_addr_t dma;
+	void *vaddr;
+};
+
+struct nitrox_crypto_ctx {
+	struct nitrox_device *ndev;
+	union {
+		u64 ctx_handle;
+		struct flexi_crypto_context *fctx;
+	} u;
+	struct crypto_ctx_hdr *chdr;
+	sereq_completion_t callback;
+};
+
+struct nitrox_kcrypt_request {
+	struct se_crypto_request creq;
+	u8 *src;
+	u8 *dst;
+	u8 *iv_out;
+};
+
+/**
+ * struct nitrox_aead_rctx - AEAD request context
+ * @nkreq: Base request context
+ * @cryptlen: Encryption/Decryption data length
+ * @assoclen: AAD length
+ * @srclen: Input buffer length
+ * @dstlen: Output buffer length
+ * @iv: IV data
+ * @ivsize: IV data length
+ * @flags: AEAD req flags
+ * @ctx_handle: Device context handle
+ * @src: Source sglist
+ * @dst: Destination sglist
+ * @ctrl_arg: Identifies the request type (ENCRYPT/DECRYPT)
+ */
+struct nitrox_aead_rctx {
+	struct nitrox_kcrypt_request nkreq;
+	unsigned int cryptlen;
+	unsigned int assoclen;
+	unsigned int srclen;
+	unsigned int dstlen;
+	u8 *iv;
+	int ivsize;
+	u32 flags;
+	u64 ctx_handle;
+	struct scatterlist *src;
+	struct scatterlist *dst;
+	u8 ctrl_arg;
+};
+
+/**
+ * struct nitrox_rfc4106_rctx - rfc4106 cipher request context
+ * @base: AEAD request context
+ * @src: Source sglist
+ * @dst: Destination sglist
+ * @assoc: AAD
+ */
+struct nitrox_rfc4106_rctx {
+	struct nitrox_aead_rctx base;
+	struct scatterlist src[3];
+	struct scatterlist dst[3];
+	u8 assoc[20];
+};
+
+/**
+ * struct pkt_instr_hdr - Packet Instruction Header
+ * @g: Gather used
+ *   When [G] is set and [GSZ] != 0, the instruction is
+ *   indirect gather instruction.
+ *   When [G] is set and [GSZ] = 0, the instruction is
+ *   direct gather instruction.
+ * @gsz: Number of pointers in the indirect gather list
+ * @ihi: When set hardware duplicates the 1st 8 bytes of pkt_instr_hdr
+ *   and adds them to the packet after the pkt_instr_hdr but before any UDD
+ * @ssz: Not used by the input hardware. But can become slc_store_int[SSZ]
+ *   when [IHI] is set.
+ * @fsz: The number of front data bytes directly included in the
+ *   PCIe instruction.
+ * @tlen: The length of the input packet in bytes, include:
+ *   - 16B pkt_hdr
+ *   - Inline context bytes if any,
+ *   - UDD if any,
+ *   - packet payload bytes
+ */
+union pkt_instr_hdr {
+	__be64 bev;
+	u64 value;
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 raz_48_63 : 16;
+		u64 g : 1;
+		u64 gsz	: 7;
+		u64 ihi	: 1;
+		u64 ssz	: 7;
+		u64 raz_30_31 : 2;
+		u64 fsz	: 6;
+		u64 raz_16_23 : 8;
+		u64 tlen : 16;
+#else
+		u64 tlen : 16;
+		u64 raz_16_23 : 8;
+		u64 fsz	: 6;
+		u64 raz_30_31 : 2;
+		u64 ssz	: 7;
+		u64 ihi	: 1;
+		u64 gsz	: 7;
+		u64 g : 1;
+		u64 raz_48_63 : 16;
+#endif
+	} s;
+};
+
+/**
+ * struct pkt_hdr - Packet Input Header
+ * @opcode: Request opcode (Major)
+ * @arg: Request opcode (Minor)
+ * @ctxc: Context control.
+ * @unca: When set [UNC] is the uncertainty count for an input packet.
+ *        The hardware uses uncertainty counts to predict
+ *        output buffer use and avoid deadlock.
+ * @info: Not used by input hardware. Available for use
+ *        during SE processing.
+ * @destport: The expected destination port/ring/channel for the packet.
+ * @unc: Uncertainty count for an input packet.
+ * @grp: SE group that will process the input packet.
+ * @ctxl: Context Length in 64-bit words.
+ * @uddl: User-defined data (UDD) length in bytes.
+ * @ctxp: Context pointer. CTXP<63,2:0> must be zero in all cases.
+ */
+union pkt_hdr {
+	__be64 bev[2];
+	u64 value[2];
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 opcode : 8;
+		u64 arg	: 8;
+		u64 ctxc : 2;
+		u64 unca : 1;
+		u64 raz_44 : 1;
+		u64 info : 3;
+		u64 destport : 9;
+		u64 unc	: 8;
+		u64 raz_19_23 : 5;
+		u64 grp	: 3;
+		u64 raz_15 : 1;
+		u64 ctxl : 7;
+		u64 uddl : 8;
+#else
+		u64 uddl : 8;
+		u64 ctxl : 7;
+		u64 raz_15 : 1;
+		u64 grp	: 3;
+		u64 raz_19_23 : 5;
+		u64 unc	: 8;
+		u64 destport : 9;
+		u64 info : 3;
+		u64 raz_44 : 1;
+		u64 unca : 1;
+		u64 ctxc : 2;
+		u64 arg	: 8;
+		u64 opcode : 8;
+#endif
+		__be64 ctxp;
+	} s;
+};
+
+/**
+ * struct slc_store_info - Solicited Paceket Output Store Information.
+ * @ssz: The number of scatterlist pointers for the solicited output port
+ *       packet.
+ * @rptr: The result pointer for the solicited output port packet.
+ *        If [SSZ]=0, [RPTR] must point directly to a buffer on the remote
+ *        host that is large enough to hold the entire output packet.
+ *        If [SSZ]!=0, [RPTR] must point to an array of ([SSZ]+3)/4
+ *        sglist components at [RPTR] on the remote host.
+ */
+union slc_store_info {
+	__be64 bev[2];
+	u64 value[2];
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 raz_39_63 : 25;
+		u64 ssz	: 7;
+		u64 raz_0_31 : 32;
+#else
+		u64 raz_0_31 : 32;
+		u64 ssz	: 7;
+		u64 raz_39_63 : 25;
+#endif
+		__be64 rptr;
+	} s;
+};
+
+/**
+ * struct nps_pkt_instr - NPS Packet Instruction of SE cores.
+ * @dptr0 : Input pointer points to buffer in remote host.
+ * @ih: Packet Instruction Header (8 bytes)
+ * @irh: Packet Input Header (16 bytes)
+ * @slc: Solicited Packet Output Store Information (16 bytes)
+ * @fdata: Front data
+ *
+ * 64-Byte Instruction Format
+ */
+struct nps_pkt_instr {
+	__be64 dptr0;
+	union pkt_instr_hdr ih;
+	union pkt_hdr irh;
+	union slc_store_info slc;
+	u64 fdata[2];
+};
+
+/**
+ * struct aqmq_command_s - The 32 byte command for AE processing.
+ * @opcode: Request opcode
+ * @param1: Request control parameter 1
+ * @param2: Request control parameter 2
+ * @dlen: Input length
+ * @dptr: Input pointer points to buffer in remote host
+ * @rptr: Result pointer points to buffer in remote host
+ * @grp: AQM Group (0..7)
+ * @cptr: Context pointer
+ */
+struct aqmq_command_s {
+	__be16 opcode;
+	__be16 param1;
+	__be16 param2;
+	__be16 dlen;
+	__be64 dptr;
+	__be64 rptr;
+	union {
+		__be64 word3;
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 grp : 3;
+		u64 cptr : 61;
+#else
+		u64 cptr : 61;
+		u64 grp : 3;
+#endif
+	};
+};
+
+/**
+ * struct ctx_hdr - Book keeping data about the crypto context
+ * @pool: Pool used to allocate crypto context
+ * @dma: Base DMA address of the crypto context
+ * @ctx_dma: Actual usable crypto context for NITROX
+ */
+struct ctx_hdr {
+	struct dma_pool *pool;
+	dma_addr_t dma;
+	dma_addr_t ctx_dma;
+};
+
+/*
+ * struct sglist_component - SG list component format
+ * @len0: The number of bytes at [PTR0] on the remote host.
+ * @len1: The number of bytes at [PTR1] on the remote host.
+ * @len2: The number of bytes at [PTR2] on the remote host.
+ * @len3: The number of bytes at [PTR3] on the remote host.
+ * @dma0: First pointer point to buffer in remote host.
+ * @dma1: Second pointer point to buffer in remote host.
+ * @dma2: Third pointer point to buffer in remote host.
+ * @dma3: Fourth pointer point to buffer in remote host.
+ */
+struct nitrox_sgcomp {
+	__be16 len[4];
+	__be64 dma[4];
+};
+
+/*
+ * strutct nitrox_sgtable - SG list information
+ * @sgmap_cnt: Number of buffers mapped
+ * @total_bytes: Total bytes in sglist.
+ * @sgcomp_len: Total sglist components length.
+ * @sgcomp_dma: DMA address of sglist component.
+ * @sg: crypto request buffer.
+ * @sgcomp: sglist component for NITROX.
+ */
+struct nitrox_sgtable {
+	u8 sgmap_cnt;
+	u16 total_bytes;
+	u32 sgcomp_len;
+	dma_addr_t sgcomp_dma;
+	struct scatterlist *sg;
+	struct nitrox_sgcomp *sgcomp;
+};
+
+/* Response Header Length */
+#define ORH_HLEN	8
+/* Completion bytes Length */
+#define COMP_HLEN	8
+
+struct resp_hdr {
+	u64 *orh;
+	u64 *completion;
+};
+
+typedef void (*completion_t)(void *arg, int err);
+
+/**
+ * struct nitrox_softreq - Represents the NIROX Request.
+ * @response: response list entry
+ * @backlog: Backlog list entry
+ * @ndev: Device used to submit the request
+ * @cmdq: Command queue for submission
+ * @resp: Response headers
+ * @instr: 64B instruction
+ * @in: SG table for input
+ * @out SG table for output
+ * @tstamp: Request submitted time in jiffies
+ * @callback: callback after request completion/timeout
+ * @cb_arg: callback argument
+ */
+struct nitrox_softreq {
+	struct list_head response;
+	struct list_head backlog;
+
+	u32 flags;
+	gfp_t gfp;
+	atomic_t status;
+
+	struct nitrox_device *ndev;
+	struct nitrox_cmdq *cmdq;
+
+	struct nps_pkt_instr instr;
+	struct resp_hdr resp;
+	struct nitrox_sgtable in;
+	struct nitrox_sgtable out;
+
+	unsigned long tstamp;
+
+	completion_t callback;
+	void *cb_arg;
+};
+
+static inline int flexi_aes_keylen(int keylen)
+{
+	int aes_keylen;
+
+	switch (keylen) {
+	case AES_KEYSIZE_128:
+		aes_keylen = 1;
+		break;
+	case AES_KEYSIZE_192:
+		aes_keylen = 2;
+		break;
+	case AES_KEYSIZE_256:
+		aes_keylen = 3;
+		break;
+	default:
+		aes_keylen = -EINVAL;
+		break;
+	}
+	return aes_keylen;
+}
+
+static inline void *alloc_req_buf(int nents, int extralen, gfp_t gfp)
+{
+	size_t size;
+
+	size = sizeof(struct scatterlist) * nents;
+	size += extralen;
+
+	return kzalloc(size, gfp);
+}
+
+/**
+ * create_single_sg - Point SG entry to the data
+ * @sg:		Destination SG list
+ * @buf:	Data
+ * @buflen:	Data length
+ *
+ * Returns next free entry in the destination SG list
+ **/
+static inline struct scatterlist *create_single_sg(struct scatterlist *sg,
+						   void *buf, int buflen)
+{
+	sg_set_buf(sg, buf, buflen);
+	sg++;
+	return sg;
+}
+
+/**
+ * create_multi_sg - Create multiple sg entries with buflen data length from
+ *		     source sglist
+ * @to_sg:	Destination SG list
+ * @from_sg:	Source SG list
+ * @buflen:	Data length
+ *
+ * Returns next free entry in the destination SG list
+ **/
+static inline struct scatterlist *create_multi_sg(struct scatterlist *to_sg,
+						  struct scatterlist *from_sg,
+						  int buflen)
+{
+	struct scatterlist *sg = to_sg;
+	unsigned int sglen;
+
+	for (; buflen && from_sg; buflen -= sglen) {
+		sglen = from_sg->length;
+		if (sglen > buflen)
+			sglen = buflen;
+
+		sg_set_buf(sg, sg_virt(from_sg), sglen);
+		from_sg = sg_next(from_sg);
+		sg++;
+	}
+
+	return sg;
+}
+
+static inline void set_orh_value(u64 *orh)
+{
+	WRITE_ONCE(*orh, PENDING_SIG);
+}
+
+static inline void set_comp_value(u64 *comp)
+{
+	WRITE_ONCE(*comp, PENDING_SIG);
+}
+
+static inline int alloc_src_req_buf(struct nitrox_kcrypt_request *nkreq,
+				    int nents, int ivsize)
+{
+	struct se_crypto_request *creq = &nkreq->creq;
+
+	nkreq->src = alloc_req_buf(nents, ivsize, creq->gfp);
+	if (!nkreq->src)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static inline void nitrox_creq_copy_iv(char *dst, char *src, int size)
+{
+	memcpy(dst, src, size);
+}
+
+static inline struct scatterlist *nitrox_creq_src_sg(char *iv, int ivsize)
+{
+	return (struct scatterlist *)(iv + ivsize);
+}
+
+static inline void nitrox_creq_set_src_sg(struct nitrox_kcrypt_request *nkreq,
+					  int nents, int ivsize,
+					  struct scatterlist *src, int buflen)
+{
+	char *iv = nkreq->src;
+	struct scatterlist *sg;
+	struct se_crypto_request *creq = &nkreq->creq;
+
+	creq->src = nitrox_creq_src_sg(iv, ivsize);
+	sg = creq->src;
+	sg_init_table(sg, nents);
+
+	/* Input format:
+	 * +----+----------------+
+	 * | IV | SRC sg entries |
+	 * +----+----------------+
+	 */
+
+	/* IV */
+	sg = create_single_sg(sg, iv, ivsize);
+	/* SRC entries */
+	create_multi_sg(sg, src, buflen);
+}
+
+static inline int alloc_dst_req_buf(struct nitrox_kcrypt_request *nkreq,
+				    int nents)
+{
+	int extralen = ORH_HLEN + COMP_HLEN;
+	struct se_crypto_request *creq = &nkreq->creq;
+
+	nkreq->dst = alloc_req_buf(nents, extralen, creq->gfp);
+	if (!nkreq->dst)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static inline void nitrox_creq_set_orh(struct nitrox_kcrypt_request *nkreq)
+{
+	struct se_crypto_request *creq = &nkreq->creq;
+
+	creq->orh = (u64 *)(nkreq->dst);
+	set_orh_value(creq->orh);
+}
+
+static inline void nitrox_creq_set_comp(struct nitrox_kcrypt_request *nkreq)
+{
+	struct se_crypto_request *creq = &nkreq->creq;
+
+	creq->comp = (u64 *)(nkreq->dst + ORH_HLEN);
+	set_comp_value(creq->comp);
+}
+
+static inline struct scatterlist *nitrox_creq_dst_sg(char *dst)
+{
+	return (struct scatterlist *)(dst + ORH_HLEN + COMP_HLEN);
+}
+
+static inline void nitrox_creq_set_dst_sg(struct nitrox_kcrypt_request *nkreq,
+					  int nents, int ivsize,
+					  struct scatterlist *dst, int buflen)
+{
+	struct se_crypto_request *creq = &nkreq->creq;
+	struct scatterlist *sg;
+	char *iv = nkreq->src;
+
+	creq->dst = nitrox_creq_dst_sg(nkreq->dst);
+	sg = creq->dst;
+	sg_init_table(sg, nents);
+
+	/* Output format:
+	 * +-----+----+----------------+-----------------+
+	 * | ORH | IV | DST sg entries | COMPLETION Bytes|
+	 * +-----+----+----------------+-----------------+
+	 */
+
+	/* ORH */
+	sg = create_single_sg(sg, creq->orh, ORH_HLEN);
+	/* IV */
+	sg = create_single_sg(sg, iv, ivsize);
+	/* DST entries */
+	sg = create_multi_sg(sg, dst, buflen);
+	/* COMPLETION Bytes */
+	create_single_sg(sg, creq->comp, COMP_HLEN);
+}
+
+#endif /* __NITROX_REQ_H */
diff --git a/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c b/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c
new file mode 100644
index 000000000..6a1bdae73
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c
@@ -0,0 +1,607 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/gfp.h>
+#include <linux/workqueue.h>
+#include <crypto/internal/skcipher.h>
+
+#include "nitrox_common.h"
+#include "nitrox_dev.h"
+#include "nitrox_req.h"
+#include "nitrox_csr.h"
+
+/* SLC_STORE_INFO */
+#define MIN_UDD_LEN 16
+/* PKT_IN_HDR + SLC_STORE_INFO */
+#define FDATA_SIZE 32
+/* Base destination port for the solicited requests */
+#define SOLICIT_BASE_DPORT 256
+
+#define REQ_NOT_POSTED 1
+#define REQ_BACKLOG    2
+#define REQ_POSTED     3
+
+/*
+ * Response codes from SE microcode
+ * 0x00 - Success
+ *   Completion with no error
+ * 0x43 - ERR_GC_DATA_LEN_INVALID
+ *   Invalid Data length if Encryption Data length is
+ *   less than 16 bytes for AES-XTS and AES-CTS.
+ * 0x45 - ERR_GC_CTX_LEN_INVALID
+ *   Invalid context length: CTXL != 23 words.
+ * 0x4F - ERR_GC_DOCSIS_CIPHER_INVALID
+ *   DOCSIS support is enabled with other than
+ *   AES/DES-CBC mode encryption.
+ * 0x50 - ERR_GC_DOCSIS_OFFSET_INVALID
+ *   Authentication offset is other than 0 with
+ *   Encryption IV source = 0.
+ *   Authentication offset is other than 8 (DES)/16 (AES)
+ *   with Encryption IV source = 1
+ * 0x51 - ERR_GC_CRC32_INVALID_SELECTION
+ *   CRC32 is enabled for other than DOCSIS encryption.
+ * 0x52 - ERR_GC_AES_CCM_FLAG_INVALID
+ *   Invalid flag options in AES-CCM IV.
+ */
+
+static inline int incr_index(int index, int count, int max)
+{
+	if ((index + count) >= max)
+		index = index + count - max;
+	else
+		index += count;
+
+	return index;
+}
+
+static void softreq_unmap_sgbufs(struct nitrox_softreq *sr)
+{
+	struct nitrox_device *ndev = sr->ndev;
+	struct device *dev = DEV(ndev);
+
+
+	dma_unmap_sg(dev, sr->in.sg, sg_nents(sr->in.sg),
+		     DMA_BIDIRECTIONAL);
+	dma_unmap_single(dev, sr->in.sgcomp_dma, sr->in.sgcomp_len,
+			 DMA_TO_DEVICE);
+	kfree(sr->in.sgcomp);
+	sr->in.sg = NULL;
+	sr->in.sgmap_cnt = 0;
+
+	dma_unmap_sg(dev, sr->out.sg, sg_nents(sr->out.sg),
+		     DMA_BIDIRECTIONAL);
+	dma_unmap_single(dev, sr->out.sgcomp_dma, sr->out.sgcomp_len,
+			 DMA_TO_DEVICE);
+	kfree(sr->out.sgcomp);
+	sr->out.sg = NULL;
+	sr->out.sgmap_cnt = 0;
+}
+
+static void softreq_destroy(struct nitrox_softreq *sr)
+{
+	softreq_unmap_sgbufs(sr);
+	kfree(sr);
+}
+
+/**
+ * create_sg_component - create SG componets for N5 device.
+ * @sr: Request structure
+ * @sgtbl: SG table
+ * @map_nents: number of dma mapped entries
+ *
+ * Component structure
+ *
+ *   63     48 47     32 31    16 15      0
+ *   --------------------------------------
+ *   |   LEN0  |  LEN1  |  LEN2  |  LEN3  |
+ *   |-------------------------------------
+ *   |               PTR0                 |
+ *   --------------------------------------
+ *   |               PTR1                 |
+ *   --------------------------------------
+ *   |               PTR2                 |
+ *   --------------------------------------
+ *   |               PTR3                 |
+ *   --------------------------------------
+ *
+ *   Returns 0 if success or a negative errno code on error.
+ */
+static int create_sg_component(struct nitrox_softreq *sr,
+			       struct nitrox_sgtable *sgtbl, int map_nents)
+{
+	struct nitrox_device *ndev = sr->ndev;
+	struct nitrox_sgcomp *sgcomp;
+	struct scatterlist *sg;
+	dma_addr_t dma;
+	size_t sz_comp;
+	int i, j, nr_sgcomp;
+
+	nr_sgcomp = roundup(map_nents, 4) / 4;
+
+	/* each component holds 4 dma pointers */
+	sz_comp = nr_sgcomp * sizeof(*sgcomp);
+	sgcomp = kzalloc(sz_comp, sr->gfp);
+	if (!sgcomp)
+		return -ENOMEM;
+
+	sgtbl->sgcomp = sgcomp;
+
+	sg = sgtbl->sg;
+	/* populate device sg component */
+	for (i = 0; i < nr_sgcomp; i++) {
+		for (j = 0; j < 4 && sg; j++) {
+			sgcomp[i].len[j] = cpu_to_be16(sg_dma_len(sg));
+			sgcomp[i].dma[j] = cpu_to_be64(sg_dma_address(sg));
+			sg = sg_next(sg);
+		}
+	}
+	/* map the device sg component */
+	dma = dma_map_single(DEV(ndev), sgtbl->sgcomp, sz_comp, DMA_TO_DEVICE);
+	if (dma_mapping_error(DEV(ndev), dma)) {
+		kfree(sgtbl->sgcomp);
+		sgtbl->sgcomp = NULL;
+		return -ENOMEM;
+	}
+
+	sgtbl->sgcomp_dma = dma;
+	sgtbl->sgcomp_len = sz_comp;
+
+	return 0;
+}
+
+/**
+ * dma_map_inbufs - DMA map input sglist and creates sglist component
+ *                  for N5 device.
+ * @sr: Request structure
+ * @req: Crypto request structre
+ *
+ * Returns 0 if successful or a negative errno code on error.
+ */
+static int dma_map_inbufs(struct nitrox_softreq *sr,
+			  struct se_crypto_request *req)
+{
+	struct device *dev = DEV(sr->ndev);
+	struct scatterlist *sg;
+	int i, nents, ret = 0;
+
+	nents = dma_map_sg(dev, req->src, sg_nents(req->src),
+			   DMA_BIDIRECTIONAL);
+	if (!nents)
+		return -EINVAL;
+
+	for_each_sg(req->src, sg, nents, i)
+		sr->in.total_bytes += sg_dma_len(sg);
+
+	sr->in.sg = req->src;
+	sr->in.sgmap_cnt = nents;
+	ret = create_sg_component(sr, &sr->in, sr->in.sgmap_cnt);
+	if (ret)
+		goto incomp_err;
+
+	return 0;
+
+incomp_err:
+	dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_BIDIRECTIONAL);
+	sr->in.sgmap_cnt = 0;
+	return ret;
+}
+
+static int dma_map_outbufs(struct nitrox_softreq *sr,
+			   struct se_crypto_request *req)
+{
+	struct device *dev = DEV(sr->ndev);
+	int nents, ret = 0;
+
+	nents = dma_map_sg(dev, req->dst, sg_nents(req->dst),
+			   DMA_BIDIRECTIONAL);
+	if (!nents)
+		return -EINVAL;
+
+	sr->out.sg = req->dst;
+	sr->out.sgmap_cnt = nents;
+	ret = create_sg_component(sr, &sr->out, sr->out.sgmap_cnt);
+	if (ret)
+		goto outcomp_map_err;
+
+	return 0;
+
+outcomp_map_err:
+	dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_BIDIRECTIONAL);
+	sr->out.sgmap_cnt = 0;
+	sr->out.sg = NULL;
+	return ret;
+}
+
+static inline int softreq_map_iobuf(struct nitrox_softreq *sr,
+				    struct se_crypto_request *creq)
+{
+	int ret;
+
+	ret = dma_map_inbufs(sr, creq);
+	if (ret)
+		return ret;
+
+	ret = dma_map_outbufs(sr, creq);
+	if (ret)
+		softreq_unmap_sgbufs(sr);
+
+	return ret;
+}
+
+static inline void backlog_list_add(struct nitrox_softreq *sr,
+				    struct nitrox_cmdq *cmdq)
+{
+	INIT_LIST_HEAD(&sr->backlog);
+
+	spin_lock_bh(&cmdq->backlog_qlock);
+	list_add_tail(&sr->backlog, &cmdq->backlog_head);
+	atomic_inc(&cmdq->backlog_count);
+	atomic_set(&sr->status, REQ_BACKLOG);
+	spin_unlock_bh(&cmdq->backlog_qlock);
+}
+
+static inline void response_list_add(struct nitrox_softreq *sr,
+				     struct nitrox_cmdq *cmdq)
+{
+	INIT_LIST_HEAD(&sr->response);
+
+	spin_lock_bh(&cmdq->resp_qlock);
+	list_add_tail(&sr->response, &cmdq->response_head);
+	spin_unlock_bh(&cmdq->resp_qlock);
+}
+
+static inline void response_list_del(struct nitrox_softreq *sr,
+				     struct nitrox_cmdq *cmdq)
+{
+	spin_lock_bh(&cmdq->resp_qlock);
+	list_del(&sr->response);
+	spin_unlock_bh(&cmdq->resp_qlock);
+}
+
+static struct nitrox_softreq *
+get_first_response_entry(struct nitrox_cmdq *cmdq)
+{
+	return list_first_entry_or_null(&cmdq->response_head,
+					struct nitrox_softreq, response);
+}
+
+static inline bool cmdq_full(struct nitrox_cmdq *cmdq, int qlen)
+{
+	if (atomic_inc_return(&cmdq->pending_count) > qlen) {
+		atomic_dec(&cmdq->pending_count);
+		/* sync with other cpus */
+		smp_mb__after_atomic();
+		return true;
+	}
+	/* sync with other cpus */
+	smp_mb__after_atomic();
+	return false;
+}
+
+/**
+ * post_se_instr - Post SE instruction to Packet Input ring
+ * @sr: Request structure
+ * @cmdq: Command queue structure
+ *
+ * Returns 0 if successful or a negative error code,
+ * if no space in ring.
+ */
+static void post_se_instr(struct nitrox_softreq *sr,
+			  struct nitrox_cmdq *cmdq)
+{
+	struct nitrox_device *ndev = sr->ndev;
+	int idx;
+	u8 *ent;
+
+	spin_lock_bh(&cmdq->cmd_qlock);
+
+	idx = cmdq->write_idx;
+	/* copy the instruction */
+	ent = cmdq->base + (idx * cmdq->instr_size);
+	memcpy(ent, &sr->instr, cmdq->instr_size);
+
+	atomic_set(&sr->status, REQ_POSTED);
+	response_list_add(sr, cmdq);
+	sr->tstamp = jiffies;
+	/* flush the command queue updates */
+	dma_wmb();
+
+	/* Ring doorbell with count 1 */
+	writeq(1, cmdq->dbell_csr_addr);
+
+	cmdq->write_idx = incr_index(idx, 1, ndev->qlen);
+
+	spin_unlock_bh(&cmdq->cmd_qlock);
+
+	/* increment the posted command count */
+	atomic64_inc(&ndev->stats.posted);
+}
+
+static int post_backlog_cmds(struct nitrox_cmdq *cmdq)
+{
+	struct nitrox_device *ndev = cmdq->ndev;
+	struct nitrox_softreq *sr, *tmp;
+	int ret = 0;
+
+	if (!atomic_read(&cmdq->backlog_count))
+		return 0;
+
+	spin_lock_bh(&cmdq->backlog_qlock);
+
+	list_for_each_entry_safe(sr, tmp, &cmdq->backlog_head, backlog) {
+		/* submit until space available */
+		if (unlikely(cmdq_full(cmdq, ndev->qlen))) {
+			ret = -ENOSPC;
+			break;
+		}
+		/* delete from backlog list */
+		list_del(&sr->backlog);
+		atomic_dec(&cmdq->backlog_count);
+		/* sync with other cpus */
+		smp_mb__after_atomic();
+
+		/* post the command */
+		post_se_instr(sr, cmdq);
+	}
+	spin_unlock_bh(&cmdq->backlog_qlock);
+
+	return ret;
+}
+
+static int nitrox_enqueue_request(struct nitrox_softreq *sr)
+{
+	struct nitrox_cmdq *cmdq = sr->cmdq;
+	struct nitrox_device *ndev = sr->ndev;
+
+	/* try to post backlog requests */
+	post_backlog_cmds(cmdq);
+
+	if (unlikely(cmdq_full(cmdq, ndev->qlen))) {
+		if (!(sr->flags & CRYPTO_TFM_REQ_MAY_BACKLOG)) {
+			/* increment drop count */
+			atomic64_inc(&ndev->stats.dropped);
+			return -ENOSPC;
+		}
+		/* add to backlog list */
+		backlog_list_add(sr, cmdq);
+		return -EINPROGRESS;
+	}
+	post_se_instr(sr, cmdq);
+
+	return -EINPROGRESS;
+}
+
+/**
+ * nitrox_process_se_request - Send request to SE core
+ * @ndev: NITROX device
+ * @req: Crypto request
+ * @callback: Completion callback
+ * @cb_arg: Completion callback arguments
+ *
+ * Returns 0 on success, or a negative error code.
+ */
+int nitrox_process_se_request(struct nitrox_device *ndev,
+			      struct se_crypto_request *req,
+			      completion_t callback,
+			      void *cb_arg)
+{
+	struct nitrox_softreq *sr;
+	dma_addr_t ctx_handle = 0;
+	int qno, ret = 0;
+
+	if (!nitrox_ready(ndev))
+		return -ENODEV;
+
+	sr = kzalloc_obj(*sr, req->gfp);
+	if (!sr)
+		return -ENOMEM;
+
+	sr->ndev = ndev;
+	sr->flags = req->flags;
+	sr->gfp = req->gfp;
+	sr->callback = callback;
+	sr->cb_arg = cb_arg;
+
+	atomic_set(&sr->status, REQ_NOT_POSTED);
+
+	sr->resp.orh = req->orh;
+	sr->resp.completion = req->comp;
+
+	ret = softreq_map_iobuf(sr, req);
+	if (ret) {
+		kfree(sr);
+		return ret;
+	}
+
+	/* get the context handle */
+	if (req->ctx_handle) {
+		struct ctx_hdr *hdr;
+		u8 *ctx_ptr;
+
+		ctx_ptr = (u8 *)(uintptr_t)req->ctx_handle;
+		hdr = (struct ctx_hdr *)(ctx_ptr - sizeof(struct ctx_hdr));
+		ctx_handle = hdr->ctx_dma;
+	}
+
+	/* select the queue */
+	qno = smp_processor_id() % ndev->nr_queues;
+
+	sr->cmdq = &ndev->pkt_inq[qno];
+
+	/*
+	 * 64-Byte Instruction Format
+	 *
+	 *  ----------------------
+	 *  |      DPTR0         | 8 bytes
+	 *  ----------------------
+	 *  |  PKT_IN_INSTR_HDR  | 8 bytes
+	 *  ----------------------
+	 *  |    PKT_IN_HDR      | 16 bytes
+	 *  ----------------------
+	 *  |    SLC_INFO        | 16 bytes
+	 *  ----------------------
+	 *  |   Front data       | 16 bytes
+	 *  ----------------------
+	 */
+
+	/* fill the packet instruction */
+	/* word 0 */
+	sr->instr.dptr0 = cpu_to_be64(sr->in.sgcomp_dma);
+
+	/* word 1 */
+	sr->instr.ih.value = 0;
+	sr->instr.ih.s.g = 1;
+	sr->instr.ih.s.gsz = sr->in.sgmap_cnt;
+	sr->instr.ih.s.ssz = sr->out.sgmap_cnt;
+	sr->instr.ih.s.fsz = FDATA_SIZE + sizeof(struct gphdr);
+	sr->instr.ih.s.tlen = sr->instr.ih.s.fsz + sr->in.total_bytes;
+	sr->instr.ih.bev = cpu_to_be64(sr->instr.ih.value);
+
+	/* word 2 */
+	sr->instr.irh.value[0] = 0;
+	sr->instr.irh.s.uddl = MIN_UDD_LEN;
+	/* context length in 64-bit words */
+	sr->instr.irh.s.ctxl = (req->ctrl.s.ctxl / 8);
+	/* offset from solicit base port 256 */
+	sr->instr.irh.s.destport = SOLICIT_BASE_DPORT + qno;
+	sr->instr.irh.s.ctxc = req->ctrl.s.ctxc;
+	sr->instr.irh.s.arg = req->ctrl.s.arg;
+	sr->instr.irh.s.opcode = req->opcode;
+	sr->instr.irh.bev[0] = cpu_to_be64(sr->instr.irh.value[0]);
+
+	/* word 3 */
+	sr->instr.irh.s.ctxp = cpu_to_be64(ctx_handle);
+
+	/* word 4 */
+	sr->instr.slc.value[0] = 0;
+	sr->instr.slc.s.ssz = sr->out.sgmap_cnt;
+	sr->instr.slc.bev[0] = cpu_to_be64(sr->instr.slc.value[0]);
+
+	/* word 5 */
+	sr->instr.slc.s.rptr = cpu_to_be64(sr->out.sgcomp_dma);
+
+	/*
+	 * No conversion for front data,
+	 * It goes into payload
+	 * put GP Header in front data
+	 */
+	sr->instr.fdata[0] = *((u64 *)&req->gph);
+	sr->instr.fdata[1] = 0;
+
+	ret = nitrox_enqueue_request(sr);
+	if (ret == -ENOSPC)
+		goto send_fail;
+
+	return ret;
+
+send_fail:
+	softreq_destroy(sr);
+	return ret;
+}
+
+static inline int cmd_timeout(unsigned long tstamp, unsigned long timeout)
+{
+	return time_after_eq(jiffies, (tstamp + timeout));
+}
+
+void backlog_qflush_work(struct work_struct *work)
+{
+	struct nitrox_cmdq *cmdq;
+
+	cmdq = container_of(work, struct nitrox_cmdq, backlog_qflush);
+	post_backlog_cmds(cmdq);
+}
+
+static bool sr_completed(struct nitrox_softreq *sr)
+{
+	u64 orh = READ_ONCE(*sr->resp.orh);
+	unsigned long timeout = jiffies + msecs_to_jiffies(1);
+
+	if ((orh != PENDING_SIG) && (orh & 0xff))
+		return true;
+
+	while (READ_ONCE(*sr->resp.completion) == PENDING_SIG) {
+		if (time_after(jiffies, timeout)) {
+			pr_err("comp not done\n");
+			return false;
+		}
+	}
+
+	return true;
+}
+
+/**
+ * process_response_list - process completed requests
+ * @cmdq: Command queue structure
+ *
+ * Returns the number of responses processed.
+ */
+static void process_response_list(struct nitrox_cmdq *cmdq)
+{
+	struct nitrox_device *ndev = cmdq->ndev;
+	struct nitrox_softreq *sr;
+	int req_completed = 0, err = 0, budget;
+	completion_t callback;
+	void *cb_arg;
+
+	/* check all pending requests */
+	budget = atomic_read(&cmdq->pending_count);
+
+	while (req_completed < budget) {
+		sr = get_first_response_entry(cmdq);
+		if (!sr)
+			break;
+
+		if (atomic_read(&sr->status) != REQ_POSTED)
+			break;
+
+		/* check orh and completion bytes updates */
+		if (!sr_completed(sr)) {
+			/* request not completed, check for timeout */
+			if (!cmd_timeout(sr->tstamp, ndev->timeout))
+				break;
+			dev_err_ratelimited(DEV(ndev),
+					    "Request timeout, orh 0x%016llx\n",
+					    READ_ONCE(*sr->resp.orh));
+		}
+		atomic_dec(&cmdq->pending_count);
+		atomic64_inc(&ndev->stats.completed);
+		/* sync with other cpus */
+		smp_mb__after_atomic();
+		/* remove from response list */
+		response_list_del(sr, cmdq);
+		/* ORH error code */
+		err = READ_ONCE(*sr->resp.orh) & 0xff;
+		callback = sr->callback;
+		cb_arg = sr->cb_arg;
+		softreq_destroy(sr);
+		if (callback)
+			callback(cb_arg, err);
+
+		req_completed++;
+	}
+}
+
+/*
+ * pkt_slc_resp_tasklet - post processing of SE responses
+ */
+void pkt_slc_resp_tasklet(unsigned long data)
+{
+	struct nitrox_q_vector *qvec = (void *)(uintptr_t)(data);
+	struct nitrox_cmdq *cmdq = qvec->cmdq;
+	union nps_pkt_slc_cnts slc_cnts;
+
+	/* read completion count */
+	slc_cnts.value = readq(cmdq->compl_cnt_csr_addr);
+	/* resend the interrupt if more work to do */
+	slc_cnts.s.resend = 1;
+
+	process_response_list(cmdq);
+
+	/*
+	 * clear the interrupt with resend bit enabled,
+	 * MSI-X interrupt generates if Completion count > Threshold
+	 */
+	writeq(slc_cnts.value, cmdq->compl_cnt_csr_addr);
+
+	if (atomic_read(&cmdq->backlog_count))
+		schedule_work(&cmdq->backlog_qflush);
+}
diff --git a/drivers/crypto/cavium/nitrox/nitrox_skcipher.c b/drivers/crypto/cavium/nitrox/nitrox_skcipher.c
new file mode 100644
index 000000000..6e5e667ba
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/nitrox_skcipher.c
@@ -0,0 +1,531 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+
+#include <crypto/aes.h>
+#include <crypto/skcipher.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/ctr.h>
+#include <crypto/internal/des.h>
+#include <crypto/xts.h>
+
+#include "nitrox_dev.h"
+#include "nitrox_common.h"
+#include "nitrox_req.h"
+
+struct nitrox_cipher {
+	const char *name;
+	enum flexi_cipher value;
+};
+
+/*
+ * supported cipher list
+ */
+static const struct nitrox_cipher flexi_cipher_table[] = {
+	{ "null",		CIPHER_NULL },
+	{ "cbc(des3_ede)",	CIPHER_3DES_CBC },
+	{ "ecb(des3_ede)",	CIPHER_3DES_ECB },
+	{ "cbc(aes)",		CIPHER_AES_CBC },
+	{ "ecb(aes)",		CIPHER_AES_ECB },
+	{ "cfb(aes)",		CIPHER_AES_CFB },
+	{ "rfc3686(ctr(aes))",	CIPHER_AES_CTR },
+	{ "xts(aes)",		CIPHER_AES_XTS },
+	{ "cts(cbc(aes))",	CIPHER_AES_CBC_CTS },
+	{ NULL,			CIPHER_INVALID }
+};
+
+static enum flexi_cipher flexi_cipher_type(const char *name)
+{
+	const struct nitrox_cipher *cipher = flexi_cipher_table;
+
+	while (cipher->name) {
+		if (!strcmp(cipher->name, name))
+			break;
+		cipher++;
+	}
+	return cipher->value;
+}
+
+static void free_src_sglist(struct skcipher_request *skreq)
+{
+	struct nitrox_kcrypt_request *nkreq = skcipher_request_ctx(skreq);
+
+	kfree(nkreq->src);
+}
+
+static void free_dst_sglist(struct skcipher_request *skreq)
+{
+	struct nitrox_kcrypt_request *nkreq = skcipher_request_ctx(skreq);
+
+	kfree(nkreq->dst);
+}
+
+static void nitrox_skcipher_callback(void *arg, int err)
+{
+	struct skcipher_request *skreq = arg;
+
+	free_src_sglist(skreq);
+	free_dst_sglist(skreq);
+	if (err) {
+		pr_err_ratelimited("request failed status 0x%0x\n", err);
+		err = -EINVAL;
+	}
+
+	skcipher_request_complete(skreq, err);
+}
+
+static void nitrox_cbc_cipher_callback(void *arg, int err)
+{
+	struct skcipher_request *skreq = arg;
+	struct nitrox_kcrypt_request *nkreq = skcipher_request_ctx(skreq);
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(skreq);
+	int ivsize = crypto_skcipher_ivsize(cipher);
+	unsigned int start = skreq->cryptlen - ivsize;
+
+	if (err) {
+		nitrox_skcipher_callback(arg, err);
+		return;
+	}
+
+	if (nkreq->creq.ctrl.s.arg == ENCRYPT) {
+		scatterwalk_map_and_copy(skreq->iv, skreq->dst, start, ivsize,
+					 0);
+	} else {
+		if (skreq->src != skreq->dst) {
+			scatterwalk_map_and_copy(skreq->iv, skreq->src, start,
+						 ivsize, 0);
+		} else {
+			memcpy(skreq->iv, nkreq->iv_out, ivsize);
+			kfree(nkreq->iv_out);
+		}
+	}
+
+	nitrox_skcipher_callback(arg, err);
+}
+
+static int nitrox_skcipher_init(struct crypto_skcipher *tfm)
+{
+	struct nitrox_crypto_ctx *nctx = crypto_skcipher_ctx(tfm);
+	struct crypto_ctx_hdr *chdr;
+
+	/* get the first device */
+	nctx->ndev = nitrox_get_first_device();
+	if (!nctx->ndev)
+		return -ENODEV;
+
+	/* allocate nitrox crypto context */
+	chdr = crypto_alloc_context(nctx->ndev);
+	if (!chdr) {
+		nitrox_put_device(nctx->ndev);
+		return -ENOMEM;
+	}
+
+	nctx->callback = nitrox_skcipher_callback;
+	nctx->chdr = chdr;
+	nctx->u.ctx_handle = (uintptr_t)((u8 *)chdr->vaddr +
+					 sizeof(struct ctx_hdr));
+	crypto_skcipher_set_reqsize(tfm, crypto_skcipher_reqsize(tfm) +
+				    sizeof(struct nitrox_kcrypt_request));
+	return 0;
+}
+
+static int nitrox_cbc_init(struct crypto_skcipher *tfm)
+{
+	int err;
+	struct nitrox_crypto_ctx *nctx = crypto_skcipher_ctx(tfm);
+
+	err = nitrox_skcipher_init(tfm);
+	if (err)
+		return err;
+
+	nctx->callback = nitrox_cbc_cipher_callback;
+	return 0;
+}
+
+static void nitrox_skcipher_exit(struct crypto_skcipher *tfm)
+{
+	struct nitrox_crypto_ctx *nctx = crypto_skcipher_ctx(tfm);
+
+	/* free the nitrox crypto context */
+	if (nctx->u.ctx_handle) {
+		struct flexi_crypto_context *fctx = nctx->u.fctx;
+
+		memzero_explicit(&fctx->crypto, sizeof(struct crypto_keys));
+		memzero_explicit(&fctx->auth, sizeof(struct auth_keys));
+		crypto_free_context((void *)nctx->chdr);
+	}
+	nitrox_put_device(nctx->ndev);
+
+	nctx->u.ctx_handle = 0;
+	nctx->ndev = NULL;
+}
+
+static inline int nitrox_skcipher_setkey(struct crypto_skcipher *cipher,
+					 int aes_keylen, const u8 *key,
+					 unsigned int keylen)
+{
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(cipher);
+	struct nitrox_crypto_ctx *nctx = crypto_tfm_ctx(tfm);
+	struct flexi_crypto_context *fctx;
+	union fc_ctx_flags *flags;
+	enum flexi_cipher cipher_type;
+	const char *name;
+
+	name = crypto_tfm_alg_name(tfm);
+	cipher_type = flexi_cipher_type(name);
+	if (unlikely(cipher_type == CIPHER_INVALID)) {
+		pr_err("unsupported cipher: %s\n", name);
+		return -EINVAL;
+	}
+
+	/* fill crypto context */
+	fctx = nctx->u.fctx;
+	flags = &fctx->flags;
+	flags->f = 0;
+	flags->w0.cipher_type = cipher_type;
+	flags->w0.aes_keylen = aes_keylen;
+	flags->w0.iv_source = IV_FROM_DPTR;
+	flags->f = cpu_to_be64(*(u64 *)&flags->w0);
+	/* copy the key to context */
+	memcpy(fctx->crypto.u.key, key, keylen);
+
+	return 0;
+}
+
+static int nitrox_aes_setkey(struct crypto_skcipher *cipher, const u8 *key,
+			     unsigned int keylen)
+{
+	int aes_keylen;
+
+	aes_keylen = flexi_aes_keylen(keylen);
+	if (aes_keylen < 0)
+		return -EINVAL;
+	return nitrox_skcipher_setkey(cipher, aes_keylen, key, keylen);
+}
+
+static int alloc_src_sglist(struct skcipher_request *skreq, int ivsize)
+{
+	struct nitrox_kcrypt_request *nkreq = skcipher_request_ctx(skreq);
+	int nents = sg_nents(skreq->src) + 1;
+	int ret;
+
+	/* Allocate buffer to hold IV and input scatterlist array */
+	ret = alloc_src_req_buf(nkreq, nents, ivsize);
+	if (ret)
+		return ret;
+
+	nitrox_creq_copy_iv(nkreq->src, skreq->iv, ivsize);
+	nitrox_creq_set_src_sg(nkreq, nents, ivsize, skreq->src,
+			       skreq->cryptlen);
+
+	return 0;
+}
+
+static int alloc_dst_sglist(struct skcipher_request *skreq, int ivsize)
+{
+	struct nitrox_kcrypt_request *nkreq = skcipher_request_ctx(skreq);
+	int nents = sg_nents(skreq->dst) + 3;
+	int ret;
+
+	/* Allocate buffer to hold ORH, COMPLETION and output scatterlist
+	 * array
+	 */
+	ret = alloc_dst_req_buf(nkreq, nents);
+	if (ret)
+		return ret;
+
+	nitrox_creq_set_orh(nkreq);
+	nitrox_creq_set_comp(nkreq);
+	nitrox_creq_set_dst_sg(nkreq, nents, ivsize, skreq->dst,
+			       skreq->cryptlen);
+
+	return 0;
+}
+
+static int nitrox_skcipher_crypt(struct skcipher_request *skreq, bool enc)
+{
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(skreq);
+	struct nitrox_crypto_ctx *nctx = crypto_skcipher_ctx(cipher);
+	struct nitrox_kcrypt_request *nkreq = skcipher_request_ctx(skreq);
+	int ivsize = crypto_skcipher_ivsize(cipher);
+	struct se_crypto_request *creq;
+	int ret;
+
+	creq = &nkreq->creq;
+	creq->flags = skreq->base.flags;
+	creq->gfp = (skreq->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+		     GFP_KERNEL : GFP_ATOMIC;
+
+	/* fill the request */
+	creq->ctrl.value = 0;
+	creq->opcode = FLEXI_CRYPTO_ENCRYPT_HMAC;
+	creq->ctrl.s.arg = (enc ? ENCRYPT : DECRYPT);
+	/* param0: length of the data to be encrypted */
+	creq->gph.param0 = cpu_to_be16(skreq->cryptlen);
+	creq->gph.param1 = 0;
+	/* param2: encryption data offset */
+	creq->gph.param2 = cpu_to_be16(ivsize);
+	creq->gph.param3 = 0;
+
+	creq->ctx_handle = nctx->u.ctx_handle;
+	creq->ctrl.s.ctxl = sizeof(struct flexi_crypto_context);
+
+	ret = alloc_src_sglist(skreq, ivsize);
+	if (ret)
+		return ret;
+
+	ret = alloc_dst_sglist(skreq, ivsize);
+	if (ret) {
+		free_src_sglist(skreq);
+		return ret;
+	}
+
+	/* send the crypto request */
+	return nitrox_process_se_request(nctx->ndev, creq, nctx->callback,
+					 skreq);
+}
+
+static int nitrox_cbc_decrypt(struct skcipher_request *skreq)
+{
+	struct nitrox_kcrypt_request *nkreq = skcipher_request_ctx(skreq);
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(skreq);
+	int ivsize = crypto_skcipher_ivsize(cipher);
+	gfp_t flags = (skreq->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+			GFP_KERNEL : GFP_ATOMIC;
+	unsigned int start = skreq->cryptlen - ivsize;
+
+	if (skreq->src != skreq->dst)
+		return nitrox_skcipher_crypt(skreq, false);
+
+	nkreq->iv_out = kmalloc(ivsize, flags);
+	if (!nkreq->iv_out)
+		return -ENOMEM;
+
+	scatterwalk_map_and_copy(nkreq->iv_out, skreq->src, start, ivsize, 0);
+	return nitrox_skcipher_crypt(skreq, false);
+}
+
+static int nitrox_aes_encrypt(struct skcipher_request *skreq)
+{
+	return nitrox_skcipher_crypt(skreq, true);
+}
+
+static int nitrox_aes_decrypt(struct skcipher_request *skreq)
+{
+	return nitrox_skcipher_crypt(skreq, false);
+}
+
+static int nitrox_3des_setkey(struct crypto_skcipher *cipher,
+			      const u8 *key, unsigned int keylen)
+{
+	return verify_skcipher_des3_key(cipher, key) ?:
+	       nitrox_skcipher_setkey(cipher, 0, key, keylen);
+}
+
+static int nitrox_3des_encrypt(struct skcipher_request *skreq)
+{
+	return nitrox_skcipher_crypt(skreq, true);
+}
+
+static int nitrox_3des_decrypt(struct skcipher_request *skreq)
+{
+	return nitrox_skcipher_crypt(skreq, false);
+}
+
+static int nitrox_aes_xts_setkey(struct crypto_skcipher *cipher,
+				 const u8 *key, unsigned int keylen)
+{
+	struct nitrox_crypto_ctx *nctx = crypto_skcipher_ctx(cipher);
+	struct flexi_crypto_context *fctx;
+	int aes_keylen, ret;
+
+	ret = xts_verify_key(cipher, key, keylen);
+	if (ret)
+		return ret;
+
+	keylen /= 2;
+
+	aes_keylen = flexi_aes_keylen(keylen);
+	if (aes_keylen < 0)
+		return -EINVAL;
+
+	fctx = nctx->u.fctx;
+	/* copy KEY2 */
+	memcpy(fctx->auth.u.key2, (key + keylen), keylen);
+
+	return nitrox_skcipher_setkey(cipher, aes_keylen, key, keylen);
+}
+
+static int nitrox_aes_ctr_rfc3686_setkey(struct crypto_skcipher *cipher,
+					 const u8 *key, unsigned int keylen)
+{
+	struct nitrox_crypto_ctx *nctx = crypto_skcipher_ctx(cipher);
+	struct flexi_crypto_context *fctx;
+	int aes_keylen;
+
+	if (keylen < CTR_RFC3686_NONCE_SIZE)
+		return -EINVAL;
+
+	fctx = nctx->u.fctx;
+
+	memcpy(fctx->crypto.iv, key + (keylen - CTR_RFC3686_NONCE_SIZE),
+	       CTR_RFC3686_NONCE_SIZE);
+
+	keylen -= CTR_RFC3686_NONCE_SIZE;
+
+	aes_keylen = flexi_aes_keylen(keylen);
+	if (aes_keylen < 0)
+		return -EINVAL;
+	return nitrox_skcipher_setkey(cipher, aes_keylen, key, keylen);
+}
+
+static struct skcipher_alg nitrox_skciphers[] = { {
+	.base = {
+		.cra_name = "cbc(aes)",
+		.cra_driver_name = "n5_cbc(aes)",
+		.cra_priority = PRIO,
+		.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY,
+		.cra_blocksize = AES_BLOCK_SIZE,
+		.cra_ctxsize = sizeof(struct nitrox_crypto_ctx),
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+	},
+	.min_keysize = AES_MIN_KEY_SIZE,
+	.max_keysize = AES_MAX_KEY_SIZE,
+	.ivsize = AES_BLOCK_SIZE,
+	.setkey = nitrox_aes_setkey,
+	.encrypt = nitrox_aes_encrypt,
+	.decrypt = nitrox_cbc_decrypt,
+	.init = nitrox_cbc_init,
+	.exit = nitrox_skcipher_exit,
+}, {
+	.base = {
+		.cra_name = "ecb(aes)",
+		.cra_driver_name = "n5_ecb(aes)",
+		.cra_priority = PRIO,
+		.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY,
+		.cra_blocksize = AES_BLOCK_SIZE,
+		.cra_ctxsize = sizeof(struct nitrox_crypto_ctx),
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+	},
+	.min_keysize = AES_MIN_KEY_SIZE,
+	.max_keysize = AES_MAX_KEY_SIZE,
+	.ivsize = AES_BLOCK_SIZE,
+	.setkey = nitrox_aes_setkey,
+	.encrypt = nitrox_aes_encrypt,
+	.decrypt = nitrox_aes_decrypt,
+	.init = nitrox_skcipher_init,
+	.exit = nitrox_skcipher_exit,
+}, {
+	.base = {
+		.cra_name = "xts(aes)",
+		.cra_driver_name = "n5_xts(aes)",
+		.cra_priority = PRIO,
+		.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY,
+		.cra_blocksize = AES_BLOCK_SIZE,
+		.cra_ctxsize = sizeof(struct nitrox_crypto_ctx),
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+	},
+	.min_keysize = 2 * AES_MIN_KEY_SIZE,
+	.max_keysize = 2 * AES_MAX_KEY_SIZE,
+	.ivsize = AES_BLOCK_SIZE,
+	.setkey = nitrox_aes_xts_setkey,
+	.encrypt = nitrox_aes_encrypt,
+	.decrypt = nitrox_aes_decrypt,
+	.init = nitrox_skcipher_init,
+	.exit = nitrox_skcipher_exit,
+}, {
+	.base = {
+		.cra_name = "rfc3686(ctr(aes))",
+		.cra_driver_name = "n5_rfc3686(ctr(aes))",
+		.cra_priority = PRIO,
+		.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY,
+		.cra_blocksize = 1,
+		.cra_ctxsize = sizeof(struct nitrox_crypto_ctx),
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+	},
+	.min_keysize = AES_MIN_KEY_SIZE + CTR_RFC3686_NONCE_SIZE,
+	.max_keysize = AES_MAX_KEY_SIZE + CTR_RFC3686_NONCE_SIZE,
+	.ivsize = CTR_RFC3686_IV_SIZE,
+	.init = nitrox_skcipher_init,
+	.exit = nitrox_skcipher_exit,
+	.setkey = nitrox_aes_ctr_rfc3686_setkey,
+	.encrypt = nitrox_aes_encrypt,
+	.decrypt = nitrox_aes_decrypt,
+}, {
+	.base = {
+		.cra_name = "cts(cbc(aes))",
+		.cra_driver_name = "n5_cts(cbc(aes))",
+		.cra_priority = PRIO,
+		.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY,
+		.cra_blocksize = AES_BLOCK_SIZE,
+		.cra_ctxsize = sizeof(struct nitrox_crypto_ctx),
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+	},
+	.min_keysize = AES_MIN_KEY_SIZE,
+	.max_keysize = AES_MAX_KEY_SIZE,
+	.ivsize = AES_BLOCK_SIZE,
+	.setkey = nitrox_aes_setkey,
+	.encrypt = nitrox_aes_encrypt,
+	.decrypt = nitrox_aes_decrypt,
+	.init = nitrox_skcipher_init,
+	.exit = nitrox_skcipher_exit,
+}, {
+	.base = {
+		.cra_name = "cbc(des3_ede)",
+		.cra_driver_name = "n5_cbc(des3_ede)",
+		.cra_priority = PRIO,
+		.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY,
+		.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+		.cra_ctxsize = sizeof(struct nitrox_crypto_ctx),
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+	},
+	.min_keysize = DES3_EDE_KEY_SIZE,
+	.max_keysize = DES3_EDE_KEY_SIZE,
+	.ivsize = DES3_EDE_BLOCK_SIZE,
+	.setkey = nitrox_3des_setkey,
+	.encrypt = nitrox_3des_encrypt,
+	.decrypt = nitrox_cbc_decrypt,
+	.init = nitrox_cbc_init,
+	.exit = nitrox_skcipher_exit,
+}, {
+	.base = {
+		.cra_name = "ecb(des3_ede)",
+		.cra_driver_name = "n5_ecb(des3_ede)",
+		.cra_priority = PRIO,
+		.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY,
+		.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+		.cra_ctxsize = sizeof(struct nitrox_crypto_ctx),
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+	},
+	.min_keysize = DES3_EDE_KEY_SIZE,
+	.max_keysize = DES3_EDE_KEY_SIZE,
+	.ivsize = DES3_EDE_BLOCK_SIZE,
+	.setkey = nitrox_3des_setkey,
+	.encrypt = nitrox_3des_encrypt,
+	.decrypt = nitrox_3des_decrypt,
+	.init = nitrox_skcipher_init,
+	.exit = nitrox_skcipher_exit,
+}
+
+};
+
+int nitrox_register_skciphers(void)
+{
+	return crypto_register_skciphers(nitrox_skciphers,
+					 ARRAY_SIZE(nitrox_skciphers));
+}
+
+void nitrox_unregister_skciphers(void)
+{
+	crypto_unregister_skciphers(nitrox_skciphers,
+				    ARRAY_SIZE(nitrox_skciphers));
+}
diff --git a/drivers/crypto/cavium/nitrox/nitrox_sriov.c b/drivers/crypto/cavium/nitrox/nitrox_sriov.c
new file mode 100644
index 000000000..43287f847
--- /dev/null
+++ b/drivers/crypto/cavium/nitrox/nitrox_sriov.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/pci.h>
+#include <linux/delay.h>
+
+#include "nitrox_dev.h"
+#include "nitrox_hal.h"
+#include "nitrox_common.h"
+#include "nitrox_isr.h"
+#include "nitrox_mbx.h"
+
+/**
+ * num_vfs_valid - validate VF count
+ * @num_vfs: number of VF(s)
+ */
+static inline bool num_vfs_valid(int num_vfs)
+{
+	bool valid = false;
+
+	switch (num_vfs) {
+	case 16:
+	case 32:
+	case 64:
+	case 128:
+		valid = true;
+		break;
+	}
+
+	return valid;
+}
+
+static inline enum vf_mode num_vfs_to_mode(int num_vfs)
+{
+	enum vf_mode mode = 0;
+
+	switch (num_vfs) {
+	case 0:
+		mode = __NDEV_MODE_PF;
+		break;
+	case 16:
+		mode = __NDEV_MODE_VF16;
+		break;
+	case 32:
+		mode = __NDEV_MODE_VF32;
+		break;
+	case 64:
+		mode = __NDEV_MODE_VF64;
+		break;
+	case 128:
+		mode = __NDEV_MODE_VF128;
+		break;
+	}
+
+	return mode;
+}
+
+static inline int vf_mode_to_nr_queues(enum vf_mode mode)
+{
+	int nr_queues = 0;
+
+	switch (mode) {
+	case __NDEV_MODE_PF:
+		nr_queues = MAX_PF_QUEUES;
+		break;
+	case __NDEV_MODE_VF16:
+		nr_queues = 8;
+		break;
+	case __NDEV_MODE_VF32:
+		nr_queues = 4;
+		break;
+	case __NDEV_MODE_VF64:
+		nr_queues = 2;
+		break;
+	case __NDEV_MODE_VF128:
+		nr_queues = 1;
+		break;
+	}
+
+	return nr_queues;
+}
+
+static void nitrox_pf_cleanup(struct nitrox_device *ndev)
+{
+	 /* PF has no queues in SR-IOV mode */
+	atomic_set(&ndev->state, __NDEV_NOT_READY);
+	/* unregister crypto algorithms */
+	nitrox_crypto_unregister();
+
+	/* cleanup PF resources */
+	nitrox_unregister_interrupts(ndev);
+	nitrox_common_sw_cleanup(ndev);
+}
+
+/**
+ * nitrox_pf_reinit - re-initialize PF resources once SR-IOV is disabled
+ * @ndev: NITROX device
+ */
+static int nitrox_pf_reinit(struct nitrox_device *ndev)
+{
+	int err;
+
+	/* allocate resources for PF */
+	err = nitrox_common_sw_init(ndev);
+	if (err)
+		return err;
+
+	err = nitrox_register_interrupts(ndev);
+	if (err) {
+		nitrox_common_sw_cleanup(ndev);
+		return err;
+	}
+
+	/* configure the AQM queues */
+	nitrox_config_aqm_rings(ndev);
+
+	/* configure the packet queues */
+	nitrox_config_pkt_input_rings(ndev);
+	nitrox_config_pkt_solicit_ports(ndev);
+
+	/* set device to ready state */
+	atomic_set(&ndev->state, __NDEV_READY);
+
+	/* register crypto algorithms */
+	return nitrox_crypto_register();
+}
+
+static void nitrox_sriov_cleanup(struct nitrox_device *ndev)
+{
+	/* unregister interrupts for PF in SR-IOV */
+	nitrox_sriov_unregister_interrupts(ndev);
+	nitrox_mbox_cleanup(ndev);
+}
+
+static int nitrox_sriov_init(struct nitrox_device *ndev)
+{
+	int ret;
+
+	/* register interrupts for PF in SR-IOV */
+	ret = nitrox_sriov_register_interupts(ndev);
+	if (ret)
+		return ret;
+
+	ret = nitrox_mbox_init(ndev);
+	if (ret)
+		goto sriov_init_fail;
+
+	return 0;
+
+sriov_init_fail:
+	nitrox_sriov_cleanup(ndev);
+	return ret;
+}
+
+static int nitrox_sriov_enable(struct pci_dev *pdev, int num_vfs)
+{
+	struct nitrox_device *ndev = pci_get_drvdata(pdev);
+	int err;
+
+	if (!num_vfs_valid(num_vfs)) {
+		dev_err(DEV(ndev), "Invalid num_vfs %d\n", num_vfs);
+		return -EINVAL;
+	}
+
+	if (pci_num_vf(pdev) == num_vfs)
+		return num_vfs;
+
+	err = pci_enable_sriov(pdev, num_vfs);
+	if (err) {
+		dev_err(DEV(ndev), "failed to enable PCI sriov %d\n", err);
+		return err;
+	}
+	dev_info(DEV(ndev), "Enabled VF(s) %d\n", num_vfs);
+
+	ndev->mode = num_vfs_to_mode(num_vfs);
+	ndev->iov.num_vfs = num_vfs;
+	ndev->iov.max_vf_queues = vf_mode_to_nr_queues(ndev->mode);
+	/* set bit in flags */
+	set_bit(__NDEV_SRIOV_BIT, &ndev->flags);
+
+	/* cleanup PF resources */
+	nitrox_pf_cleanup(ndev);
+
+	/* PF SR-IOV mode initialization */
+	err = nitrox_sriov_init(ndev);
+	if (err)
+		goto iov_fail;
+
+	config_nps_core_vfcfg_mode(ndev, ndev->mode);
+	return num_vfs;
+
+iov_fail:
+	pci_disable_sriov(pdev);
+	/* clear bit in flags */
+	clear_bit(__NDEV_SRIOV_BIT, &ndev->flags);
+	ndev->iov.num_vfs = 0;
+	ndev->mode = __NDEV_MODE_PF;
+	/* reset back to working mode in PF */
+	nitrox_pf_reinit(ndev);
+	return err;
+}
+
+static int nitrox_sriov_disable(struct pci_dev *pdev)
+{
+	struct nitrox_device *ndev = pci_get_drvdata(pdev);
+
+	if (!test_bit(__NDEV_SRIOV_BIT, &ndev->flags))
+		return 0;
+
+	if (pci_vfs_assigned(pdev)) {
+		dev_warn(DEV(ndev), "VFs are attached to VM. Can't disable SR-IOV\n");
+		return -EPERM;
+	}
+	pci_disable_sriov(pdev);
+	/* clear bit in flags */
+	clear_bit(__NDEV_SRIOV_BIT, &ndev->flags);
+
+	ndev->iov.num_vfs = 0;
+	ndev->iov.max_vf_queues = 0;
+	ndev->mode = __NDEV_MODE_PF;
+
+	/* cleanup PF SR-IOV resources */
+	nitrox_sriov_cleanup(ndev);
+
+	config_nps_core_vfcfg_mode(ndev, ndev->mode);
+
+	return nitrox_pf_reinit(ndev);
+}
+
+int nitrox_sriov_configure(struct pci_dev *pdev, int num_vfs)
+{
+	if (!num_vfs)
+		return nitrox_sriov_disable(pdev);
+
+	return nitrox_sriov_enable(pdev, num_vfs);
+}