From: Subject: [PATCH v3 1/3] drivers: crypto: Add Support for Octeon-tx CPT Engine Date: Wed, 21 Dec 2016 11:56:11 +0000 Message-ID: <1482321373-407-2-git-send-email-george.cherian@cavium.com> References: <1482321373-407-1-git-send-email-george.cherian@cavium.com> Mime-Version: 1.0 Content-Type: text/plain Cc: , , , George Cherian To: , Return-path: Received: from mail-by2nam01on0047.outbound.protection.outlook.com ([104.47.34.47]:12640 "EHLO NAM01-BY2-obe.outbound.protection.outlook.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1755351AbcLUL4p (ORCPT ); Wed, 21 Dec 2016 06:56:45 -0500 In-Reply-To: <1482321373-407-1-git-send-email-george.cherian@cavium.com> Sender: linux-crypto-owner@vger.kernel.org List-ID: From: George Cherian Enable the Physical Function diver for the Cavium Crypto Engine (CPT) found in Octeon-tx series of SoC's. CPT is the Cryptographic Acceleration Unit. CPT includes microcoded GigaCypher symmetric engines (SEs) and asymmetric engines (AEs). Signed-off-by: George Cherian Reviewed-by: David Daney --- drivers/crypto/cavium/cpt/Kconfig | 16 + drivers/crypto/cavium/cpt/Makefile | 2 + drivers/crypto/cavium/cpt/cpt_common.h | 158 +++++++ drivers/crypto/cavium/cpt/cpt_hw_types.h | 658 +++++++++++++++++++++++++++++ drivers/crypto/cavium/cpt/cptpf.h | 69 +++ drivers/crypto/cavium/cpt/cptpf_main.c | 703 +++++++++++++++++++++++++++++++ drivers/crypto/cavium/cpt/cptpf_mbox.c | 163 +++++++ 7 files changed, 1769 insertions(+) create mode 100644 drivers/crypto/cavium/cpt/Kconfig create mode 100644 drivers/crypto/cavium/cpt/Makefile create mode 100644 drivers/crypto/cavium/cpt/cpt_common.h create mode 100644 drivers/crypto/cavium/cpt/cpt_hw_types.h create mode 100644 drivers/crypto/cavium/cpt/cptpf.h create mode 100644 drivers/crypto/cavium/cpt/cptpf_main.c create mode 100644 drivers/crypto/cavium/cpt/cptpf_mbox.c diff --git a/drivers/crypto/cavium/cpt/Kconfig b/drivers/crypto/cavium/cpt/Kconfig new file mode 100644 index 0000000..247f1cb --- /dev/null +++ b/drivers/crypto/cavium/cpt/Kconfig @@ -0,0 +1,16 @@ +# +# Cavium crypto device configuration +# + +config CRYPTO_DEV_CPT + tristate + +config CAVIUM_CPT + tristate "Cavium Cryptographic Accelerator driver" + depends on ARCH_THUNDER + 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 0000000..fe3d454 --- /dev/null +++ b/drivers/crypto/cavium/cpt/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_CAVIUM_CPT) += cptpf.o +cptpf-objs := cptpf_main.o cptpf_mbox.o diff --git a/drivers/crypto/cavium/cpt/cpt_common.h b/drivers/crypto/cavium/cpt/cpt_common.h new file mode 100644 index 0000000..ede612f --- /dev/null +++ b/drivers/crypto/cavium/cpt/cpt_common.h @@ -0,0 +1,158 @@ +/* + * Copyright (C) 2016 Cavium, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU General Public License + * as published by the Free Software Foundation. + */ + +#ifndef __CPT_COMMON_H +#define __CPT_COMMON_H + +#include +#include +#include + +#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_MSIX_ENABLED BIT(0) +#define CPT_FLAG_SRIOV_ENABLED BIT(1) +#define CPT_FLAG_VF_DRIVER BIT(2) +#define CPT_FLAG_DEVICE_READY BIT(3) + +#define cpt_msix_enabled(cpt) ((cpt)->flags & CPT_FLAG_MSIX_ENABLED) +#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 0000000..2796694 --- /dev/null +++ b/drivers/crypto/cavium/cpt/cpt_hw_types.h @@ -0,0 +1,658 @@ +/* + * Copyright (C) 2016 Cavium, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU General Public License + * as published by the Free Software Foundation. + */ + +#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 is 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 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 0000000..deee67a --- /dev/null +++ b/drivers/crypto/cavium/cpt/cptpf.h @@ -0,0 +1,69 @@ +/* + * Copyright (C) 2016 Cavium, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU General Public License + * as published by the Free Software Foundation. + */ + +#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)) + +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[32]; + /* 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 */ + /* MSI-X */ + u8 num_vec; + bool msix_enabled; + struct msix_entry msix_entries[CPT_PF_MSIX_VECTORS]; + bool irq_allocated[CPT_PF_MSIX_VECTORS]; + 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 0000000..f9c8c12 --- /dev/null +++ b/drivers/crypto/cavium/cpt/cptpf_main.c @@ -0,0 +1,703 @@ +/* + * Copyright (C) 2016 Cavium, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License + * as published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#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 = 0xFFFFFFFF; + 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; + } + + /* 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 1; + } + + if (mcode->code_size == 0) { + dev_err(dev, "microcode size is 0\n"); + return 1; + } + + /* 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 = -1; + 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 */ + if (cpt_load_microcode(cpt, mcode)) { + dev_err(dev, "Microcode load Failed for %s\n", + mcode->version); + ret = -1; + 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 = -1; + 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 */ + if (cpt_load_microcode(cpt, mcode)) { + dev_err(dev, "Microcode load Failed for %s\n", + mcode->version); + ret = -1; + 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[32]; + u32 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; + struct microcode *mcode; + int j, ret = 0; + + ret = request_firmware(&fw_entry, fw, dev); + if (ret) + return ret; + + mcode = &cpt->mcode[cpt->next_mc_idx]; + ucode = (struct ucode_header *)fw_entry->data; + memcpy(mcode->version, (u8 *)fw_entry->data, 32); + mcode->code_size = ntohl(ucode->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_zalloc_coherent(&cpt->pdev->dev, mcode->code_size, + &mcode->phys_base, GFP_KERNEL); + if (!mcode->code) { + dev_err(dev, "Unable to allocate space for microcode"); + return -ENOMEM; + } + + 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++) + ((u64 *)mcode->code)[j] = cpu_to_be64(((u64 *)mcode->code)[j]); + /* MC needs 16-bit swap */ + for (j = 0; j < (mcode->code_size / 2); j++) + ((u16 *)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) { + dev_err(dev, "do_cpt_init failed with ret: %d\n", ret); + return ret; + } + + dev_info(dev, "Microcode Loaded %s\n", mcode->version); + mcode->is_mc_valid = 1; + cpt->next_mc_idx++; + 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 int cpt_enable_msix(struct cpt_device *cpt) +{ + int i, ret; + + cpt->num_vec = CPT_PF_MSIX_VECTORS; + + for (i = 0; i < cpt->num_vec; i++) + cpt->msix_entries[i].entry = i; + + ret = pci_enable_msix(cpt->pdev, cpt->msix_entries, cpt->num_vec); + if (ret) { + dev_err(&cpt->pdev->dev, "Request for #%d msix vectors failed\n", + cpt->num_vec); + return ret; + } + + cpt->msix_enabled = 1; + return 0; +} + +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_disable_msix(struct cpt_device *cpt) +{ + if (cpt->msix_enabled) { + pci_disable_msix(cpt->pdev); + cpt->msix_enabled = 0; + cpt->num_vec = 0; + } +} + +static void cpt_free_all_interrupts(struct cpt_device *cpt) +{ + int irq; + + for (irq = 0; irq < cpt->num_vec; irq++) { + if (cpt->irq_allocated[irq]) + free_irq(cpt->msix_entries[irq].vector, cpt); + cpt->irq_allocated[irq] = false; + } +} + +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 = 0xFFFFFFFF; + 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; + } + /* Disable the cores */ + cpt_write_csr64(cpt->reg_base, CPTX_PF_EXE_CTL(0), 0); +} + +/** + * Ensure all cores are disenganed 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; + //mcode->base = 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); + mdelay((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 = cpt_enable_msix(cpt); + if (ret) + return ret; + + /* Register mailbox interrupt handlers */ + ret = request_irq(cpt->msix_entries[CPT_PF_INT_VEC_E_MBOXX(0)].vector, + cpt_mbx0_intr_handler, 0, "CPT Mbox0", cpt); + if (ret) + goto fail; + + cpt->irq_allocated[CPT_PF_INT_VEC_E_MBOXX(0)] = true; + + /* Enable mailbox interrupt */ + cpt_enable_mbox_interrupts(cpt); + return 0; + +fail: + dev_err(dev, "Request irq failed\n"); + cpt_free_all_interrupts(cpt); + return ret; +} + +static void cpt_unregister_interrupts(struct cpt_device *cpt) +{ + cpt_free_all_interrupts(cpt); + cpt_disable_msix(cpt); +} + +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) { + pr_warn("Invalid vf count %d, Resetting it to 4(default)\n", + num_vfs); + num_vfs = 4; + } + + cpt = devm_kzalloc(dev, sizeof(struct cpt_device), 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 = pci_set_dma_mask(pdev, DMA_BIT_MASK(48)); + if (err) { + dev_err(dev, "Unable to get usable DMA configuration\n"); + goto cpt_err_release_regions; + } + + err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(48)); + if (err) { + dev_err(dev, "Unable to get 48-bit DMA for consistent allocations\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); + kzfree(cpt); +} + +/* 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 */ +}; + +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 "); +MODULE_DESCRIPTION("Cavium Thunder CPT Physical Function Driver"); +MODULE_LICENSE("GPL v2"); +MODULE_VERSION(DRV_VERSION); +MODULE_DEVICE_TABLE(pci, cpt_id_table); diff --git a/drivers/crypto/cavium/cpt/cptpf_mbox.c b/drivers/crypto/cavium/cpt/cptpf_mbox.c new file mode 100644 index 0000000..5818b41 --- /dev/null +++ b/drivers/crypto/cavium/cpt/cptpf_mbox.c @@ -0,0 +1,163 @@ +/* + * Copyright (C) 2016 Cavium, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License + * as published by the Free Software Foundation. + */ +#include +#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 u8 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 = {}; + u8 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); + } + } +} -- 2.1.4