From patchwork Mon May 31 07:05:36 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Nilesh Javali X-Patchwork-Id: 450662 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-18.8 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER, INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, SPF_PASS, URIBL_BLOCKED, USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 70AA7C4708F for ; Mon, 31 May 2021 07:06:41 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 4F87E61186 for ; Mon, 31 May 2021 07:06:41 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230205AbhEaHIT (ORCPT ); Mon, 31 May 2021 03:08:19 -0400 Received: from mx0b-0016f401.pphosted.com ([67.231.156.173]:13434 "EHLO mx0b-0016f401.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230201AbhEaHIP (ORCPT ); Mon, 31 May 2021 03:08:15 -0400 Received: from pps.filterd (m0045851.ppops.net [127.0.0.1]) by mx0b-0016f401.pphosted.com (8.16.0.43/8.16.0.43) with SMTP id 14V76FXh026830 for ; Mon, 31 May 2021 00:06:36 -0700 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=marvell.com; h=from : to : cc : subject : date : message-id : in-reply-to : references : mime-version : content-type; s=pfpt0220; bh=tAoJ9jXIeRxZuf2RH+g5V+Hgvmj/XeUN3ru4wzFpb7o=; b=ZXfBjtrySK+bmzHW9kpR+oD20vOG+ODG1u98C/CuGNVUOr33JVBYhQMPSoeo51wAnsyr evPm5+ONpS+npGrQajmNDWLTAzERnSkoSz1aJcupuHP1xLvOoJLvhR0DoFnIQLHznrvp +Rplcp6ncJlRH33xMD2uzBmgPoXDh0TxnfJlbDE31JMTAsyahVD9CgiYRbjvUz4id3pf wySPg7t91w60LHf2vSdyF2543ODyAmSphfuWj4meSSy6V7vubmsS3abiYtEULSG8Bk8B eQCTD/53drrzfqvYcmkC+yyw7YRj6v0zVhxkz8fUl/kq5OCFifa3aha0G5A+YG8gXbzt 1Q== Received: from dc5-exch01.marvell.com ([199.233.59.181]) by mx0b-0016f401.pphosted.com with ESMTP id 38vtnj82ej-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-SHA384 bits=256 verify=NOT) for ; Mon, 31 May 2021 00:06:36 -0700 Received: from DC5-EXCH01.marvell.com (10.69.176.38) by DC5-EXCH01.marvell.com (10.69.176.38) with Microsoft SMTP Server (TLS) id 15.0.1497.2; Mon, 31 May 2021 00:06:33 -0700 Received: from maili.marvell.com (10.69.176.80) by DC5-EXCH01.marvell.com (10.69.176.38) with Microsoft SMTP Server id 15.0.1497.2 via Frontend Transport; Mon, 31 May 2021 00:06:33 -0700 Received: from dut1171.mv.qlogic.com (unknown [10.112.88.18]) by maili.marvell.com (Postfix) with ESMTP id D0D0E3F703F; Mon, 31 May 2021 00:06:33 -0700 (PDT) Received: from dut1171.mv.qlogic.com (localhost [127.0.0.1]) by dut1171.mv.qlogic.com (8.14.7/8.14.7) with ESMTP id 14V76Xua032120; Mon, 31 May 2021 00:06:33 -0700 Received: (from root@localhost) by dut1171.mv.qlogic.com (8.14.7/8.14.7/Submit) id 14V76Xim032111; Mon, 31 May 2021 00:06:33 -0700 From: Nilesh Javali To: CC: , Subject: [PATCH v2 01/10] qla2xxx: Add start + stop bsg's Date: Mon, 31 May 2021 00:05:36 -0700 Message-ID: <20210531070545.32072-2-njavali@marvell.com> X-Mailer: git-send-email 2.12.0 In-Reply-To: <20210531070545.32072-1-njavali@marvell.com> References: <20210531070545.32072-1-njavali@marvell.com> MIME-Version: 1.0 X-Proofpoint-GUID: -XUJcFF4Ry1O-z_myacbFnTe_axPngx2 X-Proofpoint-ORIG-GUID: -XUJcFF4Ry1O-z_myacbFnTe_axPngx2 X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.391, 18.0.761 definitions=2021-05-31_04:2021-05-31,2021-05-31 signatures=0 Precedence: bulk List-ID: X-Mailing-List: linux-scsi@vger.kernel.org From: Quinn Tran Latest FC adapter from Marvell has the ability to encrypt data in flight (EDIF) feature. This feature require an application (ex: ipsec, etc) to act as an authenticator. This patch add 2 new BSG calls: QL_VND_SC_APP_START: application will announce its present to driver with this call. Driver will restart all connections to see if remote device support security or not. QL_VND_SC_APP_STOP: application announce it's in the process of exiting. Driver will restart all connections to revert back to non-secure. Provided the remote device is willing to allow a non-secure connection. Signed-off-by: Larry Wisneski Signed-off-by: Duane Grigsby Signed-off-by: Rick Hicksted Jr Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali --- drivers/scsi/qla2xxx/Makefile | 3 +- drivers/scsi/qla2xxx/qla_bsg.c | 3 + drivers/scsi/qla2xxx/qla_bsg.h | 3 + drivers/scsi/qla2xxx/qla_dbg.h | 1 + drivers/scsi/qla2xxx/qla_def.h | 70 ++++-- drivers/scsi/qla2xxx/qla_edif.c | 349 ++++++++++++++++++++++++++++ drivers/scsi/qla2xxx/qla_edif.h | 32 +++ drivers/scsi/qla2xxx/qla_edif_bsg.h | 225 ++++++++++++++++++ drivers/scsi/qla2xxx/qla_gbl.h | 4 + 9 files changed, 666 insertions(+), 24 deletions(-) create mode 100644 drivers/scsi/qla2xxx/qla_edif.c create mode 100644 drivers/scsi/qla2xxx/qla_edif.h create mode 100644 drivers/scsi/qla2xxx/qla_edif_bsg.h diff --git a/drivers/scsi/qla2xxx/Makefile b/drivers/scsi/qla2xxx/Makefile index 17d5bc1cc56b..cbc1303e761e 100644 --- a/drivers/scsi/qla2xxx/Makefile +++ b/drivers/scsi/qla2xxx/Makefile @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 qla2xxx-y := qla_os.o qla_init.o qla_mbx.o qla_iocb.o qla_isr.o qla_gs.o \ qla_dbg.o qla_sup.o qla_attr.o qla_mid.o qla_dfs.o qla_bsg.o \ - qla_nx.o qla_mr.o qla_nx2.o qla_target.o qla_tmpl.o qla_nvme.o + qla_nx.o qla_mr.o qla_nx2.o qla_target.o qla_tmpl.o qla_nvme.o \ + qla_edif.o obj-$(CONFIG_SCSI_QLA_FC) += qla2xxx.o obj-$(CONFIG_TCM_QLA2XXX) += tcm_qla2xxx.o diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c index d42b2ad84049..e6cccbcc7a1b 100644 --- a/drivers/scsi/qla2xxx/qla_bsg.c +++ b/drivers/scsi/qla2xxx/qla_bsg.c @@ -2840,6 +2840,9 @@ qla2x00_process_vendor_specific(struct bsg_job *bsg_job) case QL_VND_DPORT_DIAGNOSTICS: return qla2x00_do_dport_diagnostics(bsg_job); + case QL_VND_EDIF_MGMT: + return qla_edif_app_mgmt(bsg_job); + case QL_VND_SS_GET_FLASH_IMAGE_STATUS: return qla2x00_get_flash_image_status(bsg_job); diff --git a/drivers/scsi/qla2xxx/qla_bsg.h b/drivers/scsi/qla2xxx/qla_bsg.h index 0274e99e4a12..dd793cf8bc1e 100644 --- a/drivers/scsi/qla2xxx/qla_bsg.h +++ b/drivers/scsi/qla2xxx/qla_bsg.h @@ -31,6 +31,7 @@ #define QL_VND_DPORT_DIAGNOSTICS 0x19 #define QL_VND_GET_PRIV_STATS_EX 0x1A #define QL_VND_SS_GET_FLASH_IMAGE_STATUS 0x1E +#define QL_VND_EDIF_MGMT 0X1F #define QL_VND_MANAGE_HOST_STATS 0x23 #define QL_VND_GET_HOST_STATS 0x24 #define QL_VND_GET_TGT_STATS 0x25 @@ -294,4 +295,6 @@ struct qla_active_regions { uint8_t reserved[32]; } __packed; +#include "qla_edif_bsg.h" + #endif diff --git a/drivers/scsi/qla2xxx/qla_dbg.h b/drivers/scsi/qla2xxx/qla_dbg.h index 9eb708e5e22e..f1f6c740bdcd 100644 --- a/drivers/scsi/qla2xxx/qla_dbg.h +++ b/drivers/scsi/qla2xxx/qla_dbg.h @@ -367,6 +367,7 @@ ql_log_qp(uint32_t, struct qla_qpair *, int32_t, const char *fmt, ...); #define ql_dbg_tgt_mgt 0x00002000 /* Target mode management */ #define ql_dbg_tgt_tmr 0x00001000 /* Target mode task management */ #define ql_dbg_tgt_dif 0x00000800 /* Target mode dif */ +#define ql_dbg_edif 0x00000400 /* edif and purex debug */ extern int qla27xx_dump_mpi_ram(struct qla_hw_data *, uint32_t, uint32_t *, uint32_t, void **); diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index def4d99f80e9..ac3b9b39d741 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -49,6 +49,28 @@ typedef struct { uint8_t domain; } le_id_t; +/* + * 24 bit port ID type definition. + */ +typedef union { + uint32_t b24 : 24; + struct { +#ifdef __BIG_ENDIAN + uint8_t domain; + uint8_t area; + uint8_t al_pa; +#elif defined(__LITTLE_ENDIAN) + uint8_t al_pa; + uint8_t area; + uint8_t domain; +#else +#error "__BIG_ENDIAN or __LITTLE_ENDIAN must be defined!" +#endif + uint8_t rsvd_1; + } b; +} port_id_t; +#define INVALID_PORT_ID 0xFFFFFF + #include "qla_bsg.h" #include "qla_dsd.h" #include "qla_nx.h" @@ -345,6 +367,8 @@ struct name_list_extended { #define FW_MAX_EXCHANGES_CNT (32 * 1024) #define REDUCE_EXCHANGES_CNT (8 * 1024) +#define SET_DID_STATUS(stat_var, status) (stat_var = status << 16) + struct req_que; struct qla_tgt_sess; @@ -373,29 +397,6 @@ struct srb_cmd { /* To identify if a srb is of T10-CRC type. @sp => srb_t pointer */ #define IS_PROT_IO(sp) (sp->flags & SRB_CRC_CTX_DSD_VALID) - -/* - * 24 bit port ID type definition. - */ -typedef union { - uint32_t b24 : 24; - - struct { -#ifdef __BIG_ENDIAN - uint8_t domain; - uint8_t area; - uint8_t al_pa; -#elif defined(__LITTLE_ENDIAN) - uint8_t al_pa; - uint8_t area; - uint8_t domain; -#else -#error "__BIG_ENDIAN or __LITTLE_ENDIAN must be defined!" -#endif - uint8_t rsvd_1; - } b; -} port_id_t; -#define INVALID_PORT_ID 0xFFFFFF #define ISP_REG16_DISCONNECT 0xFFFF static inline le_id_t be_id_to_le(be_id_t id) @@ -2424,6 +2425,7 @@ enum discovery_state { DSC_LOGIN_COMPLETE, DSC_ADISC, DSC_DELETE_PEND, + DSC_LOGIN_AUTH_PEND, }; enum login_state { /* FW control Target side */ @@ -2563,6 +2565,22 @@ typedef struct fc_port { u64 tgt_short_link_down_cnt; u64 tgt_link_down_time; u64 dev_loss_tmo; + /* + * EDIF parameters for encryption. + */ + struct { + uint16_t enable:1; // device is edif enabled/req'd + uint16_t app_stop:2; + uint16_t app_started:1; + uint16_t secured_login:1; + uint16_t app_sess_online:1; + uint32_t tx_rekey_cnt; + uint32_t rx_rekey_cnt; + // delayed rx delete data structure list + uint64_t tx_bytes; + uint64_t rx_bytes; + uint8_t non_secured_login; + } edif; } fc_port_t; enum { @@ -2616,6 +2634,7 @@ static const char * const port_dstate_str[] = { #define FCF_ASYNC_SENT BIT_3 #define FCF_CONF_COMP_SUPPORTED BIT_4 #define FCF_ASYNC_ACTIVE BIT_5 +#define FCF_FCSP_DEVICE BIT_6 /* No loop ID flag. */ #define FC_NO_LOOP_ID 0x1000 @@ -3933,6 +3952,7 @@ struct qla_hw_data { uint32_t scm_supported_f:1; /* Enabled in Driver */ uint32_t scm_enabled:1; + uint32_t edif_enabled:1; uint32_t max_req_queue_warned:1; uint32_t plogi_template_valid:1; uint32_t port_isolated:1; @@ -4656,6 +4676,8 @@ struct purex_item { } iocb; }; +#include "qla_edif.h" + #define SCM_FLAG_RDF_REJECT 0x00 #define SCM_FLAG_RDF_COMPLETED 0x01 @@ -4884,6 +4906,8 @@ typedef struct scsi_qla_host { u64 reset_cmd_err_cnt; u64 link_down_time; u64 short_link_down_cnt; + struct edif_dbell e_dbell; + struct pur_core pur_cinfo; } scsi_qla_host_t; struct qla27xx_image_status { diff --git a/drivers/scsi/qla2xxx/qla_edif.c b/drivers/scsi/qla2xxx/qla_edif.c new file mode 100644 index 000000000000..38d79ef2e700 --- /dev/null +++ b/drivers/scsi/qla2xxx/qla_edif.c @@ -0,0 +1,349 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Marvell Fibre Channel HBA Driver + * Copyright (c) 2021 Marvell + */ +#include "qla_def.h" +//#include "qla_edif.h" + +#include +#include +#include +#include + +static void +qla_edif_sa_ctl_init(scsi_qla_host_t *vha, struct fc_port *fcport) +{ + ql_dbg(ql_dbg_edif, vha, 0x2058, + "Init SA_CTL List for fcport - nn %8phN pn %8phN portid=%02x%02x%02x.\n", + fcport->node_name, fcport->port_name, + fcport->d_id.b.domain, fcport->d_id.b.area, + fcport->d_id.b.al_pa); + + fcport->edif.tx_rekey_cnt = 0; + fcport->edif.rx_rekey_cnt = 0; + + fcport->edif.tx_bytes = 0; + fcport->edif.rx_bytes = 0; +} + +static int +qla_edif_app_check(scsi_qla_host_t *vha, struct app_id appid) +{ + int rval = 0; /* assume failure */ + + /* check that the app is allow/known to the driver */ + + /* TODO: edif: implement key/cert check for permitted apps... */ + + if (appid.app_vid == 0x73730001) { + rval = 1; + ql_dbg(ql_dbg_edif + ql_dbg_verbose, vha, 0x911d, "%s app id ok\n", __func__); + } else { + ql_dbg(ql_dbg_edif, vha, 0x911d, "%s app id not ok (%x)", + __func__, appid.app_vid); + } + + return rval; +} + +/* + * reset the session to auth wait. + */ +static void qla_edif_reset_auth_wait(struct fc_port *fcport, int state, + int waitonly) +{ + int cnt, max_cnt = 200; + bool traced = false; + + fcport->keep_nport_handle = 1; + + if (!waitonly) { + qla2x00_set_fcport_disc_state(fcport, state); + qlt_schedule_sess_for_deletion(fcport); + } else { + qla2x00_set_fcport_disc_state(fcport, state); + } + + ql_dbg(ql_dbg_edif, fcport->vha, 0xf086, + "%s: waiting for session, max_cnt=%u\n", + __func__, max_cnt); + + cnt = 0; + + if (waitonly) { + /* Marker wait min 10 msecs. */ + msleep(50); + cnt += 50; + } + while (1) { + if (!traced) { + ql_dbg(ql_dbg_edif, fcport->vha, 0xf086, + "%s: session sleep.\n", + __func__); + traced = true; + } + msleep(20); + cnt++; + if (waitonly && (fcport->disc_state == state || + fcport->disc_state == DSC_LOGIN_COMPLETE)) + break; + if (fcport->disc_state == DSC_LOGIN_AUTH_PEND) + break; + if (cnt > max_cnt) + break; + } + + if (!waitonly) { + ql_dbg(ql_dbg_edif, fcport->vha, 0xf086, + "%s: waited for session - %8phC, loopid=%x portid=%06x fcport=%p state=%u, cnt=%u\n", + __func__, fcport->port_name, fcport->loop_id, + fcport->d_id.b24, fcport, fcport->disc_state, cnt); + } else { + ql_dbg(ql_dbg_edif, fcport->vha, 0xf086, + "%s: waited ONLY for session - %8phC, loopid=%x portid=%06x fcport=%p state=%u, cnt=%u\n", + __func__, fcport->port_name, fcport->loop_id, + fcport->d_id.b24, fcport, fcport->disc_state, cnt); + } +} + +/* + * event that the app has started. Clear and start doorbell + */ +static int +qla_edif_app_start(scsi_qla_host_t *vha, struct bsg_job *bsg_job) +{ + int32_t rval = 0; + struct fc_bsg_reply *bsg_reply = bsg_job->reply; + struct app_start appstart; + struct app_start_reply appreply; + struct fc_port *fcport, *tf; + + ql_dbg(ql_dbg_edif, vha, 0x911d, "%s app start\n", __func__); + + sg_copy_to_buffer(bsg_job->request_payload.sg_list, + bsg_job->request_payload.sg_cnt, &appstart, + sizeof(struct app_start)); + + ql_dbg(ql_dbg_edif, vha, 0x911d, "%s app_vid=%x app_start_flags %x\n", + __func__, appstart.app_info.app_vid, appstart.app_start_flags); + + if (vha->e_dbell.db_flags != EDB_ACTIVE) { + /* mark doorbell as active since an app is now present */ + vha->e_dbell.db_flags = EDB_ACTIVE; + } else { + ql_dbg(ql_dbg_edif, vha, 0x911e, "%s doorbell already active\n", + __func__); + } + + list_for_each_entry_safe(fcport, tf, &vha->vp_fcports, list) { + if ((fcport->flags & FCF_FCSP_DEVICE)) { + ql_dbg(ql_dbg_edif, vha, 0xf084, + "%s: sess %p %8phC lid %#04x s_id %06x logout %d\n", + __func__, fcport, fcport->port_name, + fcport->loop_id, fcport->d_id.b24, + fcport->logout_on_delete); + + if (atomic_read(&vha->loop_state) == LOOP_DOWN) + break; + + if (!fcport->edif.secured_login) + continue; + + fcport->edif.app_started = 1; + if (fcport->edif.app_stop || + (fcport->disc_state != DSC_LOGIN_COMPLETE && + fcport->disc_state != DSC_LOGIN_PEND && + fcport->disc_state != DSC_DELETED)) { + /* no activity */ + fcport->edif.app_stop = 0; + + ql_dbg(ql_dbg_edif, vha, 0x911e, + "%s wwpn %8phC calling qla_edif_reset_auth_wait\n", + __func__, fcport->port_name); + fcport->edif.app_sess_online = 1; + qla_edif_reset_auth_wait(fcport, DSC_LOGIN_PEND, 0); + } + qla_edif_sa_ctl_init(vha, fcport); + } + } + + if (vha->pur_cinfo.enode_flags != ENODE_ACTIVE) { + /* mark as active since an app is now present */ + vha->pur_cinfo.enode_flags = ENODE_ACTIVE; + } else { + ql_dbg(ql_dbg_edif, vha, 0x911f, "%s enode already active\n", + __func__); + } + + appreply.host_support_edif = vha->hw->flags.edif_enabled; + appreply.edif_enode_active = vha->pur_cinfo.enode_flags; + appreply.edif_edb_active = vha->e_dbell.db_flags; + + bsg_job->reply_len = sizeof(struct fc_bsg_reply) + + sizeof(struct app_start_reply); + + SET_DID_STATUS(bsg_reply->result, DID_OK); + + sg_copy_from_buffer(bsg_job->reply_payload.sg_list, + bsg_job->reply_payload.sg_cnt, &appreply, + sizeof(struct app_start_reply)); + + ql_dbg(ql_dbg_edif, vha, 0x911d, + "%s app start completed with 0x%x\n", + __func__, rval); + + return rval; +} + +/* + * notification from the app that the app is stopping. + * actions: stop and doorbell + * stop and clear enode + */ +static int +qla_edif_app_stop(scsi_qla_host_t *vha, struct bsg_job *bsg_job) +{ + int32_t rval = 0; + struct app_stop appstop; + struct fc_bsg_reply *bsg_reply = bsg_job->reply; + struct fc_port *fcport, *tf; + + sg_copy_to_buffer(bsg_job->request_payload.sg_list, + bsg_job->request_payload.sg_cnt, &appstop, + sizeof(struct app_stop)); + + ql_dbg(ql_dbg_edif, vha, 0x911d, "%s Stopping APP: app_vid=%x\n", + __func__, appstop.app_info.app_vid); + + /* Call db stop and enode stop functions */ + + /* if we leave this running short waits are operational < 16 secs */ + qla_enode_stop(vha); /* stop enode */ + qla_edb_stop(vha); /* stop db */ + + list_for_each_entry_safe(fcport, tf, &vha->vp_fcports, list) { + if (fcport->edif.non_secured_login) + continue; + + if (fcport->flags & FCF_FCSP_DEVICE) { + ql_dbg(ql_dbg_edif, vha, 0xf084, + "%s: sess %p from port %8phC lid %#04x s_id %06x logout %d keep %d els_logo %d\n", + __func__, fcport, + fcport->port_name, fcport->loop_id, + fcport->d_id.b24, fcport->logout_on_delete, + fcport->keep_nport_handle, fcport->send_els_logo); + + if (atomic_read(&vha->loop_state) == LOOP_DOWN) + break; + + fcport->edif.app_stop = 1; + ql_dbg(ql_dbg_edif, vha, 0x911e, + "%s wwpn %8phC calling qla_edif_reset_auth_wait\n", + __func__, fcport->port_name); + + fcport->send_els_logo = 1; + qlt_schedule_sess_for_deletion(fcport); + + /* qla_edif_flush_sa_ctl_lists(fcport); */ + fcport->edif.app_started = 0; + } + } + + bsg_job->reply_len = sizeof(struct fc_bsg_reply); + SET_DID_STATUS(bsg_reply->result, DID_OK); + + /* no return interface to app - it assumes we cleaned up ok */ + + return rval; +} + +int32_t +qla_edif_app_mgmt(struct bsg_job *bsg_job) +{ + struct fc_bsg_request *bsg_request = bsg_job->request; + struct fc_bsg_reply *bsg_reply = bsg_job->reply; + struct Scsi_Host *host = fc_bsg_to_shost(bsg_job); + scsi_qla_host_t *vha = shost_priv(host); + struct app_id appcheck; + bool done = true; + int32_t rval = 0; + uint32_t vnd_sc = bsg_request->rqst_data.h_vendor.vendor_cmd[1]; + + ql_dbg(ql_dbg_edif, vha, 0x911d, "%s vnd subcmd=%x\n", + __func__, vnd_sc); + + sg_copy_to_buffer(bsg_job->request_payload.sg_list, + bsg_job->request_payload.sg_cnt, &appcheck, + sizeof(struct app_id)); + + if (!vha->hw->flags.edif_enabled || + test_bit(VPORT_DELETE, &vha->dpc_flags)) { + ql_dbg(ql_dbg_edif, vha, 0x911d, + "%s edif not enabled or vp delete. bsg ptr done %p\n", + __func__, bsg_job); + + SET_DID_STATUS(bsg_reply->result, DID_ERROR); + goto done; + } + + if (qla_edif_app_check(vha, appcheck) == 0) { + ql_dbg(ql_dbg_edif, vha, 0x911d, + "%s app checked failed.\n", + __func__); + + bsg_job->reply_len = sizeof(struct fc_bsg_reply); + SET_DID_STATUS(bsg_reply->result, DID_ERROR); + goto done; + } + + switch (vnd_sc) { + case QL_VND_SC_APP_START: + rval = qla_edif_app_start(vha, bsg_job); + break; + case QL_VND_SC_APP_STOP: + rval = qla_edif_app_stop(vha, bsg_job); + break; + default: + ql_dbg(ql_dbg_edif, vha, 0x911d, "%s unknown cmd=%x\n", + __func__, + bsg_request->rqst_data.h_vendor.vendor_cmd[1]); + rval = EXT_STATUS_INVALID_PARAM; + bsg_job->reply_len = sizeof(struct fc_bsg_reply); + SET_DID_STATUS(bsg_reply->result, DID_ERROR); + break; + } + +done: + if (done) { + ql_dbg(ql_dbg_user, vha, 0x7009, + "%s: %d bsg ptr done %p\n", __func__, __LINE__, bsg_job); + bsg_job_done(bsg_job, bsg_reply->result, + bsg_reply->reply_payload_rcv_len); + } + + return rval; +} +void +qla_enode_stop(scsi_qla_host_t *vha) +{ + if (vha->pur_cinfo.enode_flags != ENODE_ACTIVE) { + /* doorbell list not enabled */ + ql_dbg(ql_dbg_edif, vha, 0x09102, + "%s enode not active\n", __func__); + return; + } +} + +/* function called when app is stopping */ + +void +qla_edb_stop(scsi_qla_host_t *vha) +{ + if (vha->e_dbell.db_flags != EDB_ACTIVE) { + /* doorbell list not enabled */ + ql_dbg(ql_dbg_edif, vha, 0x09102, + "%s doorbell not enabled\n", __func__); + return; + } +} diff --git a/drivers/scsi/qla2xxx/qla_edif.h b/drivers/scsi/qla2xxx/qla_edif.h new file mode 100644 index 000000000000..dc0a08570a0b --- /dev/null +++ b/drivers/scsi/qla2xxx/qla_edif.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Marvell Fibre Channel HBA Driver + * Copyright (c) 2021 Marvell + */ +#ifndef __QLA_EDIF_H +#define __QLA_EDIF_H + +struct qla_scsi_host; + +enum enode_flags_t { + ENODE_ACTIVE = 0x1, // means that app has started +}; + +struct pur_core { + enum enode_flags_t enode_flags; + spinlock_t pur_lock; /* protects list */ + struct list_head head; +}; + +enum db_flags_t { + EDB_ACTIVE = 0x1, +}; + +struct edif_dbell { + enum db_flags_t db_flags; + spinlock_t db_lock; /* protects list */ + struct list_head head; + struct completion dbell; /* doorbell ring */ +}; + +#endif /* __QLA_EDIF_H */ diff --git a/drivers/scsi/qla2xxx/qla_edif_bsg.h b/drivers/scsi/qla2xxx/qla_edif_bsg.h new file mode 100644 index 000000000000..9c05b78253e7 --- /dev/null +++ b/drivers/scsi/qla2xxx/qla_edif_bsg.h @@ -0,0 +1,225 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Marvell Fibre Channel HBA Driver + * Copyright (C) 2018- Marvell + * + */ +#ifndef __QLA_EDIF_BSG_H +#define __QLA_EDIF_BSG_H + +/* BSG Vendor specific commands */ +#define ELS_MAX_PAYLOAD 1024 +#ifndef WWN_SIZE +#define WWN_SIZE 8 /* Size of WWPN, WWN & WWNN */ +#endif +#define VND_CMD_APP_RESERVED_SIZE 32 + +enum auth_els_sub_cmd { + SEND_ELS = 0, + SEND_ELS_REPLY, + PULL_ELS, +}; + +struct extra_auth_els { + enum auth_els_sub_cmd sub_cmd; + uint32_t extra_rx_xchg_address; // FC_ELS_ACC | FC_ELS_RJT + uint8_t extra_control_flags; +#define BSG_CTL_FLAG_INIT 0 +#define BSG_CTL_FLAG_LS_ACC 1 +#define BSG_CTL_FLAG_LS_RJT 2 +#define BSG_CTL_FLAG_TRM 3 + uint8_t extra_rsvd[3]; +} __packed; + +struct qla_bsg_auth_els_request { + struct fc_bsg_request r; + struct extra_auth_els e; +}; + +struct qla_bsg_auth_els_reply { + struct fc_bsg_reply r; + uint32_t rx_xchg_address; +}; + +struct app_id { + int app_vid; + uint8_t app_key[32]; +} __packed; + +struct app_start_reply { + uint32_t host_support_edif; // 0=disable, 1=enable + uint32_t edif_enode_active; // 0=disable, 1=enable + uint32_t edif_edb_active; // 0=disable, 1=enable + uint32_t reserved[VND_CMD_APP_RESERVED_SIZE]; +} __packed; + +struct app_start { + struct app_id app_info; + uint32_t prli_to; // timer plogi/prli to complete + uint32_t key_shred; // timer before shredding old keys + uint8_t app_start_flags; + uint8_t reserved[VND_CMD_APP_RESERVED_SIZE - 1]; +} __packed; + +struct app_stop { + struct app_id app_info; + char buf[16]; +} __packed; + +struct app_plogi_reply { + uint32_t prli_status; // 0=failed, 1=succeeded + uint8_t reserved[VND_CMD_APP_RESERVED_SIZE]; +} __packed; + +#define RECFG_TIME 1 +#define RECFG_BYTES 2 + +struct app_rekey_cfg { + struct app_id app_info; + uint8_t rekey_mode; // 1=time based (in sec), 2: bytes based + port_id_t d_id; // 000 = all entries; anything else + // specifies a specific d_id + uint8_t force; // 0=no force to change config if + // existing rekey mode changed, + // 1=force to re auth and change + // existing rekey mode if different + union { + int64_t bytes; // # of bytes before rekey, 0=no limit + int64_t time; // # of seconds before rekey, 0=no time limit + } rky_units; + + uint8_t reserved[VND_CMD_APP_RESERVED_SIZE]; +} __packed; + +struct app_pinfo_req { + struct app_id app_info; + uint8_t num_ports; // space allocated for app_pinfo_reply_t.ports[] + port_id_t remote_pid; + uint8_t reserved[VND_CMD_APP_RESERVED_SIZE]; +} __packed; + +struct app_pinfo { + port_id_t remote_pid; // contains device d_id + uint8_t remote_wwpn[WWN_SIZE]; + uint8_t remote_type; // contains TGT or INIT +#define VND_CMD_RTYPE_UNKNOWN 0 +#define VND_CMD_RTYPE_TARGET 1 +#define VND_CMD_RTYPE_INITIATOR 2 + uint8_t remote_state; // 0=bad, 1=good + uint8_t auth_state; // 0=auth N/A (unsecured fcport), + // 1=auth req'd + // 2=auth done + uint8_t rekey_mode; // 1=time based, 2=bytes based + int64_t rekey_count; // # of times device rekeyed + int64_t rekey_config_value; // orig rekey value (MB or sec) + // (0 for no limit) + int64_t rekey_consumed_value; // remaining MB/time,0=no limit + + uint8_t reserved[VND_CMD_APP_RESERVED_SIZE]; +} __packed; + +/* AUTH States */ +#define VND_CMD_AUTH_STATE_UNDEF 0 +#define VND_CMD_AUTH_STATE_SESSION_SHUTDOWN 1 +#define VND_CMD_AUTH_STATE_NEEDED 2 +#define VND_CMD_AUTH_STATE_ELS_RCVD 3 +#define VND_CMD_AUTH_STATE_SAUPDATE_COMPL 4 + +struct app_pinfo_reply { + uint8_t port_count; // possible value => 0 to 255 + uint8_t reserved[VND_CMD_APP_RESERVED_SIZE]; + struct app_pinfo ports[0]; // variable - specified by app_pinfo_req num_ports +} __packed; + +struct app_sinfo_req { + struct app_id app_info; + uint8_t num_ports; // app space alloc for elem[] + uint8_t reserved[VND_CMD_APP_RESERVED_SIZE]; +} __packed; + +// temp data - actual data TBD +struct app_sinfo { + uint8_t remote_wwpn[WWN_SIZE]; + int64_t rekey_count; // # of times device rekeyed + uint8_t rekey_mode; // 1=time based (in sec), 2: bytes based + int64_t tx_bytes; // orig rekey value + int64_t rx_bytes; // amount left +} __packed; + +struct app_stats_reply { + uint8_t elem_count; // possible value => 0 to 255 + struct app_sinfo elem[0]; // specified by app_sinfo_t elem_count +} __packed; + +struct qla_sa_update_frame { + struct app_id app_info; + uint16_t flags; +#define SAU_FLG_INV 0x01 // delete key +#define SAU_FLG_TX 0x02 // 1=tx, 0 = rx +#define SAU_FLG_FORCE_DELETE 0x08 // force RX sa_index delete +#define SAU_FLG_GMAC_MODE 0x20 // GMAC mode is cleartext for the IO (i.e. NULL encryption) +#define SAU_FLG_KEY128 0x40 +#define SAU_FLG_KEY256 0x80 + uint16_t fast_sa_index:10, + reserved:6; + uint32_t salt; + uint32_t spi; + uint8_t sa_key[32]; + uint8_t node_name[WWN_SIZE]; + uint8_t port_name[WWN_SIZE]; + port_id_t port_id; +} __packed; + +// used for edif mgmt bsg interface +#define QL_VND_SC_UNDEF 0 +#define QL_VND_SC_SA_UPDATE 1 // sa key info +#define QL_VND_SC_APP_START 2 // app started event +#define QL_VND_SC_APP_STOP 3 // app stopped event +#define QL_VND_SC_AUTH_OK 4 // plogi auth'd ok +#define QL_VND_SC_AUTH_FAIL 5 // plogi auth bad +#define QL_VND_SC_REKEY_CONFIG 6 // auth rekey set parms (time/data) +#define QL_VND_SC_GET_FCINFO 7 // get port info +#define QL_VND_SC_GET_STATS 8 // get edif stats + +/* Application interface data structure for rtn data */ +#define EXT_DEF_EVENT_DATA_SIZE 64 +struct edif_app_dbell { + uint32_t event_code; + uint32_t event_data_size; + union { + port_id_t port_id; + uint8_t event_data[EXT_DEF_EVENT_DATA_SIZE]; + }; +} __packed; + +struct edif_sa_update_aen { + port_id_t port_id; + uint32_t key_type; /* Tx (1) or RX (2) */ + uint32_t status; /* 0 succes, 1 failed, 2 timeout , 3 error */ + uint8_t reserved[16]; +} __packed; + +#define QL_VND_SA_STAT_SUCCESS 0 +#define QL_VND_SA_STAT_FAILED 1 +#define QL_VND_SA_STAT_TIMEOUT 2 +#define QL_VND_SA_STAT_ERROR 3 + +#define QL_VND_RX_SA_KEY 1 +#define QL_VND_TX_SA_KEY 2 + +/* App defines for plogi auth'd ok and plogi auth bad requests */ +struct auth_complete_cmd { + struct app_id app_info; +#define PL_TYPE_WWPN 1 +#define PL_TYPE_DID 2 + uint32_t type; + union { + uint8_t wwpn[WWN_SIZE]; + port_id_t d_id; + } u; + uint32_t reserved[VND_CMD_APP_RESERVED_SIZE]; +} __packed; + +#define RX_DELAY_DELETE_TIMEOUT 20 // 30 second timeout + +#endif /* QLA_EDIF_BSG_H */ diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index fae5cae6f0a8..02c10caed18b 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -953,6 +953,10 @@ extern void qla_nvme_abort_process_comp_status /* nvme.c */ void qla_nvme_unregister_remote_port(struct fc_port *fcport); +void qla_edb_stop(scsi_qla_host_t *vha); +int32_t qla_edif_app_mgmt(struct bsg_job *bsg_job); +void qla_enode_init(scsi_qla_host_t *vha); +void qla_enode_stop(scsi_qla_host_t *vha); void qla_handle_els_plogi_done(scsi_qla_host_t *vha, struct event_arg *ea); #define QLA2XX_HW_ERROR BIT_0 From patchwork Mon May 31 07:05:38 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Nilesh Javali X-Patchwork-Id: 450661 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-18.8 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER, INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, SPF_PASS, URIBL_BLOCKED, USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 17DC4C4708F for ; Mon, 31 May 2021 07:07:29 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id D4C76611CA for ; Mon, 31 May 2021 07:07:28 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230205AbhEaHJG (ORCPT ); Mon, 31 May 2021 03:09:06 -0400 Received: from mx0b-0016f401.pphosted.com ([67.231.156.173]:24258 "EHLO mx0b-0016f401.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230091AbhEaHJF (ORCPT ); Mon, 31 May 2021 03:09:05 -0400 Received: from pps.filterd (m0045851.ppops.net [127.0.0.1]) by mx0b-0016f401.pphosted.com (8.16.0.43/8.16.0.43) with SMTP id 14V7673n026046 for ; Mon, 31 May 2021 00:07:25 -0700 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=marvell.com; h=from : to : cc : subject : date : message-id : in-reply-to : references : mime-version : content-type; s=pfpt0220; bh=q9NWCx0/ndcK+9Uw/iMZ93l4OPEbIbCMFlsGdbX1d5I=; b=QRQcxkDS+6JQIgajd0ceXqC/F0ZBOds4Urzlq79SAjKDTAzrSl/lm9o9gajnj6nY2Bbw lxreNqYlYhI0Vjvi5dLnEwSiE5vCaM1VO38qmgwYjNqe3LISyLEqDWck+Ca/eW598FM6 EOorlbOKRiuFGLpYmNEdUF5kXRSHBZ4bJ0vnTRbMfAtuoDIN+5UHhMiOMuMl/Q/Dw2Es 9WwSwnQTpGGTQxmvAlQc64NopgibUSspFlbT7jv6IIUhEQdiDyDgxsh+2n5RZ3/fMjmU +nkCWgMNPLSk5L5YvwmSg/GmuKOfhryaBvJABX82K+cRYJN0xrIjCD8vfVmJA1qG82p/ OA== Received: from dc5-exch01.marvell.com ([199.233.59.181]) by mx0b-0016f401.pphosted.com with ESMTP id 38vtnj82gk-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-SHA384 bits=256 verify=NOT) for ; Mon, 31 May 2021 00:07:24 -0700 Received: from DC5-EXCH01.marvell.com (10.69.176.38) by DC5-EXCH01.marvell.com (10.69.176.38) with Microsoft SMTP Server (TLS) id 15.0.1497.2; Mon, 31 May 2021 00:07:22 -0700 Received: from maili.marvell.com (10.69.176.80) by DC5-EXCH01.marvell.com (10.69.176.38) with Microsoft SMTP Server id 15.0.1497.2 via Frontend Transport; Mon, 31 May 2021 00:07:22 -0700 Received: from dut1171.mv.qlogic.com (unknown [10.112.88.18]) by maili.marvell.com (Postfix) with ESMTP id 3B2703F703F; Mon, 31 May 2021 00:07:22 -0700 (PDT) Received: from dut1171.mv.qlogic.com (localhost [127.0.0.1]) by dut1171.mv.qlogic.com (8.14.7/8.14.7) with ESMTP id 14V77Mwx032128; Mon, 31 May 2021 00:07:22 -0700 Received: (from root@localhost) by dut1171.mv.qlogic.com (8.14.7/8.14.7/Submit) id 14V77MWt032127; Mon, 31 May 2021 00:07:22 -0700 From: Nilesh Javali To: CC: , Subject: [PATCH v2 03/10] qla2xxx: Add send, receive and accept for auth_els Date: Mon, 31 May 2021 00:05:38 -0700 Message-ID: <20210531070545.32072-4-njavali@marvell.com> X-Mailer: git-send-email 2.12.0 In-Reply-To: <20210531070545.32072-1-njavali@marvell.com> References: <20210531070545.32072-1-njavali@marvell.com> MIME-Version: 1.0 X-Proofpoint-GUID: pUBanBDn2_NsaXenrETkjKa3upGdSTty X-Proofpoint-ORIG-GUID: pUBanBDn2_NsaXenrETkjKa3upGdSTty X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.391, 18.0.761 definitions=2021-05-31_04:2021-05-31,2021-05-31 signatures=0 Precedence: bulk List-ID: X-Mailing-List: linux-scsi@vger.kernel.org From: Quinn Tran Latest FC adapter from Marvell has the ability to encrypt data in flight (EDIF) feature. This feature require an application (ex: ipsec, etc) to act as an authenticator. This patch add ability for authentication application to send and retrieve message(s) as part of the authentication process via existing FC_BSG_HST_ELS_NOLOGIN BSG interface To send a message, application is expected to format the data in the AUTH ELS format. Refer to FC-SP2 for details. If a message was received, application is required to reply with either a LS_ACC or LS_RJT complete the exchange using the same interface. Otherwise, remote device will treat it as a timeout. Signed-off-by: Larry Wisneski Signed-off-by: Duane Grigsby Signed-off-by: Rick Hicksted Jr Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali --- drivers/scsi/qla2xxx/qla_attr.c | 1 + drivers/scsi/qla2xxx/qla_bsg.c | 63 +++-- drivers/scsi/qla2xxx/qla_def.h | 48 ++++ drivers/scsi/qla2xxx/qla_edif.c | 430 ++++++++++++++++++++++++++++++ drivers/scsi/qla2xxx/qla_edif.h | 38 +++ drivers/scsi/qla2xxx/qla_gbl.h | 6 +- drivers/scsi/qla2xxx/qla_iocb.c | 42 +++ drivers/scsi/qla2xxx/qla_isr.c | 95 ++++++- drivers/scsi/qla2xxx/qla_os.c | 41 +++ drivers/scsi/qla2xxx/qla_target.c | 7 +- 10 files changed, 731 insertions(+), 40 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 3aa9869f6fae..d78db2949ef6 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -3107,6 +3107,7 @@ qla24xx_vport_delete(struct fc_vport *fc_vport) qla2x00_wait_for_sess_deletion(vha); qla_nvme_delete(vha); + qla_enode_stop(vha); vha->flags.delete_progress = 1; qlt_remove_target(ha, vha); diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c index e6cccbcc7a1b..2d43603e31ec 100644 --- a/drivers/scsi/qla2xxx/qla_bsg.c +++ b/drivers/scsi/qla2xxx/qla_bsg.c @@ -27,6 +27,10 @@ void qla2x00_bsg_job_done(srb_t *sp, int res) sp->free(sp); + ql_dbg(ql_dbg_user, sp->vha, 0x7009, + "%s: sp hdl %x, result=%x bsg ptr %p\n", + __func__, sp->handle, res, bsg_job); + bsg_reply->result = res; bsg_job_done(bsg_job, bsg_reply->result, bsg_reply->reply_payload_rcv_len); @@ -53,11 +57,19 @@ void qla2x00_bsg_sp_free(srb_t *sp) bsg_job->reply_payload.sg_list, bsg_job->reply_payload.sg_cnt, DMA_FROM_DEVICE); } else { - dma_unmap_sg(&ha->pdev->dev, bsg_job->request_payload.sg_list, - bsg_job->request_payload.sg_cnt, DMA_TO_DEVICE); - dma_unmap_sg(&ha->pdev->dev, bsg_job->reply_payload.sg_list, - bsg_job->reply_payload.sg_cnt, DMA_FROM_DEVICE); + if (sp->remap.remapped) { + dma_pool_free(ha->purex_dma_pool, sp->remap.rsp.buf, + sp->remap.rsp.dma); + dma_pool_free(ha->purex_dma_pool, sp->remap.req.buf, + sp->remap.req.dma); + } else { + dma_unmap_sg(&ha->pdev->dev, bsg_job->request_payload.sg_list, + bsg_job->request_payload.sg_cnt, DMA_TO_DEVICE); + + dma_unmap_sg(&ha->pdev->dev, bsg_job->reply_payload.sg_list, + bsg_job->reply_payload.sg_cnt, DMA_FROM_DEVICE); + } } if (sp->type == SRB_CT_CMD || @@ -266,6 +278,7 @@ qla2x00_process_els(struct bsg_job *bsg_job) int req_sg_cnt, rsp_sg_cnt; int rval = (DID_ERROR << 16); uint16_t nextlid = 0; + uint32_t els_cmd = 0; if (bsg_request->msgcode == FC_BSG_RPT_ELS) { rport = fc_bsg_to_rport(bsg_job); @@ -279,6 +292,9 @@ qla2x00_process_els(struct bsg_job *bsg_job) vha = shost_priv(host); ha = vha->hw; type = "FC_BSG_HST_ELS_NOLOGIN"; + els_cmd = bsg_request->rqst_data.h_els.command_code; + if (els_cmd == ELS_AUTH_ELS) + return qla_edif_process_els(vha, bsg_job); } if (!vha->flags.online) { @@ -2948,27 +2964,26 @@ qla24xx_bsg_timeout(struct bsg_job *bsg_job) for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++) { sp = req->outstanding_cmds[cnt]; - if (sp) { - if (((sp->type == SRB_CT_CMD) || - (sp->type == SRB_ELS_CMD_HST) || - (sp->type == SRB_FXIOCB_BCMD)) - && (sp->u.bsg_job == bsg_job)) { - req->outstanding_cmds[cnt] = NULL; - spin_unlock_irqrestore(&ha->hardware_lock, flags); - if (ha->isp_ops->abort_command(sp)) { - ql_log(ql_log_warn, vha, 0x7089, - "mbx abort_command " - "failed.\n"); - bsg_reply->result = -EIO; - } else { - ql_dbg(ql_dbg_user, vha, 0x708a, - "mbx abort_command " - "success.\n"); - bsg_reply->result = 0; - } - spin_lock_irqsave(&ha->hardware_lock, flags); - goto done; + if (sp && + (sp->type == SRB_CT_CMD || + sp->type == SRB_ELS_CMD_HST || + sp->type == SRB_ELS_CMD_HST_NOLOGIN || + sp->type == SRB_FXIOCB_BCMD) && + sp->u.bsg_job == bsg_job) { + req->outstanding_cmds[cnt] = NULL; + spin_unlock_irqrestore(&ha->hardware_lock, flags); + if (ha->isp_ops->abort_command(sp)) { + ql_log(ql_log_warn, vha, 0x7089, + "mbx abort_command failed.\n"); + bsg_reply->result = -EIO; + } else { + ql_dbg(ql_dbg_user, vha, 0x708a, + "mbx abort_command success.\n"); + bsg_reply->result = 0; } + spin_lock_irqsave(&ha->hardware_lock, flags); + goto done; + } } } diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 9c921381d020..517a4a4c178e 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -341,6 +341,13 @@ struct name_list_extended { u32 size; u8 sent; }; + +struct els_reject { + struct fc_els_ls_rjt *c; + dma_addr_t cdma; + u16 size; +}; + /* * Timeout timer counts in seconds */ @@ -618,6 +625,21 @@ struct srb_iocb { #define SRB_PRLI_CMD 21 #define SRB_CTRL_VP 22 #define SRB_PRLO_CMD 23 +#define SRB_SA_UPDATE 25 +#define SRB_ELS_CMD_HST_NOLOGIN 26 +#define SRB_SA_REPLACE 27 + +struct qla_els_pt_arg { + u8 els_opcode; + u8 vp_idx; + __le16 nport_handle; + u16 control_flags; + __le32 rx_xchg_address; + port_id_t did; + u32 tx_len, tx_byte_count, rx_len, rx_byte_count; + dma_addr_t tx_addr, rx_addr; + +}; enum { TYPE_SRB, @@ -631,6 +653,13 @@ struct iocb_resource { u16 iocb_cnt; }; +struct bsg_cmd { + struct bsg_job *bsg_job; + union { + struct qla_els_pt_arg els_arg; + } u; +}; + typedef struct srb { /* * Do not move cmd_type field, it needs to @@ -663,7 +692,21 @@ typedef struct srb { struct srb_iocb iocb_cmd; struct bsg_job *bsg_job; struct srb_cmd scmd; + struct bsg_cmd bsg_cmd; } u; + struct { + bool remapped; + struct { + dma_addr_t dma; + void *buf; + uint len; + } req; + struct { + dma_addr_t dma; + void *buf; + uint len; + } rsp; + } remap; /* * Report completion status @res and call sp_put(@sp). @res is * an NVMe status code, a SCSI result (e.g. DID_OK << 16) or a @@ -4638,8 +4681,12 @@ struct qla_hw_data { struct qla_hw_data_stat stat; pci_error_state_t pci_error_state; + struct dma_pool *purex_dma_pool; + struct els_reject elsrej; }; +#define RX_ELS_SIZE (roundup(sizeof(struct enode) + ELS_MAX_PAYLOAD, SMP_CACHE_BYTES)) + struct active_regions { uint8_t global; struct { @@ -5110,6 +5157,7 @@ enum nexus_wait_type { WAIT_LUN, }; +#define QLA_SKIP_HANDLE QLA_TGT_SKIP_HANDLE /* Refer to SNIA SFF 8247 */ struct sff_8247_a0 { u8 txid; /* transceiver id */ diff --git a/drivers/scsi/qla2xxx/qla_edif.c b/drivers/scsi/qla2xxx/qla_edif.c index fd39232fa68d..4c788f4588ca 100644 --- a/drivers/scsi/qla2xxx/qla_edif.c +++ b/drivers/scsi/qla2xxx/qla_edif.c @@ -11,6 +11,30 @@ #include #include +static int qla_pur_get_pending(scsi_qla_host_t *, fc_port_t *, struct bsg_job *); + +static struct els_sub_cmd { + uint16_t cmd; + const char *str; +} sc_str[] = { + {SEND_ELS, "send ELS"}, + {SEND_ELS_REPLY, "send ELS Reply"}, + {PULL_ELS, "retrieve ELS"}, +}; + +const char *sc_to_str(uint16_t cmd) +{ + int i; + struct els_sub_cmd *e; + + for (i = 0; i < ARRAY_SIZE(sc_str); i++) { + e = sc_str + i; + if (cmd == e->cmd) + return e->str; + } + return "unknown"; +} + static void qla_edif_sa_ctl_init(scsi_qla_host_t *vha, struct fc_port *fcport) { @@ -27,6 +51,73 @@ qla_edif_sa_ctl_init(scsi_qla_host_t *vha, struct fc_port *fcport) fcport->edif.rx_bytes = 0; } +static int qla_bsg_check(scsi_qla_host_t *vha, struct bsg_job *bsg_job, +fc_port_t *fcport) +{ + struct extra_auth_els *p; + struct fc_bsg_reply *bsg_reply = bsg_job->reply; + struct qla_bsg_auth_els_request *req = + (struct qla_bsg_auth_els_request *)bsg_job->request; + + if (!vha->hw->flags.edif_enabled) { + /* edif support not enabled */ + ql_dbg(ql_dbg_edif, vha, 0x9105, + "%s edif not enabled\n", __func__); + goto done; + } + if (vha->e_dbell.db_flags != EDB_ACTIVE) { + /* doorbell list not enabled */ + ql_dbg(ql_dbg_edif, vha, 0x09102, + "%s doorbell not enabled\n", __func__); + goto done; + } + + p = &req->e; + + /* Get response */ + if (p->sub_cmd == PULL_ELS) { + struct qla_bsg_auth_els_reply *rpl = + (struct qla_bsg_auth_els_reply *)bsg_job->reply; + + qla_pur_get_pending(vha, fcport, bsg_job); + + ql_dbg(ql_dbg_edif, vha, 0x911d, + "%s %s %8phN sid=%x. xchg %x, nb=%xh bsg ptr %p\n", + __func__, sc_to_str(p->sub_cmd), fcport->port_name, + fcport->d_id.b24, rpl->rx_xchg_address, + rpl->r.reply_payload_rcv_len, bsg_job); + + goto done; + } + return 0; + +done: + + bsg_job_done(bsg_job, bsg_reply->result, + bsg_reply->reply_payload_rcv_len); + return -EIO; +} + +fc_port_t * +qla2x00_find_fcport_by_pid(scsi_qla_host_t *vha, port_id_t *id) +{ + fc_port_t *f, *tf; + + f = NULL; + list_for_each_entry_safe(f, tf, &vha->vp_fcports, list) { + if ((f->flags & FCF_FCSP_DEVICE)) { + ql_dbg(ql_dbg_edif + ql_dbg_verbose, vha, 0x2058, + "Found secure fcport - nn %8phN pn %8phN portid=%02x%02x%02x, 0x%x, 0x%x.\n", + f->node_name, f->port_name, + f->d_id.b.domain, f->d_id.b.area, + f->d_id.b.al_pa, f->d_id.b24, id->b24); + if (f->d_id.b24 == id->b24) + return f; + } + } + return NULL; +} + static int qla_edif_app_check(scsi_qla_host_t *vha, struct app_id appid) { @@ -506,17 +597,192 @@ qla_edif_app_mgmt(struct bsg_job *bsg_job) return rval; } + +static void +qla_enode_free(scsi_qla_host_t *vha, struct enode *node) +{ + /* + * releases the space held by this enode entry + * this function does _not_ free the enode itself + * NB: the pur node entry passed should not be on any list + */ + + if (!node) { + ql_dbg(ql_dbg_edif, vha, 0x09122, + "%s error - no valid node passed\n", __func__); + return; + } + + node->dinfo.lstate = LSTATE_DEST; + node->ntype = N_UNDEF; + kfree(node); +} + +/* + * function to initialize enode structs & lock + * NB: should only be called when driver attaching + */ +void +qla_enode_init(scsi_qla_host_t *vha) +{ + struct qla_hw_data *ha = vha->hw; + char name[32]; + + if (vha->pur_cinfo.enode_flags == ENODE_ACTIVE) { + /* list still active - error */ + ql_dbg(ql_dbg_edif, vha, 0x09102, "%s enode still active\n", + __func__); + return; + } + + /* initialize lock which protects pur_core & init list */ + spin_lock_init(&vha->pur_cinfo.pur_lock); + INIT_LIST_HEAD(&vha->pur_cinfo.head); + + snprintf(name, sizeof(name), "%s_%d_purex", QLA2XXX_DRIVER_NAME, + ha->pdev->device); +} + +/* + * function to stop and clear and enode data + * called when app notified it is stopping + */ + void qla_enode_stop(scsi_qla_host_t *vha) { + unsigned long flags; + struct enode *node, *q; + if (vha->pur_cinfo.enode_flags != ENODE_ACTIVE) { /* doorbell list not enabled */ ql_dbg(ql_dbg_edif, vha, 0x09102, "%s enode not active\n", __func__); return; } + + /* grab lock so list doesn't move */ + spin_lock_irqsave(&vha->pur_cinfo.pur_lock, flags); + + vha->pur_cinfo.enode_flags &= ~ENODE_ACTIVE; /* mark it not active */ + + /* hopefully this is a null list at this point */ + list_for_each_entry_safe(node, q, &vha->pur_cinfo.head, list) { + ql_dbg(ql_dbg_edif, vha, 0x910f, + "%s freeing enode type=%x, cnt=%x\n", __func__, node->ntype, + node->dinfo.nodecnt); + list_del_init(&node->list); + spin_unlock_irqrestore(&vha->pur_cinfo.pur_lock, flags); + qla_enode_free(vha, node); + spin_lock_irqsave(&vha->pur_cinfo.pur_lock, flags); + } + spin_unlock_irqrestore(&vha->pur_cinfo.pur_lock, flags); +} + +/* + * allocate enode struct and populate buffer + * returns: enode pointer with buffers + * NULL on error + */ + +static struct enode * +qla_enode_find(scsi_qla_host_t *vha, uint32_t ntype, uint32_t p1, uint32_t p2) +{ + struct enode *node_rtn = NULL; + struct enode *list_node = NULL; + unsigned long flags; + struct list_head *pos, *q; + + uint32_t sid; + uint32_t rw_flag; + + struct purexevent *purex; + + /* secure the list from moving under us */ + spin_lock_irqsave(&vha->pur_cinfo.pur_lock, flags); + + list_for_each_safe(pos, q, &vha->pur_cinfo.head) { + list_node = list_entry(pos, struct enode, list); + + /* node type determines what p1 and p2 are */ + purex = &list_node->u.purexinfo; + sid = p1; + rw_flag = p2; + + if (purex->pur_info.pur_sid.b24 == sid) { + if (purex->pur_info.pur_pend == 1 && + rw_flag == PUR_GET) { + /* + * if the receive is in progress + * and its a read/get then can't + * transfer yet + */ + ql_dbg(ql_dbg_edif, vha, 0x9106, + "%s purex xfer in progress for sid=%x\n", + __func__, sid); + } else { + /* found it and its complete */ + node_rtn = list_node; + } + } + + if (node_rtn) { + /* + * found node that we're looking for so take it + * off the list and return it to the caller + */ + list_del(pos); + list_node->dinfo.lstate = LSTATE_OFF; + break; + } + } + + spin_unlock_irqrestore(&vha->pur_cinfo.pur_lock, flags); + + return node_rtn; } +/* + * Return number of bytes of purex payload pending for consumption + */ +static int +qla_pur_get_pending(scsi_qla_host_t *vha, fc_port_t *fcport, struct bsg_job *bsg_job) +{ + struct enode *ptr; + struct purexevent *purex; + struct qla_bsg_auth_els_reply *rpl = + (struct qla_bsg_auth_els_reply *)bsg_job->reply; + + bsg_job->reply_len = sizeof(*rpl); + + ptr = qla_enode_find(vha, N_PUREX, fcport->d_id.b24, PUR_GET); + if (!ptr) { + ql_dbg(ql_dbg_edif, vha, 0x9111, + "%s no enode data found for %8phN sid=%06x\n", + __func__, fcport->port_name, fcport->d_id.b24); + SET_DID_STATUS(rpl->r.result, DID_IMM_RETRY); + return -EIO; + } + + /* + * enode is now off the linked list and is ours to deal with + */ + purex = &ptr->u.purexinfo; + + /* Copy info back to caller */ + rpl->rx_xchg_address = purex->pur_info.pur_rx_xchg_address; + + SET_DID_STATUS(rpl->r.result, DID_OK); + rpl->r.reply_payload_rcv_len = + sg_pcopy_from_buffer(bsg_job->reply_payload.sg_list, + bsg_job->reply_payload.sg_cnt, purex->msgp, + purex->pur_info.pur_bytes_rcvd, 0); + + /* data copy / passback completed - destroy enode */ + qla_enode_free(vha, ptr); + + return 0; +} /* function called when app is stopping */ void @@ -529,3 +795,167 @@ qla_edb_stop(scsi_qla_host_t *vha) return; } } + +static void qla_parse_auth_els_ctl(struct srb *sp) +{ + struct qla_els_pt_arg *a = &sp->u.bsg_cmd.u.els_arg; + struct bsg_job *bsg_job = sp->u.bsg_cmd.bsg_job; + struct fc_bsg_request *request = bsg_job->request; + struct qla_bsg_auth_els_request *p = + (struct qla_bsg_auth_els_request *)bsg_job->request; + + a->tx_len = a->tx_byte_count = sp->remap.req.len; + a->tx_addr = sp->remap.req.dma; + a->rx_len = a->rx_byte_count = sp->remap.rsp.len; + a->rx_addr = sp->remap.rsp.dma; + + if (p->e.sub_cmd == SEND_ELS_REPLY) { + a->control_flags = p->e.extra_control_flags << 13; + a->rx_xchg_address = cpu_to_le32(p->e.extra_rx_xchg_address); + if (p->e.extra_control_flags == BSG_CTL_FLAG_LS_ACC) + a->els_opcode = ELS_LS_ACC; + else if (p->e.extra_control_flags == BSG_CTL_FLAG_LS_RJT) + a->els_opcode = ELS_LS_RJT; + } + a->did = sp->fcport->d_id; + a->els_opcode = request->rqst_data.h_els.command_code; + a->nport_handle = cpu_to_le16(sp->fcport->loop_id); + a->vp_idx = sp->vha->vp_idx; +} + +int qla_edif_process_els(scsi_qla_host_t *vha, struct bsg_job *bsg_job) +{ + struct fc_bsg_request *bsg_request = bsg_job->request; + struct fc_bsg_reply *bsg_reply = bsg_job->reply; + fc_port_t *fcport = NULL; + struct qla_hw_data *ha = vha->hw; + srb_t *sp; + int rval = (DID_ERROR << 16); + port_id_t d_id; + struct qla_bsg_auth_els_request *p = + (struct qla_bsg_auth_els_request *)bsg_job->request; + + d_id.b.al_pa = bsg_request->rqst_data.h_els.port_id[2]; + d_id.b.area = bsg_request->rqst_data.h_els.port_id[1]; + d_id.b.domain = bsg_request->rqst_data.h_els.port_id[0]; + + /* find matching d_id in fcport list */ + fcport = qla2x00_find_fcport_by_pid(vha, &d_id); + if (!fcport) { + ql_dbg(ql_dbg_edif, vha, 0x911a, + "%s fcport not find online portid=%06x.\n", + __func__, d_id.b24); + SET_DID_STATUS(bsg_reply->result, DID_ERROR); + return -EIO; + } + + if (qla_bsg_check(vha, bsg_job, fcport)) + return 0; + + if (fcport->loop_id == FC_NO_LOOP_ID) { + ql_dbg(ql_dbg_edif, vha, 0x910d, + "%s ELS code %x, no loop id.\n", __func__, + bsg_request->rqst_data.r_els.els_code); + SET_DID_STATUS(bsg_reply->result, DID_BAD_TARGET); + return -ENXIO; + } + + if (!vha->flags.online) { + ql_log(ql_log_warn, vha, 0x7005, "Host not online.\n"); + SET_DID_STATUS(bsg_reply->result, DID_BAD_TARGET); + rval = -EIO; + goto done; + } + + /* pass through is supported only for ISP 4Gb or higher */ + if (!IS_FWI2_CAPABLE(ha)) { + ql_dbg(ql_dbg_user, vha, 0x7001, + "ELS passthru not supported for ISP23xx based adapters.\n"); + SET_DID_STATUS(bsg_reply->result, DID_BAD_TARGET); + rval = -EPERM; + goto done; + } + + /* Alloc SRB structure */ + sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL); + if (!sp) { + ql_dbg(ql_dbg_user, vha, 0x7004, + "Failed get sp pid=%06x\n", fcport->d_id.b24); + rval = -ENOMEM; + SET_DID_STATUS(bsg_reply->result, DID_IMM_RETRY); + goto done; + } + + sp->remap.req.len = bsg_job->request_payload.payload_len; + sp->remap.req.buf = dma_pool_alloc(ha->purex_dma_pool, + GFP_KERNEL, &sp->remap.req.dma); + if (!sp->remap.req.buf) { + ql_dbg(ql_dbg_user, vha, 0x7005, + "Failed allocate request dma len=%x\n", + bsg_job->request_payload.payload_len); + rval = -ENOMEM; + SET_DID_STATUS(bsg_reply->result, DID_IMM_RETRY); + goto done_free_sp; + } + + sp->remap.rsp.len = bsg_job->reply_payload.payload_len; + sp->remap.rsp.buf = dma_pool_alloc(ha->purex_dma_pool, + GFP_KERNEL, &sp->remap.rsp.dma); + if (!sp->remap.rsp.buf) { + ql_dbg(ql_dbg_user, vha, 0x7006, + "Failed allocate response dma len=%x\n", + bsg_job->reply_payload.payload_len); + rval = -ENOMEM; + SET_DID_STATUS(bsg_reply->result, DID_IMM_RETRY); + goto done_free_remap_req; + } + /* + * ql_print_bsg_sglist(ql_dbg_user, vha, 0x7008, + * "SG bsg->request", &bsg_job->request_payload); + */ + sg_copy_to_buffer(bsg_job->request_payload.sg_list, + bsg_job->request_payload.sg_cnt, sp->remap.req.buf, + sp->remap.req.len); + sp->remap.remapped = true; + /* + * ql_dump_buffer(ql_dbg_edif, vha, 0x70e0, + * sp->remap.req.buf, bsg_job->request_payload.payload_len); + */ + + sp->type = SRB_ELS_CMD_HST_NOLOGIN; + sp->name = "SPCN_BSG_HST_NOLOGIN"; + sp->u.bsg_cmd.bsg_job = bsg_job; + qla_parse_auth_els_ctl(sp); + + sp->free = qla2x00_bsg_sp_free; + sp->done = qla2x00_bsg_job_done; + + rval = qla2x00_start_sp(sp); + + ql_dbg(ql_dbg_edif, vha, 0x700a, + "%s %s %8phN xchg %x ctlflag %x hdl %x reqlen %xh bsg ptr %p\n", + __func__, sc_to_str(p->e.sub_cmd), fcport->port_name, + p->e.extra_rx_xchg_address, p->e.extra_control_flags, + sp->handle, sp->remap.req.len, bsg_job); + + if (rval != QLA_SUCCESS) { + ql_log(ql_log_warn, vha, 0x700e, + "qla2x00_start_sp failed = %d\n", rval); + SET_DID_STATUS(bsg_reply->result, DID_IMM_RETRY); + rval = -EIO; + goto done_free_remap_rsp; + } + return rval; + +done_free_remap_rsp: + dma_pool_free(ha->purex_dma_pool, sp->remap.rsp.buf, + sp->remap.rsp.dma); +done_free_remap_req: + dma_pool_free(ha->purex_dma_pool, sp->remap.req.buf, + sp->remap.req.dma); +done_free_sp: + qla2x00_rel_sp(sp); + +done: + return rval; +} diff --git a/drivers/scsi/qla2xxx/qla_edif.h b/drivers/scsi/qla2xxx/qla_edif.h index dc0a08570a0b..12607218df17 100644 --- a/drivers/scsi/qla2xxx/qla_edif.h +++ b/drivers/scsi/qla2xxx/qla_edif.h @@ -29,4 +29,42 @@ struct edif_dbell { struct completion dbell; /* doorbell ring */ }; +#define MAX_PAYLOAD 1024 +#define PUR_GET 1 + +#define LSTATE_OFF 1 // node not on list +#define LSTATE_ON 2 // node on list +#define LSTATE_DEST 3 // node destoyed + +struct dinfo { + int nodecnt; // create seq count + int lstate; // node's list state +}; + +struct pur_ninfo { + unsigned int pur_pend:1; + port_id_t pur_sid; + port_id_t pur_did; + uint8_t vp_idx; + short pur_bytes_rcvd; + unsigned short pur_nphdl; + unsigned int pur_rx_xchg_address; +}; + +struct purexevent { + struct pur_ninfo pur_info; + unsigned char *msgp; + u32 msgp_len; +}; + +#define N_UNDEF 0 // node not used/defined +#define N_PUREX 1 // purex info +struct enode { + struct list_head list; + struct dinfo dinfo; + uint32_t ntype; + union { + struct purexevent purexinfo; + } u; +}; #endif /* __QLA_EDIF_H */ diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index 02c10caed18b..7ff05aa10b2d 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -130,6 +130,8 @@ void qla24xx_free_purex_item(struct purex_item *item); extern bool qla24xx_risc_firmware_invalid(uint32_t *); void qla_init_iocb_limit(scsi_qla_host_t *); +int qla_edif_process_els(scsi_qla_host_t *vha, struct bsg_job *bsgjob); +const char *sc_to_str(uint16_t cmd); /* * Global Data in qla_os.c source file. @@ -282,7 +284,8 @@ extern int qla2x00_vp_abort_isp(scsi_qla_host_t *); /* * Global Function Prototypes in qla_iocb.c source file. */ - +void qla_els_pt_iocb(struct scsi_qla_host *vha, + struct els_entry_24xx *pkt, struct qla_els_pt_arg *a); extern uint16_t qla2x00_calc_iocbs_32(uint16_t); extern uint16_t qla2x00_calc_iocbs_64(uint16_t); extern void qla2x00_build_scsi_iocbs_32(srb_t *, cmd_entry_t *, uint16_t); @@ -953,6 +956,7 @@ extern void qla_nvme_abort_process_comp_status /* nvme.c */ void qla_nvme_unregister_remote_port(struct fc_port *fcport); +fc_port_t *qla2x00_find_fcport_by_pid(scsi_qla_host_t *vha, port_id_t *id); void qla_edb_stop(scsi_qla_host_t *vha); int32_t qla_edif_app_mgmt(struct bsg_job *bsg_job); void qla_enode_init(scsi_qla_host_t *vha); diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index 38b5bdde2405..6f996fb5e8f9 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -3102,6 +3102,44 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, return rval; } +/* it is assume qpair lock is held */ +void qla_els_pt_iocb(struct scsi_qla_host *vha, + struct els_entry_24xx *els_iocb, + struct qla_els_pt_arg *a) +{ + els_iocb->entry_type = ELS_IOCB_TYPE; + els_iocb->entry_count = 1; + els_iocb->sys_define = 0; + els_iocb->entry_status = 0; + els_iocb->handle = QLA_SKIP_HANDLE; + els_iocb->nport_handle = a->nport_handle; + // no need for endiance conversion. + els_iocb->rx_xchg_address = a->rx_xchg_address; + els_iocb->tx_dsd_count = cpu_to_le16(1); + els_iocb->vp_index = a->vp_idx; + els_iocb->sof_type = EST_SOFI3; + els_iocb->rx_dsd_count = cpu_to_le16(0); + els_iocb->opcode = a->els_opcode; + + els_iocb->d_id[0] = a->did.b.al_pa; + els_iocb->d_id[1] = a->did.b.area; + els_iocb->d_id[2] = a->did.b.domain; + /* For SID the byte order is different than DID */ + els_iocb->s_id[1] = vha->d_id.b.al_pa; + els_iocb->s_id[2] = vha->d_id.b.area; + els_iocb->s_id[0] = vha->d_id.b.domain; + + els_iocb->control_flags = cpu_to_le16(a->control_flags); + + els_iocb->tx_byte_count = cpu_to_le32(a->tx_byte_count); + els_iocb->tx_len = cpu_to_le32(a->tx_len); + put_unaligned_le64(a->tx_addr, &els_iocb->tx_address); + + els_iocb->rx_byte_count = cpu_to_le32(a->rx_byte_count); + els_iocb->rx_len = cpu_to_le32(a->rx_len); + put_unaligned_le64(a->rx_addr, &els_iocb->rx_address); +} + static void qla24xx_els_iocb(srb_t *sp, struct els_entry_24xx *els_iocb) { @@ -3800,6 +3838,10 @@ qla2x00_start_sp(srb_t *sp) case SRB_ELS_CMD_HST: qla24xx_els_iocb(sp, pkt); break; + case SRB_ELS_CMD_HST_NOLOGIN: + qla_els_pt_iocb(sp->vha, pkt, &sp->u.bsg_cmd.u.els_arg); + ((struct els_entry_24xx *)pkt)->handle = sp->handle; + break; case SRB_CT_CMD: IS_FWI2_CAPABLE(ha) ? qla24xx_ct_iocb(sp, pkt) : diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 6e8f737a4af3..a130a2db2cba 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -1971,7 +1971,7 @@ qla2x00_ct_entry(scsi_qla_host_t *vha, struct req_que *req, } static void -qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req, +qla24xx_els_ct_entry(scsi_qla_host_t *v, struct req_que *req, struct sts_entry_24xx *pkt, int iocb_type) { struct els_sts_entry_24xx *ese = (struct els_sts_entry_24xx *)pkt; @@ -1982,18 +1982,58 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req, struct fc_bsg_reply *bsg_reply; uint16_t comp_status; uint32_t fw_status[3]; - int res; + int res, logit = 1; struct srb_iocb *els; + uint n; + scsi_qla_host_t *vha; + struct els_sts_entry_24xx *e = (struct els_sts_entry_24xx *)pkt; - sp = qla2x00_get_sp_from_handle(vha, func, req, pkt); + sp = qla2x00_get_sp_from_handle(v, func, req, pkt); if (!sp) return; + bsg_job = sp->u.bsg_job; + vha = sp->vha; type = NULL; + + comp_status = fw_status[0] = le16_to_cpu(pkt->comp_status); + fw_status[1] = le32_to_cpu(((struct els_sts_entry_24xx *)pkt)->error_subcode_1); + fw_status[2] = le32_to_cpu(((struct els_sts_entry_24xx *)pkt)->error_subcode_2); + switch (sp->type) { case SRB_ELS_CMD_RPT: case SRB_ELS_CMD_HST: + type = "rpt hst"; + break; + case SRB_ELS_CMD_HST_NOLOGIN: type = "els"; + { + struct els_entry_24xx *els = (void *)pkt; + struct qla_bsg_auth_els_request *p = + (struct qla_bsg_auth_els_request *)bsg_job->request; + + ql_dbg(ql_dbg_user, vha, 0x700f, + "%s %s. portid=%02x%02x%02x status %x xchg %x bsg ptr %p\n", + __func__, sc_to_str(p->e.sub_cmd), + e->d_id[2], e->d_id[1], e->d_id[0], + comp_status, p->e.extra_rx_xchg_address, bsg_job); + + if (!(le16_to_cpu(els->control_flags) & ECF_PAYLOAD_DESCR_MASK)) { + if (sp->remap.remapped) { + n = sg_copy_from_buffer(bsg_job->reply_payload.sg_list, + bsg_job->reply_payload.sg_cnt, + sp->remap.rsp.buf, + sp->remap.rsp.len); + ql_dbg(ql_dbg_user + ql_dbg_verbose, vha, 0x700e, + "%s: SG copied %x of %x\n", + __func__, n, sp->remap.rsp.len); + } else { + ql_dbg(ql_dbg_user, vha, 0x700f, + "%s: NOT REMAPPED (error)...!!!\n", + __func__); + } + } + } break; case SRB_CT_CMD: type = "ct pass-through"; @@ -2023,10 +2063,6 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req, return; } - comp_status = fw_status[0] = le16_to_cpu(pkt->comp_status); - fw_status[1] = le32_to_cpu(ese->error_subcode_1); - fw_status[2] = le32_to_cpu(ese->error_subcode_2); - if (iocb_type == ELS_IOCB_TYPE) { els = &sp->u.iocb_cmd; els->u.els_plogi.fw_status[0] = cpu_to_le32(fw_status[0]); @@ -2040,15 +2076,52 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req, res = DID_OK << 16; els->u.els_plogi.len = cpu_to_le16(le32_to_cpu( ese->total_byte_count)); + + if (sp->remap.remapped && + ((u8 *)sp->remap.rsp.buf)[0] == ELS_LS_ACC) { + ql_dbg(ql_dbg_user, vha, 0x503f, + "%s IOCB Done LS_ACC %02x%02x%02x -> %02x%02x%02x", + __func__, e->s_id[0], e->s_id[2], e->s_id[1], + e->d_id[2], e->d_id[1], e->d_id[0]); + logit = 0; + } + + } else if (comp_status == CS_PORT_LOGGED_OUT) { + els->u.els_plogi.len = 0; + res = DID_IMM_RETRY << 16; } else { els->u.els_plogi.len = 0; res = DID_ERROR << 16; } + + if (logit) { + if (sp->remap.remapped && + ((u8 *)sp->remap.rsp.buf)[0] == ELS_LS_RJT) { + ql_dbg(ql_dbg_user, vha, 0x503f, + "%s IOCB Done LS_RJT hdl=%x comp_status=0x%x\n", + type, sp->handle, comp_status); + + ql_dbg(ql_dbg_user, vha, 0x503f, + "subcode 1=0x%x subcode 2=0x%x bytes=0x%x %02x%02x%02x -> %02x%02x%02x\n", + fw_status[1], fw_status[2], + le32_to_cpu(((struct els_sts_entry_24xx *) + pkt)->total_byte_count), + e->s_id[0], e->s_id[2], e->s_id[1], + e->d_id[2], e->d_id[1], e->d_id[0]); + } else { + ql_log(ql_log_info, vha, 0x503f, + "%s IOCB Done hdl=%x comp_status=0x%x\n", + type, sp->handle, comp_status); + ql_log(ql_log_info, vha, 0x503f, + "subcode 1=0x%x subcode 2=0x%x bytes=0x%x %02x%02x%02x -> %02x%02x%02x\n", + fw_status[1], fw_status[2], + le32_to_cpu(((struct els_sts_entry_24xx *) + pkt)->total_byte_count), + e->s_id[0], e->s_id[2], e->s_id[1], + e->d_id[2], e->d_id[1], e->d_id[0]); + } + } //logit } - ql_dbg(ql_dbg_disc, vha, 0x503f, - "ELS IOCB Done -%s hdl=%x comp_status=0x%x error subcode 1=0x%x error subcode 2=0x%x total_byte=0x%x\n", - type, sp->handle, comp_status, fw_status[1], fw_status[2], - le32_to_cpu(ese->total_byte_count)); goto els_ct_done; } diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 4eab564ea6a0..5e39977af9ba 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -3460,6 +3460,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) return 0; probe_failed: + qla_enode_stop(base_vha); if (base_vha->gnl.l) { dma_free_coherent(&ha->pdev->dev, base_vha->gnl.size, base_vha->gnl.l, base_vha->gnl.ldma); @@ -3762,6 +3763,7 @@ qla2x00_remove_one(struct pci_dev *pdev) base_vha->gnl.size, base_vha->gnl.l, base_vha->gnl.ldma); base_vha->gnl.l = NULL; + qla_enode_stop(base_vha); vfree(base_vha->scan.l); @@ -4264,8 +4266,36 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len, goto fail_flt_buffer; } + /* allocate the purex dma pool */ + ha->purex_dma_pool = dma_pool_create(name, &ha->pdev->dev, + MAX_PAYLOAD, 8, 0); + + if (!ha->purex_dma_pool) { + ql_dbg_pci(ql_dbg_init, ha->pdev, 0x011b, + "Unable to allocate purex_dma_pool.\n"); + goto fail_flt; + } + + ha->elsrej.size = sizeof(struct fc_els_ls_rjt) + 16; + ha->elsrej.c = dma_alloc_coherent(&ha->pdev->dev, + ha->elsrej.size, &ha->elsrej.cdma, GFP_KERNEL); + + if (!ha->elsrej.c) { + ql_dbg_pci(ql_dbg_init, ha->pdev, 0xffff, + "Alloc failed for els reject cmd.\n"); + goto fail_elsrej; + } + ha->elsrej.c->er_cmd = ELS_LS_RJT; + ha->elsrej.c->er_reason = ELS_RJT_BUSY; + ha->elsrej.c->er_explan = ELS_EXPL_UNAB_DATA; return 0; +fail_elsrej: + dma_pool_destroy(ha->purex_dma_pool); +fail_flt: + dma_free_coherent(&ha->pdev->dev, SFP_DEV_SIZE, + ha->flt, ha->flt_dma); + fail_flt_buffer: dma_free_coherent(&ha->pdev->dev, SFP_DEV_SIZE, ha->sfp_data, ha->sfp_data_dma); @@ -4776,6 +4806,16 @@ qla2x00_mem_free(struct qla_hw_data *ha) if (ha->init_cb) dma_free_coherent(&ha->pdev->dev, ha->init_cb_size, ha->init_cb, ha->init_cb_dma); + + dma_pool_destroy(ha->purex_dma_pool); + ha->purex_dma_pool = NULL; + + if (ha->elsrej.c) { + dma_free_coherent(&ha->pdev->dev, ha->elsrej.size, + ha->elsrej.c, ha->elsrej.cdma); + ha->elsrej.c = NULL; + } + ha->init_cb = NULL; ha->init_cb_dma = 0; @@ -4837,6 +4877,7 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht, spin_lock_init(&vha->cmd_list_lock); init_waitqueue_head(&vha->fcport_waitQ); init_waitqueue_head(&vha->vref_waitq); + qla_enode_init(vha); vha->gnl.size = sizeof(struct get_name_list_extended) * (ha->max_loop_id + 1); diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index b2008fb1dd38..abf18b88579c 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -184,8 +184,7 @@ static inline int qlt_issue_marker(struct scsi_qla_host *vha, int vha_locked) return QLA_SUCCESS; } -static inline -struct scsi_qla_host *qlt_find_host_by_d_id(struct scsi_qla_host *vha, +struct scsi_qla_host *qla_find_host_by_d_id(struct scsi_qla_host *vha, be_id_t d_id) { struct scsi_qla_host *host; @@ -299,7 +298,7 @@ static void qlt_try_to_dequeue_unknown_atios(struct scsi_qla_host *vha, goto abort; } - host = qlt_find_host_by_d_id(vha, u->atio.u.isp24.fcp_hdr.d_id); + host = qla_find_host_by_d_id(vha, u->atio.u.isp24.fcp_hdr.d_id); if (host != NULL) { ql_dbg(ql_dbg_async + ql_dbg_verbose, vha, 0x502f, "Requeuing unknown ATIO_TYPE7 %p\n", u); @@ -348,7 +347,7 @@ static bool qlt_24xx_atio_pkt_all_vps(struct scsi_qla_host *vha, switch (atio->u.raw.entry_type) { case ATIO_TYPE7: { - struct scsi_qla_host *host = qlt_find_host_by_d_id(vha, + struct scsi_qla_host *host = qla_find_host_by_d_id(vha, atio->u.isp24.fcp_hdr.d_id); if (unlikely(NULL == host)) { ql_dbg(ql_dbg_tgt, vha, 0xe03e, From patchwork Mon May 31 07:05:40 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Nilesh Javali X-Patchwork-Id: 450660 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-18.8 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER, INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, SPF_PASS, URIBL_BLOCKED, USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 5FB56C4708F for ; Mon, 31 May 2021 07:08:17 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 2B337611CA for ; Mon, 31 May 2021 07:08:17 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230135AbhEaHJy (ORCPT ); Mon, 31 May 2021 03:09:54 -0400 Received: from mx0b-0016f401.pphosted.com ([67.231.156.173]:16434 "EHLO mx0b-0016f401.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230070AbhEaHJw (ORCPT ); Mon, 31 May 2021 03:09:52 -0400 Received: from pps.filterd (m0045851.ppops.net [127.0.0.1]) by mx0b-0016f401.pphosted.com (8.16.0.43/8.16.0.43) with SMTP id 14V767Bf026053 for ; Mon, 31 May 2021 00:08:13 -0700 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=marvell.com; h=from : to : cc : subject : date : message-id : in-reply-to : references : mime-version : content-type; s=pfpt0220; bh=vICV1pJ85vSQ9bjXRZMpKNKSwPUTbAfRX9LAUY3O7J0=; b=TdVtaAt45LBWRYXNKNIZZiFvkOhznIR8vg+apo6hdygD4a1kcjQM8VhrasxcIICetgLn dBS99BrE+Ekl6AramTD6qO9IiRnqfekAKUs6NKL7tQtdvb7fCVcMwuuUcFpPcA6Wuad2 Z+ST1fyhc5nfm6xhK5xV0oEiiWvCba1Y0CpQF8DM5azMyZ/DlfN1wa2nQ0Sd3Bmr2PgL vTKwIJ+9w7WqPTBNwa6ntvINUg2CKGTurWyVWLJZA76kwXY0PQiLrNeF+ugoOxHbk2eA b2Jz5J09b0HvSSmdg6AdEXBAKsmFJldf7ppLj7J5mkE5oRR0GSm0YQEx9rWc6T2BBcnN bg== Received: from dc5-exch02.marvell.com ([199.233.59.182]) by mx0b-0016f401.pphosted.com with ESMTP id 38vtnj82ju-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-SHA384 bits=256 verify=NOT) for ; Mon, 31 May 2021 00:08:12 -0700 Received: from DC5-EXCH01.marvell.com (10.69.176.38) by DC5-EXCH02.marvell.com (10.69.176.39) with Microsoft SMTP Server (TLS) id 15.0.1497.2; Mon, 31 May 2021 00:08:10 -0700 Received: from maili.marvell.com (10.69.176.80) by DC5-EXCH01.marvell.com (10.69.176.38) with Microsoft SMTP Server id 15.0.1497.2 via Frontend Transport; Mon, 31 May 2021 00:08:10 -0700 Received: from dut1171.mv.qlogic.com (unknown [10.112.88.18]) by maili.marvell.com (Postfix) with ESMTP id 8743A3F703F; Mon, 31 May 2021 00:08:10 -0700 (PDT) Received: from dut1171.mv.qlogic.com (localhost [127.0.0.1]) by dut1171.mv.qlogic.com (8.14.7/8.14.7) with ESMTP id 14V78AF3032145; Mon, 31 May 2021 00:08:10 -0700 Received: (from root@localhost) by dut1171.mv.qlogic.com (8.14.7/8.14.7/Submit) id 14V78AIS032143; Mon, 31 May 2021 00:08:10 -0700 From: Nilesh Javali To: CC: , Subject: [PATCH v2 05/10] qla2xxx: Add key update Date: Mon, 31 May 2021 00:05:40 -0700 Message-ID: <20210531070545.32072-6-njavali@marvell.com> X-Mailer: git-send-email 2.12.0 In-Reply-To: <20210531070545.32072-1-njavali@marvell.com> References: <20210531070545.32072-1-njavali@marvell.com> MIME-Version: 1.0 X-Proofpoint-GUID: FBiUFw7H4adOerhxb0-Pi41PiUYLpcsW X-Proofpoint-ORIG-GUID: FBiUFw7H4adOerhxb0-Pi41PiUYLpcsW X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.391, 18.0.761 definitions=2021-05-31_04:2021-05-31,2021-05-31 signatures=0 Precedence: bulk List-ID: X-Mailing-List: linux-scsi@vger.kernel.org From: Quinn Tran Latest FC adapter from Marvell has the ability to encrypt data in flight (EDIF) feature. This feature require an application (ex: ipsec, etc) to act as an authenticator. As part of the authentication process, the authentication application will generate a SADB entry (Security Association/SA, key, SPI value, etc). This SADB is then pass to driver to be programmed into hardware. There will be a pair of SADB's (Tx and Rx) for each connection. After some period, the application can choose to change the key. At that time, a new set of SADB pair is given to driver. The old set of SADB will be deleted. This patch add a new bsg call (QL_VND_SC_SA_UPDATE) to allow application to allow add | delete of SADB. Driver will not keep the key in memory. It will pass it to HW. It is assume that application will assign a unique SPI value to this SADB(SA + key). Driver + HW will assign a handle to track this unique SPI/SADB. Signed-off-by: Larry Wisneski Signed-off-by: Duane Grigsby Signed-off-by: Rick Hicksted Jr Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali --- drivers/scsi/qla2xxx/qla_def.h | 69 ++ drivers/scsi/qla2xxx/qla_edif.c | 1482 ++++++++++++++++++++++++++++- drivers/scsi/qla2xxx/qla_edif.h | 61 ++ drivers/scsi/qla2xxx/qla_fw.h | 1 + drivers/scsi/qla2xxx/qla_gbl.h | 21 + drivers/scsi/qla2xxx/qla_init.c | 11 + drivers/scsi/qla2xxx/qla_iocb.c | 6 + drivers/scsi/qla2xxx/qla_isr.c | 10 + drivers/scsi/qla2xxx/qla_os.c | 20 + drivers/scsi/qla2xxx/qla_target.h | 2 +- 10 files changed, 1681 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index e47a7b3618d6..164b87fd66ba 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -401,6 +401,7 @@ struct srb_cmd { #define SRB_CRC_CTX_DSD_VALID BIT_5 /* DIF: dsd_list valid */ #define SRB_WAKEUP_ON_COMP BIT_6 #define SRB_DIF_BUNDL_DMA_VALID BIT_7 /* DIF: DMA list valid */ +#define SRB_EDIF_CLEANUP_DELETE BIT_9 /* To identify if a srb is of T10-CRC type. @sp => srb_t pointer */ #define IS_PROT_IO(sp) (sp->flags & SRB_CRC_CTX_DSD_VALID) @@ -595,6 +596,10 @@ struct srb_iocb { u16 cmd; u16 vp_index; } ctrlvp; + struct { + struct edif_sa_ctl *sa_ctl; + struct qla_sa_update_frame sa_frame; + } sa_update; } u; struct timer_list timer; @@ -2616,15 +2621,26 @@ typedef struct fc_port { uint16_t app_stop:2; uint16_t app_started:1; uint16_t secured_login:1; + uint16_t aes_gmac:1; uint16_t app_sess_online:1; uint16_t rekey_cnt; // num of times rekeyed uint8_t auth_state; /* cureent auth state */ + uint8_t tx_sa_set; + uint8_t rx_sa_set; + uint8_t tx_sa_pending; + uint8_t rx_sa_pending; uint32_t tx_rekey_cnt; uint32_t rx_rekey_cnt; // delayed rx delete data structure list uint64_t tx_bytes; uint64_t rx_bytes; uint8_t non_secured_login; + struct list_head edif_indx_list; + spinlock_t indx_list_lock; // protects the edif index list + + struct list_head tx_sa_list; + struct list_head rx_sa_list; + spinlock_t sa_list_lock; /* protects list */ } edif; } fc_port_t; @@ -2680,6 +2696,7 @@ static const char * const port_dstate_str[] = { #define FCF_CONF_COMP_SUPPORTED BIT_4 #define FCF_ASYNC_ACTIVE BIT_5 #define FCF_FCSP_DEVICE BIT_6 +#define FCF_EDIF_DELETE BIT_7 /* No loop ID flag. */ #define FC_NO_LOOP_ID 0x1000 @@ -3450,6 +3467,7 @@ enum qla_work_type { QLA_EVT_SP_RETRY, QLA_EVT_IIDMA, QLA_EVT_ELS_PLOGI, + QLA_EVT_SA_REPLACE, }; @@ -3508,6 +3526,11 @@ struct qla_work_evt { u8 fc4_type; srb_t *sp; } gpnft; + struct { + struct edif_sa_ctl *sa_ctl; + fc_port_t *fcport; + uint16_t nport_handle; + } sa_update; } u; }; @@ -4682,6 +4705,16 @@ struct qla_hw_data { pci_error_state_t pci_error_state; struct dma_pool *purex_dma_pool; struct btree_head32 host_map; + + #define EDIF_NUM_SA_INDEX 512 + #define EDIF_TX_SA_INDEX_BASE EDIF_NUM_SA_INDEX + void *edif_rx_sa_id_map; + void *edif_tx_sa_id_map; + spinlock_t sadb_fp_lock; + + struct list_head sadb_tx_index_list; + struct list_head sadb_rx_index_list; + spinlock_t sadb_lock; /* protects list */ struct els_reject elsrej; }; @@ -5157,7 +5190,43 @@ enum nexus_wait_type { WAIT_LUN, }; +#define INVALID_EDIF_SA_INDEX 0xffff +#define RX_DELETE_NO_EDIF_SA_INDEX 0xfffe + #define QLA_SKIP_HANDLE QLA_TGT_SKIP_HANDLE + +/* edif hash element */ +struct edif_list_entry { + uint16_t handle; /* nport_handle */ + uint32_t update_sa_index; + uint32_t delete_sa_index; + uint32_t count; /* counter for filtering sa_index */ +#define EDIF_ENTRY_FLAGS_CLEANUP 0x01 /* this index is being cleaned up */ + uint32_t flags; /* used by sadb cleanup code */ + fc_port_t *fcport; /* needed by rx delay timer function */ + struct timer_list timer; /* rx delay timer */ + struct list_head next; +}; + +#define EDIF_TX_INDX_BASE 512 +#define EDIF_RX_INDX_BASE 0 +#define EDIF_RX_DELETE_FILTER_COUNT 3 /* delay queuing rx delete until this many */ + +/* entry in the sa_index free pool */ + +struct sa_index_pair { + uint16_t sa_index; + uint32_t spi; +}; + +/* edif sa_index data structure */ +struct edif_sa_index_entry { + struct sa_index_pair sa_pair[2]; + fc_port_t *fcport; + uint16_t handle; + struct list_head next; +}; + /* Refer to SNIA SFF 8247 */ struct sff_8247_a0 { u8 txid; /* transceiver id */ diff --git a/drivers/scsi/qla2xxx/qla_edif.c b/drivers/scsi/qla2xxx/qla_edif.c index df8dff447c6a..4c5cc99bdbd4 100644 --- a/drivers/scsi/qla2xxx/qla_edif.c +++ b/drivers/scsi/qla2xxx/qla_edif.c @@ -4,13 +4,19 @@ * Copyright (c) 2021 Marvell */ #include "qla_def.h" -//#include "qla_edif.h" +#include "qla_edif.h" #include #include #include #include +static struct edif_sa_index_entry *qla_edif_sadb_find_sa_index_entry(uint16_t nport_handle, + struct list_head *sa_list); +static uint16_t qla_edif_sadb_get_sa_index(fc_port_t *fcport, + struct qla_sa_update_frame *sa_frame); +static int qla_edif_sadb_delete_sa_index(fc_port_t *fcport, uint16_t nport_handle, + uint16_t sa_index); static int qla_pur_get_pending(scsi_qla_host_t *, fc_port_t *, struct bsg_job *); static struct els_sub_cmd { @@ -35,6 +41,147 @@ const char *sc_to_str(uint16_t cmd) return "unknown"; } +/* find an edif list entry for an nport_handle */ +static struct edif_list_entry *qla_edif_list_find_sa_index(fc_port_t *fcport, + uint16_t handle) +{ + struct edif_list_entry *entry; + struct edif_list_entry *tentry; + struct list_head *indx_list = &fcport->edif.edif_indx_list; + + list_for_each_entry_safe(entry, tentry, indx_list, next) { + if (entry->handle == handle) + return entry; + } + return NULL; +} + +/* timeout called when no traffic and delayed rx sa_index delete */ +static void qla2x00_sa_replace_iocb_timeout(struct timer_list *t) +{ + struct edif_list_entry *edif_entry = from_timer(edif_entry, t, timer); + fc_port_t *fcport = edif_entry->fcport; + + struct scsi_qla_host *vha = fcport->vha; + struct edif_sa_ctl *sa_ctl; + uint16_t nport_handle; + unsigned long flags = 0; + + ql_dbg(ql_dbg_edif, vha, 0x3069, + "%s: nport_handle 0x%x, SA REPL Delay Timeout, %8phC portid=%06x\n", + __func__, edif_entry->handle, fcport->port_name, fcport->d_id.b24); + + /* + * if delete_sa_index is valid then no one has serviced this + * delayed delete + */ + spin_lock_irqsave(&fcport->edif.indx_list_lock, flags); + + /* + * delete_sa_index is invalidated when we find the new sa_index in + * the incoming data stream. If it is not invalidated then we are + * still looking for the new sa_index because there is no I/O and we + * need to just force the rx delete and move on. Otherwise + * we could get another rekey which will result in an error 66. + */ + if (edif_entry->delete_sa_index != INVALID_EDIF_SA_INDEX) { + uint16_t delete_sa_index = edif_entry->delete_sa_index; + + edif_entry->delete_sa_index = INVALID_EDIF_SA_INDEX; + nport_handle = edif_entry->handle; + spin_unlock_irqrestore(&fcport->edif.indx_list_lock, flags); + + sa_ctl = qla_edif_find_sa_ctl_by_index(fcport, + delete_sa_index, 0); + + if (sa_ctl) { + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: POST SA DELETE TIMEOUT sa_ctl: %p, delete index %d, update index: %d, lid: 0x%x\n", + __func__, sa_ctl, delete_sa_index, + edif_entry->update_sa_index, nport_handle); + + sa_ctl->flags = EDIF_SA_CTL_FLG_DEL; + set_bit(EDIF_SA_CTL_REPL, &sa_ctl->state); + qla_post_sa_replace_work(fcport->vha, fcport, + nport_handle, sa_ctl); + + } else { + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: POST SA DELETE TIMEOUT sa_ctl not found for delete_sa_index: %d\n", + __func__, edif_entry->delete_sa_index); + } + } else { + spin_unlock_irqrestore(&fcport->edif.indx_list_lock, flags); + } +} + +/* + * create a new list entry for this nport handle and + * add an sa_update index to the list - called for sa_update + */ +static int qla_edif_list_add_sa_update_index(fc_port_t *fcport, + uint16_t sa_index, uint16_t handle) +{ + struct edif_list_entry *entry; + unsigned long flags = 0; + + /* if the entry exists, then just update the sa_index */ + entry = qla_edif_list_find_sa_index(fcport, handle); + if (entry) { + entry->update_sa_index = sa_index; + entry->count = 0; + return 0; + } + + /* + * This is the normal path - there should be no existing entry + * when update is called. The exception is at startup + * when update is called for the first two sa_indexes + * followed by a delete of the first sa_index + */ + entry = kzalloc((sizeof(struct edif_list_entry)), GFP_ATOMIC); + if (!entry) + return -ENOMEM; + + INIT_LIST_HEAD(&entry->next); + entry->handle = handle; + entry->update_sa_index = sa_index; + entry->delete_sa_index = INVALID_EDIF_SA_INDEX; + entry->count = 0; + entry->flags = 0; + timer_setup(&entry->timer, qla2x00_sa_replace_iocb_timeout, 0); + spin_lock_irqsave(&fcport->edif.indx_list_lock, flags); + list_add_tail(&entry->next, &fcport->edif.edif_indx_list); + spin_unlock_irqrestore(&fcport->edif.indx_list_lock, flags); + return 0; +} + +/* remove an entry from the list */ +static void qla_edif_list_delete_sa_index(fc_port_t *fcport, struct edif_list_entry *entry) +{ + unsigned long flags = 0; + + spin_lock_irqsave(&fcport->edif.indx_list_lock, flags); + list_del(&entry->next); + spin_unlock_irqrestore(&fcport->edif.indx_list_lock, flags); +} + +int qla_post_sa_replace_work(struct scsi_qla_host *vha, + fc_port_t *fcport, uint16_t nport_handle, struct edif_sa_ctl *sa_ctl) +{ + struct qla_work_evt *e; + + e = qla2x00_alloc_work(vha, QLA_EVT_SA_REPLACE); + if (!e) + return QLA_FUNCTION_FAILED; + + e->u.sa_update.fcport = fcport; + e->u.sa_update.sa_ctl = sa_ctl; + e->u.sa_update.nport_handle = nport_handle; + fcport->flags |= FCF_ASYNC_ACTIVE; + return qla2x00_post_work(vha, e); +} + static void qla_edif_sa_ctl_init(scsi_qla_host_t *vha, struct fc_port *fcport) { @@ -198,6 +345,171 @@ static void qla_edif_reset_auth_wait(struct fc_port *fcport, int state, } } +static void +qla_edif_free_sa_ctl(fc_port_t *fcport, struct edif_sa_ctl *sa_ctl, + int index) +{ + unsigned long flags = 0; + + spin_lock_irqsave(&fcport->edif.sa_list_lock, flags); + list_del(&sa_ctl->next); + spin_unlock_irqrestore(&fcport->edif.sa_list_lock, flags); + if (index >= 512) + fcport->edif.tx_rekey_cnt--; + else + fcport->edif.rx_rekey_cnt--; + kfree(sa_ctl); +} + +/* return an index to the freepool */ +static void qla_edif_add_sa_index_to_freepool(fc_port_t *fcport, int dir, + uint16_t sa_index) +{ + void *sa_id_map; + struct scsi_qla_host *vha = fcport->vha; + struct qla_hw_data *ha = vha->hw; + unsigned long flags = 0; + u16 lsa_index = sa_index; + + ql_dbg(ql_dbg_edif + ql_dbg_verbose, vha, 0x3063, + "%s: entry\n", __func__); + + if (dir) { + sa_id_map = ha->edif_tx_sa_id_map; + lsa_index -= EDIF_TX_SA_INDEX_BASE; + } else { + sa_id_map = ha->edif_rx_sa_id_map; + } + + spin_lock_irqsave(&ha->sadb_fp_lock, flags); + clear_bit(lsa_index, sa_id_map); + spin_unlock_irqrestore(&ha->sadb_fp_lock, flags); + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: index %d added to free pool\n", __func__, sa_index); +} + +static void __qla2x00_release_all_sadb(struct scsi_qla_host *vha, + struct fc_port *fcport, struct edif_sa_index_entry *entry, + int pdir) +{ + struct edif_list_entry *edif_entry; + struct edif_sa_ctl *sa_ctl; + int i, dir; + int key_cnt = 0; + + for (i = 0; i < 2; i++) { + if (entry->sa_pair[i].sa_index == INVALID_EDIF_SA_INDEX) + continue; + + if (fcport->loop_id != entry->handle) { + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: ** WARNING %d** entry handle: 0x%x, fcport nport_handle: 0x%x, sa_index: %d\n", + __func__, i, entry->handle, + fcport->loop_id, + entry->sa_pair[i].sa_index); + } + + /* release the sa_ctl */ + sa_ctl = qla_edif_find_sa_ctl_by_index(fcport, + entry->sa_pair[i].sa_index, pdir); + if (sa_ctl && + qla_edif_find_sa_ctl_by_index(fcport, sa_ctl->index, pdir)) { + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: freeing sa_ctl for index %d\n", + __func__, sa_ctl->index); + qla_edif_free_sa_ctl(fcport, sa_ctl, sa_ctl->index); + } else { + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: sa_ctl NOT freed, sa_ctl: %p\n", + __func__, sa_ctl); + } + + /* Release the index */ + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: freeing sa_index %d, nph: 0x%x\n", + __func__, entry->sa_pair[i].sa_index, entry->handle); + + dir = (entry->sa_pair[i].sa_index < + EDIF_TX_SA_INDEX_BASE) ? 0 : 1; + qla_edif_add_sa_index_to_freepool(fcport, dir, + entry->sa_pair[i].sa_index); + + /* Delete timer on RX */ + if (pdir != SAU_FLG_TX) { + edif_entry = + qla_edif_list_find_sa_index(fcport, entry->handle); + if (edif_entry) { + ql_dbg(ql_dbg_edif, vha, 0x5033, + "%s: removing edif_entry %p, update_sa_index: 0x%x, delete_sa_index: 0x%x\n", + __func__, edif_entry, edif_entry->update_sa_index, + edif_entry->delete_sa_index); + qla_edif_list_delete_sa_index(fcport, edif_entry); + /* + * valid delete_sa_index indicates there is a rx + * delayed delete queued + */ + if (edif_entry->delete_sa_index != + INVALID_EDIF_SA_INDEX) { + del_timer(&edif_entry->timer); + + /* build and send the aen */ + fcport->edif.rx_sa_set = 1; + fcport->edif.rx_sa_pending = 0; + } + ql_dbg(ql_dbg_edif, vha, 0x5033, + "%s: releasing edif_entry %p, update_sa_index: 0x%x, delete_sa_index: 0x%x\n", + __func__, edif_entry, + edif_entry->update_sa_index, + edif_entry->delete_sa_index); + + kfree(edif_entry); + } + } + key_cnt++; + } + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: %d %s keys released\n", + __func__, key_cnt, pdir ? "tx" : "rx"); +} + +/* find an release all outstanding sadb sa_indicies */ +void qla2x00_release_all_sadb(struct scsi_qla_host *vha, struct fc_port *fcport) +{ + struct edif_sa_index_entry *entry, *tmp; + struct qla_hw_data *ha = vha->hw; + unsigned long flags; + + ql_dbg(ql_dbg_edif + ql_dbg_verbose, vha, 0x3063, + "%s: Starting...\n", __func__); + + spin_lock_irqsave(&ha->sadb_lock, flags); + + list_for_each_entry_safe(entry, tmp, &ha->sadb_rx_index_list, next) { + if (entry->fcport == fcport) { + list_del(&entry->next); + spin_unlock_irqrestore(&ha->sadb_lock, flags); + __qla2x00_release_all_sadb(vha, fcport, entry, 0); + kfree(entry); + spin_lock_irqsave(&ha->sadb_lock, flags); + break; + } + } + + list_for_each_entry_safe(entry, tmp, &ha->sadb_tx_index_list, next) { + if (entry->fcport == fcport) { + list_del(&entry->next); + spin_unlock_irqrestore(&ha->sadb_lock, flags); + + __qla2x00_release_all_sadb(vha, fcport, entry, SAU_FLG_TX); + + kfree(entry); + spin_lock_irqsave(&ha->sadb_lock, flags); + break; + } + } + spin_unlock_irqrestore(&ha->sadb_lock, flags); +} + /* * event that the app has started. Clear and start doorbell */ @@ -565,6 +877,10 @@ qla_edif_app_mgmt(struct bsg_job *bsg_job) } switch (vnd_sc) { + case QL_VND_SC_SA_UPDATE: + done = false; + rval = qla24xx_sadb_update(bsg_job); + break; case QL_VND_SC_APP_START: rval = qla_edif_app_start(vha, bsg_job); break; @@ -598,6 +914,435 @@ qla_edif_app_mgmt(struct bsg_job *bsg_job) return rval; } +static struct edif_sa_ctl * +qla_edif_add_sa_ctl(fc_port_t *fcport, struct qla_sa_update_frame *sa_frame, + int dir) +{ + struct edif_sa_ctl *sa_ctl; + struct qla_sa_update_frame *sap; + int index = sa_frame->fast_sa_index; + unsigned long flags = 0; + + sa_ctl = kzalloc(sizeof(*sa_ctl), GFP_KERNEL); + if (!sa_ctl) { + /* couldn't get space */ + ql_dbg(ql_dbg_edif, fcport->vha, 0x9100, + "unable to allocate SA CTL\n"); + return NULL; + } + + /* + * need to allocate sa_index here and save it + * in both sa_ctl->index and sa_frame->fast_sa_index; + * If alloc fails then delete sa_ctl and return NULL + */ + INIT_LIST_HEAD(&sa_ctl->next); + sap = &sa_ctl->sa_frame; + *sap = *sa_frame; + sa_ctl->index = index; + sa_ctl->fcport = fcport; + sa_ctl->flags = 0; + sa_ctl->state = 0L; + ql_dbg(ql_dbg_edif, fcport->vha, 0x9100, + "%s: Added sa_ctl %p, index %d, state 0x%lx\n", + __func__, sa_ctl, sa_ctl->index, sa_ctl->state); + spin_lock_irqsave(&fcport->edif.sa_list_lock, flags); + if (dir == SAU_FLG_TX) + list_add_tail(&sa_ctl->next, &fcport->edif.tx_sa_list); + else + list_add_tail(&sa_ctl->next, &fcport->edif.rx_sa_list); + spin_unlock_irqrestore(&fcport->edif.sa_list_lock, flags); + return sa_ctl; +} + +void +qla_edif_flush_sa_ctl_lists(fc_port_t *fcport) +{ + struct edif_sa_ctl *sa_ctl, *tsa_ctl; + unsigned long flags = 0; + + spin_lock_irqsave(&fcport->edif.sa_list_lock, flags); + + list_for_each_entry_safe(sa_ctl, tsa_ctl, &fcport->edif.tx_sa_list, + next) { + list_del(&sa_ctl->next); + kfree(sa_ctl); + } + + list_for_each_entry_safe(sa_ctl, tsa_ctl, &fcport->edif.rx_sa_list, + next) { + list_del(&sa_ctl->next); + kfree(sa_ctl); + } + + spin_unlock_irqrestore(&fcport->edif.sa_list_lock, flags); +} + +struct edif_sa_ctl * +qla_edif_find_sa_ctl_by_index(fc_port_t *fcport, int index, int dir) +{ + struct edif_sa_ctl *sa_ctl, *tsa_ctl; + struct list_head *sa_list; + + if (dir == SAU_FLG_TX) + sa_list = &fcport->edif.tx_sa_list; + else + sa_list = &fcport->edif.rx_sa_list; + list_for_each_entry_safe(sa_ctl, tsa_ctl, sa_list, next) { + if (test_bit(EDIF_SA_CTL_USED, &sa_ctl->state) && + sa_ctl->index == index) + return sa_ctl; + } + return NULL; +} + +/* add the sa to the correct list */ +static int +qla24xx_check_sadb_avail_slot(struct bsg_job *bsg_job, fc_port_t *fcport, + struct qla_sa_update_frame *sa_frame) +{ + struct edif_sa_ctl *sa_ctl = NULL; + int dir; + uint16_t sa_index; + + dir = (sa_frame->flags & SAU_FLG_TX); + + /* map the spi to an sa_index */ + sa_index = qla_edif_sadb_get_sa_index(fcport, sa_frame); + if (sa_index == RX_DELETE_NO_EDIF_SA_INDEX) { + /* process rx delete */ + ql_dbg(ql_dbg_edif, fcport->vha, 0x3063, + "%s: rx delete for lid 0x%x, spi 0x%x, no entry found\n", + __func__, fcport->loop_id, sa_frame->spi); + + /* build and send the aen */ + fcport->edif.rx_sa_set = 1; + fcport->edif.rx_sa_pending = 0; + + /* force a return of good bsg status; */ + return RX_DELETE_NO_EDIF_SA_INDEX; + } else if (sa_index == INVALID_EDIF_SA_INDEX) { + ql_dbg(ql_dbg_edif, fcport->vha, 0x9100, + "%s: Failed to get sa_index for spi 0x%x, dir: %d\n", + __func__, sa_frame->spi, dir); + return INVALID_EDIF_SA_INDEX; + } + + ql_dbg(ql_dbg_edif, fcport->vha, 0x9100, + "%s: index %d allocated to spi 0x%x, dir: %d, nport_handle: 0x%x\n", + __func__, sa_index, sa_frame->spi, dir, fcport->loop_id); + + /* This is a local copy of sa_frame. */ + sa_frame->fast_sa_index = sa_index; + /* create the sa_ctl */ + sa_ctl = qla_edif_add_sa_ctl(fcport, sa_frame, dir); + if (!sa_ctl) { + ql_dbg(ql_dbg_edif, fcport->vha, 0x9100, + "%s: Failed to add sa_ctl for spi 0x%x, dir: %d, sa_index: %d\n", + __func__, sa_frame->spi, dir, sa_index); + return -1; + } + + set_bit(EDIF_SA_CTL_USED, &sa_ctl->state); + + if (dir == SAU_FLG_TX) + fcport->edif.tx_rekey_cnt++; + else + fcport->edif.rx_rekey_cnt++; + + ql_dbg(ql_dbg_edif, fcport->vha, 0x9100, + "%s: Found sa_ctl %p, index %d, state 0x%lx, tx_cnt %d, rx_cnt %d, nport_handle: 0x%x\n", + __func__, sa_ctl, sa_ctl->index, sa_ctl->state, + fcport->edif.tx_rekey_cnt, + fcport->edif.rx_rekey_cnt, fcport->loop_id); + return 0; +} + +#define QLA_SA_UPDATE_FLAGS_RX_KEY 0x0 +#define QLA_SA_UPDATE_FLAGS_TX_KEY 0x2 + +int +qla24xx_sadb_update(struct bsg_job *bsg_job) +{ + struct fc_bsg_reply *bsg_reply = bsg_job->reply; + struct Scsi_Host *host = fc_bsg_to_shost(bsg_job); + scsi_qla_host_t *vha = shost_priv(host); + fc_port_t *fcport = NULL; + srb_t *sp = NULL; + struct edif_list_entry *edif_entry = NULL; + int found = 0; + int rval = 0; + int result = 0; + struct qla_sa_update_frame sa_frame; + struct srb_iocb *iocb_cmd; + + ql_dbg(ql_dbg_edif + ql_dbg_verbose, vha, 0x911d, + "%s entered, vha: 0x%p\n", __func__, vha); + + sg_copy_to_buffer(bsg_job->request_payload.sg_list, + bsg_job->request_payload.sg_cnt, &sa_frame, + sizeof(struct qla_sa_update_frame)); + + /* Check if host is online */ + if (!vha->flags.online) { + ql_log(ql_log_warn, vha, 0x70a1, "Host is not online\n"); + rval = -EIO; + SET_DID_STATUS(bsg_reply->result, DID_ERROR); + goto done; + } + + if (vha->e_dbell.db_flags != EDB_ACTIVE) { + ql_log(ql_log_warn, vha, 0x70a1, "App not started\n"); + rval = -EIO; + SET_DID_STATUS(bsg_reply->result, DID_ERROR); + goto done; + } + + fcport = qla2x00_find_fcport_by_pid(vha, &sa_frame.port_id); + if (fcport) { + found = 1; + if (sa_frame.flags == QLA_SA_UPDATE_FLAGS_TX_KEY) + fcport->edif.tx_bytes = 0; + if (sa_frame.flags == QLA_SA_UPDATE_FLAGS_RX_KEY) + fcport->edif.rx_bytes = 0; + } + + if (!found) { + ql_dbg(ql_dbg_edif, vha, 0x70a3, "Failed to find port= %06x\n", + sa_frame.port_id.b24); + rval = -EINVAL; + SET_DID_STATUS(bsg_reply->result, DID_TARGET_FAILURE); + goto done; + } + + /* make sure the nport_handle is valid */ + if (fcport->loop_id == FC_NO_LOOP_ID) { + ql_dbg(ql_dbg_edif, vha, 0x70e1, + "%s: %8phN lid=FC_NO_LOOP_ID, spi: 0x%x, DS %d, returning NO_CONNECT\n", + __func__, fcport->port_name, sa_frame.spi, + fcport->disc_state); + rval = -EINVAL; + SET_DID_STATUS(bsg_reply->result, DID_NO_CONNECT); + goto done; + } + + /* allocate and queue an sa_ctl */ + result = qla24xx_check_sadb_avail_slot(bsg_job, fcport, &sa_frame); + + /* failure of bsg */ + if (result == INVALID_EDIF_SA_INDEX) { + ql_dbg(ql_dbg_edif, vha, 0x70e1, + "%s: %8phN, skipping update.\n", + __func__, fcport->port_name); + rval = -EINVAL; + SET_DID_STATUS(bsg_reply->result, DID_ERROR); + goto done; + + /* rx delete failure */ + } else if (result == RX_DELETE_NO_EDIF_SA_INDEX) { + ql_dbg(ql_dbg_edif, vha, 0x70e1, + "%s: %8phN, skipping rx delete.\n", + __func__, fcport->port_name); + SET_DID_STATUS(bsg_reply->result, DID_OK); + goto done; + } + + ql_dbg(ql_dbg_edif, vha, 0x70e1, + "%s: %8phN, sa_index in sa_frame: %d flags %xh\n", + __func__, fcport->port_name, sa_frame.fast_sa_index, + sa_frame.flags); + + /* looking for rx index and delete */ + if (((sa_frame.flags & SAU_FLG_TX) == 0) && + (sa_frame.flags & SAU_FLG_INV)) { + uint16_t nport_handle = fcport->loop_id; + uint16_t sa_index = sa_frame.fast_sa_index; + + /* + * make sure we have an existing rx key, otherwise just process + * this as a straight delete just like TX + * This is NOT a normal case, it indicates an error recovery or key cleanup + * by the ipsec code above us. + */ + edif_entry = qla_edif_list_find_sa_index(fcport, fcport->loop_id); + if (!edif_entry) { + ql_dbg(ql_dbg_edif, vha, 0x911d, + "%s: WARNING: no active sa_index for nport_handle 0x%x, forcing delete for sa_index 0x%x\n", + __func__, fcport->loop_id, sa_index); + goto force_rx_delete; + } + + /* + * if we have a forced delete for rx, remove the sa_index from the edif list + * and proceed with normal delete. The rx delay timer should not be running + */ + if ((sa_frame.flags & SAU_FLG_FORCE_DELETE) == SAU_FLG_FORCE_DELETE) { + qla_edif_list_delete_sa_index(fcport, edif_entry); + ql_dbg(ql_dbg_edif, vha, 0x911d, + "%s: FORCE DELETE flag found for nport_handle 0x%x, sa_index 0x%x, forcing DELETE\n", + __func__, fcport->loop_id, sa_index); + kfree(edif_entry); + goto force_rx_delete; + } + + /* + * delayed rx delete + * + * if delete_sa_index is not invalid then there is already + * a delayed index in progress, return bsg bad status + */ + if (edif_entry->delete_sa_index != INVALID_EDIF_SA_INDEX) { + struct edif_sa_ctl *sa_ctl; + + ql_dbg(ql_dbg_edif, vha, 0x911d, + "%s: delete for lid 0x%x, delete_sa_index %d is pending\n", + __func__, edif_entry->handle, + edif_entry->delete_sa_index); + + /* free up the sa_ctl that was allocated with the sa_index */ + sa_ctl = qla_edif_find_sa_ctl_by_index(fcport, sa_index, + (sa_frame.flags & SAU_FLG_TX)); + if (sa_ctl) { + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: freeing sa_ctl for index %d\n", + __func__, sa_ctl->index); + qla_edif_free_sa_ctl(fcport, sa_ctl, sa_ctl->index); + } + + /* release the sa_index */ + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: freeing sa_index %d, nph: 0x%x\n", + __func__, sa_index, nport_handle); + qla_edif_sadb_delete_sa_index(fcport, nport_handle, sa_index); + + rval = -EINVAL; + SET_DID_STATUS(bsg_reply->result, DID_ERROR); + goto done; + } + + fcport->edif.rekey_cnt++; + + /* configure and start the rx delay timer */ + edif_entry->fcport = fcport; + edif_entry->timer.expires = jiffies + RX_DELAY_DELETE_TIMEOUT * HZ; + + ql_dbg(ql_dbg_edif, vha, 0x911d, + "%s: adding timer, entry: %p, delete sa_index %d, lid 0x%x to edif_list\n", + __func__, edif_entry, sa_index, nport_handle); + + /* + * Start the timer when we queue the delayed rx delete. + * This is an activity timer that goes off if we have not + * received packets with the new sa_index + */ + add_timer(&edif_entry->timer); + + /* + * sa_delete for rx key with an active rx key including this one + * add the delete rx sa index to the hash so we can look for it + * in the rsp queue. Do this after making any changes to the + * edif_entry as part of the rx delete. + */ + + ql_dbg(ql_dbg_edif, vha, 0x911d, + "%s: delete sa_index %d, lid 0x%x to edif_list. bsg done ptr %p\n", + __func__, sa_index, nport_handle, bsg_job); + + edif_entry->delete_sa_index = sa_index; + + bsg_job->reply_len = sizeof(struct fc_bsg_reply); + bsg_reply->result = DID_OK << 16; + + goto done; + + /* + * rx index and update + * add the index to the list and continue with normal update + */ + } else if (((sa_frame.flags & SAU_FLG_TX) == 0) && + ((sa_frame.flags & SAU_FLG_INV) == 0)) { + /* sa_update for rx key */ + uint32_t nport_handle = fcport->loop_id; + uint16_t sa_index = sa_frame.fast_sa_index; + int result; + + /* + * add the update rx sa index to the hash so we can look for it + * in the rsp queue and continue normally + */ + + ql_dbg(ql_dbg_edif, vha, 0x911d, + "%s: adding update sa_index %d, lid 0x%x to edif_list\n", + __func__, sa_index, nport_handle); + + result = qla_edif_list_add_sa_update_index(fcport, sa_index, + nport_handle); + if (result) { + ql_dbg(ql_dbg_edif, vha, 0x911d, + "%s: SA_UPDATE failed to add new sa index %d to list for lid 0x%x\n", + __func__, sa_index, nport_handle); + } + } + if (sa_frame.flags & SAU_FLG_GMAC_MODE) + fcport->edif.aes_gmac = 1; + else + fcport->edif.aes_gmac = 0; + +force_rx_delete: + /* + * sa_update for both rx and tx keys, sa_delete for tx key + * immediately process the request + */ + sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL); + if (!sp) { + rval = -ENOMEM; + SET_DID_STATUS(bsg_reply->result, DID_IMM_RETRY); + goto done; + } + + sp->type = SRB_SA_UPDATE; + sp->name = "bsg_sa_update"; + sp->u.bsg_job = bsg_job; + /* sp->free = qla2x00_bsg_sp_free; */ + sp->free = qla2x00_rel_sp; + sp->done = qla2x00_bsg_job_done; + iocb_cmd = &sp->u.iocb_cmd; + iocb_cmd->u.sa_update.sa_frame = sa_frame; + + rval = qla2x00_start_sp(sp); + if (rval != QLA_SUCCESS) { + ql_log(ql_dbg_edif, vha, 0x70e3, + "qla2x00_start_sp failed=%d.\n", rval); + + qla2x00_rel_sp(sp); + rval = -EIO; + SET_DID_STATUS(bsg_reply->result, DID_IMM_RETRY); + goto done; + } + + ql_dbg(ql_dbg_edif, vha, 0x911d, + "%s: %s sent, hdl=%x, portid=%06x.\n", + __func__, sp->name, sp->handle, fcport->d_id.b24); + + fcport->edif.rekey_cnt++; + bsg_job->reply_len = sizeof(struct fc_bsg_reply); + SET_DID_STATUS(bsg_reply->result, DID_OK); + + return 0; + +/* + * send back error status + */ +done: + bsg_job->reply_len = sizeof(struct fc_bsg_reply); + ql_dbg(ql_dbg_edif, vha, 0x911d, + "%s:status: FAIL, result: 0x%x, bsg ptr done %p\n", + __func__, bsg_reply->result, bsg_job); + bsg_job_done(bsg_job, bsg_reply->result, + bsg_reply->reply_payload_rcv_len); + return 0; +} + static void qla_enode_free(scsi_qla_host_t *vha, struct enode *node) { @@ -860,6 +1605,200 @@ qla_edb_stop(scsi_qla_host_t *vha) } } +static void qla_noop_sp_done(srb_t *sp, int res) +{ + sp->free(sp); +} + +/* + * Called from work queue + * build and send the sa_update iocb to delete an rx sa_index + */ +int +qla24xx_issue_sa_replace_iocb(scsi_qla_host_t *vha, struct qla_work_evt *e) +{ + srb_t *sp; + fc_port_t *fcport = NULL; + struct srb_iocb *iocb_cmd = NULL; + int rval = QLA_SUCCESS; + struct edif_sa_ctl *sa_ctl = e->u.sa_update.sa_ctl; + uint16_t nport_handle = e->u.sa_update.nport_handle; + + ql_dbg(ql_dbg_edif, vha, 0x70e6, + "%s: starting, sa_ctl: %p\n", __func__, sa_ctl); + + if (!sa_ctl) { + ql_dbg(ql_dbg_edif, vha, 0x70e6, + "sa_ctl allocation failed\n"); + return -ENOMEM; + } + + fcport = sa_ctl->fcport; + + /* Alloc SRB structure */ + sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL); + if (!sp) { + ql_dbg(ql_dbg_edif, vha, 0x70e6, + "SRB allocation failed\n"); + return -ENOMEM; + } + + fcport->flags |= FCF_ASYNC_SENT; + iocb_cmd = &sp->u.iocb_cmd; + iocb_cmd->u.sa_update.sa_ctl = sa_ctl; + + ql_dbg(ql_dbg_edif, vha, 0x3073, + "Enter: SA REPL portid=%06x, sa_ctl %p, index %x, nport_handle: 0x%x\n", + fcport->d_id.b24, sa_ctl, sa_ctl->index, nport_handle); + /* + * if this is a sadb cleanup delete, mark it so the isr can + * take the correct action + */ + if (sa_ctl->flags & EDIF_SA_CTL_FLG_CLEANUP_DEL) { + /* mark this srb as a cleanup delete */ + sp->flags |= SRB_EDIF_CLEANUP_DELETE; + ql_dbg(ql_dbg_edif, vha, 0x70e6, + "%s: sp 0x%p flagged as cleanup delete\n", __func__, sp); + } + + sp->type = SRB_SA_REPLACE; + sp->name = "SA_REPLACE"; + sp->fcport = fcport; + sp->free = qla2x00_rel_sp; + sp->done = qla_noop_sp_done; + + rval = qla2x00_start_sp(sp); + + if (rval != QLA_SUCCESS) + rval = QLA_FUNCTION_FAILED; + + return rval; +} + +void qla24xx_sa_update_iocb(srb_t *sp, struct sa_update_28xx *sa_update_iocb) +{ + int itr = 0; + struct scsi_qla_host *vha = sp->vha; + struct qla_sa_update_frame *sa_frame = + &sp->u.iocb_cmd.u.sa_update.sa_frame; + u8 flags = 0; + + switch (sa_frame->flags & (SAU_FLG_INV | SAU_FLG_TX)) { + case 0: + ql_dbg(ql_dbg_edif, vha, 0x911d, + "%s: EDIF SA UPDATE RX IOCB vha: 0x%p index: %d\n", + __func__, vha, sa_frame->fast_sa_index); + break; + case 1: + ql_dbg(ql_dbg_edif, vha, 0x911d, + "%s: EDIF SA DELETE RX IOCB vha: 0x%p index: %d\n", + __func__, vha, sa_frame->fast_sa_index); + flags |= SA_FLAG_INVALIDATE; + break; + case 2: + ql_dbg(ql_dbg_edif, vha, 0x911d, + "%s: EDIF SA UPDATE TX IOCB vha: 0x%p index: %d\n", + __func__, vha, sa_frame->fast_sa_index); + flags |= SA_FLAG_TX; + break; + case 3: + ql_dbg(ql_dbg_edif, vha, 0x911d, + "%s: EDIF SA DELETE TX IOCB vha: 0x%p index: %d\n", + __func__, vha, sa_frame->fast_sa_index); + flags |= SA_FLAG_TX | SA_FLAG_INVALIDATE; + break; + } + + sa_update_iocb->entry_type = SA_UPDATE_IOCB_TYPE; + sa_update_iocb->entry_count = 1; + sa_update_iocb->sys_define = 0; + sa_update_iocb->entry_status = 0; + sa_update_iocb->handle = sp->handle; + sa_update_iocb->u.nport_handle = cpu_to_le16(sp->fcport->loop_id); + sa_update_iocb->vp_index = sp->fcport->vha->vp_idx; + sa_update_iocb->port_id[0] = sp->fcport->d_id.b.al_pa; + sa_update_iocb->port_id[1] = sp->fcport->d_id.b.area; + sa_update_iocb->port_id[2] = sp->fcport->d_id.b.domain; + + sa_update_iocb->flags = flags; + sa_update_iocb->salt = cpu_to_le32(sa_frame->salt); + sa_update_iocb->spi = cpu_to_le32(sa_frame->spi); + sa_update_iocb->sa_index = cpu_to_le16(sa_frame->fast_sa_index); + + sa_update_iocb->sa_control |= SA_CNTL_ENC_FCSP; + if (sp->fcport->edif.aes_gmac) + sa_update_iocb->sa_control |= SA_CNTL_AES_GMAC; + + if (sa_frame->flags & SAU_FLG_KEY256) { + sa_update_iocb->sa_control |= SA_CNTL_KEY256; + for (itr = 0; itr < 32; itr++) + sa_update_iocb->sa_key[itr] = sa_frame->sa_key[itr]; + + ql_dbg(ql_dbg_edif + ql_dbg_verbose, vha, 0x921f, "%s 256 sa key=%32phN\n", + __func__, sa_update_iocb->sa_key); + } else { + sa_update_iocb->sa_control |= SA_CNTL_KEY128; + for (itr = 0; itr < 16; itr++) + sa_update_iocb->sa_key[itr] = sa_frame->sa_key[itr]; + + ql_dbg(ql_dbg_edif + ql_dbg_verbose, vha, 0x921f, "%s 128 sa key=%16phN\n", + __func__, sa_update_iocb->sa_key); + } + + ql_dbg(ql_dbg_edif, vha, 0x921d, +"%s SAU Port ID = %02x:%02x:%02x, flags=%xh, index=%u, ctl=%xh, SPI 0x%x user flags 0x%x hdl=%x gmac %d\n", + __func__, sa_update_iocb->port_id[2], + sa_update_iocb->port_id[1], sa_update_iocb->port_id[0], + sa_update_iocb->flags, sa_update_iocb->sa_index, + sa_update_iocb->sa_control, sa_update_iocb->spi, + sa_frame->flags, sp->handle, sp->fcport->edif.aes_gmac); + + if (sa_frame->flags & SAU_FLG_TX) + sp->fcport->edif.tx_sa_pending = 1; + else + sp->fcport->edif.rx_sa_pending = 1; + + sp->fcport->vha->qla_stats.control_requests++; +} + +void +qla24xx_sa_replace_iocb(srb_t *sp, struct sa_update_28xx *sa_update_iocb) +{ + struct scsi_qla_host *vha = sp->vha; + struct srb_iocb *srb_iocb = &sp->u.iocb_cmd; + struct edif_sa_ctl *sa_ctl = srb_iocb->u.sa_update.sa_ctl; + uint16_t nport_handle = sp->fcport->loop_id; + + sa_update_iocb->entry_type = SA_UPDATE_IOCB_TYPE; + sa_update_iocb->entry_count = 1; + sa_update_iocb->sys_define = 0; + sa_update_iocb->entry_status = 0; + sa_update_iocb->handle = sp->handle; + + sa_update_iocb->u.nport_handle = cpu_to_le16(nport_handle); + + sa_update_iocb->vp_index = sp->fcport->vha->vp_idx; + sa_update_iocb->port_id[0] = sp->fcport->d_id.b.al_pa; + sa_update_iocb->port_id[1] = sp->fcport->d_id.b.area; + sa_update_iocb->port_id[2] = sp->fcport->d_id.b.domain; + + /* Invalidate the index. salt, spi, control & key are ignore */ + sa_update_iocb->flags = SA_FLAG_INVALIDATE; + sa_update_iocb->salt = 0; + sa_update_iocb->spi = 0; + sa_update_iocb->sa_index = cpu_to_le16(sa_ctl->index); + sa_update_iocb->sa_control = 0; + + ql_dbg(ql_dbg_edif, vha, 0x921d, + "%s SAU DELETE RX Port ID = %02x:%02x:%02x, lid %d flags=%xh, index=%u, hdl=%x\n", + __func__, sa_update_iocb->port_id[2], + sa_update_iocb->port_id[1], sa_update_iocb->port_id[0], + nport_handle, sa_update_iocb->flags, sa_update_iocb->sa_index, + sp->handle); + + sp->fcport->vha->qla_stats.control_requests++; +} + void qla24xx_auth_els(scsi_qla_host_t *vha, void **pkt, struct rsp_que **rsp) { struct purex_entry_24xx *p = *pkt; @@ -987,6 +1926,547 @@ void qla24xx_auth_els(scsi_qla_host_t *vha, void **pkt, struct rsp_que **rsp) purex->pur_info.pur_did.b24, p->rx_xchg_addr); } +static uint16_t qla_edif_get_sa_index_from_freepool(fc_port_t *fcport, int dir) +{ + struct scsi_qla_host *vha = fcport->vha; + struct qla_hw_data *ha = vha->hw; + void *sa_id_map; + unsigned long flags = 0; + u16 sa_index; + + ql_dbg(ql_dbg_edif + ql_dbg_verbose, vha, 0x3063, + "%s: entry\n", __func__); + + if (dir) + sa_id_map = ha->edif_tx_sa_id_map; + else + sa_id_map = ha->edif_rx_sa_id_map; + + spin_lock_irqsave(&ha->sadb_fp_lock, flags); + sa_index = find_first_zero_bit(sa_id_map, EDIF_NUM_SA_INDEX); + if (sa_index >= EDIF_NUM_SA_INDEX) { + spin_unlock_irqrestore(&ha->sadb_fp_lock, flags); + return INVALID_EDIF_SA_INDEX; + } + set_bit(sa_index, sa_id_map); + spin_unlock_irqrestore(&ha->sadb_fp_lock, flags); + + if (dir) + sa_index += EDIF_TX_SA_INDEX_BASE; + + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: index retrieved from free pool %d\n", __func__, sa_index); + + return sa_index; +} + +/* find an sadb entry for an nport_handle */ +static struct edif_sa_index_entry * +qla_edif_sadb_find_sa_index_entry(uint16_t nport_handle, + struct list_head *sa_list) +{ + struct edif_sa_index_entry *entry; + struct edif_sa_index_entry *tentry; + struct list_head *indx_list = sa_list; + + list_for_each_entry_safe(entry, tentry, indx_list, next) { + if (entry->handle == nport_handle) + return entry; + } + return NULL; +} + +/* remove an sa_index from the nport_handle and return it to the free pool */ +static int qla_edif_sadb_delete_sa_index(fc_port_t *fcport, uint16_t nport_handle, + uint16_t sa_index) +{ + struct edif_sa_index_entry *entry; + struct list_head *sa_list; + int dir = (sa_index < EDIF_TX_SA_INDEX_BASE) ? 0 : 1; + int slot = 0; + int free_slot_count = 0; + scsi_qla_host_t *vha = fcport->vha; + struct qla_hw_data *ha = vha->hw; + unsigned long flags = 0; + + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: entry\n", __func__); + + if (dir) + sa_list = &ha->sadb_tx_index_list; + else + sa_list = &ha->sadb_rx_index_list; + + entry = qla_edif_sadb_find_sa_index_entry(nport_handle, sa_list); + if (!entry) { + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: no entry found for nport_handle 0x%x\n", + __func__, nport_handle); + return -1; + } + + spin_lock_irqsave(&ha->sadb_lock, flags); + for (slot = 0; slot < 2; slot++) { + if (entry->sa_pair[slot].sa_index == sa_index) { + entry->sa_pair[slot].sa_index = INVALID_EDIF_SA_INDEX; + entry->sa_pair[slot].spi = 0; + free_slot_count++; + qla_edif_add_sa_index_to_freepool(fcport, dir, sa_index); + } else if (entry->sa_pair[slot].sa_index == INVALID_EDIF_SA_INDEX) { + free_slot_count++; + } + } + + if (free_slot_count == 2) { + list_del(&entry->next); + kfree(entry); + } + spin_unlock_irqrestore(&ha->sadb_lock, flags); + + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: sa_index %d removed, free_slot_count: %d\n", + __func__, sa_index, free_slot_count); + + return 0; +} + +void +qla28xx_sa_update_iocb_entry(scsi_qla_host_t *v, struct req_que *req, + struct sa_update_28xx *pkt) +{ + const char *func = "SA_UPDATE_RESPONSE_IOCB"; + srb_t *sp; + struct edif_sa_ctl *sa_ctl; + int old_sa_deleted = 1; + uint16_t nport_handle; + struct scsi_qla_host *vha; + + sp = qla2x00_get_sp_from_handle(v, func, req, pkt); + + if (!sp) { + ql_dbg(ql_dbg_edif, v, 0x3063, + "%s: no sp found for pkt\n", __func__); + return; + } + /* use sp->vha due to npiv */ + vha = sp->vha; + + switch (pkt->flags & (SA_FLAG_INVALIDATE | SA_FLAG_TX)) { + case 0: + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: EDIF SA UPDATE RX IOCB vha: 0x%p index: %d\n", + __func__, vha, pkt->sa_index); + break; + case 1: + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: EDIF SA DELETE RX IOCB vha: 0x%p index: %d\n", + __func__, vha, pkt->sa_index); + break; + case 2: + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: EDIF SA UPDATE TX IOCB vha: 0x%p index: %d\n", + __func__, vha, pkt->sa_index); + break; + case 3: + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: EDIF SA DELETE TX IOCB vha: 0x%p index: %d\n", + __func__, vha, pkt->sa_index); + break; + } + + /* + * dig the nport handle out of the iocb, fcport->loop_id can not be trusted + * to be correct during cleanup sa_update iocbs. + */ + nport_handle = sp->fcport->loop_id; + + ql_dbg(ql_dbg_edif, vha, 0x3063, +"%s: %8phN comp status=%x old_sa_info=%x new_sa_info=%x lid %d, index=0x%x pkt_flags %xh hdl=%x\n", + __func__, sp->fcport->port_name, + pkt->u.comp_sts, pkt->old_sa_info, pkt->new_sa_info, nport_handle, + pkt->sa_index, pkt->flags, sp->handle); + + /* if rx delete, remove the timer */ + if ((pkt->flags & (SA_FLAG_INVALIDATE | SA_FLAG_TX)) == SA_FLAG_INVALIDATE) { + struct edif_list_entry *edif_entry; + + sp->fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); + + edif_entry = qla_edif_list_find_sa_index(sp->fcport, nport_handle); + if (edif_entry) { + ql_dbg(ql_dbg_edif, vha, 0x5033, + "%s: removing edif_entry %p, new sa_index: 0x%x\n", + __func__, edif_entry, pkt->sa_index); + qla_edif_list_delete_sa_index(sp->fcport, edif_entry); + del_timer(&edif_entry->timer); + + ql_dbg(ql_dbg_edif, vha, 0x5033, + "%s: releasing edif_entry %p, new sa_index: 0x%x\n", + __func__, edif_entry, pkt->sa_index); + + kfree(edif_entry); + } + } + + /* + * if this is a delete for either tx or rx, make sure it succeeded. + * The new_sa_info field should be 0xffff on success + */ + if (pkt->flags & SA_FLAG_INVALIDATE) + old_sa_deleted = (le16_to_cpu(pkt->new_sa_info) == 0xffff) ? 1 : 0; + + /* Process update and delete the same way */ + + /* If this is an sadb cleanup delete, bypass sending events to IPSEC */ + if (sp->flags & SRB_EDIF_CLEANUP_DELETE) { + sp->fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: nph 0x%x, sa_index %d removed from fw\n", + __func__, sp->fcport->loop_id, pkt->sa_index); + + } else if ((pkt->entry_status == 0) && (pkt->u.comp_sts == 0) && + old_sa_deleted) { + /* + * Note: Wa are only keeping track of latest SA, + * so we know when we can start enableing encryption per I/O. + * If all SA's get deleted, let FW reject the IOCB. + + * TODO: edif: don't set enabled here I think + * TODO: edif: prli complete is where it should be set + */ + ql_dbg(ql_dbg_edif + ql_dbg_verbose, vha, 0x3063, + "SA(%x)updated for s_id %02x%02x%02x\n", + pkt->new_sa_info, + pkt->port_id[2], pkt->port_id[1], pkt->port_id[0]); + sp->fcport->edif.enable = 1; + if (pkt->flags & SA_FLAG_TX) { + sp->fcport->edif.tx_sa_set = 1; + sp->fcport->edif.tx_sa_pending = 0; + } else { + sp->fcport->edif.rx_sa_set = 1; + sp->fcport->edif.rx_sa_pending = 0; + } + } else { + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: %8phN SA update FAILED: sa_index: %d, new_sa_info %d, %02x%02x%02x -- dumping\n", + __func__, sp->fcport->port_name, + pkt->sa_index, pkt->new_sa_info, pkt->port_id[2], + pkt->port_id[1], pkt->port_id[0]); + } + + /* for delete, release sa_ctl, sa_index */ + if (pkt->flags & SA_FLAG_INVALIDATE) { + /* release the sa_ctl */ + sa_ctl = qla_edif_find_sa_ctl_by_index(sp->fcport, + le16_to_cpu(pkt->sa_index), (pkt->flags & SA_FLAG_TX)); + if (sa_ctl && + qla_edif_find_sa_ctl_by_index(sp->fcport, sa_ctl->index, + (pkt->flags & SA_FLAG_TX)) != NULL) { + ql_dbg(ql_dbg_edif + ql_dbg_verbose, vha, 0x3063, + "%s: freeing sa_ctl for index %d\n", + __func__, sa_ctl->index); + qla_edif_free_sa_ctl(sp->fcport, sa_ctl, sa_ctl->index); + } else { + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: sa_ctl NOT freed, sa_ctl: %p\n", + __func__, sa_ctl); + } + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: freeing sa_index %d, nph: 0x%x\n", + __func__, le16_to_cpu(pkt->sa_index), nport_handle); + qla_edif_sadb_delete_sa_index(sp->fcport, nport_handle, + le16_to_cpu(pkt->sa_index)); + /* + * check for a failed sa_update and remove + * the sadb entry. + */ + } else if (pkt->u.comp_sts) { + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: freeing sa_index %d, nph: 0x%x\n", + __func__, pkt->sa_index, nport_handle); + qla_edif_sadb_delete_sa_index(sp->fcport, nport_handle, + le16_to_cpu(pkt->sa_index)); + } + + sp->done(sp, 0); +} + +/****************** + * SADB functions * + ******************/ + +/* allocate/retrieve an sa_index for a given spi */ +static uint16_t qla_edif_sadb_get_sa_index(fc_port_t *fcport, + struct qla_sa_update_frame *sa_frame) +{ + struct edif_sa_index_entry *entry; + struct list_head *sa_list; + uint16_t sa_index; + int dir = sa_frame->flags & SAU_FLG_TX; + int slot = 0; + int free_slot = -1; + scsi_qla_host_t *vha = fcport->vha; + struct qla_hw_data *ha = vha->hw; + unsigned long flags = 0; + uint16_t nport_handle = fcport->loop_id; + + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: entry fc_port: %p, nport_handle: 0x%x\n", + __func__, fcport, nport_handle); + + if (dir) + sa_list = &ha->sadb_tx_index_list; + else + sa_list = &ha->sadb_rx_index_list; + + entry = qla_edif_sadb_find_sa_index_entry(nport_handle, sa_list); + if (!entry) { + if ((sa_frame->flags & (SAU_FLG_TX | SAU_FLG_INV)) == SAU_FLG_INV) { + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: rx delete request with no entry\n", __func__); + return RX_DELETE_NO_EDIF_SA_INDEX; + } + + /* if there is no entry for this nport, add one */ + entry = kzalloc((sizeof(struct edif_sa_index_entry)), GFP_ATOMIC); + if (!entry) + return INVALID_EDIF_SA_INDEX; + + sa_index = qla_edif_get_sa_index_from_freepool(fcport, dir); + if (sa_index == INVALID_EDIF_SA_INDEX) { + kfree(entry); + return INVALID_EDIF_SA_INDEX; + } + + INIT_LIST_HEAD(&entry->next); + entry->handle = nport_handle; + entry->fcport = fcport; + entry->sa_pair[0].spi = sa_frame->spi; + entry->sa_pair[0].sa_index = sa_index; + entry->sa_pair[1].spi = 0; + entry->sa_pair[1].sa_index = INVALID_EDIF_SA_INDEX; + spin_lock_irqsave(&ha->sadb_lock, flags); + list_add_tail(&entry->next, sa_list); + spin_unlock_irqrestore(&ha->sadb_lock, flags); + ql_dbg(ql_dbg_edif, vha, 0x3063, +"%s: Created new sadb entry for nport_handle 0x%x, spi 0x%x, returning sa_index %d\n", + __func__, nport_handle, sa_frame->spi, sa_index); + return sa_index; + } + + spin_lock_irqsave(&ha->sadb_lock, flags); + + /* see if we already have an entry for this spi */ + for (slot = 0; slot < 2; slot++) { + if (entry->sa_pair[slot].sa_index == INVALID_EDIF_SA_INDEX) { + free_slot = slot; + } else { + if (entry->sa_pair[slot].spi == sa_frame->spi) { + spin_unlock_irqrestore(&ha->sadb_lock, flags); + ql_dbg(ql_dbg_edif, vha, 0x3063, +"%s: sadb slot %d entry for lid 0x%x, spi 0x%x found, sa_index %d\n", + __func__, slot, entry->handle, + sa_frame->spi, entry->sa_pair[slot].sa_index); + return entry->sa_pair[slot].sa_index; + } + } + } + spin_unlock_irqrestore(&ha->sadb_lock, flags); + + /* both slots are used */ + if (free_slot == -1) { + ql_dbg(ql_dbg_edif, vha, 0x3063, +"%s: WARNING: No free slots in sadb for nport_handle 0x%x, spi: 0x%x\n", + __func__, entry->handle, sa_frame->spi); + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: Slot 0 spi: 0x%x sa_index: %d\n", + __func__, entry->sa_pair[0].spi, + entry->sa_pair[0].sa_index); + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: Slot 1 spi: 0x%x sa_index: %d\n", + __func__, entry->sa_pair[1].spi, + entry->sa_pair[1].sa_index); + + return INVALID_EDIF_SA_INDEX; + } + + /* there is at least one free slot, use it */ + sa_index = qla_edif_get_sa_index_from_freepool(fcport, dir); + if (sa_index == INVALID_EDIF_SA_INDEX) { + ql_dbg(ql_dbg_edif, fcport->vha, 0x3063, + "%s: empty freepool!!\n", __func__); + return INVALID_EDIF_SA_INDEX; + } + + spin_lock_irqsave(&ha->sadb_lock, flags); + entry->sa_pair[free_slot].spi = sa_frame->spi; + entry->sa_pair[free_slot].sa_index = sa_index; + spin_unlock_irqrestore(&ha->sadb_lock, flags); + ql_dbg(ql_dbg_edif, fcport->vha, 0x3063, +"%s: sadb slot %d entry for nport_handle 0x%x, spi 0x%x added, returning sa_index %d\n", + __func__, free_slot, entry->handle, sa_frame->spi, + sa_index); + + return sa_index; +} + +/* release any sadb entries -- only done at teardown */ +void qla_edif_sadb_release(struct qla_hw_data *ha) +{ + struct list_head *pos; + struct list_head *tmp; + struct edif_sa_index_entry *entry; + + list_for_each_safe(pos, tmp, &ha->sadb_rx_index_list) { + entry = list_entry(pos, struct edif_sa_index_entry, next); + list_del(&entry->next); + kfree(entry); + } + + list_for_each_safe(pos, tmp, &ha->sadb_tx_index_list) { + entry = list_entry(pos, struct edif_sa_index_entry, next); + list_del(&entry->next); + kfree(entry); + } +} + +/************************** + * sadb freepool functions + **************************/ + +/* build the rx and tx sa_index free pools -- only done at fcport init */ +int qla_edif_sadb_build_free_pool(struct qla_hw_data *ha) +{ + ha->edif_tx_sa_id_map = + kcalloc(BITS_TO_LONGS(EDIF_NUM_SA_INDEX), sizeof(long), GFP_KERNEL); + + if (!ha->edif_tx_sa_id_map) { + ql_log_pci(ql_log_fatal, ha->pdev, 0x0009, + "Unable to allocate memory for sadb tx.\n"); + return -ENOMEM; + } + + ha->edif_rx_sa_id_map = + kcalloc(BITS_TO_LONGS(EDIF_NUM_SA_INDEX), sizeof(long), GFP_KERNEL); + if (!ha->edif_rx_sa_id_map) { + kfree(ha->edif_tx_sa_id_map); + ha->edif_tx_sa_id_map = NULL; + ql_log_pci(ql_log_fatal, ha->pdev, 0x0009, + "Unable to allocate memory for sadb rx.\n"); + return -ENOMEM; + } + return 0; +} + +/* release the free pool - only done during fcport teardown */ +void qla_edif_sadb_release_free_pool(struct qla_hw_data *ha) +{ + kfree(ha->edif_tx_sa_id_map); + ha->edif_tx_sa_id_map = NULL; + kfree(ha->edif_rx_sa_id_map); + ha->edif_rx_sa_id_map = NULL; +} + +static void __chk_edif_rx_sa_delete_pending(scsi_qla_host_t *vha, + fc_port_t *fcport, uint32_t handle, uint16_t sa_index) +{ + struct edif_list_entry *edif_entry; + struct edif_sa_ctl *sa_ctl; + uint16_t delete_sa_index = INVALID_EDIF_SA_INDEX; + unsigned long flags = 0; + uint16_t nport_handle = fcport->loop_id; + uint16_t cached_nport_handle; + + spin_lock_irqsave(&fcport->edif.indx_list_lock, flags); + edif_entry = qla_edif_list_find_sa_index(fcport, nport_handle); + if (!edif_entry) { + spin_unlock_irqrestore(&fcport->edif.indx_list_lock, flags); + return; /* no pending delete for this handle */ + } + + /* + * check for no pending delete for this index or iocb does not + * match rx sa_index + */ + if (edif_entry->delete_sa_index == INVALID_EDIF_SA_INDEX || + edif_entry->update_sa_index != sa_index) { + spin_unlock_irqrestore(&fcport->edif.indx_list_lock, flags); + return; + } + + /* + * wait until we have seen at least EDIF_DELAY_COUNT transfers before + * queueing RX delete + */ + if (edif_entry->count++ < EDIF_RX_DELETE_FILTER_COUNT) { + spin_unlock_irqrestore(&fcport->edif.indx_list_lock, flags); + return; + } + + ql_dbg(ql_dbg_edif, vha, 0x5033, +"%s: invalidating delete_sa_index, update_sa_index: 0x%x sa_index: 0x%x, delete_sa_index: 0x%x\n", + __func__, edif_entry->update_sa_index, sa_index, + edif_entry->delete_sa_index); + + delete_sa_index = edif_entry->delete_sa_index; + edif_entry->delete_sa_index = INVALID_EDIF_SA_INDEX; + cached_nport_handle = edif_entry->handle; + spin_unlock_irqrestore(&fcport->edif.indx_list_lock, flags); + + /* sanity check on the nport handle */ + if (nport_handle != cached_nport_handle) { + ql_dbg(ql_dbg_edif, vha, 0x3063, +"%s: POST SA DELETE nport_handle mismatch: lid: 0x%x, edif_entry nph: 0x%x\n", + __func__, nport_handle, cached_nport_handle); + } + + /* find the sa_ctl for the delete and schedule the delete */ + sa_ctl = qla_edif_find_sa_ctl_by_index(fcport, delete_sa_index, 0); + if (sa_ctl) { + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: POST SA DELETE sa_ctl: %p, index recvd %d\n", + __func__, sa_ctl, sa_index); + ql_dbg(ql_dbg_edif, vha, 0x3063, + "delete index %d, update index: %d, nport handle: 0x%x, handle: 0x%x\n", + delete_sa_index, + edif_entry->update_sa_index, nport_handle, handle); + + sa_ctl->flags = EDIF_SA_CTL_FLG_DEL; + set_bit(EDIF_SA_CTL_REPL, &sa_ctl->state); + qla_post_sa_replace_work(fcport->vha, fcport, + nport_handle, sa_ctl); + } else { + ql_dbg(ql_dbg_edif, vha, 0x3063, + "%s: POST SA DELETE sa_ctl not found for delete_sa_index: %d\n", + __func__, delete_sa_index); + } +} + +void qla_chk_edif_rx_sa_delete_pending(scsi_qla_host_t *vha, + srb_t *sp, struct sts_entry_24xx *sts24) +{ + fc_port_t *fcport = sp->fcport; + /* sa_index used by this iocb */ + struct scsi_cmnd *cmd = GET_CMD_SP(sp); + uint32_t handle; + + handle = (uint32_t)LSW(sts24->handle); + + /* find out if this status iosb is for a scsi read */ + if (cmd->sc_data_direction != DMA_FROM_DEVICE) + return; + + return __chk_edif_rx_sa_delete_pending(vha, fcport, handle, + le16_to_cpu(sts24->edif_sa_index)); +} + +void qlt_chk_edif_rx_sa_delete_pending(scsi_qla_host_t *vha, fc_port_t *fcport, + struct ctio7_from_24xx *pkt) +{ + __chk_edif_rx_sa_delete_pending(vha, fcport, + pkt->handle, le16_to_cpu(pkt->edif_sa_index)); +} + static void qla_parse_auth_els_ctl(struct srb *sp) { struct qla_els_pt_arg *a = &sp->u.bsg_cmd.u.els_arg; diff --git a/drivers/scsi/qla2xxx/qla_edif.h b/drivers/scsi/qla2xxx/qla_edif.h index 12607218df17..799446ea9fbc 100644 --- a/drivers/scsi/qla2xxx/qla_edif.h +++ b/drivers/scsi/qla2xxx/qla_edif.h @@ -8,6 +8,27 @@ struct qla_scsi_host; +#define EDIF_MAX_INDEX 2048 +struct edif_sa_ctl { + struct list_head next; + uint16_t del_index; + uint16_t index; + uint16_t slot; + uint16_t flags; +#define EDIF_SA_CTL_FLG_REPL BIT_0 +#define EDIF_SA_CTL_FLG_DEL BIT_1 +#define EDIF_SA_CTL_FLG_CLEANUP_DEL BIT_4 + // Invalidate Index bit and mirrors QLA_SA_UPDATE_FLAGS_DELETE + unsigned long state; +#define EDIF_SA_CTL_USED 1 /* Active Sa update */ +#define EDIF_SA_CTL_PEND 2 /* Waiting for slot */ +#define EDIF_SA_CTL_REPL 3 /* Active Replace and Delete */ +#define EDIF_SA_CTL_DEL 4 /* Delete Pending */ + struct fc_port *fcport; + struct bsg_job *bsg_job; + struct qla_sa_update_frame sa_frame; +}; + enum enode_flags_t { ENODE_ACTIVE = 0x1, // means that app has started }; @@ -29,6 +50,46 @@ struct edif_dbell { struct completion dbell; /* doorbell ring */ }; +#define SA_UPDATE_IOCB_TYPE 0x71 /* Security Association Update IOCB entry */ +struct sa_update_28xx { + uint8_t entry_type; /* Entry type. */ + uint8_t entry_count; /* Entry count. */ + uint8_t sys_define; /* System Defined. */ + uint8_t entry_status; /* Entry Status. */ + + uint32_t handle; /* IOCB System handle. */ + + union { + __le16 nport_handle; /* in: N_PORT handle. */ + __le16 comp_sts; /* out: completion status */ +#define CS_PORT_EDIF_SUPP_NOT_RDY 0x64 +#define CS_PORT_EDIF_INV_REQ 0x66 + } u; + uint8_t vp_index; + uint8_t reserved_1; + uint8_t port_id[3]; + uint8_t flags; +#define SA_FLAG_INVALIDATE BIT_0 +#define SA_FLAG_TX BIT_1 // 1=tx, 0=rx + + uint8_t sa_key[32]; /* 256 bit key */ + __le32 salt; + __le32 spi; + uint8_t sa_control; +#define SA_CNTL_ENC_FCSP (1 << 3) +#define SA_CNTL_ENC_OPD (2 << 3) +#define SA_CNTL_ENC_MSK (3 << 3) // mask bits 4,3 +#define SA_CNTL_AES_GMAC (1 << 2) +#define SA_CNTL_KEY256 (2 << 0) +#define SA_CNTL_KEY128 0 + + uint8_t reserved_2; + __le16 sa_index; // reserve: bit 11-15 + __le16 old_sa_info; + __le16 new_sa_info; +}; + +#define NUM_ENTRIES 256 #define MAX_PAYLOAD 1024 #define PUR_GET 1 diff --git a/drivers/scsi/qla2xxx/qla_fw.h b/drivers/scsi/qla2xxx/qla_fw.h index 49df418030e4..c067cd202dc4 100644 --- a/drivers/scsi/qla2xxx/qla_fw.h +++ b/drivers/scsi/qla2xxx/qla_fw.h @@ -611,6 +611,7 @@ struct sts_entry_24xx { union { __le16 reserved_1; __le16 nvme_rsp_pyld_len; + __le16 edif_sa_index; /* edif sa_index used for initiator read data */ }; __le16 state_flags; /* State flags. */ diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index a4cb8092e97e..f4a98d92c4b3 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -130,6 +130,13 @@ void qla24xx_free_purex_item(struct purex_item *item); extern bool qla24xx_risc_firmware_invalid(uint32_t *); void qla_init_iocb_limit(scsi_qla_host_t *); +void qla_edif_sadb_release(struct qla_hw_data *ha); +int qla_edif_sadb_build_free_pool(struct qla_hw_data *ha); +void qla_edif_sadb_release_free_pool(struct qla_hw_data *ha); +void qla_chk_edif_rx_sa_delete_pending(scsi_qla_host_t *vha, + srb_t *sp, struct sts_entry_24xx *sts24); +void qlt_chk_edif_rx_sa_delete_pending(scsi_qla_host_t *vha, fc_port_t *fcport, + struct ctio7_from_24xx *ctio); int qla_edif_process_els(scsi_qla_host_t *vha, struct bsg_job *bsgjob); const char *sc_to_str(uint16_t cmd); @@ -240,6 +247,8 @@ void qla24xx_process_purex_rdp(struct scsi_qla_host *vha, struct purex_item *pkt); void qla_pci_set_eeh_busy(struct scsi_qla_host *); void qla_schedule_eeh_work(struct scsi_qla_host *); +struct edif_sa_ctl *qla_edif_find_sa_ctl_by_index(fc_port_t *fcport, + int index, int dir); /* * Global Functions in qla_mid.c source file. @@ -315,6 +324,8 @@ extern int qla24xx_walk_and_build_prot_sglist(struct qla_hw_data *, srb_t *, struct dsd64 *, uint16_t, struct qla_tgt_cmd *); extern int qla24xx_get_one_block_sg(uint32_t, struct qla2_sgx *, uint32_t *); extern int qla24xx_configure_prot_mode(srb_t *, uint16_t *); +extern int qla24xx_issue_sa_replace_iocb(scsi_qla_host_t *vha, + struct qla_work_evt *e); /* * Global Function Prototypes in qla_mbx.c source file. @@ -888,6 +899,9 @@ extern int qla2x00_issue_iocb_timeout(scsi_qla_host_t *, void *, dma_addr_t, size_t, uint32_t); extern int qla2x00_get_idma_speed(scsi_qla_host_t *, uint16_t, uint16_t *, uint16_t *); +extern int qla24xx_sadb_update(struct bsg_job *bsg_job); +extern int qla_post_sa_replace_work(struct scsi_qla_host *vha, + fc_port_t *fcport, uint16_t nport_handle, struct edif_sa_ctl *sa_ctl); /* 83xx related functions */ void qla83xx_fw_dump(scsi_qla_host_t *vha); @@ -960,12 +974,19 @@ extern void qla_nvme_abort_process_comp_status /* nvme.c */ void qla_nvme_unregister_remote_port(struct fc_port *fcport); + +/* qla_edif.c */ fc_port_t *qla2x00_find_fcport_by_pid(scsi_qla_host_t *vha, port_id_t *id); void qla_edb_stop(scsi_qla_host_t *vha); int32_t qla_edif_app_mgmt(struct bsg_job *bsg_job); void qla_enode_init(scsi_qla_host_t *vha); void qla_enode_stop(scsi_qla_host_t *vha); +void qla_edif_flush_sa_ctl_lists(fc_port_t *fcport); +void qla24xx_sa_update_iocb(srb_t *sp, struct sa_update_28xx *sa_update_iocb); +void qla24xx_sa_replace_iocb(srb_t *sp, struct sa_update_28xx *sa_update_iocb); void qla24xx_auth_els(scsi_qla_host_t *vha, void **pkt, struct rsp_que **rsp); +void qla28xx_sa_update_iocb_entry(scsi_qla_host_t *vha, struct req_que *req, + struct sa_update_28xx *pkt); void qla_handle_els_plogi_done(scsi_qla_host_t *vha, struct event_arg *ea); #define QLA2XX_HW_ERROR BIT_0 diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 0de250570e39..97da4ebadc33 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -5073,6 +5073,17 @@ qla2x00_alloc_fcport(scsi_qla_host_t *vha, gfp_t flags) INIT_LIST_HEAD(&fcport->sess_cmd_list); spin_lock_init(&fcport->sess_cmd_lock); + spin_lock_init(&fcport->edif.sa_list_lock); + INIT_LIST_HEAD(&fcport->edif.tx_sa_list); + INIT_LIST_HEAD(&fcport->edif.rx_sa_list); + + if (vha->e_dbell.db_flags == EDB_ACTIVE) + fcport->edif.app_started = 1; + + // edif rx delete data structure + spin_lock_init(&fcport->edif.indx_list_lock); + INIT_LIST_HEAD(&fcport->edif.edif_indx_list); + return fcport; } diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index 6f996fb5e8f9..168e7832bdfd 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -3889,6 +3889,12 @@ qla2x00_start_sp(srb_t *sp) case SRB_PRLO_CMD: qla24xx_prlo_iocb(sp, pkt); break; + case SRB_SA_UPDATE: + qla24xx_sa_update_iocb(sp, pkt); + break; + case SRB_SA_REPLACE: + qla24xx_sa_replace_iocb(sp, pkt); + break; default: break; } diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index ea7635af03a8..dcbee5cf4306 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -3174,6 +3174,8 @@ qla2x00_status_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, void *pkt) } /* Fast path completion. */ + qla_chk_edif_rx_sa_delete_pending(vha, sp, sts24); + if (comp_status == CS_COMPLETE && scsi_status == 0) { qla2x00_process_completed_request(vha, req, handle); @@ -3568,6 +3570,9 @@ qla2x00_error_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, sts_entry_t *pkt) } break; + case SA_UPDATE_IOCB_TYPE: + return 1; // let sa_update_iocb_entry cleanup everything + case ABTS_RESP_24XX: case CTIO_TYPE7: case CTIO_CRC2: @@ -3858,6 +3863,11 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha, purex_entry->els_frame_payload[3]); } break; + case SA_UPDATE_IOCB_TYPE: + qla28xx_sa_update_iocb_entry(vha, rsp->req, + (struct sa_update_28xx *)pkt); + break; + default: /* Type Not Supported. */ ql_dbg(ql_dbg_async, vha, 0x5042, diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 6be06b994c43..51be079fadd7 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -2835,6 +2835,20 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) spin_lock_init(&ha->tgt.sess_lock); spin_lock_init(&ha->tgt.atio_lock); + // edif sadb + spin_lock_init(&ha->sadb_lock); + INIT_LIST_HEAD(&ha->sadb_tx_index_list); + INIT_LIST_HEAD(&ha->sadb_rx_index_list); + + // edif sa_index free pool + spin_lock_init(&ha->sadb_fp_lock); + + // build the sadb sa_index free pool + if (qla_edif_sadb_build_free_pool(ha)) { + kfree(ha); + goto disable_device; + } + atomic_set(&ha->nvme_active_aen_cnt, 0); /* Clear our data area */ @@ -3868,6 +3882,9 @@ qla2x00_free_device(scsi_qla_host_t *vha) qla82xx_md_free(vha); + qla_edif_sadb_release_free_pool(ha); + qla_edif_sadb_release(ha); + qla2x00_free_queues(ha); } @@ -5375,6 +5392,9 @@ qla2x00_do_work(struct scsi_qla_host *vha) qla24xx_els_dcmd2_iocb(vha, ELS_DCMD_PLOGI, e->u.fcport.fcport, false); break; + case QLA_EVT_SA_REPLACE: + qla24xx_issue_sa_replace_iocb(vha, e); + break; } if (rc == EAGAIN) { diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h index 01620f3eab39..8a319b78cdf6 100644 --- a/drivers/scsi/qla2xxx/qla_target.h +++ b/drivers/scsi/qla2xxx/qla_target.h @@ -446,7 +446,7 @@ struct ctio7_from_24xx { uint8_t vp_index; uint8_t reserved1[5]; __le32 exchange_address; - __le16 reserved2; + __le16 edif_sa_index; __le16 flags; __le32 residual; __le16 ox_id; From patchwork Mon May 31 07:05:42 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Nilesh Javali X-Patchwork-Id: 450659 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-18.8 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER, INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, SPF_PASS, URIBL_BLOCKED, USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 75D48C47082 for ; Mon, 31 May 2021 07:09:04 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 408D261186 for ; Mon, 31 May 2021 07:09:04 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230070AbhEaHKm (ORCPT ); Mon, 31 May 2021 03:10:42 -0400 Received: from mx0b-0016f401.pphosted.com ([67.231.156.173]:21196 "EHLO mx0b-0016f401.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230169AbhEaHKk (ORCPT ); Mon, 31 May 2021 03:10:40 -0400 Received: from pps.filterd (m0045851.ppops.net [127.0.0.1]) by mx0b-0016f401.pphosted.com (8.16.0.43/8.16.0.43) with SMTP id 14V76FXo026830 for ; Mon, 31 May 2021 00:09:01 -0700 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=marvell.com; h=from : to : cc : subject : date : message-id : in-reply-to : references : mime-version : content-type; s=pfpt0220; bh=F2IzX69By7X3XkFNWVV+FDHRv7cm4f5otIqBU2/4Pvc=; b=is2DsNynmymnW+sQw9dZGw/xsi2ULDLONBwoONtsdf7oWdbYG9MWwLdUC9kvGAOtO7M7 XYEcL7kkaJ2JDabDmwz7X106pRDK26CsOqAYk2dJgMSroWZ6DA2MqRO8Dcwr/V5H7Jcs v8hszSTWk7iqJa2p7NjMljq3zUdcXgVCSo2rAagaX0zIQZM77POL9MUs/Uq+2MjvrYYw DjYe3S46hhfS1xqFyKDQTBFvxm8uyUYUFFJa9JD6kMDWyBmXYiB3bZYBUnZzYNjdSjna o7rxPMlRHLJ8bim/S9LLRd+ZtlVXHlZLQ7xOWA9vNKIItNPOw90ynrtLqK0L/cBZdNpe Kw== Received: from dc5-exch02.marvell.com ([199.233.59.182]) by mx0b-0016f401.pphosted.com with ESMTP id 38vtnj82nm-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-SHA384 bits=256 verify=NOT) for ; Mon, 31 May 2021 00:09:01 -0700 Received: from DC5-EXCH01.marvell.com (10.69.176.38) by DC5-EXCH02.marvell.com (10.69.176.39) with Microsoft SMTP Server (TLS) id 15.0.1497.2; Mon, 31 May 2021 00:08:59 -0700 Received: from maili.marvell.com (10.69.176.80) by DC5-EXCH01.marvell.com (10.69.176.38) with Microsoft SMTP Server id 15.0.1497.2 via Frontend Transport; Mon, 31 May 2021 00:08:58 -0700 Received: from dut1171.mv.qlogic.com (unknown [10.112.88.18]) by maili.marvell.com (Postfix) with ESMTP id E23EF3F703F; Mon, 31 May 2021 00:08:58 -0700 (PDT) Received: from dut1171.mv.qlogic.com (localhost [127.0.0.1]) by dut1171.mv.qlogic.com (8.14.7/8.14.7) with ESMTP id 14V78wP9032161; Mon, 31 May 2021 00:08:58 -0700 Received: (from root@localhost) by dut1171.mv.qlogic.com (8.14.7/8.14.7/Submit) id 14V78wpG032160; Mon, 31 May 2021 00:08:58 -0700 From: Nilesh Javali To: CC: , Subject: [PATCH v2 07/10] qla2xxx: Add detection of secure device Date: Mon, 31 May 2021 00:05:42 -0700 Message-ID: <20210531070545.32072-8-njavali@marvell.com> X-Mailer: git-send-email 2.12.0 In-Reply-To: <20210531070545.32072-1-njavali@marvell.com> References: <20210531070545.32072-1-njavali@marvell.com> MIME-Version: 1.0 X-Proofpoint-GUID: h5SO9ZNbTDRVTv_cZQ2OsM-K9ZNPusLm X-Proofpoint-ORIG-GUID: h5SO9ZNbTDRVTv_cZQ2OsM-K9ZNPusLm X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.391, 18.0.761 definitions=2021-05-31_04:2021-05-31,2021-05-31 signatures=0 Precedence: bulk List-ID: X-Mailing-List: linux-scsi@vger.kernel.org From: Quinn Tran Latest FC adapter from Marvell has the ability to encrypt data in flight (EDIF) feature. This feature require an application (ex: ipsec, etc) to act as an authenticator. At this time, there is no FC switch scan service that indicate a device is secure or non-secure. In order to detect whether the remote port support secured or not, driver must first do a PLOGI with the remote device. On completion of the PLOGI, driver will query FW to see if the device supports secure login. To do that, driver + FW must advertise the security bit via PLOGI's service parameter. The remote device shall respond with the same service parameter bit on whether it supports it or not. Signed-off-by: Larry Wisneski Signed-off-by: Duane Grigsby Signed-off-by: Rick Hicksted Jr Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Reviewed-by: Himanshu Madhani --- drivers/scsi/qla2xxx/qla_def.h | 5 +- drivers/scsi/qla2xxx/qla_edif.c | 31 +++++++ drivers/scsi/qla2xxx/qla_fw.h | 8 +- drivers/scsi/qla2xxx/qla_gbl.h | 3 + drivers/scsi/qla2xxx/qla_gs.c | 4 + drivers/scsi/qla2xxx/qla_init.c | 142 +++++++++++++++++++++++++----- drivers/scsi/qla2xxx/qla_iocb.c | 17 +++- drivers/scsi/qla2xxx/qla_isr.c | 4 + drivers/scsi/qla2xxx/qla_mbx.c | 6 ++ drivers/scsi/qla2xxx/qla_mid.c | 7 +- drivers/scsi/qla2xxx/qla_os.c | 20 ++++- drivers/scsi/qla2xxx/qla_target.c | 61 ++++++++++++- drivers/scsi/qla2xxx/qla_target.h | 1 + 13 files changed, 280 insertions(+), 29 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 164b87fd66ba..669a2399e67f 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -492,6 +492,7 @@ struct srb_iocb { #define SRB_LOGIN_SKIP_PRLI BIT_2 #define SRB_LOGIN_NVME_PRLI BIT_3 #define SRB_LOGIN_PRLI_ONLY BIT_4 +#define SRB_LOGIN_FCSP BIT_5 uint16_t data[2]; u32 iop[2]; } logio; @@ -2343,6 +2344,7 @@ struct imm_ntfy_from_isp { __le16 nport_handle; uint16_t reserved_2; __le16 flags; +#define NOTIFY24XX_FLAGS_FCSP BIT_5 #define NOTIFY24XX_FLAGS_GLOBAL_TPRLO BIT_1 #define NOTIFY24XX_FLAGS_PUREX_IOCB BIT_0 __le16 srr_rx_id; @@ -2683,7 +2685,8 @@ static const char * const port_dstate_str[] = { "UPD_FCPORT", "LOGIN_COMPLETE", "ADISC", - "DELETE_PEND" + "DELETE_PEND", + "LOGIN_AUTH_PEND", }; /* diff --git a/drivers/scsi/qla2xxx/qla_edif.c b/drivers/scsi/qla2xxx/qla_edif.c index c86d64512702..0fa6a1420c30 100644 --- a/drivers/scsi/qla2xxx/qla_edif.c +++ b/drivers/scsi/qla2xxx/qla_edif.c @@ -2405,6 +2405,26 @@ qla28xx_sa_update_iocb_entry(scsi_qla_host_t *v, struct req_que *req, sp->done(sp, 0); } +/********************************************** + * edif update/delete sa_index list functions * + **********************************************/ + +/* clear the edif_indx_list for this port */ +void qla_edif_list_del(fc_port_t *fcport) +{ + struct edif_list_entry *indx_lst; + struct edif_list_entry *tindx_lst; + struct list_head *indx_list = &fcport->edif.edif_indx_list; + unsigned long flags = 0; + + list_for_each_entry_safe(indx_lst, tindx_lst, indx_list, next) { + spin_lock_irqsave(&fcport->edif.indx_list_lock, flags); + list_del(&indx_lst->next); + spin_unlock_irqrestore(&fcport->edif.indx_list_lock, flags); + kfree(indx_lst); + } +} + /****************** * SADB functions * ******************/ @@ -2844,3 +2864,14 @@ int qla_edif_process_els(scsi_qla_host_t *vha, struct bsg_job *bsg_job) done: return rval; } + +void qla_edif_sess_down(struct scsi_qla_host *vha, struct fc_port *sess) +{ + if (sess->edif.app_sess_online && vha->e_dbell.db_flags & EDB_ACTIVE) { + ql_dbg(ql_dbg_disc, vha, 0xf09c, + "%s: sess %8phN send port_offline event\n", + __func__, sess->port_name); + sess->edif.app_sess_online = 0; + qla2x00_post_aen_work(vha, FCH_EVT_PORT_OFFLINE, sess->d_id.b24); + } +} diff --git a/drivers/scsi/qla2xxx/qla_fw.h b/drivers/scsi/qla2xxx/qla_fw.h index c067cd202dc4..4934b08a8990 100644 --- a/drivers/scsi/qla2xxx/qla_fw.h +++ b/drivers/scsi/qla2xxx/qla_fw.h @@ -82,10 +82,11 @@ struct port_database_24xx { uint8_t port_name[WWN_SIZE]; uint8_t node_name[WWN_SIZE]; - uint8_t reserved_3[4]; + uint8_t reserved_3[2]; + uint16_t nvme_first_burst_size; uint16_t prli_nvme_svc_param_word_0; /* Bits 15-0 of word 0 */ uint16_t prli_nvme_svc_param_word_3; /* Bits 15-0 of word 3 */ - uint16_t nvme_first_burst_size; + uint8_t secure_login; uint8_t reserved_4[14]; }; @@ -897,6 +898,7 @@ struct logio_entry_24xx { #define LCF_FCP2_OVERRIDE BIT_9 /* Set/Reset word 3 of PRLI. */ #define LCF_CLASS_2 BIT_8 /* Enable class 2 during PLOGI. */ #define LCF_FREE_NPORT BIT_7 /* Release NPORT handle after LOGO. */ +#define LCF_COMMON_FEAT BIT_7 /* PLOGI - Set Common Features Field */ #define LCF_EXPL_LOGO BIT_6 /* Perform an explicit LOGO. */ #define LCF_NVME_PRLI BIT_6 /* Perform NVME FC4 PRLI */ #define LCF_SKIP_PRLI BIT_5 /* Skip PRLI after PLOGI. */ @@ -921,6 +923,8 @@ struct logio_entry_24xx { uint8_t rsp_size; /* Response size in 32bit words. */ __le32 io_parameter[11]; /* General I/O parameters. */ +#define LIO_COMM_FEAT_FCSP BIT_21 +#define LIO_COMM_FEAT_CIO BIT_31 #define LSC_SCODE_NOLINK 0x01 #define LSC_SCODE_NOIOCB 0x02 #define LSC_SCODE_NOXCB 0x03 diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index 236eb610b5be..c695f5a58d4d 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -131,6 +131,7 @@ void qla24xx_free_purex_item(struct purex_item *item); extern bool qla24xx_risc_firmware_invalid(uint32_t *); void qla_init_iocb_limit(scsi_qla_host_t *); +void qla_edif_list_del(fc_port_t *fcport); void qla_edif_sadb_release(struct qla_hw_data *ha); int qla_edif_sadb_build_free_pool(struct qla_hw_data *ha); void qla_edif_sadb_release_free_pool(struct qla_hw_data *ha); @@ -138,7 +139,9 @@ void qla_chk_edif_rx_sa_delete_pending(scsi_qla_host_t *vha, srb_t *sp, struct sts_entry_24xx *sts24); void qlt_chk_edif_rx_sa_delete_pending(scsi_qla_host_t *vha, fc_port_t *fcport, struct ctio7_from_24xx *ctio); +void qla2x00_release_all_sadb(struct scsi_qla_host *vha, struct fc_port *fcport); int qla_edif_process_els(scsi_qla_host_t *vha, struct bsg_job *bsgjob); +void qla_edif_sess_down(struct scsi_qla_host *vha, struct fc_port *sess); const char *sc_to_str(uint16_t cmd); /* diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index 5b6e04a91a18..99fb330053ae 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -2826,6 +2826,10 @@ void qla24xx_handle_gpsc_event(scsi_qla_host_t *vha, struct event_arg *ea) if (fcport->disc_state == DSC_DELETE_PEND) return; + /* We will figure-out what happen after AUTH completes */ + if (fcport->disc_state == DSC_LOGIN_AUTH_PEND) + return; + if (ea->sp->gen2 != fcport->login_gen) { /* target side must have changed it. */ ql_dbg(ql_dbg_disc, vha, 0x20d3, diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index bd528c249aa7..7a20b1ddc63f 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -342,10 +342,23 @@ qla2x00_async_login(struct scsi_qla_host *vha, fc_port_t *fcport, qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha) + 2); sp->done = qla2x00_async_login_sp_done; - if (N2N_TOPO(fcport->vha->hw) && fcport_is_bigger(fcport)) + if (N2N_TOPO(fcport->vha->hw) && fcport_is_bigger(fcport)) { lio->u.logio.flags |= SRB_LOGIN_PRLI_ONLY; - else - lio->u.logio.flags |= SRB_LOGIN_COND_PLOGI; + } else { + if (vha->hw->flags.edif_enabled) { + if (fcport->edif.non_secured_login == 0) { + lio->u.logio.flags |= + (SRB_LOGIN_FCSP | SRB_LOGIN_SKIP_PRLI); + ql_dbg(ql_dbg_disc, vha, 0x2072, + "Async-login: w/ FCSP %8phC hdl=%x, loopid=%x portid=%06x\n", + fcport->port_name, sp->handle, + fcport->loop_id, + fcport->d_id.b24); + } + } else { + lio->u.logio.flags |= SRB_LOGIN_COND_PLOGI; + } + } if (NVME_TARGET(vha->hw, fcport)) lio->u.logio.flags |= SRB_LOGIN_SKIP_PRLI; @@ -377,7 +390,7 @@ static void qla2x00_async_logout_sp_done(srb_t *sp, int res) { sp->fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); sp->fcport->login_gen++; - qlt_logo_completion_handler(sp->fcport, res); + qlt_logo_completion_handler(sp->fcport, sp->u.iocb_cmd.u.logio.data[0]); sp->free(sp); } @@ -403,10 +416,10 @@ qla2x00_async_logout(struct scsi_qla_host *vha, fc_port_t *fcport) sp->done = qla2x00_async_logout_sp_done; ql_dbg(ql_dbg_disc, vha, 0x2070, - "Async-logout - hdl=%x loop-id=%x portid=%02x%02x%02x %8phC.\n", + "Async-logout - hdl=%x loop-id=%x portid=%02x%02x%02x %8phC explicit %d.\n", sp->handle, fcport->loop_id, fcport->d_id.b.domain, fcport->d_id.b.area, fcport->d_id.b.al_pa, - fcport->port_name); + fcport->port_name, fcport->explicit_logout); rval = qla2x00_start_sp(sp); if (rval != QLA_SUCCESS) @@ -691,11 +704,11 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha, fcport = ea->fcport; ql_dbg(ql_dbg_disc, vha, 0xffff, - "%s %8phC DS %d LS rc %d %d login %d|%d rscn %d|%d lid %d\n", + "%s %8phC DS %d LS rc %d %d login %d|%d rscn %d|%d lid %d edif %d\n", __func__, fcport->port_name, fcport->disc_state, fcport->fw_login_state, ea->rc, fcport->login_gen, fcport->last_login_gen, - fcport->rscn_gen, fcport->last_rscn_gen, vha->loop_id); + fcport->rscn_gen, fcport->last_rscn_gen, vha->loop_id, fcport->edif.enable); if (fcport->disc_state == DSC_DELETE_PEND) return; @@ -821,6 +834,13 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha, qla2x00_post_async_adisc_work(vha, fcport, data); break; + case DSC_LS_PLOGI_COMP: + if (vha->hw->flags.edif_enabled) { + /* check to see if he support Secure */ + qla24xx_post_gpdb_work(vha, fcport, 0); + break; + } + fallthrough; case DSC_LS_PORT_UNAVAIL: default: if (fcport->loop_id == FC_NO_LOOP_ID) { @@ -1417,6 +1437,57 @@ void __qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea) spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); } +static int qla_chk_secure_login(scsi_qla_host_t *vha, fc_port_t *fcport, + struct port_database_24xx *pd) +{ + int rc = 0; + + if (pd->secure_login) { + ql_dbg(ql_dbg_disc, vha, 0x104d, + "Secure Login established on %8phC\n", + fcport->port_name); + fcport->edif.secured_login = 1; + fcport->edif.non_secured_login = 0; + fcport->flags |= FCF_FCSP_DEVICE; + } else { + ql_dbg(ql_dbg_disc, vha, 0x104d, + "non-Secure Login %8phC", + fcport->port_name); + fcport->edif.secured_login = 0; + fcport->edif.non_secured_login = 1; + } + if (vha->hw->flags.edif_enabled) { + if (fcport->flags & FCF_FCSP_DEVICE) { + qla2x00_set_fcport_disc_state(fcport, DSC_LOGIN_AUTH_PEND); + /* Start edif prli timer & ring doorbell for app */ + fcport->edif.rx_sa_set = 0; + fcport->edif.tx_sa_set = 0; + fcport->edif.rx_sa_pending = 0; + fcport->edif.tx_sa_pending = 0; + + qla2x00_post_aen_work(vha, FCH_EVT_PORT_ONLINE, + fcport->d_id.b24); + + if (vha->e_dbell.db_flags == EDB_ACTIVE) { + ql_dbg(ql_dbg_disc, vha, 0x20ef, + "%s %d %8phC EDIF: post DB_AUTH: AUTH needed\n", + __func__, __LINE__, fcport->port_name); + fcport->edif.app_started = 1; + fcport->edif.app_sess_online = 1; + } + + rc = 1; + } else { + ql_dbg(ql_dbg_disc, vha, 0x2117, + "%s %d %8phC post prli\n", + __func__, __LINE__, fcport->port_name); + qla24xx_post_prli_work(vha, fcport); + rc = 1; + } + } + return rc; +} + static void qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea) { @@ -1459,8 +1530,11 @@ void qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea) case PDS_PRLI_COMPLETE: __qla24xx_parse_gpdb(vha, fcport, pd); break; - case PDS_PLOGI_PENDING: case PDS_PLOGI_COMPLETE: + if (qla_chk_secure_login(vha, fcport, pd)) + return; + fallthrough; + case PDS_PLOGI_PENDING: case PDS_PRLI_PENDING: case PDS_PRLI2_PENDING: /* Set discovery state back to GNL to Relogin attempt */ @@ -2052,26 +2126,38 @@ qla24xx_handle_plogi_done_event(struct scsi_qla_host *vha, struct event_arg *ea) * force a relogin attempt via implicit LOGO, PLOGI, and PRLI * requests. */ - if (NVME_TARGET(vha->hw, ea->fcport)) { - ql_dbg(ql_dbg_disc, vha, 0x2117, - "%s %d %8phC post prli\n", - __func__, __LINE__, ea->fcport->port_name); - qla24xx_post_prli_work(vha, ea->fcport); - } else { - ql_dbg(ql_dbg_disc, vha, 0x20ea, - "%s %d %8phC LoopID 0x%x in use with %06x. post gpdb\n", - __func__, __LINE__, ea->fcport->port_name, - ea->fcport->loop_id, ea->fcport->d_id.b24); - + if (vha->hw->flags.edif_enabled) { set_bit(ea->fcport->loop_id, vha->hw->loop_id_map); spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); ea->fcport->chip_reset = vha->hw->base_qpair->chip_reset; ea->fcport->logout_on_delete = 1; ea->fcport->send_els_logo = 0; - ea->fcport->fw_login_state = DSC_LS_PRLI_COMP; + ea->fcport->fw_login_state = DSC_LS_PLOGI_COMP; spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); qla24xx_post_gpdb_work(vha, ea->fcport, 0); + } else { + if (NVME_TARGET(vha->hw, fcport)) { + ql_dbg(ql_dbg_disc, vha, 0x2117, + "%s %d %8phC post prli\n", + __func__, __LINE__, fcport->port_name); + qla24xx_post_prli_work(vha, fcport); + } else { + ql_dbg(ql_dbg_disc, vha, 0x20ea, + "%s %d %8phC LoopID 0x%x in use with %06x. post gpdb\n", + __func__, __LINE__, fcport->port_name, + fcport->loop_id, fcport->d_id.b24); + + set_bit(fcport->loop_id, vha->hw->loop_id_map); + spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); + fcport->chip_reset = vha->hw->base_qpair->chip_reset; + fcport->logout_on_delete = 1; + fcport->send_els_logo = 0; + fcport->fw_login_state = DSC_LS_PRLI_COMP; + spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + + qla24xx_post_gpdb_work(vha, fcport, 0); + } } break; case MBS_COMMAND_ERROR: @@ -5096,8 +5182,13 @@ qla2x00_free_fcport(fc_port_t *fcport) fcport->ct_desc.ct_sns = NULL; } + + qla_edif_flush_sa_ctl_lists(fcport); list_del(&fcport->list); qla2x00_clear_loop_id(fcport); + + qla_edif_list_del(fcport); + kfree(fcport); } @@ -5216,6 +5307,12 @@ qla2x00_configure_loop(scsi_qla_host_t *vha) "LOOP READY.\n"); ha->flags.fw_init_done = 1; + if (vha->hw->flags.edif_enabled && + vha->e_dbell.db_flags != EDB_ACTIVE) { + /* wake up authentication app to get ready */ + qla2x00_post_aen_work(vha, FCH_EVT_PORT_ONLINE, 0); + } + /* * Process any ATIO queue entries that came in * while we weren't online. @@ -5235,7 +5332,8 @@ qla2x00_configure_loop(scsi_qla_host_t *vha) "%s *** FAILED ***.\n", __func__); } else { ql_dbg(ql_dbg_disc, vha, 0x206b, - "%s: exiting normally.\n", __func__); + "%s: exiting normally. local port wwpn %8phN id %06x)\n", + __func__, vha->port_name, vha->d_id.b24); } /* Restore state if a resync event occurred during processing */ diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index 168e7832bdfd..ba36084d17a9 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -2462,6 +2462,12 @@ qla24xx_login_iocb(srb_t *sp, struct logio_entry_24xx *logio) logio->control_flags |= cpu_to_le16(LCF_COND_PLOGI); if (lio->u.logio.flags & SRB_LOGIN_SKIP_PRLI) logio->control_flags |= cpu_to_le16(LCF_SKIP_PRLI); + if (lio->u.logio.flags & SRB_LOGIN_FCSP) { + logio->control_flags |= + cpu_to_le16(LCF_COMMON_FEAT | LCF_SKIP_PRLI); + logio->io_parameter[0] = + cpu_to_le32(LIO_COMM_FEAT_FCSP | LIO_COMM_FEAT_CIO); + } } logio->nport_handle = cpu_to_le16(sp->fcport->loop_id); logio->port_id[0] = sp->fcport->d_id.b.al_pa; @@ -2802,7 +2808,6 @@ qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb) (uint8_t *)els_iocb, sizeof(*els_iocb)); } else { - els_iocb->control_flags = cpu_to_le16(1 << 13); els_iocb->tx_byte_count = cpu_to_le32(sizeof(struct els_logo_payload)); put_unaligned_le64(elsio->u.els_logo.els_logo_pyld_dma, @@ -3734,6 +3739,16 @@ static void qla2x00_send_notify_ack_iocb(srb_t *sp, nack->u.isp24.srr_reject_code = 0; nack->u.isp24.srr_reject_code_expl = 0; nack->u.isp24.vp_index = ntfy->u.isp24.vp_index; + + if (ntfy->u.isp24.status_subcode == ELS_PLOGI && + (le16_to_cpu(ntfy->u.isp24.flags) & NOTIFY24XX_FLAGS_FCSP) && + sp->vha->hw->flags.edif_enabled) { + ql_dbg(ql_dbg_disc, sp->vha, 0x3074, + "%s PLOGI NACK sent with FC SECURITY bit, hdl=%x, loopid=%x, to pid %06x\n", + sp->name, sp->handle, sp->fcport->loop_id, + sp->fcport->d_id.b24); + nack->u.isp24.flags |= cpu_to_le16(NOTIFY_ACK_FLAGS_FCSP); + } } /* diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index dcbee5cf4306..121adeee88cc 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -2350,6 +2350,10 @@ qla24xx_logio_entry(scsi_qla_host_t *vha, struct req_que *req, if (sp->type != SRB_LOGIN_CMD) goto logio_done; + lio->u.logio.iop[1] = le32_to_cpu(logio->io_parameter[5]); // common features + if (le32_to_cpu(logio->io_parameter[5]) & LIO_COMM_FEAT_FCSP) + fcport->flags |= FCF_FCSP_DEVICE; + iop[0] = le32_to_cpu(logio->io_parameter[0]); if (iop[0] & BIT_4) { fcport->port_type = FCT_TARGET; diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 0bcd8afdc0ff..f4b9fa9d8078 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -6588,6 +6588,12 @@ int __qla24xx_parse_gpdb(struct scsi_qla_host *vha, fc_port_t *fcport, fcport->d_id.b.al_pa = pd->port_id[2]; fcport->d_id.b.rsvd_1 = 0; + ql_dbg(ql_dbg_disc, vha, 0x2062, + "%8phC SVC Param w3 %02x%02x", + fcport->port_name, + pd->prli_svc_param_word_3[1], + pd->prli_svc_param_word_3[0]); + if (NVME_TARGET(vha->hw, fcport)) { fcport->port_type = FCT_NVME; if ((pd->prli_svc_param_word_3[0] & BIT_5) == 0) diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c index c7caf322f445..432fbba47922 100644 --- a/drivers/scsi/qla2xxx/qla_mid.c +++ b/drivers/scsi/qla2xxx/qla_mid.c @@ -158,6 +158,10 @@ qla24xx_disable_vp(scsi_qla_host_t *vha) int ret = QLA_SUCCESS; fc_port_t *fcport; + if (vha->hw->flags.edif_enabled) + // delete sessions and flush sa_indexes + qla2x00_wait_for_sess_deletion(vha); + if (vha->hw->flags.fw_started) ret = qla24xx_control_vp(vha, VCE_COMMAND_DISABLE_VPS_LOGO_ALL); @@ -166,7 +170,8 @@ qla24xx_disable_vp(scsi_qla_host_t *vha) list_for_each_entry(fcport, &vha->vp_fcports, list) fcport->logout_on_delete = 0; - qla2x00_mark_all_devices_lost(vha); + if (!vha->hw->flags.edif_enabled) + qla2x00_wait_for_sess_deletion(vha); /* Remove port id from vp target map */ spin_lock_irqsave(&vha->hw->hardware_lock, flags); diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 51be079fadd7..0b379ac179fa 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1119,13 +1119,28 @@ static inline int test_fcport_count(scsi_qla_host_t *vha) { struct qla_hw_data *ha = vha->hw; unsigned long flags; - int res; + int res; // 0 = sleep, x=wake spin_lock_irqsave(&ha->tgt.sess_lock, flags); ql_dbg(ql_dbg_init, vha, 0x00ec, "tgt %p, fcport_count=%d\n", vha, vha->fcport_count); res = (vha->fcport_count == 0); + if (res) { + struct fc_port *fcport; + + list_for_each_entry(fcport, &vha->vp_fcports, list) { + if (fcport->deleted != QLA_SESS_DELETED) { + /* session(s) may not be fully logged in + * (ie fcport_count=0), but session + * deletion thread(s) may be inflight. + */ + + res = 0; + break; + } + } + } spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); return res; @@ -3937,6 +3952,8 @@ void qla2x00_mark_device_lost(scsi_qla_host_t *vha, fc_port_t *fcport, qla2x00_set_fcport_state(fcport, FCS_DEVICE_LOST); qla2x00_schedule_rport_del(vha, fcport); } + + qla_edif_sess_down(vha, fcport); /* * We may need to retry the login, so don't change the state of the * port but do the retries. @@ -5444,6 +5461,7 @@ void qla2x00_relogin(struct scsi_qla_host *vha) if (atomic_read(&fcport->state) != FCS_ONLINE && fcport->login_retry) { if (fcport->scan_state != QLA_FCPORT_FOUND || + fcport->disc_state == DSC_LOGIN_AUTH_PEND || fcport->disc_state == DSC_LOGIN_COMPLETE) continue; diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 365e64ebef8b..faf446f0fe8c 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -576,6 +576,16 @@ static void qla2x00_async_nack_sp_done(srb_t *sp, int res) sp->fcport->logout_on_delete = 1; sp->fcport->plogi_nack_done_deadline = jiffies + HZ; sp->fcport->send_els_logo = 0; + + if (sp->fcport->flags & FCF_FCSP_DEVICE) { + ql_dbg(ql_dbg_edif, vha, 0x20ef, + "%s %8phC edif: PLOGI- AUTH WAIT\n", __func__, + sp->fcport->port_name); + qla2x00_set_fcport_disc_state(sp->fcport, + DSC_LOGIN_AUTH_PEND); + qla2x00_post_aen_work(vha, FCH_EVT_PORT_ONLINE, + sp->fcport->d_id.b24); + } break; case SRB_NACK_PRLI: @@ -623,6 +633,10 @@ int qla24xx_async_notify_ack(scsi_qla_host_t *vha, fc_port_t *fcport, case SRB_NACK_PLOGI: fcport->fw_login_state = DSC_LS_PLOGI_PEND; c = "PLOGI"; + if (vha->hw->flags.edif_enabled && + (le16_to_cpu(ntfy->u.isp24.flags) & NOTIFY24XX_FLAGS_FCSP)) { + fcport->flags |= FCF_FCSP_DEVICE; + } break; case SRB_NACK_PRLI: fcport->fw_login_state = DSC_LS_PRLI_PEND; @@ -692,7 +706,12 @@ void qla24xx_do_nack_work(struct scsi_qla_host *vha, struct qla_work_evt *e) void qla24xx_delete_sess_fn(struct work_struct *work) { fc_port_t *fcport = container_of(work, struct fc_port, del_work); - struct qla_hw_data *ha = fcport->vha->hw; + struct qla_hw_data *ha = NULL; + + if (!fcport || !fcport->vha || !fcport->vha->hw) + return; + + ha = fcport->vha->hw; if (fcport->se_sess) { ha->tgt.tgt_ops->shutdown_sess(fcport); @@ -964,6 +983,19 @@ void qlt_free_session_done(struct work_struct *work) sess->send_els_logo); if (!IS_SW_RESV_ADDR(sess->d_id)) { + if (ha->flags.edif_enabled && + (!own || own->iocb.u.isp24.status_subcode == ELS_PLOGI)) { + if (!ha->flags.host_shutting_down) { + ql_dbg(ql_dbg_edif, vha, 0x911e, + "%s wwpn %8phC calling qla2x00_release_all_sadb\n", + __func__, sess->port_name); + qla2x00_release_all_sadb(vha, sess); + } else { + ql_dbg(ql_dbg_edif, vha, 0x911e, + "%s bypassing release_all_sadb\n", + __func__); + } + } qla2x00_mark_device_lost(vha, sess, 0); if (sess->send_els_logo) { @@ -971,6 +1003,7 @@ void qlt_free_session_done(struct work_struct *work) logo.id = sess->d_id; logo.cmd_count = 0; + INIT_LIST_HEAD(&logo.list); if (!own) qlt_send_first_logo(vha, &logo); sess->send_els_logo = 0; @@ -981,6 +1014,7 @@ void qlt_free_session_done(struct work_struct *work) if (!own || (own->iocb.u.isp24.status_subcode == ELS_PLOGI)) { + sess->logout_completed = 0; rc = qla2x00_post_async_logout_work(vha, sess, NULL); if (rc != QLA_SUCCESS) @@ -1717,6 +1751,12 @@ static void qlt_send_notify_ack(struct qla_qpair *qpair, nack->u.isp24.srr_reject_code_expl = srr_explan; nack->u.isp24.vp_index = ntfy->u.isp24.vp_index; + // TODO qualify this with EDIF enable + if (ntfy->u.isp24.status_subcode == ELS_PLOGI && + (le16_to_cpu(ntfy->u.isp24.flags) & NOTIFY24XX_FLAGS_FCSP)) { + nack->u.isp24.flags |= cpu_to_le16(NOTIFY_ACK_FLAGS_FCSP); + } + ql_dbg(ql_dbg_tgt, vha, 0xe005, "qla_target(%d): Sending 24xx Notify Ack %d\n", vha->vp_idx, nack->u.isp24.status); @@ -4724,6 +4764,15 @@ static int qlt_handle_login(struct scsi_qla_host *vha, goto out; } + if (vha->hw->flags.edif_enabled && + vha->e_dbell.db_flags != EDB_ACTIVE) { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d Term INOT due to app not available lid=%d, NportID %06X ", + __func__, __LINE__, loop_id, port_id.b24); + qlt_send_term_imm_notif(vha, iocb, 1); + goto out; + } + pla = qlt_plogi_ack_find_add(vha, &port_id, iocb); if (!pla) { ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0xffff, @@ -4789,6 +4838,16 @@ static int qlt_handle_login(struct scsi_qla_host *vha, qlt_plogi_ack_link(vha, pla, sess, QLT_PLOGI_LINK_SAME_WWN); sess->d_id = port_id; sess->login_gen++; + sess->loop_id = loop_id; + + if (iocb->u.isp24.status_subcode == ELS_PLOGI) { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %8phC - send port online\n", + __func__, sess->port_name); + + qla2x00_post_aen_work(vha, FCH_EVT_PORT_ONLINE, + sess->d_id.b24); + } if (iocb->u.isp24.status_subcode == ELS_PRLI) { sess->fw_login_state = DSC_LS_PRLI_PEND; diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h index 8a319b78cdf6..b910f8f09353 100644 --- a/drivers/scsi/qla2xxx/qla_target.h +++ b/drivers/scsi/qla2xxx/qla_target.h @@ -176,6 +176,7 @@ struct nack_to_isp { uint8_t reserved[2]; __le16 ox_id; } __packed; +#define NOTIFY_ACK_FLAGS_FCSP BIT_5 #define NOTIFY_ACK_FLAGS_TERMINATE BIT_3 #define NOTIFY_ACK_SRR_FLAGS_ACCEPT 0 #define NOTIFY_ACK_SRR_FLAGS_REJECT 1 From patchwork Mon May 31 07:05:44 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Nilesh Javali X-Patchwork-Id: 450658 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-18.8 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER, INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, SPF_PASS, URIBL_BLOCKED, USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 4AD13C4708F for ; Mon, 31 May 2021 07:09:53 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 22D51611CA for ; Mon, 31 May 2021 07:09:53 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230143AbhEaHLb (ORCPT ); Mon, 31 May 2021 03:11:31 -0400 Received: from mx0b-0016f401.pphosted.com ([67.231.156.173]:54758 "EHLO mx0b-0016f401.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230107AbhEaHL3 (ORCPT ); Mon, 31 May 2021 03:11:29 -0400 Received: from pps.filterd (m0045851.ppops.net [127.0.0.1]) by mx0b-0016f401.pphosted.com (8.16.0.43/8.16.0.43) with SMTP id 14V767Bn026053 for ; Mon, 31 May 2021 00:09:49 -0700 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=marvell.com; h=from : to : cc : subject : date : message-id : in-reply-to : references : mime-version : content-type; s=pfpt0220; bh=PqdWKY4vdpgZkeaRNMOXRzWC8lb8dw3aWW73po28P6M=; b=e15SLHnEpkHSteOLPSeN06edgPKBTNa/sfh4Dftyaxahj2JAcInbQOtDvWpXA2kpLl9F U3L3bdSZGOQrohkIQvUzxvjpuXR+CgJItvOjA3d1KpYfP7T4hXcQntbeST1ipAvHkL9L DggzL6bNVAkrCgDi2kFIeMja5KWDVh/CBmU34CLPQbPqymOd8akgdeaJ6l1+3JYDsGQN +iSZE4uoiIugB3JWXXed04YcRptegxDVGeFl4end3Th0ruidLwyREO0LROk8jUHfI9F+ AcrQKgj0DFt/Hb0AmhMUlrm7/keDHrMCdumVcmK2vp4eFo3HFmD1GdPz1EGdRXhs2VYG Iw== Received: from dc5-exch01.marvell.com ([199.233.59.181]) by mx0b-0016f401.pphosted.com with ESMTP id 38vtnj82qt-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-SHA384 bits=256 verify=NOT) for ; Mon, 31 May 2021 00:09:49 -0700 Received: from DC5-EXCH01.marvell.com (10.69.176.38) by DC5-EXCH01.marvell.com (10.69.176.38) with Microsoft SMTP Server (TLS) id 15.0.1497.2; Mon, 31 May 2021 00:09:47 -0700 Received: from maili.marvell.com (10.69.176.80) by DC5-EXCH01.marvell.com (10.69.176.38) with Microsoft SMTP Server id 15.0.1497.2 via Frontend Transport; Mon, 31 May 2021 00:09:47 -0700 Received: from dut1171.mv.qlogic.com (unknown [10.112.88.18]) by maili.marvell.com (Postfix) with ESMTP id 388883F703F; Mon, 31 May 2021 00:09:47 -0700 (PDT) Received: from dut1171.mv.qlogic.com (localhost [127.0.0.1]) by dut1171.mv.qlogic.com (8.14.7/8.14.7) with ESMTP id 14V79lhv032177; Mon, 31 May 2021 00:09:47 -0700 Received: (from root@localhost) by dut1171.mv.qlogic.com (8.14.7/8.14.7/Submit) id 14V79lML032168; Mon, 31 May 2021 00:09:47 -0700 From: Nilesh Javali To: CC: , Subject: [PATCH v2 09/10] qla2xxx: Add encryption to IO path Date: Mon, 31 May 2021 00:05:44 -0700 Message-ID: <20210531070545.32072-10-njavali@marvell.com> X-Mailer: git-send-email 2.12.0 In-Reply-To: <20210531070545.32072-1-njavali@marvell.com> References: <20210531070545.32072-1-njavali@marvell.com> MIME-Version: 1.0 X-Proofpoint-GUID: a1tqgg3qiSJ3zo-hH5K3lvKRyZgl85eG X-Proofpoint-ORIG-GUID: a1tqgg3qiSJ3zo-hH5K3lvKRyZgl85eG X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.391, 18.0.761 definitions=2021-05-31_04:2021-05-31,2021-05-31 signatures=0 Precedence: bulk List-ID: X-Mailing-List: linux-scsi@vger.kernel.org From: Quinn Tran Latest FC adapter from Marvell has the ability to encrypt data in flight (EDIF) feature. This feature require an application (ex: ipsec, etc) to act as an authenticator. After the completion of PLOGI, both sides have authenticated and PRLI completion, encrypted IOs are allow to proceed. This patch adds the follow: - use new FW api to encrypt traffic on the wire. - add driver parameter to enable|disable EDIF feature. modprobe qla2xxx ql2xsecenable=1 Signed-off-by: Larry Wisneski Signed-off-by: Duane Grigsby Signed-off-by: Rick Hicksted Jr Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Reviewed-by: Hannes Reinecke Reviewed-by: Himanshu Madhani --- drivers/scsi/qla2xxx/qla_edif.c | 341 ++++++++++++++++++++++++++---- drivers/scsi/qla2xxx/qla_fw.h | 3 + drivers/scsi/qla2xxx/qla_gbl.h | 4 + drivers/scsi/qla2xxx/qla_gs.c | 2 +- drivers/scsi/qla2xxx/qla_init.c | 25 +-- drivers/scsi/qla2xxx/qla_iocb.c | 5 +- drivers/scsi/qla2xxx/qla_mbx.c | 28 ++- drivers/scsi/qla2xxx/qla_nvme.c | 4 + drivers/scsi/qla2xxx/qla_os.c | 9 +- drivers/scsi/qla2xxx/qla_target.c | 41 +++- drivers/scsi/qla2xxx/qla_target.h | 16 +- 11 files changed, 407 insertions(+), 71 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_edif.c b/drivers/scsi/qla2xxx/qla_edif.c index 721898afb064..9f66ac6d1c77 100644 --- a/drivers/scsi/qla2xxx/qla_edif.c +++ b/drivers/scsi/qla2xxx/qla_edif.c @@ -556,41 +556,30 @@ qla_edif_app_start(scsi_qla_host_t *vha, struct bsg_job *bsg_job) } list_for_each_entry_safe(fcport, tf, &vha->vp_fcports, list) { - if ((fcport->flags & FCF_FCSP_DEVICE)) { - ql_dbg(ql_dbg_edif, vha, 0xf084, - "%s: sess %p %8phC lid %#04x s_id %06x logout %d\n", - __func__, fcport, fcport->port_name, - fcport->loop_id, fcport->d_id.b24, - fcport->logout_on_delete); - - ql_dbg(ql_dbg_edif, vha, 0xf084, - "keep %d els_logo %d disc state %d auth state %d stop state %d\n", - fcport->keep_nport_handle, - fcport->send_els_logo, fcport->disc_state, - fcport->edif.auth_state, fcport->edif.app_stop); - - if (atomic_read(&vha->loop_state) == LOOP_DOWN) - break; + ql_dbg(ql_dbg_edif, vha, 0xf084, + "%s: sess %p %8phC lid %#04x s_id %06x logout %d\n", + __func__, fcport, fcport->port_name, + fcport->loop_id, fcport->d_id.b24, + fcport->logout_on_delete); + + ql_dbg(ql_dbg_edif, vha, 0xf084, + "keep %d els_logo %d disc state %d auth state %d stop state %d\n", + fcport->keep_nport_handle, + fcport->send_els_logo, fcport->disc_state, + fcport->edif.auth_state, fcport->edif.app_stop); + + if (atomic_read(&vha->loop_state) == LOOP_DOWN) + break; - if (!fcport->edif.secured_login) - continue; + fcport->edif.app_started = 1; + fcport->edif.app_stop = 0; - fcport->edif.app_started = 1; - if (fcport->edif.app_stop || - (fcport->disc_state != DSC_LOGIN_COMPLETE && - fcport->disc_state != DSC_LOGIN_PEND && - fcport->disc_state != DSC_DELETED)) { - /* no activity */ - fcport->edif.app_stop = 0; - - ql_dbg(ql_dbg_edif, vha, 0x911e, - "%s wwpn %8phC calling qla_edif_reset_auth_wait\n", - __func__, fcport->port_name); - fcport->edif.app_sess_online = 1; - qla_edif_reset_auth_wait(fcport, DSC_LOGIN_PEND, 0); - } - qla_edif_sa_ctl_init(vha, fcport); - } + ql_dbg(ql_dbg_edif, vha, 0x911e, + "%s wwpn %8phC calling qla_edif_reset_auth_wait\n", + __func__, fcport->port_name); + fcport->edif.app_sess_online = 1; + qla_edif_reset_auth_wait(fcport, DSC_LOGIN_PEND, 0); + qla_edif_sa_ctl_init(vha, fcport); } if (vha->pur_cinfo.enode_flags != ENODE_ACTIVE) { @@ -720,10 +709,7 @@ qla_edif_app_authok(scsi_qla_host_t *vha, struct bsg_job *bsg_job) struct fc_bsg_reply *bsg_reply = bsg_job->reply; fc_port_t *fcport = NULL; port_id_t portid = {0}; - /* port_id_t portid = {0x10100}; */ - /* int i; */ - /* ql_dbg(ql_dbg_edif, vha, 0x911d, "%s app auth ok\n", __func__); */ sg_copy_to_buffer(bsg_job->request_payload.sg_list, bsg_job->request_payload.sg_cnt, &appplogiok, @@ -938,6 +924,9 @@ qla_edif_app_getfcinfo(scsi_qla_host_t *vha, struct bsg_job *bsg_job) if (tdid.b24 != 0 && tdid.b24 != fcport->d_id.b24) continue; + app_reply->ports[pcnt].rekey_count = + fcport->edif.rekey_cnt; + app_reply->ports[pcnt].remote_type = VND_CMD_RTYPE_UNKNOWN; if (fcport->port_type & (FCT_NVME_TARGET | FCT_TARGET)) @@ -1089,8 +1078,8 @@ qla_edif_app_mgmt(struct bsg_job *bsg_job) if (!vha->hw->flags.edif_enabled || test_bit(VPORT_DELETE, &vha->dpc_flags)) { ql_dbg(ql_dbg_edif, vha, 0x911d, - "%s edif not enabled or vp delete. bsg ptr done %p\n", - __func__, bsg_job); + "%s edif not enabled or vp delete. bsg ptr done %p. dpc_flags %lx\n", + __func__, bsg_job, vha->dpc_flags); SET_DID_STATUS(bsg_reply->result, DID_ERROR); goto done; @@ -2270,16 +2259,10 @@ void qla24xx_sa_update_iocb(srb_t *sp, struct sa_update_28xx *sa_update_iocb) sa_update_iocb->sa_control |= SA_CNTL_KEY256; for (itr = 0; itr < 32; itr++) sa_update_iocb->sa_key[itr] = sa_frame->sa_key[itr]; - - ql_dbg(ql_dbg_edif + ql_dbg_verbose, vha, 0x921f, "%s 256 sa key=%32phN\n", - __func__, sa_update_iocb->sa_key); } else { sa_update_iocb->sa_control |= SA_CNTL_KEY128; for (itr = 0; itr < 16; itr++) sa_update_iocb->sa_key[itr] = sa_frame->sa_key[itr]; - - ql_dbg(ql_dbg_edif + ql_dbg_verbose, vha, 0x921f, "%s 128 sa key=%16phN\n", - __func__, sa_update_iocb->sa_key); } ql_dbg(ql_dbg_edif, vha, 0x921d, @@ -2745,6 +2728,276 @@ qla28xx_sa_update_iocb_entry(scsi_qla_host_t *v, struct req_que *req, sp->done(sp, 0); } +/* + * qla28xx_start_scsi_edif() - Send a SCSI type 6 command ot the ISP + * @sp: command to send to the ISP + * req/rsp queue to use for this request + * lock to protect submission + * + * Returns non-zero if a failure occurred, else zero. + */ +int +qla28xx_start_scsi_edif(srb_t *sp) +{ + int nseg; + unsigned long flags; + struct scsi_cmnd *cmd; + uint32_t *clr_ptr; + uint32_t index, i; + uint32_t handle; + uint16_t cnt; + int16_t req_cnt; + uint16_t tot_dsds; + __be32 *fcp_dl; + uint8_t additional_cdb_len; + struct ct6_dsd *ctx; + struct scsi_qla_host *vha = sp->vha; + struct qla_hw_data *ha = vha->hw; + struct cmd_type_6 *cmd_pkt; + struct dsd64 *cur_dsd; + uint8_t avail_dsds = 0; + struct scatterlist *sg; + struct req_que *req = sp->qpair->req; + spinlock_t *lock = sp->qpair->qp_lock_ptr; + + /* Setup device pointers. */ + cmd = GET_CMD_SP(sp); + + /* So we know we haven't pci_map'ed anything yet */ + tot_dsds = 0; + + /* Send marker if required */ + if (vha->marker_needed != 0) { + if (qla2x00_marker(vha, sp->qpair, 0, 0, MK_SYNC_ALL) != + QLA_SUCCESS) { + ql_log(ql_log_warn, vha, 0x300c, + "qla2x00_marker failed for cmd=%p.\n", cmd); + return QLA_FUNCTION_FAILED; + } + vha->marker_needed = 0; + } + + /* Acquire ring specific lock */ + spin_lock_irqsave(lock, flags); + + /* Check for room in outstanding command list. */ + handle = req->current_outstanding_cmd; + for (index = 1; index < req->num_outstanding_cmds; index++) { + handle++; + if (handle == req->num_outstanding_cmds) + handle = 1; + if (!req->outstanding_cmds[handle]) + break; + } + if (index == req->num_outstanding_cmds) + goto queuing_error; + + /* Map the sg table so we have an accurate count of sg entries needed */ + if (scsi_sg_count(cmd)) { + nseg = dma_map_sg(&ha->pdev->dev, scsi_sglist(cmd), + scsi_sg_count(cmd), cmd->sc_data_direction); + if (unlikely(!nseg)) + goto queuing_error; + } else { + nseg = 0; + } + + tot_dsds = nseg; + req_cnt = qla24xx_calc_iocbs(vha, tot_dsds); + if (req->cnt < (req_cnt + 2)) { + cnt = IS_SHADOW_REG_CAPABLE(ha) ? *req->out_ptr : + rd_reg_dword(req->req_q_out); + if (req->ring_index < cnt) + req->cnt = cnt - req->ring_index; + else + req->cnt = req->length - + (req->ring_index - cnt); + if (req->cnt < (req_cnt + 2)) + goto queuing_error; + } + + ctx = sp->u.scmd.ct6_ctx = + mempool_alloc(ha->ctx_mempool, GFP_ATOMIC); + if (!ctx) { + ql_log(ql_log_fatal, vha, 0x3010, + "Failed to allocate ctx for cmd=%p.\n", cmd); + goto queuing_error; + } + + memset(ctx, 0, sizeof(struct ct6_dsd)); + ctx->fcp_cmnd = dma_pool_zalloc(ha->fcp_cmnd_dma_pool, + GFP_ATOMIC, &ctx->fcp_cmnd_dma); + if (!ctx->fcp_cmnd) { + ql_log(ql_log_fatal, vha, 0x3011, + "Failed to allocate fcp_cmnd for cmd=%p.\n", cmd); + goto queuing_error; + } + + /* Initialize the DSD list and dma handle */ + INIT_LIST_HEAD(&ctx->dsd_list); + ctx->dsd_use_cnt = 0; + + if (cmd->cmd_len > 16) { + additional_cdb_len = cmd->cmd_len - 16; + if ((cmd->cmd_len % 4) != 0) { + /* + * SCSI command bigger than 16 bytes must be + * multiple of 4 + */ + ql_log(ql_log_warn, vha, 0x3012, + "scsi cmd len %d not multiple of 4 for cmd=%p.\n", + cmd->cmd_len, cmd); + goto queuing_error_fcp_cmnd; + } + ctx->fcp_cmnd_len = 12 + cmd->cmd_len + 4; + } else { + additional_cdb_len = 0; + ctx->fcp_cmnd_len = 12 + 16 + 4; + } + + cmd_pkt = (struct cmd_type_6 *)req->ring_ptr; + cmd_pkt->handle = make_handle(req->id, handle); + + /* + * Zero out remaining portion of packet. + * tagged queuing modifier -- default is TSK_SIMPLE (0). + */ + clr_ptr = (uint32_t *)cmd_pkt + 2; + memset(clr_ptr, 0, REQUEST_ENTRY_SIZE - 8); + cmd_pkt->dseg_count = cpu_to_le16(tot_dsds); + + /* No data transfer */ + if (!scsi_bufflen(cmd) || cmd->sc_data_direction == DMA_NONE) { + cmd_pkt->byte_count = cpu_to_le32(0); + goto no_dsds; + } + + /* Set transfer direction */ + if (cmd->sc_data_direction == DMA_TO_DEVICE) { + cmd_pkt->control_flags = cpu_to_le16(CF_WRITE_DATA); + vha->qla_stats.output_bytes += scsi_bufflen(cmd); + vha->qla_stats.output_requests++; + sp->fcport->edif.tx_bytes += scsi_bufflen(cmd); + } else if (cmd->sc_data_direction == DMA_FROM_DEVICE) { + cmd_pkt->control_flags = cpu_to_le16(CF_READ_DATA); + vha->qla_stats.input_bytes += scsi_bufflen(cmd); + vha->qla_stats.input_requests++; + sp->fcport->edif.rx_bytes += scsi_bufflen(cmd); + } + + cmd_pkt->control_flags |= cpu_to_le16(CF_EN_EDIF); + cmd_pkt->control_flags &= ~(cpu_to_le16(CF_NEW_SA)); + + /* One DSD is available in the Command Type 6 IOCB */ + avail_dsds = 1; + cur_dsd = &cmd_pkt->fcp_dsd; + + /* Load data segments */ + scsi_for_each_sg(cmd, sg, tot_dsds, i) { + dma_addr_t sle_dma; + cont_a64_entry_t *cont_pkt; + + /* Allocate additional continuation packets? */ + if (avail_dsds == 0) { + /* + * Five DSDs are available in the Continuation + * Type 1 IOCB. + */ + cont_pkt = qla2x00_prep_cont_type1_iocb(vha, req); + cur_dsd = cont_pkt->dsd; + avail_dsds = 5; + } + + sle_dma = sg_dma_address(sg); + put_unaligned_le64(sle_dma, &cur_dsd->address); + cur_dsd->length = cpu_to_le32(sg_dma_len(sg)); + cur_dsd++; + avail_dsds--; + } + +no_dsds: + /* Set NPORT-ID and LUN number*/ + cmd_pkt->nport_handle = cpu_to_le16(sp->fcport->loop_id); + cmd_pkt->port_id[0] = sp->fcport->d_id.b.al_pa; + cmd_pkt->port_id[1] = sp->fcport->d_id.b.area; + cmd_pkt->port_id[2] = sp->fcport->d_id.b.domain; + cmd_pkt->vp_index = sp->vha->vp_idx; + + cmd_pkt->entry_type = COMMAND_TYPE_6; + + /* Set total data segment count. */ + cmd_pkt->entry_count = (uint8_t)req_cnt; + + int_to_scsilun(cmd->device->lun, &cmd_pkt->lun); + host_to_fcp_swap((uint8_t *)&cmd_pkt->lun, sizeof(cmd_pkt->lun)); + + /* build FCP_CMND IU */ + int_to_scsilun(cmd->device->lun, &ctx->fcp_cmnd->lun); + ctx->fcp_cmnd->additional_cdb_len = additional_cdb_len; + + if (cmd->sc_data_direction == DMA_TO_DEVICE) + ctx->fcp_cmnd->additional_cdb_len |= 1; + else if (cmd->sc_data_direction == DMA_FROM_DEVICE) + ctx->fcp_cmnd->additional_cdb_len |= 2; + + /* Populate the FCP_PRIO. */ + if (ha->flags.fcp_prio_enabled) + ctx->fcp_cmnd->task_attribute |= + sp->fcport->fcp_prio << 3; + + memcpy(ctx->fcp_cmnd->cdb, cmd->cmnd, cmd->cmd_len); + + fcp_dl = (__be32 *)(ctx->fcp_cmnd->cdb + 16 + + additional_cdb_len); + *fcp_dl = htonl((uint32_t)scsi_bufflen(cmd)); + + cmd_pkt->fcp_cmnd_dseg_len = cpu_to_le16(ctx->fcp_cmnd_len); + put_unaligned_le64(ctx->fcp_cmnd_dma, &cmd_pkt->fcp_cmnd_dseg_address); + + sp->flags |= SRB_FCP_CMND_DMA_VALID; + cmd_pkt->byte_count = cpu_to_le32((uint32_t)scsi_bufflen(cmd)); + /* Set total data segment count. */ + cmd_pkt->entry_count = (uint8_t)req_cnt; + cmd_pkt->entry_status = 0; + + /* Build command packet. */ + req->current_outstanding_cmd = handle; + req->outstanding_cmds[handle] = sp; + sp->handle = handle; + cmd->host_scribble = (unsigned char *)(unsigned long)handle; + req->cnt -= req_cnt; + + /* Adjust ring index. */ + wmb(); + req->ring_index++; + if (req->ring_index == req->length) { + req->ring_index = 0; + req->ring_ptr = req->ring; + } else { + req->ring_ptr++; + } + + /* Set chip new ring index. */ + wrt_reg_dword(req->req_q_in, req->ring_index); + + spin_unlock_irqrestore(lock, flags); + return QLA_SUCCESS; + +queuing_error_fcp_cmnd: + dma_pool_free(ha->fcp_cmnd_dma_pool, ctx->fcp_cmnd, ctx->fcp_cmnd_dma); +queuing_error: + if (tot_dsds) + scsi_dma_unmap(cmd); + + if (sp->u.scmd.ct6_ctx) { + mempool_free(sp->u.scmd.ct6_ctx, ha->ctx_mempool); + sp->u.scmd.ct6_ctx = NULL; + } + spin_unlock_irqrestore(lock, flags); + + return QLA_FUNCTION_FAILED; +} + /********************************************** * edif update/delete sa_index list functions * **********************************************/ diff --git a/drivers/scsi/qla2xxx/qla_fw.h b/drivers/scsi/qla2xxx/qla_fw.h index 4934b08a8990..c257af8d87fd 100644 --- a/drivers/scsi/qla2xxx/qla_fw.h +++ b/drivers/scsi/qla2xxx/qla_fw.h @@ -490,6 +490,9 @@ struct cmd_type_6 { struct scsi_lun lun; /* FCP LUN (BE). */ __le16 control_flags; /* Control flags. */ +#define CF_NEW_SA BIT_12 +#define CF_EN_EDIF BIT_9 +#define CF_ADDITIONAL_PARAM_BLK BIT_8 #define CF_DIF_SEG_DESCR_ENABLE BIT_3 #define CF_DATA_SEG_DESCR_ENABLE BIT_2 #define CF_READ_DATA BIT_1 diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index cc78339b47ac..be94b335f211 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -189,6 +189,7 @@ extern int qla2xuseresexchforels; extern int ql2xexlogins; extern int ql2xdifbundlinginternalbuffers; extern int ql2xfulldump_on_mpifail; +extern int ql2xsecenable; extern int ql2xenforce_iocb_limit; extern int ql2xabts_wait_nvme; @@ -299,6 +300,8 @@ extern int qla2x00_vp_abort_isp(scsi_qla_host_t *); */ void qla_els_pt_iocb(struct scsi_qla_host *vha, struct els_entry_24xx *pkt, struct qla_els_pt_arg *a); +cont_a64_entry_t *qla2x00_prep_cont_type1_iocb(scsi_qla_host_t *vha, + struct req_que *que); extern uint16_t qla2x00_calc_iocbs_32(uint16_t); extern uint16_t qla2x00_calc_iocbs_64(uint16_t); extern void qla2x00_build_scsi_iocbs_32(srb_t *, cmd_entry_t *, uint16_t); @@ -990,6 +993,7 @@ void qla_enode_init(scsi_qla_host_t *vha); void qla_enode_stop(scsi_qla_host_t *vha); void qla_edif_flush_sa_ctl_lists(fc_port_t *fcport); void qla_edb_init(scsi_qla_host_t *vha); +int qla28xx_start_scsi_edif(srb_t *sp); void qla24xx_sa_update_iocb(srb_t *sp, struct sa_update_28xx *sa_update_iocb); void qla24xx_sa_replace_iocb(srb_t *sp, struct sa_update_28xx *sa_update_iocb); void qla24xx_auth_els(scsi_qla_host_t *vha, void **pkt, struct rsp_que **rsp); diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index 99fb330053ae..b16b7d16be12 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -632,7 +632,7 @@ static int qla_async_rftid(scsi_qla_host_t *vha, port_id_t *d_id) ct_req->req.rft_id.port_id = port_id_to_be_id(vha->d_id); ct_req->req.rft_id.fc4_types[2] = 0x01; /* FCP-3 */ - if (vha->flags.nvme_enabled) + if (vha->flags.nvme_enabled && qla_ini_mode_enabled(vha)) ct_req->req.rft_id.fc4_types[6] = 1; /* NVMe type 28h */ sp->u.iocb_cmd.u.ctarg.req_size = RFT_ID_REQ_SIZE; diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index bef9bf59bc50..f6ea51143651 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -345,16 +345,15 @@ qla2x00_async_login(struct scsi_qla_host *vha, fc_port_t *fcport, if (N2N_TOPO(fcport->vha->hw) && fcport_is_bigger(fcport)) { lio->u.logio.flags |= SRB_LOGIN_PRLI_ONLY; } else { - if (vha->hw->flags.edif_enabled) { - if (fcport->edif.non_secured_login == 0) { - lio->u.logio.flags |= - (SRB_LOGIN_FCSP | SRB_LOGIN_SKIP_PRLI); - ql_dbg(ql_dbg_disc, vha, 0x2072, + if (vha->hw->flags.edif_enabled && + vha->e_dbell.db_flags & EDB_ACTIVE) { + lio->u.logio.flags |= + (SRB_LOGIN_FCSP | SRB_LOGIN_SKIP_PRLI); + ql_dbg(ql_dbg_disc, vha, 0x2072, "Async-login: w/ FCSP %8phC hdl=%x, loopid=%x portid=%06x\n", - fcport->port_name, sp->handle, - fcport->loop_id, - fcport->d_id.b24); - } + fcport->port_name, sp->handle, + fcport->loop_id, + fcport->d_id.b24); } else { lio->u.logio.flags |= SRB_LOGIN_COND_PLOGI; } @@ -3965,7 +3964,8 @@ qla2x00_setup_chip(scsi_qla_host_t *vha) } /* Enable PUREX PASSTHRU */ - if (ql2xrdpenable || ha->flags.scm_supported_f) + if (ql2xrdpenable || ha->flags.scm_supported_f || + ha->flags.edif_enabled) qla25xx_set_els_cmds_supported(vha); } else goto failed; @@ -4150,7 +4150,7 @@ qla24xx_update_fw_options(scsi_qla_host_t *vha) } /* Move PUREX, ABTS RX & RIDA to ATIOQ */ - if (ql2xmvasynctoatio && + if (ql2xmvasynctoatio && !ha->flags.edif_enabled && (IS_QLA83XX(ha) || IS_QLA27XX(ha) || IS_QLA28XX(ha))) { if (qla_tgt_mode_enabled(vha) || qla_dual_mode_enabled(vha)) @@ -4178,7 +4178,8 @@ qla24xx_update_fw_options(scsi_qla_host_t *vha) ha->fw_options[2] &= ~BIT_8; } - if (ql2xrdpenable || ha->flags.scm_supported_f) + if (ql2xrdpenable || ha->flags.scm_supported_f || + ha->flags.edif_enabled) ha->fw_options[1] |= ADD_FO1_ENABLE_PUREX_IOCB; /* Enable Async 8130/8131 events -- transceiver insertion/removal */ diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index ba36084d17a9..67c28a2baeee 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -118,7 +118,7 @@ qla2x00_prep_cont_type0_iocb(struct scsi_qla_host *vha) * * Returns a pointer to the continuation type 1 IOCB packet. */ -static inline cont_a64_entry_t * +cont_a64_entry_t * qla2x00_prep_cont_type1_iocb(scsi_qla_host_t *vha, struct req_que *req) { cont_a64_entry_t *cont_pkt; @@ -1961,6 +1961,9 @@ qla2xxx_start_scsi_mq(srb_t *sp) struct qla_hw_data *ha = vha->hw; struct qla_qpair *qpair = sp->qpair; + if (sp->fcport->edif.enable) + return qla28xx_start_scsi_edif(sp); + /* Acquire qpair specific lock */ spin_lock_irqsave(&qpair->qp_lock, flags); diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index f4b9fa9d8078..f8a060862512 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -61,6 +61,7 @@ static struct rom_cmd { { MBC_SET_RNID_PARAMS }, { MBC_GET_RNID_PARAMS }, { MBC_GET_SET_ZIO_THRESHOLD }, + { MBC_GET_RNID_PARAMS }, }; static int is_rom_cmd(uint16_t cmd) @@ -739,7 +740,7 @@ qla2x00_execute_fw(scsi_qla_host_t *vha, uint32_t risc_addr) mcp->mb[11] |= EXE_FW_FORCE_SEMAPHORE; mcp->out_mb |= MBX_4 | MBX_3 | MBX_2 | MBX_1 | MBX_11; - mcp->in_mb |= MBX_3 | MBX_2 | MBX_1; + mcp->in_mb |= MBX_5|MBX_3|MBX_2|MBX_1; } else { mcp->mb[1] = LSW(risc_addr); mcp->out_mb |= MBX_1; @@ -795,6 +796,12 @@ qla2x00_execute_fw(scsi_qla_host_t *vha, uint32_t risc_addr) } } + if (IS_QLA28XX(ha) && (mcp->mb[5] & BIT_10) && ql2xsecenable) { + ha->flags.edif_enabled = 1; + ql_log(ql_log_info, vha, 0xffff, + "%s: edif is enabled\n", __func__); + } + done: ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1028, "Done %s.\n", __func__); @@ -4946,7 +4953,7 @@ qla24xx_get_port_login_templ(scsi_qla_host_t *vha, dma_addr_t buf_dma, return rval; } -#define PUREX_CMD_COUNT 2 +#define PUREX_CMD_COUNT 4 int qla25xx_set_els_cmds_supported(scsi_qla_host_t *vha) { @@ -4954,6 +4961,7 @@ qla25xx_set_els_cmds_supported(scsi_qla_host_t *vha) mbx_cmd_t mc; mbx_cmd_t *mcp = &mc; uint8_t *els_cmd_map; + uint8_t active_cnt = 0; dma_addr_t els_cmd_map_dma; uint8_t cmd_opcode[PUREX_CMD_COUNT]; uint8_t i, index, purex_bit; @@ -4975,10 +4983,20 @@ qla25xx_set_els_cmds_supported(scsi_qla_host_t *vha) } /* List of Purex ELS */ - cmd_opcode[0] = ELS_FPIN; - cmd_opcode[1] = ELS_RDP; + if (ql2xrdpenable) { + cmd_opcode[active_cnt] = ELS_RDP; + active_cnt++; + } + if (ha->flags.scm_supported_f) { + cmd_opcode[active_cnt] = ELS_FPIN; + active_cnt++; + } + if (ha->flags.edif_enabled) { + cmd_opcode[active_cnt] = ELS_AUTH_ELS; + active_cnt++; + } - for (i = 0; i < PUREX_CMD_COUNT; i++) { + for (i = 0; i < active_cnt; i++) { index = cmd_opcode[i] / 8; purex_bit = cmd_opcode[i] % 8; els_cmd_map[index] |= 1 << purex_bit; diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 0cacb667a88b..3f2585798a44 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -463,6 +463,10 @@ static inline int qla2x00_start_nvme_mq(srb_t *sp) } else if (fd->io_dir == 0) { cmd_pkt->control_flags = 0; } + + if (sp->fcport->edif.enable && fd->io_dir != 0) + cmd_pkt->control_flags |= cpu_to_le16(CF_EN_EDIF); + /* Set BIT_13 of control flags for Async event */ if (vha->flags.nvme2_enabled && cmd->sqe.common.opcode == nvme_admin_async_event) { diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index efc21ef80142..ffc7367fc98e 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -53,6 +53,11 @@ static struct kmem_cache *ctx_cachep; */ uint ql_errlev = 0x8001; +int ql2xsecenable; +module_param(ql2xsecenable, int, S_IRUGO); +MODULE_PARM_DESC(ql2xsecenable, + "Enable/disable security. 0(Default) - Security disabled. 1 - Security enabled."); + static int ql2xenableclass2; module_param(ql2xenableclass2, int, S_IRUGO|S_IRUSR); MODULE_PARM_DESC(ql2xenableclass2, @@ -4032,7 +4037,7 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len, if (!ha->srb_mempool) goto fail_free_gid_list; - if (IS_P3P_TYPE(ha)) { + if (IS_P3P_TYPE(ha) || IS_QLA27XX(ha) || (ql2xsecenable && IS_QLA28XX(ha))) { /* Allocate cache for CT6 Ctx. */ if (!ctx_cachep) { ctx_cachep = kmem_cache_create("qla2xxx_ctx", @@ -4066,7 +4071,7 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len, "init_cb=%p gid_list=%p, srb_mempool=%p s_dma_pool=%p.\n", ha->init_cb, ha->gid_list, ha->srb_mempool, ha->s_dma_pool); - if (IS_P3P_TYPE(ha) || ql2xenabledif) { + if (IS_P3P_TYPE(ha) || ql2xenabledif || (IS_QLA28XX(ha) && ql2xsecenable)) { ha->dl_dma_pool = dma_pool_create(name, &ha->pdev->dev, DSD_LIST_DMA_POOL_SIZE, 8, 0); if (!ha->dl_dma_pool) { diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 5d9fafa0c5d9..6a89ea47d90e 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1313,8 +1313,8 @@ void qlt_schedule_sess_for_deletion(struct fc_port *sess) qla24xx_chk_fcp_state(sess); ql_dbg(ql_log_warn, sess->vha, 0xe001, - "Scheduling sess %p for deletion %8phC\n", - sess, sess->port_name); + "Scheduling sess %p for deletion %8phC fc4_type %x\n", + sess, sess->port_name, sess->fc4_type); WARN_ON(!queue_work(sess->vha->hw->wq, &sess->del_work)); } @@ -2610,6 +2610,7 @@ static int qlt_24xx_build_ctio_pkt(struct qla_qpair *qpair, struct ctio7_to_24xx *pkt; struct atio_from_isp *atio = &prm->cmd->atio; uint16_t temp; + struct qla_tgt_cmd *cmd = prm->cmd; pkt = (struct ctio7_to_24xx *)qpair->req->ring_ptr; prm->pkt = pkt; @@ -2642,6 +2643,15 @@ static int qlt_24xx_build_ctio_pkt(struct qla_qpair *qpair, pkt->u.status0.ox_id = cpu_to_le16(temp); pkt->u.status0.relative_offset = cpu_to_le32(prm->cmd->offset); + if (cmd->edif) { + if (cmd->dma_data_direction == DMA_TO_DEVICE) + prm->cmd->sess->edif.rx_bytes += cmd->bufflen; + if (cmd->dma_data_direction == DMA_FROM_DEVICE) + prm->cmd->sess->edif.tx_bytes += cmd->bufflen; + + pkt->u.status0.edif_flags |= EF_EN_EDIF; + } + return 0; } @@ -3332,8 +3342,10 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type, if (xmit_type & QLA_TGT_XMIT_STATUS) { pkt->u.status0.scsi_status = cpu_to_le16(prm.rq_result); - pkt->u.status0.residual = - cpu_to_le32(prm.residual); + if (!cmd->edif) + pkt->u.status0.residual = + cpu_to_le32(prm.residual); + pkt->u.status0.flags |= cpu_to_le16( CTIO7_FLAGS_SEND_STATUS); if (qlt_need_explicit_conf(cmd, 0)) { @@ -3980,6 +3992,12 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, if (cmd == NULL) return; + if ((le16_to_cpu(((struct ctio7_from_24xx *)ctio)->flags) & CTIO7_FLAGS_DATA_OUT) && + cmd->sess) { + qlt_chk_edif_rx_sa_delete_pending(vha, cmd->sess, + (struct ctio7_from_24xx *)ctio); + } + se_cmd = &cmd->se_cmd; cmd->cmd_sent_to_fw = 0; @@ -4050,6 +4068,16 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, qlt_handle_dif_error(qpair, cmd, ctio); return; } + + case CTIO_FAST_AUTH_ERR: + case CTIO_FAST_INCOMP_PAD_LEN: + case CTIO_FAST_INVALID_REQ: + case CTIO_FAST_SPI_ERR: + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf05b, + "qla_target(%d): CTIO with EDIF error status 0x%x received (state %x, se_cmd %p\n", + vha->vp_idx, status, cmd->state, se_cmd); + break; + default: ql_dbg(ql_dbg_tgt_mgt, vha, 0xf05b, "qla_target(%d): CTIO with error status 0x%x received (state %x, se_cmd %p\n", @@ -4351,6 +4379,7 @@ static struct qla_tgt_cmd *qlt_get_tag(scsi_qla_host_t *vha, qlt_assign_qpair(vha, cmd); cmd->reset_count = vha->hw->base_qpair->chip_reset; cmd->vp_idx = vha->vp_idx; + cmd->edif = sess->edif.enable; return cmd; } @@ -4767,7 +4796,9 @@ static int qlt_handle_login(struct scsi_qla_host *vha, } if (vha->hw->flags.edif_enabled && - vha->e_dbell.db_flags != EDB_ACTIVE) { + !(vha->e_dbell.db_flags & EDB_ACTIVE) && + iocb->u.isp24.status_subcode == ELS_PLOGI && + !(le16_to_cpu(iocb->u.isp24.flags) & NOTIFY24XX_FLAGS_FCSP)) { ql_dbg(ql_dbg_disc, vha, 0xffff, "%s %d Term INOT due to app not available lid=%d, NportID %06X ", __func__, __LINE__, loop_id, port_id.b24); diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h index b910f8f09353..156b950ca7e7 100644 --- a/drivers/scsi/qla2xxx/qla_target.h +++ b/drivers/scsi/qla2xxx/qla_target.h @@ -239,6 +239,10 @@ struct ctio_to_2xxx { #define CTIO_PORT_LOGGED_OUT 0x29 #define CTIO_PORT_CONF_CHANGED 0x2A #define CTIO_SRR_RECEIVED 0x45 +#define CTIO_FAST_AUTH_ERR 0x63 +#define CTIO_FAST_INCOMP_PAD_LEN 0x65 +#define CTIO_FAST_INVALID_REQ 0x66 +#define CTIO_FAST_SPI_ERR 0x67 #endif #ifndef CTIO_RET_TYPE @@ -409,7 +413,16 @@ struct ctio7_to_24xx { struct { __le16 reserved1; __le16 flags; - __le32 residual; + union { + __le32 residual; + struct { + uint8_t rsvd1; + uint8_t edif_flags; +#define EF_EN_EDIF BIT_0 +#define EF_NEW_SA BIT_1 + uint16_t rsvd2; + }; + }; __le16 ox_id; __le16 scsi_status; __le32 relative_offset; @@ -876,6 +889,7 @@ struct qla_tgt_cmd { unsigned int term_exchg:1; unsigned int cmd_sent_to_fw:1; unsigned int cmd_in_wq:1; + unsigned int edif:1; /* * This variable may be set from outside the LIO and I/O completion