From e1364711359f3ced054bda9920477c8bf93b74c5 Mon Sep 17 00:00:00 2001 From: James Smart Date: Wed, 21 Apr 2021 16:44:33 -0700 Subject: scsi: lpfc: Fix illegal memory access on Abort IOCBs In devloss timer handler and in backend calls to terminate remote port I/O, there is logic to walk through all active IOCBs and validate them to potentially trigger an abort request. This logic is causing illegal memory accesses which leads to a crash. Abort IOCBs, which may be on the list, do not have an associated lpfc_io_buf struct. The driver is trying to map an lpfc_io_buf struct on the IOCB and which results in a bogus address thus the issue. Fix by skipping over ABORT IOCBs (CLOSE IOCBs are ABORTS that don't send ABTS) in the IOCB scan logic. Link: https://lore.kernel.org/r/20210421234433.102079-1-jsmart2021@gmail.com Co-developed-by: Justin Tee Signed-off-by: Justin Tee Signed-off-by: James Smart Signed-off-by: Martin K. Petersen --- drivers/scsi/lpfc/lpfc_sli.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 06ccc0157bd8..579ac75dfe79 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -11804,13 +11804,20 @@ lpfc_sli_validate_fcp_iocb(struct lpfc_iocbq *iocbq, struct lpfc_vport *vport, lpfc_ctx_cmd ctx_cmd) { struct lpfc_io_buf *lpfc_cmd; + IOCB_t *icmd = NULL; int rc = 1; if (!iocbq || iocbq->vport != vport) return rc; - if (!(iocbq->iocb_flag & LPFC_IO_FCP) || - !(iocbq->iocb_flag & LPFC_IO_ON_TXCMPLQ)) + if (!(iocbq->iocb_flag & LPFC_IO_FCP) || + !(iocbq->iocb_flag & LPFC_IO_ON_TXCMPLQ) || + iocbq->iocb_flag & LPFC_DRIVER_ABORTED) + return rc; + + icmd = &iocbq->iocb; + if (icmd->ulpCommand == CMD_ABORT_XRI_CN || + icmd->ulpCommand == CMD_CLOSE_XRI_CN) return rc; lpfc_cmd = container_of(iocbq, struct lpfc_io_buf, cur_iocbq); -- cgit v1.2.3 From 83adbba746d1c8b6e3b07d73ae7815044804c96e Mon Sep 17 00:00:00 2001 From: James Smart Date: Wed, 21 Apr 2021 16:44:48 -0700 Subject: scsi: lpfc: Fix DMA virtual address ptr assignment in bsg lpfc_bsg_ct_unsol_event() routine acts assigns a ct_request to the wrong structure address, resulting in a bad address that results in bsg related timeouts. Correct the ct_request assignment to use the kernel virtual buffer address (not the control structure address). Link: https://lore.kernel.org/r/20210421234448.102132-1-jsmart2021@gmail.com Co-developed-by: Justin Tee Signed-off-by: Justin Tee Signed-off-by: James Smart Signed-off-by: Martin K. Petersen --- drivers/scsi/lpfc/lpfc_bsg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c index c2776b88d493..38cfe1bc6a4d 100644 --- a/drivers/scsi/lpfc/lpfc_bsg.c +++ b/drivers/scsi/lpfc/lpfc_bsg.c @@ -934,7 +934,7 @@ lpfc_bsg_ct_unsol_event(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, INIT_LIST_HEAD(&head); list_add_tail(&head, &piocbq->list); - ct_req = (struct lpfc_sli_ct_request *)bdeBuf1; + ct_req = (struct lpfc_sli_ct_request *)bdeBuf1->virt; evt_req_id = ct_req->FsType; cmd = ct_req->CommandResponse.bits.CmdRsp; -- cgit v1.2.3 From e4ec10228fdf09b88ba018009f14a696fb50d3f2 Mon Sep 17 00:00:00 2001 From: James Smart Date: Wed, 21 Apr 2021 16:45:11 -0700 Subject: scsi: lpfc: Fix bad memory access during VPD DUMP mailbox command The dump command for reading a region passes a requested read length specified in words (4-byte units). The response overwrites the same field with the actual number of bytes read. The mailbox handler for DUMP which reads VPD data (region 23) is treating the response field as if it were still a word_cnt, thus multiplying it by 4 to set the read's "length". Given the read value was calculated based on the size of the read buffer, the longer response length runs off the end of the buffer. Fix by reworking the code to use the response field as a byte count. Link: https://lore.kernel.org/r/20210421234511.102206-1-jsmart2021@gmail.com Co-developed-by: Justin Tee Signed-off-by: Justin Tee Signed-off-by: James Smart Signed-off-by: Martin K. Petersen --- drivers/scsi/lpfc/lpfc_init.c | 12 ++++++------ drivers/scsi/lpfc/lpfc_sli.c | 15 ++++++++------- 2 files changed, 14 insertions(+), 13 deletions(-) (limited to 'drivers') diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 1e4c792bb660..5f018d02bf56 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -254,13 +254,13 @@ lpfc_config_port_prep(struct lpfc_hba *phba) if (mb->un.varDmp.word_cnt == 0) break; - i = mb->un.varDmp.word_cnt * sizeof(uint32_t); - if (offset + i > DMP_VPD_SIZE) - i = DMP_VPD_SIZE - offset; + if (mb->un.varDmp.word_cnt > DMP_VPD_SIZE - offset) + mb->un.varDmp.word_cnt = DMP_VPD_SIZE - offset; lpfc_sli_pcimem_bcopy(((uint8_t *)mb) + DMP_RSP_OFFSET, - lpfc_vpd_data + offset, i); - offset += i; - } while (offset < DMP_VPD_SIZE); + lpfc_vpd_data + offset, + mb->un.varDmp.word_cnt); + offset += mb->un.varDmp.word_cnt; + } while (mb->un.varDmp.word_cnt && offset < DMP_VPD_SIZE); lpfc_parse_vpd(phba, lpfc_vpd_data, offset); diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 579ac75dfe79..573c8599d71c 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -19777,7 +19777,7 @@ lpfc_sli_get_config_region23(struct lpfc_hba *phba, char *rgn23_data) LPFC_MBOXQ_t *pmb = NULL; MAILBOX_t *mb; uint32_t offset = 0; - int i, rc; + int rc; if (!rgn23_data) return 0; @@ -19808,13 +19808,14 @@ lpfc_sli_get_config_region23(struct lpfc_hba *phba, char *rgn23_data) if (mb->un.varDmp.word_cnt == 0) break; - i = mb->un.varDmp.word_cnt * sizeof(uint32_t); - if (offset + i > DMP_RGN23_SIZE) - i = DMP_RGN23_SIZE - offset; + if (mb->un.varDmp.word_cnt > DMP_RGN23_SIZE - offset) + mb->un.varDmp.word_cnt = DMP_RGN23_SIZE - offset; + lpfc_sli_pcimem_bcopy(((uint8_t *)mb) + DMP_RSP_OFFSET, - rgn23_data + offset, i); - offset += i; - } while (offset < DMP_RGN23_SIZE); + rgn23_data + offset, + mb->un.varDmp.word_cnt); + offset += mb->un.varDmp.word_cnt; + } while (mb->un.varDmp.word_cnt && offset < DMP_RGN23_SIZE); mempool_free(pmb, phba->mbox_mem_pool); return offset; -- cgit v1.2.3 From 2f1137140fbcffad582d9e5eacc7f189ae0cc110 Mon Sep 17 00:00:00 2001 From: Keoseong Park Date: Tue, 27 Apr 2021 16:38:42 +0900 Subject: scsi: ufs: core: Fix a typo in ufs-sysfs.c Fix the following typo: ufschd_uic_link_state_to_string() -> ufshcd_uic_link_state_to_string() ufschd_ufs_dev_pwr_mode_to_string() -> ufshcd_ufs_dev_pwr_mode_to_string() Link: https://lore.kernel.org/r/1381713434.61619509208911.JavaMail.epsvc@epcpadp3 Signed-off-by: Keoseong Park Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufs-sysfs.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'drivers') diff --git a/drivers/scsi/ufs/ufs-sysfs.c b/drivers/scsi/ufs/ufs-sysfs.c index d7c3cff9662f..5d0e98a05ada 100644 --- a/drivers/scsi/ufs/ufs-sysfs.c +++ b/drivers/scsi/ufs/ufs-sysfs.c @@ -9,7 +9,7 @@ #include "ufs.h" #include "ufs-sysfs.h" -static const char *ufschd_uic_link_state_to_string( +static const char *ufshcd_uic_link_state_to_string( enum uic_link_state state) { switch (state) { @@ -21,7 +21,7 @@ static const char *ufschd_uic_link_state_to_string( } } -static const char *ufschd_ufs_dev_pwr_mode_to_string( +static const char *ufshcd_ufs_dev_pwr_mode_to_string( enum ufs_dev_pwr_mode state) { switch (state) { @@ -81,7 +81,7 @@ static ssize_t rpm_target_dev_state_show(struct device *dev, { struct ufs_hba *hba = dev_get_drvdata(dev); - return sysfs_emit(buf, "%s\n", ufschd_ufs_dev_pwr_mode_to_string( + return sysfs_emit(buf, "%s\n", ufshcd_ufs_dev_pwr_mode_to_string( ufs_pm_lvl_states[hba->rpm_lvl].dev_state)); } @@ -90,7 +90,7 @@ static ssize_t rpm_target_link_state_show(struct device *dev, { struct ufs_hba *hba = dev_get_drvdata(dev); - return sysfs_emit(buf, "%s\n", ufschd_uic_link_state_to_string( + return sysfs_emit(buf, "%s\n", ufshcd_uic_link_state_to_string( ufs_pm_lvl_states[hba->rpm_lvl].link_state)); } @@ -113,7 +113,7 @@ static ssize_t spm_target_dev_state_show(struct device *dev, { struct ufs_hba *hba = dev_get_drvdata(dev); - return sysfs_emit(buf, "%s\n", ufschd_ufs_dev_pwr_mode_to_string( + return sysfs_emit(buf, "%s\n", ufshcd_ufs_dev_pwr_mode_to_string( ufs_pm_lvl_states[hba->spm_lvl].dev_state)); } @@ -122,7 +122,7 @@ static ssize_t spm_target_link_state_show(struct device *dev, { struct ufs_hba *hba = dev_get_drvdata(dev); - return sysfs_emit(buf, "%s\n", ufschd_uic_link_state_to_string( + return sysfs_emit(buf, "%s\n", ufshcd_uic_link_state_to_string( ufs_pm_lvl_states[hba->spm_lvl].link_state)); } -- cgit v1.2.3 From 9814b55cde0588b6d9bc496cee43f87316cbc6f1 Mon Sep 17 00:00:00 2001 From: Bodo Stroesser Date: Fri, 23 Apr 2021 17:01:23 +0200 Subject: scsi: target: tcmu: Return from tcmu_handle_completions() if cmd_id not found If tcmu_handle_completions() finds an invalid cmd_id while looping over cmd responses from userspace it sets TCMU_DEV_BIT_BROKEN and breaks the loop. This means that it does further handling for the tcmu device. Skip that handling by replacing 'break' with 'return'. Additionally change tcmu_handle_completions() from unsigned int to bool, since the value used in return already is bool. Link: https://lore.kernel.org/r/20210423150123.24468-1-bostroesser@gmail.com Signed-off-by: Bodo Stroesser Signed-off-by: Martin K. Petersen --- drivers/target/target_core_user.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index eec2fd573e2b..198d25ae482a 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1413,7 +1413,7 @@ static int tcmu_run_tmr_queue(struct tcmu_dev *udev) return 1; } -static unsigned int tcmu_handle_completions(struct tcmu_dev *udev) +static bool tcmu_handle_completions(struct tcmu_dev *udev) { struct tcmu_mailbox *mb; struct tcmu_cmd *cmd; @@ -1456,7 +1456,7 @@ static unsigned int tcmu_handle_completions(struct tcmu_dev *udev) pr_err("cmd_id %u not found, ring is broken\n", entry->hdr.cmd_id); set_bit(TCMU_DEV_BIT_BROKEN, &udev->flags); - break; + return false; } tcmu_handle_completion(cmd, entry); -- cgit v1.2.3 From 000e68faefe6240ea2e4c98b606c594b20974fb7 Mon Sep 17 00:00:00 2001 From: Bikash Hazarika Date: Mon, 26 Apr 2021 22:09:14 -0700 Subject: scsi: qla2xxx: Add marginal path handling support Add support for eh_should_retry_cmd callback in qla2xxx host template. Link: https://lore.kernel.org/r/20210427050914.7270-1-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Bikash Hazarika Signed-off-by: Nilesh Javali Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_os.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers') diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index d74c32f84ef5..4eab564ea6a0 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -7707,6 +7707,7 @@ struct scsi_host_template qla2xxx_driver_template = { .eh_timed_out = fc_eh_timed_out, .eh_abort_handler = qla2xxx_eh_abort, + .eh_should_retry_cmd = fc_eh_should_retry_cmd, .eh_device_reset_handler = qla2xxx_eh_device_reset, .eh_target_reset_handler = qla2xxx_eh_target_reset, .eh_bus_reset_handler = qla2xxx_eh_bus_reset, -- cgit v1.2.3 From fcb16d9a8ecf1e9bfced0fc654ea4e2caa7517f4 Mon Sep 17 00:00:00 2001 From: Anastasia Kovaleva Date: Thu, 22 Apr 2021 18:34:14 +0300 Subject: scsi: qla2xxx: Prevent PRLI in target mode In a case when the initiator in P2P mode by some circumstances does not send PRLI, the target, in a case when the target port's WWPN is less than initiator's, changes the discovery state in DSC_GNL. When gnl completes it sends PRLI to the initiator. Usually the initiator in P2P mode always sends PRLI. We caught this issue on Linux stable v5.4.6 https://www.spinics.net/lists/stable/msg458515.html. Fix this particular corner case in the behaviour of the P2P mod target login state machine. Link: https://lore.kernel.org/r/20210422153414.4022-1-a.kovaleva@yadro.com Fixes: a9ed06d4e640 ("scsi: qla2xxx: Allow PLOGI in target mode") Reviewed-by: Roman Bolshakov Reviewed-by: Himanshu Madhani Signed-off-by: Anastasia Kovaleva Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_init.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers') diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 9c5782e946e0..0de250570e39 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -1195,6 +1195,9 @@ static int qla24xx_post_prli_work(struct scsi_qla_host *vha, fc_port_t *fcport) { struct qla_work_evt *e; + if (vha->host->active_mode == MODE_TARGET) + return QLA_FUNCTION_FAILED; + e = qla2x00_alloc_work(vha, QLA_EVT_PRLI); if (!e) return QLA_FUNCTION_FAILED; -- cgit v1.2.3 From 23043dd87b153d02eaf676e752d32429be5e5126 Mon Sep 17 00:00:00 2001 From: Can Guo Date: Sun, 25 Apr 2021 20:48:38 -0700 Subject: scsi: ufs: core: Do not put UFS power into LPM if link is broken During resume, if link is broken due to AH8 failure, make sure ufshcd_resume() does not put UFS power back into LPM. Link: https://lore.kernel.org/r/1619408921-30426-2-git-send-email-cang@codeaurora.org Fixes: 4db7a2360597 ("scsi: ufs: Fix concurrency of error handler and other error recovery paths") Reviewed-by: Daejun Park Signed-off-by: Can Guo Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufshcd.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 0625da7a42ee..19d3049a867c 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -8593,7 +8593,7 @@ static void ufshcd_vreg_set_lpm(struct ufs_hba *hba) } else if (!ufshcd_is_ufs_dev_active(hba)) { ufshcd_toggle_vreg(hba->dev, hba->vreg_info.vcc, false); vcc_off = true; - if (!ufshcd_is_link_active(hba)) { + if (ufshcd_is_link_hibern8(hba) || ufshcd_is_link_off(hba)) { ufshcd_config_vreg_lpm(hba, hba->vreg_info.vccq); ufshcd_config_vreg_lpm(hba, hba->vreg_info.vccq2); } @@ -8615,7 +8615,7 @@ static int ufshcd_vreg_set_hpm(struct ufs_hba *hba) !hba->dev_info.is_lu_power_on_wp) { ret = ufshcd_setup_vreg(hba, true); } else if (!ufshcd_is_ufs_dev_active(hba)) { - if (!ret && !ufshcd_is_link_active(hba)) { + if (!ufshcd_is_link_active(hba)) { ret = ufshcd_config_vreg_hpm(hba, hba->vreg_info.vccq); if (ret) goto vcc_disable; -- cgit v1.2.3 From 637822e63b79ee8a729f7ba2645a26cf5a524ee4 Mon Sep 17 00:00:00 2001 From: Can Guo Date: Sun, 25 Apr 2021 20:48:39 -0700 Subject: scsi: ufs: core: Cancel rpm_dev_flush_recheck_work during system suspend During ufs system suspend, leaving rpm_dev_flush_recheck_work running or pending is risky because concurrency may happen between system suspend/resume and runtime resume routine. Fix this by cancelling rpm_dev_flush_recheck_work synchronously during system suspend. Link: https://lore.kernel.org/r/1619408921-30426-3-git-send-email-cang@codeaurora.org Fixes: 51dd905bd2f6 ("scsi: ufs: Fix WriteBooster flush during runtime suspend") Reviewed-by: Daejun Park Signed-off-by: Can Guo Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufshcd.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers') diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 19d3049a867c..f65f2dc92029 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -8975,6 +8975,8 @@ int ufshcd_system_suspend(struct ufs_hba *hba) if (!hba->is_powered) return 0; + cancel_delayed_work_sync(&hba->rpm_dev_flush_recheck_work); + if ((ufs_get_pm_lvl_to_dev_pwr_mode(hba->spm_lvl) == hba->curr_dev_pwr_mode) && (ufs_get_pm_lvl_to_link_pwr_state(hba->spm_lvl) == -- cgit v1.2.3 From ce4f62f9dd8cf43ac044045ed598a0b80ef33890 Mon Sep 17 00:00:00 2001 From: Can Guo Date: Sun, 25 Apr 2021 20:48:40 -0700 Subject: scsi: ufs: core: Narrow down fast path in system suspend path If spm_lvl is set to 0 or 1, when system suspend kicks start and HBA is runtime active, system suspend may just bail without doing anything (the fast path), leaving other contexts still running, e.g., clock gating and clock scaling. When system resume kicks start, concurrency can happen between ufshcd_resume() and these contexts, leading to various stability issues. Add a check against HBA's runtime state and allowing fast path only if HBA is runtime suspended, otherwise let system suspend go ahead call ufshcd_suspend(). This will guarantee that these contexts are stopped by either runtime suspend or system suspend. Link: https://lore.kernel.org/r/1619408921-30426-4-git-send-email-cang@codeaurora.org Fixes: 0b257734344a ("scsi: ufs: optimize system suspend handling") Reviewed-by: Daejun Park Signed-off-by: Can Guo Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufshcd.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers') diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index f65f2dc92029..3eb54937f1d8 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -8981,6 +8981,7 @@ int ufshcd_system_suspend(struct ufs_hba *hba) hba->curr_dev_pwr_mode) && (ufs_get_pm_lvl_to_link_pwr_state(hba->spm_lvl) == hba->uic_link_state) && + pm_runtime_suspended(hba->dev) && !hba->dev_info.b_rpm_dev_flush_capable) goto out; -- cgit v1.2.3 From fc09acb7de31badb2ea9e85d21e071be1a5736e4 Mon Sep 17 00:00:00 2001 From: Douglas Gilbert Date: Wed, 14 Apr 2021 21:50:31 -0400 Subject: scsi: scsi_debug: Fix cmd_per_lun, set to max_queue Make sure that the cmd_per_lun value placed in the host template never exceeds the can_queue value. If the max_queue driver parameter is not specified then both cmd_per_lun and can_queue are set to CAN_QUEUE. CAN_QUEUE is a compile time constant and is used to dimension an array to hold queued requests. If the max_queue driver parameter is given it is must be less than or equal to CAN_QUEUE and if so, the host template values are adjusted. Remove undocumented code that allowed queue_depth to exceed CAN_QUEUE and cause stack full type errors. There is a documented way to do that with every_nth and echo 0x8000 > /sys/bus/pseudo/drivers/scsi_debug/opts See: https://sg.danny.cz/sg/scsi_debug.html Tweak some formatting, and add a suggestion to the "trim poll_queues" warning. Link: https://lore.kernel.org/r/20210415015031.607153-1-dgilbert@interlog.com Reported-by: Kashyap Desai Reviewed-by: John Garry Signed-off-by: Douglas Gilbert Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_debug.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) (limited to 'drivers') diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 70165be10f00..a5d1633b5bd8 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -218,7 +218,7 @@ static const char *sdebug_version_date = "20200710"; */ #define SDEBUG_CANQUEUE_WORDS 3 /* a WORD is bits in a long */ #define SDEBUG_CANQUEUE (SDEBUG_CANQUEUE_WORDS * BITS_PER_LONG) -#define DEF_CMD_PER_LUN 255 +#define DEF_CMD_PER_LUN SDEBUG_CANQUEUE /* UA - Unit Attention; SA - Service Action; SSU - Start Stop Unit */ #define F_D_IN 1 /* Data-in command (e.g. READ) */ @@ -5695,8 +5695,8 @@ MODULE_PARM_DESC(lbpu, "enable LBP, support UNMAP command (def=0)"); MODULE_PARM_DESC(lbpws, "enable LBP, support WRITE SAME(16) with UNMAP bit (def=0)"); MODULE_PARM_DESC(lbpws10, "enable LBP, support WRITE SAME(10) with UNMAP bit (def=0)"); MODULE_PARM_DESC(lowest_aligned, "lowest aligned lba (def=0)"); -MODULE_PARM_DESC(max_luns, "number of LUNs per target to simulate(def=1)"); MODULE_PARM_DESC(lun_format, "LUN format: 0->peripheral (def); 1 --> flat address method"); +MODULE_PARM_DESC(max_luns, "number of LUNs per target to simulate(def=1)"); MODULE_PARM_DESC(max_queue, "max number of queued commands (1 to max(def))"); MODULE_PARM_DESC(medium_error_count, "count of sectors to return follow on MEDIUM error"); MODULE_PARM_DESC(medium_error_start, "starting sector number to return MEDIUM error"); @@ -5710,7 +5710,7 @@ MODULE_PARM_DESC(opt_xferlen_exp, "optimal transfer length granularity exponent MODULE_PARM_DESC(opts, "1->noise, 2->medium_err, 4->timeout, 8->recovered_err... (def=0)"); MODULE_PARM_DESC(per_host_store, "If set, next positive add_host will get new store (def=0)"); MODULE_PARM_DESC(physblk_exp, "physical block exponent (def=0)"); -MODULE_PARM_DESC(poll_queues, "support for iouring iopoll queues (1 to max(submit_queues - 1)"); +MODULE_PARM_DESC(poll_queues, "support for iouring iopoll queues (1 to max(submit_queues - 1))"); MODULE_PARM_DESC(ptype, "SCSI peripheral type(def=0[disk])"); MODULE_PARM_DESC(random, "If set, uniformly randomize command duration between 0 and delay_in_ns"); MODULE_PARM_DESC(removable, "claim to have removable media (def=0)"); @@ -7165,12 +7165,15 @@ static int sdebug_change_qdepth(struct scsi_device *sdev, int qdepth) } num_in_q = atomic_read(&devip->num_in_q); + if (qdepth > SDEBUG_CANQUEUE) { + qdepth = SDEBUG_CANQUEUE; + pr_warn("%s: requested qdepth [%d] exceeds canqueue [%d], trim\n", __func__, + qdepth, SDEBUG_CANQUEUE); + } if (qdepth < 1) qdepth = 1; - /* allow to exceed max host qc_arr elements for testing */ - if (qdepth > SDEBUG_CANQUEUE + 10) - qdepth = SDEBUG_CANQUEUE + 10; - scsi_change_queue_depth(sdev, qdepth); + if (qdepth != sdev->queue_depth) + scsi_change_queue_depth(sdev, qdepth); if (SDEBUG_OPT_Q_NOISE & sdebug_opts) { sdev_printk(KERN_INFO, sdev, "%s: qdepth=%d, num_in_q=%d\n", @@ -7558,6 +7561,7 @@ static int sdebug_driver_probe(struct device *dev) sdbg_host = to_sdebug_host(dev); sdebug_driver_template.can_queue = sdebug_max_queue; + sdebug_driver_template.cmd_per_lun = sdebug_max_queue; if (!sdebug_clustering) sdebug_driver_template.dma_boundary = PAGE_SIZE - 1; @@ -7593,7 +7597,11 @@ static int sdebug_driver_probe(struct device *dev) * If condition not met, trim poll_queues to 1 (just for simplicity). */ if (poll_queues >= submit_queues) { - pr_warn("%s: trim poll_queues to 1\n", my_name); + if (submit_queues < 3) + pr_warn("%s: trim poll_queues to 1\n", my_name); + else + pr_warn("%s: trim poll_queues to 1. Perhaps try poll_queues=%d\n", + my_name, submit_queues - 1); poll_queues = 1; } if (poll_queues) -- cgit v1.2.3 From 3ba1eeff00c42ccb31c0089c8c95c3ade546e9b0 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Thu, 29 Apr 2021 14:25:15 +0200 Subject: scsi: fnic: Kill 'exclude_id' argument to fnic_cleanup_io() 'exclude_id' is always SCSI_NO_TAG which will never be reached when traversing the list of tags. Link: https://lore.kernel.org/r/20210429122517.39659-2-hare@suse.de Reviewed-by: Ming Lei Signed-off-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/scsi/fnic/fnic_scsi.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'drivers') diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c index e619a82f921b..f41d1b1c2e39 100644 --- a/drivers/scsi/fnic/fnic_scsi.c +++ b/drivers/scsi/fnic/fnic_scsi.c @@ -102,7 +102,7 @@ static const char *fnic_fcpio_status_to_str(unsigned int status) return fcpio_status_str[status]; } -static void fnic_cleanup_io(struct fnic *fnic, int exclude_id); +static void fnic_cleanup_io(struct fnic *fnic); static inline spinlock_t *fnic_io_lock_hash(struct fnic *fnic, struct scsi_cmnd *sc) @@ -638,7 +638,7 @@ static int fnic_fcpio_fw_reset_cmpl_handler(struct fnic *fnic, atomic64_inc(&reset_stats->fw_reset_completions); /* Clean up all outstanding io requests */ - fnic_cleanup_io(fnic, SCSI_NO_TAG); + fnic_cleanup_io(fnic); atomic64_set(&fnic->fnic_stats.fw_stats.active_fw_reqs, 0); atomic64_set(&fnic->fnic_stats.io_stats.active_ios, 0); @@ -1361,7 +1361,7 @@ int fnic_wq_copy_cmpl_handler(struct fnic *fnic, int copy_work_to_do) return wq_work_done; } -static void fnic_cleanup_io(struct fnic *fnic, int exclude_id) +static void fnic_cleanup_io(struct fnic *fnic) { int i; struct fnic_io_req *io_req; @@ -1372,9 +1372,6 @@ static void fnic_cleanup_io(struct fnic *fnic, int exclude_id) struct fnic_stats *fnic_stats = &fnic->fnic_stats; for (i = 0; i < fnic->fnic_max_tag_id; i++) { - if (i == exclude_id) - continue; - io_lock = fnic_io_lock_tag(fnic, i); spin_lock_irqsave(io_lock, flags); sc = scsi_host_find_tag(fnic->lport->host, i); -- cgit v1.2.3 From 35ffbb60bdad652d461aa8e97fa094faa9eb46ec Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Thu, 29 Apr 2021 14:25:16 +0200 Subject: scsi: fnic: Use scsi_host_busy_iter() to traverse commands Use scsi_host_busy_iter() to traverse commands instead of hand-crafted routines walking the command list. Link: https://lore.kernel.org/r/20210429122517.39659-3-hare@suse.de Reviewed-by: Ming Lei Signed-off-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/scsi/fnic/fnic_scsi.c | 821 +++++++++++++++++++----------------------- 1 file changed, 375 insertions(+), 446 deletions(-) (limited to 'drivers') diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c index f41d1b1c2e39..762cc8bd2653 100644 --- a/drivers/scsi/fnic/fnic_scsi.c +++ b/drivers/scsi/fnic/fnic_scsi.c @@ -1361,90 +1361,90 @@ int fnic_wq_copy_cmpl_handler(struct fnic *fnic, int copy_work_to_do) return wq_work_done; } -static void fnic_cleanup_io(struct fnic *fnic) +static bool fnic_cleanup_io_iter(struct scsi_cmnd *sc, void *data, + bool reserved) { - int i; + struct fnic *fnic = data; struct fnic_io_req *io_req; unsigned long flags = 0; - struct scsi_cmnd *sc; spinlock_t *io_lock; unsigned long start_time = 0; struct fnic_stats *fnic_stats = &fnic->fnic_stats; - for (i = 0; i < fnic->fnic_max_tag_id; i++) { - io_lock = fnic_io_lock_tag(fnic, i); - spin_lock_irqsave(io_lock, flags); - sc = scsi_host_find_tag(fnic->lport->host, i); - if (!sc) { - spin_unlock_irqrestore(io_lock, flags); - continue; - } - - io_req = (struct fnic_io_req *)CMD_SP(sc); - if ((CMD_FLAGS(sc) & FNIC_DEVICE_RESET) && - !(CMD_FLAGS(sc) & FNIC_DEV_RST_DONE)) { - /* - * We will be here only when FW completes reset - * without sending completions for outstanding ios. - */ - CMD_FLAGS(sc) |= FNIC_DEV_RST_DONE; - if (io_req && io_req->dr_done) - complete(io_req->dr_done); - else if (io_req && io_req->abts_done) - complete(io_req->abts_done); - spin_unlock_irqrestore(io_lock, flags); - continue; - } else if (CMD_FLAGS(sc) & FNIC_DEVICE_RESET) { - spin_unlock_irqrestore(io_lock, flags); - continue; - } - if (!io_req) { - spin_unlock_irqrestore(io_lock, flags); - continue; - } - - CMD_SP(sc) = NULL; - - spin_unlock_irqrestore(io_lock, flags); + io_lock = fnic_io_lock_tag(fnic, sc->request->tag); + spin_lock_irqsave(io_lock, flags); + io_req = (struct fnic_io_req *)CMD_SP(sc); + if ((CMD_FLAGS(sc) & FNIC_DEVICE_RESET) && + !(CMD_FLAGS(sc) & FNIC_DEV_RST_DONE)) { /* - * If there is a scsi_cmnd associated with this io_req, then - * free the corresponding state + * We will be here only when FW completes reset + * without sending completions for outstanding ios. */ - start_time = io_req->start_time; - fnic_release_ioreq_buf(fnic, io_req, sc); - mempool_free(io_req, fnic->io_req_pool); + CMD_FLAGS(sc) |= FNIC_DEV_RST_DONE; + if (io_req && io_req->dr_done) + complete(io_req->dr_done); + else if (io_req && io_req->abts_done) + complete(io_req->abts_done); + spin_unlock_irqrestore(io_lock, flags); + return true; + } else if (CMD_FLAGS(sc) & FNIC_DEVICE_RESET) { + spin_unlock_irqrestore(io_lock, flags); + return true; + } + if (!io_req) { + spin_unlock_irqrestore(io_lock, flags); + goto cleanup_scsi_cmd; + } - sc->result = DID_TRANSPORT_DISRUPTED << 16; - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, - "%s: tag:0x%x : sc:0x%p duration = %lu DID_TRANSPORT_DISRUPTED\n", - __func__, sc->request->tag, sc, - (jiffies - start_time)); + CMD_SP(sc) = NULL; - if (atomic64_read(&fnic->io_cmpl_skip)) - atomic64_dec(&fnic->io_cmpl_skip); - else - atomic64_inc(&fnic_stats->io_stats.io_completions); + spin_unlock_irqrestore(io_lock, flags); - /* Complete the command to SCSI */ - if (sc->scsi_done) { - if (!(CMD_FLAGS(sc) & FNIC_IO_ISSUED)) - shost_printk(KERN_ERR, fnic->lport->host, - "Calling done for IO not issued to fw: tag:0x%x sc:0x%p\n", - sc->request->tag, sc); + /* + * If there is a scsi_cmnd associated with this io_req, then + * free the corresponding state + */ + start_time = io_req->start_time; + fnic_release_ioreq_buf(fnic, io_req, sc); + mempool_free(io_req, fnic->io_req_pool); - FNIC_TRACE(fnic_cleanup_io, - sc->device->host->host_no, i, sc, - jiffies_to_msecs(jiffies - start_time), - 0, ((u64)sc->cmnd[0] << 32 | - (u64)sc->cmnd[2] << 24 | - (u64)sc->cmnd[3] << 16 | - (u64)sc->cmnd[4] << 8 | sc->cmnd[5]), - (((u64)CMD_FLAGS(sc) << 32) | CMD_STATE(sc))); +cleanup_scsi_cmd: + sc->result = DID_TRANSPORT_DISRUPTED << 16; + FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, + "fnic_cleanup_io: tag:0x%x : sc:0x%p duration = %lu DID_TRANSPORT_DISRUPTED\n", + sc->request->tag, sc, (jiffies - start_time)); - sc->scsi_done(sc); - } + if (atomic64_read(&fnic->io_cmpl_skip)) + atomic64_dec(&fnic->io_cmpl_skip); + else + atomic64_inc(&fnic_stats->io_stats.io_completions); + + /* Complete the command to SCSI */ + if (sc->scsi_done) { + if (!(CMD_FLAGS(sc) & FNIC_IO_ISSUED)) + shost_printk(KERN_ERR, fnic->lport->host, + "Calling done for IO not issued to fw: tag:0x%x sc:0x%p\n", + sc->request->tag, sc); + + FNIC_TRACE(fnic_cleanup_io, + sc->device->host->host_no, sc->request->tag, sc, + jiffies_to_msecs(jiffies - start_time), + 0, ((u64)sc->cmnd[0] << 32 | + (u64)sc->cmnd[2] << 24 | + (u64)sc->cmnd[3] << 16 | + (u64)sc->cmnd[4] << 8 | sc->cmnd[5]), + (((u64)CMD_FLAGS(sc) << 32) | CMD_STATE(sc))); + + sc->scsi_done(sc); } + return true; +} + +static void fnic_cleanup_io(struct fnic *fnic) +{ + scsi_host_busy_iter(fnic->lport->host, + fnic_cleanup_io_iter, fnic); } void fnic_wq_copy_cleanup_handler(struct vnic_wq_copy *wq, @@ -1555,143 +1555,141 @@ static inline int fnic_queue_abort_io_req(struct fnic *fnic, int tag, return 0; } -static void fnic_rport_exch_reset(struct fnic *fnic, u32 port_id) +struct fnic_rport_abort_io_iter_data { + struct fnic *fnic; + u32 port_id; + int term_cnt; +}; + +static bool fnic_rport_abort_io_iter(struct scsi_cmnd *sc, void *data, + bool reserved) { - int tag; - int abt_tag; - int term_cnt = 0; + struct fnic_rport_abort_io_iter_data *iter_data = data; + struct fnic *fnic = iter_data->fnic; + int abt_tag = sc->request->tag; struct fnic_io_req *io_req; spinlock_t *io_lock; unsigned long flags; - struct scsi_cmnd *sc; struct reset_stats *reset_stats = &fnic->fnic_stats.reset_stats; struct terminate_stats *term_stats = &fnic->fnic_stats.term_stats; struct scsi_lun fc_lun; enum fnic_ioreq_state old_ioreq_state; - FNIC_SCSI_DBG(KERN_DEBUG, - fnic->lport->host, - "fnic_rport_exch_reset called portid 0x%06x\n", - port_id); - - if (fnic->in_remove) - return; - - for (tag = 0; tag < fnic->fnic_max_tag_id; tag++) { - abt_tag = tag; - io_lock = fnic_io_lock_tag(fnic, tag); - spin_lock_irqsave(io_lock, flags); - sc = scsi_host_find_tag(fnic->lport->host, tag); - if (!sc) { - spin_unlock_irqrestore(io_lock, flags); - continue; - } + io_lock = fnic_io_lock_tag(fnic, abt_tag); + spin_lock_irqsave(io_lock, flags); - io_req = (struct fnic_io_req *)CMD_SP(sc); + io_req = (struct fnic_io_req *)CMD_SP(sc); - if (!io_req || io_req->port_id != port_id) { - spin_unlock_irqrestore(io_lock, flags); - continue; - } + if (!io_req || io_req->port_id != iter_data->port_id) { + spin_unlock_irqrestore(io_lock, flags); + return true; + } - if ((CMD_FLAGS(sc) & FNIC_DEVICE_RESET) && - (!(CMD_FLAGS(sc) & FNIC_DEV_RST_ISSUED))) { - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, + if ((CMD_FLAGS(sc) & FNIC_DEVICE_RESET) && + (!(CMD_FLAGS(sc) & FNIC_DEV_RST_ISSUED))) { + FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, "fnic_rport_exch_reset dev rst not pending sc 0x%p\n", sc); - spin_unlock_irqrestore(io_lock, flags); - continue; - } + spin_unlock_irqrestore(io_lock, flags); + return true; + } - /* - * Found IO that is still pending with firmware and - * belongs to rport that went away - */ - if (CMD_STATE(sc) == FNIC_IOREQ_ABTS_PENDING) { - spin_unlock_irqrestore(io_lock, flags); - continue; - } - if (io_req->abts_done) { - shost_printk(KERN_ERR, fnic->lport->host, + /* + * Found IO that is still pending with firmware and + * belongs to rport that went away + */ + if (CMD_STATE(sc) == FNIC_IOREQ_ABTS_PENDING) { + spin_unlock_irqrestore(io_lock, flags); + return true; + } + if (io_req->abts_done) { + shost_printk(KERN_ERR, fnic->lport->host, "fnic_rport_exch_reset: io_req->abts_done is set " "state is %s\n", fnic_ioreq_state_to_str(CMD_STATE(sc))); - } + } - if (!(CMD_FLAGS(sc) & FNIC_IO_ISSUED)) { - shost_printk(KERN_ERR, fnic->lport->host, - "rport_exch_reset " - "IO not yet issued %p tag 0x%x flags " - "%x state %d\n", - sc, tag, CMD_FLAGS(sc), CMD_STATE(sc)); - } - old_ioreq_state = CMD_STATE(sc); - CMD_STATE(sc) = FNIC_IOREQ_ABTS_PENDING; - CMD_ABTS_STATUS(sc) = FCPIO_INVALID_CODE; - if (CMD_FLAGS(sc) & FNIC_DEVICE_RESET) { - atomic64_inc(&reset_stats->device_reset_terminates); - abt_tag = (tag | FNIC_TAG_DEV_RST); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, - "fnic_rport_exch_reset dev rst sc 0x%p\n", - sc); - } + if (!(CMD_FLAGS(sc) & FNIC_IO_ISSUED)) { + shost_printk(KERN_ERR, fnic->lport->host, + "rport_exch_reset " + "IO not yet issued %p tag 0x%x flags " + "%x state %d\n", + sc, abt_tag, CMD_FLAGS(sc), CMD_STATE(sc)); + } + old_ioreq_state = CMD_STATE(sc); + CMD_STATE(sc) = FNIC_IOREQ_ABTS_PENDING; + CMD_ABTS_STATUS(sc) = FCPIO_INVALID_CODE; + if (CMD_FLAGS(sc) & FNIC_DEVICE_RESET) { + atomic64_inc(&reset_stats->device_reset_terminates); + abt_tag |= FNIC_TAG_DEV_RST; + } + FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, + "fnic_rport_exch_reset dev rst sc 0x%p\n", sc); + BUG_ON(io_req->abts_done); - BUG_ON(io_req->abts_done); + FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, + "fnic_rport_reset_exch: Issuing abts\n"); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, - "fnic_rport_reset_exch: Issuing abts\n"); + spin_unlock_irqrestore(io_lock, flags); + /* Now queue the abort command to firmware */ + int_to_scsilun(sc->device->lun, &fc_lun); + + if (fnic_queue_abort_io_req(fnic, abt_tag, + FCPIO_ITMF_ABT_TASK_TERM, + fc_lun.scsi_lun, io_req)) { + /* + * Revert the cmd state back to old state, if + * it hasn't changed in between. This cmd will get + * aborted later by scsi_eh, or cleaned up during + * lun reset + */ + spin_lock_irqsave(io_lock, flags); + if (CMD_STATE(sc) == FNIC_IOREQ_ABTS_PENDING) + CMD_STATE(sc) = old_ioreq_state; + spin_unlock_irqrestore(io_lock, flags); + } else { + spin_lock_irqsave(io_lock, flags); + if (CMD_FLAGS(sc) & FNIC_DEVICE_RESET) + CMD_FLAGS(sc) |= FNIC_DEV_RST_TERM_ISSUED; + else + CMD_FLAGS(sc) |= FNIC_IO_INTERNAL_TERM_ISSUED; spin_unlock_irqrestore(io_lock, flags); + atomic64_inc(&term_stats->terminates); + iter_data->term_cnt++; + } + return true; +} - /* Now queue the abort command to firmware */ - int_to_scsilun(sc->device->lun, &fc_lun); +static void fnic_rport_exch_reset(struct fnic *fnic, u32 port_id) +{ + struct terminate_stats *term_stats = &fnic->fnic_stats.term_stats; + struct fnic_rport_abort_io_iter_data iter_data = { + .fnic = fnic, + .port_id = port_id, + .term_cnt = 0, + }; - if (fnic_queue_abort_io_req(fnic, abt_tag, - FCPIO_ITMF_ABT_TASK_TERM, - fc_lun.scsi_lun, io_req)) { - /* - * Revert the cmd state back to old state, if - * it hasn't changed in between. This cmd will get - * aborted later by scsi_eh, or cleaned up during - * lun reset - */ - spin_lock_irqsave(io_lock, flags); - if (CMD_STATE(sc) == FNIC_IOREQ_ABTS_PENDING) - CMD_STATE(sc) = old_ioreq_state; - spin_unlock_irqrestore(io_lock, flags); - } else { - spin_lock_irqsave(io_lock, flags); - if (CMD_FLAGS(sc) & FNIC_DEVICE_RESET) - CMD_FLAGS(sc) |= FNIC_DEV_RST_TERM_ISSUED; - else - CMD_FLAGS(sc) |= FNIC_IO_INTERNAL_TERM_ISSUED; - spin_unlock_irqrestore(io_lock, flags); - atomic64_inc(&term_stats->terminates); - term_cnt++; - } - } - if (term_cnt > atomic64_read(&term_stats->max_terminates)) - atomic64_set(&term_stats->max_terminates, term_cnt); + FNIC_SCSI_DBG(KERN_DEBUG, + fnic->lport->host, + "fnic_rport_exch_reset called portid 0x%06x\n", + port_id); + + if (fnic->in_remove) + return; + + scsi_host_busy_iter(fnic->lport->host, fnic_rport_abort_io_iter, + &iter_data); + if (iter_data.term_cnt > atomic64_read(&term_stats->max_terminates)) + atomic64_set(&term_stats->max_terminates, iter_data.term_cnt); } void fnic_terminate_rport_io(struct fc_rport *rport) { - int tag; - int abt_tag; - int term_cnt = 0; - struct fnic_io_req *io_req; - spinlock_t *io_lock; - unsigned long flags; - struct scsi_cmnd *sc; - struct scsi_lun fc_lun; struct fc_rport_libfc_priv *rdata; struct fc_lport *lport; struct fnic *fnic; - struct fc_rport *cmd_rport; - struct reset_stats *reset_stats; - struct terminate_stats *term_stats; - enum fnic_ioreq_state old_ioreq_state; if (!rport) { printk(KERN_ERR "fnic_terminate_rport_io: rport is NULL\n"); @@ -1719,108 +1717,7 @@ void fnic_terminate_rport_io(struct fc_rport *rport) if (fnic->in_remove) return; - reset_stats = &fnic->fnic_stats.reset_stats; - term_stats = &fnic->fnic_stats.term_stats; - - for (tag = 0; tag < fnic->fnic_max_tag_id; tag++) { - abt_tag = tag; - io_lock = fnic_io_lock_tag(fnic, tag); - spin_lock_irqsave(io_lock, flags); - sc = scsi_host_find_tag(fnic->lport->host, tag); - if (!sc) { - spin_unlock_irqrestore(io_lock, flags); - continue; - } - - io_req = (struct fnic_io_req *)CMD_SP(sc); - if (!io_req) { - spin_unlock_irqrestore(io_lock, flags); - continue; - } - - cmd_rport = starget_to_rport(scsi_target(sc->device)); - if (rport != cmd_rport) { - spin_unlock_irqrestore(io_lock, flags); - continue; - } - - if ((CMD_FLAGS(sc) & FNIC_DEVICE_RESET) && - (!(CMD_FLAGS(sc) & FNIC_DEV_RST_ISSUED))) { - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, - "fnic_terminate_rport_io dev rst not pending sc 0x%p\n", - sc); - spin_unlock_irqrestore(io_lock, flags); - continue; - } - /* - * Found IO that is still pending with firmware and - * belongs to rport that went away - */ - if (CMD_STATE(sc) == FNIC_IOREQ_ABTS_PENDING) { - spin_unlock_irqrestore(io_lock, flags); - continue; - } - if (io_req->abts_done) { - shost_printk(KERN_ERR, fnic->lport->host, - "fnic_terminate_rport_io: io_req->abts_done is set " - "state is %s\n", - fnic_ioreq_state_to_str(CMD_STATE(sc))); - } - if (!(CMD_FLAGS(sc) & FNIC_IO_ISSUED)) { - FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, - "fnic_terminate_rport_io " - "IO not yet issued %p tag 0x%x flags " - "%x state %d\n", - sc, tag, CMD_FLAGS(sc), CMD_STATE(sc)); - } - old_ioreq_state = CMD_STATE(sc); - CMD_STATE(sc) = FNIC_IOREQ_ABTS_PENDING; - CMD_ABTS_STATUS(sc) = FCPIO_INVALID_CODE; - if (CMD_FLAGS(sc) & FNIC_DEVICE_RESET) { - atomic64_inc(&reset_stats->device_reset_terminates); - abt_tag = (tag | FNIC_TAG_DEV_RST); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, - "fnic_terminate_rport_io dev rst sc 0x%p\n", sc); - } - - BUG_ON(io_req->abts_done); - - FNIC_SCSI_DBG(KERN_DEBUG, - fnic->lport->host, - "fnic_terminate_rport_io: Issuing abts\n"); - - spin_unlock_irqrestore(io_lock, flags); - - /* Now queue the abort command to firmware */ - int_to_scsilun(sc->device->lun, &fc_lun); - - if (fnic_queue_abort_io_req(fnic, abt_tag, - FCPIO_ITMF_ABT_TASK_TERM, - fc_lun.scsi_lun, io_req)) { - /* - * Revert the cmd state back to old state, if - * it hasn't changed in between. This cmd will get - * aborted later by scsi_eh, or cleaned up during - * lun reset - */ - spin_lock_irqsave(io_lock, flags); - if (CMD_STATE(sc) == FNIC_IOREQ_ABTS_PENDING) - CMD_STATE(sc) = old_ioreq_state; - spin_unlock_irqrestore(io_lock, flags); - } else { - spin_lock_irqsave(io_lock, flags); - if (CMD_FLAGS(sc) & FNIC_DEVICE_RESET) - CMD_FLAGS(sc) |= FNIC_DEV_RST_TERM_ISSUED; - else - CMD_FLAGS(sc) |= FNIC_IO_INTERNAL_TERM_ISSUED; - spin_unlock_irqrestore(io_lock, flags); - atomic64_inc(&term_stats->terminates); - term_cnt++; - } - } - if (term_cnt > atomic64_read(&term_stats->max_terminates)) - atomic64_set(&term_stats->max_terminates, term_cnt); - + fnic_rport_exch_reset(fnic, rport->port_id); } /* @@ -2115,165 +2012,183 @@ lr_io_req_end: return ret; } -/* - * Clean up any pending aborts on the lun - * For each outstanding IO on this lun, whose abort is not completed by fw, - * issue a local abort. Wait for abort to complete. Return 0 if all commands - * successfully aborted, 1 otherwise - */ -static int fnic_clean_pending_aborts(struct fnic *fnic, - struct scsi_cmnd *lr_sc, - bool new_sc) +struct fnic_pending_aborts_iter_data { + struct fnic *fnic; + struct scsi_cmnd *lr_sc; + struct scsi_device *lun_dev; + int ret; +}; +static bool fnic_pending_aborts_iter(struct scsi_cmnd *sc, + void *data, bool reserved) { - int tag, abt_tag; + struct fnic_pending_aborts_iter_data *iter_data = data; + struct fnic *fnic = iter_data->fnic; + struct scsi_device *lun_dev = iter_data->lun_dev; + int abt_tag = sc->request->tag; struct fnic_io_req *io_req; spinlock_t *io_lock; unsigned long flags; - int ret = 0; - struct scsi_cmnd *sc; struct scsi_lun fc_lun; - struct scsi_device *lun_dev = lr_sc->device; DECLARE_COMPLETION_ONSTACK(tm_done); enum fnic_ioreq_state old_ioreq_state; - for (tag = 0; tag < fnic->fnic_max_tag_id; tag++) { - io_lock = fnic_io_lock_tag(fnic, tag); - spin_lock_irqsave(io_lock, flags); - sc = scsi_host_find_tag(fnic->lport->host, tag); - /* - * ignore this lun reset cmd if issued using new SC - * or cmds that do not belong to this lun - */ - if (!sc || ((sc == lr_sc) && new_sc) || sc->device != lun_dev) { - spin_unlock_irqrestore(io_lock, flags); - continue; - } + if (sc == iter_data->lr_sc || sc->device != lun_dev) + return true; + if (reserved) + return true; - io_req = (struct fnic_io_req *)CMD_SP(sc); - - if (!io_req || sc->device != lun_dev) { - spin_unlock_irqrestore(io_lock, flags); - continue; - } - - /* - * Found IO that is still pending with firmware and - * belongs to the LUN that we are resetting - */ - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, - "Found IO in %s on lun\n", - fnic_ioreq_state_to_str(CMD_STATE(sc))); - - if (CMD_STATE(sc) == FNIC_IOREQ_ABTS_PENDING) { - spin_unlock_irqrestore(io_lock, flags); - continue; - } - if ((CMD_FLAGS(sc) & FNIC_DEVICE_RESET) && - (!(CMD_FLAGS(sc) & FNIC_DEV_RST_ISSUED))) { - FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, - "%s dev rst not pending sc 0x%p\n", __func__, - sc); - spin_unlock_irqrestore(io_lock, flags); - continue; - } + io_lock = fnic_io_lock_tag(fnic, abt_tag); + spin_lock_irqsave(io_lock, flags); + io_req = (struct fnic_io_req *)CMD_SP(sc); + if (!io_req) { + spin_unlock_irqrestore(io_lock, flags); + return true; + } - if (io_req->abts_done) - shost_printk(KERN_ERR, fnic->lport->host, - "%s: io_req->abts_done is set state is %s\n", - __func__, fnic_ioreq_state_to_str(CMD_STATE(sc))); - old_ioreq_state = CMD_STATE(sc); - /* - * Any pending IO issued prior to reset is expected to be - * in abts pending state, if not we need to set - * FNIC_IOREQ_ABTS_PENDING to indicate the IO is abort pending. - * When IO is completed, the IO will be handed over and - * handled in this function. - */ - CMD_STATE(sc) = FNIC_IOREQ_ABTS_PENDING; + /* + * Found IO that is still pending with firmware and + * belongs to the LUN that we are resetting + */ + FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, + "Found IO in %s on lun\n", + fnic_ioreq_state_to_str(CMD_STATE(sc))); - BUG_ON(io_req->abts_done); + if (CMD_STATE(sc) == FNIC_IOREQ_ABTS_PENDING) { + spin_unlock_irqrestore(io_lock, flags); + return true; + } + if ((CMD_FLAGS(sc) & FNIC_DEVICE_RESET) && + (!(CMD_FLAGS(sc) & FNIC_DEV_RST_ISSUED))) { + FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, + "%s dev rst not pending sc 0x%p\n", __func__, + sc); + spin_unlock_irqrestore(io_lock, flags); + return true; + } - abt_tag = tag; - if (CMD_FLAGS(sc) & FNIC_DEVICE_RESET) { - abt_tag |= FNIC_TAG_DEV_RST; - FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, - "%s: dev rst sc 0x%p\n", __func__, sc); - } + if (io_req->abts_done) + shost_printk(KERN_ERR, fnic->lport->host, + "%s: io_req->abts_done is set state is %s\n", + __func__, fnic_ioreq_state_to_str(CMD_STATE(sc))); + old_ioreq_state = CMD_STATE(sc); + /* + * Any pending IO issued prior to reset is expected to be + * in abts pending state, if not we need to set + * FNIC_IOREQ_ABTS_PENDING to indicate the IO is abort pending. + * When IO is completed, the IO will be handed over and + * handled in this function. + */ + CMD_STATE(sc) = FNIC_IOREQ_ABTS_PENDING; - CMD_ABTS_STATUS(sc) = FCPIO_INVALID_CODE; - io_req->abts_done = &tm_done; - spin_unlock_irqrestore(io_lock, flags); + BUG_ON(io_req->abts_done); - /* Now queue the abort command to firmware */ - int_to_scsilun(sc->device->lun, &fc_lun); + if (CMD_FLAGS(sc) & FNIC_DEVICE_RESET) { + abt_tag |= FNIC_TAG_DEV_RST; + FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, + "%s: dev rst sc 0x%p\n", __func__, sc); + } - if (fnic_queue_abort_io_req(fnic, abt_tag, - FCPIO_ITMF_ABT_TASK_TERM, - fc_lun.scsi_lun, io_req)) { - spin_lock_irqsave(io_lock, flags); - io_req = (struct fnic_io_req *)CMD_SP(sc); - if (io_req) - io_req->abts_done = NULL; - if (CMD_STATE(sc) == FNIC_IOREQ_ABTS_PENDING) - CMD_STATE(sc) = old_ioreq_state; - spin_unlock_irqrestore(io_lock, flags); - ret = 1; - goto clean_pending_aborts_end; - } else { - spin_lock_irqsave(io_lock, flags); - if (CMD_FLAGS(sc) & FNIC_DEVICE_RESET) - CMD_FLAGS(sc) |= FNIC_DEV_RST_TERM_ISSUED; - spin_unlock_irqrestore(io_lock, flags); - } - CMD_FLAGS(sc) |= FNIC_IO_INTERNAL_TERM_ISSUED; + CMD_ABTS_STATUS(sc) = FCPIO_INVALID_CODE; + io_req->abts_done = &tm_done; + spin_unlock_irqrestore(io_lock, flags); - wait_for_completion_timeout(&tm_done, - msecs_to_jiffies - (fnic->config.ed_tov)); + /* Now queue the abort command to firmware */ + int_to_scsilun(sc->device->lun, &fc_lun); - /* Recheck cmd state to check if it is now aborted */ + if (fnic_queue_abort_io_req(fnic, abt_tag, + FCPIO_ITMF_ABT_TASK_TERM, + fc_lun.scsi_lun, io_req)) { spin_lock_irqsave(io_lock, flags); io_req = (struct fnic_io_req *)CMD_SP(sc); - if (!io_req) { - spin_unlock_irqrestore(io_lock, flags); - CMD_FLAGS(sc) |= FNIC_IO_ABT_TERM_REQ_NULL; - continue; - } + if (io_req) + io_req->abts_done = NULL; + if (CMD_STATE(sc) == FNIC_IOREQ_ABTS_PENDING) + CMD_STATE(sc) = old_ioreq_state; + spin_unlock_irqrestore(io_lock, flags); + iter_data->ret = FAILED; + return false; + } else { + spin_lock_irqsave(io_lock, flags); + if (CMD_FLAGS(sc) & FNIC_DEVICE_RESET) + CMD_FLAGS(sc) |= FNIC_DEV_RST_TERM_ISSUED; + spin_unlock_irqrestore(io_lock, flags); + } + CMD_FLAGS(sc) |= FNIC_IO_INTERNAL_TERM_ISSUED; - io_req->abts_done = NULL; + wait_for_completion_timeout(&tm_done, msecs_to_jiffies + (fnic->config.ed_tov)); - /* if abort is still pending with fw, fail */ - if (CMD_ABTS_STATUS(sc) == FCPIO_INVALID_CODE) { - spin_unlock_irqrestore(io_lock, flags); - CMD_FLAGS(sc) |= FNIC_IO_ABT_TERM_DONE; - ret = 1; - goto clean_pending_aborts_end; - } - CMD_STATE(sc) = FNIC_IOREQ_ABTS_COMPLETE; + /* Recheck cmd state to check if it is now aborted */ + spin_lock_irqsave(io_lock, flags); + io_req = (struct fnic_io_req *)CMD_SP(sc); + if (!io_req) { + spin_unlock_irqrestore(io_lock, flags); + CMD_FLAGS(sc) |= FNIC_IO_ABT_TERM_REQ_NULL; + return true; + } - /* original sc used for lr is handled by dev reset code */ - if (sc != lr_sc) - CMD_SP(sc) = NULL; + io_req->abts_done = NULL; + + /* if abort is still pending with fw, fail */ + if (CMD_ABTS_STATUS(sc) == FCPIO_INVALID_CODE) { spin_unlock_irqrestore(io_lock, flags); + CMD_FLAGS(sc) |= FNIC_IO_ABT_TERM_DONE; + iter_data->ret = FAILED; + return false; + } + CMD_STATE(sc) = FNIC_IOREQ_ABTS_COMPLETE; - /* original sc used for lr is handled by dev reset code */ - if (sc != lr_sc) { - fnic_release_ioreq_buf(fnic, io_req, sc); - mempool_free(io_req, fnic->io_req_pool); - } + /* original sc used for lr is handled by dev reset code */ + if (sc != iter_data->lr_sc) + CMD_SP(sc) = NULL; + spin_unlock_irqrestore(io_lock, flags); - /* - * Any IO is returned during reset, it needs to call scsi_done - * to return the scsi_cmnd to upper layer. - */ - if (sc->scsi_done) { - /* Set result to let upper SCSI layer retry */ - sc->result = DID_RESET << 16; - sc->scsi_done(sc); - } + /* original sc used for lr is handled by dev reset code */ + if (sc != iter_data->lr_sc) { + fnic_release_ioreq_buf(fnic, io_req, sc); + mempool_free(io_req, fnic->io_req_pool); } + /* + * Any IO is returned during reset, it needs to call scsi_done + * to return the scsi_cmnd to upper layer. + */ + if (sc->scsi_done) { + /* Set result to let upper SCSI layer retry */ + sc->result = DID_RESET << 16; + sc->scsi_done(sc); + } + return true; +} + +/* + * Clean up any pending aborts on the lun + * For each outstanding IO on this lun, whose abort is not completed by fw, + * issue a local abort. Wait for abort to complete. Return 0 if all commands + * successfully aborted, 1 otherwise + */ +static int fnic_clean_pending_aborts(struct fnic *fnic, + struct scsi_cmnd *lr_sc, + bool new_sc) + +{ + int ret = SUCCESS; + struct fnic_pending_aborts_iter_data iter_data = { + .fnic = fnic, + .lun_dev = lr_sc->device, + .ret = SUCCESS, + }; + + if (new_sc) + iter_data.lr_sc = lr_sc; + + scsi_host_busy_iter(fnic->lport->host, + fnic_pending_aborts_iter, &iter_data); + if (iter_data.ret == FAILED) { + ret = iter_data.ret; + goto clean_pending_aborts_end; + } schedule_timeout(msecs_to_jiffies(2 * fnic->config.ed_tov)); /* walk again to check, if IOs are still pending in fw */ @@ -2772,58 +2687,72 @@ call_fc_exch_mgr_reset: } -/* - * fnic_is_abts_pending() is a helper function that - * walks through tag map to check if there is any IOs pending,if there is one, - * then it returns 1 (true), otherwise 0 (false) - * if @lr_sc is non NULL, then it checks IOs specific to particular LUN, - * otherwise, it checks for all IOs. - */ -int fnic_is_abts_pending(struct fnic *fnic, struct scsi_cmnd *lr_sc) +static bool fnic_abts_pending_iter(struct scsi_cmnd *sc, void *data, + bool reserved) { - int tag; + struct fnic_pending_aborts_iter_data *iter_data = data; + struct fnic *fnic = iter_data->fnic; + int cmd_state; struct fnic_io_req *io_req; spinlock_t *io_lock; unsigned long flags; - int ret = 0; - struct scsi_cmnd *sc; - struct scsi_device *lun_dev = NULL; - if (lr_sc) - lun_dev = lr_sc->device; + /* + * ignore this lun reset cmd or cmds that do not belong to + * this lun + */ + if (iter_data->lr_sc && sc == iter_data->lr_sc) + return true; + if (iter_data->lun_dev && sc->device != iter_data->lun_dev) + return true; - /* walk again to check, if IOs are still pending in fw */ - for (tag = 0; tag < fnic->fnic_max_tag_id; tag++) { - sc = scsi_host_find_tag(fnic->lport->host, tag); - /* - * ignore this lun reset cmd or cmds that do not belong to - * this lun - */ - if (!sc || (lr_sc && (sc->device != lun_dev || sc == lr_sc))) - continue; + io_lock = fnic_io_lock_hash(fnic, sc); + spin_lock_irqsave(io_lock, flags); - io_lock = fnic_io_lock_hash(fnic, sc); - spin_lock_irqsave(io_lock, flags); + io_req = (struct fnic_io_req *)CMD_SP(sc); + if (!io_req) { + spin_unlock_irqrestore(io_lock, flags); + return true; + } - io_req = (struct fnic_io_req *)CMD_SP(sc); + /* + * Found IO that is still pending with firmware and + * belongs to the LUN that we are resetting + */ + FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, + "Found IO in %s on lun\n", + fnic_ioreq_state_to_str(CMD_STATE(sc))); + cmd_state = CMD_STATE(sc); + spin_unlock_irqrestore(io_lock, flags); + if (cmd_state == FNIC_IOREQ_ABTS_PENDING) + iter_data->ret = 1; - if (!io_req || sc->device != lun_dev) { - spin_unlock_irqrestore(io_lock, flags); - continue; - } + return iter_data->ret ? false : true; +} - /* - * Found IO that is still pending with firmware and - * belongs to the LUN that we are resetting - */ - FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, - "Found IO in %s on lun\n", - fnic_ioreq_state_to_str(CMD_STATE(sc))); +/* + * fnic_is_abts_pending() is a helper function that + * walks through tag map to check if there is any IOs pending,if there is one, + * then it returns 1 (true), otherwise 0 (false) + * if @lr_sc is non NULL, then it checks IOs specific to particular LUN, + * otherwise, it checks for all IOs. + */ +int fnic_is_abts_pending(struct fnic *fnic, struct scsi_cmnd *lr_sc) +{ + struct fnic_pending_aborts_iter_data iter_data = { + .fnic = fnic, + .lun_dev = NULL, + .ret = 0, + }; - if (CMD_STATE(sc) == FNIC_IOREQ_ABTS_PENDING) - ret = 1; - spin_unlock_irqrestore(io_lock, flags); + if (lr_sc) { + iter_data.lun_dev = lr_sc->device; + iter_data.lr_sc = lr_sc; } - return ret; + /* walk again to check, if IOs are still pending in fw */ + scsi_host_busy_iter(fnic->lport->host, + fnic_abts_pending_iter, &iter_data); + + return iter_data.ret; } -- cgit v1.2.3