From 165aa2bfb42904b1bec4bf2fa257c8c603c14a06 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Mon, 28 Jan 2019 15:24:42 +0100 Subject: scsi: iscsi: flush running unbind operations when removing a session In some cases, the iscsi_remove_session() function is called while an unbind_work operation is still running. This may cause a situation where sysfs objects are removed in an incorrect order, triggering a kernel warning. [ 605.249442] ------------[ cut here ]------------ [ 605.259180] sysfs group 'power' not found for kobject 'target2:0:0' [ 605.321371] WARNING: CPU: 1 PID: 26794 at fs/sysfs/group.c:235 sysfs_remove_group+0x76/0x80 [ 605.341266] Modules linked in: dm_service_time target_core_user target_core_pscsi target_core_file target_core_iblock iscsi_target_mod target_core_mod nls_utf8 isofs ppdev bochs_drm nfit ttm libnvdimm drm_kms_helper syscopyarea sysfillrect sysimgblt joydev pcspkr fb_sys_fops drm i2c_piix4 sg parport_pc parport xfs libcrc32c dm_multipath sr_mod sd_mod cdrom ata_generic 8021q garp mrp ata_piix stp crct10dif_pclmul crc32_pclmul llc libata crc32c_intel virtio_net net_failover ghash_clmulni_intel serio_raw failover sunrpc dm_mirror dm_region_hash dm_log dm_mod be2iscsi bnx2i cnic uio cxgb4i cxgb4 libcxgbi libcxgb qla4xxx iscsi_boot_sysfs iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi [ 605.627479] CPU: 1 PID: 26794 Comm: kworker/u32:2 Not tainted 4.18.0-60.el8.x86_64 #1 [ 605.721401] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20180724_192412-buildhw-07.phx2.fedoraproject.org-1.fc29 04/01/2014 [ 605.823651] Workqueue: scsi_wq_2 __iscsi_unbind_session [scsi_transport_iscsi] [ 605.830940] RIP: 0010:sysfs_remove_group+0x76/0x80 [ 605.922907] Code: 48 89 df 5b 5d 41 5c e9 38 c4 ff ff 48 89 df e8 e0 bf ff ff eb cb 49 8b 14 24 48 8b 75 00 48 c7 c7 38 73 cb a7 e8 24 77 d7 ff <0f> 0b 5b 5d 41 5c c3 0f 1f 00 0f 1f 44 00 00 41 56 41 55 41 54 55 [ 606.122304] RSP: 0018:ffffbadcc8d1bda8 EFLAGS: 00010286 [ 606.218492] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 606.326381] RDX: ffff98bdfe85eb40 RSI: ffff98bdfe856818 RDI: ffff98bdfe856818 [ 606.514498] RBP: ffffffffa7ab73e0 R08: 0000000000000268 R09: 0000000000000007 [ 606.529469] R10: 0000000000000000 R11: ffffffffa860d9ad R12: ffff98bdf978e838 [ 606.630535] R13: ffff98bdc2cd4010 R14: ffff98bdc2cd3ff0 R15: ffff98bdc2cd4000 [ 606.824707] FS: 0000000000000000(0000) GS:ffff98bdfe840000(0000) knlGS:0000000000000000 [ 607.018333] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 607.117844] CR2: 00007f84b78ac024 CR3: 000000002c00a003 CR4: 00000000003606e0 [ 607.117844] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 607.420926] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 607.524236] Call Trace: [ 607.530591] device_del+0x56/0x350 [ 607.624393] ? ata_tlink_match+0x30/0x30 [libata] [ 607.727805] ? attribute_container_device_trigger+0xb4/0xf0 [ 607.829911] scsi_target_reap_ref_release+0x39/0x50 [ 607.928572] scsi_remove_target+0x1a2/0x1d0 [ 608.017350] __iscsi_unbind_session+0xb3/0x160 [scsi_transport_iscsi] [ 608.117435] process_one_work+0x1a7/0x360 [ 608.132917] worker_thread+0x30/0x390 [ 608.222900] ? pwq_unbound_release_workfn+0xd0/0xd0 [ 608.323989] kthread+0x112/0x130 [ 608.418318] ? kthread_bind+0x30/0x30 [ 608.513821] ret_from_fork+0x35/0x40 [ 608.613909] ---[ end trace 0b98c310c8a6138c ]--- Signed-off-by: Maurizio Lombardi Acked-by: Chris Leech Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_transport_iscsi.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers') diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 0508831d6fb9..0a82e93566dc 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -2200,6 +2200,8 @@ void iscsi_remove_session(struct iscsi_cls_session *session) scsi_target_unblock(&session->dev, SDEV_TRANSPORT_OFFLINE); /* flush running scans then delete devices */ flush_work(&session->scan_work); + /* flush running unbind operations */ + flush_work(&session->unbind_work); __iscsi_unbind_session(&session->unbind_work); /* hw iscsi may not have removed all connections from session */ -- cgit v1.2.3 From db983f6eef57a9d78af79bc32389b7e60eb3c47d Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 18 Mar 2019 09:29:26 -0700 Subject: scsi: core: Also call destroy_rcu_head() for passthrough requests cmd->rcu is initialized by scsi_initialize_rq(). For passthrough requests, blk_get_request() calls scsi_initialize_rq(). For filesystem requests, scsi_init_command() calls scsi_initialize_rq(). Make sure that destroy_rcu_head() is called for passthrough requests. Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Ewan D. Milne Cc: Johannes Thumshirn Reported-by: Ewan D. Milne Signed-off-by: Bart Van Assche Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_lib.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 20189675677a..f0db2dd0be75 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -585,9 +585,16 @@ static bool scsi_end_request(struct request *req, blk_status_t error, if (!blk_rq_is_scsi(req)) { WARN_ON_ONCE(!(cmd->flags & SCMD_INITIALIZED)); cmd->flags &= ~SCMD_INITIALIZED; - destroy_rcu_head(&cmd->rcu); } + /* + * Calling rcu_barrier() is not necessary here because the + * SCSI error handler guarantees that the function called by + * call_rcu() has been called before scsi_end_request() is + * called. + */ + destroy_rcu_head(&cmd->rcu); + /* * In the MQ case the command gets freed by __blk_mq_end_request, * so we have to do all cleanup that depends on it earlier. -- cgit v1.2.3 From 17605afaae825b0291f80c62a7f6565879edaa8a Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 15 Mar 2019 16:27:58 -0700 Subject: scsi: core: Avoid that a kernel warning appears during system resume Since scsi_device_quiesce() skips SCSI devices that have another state than RUNNING, OFFLINE or TRANSPORT_OFFLINE, scsi_device_resume() should not complain about SCSI devices that have been skipped. Hence this patch. This patch avoids that the following warning appears during resume: WARNING: CPU: 3 PID: 1039 at blk_clear_pm_only+0x2a/0x30 CPU: 3 PID: 1039 Comm: kworker/u8:49 Not tainted 5.0.0+ #1 Hardware name: LENOVO 4180F42/4180F42, BIOS 83ET75WW (1.45 ) 05/10/2013 Workqueue: events_unbound async_run_entry_fn RIP: 0010:blk_clear_pm_only+0x2a/0x30 Call Trace: ? scsi_device_resume+0x28/0x50 ? scsi_dev_type_resume+0x2b/0x80 ? async_run_entry_fn+0x2c/0xd0 ? process_one_work+0x1f0/0x3f0 ? worker_thread+0x28/0x3c0 ? process_one_work+0x3f0/0x3f0 ? kthread+0x10c/0x130 ? __kthread_create_on_node+0x150/0x150 ? ret_from_fork+0x1f/0x30 Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Ming Lei Cc: Johannes Thumshirn Cc: Oleksandr Natalenko Cc: Martin Steigerwald Cc: Reported-by: Jisheng Zhang Tested-by: Jisheng Zhang Fixes: 3a0a529971ec ("block, scsi: Make SCSI quiesce and resume work reliably") # v4.15 Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_lib.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index f0db2dd0be75..601b9f1de267 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -2548,8 +2548,10 @@ void scsi_device_resume(struct scsi_device *sdev) * device deleted during suspend) */ mutex_lock(&sdev->state_mutex); - sdev->quiesced_by = NULL; - blk_clear_pm_only(sdev->request_queue); + if (sdev->quiesced_by) { + sdev->quiesced_by = NULL; + blk_clear_pm_only(sdev->request_queue); + } if (sdev->sdev_state == SDEV_QUIESCE) scsi_device_set_state(sdev, SDEV_RUNNING); mutex_unlock(&sdev->state_mutex); -- cgit v1.2.3 From 4705f10e82c63924bd84a9b31d15839ec9ba3d06 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 15 Mar 2019 15:04:18 -0700 Subject: scsi: qla2xxx: Fix FC-AL connection target discovery Commit 7f147f9bfd44 ("scsi: qla2xxx: Fix N2N target discovery with Local loop") fixed N2N target discovery for local loop. However, same code is used for FC-AL discovery as well. Added check to make sure we are bypassing area and domain check only in N2N topology for target discovery. Fixes: 7f147f9bfd44 ("scsi: qla2xxx: Fix N2N target discovery with Local loop") Cc: stable@vger.kernel.org # 5.0+ Signed-off-by: Quinn Tran Signed-off-by: Himanshu Madhani Reviewed-by: Ewan D. Milne Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_init.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'drivers') diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 420045155ba0..0c700b140ce7 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -4991,6 +4991,13 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha) if ((domain & 0xf0) == 0xf0) continue; + /* Bypass if not same domain and area of adapter. */ + if (area && domain && ((area != vha->d_id.b.area) || + (domain != vha->d_id.b.domain)) && + (ha->current_topology == ISP_CFG_NL)) + continue; + + /* Bypass invalid local loop ID. */ if (loop_id > LAST_LOCAL_LOOP_ID) continue; -- cgit v1.2.3 From ac444b4f0ace05d7c4c99f6b1e5b0cae0852f025 Mon Sep 17 00:00:00 2001 From: Himanshu Madhani Date: Fri, 15 Mar 2019 15:04:19 -0700 Subject: scsi: qla2xxx: Fix NULL pointer crash due to stale CPUID This patch fixes crash due to NULL pointer derefrence because CPU pointer is not set and used by driver. Instead, driver is passes CPU as tag via ha->isp_ops->{lun_reset|target_reset} [ 30.160780] qla2xxx [0000:a0:00.1]-8038:9: Cable is unplugged... [ 69.984045] qla2xxx [0000:a0:00.0]-8009:8: DEVICE RESET ISSUED nexus=8:0:0 cmd=00000000b0d62f46. [ 69.992849] BUG: unable to handle kernel NULL pointer dereference at 0000000000000040 [ 70.000680] PGD 0 P4D 0 [ 70.003232] Oops: 0000 [#1] SMP PTI [ 70.006727] CPU: 2 PID: 6714 Comm: sg_reset Kdump: loaded Not tainted 4.18.0-67.el8.x86_64 #1 [ 70.015258] Hardware name: NEC Express5800/T110j [N8100-2758Y]/MX32-PH0-NJ, BIOS F11 02/13/2019 [ 70.024016] RIP: 0010:blk_mq_rq_cpu+0x9/0x10 [ 70.028315] Code: 01 58 01 00 00 48 83 c0 28 48 3d 80 02 00 00 75 ab c3 0f 1f 44 00 00 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 8b 47 08 <8b> 40 40 c3 0f 1f 00 0f 1f 44 00 00 48 83 ec 10 48 c7 c6 20 6e 7c [ 70.047087] RSP: 0018:ffff99a481487d58 EFLAGS: 00010246 [ 70.052322] RAX: 0000000000000000 RBX: ffffffffc041b08b RCX: 0000000000000000 [ 70.059466] RDX: 0000000000000000 RSI: ffff8d10b6b16898 RDI: ffff8d10b341e400 [ 70.066615] RBP: ffffffffc03a6bd0 R08: 0000000000000415 R09: 0000000000aaaaaa [ 70.073765] R10: 0000000000000001 R11: 0000000000000001 R12: ffff8d10b341e528 [ 70.080914] R13: ffff8d10aadefc00 R14: ffff8d0f64efa998 R15: ffff8d0f64efa000 [ 70.088083] FS: 00007f90a201e540(0000) GS:ffff8d10b6b00000(0000) knlGS:0000000000000000 [ 70.096188] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 70.101959] CR2: 0000000000000040 CR3: 0000000268886005 CR4: 00000000003606e0 [ 70.109127] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 70.116277] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 70.123425] Call Trace: [ 70.125896] __qla2xxx_eh_generic_reset+0xb1/0x220 [qla2xxx] [ 70.131572] scsi_ioctl_reset+0x1f5/0x2a0 [ 70.135600] scsi_ioctl+0x18e/0x397 [ 70.139099] ? sd_ioctl+0x7c/0x100 [sd_mod] [ 70.143287] blkdev_ioctl+0x32b/0x9f0 [ 70.146954] ? __check_object_size+0xa3/0x181 [ 70.151323] block_ioctl+0x39/0x40 [ 70.154735] do_vfs_ioctl+0xa4/0x630 [ 70.158322] ? syscall_trace_enter+0x1d3/0x2c0 [ 70.162769] ksys_ioctl+0x60/0x90 [ 70.166104] __x64_sys_ioctl+0x16/0x20 [ 70.169859] do_syscall_64+0x5b/0x1b0 [ 70.173532] entry_SYSCALL_64_after_hwframe+0x65/0xca [ 70.178587] RIP: 0033:0x7f90a1b3445b [ 70.182183] Code: 0f 1e fa 48 8b 05 2d aa 2c 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 0f 1f 44 00 00 f3 0f 1e fa b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d fd a9 2c 00 f7 d8 64 89 01 48 [ 70.200956] RSP: 002b:00007fffdca88b68 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [ 70.208535] RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f90a1b3445b [ 70.215684] RDX: 00007fffdca88b84 RSI: 0000000000002284 RDI: 0000000000000003 [ 70.222833] RBP: 00007fffdca88ca8 R08: 00007fffdca88b84 R09: 0000000000000000 [ 70.229981] R10: 0000000000000000 R11: 0000000000000246 R12: 00007fffdca88b84 [ 70.237131] R13: 0000000000000000 R14: 000055ab09b0bd28 R15: 0000000000000000 [ 70.244284] Modules linked in: nft_chain_route_ipv4 xt_CHECKSUM nft_chain_nat_ipv4 ipt_MASQUERADE nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack libcrc32c ipt_REJECT nf_reject_ipv4 nft_counter nft_compat tun bridge stp llc nf_tables nfnetli nk devlink sunrpc vfat fat intel_rapl intel_pmc_core x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm wmi_bmof iTCO_wdt iTCO_ vendor_support irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel ipmi_ssif intel_cstate intel_uncore intel_rapl_perf ipmi_si jo ydev pcspkr ipmi_devintf sg wmi ipmi_msghandler video acpi_power_meter acpi_pad mei_me i2c_i801 mei ip_tables ext4 mbcache jbd2 sr_mod cd rom sd_mod qla2xxx ast i2c_algo_bit drm_kms_helper nvme_fc syscopyarea sysfillrect uas sysimgblt fb_sys_fops nvme_fabrics ttm [ 70.314805] usb_storage nvme_core crc32c_intel scsi_transport_fc ahci drm libahci tg3 libata megaraid_sas pinctrl_cannonlake pinctrl_ intel [ 70.327335] CR2: 0000000000000040 Fixes: 9cf2bab630765 ("block: kill request ->cpu member") Signed-off-by: Himanshu Madhani Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_os.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 677f82fdf56f..91f576d743fe 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1517,7 +1517,7 @@ __qla2xxx_eh_generic_reset(char *name, enum nexus_wait_type type, goto eh_reset_failed; } err = 2; - if (do_reset(fcport, cmd->device->lun, blk_mq_rq_cpu(cmd->request) + 1) + if (do_reset(fcport, cmd->device->lun, 1) != QLA_SUCCESS) { ql_log(ql_log_warn, vha, 0x800c, "do_reset failed for cmd=%p.\n", cmd); -- cgit v1.2.3 From 0e83fc61eee62979260f6aeadd23ee8b615ee1a2 Mon Sep 17 00:00:00 2001 From: Luo Jiaxing Date: Wed, 20 Mar 2019 18:21:34 +0800 Subject: scsi: hisi_sas: Add softreset in hisi_sas_I_T_nexus_reset() We found out that for v2 hw, a SATA disk can not be written to after the system comes up. In commit ffb1c820b8b6 ("scsi: hisi_sas: remove the check of sas_dev status in hisi_sas_I_T_nexus_reset()"), we introduced a path where we may issue an internal abort for a SATA device, but without following it with a softreset. We need to always follow an internal abort with a software reset, as per HW programming flow, so add this. Fixes: ffb1c820b8b6 ("scsi: hisi_sas: remove the check of sas_dev status in hisi_sas_I_T_nexus_reset()") Signed-off-by: Luo Jiaxing Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- drivers/scsi/hisi_sas/hisi_sas_main.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'drivers') diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index 3c3cf89f713f..14bac4966c87 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -1801,6 +1801,12 @@ static int hisi_sas_I_T_nexus_reset(struct domain_device *device) } hisi_sas_dereg_device(hisi_hba, device); + if (dev_is_sata(device)) { + rc = hisi_sas_softreset_ata_disk(device); + if (rc) + return TMF_RESP_FUNC_FAILED; + } + rc = hisi_sas_debug_I_T_nexus_reset(device); if ((rc == TMF_RESP_FUNC_COMPLETE) || (rc == -ENODEV)) -- cgit v1.2.3 From 7205981e045e752ccf96cf6ddd703a98c59d4339 Mon Sep 17 00:00:00 2001 From: Tyrel Datwyler Date: Wed, 20 Mar 2019 13:41:50 -0500 Subject: scsi: ibmvscsi: Protect ibmvscsi_head from concurrent modificaiton For each ibmvscsi host created during a probe or destroyed during a remove we either add or remove that host to/from the global ibmvscsi_head list. This runs the risk of concurrent modification. This patch adds a simple spinlock around the list modification calls to prevent concurrent updates as is done similarly in the ibmvfc driver and ipr driver. Fixes: 32d6e4b6e4ea ("scsi: ibmvscsi: add vscsi hosts to global list_head") Cc: # v4.10+ Signed-off-by: Tyrel Datwyler Signed-off-by: Martin K. Petersen --- drivers/scsi/ibmvscsi/ibmvscsi.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'drivers') diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c index 1135e74646e2..2b22969f3f63 100644 --- a/drivers/scsi/ibmvscsi/ibmvscsi.c +++ b/drivers/scsi/ibmvscsi/ibmvscsi.c @@ -96,6 +96,7 @@ static int client_reserve = 1; static char partition_name[96] = "UNKNOWN"; static unsigned int partition_number = -1; static LIST_HEAD(ibmvscsi_head); +static DEFINE_SPINLOCK(ibmvscsi_driver_lock); static struct scsi_transport_template *ibmvscsi_transport_template; @@ -2270,7 +2271,9 @@ static int ibmvscsi_probe(struct vio_dev *vdev, const struct vio_device_id *id) } dev_set_drvdata(&vdev->dev, hostdata); + spin_lock(&ibmvscsi_driver_lock); list_add_tail(&hostdata->host_list, &ibmvscsi_head); + spin_unlock(&ibmvscsi_driver_lock); return 0; add_srp_port_failed: @@ -2292,7 +2295,9 @@ static int ibmvscsi_probe(struct vio_dev *vdev, const struct vio_device_id *id) static int ibmvscsi_remove(struct vio_dev *vdev) { struct ibmvscsi_host_data *hostdata = dev_get_drvdata(&vdev->dev); + spin_lock(&ibmvscsi_driver_lock); list_del(&hostdata->host_list); + spin_unlock(&ibmvscsi_driver_lock); unmap_persist_bufs(hostdata); release_event_pool(&hostdata->pool, hostdata); ibmvscsi_release_crq_queue(&hostdata->queue, hostdata, -- cgit v1.2.3 From 7f5203c13ba8a7b7f9f6ecfe5a4d5567188d7835 Mon Sep 17 00:00:00 2001 From: Tyrel Datwyler Date: Wed, 20 Mar 2019 13:41:51 -0500 Subject: scsi: ibmvscsi: Fix empty event pool access during host removal The event pool used for queueing commands is destroyed fairly early in the ibmvscsi_remove() code path. Since, this happens prior to the call so scsi_remove_host() it is possible for further calls to queuecommand to be processed which manifest as a panic due to a NULL pointer dereference as seen here: PANIC: "Unable to handle kernel paging request for data at address 0x00000000" Context process backtrace: DSISR: 0000000042000000 ????Syscall Result: 0000000000000000 4 [c000000002cb3820] memcpy_power7 at c000000000064204 [Link Register] [c000000002cb3820] ibmvscsi_send_srp_event at d000000003ed14a4 5 [c000000002cb3920] ibmvscsi_send_srp_event at d000000003ed14a4 [ibmvscsi] ?(unreliable) 6 [c000000002cb39c0] ibmvscsi_queuecommand at d000000003ed2388 [ibmvscsi] 7 [c000000002cb3a70] scsi_dispatch_cmd at d00000000395c2d8 [scsi_mod] 8 [c000000002cb3af0] scsi_request_fn at d00000000395ef88 [scsi_mod] 9 [c000000002cb3be0] __blk_run_queue at c000000000429860 10 [c000000002cb3c10] blk_delay_work at c00000000042a0ec 11 [c000000002cb3c40] process_one_work at c0000000000dac30 12 [c000000002cb3cd0] worker_thread at c0000000000db110 13 [c000000002cb3d80] kthread at c0000000000e3378 14 [c000000002cb3e30] ret_from_kernel_thread at c00000000000982c The kernel buffer log is overfilled with this log: [11261.952732] ibmvscsi: found no event struct in pool! This patch reorders the operations during host teardown. Start by calling the SRP transport and Scsi_Host remove functions to flush any outstanding work and set the host offline. LLDD teardown follows including destruction of the event pool, freeing the Command Response Queue (CRQ), and unmapping any persistent buffers. The event pool destruction is protected by the scsi_host lock, and the pool is purged prior of any requests for which we never received a response. Finally, move the removal of the scsi host from our global list to the end so that the host is easily locatable for debugging purposes during teardown. Cc: # v2.6.12+ Signed-off-by: Tyrel Datwyler Signed-off-by: Martin K. Petersen --- drivers/scsi/ibmvscsi/ibmvscsi.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) (limited to 'drivers') diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c index 2b22969f3f63..8cec5230fe31 100644 --- a/drivers/scsi/ibmvscsi/ibmvscsi.c +++ b/drivers/scsi/ibmvscsi/ibmvscsi.c @@ -2295,17 +2295,27 @@ static int ibmvscsi_probe(struct vio_dev *vdev, const struct vio_device_id *id) static int ibmvscsi_remove(struct vio_dev *vdev) { struct ibmvscsi_host_data *hostdata = dev_get_drvdata(&vdev->dev); - spin_lock(&ibmvscsi_driver_lock); - list_del(&hostdata->host_list); - spin_unlock(&ibmvscsi_driver_lock); - unmap_persist_bufs(hostdata); + unsigned long flags; + + srp_remove_host(hostdata->host); + scsi_remove_host(hostdata->host); + + purge_requests(hostdata, DID_ERROR); + + spin_lock_irqsave(hostdata->host->host_lock, flags); release_event_pool(&hostdata->pool, hostdata); + spin_unlock_irqrestore(hostdata->host->host_lock, flags); + ibmvscsi_release_crq_queue(&hostdata->queue, hostdata, max_events); kthread_stop(hostdata->work_thread); - srp_remove_host(hostdata->host); - scsi_remove_host(hostdata->host); + unmap_persist_bufs(hostdata); + + spin_lock(&ibmvscsi_driver_lock); + list_del(&hostdata->host_list); + spin_unlock(&ibmvscsi_driver_lock); + scsi_host_put(hostdata->host); return 0; -- cgit v1.2.3 From c2fe742ff6e77c5b4fe4ad273191ddf28fdea25e Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Mon, 4 Mar 2019 07:26:35 -0500 Subject: scsi: mpt3sas: Fix kernel panic during expander reset During expander reset handling, the driver invokes kernel function scsi_host_find_tag() to obtain outstanding requests associated with the scsi host managed by the driver. Driver loops from tag value zero to hba queue depth to obtain the outstanding scmds. But when blk-mq is enabled, the block layer may return stale entry for one or more requests. This may lead to kernel panic if the returned value is inaccessible or the memory pointed by the returned value is reused. Reference of upstream discussion: https://patchwork.kernel.org/patch/10734933/ Instead of calling scsi_host_find_tag() API for each and every smid (smid is tag +1) from one to shost->can_queue, now driver will call this API (to obtain the outstanding scmd) only for those smid's which are outstanding at the driver level. Driver will determine whether this smid is outstanding at driver level by looking into it's corresponding MPI request frame, if its MPI request frame is empty, then it means that this smid is free and does not need to call scsi_host_find_tag() for it. By doing this, driver will invoke scsi_host_find_tag() for only those tags which are outstanding at the driver level. Driver will check whether particular MPI request frame is empty or not by looking into the "DevHandle" field. If this field is zero then it means that this MPI request is empty. For active MPI request DevHandle must be non-zero. Also driver will memset the MPI request frame once the corresponding scmd is processed (i.e. just before calling scmd->done function). Signed-off-by: Sreekanth Reddy Signed-off-by: Martin K. Petersen --- drivers/scsi/mpt3sas/mpt3sas_base.c | 6 ++++++ drivers/scsi/mpt3sas/mpt3sas_scsih.c | 12 ++++++++++++ 2 files changed, 18 insertions(+) (limited to 'drivers') diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index e57774472e75..1d8c584ec1e9 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -3281,12 +3281,18 @@ mpt3sas_base_free_smid(struct MPT3SAS_ADAPTER *ioc, u16 smid) if (smid < ioc->hi_priority_smid) { struct scsiio_tracker *st; + void *request; st = _get_st_from_smid(ioc, smid); if (!st) { _base_recovery_check(ioc); return; } + + /* Clear MPI request frame */ + request = mpt3sas_base_get_msg_frame(ioc, smid); + memset(request, 0, ioc->request_sz); + mpt3sas_base_clear_st(ioc, st); _base_recovery_check(ioc); return; diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 8bb5b8f9f4d2..1ccfbc7eebe0 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -1462,11 +1462,23 @@ mpt3sas_scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc, u16 smid) { struct scsi_cmnd *scmd = NULL; struct scsiio_tracker *st; + Mpi25SCSIIORequest_t *mpi_request; if (smid > 0 && smid <= ioc->scsiio_depth - INTERNAL_SCSIIO_CMDS_COUNT) { u32 unique_tag = smid - 1; + mpi_request = mpt3sas_base_get_msg_frame(ioc, smid); + + /* + * If SCSI IO request is outstanding at driver level then + * DevHandle filed must be non-zero. If DevHandle is zero + * then it means that this smid is free at driver level, + * so return NULL. + */ + if (!mpi_request->DevHandle) + return scmd; + scmd = scsi_host_find_tag(ioc->shost, unique_tag); if (scmd) { st = scsi_cmd_priv(scmd); -- cgit v1.2.3 From b6554cfe09e1f610aed7d57164ab7760be57acd9 Mon Sep 17 00:00:00 2001 From: Dave Carroll Date: Fri, 22 Mar 2019 12:16:03 -0600 Subject: scsi: aacraid: Insure we don't access PCIe space during AER/EEH There are a few windows during AER/EEH when we can access PCIe I/O mapped registers. This will harden the access to insure we do not allow PCIe access during errors Signed-off-by: Dave Carroll Reviewed-by: Sagar Biradar Signed-off-by: Martin K. Petersen --- drivers/scsi/aacraid/aacraid.h | 7 ++++++- drivers/scsi/aacraid/commsup.c | 4 ++-- 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'drivers') diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 1df5171594b8..11fb68d7e60d 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -2640,9 +2640,14 @@ static inline unsigned int cap_to_cyls(sector_t capacity, unsigned divisor) return capacity; } +static inline int aac_pci_offline(struct aac_dev *dev) +{ + return pci_channel_offline(dev->pdev) || dev->handle_pci_error; +} + static inline int aac_adapter_check_health(struct aac_dev *dev) { - if (unlikely(pci_channel_offline(dev->pdev))) + if (unlikely(aac_pci_offline(dev))) return -1; return (dev)->a_ops.adapter_check_health(dev); diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index e67e032936ef..78430a7b294c 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -672,7 +672,7 @@ int aac_fib_send(u16 command, struct fib *fibptr, unsigned long size, return -ETIMEDOUT; } - if (unlikely(pci_channel_offline(dev->pdev))) + if (unlikely(aac_pci_offline(dev))) return -EFAULT; if ((blink = aac_adapter_check_health(dev)) > 0) { @@ -772,7 +772,7 @@ int aac_hba_send(u8 command, struct fib *fibptr, fib_callback callback, spin_unlock_irqrestore(&fibptr->event_lock, flags); - if (unlikely(pci_channel_offline(dev->pdev))) + if (unlikely(aac_pci_offline(dev))) return -EFAULT; fibptr->flags |= FIB_CONTEXT_FLAG_WAIT; -- cgit v1.2.3 From fba1bdd2a9a93f3e2181ec1936a3c2f6b37e7ed6 Mon Sep 17 00:00:00 2001 From: Kangjie Lu Date: Thu, 14 Mar 2019 01:30:59 -0500 Subject: scsi: qla4xxx: fix a potential NULL pointer dereference In case iscsi_lookup_endpoint fails, the fix returns -EINVAL to avoid NULL pointer dereference. Signed-off-by: Kangjie Lu Acked-by: Manish Rangankar Reviewed-by: Mukesh Ojha Signed-off-by: Martin K. Petersen --- drivers/scsi/qla4xxx/ql4_os.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers') diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index 16a18d5d856f..6e4f4931ae17 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -3203,6 +3203,8 @@ static int qla4xxx_conn_bind(struct iscsi_cls_session *cls_session, if (iscsi_conn_bind(cls_session, cls_conn, is_leading)) return -EINVAL; ep = iscsi_lookup_endpoint(transport_fd); + if (!ep) + return -EINVAL; conn = cls_conn->dd_data; qla_conn = conn->dd_data; qla_conn->qla_ep = ep->dd_data; -- cgit v1.2.3 From 70fc085c5015c54a7b8742a45fc9ab05d6da90da Mon Sep 17 00:00:00 2001 From: zhengbin Date: Fri, 22 Mar 2019 10:56:46 +0800 Subject: scsi: core: Run queue when state is set to running after being blocked Use dd to test a SCSI device: 1. echo "blocked" >/sys/block/sda/device/state 2. dd if=/dev/sda of=/mnt/t.log bs=1M count=10 3. echo "running" >/sys/block/sda/device/state dd should finish this work after step 3, but it hangs. After step2, the call chain is this: blk_mq_dispatch_rq_list-->scsi_queue_rq-->prep_to_mq prep_to_mq will return BLK_STS_RESOURCE, and scsi_queue_rq will transition it to BLK_STS_DEV_RESOURCE which means that driver can guarantee that IO dispatch will be triggered in future when the resource is available. Need to follow the rule if we set the device state to running. [mkp: tweaked commit description and code comment as suggested by Bart] Signed-off-by: zhengbin Reviewed-by: Ming Lei Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_sysfs.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'drivers') diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 6a9040faed00..3b119ca0cc0c 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -771,6 +771,12 @@ store_state_field(struct device *dev, struct device_attribute *attr, mutex_lock(&sdev->state_mutex); ret = scsi_device_set_state(sdev, state); + /* + * If the device state changes to SDEV_RUNNING, we need to run + * the queue to avoid I/O hang. + */ + if (ret == 0 && state == SDEV_RUNNING) + blk_mq_run_hw_queues(sdev->request_queue, true); mutex_unlock(&sdev->state_mutex); return ret == 0 ? count : -EINVAL; -- cgit v1.2.3 From c14a57264399efd39514a2329c591a4b954246d8 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 25 Mar 2019 10:01:46 -0700 Subject: scsi: sd: Fix a race between closing an sd device and sd I/O The scsi_end_request() function calls scsi_cmd_to_driver() indirectly and hence needs the disk->private_data pointer. Avoid that that pointer is cleared before all affected I/O requests have finished. This patch avoids that the following crash occurs: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 Call trace: scsi_mq_uninit_cmd+0x1c/0x30 scsi_end_request+0x7c/0x1b8 scsi_io_completion+0x464/0x668 scsi_finish_command+0xbc/0x160 scsi_eh_flush_done_q+0x10c/0x170 sas_scsi_recover_host+0x84c/0xa98 [libsas] scsi_error_handler+0x140/0x5b0 kthread+0x100/0x12c ret_from_fork+0x10/0x18 Cc: Christoph Hellwig Cc: Ming Lei Cc: Hannes Reinecke Cc: Johannes Thumshirn Cc: Jason Yan Cc: Signed-off-by: Bart Van Assche Reported-by: Jason Yan Reviewed-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- drivers/scsi/sd.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) (limited to 'drivers') diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 251db30d0882..3ffa34dc2fd5 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1415,11 +1415,6 @@ static void sd_release(struct gendisk *disk, fmode_t mode) scsi_set_medium_removal(sdev, SCSI_REMOVAL_ALLOW); } - /* - * XXX and what if there are packets in flight and this close() - * XXX is followed by a "rmmod sd_mod"? - */ - scsi_disk_put(sdkp); } @@ -3505,9 +3500,21 @@ static void scsi_disk_release(struct device *dev) { struct scsi_disk *sdkp = to_scsi_disk(dev); struct gendisk *disk = sdkp->disk; - + struct request_queue *q = disk->queue; + ida_free(&sd_index_ida, sdkp->index); + /* + * Wait until all requests that are in progress have completed. + * This is necessary to avoid that e.g. scsi_end_request() crashes + * due to clearing the disk->private_data pointer. Wait from inside + * scsi_disk_release() instead of from sd_release() to avoid that + * freezing and unfreezing the request queue affects user space I/O + * in case multiple processes open a /dev/sd... node concurrently. + */ + blk_mq_freeze_queue(q); + blk_mq_unfreeze_queue(q); + disk->private_data = NULL; put_disk(disk); put_device(&sdkp->device->sdev_gendev); -- cgit v1.2.3 From 1d5de5bd311be7cd54f02f7cd164f0349a75c876 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 27 Mar 2019 12:11:52 -0400 Subject: scsi: sd: Quiesce warning if device does not report optimal I/O size Commit a83da8a4509d ("scsi: sd: Optimal I/O size should be a multiple of physical block size") split one conditional into several separate statements in an effort to provide more accurate warning messages when a device reports a nonsensical value. However, this reorganization accidentally dropped the precondition of the reported value being larger than zero. This lead to a warning getting emitted on devices that do not report an optimal I/O size at all. Remain silent if a device does not report an optimal I/O size. Fixes: a83da8a4509d ("scsi: sd: Optimal I/O size should be a multiple of physical block size") Cc: Randy Dunlap Cc: Reported-by: Hussam Al-Tayeb Tested-by: Hussam Al-Tayeb Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/sd.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers') diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 3ffa34dc2fd5..2b2bc4b49d78 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3071,6 +3071,9 @@ static bool sd_validate_opt_xfer_size(struct scsi_disk *sdkp, unsigned int opt_xfer_bytes = logical_to_bytes(sdp, sdkp->opt_xfer_blocks); + if (sdkp->opt_xfer_blocks == 0) + return false; + if (sdkp->opt_xfer_blocks > dev_max) { sd_first_printk(KERN_WARNING, sdkp, "Optimal transfer size %u logical blocks " \ -- cgit v1.2.3 From fe67888fc007a76b81e37da23ce5bd8fb95890b0 Mon Sep 17 00:00:00 2001 From: Steffen Maier Date: Tue, 26 Mar 2019 14:36:58 +0100 Subject: scsi: zfcp: fix rport unblock if deleted SCSI devices on Scsi_Host An already deleted SCSI device can exist on the Scsi_Host and remain there because something still holds a reference. A new SCSI device with the same H:C:T:L and FCP device, target port WWPN, and FCP LUN can be created. When we try to unblock an rport, we still find the deleted SCSI device and return early because the zfcp_scsi_dev of that SCSI device is not ZFCP_STATUS_COMMON_UNBLOCKED. Hence we miss to unblock the rport, even if the new proper SCSI device would be in good state. Therefore, skip deleted SCSI devices when iterating the sdevs of the shost. [cf. __scsi_device_lookup{_by_target}() or scsi_device_get()] The following abbreviated trace sequence can indicate such problem: Area : REC Tag : ersfs_3 LUN : 0x4045400300000000 WWPN : 0x50050763031bd327 LUN status : 0x40000000 not ZFCP_STATUS_COMMON_UNBLOCKED Ready count : n not incremented yet Running count : 0x00000000 ERP want : 0x01 ERP need : 0xc1 ZFCP_ERP_ACTION_NONE Area : REC Tag : ersfs_3 LUN : 0x4045400300000000 WWPN : 0x50050763031bd327 LUN status : 0x41000000 Ready count : n+1 Running count : 0x00000000 ERP want : 0x01 ERP need : 0x01 ... Area : REC Level : 4 only with increased trace level Tag : ertru_l LUN : 0x4045400300000000 WWPN : 0x50050763031bd327 LUN status : 0x40000000 Request ID : 0x0000000000000000 ERP status : 0x01800000 ERP step : 0x1000 ERP action : 0x01 ERP count : 0x00 NOT followed by a trace record with tag "scpaddy" for WWPN 0x50050763031bd327. Signed-off-by: Steffen Maier Fixes: 6f2ce1c6af37 ("scsi: zfcp: fix rport unblock race with LUN recovery") Cc: #2.6.32+ Reviewed-by: Jens Remus Reviewed-by: Benjamin Block Signed-off-by: Martin K. Petersen --- drivers/s390/scsi/zfcp_erp.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers') diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c index 744a64680d5b..c0b2348d7ce6 100644 --- a/drivers/s390/scsi/zfcp_erp.c +++ b/drivers/s390/scsi/zfcp_erp.c @@ -1341,6 +1341,9 @@ static void zfcp_erp_try_rport_unblock(struct zfcp_port *port) struct zfcp_scsi_dev *zsdev = sdev_to_zfcp(sdev); int lun_status; + if (sdev->sdev_state == SDEV_DEL || + sdev->sdev_state == SDEV_CANCEL) + continue; if (zsdev->port != port) continue; /* LUN under port of interest */ -- cgit v1.2.3 From 242ec1455151267fe35a0834aa9038e4c4670884 Mon Sep 17 00:00:00 2001 From: Steffen Maier Date: Tue, 26 Mar 2019 14:36:59 +0100 Subject: scsi: zfcp: fix scsi_eh host reset with port_forced ERP for non-NPIV FCP devices Suppose more than one non-NPIV FCP device is active on the same channel. Send I/O to storage and have some of the pending I/O run into a SCSI command timeout, e.g. due to bit errors on the fibre. Now the error situation stops. However, we saw FCP requests continue to timeout in the channel. The abort will be successful, but the subsequent TUR fails. Scsi_eh starts. The LUN reset fails. The target reset fails. The host reset only did an FCP device recovery. However, for non-NPIV FCP devices, this does not close and reopen ports on the SAN-side if other non-NPIV FCP device(s) share the same open ports. In order to resolve the continuing FCP request timeouts, we need to explicitly close and reopen ports on the SAN-side. This was missing since the beginning of zfcp in v2.6.0 history commit ea127f975424 ("[PATCH] s390 (7/7): zfcp host adapter."). Note: The FSF requests for forced port reopen could run into FSF request timeouts due to other reasons. This would trigger an internal FCP device recovery. Pending forced port reopen recoveries would get dismissed. So some ports might not get fully reopened during this host reset handler. However, subsequent I/O would trigger the above described escalation and eventually all ports would be forced reopen to resolve any continuing FCP request timeouts due to earlier bit errors. Signed-off-by: Steffen Maier Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: #3.0+ Reviewed-by: Jens Remus Reviewed-by: Benjamin Block Signed-off-by: Martin K. Petersen --- drivers/s390/scsi/zfcp_erp.c | 14 ++++++++++++++ drivers/s390/scsi/zfcp_ext.h | 2 ++ drivers/s390/scsi/zfcp_scsi.c | 4 ++++ 3 files changed, 20 insertions(+) (limited to 'drivers') diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c index c0b2348d7ce6..e8fc28dba8df 100644 --- a/drivers/s390/scsi/zfcp_erp.c +++ b/drivers/s390/scsi/zfcp_erp.c @@ -624,6 +624,20 @@ static void zfcp_erp_strategy_memwait(struct zfcp_erp_action *erp_action) add_timer(&erp_action->timer); } +void zfcp_erp_port_forced_reopen_all(struct zfcp_adapter *adapter, + int clear, char *dbftag) +{ + unsigned long flags; + struct zfcp_port *port; + + write_lock_irqsave(&adapter->erp_lock, flags); + read_lock(&adapter->port_list_lock); + list_for_each_entry(port, &adapter->port_list, list) + _zfcp_erp_port_forced_reopen(port, clear, dbftag); + read_unlock(&adapter->port_list_lock); + write_unlock_irqrestore(&adapter->erp_lock, flags); +} + static void _zfcp_erp_port_reopen_all(struct zfcp_adapter *adapter, int clear, char *dbftag) { diff --git a/drivers/s390/scsi/zfcp_ext.h b/drivers/s390/scsi/zfcp_ext.h index 3fce47b0b21b..c6acca521ffe 100644 --- a/drivers/s390/scsi/zfcp_ext.h +++ b/drivers/s390/scsi/zfcp_ext.h @@ -70,6 +70,8 @@ extern void zfcp_erp_port_reopen(struct zfcp_port *port, int clear, char *dbftag); extern void zfcp_erp_port_shutdown(struct zfcp_port *, int, char *); extern void zfcp_erp_port_forced_reopen(struct zfcp_port *, int, char *); +extern void zfcp_erp_port_forced_reopen_all(struct zfcp_adapter *adapter, + int clear, char *dbftag); extern void zfcp_erp_set_lun_status(struct scsi_device *, u32); extern void zfcp_erp_clear_lun_status(struct scsi_device *, u32); extern void zfcp_erp_lun_reopen(struct scsi_device *, int, char *); diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c index f4f6a07c5222..221d0dfb8493 100644 --- a/drivers/s390/scsi/zfcp_scsi.c +++ b/drivers/s390/scsi/zfcp_scsi.c @@ -368,6 +368,10 @@ static int zfcp_scsi_eh_host_reset_handler(struct scsi_cmnd *scpnt) struct zfcp_adapter *adapter = zfcp_sdev->port->adapter; int ret = SUCCESS, fc_ret; + if (!(adapter->connection_features & FSF_FEATURE_NPIV_MODE)) { + zfcp_erp_port_forced_reopen_all(adapter, 0, "schrh_p"); + zfcp_erp_wait(adapter); + } zfcp_erp_adapter_reopen(adapter, 0, "schrh_1"); zfcp_erp_wait(adapter); fc_ret = fc_block_scsi_eh(scpnt); -- cgit v1.2.3 From c8206579175c34a2546de8a74262456278a7795a Mon Sep 17 00:00:00 2001 From: Steffen Maier Date: Tue, 26 Mar 2019 14:37:00 +0100 Subject: scsi: zfcp: reduce flood of fcrscn1 trace records on multi-element RSCN If an incoming ELS of type RSCN contains more than one element, zfcp suboptimally causes repeated erp trigger NOP trace records for each previously failed port. These could be ports that went away. It loops over each RSCN element, and for each of those in an inner loop over all zfcp_ports. The trigger to recover failed ports should be just the reception of some RSCN, no matter how many elements it has. So we can loop over failed ports separately, and only then loop over each RSCN element to handle the non-failed ports. The call chain was: zfcp_fc_incoming_rscn for (i = 1; i < no_entries; i++) _zfcp_fc_incoming_rscn list_for_each_entry(port, &adapter->port_list, list) if (masked port->d_id match) zfcp_fc_test_link if (!port->d_id) zfcp_erp_port_reopen "fcrscn1" <=== In order the reduce the "flooding" of the REC trace area in such cases, we factor out handling the failed ports to be outside of the entries loop: zfcp_fc_incoming_rscn if (no_entries > 1) <=== list_for_each_entry(port, &adapter->port_list, list) <=== if (!port->d_id) zfcp_erp_port_reopen "fcrscn1" <=== for (i = 1; i < no_entries; i++) _zfcp_fc_incoming_rscn list_for_each_entry(port, &adapter->port_list, list) if (masked port->d_id match) zfcp_fc_test_link Abbreviated example trace records before this code change: Tag : fcrscn1 WWPN : 0x500507630310d327 ERP want : 0x02 ERP need : 0x02 Tag : fcrscn1 WWPN : 0x500507630310d327 ERP want : 0x02 ERP need : 0x00 NOP => superfluous trace record The last trace entry repeats if there are more than 2 RSCN elements. Signed-off-by: Steffen Maier Reviewed-by: Benjamin Block Reviewed-by: Jens Remus Signed-off-by: Martin K. Petersen --- drivers/s390/scsi/zfcp_fc.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'drivers') diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c index db00b5e3abbe..33eddb02ee30 100644 --- a/drivers/s390/scsi/zfcp_fc.c +++ b/drivers/s390/scsi/zfcp_fc.c @@ -239,10 +239,6 @@ static void _zfcp_fc_incoming_rscn(struct zfcp_fsf_req *fsf_req, u32 range, list_for_each_entry(port, &adapter->port_list, list) { if ((port->d_id & range) == (ntoh24(page->rscn_fid) & range)) zfcp_fc_test_link(port); - if (!port->d_id) - zfcp_erp_port_reopen(port, - ZFCP_STATUS_COMMON_ERP_FAILED, - "fcrscn1"); } read_unlock_irqrestore(&adapter->port_list_lock, flags); } @@ -250,6 +246,7 @@ static void _zfcp_fc_incoming_rscn(struct zfcp_fsf_req *fsf_req, u32 range, static void zfcp_fc_incoming_rscn(struct zfcp_fsf_req *fsf_req) { struct fsf_status_read_buffer *status_buffer = (void *)fsf_req->data; + struct zfcp_adapter *adapter = fsf_req->adapter; struct fc_els_rscn *head; struct fc_els_rscn_page *page; u16 i; @@ -263,6 +260,22 @@ static void zfcp_fc_incoming_rscn(struct zfcp_fsf_req *fsf_req) no_entries = be16_to_cpu(head->rscn_plen) / sizeof(struct fc_els_rscn_page); + if (no_entries > 1) { + /* handle failed ports */ + unsigned long flags; + struct zfcp_port *port; + + read_lock_irqsave(&adapter->port_list_lock, flags); + list_for_each_entry(port, &adapter->port_list, list) { + if (port->d_id) + continue; + zfcp_erp_port_reopen(port, + ZFCP_STATUS_COMMON_ERP_FAILED, + "fcrscn1"); + } + read_unlock_irqrestore(&adapter->port_list_lock, flags); + } + for (i = 1; i < no_entries; i++) { /* skip head and start with 1st element */ page++; -- cgit v1.2.3 From 6dc6a944d58aea3d9de3828318b0fffdb60a7097 Mon Sep 17 00:00:00 2001 From: Tyrel Datwyler Date: Wed, 20 Mar 2019 14:56:51 -0500 Subject: scsi: ibmvfc: Remove "failed" from logged errors The text of messages logged with ibmvfc_log_error() always contain the term "failed". In the case of cancelled commands during EH they are reported back by the VIOS using error codes. This can be confusing to somebody looking at these log messages as to whether a command was successfully cancelled. The following real log message for example it is unclear if the transaction was actaully cancelled. <6>sd 0:0:1:1: Cancelling outstanding commands. <3>sd 0:0:1:1: [sde] Command (28) failed: transaction cancelled (2:6) flags: 0 fcp_rsp: 0, resid=0, scsi_status: 0 Remove prefixing of "failed" to all error logged messages. The ibmvfc_log_error() function translates the returned error/status codes to a human readable message already. Signed-off-by: Tyrel Datwyler Signed-off-by: Martin K. Petersen --- drivers/scsi/ibmvscsi/ibmvfc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index dbaa4f131433..c3ce27039552 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -1494,7 +1494,7 @@ static void ibmvfc_log_error(struct ibmvfc_event *evt) if (rsp->flags & FCP_RSP_LEN_VALID) rsp_code = rsp->data.info.rsp_code; - scmd_printk(KERN_ERR, cmnd, "Command (%02X) failed: %s (%x:%x) " + scmd_printk(KERN_ERR, cmnd, "Command (%02X) : %s (%x:%x) " "flags: %x fcp_rsp: %x, resid=%d, scsi_status: %x\n", cmnd->cmnd[0], err, vfc_cmd->status, vfc_cmd->error, rsp->flags, rsp_code, scsi_get_resid(cmnd), rsp->scsi_status); -- cgit v1.2.3 From 95237c25d8d08ebc451dd2d793f7e765f57b0c9f Mon Sep 17 00:00:00 2001 From: Tyrel Datwyler Date: Wed, 20 Mar 2019 14:56:52 -0500 Subject: scsi: ibmvfc: Add failed PRLI to cmd_status lookup array The VIOS uses the SCSI_ERROR class to report PRLI failures. These errors are indicated with the combination of a IBMVFC_FC_SCSI_ERROR return status and 0x8000 error code. Add these codes to cmd_status[] with appropriate human readable error message. Signed-off-by: Tyrel Datwyler Signed-off-by: Martin K. Petersen --- drivers/scsi/ibmvscsi/ibmvfc.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers') diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index c3ce27039552..18ee2a8ec3d5 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -139,6 +139,7 @@ static const struct { { IBMVFC_FC_FAILURE, IBMVFC_VENDOR_SPECIFIC, DID_ERROR, 1, 1, "vendor specific" }, { IBMVFC_FC_SCSI_ERROR, 0, DID_OK, 1, 0, "SCSI error" }, + { IBMVFC_FC_SCSI_ERROR, IBMVFC_COMMAND_FAILED, DID_ERROR, 0, 1, "PRLI to device failed." }, }; static void ibmvfc_npiv_login(struct ibmvfc_host *); -- cgit v1.2.3 From 3e6f7de43f4960fba8322b16531b0d6624a9322d Mon Sep 17 00:00:00 2001 From: Tyrel Datwyler Date: Wed, 20 Mar 2019 14:56:53 -0500 Subject: scsi: ibmvfc: Byte swap status and error codes when logging Status and error codes are returned in big endian from the VIOS. The values are translated into a human readable format when logged, but the values are also logged. This patch byte swaps those values so that they are consistent between BE and LE platforms. Signed-off-by: Tyrel Datwyler Signed-off-by: Martin K. Petersen --- drivers/scsi/ibmvscsi/ibmvfc.c | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) (limited to 'drivers') diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index 18ee2a8ec3d5..33dda4d32f65 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -1497,7 +1497,7 @@ static void ibmvfc_log_error(struct ibmvfc_event *evt) scmd_printk(KERN_ERR, cmnd, "Command (%02X) : %s (%x:%x) " "flags: %x fcp_rsp: %x, resid=%d, scsi_status: %x\n", - cmnd->cmnd[0], err, vfc_cmd->status, vfc_cmd->error, + cmnd->cmnd[0], err, be16_to_cpu(vfc_cmd->status), be16_to_cpu(vfc_cmd->error), rsp->flags, rsp_code, scsi_get_resid(cmnd), rsp->scsi_status); } @@ -2023,7 +2023,7 @@ static int ibmvfc_reset_device(struct scsi_device *sdev, int type, char *desc) sdev_printk(KERN_ERR, sdev, "%s reset failed: %s (%x:%x) " "flags: %x fcp_rsp: %x, scsi_status: %x\n", desc, ibmvfc_get_cmd_error(be16_to_cpu(rsp_iu.cmd.status), be16_to_cpu(rsp_iu.cmd.error)), - rsp_iu.cmd.status, rsp_iu.cmd.error, fc_rsp->flags, rsp_code, + be16_to_cpu(rsp_iu.cmd.status), be16_to_cpu(rsp_iu.cmd.error), fc_rsp->flags, rsp_code, fc_rsp->scsi_status); rsp_rc = -EIO; } else @@ -2382,7 +2382,7 @@ static int ibmvfc_abort_task_set(struct scsi_device *sdev) sdev_printk(KERN_ERR, sdev, "Abort failed: %s (%x:%x) " "flags: %x fcp_rsp: %x, scsi_status: %x\n", ibmvfc_get_cmd_error(be16_to_cpu(rsp_iu.cmd.status), be16_to_cpu(rsp_iu.cmd.error)), - rsp_iu.cmd.status, rsp_iu.cmd.error, fc_rsp->flags, rsp_code, + be16_to_cpu(rsp_iu.cmd.status), be16_to_cpu(rsp_iu.cmd.error), fc_rsp->flags, rsp_code, fc_rsp->scsi_status); rsp_rc = -EIO; } else @@ -3349,7 +3349,7 @@ static void ibmvfc_tgt_prli_done(struct ibmvfc_event *evt) tgt_log(tgt, level, "Process Login failed: %s (%x:%x) rc=0x%02X\n", ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)), - rsp->status, rsp->error, status); + be16_to_cpu(rsp->status), be16_to_cpu(rsp->error), status); break; } @@ -3447,9 +3447,10 @@ static void ibmvfc_tgt_plogi_done(struct ibmvfc_event *evt) ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_DEL_RPORT); tgt_log(tgt, level, "Port Login failed: %s (%x:%x) %s (%x) %s (%x) rc=0x%02X\n", - ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)), rsp->status, rsp->error, - ibmvfc_get_fc_type(be16_to_cpu(rsp->fc_type)), rsp->fc_type, - ibmvfc_get_ls_explain(be16_to_cpu(rsp->fc_explain)), rsp->fc_explain, status); + ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)), + be16_to_cpu(rsp->status), be16_to_cpu(rsp->error), + ibmvfc_get_fc_type(be16_to_cpu(rsp->fc_type)), be16_to_cpu(rsp->fc_type), + ibmvfc_get_ls_explain(be16_to_cpu(rsp->fc_explain)), be16_to_cpu(rsp->fc_explain), status); break; } @@ -3620,7 +3621,7 @@ static void ibmvfc_tgt_adisc_done(struct ibmvfc_event *evt) fc_explain = (be32_to_cpu(mad->fc_iu.response[1]) & 0x0000ff00) >> 8; tgt_info(tgt, "ADISC failed: %s (%x:%x) %s (%x) %s (%x) rc=0x%02X\n", ibmvfc_get_cmd_error(be16_to_cpu(mad->iu.status), be16_to_cpu(mad->iu.error)), - mad->iu.status, mad->iu.error, + be16_to_cpu(mad->iu.status), be16_to_cpu(mad->iu.error), ibmvfc_get_fc_type(fc_reason), fc_reason, ibmvfc_get_ls_explain(fc_explain), fc_explain, status); break; @@ -3832,9 +3833,10 @@ static void ibmvfc_tgt_query_target_done(struct ibmvfc_event *evt) tgt_log(tgt, level, "Query Target failed: %s (%x:%x) %s (%x) %s (%x) rc=0x%02X\n", ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)), - rsp->status, rsp->error, ibmvfc_get_fc_type(be16_to_cpu(rsp->fc_type)), - rsp->fc_type, ibmvfc_get_gs_explain(be16_to_cpu(rsp->fc_explain)), - rsp->fc_explain, status); + be16_to_cpu(rsp->status), be16_to_cpu(rsp->error), + ibmvfc_get_fc_type(be16_to_cpu(rsp->fc_type)), be16_to_cpu(rsp->fc_type), + ibmvfc_get_gs_explain(be16_to_cpu(rsp->fc_explain)), be16_to_cpu(rsp->fc_explain), + status); break; } @@ -3960,7 +3962,7 @@ static void ibmvfc_discover_targets_done(struct ibmvfc_event *evt) level += ibmvfc_retry_host_init(vhost); ibmvfc_log(vhost, level, "Discover Targets failed: %s (%x:%x)\n", ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)), - rsp->status, rsp->error); + be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)); break; case IBMVFC_MAD_DRIVER_FAILED: break; @@ -4025,7 +4027,7 @@ static void ibmvfc_npiv_login_done(struct ibmvfc_event *evt) ibmvfc_link_down(vhost, IBMVFC_LINK_DEAD); ibmvfc_log(vhost, level, "NPIV Login failed: %s (%x:%x)\n", ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)), - rsp->status, rsp->error); + be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)); ibmvfc_free_event(evt); return; case IBMVFC_MAD_CRQ_ERROR: -- cgit v1.2.3 From d6e2635b9cf7982102750c5d9e4ba1474afa0981 Mon Sep 17 00:00:00 2001 From: Tyrel Datwyler Date: Wed, 20 Mar 2019 14:56:54 -0500 Subject: scsi: ibmvfc: Clean up transport events No change to functionality. Simply make transport event messages a little clearer, and rework CRQ format enums such that we have separate enums for INIT messages and XPORT events. [mkp: typo] Signed-off-by: Tyrel Datwyler Signed-off-by: Martin K. Petersen --- drivers/scsi/ibmvscsi/ibmvfc.c | 8 +++++--- drivers/scsi/ibmvscsi/ibmvfc.h | 7 ++++++- 2 files changed, 11 insertions(+), 4 deletions(-) (limited to 'drivers') diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index 33dda4d32f65..3ad997ac3510 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -2756,16 +2756,18 @@ static void ibmvfc_handle_crq(struct ibmvfc_crq *crq, struct ibmvfc_host *vhost) ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_NONE); if (crq->format == IBMVFC_PARTITION_MIGRATED) { /* We need to re-setup the interpartition connection */ - dev_info(vhost->dev, "Re-enabling adapter\n"); + dev_info(vhost->dev, "Partition migrated, Re-enabling adapter\n"); vhost->client_migrated = 1; ibmvfc_purge_requests(vhost, DID_REQUEUE); ibmvfc_link_down(vhost, IBMVFC_LINK_DOWN); ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_REENABLE); - } else { - dev_err(vhost->dev, "Virtual adapter failed (rc=%d)\n", crq->format); + } else if (crq->format == IBMVFC_PARTNER_FAILED || crq->format == IBMVFC_PARTNER_DEREGISTER) { + dev_err(vhost->dev, "Host partner adapter deregistered or failed (rc=%d)\n", crq->format); ibmvfc_purge_requests(vhost, DID_ERROR); ibmvfc_link_down(vhost, IBMVFC_LINK_DOWN); ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_RESET); + } else { + dev_err(vhost->dev, "Received unknown transport event from partner (rc=%d)\n", crq->format); } return; case IBMVFC_CRQ_CMD_RSP: diff --git a/drivers/scsi/ibmvscsi/ibmvfc.h b/drivers/scsi/ibmvscsi/ibmvfc.h index b81a53c4a9a8..459cc288ba1d 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.h +++ b/drivers/scsi/ibmvscsi/ibmvfc.h @@ -78,9 +78,14 @@ enum ibmvfc_crq_valid { IBMVFC_CRQ_XPORT_EVENT = 0xFF, }; -enum ibmvfc_crq_format { +enum ibmvfc_crq_init_msg { IBMVFC_CRQ_INIT = 0x01, IBMVFC_CRQ_INIT_COMPLETE = 0x02, +}; + +enum ibmvfc_crq_xport_evts { + IBMVFC_PARTNER_FAILED = 0x01, + IBMVFC_PARTNER_DEREGISTER = 0x02, IBMVFC_PARTITION_MIGRATED = 0x06, }; -- cgit v1.2.3 From 872e192fab643887f143106eb56443d87e5e87c1 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 27 Mar 2019 18:11:03 +0000 Subject: scsi: qedi: remove declaration of nvm_image from stack The nvm_image is a large struct qedi_nvm_iscsi_image object of over 24K so don't declare it on the stack just for a sizeof requirement; use sizeof on struct qedi_nvm_iscsi_image instead. Fixes: c77a2fa3ff8f ("scsi: qedi: Add the CRC size within iSCSI NVM image") Signed-off-by: Colin Ian King Acked-by: Manish Rangankar Signed-off-by: Martin K. Petersen --- drivers/scsi/qedi/qedi_main.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'drivers') diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index e74a62448ba4..e5db9a9954dc 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -1392,10 +1392,8 @@ static void qedi_free_nvm_iscsi_cfg(struct qedi_ctx *qedi) static int qedi_alloc_nvm_iscsi_cfg(struct qedi_ctx *qedi) { - struct qedi_nvm_iscsi_image nvm_image; - qedi->iscsi_image = dma_alloc_coherent(&qedi->pdev->dev, - sizeof(nvm_image), + sizeof(struct qedi_nvm_iscsi_image), &qedi->nvm_buf_dma, GFP_KERNEL); if (!qedi->iscsi_image) { QEDI_ERR(&qedi->dbg_ctx, "Could not allocate NVM BUF.\n"); @@ -2236,14 +2234,13 @@ static void qedi_boot_release(void *data) static int qedi_get_boot_info(struct qedi_ctx *qedi) { int ret = 1; - struct qedi_nvm_iscsi_image nvm_image; QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, "Get NVM iSCSI CFG image\n"); ret = qedi_ops->common->nvm_get_image(qedi->cdev, QED_NVM_IMAGE_ISCSI_CFG, (char *)qedi->iscsi_image, - sizeof(nvm_image)); + sizeof(struct qedi_nvm_iscsi_image)); if (ret) QEDI_ERR(&qedi->dbg_ctx, "Could not get NVM image. ret = %d\n", ret); -- cgit v1.2.3 From 1cb1d2c64e812928fe0a40b8f7e74523d0283dbe Mon Sep 17 00:00:00 2001 From: Xose Vazquez Perez Date: Sat, 30 Mar 2019 15:43:31 +0100 Subject: scsi: core: add new RDAC LENOVO/DE_Series device Blacklist "Universal Xport" LUN. It's used for in-band storage array management. Also add model to the rdac dh family. Cc: Martin Wilck Cc: Hannes Reinecke Cc: NetApp RDAC team Cc: Christophe Varoqui Cc: James E.J. Bottomley Cc: Martin K. Petersen Cc: SCSI ML Cc: DM ML Signed-off-by: Xose Vazquez Perez Reviewed-by: Martin Wilck Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_devinfo.c | 1 + drivers/scsi/scsi_dh.c | 1 + 2 files changed, 2 insertions(+) (limited to 'drivers') diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index c4cbfd07b916..a08ff3bd6310 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -238,6 +238,7 @@ static struct { {"NETAPP", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, {"LSI", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, {"ENGENIO", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, + {"LENOVO", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, {"SMSC", "USB 2 HS-CF", NULL, BLIST_SPARSELUN | BLIST_INQUIRY_36}, {"SONY", "CD-ROM CDU-8001", NULL, BLIST_BORKEN}, {"SONY", "TSL", NULL, BLIST_FORCELUN}, /* DDS3 & DDS4 autoloaders */ diff --git a/drivers/scsi/scsi_dh.c b/drivers/scsi/scsi_dh.c index 5a58cbf3a75d..c14006ac98f9 100644 --- a/drivers/scsi/scsi_dh.c +++ b/drivers/scsi/scsi_dh.c @@ -75,6 +75,7 @@ static const struct scsi_dh_blist scsi_dh_blist[] = { {"NETAPP", "INF-01-00", "rdac", }, {"LSI", "INF-01-00", "rdac", }, {"ENGENIO", "INF-01-00", "rdac", }, + {"LENOVO", "DE_Series", "rdac", }, {NULL, NULL, NULL }, }; -- cgit v1.2.3 From 382e06d11e075a40b4094b6ef809f8d4bcc7ab2a Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Mon, 1 Apr 2019 16:10:52 +0000 Subject: scsi: storvsc: Fix calculation of sub-channel count When the number of sub-channels offered by Hyper-V is >= the number of CPUs in the VM, calculate the correct number of sub-channels. The current code produces one too many. This scenario arises only when the number of CPUs is artificially restricted (for example, with maxcpus= on the kernel boot line), because Hyper-V normally offers a sub-channel count < number of CPUs. While the current code doesn't break, the extra sub-channel is unbalanced across the CPUs (for example, a total of 5 channels on a VM with 4 CPUs). Signed-off-by: Michael Kelley Reviewed-by: Vitaly Kuznetsov Reviewed-by: Long Li Signed-off-by: Martin K. Petersen --- drivers/scsi/storvsc_drv.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 84380bae20f1..e186743033f4 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -668,13 +668,22 @@ static void handle_multichannel_storage(struct hv_device *device, int max_chns) { struct device *dev = &device->device; struct storvsc_device *stor_device; - int num_cpus = num_online_cpus(); int num_sc; struct storvsc_cmd_request *request; struct vstor_packet *vstor_packet; int ret, t; - num_sc = ((max_chns > num_cpus) ? num_cpus : max_chns); + /* + * If the number of CPUs is artificially restricted, such as + * with maxcpus=1 on the kernel boot line, Hyper-V could offer + * sub-channels >= the number of CPUs. These sub-channels + * should not be created. The primary channel is already created + * and assigned to one CPU, so check against # CPUs - 1. + */ + num_sc = min((int)(num_online_cpus() - 1), max_chns); + if (!num_sc) + return; + stor_device = get_out_stor_device(device); if (!stor_device) return; -- cgit v1.2.3 From ed2e63aaec4fbf248275d2d83c4cfd65e069594f Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Mon, 1 Apr 2019 21:42:06 +0000 Subject: scsi: storvsc: Reduce default ring buffer size to 128 Kbytes Reduce the default VMbus channel ring buffer size for storvsc SCSI devices from 1 Mbyte to 128 Kbytes. Measurements show that ring buffer sizes above 128 Kbytes do not increase performance even at very high IOPS rates, so don't waste the memory. Also remove the dependence on PAGE_SIZE, since the ring buffer size should not change on architectures where PAGE_SIZE is not 4 Kbytes. Signed-off-by: Michael Kelley Reviewed-by: Haiyang Zhang Signed-off-by: Martin K. Petersen --- drivers/scsi/storvsc_drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index e186743033f4..8472de1007ff 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -385,7 +385,7 @@ enum storvsc_request_type { * This is the end of Protocol specific defines. */ -static int storvsc_ringbuffer_size = (256 * PAGE_SIZE); +static int storvsc_ringbuffer_size = (128 * 1024); static u32 max_outstanding_req_per_channel; static int storvsc_vcpus_per_sub_channel = 4; -- cgit v1.2.3 From 4eb01535886644d79a58fe652e0782a194bc3402 Mon Sep 17 00:00:00 2001 From: James Smart Date: Wed, 3 Apr 2019 11:10:34 -0700 Subject: scsi: lpfc: Fix missing wakeups on abort threads Abort thread wakeups, on some wqe types, are not happening. The thread wakeup logic is dependent upon the LPFC_DRIVER_ABORTED flag. However, on these wqes, the completion handler running prior to the io completion routine ends up clearing the flag. Rework the wakeup logic to look at a non-null waitq element which must be set if the abort thread is waiting. This is reverting the change in the indicated patch. Fixes: c2017260eea2d ("scsi: lpfc: Rework locking on SCSI io completion") Signed-off-by: Dick Kennedy Signed-off-by: James Smart Signed-off-by: Martin K. Petersen --- drivers/scsi/lpfc/lpfc_scsi.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'drivers') diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index c98f264f1d83..a497b2c0cb79 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -3878,10 +3878,9 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn, * wake up the thread. */ spin_lock(&lpfc_cmd->buf_lock); - if (unlikely(lpfc_cmd->cur_iocbq.iocb_flag & LPFC_DRIVER_ABORTED)) { - lpfc_cmd->cur_iocbq.iocb_flag &= ~LPFC_DRIVER_ABORTED; - if (lpfc_cmd->waitq) - wake_up(lpfc_cmd->waitq); + lpfc_cmd->cur_iocbq.iocb_flag &= ~LPFC_DRIVER_ABORTED; + if (lpfc_cmd->waitq) { + wake_up(lpfc_cmd->waitq); lpfc_cmd->waitq = NULL; } spin_unlock(&lpfc_cmd->buf_lock); -- cgit v1.2.3 From 5c2442fd78998af60e13aba506d103f7f43f8701 Mon Sep 17 00:00:00 2001 From: Varun Prakash Date: Fri, 5 Apr 2019 20:39:13 +0530 Subject: scsi: csiostor: fix missing data copy in csio_scsi_err_handler() If scsi cmd sglist is not suitable for DDP then csiostor driver uses preallocated buffers for DDP, because of this data copy is required from DDP buffer to scsi cmd sglist before calling ->scsi_done(). Signed-off-by: Varun Prakash Signed-off-by: Martin K. Petersen --- drivers/scsi/csiostor/csio_scsi.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/scsi/csiostor/csio_scsi.c b/drivers/scsi/csiostor/csio_scsi.c index 462560b2855e..469d0bc9f5fe 100644 --- a/drivers/scsi/csiostor/csio_scsi.c +++ b/drivers/scsi/csiostor/csio_scsi.c @@ -1713,8 +1713,11 @@ csio_scsi_err_handler(struct csio_hw *hw, struct csio_ioreq *req) } out: - if (req->nsge > 0) + if (req->nsge > 0) { scsi_dma_unmap(cmnd); + if (req->dcopy && (host_status == DID_OK)) + host_status = csio_scsi_copy_to_sgl(hw, req); + } cmnd->result = (((host_status) << 16) | scsi_status); cmnd->scsi_done(cmnd); -- cgit v1.2.3