- Linux-stable-mirror - lists.linaro.org

[PATCH 06/25] zfcp: fix missing REC trigger trace for all objects in ERP_FAILED

by Steffen Maier

That other commit introduced an inconsistency because it would trace on ERP_FAILED for all callers of port forced reopen triggers (not just terminate_rport_io), but it would not trace on ERP_FAILED for all callers of other ERP triggers such as adapter, port regular, LUN. Therefore, generalize that other commit. zfcp_erp_action_enqueue() already had two early outs which re-used the one zfcp_dbf_rec_trig() call. All ERP trigger functions finally run through zfcp_erp_action_enqueue(). So move the special handling for ZFCP_STATUS_COMMON_ERP_FAILED into zfcp_erp_action_enqueue() and add another early out with new trace marker for pseudo ERP need in this case. This removes all early returns from all ERP trigger functions so we always end up at zfcp_dbf_rec_trig(). Example trace record formatted with zfcpdbf from s390-tools: Timestamp : ... Area : REC Subarea : 00 Level : 1 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 ZFCP_DBF_REC_TRIG Tag : ....... LUN : 0x... WWPN : 0x... D_ID : 0x... Adapter status : 0x... Port status : 0x... LUN status : 0x... Ready count : 0x... Running count : 0x... ERP want : 0x0. ZFCP_ERP_ACTION_REOPEN_... ERP need : 0xe0 ZFCP_ERP_ACTION_FAILED Signed-off-by: Steffen Maier <maier(a)linux.ibm.com> Cc: <stable(a)vger.kernel.org> #2.6.38+ Reviewed-by: Benjamin Block <bblock(a)linux.ibm.com> --- drivers/s390/scsi/zfcp_erp.c | 79 ++++++++++++++++++++++++++++---------------- 1 file changed, 51 insertions(+), 28 deletions(-) diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c index 5c368cdfc455..20fe59300d0e 100644 --- a/drivers/s390/scsi/zfcp_erp.c +++ b/drivers/s390/scsi/zfcp_erp.c @@ -143,6 +143,49 @@ static void zfcp_erp_action_dismiss_adapter(struct zfcp_adapter *adapter) } } +static int zfcp_erp_handle_failed(int want, struct zfcp_adapter *adapter, + struct zfcp_port *port, + struct scsi_device *sdev) +{ + int need = want; + struct zfcp_scsi_dev *zsdev; + + switch (want) { + case ZFCP_ERP_ACTION_REOPEN_LUN: + zsdev = sdev_to_zfcp(sdev); + if (atomic_read(&zsdev->status) & ZFCP_STATUS_COMMON_ERP_FAILED) + need = 0; + break; + case ZFCP_ERP_ACTION_REOPEN_PORT_FORCED: + if (atomic_read(&port->status) & ZFCP_STATUS_COMMON_ERP_FAILED) + need = 0; + break; + case ZFCP_ERP_ACTION_REOPEN_PORT: + if (atomic_read(&port->status) & + ZFCP_STATUS_COMMON_ERP_FAILED) { + need = 0; + /* ensure propagation of failed status to new devices */ + zfcp_erp_set_port_status( + port, ZFCP_STATUS_COMMON_ERP_FAILED); + } + break; + case ZFCP_ERP_ACTION_REOPEN_ADAPTER: + if (atomic_read(&adapter->status) & + ZFCP_STATUS_COMMON_ERP_FAILED) { + need = 0; + /* ensure propagation of failed status to new devices */ + zfcp_erp_set_adapter_status( + adapter, ZFCP_STATUS_COMMON_ERP_FAILED); + } + break; + default: + need = 0; + break; + } + + return need; +} + static int zfcp_erp_required_act(int want, struct zfcp_adapter *adapter, struct zfcp_port *port, struct scsi_device *sdev) @@ -266,6 +309,12 @@ static int zfcp_erp_action_enqueue(int want, struct zfcp_adapter *adapter, int retval = 1, need; struct zfcp_erp_action *act; + need = zfcp_erp_handle_failed(want, adapter, port, sdev); + if (!need) { + need = ZFCP_ERP_ACTION_FAILED; /* marker for trace */ + goto out; + } + if (!adapter->erp_thread) return -EIO; @@ -314,12 +363,6 @@ static int _zfcp_erp_adapter_reopen(struct zfcp_adapter *adapter, zfcp_erp_adapter_block(adapter, clear_mask); zfcp_scsi_schedule_rports_block(adapter); - /* ensure propagation of failed status to new devices */ - if (atomic_read(&adapter->status) & ZFCP_STATUS_COMMON_ERP_FAILED) { - zfcp_erp_set_adapter_status(adapter, - ZFCP_STATUS_COMMON_ERP_FAILED); - return -EIO; - } return zfcp_erp_action_enqueue(ZFCP_ERP_ACTION_REOPEN_ADAPTER, adapter, NULL, NULL, id, 0); } @@ -338,12 +381,8 @@ void zfcp_erp_adapter_reopen(struct zfcp_adapter *adapter, int clear, char *id) zfcp_scsi_schedule_rports_block(adapter); write_lock_irqsave(&adapter->erp_lock, flags); - if (atomic_read(&adapter->status) & ZFCP_STATUS_COMMON_ERP_FAILED) - zfcp_erp_set_adapter_status(adapter, - ZFCP_STATUS_COMMON_ERP_FAILED); - else - zfcp_erp_action_enqueue(ZFCP_ERP_ACTION_REOPEN_ADAPTER, adapter, - NULL, NULL, id, 0); + zfcp_erp_action_enqueue(ZFCP_ERP_ACTION_REOPEN_ADAPTER, adapter, + NULL, NULL, id, 0); write_unlock_irqrestore(&adapter->erp_lock, flags); } @@ -384,13 +423,6 @@ static void _zfcp_erp_port_forced_reopen(struct zfcp_port *port, int clear, zfcp_erp_port_block(port, clear); zfcp_scsi_schedule_rport_block(port); - if (atomic_read(&port->status) & ZFCP_STATUS_COMMON_ERP_FAILED) { - zfcp_dbf_rec_trig(id, port->adapter, port, NULL, - ZFCP_ERP_ACTION_REOPEN_PORT_FORCED, - ZFCP_ERP_ACTION_FAILED); - return; - } - zfcp_erp_action_enqueue(ZFCP_ERP_ACTION_REOPEN_PORT_FORCED, port->adapter, port, NULL, id, 0); } @@ -416,12 +448,6 @@ static int _zfcp_erp_port_reopen(struct zfcp_port *port, int clear, char *id) zfcp_erp_port_block(port, clear); zfcp_scsi_schedule_rport_block(port); - if (atomic_read(&port->status) & ZFCP_STATUS_COMMON_ERP_FAILED) { - /* ensure propagation of failed status to new devices */ - zfcp_erp_set_port_status(port, ZFCP_STATUS_COMMON_ERP_FAILED); - return -EIO; - } - return zfcp_erp_action_enqueue(ZFCP_ERP_ACTION_REOPEN_PORT, port->adapter, port, NULL, id, 0); } @@ -461,9 +487,6 @@ static void _zfcp_erp_lun_reopen(struct scsi_device *sdev, int clear, char *id, zfcp_erp_lun_block(sdev, clear); - if (atomic_read(&zfcp_sdev->status) & ZFCP_STATUS_COMMON_ERP_FAILED) - return; - zfcp_erp_action_enqueue(ZFCP_ERP_ACTION_REOPEN_LUN, adapter, zfcp_sdev->port, sdev, id, act_status); } -- 2.16.3

7 years, 7 months

1
0
0 0

[PATCH 05/25] zfcp: fix missing REC trigger trace on terminate_rport_io for ERP_FAILED

by Steffen Maier

For problem determination we always want to see when we were invoked on the terminate_rport_io callback whether we perform something or not. Temporal event sequence of interest with a long fast_io_fail_tmo of 27 sec: loose remote port t workqueue [s] zfcp_q_<dev> IRQ zfcperp<dev> === ================== =================== ============================ 0 recv RSCN q p.test_link_work block rport start fast_io_fail_tmo send ADISC ELS 4 recv ADISC fail block zfcp_port port forced reopen send open port 12 recv open port fail q p.gid_pn_work zfcp_erp_wakeup (zfcp_erp_wait would return) GID_PN fail Before this point, we got a SCSI trace with tag "sctrpi1" on fast_io_fail, e.g. with the typical 5 sec setting. port.status |= ERP_FAILED If fast_io_fail_tmo triggers after this point, we missed a SCSI trace. workqueue fc_dl_<host> ================== 27 fc_timeout_fail_rport_io fc_terminate_rport_io zfcp_scsi_terminate_rport_io zfcp_erp_port_forced_reopen _zfcp_erp_port_forced_reopen if (port.status & ERP_FAILED) return; Therefore, write a trace before above early return. Example trace record formatted with zfcpdbf from s390-tools: Timestamp : ... Area : REC Subarea : 00 Level : 1 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 ZFCP_DBF_REC_TRIG Tag : sctrpi1 SCSI terminate rport I/O LUN : 0xffffffffffffffff none (invalid) WWPN : 0x<wwpn> D_ID : 0x<n_port_id> Adapter status : 0x... Port status : 0x... LUN status : 0x00000000 none (invalid) Ready count : 0x... Running count : 0x... ERP want : 0x03 ZFCP_ERP_ACTION_REOPEN_PORT_FORCED ERP need : 0xe0 ZFCP_ERP_ACTION_FAILED Signed-off-by: Steffen Maier <maier(a)linux.ibm.com> Cc: <stable(a)vger.kernel.org> #2.6.38+ Reviewed-by: Benjamin Block <bblock(a)linux.ibm.com> --- drivers/s390/scsi/zfcp_erp.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c index 3489b1bc9121..5c368cdfc455 100644 --- a/drivers/s390/scsi/zfcp_erp.c +++ b/drivers/s390/scsi/zfcp_erp.c @@ -42,9 +42,13 @@ enum zfcp_erp_steps { * @ZFCP_ERP_ACTION_REOPEN_PORT_FORCED: Forced port recovery. * @ZFCP_ERP_ACTION_REOPEN_ADAPTER: Adapter recovery. * @ZFCP_ERP_ACTION_NONE: Eyecatcher pseudo flag to bitwise or-combine with - * either of the other enum values. + * either of the first four enum values. * Used to indicate that an ERP action could not be * set up despite a detected need for some recovery. + * @ZFCP_ERP_ACTION_FAILED: Eyecatcher pseudo flag to bitwise or-combine with + * either of the first four enum values. + * Used to indicate that ERP not needed because + * the object has ZFCP_STATUS_COMMON_ERP_FAILED. */ enum zfcp_erp_act_type { ZFCP_ERP_ACTION_REOPEN_LUN = 1, @@ -52,6 +56,7 @@ enum zfcp_erp_act_type { ZFCP_ERP_ACTION_REOPEN_PORT_FORCED = 3, ZFCP_ERP_ACTION_REOPEN_ADAPTER = 4, ZFCP_ERP_ACTION_NONE = 0xc0, + ZFCP_ERP_ACTION_FAILED = 0xe0, }; enum zfcp_erp_act_state { @@ -379,8 +384,12 @@ static void _zfcp_erp_port_forced_reopen(struct zfcp_port *port, int clear, zfcp_erp_port_block(port, clear); zfcp_scsi_schedule_rport_block(port); - if (atomic_read(&port->status) & ZFCP_STATUS_COMMON_ERP_FAILED) + if (atomic_read(&port->status) & ZFCP_STATUS_COMMON_ERP_FAILED) { + zfcp_dbf_rec_trig(id, port->adapter, port, NULL, + ZFCP_ERP_ACTION_REOPEN_PORT_FORCED, + ZFCP_ERP_ACTION_FAILED); return; + } zfcp_erp_action_enqueue(ZFCP_ERP_ACTION_REOPEN_PORT_FORCED, port->adapter, port, NULL, id, 0); -- 2.16.3

7 years, 7 months

1
0
0 0

[PATCH 04/25] zfcp: fix missing REC trigger trace on terminate_rport_io early return

by Steffen Maier

get_device() and its internally used kobject_get() only return NULL if they get passed NULL as argument. zfcp_get_port_by_wwpn() loops over adapter->port_list so the iteration variable port is always non-NULL. Struct device is embedded in struct zfcp_port so &port->dev is always non-NULL. This is the argument to get_device(). However, if we get an fc_rport in terminate_rport_io() for which we cannot find a match within zfcp_get_port_by_wwpn(), the latter can return NULL. v2.6.30 commit 70932935b61e ("[SCSI] zfcp: Fix oops when port disappears") introduced an early return without adding a trace record for this case. Even if we don't need recovery in this case, for debugging we should still see that our callback was invoked originally by scsi_transport_fc. Example trace record formatted with zfcpdbf from s390-tools: Timestamp : ... Area : REC Subarea : 00 Level : 1 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : sctrpin SCSI terminate rport I/O, no zfcp port LUN : 0xffffffffffffffff none (invalid) WWPN : 0x<wwpn> WWPN D_ID : 0x<n_port_id> N_Port-ID Adapter status : 0x... Port status : 0xffffffff unknown (-1) LUN status : 0x00000000 none (invalid) Ready count : 0x... Running count : 0x... ERP want : 0x03 ZFCP_ERP_ACTION_REOPEN_PORT_FORCED ERP need : 0xc0 ZFCP_ERP_ACTION_NONE Signed-off-by: Steffen Maier <maier(a)linux.ibm.com> Fixes: 70932935b61e ("[SCSI] zfcp: Fix oops when port disappears") Cc: <stable(a)vger.kernel.org> #2.6.38+ Reviewed-by: Benjamin Block <bblock(a)linux.ibm.com> --- drivers/s390/scsi/zfcp_erp.c | 20 ++++++++++++++++++++ drivers/s390/scsi/zfcp_ext.h | 3 +++ drivers/s390/scsi/zfcp_scsi.c | 5 +++++ 3 files changed, 28 insertions(+) diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c index d9cd25b56cfa..3489b1bc9121 100644 --- a/drivers/s390/scsi/zfcp_erp.c +++ b/drivers/s390/scsi/zfcp_erp.c @@ -283,6 +283,26 @@ static int zfcp_erp_action_enqueue(int want, struct zfcp_adapter *adapter, return retval; } +void zfcp_erp_port_forced_no_port_dbf(char *id, struct zfcp_adapter *adapter, + u64 port_name, u32 port_id) +{ + unsigned long flags; + static /* don't waste stack */ struct zfcp_port tmpport; + + write_lock_irqsave(&adapter->erp_lock, flags); + /* Stand-in zfcp port with fields just good enough for + * zfcp_dbf_rec_trig() and zfcp_dbf_set_common(). + * Under lock because tmpport is static. + */ + atomic_set(&tmpport.status, -1); /* unknown */ + tmpport.wwpn = port_name; + tmpport.d_id = port_id; + zfcp_dbf_rec_trig(id, adapter, &tmpport, NULL, + ZFCP_ERP_ACTION_REOPEN_PORT_FORCED, + ZFCP_ERP_ACTION_NONE); + write_unlock_irqrestore(&adapter->erp_lock, flags); +} + static int _zfcp_erp_adapter_reopen(struct zfcp_adapter *adapter, int clear_mask, char *id) { diff --git a/drivers/s390/scsi/zfcp_ext.h b/drivers/s390/scsi/zfcp_ext.h index e55f42ce1168..3299bd345076 100644 --- a/drivers/s390/scsi/zfcp_ext.h +++ b/drivers/s390/scsi/zfcp_ext.h @@ -55,6 +55,9 @@ extern void zfcp_dbf_scsi_eh(char *tag, struct zfcp_adapter *adapter, /* zfcp_erp.c */ extern void zfcp_erp_set_adapter_status(struct zfcp_adapter *, u32); extern void zfcp_erp_clear_adapter_status(struct zfcp_adapter *, u32); +extern void zfcp_erp_port_forced_no_port_dbf(char *id, + struct zfcp_adapter *adapter, + u64 port_name, u32 port_id); extern void zfcp_erp_adapter_reopen(struct zfcp_adapter *, int, char *); extern void zfcp_erp_adapter_shutdown(struct zfcp_adapter *, int, char *); extern void zfcp_erp_set_port_status(struct zfcp_port *, u32); diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c index 4fdb1665b0e6..478e7ef9ea2f 100644 --- a/drivers/s390/scsi/zfcp_scsi.c +++ b/drivers/s390/scsi/zfcp_scsi.c @@ -605,6 +605,11 @@ static void zfcp_scsi_terminate_rport_io(struct fc_rport *rport) if (port) { zfcp_erp_port_forced_reopen(port, 0, "sctrpi1"); put_device(&port->dev); + } else { + zfcp_erp_port_forced_no_port_dbf( + "sctrpin", adapter, + rport->port_name /* zfcp_scsi_rport_register */, + rport->port_id /* zfcp_scsi_rport_register */); } } -- 2.16.3

7 years, 7 months

1
0
0 0

[PATCH 03/25] zfcp: fix misleading REC trigger trace where erp_action setup failed

by Steffen Maier

If a SCSI device is deleted during scsi_eh host reset, we cannot get a reference to the SCSI device anymore since scsi_device_get returns !=0 by design. Assuming the recovery of adapter and port(s) was successful, zfcp_erp_strategy_followup_success() attempts to trigger a LUN reset for the half-gone SCSI device. Unfortunately, it causes the following confusing trace record which states that zfcp will do a LUN recovery as "ERP need" is ZFCP_ERP_ACTION_REOPEN_LUN == 1 and equals "ERP want". Old example trace record formatted with zfcpdbf from s390-tools: Tag: : ersfs_3 ERP, trigger, unit reopen, port reopen succeeded LUN : 0x<FCP_LUN> WWPN : 0x<WWPN> D_ID : 0x<N_Port-ID> Adapter status : 0x5400050b Port status : 0x54000001 LUN status : 0x40000000 ZFCP_STATUS_COMMON_RUNNING but not ZFCP_STATUS_COMMON_UNBLOCKED as it was closed on close part of adapter reopen ERP want : 0x01 ERP need : 0x01 misleading However, zfcp_erp_setup_act() returns NULL as it cannot get the reference. Hence, zfcp_erp_action_enqueue() takes an early goto out and _NO_ recovery actually happens. We always do want the recovery trigger trace record even if no erp_action could be enqueued as in this case. For other cases where we did not enqueue an erp_action, 'need' has always been zero to indicate this. In order to indicate above goto out, introduce an eyecatcher "flag" to mark the "ERP need" as 'not needed' but still keep the information which erp_action type, that zfcp_erp_required_act() had decided upon, is needed. 0xc_ is chosen to be visibly different from 0x0_ in "ERP want". New example trace record formatted with zfcpdbf from s390-tools: Tag: : ersfs_3 ERP, trigger, unit reopen, port reopen succeeded LUN : 0x<FCP_LUN> WWPN : 0x<WWPN> D_ID : 0x<N_Port-ID> Adapter status : 0x5400050b Port status : 0x54000001 LUN status : 0x40000000 ERP want : 0x01 ERP need : 0xc1 would need LUN ERP, but no action set up ^ Before v2.6.38 commit ae0904f60fab ("[SCSI] zfcp: Redesign of the debug tracing for recovery actions.") we could detect this case because the "erp_action" field in the trace was NULL. The rework removed erp_action as argument and field from the trace. This patch here is for tracing. A fix to allow LUN recovery in the case at hand is a topic for a separate patch. See also commit fdbd1c5e27da ("[SCSI] zfcp: Allow running unit/LUN shutdown without acquiring reference") for a similar case and background info. Signed-off-by: Steffen Maier <maier(a)linux.ibm.com> Fixes: ae0904f60fab ("[SCSI] zfcp: Redesign of the debug tracing for recovery actions.") Cc: <stable(a)vger.kernel.org> #2.6.38+ Reviewed-by: Benjamin Block <bblock(a)linux.ibm.com> --- drivers/s390/scsi/zfcp_erp.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c index 1d91a32db08e..d9cd25b56cfa 100644 --- a/drivers/s390/scsi/zfcp_erp.c +++ b/drivers/s390/scsi/zfcp_erp.c @@ -35,11 +35,23 @@ enum zfcp_erp_steps { ZFCP_ERP_STEP_LUN_OPENING = 0x2000, }; +/** + * enum zfcp_erp_act_type - Type of ERP action object. + * @ZFCP_ERP_ACTION_REOPEN_LUN: LUN recovery. + * @ZFCP_ERP_ACTION_REOPEN_PORT: Port recovery. + * @ZFCP_ERP_ACTION_REOPEN_PORT_FORCED: Forced port recovery. + * @ZFCP_ERP_ACTION_REOPEN_ADAPTER: Adapter recovery. + * @ZFCP_ERP_ACTION_NONE: Eyecatcher pseudo flag to bitwise or-combine with + * either of the other enum values. + * Used to indicate that an ERP action could not be + * set up despite a detected need for some recovery. + */ enum zfcp_erp_act_type { ZFCP_ERP_ACTION_REOPEN_LUN = 1, ZFCP_ERP_ACTION_REOPEN_PORT = 2, ZFCP_ERP_ACTION_REOPEN_PORT_FORCED = 3, ZFCP_ERP_ACTION_REOPEN_ADAPTER = 4, + ZFCP_ERP_ACTION_NONE = 0xc0, }; enum zfcp_erp_act_state { @@ -257,8 +269,10 @@ static int zfcp_erp_action_enqueue(int want, struct zfcp_adapter *adapter, goto out; act = zfcp_erp_setup_act(need, act_status, adapter, port, sdev); - if (!act) + if (!act) { + need |= ZFCP_ERP_ACTION_NONE; /* marker for trace */ goto out; + } atomic_or(ZFCP_STATUS_ADAPTER_ERP_PENDING, &adapter->status); ++adapter->erp_total_count; list_add_tail(&act->list, &adapter->erp_ready_head); -- 2.16.3

7 years, 7 months

1
0
0 0

[PATCH 02/25] zfcp: fix missing SCSI trace for retry of abort / scsi_eh TMF

by Steffen Maier

We already have a SCSI trace for the end of abort and scsi_eh TMF. Due to zfcp_erp_wait() and fc_block_scsi_eh() time can pass between the start of our eh callback and an actual send/recv of an abort / TMF request. In order to see the temporal sequence including any abort / TMF send retries, add a trace before the above two blocking functions. This supports problem determination with scsi_eh and parallel zfcp ERP. No need to explicitly trace the beginning of our eh callback, since we typically can send an abort / TMF and see its HBA response (in the worst case, it's a pseudo response on dismiss all of adapter recovery, e.g. due to an FSF request timeout [fsrth_1] of the abort / TMF). If we cannot send, we now get a trace record for the first "abrt_wt" or "[lt]r_wait" which denotes almost the beginning of the callback. No need to explicitly trace the wakeup after the above two blocking functions because the next retry loop causes another trace in any case and that is sufficient. Example trace records formatted with zfcpdbf from s390-tools: Timestamp : ... Area : SCSI Subarea : 00 Level : 1 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : abrt_wt abort, before zfcp_erp_wait() Request ID : 0x0000000000000000 none (invalid) SCSI ID : 0x<scsi_id> SCSI LUN : 0x<scsi_lun> SCSI LUN high : 0x<scsi_lun_high> SCSI result : 0x<scsi_result_of_cmd_to_be_aborted> SCSI retries : 0x<retries_of_cmd_to_be_aborted> SCSI allowed : 0x<allowed_retries_of_cmd_to_be_aborted> SCSI scribble : 0x<req_id_of_cmd_to_be_aborted> SCSI opcode : <CDB_of_cmd_to_be_aborted> FCP rsp inf cod: 0x.. none (invalid) FCP rsp IU : ... none (invalid) Timestamp : ... Area : SCSI Subarea : 00 Level : 1 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : lr_wait LUN reset, before zfcp_erp_wait() Request ID : 0x0000000000000000 none (invalid) SCSI ID : 0x<scsi_id> SCSI LUN : 0x<scsi_lun> SCSI LUN high : 0x<scsi_lun_high> SCSI result : 0x... unrelated SCSI retries : 0x.. unrelated SCSI allowed : 0x.. unrelated SCSI scribble : 0x... unrelated SCSI opcode : ... unrelated FCP rsp inf cod: 0x.. none (invalid) FCP rsp IU : ... none (invalid) Signed-off-by: Steffen Maier <maier(a)linux.ibm.com> Fixes: 63caf367e1c9 ("[SCSI] zfcp: Improve reliability of SCSI eh handlers in zfcp") Fixes: af4de36d911a ("[SCSI] zfcp: Block scsi_eh thread for rport state BLOCKED") Cc: <stable(a)vger.kernel.org> #2.6.38+ Reviewed-by: Benjamin Block <bblock(a)linux.ibm.com> --- drivers/s390/scsi/zfcp_scsi.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c index a62357f5e8b4..4fdb1665b0e6 100644 --- a/drivers/s390/scsi/zfcp_scsi.c +++ b/drivers/s390/scsi/zfcp_scsi.c @@ -181,6 +181,7 @@ static int zfcp_scsi_eh_abort_handler(struct scsi_cmnd *scpnt) if (abrt_req) break; + zfcp_dbf_scsi_abort("abrt_wt", scpnt, NULL); zfcp_erp_wait(adapter); ret = fc_block_scsi_eh(scpnt); if (ret) { @@ -277,6 +278,7 @@ static int zfcp_task_mgmt_function(struct scsi_cmnd *scpnt, u8 tm_flags) if (fsf_req) break; + zfcp_dbf_scsi_devreset("wait", scpnt, tm_flags, NULL); zfcp_erp_wait(adapter); ret = fc_block_scsi_eh(scpnt); if (ret) { -- 2.16.3

7 years, 7 months

1
0
0 0

[PATCH 01/25] zfcp: fix missing SCSI trace for result of eh_host_reset_handler

by Steffen Maier

For problem determination we need to see whether and why we were successful or not. This allows deduction of scsi_eh escalation. Example trace record formatted with zfcpdbf from s390-tools: Timestamp : ... Area : SCSI Subarea : 00 Level : 1 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : schrh_r SCSI host reset handler result Request ID : 0x0000000000000000 none (invalid) SCSI ID : 0xffffffff none (invalid) SCSI LUN : 0xffffffff none (invalid) SCSI LUN high : 0xffffffff none (invalid) SCSI result : 0x00002002 field re-used for midlayer value: SUCCESS or in other cases: 0x2009 == FAST_IO_FAIL SCSI retries : 0xff none (invalid) SCSI allowed : 0xff none (invalid) SCSI scribble : 0xffffffffffffffff none (invalid) SCSI opcode : ffffffff ffffffff ffffffff ffffffff none (invalid) FCP rsp inf cod: 0xff none (invalid) FCP rsp IU : 00000000 00000000 00000000 00000000 none (invalid) 00000000 00000000 v2.6.35 commit a1dbfddd02d2 ("[SCSI] zfcp: Pass return code from fc_block_scsi_eh to scsi eh") introduced the first return with something other than the previously hardcoded single SUCCESS return path. Signed-off-by: Steffen Maier <maier(a)linux.ibm.com> Fixes: a1dbfddd02d2 ("[SCSI] zfcp: Pass return code from fc_block_scsi_eh to scsi eh") Cc: <stable(a)vger.kernel.org> #2.6.38+ Reviewed-by: Jens Remus <jremus(a)linux.ibm.com> Reviewed-by: Benjamin Block <bblock(a)linux.ibm.com> --- drivers/s390/scsi/zfcp_dbf.c | 40 ++++++++++++++++++++++++++++++++++++++++ drivers/s390/scsi/zfcp_ext.h | 2 ++ drivers/s390/scsi/zfcp_scsi.c | 11 ++++++----- 3 files changed, 48 insertions(+), 5 deletions(-) diff --git a/drivers/s390/scsi/zfcp_dbf.c b/drivers/s390/scsi/zfcp_dbf.c index a8b831000b2d..1e5ea5e4992b 100644 --- a/drivers/s390/scsi/zfcp_dbf.c +++ b/drivers/s390/scsi/zfcp_dbf.c @@ -643,6 +643,46 @@ void zfcp_dbf_scsi(char *tag, int level, struct scsi_cmnd *sc, spin_unlock_irqrestore(&dbf->scsi_lock, flags); } +/** + * zfcp_dbf_scsi_eh() - Trace event for special cases of scsi_eh callbacks. + * @tag: Identifier for event. + * @adapter: Pointer to zfcp adapter as context for this event. + * @scsi_id: SCSI ID/target to indicate scope of task management function (TMF). + * @ret: Return value of calling function. + * + * This SCSI trace variant does not depend on any of: + * scsi_cmnd, zfcp_fsf_req, scsi_device. + */ +void zfcp_dbf_scsi_eh(char *tag, struct zfcp_adapter *adapter, + unsigned int scsi_id, int ret) +{ + struct zfcp_dbf *dbf = adapter->dbf; + struct zfcp_dbf_scsi *rec = &dbf->scsi_buf; + unsigned long flags; + static int const level = 1; + + if (unlikely(!debug_level_enabled(adapter->dbf->scsi, level))) + return; + + spin_lock_irqsave(&dbf->scsi_lock, flags); + memset(rec, 0, sizeof(*rec)); + + memcpy(rec->tag, tag, ZFCP_DBF_TAG_LEN); + rec->id = ZFCP_DBF_SCSI_CMND; + rec->scsi_result = ret; /* re-use field, int is 4 bytes and fits */ + rec->scsi_retries = ~0; + rec->scsi_allowed = ~0; + rec->fcp_rsp_info = ~0; + rec->scsi_id = scsi_id; + rec->scsi_lun = (u32)ZFCP_DBF_INVALID_LUN; + rec->scsi_lun_64_hi = (u32)(ZFCP_DBF_INVALID_LUN >> 32); + rec->host_scribble = ~0; + memset(rec->scsi_opcode, 0xff, ZFCP_DBF_SCSI_OPCODE); + + debug_event(dbf->scsi, level, rec, sizeof(*rec)); + spin_unlock_irqrestore(&dbf->scsi_lock, flags); +} + static debug_info_t *zfcp_dbf_reg(const char *name, int size, int rec_size) { struct debug_info *d; diff --git a/drivers/s390/scsi/zfcp_ext.h b/drivers/s390/scsi/zfcp_ext.h index bf8ea4df2bb8..e55f42ce1168 100644 --- a/drivers/s390/scsi/zfcp_ext.h +++ b/drivers/s390/scsi/zfcp_ext.h @@ -49,6 +49,8 @@ extern void zfcp_dbf_san_res(char *, struct zfcp_fsf_req *); extern void zfcp_dbf_san_in_els(char *, struct zfcp_fsf_req *); extern void zfcp_dbf_scsi(char *, int, struct scsi_cmnd *, struct zfcp_fsf_req *); +extern void zfcp_dbf_scsi_eh(char *tag, struct zfcp_adapter *adapter, + unsigned int scsi_id, int ret); /* zfcp_erp.c */ extern void zfcp_erp_set_adapter_status(struct zfcp_adapter *, u32); diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c index 4d2ba5682493..a62357f5e8b4 100644 --- a/drivers/s390/scsi/zfcp_scsi.c +++ b/drivers/s390/scsi/zfcp_scsi.c @@ -323,15 +323,16 @@ static int zfcp_scsi_eh_host_reset_handler(struct scsi_cmnd *scpnt) { struct zfcp_scsi_dev *zfcp_sdev = sdev_to_zfcp(scpnt->device); struct zfcp_adapter *adapter = zfcp_sdev->port->adapter; - int ret; + int ret = SUCCESS, fc_ret; zfcp_erp_adapter_reopen(adapter, 0, "schrh_1"); zfcp_erp_wait(adapter); - ret = fc_block_scsi_eh(scpnt); - if (ret) - return ret; + fc_ret = fc_block_scsi_eh(scpnt); + if (fc_ret) + ret = fc_ret; - return SUCCESS; + zfcp_dbf_scsi_eh("schrh_r", adapter, ~0, ret); + return ret; } struct scsi_transport_template *zfcp_scsi_transport_template; -- 2.16.3

7 years, 7 months

1
0
0 0

FAILED: patch "net: ethernet: ti: cpsw: fix packet leaking in dual_mac mode" failed to build on 4.4 tree

by Dan Rue

It seems that patch "net: ethernet: ti: cpsw: fix packet leaking in dual_mac mode" fails to build in the upcoming 4.4 release candidate. CC drivers/net/ethernet/ti/cpsw.o ../drivers/net/ethernet/ti/cpsw.c: In function ‘cpsw_add_dual_emac_def_ale_entries’: ../drivers/net/ethernet/ti/cpsw.c:1112:23: error: ‘cpsw’ undeclared (first use in this function); did you mean ‘cpts’? cpsw_ale_control_set(cpsw->ale, slave_port, ^~~~ cpts ../drivers/net/ethernet/ti/cpsw.c:1112:23: note: each undeclared identifier is reported only once for each function it appears in Thanks, Dan -- Linaro LKFT https://lkft.linaro.org/

7 years, 7 months

2
1
0 0

Applied "spi: spi-s3c64xx: Fix system resume support" to the spi tree

by Mark Brown

The patch spi: spi-s3c64xx: Fix system resume support has been applied to the spi tree at https://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi.git All being well this means that it will be integrated into the linux-next tree (usually sometime in the next 24 hours) and sent to Linus during the next merge window (or sooner if it is a bug fix), however if problems are discovered then the patch may be dropped or reverted. You may get further e-mails resulting from automated or manual testing and review of the tree, please engage with people reporting problems and send followup patches addressing any issues that are reported if needed. If any updates are required or you are submitting further changes they should be sent as incremental updates against current git, existing patches will not be replaced. Please add any relevant lists and maintainers to the CCs when replying to this mail. Thanks, Mark >From e935dba111621bd6a0c5d48e6511a4d9885103b4 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski <m.szyprowski(a)samsung.com> Date: Wed, 16 May 2018 10:42:39 +0200 Subject: [PATCH] spi: spi-s3c64xx: Fix system resume support Since Linux v4.10 release (commit 1d9174fbc55e "PM / Runtime: Defer resuming of the device in pm_runtime_force_resume()"), pm_runtime_force_resume() function doesn't runtime resume device if it was not runtime active before system suspend. Thus, driver should not do any register access after pm_runtime_force_resume() without checking the runtime status of the device. To fix this issue, simply move s3c64xx_spi_hwinit() call to s3c64xx_spi_runtime_resume() to ensure that hardware is always properly initialized. This fixes Synchronous external abort issue on system suspend/resume cycle on newer Exynos SoCs. Signed-off-by: Marek Szyprowski <m.szyprowski(a)samsung.com> Reviewed-by: Krzysztof Kozlowski <krzk(a)kernel.org> Signed-off-by: Mark Brown <broonie(a)kernel.org> Cc: stable(a)vger.kernel.org --- drivers/spi/spi-s3c64xx.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c index f55dc78957ad..7b7151ec14c8 100644 --- a/drivers/spi/spi-s3c64xx.c +++ b/drivers/spi/spi-s3c64xx.c @@ -1292,8 +1292,6 @@ static int s3c64xx_spi_resume(struct device *dev) if (ret < 0) return ret; - s3c64xx_spi_hwinit(sdd); - return spi_master_resume(master); } #endif /* CONFIG_PM_SLEEP */ @@ -1331,6 +1329,8 @@ static int s3c64xx_spi_runtime_resume(struct device *dev) if (ret != 0) goto err_disable_src_clk; + s3c64xx_spi_hwinit(sdd); + return 0; err_disable_src_clk: -- 2.17.0

7 years, 7 months

1
0
0 0

net: ieee802154: 6lowpan: fix frag reassembly

by Stefan Schmidt

Hello. Please apply f18fa5de5ba7f1d6650951502bb96a6e4715a948 (net: ieee802154: 6lowpan: fix frag reassembly) to the 4.16.x stable tree. Earlier trees are not needed as the problem was introduced in 4.16. Normally net/ patches would come through DaveM, but he asked me for this one to submit it directly when i sent him the pull request. First time stable request on my side here, let me know if I got something wrong. regards Stefan Schmidt

7 years, 7 months

4
5
0 0

[PATCH v3-UPADATE 2/3] ioremap: Update pgtable free interfaces with addr

by Toshi Kani

From: Chintan Pandya <cpandya(a)codeaurora.org> The following kernel panic was observed on ARM64 platform due to a stale TLB entry. 1. ioremap with 4K size, a valid pte page table is set. 2. iounmap it, its pte entry is set to 0. 3. ioremap the same address with 2M size, update its pmd entry with a new value. 4. CPU may hit an exception because the old pmd entry is still in TLB, which leads to a kernel panic. Commit b6bdb7517c3d ("mm/vmalloc: add interfaces to free unmapped page table") has addressed this panic by falling to pte mappings in the above case on ARM64. To support pmd mappings in all cases, TLB purge needs to be performed in this case on ARM64. Add a new arg, 'addr', to pud_free_pmd_page() and pmd_free_pte_page() so that TLB purge can be added later in seprate patches. [toshi(a)hpe.com: merge changes, rewrite patch description] Fixes: 28ee90fe6048 ("x86/mm: implement free pmd/pte page interfaces") Signed-off-by: Chintan Pandya <cpandya(a)codeaurora.org> Signed-off-by: Toshi Kani <toshi.kani(a)hpe.com> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Will Deacon <will.deacon(a)arm.com> Cc: Joerg Roedel <joro(a)8bytes.org> Cc: <stable(a)vger.kernel.org> --- v3-UPDATE - Rewrite patch description --- arch/arm64/mm/mmu.c | 4 ++-- arch/x86/mm/pgtable.c | 12 +++++++----- include/asm-generic/pgtable.h | 8 ++++---- lib/ioremap.c | 4 ++-- 4 files changed, 15 insertions(+), 13 deletions(-) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 2dbb2c9f1ec1..da98828609a1 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -973,12 +973,12 @@ int pmd_clear_huge(pmd_t *pmdp) return 1; } -int pud_free_pmd_page(pud_t *pud) +int pud_free_pmd_page(pud_t *pud, unsigned long addr) { return pud_none(*pud); } -int pmd_free_pte_page(pmd_t *pmd) +int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { return pmd_none(*pmd); } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 3f7180bc5f52..f60fdf411103 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -719,11 +719,12 @@ int pmd_clear_huge(pmd_t *pmd) /** * pud_free_pmd_page - Clear pud entry and free pmd page. * @pud: Pointer to a PUD. + * @addr: Virtual address associated with pud. * * Context: The pud range has been unmaped and TLB purged. * Return: 1 if clearing the entry succeeded. 0 otherwise. */ -int pud_free_pmd_page(pud_t *pud) +int pud_free_pmd_page(pud_t *pud, unsigned long addr) { pmd_t *pmd; int i; @@ -734,7 +735,7 @@ int pud_free_pmd_page(pud_t *pud) pmd = (pmd_t *)pud_page_vaddr(*pud); for (i = 0; i < PTRS_PER_PMD; i++) - if (!pmd_free_pte_page(&pmd[i])) + if (!pmd_free_pte_page(&pmd[i], addr + (i * PMD_SIZE))) return 0; pud_clear(pud); @@ -746,11 +747,12 @@ int pud_free_pmd_page(pud_t *pud) /** * pmd_free_pte_page - Clear pmd entry and free pte page. * @pmd: Pointer to a PMD. + * @addr: Virtual address associated with pmd. * * Context: The pmd range has been unmaped and TLB purged. * Return: 1 if clearing the entry succeeded. 0 otherwise. */ -int pmd_free_pte_page(pmd_t *pmd) +int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { pte_t *pte; @@ -766,7 +768,7 @@ int pmd_free_pte_page(pmd_t *pmd) #else /* !CONFIG_X86_64 */ -int pud_free_pmd_page(pud_t *pud) +int pud_free_pmd_page(pud_t *pud, unsigned long addr) { return pud_none(*pud); } @@ -775,7 +777,7 @@ int pud_free_pmd_page(pud_t *pud) * Disable free page handling on x86-PAE. This assures that ioremap() * does not update sync'd pmd entries. See vmalloc_sync_one(). */ -int pmd_free_pte_page(pmd_t *pmd) +int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { return pmd_none(*pmd); } diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index f59639afaa39..b081794ba135 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1019,8 +1019,8 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pud_clear_huge(pud_t *pud); int pmd_clear_huge(pmd_t *pmd); -int pud_free_pmd_page(pud_t *pud); -int pmd_free_pte_page(pmd_t *pmd); +int pud_free_pmd_page(pud_t *pud, unsigned long addr); +int pmd_free_pte_page(pmd_t *pmd, unsigned long addr); #else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { @@ -1046,11 +1046,11 @@ static inline int pmd_clear_huge(pmd_t *pmd) { return 0; } -static inline int pud_free_pmd_page(pud_t *pud) +static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr) { return 0; } -static inline int pmd_free_pte_page(pmd_t *pmd) +static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { return 0; } diff --git a/lib/ioremap.c b/lib/ioremap.c index 54e5bbaa3200..517f5853ffed 100644 --- a/lib/ioremap.c +++ b/lib/ioremap.c @@ -92,7 +92,7 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr, if (ioremap_pmd_enabled() && ((next - addr) == PMD_SIZE) && IS_ALIGNED(phys_addr + addr, PMD_SIZE) && - pmd_free_pte_page(pmd)) { + pmd_free_pte_page(pmd, addr)) { if (pmd_set_huge(pmd, phys_addr + addr, prot)) continue; } @@ -119,7 +119,7 @@ static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr, if (ioremap_pud_enabled() && ((next - addr) == PUD_SIZE) && IS_ALIGNED(phys_addr + addr, PUD_SIZE) && - pud_free_pmd_page(pud)) { + pud_free_pmd_page(pud, addr)) { if (pud_set_huge(pud, phys_addr + addr, prot)) continue; }

7 years, 7 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror