OpenCloudOS-Kernel/drivers/s390/scsi/zfcp_dbf.c

742 lines
21 KiB
C
Raw Normal View History

/*
* zfcp device driver
*
* Debug traces for zfcp.
*
scsi: zfcp: fix capping of unsuccessful GPN_FT SAN response trace records v4.9 commit aceeffbb59bb ("zfcp: trace full payload of all SAN records (req,resp,iels)") fixed trace data loss of 2.6.38 commit 2c55b750a884 ("[SCSI] zfcp: Redesign of the debug tracing for SAN records.") necessary for problem determination, e.g. to see the currently active zone set during automatic port scan. While it already saves space by not dumping any empty residual entries of the large successful GPN_FT response (4 pages), there are seldom cases where the GPN_FT response is unsuccessful and likely does not have FC_NS_FID_LAST set in fp_flags so we did not cap the trace record. We typically see such case for an initiator WWPN, which is not in any zone. Cap unsuccessful responses to at least the actual basic CT_IU response plus whatever fits the SAN trace record built-in "payload" buffer just in case there's trailing information of which we would at least see the existence and its beginning. In order not to erroneously cap successful responses, we need to swap calling the trace function and setting the CT / ELS status to success (0). Example trace record pair formatted with zfcpdbf: Timestamp : ... Area : SAN Subarea : 00 Level : 1 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : fssct_1 Request ID : 0x<request_id> Destination ID : 0x00fffffc SAN req short : 01000000 fc020000 01720ffc 00000000 00000008 SAN req length : 20 | Timestamp : ... Area : SAN Subarea : 00 Level : 1 Exception : - CPU ID : .. Caller : 0x... Record ID : 2 Tag : fsscth2 Request ID : 0x<request_id> Destination ID : 0x00fffffc SAN resp short : 01000000 fc020000 80010000 00090700 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] SAN resp length: 16384 San resp info : 01000000 fc020000 80010000 00090700 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] The fix saves all but one of the previously associated 64 PAYload trace record chunks of size 256 bytes each. Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com> Fixes: aceeffbb59bb ("zfcp: trace full payload of all SAN records (req,resp,iels)") Fixes: 2c55b750a884 ("[SCSI] zfcp: Redesign of the debug tracing for SAN records.") Cc: <stable@vger.kernel.org> #2.6.38+ Reviewed-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-07-28 18:30:53 +08:00
* Copyright IBM Corp. 2002, 2017
*/
#define KMSG_COMPONENT "zfcp"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
#include <linux/module.h>
#include <linux/ctype.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <asm/debug.h>
#include "zfcp_dbf.h"
#include "zfcp_ext.h"
#include "zfcp_fc.h"
static u32 dbfsize = 4;
module_param(dbfsize, uint, 0400);
MODULE_PARM_DESC(dbfsize,
"number of pages for each debug feature area (default 4)");
static u32 dbflevel = 3;
module_param(dbflevel, uint, 0400);
MODULE_PARM_DESC(dbflevel,
"log level for each debug feature area "
"(default 3, range 0..6)");
static inline unsigned int zfcp_dbf_plen(unsigned int offset)
{
return sizeof(struct zfcp_dbf_pay) + offset - ZFCP_DBF_PAY_MAX_REC;
}
static inline
void zfcp_dbf_pl_write(struct zfcp_dbf *dbf, void *data, u16 length, char *area,
u64 req_id)
{
struct zfcp_dbf_pay *pl = &dbf->pay_buf;
u16 offset = 0, rec_length;
spin_lock(&dbf->pay_lock);
memset(pl, 0, sizeof(*pl));
pl->fsf_req_id = req_id;
memcpy(pl->area, area, ZFCP_DBF_TAG_LEN);
while (offset < length) {
rec_length = min((u16) ZFCP_DBF_PAY_MAX_REC,
(u16) (length - offset));
memcpy(pl->data, data + offset, rec_length);
debug_event(dbf->pay, 1, pl, zfcp_dbf_plen(rec_length));
offset += rec_length;
pl->counter++;
}
spin_unlock(&dbf->pay_lock);
}
/**
* zfcp_dbf_hba_fsf_res - trace event for fsf responses
* @tag: tag indicating which kind of unsolicited status has been received
* @req: request for which a response was received
*/
void zfcp_dbf_hba_fsf_res(char *tag, int level, struct zfcp_fsf_req *req)
{
struct zfcp_dbf *dbf = req->adapter->dbf;
struct fsf_qtcb_prefix *q_pref = &req->qtcb->prefix;
struct fsf_qtcb_header *q_head = &req->qtcb->header;
struct zfcp_dbf_hba *rec = &dbf->hba_buf;
unsigned long flags;
spin_lock_irqsave(&dbf->hba_lock, flags);
memset(rec, 0, sizeof(*rec));
memcpy(rec->tag, tag, ZFCP_DBF_TAG_LEN);
rec->id = ZFCP_DBF_HBA_RES;
rec->fsf_req_id = req->req_id;
rec->fsf_req_status = req->status;
rec->fsf_cmd = req->fsf_command;
rec->fsf_seq_no = req->seq_no;
rec->u.res.req_issued = req->issued;
rec->u.res.prot_status = q_pref->prot_status;
rec->u.res.fsf_status = q_head->fsf_status;
rec->u.res.port_handle = q_head->port_handle;
rec->u.res.lun_handle = q_head->lun_handle;
memcpy(rec->u.res.prot_status_qual, &q_pref->prot_status_qual,
FSF_PROT_STATUS_QUAL_SIZE);
memcpy(rec->u.res.fsf_status_qual, &q_head->fsf_status_qual,
FSF_STATUS_QUALIFIER_SIZE);
if (req->fsf_command != FSF_QTCB_FCP_CMND) {
rec->pl_len = q_head->log_length;
zfcp_dbf_pl_write(dbf, (char *)q_pref + q_head->log_start,
rec->pl_len, "fsf_res", req->req_id);
}
debug_event(dbf->hba, level, rec, sizeof(*rec));
spin_unlock_irqrestore(&dbf->hba_lock, flags);
}
/**
* zfcp_dbf_hba_fsf_uss - trace event for an unsolicited status buffer
* @tag: tag indicating which kind of unsolicited status has been received
* @req: request providing the unsolicited status
*/
void zfcp_dbf_hba_fsf_uss(char *tag, struct zfcp_fsf_req *req)
{
struct zfcp_dbf *dbf = req->adapter->dbf;
struct fsf_status_read_buffer *srb = req->data;
struct zfcp_dbf_hba *rec = &dbf->hba_buf;
static int const level = 2;
unsigned long flags;
if (unlikely(!debug_level_enabled(dbf->hba, level)))
return;
spin_lock_irqsave(&dbf->hba_lock, flags);
memset(rec, 0, sizeof(*rec));
memcpy(rec->tag, tag, ZFCP_DBF_TAG_LEN);
rec->id = ZFCP_DBF_HBA_USS;
rec->fsf_req_id = req->req_id;
rec->fsf_req_status = req->status;
rec->fsf_cmd = req->fsf_command;
if (!srb)
goto log;
rec->u.uss.status_type = srb->status_type;
rec->u.uss.status_subtype = srb->status_subtype;
rec->u.uss.d_id = ntoh24(srb->d_id);
rec->u.uss.lun = srb->fcp_lun;
memcpy(&rec->u.uss.queue_designator, &srb->queue_designator,
sizeof(rec->u.uss.queue_designator));
/* status read buffer payload length */
rec->pl_len = (!srb->length) ? 0 : srb->length -
offsetof(struct fsf_status_read_buffer, payload);
if (rec->pl_len)
zfcp_dbf_pl_write(dbf, srb->payload.data, rec->pl_len,
"fsf_uss", req->req_id);
log:
debug_event(dbf->hba, level, rec, sizeof(*rec));
spin_unlock_irqrestore(&dbf->hba_lock, flags);
}
/**
* zfcp_dbf_hba_bit_err - trace event for bit error conditions
* @tag: tag indicating which kind of unsolicited status has been received
* @req: request which caused the bit_error condition
*/
void zfcp_dbf_hba_bit_err(char *tag, struct zfcp_fsf_req *req)
{
struct zfcp_dbf *dbf = req->adapter->dbf;
struct zfcp_dbf_hba *rec = &dbf->hba_buf;
struct fsf_status_read_buffer *sr_buf = req->data;
static int const level = 1;
unsigned long flags;
if (unlikely(!debug_level_enabled(dbf->hba, level)))
return;
spin_lock_irqsave(&dbf->hba_lock, flags);
memset(rec, 0, sizeof(*rec));
memcpy(rec->tag, tag, ZFCP_DBF_TAG_LEN);
rec->id = ZFCP_DBF_HBA_BIT;
rec->fsf_req_id = req->req_id;
rec->fsf_req_status = req->status;
rec->fsf_cmd = req->fsf_command;
memcpy(&rec->u.be, &sr_buf->payload.bit_error,
sizeof(struct fsf_bit_error_payload));
debug_event(dbf->hba, level, rec, sizeof(*rec));
spin_unlock_irqrestore(&dbf->hba_lock, flags);
}
/**
* zfcp_dbf_hba_def_err - trace event for deferred error messages
* @adapter: pointer to struct zfcp_adapter
* @req_id: request id which caused the deferred error message
* @scount: number of sbals incl. the signaling sbal
* @pl: array of all involved sbals
*/
void zfcp_dbf_hba_def_err(struct zfcp_adapter *adapter, u64 req_id, u16 scount,
void **pl)
{
struct zfcp_dbf *dbf = adapter->dbf;
struct zfcp_dbf_pay *payload = &dbf->pay_buf;
unsigned long flags;
static int const level = 1;
u16 length;
if (unlikely(!debug_level_enabled(dbf->pay, level)))
return;
if (!pl)
return;
spin_lock_irqsave(&dbf->pay_lock, flags);
memset(payload, 0, sizeof(*payload));
memcpy(payload->area, "def_err", 7);
payload->fsf_req_id = req_id;
payload->counter = 0;
length = min((u16)sizeof(struct qdio_buffer),
(u16)ZFCP_DBF_PAY_MAX_REC);
while (payload->counter < scount && (char *)pl[payload->counter]) {
memcpy(payload->data, (char *)pl[payload->counter], length);
debug_event(dbf->pay, level, payload, zfcp_dbf_plen(length));
payload->counter++;
}
spin_unlock_irqrestore(&dbf->pay_lock, flags);
}
[SCSI] zfcp: Do not wakeup while suspended If the mapping of FCP device bus ID and corresponding subchannel is modified while the Linux image is suspended, the resume of FCP devices can fail. During resume, zfcp gets callbacks from cio regarding the modified subchannels but they can be arbitrarily mixed with the restore/resume callback. Since the cio callbacks would trigger adapter recovery, zfcp could wakeup before the resume callback. Therefore, ignore the cio callbacks regarding subchannels while being suspended. We can safely do so, since zfcp does not deal itself with subchannels. For problem determination purposes, we still trace the ignored callback events. The following kernel messages could be seen on resume: kernel: <WWPN>: parent <FCP device bus ID> should not be sleeping As part of adapter reopen recovery, zfcp performs auto port scanning which can erroneously try to register new remote ports with scsi_transport_fc and the device core code complains about the parent (adapter) still sleeping. kernel: zfcp.3dff9c: <FCP device bus ID>:\ Setting up the QDIO connection to the FCP adapter failed <last kernel message repeated 3 more times> kernel: zfcp.574d43: <FCP device bus ID>:\ ERP cannot recover an error on the FCP device In such cases, the adapter gave up recovery and remained blocked along with its child objects: remote ports and LUNs/scsi devices. Even the adapter shutdown as part of giving up recovery failed because the ccw device state remained disconnected. Later, the corresponding remote ports ran into dev_loss_tmo. As a result, the LUNs were erroneously not available again after resume. Even a manually triggered adapter recovery (e.g. sysfs attribute failed, or device offline/online via sysfs) could not recover the adapter due to the remaining disconnected state of the corresponding ccw device. Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com> Cc: <stable@vger.kernel.org> #2.6.32+ Signed-off-by: James Bottomley <JBottomley@Parallels.com>
2012-09-04 21:23:32 +08:00
/**
* zfcp_dbf_hba_basic - trace event for basic adapter events
* @adapter: pointer to struct zfcp_adapter
*/
void zfcp_dbf_hba_basic(char *tag, struct zfcp_adapter *adapter)
{
struct zfcp_dbf *dbf = adapter->dbf;
struct zfcp_dbf_hba *rec = &dbf->hba_buf;
static int const level = 1;
[SCSI] zfcp: Do not wakeup while suspended If the mapping of FCP device bus ID and corresponding subchannel is modified while the Linux image is suspended, the resume of FCP devices can fail. During resume, zfcp gets callbacks from cio regarding the modified subchannels but they can be arbitrarily mixed with the restore/resume callback. Since the cio callbacks would trigger adapter recovery, zfcp could wakeup before the resume callback. Therefore, ignore the cio callbacks regarding subchannels while being suspended. We can safely do so, since zfcp does not deal itself with subchannels. For problem determination purposes, we still trace the ignored callback events. The following kernel messages could be seen on resume: kernel: <WWPN>: parent <FCP device bus ID> should not be sleeping As part of adapter reopen recovery, zfcp performs auto port scanning which can erroneously try to register new remote ports with scsi_transport_fc and the device core code complains about the parent (adapter) still sleeping. kernel: zfcp.3dff9c: <FCP device bus ID>:\ Setting up the QDIO connection to the FCP adapter failed <last kernel message repeated 3 more times> kernel: zfcp.574d43: <FCP device bus ID>:\ ERP cannot recover an error on the FCP device In such cases, the adapter gave up recovery and remained blocked along with its child objects: remote ports and LUNs/scsi devices. Even the adapter shutdown as part of giving up recovery failed because the ccw device state remained disconnected. Later, the corresponding remote ports ran into dev_loss_tmo. As a result, the LUNs were erroneously not available again after resume. Even a manually triggered adapter recovery (e.g. sysfs attribute failed, or device offline/online via sysfs) could not recover the adapter due to the remaining disconnected state of the corresponding ccw device. Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com> Cc: <stable@vger.kernel.org> #2.6.32+ Signed-off-by: James Bottomley <JBottomley@Parallels.com>
2012-09-04 21:23:32 +08:00
unsigned long flags;
if (unlikely(!debug_level_enabled(dbf->hba, level)))
return;
[SCSI] zfcp: Do not wakeup while suspended If the mapping of FCP device bus ID and corresponding subchannel is modified while the Linux image is suspended, the resume of FCP devices can fail. During resume, zfcp gets callbacks from cio regarding the modified subchannels but they can be arbitrarily mixed with the restore/resume callback. Since the cio callbacks would trigger adapter recovery, zfcp could wakeup before the resume callback. Therefore, ignore the cio callbacks regarding subchannels while being suspended. We can safely do so, since zfcp does not deal itself with subchannels. For problem determination purposes, we still trace the ignored callback events. The following kernel messages could be seen on resume: kernel: <WWPN>: parent <FCP device bus ID> should not be sleeping As part of adapter reopen recovery, zfcp performs auto port scanning which can erroneously try to register new remote ports with scsi_transport_fc and the device core code complains about the parent (adapter) still sleeping. kernel: zfcp.3dff9c: <FCP device bus ID>:\ Setting up the QDIO connection to the FCP adapter failed <last kernel message repeated 3 more times> kernel: zfcp.574d43: <FCP device bus ID>:\ ERP cannot recover an error on the FCP device In such cases, the adapter gave up recovery and remained blocked along with its child objects: remote ports and LUNs/scsi devices. Even the adapter shutdown as part of giving up recovery failed because the ccw device state remained disconnected. Later, the corresponding remote ports ran into dev_loss_tmo. As a result, the LUNs were erroneously not available again after resume. Even a manually triggered adapter recovery (e.g. sysfs attribute failed, or device offline/online via sysfs) could not recover the adapter due to the remaining disconnected state of the corresponding ccw device. Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com> Cc: <stable@vger.kernel.org> #2.6.32+ Signed-off-by: James Bottomley <JBottomley@Parallels.com>
2012-09-04 21:23:32 +08:00
spin_lock_irqsave(&dbf->hba_lock, flags);
memset(rec, 0, sizeof(*rec));
memcpy(rec->tag, tag, ZFCP_DBF_TAG_LEN);
rec->id = ZFCP_DBF_HBA_BASIC;
debug_event(dbf->hba, level, rec, sizeof(*rec));
[SCSI] zfcp: Do not wakeup while suspended If the mapping of FCP device bus ID and corresponding subchannel is modified while the Linux image is suspended, the resume of FCP devices can fail. During resume, zfcp gets callbacks from cio regarding the modified subchannels but they can be arbitrarily mixed with the restore/resume callback. Since the cio callbacks would trigger adapter recovery, zfcp could wakeup before the resume callback. Therefore, ignore the cio callbacks regarding subchannels while being suspended. We can safely do so, since zfcp does not deal itself with subchannels. For problem determination purposes, we still trace the ignored callback events. The following kernel messages could be seen on resume: kernel: <WWPN>: parent <FCP device bus ID> should not be sleeping As part of adapter reopen recovery, zfcp performs auto port scanning which can erroneously try to register new remote ports with scsi_transport_fc and the device core code complains about the parent (adapter) still sleeping. kernel: zfcp.3dff9c: <FCP device bus ID>:\ Setting up the QDIO connection to the FCP adapter failed <last kernel message repeated 3 more times> kernel: zfcp.574d43: <FCP device bus ID>:\ ERP cannot recover an error on the FCP device In such cases, the adapter gave up recovery and remained blocked along with its child objects: remote ports and LUNs/scsi devices. Even the adapter shutdown as part of giving up recovery failed because the ccw device state remained disconnected. Later, the corresponding remote ports ran into dev_loss_tmo. As a result, the LUNs were erroneously not available again after resume. Even a manually triggered adapter recovery (e.g. sysfs attribute failed, or device offline/online via sysfs) could not recover the adapter due to the remaining disconnected state of the corresponding ccw device. Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com> Cc: <stable@vger.kernel.org> #2.6.32+ Signed-off-by: James Bottomley <JBottomley@Parallels.com>
2012-09-04 21:23:32 +08:00
spin_unlock_irqrestore(&dbf->hba_lock, flags);
}
static void zfcp_dbf_set_common(struct zfcp_dbf_rec *rec,
struct zfcp_adapter *adapter,
struct zfcp_port *port,
struct scsi_device *sdev)
{
rec->adapter_status = atomic_read(&adapter->status);
if (port) {
rec->port_status = atomic_read(&port->status);
rec->wwpn = port->wwpn;
rec->d_id = port->d_id;
}
if (sdev) {
rec->lun_status = atomic_read(&sdev_to_zfcp(sdev)->status);
rec->lun = zfcp_scsi_dev_lun(sdev);
} else
rec->lun = ZFCP_DBF_INVALID_LUN;
}
/**
* zfcp_dbf_rec_trig - trace event related to triggered recovery
* @tag: identifier for event
* @adapter: adapter on which the erp_action should run
* @port: remote port involved in the erp_action
* @sdev: scsi device involved in the erp_action
* @want: wanted erp_action
* @need: required erp_action
*
* The adapter->erp_lock has to be held.
*/
void zfcp_dbf_rec_trig(char *tag, struct zfcp_adapter *adapter,
struct zfcp_port *port, struct scsi_device *sdev,
u8 want, u8 need)
{
struct zfcp_dbf *dbf = adapter->dbf;
struct zfcp_dbf_rec *rec = &dbf->rec_buf;
static int const level = 1;
struct list_head *entry;
unsigned long flags;
if (unlikely(!debug_level_enabled(dbf->rec, level)))
return;
spin_lock_irqsave(&dbf->rec_lock, flags);
memset(rec, 0, sizeof(*rec));
rec->id = ZFCP_DBF_REC_TRIG;
memcpy(rec->tag, tag, ZFCP_DBF_TAG_LEN);
zfcp_dbf_set_common(rec, adapter, port, sdev);
list_for_each(entry, &adapter->erp_ready_head)
rec->u.trig.ready++;
list_for_each(entry, &adapter->erp_running_head)
rec->u.trig.running++;
rec->u.trig.want = want;
rec->u.trig.need = need;
debug_event(dbf->rec, level, rec, sizeof(*rec));
spin_unlock_irqrestore(&dbf->rec_lock, flags);
}
/**
scsi: zfcp: fix rport unblock race with LUN recovery It is unavoidable that zfcp_scsi_queuecommand() has to finish requests with DID_IMM_RETRY (like fc_remote_port_chkready()) during the time window when zfcp detected an unavailable rport but fc_remote_port_delete(), which is asynchronous via zfcp_scsi_schedule_rport_block(), has not yet blocked the rport. However, for the case when the rport becomes available again, we should prevent unblocking the rport too early. In contrast to other FCP LLDDs, zfcp has to open each LUN with the FCP channel hardware before it can send I/O to a LUN. So if a port already has LUNs attached and we unblock the rport just after port recovery, recoveries of LUNs behind this port can still be pending which in turn force zfcp_scsi_queuecommand() to unnecessarily finish requests with DID_IMM_RETRY. This also opens a time window with unblocked rport (until the followup LUN reopen recovery has finished). If a scsi_cmnd timeout occurs during this time window fc_timed_out() cannot work as desired and such command would indeed time out and trigger scsi_eh. This prevents a clean and timely path failover. This should not happen if the path issue can be recovered on FC transport layer such as path issues involving RSCNs. Fix this by only calling zfcp_scsi_schedule_rport_register(), to asynchronously trigger fc_remote_port_add(), after all LUN recoveries as children of the rport have finished and no new recoveries of equal or higher order were triggered meanwhile. Finished intentionally includes any recovery result no matter if successful or failed (still unblock rport so other successful LUNs work). For simplicity, we check after each finished LUN recovery if there is another LUN recovery pending on the same port and then do nothing. We handle the special case of a successful recovery of a port without LUN children the same way without changing this case's semantics. For debugging we introduce 2 new trace records written if the rport unblock attempt was aborted due to still unfinished or freshly triggered recovery. The records are only written above the default trace level. Benjamin noticed the important special case of new recovery that can be triggered between having given up the erp_lock and before calling zfcp_erp_action_cleanup() within zfcp_erp_strategy(). We must avoid the following sequence: ERP thread rport_work other context ------------------------- -------------- -------------------------------- port is unblocked, rport still blocked, due to pending/running ERP action, so ((port->status & ...UNBLOCK) != 0) and (port->rport == NULL) unlock ERP zfcp_erp_action_cleanup() case ZFCP_ERP_ACTION_REOPEN_LUN: zfcp_erp_try_rport_unblock() ((status & ...UNBLOCK) != 0) [OLD!] zfcp_erp_port_reopen() lock ERP zfcp_erp_port_block() port->status clear ...UNBLOCK unlock ERP zfcp_scsi_schedule_rport_block() port->rport_task = RPORT_DEL queue_work(rport_work) zfcp_scsi_rport_work() (port->rport_task != RPORT_ADD) port->rport_task = RPORT_NONE zfcp_scsi_rport_block() if (!port->rport) return zfcp_scsi_schedule_rport_register() port->rport_task = RPORT_ADD queue_work(rport_work) zfcp_scsi_rport_work() (port->rport_task == RPORT_ADD) port->rport_task = RPORT_NONE zfcp_scsi_rport_register() (port->rport == NULL) rport = fc_remote_port_add() port->rport = rport; Now the rport was erroneously unblocked while the zfcp_port is blocked. This is another situation we want to avoid due to scsi_eh potential. This state would at least remain until the new recovery from the other context finished successfully, or potentially forever if it failed. In order to close this race, we take the erp_lock inside zfcp_erp_try_rport_unblock() when checking the status of zfcp_port or LUN. With that, the possible corresponding rport state sequences would be: (unblock[ERP thread],block[other context]) if the ERP thread gets erp_lock first and still sees ((port->status & ...UNBLOCK) != 0), (block[other context],NOP[ERP thread]) if the ERP thread gets erp_lock after the other context has already cleard ...UNBLOCK from port->status. Since checking fields of struct erp_action is unsafe because they could have been overwritten (re-used for new recovery) meanwhile, we only check status of zfcp_port and LUN since these are only changed under erp_lock elsewhere. Regarding the check of the proper status flags (port or port_forced are similar to the shown adapter recovery): [zfcp_erp_adapter_shutdown()] zfcp_erp_adapter_reopen() zfcp_erp_adapter_block() * clear UNBLOCK ---------------------------------------+ zfcp_scsi_schedule_rports_block() | write_lock_irqsave(&adapter->erp_lock, flags);-------+ | zfcp_erp_action_enqueue() | | zfcp_erp_setup_act() | | * set ERP_INUSE -----------------------------------|--|--+ write_unlock_irqrestore(&adapter->erp_lock, flags);--+ | | .context-switch. | | zfcp_erp_thread() | | zfcp_erp_strategy() | | write_lock_irqsave(&adapter->erp_lock, flags);------+ | | ... | | | zfcp_erp_strategy_check_target() | | | zfcp_erp_strategy_check_adapter() | | | zfcp_erp_adapter_unblock() | | | * set UNBLOCK -----------------------------------|--+ | zfcp_erp_action_dequeue() | | * clear ERP_INUSE ---------------------------------|-----+ ... | write_unlock_irqrestore(&adapter->erp_lock, flags);-+ Hence, we should check for both UNBLOCK and ERP_INUSE because they are interleaved. Also we need to explicitly check ERP_FAILED for the link down case which currently does not clear the UNBLOCK flag in zfcp_fsf_link_down_info_eval(). Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com> Fixes: 8830271c4819 ("[SCSI] zfcp: Dont fail SCSI commands when transitioning to blocked fc_rport") Fixes: a2fa0aede07c ("[SCSI] zfcp: Block FC transport rports early on errors") Fixes: 5f852be9e11d ("[SCSI] zfcp: Fix deadlock between zfcp ERP and SCSI") Fixes: 338151e06608 ("[SCSI] zfcp: make use of fc_remote_port_delete when target port is unavailable") Fixes: 3859f6a248cb ("[PATCH] zfcp: add rports to enable scsi_add_device to work again") Cc: <stable@vger.kernel.org> #2.6.32+ Reviewed-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2016-12-10 00:16:33 +08:00
* zfcp_dbf_rec_run_lvl - trace event related to running recovery
* @level: trace level to be used for event
* @tag: identifier for event
* @erp: erp_action running
*/
scsi: zfcp: fix rport unblock race with LUN recovery It is unavoidable that zfcp_scsi_queuecommand() has to finish requests with DID_IMM_RETRY (like fc_remote_port_chkready()) during the time window when zfcp detected an unavailable rport but fc_remote_port_delete(), which is asynchronous via zfcp_scsi_schedule_rport_block(), has not yet blocked the rport. However, for the case when the rport becomes available again, we should prevent unblocking the rport too early. In contrast to other FCP LLDDs, zfcp has to open each LUN with the FCP channel hardware before it can send I/O to a LUN. So if a port already has LUNs attached and we unblock the rport just after port recovery, recoveries of LUNs behind this port can still be pending which in turn force zfcp_scsi_queuecommand() to unnecessarily finish requests with DID_IMM_RETRY. This also opens a time window with unblocked rport (until the followup LUN reopen recovery has finished). If a scsi_cmnd timeout occurs during this time window fc_timed_out() cannot work as desired and such command would indeed time out and trigger scsi_eh. This prevents a clean and timely path failover. This should not happen if the path issue can be recovered on FC transport layer such as path issues involving RSCNs. Fix this by only calling zfcp_scsi_schedule_rport_register(), to asynchronously trigger fc_remote_port_add(), after all LUN recoveries as children of the rport have finished and no new recoveries of equal or higher order were triggered meanwhile. Finished intentionally includes any recovery result no matter if successful or failed (still unblock rport so other successful LUNs work). For simplicity, we check after each finished LUN recovery if there is another LUN recovery pending on the same port and then do nothing. We handle the special case of a successful recovery of a port without LUN children the same way without changing this case's semantics. For debugging we introduce 2 new trace records written if the rport unblock attempt was aborted due to still unfinished or freshly triggered recovery. The records are only written above the default trace level. Benjamin noticed the important special case of new recovery that can be triggered between having given up the erp_lock and before calling zfcp_erp_action_cleanup() within zfcp_erp_strategy(). We must avoid the following sequence: ERP thread rport_work other context ------------------------- -------------- -------------------------------- port is unblocked, rport still blocked, due to pending/running ERP action, so ((port->status & ...UNBLOCK) != 0) and (port->rport == NULL) unlock ERP zfcp_erp_action_cleanup() case ZFCP_ERP_ACTION_REOPEN_LUN: zfcp_erp_try_rport_unblock() ((status & ...UNBLOCK) != 0) [OLD!] zfcp_erp_port_reopen() lock ERP zfcp_erp_port_block() port->status clear ...UNBLOCK unlock ERP zfcp_scsi_schedule_rport_block() port->rport_task = RPORT_DEL queue_work(rport_work) zfcp_scsi_rport_work() (port->rport_task != RPORT_ADD) port->rport_task = RPORT_NONE zfcp_scsi_rport_block() if (!port->rport) return zfcp_scsi_schedule_rport_register() port->rport_task = RPORT_ADD queue_work(rport_work) zfcp_scsi_rport_work() (port->rport_task == RPORT_ADD) port->rport_task = RPORT_NONE zfcp_scsi_rport_register() (port->rport == NULL) rport = fc_remote_port_add() port->rport = rport; Now the rport was erroneously unblocked while the zfcp_port is blocked. This is another situation we want to avoid due to scsi_eh potential. This state would at least remain until the new recovery from the other context finished successfully, or potentially forever if it failed. In order to close this race, we take the erp_lock inside zfcp_erp_try_rport_unblock() when checking the status of zfcp_port or LUN. With that, the possible corresponding rport state sequences would be: (unblock[ERP thread],block[other context]) if the ERP thread gets erp_lock first and still sees ((port->status & ...UNBLOCK) != 0), (block[other context],NOP[ERP thread]) if the ERP thread gets erp_lock after the other context has already cleard ...UNBLOCK from port->status. Since checking fields of struct erp_action is unsafe because they could have been overwritten (re-used for new recovery) meanwhile, we only check status of zfcp_port and LUN since these are only changed under erp_lock elsewhere. Regarding the check of the proper status flags (port or port_forced are similar to the shown adapter recovery): [zfcp_erp_adapter_shutdown()] zfcp_erp_adapter_reopen() zfcp_erp_adapter_block() * clear UNBLOCK ---------------------------------------+ zfcp_scsi_schedule_rports_block() | write_lock_irqsave(&adapter->erp_lock, flags);-------+ | zfcp_erp_action_enqueue() | | zfcp_erp_setup_act() | | * set ERP_INUSE -----------------------------------|--|--+ write_unlock_irqrestore(&adapter->erp_lock, flags);--+ | | .context-switch. | | zfcp_erp_thread() | | zfcp_erp_strategy() | | write_lock_irqsave(&adapter->erp_lock, flags);------+ | | ... | | | zfcp_erp_strategy_check_target() | | | zfcp_erp_strategy_check_adapter() | | | zfcp_erp_adapter_unblock() | | | * set UNBLOCK -----------------------------------|--+ | zfcp_erp_action_dequeue() | | * clear ERP_INUSE ---------------------------------|-----+ ... | write_unlock_irqrestore(&adapter->erp_lock, flags);-+ Hence, we should check for both UNBLOCK and ERP_INUSE because they are interleaved. Also we need to explicitly check ERP_FAILED for the link down case which currently does not clear the UNBLOCK flag in zfcp_fsf_link_down_info_eval(). Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com> Fixes: 8830271c4819 ("[SCSI] zfcp: Dont fail SCSI commands when transitioning to blocked fc_rport") Fixes: a2fa0aede07c ("[SCSI] zfcp: Block FC transport rports early on errors") Fixes: 5f852be9e11d ("[SCSI] zfcp: Fix deadlock between zfcp ERP and SCSI") Fixes: 338151e06608 ("[SCSI] zfcp: make use of fc_remote_port_delete when target port is unavailable") Fixes: 3859f6a248cb ("[PATCH] zfcp: add rports to enable scsi_add_device to work again") Cc: <stable@vger.kernel.org> #2.6.32+ Reviewed-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2016-12-10 00:16:33 +08:00
void zfcp_dbf_rec_run_lvl(int level, char *tag, struct zfcp_erp_action *erp)
{
struct zfcp_dbf *dbf = erp->adapter->dbf;
struct zfcp_dbf_rec *rec = &dbf->rec_buf;
unsigned long flags;
if (!debug_level_enabled(dbf->rec, level))
return;
spin_lock_irqsave(&dbf->rec_lock, flags);
memset(rec, 0, sizeof(*rec));
rec->id = ZFCP_DBF_REC_RUN;
memcpy(rec->tag, tag, ZFCP_DBF_TAG_LEN);
zfcp_dbf_set_common(rec, erp->adapter, erp->port, erp->sdev);
rec->u.run.fsf_req_id = erp->fsf_req_id;
rec->u.run.rec_status = erp->status;
rec->u.run.rec_step = erp->step;
rec->u.run.rec_action = erp->action;
if (erp->sdev)
rec->u.run.rec_count =
atomic_read(&sdev_to_zfcp(erp->sdev)->erp_counter);
else if (erp->port)
rec->u.run.rec_count = atomic_read(&erp->port->erp_counter);
else
rec->u.run.rec_count = atomic_read(&erp->adapter->erp_counter);
scsi: zfcp: fix rport unblock race with LUN recovery It is unavoidable that zfcp_scsi_queuecommand() has to finish requests with DID_IMM_RETRY (like fc_remote_port_chkready()) during the time window when zfcp detected an unavailable rport but fc_remote_port_delete(), which is asynchronous via zfcp_scsi_schedule_rport_block(), has not yet blocked the rport. However, for the case when the rport becomes available again, we should prevent unblocking the rport too early. In contrast to other FCP LLDDs, zfcp has to open each LUN with the FCP channel hardware before it can send I/O to a LUN. So if a port already has LUNs attached and we unblock the rport just after port recovery, recoveries of LUNs behind this port can still be pending which in turn force zfcp_scsi_queuecommand() to unnecessarily finish requests with DID_IMM_RETRY. This also opens a time window with unblocked rport (until the followup LUN reopen recovery has finished). If a scsi_cmnd timeout occurs during this time window fc_timed_out() cannot work as desired and such command would indeed time out and trigger scsi_eh. This prevents a clean and timely path failover. This should not happen if the path issue can be recovered on FC transport layer such as path issues involving RSCNs. Fix this by only calling zfcp_scsi_schedule_rport_register(), to asynchronously trigger fc_remote_port_add(), after all LUN recoveries as children of the rport have finished and no new recoveries of equal or higher order were triggered meanwhile. Finished intentionally includes any recovery result no matter if successful or failed (still unblock rport so other successful LUNs work). For simplicity, we check after each finished LUN recovery if there is another LUN recovery pending on the same port and then do nothing. We handle the special case of a successful recovery of a port without LUN children the same way without changing this case's semantics. For debugging we introduce 2 new trace records written if the rport unblock attempt was aborted due to still unfinished or freshly triggered recovery. The records are only written above the default trace level. Benjamin noticed the important special case of new recovery that can be triggered between having given up the erp_lock and before calling zfcp_erp_action_cleanup() within zfcp_erp_strategy(). We must avoid the following sequence: ERP thread rport_work other context ------------------------- -------------- -------------------------------- port is unblocked, rport still blocked, due to pending/running ERP action, so ((port->status & ...UNBLOCK) != 0) and (port->rport == NULL) unlock ERP zfcp_erp_action_cleanup() case ZFCP_ERP_ACTION_REOPEN_LUN: zfcp_erp_try_rport_unblock() ((status & ...UNBLOCK) != 0) [OLD!] zfcp_erp_port_reopen() lock ERP zfcp_erp_port_block() port->status clear ...UNBLOCK unlock ERP zfcp_scsi_schedule_rport_block() port->rport_task = RPORT_DEL queue_work(rport_work) zfcp_scsi_rport_work() (port->rport_task != RPORT_ADD) port->rport_task = RPORT_NONE zfcp_scsi_rport_block() if (!port->rport) return zfcp_scsi_schedule_rport_register() port->rport_task = RPORT_ADD queue_work(rport_work) zfcp_scsi_rport_work() (port->rport_task == RPORT_ADD) port->rport_task = RPORT_NONE zfcp_scsi_rport_register() (port->rport == NULL) rport = fc_remote_port_add() port->rport = rport; Now the rport was erroneously unblocked while the zfcp_port is blocked. This is another situation we want to avoid due to scsi_eh potential. This state would at least remain until the new recovery from the other context finished successfully, or potentially forever if it failed. In order to close this race, we take the erp_lock inside zfcp_erp_try_rport_unblock() when checking the status of zfcp_port or LUN. With that, the possible corresponding rport state sequences would be: (unblock[ERP thread],block[other context]) if the ERP thread gets erp_lock first and still sees ((port->status & ...UNBLOCK) != 0), (block[other context],NOP[ERP thread]) if the ERP thread gets erp_lock after the other context has already cleard ...UNBLOCK from port->status. Since checking fields of struct erp_action is unsafe because they could have been overwritten (re-used for new recovery) meanwhile, we only check status of zfcp_port and LUN since these are only changed under erp_lock elsewhere. Regarding the check of the proper status flags (port or port_forced are similar to the shown adapter recovery): [zfcp_erp_adapter_shutdown()] zfcp_erp_adapter_reopen() zfcp_erp_adapter_block() * clear UNBLOCK ---------------------------------------+ zfcp_scsi_schedule_rports_block() | write_lock_irqsave(&adapter->erp_lock, flags);-------+ | zfcp_erp_action_enqueue() | | zfcp_erp_setup_act() | | * set ERP_INUSE -----------------------------------|--|--+ write_unlock_irqrestore(&adapter->erp_lock, flags);--+ | | .context-switch. | | zfcp_erp_thread() | | zfcp_erp_strategy() | | write_lock_irqsave(&adapter->erp_lock, flags);------+ | | ... | | | zfcp_erp_strategy_check_target() | | | zfcp_erp_strategy_check_adapter() | | | zfcp_erp_adapter_unblock() | | | * set UNBLOCK -----------------------------------|--+ | zfcp_erp_action_dequeue() | | * clear ERP_INUSE ---------------------------------|-----+ ... | write_unlock_irqrestore(&adapter->erp_lock, flags);-+ Hence, we should check for both UNBLOCK and ERP_INUSE because they are interleaved. Also we need to explicitly check ERP_FAILED for the link down case which currently does not clear the UNBLOCK flag in zfcp_fsf_link_down_info_eval(). Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com> Fixes: 8830271c4819 ("[SCSI] zfcp: Dont fail SCSI commands when transitioning to blocked fc_rport") Fixes: a2fa0aede07c ("[SCSI] zfcp: Block FC transport rports early on errors") Fixes: 5f852be9e11d ("[SCSI] zfcp: Fix deadlock between zfcp ERP and SCSI") Fixes: 338151e06608 ("[SCSI] zfcp: make use of fc_remote_port_delete when target port is unavailable") Fixes: 3859f6a248cb ("[PATCH] zfcp: add rports to enable scsi_add_device to work again") Cc: <stable@vger.kernel.org> #2.6.32+ Reviewed-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2016-12-10 00:16:33 +08:00
debug_event(dbf->rec, level, rec, sizeof(*rec));
spin_unlock_irqrestore(&dbf->rec_lock, flags);
}
scsi: zfcp: fix rport unblock race with LUN recovery It is unavoidable that zfcp_scsi_queuecommand() has to finish requests with DID_IMM_RETRY (like fc_remote_port_chkready()) during the time window when zfcp detected an unavailable rport but fc_remote_port_delete(), which is asynchronous via zfcp_scsi_schedule_rport_block(), has not yet blocked the rport. However, for the case when the rport becomes available again, we should prevent unblocking the rport too early. In contrast to other FCP LLDDs, zfcp has to open each LUN with the FCP channel hardware before it can send I/O to a LUN. So if a port already has LUNs attached and we unblock the rport just after port recovery, recoveries of LUNs behind this port can still be pending which in turn force zfcp_scsi_queuecommand() to unnecessarily finish requests with DID_IMM_RETRY. This also opens a time window with unblocked rport (until the followup LUN reopen recovery has finished). If a scsi_cmnd timeout occurs during this time window fc_timed_out() cannot work as desired and such command would indeed time out and trigger scsi_eh. This prevents a clean and timely path failover. This should not happen if the path issue can be recovered on FC transport layer such as path issues involving RSCNs. Fix this by only calling zfcp_scsi_schedule_rport_register(), to asynchronously trigger fc_remote_port_add(), after all LUN recoveries as children of the rport have finished and no new recoveries of equal or higher order were triggered meanwhile. Finished intentionally includes any recovery result no matter if successful or failed (still unblock rport so other successful LUNs work). For simplicity, we check after each finished LUN recovery if there is another LUN recovery pending on the same port and then do nothing. We handle the special case of a successful recovery of a port without LUN children the same way without changing this case's semantics. For debugging we introduce 2 new trace records written if the rport unblock attempt was aborted due to still unfinished or freshly triggered recovery. The records are only written above the default trace level. Benjamin noticed the important special case of new recovery that can be triggered between having given up the erp_lock and before calling zfcp_erp_action_cleanup() within zfcp_erp_strategy(). We must avoid the following sequence: ERP thread rport_work other context ------------------------- -------------- -------------------------------- port is unblocked, rport still blocked, due to pending/running ERP action, so ((port->status & ...UNBLOCK) != 0) and (port->rport == NULL) unlock ERP zfcp_erp_action_cleanup() case ZFCP_ERP_ACTION_REOPEN_LUN: zfcp_erp_try_rport_unblock() ((status & ...UNBLOCK) != 0) [OLD!] zfcp_erp_port_reopen() lock ERP zfcp_erp_port_block() port->status clear ...UNBLOCK unlock ERP zfcp_scsi_schedule_rport_block() port->rport_task = RPORT_DEL queue_work(rport_work) zfcp_scsi_rport_work() (port->rport_task != RPORT_ADD) port->rport_task = RPORT_NONE zfcp_scsi_rport_block() if (!port->rport) return zfcp_scsi_schedule_rport_register() port->rport_task = RPORT_ADD queue_work(rport_work) zfcp_scsi_rport_work() (port->rport_task == RPORT_ADD) port->rport_task = RPORT_NONE zfcp_scsi_rport_register() (port->rport == NULL) rport = fc_remote_port_add() port->rport = rport; Now the rport was erroneously unblocked while the zfcp_port is blocked. This is another situation we want to avoid due to scsi_eh potential. This state would at least remain until the new recovery from the other context finished successfully, or potentially forever if it failed. In order to close this race, we take the erp_lock inside zfcp_erp_try_rport_unblock() when checking the status of zfcp_port or LUN. With that, the possible corresponding rport state sequences would be: (unblock[ERP thread],block[other context]) if the ERP thread gets erp_lock first and still sees ((port->status & ...UNBLOCK) != 0), (block[other context],NOP[ERP thread]) if the ERP thread gets erp_lock after the other context has already cleard ...UNBLOCK from port->status. Since checking fields of struct erp_action is unsafe because they could have been overwritten (re-used for new recovery) meanwhile, we only check status of zfcp_port and LUN since these are only changed under erp_lock elsewhere. Regarding the check of the proper status flags (port or port_forced are similar to the shown adapter recovery): [zfcp_erp_adapter_shutdown()] zfcp_erp_adapter_reopen() zfcp_erp_adapter_block() * clear UNBLOCK ---------------------------------------+ zfcp_scsi_schedule_rports_block() | write_lock_irqsave(&adapter->erp_lock, flags);-------+ | zfcp_erp_action_enqueue() | | zfcp_erp_setup_act() | | * set ERP_INUSE -----------------------------------|--|--+ write_unlock_irqrestore(&adapter->erp_lock, flags);--+ | | .context-switch. | | zfcp_erp_thread() | | zfcp_erp_strategy() | | write_lock_irqsave(&adapter->erp_lock, flags);------+ | | ... | | | zfcp_erp_strategy_check_target() | | | zfcp_erp_strategy_check_adapter() | | | zfcp_erp_adapter_unblock() | | | * set UNBLOCK -----------------------------------|--+ | zfcp_erp_action_dequeue() | | * clear ERP_INUSE ---------------------------------|-----+ ... | write_unlock_irqrestore(&adapter->erp_lock, flags);-+ Hence, we should check for both UNBLOCK and ERP_INUSE because they are interleaved. Also we need to explicitly check ERP_FAILED for the link down case which currently does not clear the UNBLOCK flag in zfcp_fsf_link_down_info_eval(). Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com> Fixes: 8830271c4819 ("[SCSI] zfcp: Dont fail SCSI commands when transitioning to blocked fc_rport") Fixes: a2fa0aede07c ("[SCSI] zfcp: Block FC transport rports early on errors") Fixes: 5f852be9e11d ("[SCSI] zfcp: Fix deadlock between zfcp ERP and SCSI") Fixes: 338151e06608 ("[SCSI] zfcp: make use of fc_remote_port_delete when target port is unavailable") Fixes: 3859f6a248cb ("[PATCH] zfcp: add rports to enable scsi_add_device to work again") Cc: <stable@vger.kernel.org> #2.6.32+ Reviewed-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2016-12-10 00:16:33 +08:00
/**
* zfcp_dbf_rec_run - trace event related to running recovery
* @tag: identifier for event
* @erp: erp_action running
*/
void zfcp_dbf_rec_run(char *tag, struct zfcp_erp_action *erp)
{
zfcp_dbf_rec_run_lvl(1, tag, erp);
}
/**
* zfcp_dbf_rec_run_wka - trace wka port event with info like running recovery
* @tag: identifier for event
* @wka_port: well known address port
* @req_id: request ID to correlate with potential HBA trace record
*/
void zfcp_dbf_rec_run_wka(char *tag, struct zfcp_fc_wka_port *wka_port,
u64 req_id)
{
struct zfcp_dbf *dbf = wka_port->adapter->dbf;
struct zfcp_dbf_rec *rec = &dbf->rec_buf;
static int const level = 1;
unsigned long flags;
if (unlikely(!debug_level_enabled(dbf->rec, level)))
return;
spin_lock_irqsave(&dbf->rec_lock, flags);
memset(rec, 0, sizeof(*rec));
rec->id = ZFCP_DBF_REC_RUN;
memcpy(rec->tag, tag, ZFCP_DBF_TAG_LEN);
rec->port_status = wka_port->status;
rec->d_id = wka_port->d_id;
rec->lun = ZFCP_DBF_INVALID_LUN;
rec->u.run.fsf_req_id = req_id;
rec->u.run.rec_status = ~0;
rec->u.run.rec_step = ~0;
rec->u.run.rec_action = ~0;
rec->u.run.rec_count = ~0;
debug_event(dbf->rec, level, rec, sizeof(*rec));
spin_unlock_irqrestore(&dbf->rec_lock, flags);
}
#define ZFCP_DBF_SAN_LEVEL 1
static inline
void zfcp_dbf_san(char *tag, struct zfcp_dbf *dbf,
char *paytag, struct scatterlist *sg, u8 id, u16 len,
u64 req_id, u32 d_id, u16 cap_len)
{
struct zfcp_dbf_san *rec = &dbf->san_buf;
u16 rec_len;
unsigned long flags;
struct zfcp_dbf_pay *payload = &dbf->pay_buf;
u16 pay_sum = 0;
spin_lock_irqsave(&dbf->san_lock, flags);
memset(rec, 0, sizeof(*rec));
rec->id = id;
rec->fsf_req_id = req_id;
rec->d_id = d_id;
memcpy(rec->tag, tag, ZFCP_DBF_TAG_LEN);
rec->pl_len = len; /* full length even if we cap pay below */
if (!sg)
goto out;
rec_len = min_t(unsigned int, sg->length, ZFCP_DBF_SAN_MAX_PAYLOAD);
memcpy(rec->payload, sg_virt(sg), rec_len); /* part of 1st sg entry */
if (len <= rec_len)
goto out; /* skip pay record if full content in rec->payload */
/* if (len > rec_len):
* dump data up to cap_len ignoring small duplicate in rec->payload
*/
spin_lock(&dbf->pay_lock);
memset(payload, 0, sizeof(*payload));
memcpy(payload->area, paytag, ZFCP_DBF_TAG_LEN);
payload->fsf_req_id = req_id;
payload->counter = 0;
for (; sg && pay_sum < cap_len; sg = sg_next(sg)) {
u16 pay_len, offset = 0;
while (offset < sg->length && pay_sum < cap_len) {
pay_len = min((u16)ZFCP_DBF_PAY_MAX_REC,
(u16)(sg->length - offset));
/* cap_len <= pay_sum < cap_len+ZFCP_DBF_PAY_MAX_REC */
memcpy(payload->data, sg_virt(sg) + offset, pay_len);
debug_event(dbf->pay, ZFCP_DBF_SAN_LEVEL, payload,
zfcp_dbf_plen(pay_len));
payload->counter++;
offset += pay_len;
pay_sum += pay_len;
}
}
spin_unlock(&dbf->pay_lock);
out:
debug_event(dbf->san, ZFCP_DBF_SAN_LEVEL, rec, sizeof(*rec));
spin_unlock_irqrestore(&dbf->san_lock, flags);
}
/**
* zfcp_dbf_san_req - trace event for issued SAN request
* @tag: identifier for event
* @fsf_req: request containing issued CT data
* d_id: destination ID
*/
void zfcp_dbf_san_req(char *tag, struct zfcp_fsf_req *fsf, u32 d_id)
{
struct zfcp_dbf *dbf = fsf->adapter->dbf;
struct zfcp_fsf_ct_els *ct_els = fsf->data;
u16 length;
if (unlikely(!debug_level_enabled(dbf->san, ZFCP_DBF_SAN_LEVEL)))
return;
length = (u16)zfcp_qdio_real_bytes(ct_els->req);
zfcp_dbf_san(tag, dbf, "san_req", ct_els->req, ZFCP_DBF_SAN_REQ,
length, fsf->req_id, d_id, length);
}
static u16 zfcp_dbf_san_res_cap_len_if_gpn_ft(char *tag,
struct zfcp_fsf_req *fsf,
u16 len)
{
struct zfcp_fsf_ct_els *ct_els = fsf->data;
struct fc_ct_hdr *reqh = sg_virt(ct_els->req);
struct fc_ns_gid_ft *reqn = (struct fc_ns_gid_ft *)(reqh + 1);
struct scatterlist *resp_entry = ct_els->resp;
scsi: zfcp: fix capping of unsuccessful GPN_FT SAN response trace records v4.9 commit aceeffbb59bb ("zfcp: trace full payload of all SAN records (req,resp,iels)") fixed trace data loss of 2.6.38 commit 2c55b750a884 ("[SCSI] zfcp: Redesign of the debug tracing for SAN records.") necessary for problem determination, e.g. to see the currently active zone set during automatic port scan. While it already saves space by not dumping any empty residual entries of the large successful GPN_FT response (4 pages), there are seldom cases where the GPN_FT response is unsuccessful and likely does not have FC_NS_FID_LAST set in fp_flags so we did not cap the trace record. We typically see such case for an initiator WWPN, which is not in any zone. Cap unsuccessful responses to at least the actual basic CT_IU response plus whatever fits the SAN trace record built-in "payload" buffer just in case there's trailing information of which we would at least see the existence and its beginning. In order not to erroneously cap successful responses, we need to swap calling the trace function and setting the CT / ELS status to success (0). Example trace record pair formatted with zfcpdbf: Timestamp : ... Area : SAN Subarea : 00 Level : 1 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : fssct_1 Request ID : 0x<request_id> Destination ID : 0x00fffffc SAN req short : 01000000 fc020000 01720ffc 00000000 00000008 SAN req length : 20 | Timestamp : ... Area : SAN Subarea : 00 Level : 1 Exception : - CPU ID : .. Caller : 0x... Record ID : 2 Tag : fsscth2 Request ID : 0x<request_id> Destination ID : 0x00fffffc SAN resp short : 01000000 fc020000 80010000 00090700 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] SAN resp length: 16384 San resp info : 01000000 fc020000 80010000 00090700 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] The fix saves all but one of the previously associated 64 PAYload trace record chunks of size 256 bytes each. Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com> Fixes: aceeffbb59bb ("zfcp: trace full payload of all SAN records (req,resp,iels)") Fixes: 2c55b750a884 ("[SCSI] zfcp: Redesign of the debug tracing for SAN records.") Cc: <stable@vger.kernel.org> #2.6.38+ Reviewed-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-07-28 18:30:53 +08:00
struct fc_ct_hdr *resph;
struct fc_gpn_ft_resp *acc;
int max_entries, x, last = 0;
if (!(memcmp(tag, "fsscth2", 7) == 0
&& ct_els->d_id == FC_FID_DIR_SERV
&& reqh->ct_rev == FC_CT_REV
&& reqh->ct_in_id[0] == 0
&& reqh->ct_in_id[1] == 0
&& reqh->ct_in_id[2] == 0
&& reqh->ct_fs_type == FC_FST_DIR
&& reqh->ct_fs_subtype == FC_NS_SUBTYPE
&& reqh->ct_options == 0
&& reqh->_ct_resvd1 == 0
scsi: zfcp: use endianness conversions with common FC(P) struct fields Just to silence sparse. Since zfcp only exists for s390 and s390 is big endian, this has been working correctly without conversions and all the new conversions are NOPs so no performance impact. Nonetheless, use the conversion on the constant expression where possible. NB: N_Port-IDs have always been handled with hton24 or ntoh24 conversions because they also convert to / from character array. Affected common code structs and .fields are: HOT I/O PATH: fcp_cmnd .fc_dl FCP command: regular SCSI I/O, including DIX case SEMI-HOT I/O PATH: fcp_cmnd .fc_dl recovery FCP command: task management function (LUN / target reset) fcp_resp_ext FCP response having FCP_SNS_LEN_VAL with .fr_rsp_len .fr_sns_len FCP response having FCP_RESID_UNDER with .fr_resid RECOVERY / DISCOVERY PATHS: fc_ct_hdr .ct_cmd .ct_mr_size zfcp auto port scan [GPN_FT] with fc_gpn_ft_resp.fp_wwpn, recovery for returned port [GID_PN] with fc_ns_gid_pn.fn_wwpn, get symbolic port name [GSPN], register symbolic port name [RSPN] (NPIV only). fc_els_rscn .rscn_plen incoming ELS (RSCN). fc_els_flogi .fl_wwpn .fl_wwnn incoming ELS (PLOGI), port open response with .fl_csp.sp_bb_data .fl_cssp[0..3].cp_class, FCP channel physical port, point-to-point peer (P2P only). fc_els_logo .fl_n_port_wwn incoming ELS (LOGO). fc_els_adisc .adisc_wwnn .adisc_wwpn path test after RSCN for gone target port. Since v4.10 commit 05de97003c77 ("linux/types.h: enable endian checks for all sparse builds"), below sparse endianness reports appear by default. Previously, one needed to pass argument CF="-D__CHECK_ENDIAN__" to make as in: $ make C=1 CF="-D__CHECK_ENDIAN__" M=drivers/s390/scsi. Silenced sparse warnings and one error: $ make C=1 M=drivers/s390/scsi ... CHECK drivers/s390/scsi/zfcp_dbf.c drivers/s390/scsi/zfcp_dbf.c:463:22: warning: restricted __be16 degrades to integer drivers/s390/scsi/zfcp_dbf.c:476:28: warning: restricted __be16 degrades to integer CC drivers/s390/scsi/zfcp_dbf.o ... CHECK drivers/s390/scsi/zfcp_fc.c drivers/s390/scsi/zfcp_fc.c:263:26: warning: restricted __be16 degrades to integer drivers/s390/scsi/zfcp_fc.c:299:41: warning: incorrect type in argument 2 (different base types) drivers/s390/scsi/zfcp_fc.c:299:41: expected unsigned long long [unsigned] [usertype] wwpn drivers/s390/scsi/zfcp_fc.c:299:41: got restricted __be64 [usertype] fl_wwpn drivers/s390/scsi/zfcp_fc.c:309:40: warning: incorrect type in argument 2 (different base types) drivers/s390/scsi/zfcp_fc.c:309:40: expected unsigned long long [unsigned] [usertype] wwpn drivers/s390/scsi/zfcp_fc.c:309:40: got restricted __be64 [usertype] fl_n_port_wwn drivers/s390/scsi/zfcp_fc.c:338:31: warning: restricted __be16 degrades to integer drivers/s390/scsi/zfcp_fc.c:355:24: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fc.c:355:24: expected restricted __be16 [usertype] ct_cmd drivers/s390/scsi/zfcp_fc.c:355:24: got unsigned short [unsigned] [usertype] cmd drivers/s390/scsi/zfcp_fc.c:356:28: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fc.c:356:28: expected restricted __be16 [usertype] ct_mr_size drivers/s390/scsi/zfcp_fc.c:356:28: got int drivers/s390/scsi/zfcp_fc.c:379:36: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fc.c:379:36: expected restricted __be64 [usertype] fn_wwpn drivers/s390/scsi/zfcp_fc.c:379:36: got unsigned long long [unsigned] [usertype] wwpn drivers/s390/scsi/zfcp_fc.c:463:18: warning: restricted __be64 degrades to integer drivers/s390/scsi/zfcp_fc.c:465:17: warning: cast from restricted __be64 drivers/s390/scsi/zfcp_fc.c:473:20: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fc.c:473:20: expected unsigned long long [unsigned] [usertype] wwnn drivers/s390/scsi/zfcp_fc.c:473:20: got restricted __be64 [usertype] fl_wwnn drivers/s390/scsi/zfcp_fc.c:474:29: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fc.c:474:29: expected unsigned int [unsigned] [usertype] maxframe_size drivers/s390/scsi/zfcp_fc.c:474:29: got restricted __be16 [usertype] sp_bb_data drivers/s390/scsi/zfcp_fc.c:476:30: warning: restricted __be16 degrades to integer drivers/s390/scsi/zfcp_fc.c:478:30: warning: restricted __be16 degrades to integer drivers/s390/scsi/zfcp_fc.c:480:30: warning: restricted __be16 degrades to integer drivers/s390/scsi/zfcp_fc.c:482:30: warning: restricted __be16 degrades to integer drivers/s390/scsi/zfcp_fc.c:500:28: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fc.c:500:28: expected unsigned long long [unsigned] [usertype] wwnn drivers/s390/scsi/zfcp_fc.c:500:28: got restricted __be64 [usertype] adisc_wwnn drivers/s390/scsi/zfcp_fc.c:502:38: warning: restricted __be64 degrades to integer drivers/s390/scsi/zfcp_fc.c:541:40: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fc.c:541:40: expected restricted __be64 [usertype] adisc_wwpn drivers/s390/scsi/zfcp_fc.c:541:40: got unsigned long long [unsigned] [usertype] port_name drivers/s390/scsi/zfcp_fc.c:542:40: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fc.c:542:40: expected restricted __be64 [usertype] adisc_wwnn drivers/s390/scsi/zfcp_fc.c:542:40: got unsigned long long [unsigned] [usertype] node_name drivers/s390/scsi/zfcp_fc.c:669:16: warning: restricted __be16 degrades to integer drivers/s390/scsi/zfcp_fc.c:696:24: warning: restricted __be64 degrades to integer drivers/s390/scsi/zfcp_fc.c:699:54: warning: incorrect type in argument 2 (different base types) drivers/s390/scsi/zfcp_fc.c:699:54: expected unsigned long long [unsigned] [usertype] <noident> drivers/s390/scsi/zfcp_fc.c:699:54: got restricted __be64 [usertype] fp_wwpn CC drivers/s390/scsi/zfcp_fc.o CHECK drivers/s390/scsi/zfcp_fsf.c drivers/s390/scsi/zfcp_fsf.c:479:34: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fsf.c:479:34: expected unsigned long long [unsigned] [usertype] port_name drivers/s390/scsi/zfcp_fsf.c:479:34: got restricted __be64 [usertype] fl_wwpn drivers/s390/scsi/zfcp_fsf.c:480:34: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fsf.c:480:34: expected unsigned long long [unsigned] [usertype] node_name drivers/s390/scsi/zfcp_fsf.c:480:34: got restricted __be64 [usertype] fl_wwnn drivers/s390/scsi/zfcp_fsf.c:506:36: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fsf.c:506:36: expected unsigned long long [unsigned] [usertype] peer_wwpn drivers/s390/scsi/zfcp_fsf.c:506:36: got restricted __be64 [usertype] fl_wwpn drivers/s390/scsi/zfcp_fsf.c:507:36: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fsf.c:507:36: expected unsigned long long [unsigned] [usertype] peer_wwnn drivers/s390/scsi/zfcp_fsf.c:507:36: got restricted __be64 [usertype] fl_wwnn drivers/s390/scsi/zfcp_fc.h:269:46: warning: restricted __be32 degrades to integer drivers/s390/scsi/zfcp_fc.h:270:29: error: incompatible types in comparison expression (different base types) Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com> Reviewed-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-07-28 18:31:02 +08:00
&& reqh->ct_cmd == cpu_to_be16(FC_NS_GPN_FT)
/* reqh->ct_mr_size can vary so do not match but read below */
&& reqh->_ct_resvd2 == 0
&& reqh->ct_reason == 0
&& reqh->ct_explan == 0
&& reqh->ct_vendor == 0
&& reqn->fn_resvd == 0
&& reqn->fn_domain_id_scope == 0
&& reqn->fn_area_id_scope == 0
&& reqn->fn_fc4_type == FC_TYPE_FCP))
return len; /* not GPN_FT response so do not cap */
acc = sg_virt(resp_entry);
scsi: zfcp: fix capping of unsuccessful GPN_FT SAN response trace records v4.9 commit aceeffbb59bb ("zfcp: trace full payload of all SAN records (req,resp,iels)") fixed trace data loss of 2.6.38 commit 2c55b750a884 ("[SCSI] zfcp: Redesign of the debug tracing for SAN records.") necessary for problem determination, e.g. to see the currently active zone set during automatic port scan. While it already saves space by not dumping any empty residual entries of the large successful GPN_FT response (4 pages), there are seldom cases where the GPN_FT response is unsuccessful and likely does not have FC_NS_FID_LAST set in fp_flags so we did not cap the trace record. We typically see such case for an initiator WWPN, which is not in any zone. Cap unsuccessful responses to at least the actual basic CT_IU response plus whatever fits the SAN trace record built-in "payload" buffer just in case there's trailing information of which we would at least see the existence and its beginning. In order not to erroneously cap successful responses, we need to swap calling the trace function and setting the CT / ELS status to success (0). Example trace record pair formatted with zfcpdbf: Timestamp : ... Area : SAN Subarea : 00 Level : 1 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : fssct_1 Request ID : 0x<request_id> Destination ID : 0x00fffffc SAN req short : 01000000 fc020000 01720ffc 00000000 00000008 SAN req length : 20 | Timestamp : ... Area : SAN Subarea : 00 Level : 1 Exception : - CPU ID : .. Caller : 0x... Record ID : 2 Tag : fsscth2 Request ID : 0x<request_id> Destination ID : 0x00fffffc SAN resp short : 01000000 fc020000 80010000 00090700 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] SAN resp length: 16384 San resp info : 01000000 fc020000 80010000 00090700 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] 00000000 00000000 00000000 00000000 [trailing info] The fix saves all but one of the previously associated 64 PAYload trace record chunks of size 256 bytes each. Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com> Fixes: aceeffbb59bb ("zfcp: trace full payload of all SAN records (req,resp,iels)") Fixes: 2c55b750a884 ("[SCSI] zfcp: Redesign of the debug tracing for SAN records.") Cc: <stable@vger.kernel.org> #2.6.38+ Reviewed-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-07-28 18:30:53 +08:00
/* cap all but accept CT responses to at least the CT header */
resph = (struct fc_ct_hdr *)acc;
if ((ct_els->status) ||
(resph->ct_cmd != cpu_to_be16(FC_FS_ACC)))
return max(FC_CT_HDR_LEN, ZFCP_DBF_SAN_MAX_PAYLOAD);
scsi: zfcp: use endianness conversions with common FC(P) struct fields Just to silence sparse. Since zfcp only exists for s390 and s390 is big endian, this has been working correctly without conversions and all the new conversions are NOPs so no performance impact. Nonetheless, use the conversion on the constant expression where possible. NB: N_Port-IDs have always been handled with hton24 or ntoh24 conversions because they also convert to / from character array. Affected common code structs and .fields are: HOT I/O PATH: fcp_cmnd .fc_dl FCP command: regular SCSI I/O, including DIX case SEMI-HOT I/O PATH: fcp_cmnd .fc_dl recovery FCP command: task management function (LUN / target reset) fcp_resp_ext FCP response having FCP_SNS_LEN_VAL with .fr_rsp_len .fr_sns_len FCP response having FCP_RESID_UNDER with .fr_resid RECOVERY / DISCOVERY PATHS: fc_ct_hdr .ct_cmd .ct_mr_size zfcp auto port scan [GPN_FT] with fc_gpn_ft_resp.fp_wwpn, recovery for returned port [GID_PN] with fc_ns_gid_pn.fn_wwpn, get symbolic port name [GSPN], register symbolic port name [RSPN] (NPIV only). fc_els_rscn .rscn_plen incoming ELS (RSCN). fc_els_flogi .fl_wwpn .fl_wwnn incoming ELS (PLOGI), port open response with .fl_csp.sp_bb_data .fl_cssp[0..3].cp_class, FCP channel physical port, point-to-point peer (P2P only). fc_els_logo .fl_n_port_wwn incoming ELS (LOGO). fc_els_adisc .adisc_wwnn .adisc_wwpn path test after RSCN for gone target port. Since v4.10 commit 05de97003c77 ("linux/types.h: enable endian checks for all sparse builds"), below sparse endianness reports appear by default. Previously, one needed to pass argument CF="-D__CHECK_ENDIAN__" to make as in: $ make C=1 CF="-D__CHECK_ENDIAN__" M=drivers/s390/scsi. Silenced sparse warnings and one error: $ make C=1 M=drivers/s390/scsi ... CHECK drivers/s390/scsi/zfcp_dbf.c drivers/s390/scsi/zfcp_dbf.c:463:22: warning: restricted __be16 degrades to integer drivers/s390/scsi/zfcp_dbf.c:476:28: warning: restricted __be16 degrades to integer CC drivers/s390/scsi/zfcp_dbf.o ... CHECK drivers/s390/scsi/zfcp_fc.c drivers/s390/scsi/zfcp_fc.c:263:26: warning: restricted __be16 degrades to integer drivers/s390/scsi/zfcp_fc.c:299:41: warning: incorrect type in argument 2 (different base types) drivers/s390/scsi/zfcp_fc.c:299:41: expected unsigned long long [unsigned] [usertype] wwpn drivers/s390/scsi/zfcp_fc.c:299:41: got restricted __be64 [usertype] fl_wwpn drivers/s390/scsi/zfcp_fc.c:309:40: warning: incorrect type in argument 2 (different base types) drivers/s390/scsi/zfcp_fc.c:309:40: expected unsigned long long [unsigned] [usertype] wwpn drivers/s390/scsi/zfcp_fc.c:309:40: got restricted __be64 [usertype] fl_n_port_wwn drivers/s390/scsi/zfcp_fc.c:338:31: warning: restricted __be16 degrades to integer drivers/s390/scsi/zfcp_fc.c:355:24: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fc.c:355:24: expected restricted __be16 [usertype] ct_cmd drivers/s390/scsi/zfcp_fc.c:355:24: got unsigned short [unsigned] [usertype] cmd drivers/s390/scsi/zfcp_fc.c:356:28: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fc.c:356:28: expected restricted __be16 [usertype] ct_mr_size drivers/s390/scsi/zfcp_fc.c:356:28: got int drivers/s390/scsi/zfcp_fc.c:379:36: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fc.c:379:36: expected restricted __be64 [usertype] fn_wwpn drivers/s390/scsi/zfcp_fc.c:379:36: got unsigned long long [unsigned] [usertype] wwpn drivers/s390/scsi/zfcp_fc.c:463:18: warning: restricted __be64 degrades to integer drivers/s390/scsi/zfcp_fc.c:465:17: warning: cast from restricted __be64 drivers/s390/scsi/zfcp_fc.c:473:20: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fc.c:473:20: expected unsigned long long [unsigned] [usertype] wwnn drivers/s390/scsi/zfcp_fc.c:473:20: got restricted __be64 [usertype] fl_wwnn drivers/s390/scsi/zfcp_fc.c:474:29: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fc.c:474:29: expected unsigned int [unsigned] [usertype] maxframe_size drivers/s390/scsi/zfcp_fc.c:474:29: got restricted __be16 [usertype] sp_bb_data drivers/s390/scsi/zfcp_fc.c:476:30: warning: restricted __be16 degrades to integer drivers/s390/scsi/zfcp_fc.c:478:30: warning: restricted __be16 degrades to integer drivers/s390/scsi/zfcp_fc.c:480:30: warning: restricted __be16 degrades to integer drivers/s390/scsi/zfcp_fc.c:482:30: warning: restricted __be16 degrades to integer drivers/s390/scsi/zfcp_fc.c:500:28: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fc.c:500:28: expected unsigned long long [unsigned] [usertype] wwnn drivers/s390/scsi/zfcp_fc.c:500:28: got restricted __be64 [usertype] adisc_wwnn drivers/s390/scsi/zfcp_fc.c:502:38: warning: restricted __be64 degrades to integer drivers/s390/scsi/zfcp_fc.c:541:40: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fc.c:541:40: expected restricted __be64 [usertype] adisc_wwpn drivers/s390/scsi/zfcp_fc.c:541:40: got unsigned long long [unsigned] [usertype] port_name drivers/s390/scsi/zfcp_fc.c:542:40: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fc.c:542:40: expected restricted __be64 [usertype] adisc_wwnn drivers/s390/scsi/zfcp_fc.c:542:40: got unsigned long long [unsigned] [usertype] node_name drivers/s390/scsi/zfcp_fc.c:669:16: warning: restricted __be16 degrades to integer drivers/s390/scsi/zfcp_fc.c:696:24: warning: restricted __be64 degrades to integer drivers/s390/scsi/zfcp_fc.c:699:54: warning: incorrect type in argument 2 (different base types) drivers/s390/scsi/zfcp_fc.c:699:54: expected unsigned long long [unsigned] [usertype] <noident> drivers/s390/scsi/zfcp_fc.c:699:54: got restricted __be64 [usertype] fp_wwpn CC drivers/s390/scsi/zfcp_fc.o CHECK drivers/s390/scsi/zfcp_fsf.c drivers/s390/scsi/zfcp_fsf.c:479:34: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fsf.c:479:34: expected unsigned long long [unsigned] [usertype] port_name drivers/s390/scsi/zfcp_fsf.c:479:34: got restricted __be64 [usertype] fl_wwpn drivers/s390/scsi/zfcp_fsf.c:480:34: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fsf.c:480:34: expected unsigned long long [unsigned] [usertype] node_name drivers/s390/scsi/zfcp_fsf.c:480:34: got restricted __be64 [usertype] fl_wwnn drivers/s390/scsi/zfcp_fsf.c:506:36: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fsf.c:506:36: expected unsigned long long [unsigned] [usertype] peer_wwpn drivers/s390/scsi/zfcp_fsf.c:506:36: got restricted __be64 [usertype] fl_wwpn drivers/s390/scsi/zfcp_fsf.c:507:36: warning: incorrect type in assignment (different base types) drivers/s390/scsi/zfcp_fsf.c:507:36: expected unsigned long long [unsigned] [usertype] peer_wwnn drivers/s390/scsi/zfcp_fsf.c:507:36: got restricted __be64 [usertype] fl_wwnn drivers/s390/scsi/zfcp_fc.h:269:46: warning: restricted __be32 degrades to integer drivers/s390/scsi/zfcp_fc.h:270:29: error: incompatible types in comparison expression (different base types) Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com> Reviewed-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-07-28 18:31:02 +08:00
max_entries = (be16_to_cpu(reqh->ct_mr_size) * 4 /
sizeof(struct fc_gpn_ft_resp))
+ 1 /* zfcp_fc_scan_ports: bytes correct, entries off-by-one
* to account for header as 1st pseudo "entry" */;
/* the basic CT_IU preamble is the same size as one entry in the GPN_FT
* response, allowing us to skip special handling for it - just skip it
*/
for (x = 1; x < max_entries && !last; x++) {
if (x % (ZFCP_FC_GPN_FT_ENT_PAGE + 1))
acc++;
else
acc = sg_virt(++resp_entry);
last = acc->fp_flags & FC_NS_FID_LAST;
}
len = min(len, (u16)(x * sizeof(struct fc_gpn_ft_resp)));
return len; /* cap after last entry */
}
/**
* zfcp_dbf_san_res - trace event for received SAN request
* @tag: identifier for event
* @fsf_req: request containing issued CT data
*/
void zfcp_dbf_san_res(char *tag, struct zfcp_fsf_req *fsf)
{
struct zfcp_dbf *dbf = fsf->adapter->dbf;
struct zfcp_fsf_ct_els *ct_els = fsf->data;
u16 length;
if (unlikely(!debug_level_enabled(dbf->san, ZFCP_DBF_SAN_LEVEL)))
return;
length = (u16)zfcp_qdio_real_bytes(ct_els->resp);
zfcp_dbf_san(tag, dbf, "san_res", ct_els->resp, ZFCP_DBF_SAN_RES,
length, fsf->req_id, ct_els->d_id,
zfcp_dbf_san_res_cap_len_if_gpn_ft(tag, fsf, length));
}
/**
* zfcp_dbf_san_in_els - trace event for incoming ELS
* @tag: identifier for event
* @fsf_req: request containing issued CT data
*/
void zfcp_dbf_san_in_els(char *tag, struct zfcp_fsf_req *fsf)
{
struct zfcp_dbf *dbf = fsf->adapter->dbf;
struct fsf_status_read_buffer *srb =
(struct fsf_status_read_buffer *) fsf->data;
u16 length;
struct scatterlist sg;
if (unlikely(!debug_level_enabled(dbf->san, ZFCP_DBF_SAN_LEVEL)))
return;
length = (u16)(srb->length -
offsetof(struct fsf_status_read_buffer, payload));
sg_init_one(&sg, srb->payload.data, length);
zfcp_dbf_san(tag, dbf, "san_els", &sg, ZFCP_DBF_SAN_ELS, length,
fsf->req_id, ntoh24(srb->d_id), length);
}
/**
* zfcp_dbf_scsi - trace event for scsi commands
* @tag: identifier for event
* @sc: pointer to struct scsi_cmnd
* @fsf: pointer to struct zfcp_fsf_req
*/
void zfcp_dbf_scsi(char *tag, int level, struct scsi_cmnd *sc,
struct zfcp_fsf_req *fsf)
{
struct zfcp_adapter *adapter =
(struct zfcp_adapter *) sc->device->host->hostdata[0];
struct zfcp_dbf *dbf = adapter->dbf;
struct zfcp_dbf_scsi *rec = &dbf->scsi_buf;
struct fcp_resp_with_ext *fcp_rsp;
struct fcp_resp_rsp_info *fcp_rsp_info;
unsigned long flags;
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 = sc->result;
rec->scsi_retries = sc->retries;
rec->scsi_allowed = sc->allowed;
rec->scsi_id = sc->device->id;
rec->scsi_lun = (u32)sc->device->lun;
scsi: zfcp: trace high part of "new" 64 bit SCSI LUN Complements debugging aspects of the otherwise functionally complete v3.17 commit 9cb78c16f5da ("scsi: use 64-bit LUNs"). While I don't have access to a target exporting 3 or 4 level LUNs, I did test it by explicitly attaching a non-existent fake 4 level LUN by means of zfcp sysfs attribute "unit_add". In order to see corresponding trace records of otherwise successful events, we had to increase the trace level of area SCSI and HBA to 6. $ echo 6 > /sys/kernel/debug/s390dbf/zfcp_0.0.1880_scsi/level $ echo 6 > /sys/kernel/debug/s390dbf/zfcp_0.0.1880_hba/level $ echo 0x4011402240334044 > \ /sys/bus/ccw/drivers/zfcp/0.0.1880/0x50050763031bd327/unit_add Example output formatted by an updated zfcpdbf from the s390-tools package interspersed with kernel messages at scsi_logging_level=4605: Timestamp : ... Area : REC Subarea : 00 Level : 1 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : scsla_1 LUN : 0x4011402240334044 WWPN : 0x50050763031bd327 D_ID : 0x00...... Adapter status : 0x5400050b Port status : 0x54000001 LUN status : 0x41000000 Ready count : 0x00000001 Running count : 0x00000000 ERP want : 0x01 ERP need : 0x01 scsi 2:0:0:4630896905707208721: scsi scan: INQUIRY pass 1 length 36 scsi 2:0:0:4630896905707208721: scsi scan: INQUIRY successful with code 0x0 Timestamp : ... Area : HBA Subarea : 00 Level : 6 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : fs_norm Request ID : 0x<inquiry2-req-id> Request status : 0x00000010 FSF cmnd : 0x00000001 FSF sequence no: 0x... FSF issued : ... FSF stat : 0x00000000 FSF stat qual : 00000000 00000000 00000000 00000000 Prot stat : 0x00000001 Prot stat qual : ........ ........ 00000000 00000000 Port handle : 0x... LUN handle : 0x... | Timestamp : ... Area : SCSI Subarea : 00 Level : 6 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : rsl_nor Request ID : 0x<inquiry2-req-id> SCSI ID : 0x00000000 SCSI LUN : 0x40224011 SCSI LUN high : 0x40444033 <======================= SCSI result : 0x00000000 SCSI retries : 0x00 SCSI allowed : 0x03 SCSI scribble : 0x<inquiry2-req-id> SCSI opcode : 12000000 a4000000 00000000 00000000 FCP rsp inf cod: 0x00 FCP rsp IU : 00000000 00000000 00000000 00000000 00000000 00000000 scsi 2:0:0:4630896905707208721: scsi scan: INQUIRY pass 2 length 164 scsi 2:0:0:4630896905707208721: scsi scan: INQUIRY successful with code 0x0 scsi 2:0:0:4630896905707208721: scsi scan: peripheral device type of 31, \ no device added Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com> Fixes: 9cb78c16f5da ("scsi: use 64-bit LUNs") Cc: <stable@vger.kernel.org> #3.17+ Reviewed-by: Benjamin Block <bblock@linux.vnet.ibm.com> Reviewed-by: Jens Remus <jremus@linux.vnet.ibm.com> Signed-off-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-07-28 18:30:58 +08:00
rec->scsi_lun_64_hi = (u32)(sc->device->lun >> 32);
rec->host_scribble = (unsigned long)sc->host_scribble;
memcpy(rec->scsi_opcode, sc->cmnd,
min((int)sc->cmd_len, ZFCP_DBF_SCSI_OPCODE));
if (fsf) {
rec->fsf_req_id = fsf->req_id;
scsi: zfcp: fix payload with full FCP_RSP IU in SCSI trace records If the FCP_RSP UI has optional parts (FCP_SNS_INFO or FCP_RSP_INFO) and thus does not fit into the fsp_rsp field built into a SCSI trace record, trace the full FCP_RSP UI with all optional parts as payload record instead of just FCP_SNS_INFO as payload and a 1 byte RSP_INFO_CODE part of FCP_RSP_INFO built into the SCSI record. That way we would also get the full FCP_SNS_INFO in case a target would ever send more than min(SCSI_SENSE_BUFFERSIZE==96, ZFCP_DBF_PAY_MAX_REC==256)==96. The mandatory part of FCP_RSP IU is only 24 bytes. PAYload costs at least one full PAY record of 256 bytes anyway. We cap to the hardware response size which is only FSF_FCP_RSP_SIZE==128. So we can just put the whole FCP_RSP IU with any optional parts into PAYload similarly as we do for SAN PAY since v4.9 commit aceeffbb59bb ("zfcp: trace full payload of all SAN records (req,resp,iels)"). This does not cause any additional trace records wasting memory. Decoded trace records were confusing because they showed a hard-coded sense data length of 96 even if the FCP_RSP_IU field FCP_SNS_LEN showed actually less. Since the same commit, we set pl_len for SAN traces to the full length of a request/response even if we cap the corresponding trace. In contrast, here for SCSI traces we set pl_len to the pre-computed length of FCP_RSP IU considering SNS_LEN or RSP_LEN if valid. Nonetheless we trace a hardcoded payload of length FSF_FCP_RSP_SIZE==128 if there were optional parts. This makes it easier for the zfcpdbf tool to format only the relevant part of the long FCP_RSP UI buffer. And any trailing information is still available in the payload trace record just in case. Rename the payload record tag from "fcp_sns" to "fcp_riu" to make the new content explicit to zfcpdbf which can then pick a suitable field name such as "FCP rsp IU all:" instead of "Sense info :" Also, the same zfcpdbf can still be backwards compatible with "fcp_sns". Old example trace record before this fix, formatted with the tool zfcpdbf from s390-tools: Timestamp : ... Area : SCSI Subarea : 00 Level : 3 Exception : - CPU id : .. Caller : 0x... Record id : 1 Tag : rsl_err Request id : 0x<request_id> SCSI ID : 0x... SCSI LUN : 0x... SCSI result : 0x00000002 SCSI retries : 0x00 SCSI allowed : 0x05 SCSI scribble : 0x<request_id> SCSI opcode : 00000000 00000000 00000000 00000000 FCP rsp inf cod: 0x00 FCP rsp IU : 00000000 00000000 00000202 00000000 ^^==FCP_SNS_LEN_VALID 00000020 00000000 ^^^^^^^^==FCP_SNS_LEN==32 Sense len : 96 <==min(SCSI_SENSE_BUFFERSIZE,ZFCP_DBF_PAY_MAX_REC) Sense info : 70000600 00000018 00000000 29000000 00000400 00000000 00000000 00000000 00000000 00000000 00000000 00000000<==superfluous 00000000 00000000 00000000 00000000<==superfluous 00000000 00000000 00000000 00000000<==superfluous 00000000 00000000 00000000 00000000<==superfluous New example trace records with this fix: Timestamp : ... Area : SCSI Subarea : 00 Level : 3 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : rsl_err Request ID : 0x<request_id> SCSI ID : 0x... SCSI LUN : 0x... SCSI result : 0x00000002 SCSI retries : 0x00 SCSI allowed : 0x03 SCSI scribble : 0x<request_id> SCSI opcode : a30c0112 00000000 02000000 00000000 FCP rsp inf cod: 0x00 FCP rsp IU : 00000000 00000000 00000a02 00000200 00000020 00000000 FCP rsp IU len : 56 FCP rsp IU all : 00000000 00000000 00000a02 00000200 ^^=FCP_RESID_UNDER|FCP_SNS_LEN_VALID 00000020 00000000 70000500 00000018 ^^^^^^^^==FCP_SNS_LEN ^^^^^^^^^^^^^^^^^ 00000000 240000cb 00011100 00000000 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 00000000 00000000 ^^^^^^^^^^^^^^^^^==FCP_SNS_INFO Timestamp : ... Area : SCSI Subarea : 00 Level : 1 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : lr_okay Request ID : 0x<request_id> SCSI ID : 0x... SCSI LUN : 0x... SCSI result : 0x00000000 SCSI retries : 0x00 SCSI allowed : 0x05 SCSI scribble : 0x<request_id> SCSI opcode : <CDB of unrelated SCSI command passed to eh handler> FCP rsp inf cod: 0x00 FCP rsp IU : 00000000 00000000 00000100 00000000 00000000 00000008 FCP rsp IU len : 32 FCP rsp IU all : 00000000 00000000 00000100 00000000 ^^==FCP_RSP_LEN_VALID 00000000 00000008 00000000 00000000 ^^^^^^^^==FCP_RSP_LEN ^^^^^^^^^^^^^^^^^==FCP_RSP_INFO Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com> Fixes: 250a1352b95e ("[SCSI] zfcp: Redesign of the debug tracing for SCSI records.") Cc: <stable@vger.kernel.org> #2.6.38+ Reviewed-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-07-28 18:30:56 +08:00
rec->pl_len = FCP_RESP_WITH_EXT;
fcp_rsp = &(fsf->qtcb->bottom.io.fcp_rsp.iu);
scsi: zfcp: fix payload with full FCP_RSP IU in SCSI trace records If the FCP_RSP UI has optional parts (FCP_SNS_INFO or FCP_RSP_INFO) and thus does not fit into the fsp_rsp field built into a SCSI trace record, trace the full FCP_RSP UI with all optional parts as payload record instead of just FCP_SNS_INFO as payload and a 1 byte RSP_INFO_CODE part of FCP_RSP_INFO built into the SCSI record. That way we would also get the full FCP_SNS_INFO in case a target would ever send more than min(SCSI_SENSE_BUFFERSIZE==96, ZFCP_DBF_PAY_MAX_REC==256)==96. The mandatory part of FCP_RSP IU is only 24 bytes. PAYload costs at least one full PAY record of 256 bytes anyway. We cap to the hardware response size which is only FSF_FCP_RSP_SIZE==128. So we can just put the whole FCP_RSP IU with any optional parts into PAYload similarly as we do for SAN PAY since v4.9 commit aceeffbb59bb ("zfcp: trace full payload of all SAN records (req,resp,iels)"). This does not cause any additional trace records wasting memory. Decoded trace records were confusing because they showed a hard-coded sense data length of 96 even if the FCP_RSP_IU field FCP_SNS_LEN showed actually less. Since the same commit, we set pl_len for SAN traces to the full length of a request/response even if we cap the corresponding trace. In contrast, here for SCSI traces we set pl_len to the pre-computed length of FCP_RSP IU considering SNS_LEN or RSP_LEN if valid. Nonetheless we trace a hardcoded payload of length FSF_FCP_RSP_SIZE==128 if there were optional parts. This makes it easier for the zfcpdbf tool to format only the relevant part of the long FCP_RSP UI buffer. And any trailing information is still available in the payload trace record just in case. Rename the payload record tag from "fcp_sns" to "fcp_riu" to make the new content explicit to zfcpdbf which can then pick a suitable field name such as "FCP rsp IU all:" instead of "Sense info :" Also, the same zfcpdbf can still be backwards compatible with "fcp_sns". Old example trace record before this fix, formatted with the tool zfcpdbf from s390-tools: Timestamp : ... Area : SCSI Subarea : 00 Level : 3 Exception : - CPU id : .. Caller : 0x... Record id : 1 Tag : rsl_err Request id : 0x<request_id> SCSI ID : 0x... SCSI LUN : 0x... SCSI result : 0x00000002 SCSI retries : 0x00 SCSI allowed : 0x05 SCSI scribble : 0x<request_id> SCSI opcode : 00000000 00000000 00000000 00000000 FCP rsp inf cod: 0x00 FCP rsp IU : 00000000 00000000 00000202 00000000 ^^==FCP_SNS_LEN_VALID 00000020 00000000 ^^^^^^^^==FCP_SNS_LEN==32 Sense len : 96 <==min(SCSI_SENSE_BUFFERSIZE,ZFCP_DBF_PAY_MAX_REC) Sense info : 70000600 00000018 00000000 29000000 00000400 00000000 00000000 00000000 00000000 00000000 00000000 00000000<==superfluous 00000000 00000000 00000000 00000000<==superfluous 00000000 00000000 00000000 00000000<==superfluous 00000000 00000000 00000000 00000000<==superfluous New example trace records with this fix: Timestamp : ... Area : SCSI Subarea : 00 Level : 3 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : rsl_err Request ID : 0x<request_id> SCSI ID : 0x... SCSI LUN : 0x... SCSI result : 0x00000002 SCSI retries : 0x00 SCSI allowed : 0x03 SCSI scribble : 0x<request_id> SCSI opcode : a30c0112 00000000 02000000 00000000 FCP rsp inf cod: 0x00 FCP rsp IU : 00000000 00000000 00000a02 00000200 00000020 00000000 FCP rsp IU len : 56 FCP rsp IU all : 00000000 00000000 00000a02 00000200 ^^=FCP_RESID_UNDER|FCP_SNS_LEN_VALID 00000020 00000000 70000500 00000018 ^^^^^^^^==FCP_SNS_LEN ^^^^^^^^^^^^^^^^^ 00000000 240000cb 00011100 00000000 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 00000000 00000000 ^^^^^^^^^^^^^^^^^==FCP_SNS_INFO Timestamp : ... Area : SCSI Subarea : 00 Level : 1 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : lr_okay Request ID : 0x<request_id> SCSI ID : 0x... SCSI LUN : 0x... SCSI result : 0x00000000 SCSI retries : 0x00 SCSI allowed : 0x05 SCSI scribble : 0x<request_id> SCSI opcode : <CDB of unrelated SCSI command passed to eh handler> FCP rsp inf cod: 0x00 FCP rsp IU : 00000000 00000000 00000100 00000000 00000000 00000008 FCP rsp IU len : 32 FCP rsp IU all : 00000000 00000000 00000100 00000000 ^^==FCP_RSP_LEN_VALID 00000000 00000008 00000000 00000000 ^^^^^^^^==FCP_RSP_LEN ^^^^^^^^^^^^^^^^^==FCP_RSP_INFO Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com> Fixes: 250a1352b95e ("[SCSI] zfcp: Redesign of the debug tracing for SCSI records.") Cc: <stable@vger.kernel.org> #2.6.38+ Reviewed-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-07-28 18:30:56 +08:00
/* mandatory parts of FCP_RSP IU in this SCSI record */
memcpy(&rec->fcp_rsp, fcp_rsp, FCP_RESP_WITH_EXT);
if (fcp_rsp->resp.fr_flags & FCP_RSP_LEN_VAL) {
fcp_rsp_info = (struct fcp_resp_rsp_info *) &fcp_rsp[1];
rec->fcp_rsp_info = fcp_rsp_info->rsp_code;
scsi: zfcp: fix payload with full FCP_RSP IU in SCSI trace records If the FCP_RSP UI has optional parts (FCP_SNS_INFO or FCP_RSP_INFO) and thus does not fit into the fsp_rsp field built into a SCSI trace record, trace the full FCP_RSP UI with all optional parts as payload record instead of just FCP_SNS_INFO as payload and a 1 byte RSP_INFO_CODE part of FCP_RSP_INFO built into the SCSI record. That way we would also get the full FCP_SNS_INFO in case a target would ever send more than min(SCSI_SENSE_BUFFERSIZE==96, ZFCP_DBF_PAY_MAX_REC==256)==96. The mandatory part of FCP_RSP IU is only 24 bytes. PAYload costs at least one full PAY record of 256 bytes anyway. We cap to the hardware response size which is only FSF_FCP_RSP_SIZE==128. So we can just put the whole FCP_RSP IU with any optional parts into PAYload similarly as we do for SAN PAY since v4.9 commit aceeffbb59bb ("zfcp: trace full payload of all SAN records (req,resp,iels)"). This does not cause any additional trace records wasting memory. Decoded trace records were confusing because they showed a hard-coded sense data length of 96 even if the FCP_RSP_IU field FCP_SNS_LEN showed actually less. Since the same commit, we set pl_len for SAN traces to the full length of a request/response even if we cap the corresponding trace. In contrast, here for SCSI traces we set pl_len to the pre-computed length of FCP_RSP IU considering SNS_LEN or RSP_LEN if valid. Nonetheless we trace a hardcoded payload of length FSF_FCP_RSP_SIZE==128 if there were optional parts. This makes it easier for the zfcpdbf tool to format only the relevant part of the long FCP_RSP UI buffer. And any trailing information is still available in the payload trace record just in case. Rename the payload record tag from "fcp_sns" to "fcp_riu" to make the new content explicit to zfcpdbf which can then pick a suitable field name such as "FCP rsp IU all:" instead of "Sense info :" Also, the same zfcpdbf can still be backwards compatible with "fcp_sns". Old example trace record before this fix, formatted with the tool zfcpdbf from s390-tools: Timestamp : ... Area : SCSI Subarea : 00 Level : 3 Exception : - CPU id : .. Caller : 0x... Record id : 1 Tag : rsl_err Request id : 0x<request_id> SCSI ID : 0x... SCSI LUN : 0x... SCSI result : 0x00000002 SCSI retries : 0x00 SCSI allowed : 0x05 SCSI scribble : 0x<request_id> SCSI opcode : 00000000 00000000 00000000 00000000 FCP rsp inf cod: 0x00 FCP rsp IU : 00000000 00000000 00000202 00000000 ^^==FCP_SNS_LEN_VALID 00000020 00000000 ^^^^^^^^==FCP_SNS_LEN==32 Sense len : 96 <==min(SCSI_SENSE_BUFFERSIZE,ZFCP_DBF_PAY_MAX_REC) Sense info : 70000600 00000018 00000000 29000000 00000400 00000000 00000000 00000000 00000000 00000000 00000000 00000000<==superfluous 00000000 00000000 00000000 00000000<==superfluous 00000000 00000000 00000000 00000000<==superfluous 00000000 00000000 00000000 00000000<==superfluous New example trace records with this fix: Timestamp : ... Area : SCSI Subarea : 00 Level : 3 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : rsl_err Request ID : 0x<request_id> SCSI ID : 0x... SCSI LUN : 0x... SCSI result : 0x00000002 SCSI retries : 0x00 SCSI allowed : 0x03 SCSI scribble : 0x<request_id> SCSI opcode : a30c0112 00000000 02000000 00000000 FCP rsp inf cod: 0x00 FCP rsp IU : 00000000 00000000 00000a02 00000200 00000020 00000000 FCP rsp IU len : 56 FCP rsp IU all : 00000000 00000000 00000a02 00000200 ^^=FCP_RESID_UNDER|FCP_SNS_LEN_VALID 00000020 00000000 70000500 00000018 ^^^^^^^^==FCP_SNS_LEN ^^^^^^^^^^^^^^^^^ 00000000 240000cb 00011100 00000000 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 00000000 00000000 ^^^^^^^^^^^^^^^^^==FCP_SNS_INFO Timestamp : ... Area : SCSI Subarea : 00 Level : 1 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : lr_okay Request ID : 0x<request_id> SCSI ID : 0x... SCSI LUN : 0x... SCSI result : 0x00000000 SCSI retries : 0x00 SCSI allowed : 0x05 SCSI scribble : 0x<request_id> SCSI opcode : <CDB of unrelated SCSI command passed to eh handler> FCP rsp inf cod: 0x00 FCP rsp IU : 00000000 00000000 00000100 00000000 00000000 00000008 FCP rsp IU len : 32 FCP rsp IU all : 00000000 00000000 00000100 00000000 ^^==FCP_RSP_LEN_VALID 00000000 00000008 00000000 00000000 ^^^^^^^^==FCP_RSP_LEN ^^^^^^^^^^^^^^^^^==FCP_RSP_INFO Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com> Fixes: 250a1352b95e ("[SCSI] zfcp: Redesign of the debug tracing for SCSI records.") Cc: <stable@vger.kernel.org> #2.6.38+ Reviewed-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-07-28 18:30:56 +08:00
rec->pl_len += be32_to_cpu(fcp_rsp->ext.fr_rsp_len);
}
if (fcp_rsp->resp.fr_flags & FCP_SNS_LEN_VAL) {
scsi: zfcp: fix payload with full FCP_RSP IU in SCSI trace records If the FCP_RSP UI has optional parts (FCP_SNS_INFO or FCP_RSP_INFO) and thus does not fit into the fsp_rsp field built into a SCSI trace record, trace the full FCP_RSP UI with all optional parts as payload record instead of just FCP_SNS_INFO as payload and a 1 byte RSP_INFO_CODE part of FCP_RSP_INFO built into the SCSI record. That way we would also get the full FCP_SNS_INFO in case a target would ever send more than min(SCSI_SENSE_BUFFERSIZE==96, ZFCP_DBF_PAY_MAX_REC==256)==96. The mandatory part of FCP_RSP IU is only 24 bytes. PAYload costs at least one full PAY record of 256 bytes anyway. We cap to the hardware response size which is only FSF_FCP_RSP_SIZE==128. So we can just put the whole FCP_RSP IU with any optional parts into PAYload similarly as we do for SAN PAY since v4.9 commit aceeffbb59bb ("zfcp: trace full payload of all SAN records (req,resp,iels)"). This does not cause any additional trace records wasting memory. Decoded trace records were confusing because they showed a hard-coded sense data length of 96 even if the FCP_RSP_IU field FCP_SNS_LEN showed actually less. Since the same commit, we set pl_len for SAN traces to the full length of a request/response even if we cap the corresponding trace. In contrast, here for SCSI traces we set pl_len to the pre-computed length of FCP_RSP IU considering SNS_LEN or RSP_LEN if valid. Nonetheless we trace a hardcoded payload of length FSF_FCP_RSP_SIZE==128 if there were optional parts. This makes it easier for the zfcpdbf tool to format only the relevant part of the long FCP_RSP UI buffer. And any trailing information is still available in the payload trace record just in case. Rename the payload record tag from "fcp_sns" to "fcp_riu" to make the new content explicit to zfcpdbf which can then pick a suitable field name such as "FCP rsp IU all:" instead of "Sense info :" Also, the same zfcpdbf can still be backwards compatible with "fcp_sns". Old example trace record before this fix, formatted with the tool zfcpdbf from s390-tools: Timestamp : ... Area : SCSI Subarea : 00 Level : 3 Exception : - CPU id : .. Caller : 0x... Record id : 1 Tag : rsl_err Request id : 0x<request_id> SCSI ID : 0x... SCSI LUN : 0x... SCSI result : 0x00000002 SCSI retries : 0x00 SCSI allowed : 0x05 SCSI scribble : 0x<request_id> SCSI opcode : 00000000 00000000 00000000 00000000 FCP rsp inf cod: 0x00 FCP rsp IU : 00000000 00000000 00000202 00000000 ^^==FCP_SNS_LEN_VALID 00000020 00000000 ^^^^^^^^==FCP_SNS_LEN==32 Sense len : 96 <==min(SCSI_SENSE_BUFFERSIZE,ZFCP_DBF_PAY_MAX_REC) Sense info : 70000600 00000018 00000000 29000000 00000400 00000000 00000000 00000000 00000000 00000000 00000000 00000000<==superfluous 00000000 00000000 00000000 00000000<==superfluous 00000000 00000000 00000000 00000000<==superfluous 00000000 00000000 00000000 00000000<==superfluous New example trace records with this fix: Timestamp : ... Area : SCSI Subarea : 00 Level : 3 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : rsl_err Request ID : 0x<request_id> SCSI ID : 0x... SCSI LUN : 0x... SCSI result : 0x00000002 SCSI retries : 0x00 SCSI allowed : 0x03 SCSI scribble : 0x<request_id> SCSI opcode : a30c0112 00000000 02000000 00000000 FCP rsp inf cod: 0x00 FCP rsp IU : 00000000 00000000 00000a02 00000200 00000020 00000000 FCP rsp IU len : 56 FCP rsp IU all : 00000000 00000000 00000a02 00000200 ^^=FCP_RESID_UNDER|FCP_SNS_LEN_VALID 00000020 00000000 70000500 00000018 ^^^^^^^^==FCP_SNS_LEN ^^^^^^^^^^^^^^^^^ 00000000 240000cb 00011100 00000000 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 00000000 00000000 ^^^^^^^^^^^^^^^^^==FCP_SNS_INFO Timestamp : ... Area : SCSI Subarea : 00 Level : 1 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : lr_okay Request ID : 0x<request_id> SCSI ID : 0x... SCSI LUN : 0x... SCSI result : 0x00000000 SCSI retries : 0x00 SCSI allowed : 0x05 SCSI scribble : 0x<request_id> SCSI opcode : <CDB of unrelated SCSI command passed to eh handler> FCP rsp inf cod: 0x00 FCP rsp IU : 00000000 00000000 00000100 00000000 00000000 00000008 FCP rsp IU len : 32 FCP rsp IU all : 00000000 00000000 00000100 00000000 ^^==FCP_RSP_LEN_VALID 00000000 00000008 00000000 00000000 ^^^^^^^^==FCP_RSP_LEN ^^^^^^^^^^^^^^^^^==FCP_RSP_INFO Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com> Fixes: 250a1352b95e ("[SCSI] zfcp: Redesign of the debug tracing for SCSI records.") Cc: <stable@vger.kernel.org> #2.6.38+ Reviewed-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-07-28 18:30:56 +08:00
rec->pl_len += be32_to_cpu(fcp_rsp->ext.fr_sns_len);
}
scsi: zfcp: fix payload with full FCP_RSP IU in SCSI trace records If the FCP_RSP UI has optional parts (FCP_SNS_INFO or FCP_RSP_INFO) and thus does not fit into the fsp_rsp field built into a SCSI trace record, trace the full FCP_RSP UI with all optional parts as payload record instead of just FCP_SNS_INFO as payload and a 1 byte RSP_INFO_CODE part of FCP_RSP_INFO built into the SCSI record. That way we would also get the full FCP_SNS_INFO in case a target would ever send more than min(SCSI_SENSE_BUFFERSIZE==96, ZFCP_DBF_PAY_MAX_REC==256)==96. The mandatory part of FCP_RSP IU is only 24 bytes. PAYload costs at least one full PAY record of 256 bytes anyway. We cap to the hardware response size which is only FSF_FCP_RSP_SIZE==128. So we can just put the whole FCP_RSP IU with any optional parts into PAYload similarly as we do for SAN PAY since v4.9 commit aceeffbb59bb ("zfcp: trace full payload of all SAN records (req,resp,iels)"). This does not cause any additional trace records wasting memory. Decoded trace records were confusing because they showed a hard-coded sense data length of 96 even if the FCP_RSP_IU field FCP_SNS_LEN showed actually less. Since the same commit, we set pl_len for SAN traces to the full length of a request/response even if we cap the corresponding trace. In contrast, here for SCSI traces we set pl_len to the pre-computed length of FCP_RSP IU considering SNS_LEN or RSP_LEN if valid. Nonetheless we trace a hardcoded payload of length FSF_FCP_RSP_SIZE==128 if there were optional parts. This makes it easier for the zfcpdbf tool to format only the relevant part of the long FCP_RSP UI buffer. And any trailing information is still available in the payload trace record just in case. Rename the payload record tag from "fcp_sns" to "fcp_riu" to make the new content explicit to zfcpdbf which can then pick a suitable field name such as "FCP rsp IU all:" instead of "Sense info :" Also, the same zfcpdbf can still be backwards compatible with "fcp_sns". Old example trace record before this fix, formatted with the tool zfcpdbf from s390-tools: Timestamp : ... Area : SCSI Subarea : 00 Level : 3 Exception : - CPU id : .. Caller : 0x... Record id : 1 Tag : rsl_err Request id : 0x<request_id> SCSI ID : 0x... SCSI LUN : 0x... SCSI result : 0x00000002 SCSI retries : 0x00 SCSI allowed : 0x05 SCSI scribble : 0x<request_id> SCSI opcode : 00000000 00000000 00000000 00000000 FCP rsp inf cod: 0x00 FCP rsp IU : 00000000 00000000 00000202 00000000 ^^==FCP_SNS_LEN_VALID 00000020 00000000 ^^^^^^^^==FCP_SNS_LEN==32 Sense len : 96 <==min(SCSI_SENSE_BUFFERSIZE,ZFCP_DBF_PAY_MAX_REC) Sense info : 70000600 00000018 00000000 29000000 00000400 00000000 00000000 00000000 00000000 00000000 00000000 00000000<==superfluous 00000000 00000000 00000000 00000000<==superfluous 00000000 00000000 00000000 00000000<==superfluous 00000000 00000000 00000000 00000000<==superfluous New example trace records with this fix: Timestamp : ... Area : SCSI Subarea : 00 Level : 3 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : rsl_err Request ID : 0x<request_id> SCSI ID : 0x... SCSI LUN : 0x... SCSI result : 0x00000002 SCSI retries : 0x00 SCSI allowed : 0x03 SCSI scribble : 0x<request_id> SCSI opcode : a30c0112 00000000 02000000 00000000 FCP rsp inf cod: 0x00 FCP rsp IU : 00000000 00000000 00000a02 00000200 00000020 00000000 FCP rsp IU len : 56 FCP rsp IU all : 00000000 00000000 00000a02 00000200 ^^=FCP_RESID_UNDER|FCP_SNS_LEN_VALID 00000020 00000000 70000500 00000018 ^^^^^^^^==FCP_SNS_LEN ^^^^^^^^^^^^^^^^^ 00000000 240000cb 00011100 00000000 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 00000000 00000000 ^^^^^^^^^^^^^^^^^==FCP_SNS_INFO Timestamp : ... Area : SCSI Subarea : 00 Level : 1 Exception : - CPU ID : .. Caller : 0x... Record ID : 1 Tag : lr_okay Request ID : 0x<request_id> SCSI ID : 0x... SCSI LUN : 0x... SCSI result : 0x00000000 SCSI retries : 0x00 SCSI allowed : 0x05 SCSI scribble : 0x<request_id> SCSI opcode : <CDB of unrelated SCSI command passed to eh handler> FCP rsp inf cod: 0x00 FCP rsp IU : 00000000 00000000 00000100 00000000 00000000 00000008 FCP rsp IU len : 32 FCP rsp IU all : 00000000 00000000 00000100 00000000 ^^==FCP_RSP_LEN_VALID 00000000 00000008 00000000 00000000 ^^^^^^^^==FCP_RSP_LEN ^^^^^^^^^^^^^^^^^==FCP_RSP_INFO Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com> Fixes: 250a1352b95e ("[SCSI] zfcp: Redesign of the debug tracing for SCSI records.") Cc: <stable@vger.kernel.org> #2.6.38+ Reviewed-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Benjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-07-28 18:30:56 +08:00
/* complete FCP_RSP IU in associated PAYload record
* but only if there are optional parts
*/
if (fcp_rsp->resp.fr_flags != 0)
zfcp_dbf_pl_write(
dbf, fcp_rsp,
/* at least one full PAY record
* but not beyond hardware response field
*/
min_t(u16, max_t(u16, rec->pl_len,
ZFCP_DBF_PAY_MAX_REC),
FSF_FCP_RSP_SIZE),
"fcp_riu", fsf->req_id);
}
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;
d = debug_register(name, size, 1, rec_size);
if (!d)
return NULL;
debug_register_view(d, &debug_hex_ascii_view);
debug_set_level(d, dbflevel);
return d;
}
static void zfcp_dbf_unregister(struct zfcp_dbf *dbf)
{
if (!dbf)
return;
debug_unregister(dbf->scsi);
debug_unregister(dbf->san);
debug_unregister(dbf->hba);
debug_unregister(dbf->pay);
debug_unregister(dbf->rec);
kfree(dbf);
}
/**
* zfcp_adapter_debug_register - registers debug feature for an adapter
* @adapter: pointer to adapter for which debug features should be registered
* return: -ENOMEM on error, 0 otherwise
*/
int zfcp_dbf_adapter_register(struct zfcp_adapter *adapter)
{
char name[DEBUG_MAX_NAME_LEN];
struct zfcp_dbf *dbf;
dbf = kzalloc(sizeof(struct zfcp_dbf), GFP_KERNEL);
if (!dbf)
return -ENOMEM;
spin_lock_init(&dbf->pay_lock);
spin_lock_init(&dbf->hba_lock);
spin_lock_init(&dbf->san_lock);
spin_lock_init(&dbf->scsi_lock);
spin_lock_init(&dbf->rec_lock);
/* debug feature area which records recovery activity */
sprintf(name, "zfcp_%s_rec", dev_name(&adapter->ccw_device->dev));
dbf->rec = zfcp_dbf_reg(name, dbfsize, sizeof(struct zfcp_dbf_rec));
if (!dbf->rec)
goto err_out;
/* debug feature area which records HBA (FSF and QDIO) conditions */
sprintf(name, "zfcp_%s_hba", dev_name(&adapter->ccw_device->dev));
dbf->hba = zfcp_dbf_reg(name, dbfsize, sizeof(struct zfcp_dbf_hba));
if (!dbf->hba)
goto err_out;
/* debug feature area which records payload info */
sprintf(name, "zfcp_%s_pay", dev_name(&adapter->ccw_device->dev));
dbf->pay = zfcp_dbf_reg(name, dbfsize * 2, sizeof(struct zfcp_dbf_pay));
if (!dbf->pay)
goto err_out;
/* debug feature area which records SAN command failures and recovery */
sprintf(name, "zfcp_%s_san", dev_name(&adapter->ccw_device->dev));
dbf->san = zfcp_dbf_reg(name, dbfsize, sizeof(struct zfcp_dbf_san));
if (!dbf->san)
goto err_out;
/* debug feature area which records SCSI command failures and recovery */
sprintf(name, "zfcp_%s_scsi", dev_name(&adapter->ccw_device->dev));
dbf->scsi = zfcp_dbf_reg(name, dbfsize, sizeof(struct zfcp_dbf_scsi));
if (!dbf->scsi)
goto err_out;
adapter->dbf = dbf;
return 0;
err_out:
zfcp_dbf_unregister(dbf);
return -ENOMEM;
}
/**
* zfcp_adapter_debug_unregister - unregisters debug feature for an adapter
* @adapter: pointer to adapter for which debug features should be unregistered
*/
void zfcp_dbf_adapter_unregister(struct zfcp_adapter *adapter)
{
struct zfcp_dbf *dbf = adapter->dbf;
adapter->dbf = NULL;
zfcp_dbf_unregister(dbf);
}