forked from Minki/linux
d0dff2ac98
At the moment we allocate and register the Scsi_Host object corresponding to a zfcp adapter (FCP device) very early in the life cycle of the adapter - even before we fully discover and initialize the underlying firmware/hardware. This had the advantage that we could already use the Scsi_Host object, and fill in all its information during said discover and initialize. Due to commit737eb78e82("block: Delay default elevator initialization") (first released in v5.4), we noticed a regression that would prevent us from using any storage volume if zfcp is configured with support for DIF or DIX (zfcp.dif=1 || zfcp.dix=1). Doing so would result in an illegal memory access as soon as the first request is sent with such an configuration. As example for a crash resulting from this: scsi host0: scsi_eh_0: sleeping scsi host0: zfcp qdio: 0.0.1900 ZFCP on SC 4bd using AI:1 QEBSM:0 PRI:1 TDD:1 SIGA: W AP scsi 0:0:0:0: scsi scan: INQUIRY pass 1 length 36 Unable to handle kernel pointer dereference in virtual kernel address space Failing address: 0000000000000000 TEID: 0000000000000483 Fault in home space mode while using kernel ASCE. AS:0000000035c7c007 R3:00000001effcc007 S:00000001effd1000 P:000000000000003d Oops: 0004 ilc:3 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: ... CPU: 1 PID: 783 Comm: kworker/u760:5 Kdump: loaded Not tainted 5.6.0-rc2-bb-next+ #1 Hardware name: ... Workqueue: scsi_wq_0 fc_scsi_scan_rport [scsi_transport_fc] Krnl PSW : 0704e00180000000 000003ff801fcdae (scsi_queue_rq+0x436/0x740 [scsi_mod]) R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:3 CC:2 PM:0 RI:0 EA:3 Krnl GPRS: 0fffffffffffffff 0000000000000000 0000000187150120 0000000000000000 000003ff80223d20 000000000000018e 000000018adc6400 0000000187711000 000003e0062337e8 00000001ae719000 0000000187711000 0000000187150000 00000001ab808100 0000000187150120 000003ff801fcd74 000003e0062336a0 Krnl Code: 000003ff801fcd9e: e310a35c0012 lt %r1,860(%r10) 000003ff801fcda4: a7840010 brc 8,000003ff801fcdc4 #000003ff801fcda8: e310b2900004 lg %r1,656(%r11) >000003ff801fcdae: d71710001000 xc 0(24,%r1),0(%r1) 000003ff801fcdb4: e310b2900004 lg %r1,656(%r11) 000003ff801fcdba: 41201018 la %r2,24(%r1) 000003ff801fcdbe: e32010000024 stg %r2,0(%r1) 000003ff801fcdc4: b904002b lgr %r2,%r11 Call Trace: [<000003ff801fcdae>] scsi_queue_rq+0x436/0x740 [scsi_mod] ([<000003ff801fcd74>] scsi_queue_rq+0x3fc/0x740 [scsi_mod]) [<00000000349c9970>] blk_mq_dispatch_rq_list+0x390/0x680 [<00000000349d1596>] blk_mq_sched_dispatch_requests+0x196/0x1a8 [<00000000349c7a04>] __blk_mq_run_hw_queue+0x144/0x160 [<00000000349c7ab6>] __blk_mq_delay_run_hw_queue+0x96/0x228 [<00000000349c7d5a>] blk_mq_run_hw_queue+0xd2/0xe0 [<00000000349d194a>] blk_mq_sched_insert_request+0x192/0x1d8 [<00000000349c17b8>] blk_execute_rq_nowait+0x80/0x90 [<00000000349c1856>] blk_execute_rq+0x6e/0xb0 [<000003ff801f8ac2>] __scsi_execute+0xe2/0x1f0 [scsi_mod] [<000003ff801fef98>] scsi_probe_and_add_lun+0x358/0x840 [scsi_mod] [<000003ff8020001c>] __scsi_scan_target+0xc4/0x228 [scsi_mod] [<000003ff80200254>] scsi_scan_target+0xd4/0x100 [scsi_mod] [<000003ff802d8b96>] fc_scsi_scan_rport+0x96/0xc0 [scsi_transport_fc] [<0000000034245ce8>] process_one_work+0x458/0x7d0 [<00000000342462a2>] worker_thread+0x242/0x448 [<0000000034250994>] kthread+0x15c/0x170 [<0000000034e1979c>] ret_from_fork+0x30/0x38 INFO: lockdep is turned off. Last Breaking-Event-Address: [<000003ff801fbc36>] scsi_add_cmd_to_list+0x9e/0xa8 [scsi_mod] Kernel panic - not syncing: Fatal exception: panic_on_oops While this issue is exposed by the commit named above, this is only by accident. The real issue exists for longer already - basically since it's possible to use blk-mq via scsi-mq, and blk-mq pre-allocates all requests for a tag-set during initialization of the same. For a given Scsi_Host object this is done when adding the object to the midlayer (`scsi_add_host()` and such). In `scsi_mq_setup_tags()` the midlayer calculates how much memory is required for a single scsi_cmnd, and its additional data, which also might include space for additional protection data - depending on whether the Scsi_Host has any form of protection capabilities (`scsi_host_get_prot()`). The problem is now thus, because zfcp does this step before we actually know whether the firmware/hardware has these capabilities, we don't set any protection capabilities in the Scsi_Host object. And so, no space is allocated for additional protection data for requests in the Scsi_Host tag-set. Once we go through discover and initialize the FCP device firmware/hardware fully (this is done via the firmware commands "Exchange Config Data" and "Exchange Port Data") we find out whether it actually supports DIF and DIX, and we set the corresponding capabilities in the Scsi_Host object (in `zfcp_scsi_set_prot()`). Now the Scsi_Host potentially has protection capabilities, but the already allocated requests in the tag-set don't have any space allocated for that. When we then trigger target scanning or add scsi_devices manually, the midlayer will use requests from that tag-set, and before sending most requests, it will also call `scsi_mq_prep_fn()`. To prepare the scsi_cmnd this function will check again whether the used Scsi_Host has any protection capabilities - and now it potentially has - and if so, it will try to initialize the assumed to be preallocated structures and thus it causes the crash, like shown above. Before delaying the default elevator initialization with the commit named above, we always would also allocate an elevator for any scsi_device before ever sending any requests - in contrast to now, where we do it after device-probing. That elevator in turn would have its own tag-set, and that is initialized after we went through discovery and initialization of the underlying firmware/hardware. So requests from that tag-set can be allocated properly, and if used - unless the user changes/disabled the default elevator - this would hide the underlying issue. To fix this for any configuration - with or without an elevator - we move the allocation and registration of the Scsi_Host object for a given FCP device to after the first complete discovery and initialization of the underlying firmware/hardware. By doing that we can make all basic properties of the Scsi_Host known to the midlayer by the time we call `scsi_add_host()`, including whether we have any protection capabilities. To do that we have to delay all the accesses that we would have done in the past during discovery and initialization, and do them instead once we are finished with it. The previous patches ramp up to this by fencing and factoring out all these accesses, and make it possible to re-do them later on. In addition we make also use of the diagnostic buffers we recently added with commit92953c6e0a("scsi: zfcp: signal incomplete or error for sync exchange config/port data") commit7e418833e6("scsi: zfcp: diagnostics buffer caching and use for exchange port data") commit088210233e("scsi: zfcp: add diagnostics buffer for exchange config data") (first released in v5.5), because these already cache all the information we need for that "re-do operation" - the information cached are always updated during xconf or xport data, so it won't be stale. In addition to the move and re-do, this patch also updates the function-documentation of `zfcp_scsi_adapter_register()` and changes how it reports if a Scsi_Host object already exists. In that case future recovery-operations can skip this step completely and behave much like they would do in the past - zfcp does not release a once allocated Scsi_Host object unless the corresponding FCP device is deconstructed completely. Link: https://lore.kernel.org/r/030dd6da318bbb529f0b5268ec65cebcd20fc0a3.1588956679.git.bblock@linux.ibm.com Reviewed-by: Steffen Maier <maier@linux.ibm.com> Signed-off-by: Benjamin Block <bblock@linux.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
102 lines
3.2 KiB
C
102 lines
3.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* zfcp device driver
|
|
*
|
|
* Definitions for handling diagnostics in the the zfcp device driver.
|
|
*
|
|
* Copyright IBM Corp. 2018, 2020
|
|
*/
|
|
|
|
#ifndef ZFCP_DIAG_H
|
|
#define ZFCP_DIAG_H
|
|
|
|
#include <linux/spinlock.h>
|
|
|
|
#include "zfcp_fsf.h"
|
|
#include "zfcp_def.h"
|
|
|
|
/**
|
|
* struct zfcp_diag_header - general part of a diagnostic buffer.
|
|
* @access_lock: lock protecting all the data in this buffer.
|
|
* @updating: flag showing that an update for this buffer is currently running.
|
|
* @incomplete: flag showing that the data in @buffer is incomplete.
|
|
* @timestamp: time in jiffies when the data of this buffer was last captured.
|
|
* @buffer: implementation-depending data of this buffer
|
|
* @buffer_size: size of @buffer
|
|
*/
|
|
struct zfcp_diag_header {
|
|
spinlock_t access_lock;
|
|
|
|
/* Flags */
|
|
u64 updating :1;
|
|
u64 incomplete :1;
|
|
|
|
unsigned long timestamp;
|
|
|
|
void *buffer;
|
|
size_t buffer_size;
|
|
};
|
|
|
|
/**
|
|
* struct zfcp_diag_adapter - central storage for all diagnostics concerning an
|
|
* adapter.
|
|
* @sysfs_established: flag showing that the associated sysfs-group was created
|
|
* during run of zfcp_adapter_enqueue().
|
|
* @max_age: maximum age of data in diagnostic buffers before they need to be
|
|
* refreshed (in ms).
|
|
* @port_data: data retrieved using exchange port data.
|
|
* @port_data.header: header with metadata for the cache in @port_data.data.
|
|
* @port_data.data: cached QTCB Bottom of command exchange port data.
|
|
* @config_data: data retrieved using exchange config data.
|
|
* @config_data.header: header with metadata for the cache in @config_data.data.
|
|
* @config_data.data: cached QTCB Bottom of command exchange config data.
|
|
*/
|
|
struct zfcp_diag_adapter {
|
|
u64 sysfs_established :1;
|
|
|
|
unsigned long max_age;
|
|
|
|
struct zfcp_diag_adapter_port_data {
|
|
struct zfcp_diag_header header;
|
|
struct fsf_qtcb_bottom_port data;
|
|
} port_data;
|
|
struct zfcp_diag_adapter_config_data {
|
|
struct zfcp_diag_header header;
|
|
struct fsf_qtcb_bottom_config data;
|
|
} config_data;
|
|
};
|
|
|
|
int zfcp_diag_adapter_setup(struct zfcp_adapter *const adapter);
|
|
void zfcp_diag_adapter_free(struct zfcp_adapter *const adapter);
|
|
|
|
int zfcp_diag_sysfs_setup(struct zfcp_adapter *const adapter);
|
|
void zfcp_diag_sysfs_destroy(struct zfcp_adapter *const adapter);
|
|
|
|
void zfcp_diag_update_xdata(struct zfcp_diag_header *const hdr,
|
|
const void *const data, const bool incomplete);
|
|
|
|
/*
|
|
* Function-Type used in zfcp_diag_update_buffer_limited() for the function
|
|
* that does the buffer-implementation dependent work.
|
|
*/
|
|
typedef int (*zfcp_diag_update_buffer_func)(struct zfcp_adapter *const adapter);
|
|
|
|
int zfcp_diag_update_config_data_buffer(struct zfcp_adapter *const adapter);
|
|
int zfcp_diag_update_port_data_buffer(struct zfcp_adapter *const adapter);
|
|
int zfcp_diag_update_buffer_limited(struct zfcp_adapter *const adapter,
|
|
struct zfcp_diag_header *const hdr,
|
|
zfcp_diag_update_buffer_func buffer_update);
|
|
|
|
/**
|
|
* zfcp_diag_support_sfp() - Return %true if the @adapter supports reporting
|
|
* SFP Data.
|
|
* @adapter: adapter to test the availability of SFP Data reporting for.
|
|
*/
|
|
static inline bool
|
|
zfcp_diag_support_sfp(const struct zfcp_adapter *const adapter)
|
|
{
|
|
return !!(adapter->adapter_features & FSF_FEATURE_REPORT_SFP_DATA);
|
|
}
|
|
|
|
#endif /* ZFCP_DIAG_H */
|