linux_dsm_epyc7002/drivers/scsi/scsi_lib.c
AuxXxilium 5fa3ea047a init: add dsm gpl source
Signed-off-by: AuxXxilium <info@auxxxilium.tech>
2024-07-05 18:00:04 +02:00

3779 lines
98 KiB
C

#ifndef MY_ABC_HERE
#define MY_ABC_HERE
#endif
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 1999 Eric Youngdale
* Copyright (C) 2014 Christoph Hellwig
*
* SCSI queueing library.
* Initial versions: Eric Youngdale (eric@andante.org).
* Based upon conversations with large numbers
* of people at Linux Expo.
*/
#include <linux/bio.h>
#include <linux/bitops.h>
#include <linux/blkdev.h>
#include <linux/completion.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/init.h>
#include <linux/pci.h>
#include <linux/delay.h>
#include <linux/hardirq.h>
#include <linux/scatterlist.h>
#include <linux/blk-mq.h>
#include <linux/ratelimit.h>
#include <asm/unaligned.h>
#include <scsi/scsi.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_dbg.h>
#include <scsi/scsi_device.h>
#include <scsi/scsi_driver.h>
#include <scsi/scsi_eh.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi_transport.h> /* __scsi_init_queue() */
#include <scsi/scsi_dh.h>
#include <trace/events/scsi.h>
#include "scsi_debugfs.h"
#include "scsi_priv.h"
#include "scsi_logging.h"
#ifdef MY_ABC_HERE
#include "libsyno_report.h"
#endif /* MY_ABC_HERE */
#ifdef MY_ABC_HERE
#include <scsi/scsi_transport.h>
#include "scsi_transport_api.h"
#endif /* MY_ABC_HERE */
#if defined(MY_ABC_HERE)
#include <linux/ata.h>
#endif /* MY_ABC_HERE */
#ifdef MY_ABC_HERE
#include <linux/synolib.h>
#endif /* MY_ABC_HERE */
#ifdef MY_ABC_HERE
#ifdef KERN_INFO
#undef KERN_INFO
#define KERN_INFO KERN_NOTICE
#endif
#endif /* MY_ABC_HERE */
#ifdef MY_ABC_HERE
#define SYNO_SMART_CMD_TIMEOUT 30 * HZ
#endif /* MY_ABC_HERE */
/*
* Size of integrity metadata is usually small, 1 inline sg should
* cover normal cases.
*/
#ifdef CONFIG_ARCH_NO_SG_CHAIN
#define SCSI_INLINE_PROT_SG_CNT 0
#define SCSI_INLINE_SG_CNT 0
#else
#define SCSI_INLINE_PROT_SG_CNT 1
#define SCSI_INLINE_SG_CNT 2
#endif
static struct kmem_cache *scsi_sense_cache;
static struct kmem_cache *scsi_sense_isadma_cache;
static DEFINE_MUTEX(scsi_sense_cache_mutex);
static void scsi_mq_uninit_cmd(struct scsi_cmnd *cmd);
static inline struct kmem_cache *
scsi_select_sense_cache(bool unchecked_isa_dma)
{
return unchecked_isa_dma ? scsi_sense_isadma_cache : scsi_sense_cache;
}
static void scsi_free_sense_buffer(bool unchecked_isa_dma,
unsigned char *sense_buffer)
{
kmem_cache_free(scsi_select_sense_cache(unchecked_isa_dma),
sense_buffer);
}
static unsigned char *scsi_alloc_sense_buffer(bool unchecked_isa_dma,
gfp_t gfp_mask, int numa_node)
{
return kmem_cache_alloc_node(scsi_select_sense_cache(unchecked_isa_dma),
gfp_mask, numa_node);
}
int scsi_init_sense_cache(struct Scsi_Host *shost)
{
struct kmem_cache *cache;
int ret = 0;
mutex_lock(&scsi_sense_cache_mutex);
cache = scsi_select_sense_cache(shost->unchecked_isa_dma);
if (cache)
goto exit;
if (shost->unchecked_isa_dma) {
scsi_sense_isadma_cache =
kmem_cache_create("scsi_sense_cache(DMA)",
SCSI_SENSE_BUFFERSIZE, 0,
SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA, NULL);
if (!scsi_sense_isadma_cache)
ret = -ENOMEM;
} else {
scsi_sense_cache =
kmem_cache_create_usercopy("scsi_sense_cache",
SCSI_SENSE_BUFFERSIZE, 0, SLAB_HWCACHE_ALIGN,
0, SCSI_SENSE_BUFFERSIZE, NULL);
if (!scsi_sense_cache)
ret = -ENOMEM;
}
exit:
mutex_unlock(&scsi_sense_cache_mutex);
return ret;
}
/*
* When to reinvoke queueing after a resource shortage. It's 3 msecs to
* not change behaviour from the previous unplug mechanism, experimentation
* may prove this needs changing.
*/
#define SCSI_QUEUE_DELAY 3
static void
scsi_set_blocked(struct scsi_cmnd *cmd, int reason)
{
struct Scsi_Host *host = cmd->device->host;
struct scsi_device *device = cmd->device;
struct scsi_target *starget = scsi_target(device);
/*
* Set the appropriate busy bit for the device/host.
*
* If the host/device isn't busy, assume that something actually
* completed, and that we should be able to queue a command now.
*
* Note that the prior mid-layer assumption that any host could
* always queue at least one command is now broken. The mid-layer
* will implement a user specifiable stall (see
* scsi_host.max_host_blocked and scsi_device.max_device_blocked)
* if a command is requeued with no other commands outstanding
* either for the device or for the host.
*/
switch (reason) {
case SCSI_MLQUEUE_HOST_BUSY:
atomic_set(&host->host_blocked, host->max_host_blocked);
break;
case SCSI_MLQUEUE_DEVICE_BUSY:
case SCSI_MLQUEUE_EH_RETRY:
atomic_set(&device->device_blocked,
device->max_device_blocked);
break;
case SCSI_MLQUEUE_TARGET_BUSY:
atomic_set(&starget->target_blocked,
starget->max_target_blocked);
break;
}
}
static void scsi_mq_requeue_cmd(struct scsi_cmnd *cmd)
{
if (cmd->request->rq_flags & RQF_DONTPREP) {
cmd->request->rq_flags &= ~RQF_DONTPREP;
scsi_mq_uninit_cmd(cmd);
} else {
WARN_ON_ONCE(true);
}
blk_mq_requeue_request(cmd->request, true);
}
/**
* __scsi_queue_insert - private queue insertion
* @cmd: The SCSI command being requeued
* @reason: The reason for the requeue
* @unbusy: Whether the queue should be unbusied
*
* This is a private queue insertion. The public interface
* scsi_queue_insert() always assumes the queue should be unbusied
* because it's always called before the completion. This function is
* for a requeue after completion, which should only occur in this
* file.
*/
static void __scsi_queue_insert(struct scsi_cmnd *cmd, int reason, bool unbusy)
{
struct scsi_device *device = cmd->device;
SCSI_LOG_MLQUEUE(1, scmd_printk(KERN_INFO, cmd,
"Inserting command %p into mlqueue\n", cmd));
scsi_set_blocked(cmd, reason);
/*
* Decrement the counters, since these commands are no longer
* active on the host/device.
*/
if (unbusy)
scsi_device_unbusy(device, cmd);
/*
* Requeue this command. It will go before all other commands
* that are already in the queue. Schedule requeue work under
* lock such that the kblockd_schedule_work() call happens
* before blk_cleanup_queue() finishes.
*/
cmd->result = 0;
blk_mq_requeue_request(cmd->request, true);
}
/**
* scsi_queue_insert - Reinsert a command in the queue.
* @cmd: command that we are adding to queue.
* @reason: why we are inserting command to queue.
*
* We do this for one of two cases. Either the host is busy and it cannot accept
* any more commands for the time being, or the device returned QUEUE_FULL and
* can accept no more commands.
*
* Context: This could be called either from an interrupt context or a normal
* process context.
*/
void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
{
__scsi_queue_insert(cmd, reason, true);
}
/**
* __scsi_execute - insert request and wait for the result
* @sdev: scsi device
* @cmd: scsi command
* @data_direction: data direction
* @buffer: data buffer
* @bufflen: len of buffer
* @sense: optional sense buffer
* @sshdr: optional decoded sense header
* @timeout: request timeout in seconds
* @retries: number of times to retry request
* @flags: flags for ->cmd_flags
* @rq_flags: flags for ->rq_flags
* @resid: optional residual length
*
* Returns the scsi_cmnd result field if a command was executed, or a negative
* Linux error code if we didn't get that far.
*/
int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
int data_direction, void *buffer, unsigned bufflen,
unsigned char *sense, struct scsi_sense_hdr *sshdr,
int timeout, int retries, u64 flags, req_flags_t rq_flags,
int *resid)
{
struct request *req;
struct scsi_request *rq;
int ret = DRIVER_ERROR << 24;
req = blk_get_request(sdev->request_queue,
data_direction == DMA_TO_DEVICE ?
REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
rq_flags & RQF_PM ? BLK_MQ_REQ_PM : 0);
if (IS_ERR(req))
return ret;
rq = scsi_req(req);
if (bufflen && blk_rq_map_kern(sdev->request_queue, req,
buffer, bufflen, GFP_NOIO))
goto out;
rq->cmd_len = COMMAND_SIZE(cmd[0]);
memcpy(rq->cmd, cmd, rq->cmd_len);
rq->retries = retries;
#ifdef MY_ABC_HERE
req->timeout = ((sdev->scmd_timeout_sec*HZ) > timeout ? (sdev->scmd_timeout_sec*HZ) : timeout);
// Set smart command timeout at least 30s
if ((ATA_CMD_SMART == rq->cmd[0] ||
(ATA_16 == rq->cmd[0] && ATA_CMD_SMART == rq->cmd[14])) &&
SYNO_SMART_CMD_TIMEOUT > req->timeout) {
req->timeout = SYNO_SMART_CMD_TIMEOUT;
}
#else /* MY_ABC_HERE */
req->timeout = timeout;
#endif /* MY_ABC_HERE */
req->cmd_flags |= flags;
req->rq_flags |= rq_flags | RQF_QUIET;
/*
* head injection *required* here otherwise quiesce won't work
*/
blk_execute_rq(req->q, NULL, req, 1);
/*
* Some devices (USB mass-storage in particular) may transfer
* garbage data together with a residue indicating that the data
* is invalid. Prevent the garbage from being misinterpreted
* and prevent security leaks by zeroing out the excess data.
*/
if (unlikely(rq->resid_len > 0 && rq->resid_len <= bufflen))
memset(buffer + (bufflen - rq->resid_len), 0, rq->resid_len);
if (resid)
*resid = rq->resid_len;
if (sense && rq->sense_len)
memcpy(sense, rq->sense, SCSI_SENSE_BUFFERSIZE);
if (sshdr)
scsi_normalize_sense(rq->sense, rq->sense_len, sshdr);
ret = rq->result;
out:
blk_put_request(req);
return ret;
}
EXPORT_SYMBOL(__scsi_execute);
/*
* Wake up the error handler if necessary. Avoid as follows that the error
* handler is not woken up if host in-flight requests number ==
* shost->host_failed: use call_rcu() in scsi_eh_scmd_add() in combination
* with an RCU read lock in this function to ensure that this function in
* its entirety either finishes before scsi_eh_scmd_add() increases the
* host_failed counter or that it notices the shost state change made by
* scsi_eh_scmd_add().
*/
static void scsi_dec_host_busy(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
{
unsigned long flags;
rcu_read_lock();
__clear_bit(SCMD_STATE_INFLIGHT, &cmd->state);
if (unlikely(scsi_host_in_recovery(shost))) {
spin_lock_irqsave(shost->host_lock, flags);
if (shost->host_failed || shost->host_eh_scheduled)
scsi_eh_wakeup(shost);
spin_unlock_irqrestore(shost->host_lock, flags);
}
rcu_read_unlock();
}
void scsi_device_unbusy(struct scsi_device *sdev, struct scsi_cmnd *cmd)
{
struct Scsi_Host *shost = sdev->host;
struct scsi_target *starget = scsi_target(sdev);
scsi_dec_host_busy(shost, cmd);
if (starget->can_queue > 0)
atomic_dec(&starget->target_busy);
atomic_dec(&sdev->device_busy);
}
static void scsi_kick_queue(struct request_queue *q)
{
blk_mq_run_hw_queues(q, false);
}
/*
* Called for single_lun devices on IO completion. Clear starget_sdev_user,
* and call blk_run_queue for all the scsi_devices on the target -
* including current_sdev first.
*
* Called with *no* scsi locks held.
*/
static void scsi_single_lun_run(struct scsi_device *current_sdev)
{
struct Scsi_Host *shost = current_sdev->host;
struct scsi_device *sdev, *tmp;
struct scsi_target *starget = scsi_target(current_sdev);
unsigned long flags;
spin_lock_irqsave(shost->host_lock, flags);
starget->starget_sdev_user = NULL;
spin_unlock_irqrestore(shost->host_lock, flags);
/*
* Call blk_run_queue for all LUNs on the target, starting with
* current_sdev. We race with others (to set starget_sdev_user),
* but in most cases, we will be first. Ideally, each LU on the
* target would get some limited time or requests on the target.
*/
scsi_kick_queue(current_sdev->request_queue);
spin_lock_irqsave(shost->host_lock, flags);
if (starget->starget_sdev_user)
goto out;
list_for_each_entry_safe(sdev, tmp, &starget->devices,
same_target_siblings) {
if (sdev == current_sdev)
continue;
if (scsi_device_get(sdev))
continue;
spin_unlock_irqrestore(shost->host_lock, flags);
scsi_kick_queue(sdev->request_queue);
spin_lock_irqsave(shost->host_lock, flags);
scsi_device_put(sdev);
}
out:
spin_unlock_irqrestore(shost->host_lock, flags);
}
static inline bool scsi_device_is_busy(struct scsi_device *sdev)
{
if (atomic_read(&sdev->device_busy) >= sdev->queue_depth)
return true;
if (atomic_read(&sdev->device_blocked) > 0)
return true;
return false;
}
static inline bool scsi_target_is_busy(struct scsi_target *starget)
{
if (starget->can_queue > 0) {
if (atomic_read(&starget->target_busy) >= starget->can_queue)
return true;
if (atomic_read(&starget->target_blocked) > 0)
return true;
}
return false;
}
static inline bool scsi_host_is_busy(struct Scsi_Host *shost)
{
if (atomic_read(&shost->host_blocked) > 0)
return true;
if (shost->host_self_blocked)
return true;
return false;
}
static void scsi_starved_list_run(struct Scsi_Host *shost)
{
LIST_HEAD(starved_list);
struct scsi_device *sdev;
unsigned long flags;
spin_lock_irqsave(shost->host_lock, flags);
list_splice_init(&shost->starved_list, &starved_list);
while (!list_empty(&starved_list)) {
struct request_queue *slq;
/*
* As long as shost is accepting commands and we have
* starved queues, call blk_run_queue. scsi_request_fn
* drops the queue_lock and can add us back to the
* starved_list.
*
* host_lock protects the starved_list and starved_entry.
* scsi_request_fn must get the host_lock before checking
* or modifying starved_list or starved_entry.
*/
if (scsi_host_is_busy(shost))
break;
sdev = list_entry(starved_list.next,
struct scsi_device, starved_entry);
list_del_init(&sdev->starved_entry);
if (scsi_target_is_busy(scsi_target(sdev))) {
list_move_tail(&sdev->starved_entry,
&shost->starved_list);
continue;
}
/*
* Once we drop the host lock, a racing scsi_remove_device()
* call may remove the sdev from the starved list and destroy
* it and the queue. Mitigate by taking a reference to the
* queue and never touching the sdev again after we drop the
* host lock. Note: if __scsi_remove_device() invokes
* blk_cleanup_queue() before the queue is run from this
* function then blk_run_queue() will return immediately since
* blk_cleanup_queue() marks the queue with QUEUE_FLAG_DYING.
*/
slq = sdev->request_queue;
if (!blk_get_queue(slq))
continue;
spin_unlock_irqrestore(shost->host_lock, flags);
scsi_kick_queue(slq);
blk_put_queue(slq);
spin_lock_irqsave(shost->host_lock, flags);
}
/* put any unprocessed entries back */
list_splice(&starved_list, &shost->starved_list);
spin_unlock_irqrestore(shost->host_lock, flags);
}
/**
* scsi_run_queue - Select a proper request queue to serve next.
* @q: last request's queue
*
* The previous command was completely finished, start a new one if possible.
*/
static void scsi_run_queue(struct request_queue *q)
{
struct scsi_device *sdev = q->queuedata;
if (scsi_target(sdev)->single_lun)
scsi_single_lun_run(sdev);
if (!list_empty(&sdev->host->starved_list))
scsi_starved_list_run(sdev->host);
blk_mq_run_hw_queues(q, false);
}
void scsi_requeue_run_queue(struct work_struct *work)
{
struct scsi_device *sdev;
struct request_queue *q;
sdev = container_of(work, struct scsi_device, requeue_work);
q = sdev->request_queue;
scsi_run_queue(q);
}
void scsi_run_host_queues(struct Scsi_Host *shost)
{
struct scsi_device *sdev;
shost_for_each_device(sdev, shost)
scsi_run_queue(sdev->request_queue);
}
static void scsi_uninit_cmd(struct scsi_cmnd *cmd)
{
if (!blk_rq_is_passthrough(cmd->request)) {
struct scsi_driver *drv = scsi_cmd_to_driver(cmd);
if (drv->uninit_command)
drv->uninit_command(cmd);
}
}
void scsi_free_sgtables(struct scsi_cmnd *cmd)
{
if (cmd->sdb.table.nents)
sg_free_table_chained(&cmd->sdb.table,
SCSI_INLINE_SG_CNT);
if (scsi_prot_sg_count(cmd))
sg_free_table_chained(&cmd->prot_sdb->table,
SCSI_INLINE_PROT_SG_CNT);
}
EXPORT_SYMBOL_GPL(scsi_free_sgtables);
static void scsi_mq_uninit_cmd(struct scsi_cmnd *cmd)
{
scsi_free_sgtables(cmd);
scsi_uninit_cmd(cmd);
}
static void scsi_run_queue_async(struct scsi_device *sdev)
{
if (scsi_target(sdev)->single_lun ||
!list_empty(&sdev->host->starved_list)) {
kblockd_schedule_work(&sdev->requeue_work);
} else {
/*
* smp_mb() present in sbitmap_queue_clear() or implied in
* .end_io is for ordering writing .device_busy in
* scsi_device_unbusy() and reading sdev->restarts.
*/
int old = atomic_read(&sdev->restarts);
/*
* ->restarts has to be kept as non-zero if new budget
* contention occurs.
*
* No need to run queue when either another re-run
* queue wins in updating ->restarts or a new budget
* contention occurs.
*/
if (old && atomic_cmpxchg(&sdev->restarts, old, 0) == old)
blk_mq_run_hw_queues(sdev->request_queue, true);
}
}
#ifdef MY_DEF_HERE
static void SynoSpinupDone(struct request *req, blk_status_t status)
{
struct scsi_device *sdev = req->q->queuedata;
blk_put_request(req);
SynoSpinupEnd(sdev);
}
extern struct workqueue_struct *spinup_workqueue;
void SynoQueueSpinupReq (struct scsi_device *sdev)
{
if (spinup_workqueue) {
queue_work(spinup_workqueue, &sdev->spinup_work);
} else {
schedule_work(&sdev->spinup_work);
}
}
void SynoSubmitSpinupReq(struct work_struct *work)
{
struct request *req;
struct scsi_request *rq;
struct scsi_device *sdev;
sdev = container_of(work, struct scsi_device, spinup_work);
req = blk_get_request(sdev->request_queue, REQ_OP_SCSI_IN, BLK_MQ_REQ_PM);
if (IS_ERR(req)) {
SynoQueueSpinupReq(sdev);
printk(KERN_ERR "%s: Can't get request, retry it", __FUNCTION__);
return;
}
rq = scsi_req(req);
rq->cmd[0] = START_STOP;
rq->cmd[1] = 0;
rq->cmd[2] = 0;
rq->cmd[3] = 0;
rq->cmd[4] = 1; /* START */
rq->cmd[5] = 0;
rq->cmd_len = COMMAND_SIZE(rq->cmd[0]);
req->rq_flags |= RQF_PM | RQF_QUIET;
req->timeout = 60 * HZ;
rq->retries = 5;
blk_execute_rq_nowait(req->q, NULL, req, 1, SynoSpinupDone);
}
static void SynoSpinupDisk(struct scsi_device *device)
{
if (SynoSpinupBegin(device)) {
SynoQueueSpinupReq(device);
}
}
#endif /* MY_DEF_HERE */
/* Returns false when no more bytes to process, true if there are more */
static bool scsi_end_request(struct request *req, blk_status_t error,
unsigned int bytes)
{
struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
struct scsi_device *sdev = cmd->device;
struct request_queue *q = sdev->request_queue;
if (blk_update_request(req, error, bytes))
return true;
if (blk_queue_add_random(q))
add_disk_randomness(req->rq_disk);
if (!blk_rq_is_scsi(req)) {
WARN_ON_ONCE(!(cmd->flags & SCMD_INITIALIZED));
cmd->flags &= ~SCMD_INITIALIZED;
}
/*
* Calling rcu_barrier() is not necessary here because the
* SCSI error handler guarantees that the function called by
* call_rcu() has been called before scsi_end_request() is
* called.
*/
destroy_rcu_head(&cmd->rcu);
/*
* In the MQ case the command gets freed by __blk_mq_end_request,
* so we have to do all cleanup that depends on it earlier.
*
* We also can't kick the queues from irq context, so we
* will have to defer it to a workqueue.
*/
scsi_mq_uninit_cmd(cmd);
/*
* queue is still alive, so grab the ref for preventing it
* from being cleaned up during running queue.
*/
percpu_ref_get(&q->q_usage_counter);
__blk_mq_end_request(req, error);
scsi_run_queue_async(sdev);
percpu_ref_put(&q->q_usage_counter);
return false;
}
/**
* scsi_result_to_blk_status - translate a SCSI result code into blk_status_t
* @cmd: SCSI command
* @result: scsi error code
*
* Translate a SCSI result code into a blk_status_t value. May reset the host
* byte of @cmd->result.
*/
static blk_status_t scsi_result_to_blk_status(struct scsi_cmnd *cmd, int result)
{
switch (host_byte(result)) {
case DID_OK:
/*
* Also check the other bytes than the status byte in result
* to handle the case when a SCSI LLD sets result to
* DRIVER_SENSE << 24 without setting SAM_STAT_CHECK_CONDITION.
*/
if (scsi_status_is_good(result) && (result & ~0xff) == 0)
return BLK_STS_OK;
return BLK_STS_IOERR;
case DID_TRANSPORT_FAILFAST:
return BLK_STS_TRANSPORT;
case DID_TARGET_FAILURE:
set_host_byte(cmd, DID_OK);
return BLK_STS_TARGET;
case DID_NEXUS_FAILURE:
set_host_byte(cmd, DID_OK);
return BLK_STS_NEXUS;
case DID_ALLOC_FAILURE:
set_host_byte(cmd, DID_OK);
return BLK_STS_NOSPC;
case DID_MEDIUM_ERROR:
set_host_byte(cmd, DID_OK);
return BLK_STS_MEDIUM;
default:
return BLK_STS_IOERR;
}
}
/* Helper for scsi_io_completion() when "reprep" action required. */
static void scsi_io_completion_reprep(struct scsi_cmnd *cmd,
struct request_queue *q)
{
/* A new command will be prepared and issued. */
scsi_mq_requeue_cmd(cmd);
}
static bool scsi_cmd_runtime_exceeced(struct scsi_cmnd *cmd)
{
struct request *req = cmd->request;
unsigned long wait_for;
if (cmd->allowed == SCSI_CMD_RETRIES_NO_LIMIT)
return false;
wait_for = (cmd->allowed + 1) * req->timeout;
if (time_before(cmd->jiffies_at_alloc + wait_for, jiffies)) {
scmd_printk(KERN_ERR, cmd, "timing out command, waited %lus\n",
wait_for/HZ);
return true;
}
return false;
}
#ifdef MY_ABC_HERE
static inline bool
SynoCmdNeedReport(unsigned char op)
{
return op == READ_6 || op == WRITE_6 ||
op == READ_10 || op == WRITE_10 ||
op == READ_12 || op == WRITE_12 ||
op == READ_16 || op == WRITE_16;
}
static void
SynoScsiErrorCheck(struct scsi_cmnd *scsi_cmd,
struct scsi_sense_hdr *psshdr)
{
sector_t badLba = 0;
if (NULL == scsi_cmd || NULL == scsi_cmd->device
|| NULL == scsi_cmd->sense_buffer || NULL == scsi_cmd->cmnd
|| NULL == psshdr) {
printk("%s:%s(%d) Ivalid scsi_cmd format",
__FILE__, __FUNCTION__, __LINE__);
goto END;
}
if (!SynoCmdNeedReport(scsi_cmd->cmnd[0])) {
goto END;
}
switch (psshdr->sense_key) {
case MEDIUM_ERROR:
/* FALLTHROUGH */
case HARDWARE_ERROR:
if (0 == scsi_get_sense_info_fld(scsi_cmd->sense_buffer,
SCSI_SENSE_BUFFERSIZE, (u64*) &badLba)) {
printk("%s:%s(%d) sense info in sense data invalid\n",
__FILE__, __FUNCTION__, __LINE__);
goto END;
}
SynoScsiErrorWithSenseReport(scsi_cmd->device,
psshdr->sense_key, psshdr->asc, psshdr->ascq, badLba);
break;
default:
// We only report MEDIUM_ERROR and HARDWARE_ERROR
goto END;
}
END:
return;
}
#endif /* MY_ABC_HERE */
#ifdef MY_ABC_HERE
extern unsigned char
syno_is_sector_need_auto_remap(struct gendisk *disk, sector_t lba);
#ifdef MY_ABC_HERE
extern void syno_req_set_bio_auto_remap_flag(struct request *req, sector_t lba);
#endif /* MY_ABC_HERE */
static void
syno_scsi_do_remap_done(struct request *req, blk_status_t status)
{
blk_put_request(req);
}
static unsigned int
syno_scsi_do_remap(struct scsi_cmnd *scsi_cmd, sector_t badLba)
{
unsigned int iRet = -1, iCheck = 0, i = 0;
unsigned int uSectors = 0;
struct request_queue *q = NULL;
struct scsi_request *rq;
u8 lbal = 0;
size_t size = 0;
struct scsi_device *device = NULL;
struct request *req = NULL;
char *buf = NULL, *p = NULL;
if (scsi_cmd == NULL) {
pr_warn("%s:%s(%d) Failed to get scsi_cmd", __FILE__, __func__, __LINE__);
goto OUT;
}
device = scsi_cmd->device;
if (device == NULL) {
pr_warn("%s:%s(%d) Failed to get device", __FILE__, __func__, __LINE__);
goto OUT;
}
q = device->request_queue;
if (q == NULL) {
pr_warn("%s:%s(%d) Failed to get request_queue\n", __FILE__, __func__, __LINE__);
goto OUT;
}
uSectors = queue_physical_block_size(q) / queue_logical_block_size(q);
lbal = (u8)(badLba & 0xff);
lbal = (lbal & (~(uSectors - 1))); // move lbal to first logical block of physical block
size = SYNO_SCSI_SECT_SIZE * uSectors;
req = blk_get_request(q, WRITE, BLK_MQ_REQ_NOWAIT);
if (IS_ERR(req)) {
pr_warn("%s:%s(%d) Failed to get request\n", __FILE__, __func__, __LINE__);
goto ERR;
}
buf = kmalloc(size, GFP_ATOMIC);
if (!buf) {
pr_warn("%s:%s(%d) Failed to allocate remap page memory, so use zero page instead.\n",
__FILE__, __func__, __LINE__);
p = page_address(ZERO_PAGE(0));
} else {
syno_draw_auto_remap_buffer(buf, size);
p = buf;
}
rq = scsi_req(req);
//16 types write
rq->cmd[0] = WRITE_16;
rq->cmd[1] = 0;
// lba
rq->cmd[2] = (u8)((badLba & 0xff00000000000000) >> 56);
rq->cmd[3] = (u8)((badLba & 0xff000000000000) >> 48);
rq->cmd[4] = (u8)((badLba & 0xff0000000000) >> 40);
rq->cmd[5] = (u8)((badLba & 0xff00000000) >> 32);
rq->cmd[6] = (u8)((badLba & 0xff000000) >> 24);
rq->cmd[7] = (u8)((badLba & 0xff0000) >> 16);
rq->cmd[8] = (u8)((badLba & 0xff00) >> 8);
rq->cmd[9] = lbal;
// sector counts
rq->cmd[10] = (u8)((uSectors & 0xff000000) >> 24);
rq->cmd[11] = (u8)((uSectors & 0xff0000) >> 16);
rq->cmd[12] = (u8)((uSectors & 0xff00) >> 8);
rq->cmd[13] = (u8)(uSectors & 0xff);
rq->cmd_len = COMMAND_SIZE(rq->cmd[0]);
req->cmd_flags = REQ_OP_SCSI_OUT;
req->rq_flags |= RQF_QUIET;
req->timeout = 60 * HZ;
rq->retries = 0;
iCheck = blk_rq_map_kern(q, req, p, size, GFP_DMA | GFP_KERNEL);
if (iCheck) {
pr_warn("%s:%s(%d) blk_rq_map_kern return != 0\n",
__FILE__, __func__, __LINE__);
goto ERR;
}
sdev_printk(KERN_WARNING, device, "Insert write command :");
for (i = 0; i < rq->cmd_len; ++i)
pr_warn("%02x ", rq->cmd[i]);
pr_info("\n");
blk_execute_rq_nowait(q, NULL, req, 1, syno_scsi_do_remap_done);
iRet = 0;
goto OUT;
ERR:
if (!IS_ERR(req))
blk_put_request(req);
kfree(buf);
buf = NULL;
OUT:
return iRet;
}
static int
syno_scsi_check_ncq_fake_unc(const u8 *sense_buffer, int iSbLen)
{
int iRet = 0;
const u8 *desc = NULL;
u8 format = 0;
if (iSbLen < 7)
goto OUT;
format = 0x7f & sense_buffer[0];
if (format == 0x72 || format == 0x73) {
desc = scsi_sense_desc_find(sense_buffer, iSbLen, 0 /* info desc */);
if (desc && (desc[1] == 0xa))
iRet = SYNO_NCQ_FAKE_UNC & desc[SYNO_DESCRIPTOR_RESERVED_INDEX];
}
OUT:
return iRet;
}
static unsigned int
syno_scsi_writes_sector(struct scsi_cmnd *scsi_cmd)
{
unsigned int iRet = -1, iCheck = 0;
sector_t badLba = 0;
u8 blIsWrite = 0;
struct gendisk *gd = NULL;
if (scsi_cmd == NULL) {
pr_warn("%s:%s(%d) Failed to get scsi_cmd", __FILE__, __func__, __LINE__);
goto ERR;
}
if (scsi_cmd->request == NULL) {
pr_warn("%s:%s(%d) Failed to get scsi_cmd request\n",
__FILE__, __func__, __LINE__);
goto ERR;
}
if (scsi_cmd->sense_buffer == NULL) {
pr_warn("%s:%s(%d) Failed to get scsi_cmd sense_buffer\n",
__FILE__, __func__, __LINE__);
goto ERR;
}
if (scsi_cmd->cmnd == NULL) {
pr_warn("%s:%s(%d) Failed to get scsi_cmd cmnd\n", __FILE__, __func__, __LINE__);
goto ERR;
}
gd = scsi_cmd->request->rq_disk;
if (!gd) {
pr_warn("%s:%s(%d) Failed to get general disk\n", __FILE__, __func__, __LINE__);
goto ERR;
}
iCheck = scsi_get_sense_info_fld(scsi_cmd->sense_buffer,
SCSI_SENSE_BUFFERSIZE,
(u64 *) &badLba);
if (!iCheck) {
pr_warn("%s:%s(%d) sense info in sense data invalid\n",
__FILE__, __func__, __LINE__);
goto ERR;
}
if (syno_scsi_check_ncq_fake_unc(scsi_cmd->sense_buffer, SCSI_SENSE_BUFFERSIZE)) {
scmd_printk(KERN_INFO, scsi_cmd, "UNC ERROR code but NCQ abort, do NOT remap");
goto ERR;
}
switch (scsi_cmd->cmnd[0]) {
case WRITE_6:
case WRITE_10:
case WRITE_12:
case WRITE_16:
case WRITE_32:
blIsWrite = 1;
break;
default:
if (scsi_cmd->sc_data_direction == DMA_TO_DEVICE)
blIsWrite = 1;
}
scmd_printk(KERN_INFO, scsi_cmd, "%s unc at %llu\n",
(blIsWrite) ? "write" : "read",
(unsigned long long)badLba);
if (!blIsWrite && !syno_is_sector_need_auto_remap(gd, badLba))
goto ERR;
#ifdef MY_ABC_HERE
// only report auto-remap in read
if (!blIsWrite)
syno_req_set_bio_auto_remap_flag(scsi_cmd->request, badLba);
#endif /* MY_ABC_HERE */
syno_scsi_do_remap(scsi_cmd, badLba);
iRet = 0;
ERR:
return iRet;
}
#endif /* MY_ABC_HERE */
/* Helper for scsi_io_completion() when special action required. */
static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
{
struct request_queue *q = cmd->device->request_queue;
struct request *req = cmd->request;
int level = 0;
enum {ACTION_FAIL, ACTION_REPREP, ACTION_RETRY,
ACTION_DELAYED_RETRY} action;
struct scsi_sense_hdr sshdr;
bool sense_valid;
bool sense_current = true; /* false implies "deferred sense" */
blk_status_t blk_stat;
sense_valid = scsi_command_normalize_sense(cmd, &sshdr);
if (sense_valid)
sense_current = !scsi_sense_is_deferred(&sshdr);
blk_stat = scsi_result_to_blk_status(cmd, result);
#ifdef CONFIG_SYNO_SAS_SPINUP_DELAY_DEBUG
if (0x1b == cmd->cmnd[0]) {
sdev_printk(KERN_ERR, cmd->device,
"START_STOP done - tag %02x %s - %02x %02x %02x %02x %02x %02x\n",
cmd->tag, (cmd->cmnd[4]&0x01)?"START":"STOP ",
cmd->cmnd[0], cmd->cmnd[1], cmd->cmnd[2],
cmd->cmnd[3], cmd->cmnd[4], cmd->cmnd[5]);
}
#endif /* CONFIG_SYNO_SAS_SPINUP_DELAY_DEBUG */
if (host_byte(result) == DID_RESET) {
/* Third party bus reset or reset for error recovery
* reasons. Just retry the command and see what
* happens.
*/
action = ACTION_RETRY;
} else if (sense_valid && sense_current) {
switch (sshdr.sense_key) {
case UNIT_ATTENTION:
if (cmd->device->removable) {
/* Detected disc change. Set a bit
* and quietly refuse further access.
*/
cmd->device->changed = 1;
action = ACTION_FAIL;
} else {
/* Must have been a power glitch, or a
* bus reset. Could not have been a
* media change, so we just retry the
* command and see what happens.
*/
action = ACTION_RETRY;
}
break;
case ILLEGAL_REQUEST:
/* If we had an ILLEGAL REQUEST returned, then
* we may have performed an unsupported
* command. The only thing this should be
* would be a ten byte read where only a six
* byte read was supported. Also, on a system
* where READ CAPACITY failed, we may have
* read past the end of the disk.
*/
if ((cmd->device->use_10_for_rw &&
sshdr.asc == 0x20 && sshdr.ascq == 0x00) &&
(cmd->cmnd[0] == READ_10 ||
cmd->cmnd[0] == WRITE_10)) {
/* This will issue a new 6-byte command. */
cmd->device->use_10_for_rw = 0;
action = ACTION_REPREP;
} else if (sshdr.asc == 0x10) /* DIX */ {
action = ACTION_FAIL;
blk_stat = BLK_STS_PROTECTION;
/* INVALID COMMAND OPCODE or INVALID FIELD IN CDB */
} else if (sshdr.asc == 0x20 || sshdr.asc == 0x24) {
action = ACTION_FAIL;
blk_stat = BLK_STS_TARGET;
} else
action = ACTION_FAIL;
break;
case ABORTED_COMMAND:
action = ACTION_FAIL;
if (sshdr.asc == 0x10) /* DIF */
blk_stat = BLK_STS_PROTECTION;
break;
case NOT_READY:
/* If the device is in the process of becoming
* ready, or has a temporary blockage, retry.
*/
if (sshdr.asc == 0x04) {
switch (sshdr.ascq) {
#ifdef MY_DEF_HERE
case 0x02: /* INITIALIZING COMMAND REQUIRED */
action = ACTION_FAIL;
if ((cmd->cmnd[0] != TEST_UNIT_READY) && (cmd->cmnd[0] != REQUEST_SENSE)) {
/*
* Leave TUR & REQUEST_SENSE results untouched for upper layers
* Only spin up on read/write commands
*/
if (cmd->device->spinup_queue) {
SynoSpinupDisk(cmd->device);
action = ACTION_DELAYED_RETRY;
}
}
break;
#endif /* MY_DEF_HERE */
case 0x01: /* becoming ready */
case 0x04: /* format in progress */
case 0x05: /* rebuild in progress */
case 0x06: /* recalculation in progress */
case 0x07: /* operation in progress */
case 0x08: /* Long write in progress */
case 0x09: /* self test in progress */
case 0x11: /* notify (enable spinup) required */
case 0x14: /* space allocation in progress */
case 0x1a: /* start stop unit in progress */
case 0x1b: /* sanitize in progress */
case 0x1d: /* configuration in progress */
case 0x24: /* depopulation in progress */
action = ACTION_DELAYED_RETRY;
break;
default:
action = ACTION_FAIL;
break;
}
} else
action = ACTION_FAIL;
break;
case VOLUME_OVERFLOW:
/* See SSC3rXX or current. */
action = ACTION_FAIL;
break;
#ifdef MY_ABC_HERE
case MEDIUM_ERROR:
switch (sshdr.asc) {
case 0x11:
switch (sshdr.ascq) {
case 0x00:
case 0x04:
case 0x14:
syno_scsi_writes_sector(cmd);
action = ACTION_FAIL;
break;
default:
action = ACTION_FAIL;
break;
}
break;
default:
action = ACTION_FAIL;
break;
}
break;
#endif /* MY_ABC_HERE */
case DATA_PROTECT:
action = ACTION_FAIL;
if ((sshdr.asc == 0x0C && sshdr.ascq == 0x12) ||
(sshdr.asc == 0x55 &&
(sshdr.ascq == 0x0E || sshdr.ascq == 0x0F))) {
/* Insufficient zone resources */
blk_stat = BLK_STS_ZONE_OPEN_RESOURCE;
}
break;
default:
action = ACTION_FAIL;
break;
}
#ifdef MY_ABC_HERE
SynoScsiErrorCheck(cmd, &sshdr);
#endif /* MY_ABC_HERE */
} else
action = ACTION_FAIL;
if (action != ACTION_FAIL && scsi_cmd_runtime_exceeced(cmd))
action = ACTION_FAIL;
switch (action) {
case ACTION_FAIL:
/* Give up and fail the remainder of the request */
if (!(req->rq_flags & RQF_QUIET)) {
static DEFINE_RATELIMIT_STATE(_rs,
DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
if (unlikely(scsi_logging_level))
level =
SCSI_LOG_LEVEL(SCSI_LOG_MLCOMPLETE_SHIFT,
SCSI_LOG_MLCOMPLETE_BITS);
/*
* if logging is enabled the failure will be printed
* in scsi_log_completion(), so avoid duplicate messages
*/
if (!level && __ratelimit(&_rs)) {
scsi_print_result(cmd, NULL, FAILED);
if (driver_byte(result) == DRIVER_SENSE)
scsi_print_sense(cmd);
scsi_print_command(cmd);
}
}
if (!scsi_end_request(req, blk_stat, blk_rq_err_bytes(req)))
return;
fallthrough;
case ACTION_REPREP:
scsi_io_completion_reprep(cmd, q);
break;
case ACTION_RETRY:
/* Retry the same command immediately */
__scsi_queue_insert(cmd, SCSI_MLQUEUE_EH_RETRY, false);
break;
case ACTION_DELAYED_RETRY:
/* Retry the same command after a delay */
__scsi_queue_insert(cmd, SCSI_MLQUEUE_DEVICE_BUSY, false);
break;
}
}
/*
* Helper for scsi_io_completion() when cmd->result is non-zero. Returns a
* new result that may suppress further error checking. Also modifies
* *blk_statp in some cases.
*/
static int scsi_io_completion_nz_result(struct scsi_cmnd *cmd, int result,
blk_status_t *blk_statp)
{
bool sense_valid;
bool sense_current = true; /* false implies "deferred sense" */
struct request *req = cmd->request;
struct scsi_sense_hdr sshdr;
sense_valid = scsi_command_normalize_sense(cmd, &sshdr);
if (sense_valid)
sense_current = !scsi_sense_is_deferred(&sshdr);
if (blk_rq_is_passthrough(req)) {
if (sense_valid) {
/*
* SG_IO wants current and deferred errors
*/
scsi_req(req)->sense_len =
min(8 + cmd->sense_buffer[7],
SCSI_SENSE_BUFFERSIZE);
}
if (sense_current)
*blk_statp = scsi_result_to_blk_status(cmd, result);
} else if (blk_rq_bytes(req) == 0 && sense_current) {
/*
* Flush commands do not transfers any data, and thus cannot use
* good_bytes != blk_rq_bytes(req) as the signal for an error.
* This sets *blk_statp explicitly for the problem case.
*/
*blk_statp = scsi_result_to_blk_status(cmd, result);
}
/*
* Recovered errors need reporting, but they're always treated as
* success, so fiddle the result code here. For passthrough requests
* we already took a copy of the original into sreq->result which
* is what gets returned to the user
*/
if (sense_valid && (sshdr.sense_key == RECOVERED_ERROR)) {
bool do_print = true;
/*
* if ATA PASS-THROUGH INFORMATION AVAILABLE [0x0, 0x1d]
* skip print since caller wants ATA registers. Only occurs
* on SCSI ATA PASS_THROUGH commands when CK_COND=1
*/
if ((sshdr.asc == 0x0) && (sshdr.ascq == 0x1d))
do_print = false;
else if (req->rq_flags & RQF_QUIET)
do_print = false;
if (do_print)
scsi_print_sense(cmd);
result = 0;
/* for passthrough, *blk_statp may be set */
*blk_statp = BLK_STS_OK;
}
/*
* Another corner case: the SCSI status byte is non-zero but 'good'.
* Example: PRE-FETCH command returns SAM_STAT_CONDITION_MET when
* it is able to fit nominated LBs in its cache (and SAM_STAT_GOOD
* if it can't fit). Treat SAM_STAT_CONDITION_MET and the related
* intermediate statuses (both obsolete in SAM-4) as good.
*/
if (status_byte(result) && scsi_status_is_good(result)) {
result = 0;
*blk_statp = BLK_STS_OK;
}
return result;
}
/**
* scsi_io_completion - Completion processing for SCSI commands.
* @cmd: command that is finished.
* @good_bytes: number of processed bytes.
*
* We will finish off the specified number of sectors. If we are done, the
* command block will be released and the queue function will be goosed. If we
* are not done then we have to figure out what to do next:
*
* a) We can call scsi_io_completion_reprep(). The request will be
* unprepared and put back on the queue. Then a new command will
* be created for it. This should be used if we made forward
* progress, or if we want to switch from READ(10) to READ(6) for
* example.
*
* b) We can call scsi_io_completion_action(). The request will be
* put back on the queue and retried using the same command as
* before, possibly after a delay.
*
* c) We can call scsi_end_request() with blk_stat other than
* BLK_STS_OK, to fail the remainder of the request.
*/
void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
{
int result = cmd->result;
struct request_queue *q = cmd->device->request_queue;
struct request *req = cmd->request;
blk_status_t blk_stat = BLK_STS_OK;
if (unlikely(result)) /* a nz result may or may not be an error */
result = scsi_io_completion_nz_result(cmd, result, &blk_stat);
if (unlikely(blk_rq_is_passthrough(req))) {
/*
* scsi_result_to_blk_status may have reset the host_byte
*/
scsi_req(req)->result = cmd->result;
}
/*
* Next deal with any sectors which we were able to correctly
* handle.
*/
SCSI_LOG_HLCOMPLETE(1, scmd_printk(KERN_INFO, cmd,
"%u sectors total, %d bytes done.\n",
blk_rq_sectors(req), good_bytes));
/*
* Failed, zero length commands always need to drop down
* to retry code. Fast path should return in this block.
*/
if (likely(blk_rq_bytes(req) > 0 || blk_stat == BLK_STS_OK)) {
if (likely(!scsi_end_request(req, blk_stat, good_bytes)))
return; /* no bytes remaining */
}
/* Kill remainder if no retries. */
if (unlikely(blk_stat && scsi_noretry_cmd(cmd))) {
if (scsi_end_request(req, blk_stat, blk_rq_bytes(req)))
WARN_ONCE(true,
"Bytes remaining after failed, no-retry command");
return;
}
/*
* If there had been no error, but we have leftover bytes in the
* requeues just queue the command up again.
*/
if (likely(result == 0))
scsi_io_completion_reprep(cmd, q);
else
scsi_io_completion_action(cmd, result);
}
static inline bool scsi_cmd_needs_dma_drain(struct scsi_device *sdev,
struct request *rq)
{
return sdev->dma_drain_len && blk_rq_is_passthrough(rq) &&
!op_is_write(req_op(rq)) &&
sdev->host->hostt->dma_need_drain(rq);
}
/**
* scsi_alloc_sgtables - allocate S/G tables for a command
* @cmd: command descriptor we wish to initialize
*
* Returns:
* * BLK_STS_OK - on success
* * BLK_STS_RESOURCE - if the failure is retryable
* * BLK_STS_IOERR - if the failure is fatal
*/
blk_status_t scsi_alloc_sgtables(struct scsi_cmnd *cmd)
{
struct scsi_device *sdev = cmd->device;
struct request *rq = cmd->request;
unsigned short nr_segs = blk_rq_nr_phys_segments(rq);
struct scatterlist *last_sg = NULL;
blk_status_t ret;
bool need_drain = scsi_cmd_needs_dma_drain(sdev, rq);
int count;
if (WARN_ON_ONCE(!nr_segs))
return BLK_STS_IOERR;
/*
* Make sure there is space for the drain. The driver must adjust
* max_hw_segments to be prepared for this.
*/
if (need_drain)
nr_segs++;
/*
* If sg table allocation fails, requeue request later.
*/
if (unlikely(sg_alloc_table_chained(&cmd->sdb.table, nr_segs,
cmd->sdb.table.sgl, SCSI_INLINE_SG_CNT)))
return BLK_STS_RESOURCE;
/*
* Next, walk the list, and fill in the addresses and sizes of
* each segment.
*/
count = __blk_rq_map_sg(rq->q, rq, cmd->sdb.table.sgl, &last_sg);
if (blk_rq_bytes(rq) & rq->q->dma_pad_mask) {
unsigned int pad_len =
(rq->q->dma_pad_mask & ~blk_rq_bytes(rq)) + 1;
last_sg->length += pad_len;
cmd->extra_len += pad_len;
}
if (need_drain) {
sg_unmark_end(last_sg);
last_sg = sg_next(last_sg);
sg_set_buf(last_sg, sdev->dma_drain_buf, sdev->dma_drain_len);
sg_mark_end(last_sg);
cmd->extra_len += sdev->dma_drain_len;
count++;
}
BUG_ON(count > cmd->sdb.table.nents);
cmd->sdb.table.nents = count;
cmd->sdb.length = blk_rq_payload_bytes(rq);
if (blk_integrity_rq(rq)) {
struct scsi_data_buffer *prot_sdb = cmd->prot_sdb;
int ivecs;
if (WARN_ON_ONCE(!prot_sdb)) {
/*
* This can happen if someone (e.g. multipath)
* queues a command to a device on an adapter
* that does not support DIX.
*/
ret = BLK_STS_IOERR;
goto out_free_sgtables;
}
ivecs = blk_rq_count_integrity_sg(rq->q, rq->bio);
if (sg_alloc_table_chained(&prot_sdb->table, ivecs,
prot_sdb->table.sgl,
SCSI_INLINE_PROT_SG_CNT)) {
ret = BLK_STS_RESOURCE;
goto out_free_sgtables;
}
count = blk_rq_map_integrity_sg(rq->q, rq->bio,
prot_sdb->table.sgl);
BUG_ON(count > ivecs);
BUG_ON(count > queue_max_integrity_segments(rq->q));
cmd->prot_sdb = prot_sdb;
cmd->prot_sdb->table.nents = count;
}
return BLK_STS_OK;
out_free_sgtables:
scsi_free_sgtables(cmd);
return ret;
}
EXPORT_SYMBOL(scsi_alloc_sgtables);
/**
* scsi_initialize_rq - initialize struct scsi_cmnd partially
* @rq: Request associated with the SCSI command to be initialized.
*
* This function initializes the members of struct scsi_cmnd that must be
* initialized before request processing starts and that won't be
* reinitialized if a SCSI command is requeued.
*
* Called from inside blk_get_request() for pass-through requests and from
* inside scsi_init_command() for filesystem requests.
*/
static void scsi_initialize_rq(struct request *rq)
{
struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
scsi_req_init(&cmd->req);
init_rcu_head(&cmd->rcu);
cmd->jiffies_at_alloc = jiffies;
cmd->retries = 0;
}
/*
* Only called when the request isn't completed by SCSI, and not freed by
* SCSI
*/
static void scsi_cleanup_rq(struct request *rq)
{
if (rq->rq_flags & RQF_DONTPREP) {
scsi_mq_uninit_cmd(blk_mq_rq_to_pdu(rq));
rq->rq_flags &= ~RQF_DONTPREP;
}
}
/* Called before a request is prepared. See also scsi_mq_prep_fn(). */
void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd)
{
void *buf = cmd->sense_buffer;
void *prot = cmd->prot_sdb;
struct request *rq = blk_mq_rq_from_pdu(cmd);
unsigned int flags = cmd->flags & SCMD_PRESERVED_FLAGS;
unsigned long jiffies_at_alloc;
int retries, to_clear;
bool in_flight;
if (!blk_rq_is_scsi(rq) && !(flags & SCMD_INITIALIZED)) {
flags |= SCMD_INITIALIZED;
scsi_initialize_rq(rq);
}
jiffies_at_alloc = cmd->jiffies_at_alloc;
retries = cmd->retries;
in_flight = test_bit(SCMD_STATE_INFLIGHT, &cmd->state);
/*
* Zero out the cmd, except for the embedded scsi_request. Only clear
* the driver-private command data if the LLD does not supply a
* function to initialize that data.
*/
to_clear = sizeof(*cmd) - sizeof(cmd->req);
if (!dev->host->hostt->init_cmd_priv)
to_clear += dev->host->hostt->cmd_size;
memset((char *)cmd + sizeof(cmd->req), 0, to_clear);
cmd->device = dev;
cmd->sense_buffer = buf;
cmd->prot_sdb = prot;
cmd->flags = flags;
INIT_DELAYED_WORK(&cmd->abort_work, scmd_eh_abort_handler);
cmd->jiffies_at_alloc = jiffies_at_alloc;
cmd->retries = retries;
if (in_flight)
__set_bit(SCMD_STATE_INFLIGHT, &cmd->state);
}
static blk_status_t scsi_setup_scsi_cmnd(struct scsi_device *sdev,
struct request *req)
{
struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
/*
* Passthrough requests may transfer data, in which case they must
* a bio attached to them. Or they might contain a SCSI command
* that does not transfer data, in which case they may optionally
* submit a request without an attached bio.
*/
if (req->bio) {
blk_status_t ret = scsi_alloc_sgtables(cmd);
if (unlikely(ret != BLK_STS_OK))
return ret;
} else {
BUG_ON(blk_rq_bytes(req));
memset(&cmd->sdb, 0, sizeof(cmd->sdb));
}
cmd->cmd_len = scsi_req(req)->cmd_len;
if (cmd->cmd_len == 0)
cmd->cmd_len = scsi_command_size(cmd->cmnd);
cmd->cmnd = scsi_req(req)->cmd;
cmd->transfersize = blk_rq_bytes(req);
cmd->allowed = scsi_req(req)->retries;
return BLK_STS_OK;
}
static blk_status_t
scsi_device_state_check(struct scsi_device *sdev, struct request *req)
{
switch (sdev->sdev_state) {
case SDEV_CREATED:
return BLK_STS_OK;
case SDEV_OFFLINE:
case SDEV_TRANSPORT_OFFLINE:
/*
* If the device is offline we refuse to process any
* commands. The device must be brought online
* before trying any recovery commands.
*/
if (!sdev->offline_already) {
sdev->offline_already = true;
sdev_printk(KERN_ERR, sdev,
"rejecting I/O to offline device\n");
}
return BLK_STS_IOERR;
case SDEV_DEL:
/*
* If the device is fully deleted, we refuse to
* process any commands as well.
*/
sdev_printk(KERN_ERR, sdev,
"rejecting I/O to dead device\n");
return BLK_STS_IOERR;
case SDEV_BLOCK:
case SDEV_CREATED_BLOCK:
return BLK_STS_RESOURCE;
case SDEV_QUIESCE:
/*
* If the device is blocked we only accept power management
* commands.
*/
if (req && WARN_ON_ONCE(!(req->rq_flags & RQF_PM)))
return BLK_STS_RESOURCE;
return BLK_STS_OK;
default:
/*
* For any other not fully online state we only allow
* power management commands.
*/
if (req && !(req->rq_flags & RQF_PM))
return BLK_STS_IOERR;
return BLK_STS_OK;
}
}
/*
* scsi_dev_queue_ready: if we can send requests to sdev, return 1 else
* return 0.
*
* Called with the queue_lock held.
*/
static inline int scsi_dev_queue_ready(struct request_queue *q,
struct scsi_device *sdev)
{
unsigned int busy;
busy = atomic_inc_return(&sdev->device_busy) - 1;
if (atomic_read(&sdev->device_blocked)) {
if (busy)
goto out_dec;
/*
* unblock after device_blocked iterates to zero
*/
if (atomic_dec_return(&sdev->device_blocked) > 0)
goto out_dec;
SCSI_LOG_MLQUEUE(3, sdev_printk(KERN_INFO, sdev,
"unblocking device at zero depth\n"));
}
if (busy >= sdev->queue_depth)
goto out_dec;
return 1;
out_dec:
atomic_dec(&sdev->device_busy);
return 0;
}
/*
* scsi_target_queue_ready: checks if there we can send commands to target
* @sdev: scsi device on starget to check.
*/
static inline int scsi_target_queue_ready(struct Scsi_Host *shost,
struct scsi_device *sdev)
{
struct scsi_target *starget = scsi_target(sdev);
unsigned int busy;
if (starget->single_lun) {
spin_lock_irq(shost->host_lock);
if (starget->starget_sdev_user &&
starget->starget_sdev_user != sdev) {
spin_unlock_irq(shost->host_lock);
return 0;
}
starget->starget_sdev_user = sdev;
spin_unlock_irq(shost->host_lock);
}
if (starget->can_queue <= 0)
return 1;
busy = atomic_inc_return(&starget->target_busy) - 1;
if (atomic_read(&starget->target_blocked) > 0) {
if (busy)
goto starved;
/*
* unblock after target_blocked iterates to zero
*/
if (atomic_dec_return(&starget->target_blocked) > 0)
goto out_dec;
SCSI_LOG_MLQUEUE(3, starget_printk(KERN_INFO, starget,
"unblocking target at zero depth\n"));
}
if (busy >= starget->can_queue)
goto starved;
return 1;
starved:
spin_lock_irq(shost->host_lock);
list_move_tail(&sdev->starved_entry, &shost->starved_list);
spin_unlock_irq(shost->host_lock);
out_dec:
if (starget->can_queue > 0)
atomic_dec(&starget->target_busy);
return 0;
}
/*
* scsi_host_queue_ready: if we can send requests to shost, return 1 else
* return 0. We must end up running the queue again whenever 0 is
* returned, else IO can hang.
*/
static inline int scsi_host_queue_ready(struct request_queue *q,
struct Scsi_Host *shost,
struct scsi_device *sdev,
struct scsi_cmnd *cmd)
{
if (scsi_host_in_recovery(shost))
return 0;
if (atomic_read(&shost->host_blocked) > 0) {
if (scsi_host_busy(shost) > 0)
goto starved;
/*
* unblock after host_blocked iterates to zero
*/
if (atomic_dec_return(&shost->host_blocked) > 0)
goto out_dec;
SCSI_LOG_MLQUEUE(3,
shost_printk(KERN_INFO, shost,
"unblocking host at zero depth\n"));
}
if (shost->host_self_blocked)
goto starved;
/* We're OK to process the command, so we can't be starved */
if (!list_empty(&sdev->starved_entry)) {
spin_lock_irq(shost->host_lock);
if (!list_empty(&sdev->starved_entry))
list_del_init(&sdev->starved_entry);
spin_unlock_irq(shost->host_lock);
}
__set_bit(SCMD_STATE_INFLIGHT, &cmd->state);
return 1;
starved:
spin_lock_irq(shost->host_lock);
if (list_empty(&sdev->starved_entry))
list_add_tail(&sdev->starved_entry, &shost->starved_list);
spin_unlock_irq(shost->host_lock);
out_dec:
scsi_dec_host_busy(shost, cmd);
return 0;
}
/*
* Busy state exporting function for request stacking drivers.
*
* For efficiency, no lock is taken to check the busy state of
* shost/starget/sdev, since the returned value is not guaranteed and
* may be changed after request stacking drivers call the function,
* regardless of taking lock or not.
*
* When scsi can't dispatch I/Os anymore and needs to kill I/Os scsi
* needs to return 'not busy'. Otherwise, request stacking drivers
* may hold requests forever.
*/
static bool scsi_mq_lld_busy(struct request_queue *q)
{
struct scsi_device *sdev = q->queuedata;
struct Scsi_Host *shost;
if (blk_queue_dying(q))
return false;
shost = sdev->host;
/*
* Ignore host/starget busy state.
* Since block layer does not have a concept of fairness across
* multiple queues, congestion of host/starget needs to be handled
* in SCSI layer.
*/
if (scsi_host_in_recovery(shost) || scsi_device_is_busy(sdev))
return true;
return false;
}
static void scsi_softirq_done(struct request *rq)
{
struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
int disposition;
INIT_LIST_HEAD(&cmd->eh_entry);
atomic_inc(&cmd->device->iodone_cnt);
if (cmd->result)
atomic_inc(&cmd->device->ioerr_cnt);
disposition = scsi_decide_disposition(cmd);
if (disposition != SUCCESS && scsi_cmd_runtime_exceeced(cmd))
disposition = SUCCESS;
scsi_log_completion(cmd, disposition);
switch (disposition) {
case SUCCESS:
scsi_finish_command(cmd);
break;
case NEEDS_RETRY:
scsi_queue_insert(cmd, SCSI_MLQUEUE_EH_RETRY);
break;
case ADD_TO_MLQUEUE:
scsi_queue_insert(cmd, SCSI_MLQUEUE_DEVICE_BUSY);
break;
default:
scsi_eh_scmd_add(cmd);
break;
}
}
#ifdef MY_DEF_HERE
extern int g_is_sas_model;
static int scsi_white_list_cmd_in_hibernation(struct scsi_cmnd *cmd)
{
int ret = 0;
switch (cmd->cmnd[0]) {
/* Only spin up on read/write commands */
case TEST_UNIT_READY:
case REQUEST_SENSE:
case START_STOP:
/*sas standby cmd*/
ret = 1;
break;
case ATA_16:
/*ata passthrough standby immediate*/
if (g_is_sas_model && (0xe0 == cmd->cmnd[14])) {
ret = 1;
}
break;
default:
break;
}
return ret;
}
#endif /* MY_DEF_HERE */
#ifdef MY_ABC_HERE
static int cmd_in_ignore_list(struct scsi_cmnd *cmd)
{
#ifdef MY_ABC_HERE
/* Ignore EUnit control command */
if (cmd->device->spindown && ATA_16 == cmd->cmnd[0] &&
(ATA_CMD_PMP_WRITE == cmd->cmnd[14] || ATA_CMD_PMP_READ == cmd->cmnd[14])) {
return 1;
}
#endif /* MY_ABC_HERE */
/* this is for SATA disk only, in SATA disk, we don't know which command to wake up disk
* so we need spindown to help us to remember whichever disk is sleeping
* So if disk is sleeping, then we assume any command will wake up this disk, and update the idle time */
if (cmd->device->spindown && TEST_UNIT_READY != cmd->cmnd[0]) {
cmd->device->spindown = 0;
if (0 == cmd->device->do_standby_syncing) {
return 0;
}
}
/* generally, we should assume all commands should wake up disk and idle time should be reset,
* but we need to check smart(0x0C & ATA_16) in scemd loop and sync cache before call disk to sleep
* so we must skip these commands here, and we also skip TEST_UNIT_READY, LOG_SENSE, and START_STOP for SAS disks */
/* mvSata */
if (0x0C == cmd->cmnd[0]) {
struct scatterlist *sg;
unsigned char* pBuffer;
if (cmd->sdb.table.nents) {
sg = (struct scatterlist *)cmd->sdb.table.sgl;
pBuffer = kmap_atomic(sg_page(sg)) + sg->offset;
} else {
pBuffer = (char *)cmd->sdb.table.sgl;
}
/* set disk to standby command */
if (0xE0 == pBuffer[0]) {
cmd->device->spindown = 1;
}
if (cmd->sdb.table.nents) {
kunmap_atomic(pBuffer - sg->offset);
}
} else if (ATA_16 == cmd->cmnd[0]) {
/* set disk to standby command */
if (0xE0 == cmd->cmnd[14]) {
cmd->device->spindown = 1;
}
} else if (START_STOP == cmd->cmnd[0]) {
if (0x01 == cmd->cmnd[4]) {
// start disks
if (0 == cmd->device->do_standby_syncing) {
return 0;
}
}
} else if (LOG_SENSE != cmd->cmnd[0] &&
TEST_UNIT_READY != cmd->cmnd[0] &&
SYNCHRONIZE_CACHE != cmd->cmnd[0]) {
if (0 == cmd->device->do_standby_syncing) {
return 0;
}
}
return 1;
}
#endif /* MY_ABC_HERE */
/**
* scsi_dispatch_command - Dispatch a command to the low-level driver.
* @cmd: command block we are dispatching.
*
* Return: nonzero return request was rejected and device's queue needs to be
* plugged.
*/
static int scsi_dispatch_cmd(struct scsi_cmnd *cmd)
{
struct Scsi_Host *host = cmd->device->host;
int rtn = 0;
#ifdef MY_ABC_HERE
unsigned long ulflags;
struct Scsi_Host *pMaster_host = NULL;
#endif /* MY_ABC_HERE */
atomic_inc(&cmd->device->iorequest_cnt);
/* check if the device is still usable */
if (unlikely(cmd->device->sdev_state == SDEV_DEL)) {
/* in SDEV_DEL we error all commands. DID_NO_CONNECT
* returns an immediate error upwards, and signals
* that the device is no longer present */
cmd->result = DID_NO_CONNECT << 16;
goto done;
}
/* Check to see if the scsi lld made this device blocked. */
if (unlikely(scsi_device_blocked(cmd->device))) {
/*
* in blocked state, the command is just put back on
* the device queue. The suspend state has already
* blocked the queue so future requests should not
* occur until the device transitions out of the
* suspend state.
*/
SCSI_LOG_MLQUEUE(3, scmd_printk(KERN_INFO, cmd,
"queuecommand : device blocked\n"));
return SCSI_MLQUEUE_DEVICE_BUSY;
}
#ifdef MY_DEF_HERE
if (g_is_sas_model && (SYNO_PORT_TYPE_SAS == cmd->device->host->hostt->syno_port_type)) {
if ((START_STOP == cmd->cmnd[0] && (0 == (cmd->cmnd[4] & 0x01)))/*sas standby cmd*/ ||
((ATA_16 == cmd->cmnd[0]) && (0xe0 == cmd->cmnd[14]))/*ata passthrough standby immediate*/) {
set_bit(0, &cmd->device->sas_sata_standby_flag);
}
if (test_bit(0, &cmd->device->sas_sata_standby_flag) && !scsi_white_list_cmd_in_hibernation(cmd)) {
SynoSpinupDisk(cmd->device);
return SCSI_MLQUEUE_DEVICE_BUSY;
}
}
#endif /* MY_DEF_HERE */
/* Store the LUN value in cmnd, if needed. */
if (cmd->device->lun_in_cdb)
cmd->cmnd[1] = (cmd->cmnd[1] & 0x1f) |
(cmd->device->lun << 5 & 0xe0);
scsi_log_send(cmd);
/*
* Before we queue this command, check if the command
* length exceeds what the host adapter can handle.
*/
if (cmd->cmd_len > cmd->device->host->max_cmd_len) {
SCSI_LOG_MLQUEUE(3, scmd_printk(KERN_INFO, cmd,
"queuecommand : command too long. "
"cdb_size=%d host->max_cmd_len=%d\n",
cmd->cmd_len, cmd->device->host->max_cmd_len));
cmd->result = (DID_ABORT << 16);
goto done;
}
if (unlikely(host->shost_state == SHOST_DEL)) {
cmd->result = (DID_NO_CONNECT << 16);
goto done;
}
#ifdef MY_ABC_HERE
/*
* Power on eunit from deep sleep will fail after another ata command is dispatched,
* so NO ata commands sent to the same eunit can be further dispatched until error handler is done.
*/
if (host->transportt->is_eunit_deepsleep && host->is_eunit_deepsleep && host->eunit_lock_configured){
spin_lock_irqsave(host->peunit_poweron_lock, ulflags);
if (*(host->puiata_eh_flag)) {
spin_unlock_irqrestore(host->peunit_poweron_lock, ulflags);
return SCSI_MLQUEUE_HOST_BUSY;
}
(*(host->puiata_eh_flag)) ++;
spin_unlock_irqrestore(host->peunit_poweron_lock, ulflags);
if ((pMaster_host = host->transportt->is_eunit_deepsleep(host))) {
/* Need to power on and reset the port by EH. */
scsi_schedule_eh(host);
}
(*(host->puiata_eh_flag)) --;
}
#endif /* MY_ABC_HERE */
#ifdef CONFIG_SYNO_SAS_SPINUP_DELAY_DEBUG
/* print out START_STOP commands */
if (0x1b == cmd->cmnd[0]) {
sdev_printk(KERN_ERR, cmd->device,
"START_STOP run - tag %02x %s - %02x %02x %02x %02x %02x %02x\n",
cmd->tag, (cmd->cmnd[4]&0x01)?"START":"STOP ",
cmd->cmnd[0], cmd->cmnd[1], cmd->cmnd[2],
cmd->cmnd[3], cmd->cmnd[4], cmd->cmnd[5]);
}
#endif /* CONFIG_SYNO_SAS_SPINUP_DELAY_DEBUG */
#ifdef MY_ABC_HERE
if(cmd_in_ignore_list(cmd)){
goto IGNORE;
}
#endif /* MY_ABC_HERE */
#ifdef MY_ABC_HERE
cmd->device->last_accessed = jiffies;
#endif /* MY_ABC_HERE */
#ifdef MY_ABC_HERE
IGNORE:
#endif /* MY_ABC_HERE */
trace_scsi_dispatch_cmd_start(cmd);
rtn = host->hostt->queuecommand(host, cmd);
if (rtn) {
trace_scsi_dispatch_cmd_error(cmd, rtn);
if (rtn != SCSI_MLQUEUE_DEVICE_BUSY &&
rtn != SCSI_MLQUEUE_TARGET_BUSY)
rtn = SCSI_MLQUEUE_HOST_BUSY;
SCSI_LOG_MLQUEUE(3, scmd_printk(KERN_INFO, cmd,
"queuecommand : request rejected\n"));
}
return rtn;
done:
cmd->scsi_done(cmd);
return 0;
}
/* Size in bytes of the sg-list stored in the scsi-mq command-private data. */
static unsigned int scsi_mq_inline_sgl_size(struct Scsi_Host *shost)
{
return min_t(unsigned int, shost->sg_tablesize, SCSI_INLINE_SG_CNT) *
sizeof(struct scatterlist);
}
static blk_status_t scsi_prepare_cmd(struct request *req)
{
struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
struct scsi_device *sdev = req->q->queuedata;
struct Scsi_Host *shost = sdev->host;
struct scatterlist *sg;
scsi_init_command(sdev, cmd);
cmd->request = req;
cmd->tag = req->tag;
cmd->prot_op = SCSI_PROT_NORMAL;
if (blk_rq_bytes(req))
cmd->sc_data_direction = rq_dma_dir(req);
else
cmd->sc_data_direction = DMA_NONE;
sg = (void *)cmd + sizeof(struct scsi_cmnd) + shost->hostt->cmd_size;
cmd->sdb.table.sgl = sg;
if (scsi_host_get_prot(shost)) {
memset(cmd->prot_sdb, 0, sizeof(struct scsi_data_buffer));
cmd->prot_sdb->table.sgl =
(struct scatterlist *)(cmd->prot_sdb + 1);
}
/*
* Special handling for passthrough commands, which don't go to the ULP
* at all:
*/
if (blk_rq_is_scsi(req))
return scsi_setup_scsi_cmnd(sdev, req);
if (sdev->handler && sdev->handler->prep_fn) {
blk_status_t ret = sdev->handler->prep_fn(sdev, req);
if (ret != BLK_STS_OK)
return ret;
}
cmd->cmnd = scsi_req(req)->cmd = scsi_req(req)->__cmd;
memset(cmd->cmnd, 0, BLK_MAX_CDB);
return scsi_cmd_to_driver(cmd)->init_command(cmd);
}
static void scsi_mq_done(struct scsi_cmnd *cmd)
{
if (unlikely(blk_should_fake_timeout(cmd->request->q)))
return;
if (unlikely(test_and_set_bit(SCMD_STATE_COMPLETE, &cmd->state)))
return;
trace_scsi_dispatch_cmd_done(cmd);
blk_mq_complete_request(cmd->request);
}
static void scsi_mq_put_budget(struct request_queue *q)
{
struct scsi_device *sdev = q->queuedata;
atomic_dec(&sdev->device_busy);
}
static bool scsi_mq_get_budget(struct request_queue *q)
{
struct scsi_device *sdev = q->queuedata;
if (scsi_dev_queue_ready(q, sdev))
return true;
atomic_inc(&sdev->restarts);
/*
* Orders atomic_inc(&sdev->restarts) and atomic_read(&sdev->device_busy).
* .restarts must be incremented before .device_busy is read because the
* code in scsi_run_queue_async() depends on the order of these operations.
*/
smp_mb__after_atomic();
/*
* If all in-flight requests originated from this LUN are completed
* before reading .device_busy, sdev->device_busy will be observed as
* zero, then blk_mq_delay_run_hw_queues() will dispatch this request
* soon. Otherwise, completion of one of these requests will observe
* the .restarts flag, and the request queue will be run for handling
* this request, see scsi_end_request().
*/
if (unlikely(atomic_read(&sdev->device_busy) == 0 &&
!scsi_device_blocked(sdev)))
blk_mq_delay_run_hw_queues(sdev->request_queue, SCSI_QUEUE_DELAY);
return false;
}
static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
struct request *req = bd->rq;
struct request_queue *q = req->q;
struct scsi_device *sdev = q->queuedata;
struct Scsi_Host *shost = sdev->host;
struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
blk_status_t ret;
int reason;
/*
* If the device is not in running state we will reject some or all
* commands.
*/
if (unlikely(sdev->sdev_state != SDEV_RUNNING)) {
ret = scsi_device_state_check(sdev, req);
if (ret != BLK_STS_OK)
goto out_put_budget;
}
ret = BLK_STS_RESOURCE;
if (!scsi_target_queue_ready(shost, sdev))
goto out_put_budget;
if (!scsi_host_queue_ready(q, shost, sdev, cmd))
goto out_dec_target_busy;
if (!(req->rq_flags & RQF_DONTPREP)) {
ret = scsi_prepare_cmd(req);
if (ret != BLK_STS_OK)
goto out_dec_host_busy;
req->rq_flags |= RQF_DONTPREP;
} else {
clear_bit(SCMD_STATE_COMPLETE, &cmd->state);
}
cmd->flags &= SCMD_PRESERVED_FLAGS;
if (sdev->simple_tags)
cmd->flags |= SCMD_TAGGED;
if (bd->last)
cmd->flags |= SCMD_LAST;
scsi_set_resid(cmd, 0);
memset(cmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE);
cmd->scsi_done = scsi_mq_done;
blk_mq_start_request(req);
reason = scsi_dispatch_cmd(cmd);
if (reason) {
scsi_set_blocked(cmd, reason);
ret = BLK_STS_RESOURCE;
goto out_dec_host_busy;
}
return BLK_STS_OK;
out_dec_host_busy:
scsi_dec_host_busy(shost, cmd);
out_dec_target_busy:
if (scsi_target(sdev)->can_queue > 0)
atomic_dec(&scsi_target(sdev)->target_busy);
out_put_budget:
scsi_mq_put_budget(q);
switch (ret) {
case BLK_STS_OK:
break;
case BLK_STS_RESOURCE:
case BLK_STS_ZONE_RESOURCE:
if (scsi_device_blocked(sdev))
ret = BLK_STS_DEV_RESOURCE;
break;
default:
if (unlikely(!scsi_device_online(sdev)))
scsi_req(req)->result = DID_NO_CONNECT << 16;
else
scsi_req(req)->result = DID_ERROR << 16;
/*
* Make sure to release all allocated resources when
* we hit an error, as we will never see this command
* again.
*/
if (req->rq_flags & RQF_DONTPREP)
scsi_mq_uninit_cmd(cmd);
scsi_run_queue_async(sdev);
break;
}
return ret;
}
static enum blk_eh_timer_return scsi_timeout(struct request *req,
bool reserved)
{
if (reserved)
return BLK_EH_RESET_TIMER;
return scsi_times_out(req);
}
static int scsi_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
unsigned int hctx_idx, unsigned int numa_node)
{
struct Scsi_Host *shost = set->driver_data;
const bool unchecked_isa_dma = shost->unchecked_isa_dma;
struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
struct scatterlist *sg;
int ret = 0;
if (unchecked_isa_dma)
cmd->flags |= SCMD_UNCHECKED_ISA_DMA;
cmd->sense_buffer = scsi_alloc_sense_buffer(unchecked_isa_dma,
GFP_KERNEL, numa_node);
if (!cmd->sense_buffer)
return -ENOMEM;
cmd->req.sense = cmd->sense_buffer;
if (scsi_host_get_prot(shost)) {
sg = (void *)cmd + sizeof(struct scsi_cmnd) +
shost->hostt->cmd_size;
cmd->prot_sdb = (void *)sg + scsi_mq_inline_sgl_size(shost);
}
if (shost->hostt->init_cmd_priv) {
ret = shost->hostt->init_cmd_priv(shost, cmd);
if (ret < 0)
scsi_free_sense_buffer(unchecked_isa_dma,
cmd->sense_buffer);
}
return ret;
}
static void scsi_mq_exit_request(struct blk_mq_tag_set *set, struct request *rq,
unsigned int hctx_idx)
{
struct Scsi_Host *shost = set->driver_data;
struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
if (shost->hostt->exit_cmd_priv)
shost->hostt->exit_cmd_priv(shost, cmd);
scsi_free_sense_buffer(cmd->flags & SCMD_UNCHECKED_ISA_DMA,
cmd->sense_buffer);
}
static int scsi_map_queues(struct blk_mq_tag_set *set)
{
struct Scsi_Host *shost = container_of(set, struct Scsi_Host, tag_set);
if (shost->hostt->map_queues)
return shost->hostt->map_queues(shost);
return blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]);
}
void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
{
struct device *dev = shost->dma_dev;
/*
* this limit is imposed by hardware restrictions
*/
blk_queue_max_segments(q, min_t(unsigned short, shost->sg_tablesize,
SG_MAX_SEGMENTS));
if (scsi_host_prot_dma(shost)) {
shost->sg_prot_tablesize =
min_not_zero(shost->sg_prot_tablesize,
(unsigned short)SCSI_MAX_PROT_SG_SEGMENTS);
BUG_ON(shost->sg_prot_tablesize < shost->sg_tablesize);
blk_queue_max_integrity_segments(q, shost->sg_prot_tablesize);
}
if (dev->dma_mask) {
shost->max_sectors = min_t(unsigned int, shost->max_sectors,
dma_max_mapping_size(dev) >> SECTOR_SHIFT);
}
blk_queue_max_hw_sectors(q, shost->max_sectors);
if (shost->unchecked_isa_dma)
blk_queue_bounce_limit(q, BLK_BOUNCE_ISA);
blk_queue_segment_boundary(q, shost->dma_boundary);
dma_set_seg_boundary(dev, shost->dma_boundary);
blk_queue_max_segment_size(q, shost->max_segment_size);
blk_queue_virt_boundary(q, shost->virt_boundary_mask);
dma_set_max_seg_size(dev, queue_max_segment_size(q));
/*
* Set a reasonable default alignment: The larger of 32-byte (dword),
* which is a common minimum for HBAs, and the minimum DMA alignment,
* which is set by the platform.
*
* Devices that require a bigger alignment can increase it later.
*/
blk_queue_dma_alignment(q, max(4, dma_get_cache_alignment()) - 1);
}
EXPORT_SYMBOL_GPL(__scsi_init_queue);
static const struct blk_mq_ops scsi_mq_ops_no_commit = {
.get_budget = scsi_mq_get_budget,
.put_budget = scsi_mq_put_budget,
.queue_rq = scsi_queue_rq,
.complete = scsi_softirq_done,
.timeout = scsi_timeout,
#ifdef CONFIG_BLK_DEBUG_FS
.show_rq = scsi_show_rq,
#endif
.init_request = scsi_mq_init_request,
.exit_request = scsi_mq_exit_request,
.initialize_rq_fn = scsi_initialize_rq,
.cleanup_rq = scsi_cleanup_rq,
.busy = scsi_mq_lld_busy,
.map_queues = scsi_map_queues,
};
static void scsi_commit_rqs(struct blk_mq_hw_ctx *hctx)
{
struct request_queue *q = hctx->queue;
struct scsi_device *sdev = q->queuedata;
struct Scsi_Host *shost = sdev->host;
shost->hostt->commit_rqs(shost, hctx->queue_num);
}
static const struct blk_mq_ops scsi_mq_ops = {
.get_budget = scsi_mq_get_budget,
.put_budget = scsi_mq_put_budget,
.queue_rq = scsi_queue_rq,
.commit_rqs = scsi_commit_rqs,
.complete = scsi_softirq_done,
.timeout = scsi_timeout,
#ifdef CONFIG_BLK_DEBUG_FS
.show_rq = scsi_show_rq,
#endif
.init_request = scsi_mq_init_request,
.exit_request = scsi_mq_exit_request,
.initialize_rq_fn = scsi_initialize_rq,
.cleanup_rq = scsi_cleanup_rq,
.busy = scsi_mq_lld_busy,
.map_queues = scsi_map_queues,
};
struct request_queue *scsi_mq_alloc_queue(struct scsi_device *sdev)
{
sdev->request_queue = blk_mq_init_queue(&sdev->host->tag_set);
if (IS_ERR(sdev->request_queue))
return NULL;
sdev->request_queue->queuedata = sdev;
__scsi_init_queue(sdev->host, sdev->request_queue);
blk_queue_flag_set(QUEUE_FLAG_SCSI_PASSTHROUGH, sdev->request_queue);
return sdev->request_queue;
}
int scsi_mq_setup_tags(struct Scsi_Host *shost)
{
unsigned int cmd_size, sgl_size;
struct blk_mq_tag_set *tag_set = &shost->tag_set;
sgl_size = max_t(unsigned int, sizeof(struct scatterlist),
scsi_mq_inline_sgl_size(shost));
cmd_size = sizeof(struct scsi_cmnd) + shost->hostt->cmd_size + sgl_size;
if (scsi_host_get_prot(shost))
cmd_size += sizeof(struct scsi_data_buffer) +
sizeof(struct scatterlist) * SCSI_INLINE_PROT_SG_CNT;
memset(tag_set, 0, sizeof(*tag_set));
if (shost->hostt->commit_rqs)
tag_set->ops = &scsi_mq_ops;
else
tag_set->ops = &scsi_mq_ops_no_commit;
tag_set->nr_hw_queues = shost->nr_hw_queues ? : 1;
tag_set->queue_depth = shost->can_queue;
tag_set->cmd_size = cmd_size;
tag_set->numa_node = NUMA_NO_NODE;
tag_set->flags = BLK_MQ_F_SHOULD_MERGE;
tag_set->flags |=
BLK_ALLOC_POLICY_TO_MQ_FLAG(shost->hostt->tag_alloc_policy);
tag_set->driver_data = shost;
if (shost->host_tagset)
tag_set->flags |= BLK_MQ_F_TAG_HCTX_SHARED;
return blk_mq_alloc_tag_set(tag_set);
}
void scsi_mq_destroy_tags(struct Scsi_Host *shost)
{
blk_mq_free_tag_set(&shost->tag_set);
}
/**
* scsi_device_from_queue - return sdev associated with a request_queue
* @q: The request queue to return the sdev from
*
* Return the sdev associated with a request queue or NULL if the
* request_queue does not reference a SCSI device.
*/
struct scsi_device *scsi_device_from_queue(struct request_queue *q)
{
struct scsi_device *sdev = NULL;
if (q->mq_ops == &scsi_mq_ops_no_commit ||
q->mq_ops == &scsi_mq_ops)
sdev = q->queuedata;
if (!sdev || !get_device(&sdev->sdev_gendev))
sdev = NULL;
return sdev;
}
/**
* scsi_block_requests - Utility function used by low-level drivers to prevent
* further commands from being queued to the device.
* @shost: host in question
*
* There is no timer nor any other means by which the requests get unblocked
* other than the low-level driver calling scsi_unblock_requests().
*/
void scsi_block_requests(struct Scsi_Host *shost)
{
shost->host_self_blocked = 1;
}
EXPORT_SYMBOL(scsi_block_requests);
/**
* scsi_unblock_requests - Utility function used by low-level drivers to allow
* further commands to be queued to the device.
* @shost: host in question
*
* There is no timer nor any other means by which the requests get unblocked
* other than the low-level driver calling scsi_unblock_requests(). This is done
* as an API function so that changes to the internals of the scsi mid-layer
* won't require wholesale changes to drivers that use this feature.
*/
void scsi_unblock_requests(struct Scsi_Host *shost)
{
shost->host_self_blocked = 0;
scsi_run_host_queues(shost);
}
EXPORT_SYMBOL(scsi_unblock_requests);
void scsi_exit_queue(void)
{
kmem_cache_destroy(scsi_sense_cache);
kmem_cache_destroy(scsi_sense_isadma_cache);
}
/**
* scsi_mode_select - issue a mode select
* @sdev: SCSI device to be queried
* @pf: Page format bit (1 == standard, 0 == vendor specific)
* @sp: Save page bit (0 == don't save, 1 == save)
* @modepage: mode page being requested
* @buffer: request buffer (may not be smaller than eight bytes)
* @len: length of request buffer.
* @timeout: command timeout
* @retries: number of retries before failing
* @data: returns a structure abstracting the mode header data
* @sshdr: place to put sense data (or NULL if no sense to be collected).
* must be SCSI_SENSE_BUFFERSIZE big.
*
* Returns zero if successful; negative error number or scsi
* status on error
*
*/
int
scsi_mode_select(struct scsi_device *sdev, int pf, int sp, int modepage,
unsigned char *buffer, int len, int timeout, int retries,
struct scsi_mode_data *data, struct scsi_sense_hdr *sshdr)
{
unsigned char cmd[10];
unsigned char *real_buffer;
int ret;
memset(cmd, 0, sizeof(cmd));
cmd[1] = (pf ? 0x10 : 0) | (sp ? 0x01 : 0);
if (sdev->use_10_for_ms) {
if (len > 65535)
return -EINVAL;
real_buffer = kmalloc(8 + len, GFP_KERNEL);
if (!real_buffer)
return -ENOMEM;
memcpy(real_buffer + 8, buffer, len);
len += 8;
real_buffer[0] = 0;
real_buffer[1] = 0;
real_buffer[2] = data->medium_type;
real_buffer[3] = data->device_specific;
real_buffer[4] = data->longlba ? 0x01 : 0;
real_buffer[5] = 0;
real_buffer[6] = data->block_descriptor_length >> 8;
real_buffer[7] = data->block_descriptor_length;
cmd[0] = MODE_SELECT_10;
cmd[7] = len >> 8;
cmd[8] = len;
} else {
if (len > 255 || data->block_descriptor_length > 255 ||
data->longlba)
return -EINVAL;
real_buffer = kmalloc(4 + len, GFP_KERNEL);
if (!real_buffer)
return -ENOMEM;
memcpy(real_buffer + 4, buffer, len);
len += 4;
real_buffer[0] = 0;
real_buffer[1] = data->medium_type;
real_buffer[2] = data->device_specific;
real_buffer[3] = data->block_descriptor_length;
cmd[0] = MODE_SELECT;
cmd[4] = len;
}
ret = scsi_execute_req(sdev, cmd, DMA_TO_DEVICE, real_buffer, len,
sshdr, timeout, retries, NULL);
kfree(real_buffer);
return ret;
}
EXPORT_SYMBOL_GPL(scsi_mode_select);
/**
* scsi_mode_sense - issue a mode sense, falling back from 10 to six bytes if necessary.
* @sdev: SCSI device to be queried
* @dbd: set if mode sense will allow block descriptors to be returned
* @modepage: mode page being requested
* @buffer: request buffer (may not be smaller than eight bytes)
* @len: length of request buffer.
* @timeout: command timeout
* @retries: number of retries before failing
* @data: returns a structure abstracting the mode header data
* @sshdr: place to put sense data (or NULL if no sense to be collected).
* must be SCSI_SENSE_BUFFERSIZE big.
*
* Returns zero if successful, or a negative error number on failure
*/
int
scsi_mode_sense(struct scsi_device *sdev, int dbd, int modepage,
unsigned char *buffer, int len, int timeout, int retries,
struct scsi_mode_data *data, struct scsi_sense_hdr *sshdr)
{
unsigned char cmd[12];
int use_10_for_ms;
int header_length;
int result, retry_count = retries;
struct scsi_sense_hdr my_sshdr;
memset(data, 0, sizeof(*data));
memset(&cmd[0], 0, 12);
dbd = sdev->set_dbd_for_ms ? 8 : dbd;
cmd[1] = dbd & 0x18; /* allows DBD and LLBA bits */
cmd[2] = modepage;
/* caller might not be interested in sense, but we need it */
if (!sshdr)
sshdr = &my_sshdr;
retry:
use_10_for_ms = sdev->use_10_for_ms;
if (use_10_for_ms) {
if (len < 8)
len = 8;
cmd[0] = MODE_SENSE_10;
cmd[8] = len;
header_length = 8;
} else {
if (len < 4)
len = 4;
cmd[0] = MODE_SENSE;
cmd[4] = len;
header_length = 4;
}
memset(buffer, 0, len);
result = scsi_execute_req(sdev, cmd, DMA_FROM_DEVICE, buffer, len,
sshdr, timeout, retries, NULL);
if (result < 0)
return result;
/* This code looks awful: what it's doing is making sure an
* ILLEGAL REQUEST sense return identifies the actual command
* byte as the problem. MODE_SENSE commands can return
* ILLEGAL REQUEST if the code page isn't supported */
if (use_10_for_ms && !scsi_status_is_good(result) &&
driver_byte(result) == DRIVER_SENSE) {
if (scsi_sense_valid(sshdr)) {
if ((sshdr->sense_key == ILLEGAL_REQUEST) &&
(sshdr->asc == 0x20) && (sshdr->ascq == 0)) {
/*
* Invalid command operation code
*/
sdev->use_10_for_ms = 0;
goto retry;
}
}
}
if (scsi_status_is_good(result)) {
if (unlikely(buffer[0] == 0x86 && buffer[1] == 0x0b &&
(modepage == 6 || modepage == 8))) {
/* Initio breakage? */
header_length = 0;
data->length = 13;
data->medium_type = 0;
data->device_specific = 0;
data->longlba = 0;
data->block_descriptor_length = 0;
} else if (use_10_for_ms) {
data->length = buffer[0]*256 + buffer[1] + 2;
data->medium_type = buffer[2];
data->device_specific = buffer[3];
data->longlba = buffer[4] & 0x01;
data->block_descriptor_length = buffer[6]*256
+ buffer[7];
} else {
data->length = buffer[0] + 1;
data->medium_type = buffer[1];
data->device_specific = buffer[2];
data->block_descriptor_length = buffer[3];
}
data->header_length = header_length;
result = 0;
} else if ((status_byte(result) == CHECK_CONDITION) &&
scsi_sense_valid(sshdr) &&
sshdr->sense_key == UNIT_ATTENTION && retry_count) {
retry_count--;
goto retry;
}
if (result > 0)
result = -EIO;
return result;
}
EXPORT_SYMBOL(scsi_mode_sense);
/**
* scsi_test_unit_ready - test if unit is ready
* @sdev: scsi device to change the state of.
* @timeout: command timeout
* @retries: number of retries before failing
* @sshdr: outpout pointer for decoded sense information.
*
* Returns zero if unsuccessful or an error if TUR failed. For
* removable media, UNIT_ATTENTION sets ->changed flag.
**/
int
scsi_test_unit_ready(struct scsi_device *sdev, int timeout, int retries,
struct scsi_sense_hdr *sshdr)
{
char cmd[] = {
TEST_UNIT_READY, 0, 0, 0, 0, 0,
};
int result;
/* try to eat the UNIT_ATTENTION if there are enough retries */
do {
result = scsi_execute_req(sdev, cmd, DMA_NONE, NULL, 0, sshdr,
timeout, 1, NULL);
if (sdev->removable && scsi_sense_valid(sshdr) &&
sshdr->sense_key == UNIT_ATTENTION)
sdev->changed = 1;
} while (scsi_sense_valid(sshdr) &&
sshdr->sense_key == UNIT_ATTENTION && --retries);
return result;
}
EXPORT_SYMBOL(scsi_test_unit_ready);
/**
* scsi_device_set_state - Take the given device through the device state model.
* @sdev: scsi device to change the state of.
* @state: state to change to.
*
* Returns zero if successful or an error if the requested
* transition is illegal.
*/
int
scsi_device_set_state(struct scsi_device *sdev, enum scsi_device_state state)
{
enum scsi_device_state oldstate = sdev->sdev_state;
if (state == oldstate)
return 0;
switch (state) {
case SDEV_CREATED:
switch (oldstate) {
case SDEV_CREATED_BLOCK:
break;
default:
goto illegal;
}
break;
case SDEV_RUNNING:
switch (oldstate) {
case SDEV_CREATED:
case SDEV_OFFLINE:
case SDEV_TRANSPORT_OFFLINE:
case SDEV_QUIESCE:
case SDEV_BLOCK:
break;
default:
goto illegal;
}
break;
case SDEV_QUIESCE:
switch (oldstate) {
case SDEV_RUNNING:
case SDEV_OFFLINE:
case SDEV_TRANSPORT_OFFLINE:
break;
default:
goto illegal;
}
break;
case SDEV_OFFLINE:
case SDEV_TRANSPORT_OFFLINE:
switch (oldstate) {
case SDEV_CREATED:
case SDEV_RUNNING:
case SDEV_QUIESCE:
case SDEV_BLOCK:
break;
default:
goto illegal;
}
break;
case SDEV_BLOCK:
switch (oldstate) {
case SDEV_RUNNING:
case SDEV_CREATED_BLOCK:
case SDEV_QUIESCE:
case SDEV_OFFLINE:
break;
default:
goto illegal;
}
break;
case SDEV_CREATED_BLOCK:
switch (oldstate) {
case SDEV_CREATED:
break;
default:
goto illegal;
}
break;
case SDEV_CANCEL:
switch (oldstate) {
case SDEV_CREATED:
case SDEV_RUNNING:
case SDEV_QUIESCE:
case SDEV_OFFLINE:
case SDEV_TRANSPORT_OFFLINE:
break;
default:
goto illegal;
}
break;
case SDEV_DEL:
switch (oldstate) {
case SDEV_CREATED:
case SDEV_RUNNING:
case SDEV_OFFLINE:
case SDEV_TRANSPORT_OFFLINE:
case SDEV_CANCEL:
case SDEV_BLOCK:
case SDEV_CREATED_BLOCK:
break;
default:
goto illegal;
}
break;
}
sdev->offline_already = false;
sdev->sdev_state = state;
return 0;
illegal:
SCSI_LOG_ERROR_RECOVERY(1,
sdev_printk(KERN_ERR, sdev,
"Illegal state transition %s->%s",
scsi_device_state_name(oldstate),
scsi_device_state_name(state))
);
return -EINVAL;
}
EXPORT_SYMBOL(scsi_device_set_state);
/**
* sdev_evt_emit - emit a single SCSI device uevent
* @sdev: associated SCSI device
* @evt: event to emit
*
* Send a single uevent (scsi_event) to the associated scsi_device.
*/
static void scsi_evt_emit(struct scsi_device *sdev, struct scsi_event *evt)
{
int idx = 0;
char *envp[3];
switch (evt->evt_type) {
case SDEV_EVT_MEDIA_CHANGE:
envp[idx++] = "SDEV_MEDIA_CHANGE=1";
break;
case SDEV_EVT_INQUIRY_CHANGE_REPORTED:
scsi_rescan_device(&sdev->sdev_gendev);
envp[idx++] = "SDEV_UA=INQUIRY_DATA_HAS_CHANGED";
break;
case SDEV_EVT_CAPACITY_CHANGE_REPORTED:
envp[idx++] = "SDEV_UA=CAPACITY_DATA_HAS_CHANGED";
break;
case SDEV_EVT_SOFT_THRESHOLD_REACHED_REPORTED:
envp[idx++] = "SDEV_UA=THIN_PROVISIONING_SOFT_THRESHOLD_REACHED";
break;
case SDEV_EVT_MODE_PARAMETER_CHANGE_REPORTED:
envp[idx++] = "SDEV_UA=MODE_PARAMETERS_CHANGED";
break;
case SDEV_EVT_LUN_CHANGE_REPORTED:
envp[idx++] = "SDEV_UA=REPORTED_LUNS_DATA_HAS_CHANGED";
break;
case SDEV_EVT_ALUA_STATE_CHANGE_REPORTED:
envp[idx++] = "SDEV_UA=ASYMMETRIC_ACCESS_STATE_CHANGED";
break;
case SDEV_EVT_POWER_ON_RESET_OCCURRED:
envp[idx++] = "SDEV_UA=POWER_ON_RESET_OCCURRED";
break;
default:
/* do nothing */
break;
}
envp[idx++] = NULL;
kobject_uevent_env(&sdev->sdev_gendev.kobj, KOBJ_CHANGE, envp);
}
/**
* sdev_evt_thread - send a uevent for each scsi event
* @work: work struct for scsi_device
*
* Dispatch queued events to their associated scsi_device kobjects
* as uevents.
*/
void scsi_evt_thread(struct work_struct *work)
{
struct scsi_device *sdev;
enum scsi_device_event evt_type;
LIST_HEAD(event_list);
sdev = container_of(work, struct scsi_device, event_work);
for (evt_type = SDEV_EVT_FIRST; evt_type <= SDEV_EVT_LAST; evt_type++)
if (test_and_clear_bit(evt_type, sdev->pending_events))
sdev_evt_send_simple(sdev, evt_type, GFP_KERNEL);
while (1) {
struct scsi_event *evt;
struct list_head *this, *tmp;
unsigned long flags;
spin_lock_irqsave(&sdev->list_lock, flags);
list_splice_init(&sdev->event_list, &event_list);
spin_unlock_irqrestore(&sdev->list_lock, flags);
if (list_empty(&event_list))
break;
list_for_each_safe(this, tmp, &event_list) {
evt = list_entry(this, struct scsi_event, node);
list_del(&evt->node);
scsi_evt_emit(sdev, evt);
kfree(evt);
}
}
}
/**
* sdev_evt_send - send asserted event to uevent thread
* @sdev: scsi_device event occurred on
* @evt: event to send
*
* Assert scsi device event asynchronously.
*/
void sdev_evt_send(struct scsi_device *sdev, struct scsi_event *evt)
{
unsigned long flags;
#if 0
/* FIXME: currently this check eliminates all media change events
* for polled devices. Need to update to discriminate between AN
* and polled events */
if (!test_bit(evt->evt_type, sdev->supported_events)) {
kfree(evt);
return;
}
#endif
spin_lock_irqsave(&sdev->list_lock, flags);
list_add_tail(&evt->node, &sdev->event_list);
schedule_work(&sdev->event_work);
spin_unlock_irqrestore(&sdev->list_lock, flags);
}
EXPORT_SYMBOL_GPL(sdev_evt_send);
/**
* sdev_evt_alloc - allocate a new scsi event
* @evt_type: type of event to allocate
* @gfpflags: GFP flags for allocation
*
* Allocates and returns a new scsi_event.
*/
struct scsi_event *sdev_evt_alloc(enum scsi_device_event evt_type,
gfp_t gfpflags)
{
struct scsi_event *evt = kzalloc(sizeof(struct scsi_event), gfpflags);
if (!evt)
return NULL;
evt->evt_type = evt_type;
INIT_LIST_HEAD(&evt->node);
/* evt_type-specific initialization, if any */
switch (evt_type) {
case SDEV_EVT_MEDIA_CHANGE:
case SDEV_EVT_INQUIRY_CHANGE_REPORTED:
case SDEV_EVT_CAPACITY_CHANGE_REPORTED:
case SDEV_EVT_SOFT_THRESHOLD_REACHED_REPORTED:
case SDEV_EVT_MODE_PARAMETER_CHANGE_REPORTED:
case SDEV_EVT_LUN_CHANGE_REPORTED:
case SDEV_EVT_ALUA_STATE_CHANGE_REPORTED:
case SDEV_EVT_POWER_ON_RESET_OCCURRED:
default:
/* do nothing */
break;
}
return evt;
}
EXPORT_SYMBOL_GPL(sdev_evt_alloc);
/**
* sdev_evt_send_simple - send asserted event to uevent thread
* @sdev: scsi_device event occurred on
* @evt_type: type of event to send
* @gfpflags: GFP flags for allocation
*
* Assert scsi device event asynchronously, given an event type.
*/
void sdev_evt_send_simple(struct scsi_device *sdev,
enum scsi_device_event evt_type, gfp_t gfpflags)
{
struct scsi_event *evt = sdev_evt_alloc(evt_type, gfpflags);
if (!evt) {
sdev_printk(KERN_ERR, sdev, "event %d eaten due to OOM\n",
evt_type);
return;
}
sdev_evt_send(sdev, evt);
}
EXPORT_SYMBOL_GPL(sdev_evt_send_simple);
/**
* scsi_device_quiesce - Block all commands except power management.
* @sdev: scsi device to quiesce.
*
* This works by trying to transition to the SDEV_QUIESCE state
* (which must be a legal transition). When the device is in this
* state, only power management requests will be accepted, all others will
* be deferred.
*
* Must be called with user context, may sleep.
*
* Returns zero if unsuccessful or an error if not.
*/
int
scsi_device_quiesce(struct scsi_device *sdev)
{
struct request_queue *q = sdev->request_queue;
int err;
/*
* It is allowed to call scsi_device_quiesce() multiple times from
* the same context but concurrent scsi_device_quiesce() calls are
* not allowed.
*/
WARN_ON_ONCE(sdev->quiesced_by && sdev->quiesced_by != current);
if (sdev->quiesced_by == current)
return 0;
blk_set_pm_only(q);
blk_mq_freeze_queue(q);
/*
* Ensure that the effect of blk_set_pm_only() will be visible
* for percpu_ref_tryget() callers that occur after the queue
* unfreeze even if the queue was already frozen before this function
* was called. See also https://lwn.net/Articles/573497/.
*/
synchronize_rcu();
blk_mq_unfreeze_queue(q);
mutex_lock(&sdev->state_mutex);
err = scsi_device_set_state(sdev, SDEV_QUIESCE);
if (err == 0)
sdev->quiesced_by = current;
else
blk_clear_pm_only(q);
mutex_unlock(&sdev->state_mutex);
return err;
}
EXPORT_SYMBOL(scsi_device_quiesce);
/**
* scsi_device_resume - Restart user issued commands to a quiesced device.
* @sdev: scsi device to resume.
*
* Moves the device from quiesced back to running and restarts the
* queues.
*
* Must be called with user context, may sleep.
*/
void scsi_device_resume(struct scsi_device *sdev)
{
/* check if the device state was mutated prior to resume, and if
* so assume the state is being managed elsewhere (for example
* device deleted during suspend)
*/
mutex_lock(&sdev->state_mutex);
if (sdev->sdev_state == SDEV_QUIESCE)
scsi_device_set_state(sdev, SDEV_RUNNING);
if (sdev->quiesced_by) {
sdev->quiesced_by = NULL;
blk_clear_pm_only(sdev->request_queue);
}
mutex_unlock(&sdev->state_mutex);
}
EXPORT_SYMBOL(scsi_device_resume);
static void
device_quiesce_fn(struct scsi_device *sdev, void *data)
{
scsi_device_quiesce(sdev);
}
void
scsi_target_quiesce(struct scsi_target *starget)
{
starget_for_each_device(starget, NULL, device_quiesce_fn);
}
EXPORT_SYMBOL(scsi_target_quiesce);
static void
device_resume_fn(struct scsi_device *sdev, void *data)
{
scsi_device_resume(sdev);
}
void
scsi_target_resume(struct scsi_target *starget)
{
starget_for_each_device(starget, NULL, device_resume_fn);
}
EXPORT_SYMBOL(scsi_target_resume);
/**
* scsi_internal_device_block_nowait - try to transition to the SDEV_BLOCK state
* @sdev: device to block
*
* Pause SCSI command processing on the specified device. Does not sleep.
*
* Returns zero if successful or a negative error code upon failure.
*
* Notes:
* This routine transitions the device to the SDEV_BLOCK state (which must be
* a legal transition). When the device is in this state, command processing
* is paused until the device leaves the SDEV_BLOCK state. See also
* scsi_internal_device_unblock_nowait().
*/
int scsi_internal_device_block_nowait(struct scsi_device *sdev)
{
struct request_queue *q = sdev->request_queue;
int err = 0;
err = scsi_device_set_state(sdev, SDEV_BLOCK);
if (err) {
err = scsi_device_set_state(sdev, SDEV_CREATED_BLOCK);
if (err)
return err;
}
/*
* The device has transitioned to SDEV_BLOCK. Stop the
* block layer from calling the midlayer with this device's
* request queue.
*/
blk_mq_quiesce_queue_nowait(q);
return 0;
}
EXPORT_SYMBOL_GPL(scsi_internal_device_block_nowait);
/**
* scsi_internal_device_block - try to transition to the SDEV_BLOCK state
* @sdev: device to block
*
* Pause SCSI command processing on the specified device and wait until all
* ongoing scsi_request_fn() / scsi_queue_rq() calls have finished. May sleep.
*
* Returns zero if successful or a negative error code upon failure.
*
* Note:
* This routine transitions the device to the SDEV_BLOCK state (which must be
* a legal transition). When the device is in this state, command processing
* is paused until the device leaves the SDEV_BLOCK state. See also
* scsi_internal_device_unblock().
*/
static int scsi_internal_device_block(struct scsi_device *sdev)
{
struct request_queue *q = sdev->request_queue;
int err;
mutex_lock(&sdev->state_mutex);
err = scsi_internal_device_block_nowait(sdev);
if (err == 0)
blk_mq_quiesce_queue(q);
mutex_unlock(&sdev->state_mutex);
return err;
}
void scsi_start_queue(struct scsi_device *sdev)
{
struct request_queue *q = sdev->request_queue;
blk_mq_unquiesce_queue(q);
}
/**
* scsi_internal_device_unblock_nowait - resume a device after a block request
* @sdev: device to resume
* @new_state: state to set the device to after unblocking
*
* Restart the device queue for a previously suspended SCSI device. Does not
* sleep.
*
* Returns zero if successful or a negative error code upon failure.
*
* Notes:
* This routine transitions the device to the SDEV_RUNNING state or to one of
* the offline states (which must be a legal transition) allowing the midlayer
* to goose the queue for this device.
*/
int scsi_internal_device_unblock_nowait(struct scsi_device *sdev,
enum scsi_device_state new_state)
{
switch (new_state) {
case SDEV_RUNNING:
case SDEV_TRANSPORT_OFFLINE:
break;
default:
return -EINVAL;
}
/*
* Try to transition the scsi device to SDEV_RUNNING or one of the
* offlined states and goose the device queue if successful.
*/
switch (sdev->sdev_state) {
case SDEV_BLOCK:
case SDEV_TRANSPORT_OFFLINE:
sdev->sdev_state = new_state;
break;
case SDEV_CREATED_BLOCK:
if (new_state == SDEV_TRANSPORT_OFFLINE ||
new_state == SDEV_OFFLINE)
sdev->sdev_state = new_state;
else
sdev->sdev_state = SDEV_CREATED;
break;
case SDEV_CANCEL:
case SDEV_OFFLINE:
break;
default:
return -EINVAL;
}
scsi_start_queue(sdev);
return 0;
}
EXPORT_SYMBOL_GPL(scsi_internal_device_unblock_nowait);
/**
* scsi_internal_device_unblock - resume a device after a block request
* @sdev: device to resume
* @new_state: state to set the device to after unblocking
*
* Restart the device queue for a previously suspended SCSI device. May sleep.
*
* Returns zero if successful or a negative error code upon failure.
*
* Notes:
* This routine transitions the device to the SDEV_RUNNING state or to one of
* the offline states (which must be a legal transition) allowing the midlayer
* to goose the queue for this device.
*/
static int scsi_internal_device_unblock(struct scsi_device *sdev,
enum scsi_device_state new_state)
{
int ret;
mutex_lock(&sdev->state_mutex);
ret = scsi_internal_device_unblock_nowait(sdev, new_state);
mutex_unlock(&sdev->state_mutex);
return ret;
}
static void
device_block(struct scsi_device *sdev, void *data)
{
int ret;
ret = scsi_internal_device_block(sdev);
WARN_ONCE(ret, "scsi_internal_device_block(%s) failed: ret = %d\n",
dev_name(&sdev->sdev_gendev), ret);
}
static int
target_block(struct device *dev, void *data)
{
if (scsi_is_target_device(dev))
starget_for_each_device(to_scsi_target(dev), NULL,
device_block);
return 0;
}
void
scsi_target_block(struct device *dev)
{
if (scsi_is_target_device(dev))
starget_for_each_device(to_scsi_target(dev), NULL,
device_block);
else
device_for_each_child(dev, NULL, target_block);
}
EXPORT_SYMBOL_GPL(scsi_target_block);
static void
device_unblock(struct scsi_device *sdev, void *data)
{
scsi_internal_device_unblock(sdev, *(enum scsi_device_state *)data);
}
static int
target_unblock(struct device *dev, void *data)
{
if (scsi_is_target_device(dev))
starget_for_each_device(to_scsi_target(dev), data,
device_unblock);
return 0;
}
void
scsi_target_unblock(struct device *dev, enum scsi_device_state new_state)
{
if (scsi_is_target_device(dev))
starget_for_each_device(to_scsi_target(dev), &new_state,
device_unblock);
else
device_for_each_child(dev, &new_state, target_unblock);
}
EXPORT_SYMBOL_GPL(scsi_target_unblock);
int
scsi_host_block(struct Scsi_Host *shost)
{
struct scsi_device *sdev;
int ret = 0;
/*
* Call scsi_internal_device_block_nowait so we can avoid
* calling synchronize_rcu() for each LUN.
*/
shost_for_each_device(sdev, shost) {
mutex_lock(&sdev->state_mutex);
ret = scsi_internal_device_block_nowait(sdev);
mutex_unlock(&sdev->state_mutex);
if (ret) {
scsi_device_put(sdev);
break;
}
}
/*
* SCSI never enables blk-mq's BLK_MQ_F_BLOCKING flag so
* calling synchronize_rcu() once is enough.
*/
WARN_ON_ONCE(shost->tag_set.flags & BLK_MQ_F_BLOCKING);
if (!ret)
synchronize_rcu();
return ret;
}
EXPORT_SYMBOL_GPL(scsi_host_block);
int
scsi_host_unblock(struct Scsi_Host *shost, int new_state)
{
struct scsi_device *sdev;
int ret = 0;
shost_for_each_device(sdev, shost) {
ret = scsi_internal_device_unblock(sdev, new_state);
if (ret) {
scsi_device_put(sdev);
break;
}
}
return ret;
}
EXPORT_SYMBOL_GPL(scsi_host_unblock);
/**
* scsi_kmap_atomic_sg - find and atomically map an sg-elemnt
* @sgl: scatter-gather list
* @sg_count: number of segments in sg
* @offset: offset in bytes into sg, on return offset into the mapped area
* @len: bytes to map, on return number of bytes mapped
*
* Returns virtual address of the start of the mapped page
*/
void *scsi_kmap_atomic_sg(struct scatterlist *sgl, int sg_count,
size_t *offset, size_t *len)
{
int i;
size_t sg_len = 0, len_complete = 0;
struct scatterlist *sg;
struct page *page;
WARN_ON(!irqs_disabled());
for_each_sg(sgl, sg, sg_count, i) {
len_complete = sg_len; /* Complete sg-entries */
sg_len += sg->length;
if (sg_len > *offset)
break;
}
if (unlikely(i == sg_count)) {
printk(KERN_ERR "%s: Bytes in sg: %zu, requested offset %zu, "
"elements %d\n",
__func__, sg_len, *offset, sg_count);
WARN_ON(1);
return NULL;
}
/* Offset starting from the beginning of first page in this sg-entry */
*offset = *offset - len_complete + sg->offset;
/* Assumption: contiguous pages can be accessed as "page + i" */
page = nth_page(sg_page(sg), (*offset >> PAGE_SHIFT));
*offset &= ~PAGE_MASK;
/* Bytes in this sg-entry from *offset to the end of the page */
sg_len = PAGE_SIZE - *offset;
if (*len > sg_len)
*len = sg_len;
return kmap_atomic(page);
}
EXPORT_SYMBOL(scsi_kmap_atomic_sg);
/**
* scsi_kunmap_atomic_sg - atomically unmap a virtual address, previously mapped with scsi_kmap_atomic_sg
* @virt: virtual address to be unmapped
*/
void scsi_kunmap_atomic_sg(void *virt)
{
kunmap_atomic(virt);
}
EXPORT_SYMBOL(scsi_kunmap_atomic_sg);
void sdev_disable_disk_events(struct scsi_device *sdev)
{
atomic_inc(&sdev->disk_events_disable_depth);
}
EXPORT_SYMBOL(sdev_disable_disk_events);
void sdev_enable_disk_events(struct scsi_device *sdev)
{
if (WARN_ON_ONCE(atomic_read(&sdev->disk_events_disable_depth) <= 0))
return;
atomic_dec(&sdev->disk_events_disable_depth);
}
EXPORT_SYMBOL(sdev_enable_disk_events);
static unsigned char designator_prio(const unsigned char *d)
{
if (d[1] & 0x30)
/* not associated with LUN */
return 0;
if (d[3] == 0)
/* invalid length */
return 0;
/*
* Order of preference for lun descriptor:
* - SCSI name string
* - NAA IEEE Registered Extended
* - EUI-64 based 16-byte
* - EUI-64 based 12-byte
* - NAA IEEE Registered
* - NAA IEEE Extended
* - EUI-64 based 8-byte
* - SCSI name string (truncated)
* - T10 Vendor ID
* as longer descriptors reduce the likelyhood
* of identification clashes.
*/
switch (d[1] & 0xf) {
case 8:
/* SCSI name string, variable-length UTF-8 */
return 9;
case 3:
switch (d[4] >> 4) {
case 6:
/* NAA registered extended */
return 8;
case 5:
/* NAA registered */
return 5;
case 4:
/* NAA extended */
return 4;
case 3:
/* NAA locally assigned */
return 1;
default:
break;
}
break;
case 2:
switch (d[3]) {
case 16:
/* EUI64-based, 16 byte */
return 7;
case 12:
/* EUI64-based, 12 byte */
return 6;
case 8:
/* EUI64-based, 8 byte */
return 3;
default:
break;
}
break;
case 1:
/* T10 vendor ID */
return 1;
default:
break;
}
return 0;
}
/**
* scsi_vpd_lun_id - return a unique device identification
* @sdev: SCSI device
* @id: buffer for the identification
* @id_len: length of the buffer
*
* Copies a unique device identification into @id based
* on the information in the VPD page 0x83 of the device.
* The string will be formatted as a SCSI name string.
*
* Returns the length of the identification or error on failure.
* If the identifier is longer than the supplied buffer the actual
* identifier length is returned and the buffer is not zero-padded.
*/
int scsi_vpd_lun_id(struct scsi_device *sdev, char *id, size_t id_len)
{
u8 cur_id_prio = 0;
u8 cur_id_size = 0;
const unsigned char *d, *cur_id_str;
const struct scsi_vpd *vpd_pg83;
int id_size = -EINVAL;
rcu_read_lock();
vpd_pg83 = rcu_dereference(sdev->vpd_pg83);
if (!vpd_pg83) {
rcu_read_unlock();
return -ENXIO;
}
/* The id string must be at least 20 bytes + terminating NULL byte */
if (id_len < 21) {
rcu_read_unlock();
return -EINVAL;
}
memset(id, 0, id_len);
d = vpd_pg83->data + 4;
while (d < vpd_pg83->data + vpd_pg83->len) {
u8 prio = designator_prio(d);
if (prio == 0 || cur_id_prio > prio)
goto next_desig;
switch (d[1] & 0xf) {
case 0x1:
/* T10 Vendor ID */
if (cur_id_size > d[3])
break;
cur_id_prio = prio;
cur_id_size = d[3];
if (cur_id_size + 4 > id_len)
cur_id_size = id_len - 4;
cur_id_str = d + 4;
id_size = snprintf(id, id_len, "t10.%*pE",
cur_id_size, cur_id_str);
break;
case 0x2:
/* EUI-64 */
cur_id_prio = prio;
cur_id_size = d[3];
cur_id_str = d + 4;
switch (cur_id_size) {
case 8:
id_size = snprintf(id, id_len,
"eui.%8phN",
cur_id_str);
break;
case 12:
id_size = snprintf(id, id_len,
"eui.%12phN",
cur_id_str);
break;
case 16:
id_size = snprintf(id, id_len,
"eui.%16phN",
cur_id_str);
break;
default:
break;
}
break;
case 0x3:
/* NAA */
cur_id_prio = prio;
cur_id_size = d[3];
cur_id_str = d + 4;
switch (cur_id_size) {
case 8:
id_size = snprintf(id, id_len,
"naa.%8phN",
cur_id_str);
break;
case 16:
id_size = snprintf(id, id_len,
"naa.%16phN",
cur_id_str);
break;
default:
break;
}
break;
case 0x8:
/* SCSI name string */
if (cur_id_size > d[3])
break;
/* Prefer others for truncated descriptor */
if (d[3] > id_len) {
prio = 2;
if (cur_id_prio > prio)
break;
}
cur_id_prio = prio;
cur_id_size = id_size = d[3];
cur_id_str = d + 4;
if (cur_id_size >= id_len)
cur_id_size = id_len - 1;
memcpy(id, cur_id_str, cur_id_size);
break;
default:
break;
}
next_desig:
d += d[3] + 4;
}
rcu_read_unlock();
return id_size;
}
EXPORT_SYMBOL(scsi_vpd_lun_id);
/*
* scsi_vpd_tpg_id - return a target port group identifier
* @sdev: SCSI device
*
* Returns the Target Port Group identifier from the information
* froom VPD page 0x83 of the device.
*
* Returns the identifier or error on failure.
*/
int scsi_vpd_tpg_id(struct scsi_device *sdev, int *rel_id)
{
const unsigned char *d;
const struct scsi_vpd *vpd_pg83;
int group_id = -EAGAIN, rel_port = -1;
rcu_read_lock();
vpd_pg83 = rcu_dereference(sdev->vpd_pg83);
if (!vpd_pg83) {
rcu_read_unlock();
return -ENXIO;
}
d = vpd_pg83->data + 4;
while (d < vpd_pg83->data + vpd_pg83->len) {
switch (d[1] & 0xf) {
case 0x4:
/* Relative target port */
rel_port = get_unaligned_be16(&d[6]);
break;
case 0x5:
/* Target port group */
group_id = get_unaligned_be16(&d[6]);
break;
default:
break;
}
d += d[3] + 4;
}
rcu_read_unlock();
if (group_id >= 0 && rel_id && rel_port != -1)
*rel_id = rel_port;
return group_id;
}
EXPORT_SYMBOL(scsi_vpd_tpg_id);