*
* When the host needs to go down, all users must be quiesced and their
* memory freed. This is accomplished by putting the contexts in error
- * state which will notify the user and let them 'drive' the tear-down.
+ * state which will notify the user and let them 'drive' the tear down.
* Meanwhile, this routine camps until all user contexts have been removed.
*/
void cxlflash_stop_term_user_contexts(struct cxlflash_cfg *cfg)
dev_dbg(dev, "%s: Wait for user contexts to quiesce...\n",
__func__);
- wake_up_all(&cfg->limbo_waitq);
+ wake_up_all(&cfg->reset_waitq);
ssleep(1);
}
}
if (likely(ctxid < MAX_CONTEXT)) {
while (true) {
- rc = mutex_lock_interruptible(&cfg->ctx_tbl_list_mutex);
- if (rc)
- goto out;
-
+ mutex_lock(&cfg->ctx_tbl_list_mutex);
ctxi = cfg->ctx_tbl[ctxid];
if (ctxi)
if ((file && (ctxi->file != file)) ||
{
struct device *dev = &cfg->dev->dev;
struct afu *afu = cfg->afu;
- struct sisl_ctrl_map *ctrl_map = ctxi->ctrl_map;
+ struct sisl_ctrl_map __iomem *ctrl_map = ctxi->ctrl_map;
int rc = 0;
u64 val;
* @sdev: SCSI device associated with LUN.
* @lli: LUN destined for capacity request.
*
+ * The READ_CAP16 can take quite a while to complete. Should an EEH occur while
+ * in scsi_execute(), the EEH handler will attempt to recover. As part of the
+ * recovery, the handler drains all currently running ioctls, waiting until they
+ * have completed before proceeding with a reset. As this routine is used on the
+ * ioctl path, this can create a condition where the EEH handler becomes stuck,
+ * infinitely waiting for this ioctl thread. To avoid this behavior, temporarily
+ * unmark this thread as an ioctl thread by releasing the ioctl read semaphore.
+ * This will allow the EEH handler to proceed with a recovery while this thread
+ * is still running. Once the scsi_execute() returns, reacquire the ioctl read
+ * semaphore and check the adapter state in case it changed while inside of
+ * scsi_execute(). The state check will wait if the adapter is still being
+ * recovered or return a failure if the recovery failed. In the event that the
+ * adapter reset failed, simply return the failure as the ioctl would be unable
+ * to continue.
+ *
+ * Note that the above puts a requirement on this routine to only be called on
+ * an ioctl thread.
+ *
* Return: 0 on success, -errno on failure
*/
static int read_cap16(struct scsi_device *sdev, struct llun_info *lli)
int rc = 0;
int result = 0;
int retry_cnt = 0;
- u32 tout = (MC_DISCOVERY_TIMEOUT * HZ);
+ u32 to = CMD_TIMEOUT * HZ;
retry:
cmd_buf = kzalloc(CMD_BUFSIZE, GFP_KERNEL);
dev_dbg(dev, "%s: %ssending cmd(0x%x)\n", __func__,
retry_cnt ? "re" : "", scsi_cmd[0]);
+ /* Drop the ioctl read semahpore across lengthy call */
+ up_read(&cfg->ioctl_rwsem);
result = scsi_execute(sdev, scsi_cmd, DMA_FROM_DEVICE, cmd_buf,
- CMD_BUFSIZE, sense_buf, tout, 5, 0, NULL);
+ CMD_BUFSIZE, sense_buf, to, CMD_RETRIES, 0, NULL);
+ down_read(&cfg->ioctl_rwsem);
+ rc = check_state(cfg);
+ if (rc) {
+ dev_err(dev, "%s: Failed state! result=0x08%X\n",
+ __func__, result);
+ rc = -ENODEV;
+ goto out;
+ }
if (driver_byte(result) == DRIVER_SENSE) {
result &= ~(0xFF<<24); /* DRIVER_SENSE is not an error */
* as the buffer is allocated on an aligned boundary.
*/
mutex_lock(&gli->mutex);
- gli->max_lba = be64_to_cpu(*((u64 *)&cmd_buf[0]));
- gli->blk_len = be32_to_cpu(*((u32 *)&cmd_buf[8]));
+ gli->max_lba = be64_to_cpu(*((__be64 *)&cmd_buf[0]));
+ gli->blk_len = be32_to_cpu(*((__be32 *)&cmd_buf[8]));
mutex_unlock(&gli->mutex);
out:
kfree(ctxi->rht_needs_ws);
kfree(ctxi->rht_lun);
kfree(ctxi);
- atomic_dec_if_positive(&cfg->num_user_contexts);
}
/**
struct afu *afu = cfg->afu;
struct ctx_info *ctxi = NULL;
struct llun_info **lli = NULL;
- bool *ws = NULL;
+ u8 *ws = NULL;
struct sisl_rht_entry *rhte;
ctxi = kzalloc(sizeof(*ctxi), GFP_KERNEL);
INIT_LIST_HEAD(&ctxi->luns);
INIT_LIST_HEAD(&ctxi->list); /* initialize for list_empty() */
- atomic_inc(&cfg->num_user_contexts);
mutex_lock(&ctxi->mutex);
out:
return ctxi;
sys_close(lfd);
}
+ /* Release the sdev reference that bound this LUN to the context */
+ scsi_device_put(sdev);
+
out:
if (put_ctx)
put_context(ctxi);
return rc;
}
-/*
- * Local fops for adapter file descriptor
- */
-static const struct file_operations cxlflash_cxl_fops = {
+const struct file_operations cxlflash_cxl_fops = {
.owner = THIS_MODULE,
.mmap = cxlflash_cxl_mmap,
.release = cxlflash_cxl_release,
.owner = THIS_MODULE,
};
+/**
+ * check_state() - checks and responds to the current adapter state
+ * @cfg: Internal structure associated with the host.
+ *
+ * This routine can block and should only be used on process context.
+ * It assumes that the caller is an ioctl thread and holding the ioctl
+ * read semaphore. This is temporarily let up across the wait to allow
+ * for draining actively running ioctls. Also note that when waking up
+ * from waiting in reset, the state is unknown and must be checked again
+ * before proceeding.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int check_state(struct cxlflash_cfg *cfg)
+{
+ struct device *dev = &cfg->dev->dev;
+ int rc = 0;
+
+retry:
+ switch (cfg->state) {
+ case STATE_RESET:
+ dev_dbg(dev, "%s: Reset state, going to wait...\n", __func__);
+ up_read(&cfg->ioctl_rwsem);
+ rc = wait_event_interruptible(cfg->reset_waitq,
+ cfg->state != STATE_RESET);
+ down_read(&cfg->ioctl_rwsem);
+ if (unlikely(rc))
+ break;
+ goto retry;
+ case STATE_FAILTERM:
+ dev_dbg(dev, "%s: Failed/Terminating!\n", __func__);
+ rc = -ENODEV;
+ break;
+ default:
+ break;
+ }
+
+ return rc;
+}
+
/**
* cxlflash_disk_attach() - attach a LUN to a context
* @sdev: SCSI device associated with LUN.
int fd = -1;
- /* On first attach set fileops */
- if (atomic_read(&cfg->num_user_contexts) == 0)
- cfg->cxl_fops = cxlflash_cxl_fops;
-
if (attach->num_interrupts > 4) {
dev_dbg(dev, "%s: Cannot support this many interrupts %llu\n",
__func__, attach->num_interrupts);
}
}
+ rc = scsi_device_get(sdev);
+ if (unlikely(rc)) {
+ dev_err(dev, "%s: Unable to get sdev reference!\n", __func__);
+ goto out;
+ }
+
lun_access = kzalloc(sizeof(*lun_access), GFP_KERNEL);
if (unlikely(!lun_access)) {
dev_err(dev, "%s: Unable to allocate lun_access!\n", __func__);
rc = -ENOMEM;
- goto out;
+ goto err0;
}
lun_access->lli = lli;
dev_err(dev, "%s: Could not initialize context %p\n",
__func__, ctx);
rc = -ENODEV;
- goto err0;
+ goto err1;
}
ctxid = cxl_process_element(ctx);
if (unlikely((ctxid > MAX_CONTEXT) || (ctxid < 0))) {
dev_err(dev, "%s: ctxid (%d) invalid!\n", __func__, ctxid);
rc = -EPERM;
- goto err1;
+ goto err2;
}
file = cxl_get_fd(ctx, &cfg->cxl_fops, &fd);
if (unlikely(fd < 0)) {
rc = -ENODEV;
dev_err(dev, "%s: Could not get file descriptor\n", __func__);
- goto err1;
+ goto err2;
}
/* Translate read/write O_* flags from fcntl.h to AFU permission bits */
if (unlikely(!ctxi)) {
dev_err(dev, "%s: Failed to create context! (%d)\n",
__func__, ctxid);
- goto err2;
+ goto err3;
}
work = &ctxi->work;
if (unlikely(rc)) {
dev_dbg(dev, "%s: Could not start context rc=%d\n",
__func__, rc);
- goto err3;
+ goto err4;
}
rc = afu_attach(cfg, ctxi);
if (unlikely(rc)) {
dev_err(dev, "%s: Could not attach AFU rc %d\n", __func__, rc);
- goto err4;
+ goto err5;
}
/*
attach->block_size = gli->blk_len;
attach->mmio_size = sizeof(afu->afu_map->hosts[0].harea);
attach->last_lba = gli->max_lba;
- attach->max_xfer = (sdev->host->max_sectors * 512) / gli->blk_len;
+ attach->max_xfer = sdev->host->max_sectors * MAX_SECTOR_UNIT;
+ attach->max_xfer /= gli->blk_len;
out:
attach->adap_fd = fd;
__func__, ctxid, fd, attach->block_size, rc, attach->last_lba);
return rc;
-err4:
+err5:
cxl_stop_context(ctx);
-err3:
+err4:
put_context(ctxi);
destroy_context(cfg, ctxi);
ctxi = NULL;
-err2:
+err3:
/*
* Here, we're overriding the fops with a dummy all-NULL fops because
* fput() calls the release fop, which will cause us to mistakenly
fput(file);
put_unused_fd(fd);
fd = -1;
-err1:
+err2:
cxl_release_context(ctx);
-err0:
+err1:
kfree(lun_access);
+err0:
+ scsi_device_put(sdev);
goto out;
}
goto out;
}
-/**
- * check_state() - checks and responds to the current adapter state
- * @cfg: Internal structure associated with the host.
- *
- * This routine can block and should only be used on process context.
- * Note that when waking up from waiting in limbo, the state is unknown
- * and must be checked again before proceeding.
- *
- * Return: 0 on success, -errno on failure
- */
-static int check_state(struct cxlflash_cfg *cfg)
-{
- struct device *dev = &cfg->dev->dev;
- int rc = 0;
-
-retry:
- switch (cfg->state) {
- case STATE_LIMBO:
- dev_dbg(dev, "%s: Limbo, going to wait...\n", __func__);
- rc = wait_event_interruptible(cfg->limbo_waitq,
- cfg->state != STATE_LIMBO);
- if (unlikely(rc))
- break;
- goto retry;
- case STATE_FAILTERM:
- dev_dbg(dev, "%s: Failed/Terminating!\n", __func__);
- rc = -ENODEV;
- break;
- default:
- break;
- }
-
- return rc;
-}
-
/**
* cxlflash_afu_recover() - initiates AFU recovery
* @sdev: SCSI device associated with LUN.
* quite possible for this routine to act as the kernel's EEH detection
* source (MMIO read of mbox_r). Because of this, there is a window of
* time where an EEH might have been detected but not yet 'serviced'
- * (callback invoked, causing the device to enter limbo state). To avoid
+ * (callback invoked, causing the device to enter reset state). To avoid
* looping in this routine during that window, a 1 second sleep is in place
* between the time the MMIO failure is detected and the time a wait on the
- * limbo wait queue is attempted via check_state().
+ * reset wait queue is attempted via check_state().
*
* Return: 0 on success, -errno on failure
*/
/* Test if in error state */
reg = readq_be(&afu->ctrl_map->mbox_r);
if (reg == -1) {
- dev_dbg(dev, "%s: MMIO read fail! Wait for recovery...\n",
- __func__);
- mutex_unlock(&ctxi->mutex);
+ dev_dbg(dev, "%s: MMIO fail, wait for recovery.\n", __func__);
+
+ /*
+ * Before checking the state, put back the context obtained with
+ * get_context() as it is no longer needed and sleep for a short
+ * period of time (see prolog notes).
+ */
+ put_context(ctxi);
ctxi = NULL;
ssleep(1);
rc = check_state(cfg);
* inquiry (i.e. the Unit attention is due to the WWN changing).
*/
if (verify->hint & DK_CXLFLASH_VERIFY_HINT_SENSE) {
+ /* Can't hold mutex across process_sense/read_cap16,
+ * since we could have an intervening EEH event.
+ */
+ ctxi->unavail = true;
+ mutex_unlock(&ctxi->mutex);
rc = process_sense(sdev, verify);
if (unlikely(rc)) {
dev_err(dev, "%s: Failed to validate sense data (%d)\n",
__func__, rc);
+ mutex_lock(&ctxi->mutex);
+ ctxi->unavail = false;
goto out;
}
+ mutex_lock(&ctxi->mutex);
+ ctxi->unavail = false;
}
switch (gli->mode) {
* @cmd: IOCTL command.
* @arg: Userspace ioctl data structure.
*
+ * A read/write semaphore is used to implement a 'drain' of currently
+ * running ioctls. The read semaphore is taken at the beginning of each
+ * ioctl thread and released upon concluding execution. Additionally the
+ * semaphore should be released and then reacquired in any ioctl execution
+ * path which will wait for an event to occur that is outside the scope of
+ * the ioctl (i.e. an adapter reset). To drain the ioctls currently running,
+ * a thread simply needs to acquire the write semaphore.
+ *
* Return: 0 on success, -errno on failure
*/
int cxlflash_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
{sizeof(struct dk_cxlflash_clone), (sioctl)cxlflash_disk_clone},
};
+ /* Hold read semaphore so we can drain if needed */
+ down_read(&cfg->ioctl_rwsem);
+
/* Restrict command set to physical support only for internal LUN */
if (afu->internal_lun)
switch (cmd) {
/* fall through to exit */
cxlflash_ioctl_exit:
+ up_read(&cfg->ioctl_rwsem);
if (unlikely(rc && known_ioctl))
dev_err(dev, "%s: ioctl %s (%08X) on dev(%d/%d/%d/%llu) "
"returned rc %d\n", __func__,
projects / firefly-linux-kernel-4.4.55.git / blobdiff