Commit b95cd2cd authored by Gavin Shan's avatar Gavin Shan Committed by Benjamin Herrenschmidt

powerpc/eeh: Allow to check fenced PHB proactively

It's meaningless to handle frozen PE if we already had fenced PHB.
The patch intends to check the PHB state before checking PE. If the
PHB has been put into fenced state, we need take care of that firstly.
Signed-off-by: default avatarGavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: default avatarBenjamin Herrenschmidt <benh@kernel.crashing.org>
parent be7e7446
...@@ -269,6 +269,58 @@ static inline unsigned long eeh_token_to_phys(unsigned long token) ...@@ -269,6 +269,58 @@ static inline unsigned long eeh_token_to_phys(unsigned long token)
return pa | (token & (PAGE_SIZE-1)); return pa | (token & (PAGE_SIZE-1));
} }
/*
* On PowerNV platform, we might already have fenced PHB there.
* For that case, it's meaningless to recover frozen PE. Intead,
* We have to handle fenced PHB firstly.
*/
static int eeh_phb_check_failure(struct eeh_pe *pe)
{
struct eeh_pe *phb_pe;
unsigned long flags;
int ret;
if (!eeh_probe_mode_dev())
return -EPERM;
/* Find the PHB PE */
phb_pe = eeh_phb_pe_get(pe->phb);
if (!phb_pe) {
pr_warning("%s Can't find PE for PHB#%d\n",
__func__, pe->phb->global_number);
return -EEXIST;
}
/* If the PHB has been in problematic state */
eeh_serialize_lock(&flags);
if (phb_pe->state & (EEH_PE_ISOLATED | EEH_PE_PHB_DEAD)) {
ret = 0;
goto out;
}
/* Check PHB state */
ret = eeh_ops->get_state(phb_pe, NULL);
if ((ret < 0) ||
(ret == EEH_STATE_NOT_SUPPORT) ||
(ret & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) ==
(EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) {
ret = 0;
goto out;
}
/* Isolate the PHB and send event */
eeh_pe_state_mark(phb_pe, EEH_PE_ISOLATED);
eeh_serialize_unlock(flags);
eeh_send_failure_event(phb_pe);
WARN(1, "EEH: PHB failure detected\n");
return 1;
out:
eeh_serialize_unlock(flags);
return ret;
}
/** /**
* eeh_dev_check_failure - Check if all 1's data is due to EEH slot freeze * eeh_dev_check_failure - Check if all 1's data is due to EEH slot freeze
* @edev: eeh device * @edev: eeh device
...@@ -319,6 +371,14 @@ int eeh_dev_check_failure(struct eeh_dev *edev) ...@@ -319,6 +371,14 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
return 0; return 0;
} }
/*
* On PowerNV platform, we might already have fenced PHB
* there and we need take care of that firstly.
*/
ret = eeh_phb_check_failure(pe);
if (ret > 0)
return ret;
/* If we already have a pending isolation event for this /* If we already have a pending isolation event for this
* slot, we know it's bad already, we don't need to check. * slot, we know it's bad already, we don't need to check.
* Do this checking under a lock; as multiple PCI devices * Do this checking under a lock; as multiple PCI devices
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment