powerpc/eeh: Defer printing stack trace

Currently we print a stack trace in the event handler to help with
debugging EEH issues. In the case of suprise hot-unplug this is unneeded,
so we want to prevent printing the stack trace unless we know it's due to
an actual device error. To accomplish this, we can save a stack trace at
the point of detection and only print it once the EEH recovery handler has
determined the freeze was due to an actual error.

Since the whole point of this is to prevent spurious EEH output we also
move a few prints out of the detection thread, or mark them as pr_debug
so anyone interested can get output from the eeh_check_dev_failure()
if they want.

Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190903101605.2890-6-oohall@gmail.com

1 files changed, 4 insertions, 11 deletions

diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 7b2755f5c6fd..398def61f8a6 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -420,11 +420,9 @@ static int eeh_phb_check_failure(struct eeh_pe *pe)
 	eeh_pe_mark_isolated(phb_pe);
 	eeh_serialize_unlock(flags);
 
-	pr_err("EEH: PHB#%x failure detected, location: %s\n",
+	pr_debug("EEH: PHB#%x failure detected, location: %s\n",
 		phb_pe->phb->global_number, eeh_pe_loc_get(phb_pe));
-	dump_stack();
 	eeh_send_failure_event(phb_pe);
-
 	return 1;
 out:
 	eeh_serialize_unlock(flags);
@@ -451,7 +449,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
 	unsigned long flags;
 	struct device_node *dn;
 	struct pci_dev *dev;
-	struct eeh_pe *pe, *parent_pe, *phb_pe;
+	struct eeh_pe *pe, *parent_pe;
 	int rc = 0;
 	const char *location = NULL;
 
@@ -581,13 +579,8 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
 	 * a stack trace will help the device-driver authors figure
 	 * out what happened.  So print that out.
 	 */
-	phb_pe = eeh_phb_pe_get(pe->phb);
-	pr_err("EEH: Frozen PHB#%x-PE#%x detected\n",
-	       pe->phb->global_number, pe->addr);
-	pr_err("EEH: PE location: %s, PHB location: %s\n",
-	       eeh_pe_loc_get(pe), eeh_pe_loc_get(phb_pe));
-	dump_stack();
-
+	pr_debug("EEH: %s: Frozen PHB#%x-PE#%x detected\n",
+		__func__, pe->phb->global_number, pe->addr);
 	eeh_send_failure_event(pe);
 
 	return 1;