diff options
author | Oliver O'Halloran <oohall@gmail.com> | 2019-09-03 20:15:56 +1000 |
---|---|---|
committer | Michael Ellerman <mpe@ellerman.id.au> | 2019-09-05 14:22:38 +1000 |
commit | 25baf3d81614b0b8ca8958f4d6f111ccaaaad578 (patch) | |
tree | 6c8e859c08e05b14b1c564282563f95b91da2d86 /arch/powerpc/kernel/eeh_driver.c | |
parent | b104af5a7687060792ca398bb86b033057afce75 (diff) |
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
Diffstat (limited to 'arch/powerpc/kernel/eeh_driver.c')
-rw-r--r-- | arch/powerpc/kernel/eeh_driver.c | 38 |
1 files changed, 37 insertions, 1 deletions
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 52ce7584af43..0d34cc12c529 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -863,8 +863,44 @@ void eeh_handle_normal_event(struct eeh_pe *pe) if (eeh_slot_presence_check(edev->pdev)) devices++; - if (!devices) + if (!devices) { + pr_debug("EEH: Frozen PHB#%x-PE#%x is empty!\n", + pe->phb->global_number, pe->addr); goto out; /* nothing to recover */ + } + + /* Log the event */ + if (pe->type & EEH_PE_PHB) { + pr_err("EEH: PHB#%x failure detected, location: %s\n", + pe->phb->global_number, eeh_pe_loc_get(pe)); + } else { + struct eeh_pe *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)); + } + + /* + * Print the saved stack trace now that we've verified there's + * something to recover. + */ + if (pe->trace_entries) { + void **ptrs = (void **) pe->stack_trace; + int i; + + pr_err("EEH: Frozen PHB#%x-PE#%x detected\n", + pe->phb->global_number, pe->addr); + + /* FIXME: Use the same format as dump_stack() */ + pr_err("EEH: Call Trace:\n"); + for (i = 0; i < pe->trace_entries; i++) + pr_err("EEH: [%pK] %pS\n", ptrs[i], ptrs[i]); + + pe->trace_entries = 0; + } + eeh_pe_update_time_stamp(pe); pe->freeze_count++; |