If the POWER firmware detects a bad CPU core, it will "GUARD" it out, marking it disabled. Any attempt to spin up a bad CPU will trigger a panic later on when waiting for threads on said core to wake up. Support limping along on fewer cores instead. |
||
---|---|---|
.. | ||
opal_async.c | ||
opal_console.c | ||
opal_dbg.c | ||
opal_dev.c | ||
opal_flash.c | ||
opal_hmi.c | ||
opal_i2c.c | ||
opal_i2cm.c | ||
opal_nvram.c | ||
opal_pci.c | ||
opal_sensor.c | ||
opal.c | ||
opal.h | ||
opalcall.S | ||
platform_powernv.c | ||
powernv_centaur.c | ||
powernv_xscom.c | ||
xive.c |