b2e601d14d
We currently have a race when scheduling a context to a SPE - after we have found a runnable context in spusched_tick, the same context may have been scheduled by spu_activate(). This may result in a panic if we try to unschedule a context that has been freed in the meantime. This change exits spu_schedule() if the context has already been scheduled, so we don't end up scheduling it twice. Signed-off-by: Andre Detsch <adetsch@br.ibm.com> Signed-off-by: Jeremy Kerr <jk@ozlabs.org> |
||
|---|---|---|
| .. | ||
| spufs | ||
| Kconfig | ||
| Makefile | ||
| axon_msi.c | ||
| beat.c | ||
| beat.h | ||
| beat_htab.c | ||
| beat_hvCall.S | ||
| beat_interrupt.c | ||
| beat_interrupt.h | ||
| beat_iommu.c | ||
| beat_smp.c | ||
| beat_spu_priv1.c | ||
| beat_syscall.h | ||
| beat_udbg.c | ||
| beat_wrapper.h | ||
| cbe_cpufreq.c | ||
| cbe_cpufreq.h | ||
| cbe_cpufreq_pervasive.c | ||
| cbe_cpufreq_pmi.c | ||
| cbe_powerbutton.c | ||
| cbe_regs.c | ||
| cbe_thermal.c | ||
| celleb_pci.c | ||
| celleb_pci.h | ||
| celleb_scc.h | ||
| celleb_scc_epci.c | ||
| celleb_scc_pciex.c | ||
| celleb_scc_sio.c | ||
| celleb_scc_uhc.c | ||
| celleb_setup.c | ||
| cpufreq_spudemand.c | ||
| interrupt.c | ||
| interrupt.h | ||
| io-workarounds.c | ||
| io-workarounds.h | ||
| iommu.c | ||
| pervasive.c | ||
| pervasive.h | ||
| pmu.c | ||
| ras.c | ||
| ras.h | ||
| setup.c | ||
| smp.c | ||
| spider-pci.c | ||
| spider-pic.c | ||
| spu_base.c | ||
| spu_callbacks.c | ||
| spu_fault.c | ||
| spu_manage.c | ||
| spu_notify.c | ||
| spu_priv1_mmio.c | ||
| spu_priv1_mmio.h | ||
| spu_syscalls.c | ||