Searched hist:d4e58e59 (Results 1 – 4 of 4) sorted by relevance
| /openbmc/linux/arch/powerpc/platforms/powernv/ |
| H A D | Kconfig | d4e58e59 Wed Jun 11 00:59:28 CDT 2014 Michael Neuling <mikey@neuling.org> powerpc/powernv: Enable POWER8 doorbell IPIs
This patch enables POWER8 doorbell IPIs on powernv.
Since doorbells can only IPI within a core, we test to see when we can use
doorbells and if not we fall back to XICS. This also enables hypervisor
doorbells to wakeup us up from nap/sleep via the LPCR PECEDH bit.
Based on tests by Anton, the best case IPI latency between two threads dropped
from 894ns to 512ns.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
d4e58e59 Wed Jun 11 00:59:28 CDT 2014 Michael Neuling <mikey@neuling.org> powerpc/powernv: Enable POWER8 doorbell IPIs
This patch enables POWER8 doorbell IPIs on powernv.
Since doorbells can only IPI within a core, we test to see when we can use
doorbells and if not we fall back to XICS. This also enables hypervisor
doorbells to wakeup us up from nap/sleep via the LPCR PECEDH bit.
Based on tests by Anton, the best case IPI latency between two threads dropped
from 894ns to 512ns.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
|
| H A D | smp.c | d4e58e59 Wed Jun 11 00:59:28 CDT 2014 Michael Neuling <mikey@neuling.org> powerpc/powernv: Enable POWER8 doorbell IPIs
This patch enables POWER8 doorbell IPIs on powernv.
Since doorbells can only IPI within a core, we test to see when we can use
doorbells and if not we fall back to XICS. This also enables hypervisor
doorbells to wakeup us up from nap/sleep via the LPCR PECEDH bit.
Based on tests by Anton, the best case IPI latency between two threads dropped
from 894ns to 512ns.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
d4e58e59 Wed Jun 11 00:59:28 CDT 2014 Michael Neuling <mikey@neuling.org> powerpc/powernv: Enable POWER8 doorbell IPIs
This patch enables POWER8 doorbell IPIs on powernv.
Since doorbells can only IPI within a core, we test to see when we can use
doorbells and if not we fall back to XICS. This also enables hypervisor
doorbells to wakeup us up from nap/sleep via the LPCR PECEDH bit.
Based on tests by Anton, the best case IPI latency between two threads dropped
from 894ns to 512ns.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
|
| /openbmc/linux/arch/powerpc/sysdev/xics/ |
| H A D | icp-native.c | d4e58e59 Wed Jun 11 00:59:28 CDT 2014 Michael Neuling <mikey@neuling.org> powerpc/powernv: Enable POWER8 doorbell IPIs
This patch enables POWER8 doorbell IPIs on powernv.
Since doorbells can only IPI within a core, we test to see when we can use
doorbells and if not we fall back to XICS. This also enables hypervisor
doorbells to wakeup us up from nap/sleep via the LPCR PECEDH bit.
Based on tests by Anton, the best case IPI latency between two threads dropped
from 894ns to 512ns.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
|
| /openbmc/linux/arch/powerpc/platforms/pseries/ |
| H A D | Kconfig | d4e58e59 Wed Jun 11 00:59:28 CDT 2014 Michael Neuling <mikey@neuling.org> powerpc/powernv: Enable POWER8 doorbell IPIs
This patch enables POWER8 doorbell IPIs on powernv.
Since doorbells can only IPI within a core, we test to see when we can use
doorbells and if not we fall back to XICS. This also enables hypervisor
doorbells to wakeup us up from nap/sleep via the LPCR PECEDH bit.
Based on tests by Anton, the best case IPI latency between two threads dropped
from 894ns to 512ns.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
d4e58e59 Wed Jun 11 00:59:28 CDT 2014 Michael Neuling <mikey@neuling.org> powerpc/powernv: Enable POWER8 doorbell IPIs
This patch enables POWER8 doorbell IPIs on powernv.
Since doorbells can only IPI within a core, we test to see when we can use
doorbells and if not we fall back to XICS. This also enables hypervisor
doorbells to wakeup us up from nap/sleep via the LPCR PECEDH bit.
Based on tests by Anton, the best case IPI latency between two threads dropped
from 894ns to 512ns.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
|