powerpc: Default arch idle could cede processor on pseries

commit 363edbe2614aa90df706c0f19ccfa2a6c06af0be upstream.

When adding cpuidle support to pSeries, we introduced two
regressions:

  - The new cpuidle backend driver only works under hypervisors
    supporting the "SLPLAR" option, which isn't the case of the
    old POWER4 hypervisor and the HV "light" used on js2x blades

  - The cpuidle driver registers fairly late, meaning that for
    a significant portion of the boot process, we end up having
    all threads spinning. This slows down the boot process and
    increases the overall resource usage if the hypervisor has
    shared processors.

This fixes both by implementing a "default" idle that will cede
to the hypervisor when possible, in a very simple way without
all the bells and whisles of cpuidle.

Reported-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Acked-by: Deepthi Dharwar <deepthi@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index c11c8238797c30574c9f77f88c561af049a26ab9..54b998f2750d9744315b1f395d0eb2144280d2c7 100644 (file)
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -354,7 +354,7 @@ static int alloc_dispatch_log_kmem_cache(void)
 }
 early_initcall(alloc_dispatch_log_kmem_cache);
 
-static void pSeries_idle(void)
+static void pseries_lpar_idle(void)
 {
        /* This would call on the cpuidle framework, and the back-end pseries
         * driver to  go to idle states
@@ -362,10 +362,22 @@ static void pSeries_idle(void)
        if (cpuidle_idle_call()) {
                /* On error, execute default handler
                 * to go into low thread priority and possibly
-                * low power mode.
+                * low power mode by cedeing processor to hypervisor
                 */
-               HMT_low();
-               HMT_very_low();
+
+               /* Indicate to hypervisor that we are idle. */
+               get_lppaca()->idle = 1;
+
+               /*
+                * Yield the processor to the hypervisor.  We return if
+                * an external interrupt occurs (which are driven prior
+                * to returning here) or if a prod occurs from another
+                * processor. When returning here, external interrupts
+                * are enabled.
+                */
+               cede_processor();
+
+               get_lppaca()->idle = 0;
        }
 }
 
@@ -456,15 +468,14 @@ static void __init pSeries_setup_arch(void)
 
        pSeries_nvram_init();
 
-       if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
+       if (firmware_has_feature(FW_FEATURE_LPAR)) {
                vpa_init(boot_cpuid);
-               ppc_md.power_save = pSeries_idle;
-       }
-
-       if (firmware_has_feature(FW_FEATURE_LPAR))
+               ppc_md.power_save = pseries_lpar_idle;
                ppc_md.enable_pmcs = pseries_lpar_enable_pmcs;
-       else
+       } else {
+               /* No special idle routine */
                ppc_md.enable_pmcs = power4_enable_pmcs;
+       }
 
        ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare;