Merge branch 'oprofile/core' into oprofile/x86

Conflicts:
	arch/x86/oprofile/op_model_amd.c

Signed-off-by: Robert Richter <robert.richter@amd.com>

1 files changed, 103 insertions, 15 deletions

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8b3bfc4dd708..dfb50890b5b7 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -62,7 +62,7 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/mtrr.h>
-#include <asm/vmi.h>
+#include <asm/mwait.h>
 #include <asm/apic.h>
 #include <asm/setup.h>
 #include <asm/uv/uv.h>
@@ -311,7 +311,6 @@ notrace static void __cpuinit start_secondary(void *unused)
         __flush_tlb_all();
 #endif
 
-        vmi_bringup();
         cpu_init();
         preempt_disable();
         smp_callin();
@@ -324,9 +323,9 @@ notrace static void __cpuinit start_secondary(void *unused)
         check_tsc_sync_target();
 
         if (nmi_watchdog == NMI_IO_APIC) {
-                legacy_pic->chip->mask(0);
+                legacy_pic->mask(0);
                 enable_NMI_through_LVT0();
-                legacy_pic->chip->unmask(0);
+                legacy_pic->unmask(0);
         }
 
         /* This must be done before setting cpu_online_mask */
@@ -397,6 +396,19 @@ void __cpuinit smp_store_cpu_info(int id)
                 identify_secondary_cpu(c);
 }
 
+static void __cpuinit link_thread_siblings(int cpu1, int cpu2)
+{
+        struct cpuinfo_x86 *c1 = &cpu_data(cpu1);
+        struct cpuinfo_x86 *c2 = &cpu_data(cpu2);
+
+        cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2));
+        cpumask_set_cpu(cpu2, cpu_sibling_mask(cpu1));
+        cpumask_set_cpu(cpu1, cpu_core_mask(cpu2));
+        cpumask_set_cpu(cpu2, cpu_core_mask(cpu1));
+        cpumask_set_cpu(cpu1, c2->llc_shared_map);
+        cpumask_set_cpu(cpu2, c1->llc_shared_map);
+}
+
 
 void __cpuinit set_cpu_sibling_map(int cpu)
 {
@@ -409,14 +421,13 @@ void __cpuinit set_cpu_sibling_map(int cpu)
                 for_each_cpu(i, cpu_sibling_setup_mask) {
                         struct cpuinfo_x86 *o = &cpu_data(i);
 
-                        if (c->phys_proc_id == o->phys_proc_id &&
-                            c->cpu_core_id == o->cpu_core_id) {
-                                cpumask_set_cpu(i, cpu_sibling_mask(cpu));
-                                cpumask_set_cpu(cpu, cpu_sibling_mask(i));
-                                cpumask_set_cpu(i, cpu_core_mask(cpu));
-                                cpumask_set_cpu(cpu, cpu_core_mask(i));
-                                cpumask_set_cpu(i, c->llc_shared_map);
-                                cpumask_set_cpu(cpu, o->llc_shared_map);
+                        if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
+                                if (c->phys_proc_id == o->phys_proc_id &&
+                                    c->compute_unit_id == o->compute_unit_id)
+                                        link_thread_siblings(cpu, i);
+                        } else if (c->phys_proc_id == o->phys_proc_id &&
+                                   c->cpu_core_id == o->cpu_core_id) {
+                                link_thread_siblings(cpu, i);
                         }
                 }
         } else {
@@ -1109,8 +1120,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
         }
         set_cpu_sibling_map(0);
 
-        enable_IR_x2apic();
-        default_setup_apic_routing();
 
         if (smp_sanity_check(max_cpus) < 0) {
                 printk(KERN_INFO "SMP disabled\n");
@@ -1118,6 +1127,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
                 goto out;
         }
 
+        default_setup_apic_routing();
+
         preempt_disable();
         if (read_apic_id() != boot_cpu_physical_apicid) {
                 panic("Boot APIC ID in local APIC unexpected (%d vs %d)",
@@ -1383,11 +1394,88 @@ void play_dead_common(void)
         local_irq_disable();
 }
 
+/*
+ * We need to flush the caches before going to sleep, lest we have
+ * dirty data in our caches when we come back up.
+ */
+static inline void mwait_play_dead(void)
+{
+        unsigned int eax, ebx, ecx, edx;
+        unsigned int highest_cstate = 0;
+        unsigned int highest_subcstate = 0;
+        int i;
+        void *mwait_ptr;
+
+        if (!cpu_has(&current_cpu_data, X86_FEATURE_MWAIT))
+                return;
+        if (!cpu_has(&current_cpu_data, X86_FEATURE_CLFLSH))
+                return;
+        if (current_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
+                return;
+
+        eax = CPUID_MWAIT_LEAF;
+        ecx = 0;
+        native_cpuid(&eax, &ebx, &ecx, &edx);
+
+        /*
+         * eax will be 0 if EDX enumeration is not valid.
+         * Initialized below to cstate, sub_cstate value when EDX is valid.
+         */
+        if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
+                eax = 0;
+        } else {
+                edx >>= MWAIT_SUBSTATE_SIZE;
+                for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
+                        if (edx & MWAIT_SUBSTATE_MASK) {
+                                highest_cstate = i;
+                                highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
+                        }
+                }
+                eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
+                        (highest_subcstate - 1);
+        }
+
+        /*
+         * This should be a memory location in a cache line which is
+         * unlikely to be touched by other processors.  The actual
+         * content is immaterial as it is not actually modified in any way.
+         */
+        mwait_ptr = &current_thread_info()->flags;
+
+        wbinvd();
+
+        while (1) {
+                /*
+                 * The CLFLUSH is a workaround for erratum AAI65 for
+                 * the Xeon 7400 series.  It's not clear it is actually
+                 * needed, but it should be harmless in either case.
+                 * The WBINVD is insufficient due to the spurious-wakeup
+                 * case where we return around the loop.
+                 */
+                clflush(mwait_ptr);
+                __monitor(mwait_ptr, 0, 0);
+                mb();
+                __mwait(eax, 0);
+        }
+}
+
+static inline void hlt_play_dead(void)
+{
+        if (current_cpu_data.x86 >= 4)
+                wbinvd();
+
+        while (1) {
+                native_halt();
+        }
+}
+
 void native_play_dead(void)
 {
         play_dead_common();
         tboot_shutdown(TB_SHUTDOWN_WFS);
-        wbinvd_halt();
+
+        mwait_play_dead();      /* Only returns on failure */
+        hlt_play_dead();
 }
 
 #else /* ... !CONFIG_HOTPLUG_CPU */