From 40fb17152c50a69dc304dd632131c2f41281ce44 Mon Sep 17 00:00:00 2001 From: Venki Pallipadi Date: Mon, 17 Nov 2008 16:11:37 -0800 Subject: [PATCH 1/2] x86: support always running TSC on Intel CPUs Impact: reward non-stop TSCs with good TSC-based clocksources, etc. Add support for CPUID_0x80000007_Bit8 on Intel CPUs as well. This bit means that the TSC is invariant with C/P/T states and always runs at constant frequency. With Intel CPUs, we have 3 classes * CPUs where TSC runs at constant rate and does not stop n C-states * CPUs where TSC runs at constant rate, but will stop in deep C-states * CPUs where TSC rate will vary based on P/T-states and TSC will stop in deep C-states. To cover these 3, one feature bit (CONSTANT_TSC) is not enough. So, add a second bit (NONSTOP_TSC). CONSTANT_TSC indicates that the TSC runs at constant frequency irrespective of P/T-states, and NONSTOP_TSC indicates that TSC does not stop in deep C-states. CPUID_0x8000000_Bit8 indicates both these feature bit can be set. We still have CONSTANT_TSC _set_ and NONSTOP_TSC _not_set_ on some older Intel CPUs, based on model checks. We can use TSC on such CPUs for time, as long as those CPUs do not support/enter deep C-states. Signed-off-by: Venkatesh Pallipadi Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/amd.c | 9 +++++++-- arch/x86/kernel/cpu/intel.c | 10 ++++++++++ arch/x86/kernel/process.c | 2 +- drivers/acpi/processor_idle.c | 6 +++--- 4 files changed, 21 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 8f1e31db2ad5..7c878f6aa919 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -283,9 +283,14 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c) { early_init_amd_mc(c); - /* c->x86_power is 8000_0007 edx. Bit 8 is constant TSC */ - if (c->x86_power & (1<<8)) + /* + * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate + * with P/T states and does not stop in deep C-states + */ + if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); + set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); + } #ifdef CONFIG_X86_64 set_cpu_cap(c, X86_FEATURE_SYSCALL32); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index cce0b6118d55..caec59437a22 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -41,6 +41,16 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) if (c->x86 == 15 && c->x86_cache_alignment == 64) c->x86_cache_alignment = 128; #endif + + /* + * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate + * with P/T states and does not stop in deep C-states + */ + if (c->x86_power & (1 << 8)) { + set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); + set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); + } + } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index c622772744d8..18c70fedba32 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -270,7 +270,7 @@ static void c1e_idle(void) rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi); if (lo & K8_INTP_C1E_ACTIVE_MASK) { c1e_detected = 1; - if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) + if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) mark_tsc_unstable("TSC halt in AMD C1E"); printk(KERN_INFO "System has AMD C1E enabled\n"); set_cpu_cap(&boot_cpu_data, X86_FEATURE_AMDC1E); diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 5f8d746a9b81..38aca048e951 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -374,15 +374,15 @@ static int tsc_halts_in_c(int state) { switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_AMD: + case X86_VENDOR_INTEL: /* * AMD Fam10h TSC will tick in all * C/P/S0/S1 states when this bit is set. */ - if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) + if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) return 0; + /*FALL THROUGH*/ - case X86_VENDOR_INTEL: - /* Several cases known where TSC halts in C2 too */ default: return state > ACPI_STATE_C1; } From 345077cd98ff5532b2d1158013c3fec7b1ae85ec Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Thu, 18 Dec 2008 18:09:21 -0800 Subject: [PATCH 2/2] x86: fix intel x86_64 llc_shared_map/cpu_llc_id anomolies Impact: fix wrong cache sharing detection on platforms supporting > 8 bit apicid's In the presence of extended topology eumeration leaf 0xb provided by cpuid, 32bit extended initial_apicid in cpuinfo_x86 struct will be updated by detect_extended_topology(). At this instance, we should also reinit the apicid (which could also potentially be extended to 32bit). With out this there will potentially be duplicate apicid's populated in the per cpu's cpuinfo_x86 struct, resulting in wrong cache sharing topology etc detected by init_intel_cacheinfo(). Reported-by: Dimitri Sivanich Signed-off-by: Suresh Siddha Acked-by: Dimitri Sivanich Signed-off-by: Ingo Molnar Cc: --- arch/x86/kernel/cpu/addon_cpuid_features.c | 8 ++++++++ arch/x86/kernel/cpu/intel.c | 8 +++++++- 2 files changed, 15 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c index ef8f831af823..2cf23634b6d9 100644 --- a/arch/x86/kernel/cpu/addon_cpuid_features.c +++ b/arch/x86/kernel/cpu/addon_cpuid_features.c @@ -120,9 +120,17 @@ void __cpuinit detect_extended_topology(struct cpuinfo_x86 *c) c->cpu_core_id = phys_pkg_id(c->initial_apicid, ht_mask_width) & core_select_mask; c->phys_proc_id = phys_pkg_id(c->initial_apicid, core_plus_mask_width); + /* + * Reinit the apicid, now that we have extended initial_apicid. + */ + c->apicid = phys_pkg_id(c->initial_apicid, 0); #else c->cpu_core_id = phys_pkg_id(ht_mask_width) & core_select_mask; c->phys_proc_id = phys_pkg_id(core_plus_mask_width); + /* + * Reinit the apicid, now that we have extended initial_apicid. + */ + c->apicid = phys_pkg_id(0); #endif c->x86_max_cores = (core_level_siblings / smp_num_siblings); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index caec59437a22..b21c37c060a2 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -252,6 +252,13 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) intel_workarounds(c); + /* + * Detect the extended topology information if available. This + * will reinitialise the initial_apicid which will be used + * in init_intel_cacheinfo() + */ + detect_extended_topology(c); + l2 = init_intel_cacheinfo(c); if (c->cpuid_level > 9) { unsigned eax = cpuid_eax(10); @@ -323,7 +330,6 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) #endif - detect_extended_topology(c); if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) { /* * let's use the legacy cpuid vector 0x1 and 0x4 for topology