Merge branch 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux

Pull idle update from Len Brown:
 "Add support for new Haswell-ULT CPU idle power states"

* 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux:
  intel_idle: initial C8, C9, C10 support
  tools/power turbostat: display C8, C9, C10 residency

4 files changed, 78 insertions, 2 deletions

diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index b3a4866..2af848d 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -120,6 +120,9 @@
 #define MSR_CORE_C6_RESIDENCY		0x000003fd
 #define MSR_CORE_C7_RESIDENCY		0x000003fe
 #define MSR_PKG_C2_RESIDENCY		0x0000060d
+#define MSR_PKG_C8_RESIDENCY		0x00000630
+#define MSR_PKG_C9_RESIDENCY		0x00000631
+#define MSR_PKG_C10_RESIDENCY		0x00000632
 
 /* Run Time Average Power Limiting (RAPL) Interface */
 
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 0e8fab1..fa6964d 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -273,6 +273,27 @@ static struct cpuidle_state hsw_cstates[CPUIDLE_STATE_MAX] = {
 		.target_residency = 500,
 		.enter = &intel_idle },
 	{
+		.name = "C8-HSW",
+		.desc = "MWAIT 0x40",
+		.flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 300,
+		.target_residency = 900,
+		.enter = &intel_idle },
+	{
+		.name = "C9-HSW",
+		.desc = "MWAIT 0x50",
+		.flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 600,
+		.target_residency = 1800,
+		.enter = &intel_idle },
+	{
+		.name = "C10-HSW",
+		.desc = "MWAIT 0x60",
+		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 2600,
+		.target_residency = 7700,
+		.enter = &intel_idle },
+	{
 		.enter = NULL }
 };
 
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 3c86faa..8f04062 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -17,7 +17,7 @@
 #include <linux/completion.h>
 #include <linux/hrtimer.h>
 
-#define CPUIDLE_STATE_MAX	8
+#define CPUIDLE_STATE_MAX	10
 #define CPUIDLE_NAME_LEN	16
 #define CPUIDLE_DESC_LEN	32
 
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 321e066..9e9d348 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -46,6 +46,7 @@ unsigned int skip_c0;
 unsigned int skip_c1;
 unsigned int do_nhm_cstates;
 unsigned int do_snb_cstates;
+unsigned int do_c8_c9_c10;
 unsigned int has_aperf;
 unsigned int has_epb;
 unsigned int units = 1000000000;	/* Ghz etc */
@@ -120,6 +121,9 @@ struct pkg_data {
 	unsigned long long pc3;
 	unsigned long long pc6;
 	unsigned long long pc7;
+	unsigned long long pc8;
+	unsigned long long pc9;
+	unsigned long long pc10;
 	unsigned int package_id;
 	unsigned int energy_pkg;	/* MSR_PKG_ENERGY_STATUS */
 	unsigned int energy_dram;	/* MSR_DRAM_ENERGY_STATUS */
@@ -282,6 +286,11 @@ void print_header(void)
 		outp += sprintf(outp, "   %%pc6");
 	if (do_snb_cstates)
 		outp += sprintf(outp, "   %%pc7");
+	if (do_c8_c9_c10) {
+		outp += sprintf(outp, "   %%pc8");
+		outp += sprintf(outp, "   %%pc9");
+		outp += sprintf(outp, "  %%pc10");
+	}
 
 	if (do_rapl & RAPL_PKG)
 		outp += sprintf(outp, "  Pkg_W");
@@ -336,6 +345,9 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 		fprintf(stderr, "pc3: %016llX\n", p->pc3);
 		fprintf(stderr, "pc6: %016llX\n", p->pc6);
 		fprintf(stderr, "pc7: %016llX\n", p->pc7);
+		fprintf(stderr, "pc8: %016llX\n", p->pc8);
+		fprintf(stderr, "pc9: %016llX\n", p->pc9);
+		fprintf(stderr, "pc10: %016llX\n", p->pc10);
 		fprintf(stderr, "Joules PKG: %0X\n", p->energy_pkg);
 		fprintf(stderr, "Joules COR: %0X\n", p->energy_cores);
 		fprintf(stderr, "Joules GFX: %0X\n", p->energy_gfx);
@@ -493,6 +505,11 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, " %6.2f", 100.0 * p->pc6/t->tsc);
 	if (do_snb_cstates)
 		outp += sprintf(outp, " %6.2f", 100.0 * p->pc7/t->tsc);
+	if (do_c8_c9_c10) {
+		outp += sprintf(outp, " %6.2f", 100.0 * p->pc8/t->tsc);
+		outp += sprintf(outp, " %6.2f", 100.0 * p->pc9/t->tsc);
+		outp += sprintf(outp, " %6.2f", 100.0 * p->pc10/t->tsc);
+	}
 
 	/*
  	 * If measurement interval exceeds minimum RAPL Joule Counter range,
@@ -569,6 +586,9 @@ delta_package(struct pkg_data *new, struct pkg_data *old)
 	old->pc3 = new->pc3 - old->pc3;
 	old->pc6 = new->pc6 - old->pc6;
 	old->pc7 = new->pc7 - old->pc7;
+	old->pc8 = new->pc8 - old->pc8;
+	old->pc9 = new->pc9 - old->pc9;
+	old->pc10 = new->pc10 - old->pc10;
 	old->pkg_temp_c = new->pkg_temp_c;
 
 	DELTA_WRAP32(new->energy_pkg, old->energy_pkg);
@@ -702,6 +722,9 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	p->pc3 = 0;
 	p->pc6 = 0;
 	p->pc7 = 0;
+	p->pc8 = 0;
+	p->pc9 = 0;
+	p->pc10 = 0;
 
 	p->energy_pkg = 0;
 	p->energy_dram = 0;
@@ -740,6 +763,9 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 	average.packages.pc3 += p->pc3;
 	average.packages.pc6 += p->pc6;
 	average.packages.pc7 += p->pc7;
+	average.packages.pc8 += p->pc8;
+	average.packages.pc9 += p->pc9;
+	average.packages.pc10 += p->pc10;
 
 	average.packages.energy_pkg += p->energy_pkg;
 	average.packages.energy_dram += p->energy_dram;
@@ -781,6 +807,10 @@ void compute_average(struct thread_data *t, struct core_data *c,
 	average.packages.pc3 /= topo.num_packages;
 	average.packages.pc6 /= topo.num_packages;
 	average.packages.pc7 /= topo.num_packages;
+
+	average.packages.pc8 /= topo.num_packages;
+	average.packages.pc9 /= topo.num_packages;
+	average.packages.pc10 /= topo.num_packages;
 }
 
 static unsigned long long rdtsc(void)
@@ -880,6 +910,14 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		if (get_msr(cpu, MSR_PKG_C7_RESIDENCY, &p->pc7))
 			return -12;
 	}
+	if (do_c8_c9_c10) {
+		if (get_msr(cpu, MSR_PKG_C8_RESIDENCY, &p->pc8))
+			return -13;
+		if (get_msr(cpu, MSR_PKG_C9_RESIDENCY, &p->pc9))
+			return -13;
+		if (get_msr(cpu, MSR_PKG_C10_RESIDENCY, &p->pc10))
+			return -13;
+	}
 	if (do_rapl & RAPL_PKG) {
 		if (get_msr(cpu, MSR_PKG_ENERGY_STATUS, &msr))
 			return -13;
@@ -1762,6 +1800,19 @@ int is_snb(unsigned int family, unsigned int model)
 	return 0;
 }
 
+int has_c8_c9_c10(unsigned int family, unsigned int model)
+{
+	if (!genuine_intel)
+		return 0;
+
+	switch (model) {
+	case 0x45:
+		return 1;
+	}
+	return 0;
+}
+
+
 double discover_bclk(unsigned int family, unsigned int model)
 {
 	if (is_snb(family, model))
@@ -1918,6 +1969,7 @@ void check_cpuid()
 	do_nhm_cstates = genuine_intel;	/* all Intel w/ non-stop TSC have NHM counters */
 	do_smi = do_nhm_cstates;
 	do_snb_cstates = is_snb(family, model);
+	do_c8_c9_c10 = has_c8_c9_c10(family, model);
 	bclk = discover_bclk(family, model);
 
 	do_nehalem_turbo_ratio_limit = has_nehalem_turbo_ratio_limit(family, model);
@@ -2279,7 +2331,7 @@ int main(int argc, char **argv)
 	cmdline(argc, argv);
 
 	if (verbose)
-		fprintf(stderr, "turbostat v3.3 March 15, 2013"
+		fprintf(stderr, "turbostat v3.4 April 17, 2013"
 			" - Len Brown <lenb@kernel.org>\n");
 
 	turbostat_init();