Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1465764 > unrolled thread

[PATCH 00/11] Support Intel® Turbo Boost Max Technology 3.0

Back to article view | Back to linux.kernel

Contents

  [PATCH 00/11] Support Intel® Turbo Boost Max Technology 3.0 Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> - 2016-08-19 03:20 +0200
    [PATCH 10/11] acpi: bus: Set _OSC for diverse core support Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> - 2016-08-19 03:20 +0200
      Re: [PATCH 10/11] acpi: bus: Set _OSC for diverse core support "Rafael J. Wysocki" <rjw@rjwysocki.net> - 2016-08-20 02:50 +0200
    [PATCH 02/11] sched, x86: Add SD_ASYM_PACKING flags to x86 cpu topology for cpus supporting Intel Turbo Boost Max Technology Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> - 2016-08-19 03:30 +0200
    [PATCH 08/11] acpi: cppc: Add prefix cppc to cpudata structure name Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> - 2016-08-19 03:30 +0200

#1465764 — [PATCH 00/11] Support Intel® Turbo Boost Max Technology 3.0

With Intel® Turbo Boost Max Technology 3.0 (ITMT), single-threaded performance is
optimized by identifying processor's fastest core and running critical workloads
on it.
Refere to:
http://www.intel.com/content/www/us/en/architecture-and-technology/turbo-boost/turbo-boost-max-technology.html

This patchset consist of all changes required to support ITMT feature:
- Enhance CPPC ACPI lib to support x86
- Use CPPC information in Intel P-State driver to get performance information
- Scheduler enhancements

By default this feature is OFF, to turn on:

# echo 1 > /proc/sys/kernel/sched_itmt_enabled


Srinivas Pandruvada (7):
  acpi: cppc: Allow build with ACPI_CPU_FREQ_PSS config
  acpi: cpcc: Add integer read support
  acpi: cppc: Add support for function fixed hardware address
  acpi: cppc: Add prefix cppc to cpudata structure name
  acpi: bus: Enable HWP CPPC objects
  acpi: bus: Set _OSC for diverse core support
  cpufreq: intel_pstate: Use CPPC to get max performance

Tim Chen (4):
  sched, cpuset: Add regenerate_sched_domains function to rebuild all
    sched domains
  sched, x86: Add SD_ASYM_PACKING flags to x86 cpu topology for cpus
    supporting Intel Turbo Boost Max Technology
  sched: Extend scheduler's asym packing
  sched,x86: Enable Turbo Boost Max Technology

 arch/x86/Kconfig                |   9 +++
 arch/x86/include/asm/topology.h |  26 +++++++
 arch/x86/kernel/Makefile        |   1 +
 arch/x86/kernel/itmt.c          | 147 ++++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/smpboot.c       |  77 ++++++++++++++++-----
 drivers/acpi/Kconfig            |   1 -
 drivers/acpi/bus.c              |   9 +++
 drivers/acpi/cppc_acpi.c        |  88 ++++++++++++++++++++----
 drivers/acpi/processor_driver.c |   5 +-
 drivers/cpufreq/Kconfig.x86     |   1 +
 drivers/cpufreq/cppc_cpufreq.c  |  14 ++--
 drivers/cpufreq/intel_pstate.c  |  75 +++++++++++++++++++-
 include/acpi/cppc_acpi.h        |   4 +-
 include/linux/acpi.h            |   1 +
 include/linux/cpuset.h          |   2 +
 include/linux/sched.h           |   3 +
 kernel/cpuset.c                 |  32 +++++++--
 kernel/sched/core.c             |  46 ++++++++++++-
 kernel/sched/fair.c             |  25 ++++---
 kernel/sched/sched.h            |  17 +++++
 20 files changed, 517 insertions(+), 66 deletions(-)
 create mode 100644 arch/x86/kernel/itmt.c

-- 
2.7.4

[toc] | [next] | [standalone]

#1465767 — [PATCH 10/11] acpi: bus: Set _OSC for diverse core support

Set the OSC_SB_CPC_DIVERSE_HIGH_SUPPORT (bit 12) to enable diverse
core support.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
---
 drivers/acpi/bus.c   | 4 +++-
 include/linux/acpi.h | 1 +
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 61643a5..fbd3b7c 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -336,7 +336,9 @@ static void acpi_bus_osc_support(void)
 		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_CPCV2_SUPPORT;
 	}
 #endif
-
+#ifdef CONFIG_SCHED_ITMT
+	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_CPC_DIVERSE_HIGH_SUPPORT;
+#endif
 	if (!ghes_disable)
 		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_APEI_SUPPORT;
 	if (ACPI_FAILURE(acpi_get_handle(NULL, "\\_SB", &handle)))
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 4d8452c..17f6e08 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -460,6 +460,7 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context);
 #define OSC_SB_CPCV2_SUPPORT			0x00000040
 #define OSC_SB_PCLPI_SUPPORT			0x00000080
 #define OSC_SB_OSLPI_SUPPORT			0x00000100
+#define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT		0x00001000
 
 extern bool osc_sb_apei_support_acked;
 extern bool osc_pc_lpi_support_confirmed;
-- 
2.7.4

[toc] | [prev] | [next] | [standalone]

#1466756 — Re: [PATCH 10/11] acpi: bus: Set _OSC for diverse core support

On Thursday, August 18, 2016 03:36:51 PM Srinivas Pandruvada wrote:
> Set the OSC_SB_CPC_DIVERSE_HIGH_SUPPORT (bit 12) to enable diverse
> core support.
> 
> Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
> ---
>  drivers/acpi/bus.c   | 4 +++-
>  include/linux/acpi.h | 1 +
>  2 files changed, 4 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
> index 61643a5..fbd3b7c 100644
> --- a/drivers/acpi/bus.c
> +++ b/drivers/acpi/bus.c
> @@ -336,7 +336,9 @@ static void acpi_bus_osc_support(void)
>  		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_CPCV2_SUPPORT;
>  	}
>  #endif
> -
> +#ifdef CONFIG_SCHED_ITMT
> +	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_CPC_DIVERSE_HIGH_SUPPORT;
> +#endif

	if (IS_ENABLED(CONFIG_SCHED_ITMT))
		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_CPC_DIVERSE_HIGH_SUPPORT;

pretty please.

>  	if (!ghes_disable)
>  		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_APEI_SUPPORT;
>  	if (ACPI_FAILURE(acpi_get_handle(NULL, "\\_SB", &handle)))
> diff --git a/include/linux/acpi.h b/include/linux/acpi.h
> index 4d8452c..17f6e08 100644
> --- a/include/linux/acpi.h
> +++ b/include/linux/acpi.h
> @@ -460,6 +460,7 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context);
>  #define OSC_SB_CPCV2_SUPPORT			0x00000040
>  #define OSC_SB_PCLPI_SUPPORT			0x00000080
>  #define OSC_SB_OSLPI_SUPPORT			0x00000100
> +#define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT		0x00001000
>  
>  extern bool osc_sb_apei_support_acked;
>  extern bool osc_pc_lpi_support_confirmed;
> 

Thanks,
Rafael

[toc] | [prev] | [next] | [standalone]

#1465773 — [PATCH 02/11] sched, x86: Add SD_ASYM_PACKING flags to x86 cpu topology for cpus supporting Intel Turbo Boost Max Technology

From: Tim Chen <tim.c.chen@linux.intel.com>

We uses ASYM_PACKING feature in the scheduler to move tasks to more
capable cpus that can be boosted to higher frequency.  We mark the sched
domain topology level with SD_ASYM_PACKING flag for such systems.

Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
---
 arch/x86/kernel/smpboot.c | 77 ++++++++++++++++++++++++++++++++++++-----------
 kernel/sched/core.c       |  3 ++
 2 files changed, 62 insertions(+), 18 deletions(-)

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 2a6e84a..255f64e 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -464,31 +464,59 @@ static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 	return false;
 }
 
-static struct sched_domain_topology_level numa_inside_package_topology[] = {
+#ifdef CONFIG_SCHED_ITMT
+extern unsigned int sysctl_sched_itmt_enabled;
+
+static int x86_core_flags(void)
+{
+	int flags = cpu_core_flags();
+
+	if (sysctl_sched_itmt_enabled)
+		flags |= SD_ASYM_PACKING;
+
+	return flags;
+}
+
+static int x86_smt_flags(void)
+{
+	int flags = cpu_smt_flags();
+
+	if (sysctl_sched_itmt_enabled)
+		flags |= SD_ASYM_PACKING;
+
+	return flags;
+}
+#else
+#define x86_core_flags cpu_core_flags
+#define x86_smt_flags cpu_smt_flags
+#endif
+
+static struct sched_domain_topology_level x86_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+	{ cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+#ifdef CONFIG_SCHED_MC
+	{ cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) },
+#endif
+	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ NULL, },
+};
+
+static struct sched_domain_topology_level x86_numa_in_package_topology[] = {
 #ifdef CONFIG_SCHED_SMT
-	{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+	{ cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
 #endif
 #ifdef CONFIG_SCHED_MC
-	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+	{ cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) },
 #endif
 	{ NULL, },
 };
+
 /*
- * set_sched_topology() sets the topology internal to a CPU.  The
- * NUMA topologies are layered on top of it to build the full
- * system topology.
- *
- * If NUMA nodes are observed to occur within a CPU package, this
- * function should be called.  It forces the sched domain code to
- * only use the SMT level for the CPU portion of the topology.
- * This essentially falls back to relying on NUMA information
- * from the SRAT table to describe the entire system topology
- * (except for hyperthreads).
+ * Set if a package/die has multiple NUMA nodes inside.
+ * AMD Magny-Cours and Intel Cluster-on-Die have this.
  */
-static void primarily_use_numa_for_topology(void)
-{
-	set_sched_topology(numa_inside_package_topology);
-}
+static bool x86_has_numa_in_package = false;
 
 void set_cpu_sibling_map(int cpu)
 {
@@ -551,7 +579,7 @@ void set_cpu_sibling_map(int cpu)
 				c->booted_cores = cpu_data(i).booted_cores;
 		}
 		if (match_die(c, o) && !topology_same_node(c, o))
-			primarily_use_numa_for_topology();
+			x86_has_numa_in_package = true;
 	}
 
 	threads = cpumask_weight(topology_sibling_cpumask(cpu));
@@ -1297,6 +1325,16 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
 		zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
 	}
+
+	/*
+	 * Set 'default' x86 topology, this matches default_topology() in that
+	 * it has NUMA nodes as a topology level. See also
+	 * native_smp_cpus_done().
+	 *
+	 * Must be done before set_cpus_sibling_map() is ran.
+	 */
+	set_sched_topology(x86_topology);
+
 	set_cpu_sibling_map(0);
 
 	switch (smp_sanity_check(max_cpus)) {
@@ -1363,6 +1401,9 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
 {
 	pr_debug("Boot done\n");
 
+	if (x86_has_numa_in_package)
+		set_sched_topology(x86_numa_in_package_topology);
+
 	nmi_selftest();
 	impress_friends();
 	setup_ioapic_dest();
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ec752da..342eca9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6487,6 +6487,9 @@ static struct sched_domain_topology_level *sched_domain_topology =
 
 void set_sched_topology(struct sched_domain_topology_level *tl)
 {
+	if (WARN_ON_ONCE(sched_smp_initialized))
+		return;
+
 	sched_domain_topology = tl;
 }
 
-- 
2.7.4

[toc] | [prev] | [next] | [standalone]

#1465783 — [PATCH 08/11] acpi: cppc: Add prefix cppc to cpudata structure name

Since struct cpudata is defined in a header file, add prefix cppc_ to
make it not a generic name. Otherwise it causes compile issue in locally
define structure with the same name.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
---
 drivers/acpi/cppc_acpi.c       |  4 ++--
 drivers/cpufreq/cppc_cpufreq.c | 14 +++++++-------
 include/acpi/cppc_acpi.h       |  4 ++--
 3 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 939fb5c..5ca517d 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -276,13 +276,13 @@ end:
  *
  *	Return: 0 for success or negative value for err.
  */
-int acpi_get_psd_map(struct cpudata **all_cpu_data)
+int acpi_get_psd_map(struct cppc_cpudata **all_cpu_data)
 {
 	int count_target;
 	int retval = 0;
 	unsigned int i, j;
 	cpumask_var_t covered_cpus;
-	struct cpudata *pr, *match_pr;
+	struct cppc_cpudata *pr, *match_pr;
 	struct acpi_psd_package *pdomain;
 	struct acpi_psd_package *match_pdomain;
 	struct cpc_desc *cpc_ptr, *match_cpc_ptr;
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index 8882b8e..b1b3549 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -30,13 +30,13 @@
  * performance capabilities, desired performance level
  * requested etc.
  */
-static struct cpudata **all_cpu_data;
+static struct cppc_cpudata **all_cpu_data;
 
 static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
 		unsigned int target_freq,
 		unsigned int relation)
 {
-	struct cpudata *cpu;
+	struct cppc_cpudata *cpu;
 	struct cpufreq_freqs freqs;
 	int ret = 0;
 
@@ -66,7 +66,7 @@ static int cppc_verify_policy(struct cpufreq_policy *policy)
 static void cppc_cpufreq_stop_cpu(struct cpufreq_policy *policy)
 {
 	int cpu_num = policy->cpu;
-	struct cpudata *cpu = all_cpu_data[cpu_num];
+	struct cppc_cpudata *cpu = all_cpu_data[cpu_num];
 	int ret;
 
 	cpu->perf_ctrls.desired_perf = cpu->perf_caps.lowest_perf;
@@ -79,7 +79,7 @@ static void cppc_cpufreq_stop_cpu(struct cpufreq_policy *policy)
 
 static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
-	struct cpudata *cpu;
+	struct cppc_cpudata *cpu;
 	unsigned int cpu_num = policy->cpu;
 	int ret = 0;
 
@@ -134,7 +134,7 @@ static struct cpufreq_driver cppc_cpufreq_driver = {
 static int __init cppc_cpufreq_init(void)
 {
 	int i, ret = 0;
-	struct cpudata *cpu;
+	struct cppc_cpudata *cpu;
 
 	if (acpi_disabled)
 		return -ENODEV;
@@ -144,7 +144,7 @@ static int __init cppc_cpufreq_init(void)
 		return -ENOMEM;
 
 	for_each_possible_cpu(i) {
-		all_cpu_data[i] = kzalloc(sizeof(struct cpudata), GFP_KERNEL);
+		all_cpu_data[i] = kzalloc(sizeof(struct cppc_cpudata), GFP_KERNEL);
 		if (!all_cpu_data[i])
 			goto out;
 
@@ -175,7 +175,7 @@ out:
 
 static void __exit cppc_cpufreq_exit(void)
 {
-	struct cpudata *cpu;
+	struct cppc_cpudata *cpu;
 	int i;
 
 	cpufreq_unregister_driver(&cppc_cpufreq_driver);
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index 284965c..b7816c2 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -114,7 +114,7 @@ struct cppc_perf_fb_ctrs {
 };
 
 /* Per CPU container for runtime CPPC management. */
-struct cpudata {
+struct cppc_cpudata {
 	int cpu;
 	struct cppc_perf_caps perf_caps;
 	struct cppc_perf_ctrls perf_ctrls;
@@ -127,6 +127,6 @@ struct cpudata {
 extern int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs);
 extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls);
 extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps);
-extern int acpi_get_psd_map(struct cpudata **);
+extern int acpi_get_psd_map(struct cppc_cpudata **);
 
 #endif /* _CPPC_ACPI_H*/
-- 
2.7.4

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web