From: Perry Yuan <perry.yuan@amd.com>
To: <rafael.j.wysocki@intel.com>, <Mario.Limonciello@amd.com>,
<viresh.kumar@linaro.org>, <Ray.Huang@amd.com>,
<gautham.shenoy@amd.com>, <Borislav.Petkov@amd.com>
Cc: <Alexander.Deucher@amd.com>, <Xinmei.Huang@amd.com>,
<Xiaojian.Du@amd.com>, <Li.Meng@amd.com>,
<linux-pm@vger.kernel.org>, <linux-kernel@vger.kernel.org>
Subject: [PATCH 09/11] cpufreq: amd-pstate: implement heterogeneous core topology for highest performance initialization
Date: Tue, 7 May 2024 15:15:25 +0800 [thread overview]
Message-ID: <731a28ea8dda4ca1db64f673c87770de4646290b.1715065568.git.perry.yuan@amd.com> (raw)
In-Reply-To: <cover.1715065568.git.perry.yuan@amd.com>
Introduces an optimization to the AMD-Pstate driver by implementing
a heterogeneous core topology for the initialization of the highest
performance value while driver loading.
There are two type cores designed including performance core and
efficiency Core. each core type has different highest performance value
and highest frequency initialized by power firmware, `amd_pstate` driver
need to identify the core types and set correct highest perf value.
X86_FEATURE_HETERO_CORE_TOPOLOGY is used to identify whether the
processor support heterogeneous core type by reading CPUID leaf
Fn_0x80000026_EAX and bit 30. if the bit is set as one, then amd_pstate
driver will check EBX 30:28 bits to get the core type.
Value Description:
0h Performance Core.
1h Efficiency Core.
https://www.amd.com/content/dam/amd/en/documents/processor-tech-docs/programmer-references/24593.pdf
PDF p274
Signed-off-by: Perry Yuan <perry.yuan@amd.com>
---
arch/x86/include/asm/processor.h | 2 ++
arch/x86/kernel/cpu/amd.c | 19 ++++++++++
drivers/cpufreq/amd-pstate.c | 62 ++++++++++++++++++++++++--------
include/linux/amd-pstate.h | 8 +++++
4 files changed, 77 insertions(+), 14 deletions(-)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 811548f131f4..30d1900bb7e0 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -683,10 +683,12 @@ static inline u32 per_cpu_l2c_id(unsigned int cpu)
extern u32 amd_get_highest_perf(void);
extern void amd_clear_divider(void);
extern void amd_check_microcode(void);
+extern int amd_get_this_core_type(void);
#else
static inline u32 amd_get_highest_perf(void) { return 0; }
static inline void amd_clear_divider(void) { }
static inline void amd_check_microcode(void) { }
+static inline int amd_get_this_core_type(void) { }
#endif
extern unsigned long arch_align_stack(unsigned long sp);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 307302af0aee..67966bdcde65 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1219,3 +1219,22 @@ void noinstr amd_clear_divider(void)
:: "a" (0), "d" (0), "r" (1));
}
EXPORT_SYMBOL_GPL(amd_clear_divider);
+
+#define X86_CPU_TYPE_ID_SHIFT 28
+
+/**
+ * amd_get_this_core_type - Get the type of this heterogeneous CPU
+ *
+ * Returns the CPU type [31:28] (i.e., performance or efficient) of
+ * a CPU in the processor.
+ * If the processor has no core type support, returns -1.
+ */
+
+int amd_get_this_core_type(void)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_HETERO_CORE_TOPOLOGY))
+ return -1;
+
+ return cpuid_ebx(0x80000026) >> X86_CPU_TYPE_ID_SHIFT;
+}
+EXPORT_SYMBOL_GPL(amd_get_this_core_type);
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 7145248b38ec..7fe8a8fc6227 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -50,7 +50,9 @@
#define AMD_PSTATE_TRANSITION_LATENCY 20000
#define AMD_PSTATE_TRANSITION_DELAY 1000
-#define AMD_PSTATE_PREFCORE_THRESHOLD 166
+#define CPPC_HIGHEST_PERF_EFFICIENT 132
+#define CPPC_HIGHEST_PERF_PERFORMANCE 196
+#define CPPC_HIGHEST_PERF_DEFAULT 166
/*
* TODO: We need more time to fine tune processors with shared memory solution
@@ -326,6 +328,49 @@ static inline int amd_pstate_enable(bool enable)
return static_call(amd_pstate_enable)(enable);
}
+static void get_this_core_type(void *data)
+{
+ int *cpu_type = data;
+
+ *cpu_type = amd_get_this_core_type();
+}
+
+static int amd_pstate_get_cpu_type(int cpu)
+{
+ int cpu_type = 0;
+
+ smp_call_function_single(cpu, get_this_core_type, &cpu_type, 1);
+
+ return cpu_type;
+}
+
+static u32 amd_pstate_highest_perf_set(struct amd_cpudata *cpudata)
+{
+ u32 highest_perf;
+ int core_type;
+
+ core_type = amd_pstate_get_cpu_type(cpudata->cpu);
+ pr_debug("core_type %d found\n", core_type);
+
+ switch (core_type) {
+ case CPU_CORE_TYPE_NO_HETERO_SUP:
+ highest_perf = CPPC_HIGHEST_PERF_DEFAULT;
+ break;
+ case CPU_CORE_TYPE_PERFORMANCE:
+ highest_perf = CPPC_HIGHEST_PERF_PERFORMANCE;
+ break;
+ case CPU_CORE_TYPE_EFFICIENCY:
+ highest_perf = CPPC_HIGHEST_PERF_EFFICIENT;
+ break;
+ default:
+ highest_perf = CPPC_HIGHEST_PERF_DEFAULT;
+ WARN_ONCE(true, "WARNING: Undefined core type found");
+ break;
+ }
+
+ return highest_perf;
+}
+
static int pstate_init_perf(struct amd_cpudata *cpudata)
{
u64 cap1;
@@ -336,15 +381,7 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
if (ret)
return ret;
- /* For platforms that do not support the preferred core feature, the
- * highest_pef may be configured with 166 or 255, to avoid max frequency
- * calculated wrongly. we take the AMD_CPPC_HIGHEST_PERF(cap1) value as
- * the default max perf.
- */
- if (cpudata->hw_prefcore)
- highest_perf = AMD_PSTATE_PREFCORE_THRESHOLD;
- else
- highest_perf = AMD_CPPC_HIGHEST_PERF(cap1);
+ highest_perf = amd_pstate_highest_perf_set(cpudata);
WRITE_ONCE(cpudata->highest_perf, highest_perf);
WRITE_ONCE(cpudata->max_limit_perf, highest_perf);
@@ -365,10 +402,7 @@ static int cppc_init_perf(struct amd_cpudata *cpudata)
if (ret)
return ret;
- if (cpudata->hw_prefcore)
- highest_perf = AMD_PSTATE_PREFCORE_THRESHOLD;
- else
- highest_perf = cppc_perf.highest_perf;
+ highest_perf = amd_pstate_highest_perf_set(cpudata);
WRITE_ONCE(cpudata->highest_perf, highest_perf);
WRITE_ONCE(cpudata->max_limit_perf, highest_perf);
diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h
index d58fc022ec46..869d916003f1 100644
--- a/include/linux/amd-pstate.h
+++ b/include/linux/amd-pstate.h
@@ -134,4 +134,12 @@ struct quirk_entry {
u32 lowest_freq;
};
+/* defined by CPUID_Fn80000026_EBX BIT [31:28] */
+enum amd_core_type {
+ CPU_CORE_TYPE_NO_HETERO_SUP = -1,
+ CPU_CORE_TYPE_PERFORMANCE = 0,
+ CPU_CORE_TYPE_EFFICIENCY = 1,
+ CPU_CORE_TYPE_UNDEFINED = 2,
+};
+
#endif /* _LINUX_AMD_PSTATE_H */
--
2.34.1
next prev parent reply other threads:[~2024-05-07 7:16 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-07 7:15 [PATCH 00/11] AMD Pstate Driver Fixes and Improvements Perry Yuan
2024-05-07 7:15 ` [PATCH 01/11] cpufreq: amd-pstate: optimiza the initial frequency values verification Perry Yuan
2024-05-07 14:44 ` Mario Limonciello
2024-05-07 21:02 ` kernel test robot
2024-05-07 7:15 ` [PATCH 02/11] cpufreq: amd-pstate: show CPPC debug message if CPPC is not supported Perry Yuan
2024-05-07 14:45 ` Mario Limonciello
2024-05-07 7:15 ` [PATCH 03/11] cpufreq: amd-pstate: add debug message while CPPC is supported and disabled by SBIOS Perry Yuan
2024-05-07 14:55 ` Mario Limonciello
2024-05-07 7:15 ` [PATCH 04/11] Documentation: PM: amd-pstate: introducing recommended reboot requirement during driver switch Perry Yuan
2024-05-07 7:15 ` [PATCH 05/11] Documentation: PM: amd-pstate: add debugging section for driver loading failure Perry Yuan
2024-05-07 15:01 ` Mario Limonciello
2024-05-07 7:15 ` [PATCH 06/11] Documentation: PM: amd-pstate: add guide mode to the Operation mode Perry Yuan
2024-05-07 15:02 ` Mario Limonciello
2024-05-07 7:15 ` [PATCH 07/11] cpufreq: amd-pstate: switch boot_cpu_has() to cpu_feature_enabled() Perry Yuan
2024-05-07 15:03 ` Mario Limonciello
2024-05-07 7:15 ` [PATCH 08/11] x86/cpufeatures: Add feature bits for AMD heterogeneous processor Perry Yuan
2024-05-07 7:15 ` Perry Yuan [this message]
2024-05-07 15:19 ` [PATCH 09/11] cpufreq: amd-pstate: implement heterogeneous core topology for highest performance initialization Mario Limonciello
2024-05-09 16:36 ` Yuan, Perry
2024-05-07 18:14 ` kernel test robot
2024-05-07 19:40 ` kernel test robot
2024-05-07 7:15 ` [PATCH 10/11] cpufreq: amd-pstate: fix the highest frequency issue which limit performance Perry Yuan
2024-05-07 15:23 ` Mario Limonciello
2024-05-07 7:15 ` [PATCH 11/11] cpufreq: amd-pstate: automatically load pstate driver by default Perry Yuan
2024-05-07 14:41 ` Mario Limonciello
2024-05-08 15:20 ` Oleksandr Natalenko
2024-05-08 15:24 ` Yuan, Perry
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=731a28ea8dda4ca1db64f673c87770de4646290b.1715065568.git.perry.yuan@amd.com \
--to=perry.yuan@amd.com \
--cc=Alexander.Deucher@amd.com \
--cc=Borislav.Petkov@amd.com \
--cc=Li.Meng@amd.com \
--cc=Mario.Limonciello@amd.com \
--cc=Ray.Huang@amd.com \
--cc=Xiaojian.Du@amd.com \
--cc=Xinmei.Huang@amd.com \
--cc=gautham.shenoy@amd.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=rafael.j.wysocki@intel.com \
--cc=viresh.kumar@linaro.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).