[PATCH v5 0/2] x86/fpu: Make AMX state ready for CPU idle

[PATCH v5 0/2] x86/fpu: Make AMX state ready for CPU idle

[Chang S. Bae]

Here is the fifth version of this series.

I've addressed Dave's comment [2] assuming that the change makes sense to
folks:
* Check the AMX_TILE feature bit instead of XGETBV1.
* Massage the changelog accordingly.

While many people had their eyeballs on this, Rafael's ACK was given so
far. Hopefully this can attracts more acknowledgment or endorsement if it
looks fine.

=== Cover Letter ===

AMX state is a large state (at least 8KB or more). Entering CPU idle with
this non-initialized large state may result in shallow states while a
deeper low-power state is available.

We can confirm this behavior is implementation-specific. Section 3.3 in [3]
will be updated to clarify this.

This patch set ensures the AMX state is initialized before entering the CPU
idle state.

The patch set is based on 5.19-rc1. It is also available here:
  git://github.com/intel/amx-linux.git tilerelease

[1]: V4 https://lore.kernel.org/lkml/20220517222430.24524-1-chang.seok.bae@intel.com/
[2]: https://lore.kernel.org/lkml/25a2a82f-b5e5-0fce-86c8-03d7da5fcdd1@intel.com/
[3]: Intel Architecture Instruction Set Extension Programming Reference
     May 2021, https://software.intel.com/content/dam/develop/external/us/en/documents-tps/architecture-instruction-set-extensions-programming-reference.pdf

Chang S. Bae (2):
  x86/fpu: Add a helper to prepare AMX state for low-power CPU idle
  intel_idle: Add a new flag to initialize the AMX state

 arch/x86/include/asm/fpu/api.h       |  2 ++
 arch/x86/include/asm/special_insns.h |  9 +++++++++
 arch/x86/kernel/fpu/core.c           | 14 ++++++++++++++
 drivers/idle/intel_idle.c            | 18 ++++++++++++++++--
 4 files changed, 41 insertions(+), 2 deletions(-)


base-commit: f2906aa863381afb0015a9eb7fefad885d4e5a56
-- 
2.17.1

[PATCH v5 1/2] x86/fpu: Add a helper to prepare AMX state for low-power CPU idle

[Chang S. Bae]

When a CPU enters an idle state, a non-initialized AMX register state may
be the cause of preventing a deeper low-power state. Other extended
register states whether initialized or not do not impact the CPU idle
state.

The new helper can ensure the AMX state is initialized before the CPU is
idle, and it will be used by the intel idle driver.

Check the AMX_TILE feature bit before using XGETBV1 as a chain of
dependencies was established via cpuid_deps[]: AMX->XFD->XGETBV1.

Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Cc: x86@kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: Rik van Riel <riel@fb.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Fenghua Yu <fenghua.yu@intel.com>
---
Changes from v4:
* Switch to check the AMX_TILE flag instead XGETBV1 (Dave Hansen).
* Massage the changelog.

Changes from v3:
* Call out AMX state in changelog (Thomas Glexiner).

Changes from v2:
* Check the feature flag instead of fpu_state_size_dynamic() (Dave Hansen).

Changes from v1:
* Check the dynamic state flag first, to avoid #UD with XGETBV(1).
---
 arch/x86/include/asm/fpu/api.h       |  2 ++
 arch/x86/include/asm/special_insns.h |  9 +++++++++
 arch/x86/kernel/fpu/core.c           | 14 ++++++++++++++
 3 files changed, 25 insertions(+)

diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index 6b0f31fb53f7..503a577814b2 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -164,4 +164,6 @@ static inline bool fpstate_is_confidential(struct fpu_guest *gfpu)
 /* prctl */
 extern long fpu_xstate_prctl(int option, unsigned long arg2);
 
+extern void fpu_idle_fpregs(void);
+
 #endif /* _ASM_X86_FPU_API_H */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 45b18eb94fa1..35f709f619fb 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -295,6 +295,15 @@ static inline int enqcmds(void __iomem *dst, const void *src)
 	return 0;
 }
 
+static inline void tile_release(void)
+{
+	/*
+	 * Instruction opcode for TILERELEASE; supported in binutils
+	 * version >= 2.36.
+	 */
+	asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0");
+}
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_SPECIAL_INSNS_H */
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 0531d6a06df5..3b28c5b25e12 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -851,3 +851,17 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr)
 	 */
 	return 0;
 }
+
+/*
+ * Initialize register state that may prevent from entering low-power idle.
+ * This function will be invoked from the cpuidle driver only when needed.
+ */
+void fpu_idle_fpregs(void)
+{
+	/* Note: AMX_TILE being enabled implies XGETBV1 support */
+	if (cpu_feature_enabled(X86_FEATURE_AMX_TILE) &&
+	    (xfeatures_in_use() & XFEATURE_MASK_XTILE)) {
+		tile_release();
+		fpregs_deactivate(&current->thread.fpu);
+	}
+}
-- 
2.17.1

[PATCH v5 2/2] intel_idle: Add a new flag to initialize the AMX state

[Chang S. Bae]

The non-initialized AMX state can be the cause of C-state demotion from C6
to C1E. This low-power idle state may improve power savings and thus result
in a higher available turbo frequency budget.

This behavior is implementation-specific. Initialize the state for the C6
entrance of Sapphire Rapids as needed.

Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Tested-by : Zhang Rui <rui.zhang@intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: linux-pm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Len Brown <lenb@kernel.org>
---
Changes from v2:
* Remove an unnecessary backslash (Rafael Wysocki).

Changes from v1:
* Simplify the code with a new flag (Rui).
* Rebase on Artem's patches for SPR intel_idle.
* Massage the changelog.
---
 drivers/idle/intel_idle.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index b9bb94bd0f67..5f36c4b28f9d 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -54,6 +54,7 @@
 #include <asm/intel-family.h>
 #include <asm/mwait.h>
 #include <asm/msr.h>
+#include <asm/fpu/api.h>
 
 #define INTEL_IDLE_VERSION "0.5.1"
 
@@ -105,6 +106,11 @@ static unsigned int mwait_substates __initdata;
  */
 #define CPUIDLE_FLAG_ALWAYS_ENABLE	BIT(15)
 
+/*
+ * Initialize large xstate for the C6-state entrance.
+ */
+#define CPUIDLE_FLAG_INIT_XSTATE	BIT(16)
+
 /*
  * MWAIT takes an 8-bit "hint" in EAX "suggesting"
  * the C-state (top nibble) and sub-state (bottom nibble)
@@ -139,6 +145,9 @@ static __cpuidle int intel_idle(struct cpuidle_device *dev,
 	if (state->flags & CPUIDLE_FLAG_IRQ_ENABLE)
 		local_irq_enable();
 
+	if (state->flags & CPUIDLE_FLAG_INIT_XSTATE)
+		fpu_idle_fpregs();
+
 	mwait_idle_with_hints(eax, ecx);
 
 	return index;
@@ -159,8 +168,12 @@ static __cpuidle int intel_idle(struct cpuidle_device *dev,
 static __cpuidle int intel_idle_s2idle(struct cpuidle_device *dev,
 				       struct cpuidle_driver *drv, int index)
 {
-	unsigned long eax = flg2MWAIT(drv->states[index].flags);
 	unsigned long ecx = 1; /* break on interrupt flag */
+	struct cpuidle_state *state = &drv->states[index];
+	unsigned long eax = flg2MWAIT(state->flags);
+
+	if (state->flags & CPUIDLE_FLAG_INIT_XSTATE)
+		fpu_idle_fpregs();
 
 	mwait_idle_with_hints(eax, ecx);
 
@@ -895,7 +908,8 @@ static struct cpuidle_state spr_cstates[] __initdata = {
 	{
 		.name = "C6",
 		.desc = "MWAIT 0x20",
-		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED |
+					   CPUIDLE_FLAG_INIT_XSTATE,
 		.exit_latency = 290,
 		.target_residency = 800,
 		.enter = &intel_idle,
-- 
2.17.1

[tip: x86/fpu] intel_idle: Add a new flag to initialize the AMX state

[tip-bot2 for Chang S. Bae]

The following commit has been merged into the x86/fpu branch of tip:

Commit-ID:     43843d58393026fef4a43d192b641a4fabdc42bf
Gitweb:        https://git.kernel.org/tip/43843d58393026fef4a43d192b641a4fabdc42bf
Author:        Chang S. Bae <chang.seok.bae@intel.com>
AuthorDate:    Wed, 08 Jun 2022 09:47:48 -07:00
Committer:     Dave Hansen <dave.hansen@linux.intel.com>
CommitterDate: Wed, 08 Jun 2022 12:04:11 -07:00

intel_idle: Add a new flag to initialize the AMX state

The non-initialized AMX state can be the cause of C-state demotion from C6
to C1E. This low-power idle state may improve power savings and thus result
in a higher available turbo frequency budget.

This behavior is implementation-specific. Initialize the state for the C6
entrance of Sapphire Rapids as needed.

Tested-by : Zhang Rui <rui.zhang@intel.com>
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lkml.kernel.org/r/20220608164748.11864-3-chang.seok.bae@intel.com
---
 drivers/idle/intel_idle.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index b7640cf..d357908 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -54,6 +54,7 @@
 #include <asm/intel-family.h>
 #include <asm/mwait.h>
 #include <asm/msr.h>
+#include <asm/fpu/api.h>
 
 #define INTEL_IDLE_VERSION "0.5.1"
 
@@ -101,6 +102,11 @@ static unsigned int mwait_substates __initdata;
 #define CPUIDLE_FLAG_ALWAYS_ENABLE	BIT(15)
 
 /*
+ * Initialize large xstate for the C6-state entrance.
+ */
+#define CPUIDLE_FLAG_INIT_XSTATE	BIT(16)
+
+/*
  * MWAIT takes an 8-bit "hint" in EAX "suggesting"
  * the C-state (top nibble) and sub-state (bottom nibble)
  * 0x00 means "MWAIT(C1)", 0x10 means "MWAIT(C2)" etc.
@@ -134,6 +140,9 @@ static __cpuidle int intel_idle(struct cpuidle_device *dev,
 	if (state->flags & CPUIDLE_FLAG_IRQ_ENABLE)
 		local_irq_enable();
 
+	if (state->flags & CPUIDLE_FLAG_INIT_XSTATE)
+		fpu_idle_fpregs();
+
 	mwait_idle_with_hints(eax, ecx);
 
 	return index;
@@ -154,8 +163,12 @@ static __cpuidle int intel_idle(struct cpuidle_device *dev,
 static __cpuidle int intel_idle_s2idle(struct cpuidle_device *dev,
 				       struct cpuidle_driver *drv, int index)
 {
-	unsigned long eax = flg2MWAIT(drv->states[index].flags);
 	unsigned long ecx = 1; /* break on interrupt flag */
+	struct cpuidle_state *state = &drv->states[index];
+	unsigned long eax = flg2MWAIT(state->flags);
+
+	if (state->flags & CPUIDLE_FLAG_INIT_XSTATE)
+		fpu_idle_fpregs();
 
 	mwait_idle_with_hints(eax, ecx);
 
@@ -790,7 +803,8 @@ static struct cpuidle_state spr_cstates[] __initdata = {
 	{
 		.name = "C6",
 		.desc = "MWAIT 0x20",
-		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED |
+					   CPUIDLE_FLAG_INIT_XSTATE,
 		.exit_latency = 290,
 		.target_residency = 800,
 		.enter = &intel_idle,

[tip: x86/fpu] x86/fpu: Add a helper to prepare AMX state for low-power CPU idle

[tip-bot2 for Chang S. Bae]

The following commit has been merged into the x86/fpu branch of tip:

Commit-ID:     407f1fd0780e39d60778a66c6a157d8c8c832729
Gitweb:        https://git.kernel.org/tip/407f1fd0780e39d60778a66c6a157d8c8c832729
Author:        Chang S. Bae <chang.seok.bae@intel.com>
AuthorDate:    Wed, 08 Jun 2022 09:47:47 -07:00
Committer:     Dave Hansen <dave.hansen@linux.intel.com>
CommitterDate: Wed, 08 Jun 2022 12:03:56 -07:00

x86/fpu: Add a helper to prepare AMX state for low-power CPU idle

When a CPU enters an idle state, a non-initialized AMX register state may
be the cause of preventing a deeper low-power state. Other extended
register states whether initialized or not do not impact the CPU idle
state.

The new helper can ensure the AMX state is initialized before the CPU is
idle, and it will be used by the intel idle driver.

Check the AMX_TILE feature bit before using XGETBV1 as a chain of
dependencies was established via cpuid_deps[]: AMX->XFD->XGETBV1.

Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lkml.kernel.org/r/20220608164748.11864-2-chang.seok.bae@intel.com
---
 arch/x86/include/asm/fpu/api.h       |  2 ++
 arch/x86/include/asm/special_insns.h |  9 +++++++++
 arch/x86/kernel/fpu/core.c           | 14 ++++++++++++++
 3 files changed, 25 insertions(+)

diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index c83b302..df48912 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -165,4 +165,6 @@ static inline bool fpstate_is_confidential(struct fpu_guest *gfpu)
 struct task_struct;
 extern long fpu_xstate_prctl(struct task_struct *tsk, int option, unsigned long arg2);
 
+extern void fpu_idle_fpregs(void);
+
 #endif /* _ASM_X86_FPU_API_H */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 68c257a..d434fba 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -294,6 +294,15 @@ static inline int enqcmds(void __iomem *dst, const void *src)
 	return 0;
 }
 
+static inline void tile_release(void)
+{
+	/*
+	 * Instruction opcode for TILERELEASE; supported in binutils
+	 * version >= 2.36.
+	 */
+	asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0");
+}
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_SPECIAL_INSNS_H */
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index c049561..209cfac 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -851,3 +851,17 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr)
 	 */
 	return 0;
 }
+
+/*
+ * Initialize register state that may prevent from entering low-power idle.
+ * This function will be invoked from the cpuidle driver only when needed.
+ */
+void fpu_idle_fpregs(void)
+{
+	/* Note: AMX_TILE being enabled implies XGETBV1 support */
+	if (cpu_feature_enabled(X86_FEATURE_AMX_TILE) &&
+	    (xfeatures_in_use() & XFEATURE_MASK_XTILE)) {
+		tile_release();
+		fpregs_deactivate(&current->thread.fpu);
+	}
+}

Re: [tip: x86/fpu] intel_idle: Add a new flag to initialize the AMX state

[Peter Zijlstra]

On Wed, Jun 08, 2022 at 07:32:37PM -0000, tip-bot2 for Chang S. Bae wrote:
> @@ -134,6 +140,9 @@ static __cpuidle int intel_idle(struct cpuidle_device *dev,
>  	if (state->flags & CPUIDLE_FLAG_IRQ_ENABLE)
>  		local_irq_enable();
>  
> +	if (state->flags & CPUIDLE_FLAG_INIT_XSTATE)
> +		fpu_idle_fpregs();
> +
>  	mwait_idle_with_hints(eax, ecx);
>  
>  	return index;

This will conflict with an intel_idle patch Rafael took from me; the
resolution would be something along these lines:

--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -166,6 +166,13 @@ static __cpuidle int intel_idle_irq(stru
 	return ret;
 }
 
+static __cpuidle int intel_idle_xstate(struct cpuidle_device *dev,
+				       struct cpuidle_driver *drv, int index)
+{
+	fpu_idle_fpregs();
+	return __intel_idle(dev, drv, index);
+}
+
 /**
  * intel_idle_s2idle - Ask the processor to enter the given idle state.
  * @dev: cpuidle device of the target CPU.
@@ -1831,6 +1838,9 @@ static void __init intel_idle_init_cstat
 		if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IRQ_ENABLE)
 			drv->states[drv->state_count].enter = intel_idle_irq;
 
+		if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_INIT_XSTATE)
+			drv->states[drv->state_count].enter = intel_idle_xstate;
+
 		if ((disabled_states_mask & BIT(drv->state_count)) ||
 		    ((icpu->use_acpi || force_use_acpi) &&
 		     intel_idle_off_by_default(mwait_hint) &&

[PATCH][Rebased] intel_idle: Add a new flag to initialize the AMX state

[Chang S. Bae]

The non-initialized AMX state can be the cause of C-state demotion from C6
to C1E. This low-power idle state may improve power savings and thus result
in a higher available turbo frequency budget.

This behavior is implementation-specific. Initialize the state for the C6
entrance of Sapphire Rapids as needed.

Tested-by: Zhang Rui <rui.zhang@intel.com>
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lkml.kernel.org/r/20220608164748.11864-3-chang.seok.bae@intel.com
[changb: Rebase to the upstream with peterz's help]
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
---
The patch merged in the tip's x86/fpu branch [1] has conflict with the
upstream -- commit 32d4fd5751ea ("cpuidle,intel_idle: Fix
CPUIDLE_FLAG_IRQ_ENABLE") as of v5.19-rc2.

[1] https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/log/?h=x86/fpu
---
 drivers/idle/intel_idle.c | 25 +++++++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 424ef470223d..8a19ba1c2c1b 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -54,6 +54,7 @@
 #include <asm/intel-family.h>
 #include <asm/mwait.h>
 #include <asm/msr.h>
+#include <asm/fpu/api.h>
 
 #define INTEL_IDLE_VERSION "0.5.1"
 
@@ -105,6 +106,11 @@ static unsigned int mwait_substates __initdata;
  */
 #define CPUIDLE_FLAG_ALWAYS_ENABLE	BIT(15)
 
+/*
+ * Initialize large xstate for the C6-state entrance.
+ */
+#define CPUIDLE_FLAG_INIT_XSTATE	BIT(16)
+
 /*
  * MWAIT takes an 8-bit "hint" in EAX "suggesting"
  * the C-state (top nibble) and sub-state (bottom nibble)
@@ -159,6 +165,13 @@ static __cpuidle int intel_idle_irq(struct cpuidle_device *dev,
 	return ret;
 }
 
+static __cpuidle int intel_idle_xstate(struct cpuidle_device *dev,
+				       struct cpuidle_driver *drv, int index)
+{
+	fpu_idle_fpregs();
+	return __intel_idle(dev, drv, index);
+}
+
 /**
  * intel_idle_s2idle - Ask the processor to enter the given idle state.
  * @dev: cpuidle device of the target CPU.
@@ -174,8 +187,12 @@ static __cpuidle int intel_idle_irq(struct cpuidle_device *dev,
 static __cpuidle int intel_idle_s2idle(struct cpuidle_device *dev,
 				       struct cpuidle_driver *drv, int index)
 {
-	unsigned long eax = flg2MWAIT(drv->states[index].flags);
 	unsigned long ecx = 1; /* break on interrupt flag */
+	struct cpuidle_state *state = &drv->states[index];
+	unsigned long eax = flg2MWAIT(state->flags);
+
+	if (state->flags & CPUIDLE_FLAG_INIT_XSTATE)
+		fpu_idle_fpregs();
 
 	mwait_idle_with_hints(eax, ecx);
 
@@ -910,7 +927,8 @@ static struct cpuidle_state spr_cstates[] __initdata = {
 	{
 		.name = "C6",
 		.desc = "MWAIT 0x20",
-		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED |
+					   CPUIDLE_FLAG_INIT_XSTATE,
 		.exit_latency = 290,
 		.target_residency = 800,
 		.enter = &intel_idle,
@@ -1819,6 +1837,9 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
 		if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IRQ_ENABLE)
 			drv->states[drv->state_count].enter = intel_idle_irq;
 
+		if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_INIT_XSTATE)
+			drv->states[drv->state_count].enter = intel_idle_xstate;
+
 		if ((disabled_states_mask & BIT(drv->state_count)) ||
 		    ((icpu->use_acpi || force_use_acpi) &&
 		     intel_idle_off_by_default(mwait_hint) &&
-- 
2.17.1

Re: [PATCH v5 2/2] intel_idle: Add a new flag to initialize the AMX state

[Chang S. Bae]

On 6/10/2022 3:02 AM, Artem Bityutskiy wrote:
> 
> LGTM,
> 
> Reviewed-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> 

Thanks, Artem!

Chang

[tip: x86/fpu] x86/fpu: Add a helper to prepare AMX state for low-power CPU idle

[tip-bot2 for Chang S. Bae]

The following commit has been merged into the x86/fpu branch of tip:

Commit-ID:     012b91af28e4d83240e053e16af3528a902b0d84
Gitweb:        https://git.kernel.org/tip/012b91af28e4d83240e053e16af3528a902b0d84
Author:        Chang S. Bae <chang.seok.bae@intel.com>
AuthorDate:    Wed, 08 Jun 2022 09:47:47 -07:00
Committer:     Dave Hansen <dave.hansen@linux.intel.com>
CommitterDate: Tue, 14 Jun 2022 15:42:41 -07:00

x86/fpu: Add a helper to prepare AMX state for low-power CPU idle

When a CPU enters an idle state, a non-initialized AMX register state may
be the cause of preventing a deeper low-power state. Other extended
register states whether initialized or not do not impact the CPU idle
state.

The new helper can ensure the AMX state is initialized before the CPU is
idle, and it will be used by the intel idle driver.

Check the AMX_TILE feature bit before using XGETBV1 as a chain of
dependencies was established via cpuid_deps[]: AMX->XFD->XGETBV1.

Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lkml.kernel.org/r/20220608164748.11864-2-chang.seok.bae@intel.com
---
 arch/x86/include/asm/fpu/api.h       |  2 ++
 arch/x86/include/asm/special_insns.h |  9 +++++++++
 arch/x86/kernel/fpu/core.c           | 14 ++++++++++++++
 3 files changed, 25 insertions(+)

diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index 6b0f31f..503a577 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -164,4 +164,6 @@ static inline bool fpstate_is_confidential(struct fpu_guest *gfpu)
 /* prctl */
 extern long fpu_xstate_prctl(int option, unsigned long arg2);
 
+extern void fpu_idle_fpregs(void);
+
 #endif /* _ASM_X86_FPU_API_H */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 45b18eb..35f709f 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -295,6 +295,15 @@ static inline int enqcmds(void __iomem *dst, const void *src)
 	return 0;
 }
 
+static inline void tile_release(void)
+{
+	/*
+	 * Instruction opcode for TILERELEASE; supported in binutils
+	 * version >= 2.36.
+	 */
+	asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0");
+}
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_SPECIAL_INSNS_H */
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 0fdc807..8fbbe89 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -851,3 +851,17 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr)
 	 */
 	return 0;
 }
+
+/*
+ * Initialize register state that may prevent from entering low-power idle.
+ * This function will be invoked from the cpuidle driver only when needed.
+ */
+void fpu_idle_fpregs(void)
+{
+	/* Note: AMX_TILE being enabled implies XGETBV1 support */
+	if (cpu_feature_enabled(X86_FEATURE_AMX_TILE) &&
+	    (xfeatures_in_use() & XFEATURE_MASK_XTILE)) {
+		tile_release();
+		fpregs_deactivate(&current->thread.fpu);
+	}
+}

[tip: x86/fpu] intel_idle: Add a new flag to initialize the AMX state

[tip-bot2 for Chang S. Bae]

The following commit has been merged into the x86/fpu branch of tip:

Commit-ID:     f08ef9057b7b110f44cd364744ba6b5f0115390f
Gitweb:        https://git.kernel.org/tip/f08ef9057b7b110f44cd364744ba6b5f0115390f
Author:        Chang S. Bae <chang.seok.bae@intel.com>
AuthorDate:    Tue, 14 Jun 2022 09:41:16 -07:00
Committer:     Dave Hansen <dave.hansen@linux.intel.com>
CommitterDate: Tue, 14 Jun 2022 15:48:58 -07:00

intel_idle: Add a new flag to initialize the AMX state

The non-initialized AMX state can be the cause of C-state demotion from C6
to C1E. This low-power idle state may improve power savings and thus result
in a higher available turbo frequency budget.

This behavior is implementation-specific. Initialize the state for the C6
entrance of Sapphire Rapids as needed.

Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Link: https://lkml.kernel.org/r/20220608164748.11864-3-chang.seok.bae@intel.com
Link: https://lkml.kernel.org/r/20220614164116.5196-1-chang.seok.bae@intel.com
---
 drivers/idle/intel_idle.c | 25 +++++++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 424ef47..8a19ba1 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -54,6 +54,7 @@
 #include <asm/intel-family.h>
 #include <asm/mwait.h>
 #include <asm/msr.h>
+#include <asm/fpu/api.h>
 
 #define INTEL_IDLE_VERSION "0.5.1"
 
@@ -106,6 +107,11 @@ static unsigned int mwait_substates __initdata;
 #define CPUIDLE_FLAG_ALWAYS_ENABLE	BIT(15)
 
 /*
+ * Initialize large xstate for the C6-state entrance.
+ */
+#define CPUIDLE_FLAG_INIT_XSTATE	BIT(16)
+
+/*
  * MWAIT takes an 8-bit "hint" in EAX "suggesting"
  * the C-state (top nibble) and sub-state (bottom nibble)
  * 0x00 means "MWAIT(C1)", 0x10 means "MWAIT(C2)" etc.
@@ -159,6 +165,13 @@ static __cpuidle int intel_idle_irq(struct cpuidle_device *dev,
 	return ret;
 }
 
+static __cpuidle int intel_idle_xstate(struct cpuidle_device *dev,
+				       struct cpuidle_driver *drv, int index)
+{
+	fpu_idle_fpregs();
+	return __intel_idle(dev, drv, index);
+}
+
 /**
  * intel_idle_s2idle - Ask the processor to enter the given idle state.
  * @dev: cpuidle device of the target CPU.
@@ -174,8 +187,12 @@ static __cpuidle int intel_idle_irq(struct cpuidle_device *dev,
 static __cpuidle int intel_idle_s2idle(struct cpuidle_device *dev,
 				       struct cpuidle_driver *drv, int index)
 {
-	unsigned long eax = flg2MWAIT(drv->states[index].flags);
 	unsigned long ecx = 1; /* break on interrupt flag */
+	struct cpuidle_state *state = &drv->states[index];
+	unsigned long eax = flg2MWAIT(state->flags);
+
+	if (state->flags & CPUIDLE_FLAG_INIT_XSTATE)
+		fpu_idle_fpregs();
 
 	mwait_idle_with_hints(eax, ecx);
 
@@ -910,7 +927,8 @@ static struct cpuidle_state spr_cstates[] __initdata = {
 	{
 		.name = "C6",
 		.desc = "MWAIT 0x20",
-		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED |
+					   CPUIDLE_FLAG_INIT_XSTATE,
 		.exit_latency = 290,
 		.target_residency = 800,
 		.enter = &intel_idle,
@@ -1819,6 +1837,9 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
 		if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IRQ_ENABLE)
 			drv->states[drv->state_count].enter = intel_idle_irq;
 
+		if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_INIT_XSTATE)
+			drv->states[drv->state_count].enter = intel_idle_xstate;
+
 		if ((disabled_states_mask & BIT(drv->state_count)) ||
 		    ((icpu->use_acpi || force_use_acpi) &&
 		     intel_idle_off_by_default(mwait_hint) &&

[tip: x86/fpu] x86/fpu: Add a helper to prepare AMX state for low-power CPU idle

[tip-bot2 for Chang S. Bae]

The following commit has been merged into the x86/fpu branch of tip:

Commit-ID:     418bf5f906c33e83e76239748982dc3d2330cf30
Gitweb:        https://git.kernel.org/tip/418bf5f906c33e83e76239748982dc3d2330cf30
Author:        Chang S. Bae <chang.seok.bae@intel.com>
AuthorDate:    Wed, 08 Jun 2022 09:47:47 -07:00
Committer:     Dave Hansen <dave.hansen@linux.intel.com>
CommitterDate: Tue, 14 Jun 2022 15:48:44 -07:00

x86/fpu: Add a helper to prepare AMX state for low-power CPU idle

When a CPU enters an idle state, a non-initialized AMX register state may
be the cause of preventing a deeper low-power state. Other extended
register states whether initialized or not do not impact the CPU idle
state.

The new helper can ensure the AMX state is initialized before the CPU is
idle, and it will be used by the intel idle driver.

Check the AMX_TILE feature bit before using XGETBV1 as a chain of
dependencies was established via cpuid_deps[]: AMX->XFD->XGETBV1.

Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lkml.kernel.org/r/20220608164748.11864-2-chang.seok.bae@intel.com
---
 arch/x86/include/asm/fpu/api.h       |  2 ++
 arch/x86/include/asm/special_insns.h |  9 +++++++++
 arch/x86/kernel/fpu/core.c           | 14 ++++++++++++++
 3 files changed, 25 insertions(+)

diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index 6b0f31f..503a577 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -164,4 +164,6 @@ static inline bool fpstate_is_confidential(struct fpu_guest *gfpu)
 /* prctl */
 extern long fpu_xstate_prctl(int option, unsigned long arg2);
 
+extern void fpu_idle_fpregs(void);
+
 #endif /* _ASM_X86_FPU_API_H */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 45b18eb..35f709f 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -295,6 +295,15 @@ static inline int enqcmds(void __iomem *dst, const void *src)
 	return 0;
 }
 
+static inline void tile_release(void)
+{
+	/*
+	 * Instruction opcode for TILERELEASE; supported in binutils
+	 * version >= 2.36.
+	 */
+	asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0");
+}
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_SPECIAL_INSNS_H */
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 0531d6a..3b28c5b 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -851,3 +851,17 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr)
 	 */
 	return 0;
 }
+
+/*
+ * Initialize register state that may prevent from entering low-power idle.
+ * This function will be invoked from the cpuidle driver only when needed.
+ */
+void fpu_idle_fpregs(void)
+{
+	/* Note: AMX_TILE being enabled implies XGETBV1 support */
+	if (cpu_feature_enabled(X86_FEATURE_AMX_TILE) &&
+	    (xfeatures_in_use() & XFEATURE_MASK_XTILE)) {
+		tile_release();
+		fpregs_deactivate(&current->thread.fpu);
+	}
+}

Re: [PATCH v5 2/2] intel_idle: Add a new flag to initialize the AMX state

[Artem Bityutskiy]

On Tue, 2022-06-14 at 10:23 -0700, Chang S. Bae wrote:
> On 6/10/2022 3:02 AM, Artem Bityutskiy wrote:
> > 
> > LGTM,
> > 
> > Reviewed-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> 
> 
> Thanks, Artem!

I apologize for sending that e-mail in HTML format. It did not reach the mailing
lists.

Artem.

Re: [tip: x86/fpu] intel_idle: Add a new flag to initialize the AMX state

[Borislav Petkov]

Hi,

this is conflicting with the retbleed changes which went upstream and
resolving those conflicts would practically mean rewriting your patches.

Can you please redo them ontop of -rc7 and send them again?

This is not something we normally do but retbleed is not something
normal so..

Thanks!

On Tue, Jun 14, 2022 at 10:53:58PM -0000, tip-bot2 for Chang S. Bae wrote:
> The following commit has been merged into the x86/fpu branch of tip:
> 
> Commit-ID:     f08ef9057b7b110f44cd364744ba6b5f0115390f
> Gitweb:        https://git.kernel.org/tip/f08ef9057b7b110f44cd364744ba6b5f0115390f
> Author:        Chang S. Bae <chang.seok.bae@intel.com>
> AuthorDate:    Tue, 14 Jun 2022 09:41:16 -07:00
> Committer:     Dave Hansen <dave.hansen@linux.intel.com>
> CommitterDate: Tue, 14 Jun 2022 15:48:58 -07:00
> 
> intel_idle: Add a new flag to initialize the AMX state
> 
> The non-initialized AMX state can be the cause of C-state demotion from C6
> to C1E. This low-power idle state may improve power savings and thus result
> in a higher available turbo frequency budget.
> 
> This behavior is implementation-specific. Initialize the state for the C6
> entrance of Sapphire Rapids as needed.
> 
> Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
> Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
> Tested-by: Zhang Rui <rui.zhang@intel.com>
> Link: https://lkml.kernel.org/r/20220608164748.11864-3-chang.seok.bae@intel.com
> Link: https://lkml.kernel.org/r/20220614164116.5196-1-chang.seok.bae@intel.com
> ---
>  drivers/idle/intel_idle.c | 25 +++++++++++++++++++++++--
>  1 file changed, 23 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
> index 424ef47..8a19ba1 100644
> --- a/drivers/idle/intel_idle.c
> +++ b/drivers/idle/intel_idle.c
> @@ -54,6 +54,7 @@
>  #include <asm/intel-family.h>
>  #include <asm/mwait.h>
>  #include <asm/msr.h>
> +#include <asm/fpu/api.h>
>  
>  #define INTEL_IDLE_VERSION "0.5.1"
>  
> @@ -106,6 +107,11 @@ static unsigned int mwait_substates __initdata;
>  #define CPUIDLE_FLAG_ALWAYS_ENABLE	BIT(15)
>  
>  /*
> + * Initialize large xstate for the C6-state entrance.
> + */
> +#define CPUIDLE_FLAG_INIT_XSTATE	BIT(16)
> +
> +/*
>   * MWAIT takes an 8-bit "hint" in EAX "suggesting"
>   * the C-state (top nibble) and sub-state (bottom nibble)
>   * 0x00 means "MWAIT(C1)", 0x10 means "MWAIT(C2)" etc.
> @@ -159,6 +165,13 @@ static __cpuidle int intel_idle_irq(struct cpuidle_device *dev,
>  	return ret;
>  }
>  
> +static __cpuidle int intel_idle_xstate(struct cpuidle_device *dev,
> +				       struct cpuidle_driver *drv, int index)
> +{
> +	fpu_idle_fpregs();
> +	return __intel_idle(dev, drv, index);
> +}
> +
>  /**
>   * intel_idle_s2idle - Ask the processor to enter the given idle state.
>   * @dev: cpuidle device of the target CPU.
> @@ -174,8 +187,12 @@ static __cpuidle int intel_idle_irq(struct cpuidle_device *dev,
>  static __cpuidle int intel_idle_s2idle(struct cpuidle_device *dev,
>  				       struct cpuidle_driver *drv, int index)
>  {
> -	unsigned long eax = flg2MWAIT(drv->states[index].flags);
>  	unsigned long ecx = 1; /* break on interrupt flag */
> +	struct cpuidle_state *state = &drv->states[index];
> +	unsigned long eax = flg2MWAIT(state->flags);
> +
> +	if (state->flags & CPUIDLE_FLAG_INIT_XSTATE)
> +		fpu_idle_fpregs();
>  
>  	mwait_idle_with_hints(eax, ecx);
>  
> @@ -910,7 +927,8 @@ static struct cpuidle_state spr_cstates[] __initdata = {
>  	{
>  		.name = "C6",
>  		.desc = "MWAIT 0x20",
> -		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
> +		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED |
> +					   CPUIDLE_FLAG_INIT_XSTATE,
>  		.exit_latency = 290,
>  		.target_residency = 800,
>  		.enter = &intel_idle,
> @@ -1819,6 +1837,9 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
>  		if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IRQ_ENABLE)
>  			drv->states[drv->state_count].enter = intel_idle_irq;
>  
> +		if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_INIT_XSTATE)
> +			drv->states[drv->state_count].enter = intel_idle_xstate;
> +
>  		if ((disabled_states_mask & BIT(drv->state_count)) ||
>  		    ((icpu->use_acpi || force_use_acpi) &&
>  		     intel_idle_off_by_default(mwait_hint) &&

-- 
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette

[PATCH][Rebased] intel_idle: Add a new flag to initialize the AMX state

[Chang S. Bae]

The non-initialized AMX state can be the cause of C-state demotion from C6
to C1E. This low-power idle state may improve power savings and thus result
in a higher available turbo frequency budget.

This behavior is implementation-specific. Initialize the state for the C6
entrance of Sapphire Rapids as needed.

Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Link: https://lkml.kernel.org/r/20220608164748.11864-3-chang.seok.bae@intel.com
Link: https://lkml.kernel.org/r/20220614164116.5196-1-chang.seok.bae@intel.com
[ changb: Rebased to the upstream again. ]
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
---
The patch merged in the tip's x86/fpu has conflict with the retbleed patch
-- commit bf5835bcdb96 ("intel_idle: Disable IBRS during long idle") as of
v5.19-rc7.
---
 drivers/idle/intel_idle.c | 25 +++++++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index f5c6802aa6c3..1ec221079367 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -56,6 +56,7 @@
 #include <asm/nospec-branch.h>
 #include <asm/mwait.h>
 #include <asm/msr.h>
+#include <asm/fpu/api.h>
 
 #define INTEL_IDLE_VERSION "0.5.1"
 
@@ -113,6 +114,11 @@ static unsigned int mwait_substates __initdata;
  */
 #define CPUIDLE_FLAG_IBRS		BIT(16)
 
+/*
+ * Initialize large xstate for the C6-state entrance.
+ */
+#define CPUIDLE_FLAG_INIT_XSTATE	BIT(17)
+
 /*
  * MWAIT takes an 8-bit "hint" in EAX "suggesting"
  * the C-state (top nibble) and sub-state (bottom nibble)
@@ -185,6 +191,13 @@ static __cpuidle int intel_idle_ibrs(struct cpuidle_device *dev,
 	return ret;
 }
 
+static __cpuidle int intel_idle_xstate(struct cpuidle_device *dev,
+				       struct cpuidle_driver *drv, int index)
+{
+	fpu_idle_fpregs();
+	return __intel_idle(dev, drv, index);
+}
+
 /**
  * intel_idle_s2idle - Ask the processor to enter the given idle state.
  * @dev: cpuidle device of the target CPU.
@@ -200,8 +213,12 @@ static __cpuidle int intel_idle_ibrs(struct cpuidle_device *dev,
 static __cpuidle int intel_idle_s2idle(struct cpuidle_device *dev,
 				       struct cpuidle_driver *drv, int index)
 {
-	unsigned long eax = flg2MWAIT(drv->states[index].flags);
 	unsigned long ecx = 1; /* break on interrupt flag */
+	struct cpuidle_state *state = &drv->states[index];
+	unsigned long eax = flg2MWAIT(state->flags);
+
+	if (state->flags & CPUIDLE_FLAG_INIT_XSTATE)
+		fpu_idle_fpregs();
 
 	mwait_idle_with_hints(eax, ecx);
 
@@ -936,7 +953,8 @@ static struct cpuidle_state spr_cstates[] __initdata = {
 	{
 		.name = "C6",
 		.desc = "MWAIT 0x20",
-		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED |
+					   CPUIDLE_FLAG_INIT_XSTATE,
 		.exit_latency = 290,
 		.target_residency = 800,
 		.enter = &intel_idle,
@@ -1851,6 +1869,9 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
 			drv->states[drv->state_count].enter = intel_idle_ibrs;
 		}
 
+		if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_INIT_XSTATE)
+			drv->states[drv->state_count].enter = intel_idle_xstate;
+
 		if ((disabled_states_mask & BIT(drv->state_count)) ||
 		    ((icpu->use_acpi || force_use_acpi) &&
 		     intel_idle_off_by_default(mwait_hint) &&
-- 
2.17.1

[tip: x86/fpu] intel_idle: Add a new flag to initialize the AMX state

[tip-bot2 for Chang S. Bae]

The following commit has been merged into the x86/fpu branch of tip:

Commit-ID:     9f01129382774d98ec21526f13da26a0630ee3d8
Gitweb:        https://git.kernel.org/tip/9f01129382774d98ec21526f13da26a0630ee3d8
Author:        Chang S. Bae <chang.seok.bae@intel.com>
AuthorDate:    Mon, 18 Jul 2022 11:56:11 -07:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Tue, 19 Jul 2022 19:17:28 +02:00

intel_idle: Add a new flag to initialize the AMX state

The non-initialized AMX state can be the cause of C-state demotion from C6
to C1E. This low-power idle state may improve power savings and thus result
in a higher available turbo frequency budget.

This behavior is implementation-specific. Initialize the state for the C6
entrance of Sapphire Rapids as needed.

Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Link: https://lkml.kernel.org/r/20220614164116.5196-1-chang.seok.bae@intel.com
---
 drivers/idle/intel_idle.c | 25 +++++++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index f5c6802..1ec2210 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -56,6 +56,7 @@
 #include <asm/nospec-branch.h>
 #include <asm/mwait.h>
 #include <asm/msr.h>
+#include <asm/fpu/api.h>
 
 #define INTEL_IDLE_VERSION "0.5.1"
 
@@ -114,6 +115,11 @@ static unsigned int mwait_substates __initdata;
 #define CPUIDLE_FLAG_IBRS		BIT(16)
 
 /*
+ * Initialize large xstate for the C6-state entrance.
+ */
+#define CPUIDLE_FLAG_INIT_XSTATE	BIT(17)
+
+/*
  * MWAIT takes an 8-bit "hint" in EAX "suggesting"
  * the C-state (top nibble) and sub-state (bottom nibble)
  * 0x00 means "MWAIT(C1)", 0x10 means "MWAIT(C2)" etc.
@@ -185,6 +191,13 @@ static __cpuidle int intel_idle_ibrs(struct cpuidle_device *dev,
 	return ret;
 }
 
+static __cpuidle int intel_idle_xstate(struct cpuidle_device *dev,
+				       struct cpuidle_driver *drv, int index)
+{
+	fpu_idle_fpregs();
+	return __intel_idle(dev, drv, index);
+}
+
 /**
  * intel_idle_s2idle - Ask the processor to enter the given idle state.
  * @dev: cpuidle device of the target CPU.
@@ -200,8 +213,12 @@ static __cpuidle int intel_idle_ibrs(struct cpuidle_device *dev,
 static __cpuidle int intel_idle_s2idle(struct cpuidle_device *dev,
 				       struct cpuidle_driver *drv, int index)
 {
-	unsigned long eax = flg2MWAIT(drv->states[index].flags);
 	unsigned long ecx = 1; /* break on interrupt flag */
+	struct cpuidle_state *state = &drv->states[index];
+	unsigned long eax = flg2MWAIT(state->flags);
+
+	if (state->flags & CPUIDLE_FLAG_INIT_XSTATE)
+		fpu_idle_fpregs();
 
 	mwait_idle_with_hints(eax, ecx);
 
@@ -936,7 +953,8 @@ static struct cpuidle_state spr_cstates[] __initdata = {
 	{
 		.name = "C6",
 		.desc = "MWAIT 0x20",
-		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED |
+					   CPUIDLE_FLAG_INIT_XSTATE,
 		.exit_latency = 290,
 		.target_residency = 800,
 		.enter = &intel_idle,
@@ -1851,6 +1869,9 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
 			drv->states[drv->state_count].enter = intel_idle_ibrs;
 		}
 
+		if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_INIT_XSTATE)
+			drv->states[drv->state_count].enter = intel_idle_xstate;
+
 		if ((disabled_states_mask & BIT(drv->state_count)) ||
 		    ((icpu->use_acpi || force_use_acpi) &&
 		     intel_idle_off_by_default(mwait_hint) &&

[tip: x86/fpu] x86/fpu: Add a helper to prepare AMX state for low-power CPU idle

[tip-bot2 for Chang S. Bae]

The following commit has been merged into the x86/fpu branch of tip:

Commit-ID:     f17b168734c0fe47343a7502d012266a051f9942
Gitweb:        https://git.kernel.org/tip/f17b168734c0fe47343a7502d012266a051f9942
Author:        Chang S. Bae <chang.seok.bae@intel.com>
AuthorDate:    Wed, 08 Jun 2022 09:47:47 -07:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Tue, 19 Jul 2022 18:46:15 +02:00

x86/fpu: Add a helper to prepare AMX state for low-power CPU idle

When a CPU enters an idle state, a non-initialized AMX register state may
be the cause of preventing a deeper low-power state. Other extended
register states whether initialized or not do not impact the CPU idle
state.

The new helper can ensure the AMX state is initialized before the CPU is
idle, and it will be used by the intel idle driver.

Check the AMX_TILE feature bit before using XGETBV1 as a chain of
dependencies was established via cpuid_deps[]: AMX->XFD->XGETBV1.

Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20220608164748.11864-2-chang.seok.bae@intel.com
---
 arch/x86/include/asm/fpu/api.h       |  2 ++
 arch/x86/include/asm/special_insns.h |  9 +++++++++
 arch/x86/kernel/fpu/core.c           | 14 ++++++++++++++
 3 files changed, 25 insertions(+)

diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index 6b0f31f..503a577 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -164,4 +164,6 @@ static inline bool fpstate_is_confidential(struct fpu_guest *gfpu)
 /* prctl */
 extern long fpu_xstate_prctl(int option, unsigned long arg2);
 
+extern void fpu_idle_fpregs(void);
+
 #endif /* _ASM_X86_FPU_API_H */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 45b18eb..35f709f 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -295,6 +295,15 @@ static inline int enqcmds(void __iomem *dst, const void *src)
 	return 0;
 }
 
+static inline void tile_release(void)
+{
+	/*
+	 * Instruction opcode for TILERELEASE; supported in binutils
+	 * version >= 2.36.
+	 */
+	asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0");
+}
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_SPECIAL_INSNS_H */
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 0531d6a..3b28c5b 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -851,3 +851,17 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr)
 	 */
 	return 0;
 }
+
+/*
+ * Initialize register state that may prevent from entering low-power idle.
+ * This function will be invoked from the cpuidle driver only when needed.
+ */
+void fpu_idle_fpregs(void)
+{
+	/* Note: AMX_TILE being enabled implies XGETBV1 support */
+	if (cpu_feature_enabled(X86_FEATURE_AMX_TILE) &&
+	    (xfeatures_in_use() & XFEATURE_MASK_XTILE)) {
+		tile_release();
+		fpregs_deactivate(&current->thread.fpu);
+	}
+}