x86/fpu: Make AMX state ready for CPU idle
Subsystems (2)
v5 cover x86/fpu: Make AMX state ready for CPU idle
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/[email protected]/
[2]: https://lore.kernel.org/lkml/[email protected]/
[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
Signature · 1 line
2.17.1
PATCH v5 1/2 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.
---
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(+)
arch/x86/include/asm/fpu/api.h +2 -0
@@ -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 */
arch/x86/include/asm/special_insns.h +9 -0
@@ -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. +*/ + asmvolatile (".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0" ); +} +#endif /* __KERNEL__ */ #endif /* _ASM_X86_SPECIAL_INSNS_H */
arch/x86/kernel/fpu/core.c +14 -0
@@ -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 (¤t->thread.fpu); + } +}
Signature · 1 line
2.17.1
[tip: x86/fpu] x86/fpu: Add a helper to prepare AMX state for low-power CPU idle
The following commit has been merged into the x86/fpu branch of tip:
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 <[email protected]> AuthorDate: Wed, 08 Jun 2022 09:47:47 -07:00 Committer: Dave Hansen <[email protected]> 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.
--- 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(+)
arch/x86/include/asm/fpu/api.h +2 -0
@@ -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 */
arch/x86/include/asm/special_insns.h +9 -0
@@ -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. +*/ + asmvolatile (".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0" ); +} +#endif /* __KERNEL__ */ #endif /* _ASM_X86_SPECIAL_INSNS_H */
arch/x86/kernel/fpu/core.c +14 -0
@@ -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 (¤t->thread.fpu); + } +}
[tip: x86/fpu] x86/fpu: Add a helper to prepare AMX state for low-power CPU idle
In reply to Chang S. BaeThe following commit has been merged into the x86/fpu branch of tip:
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 <[email protected]> AuthorDate: Wed, 08 Jun 2022 09:47:47 -07:00 Committer: Dave Hansen <[email protected]> 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.
--- 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(+)
arch/x86/include/asm/fpu/api.h +2 -0
@@ -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 */
arch/x86/include/asm/special_insns.h +9 -0
@@ -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. +*/ + asmvolatile (".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0" ); +} +#endif /* __KERNEL__ */ #endif /* _ASM_X86_SPECIAL_INSNS_H */
arch/x86/kernel/fpu/core.c +14 -0
@@ -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 (¤t->thread.fpu); + } +}
[tip: x86/fpu] x86/fpu: Add a helper to prepare AMX state for low-power CPU idle
In reply to Chang S. BaeThe following commit has been merged into the x86/fpu branch of tip:
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 <[email protected]> AuthorDate: Wed, 08 Jun 2022 09:47:47 -07:00 Committer: Dave Hansen <[email protected]> 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.
--- 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(+)
arch/x86/include/asm/fpu/api.h +2 -0
@@ -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 */
arch/x86/include/asm/special_insns.h +9 -0
@@ -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. +*/ + asmvolatile (".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0" ); +} +#endif /* __KERNEL__ */ #endif /* _ASM_X86_SPECIAL_INSNS_H */
arch/x86/kernel/fpu/core.c +14 -0
@@ -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 (¤t->thread.fpu); + } +}
[tip: x86/fpu] x86/fpu: Add a helper to prepare AMX state for low-power CPU idle
In reply to Chang S. BaeThe following commit has been merged into the x86/fpu branch of tip:
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 <[email protected]> AuthorDate: Wed, 08 Jun 2022 09:47:47 -07:00 Committer: Borislav Petkov <[email protected]> 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.
--- 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(+)
arch/x86/include/asm/fpu/api.h +2 -0
@@ -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 */
arch/x86/include/asm/special_insns.h +9 -0
@@ -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. +*/ + asmvolatile (".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0" ); +} +#endif /* __KERNEL__ */ #endif /* _ASM_X86_SPECIAL_INSNS_H */
arch/x86/kernel/fpu/core.c +14 -0
@@ -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 (¤t->thread.fpu); + } +}
PATCH v5 2/2 intel_idle: Add a new flag to initialize the AMX state
In reply to Chang S. BaeThe 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.
---
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(-)
drivers/idle/intel_idle.c +16 -2
@@ -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,
Signature · 1 line
2.17.1
[tip: x86/fpu] intel_idle: Add a new flag to initialize the AMX state
The following commit has been merged into the x86/fpu branch of tip:
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 <[email protected]> AuthorDate: Wed, 08 Jun 2022 09:47:48 -07:00 Committer: Dave Hansen <[email protected]> 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.
--- drivers/idle/intel_idle.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-)
drivers/idle/intel_idle.c +16 -2
@@ -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,
Re: [tip: x86/fpu] intel_idle: Add a new flag to initialize the AMX state
Review static __cpuidle int intel_idle(struct cpuidle_device *dev, · line 148
Quoted 10 lines · On Wed, Jun 08, 2022 at 07:32:37PM -0000, tip-bot2 for Chang S. Bae wrote:
(quoted diff) +3
-0@@ -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:
drivers/idle/intel_idle.c +10 -0
@@ -166,6 +166,13 @@ static __cpuidle int intel_idle_irq(strureturn 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_cstatif (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 1/1 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.
---
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(-)
drivers/idle/intel_idle.c +23 -2
@@ -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) &&
Signature · 1 line
2.17.1
[tip: x86/fpu] intel_idle: Add a new flag to initialize the AMX state
The following commit has been merged into the x86/fpu branch of tip:
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 <[email protected]> AuthorDate: Mon, 18 Jul 2022 11:56:11 -07:00 Committer: Borislav Petkov <[email protected]> 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.
--- drivers/idle/intel_idle.c | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-)
drivers/idle/intel_idle.c +23 -2
@@ -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) &&
A message that is not in the archive (sent off-list or not yet received): [email protected]
Re: [PATCH v5 2/2] intel_idle: Add a new flag to initialize the AMX state
Quoted 4 lines · Artem Bityutskiy
LGTM,
Reviewed-by Artem Bityutskiy <[email protected]>
Thanks, Artem!
Chang
Artem Bityutskiy
maintainerRe: [PATCH v5 2/2] intel_idle: Add a new flag to initialize the AMX state
Quoted 7 lines · Chang S. Bae
Quoted 4 lines · Artem Bityutskiy
LGTM,
Reviewed-by Artem Bityutskiy <[email protected]>Thanks, Artem!
I apologize for sending that e-mail in HTML format. It did not reach the mailing lists.
Artem.
[tip: x86/fpu] intel_idle: Add a new flag to initialize the AMX state
In reply to Chang S. BaeThe following commit has been merged into the x86/fpu branch of tip:
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 <[email protected]> AuthorDate: Tue, 14 Jun 2022 09:41:16 -07:00 Committer: Dave Hansen <[email protected]> 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.
--- drivers/idle/intel_idle.c | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-)
drivers/idle/intel_idle.c +23 -2
@@ -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) &&
Borislav Petkov
maintainerRe: [tip: x86/fpu] intel_idle: Add a new flag to initialize the AMX state
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!
Quoted 101 lines · 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 <[email protected]> AuthorDate: Tue, 14 Jun 2022 09:41:16 -07:00 Committer: Dave Hansen <[email protected]> CommitterDate: Tue, 14 Jun 2022 15:48:58 -07:00
intel_idle: Add a new flag to initialize the AMX stateThe 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) <[email protected]>Signed-off-by Chang S. Bae <[email protected]>Signed-off-by Dave Hansen <[email protected]>Tested-by Zhang Rui <[email protected]>--- drivers/idle/intel_idle.c | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-)drivers/idle/intel_idle.c +23
-2@@ -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) &&
Signature · 4 lines
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquettePATCH 1/1 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.
---
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(-)
drivers/idle/intel_idle.c +23 -2
@@ -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) &&
Signature · 1 line
2.17.1