@@ -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 */
@@ -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 */
@@ -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);
+ }
+}
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(+)