Merge tag 'x86_fpu_for_v6.0_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fpu update from Borislav Petkov:

 - Add machinery to initialize AMX register state in order for
   AMX-capable CPUs to be able to enter deeper low-power state

* tag 'x86_fpu_for_v6.0_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  intel_idle: Add a new flag to initialize the AMX state
  x86/fpu: Add a helper to prepare AMX state for low-power CPU idle

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 */

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 */

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);
+	}
+}

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)
@@ -191,6 +197,13 @@ 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.
@@ -206,8 +219,12 @@ 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);
 
@@ -942,7 +959,8 @@ 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,
@@ -1857,6 +1875,9 @@ 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) &&