summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--arch/x86/include/asm/fpu/api.h2
-rw-r--r--arch/x86/include/asm/special_insns.h9
-rw-r--r--arch/x86/kernel/fpu/core.c14
-rw-r--r--drivers/idle/intel_idle.c25
4 files changed, 48 insertions, 2 deletions
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);
+ }
+}
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 907700d1e78e..445b19d20b9a 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.
@@ -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) &&