[patch 3/3] x86/process: Optimize TIF_NOTSC switch
From: Thomas Gleixner
Date: Thu Dec 15 2016 - 11:47:30 EST
Provide and use a toggle helper instead of doing it with a branch.
x86_64:
3662 8505 16 12183 2f97 Before
3646 8505 16 12167 2f87 After
i386:
5906 9388 1804 17098 42ca Before
5834 9324 1740 16898 4202 After
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
---
arch/x86/include/asm/tlbflush.h | 10 ++++++++++
arch/x86/kernel/process.c | 22 ++++------------------
2 files changed, 14 insertions(+), 18 deletions(-)
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -110,6 +110,16 @@ static inline void cr4_clear_bits(unsign
}
}
+static inline void cr4_toggle_bits(unsigned long mask)
+{
+ unsigned long cr4;
+
+ cr4 = this_cpu_read(cpu_tlbstate.cr4);
+ cr4 ^= mask;
+ this_cpu_write(cpu_tlbstate.cr4, cr4);
+ __write_cr4(cr4);
+}
+
/* Read the CR4 shadow. */
static inline unsigned long cr4_read_shadow(void)
{
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -116,11 +116,6 @@ void flush_thread(void)
fpu__clear(&tsk->thread.fpu);
}
-static void hard_disable_TSC(void)
-{
- cr4_set_bits(X86_CR4_TSD);
-}
-
void disable_TSC(void)
{
preempt_disable();
@@ -129,15 +124,10 @@ void disable_TSC(void)
* Must flip the CPU state synchronously with
* TIF_NOTSC in the current running context.
*/
- hard_disable_TSC();
+ cr4_set_bits(X86_CR4_TSD);
preempt_enable();
}
-static void hard_enable_TSC(void)
-{
- cr4_clear_bits(X86_CR4_TSD);
-}
-
static void enable_TSC(void)
{
preempt_disable();
@@ -146,7 +136,7 @@ static void enable_TSC(void)
* Must flip the CPU state synchronously with
* TIF_NOTSC in the current running context.
*/
- hard_enable_TSC();
+ cr4_clear_bits(X86_CR4_TSD);
preempt_enable();
}
@@ -212,12 +202,8 @@ void __switch_to_xtra(struct task_struct
if ((tifp ^ tifn) & _TIF_BLOCKSTEP)
toggle_debugctlmsr(DEBUGCTLMSR_BTF);
- if ((tifp ^ tifn) & _TIF_NOTSC) {
- if (tifn & _TIF_NOTSC)
- hard_disable_TSC();
- else
- hard_enable_TSC();
- }
+ if ((tifp ^ tifn) & _TIF_NOTSC)
+ cr4_toggle_bits(X86_CR4_TSD);
}
/*