[PATCH v2 2/3] x86/process: Correct and optimize TIF_BLOCKSTEP switch

[Kyle Huey]

Because the MSR is "highly magical", reset DEBUGCTLMSR_BTF on every task
switch in or out of a task that uses TIF_BLOCKSTEP, even if both tasks
have TIF_BLOCKSTEP set.  Avoid branching within the TIF_BLOCKSTEP case
and evaluating boot_cpu_data twice in kernels without
CONFIG_X86_DEBUGCTLMSR.

x86_64: arch/x86/kernel/process.o
text	data	bss	dec	 hex
3024    8577    16      11617    2d61	Before
3008	8577	16	11601	 2d51	After

i386: No change

Originally-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Kyle Huey <khuey@xxxxxxxxxxxx>
---
 arch/x86/include/asm/msr-index.h |  1 +
 arch/x86/kernel/process.c        | 12 ++++++------
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 710273c617b8..a8997a7b4e74 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -127,6 +127,7 @@
 
 /* DEBUGCTLMSR bits (others vary by model): */
 #define DEBUGCTLMSR_LBR			(1UL <<  0) /* last branch recording */
+#define _DEBUGCTLMSR_BTF		1
 #define DEBUGCTLMSR_BTF			(1UL <<  1) /* single-step on branches */
 #define DEBUGCTLMSR_TR			(1UL <<  6)
 #define DEBUGCTLMSR_BTS			(1UL <<  7)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 01ef6f63d5fb..5dd08328108e 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -209,13 +209,13 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 
 	propagate_user_return_notify(prev_p, next_p);
 
-	if ((tifp ^ tifn) & _TIF_BLOCKSTEP) {
-		unsigned long debugctl = get_debugctlmsr();
-
+	if ((tifp & _TIF_BLOCKSTEP || tifn & _TIF_BLOCKSTEP) &&
+	    arch_has_block_step()) {
+		unsigned long debugctl;
+		rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
 		debugctl &= ~DEBUGCTLMSR_BTF;
-		if (tifn & _TIF_BLOCKSTEP)
-			debugctl |= DEBUGCTLMSR_BTF;
-		update_debugctlmsr(debugctl);
+		debugctl |= (tifn & _TIF_BLOCKSTEP) >> TIF_BLOCKSTEP << _DEBUGCTLMSR_BTF;
+		wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
 	}
 
 	if ((tifp ^ tifn) & _TIF_NOTSC) {
-- 
2.11.0