From b9894a2f5bd18b1691cb6872c9afe32b148d0132 Mon Sep 17 00:00:00 2001 From: Kyle Huey Date: Tue, 14 Feb 2017 00:11:03 -0800 Subject: [PATCH] x86/process: Correct and optimize TIF_BLOCKSTEP switch The debug control MSR is "highly magical" as the blockstep bit can be cleared by hardware under not well documented circumstances. So a task switch relying on the bit set by the previous task (according to the previous tasks thread flags) can trip over this and not update the flag for the next task. To fix this its required to handle DEBUGCTLMSR_BTF when either the previous or the next or both tasks have the TIF_BLOCKSTEP flag set. While at it 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 [ tglx: Made the shift value explicit, use a local variable to make the code readable and massaged changelog] Originally-by: Thomas Gleixner Signed-off-by: Kyle Huey Cc: Peter Zijlstra Cc: Andy Lutomirski Link: http://lkml.kernel.org/r/20170214081104.9244-3-khuey@kylehuey.com Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/msr-index.h | 1 + arch/x86/kernel/process.c | 12 +++++++----- 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index d8b5f8ab8ef9..4c928f332f8f 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_SHIFT 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 ea9ea2582dab..83fa3cb4f8f0 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -222,13 +222,15 @@ 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, msk; + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); debugctl &= ~DEBUGCTLMSR_BTF; - if (tifn & _TIF_BLOCKSTEP) - debugctl |= DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); + msk = tifn & _TIF_BLOCKSTEP; + debugctl |= (msk >> TIF_BLOCKSTEP) << DEBUGCTLMSR_BTF_SHIFT; + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); } if ((tifp ^ tifn) & _TIF_NOTSC) {