From: Andy Lutomirski Date: Mon, 4 Dec 2017 14:07:21 +0000 (+0100) Subject: x86/entry/64: Separate cpu_current_top_of_stack from TSS.sp0 X-Git-Tag: v4.19~1574^2~222 X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=9aaefe7b59ae00605256a7d6bd1c1456432495fc;p=platform%2Fkernel%2Flinux-rpi.git x86/entry/64: Separate cpu_current_top_of_stack from TSS.sp0 On 64-bit kernels, we used to assume that TSS.sp0 was the current top of stack. With the addition of an entry trampoline, this will no longer be the case. Store the current top of stack in TSS.sp1, which is otherwise unused but shares the same cacheline. Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Reviewed-by: Thomas Gleixner Reviewed-by: Borislav Petkov Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Dave Hansen Cc: David Laight Cc: Denys Vlasenko Cc: Eduardo Valentin Cc: Greg KH Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Will Deacon Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com Link: https://lkml.kernel.org/r/20171204150606.050864668@linutronix.de Signed-off-by: Ingo Molnar --- diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 7590512..b0cf061 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -309,7 +309,13 @@ struct x86_hw_tss { struct x86_hw_tss { u32 reserved1; u64 sp0; + + /* + * We store cpu_current_top_of_stack in sp1 so it's always accessible. + * Linux does not use ring 1, so sp1 is not otherwise needed. + */ u64 sp1; + u64 sp2; u64 reserved2; u64 ist[7]; @@ -368,6 +374,8 @@ DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss); #ifdef CONFIG_X86_32 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack); +#else +#define cpu_current_top_of_stack cpu_tss.x86_tss.sp1 #endif /* @@ -539,12 +547,12 @@ static inline void native_swapgs(void) static inline unsigned long current_top_of_stack(void) { -#ifdef CONFIG_X86_64 - return this_cpu_read_stable(cpu_tss.x86_tss.sp0); -#else - /* sp0 on x86_32 is special in and around vm86 mode. */ + /* + * We can't read directly from tss.sp0: sp0 on x86_32 is special in + * and around vm86 mode and sp0 on x86_64 is special because of the + * entry trampoline. + */ return this_cpu_read_stable(cpu_current_top_of_stack); -#endif } static inline bool on_thread_stack(void) diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 70f4259..44a0499 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -207,7 +207,7 @@ static inline int arch_within_stack_frames(const void * const stack, #else /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_64 -# define cpu_current_top_of_stack (cpu_tss + TSS_sp0) +# define cpu_current_top_of_stack (cpu_tss + TSS_sp1) #endif #endif diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index e3a5175..bf51e51 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -66,6 +66,7 @@ int main(void) OFFSET(TSS_ist, tss_struct, x86_tss.ist); OFFSET(TSS_sp0, tss_struct, x86_tss.sp0); + OFFSET(TSS_sp1, tss_struct, x86_tss.sp1); BLANK(); #ifdef CONFIG_CC_STACKPROTECTOR diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 35d6741..86e8376 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -56,6 +56,16 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { * Poison it. */ .sp0 = (1UL << (BITS_PER_LONG-1)) + 1, + +#ifdef CONFIG_X86_64 + /* + * .sp1 is cpu_current_top_of_stack. The init task never + * runs user code, but cpu_current_top_of_stack should still + * be well defined before the first context switch. + */ + .sp1 = TOP_OF_INIT_STACK, +#endif + #ifdef CONFIG_X86_32 .ss0 = __KERNEL_DS, .ss1 = __KERNEL_CS, diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 01b119b..157f818 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -461,6 +461,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Switch the PDA and FPU contexts. */ this_cpu_write(current_task, next_p); + this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p)); /* Reload sp0. */ update_sp0(next_p);