Re: [tip:x86/asm] x86/asm/entry/64: Remove unused thread_struct::usersp

[Ingo Molnar <mingo@kernel.org>]

* Ingo Molnar <mingo@kernel.org> wrote:

> Could you try just this patch (on top of broken tip:master):
> 
> diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
> index 66a1954439ea..997e6a1c288f 100644
> --- a/arch/x86/include/asm/processor.h
> +++ b/arch/x86/include/asm/processor.h
> @@ -496,6 +496,7 @@ struct thread_struct {
>  #ifdef CONFIG_X86_32
>  	unsigned long		sysenter_cs;
>  #else
> +	unsigned long		usersp;	/* Copy from PDA */
>  	unsigned short		es;
>  	unsigned short		ds;
>  	unsigned short		fsindex;
> 
> to see whether it's the changed values of old_rsp, or the change in 
> sizeof(thread_struct), that causes the regression?

Assuming this does not fix the regression, could you apply the minimal 
patch below - which reverts the old_rsp handling change.

(The rest of the commit are in a third patch, but those are only 
comment changes.)

So my theory is that this change is what will revert the regression.

Thanks,

	Ingo

======================>

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 66a1954439ea..997e6a1c288f 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -907,6 +908,11 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
 #define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
 extern unsigned long KSTK_ESP(struct task_struct *task);
 
+/*
+ * User space RSP while inside the SYSCALL fast path
+ */
+DECLARE_PER_CPU(unsigned long, old_rsp);
+
 #endif /* CONFIG_X86_64 */
 
 extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 14df2be4711f..e8c124a1f885 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -161,6 +161,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 	p->thread.sp0 = (unsigned long)task_stack_page(p) + THREAD_SIZE;
 	childregs = task_pt_regs(p);
 	p->thread.sp = (unsigned long) childregs;
+	p->thread.usersp = me->thread.usersp;
 	set_tsk_thread_flag(p, TIF_FORK);
 	p->thread.io_bitmap_ptr = NULL;
 
@@ -234,8 +235,10 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip,
 	loadsegment(es, _ds);
 	loadsegment(ds, _ds);
 	load_gs_index(0);
+	current->thread.usersp	= new_sp;
 	regs->ip		= new_ip;
 	regs->sp		= new_sp;
+	this_cpu_write(old_rsp, new_sp);
 	regs->cs		= _cs;
 	regs->ss		= _ss;
 	regs->flags		= X86_EFLAGS_IF;
@@ -395,6 +398,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	/*
 	 * Switch the PDA and FPU contexts.
 	 */
+	prev->usersp = this_cpu_read(old_rsp);
+	this_cpu_write(old_rsp, next->usersp);
 	this_cpu_write(current_task, next_p);
 
 	/*