From 45948d7720e8bd0104696087c6305fdd90e3b298 Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@novell.com>
Date: Sat, 25 Mar 2006 16:29:25 +0100
Subject: [PATCH] [PATCH] x86_64: save FPU context slightly later

Touching of the floating point state in a kernel debugger must be
NMI-safe, specifically math_state_restore() must be able to deal with
being called out of an NMI context. In order to do that reliably, the
context switch code must take care to not leave a window open where
the current task's TS_USEDFPU flag and CR0.TS could get out of sync.

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
---
 arch/x86_64/kernel/process.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c
index 0cb93abbf564..81111835722d 100644
--- a/arch/x86_64/kernel/process.c
+++ b/arch/x86_64/kernel/process.c
@@ -527,8 +527,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	int cpu = smp_processor_id();  
 	struct tss_struct *tss = &per_cpu(init_tss, cpu);
 
-	unlazy_fpu(prev_p);
-
 	/*
 	 * Reload esp0, LDT and the page table pointer:
 	 */
@@ -586,11 +584,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	}
 
 	/* 
-	 * Switch the PDA context.
+	 * Switch the PDA and FPU contexts.
 	 */
 	prev->userrsp = read_pda(oldrsp); 
 	write_pda(oldrsp, next->userrsp); 
 	write_pda(pcurrent, next_p); 
+	/* This must be here to ensure both math_state_restore() and
+	   kernel_fpu_begin() work consistently. */
+	unlazy_fpu(prev_p);
 	write_pda(kernelstack,
 		  task_stack_page(next_p) + THREAD_SIZE - PDA_STACKOFFSET);
 
-- 
2.20.1