Browse Source

x86/asm/entry/32: Stop caching MSR_IA32_SYSENTER_ESP in tss.sp1

We write a stack pointer to MSR_IA32_SYSENTER_ESP exactly once,
and we unnecessarily cache the value in tss.sp1.  We never
read the cached value.

Remove all of the caching.  It serves no purpose.

Suggested-by: Denys Vlasenko <dvlasenk@redhat.com>
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/05a0163eb33ef5208363f0015496855da7cebadd.1428002830.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Andy Lutomirski 10 years ago
parent
commit
cf9328cc99
2 changed files with 16 additions and 15 deletions
  1. 11 11
      arch/x86/include/asm/processor.h
  2. 5 4
      arch/x86/kernel/cpu/common.c

+ 11 - 11
arch/x86/include/asm/processor.h

@@ -209,21 +209,21 @@ struct x86_hw_tss {
 	unsigned short		back_link, __blh;
 	unsigned long		sp0;
 	unsigned short		ss0, __ss0h;
+	unsigned long		sp1;
 
 	/*
-	 * We don't use ring 1, so sp1 and ss1 are convenient scratch
-	 * spaces in the same cacheline as sp0.  We use them to cache
-	 * some MSR values to avoid unnecessary wrmsr instructions.
+	 * We don't use ring 1, so ss1 is a convenient scratch space in
+	 * the same cacheline as sp0.  We use ss1 to cache the value in
+	 * MSR_IA32_SYSENTER_CS.  When we context switch
+	 * MSR_IA32_SYSENTER_CS, we first check if the new value being
+	 * written matches ss1, and, if it's not, then we wrmsr the new
+	 * value and update ss1.
 	 *
-	 * We use SYSENTER_ESP to find sp0 and for the NMI emergency
-	 * stack, but we need to context switch it because we do
-	 * horrible things to the kernel stack in vm86 mode.
-	 *
-	 * We use SYSENTER_CS to disable sysenter in vm86 mode to avoid
-	 * corrupting the stack if we went through the sysenter path
-	 * from vm86 mode.
+	 * The only reason we context switch MSR_IA32_SYSENTER_CS is
+	 * that we set it to zero in vm86 tasks to avoid corrupting the
+	 * stack if we were to go through the sysenter path from vm86
+	 * mode.
 	 */
-	unsigned long		sp1;	/* MSR_IA32_SYSENTER_ESP */
 	unsigned short		ss1;	/* MSR_IA32_SYSENTER_CS */
 
 	unsigned short		__ss1h;

+ 5 - 4
arch/x86/kernel/cpu/common.c

@@ -976,15 +976,16 @@ void enable_sep_cpu(void)
 		goto out;
 
 	/*
-	 * The struct::SS1 and tss_struct::SP1 fields are not used by the hardware,
-	 * we cache the SYSENTER CS and ESP values there for easy access:
+	 * We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field --
+	 * see the big comment in struct x86_hw_tss's definition.
 	 */
 
 	tss->x86_tss.ss1 = __KERNEL_CS;
 	wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0);
 
-	tss->x86_tss.sp1 = (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack);
-	wrmsr(MSR_IA32_SYSENTER_ESP, tss->x86_tss.sp1, 0);
+	wrmsr(MSR_IA32_SYSENTER_ESP,
+	      (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack),
+	      0);
 
 	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)ia32_sysenter_target, 0);