x86/entry/32: Introduce and use X86_BUG_ESPFIX instead of paravirt_enabled

x86_64 has very clean espfix handling on paravirt: espfix64 is set
up in native_iret, so paravirt systems that override iret bypass
espfix64 automatically.  This is robust and straightforward.

x86_32 is messier.  espfix is set up before the IRET paravirt patch
point, so it can't be directly conditionalized on whether we use
native_iret.  We also can't easily move it into native_iret without
regressing performance due to a bizarre consideration.  Specifically,
on 64-bit kernels, the logic is:

  if (regs->ss & 0x4)
          setup_espfix;

On 32-bit kernels, the logic is:

  if ((regs->ss & 0x4) && (regs->cs & 0x3) == 3 &&
      (regs->flags & X86_EFLAGS_VM) == 0)
          setup_espfix;

The performance of setup_espfix itself is essentially irrelevant, but
the comparison happens on every IRET so its performance matters.  On
x86_64, there's no need for any registers except flags to implement
the comparison, so we fold the whole thing into native_iret.  On
x86_32, we don't do that because we need a free register to
implement the comparison efficiently.  We therefore do espfix setup
before restoring registers on x86_32.

This patch gets rid of the explicit paravirt_enabled check by
introducing X86_BUG_ESPFIX on 32-bit systems and using an ALTERNATIVE
to skip espfix on paravirt systems where iret != native_iret.  This is
also messy, but it's at least in line with other things we do.

This improves espfix performance by removing a branch, but no one
cares.  More importantly, it removes a paravirt_enabled user, which is
good because paravirt_enabled is ill-defined and is going away.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Reviewed-by: Borislav Petkov <bp@suse.de>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luis R. Rodriguez <mcgrof@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: boris.ostrovsky@oracle.com
Cc: david.vrabel@citrix.com
Cc: konrad.wilk@oracle.com
Cc: lguest@lists.ozlabs.org
Cc: xen-devel@lists.xensource.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 66350e6a6ca5a2dc7254c577764fc0be17564cb0..e13027247c90b7ad5d4b19919f7c118a4a19b398 100644 (file)
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -361,6 +361,8 @@ restore_all:
        TRACE_IRQS_IRET
 restore_all_notrace:
 #ifdef CONFIG_X86_ESPFIX32
+       ALTERNATIVE     "jmp restore_nocheck", "", X86_BUG_ESPFIX
+
        movl    PT_EFLAGS(%esp), %eax           # mix EFLAGS, SS and CS
        /*
         * Warning: PT_OLDSS(%esp) contains the wrong/random values if we
@@ -387,19 +389,6 @@ ENTRY(iret_exc     )
 
 #ifdef CONFIG_X86_ESPFIX32
 ldt_ss:
-#ifdef CONFIG_PARAVIRT
-       /*
-        * The kernel can't run on a non-flat stack if paravirt mode
-        * is active.  Rather than try to fixup the high bits of
-        * ESP, bypass this code entirely.  This may break DOSemu
-        * and/or Wine support in a paravirt VM, although the option
-        * is still available to implement the setting of the high
-        * 16-bits in the INTERRUPT_RETURN paravirt-op.
-        */
-       cmpl    $0, pv_info+PARAVIRT_enabled
-       jne     restore_nocheck
-#endif
-
 /*
  * Setup and switch to ESPFIX stack
  *

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 6663fae71b123d6b46566e8bcbdb087248b973cc..d11a3aaafd96bb609a7e9fa0cc9d49d57fb9dc4d 100644 (file)
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -286,4 +286,12 @@
 #define X86_BUG_CLFLUSH_MONITOR        X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
 #define X86_BUG_SYSRET_SS_ATTRS        X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
 
+#ifdef CONFIG_X86_32
+/*
+ * 64-bit kernels don't use X86_BUG_ESPFIX.  Make the define conditional
+ * to avoid confusion.
+ */
+#define X86_BUG_ESPFIX         X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
+#endif
+
 #endif /* _ASM_X86_CPUFEATURES_H */

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 079d83fc64888fdd408fa025f926ffd1da90f70f..d8337f34b5f40b304ad76a0682369d8a91f59ecc 100644 (file)
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -802,6 +802,31 @@ static void detect_nopl(struct cpuinfo_x86 *c)
        clear_cpu_cap(c, X86_FEATURE_NOPL);
 #else
        set_cpu_cap(c, X86_FEATURE_NOPL);
+#endif
+
+       /*
+        * ESPFIX is a strange bug.  All real CPUs have it.  Paravirt
+        * systems that run Linux at CPL > 0 may or may not have the
+        * issue, but, even if they have the issue, there's absolutely
+        * nothing we can do about it because we can't use the real IRET
+        * instruction.
+        *
+        * NB: For the time being, only 32-bit kernels support
+        * X86_BUG_ESPFIX as such.  64-bit kernels directly choose
+        * whether to apply espfix using paravirt hooks.  If any
+        * non-paravirt system ever shows up that does *not* have the
+        * ESPFIX issue, we can change this.
+        */
+#ifdef CONFIG_X86_32
+#ifdef CONFIG_PARAVIRT
+       do {
+               extern void native_iret(void);
+               if (pv_cpu_ops.iret == native_iret)
+                       set_cpu_bug(c, X86_BUG_ESPFIX);
+       } while (0);
+#else
+       set_cpu_bug(c, X86_BUG_ESPFIX);
+#endif
 #endif
 }