summaryrefslogtreecommitdiffstats
path: root/arch/x86/include/asm/irqflags.h
diff options
context:
space:
mode:
authorAndy Lutomirski <luto@amacapital.net>2014-07-23 08:34:11 -0700
committerH. Peter Anvin <hpa@linux.intel.com>2014-07-28 15:25:40 -0700
commit7209a75d2009dbf7745e2fd354abf25c3deb3ca3 (patch)
treee0c3050ed85e8d10aff456f7fa43eec73cbad4ca /arch/x86/include/asm/irqflags.h
parent64aa90f26c06e1cb2aacfb98a7d0eccfbd6c1a91 (diff)
downloadlinux-0-day-7209a75d2009dbf7745e2fd354abf25c3deb3ca3.tar.gz
linux-0-day-7209a75d2009dbf7745e2fd354abf25c3deb3ca3.tar.xz
x86_64/entry/xen: Do not invoke espfix64 on Xen
This moves the espfix64 logic into native_iret. To make this work, it gets rid of the native patch for INTERRUPT_RETURN: INTERRUPT_RETURN on native kernels is now 'jmp native_iret'. This changes the 16-bit SS behavior on Xen from OOPSing to leaking some bits of the Xen hypervisor's RSP (I think). [ hpa: this is a nonzero cost on native, but probably not enough to measure. Xen needs to fix this in their own code, probably doing something equivalent to espfix64. ] Signed-off-by: Andy Lutomirski <luto@amacapital.net> Link: http://lkml.kernel.org/r/7b8f1d8ef6597cb16ae004a43c56980a7de3cf94.1406129132.git.luto@amacapital.net Signed-off-by: H. Peter Anvin <hpa@linux.intel.com> Cc: <stable@vger.kernel.org>
Diffstat (limited to 'arch/x86/include/asm/irqflags.h')
-rw-r--r--arch/x86/include/asm/irqflags.h2
1 files changed, 1 insertions, 1 deletions
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index bba3cf88e6249..0a8b519226b8f 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -129,7 +129,7 @@ static inline notrace unsigned long arch_local_irq_save(void)
#define PARAVIRT_ADJUST_EXCEPTION_FRAME /* */
-#define INTERRUPT_RETURN iretq
+#define INTERRUPT_RETURN jmp native_iret
#define USERGS_SYSRET64 \
swapgs; \
sysretq;