x86/xen: Avoid fast syscall path for Xen PV guests

After 32-bit syscall rewrite, and specifically after commit:

  5f310f739b4c ("x86/entry/32: Re-implement SYSENTER using the new C path")

... the stack frame that is passed to xen_sysexit is no longer a
"standard" one (i.e. it's not pt_regs).

Since we end up calling xen_iret from xen_sysexit we don't need
to fix up the stack and instead follow entry_SYSENTER_32's IRET
path directly to xen_iret.

We can do the same thing for compat mode even though stack does
not need to be fixed. This will allow us to drop usergs_sysret32
paravirt op (in the subsequent patch)

Suggested-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Borislav Petkov <bp@suse.de>
Acked-by: Andy Lutomirski <luto@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
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: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: david.vrabel@citrix.com
Cc: konrad.wilk@oracle.com
Cc: virtualization@lists.linux-foundation.org
Cc: xen-devel@lists.xenproject.org
Link: http://lkml.kernel.org/r/1447970147-1733-2-git-send-email-boris.ostrovsky@oracle.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

4 files changed, 13 insertions, 7 deletions

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 3eb572ed3d7a..0870825a9568 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -308,8 +308,9 @@ sysenter_past_esp:
 
 	movl	%esp, %eax
 	call	do_fast_syscall_32
-	testl	%eax, %eax
-	jz	.Lsyscall_32_done
+	/* XEN PV guests always use IRET path */
+	ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
+		    "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
 
 /* Opportunistic SYSEXIT */
 	TRACE_IRQS_ON			/* User mode traces as IRQs on. */
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index c3201830a85e..402e34a21559 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -121,8 +121,9 @@ sysenter_flags_fixed:
 
 	movq	%rsp, %rdi
 	call	do_fast_syscall_32
-	testl	%eax, %eax
-	jz	.Lsyscall_32_done
+	/* XEN PV guests always use IRET path */
+	ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
+		    "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
 	jmp	sysret32_from_system_call
 
 sysenter_fix_flags:
@@ -200,8 +201,9 @@ ENTRY(entry_SYSCALL_compat)
 
 	movq	%rsp, %rdi
 	call	do_fast_syscall_32
-	testl	%eax, %eax
-	jz	.Lsyscall_32_done
+	/* XEN PV guests always use IRET path */
+	ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
+		    "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
 
 	/* Opportunistic SYSRET */
 sysret32_from_system_call:
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e4f8010f22e0..f7ba9fbf12ee 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -216,6 +216,7 @@
 #define X86_FEATURE_PAUSEFILTER ( 8*32+13) /* AMD filtered pause intercept */
 #define X86_FEATURE_PFTHRESHOLD ( 8*32+14) /* AMD pause filter threshold */
 #define X86_FEATURE_VMMCALL     ( 8*32+15) /* Prefer vmmcall to vmcall */
+#define X86_FEATURE_XENPV       ( 8*32+16) /* "" Xen paravirtual guest */
 
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 5774800ff583..d315151411e5 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1886,8 +1886,10 @@ EXPORT_SYMBOL_GPL(xen_hvm_need_lapic);
 
 static void xen_set_cpu_features(struct cpuinfo_x86 *c)
 {
-	if (xen_pv_domain())
+	if (xen_pv_domain()) {
 		clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
+		set_cpu_cap(c, X86_FEATURE_XENPV);
+	}
 }
 
 const struct hypervisor_x86 x86_hyper_xen = {