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)

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Suggested-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 3eb572ed3d7ad438d8dfd1627b5b4121314c9f67..901f186139b6e269e1811a34384e0b98ce276d44 100644 (file)
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -308,7 +308,8 @@ sysenter_past_esp:
 
        movl    %esp, %eax
        call    do_fast_syscall_32
-       testl   %eax, %eax
+       /* XEN PV guests always use IRET path */
+       ALTERNATIVE "testl %eax, %eax", "xor %eax, %eax", X86_FEATURE_XENPV
        jz      .Lsyscall_32_done
 
 /* Opportunistic SYSEXIT */

diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index c3201830a85ee8dcddabb0cab864545d99d47fd3..98893d97541f042a33f26e79436babaa85a281de 100644 (file)
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -121,7 +121,8 @@ sysenter_flags_fixed:
 
        movq    %rsp, %rdi
        call    do_fast_syscall_32
-       testl   %eax, %eax
+       /* XEN PV guests always use IRET path */
+       ALTERNATIVE "testl %eax, %eax", "xor %eax, %eax", X86_FEATURE_XENPV
        jz      .Lsyscall_32_done
        jmp     sysret32_from_system_call
 
@@ -200,7 +201,8 @@ ENTRY(entry_SYSCALL_compat)
 
        movq    %rsp, %rdi
        call    do_fast_syscall_32
-       testl   %eax, %eax
+       /* XEN PV guests always use IRET path */
+       ALTERNATIVE "testl %eax, %eax", "xor %eax, %eax", X86_FEATURE_XENPV
        jz      .Lsyscall_32_done
 
        /* Opportunistic SYSRET */

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e4f8010f22e04d2f261bb73bc7745f68f36a392f..0e4fe5bd929162660a554c82b70563bae9e06671 100644 (file)
--- 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 5774800ff583ca33916e365e408b057d982a8384..d315151411e56a7ea36bf01807d119df52316bc3 100644 (file)
--- 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 = {