x86/pv: Drop int80_bounce from struct pv_vcpu

The int80_bounce field of struct pv_vcpu is a bit of an odd special case,
because it is a simple derivation of trap_ctxt[0x80], which is also stored.

It is also the only use of {compat_,}create_bounce_frame() which isn't
referencing the plain trap_bounce field of struct pv_vcpu.  (And altering this
property the purpose of this patch.)

Remove the int80_bounce field entirely, along with init_int80_direct_trap(),
which in turn requires that the int80_direct_trap() path gain logic previously
contained in init_int80_direct_trap().

This does admittedly make the int80 fastpath slightly longer, but these few
instructions are in the noise compared to the architectural context switch
overhead, and it now matches the syscall/sysenter paths (which have far less
architectural overhead already).

No behavioural change from the guests point of view.

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>

xen/arch/x86/domain.c

@@ -892,8 +892,6 @@ int arch_set_info_guest(
         goto out;
     }
 
-    init_int80_direct_trap(v);
-
     /* IOPL privileges are virtualised. */
     v->arch.pv_vcpu.iopl = v->arch.user_regs.eflags & X86_EFLAGS_IOPL;
     v->arch.user_regs.eflags &= ~X86_EFLAGS_IOPL;

xen/arch/x86/pv/callback.c

@@ -371,7 +371,6 @@ long do_set_trap_table(XEN_GUEST_HANDLE_PARAM(const_trap_info_t) traps)
     if ( guest_handle_is_null(traps) )
     {
         memset(dst, 0, NR_VECTORS * sizeof(*dst));
-        init_int80_direct_trap(curr);
         return 0;
     }
 
@@ -393,9 +392,6 @@ long do_set_trap_table(XEN_GUEST_HANDLE_PARAM(const_trap_info_t) traps)
 
         memcpy(&dst[cur.vector], &cur, sizeof(cur));
 
-        if ( cur.vector == 0x80 )
-            init_int80_direct_trap(curr);
-
         guest_handle_add_offset(traps, 1);
 
         if ( hypercall_preempt_check() )
@@ -420,7 +416,6 @@ int compat_set_trap_table(XEN_GUEST_HANDLE(trap_info_compat_t) traps)
     if ( guest_handle_is_null(traps) )
     {
         memset(dst, 0, NR_VECTORS * sizeof(*dst));
-        init_int80_direct_trap(curr);
         return 0;
     }
 
@@ -439,9 +434,6 @@ int compat_set_trap_table(XEN_GUEST_HANDLE(trap_info_compat_t) traps)
 
         XLAT_trap_info(dst + cur.vector, &cur);
 
-        if ( cur.vector == 0x80 )
-            init_int80_direct_trap(curr);
-
         guest_handle_add_offset(traps, 1);
 
         if ( hypercall_preempt_check() )

xen/arch/x86/pv/traps.c

@@ -142,20 +142,6 @@ bool set_guest_nmi_trapbounce(void)
     return !null_trap_bounce(curr, tb);
 }
 
-void init_int80_direct_trap(struct vcpu *v)
-{
-    struct trap_info *ti = &v->arch.pv_vcpu.trap_ctxt[0x80];
-    struct trap_bounce *tb = &v->arch.pv_vcpu.int80_bounce;
-
-    tb->cs  = ti->cs;
-    tb->eip = ti->address;
-
-    if ( null_trap_bounce(v, tb) )
-        tb->flags = 0;
-    else
-        tb->flags = TBF_EXCEPTION | (TI_GET_IF(ti) ? TBF_INTERRUPT : 0);
-}
-
 struct softirq_trap {
     struct domain *domain;   /* domain to inject trap */
     struct vcpu *vcpu;       /* vcpu to inject trap */

xen/arch/x86/x86_64/asm-offsets.c

@@ -61,7 +61,6 @@ void __dummy__(void)
     OFFSET(VCPU_domain, struct vcpu, domain);
     OFFSET(VCPU_vcpu_info, struct vcpu, vcpu_info);
     OFFSET(VCPU_trap_bounce, struct vcpu, arch.pv_vcpu.trap_bounce);
-    OFFSET(VCPU_int80_bounce, struct vcpu, arch.pv_vcpu.int80_bounce);
     OFFSET(VCPU_thread_flags, struct vcpu, arch.flags);
     OFFSET(VCPU_event_addr, struct vcpu, arch.pv_vcpu.event_callback_eip);
     OFFSET(VCPU_event_sel, struct vcpu, arch.pv_vcpu.event_callback_cs);

xen/arch/x86/x86_64/entry.S

@@ -336,12 +336,36 @@ UNLIKELY_END(msi_check)
 
         movq  STACK_CPUINFO_FIELD(current_vcpu)(%rbx), %rbx
 
-        /* Check that the callback is non-null. */
-        leaq  VCPU_int80_bounce(%rbx),%rdx
-        cmpb  $0,TRAPBOUNCE_flags(%rdx)
+        mov   VCPU_trap_ctxt(%rbx), %rsi
+        mov   VCPU_domain(%rbx), %rax
+
+        /*
+         * if ( null_trap_bounce(v, &v->arch.pv_vcpu.trap_ctxt[0x80]) )
+         *    goto int80_slow_path;
+         */
+        mov    0x80 * TRAPINFO_sizeof + TRAPINFO_eip(%rsi), %rdi
+        movzwl 0x80 * TRAPINFO_sizeof + TRAPINFO_cs (%rsi), %ecx
+
+        mov   %ecx, %edx
+        and   $~3, %edx
+
+        cmpb  $0, DOMAIN_is_32bit_pv(%rax)
+        cmove %rdi, %rdx
+
+        test  %rdx, %rdx
         jz    int80_slow_path
 
-        movq  VCPU_domain(%rbx),%rax
+        /* Construct trap_bounce from trap_ctxt[0x80]. */
+        lea   VCPU_trap_bounce(%rbx), %rdx
+        movw  %cx, TRAPBOUNCE_cs(%rdx)
+        movq  %rdi, TRAPBOUNCE_eip(%rdx)
+
+        /* TB_flags = TBF_EXCEPTION | (TI_GET_IF(ti) ? TBF_INTERRUPT : 0); */
+        testb $4, 0x80 * TRAPINFO_sizeof + TRAPINFO_flags(%rsi)
+        setnz %cl
+        lea   TBF_EXCEPTION(, %rcx, TBF_INTERRUPT), %ecx
+        mov   %cl, TRAPBOUNCE_flags(%rdx)
+
         cmpb  $0, DOMAIN_is_32bit_pv(%rax)
         jne   compat_int80_direct_trap
 

xen/include/asm-x86/domain.h

@@ -482,7 +482,6 @@ struct pv_vcpu
 
     /* Bounce information for propagating an exception to guest OS. */
     struct trap_bounce trap_bounce;
-    struct trap_bounce int80_bounce;
 
     /* I/O-port access bitmap. */
     XEN_GUEST_HANDLE(uint8) iobmp; /* Guest kernel vaddr of the bitmap. */

xen/include/asm-x86/processor.h

@@ -439,8 +439,6 @@ extern idt_entry_t *idt_tables[];
 DECLARE_PER_CPU(struct tss_struct, init_tss);
 DECLARE_PER_CPU(root_pgentry_t *, root_pgt);
 
-extern void init_int80_direct_trap(struct vcpu *v);
-
 extern void write_ptbase(struct vcpu *v);
 
 /* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */