x86/paravirt: add register-saving thunks to reduce caller register pressure

Impact: Optimization

One of the problems with inserting a pile of C calls where previously
there were none is that the register pressure is greatly increased.
The C calling convention says that the caller must expect a certain
set of registers may be trashed by the callee, and that the callee can
use those registers without restriction.  This includes the function
argument registers, and several others.

This patch seeks to alleviate this pressure by introducing wrapper
thunks that will do the register saving/restoring, so that the
callsite doesn't need to worry about it, but the callee function can
be conventional compiler-generated code.  In many cases (particularly
performance-sensitive cases) the callee will be in assembler anyway,
and need not use the compiler's calling convention.

Standard calling convention is:
	 arguments	    return	scratch
x86-32	 eax edx ecx	    eax		?
x86-64	 rdi rsi rdx rcx    rax		r8 r9 r10 r11

The thunk preserves all argument and scratch registers.  The return
register is not preserved, and is available as a scratch register for
unwrapped callee code (and of course the return value).

Wrapped function pointers are themselves wrapped in a struct
paravirt_callee_save structure, in order to get some warning from the
compiler when functions with mismatched calling conventions are used.

The most common paravirt ops, both statically and dynamically, are
interrupt enable/disable/save/restore, so handle them first.  This is
particularly easy since their calls are handled specially anyway.

XXX Deal with VMI.  What's their calling convention?

Signed-off-by: H. Peter Anvin <hpa@zytor.com>

2 files changed, 12 insertions, 8 deletions

diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index dd25e2b1593..8adb6b5aa42 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -310,10 +310,10 @@ struct pv_time_ops pv_time_ops = {
 
 struct pv_irq_ops pv_irq_ops = {
 	.init_IRQ = native_init_IRQ,
-	.save_fl = native_save_fl,
-	.restore_fl = native_restore_fl,
-	.irq_disable = native_irq_disable,
-	.irq_enable = native_irq_enable,
+	.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
+	.restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl),
+	.irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable),
+	.irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable),
 	.safe_halt = native_safe_halt,
 	.halt = native_halt,
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index a688f3bfaec..c609205df59 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -37,6 +37,7 @@ static unsigned long vsmp_save_fl(void)
 		flags &= ~X86_EFLAGS_IF;
 	return flags;
 }
+PV_CALLEE_SAVE_REGS_THUNK(vsmp_save_fl);
 
 static void vsmp_restore_fl(unsigned long flags)
 {
@@ -46,6 +47,7 @@ static void vsmp_restore_fl(unsigned long flags)
 		flags |= X86_EFLAGS_AC;
 	native_restore_fl(flags);
 }
+PV_CALLEE_SAVE_REGS_THUNK(vsmp_restore_fl);
 
 static void vsmp_irq_disable(void)
 {
@@ -53,6 +55,7 @@ static void vsmp_irq_disable(void)
 
 	native_restore_fl((flags & ~X86_EFLAGS_IF) | X86_EFLAGS_AC);
 }
+PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_disable);
 
 static void vsmp_irq_enable(void)
 {
@@ -60,6 +63,7 @@ static void vsmp_irq_enable(void)
 
 	native_restore_fl((flags | X86_EFLAGS_IF) & (~X86_EFLAGS_AC));
 }
+PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_enable);
 
 static unsigned __init_or_module vsmp_patch(u8 type, u16 clobbers, void *ibuf,
 				  unsigned long addr, unsigned len)
@@ -90,10 +94,10 @@ static void __init set_vsmp_pv_ops(void)
 	       cap, ctl);
 	if (cap & ctl & (1 << 4)) {
 		/* Setup irq ops and turn on vSMP  IRQ fastpath handling */
-		pv_irq_ops.irq_disable = vsmp_irq_disable;
-		pv_irq_ops.irq_enable  = vsmp_irq_enable;
-		pv_irq_ops.save_fl  = vsmp_save_fl;
-		pv_irq_ops.restore_fl  = vsmp_restore_fl;
+		pv_irq_ops.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable);
+		pv_irq_ops.irq_enable  = PV_CALLEE_SAVE(vsmp_irq_enable);
+		pv_irq_ops.save_fl  = PV_CALLEE_SAVE(vsmp_save_fl);
+		pv_irq_ops.restore_fl  = PV_CALLEE_SAVE(vsmp_restore_fl);
 		pv_init_ops.patch = vsmp_patch;
 
 		ctl &= ~(1 << 4);