[PATCH] paravirt: Patch inline replacements for paravirt intercepts

It turns out that the most called ops, by several orders of magnitude,
are the interrupt manipulation ops.  These are obvious candidates for
patching, so mark them up and create infrastructure for it.

The method used is that the ops structure has a patch function, which
is called for each place which needs to be patched: this returns a
number of instructions (the rest are NOP-padded).

Usually we can spare a register (%eax) for the binary patched code to
use, but in a couple of critical places in entry.S we can't: we make
the clobbers explicit at the call site, and manually clobber the
allowed registers in debug mode as an extra check.

And:

Don't abuse CONFIG_DEBUG_KERNEL, add CONFIG_DEBUG_PARAVIRT.

And:

AK:  Fix warnings in x86-64 alternative.c build

And:

AK: Fix compilation with defconfig

And:

^From: Andrew Morton <akpm@osdl.org>

Some binutlises still like to emit references to __stop_parainstructions and
__start_parainstructions.

And:

AK: Fix warnings about unused variables when PARAVIRT is disabled.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>

1 files changed, 26 insertions, 13 deletions

diff --git a/arch/i386/kernel/entry.S b/arch/i386/kernel/entry.S
index d274612e05cd..de34b7fed3c1 100644
--- a/arch/i386/kernel/entry.S
+++ b/arch/i386/kernel/entry.S
@@ -53,6 +53,19 @@
 #include <asm/dwarf2.h>
 #include "irq_vectors.h"
 
+/*
+ * We use macros for low-level operations which need to be overridden
+ * for paravirtualization.  The following will never clobber any registers:
+ *   INTERRUPT_RETURN (aka. "iret")
+ *   GET_CR0_INTO_EAX (aka. "movl %cr0, %eax")
+ *   ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit").
+ *
+ * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must
+ * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY).
+ * Allowing a register to be clobbered can shrink the paravirt replacement
+ * enough to patch inline, increasing performance.
+ */
+
 #define nr_syscalls ((syscall_table_size)/4)
 
 CF_MASK         = 0x00000001
@@ -63,9 +76,9 @@ NT_MASK		= 0x00004000
 VM_MASK         = 0x00020000
 
 #ifdef CONFIG_PREEMPT
-#define preempt_stop            DISABLE_INTERRUPTS; TRACE_IRQS_OFF
+#define preempt_stop(clobbers)  DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
 #else
-#define preempt_stop
+#define preempt_stop(clobbers)
 #define resume_kernel           restore_nocheck
 #endif
 
@@ -226,7 +239,7 @@ ENTRY(ret_from_fork)
         ALIGN
         RING0_PTREGS_FRAME
 ret_from_exception:
-        preempt_stop
+        preempt_stop(CLBR_ANY)
 ret_from_intr:
         GET_THREAD_INFO(%ebp)
 check_userspace:
@@ -237,7 +250,7 @@ check_userspace:
         jb resume_kernel                # not returning to v8086 or userspace
 
 ENTRY(resume_userspace)
-        DISABLE_INTERRUPTS              # make sure we don't miss an interrupt
+        DISABLE_INTERRUPTS(CLBR_ANY)    # make sure we don't miss an interrupt
                                         # setting need_resched or sigpending
                                         # between sampling and the iret
         movl TI_flags(%ebp), %ecx
@@ -248,7 +261,7 @@ ENTRY(resume_userspace)
 
 #ifdef CONFIG_PREEMPT
 ENTRY(resume_kernel)
-        DISABLE_INTERRUPTS
+        DISABLE_INTERRUPTS(CLBR_ANY)
         cmpl $0,TI_preempt_count(%ebp)  # non-zero preempt_count ?
         jnz restore_nocheck
 need_resched:
@@ -277,7 +290,7 @@ sysenter_past_esp:
          * No need to follow this irqs on/off section: the syscall
          * disabled irqs and here we enable it straight after entry:
          */
-        ENABLE_INTERRUPTS
+        ENABLE_INTERRUPTS(CLBR_NONE)
         pushl $(__USER_DS)
         CFI_ADJUST_CFA_OFFSET 4
         /*CFI_REL_OFFSET ss, 0*/
@@ -322,7 +335,7 @@ sysenter_past_esp:
         jae syscall_badsys
         call *sys_call_table(,%eax,4)
         movl %eax,PT_EAX(%esp)
-        DISABLE_INTERRUPTS
+        DISABLE_INTERRUPTS(CLBR_ECX|CLBR_EDX)
         TRACE_IRQS_OFF
         movl TI_flags(%ebp), %ecx
         testw $_TIF_ALLWORK_MASK, %cx
@@ -364,7 +377,7 @@ syscall_call:
         call *sys_call_table(,%eax,4)
         movl %eax,PT_EAX(%esp)          # store the return value
 syscall_exit:
-        DISABLE_INTERRUPTS              # make sure we don't miss an interrupt
+        DISABLE_INTERRUPTS(CLBR_ANY)    # make sure we don't miss an interrupt
                                         # setting need_resched or sigpending
                                         # between sampling and the iret
         TRACE_IRQS_OFF
@@ -393,7 +406,7 @@ restore_nocheck_notrace:
 .section .fixup,"ax"
 iret_exc:
         TRACE_IRQS_ON
-        ENABLE_INTERRUPTS
+        ENABLE_INTERRUPTS(CLBR_NONE)
         pushl $0                        # no error code
         pushl $do_iret_error
         jmp error_code
@@ -436,7 +449,7 @@ ldt_ss:
         CFI_ADJUST_CFA_OFFSET 4
         pushl %eax
         CFI_ADJUST_CFA_OFFSET 4
-        DISABLE_INTERRUPTS
+        DISABLE_INTERRUPTS(CLBR_EAX)
         TRACE_IRQS_OFF
         lss (%esp), %esp
         CFI_ADJUST_CFA_OFFSET -8
@@ -451,7 +464,7 @@ work_pending:
         jz work_notifysig
 work_resched:
         call schedule
-        DISABLE_INTERRUPTS              # make sure we don't miss an interrupt
+        DISABLE_INTERRUPTS(CLBR_ANY)    # make sure we don't miss an interrupt
                                         # setting need_resched or sigpending
                                         # between sampling and the iret
         TRACE_IRQS_OFF
@@ -509,7 +522,7 @@ syscall_exit_work:
         testb $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP), %cl
         jz work_pending
         TRACE_IRQS_ON
-        ENABLE_INTERRUPTS               # could let do_syscall_trace() call
+        ENABLE_INTERRUPTS(CLBR_ANY)     # could let do_syscall_trace() call
                                         # schedule() instead
         movl %esp, %eax
         movl $1, %edx
@@ -693,7 +706,7 @@ ENTRY(device_not_available)
         GET_CR0_INTO_EAX
         testl $0x4, %eax                # EM (math emulation bit)
         jne device_not_available_emulate
-        preempt_stop
+        preempt_stop(CLBR_ANY)
         call math_state_restore
         jmp ret_from_exception
 device_not_available_emulate: