[PATCH] paravirt: header and stubs for paravirtualisation

Create a paravirt.h header for all the critical operations which need to be
replaced with hypervisor calls, and include that instead of defining native
operations, when CONFIG_PARAVIRT.

This patch does the dumbest possible replacement of paravirtualized
instructions: calls through a "paravirt_ops" structure.  Currently these are
function implementations of native hardware: hypervisors will override the ops
structure with their own variants.

All the pv-ops functions are declared "fastcall" so that a specific
register-based ABI is used, to make inlining assember easier.

And:

+From: Andy Whitcroft <apw@shadowen.org>

The paravirt ops introduce a 'weak' attribute onto memory_setup().
Code ordering leads to the following warnings on x86:

    arch/i386/kernel/setup.c:651: warning: weak declaration of
                `memory_setup' after first use results in unspecified behavior

Move memory_setup() to avoid this.

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

arch/i386/Kconfig

@@ -182,6 +182,17 @@ config X86_ES7000
 
 endchoice
 
+config PARAVIRT
+	bool "Paravirtualization support (EXPERIMENTAL)"
+	depends on EXPERIMENTAL
+	help
+	  Paravirtualization is a way of running multiple instances of
+	  Linux on the same machine, under a hypervisor.  This option
+	  changes the kernel so it can modify itself when it is run
+	  under a hypervisor, improving performance significantly.
+	  However, when run without a hypervisor the kernel is
+	  theoretically slower.  If in doubt, say N.
+
 config ACPI_SRAT
 	bool
 	default y

arch/i386/boot/compressed/misc.c

@@ -9,6 +9,7 @@
  * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
  */
 
+#undef CONFIG_PARAVIRT
 #include <linux/linkage.h>
 #include <linux/vmalloc.h>
 #include <linux/screen_info.h>

arch/i386/kernel/Makefile

@@ -39,6 +39,7 @@ obj-$(CONFIG_VM86)		+= vm86.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 obj-$(CONFIG_HPET_TIMER) 	+= hpet.o
 obj-$(CONFIG_K8_NB)		+= k8.o
+obj-$(CONFIG_PARAVIRT)		+= paravirt.o
 
 EXTRA_AFLAGS   := -traditional
 

arch/i386/kernel/asm-offsets.c

@@ -101,4 +101,14 @@ void foo(void)
 	BLANK();
  	OFFSET(PDA_cpu, i386_pda, cpu_number);
 	OFFSET(PDA_pcurrent, i386_pda, pcurrent);
+
+#ifdef CONFIG_PARAVIRT
+	BLANK();
+	OFFSET(PARAVIRT_enabled, paravirt_ops, paravirt_enabled);
+	OFFSET(PARAVIRT_irq_disable, paravirt_ops, irq_disable);
+	OFFSET(PARAVIRT_irq_enable, paravirt_ops, irq_enable);
+	OFFSET(PARAVIRT_irq_enable_sysexit, paravirt_ops, irq_enable_sysexit);
+	OFFSET(PARAVIRT_iret, paravirt_ops, iret);
+	OFFSET(PARAVIRT_read_cr0, paravirt_ops, read_cr0);
+#endif
 }

arch/i386/kernel/entry.S

@@ -62,13 +62,6 @@ DF_MASK		= 0x00000400
 NT_MASK		= 0x00004000
 VM_MASK		= 0x00020000
 
-/* These are replaces for paravirtualization */
-#define DISABLE_INTERRUPTS		cli
-#define ENABLE_INTERRUPTS		sti
-#define ENABLE_INTERRUPTS_SYSEXIT	sti; sysexit
-#define INTERRUPT_RETURN		iret
-#define GET_CR0_INTO_EAX		movl %cr0, %eax
-
 #ifdef CONFIG_PREEMPT
 #define preempt_stop		DISABLE_INTERRUPTS; TRACE_IRQS_OFF
 #else
@@ -416,6 +409,20 @@ ldt_ss:
 	jnz restore_nocheck
 	testl $0x00400000, %eax		# returning to 32bit stack?
 	jnz restore_nocheck		# allright, normal return
+
+#ifdef CONFIG_PARAVIRT
+	/*
+	 * The kernel can't run on a non-flat stack if paravirt mode
+	 * is active.  Rather than try to fixup the high bits of
+	 * ESP, bypass this code entirely.  This may break DOSemu
+	 * and/or Wine support in a paravirt VM, although the option
+	 * is still available to implement the setting of the high
+	 * 16-bits in the INTERRUPT_RETURN paravirt-op.
+	 */
+	cmpl $0, paravirt_ops+PARAVIRT_enabled
+	jne restore_nocheck
+#endif
+
 	/* If returning to userspace with 16bit stack,
 	 * try to fix the higher word of ESP, as the CPU
 	 * won't restore it.
@@ -833,6 +840,19 @@ nmi_espfix_stack:
 .previous
 KPROBE_END(nmi)
 
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_iret)
+1:	iret
+.section __ex_table,"a"
+	.align 4
+	.long 1b,iret_exc
+.previous
+
+ENTRY(native_irq_enable_sysexit)
+	sti
+	sysexit
+#endif
+
 KPROBE_ENTRY(int3)
 	RING0_INT_FRAME
 	pushl $-1			# mark this as an int

arch/i386/kernel/i8259.c

@@ -381,7 +381,10 @@ void __init init_ISA_irqs (void)
 	}
 }
 
-void __init init_IRQ(void)
+/* Overridden in paravirt.c */
+void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
+
+void __init native_init_IRQ(void)
 {
 	int i;