Merge branch 'xen-upstream' of ssh://master.kernel.org/pub/scm/linux/kernel/git/jeremy/xen

* 'xen-upstream' of ssh://master.kernel.org/pub/scm/linux/kernel/git/jeremy/xen: (44 commits)
  xen: disable all non-virtual drivers
  xen: use iret directly when possible
  xen: suppress abs symbol warnings for unused reloc pointers
  xen: Attempt to patch inline versions of common operations
  xen: Place vcpu_info structure into per-cpu memory
  xen: handle external requests for shutdown, reboot and sysrq
  xen: machine operations
  xen: add virtual network device driver
  xen: add virtual block device driver.
  xen: add the Xenbus sysfs and virtual device hotplug driver
  xen: Add grant table support
  xen: use the hvc console infrastructure for Xen console
  xen: hack to prevent bad segment register reload
  xen: lazy-mmu operations
  xen: Add support for preemption
  xen: SMP guest support
  xen: Implement sched_clock
  xen: Account for stolen time
  xen: ignore RW mapping of RO pages in pagetable_init
  xen: Complete pagetable pinning
  ...

Author: Linus Torvalds

arch/i386/Kconfig

@@ -222,6 +222,8 @@ config PARAVIRT
 	  However, when run without a hypervisor the kernel is
 	  theoretically slower.  If in doubt, say N.
 
+source "arch/i386/xen/Kconfig"
+
 config VMI
 	bool "VMI Paravirt-ops support"
 	depends on PARAVIRT

arch/i386/Makefile

@@ -93,6 +93,9 @@ mflags-$(CONFIG_X86_ES7000)	:= -Iinclude/asm-i386/mach-es7000
 mcore-$(CONFIG_X86_ES7000)	:= mach-default
 core-$(CONFIG_X86_ES7000)	:= arch/i386/mach-es7000/
 
+# Xen paravirtualization support
+core-$(CONFIG_XEN)		+= arch/i386/xen/
+
 # default subarch .h files
 mflags-y += -Iinclude/asm-i386/mach-default
 

arch/i386/boot/compressed/relocs.c

@@ -31,6 +31,8 @@ static const char* safe_abs_relocs[] = {
 		"__kernel_rt_sigreturn",
 		"__kernel_sigreturn",
 		"SYSENTER_RETURN",
+		"xen_irq_disable_direct_reloc",
+		"xen_save_fl_direct_reloc",
 };
 
 static int is_safe_abs_reloc(const char* sym_name)

arch/i386/kernel/asm-offsets.c

@@ -17,6 +17,8 @@
 #include <asm/thread_info.h>
 #include <asm/elf.h>
 
+#include <xen/interface/xen.h>
+
 #define DEFINE(sym, val) \
         asm volatile("\n->" #sym " %0 " #val : : "i" (val))
 
@@ -59,6 +61,7 @@ void foo(void)
 	OFFSET(TI_addr_limit, thread_info, addr_limit);
 	OFFSET(TI_restart_block, thread_info, restart_block);
 	OFFSET(TI_sysenter_return, thread_info, sysenter_return);
+	OFFSET(TI_cpu, thread_info, cpu);
 	BLANK();
 
 	OFFSET(GDS_size, Xgt_desc_struct, size);
@@ -115,4 +118,10 @@ void foo(void)
 	OFFSET(PARAVIRT_iret, paravirt_ops, iret);
 	OFFSET(PARAVIRT_read_cr0, paravirt_ops, read_cr0);
 #endif
+
+#ifdef CONFIG_XEN
+	BLANK();
+	OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
+	OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending);
+#endif
 }

arch/i386/kernel/entry.S

@@ -1023,6 +1023,91 @@ ENTRY(kernel_thread_helper)
 	CFI_ENDPROC
 ENDPROC(kernel_thread_helper)
 
+#ifdef CONFIG_XEN
+ENTRY(xen_hypervisor_callback)
+	CFI_STARTPROC
+	pushl $0
+	CFI_ADJUST_CFA_OFFSET 4
+	SAVE_ALL
+	TRACE_IRQS_OFF
+
+	/* Check to see if we got the event in the critical
+	   region in xen_iret_direct, after we've reenabled
+	   events and checked for pending events.  This simulates
+	   iret instruction's behaviour where it delivers a
+	   pending interrupt when enabling interrupts. */
+	movl PT_EIP(%esp),%eax
+	cmpl $xen_iret_start_crit,%eax
+	jb   1f
+	cmpl $xen_iret_end_crit,%eax
+	jae  1f
+
+	call xen_iret_crit_fixup
+
+1:	mov %esp, %eax
+	call xen_evtchn_do_upcall
+	jmp  ret_from_intr
+	CFI_ENDPROC
+ENDPROC(xen_hypervisor_callback)
+
+# Hypervisor uses this for application faults while it executes.
+# We get here for two reasons:
+#  1. Fault while reloading DS, ES, FS or GS
+#  2. Fault while executing IRET
+# Category 1 we fix up by reattempting the load, and zeroing the segment
+# register if the load fails.
+# Category 2 we fix up by jumping to do_iret_error. We cannot use the
+# normal Linux return path in this case because if we use the IRET hypercall
+# to pop the stack frame we end up in an infinite loop of failsafe callbacks.
+# We distinguish between categories by maintaining a status value in EAX.
+ENTRY(xen_failsafe_callback)
+	CFI_STARTPROC
+	pushl %eax
+	CFI_ADJUST_CFA_OFFSET 4
+	movl $1,%eax
+1:	mov 4(%esp),%ds
+2:	mov 8(%esp),%es
+3:	mov 12(%esp),%fs
+4:	mov 16(%esp),%gs
+	testl %eax,%eax
+	popl %eax
+	CFI_ADJUST_CFA_OFFSET -4
+	lea 16(%esp),%esp
+	CFI_ADJUST_CFA_OFFSET -16
+	jz 5f
+	addl $16,%esp
+	jmp iret_exc		# EAX != 0 => Category 2 (Bad IRET)
+5:	pushl $0		# EAX == 0 => Category 1 (Bad segment)
+	CFI_ADJUST_CFA_OFFSET 4
+	SAVE_ALL
+	jmp ret_from_exception
+	CFI_ENDPROC
+
+.section .fixup,"ax"
+6:	xorl %eax,%eax
+	movl %eax,4(%esp)
+	jmp 1b
+7:	xorl %eax,%eax
+	movl %eax,8(%esp)
+	jmp 2b
+8:	xorl %eax,%eax
+	movl %eax,12(%esp)
+	jmp 3b
+9:	xorl %eax,%eax
+	movl %eax,16(%esp)
+	jmp 4b
+.previous
+.section __ex_table,"a"
+	.align 4
+	.long 1b,6b
+	.long 2b,7b
+	.long 3b,8b
+	.long 4b,9b
+.previous
+ENDPROC(xen_failsafe_callback)
+
+#endif	/* CONFIG_XEN */
+
 .section .rodata,"a"
 #include "syscall_table.S"
 

arch/i386/kernel/head.S

@@ -510,7 +510,8 @@ ENTRY(_stext)
 /*
  * BSS section
  */
-.section ".bss.page_aligned","w"
+.section ".bss.page_aligned","wa"
+	.align PAGE_SIZE_asm
 ENTRY(swapper_pg_dir)
 	.fill 1024,4,0
 ENTRY(swapper_pg_pmd)
@@ -538,6 +539,8 @@ fault_msg:
 	.ascii "Int %d: CR2 %p  err %p  EIP %p  CS %p  flags %p\n"
 	.asciz "Stack: %p %p %p %p %p %p %p %p\n"
 
+#include "../xen/xen-head.S"
+
 /*
  * The IDT and GDT 'descriptors' are a strange 48-bit object
  * only used by the lidt and lgdt instructions. They are not

arch/i386/kernel/paravirt.c

@@ -228,6 +228,41 @@ static int __init print_banner(void)
 }
 core_initcall(print_banner);
 
+static struct resource reserve_ioports = {
+	.start = 0,
+	.end = IO_SPACE_LIMIT,
+	.name = "paravirt-ioport",
+	.flags = IORESOURCE_IO | IORESOURCE_BUSY,
+};
+
+static struct resource reserve_iomem = {
+	.start = 0,
+	.end = -1,
+	.name = "paravirt-iomem",
+	.flags = IORESOURCE_MEM | IORESOURCE_BUSY,
+};
+
+/*
+ * Reserve the whole legacy IO space to prevent any legacy drivers
+ * from wasting time probing for their hardware.  This is a fairly
+ * brute-force approach to disabling all non-virtual drivers.
+ *
+ * Note that this must be called very early to have any effect.
+ */
+int paravirt_disable_iospace(void)
+{
+	int ret;
+
+	ret = request_resource(&ioport_resource, &reserve_ioports);
+	if (ret == 0) {
+		ret = request_resource(&iomem_resource, &reserve_iomem);
+		if (ret)
+			release_resource(&reserve_ioports);
+	}
+
+	return ret;
+}
+
 struct paravirt_ops paravirt_ops = {
 	.name = "bare hardware",
 	.paravirt_enabled = 0,
@@ -267,7 +302,7 @@ struct paravirt_ops paravirt_ops = {
 	.write_msr = native_write_msr_safe,
 	.read_tsc = native_read_tsc,
 	.read_pmc = native_read_pmc,
-	.get_scheduled_cycles = native_read_tsc,
+	.sched_clock = native_sched_clock,
 	.get_cpu_khz = native_calculate_cpu_khz,
 	.load_tr_desc = native_load_tr_desc,
 	.set_ldt = native_set_ldt,

arch/i386/kernel/setup.c

@@ -601,6 +601,8 @@ void __init setup_arch(char **cmdline_p)
 	 * NOTE: at this point the bootmem allocator is fully available.
 	 */
 
+	paravirt_post_allocator_init();
+
 	dmi_scan_machine();
 
 #ifdef CONFIG_X86_GENERICARCH

arch/i386/kernel/smp.c

@@ -22,6 +22,7 @@
 
 #include <asm/mtrr.h>
 #include <asm/tlbflush.h>
+#include <asm/mmu_context.h>
 #include <mach_apic.h>
 
 /*
@@ -249,13 +250,13 @@ static unsigned long flush_va;
 static DEFINE_SPINLOCK(tlbstate_lock);
 
 /*
- * We cannot call mmdrop() because we are in interrupt context, 
+ * We cannot call mmdrop() because we are in interrupt context,
  * instead update mm->cpu_vm_mask.
  *
  * We need to reload %cr3 since the page tables may be going
  * away from under us..
  */
-static inline void leave_mm (unsigned long cpu)
+void leave_mm(unsigned long cpu)
 {
 	if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK)
 		BUG();

arch/i386/kernel/smpboot.c

@@ -148,7 +148,7 @@ void __init smp_alloc_memory(void)
  * a given CPU
  */
 
-static void __cpuinit smp_store_cpu_info(int id)
+void __cpuinit smp_store_cpu_info(int id)
 {
 	struct cpuinfo_x86 *c = cpu_data + id;
 
@@ -308,8 +308,7 @@ cpumask_t cpu_coregroup_map(int cpu)
 /* representing cpus for which sibling maps can be computed */
 static cpumask_t cpu_sibling_setup_map;
 
-static inline void
-set_cpu_sibling_map(int cpu)
+void set_cpu_sibling_map(int cpu)
 {
 	int i;
 	struct cpuinfo_x86 *c = cpu_data;
@@ -1144,8 +1143,7 @@ void __init native_smp_prepare_boot_cpu(void)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static void
-remove_siblinginfo(int cpu)
+void remove_siblinginfo(int cpu)
 {
 	int sibling;
 	struct cpuinfo_x86 *c = cpu_data;

arch/i386/kernel/tsc.c

@@ -84,7 +84,7 @@ static inline int check_tsc_unstable(void)
  *
  *			[email protected] "math is hard, lets go shopping!"
  */
-static unsigned long cyc2ns_scale __read_mostly;
+unsigned long cyc2ns_scale __read_mostly;
 
 #define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
 
@@ -93,15 +93,10 @@ static inline void set_cyc2ns_scale(unsigned long cpu_khz)
 	cyc2ns_scale = (1000000 << CYC2NS_SCALE_FACTOR)/cpu_khz;
 }
 
-static inline unsigned long long cycles_2_ns(unsigned long long cyc)
-{
-	return (cyc * cyc2ns_scale) >> CYC2NS_SCALE_FACTOR;
-}
-
 /*
  * Scheduler clock - returns current time in nanosec units.
  */
-unsigned long long sched_clock(void)
+unsigned long long native_sched_clock(void)
 {
 	unsigned long long this_offset;
 
@@ -118,12 +113,24 @@ unsigned long long sched_clock(void)
 		return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ);
 
 	/* read the Time Stamp Counter: */
-	get_scheduled_cycles(this_offset);
+	rdtscll(this_offset);
 
 	/* return the value in ns */
 	return cycles_2_ns(this_offset);
 }
 
+/* We need to define a real function for sched_clock, to override the
+   weak default version */
+#ifdef CONFIG_PARAVIRT
+unsigned long long sched_clock(void)
+{
+	return paravirt_sched_clock();
+}
+#else
+unsigned long long sched_clock(void)
+	__attribute__((alias("native_sched_clock")));
+#endif
+
 unsigned long native_calculate_cpu_khz(void)
 {
 	unsigned long long start, end;

arch/i386/kernel/vmi.c

@@ -362,7 +362,7 @@ static void *vmi_kmap_atomic_pte(struct page *page, enum km_type type)
 }
 #endif
 
-static void vmi_allocate_pt(u32 pfn)
+static void vmi_allocate_pt(struct mm_struct *mm, u32 pfn)
 {
 	vmi_set_page_type(pfn, VMI_PAGE_L1);
 	vmi_ops.allocate_page(pfn, VMI_PAGE_L1, 0, 0, 0);
@@ -891,7 +891,7 @@ static inline int __init activate_vmi(void)
 		paravirt_ops.setup_boot_clock = vmi_time_bsp_init;
 		paravirt_ops.setup_secondary_clock = vmi_time_ap_init;
 #endif
-		paravirt_ops.get_scheduled_cycles = vmi_get_sched_cycles;
+		paravirt_ops.sched_clock = vmi_sched_clock;
  		paravirt_ops.get_cpu_khz = vmi_cpu_khz;
 
 		/* We have true wallclock functions; disable CMOS clock sync */

arch/i386/kernel/vmiclock.c

@@ -64,10 +64,10 @@ int vmi_set_wallclock(unsigned long now)
 	return 0;
 }
 
-/* paravirt_ops.get_scheduled_cycles = vmi_get_sched_cycles */
-unsigned long long vmi_get_sched_cycles(void)
+/* paravirt_ops.sched_clock = vmi_sched_clock */
+unsigned long long vmi_sched_clock(void)
 {
-	return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_AVAILABLE);
+	return cycles_2_ns(vmi_timer_ops.get_cycle_counter(VMI_CYCLES_AVAILABLE));
 }
 
 /* paravirt_ops.get_cpu_khz = vmi_cpu_khz */

arch/i386/kernel/vmlinux.lds.S

@@ -88,6 +88,7 @@ SECTIONS
 
   . = ALIGN(4096);
   .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
+	*(.data.page_aligned)
 	*(.data.idt)
   }