Merge branch 'x86-xen-for-linus' of git://git.kernel.org/pub/scm/linu…

…x/kernel/git/tip/linux-2.6-tip

* 'x86-xen-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (42 commits)
  xen: cache cr0 value to avoid trap'n'emulate for read_cr0
  xen/x86-64: clean up warnings about IST-using traps
  xen/x86-64: fix breakpoints and hardware watchpoints
  xen: reserve Xen start_info rather than e820 reserving
  xen: add FIX_TEXT_POKE to fixmap
  lguest: update lazy mmu changes to match lguest's use of kvm hypercalls
  xen: honour VCPU availability on boot
  xen: add "capabilities" file
  xen: drop kexec bits from /sys/hypervisor since kexec isn't implemented yet
  xen/sys/hypervisor: change writable_pt to features
  xen: add /sys/hypervisor support
  xen/xenbus: export xenbus_dev_changed
  xen: use device model for suspending xenbus devices
  xen: remove suspend_cancel hook
  xen/dev-evtchn: clean up locking in evtchn
  xen: export ioctl headers to userspace
  xen: add /dev/xen/evtchn driver
  xen: add irq_from_evtchn
  xen: clean up gate trap/interrupt constants
  xen: set _PAGE_NX in __supported_pte_mask before pagetable construction
  ...

arch/x86/include/asm/paravirt.h

@@ -56,6 +56,7 @@ struct desc_ptr;
 struct tss_struct;
 struct mm_struct;
 struct desc_struct;
+struct task_struct;
 
 /*
  * Wrapper type for pointers to code which uses the non-standard
@@ -203,7 +204,8 @@ struct pv_cpu_ops {
 
 	void (*swapgs)(void);
 
-	struct pv_lazy_ops lazy_mode;
+	void (*start_context_switch)(struct task_struct *prev);
+	void (*end_context_switch)(struct task_struct *next);
 };
 
 struct pv_irq_ops {
@@ -1399,25 +1401,23 @@ enum paravirt_lazy_mode {
 };
 
 enum paravirt_lazy_mode paravirt_get_lazy_mode(void);
-void paravirt_enter_lazy_cpu(void);
-void paravirt_leave_lazy_cpu(void);
+void paravirt_start_context_switch(struct task_struct *prev);
+void paravirt_end_context_switch(struct task_struct *next);
+
 void paravirt_enter_lazy_mmu(void);
 void paravirt_leave_lazy_mmu(void);
-void paravirt_leave_lazy(enum paravirt_lazy_mode mode);
 
-#define  __HAVE_ARCH_ENTER_LAZY_CPU_MODE
-static inline void arch_enter_lazy_cpu_mode(void)
+#define  __HAVE_ARCH_START_CONTEXT_SWITCH
+static inline void arch_start_context_switch(struct task_struct *prev)
 {
-	PVOP_VCALL0(pv_cpu_ops.lazy_mode.enter);
+	PVOP_VCALL1(pv_cpu_ops.start_context_switch, prev);
 }
 
-static inline void arch_leave_lazy_cpu_mode(void)
+static inline void arch_end_context_switch(struct task_struct *next)
 {
-	PVOP_VCALL0(pv_cpu_ops.lazy_mode.leave);
+	PVOP_VCALL1(pv_cpu_ops.end_context_switch, next);
 }
 
-void arch_flush_lazy_cpu_mode(void);
-
 #define  __HAVE_ARCH_ENTER_LAZY_MMU_MODE
 static inline void arch_enter_lazy_mmu_mode(void)
 {

arch/x86/include/asm/pgtable.h

@@ -81,6 +81,8 @@ static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
 #define pte_val(x)	native_pte_val(x)
 #define __pte(x)	native_make_pte(x)
 
+#define arch_end_context_switch(prev)	do {} while(0)
+
 #endif	/* CONFIG_PARAVIRT */
 
 /*

arch/x86/include/asm/required-features.h

@@ -48,9 +48,15 @@
 #endif
 
 #ifdef CONFIG_X86_64
+#ifdef CONFIG_PARAVIRT
+/* Paravirtualized systems may not have PSE or PGE available */
 #define NEED_PSE	0
-#define NEED_MSR	(1<<(X86_FEATURE_MSR & 31))
 #define NEED_PGE	0
+#else
+#define NEED_PSE	(1<<(X86_FEATURE_PSE) & 31)
+#define NEED_PGE	(1<<(X86_FEATURE_PGE) & 31)
+#endif
+#define NEED_MSR	(1<<(X86_FEATURE_MSR & 31))
 #define NEED_FXSR	(1<<(X86_FEATURE_FXSR & 31))
 #define NEED_XMM	(1<<(X86_FEATURE_XMM & 31))
 #define NEED_XMM2	(1<<(X86_FEATURE_XMM2 & 31))

arch/x86/include/asm/thread_info.h

@@ -94,7 +94,8 @@ struct thread_info {
 #define TIF_FORCED_TF		24	/* true if TF in eflags artificially */
 #define TIF_DEBUGCTLMSR		25	/* uses thread_struct.debugctlmsr */
 #define TIF_DS_AREA_MSR		26      /* uses thread_struct.ds_area_msr */
-#define TIF_SYSCALL_FTRACE	27	/* for ftrace syscall instrumentation */
+#define TIF_LAZY_MMU_UPDATES	27	/* task is updating the mmu lazily */
+#define TIF_SYSCALL_FTRACE	28	/* for ftrace syscall instrumentation */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
@@ -116,6 +117,7 @@ struct thread_info {
 #define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
 #define _TIF_DEBUGCTLMSR	(1 << TIF_DEBUGCTLMSR)
 #define _TIF_DS_AREA_MSR	(1 << TIF_DS_AREA_MSR)
+#define _TIF_LAZY_MMU_UPDATES	(1 << TIF_LAZY_MMU_UPDATES)
 #define _TIF_SYSCALL_FTRACE	(1 << TIF_SYSCALL_FTRACE)
 
 /* work to do in syscall_trace_enter() */

arch/x86/include/asm/traps.h

@@ -14,6 +14,9 @@ asmlinkage void divide_error(void);
 asmlinkage void debug(void);
 asmlinkage void nmi(void);
 asmlinkage void int3(void);
+asmlinkage void xen_debug(void);
+asmlinkage void xen_int3(void);
+asmlinkage void xen_stack_segment(void);
 asmlinkage void overflow(void);
 asmlinkage void bounds(void);
 asmlinkage void invalid_op(void);

arch/x86/kernel/entry_64.S

@@ -1379,6 +1379,11 @@ END(xen_failsafe_callback)
 paranoidzeroentry_ist debug do_debug DEBUG_STACK
 paranoidzeroentry_ist int3 do_int3 DEBUG_STACK
 paranoiderrorentry stack_segment do_stack_segment
+#ifdef CONFIG_XEN
+zeroentry xen_debug do_debug
+zeroentry xen_int3 do_int3
+errorentry xen_stack_segment do_stack_segment
+#endif
 errorentry general_protection do_general_protection
 errorentry page_fault do_page_fault
 #ifdef CONFIG_X86_MCE

arch/x86/kernel/kvm.c

@@ -195,7 +195,7 @@ static void kvm_leave_lazy_mmu(void)
 	struct kvm_para_state *state = kvm_para_state();
 
 	mmu_queue_flush(state);
-	paravirt_leave_lazy(paravirt_get_lazy_mode());
+	paravirt_leave_lazy_mmu();
 	state->mode = paravirt_get_lazy_mode();
 }
 

arch/x86/kernel/paravirt.c

@@ -248,18 +248,16 @@ static DEFINE_PER_CPU(enum paravirt_lazy_mode, paravirt_lazy_mode) = PARAVIRT_LA
 
 static inline void enter_lazy(enum paravirt_lazy_mode mode)
 {
-	BUG_ON(__get_cpu_var(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE);
-	BUG_ON(preemptible());
+	BUG_ON(percpu_read(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE);
 
-	__get_cpu_var(paravirt_lazy_mode) = mode;
+	percpu_write(paravirt_lazy_mode, mode);
 }
 
-void paravirt_leave_lazy(enum paravirt_lazy_mode mode)
+static void leave_lazy(enum paravirt_lazy_mode mode)
 {
-	BUG_ON(__get_cpu_var(paravirt_lazy_mode) != mode);
-	BUG_ON(preemptible());
+	BUG_ON(percpu_read(paravirt_lazy_mode) != mode);
 
-	__get_cpu_var(paravirt_lazy_mode) = PARAVIRT_LAZY_NONE;
+	percpu_write(paravirt_lazy_mode, PARAVIRT_LAZY_NONE);
 }
 
 void paravirt_enter_lazy_mmu(void)
@@ -269,50 +267,50 @@ void paravirt_enter_lazy_mmu(void)
 
 void paravirt_leave_lazy_mmu(void)
 {
-	paravirt_leave_lazy(PARAVIRT_LAZY_MMU);
+	leave_lazy(PARAVIRT_LAZY_MMU);
 }
 
-void paravirt_enter_lazy_cpu(void)
+void paravirt_start_context_switch(struct task_struct *prev)
 {
+	BUG_ON(preemptible());
+
+	if (percpu_read(paravirt_lazy_mode) == PARAVIRT_LAZY_MMU) {
+		arch_leave_lazy_mmu_mode();
+		set_ti_thread_flag(task_thread_info(prev), TIF_LAZY_MMU_UPDATES);
+	}
 	enter_lazy(PARAVIRT_LAZY_CPU);
 }
 
-void paravirt_leave_lazy_cpu(void)
+void paravirt_end_context_switch(struct task_struct *next)
 {
-	paravirt_leave_lazy(PARAVIRT_LAZY_CPU);
+	BUG_ON(preemptible());
+
+	leave_lazy(PARAVIRT_LAZY_CPU);
+
+	if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES))
+		arch_enter_lazy_mmu_mode();
 }
 
 enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 {
-	return __get_cpu_var(paravirt_lazy_mode);
+	if (in_interrupt())
+		return PARAVIRT_LAZY_NONE;
+
+	return percpu_read(paravirt_lazy_mode);
 }
 
 void arch_flush_lazy_mmu_mode(void)
 {
 	preempt_disable();
 
 	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
-		WARN_ON(preempt_count() == 1);
 		arch_leave_lazy_mmu_mode();
 		arch_enter_lazy_mmu_mode();
 	}
 
 	preempt_enable();
 }
 
-void arch_flush_lazy_cpu_mode(void)
-{
-	preempt_disable();
-
-	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
-		WARN_ON(preempt_count() == 1);
-		arch_leave_lazy_cpu_mode();
-		arch_enter_lazy_cpu_mode();
-	}
-
-	preempt_enable();
-}
-
 struct pv_info pv_info = {
 	.name = "bare hardware",
 	.paravirt_enabled = 0,
@@ -404,10 +402,8 @@ struct pv_cpu_ops pv_cpu_ops = {
 	.set_iopl_mask = native_set_iopl_mask,
 	.io_delay = native_io_delay,
 
-	.lazy_mode = {
-		.enter = paravirt_nop,
-		.leave = paravirt_nop,
-	},
+	.start_context_switch = paravirt_nop,
+	.end_context_switch = paravirt_nop,
 };
 
 struct pv_apic_ops pv_apic_ops = {

arch/x86/kernel/process_32.c

@@ -404,7 +404,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * done before math_state_restore, so the TS bit is up
 	 * to date.
 	 */
-	arch_leave_lazy_cpu_mode();
+	arch_end_context_switch(next_p);
 
 	/* If the task has used fpu the last 5 timeslices, just do a full
 	 * restore of the math state immediately to avoid the trap; the

arch/x86/kernel/process_64.c

@@ -425,7 +425,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * done before math_state_restore, so the TS bit is up
 	 * to date.
 	 */
-	arch_leave_lazy_cpu_mode();
+	arch_end_context_switch(next_p);
 
 	/*
 	 * Switch FS and GS.

arch/x86/kernel/vmi_32.c

@@ -462,22 +462,28 @@ vmi_startup_ipi_hook(int phys_apicid, unsigned long start_eip,
 }
 #endif
 
-static void vmi_enter_lazy_cpu(void)
+static void vmi_start_context_switch(struct task_struct *prev)
 {
-	paravirt_enter_lazy_cpu();
+	paravirt_start_context_switch(prev);
 	vmi_ops.set_lazy_mode(2);
 }
 
+static void vmi_end_context_switch(struct task_struct *next)
+{
+	vmi_ops.set_lazy_mode(0);
+	paravirt_end_context_switch(next);
+}
+
 static void vmi_enter_lazy_mmu(void)
 {
 	paravirt_enter_lazy_mmu();
 	vmi_ops.set_lazy_mode(1);
 }
 
-static void vmi_leave_lazy(void)
+static void vmi_leave_lazy_mmu(void)
 {
-	paravirt_leave_lazy(paravirt_get_lazy_mode());
 	vmi_ops.set_lazy_mode(0);
+	paravirt_leave_lazy_mmu();
 }
 
 static inline int __init check_vmi_rom(struct vrom_header *rom)
@@ -711,14 +717,14 @@ static inline int __init activate_vmi(void)
 	para_fill(pv_cpu_ops.set_iopl_mask, SetIOPLMask);
 	para_fill(pv_cpu_ops.io_delay, IODelay);
 
-	para_wrap(pv_cpu_ops.lazy_mode.enter, vmi_enter_lazy_cpu,
+	para_wrap(pv_cpu_ops.start_context_switch, vmi_start_context_switch,
 		  set_lazy_mode, SetLazyMode);
-	para_wrap(pv_cpu_ops.lazy_mode.leave, vmi_leave_lazy,
+	para_wrap(pv_cpu_ops.end_context_switch, vmi_end_context_switch,
 		  set_lazy_mode, SetLazyMode);
 
 	para_wrap(pv_mmu_ops.lazy_mode.enter, vmi_enter_lazy_mmu,
 		  set_lazy_mode, SetLazyMode);
-	para_wrap(pv_mmu_ops.lazy_mode.leave, vmi_leave_lazy,
+	para_wrap(pv_mmu_ops.lazy_mode.leave, vmi_leave_lazy_mmu,
 		  set_lazy_mode, SetLazyMode);
 
 	/* user and kernel flush are just handled with different flags to FlushTLB */

arch/x86/lguest/boot.c

@@ -167,10 +167,16 @@ static void lazy_hcall3(unsigned long call,
 
 /* When lazy mode is turned off reset the per-cpu lazy mode variable and then
  * issue the do-nothing hypercall to flush any stored calls. */
-static void lguest_leave_lazy_mode(void)
+static void lguest_leave_lazy_mmu_mode(void)
 {
-	paravirt_leave_lazy(paravirt_get_lazy_mode());
 	kvm_hypercall0(LHCALL_FLUSH_ASYNC);
+	paravirt_leave_lazy_mmu();
+}
+
+static void lguest_end_context_switch(struct task_struct *next)
+{
+	kvm_hypercall0(LHCALL_FLUSH_ASYNC);
+	paravirt_end_context_switch(next);
 }
 
 /*G:033
@@ -1054,8 +1060,8 @@ __init void lguest_init(void)
 	pv_cpu_ops.write_gdt_entry = lguest_write_gdt_entry;
 	pv_cpu_ops.write_idt_entry = lguest_write_idt_entry;
 	pv_cpu_ops.wbinvd = lguest_wbinvd;
-	pv_cpu_ops.lazy_mode.enter = paravirt_enter_lazy_cpu;
-	pv_cpu_ops.lazy_mode.leave = lguest_leave_lazy_mode;
+	pv_cpu_ops.start_context_switch = paravirt_start_context_switch;
+	pv_cpu_ops.end_context_switch = lguest_end_context_switch;
 
 	/* pagetable management */
 	pv_mmu_ops.write_cr3 = lguest_write_cr3;
@@ -1068,7 +1074,7 @@ __init void lguest_init(void)
 	pv_mmu_ops.read_cr2 = lguest_read_cr2;
 	pv_mmu_ops.read_cr3 = lguest_read_cr3;
 	pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu;
-	pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mode;
+	pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode;
 	pv_mmu_ops.pte_update = lguest_pte_update;
 	pv_mmu_ops.pte_update_defer = lguest_pte_update;
 

arch/x86/mm/fault.c

@@ -201,12 +201,10 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
 	if (!pmd_present(*pmd_k))
 		return NULL;
 
-	if (!pmd_present(*pmd)) {
+	if (!pmd_present(*pmd))
 		set_pmd(pmd, *pmd_k);
-		arch_flush_lazy_mmu_mode();
-	} else {
+	else
 		BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
-	}
 
 	return pmd_k;
 }

arch/x86/mm/highmem_32.c

@@ -44,7 +44,6 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot)
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 	BUG_ON(!pte_none(*(kmap_pte-idx)));
 	set_pte(kmap_pte-idx, mk_pte(page, prot));
-	arch_flush_lazy_mmu_mode();
 
 	return (void *)vaddr;
 }
@@ -74,7 +73,6 @@ void kunmap_atomic(void *kvaddr, enum km_type type)
 #endif
 	}
 
-	arch_flush_lazy_mmu_mode();
 	pagefault_enable();
 }
 

arch/x86/mm/iomap_32.c

@@ -82,7 +82,6 @@ iounmap_atomic(void *kvaddr, enum km_type type)
 	if (vaddr == __fix_to_virt(FIX_KMAP_BEGIN+idx))
 		kpte_clear_flush(kmap_pte-idx, vaddr);
 
-	arch_flush_lazy_mmu_mode();
 	pagefault_enable();
 }
 EXPORT_SYMBOL_GPL(iounmap_atomic);