Merge branch 'linus' into tracing/ftrace

22 files changed, 113 insertions, 58 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 350bee1d54dc..d11d7b513191 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -28,7 +28,7 @@ config X86
 	select HAVE_KRETPROBES
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
-	select HAVE_FTRACE
+	select HAVE_FUNCTION_TRACER
 	select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
 	select HAVE_ARCH_KGDB if !X86_VOYAGER
 	select HAVE_ARCH_TRACEHOOK
diff --git a/arch/x86/boot/compressed/.gitignore b/arch/x86/boot/compressed/.gitignore
index be0ed065249b..63eff3b04d01 100644
--- a/arch/x86/boot/compressed/.gitignore
+++ b/arch/x86/boot/compressed/.gitignore
@@ -1 +1,3 @@
 relocs
+vmlinux.bin.all
+vmlinux.relocs
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 4a5397bfce27..7f225a4b2a26 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -255,9 +255,11 @@ static inline unsigned long dma_alloc_coherent_mask(struct device *dev,
 
 static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp)
 {
-#ifdef CONFIG_X86_64
 	unsigned long dma_mask = dma_alloc_coherent_mask(dev, gfp);
 
+	if (dma_mask <= DMA_24BIT_MASK)
+		gfp |= GFP_DMA;
+#ifdef CONFIG_X86_64
 	if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA))
 		gfp |= GFP_DMA32;
 #endif
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 47f7e65e6c1d..9e8bc29b8b17 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -1,7 +1,7 @@
 #ifndef _ASM_X86_FTRACE_H
 #define _ASM_X86_FTRACE_H
 
-#ifdef CONFIG_FTRACE
+#ifdef CONFIG_FUNCTION_TRACER
 #define MCOUNT_ADDR		((long)(mcount))
 #define MCOUNT_INSN_SIZE	5 /* sizeof mcount call */
 
@@ -19,6 +19,6 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 }
 #endif
 
-#endif /* CONFIG_FTRACE */
+#endif /* CONFIG_FUNCTION_TRACER */
 
 #endif /* _ASM_X86_FTRACE_H */
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index 98e28ea8cd16..e4a552d44465 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -7,7 +7,6 @@ extern struct dma_mapping_ops nommu_dma_ops;
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
 extern int dmar_disabled;
-extern int forbid_dac;
 
 extern unsigned long iommu_nr_pages(unsigned long addr, unsigned long len);
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 65679d006337..8346be87cfa1 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -364,6 +364,9 @@ struct kvm_arch{
 
 	struct page *ept_identity_pagetable;
 	bool ept_identity_pagetable_done;
+
+	unsigned long irq_sources_bitmap;
+	unsigned long irq_states[KVM_IOAPIC_NUM_PINS];
 };
 
 struct kvm_vm_stat {
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index d7e5a58ee22f..e489ff9cb3e2 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -6,11 +6,12 @@ extra-y                := head_$(BITS).o head$(BITS).o head.o init_task.o vmlinu
 
 CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
 
-ifdef CONFIG_FTRACE
+ifdef CONFIG_FUNCTION_TRACER
 # Do not profile debug and lowlevel utilities
 CFLAGS_REMOVE_tsc.o = -pg
 CFLAGS_REMOVE_rtc.o = -pg
 CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
+CFLAGS_REMOVE_ftrace.o = -pg
 endif
 
 #
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index dd65143941a8..28b597ef9ca1 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1149,7 +1149,7 @@ ENDPROC(xen_failsafe_callback)
 
 #endif	/* CONFIG_XEN */
 
-#ifdef CONFIG_FTRACE
+#ifdef CONFIG_FUNCTION_TRACER
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 ENTRY(mcount)
@@ -1204,7 +1204,7 @@ trace:
 	jmp ftrace_stub
 END(mcount)
 #endif /* CONFIG_DYNAMIC_FTRACE */
-#endif /* CONFIG_FTRACE */
+#endif /* CONFIG_FUNCTION_TRACER */
 
 .section .rodata,"a"
 #include "syscall_table_32.S"
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 09e7145484c5..b86f332c96a6 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -61,7 +61,7 @@
 
 	.code64
 
-#ifdef CONFIG_FTRACE
+#ifdef CONFIG_FUNCTION_TRACER
 #ifdef CONFIG_DYNAMIC_FTRACE
 ENTRY(mcount)
 	retq
@@ -138,7 +138,7 @@ trace:
 	jmp ftrace_stub
 END(mcount)
 #endif /* CONFIG_DYNAMIC_FTRACE */
-#endif /* CONFIG_FTRACE */
+#endif /* CONFIG_FUNCTION_TRACER */
 
 #ifndef CONFIG_PREEMPT
 #define retint_kernel retint_restore_args
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index d073d981a730..50ea0ac8c9bf 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -21,8 +21,7 @@
 #include <asm/nops.h>
 
 
-/* Long is fine, even if it is only 4 bytes ;-) */
-static unsigned long *ftrace_nop;
+static unsigned char ftrace_nop[MCOUNT_INSN_SIZE];
 
 union ftrace_code_union {
 	char code[MCOUNT_INSN_SIZE];
@@ -33,17 +32,17 @@ union ftrace_code_union {
 };
 
 
-static int notrace ftrace_calc_offset(long ip, long addr)
+static int ftrace_calc_offset(long ip, long addr)
 {
 	return (int)(addr - ip);
 }
 
-notrace unsigned char *ftrace_nop_replace(void)
+unsigned char *ftrace_nop_replace(void)
 {
-	return (char *)ftrace_nop;
+	return ftrace_nop;
 }
 
-notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
+unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 {
 	static union ftrace_code_union calc;
 
@@ -57,7 +56,7 @@ notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 	return calc.code;
 }
 
-notrace int
+int
 ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 		   unsigned char *new_code)
 {
@@ -66,26 +65,31 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 	/*
 	 * Note: Due to modules and __init, code can
 	 *  disappear and change, we need to protect against faulting
-	 *  as well as code changing.
+	 *  as well as code changing. We do this by using the
+	 *  probe_kernel_* functions.
 	 *
 	 * No real locking needed, this code is run through
 	 * kstop_machine, or before SMP starts.
 	 */
-	if (__copy_from_user_inatomic(replaced, (char __user *)ip, MCOUNT_INSN_SIZE))
-		return 1;
 
+	/* read the text we want to modify */
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* Make sure it is what we expect it to be */
 	if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
-		return 2;
+		return -EINVAL;
 
-	WARN_ON_ONCE(__copy_to_user_inatomic((char __user *)ip, new_code,
-				    MCOUNT_INSN_SIZE));
+	/* replace the text with the new text */
+	if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
+		return -EPERM;
 
 	sync_core();
 
 	return 0;
 }
 
-notrace int ftrace_update_ftrace_func(ftrace_func_t func)
+int ftrace_update_ftrace_func(ftrace_func_t func)
 {
 	unsigned long ip = (unsigned long)(&ftrace_call);
 	unsigned char old[MCOUNT_INSN_SIZE], *new;
@@ -98,13 +102,6 @@ notrace int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ret;
 }
 
-notrace int ftrace_mcount_set(unsigned long *data)
-{
-	/* mcount is initialized as a nop */
-	*data = 0;
-	return 0;
-}
-
 int __init ftrace_dyn_arch_init(void *data)
 {
 	extern const unsigned char ftrace_test_p6nop[];
@@ -127,9 +124,6 @@ int __init ftrace_dyn_arch_init(void *data)
 	 * TODO: check the cpuid to determine the best nop.
 	 */
 	asm volatile (
-		"jmp ftrace_test_jmp\n"
-		/* This code needs to stay around */
-		".section .text, \"ax\"\n"
 		"ftrace_test_jmp:"
 		"jmp ftrace_test_p6nop\n"
 		"nop\n"
@@ -140,8 +134,6 @@ int __init ftrace_dyn_arch_init(void *data)
 		"jmp 1f\n"
 		"ftrace_test_nop5:"
 		".byte 0x66,0x66,0x66,0x66,0x90\n"
-		"jmp 1f\n"
-		".previous\n"
 		"1:"
 		".section .fixup, \"ax\"\n"
 		"2:	movl $1, %0\n"
@@ -156,15 +148,15 @@ int __init ftrace_dyn_arch_init(void *data)
 	switch (faulted) {
 	case 0:
 		pr_info("ftrace: converting mcount calls to 0f 1f 44 00 00\n");
-		ftrace_nop = (unsigned long *)ftrace_test_p6nop;
+		memcpy(ftrace_nop, ftrace_test_p6nop, MCOUNT_INSN_SIZE);
 		break;
 	case 1:
 		pr_info("ftrace: converting mcount calls to 66 66 66 66 90\n");
-		ftrace_nop = (unsigned long *)ftrace_test_nop5;
+		memcpy(ftrace_nop, ftrace_test_nop5, MCOUNT_INSN_SIZE);
 		break;
 	case 2:
 		pr_info("ftrace: converting mcount calls to jmp . + 5\n");
-		ftrace_nop = (unsigned long *)ftrace_test_jmp;
+		memcpy(ftrace_nop, ftrace_test_jmp, MCOUNT_INSN_SIZE);
 		break;
 	}
 
diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c
index 680a06557c5e..2c7dbdb98278 100644
--- a/arch/x86/kernel/genx2apic_uv_x.c
+++ b/arch/x86/kernel/genx2apic_uv_x.c
@@ -15,7 +15,6 @@
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/sched.h>
-#include <linux/bootmem.h>
 #include <linux/module.h>
 #include <linux/hardirq.h>
 #include <asm/smp.h>
@@ -398,16 +397,16 @@ void __init uv_system_init(void)
 	printk(KERN_DEBUG "UV: Found %d blades\n", uv_num_possible_blades());
 
 	bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
-	uv_blade_info = alloc_bootmem_pages(bytes);
+	uv_blade_info = kmalloc(bytes, GFP_KERNEL);
 
 	get_lowmem_redirect(&lowmem_redir_base, &lowmem_redir_size);
 
 	bytes = sizeof(uv_node_to_blade[0]) * num_possible_nodes();
-	uv_node_to_blade = alloc_bootmem_pages(bytes);
+	uv_node_to_blade = kmalloc(bytes, GFP_KERNEL);
 	memset(uv_node_to_blade, 255, bytes);
 
 	bytes = sizeof(uv_cpu_to_blade[0]) * num_possible_cpus();
-	uv_cpu_to_blade = alloc_bootmem_pages(bytes);
+	uv_cpu_to_blade = kmalloc(bytes, GFP_KERNEL);
 	memset(uv_cpu_to_blade, 255, bytes);
 
 	blade = 0;
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index dd7ebee446af..43cec6bdda63 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -5,7 +5,7 @@
 #include <asm/desc.h>
 #include <asm/ftrace.h>
 
-#ifdef CONFIG_FTRACE
+#ifdef CONFIG_FUNCTION_TRACER
 /* mcount is defined in assembly */
 EXPORT_SYMBOL(mcount);
 #endif
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 1972266e8ba5..192624820217 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -9,6 +9,8 @@
 #include <asm/calgary.h>
 #include <asm/amd_iommu.h>
 
+static int forbid_dac __read_mostly;
+
 struct dma_mapping_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
@@ -291,3 +293,17 @@ void pci_iommu_shutdown(void)
 }
 /* Must execute after PCI subsystem */
 fs_initcall(pci_iommu_init);
+
+#ifdef CONFIG_PCI
+/* Many VIA bridges seem to corrupt data for DAC. Disable it here */
+
+static __devinit void via_no_dac(struct pci_dev *dev)
+{
+	if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && forbid_dac == 0) {
+		printk(KERN_INFO "PCI: VIA PCI bridge detected."
+				 "Disabling DAC.\n");
+		forbid_dac = 1;
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID, via_no_dac);
+#endif
diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c
index c4ce0332759e..3c539d111abb 100644
--- a/arch/x86/kernel/pci-swiotlb_64.c
+++ b/arch/x86/kernel/pci-swiotlb_64.c
@@ -18,9 +18,21 @@ swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size,
 	return swiotlb_map_single(hwdev, phys_to_virt(paddr), size, direction);
 }
 
+static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
+					dma_addr_t *dma_handle, gfp_t flags)
+{
+	void *vaddr;
+
+	vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags);
+	if (vaddr)
+		return vaddr;
+
+	return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags);
+}
+
 struct dma_mapping_ops swiotlb_dma_ops = {
 	.mapping_error = swiotlb_dma_mapping_error,
-	.alloc_coherent = swiotlb_alloc_coherent,
+	.alloc_coherent = x86_swiotlb_alloc_coherent,
 	.free_coherent = swiotlb_free_coherent,
 	.map_single = swiotlb_map_single_phys,
 	.unmap_single = swiotlb_unmap_single,
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index b545f371b5f5..695e426aa354 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -12,7 +12,7 @@
 #include <asm/desc.h>
 #include <asm/ftrace.h>
 
-#ifdef CONFIG_FTRACE
+#ifdef CONFIG_FUNCTION_TRACER
 /* mcount is defined in assembly */
 EXPORT_SYMBOL(mcount);
 #endif
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 11c6725fb798..8772dc946823 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -545,6 +545,12 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm)
 	if (!pit)
 		return NULL;
 
+	mutex_lock(&kvm->lock);
+	pit->irq_source_id = kvm_request_irq_source_id(kvm);
+	mutex_unlock(&kvm->lock);
+	if (pit->irq_source_id < 0)
+		return NULL;
+
 	mutex_init(&pit->pit_state.lock);
 	mutex_lock(&pit->pit_state.lock);
 	spin_lock_init(&pit->pit_state.inject_lock);
@@ -587,6 +593,7 @@ void kvm_free_pit(struct kvm *kvm)
 		mutex_lock(&kvm->arch.vpit->pit_state.lock);
 		timer = &kvm->arch.vpit->pit_state.pit_timer.timer;
 		hrtimer_cancel(timer);
+		kvm_free_irq_source_id(kvm, kvm->arch.vpit->irq_source_id);
 		mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 		kfree(kvm->arch.vpit);
 	}
@@ -595,8 +602,8 @@ void kvm_free_pit(struct kvm *kvm)
 static void __inject_pit_timer_intr(struct kvm *kvm)
 {
 	mutex_lock(&kvm->lock);
-	kvm_set_irq(kvm, 0, 1);
-	kvm_set_irq(kvm, 0, 0);
+	kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1);
+	kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0);
 	mutex_unlock(&kvm->lock);
 }
 
diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h
index e436d4983aa1..4178022b97aa 100644
--- a/arch/x86/kvm/i8254.h
+++ b/arch/x86/kvm/i8254.h
@@ -44,6 +44,7 @@ struct kvm_pit {
 	struct kvm_io_device speaker_dev;
 	struct kvm *kvm;
 	struct kvm_kpit_state pit_state;
+	int irq_source_id;
 };
 
 #define KVM_PIT_BASE_ADDRESS	    0x40
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 99c239c5c0ac..2a5e64881d9b 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2634,6 +2634,7 @@ static int kvm_pv_mmu_write(struct kvm_vcpu *vcpu,
 static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu)
 {
 	kvm_x86_ops->tlb_flush(vcpu);
+	set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests);
 	return 1;
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4f0677d1eae8..f1f8ff2f1fa2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1742,7 +1742,8 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			goto out;
 		if (irqchip_in_kernel(kvm)) {
 			mutex_lock(&kvm->lock);
-			kvm_set_irq(kvm, irq_event.irq, irq_event.level);
+			kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
+				    irq_event.irq, irq_event.level);
 			mutex_unlock(&kvm->lock);
 			r = 0;
 		}
@@ -4013,6 +4014,9 @@ struct  kvm *kvm_arch_create_vm(void)
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
 
+	/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
+	set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap);
+
 	return kvm;
 }
 
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index b8e461d49412..f79a02f64d10 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -350,8 +350,10 @@ phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
 		 * pagetable pages as RO. So assume someone who pre-setup
 		 * these mappings are more intelligent.
 		 */
-		if (pte_val(*pte))
+		if (pte_val(*pte)) {
+			pages++;
 			continue;
+		}
 
 		if (0)
 			printk("   pte=%p addr=%lx pte=%016lx\n",
@@ -418,8 +420,10 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
 			 * not differ with respect to page frame and
 			 * attributes.
 			 */
-			if (page_size_mask & (1 << PG_LEVEL_2M))
+			if (page_size_mask & (1 << PG_LEVEL_2M)) {
+				pages++;
 				continue;
+			}
 			new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd));
 		}
 
@@ -499,8 +503,10 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
 			 * not differ with respect to page frame and
 			 * attributes.
 			 */
-			if (page_size_mask & (1 << PG_LEVEL_1G))
+			if (page_size_mask & (1 << PG_LEVEL_1G)) {
+				pages++;
 				continue;
+			}
 			prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud));
 		}
 
@@ -831,7 +837,7 @@ int arch_add_memory(int nid, u64 start, u64 size)
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
 
-	last_mapped_pfn = init_memory_mapping(start, start + size-1);
+	last_mapped_pfn = init_memory_mapping(start, start + size);
 	if (last_mapped_pfn > max_pfn_mapped)
 		max_pfn_mapped = last_mapped_pfn;
 
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 313947940a1a..6dcefba7836f 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -1,4 +1,4 @@
-ifdef CONFIG_FTRACE
+ifdef CONFIG_FUNCTION_TRACER
 # Do not profile debug and lowlevel utilities
 CFLAGS_REMOVE_spinlock.o = -pg
 CFLAGS_REMOVE_time.o = -pg
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index d4d52f5a1cf7..aba77b2b7d18 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -246,11 +246,21 @@ xmaddr_t arbitrary_virt_to_machine(void *vaddr)
 {
 	unsigned long address = (unsigned long)vaddr;
 	unsigned int level;
-	pte_t *pte = lookup_address(address, &level);
-	unsigned offset = address & ~PAGE_MASK;
+	pte_t *pte;
+	unsigned offset;
 
-	BUG_ON(pte == NULL);
+	/*
+	 * if the PFN is in the linear mapped vaddr range, we can just use
+	 * the (quick) virt_to_machine() p2m lookup
+	 */
+	if (virt_addr_valid(vaddr))
+		return virt_to_machine(vaddr);
 
+	/* otherwise we have to do a (slower) full page-table walk */
+
+	pte = lookup_address(address, &level);
+	BUG_ON(pte == NULL);
+	offset = address & ~PAGE_MASK;
 	return XMADDR(((phys_addr_t)pte_mfn(*pte) << PAGE_SHIFT) + offset);
 }
 
@@ -410,7 +420,7 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
 
 	xen_mc_batch();
 
-	u.ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;
+	u.ptr = arbitrary_virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;
 	u.val = pte_val_ma(pte);
 	xen_extend_mmu_update(&u);