diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index d240ea950519..417777de5a40 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -39,6 +39,8 @@
 #include <linux/string.h>
 #include <linux/types.h>
 
+#include <trace/events/xen.h>
+
 #include <asm/page.h>
 #include <asm/pgtable.h>
 
@@ -459,6 +461,8 @@ MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set)
 {
 	mcl->op = __HYPERVISOR_fpu_taskswitch;
 	mcl->args[0] = set;
+
+	trace_xen_mc_entry(mcl, 1);
 }
 
 static inline void
@@ -475,6 +479,8 @@ MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va,
 		mcl->args[2] = new_val.pte >> 32;
 		mcl->args[3] = flags;
 	}
+
+	trace_xen_mc_entry(mcl, sizeof(new_val) == sizeof(long) ? 3 : 4);
 }
 
 static inline void
@@ -485,6 +491,8 @@ MULTI_grant_table_op(struct multicall_entry *mcl, unsigned int cmd,
 	mcl->args[0] = cmd;
 	mcl->args[1] = (unsigned long)uop;
 	mcl->args[2] = count;
+
+	trace_xen_mc_entry(mcl, 3);
 }
 
 static inline void
@@ -504,6 +512,8 @@ MULTI_update_va_mapping_otherdomain(struct multicall_entry *mcl, unsigned long v
 		mcl->args[3] = flags;
 		mcl->args[4] = domid;
 	}
+
+	trace_xen_mc_entry(mcl, sizeof(new_val) == sizeof(long) ? 4 : 5);
 }
 
 static inline void
@@ -520,6 +530,8 @@ MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr,
 		mcl->args[2] = desc.a;
 		mcl->args[3] = desc.b;
 	}
+
+	trace_xen_mc_entry(mcl, sizeof(maddr) == sizeof(long) ? 2 : 4);
 }
 
 static inline void
@@ -528,6 +540,8 @@ MULTI_memory_op(struct multicall_entry *mcl, unsigned int cmd, void *arg)
 	mcl->op = __HYPERVISOR_memory_op;
 	mcl->args[0] = cmd;
 	mcl->args[1] = (unsigned long)arg;
+
+	trace_xen_mc_entry(mcl, 2);
 }
 
 static inline void
@@ -539,6 +553,8 @@ MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req,
 	mcl->args[1] = count;
 	mcl->args[2] = (unsigned long)success_count;
 	mcl->args[3] = domid;
+
+	trace_xen_mc_entry(mcl, 4);
 }
 
 static inline void
@@ -550,6 +566,8 @@ MULTI_mmuext_op(struct multicall_entry *mcl, struct mmuext_op *op, int count,
 	mcl->args[1] = count;
 	mcl->args[2] = (unsigned long)success_count;
 	mcl->args[3] = domid;
+
+	trace_xen_mc_entry(mcl, 4);
 }
 
 static inline void
@@ -558,6 +576,8 @@ MULTI_set_gdt(struct multicall_entry *mcl, unsigned long *frames, int entries)
 	mcl->op = __HYPERVISOR_set_gdt;
 	mcl->args[0] = (unsigned long)frames;
 	mcl->args[1] = entries;
+
+	trace_xen_mc_entry(mcl, 2);
 }
 
 static inline void
@@ -567,6 +587,8 @@ MULTI_stack_switch(struct multicall_entry *mcl,
 	mcl->op = __HYPERVISOR_stack_switch;
 	mcl->args[0] = ss;
 	mcl->args[1] = esp;
+
+	trace_xen_mc_entry(mcl, 2);
 }
 
 #endif /* _ASM_X86_XEN_HYPERCALL_H */
diff --git a/arch/x86/include/asm/xen/trace_types.h b/arch/x86/include/asm/xen/trace_types.h
new file mode 100644
index 000000000000..21e1874c0a0b
--- /dev/null
+++ b/arch/x86/include/asm/xen/trace_types.h
@@ -0,0 +1,18 @@
+#ifndef _ASM_XEN_TRACE_TYPES_H
+#define _ASM_XEN_TRACE_TYPES_H
+
+enum xen_mc_flush_reason {
+	XEN_MC_FL_NONE,		/* explicit flush */
+	XEN_MC_FL_BATCH,	/* out of hypercall space */
+	XEN_MC_FL_ARGS,		/* out of argument space */
+	XEN_MC_FL_CALLBACK,	/* out of callback space */
+};
+
+enum xen_mc_extend_args {
+	XEN_MC_XE_OK,
+	XEN_MC_XE_BAD_OP,
+	XEN_MC_XE_NO_SPACE
+};
+typedef void (*xen_mc_callback_fn_t)(void *);
+
+#endif	/* _ASM_XEN_TRACE_TYPES_H */
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index a6575b949b11..ccf73b2f3e69 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -13,7 +13,7 @@ CFLAGS_mmu.o			:= $(nostackp)
 obj-y		:= enlighten.o setup.o multicalls.o mmu.o irq.o \
 			time.o xen-asm.o xen-asm_$(BITS).o \
 			grant-table.o suspend.o platform-pci-unplug.o \
-			p2m.o
+			p2m.o trace.o
 
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 53257421082b..974a528458a0 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -341,6 +341,8 @@ static void xen_set_ldt(const void *addr, unsigned entries)
 	struct mmuext_op *op;
 	struct multicall_space mcs = xen_mc_entry(sizeof(*op));
 
+	trace_xen_cpu_set_ldt(addr, entries);
+
 	op = mcs.args;
 	op->cmd = MMUEXT_SET_LDT;
 	op->arg1.linear_addr = (unsigned long)addr;
@@ -496,6 +498,8 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum,
 	xmaddr_t mach_lp = arbitrary_virt_to_machine(&dt[entrynum]);
 	u64 entry = *(u64 *)ptr;
 
+	trace_xen_cpu_write_ldt_entry(dt, entrynum, entry);
+
 	preempt_disable();
 
 	xen_mc_flush();
@@ -565,6 +569,8 @@ static void xen_write_idt_entry(gate_desc *dt, int entrynum, const gate_desc *g)
 	unsigned long p = (unsigned long)&dt[entrynum];
 	unsigned long start, end;
 
+	trace_xen_cpu_write_idt_entry(dt, entrynum, g);
+
 	preempt_disable();
 
 	start = __this_cpu_read(idt_desc.address);
@@ -619,6 +625,8 @@ static void xen_load_idt(const struct desc_ptr *desc)
 	static DEFINE_SPINLOCK(lock);
 	static struct trap_info traps[257];
 
+	trace_xen_cpu_load_idt(desc);
+
 	spin_lock(&lock);
 
 	__get_cpu_var(idt_desc) = *desc;
@@ -637,6 +645,8 @@ static void xen_load_idt(const struct desc_ptr *desc)
 static void xen_write_gdt_entry(struct desc_struct *dt, int entry,
 				const void *desc, int type)
 {
+	trace_xen_cpu_write_gdt_entry(dt, entry, desc, type);
+
 	preempt_disable();
 
 	switch (type) {
@@ -665,6 +675,8 @@ static void xen_write_gdt_entry(struct desc_struct *dt, int entry,
 static void __init xen_write_gdt_entry_boot(struct desc_struct *dt, int entry,
 					    const void *desc, int type)
 {
+	trace_xen_cpu_write_gdt_entry(dt, entry, desc, type);
+
 	switch (type) {
 	case DESC_LDT:
 	case DESC_TSS:
@@ -684,7 +696,9 @@ static void __init xen_write_gdt_entry_boot(struct desc_struct *dt, int entry,
 static void xen_load_sp0(struct tss_struct *tss,
 			 struct thread_struct *thread)
 {
-	struct multicall_space mcs = xen_mc_entry(0);
+	struct multicall_space mcs;
+
+	mcs = xen_mc_entry(0);
 	MULTI_stack_switch(mcs.mc, __KERNEL_DS, thread->sp0);
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
 }
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 0ccccb67a993..f987bde77c49 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -48,6 +48,8 @@
 #include <linux/memblock.h>
 #include <linux/seq_file.h>
 
+#include <trace/events/xen.h>
+
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/fixmap.h>
@@ -194,6 +196,8 @@ void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid)
 	struct multicall_space mcs;
 	struct mmu_update *u;
 
+	trace_xen_mmu_set_domain_pte(ptep, pteval, domid);
+
 	mcs = xen_mc_entry(sizeof(*u));
 	u = mcs.args;
 
@@ -225,6 +229,24 @@ static void xen_extend_mmu_update(const struct mmu_update *update)
 	*u = *update;
 }
 
+static void xen_extend_mmuext_op(const struct mmuext_op *op)
+{
+	struct multicall_space mcs;
+	struct mmuext_op *u;
+
+	mcs = xen_mc_extend_args(__HYPERVISOR_mmuext_op, sizeof(*u));
+
+	if (mcs.mc != NULL) {
+		mcs.mc->args[1]++;
+	} else {
+		mcs = __xen_mc_entry(sizeof(*u));
+		MULTI_mmuext_op(mcs.mc, mcs.args, 1, NULL, DOMID_SELF);
+	}
+
+	u = mcs.args;
+	*u = *op;
+}
+
 static void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
 {
 	struct mmu_update u;
@@ -245,6 +267,8 @@ static void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
 
 static void xen_set_pmd(pmd_t *ptr, pmd_t val)
 {
+	trace_xen_mmu_set_pmd(ptr, val);
+
 	/* If page is not pinned, we can just update the entry
 	   directly */
 	if (!xen_page_pinned(ptr)) {
@@ -282,22 +306,30 @@ static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval)
 	return true;
 }
 
-static void xen_set_pte(pte_t *ptep, pte_t pteval)
+static inline void __xen_set_pte(pte_t *ptep, pte_t pteval)
 {
 	if (!xen_batched_set_pte(ptep, pteval))
 		native_set_pte(ptep, pteval);
 }
 
+static void xen_set_pte(pte_t *ptep, pte_t pteval)
+{
+	trace_xen_mmu_set_pte(ptep, pteval);
+	__xen_set_pte(ptep, pteval);
+}
+
 static void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
 		    pte_t *ptep, pte_t pteval)
 {
-	xen_set_pte(ptep, pteval);
+	trace_xen_mmu_set_pte_at(mm, addr, ptep, pteval);
+	__xen_set_pte(ptep, pteval);
 }
 
 pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
 				 unsigned long addr, pte_t *ptep)
 {
 	/* Just return the pte as-is.  We preserve the bits on commit */
+	trace_xen_mmu_ptep_modify_prot_start(mm, addr, ptep, *ptep);
 	return *ptep;
 }
 
@@ -306,6 +338,7 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
 {
 	struct mmu_update u;
 
+	trace_xen_mmu_ptep_modify_prot_commit(mm, addr, ptep, pte);
 	xen_mc_batch();
 
 	u.ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;
@@ -530,6 +563,8 @@ static void xen_set_pud_hyper(pud_t *ptr, pud_t val)
 
 static void xen_set_pud(pud_t *ptr, pud_t val)
 {
+	trace_xen_mmu_set_pud(ptr, val);
+
 	/* If page is not pinned, we can just update the entry
 	   directly */
 	if (!xen_page_pinned(ptr)) {
@@ -543,17 +578,20 @@ static void xen_set_pud(pud_t *ptr, pud_t val)
 #ifdef CONFIG_X86_PAE
 static void xen_set_pte_atomic(pte_t *ptep, pte_t pte)
 {
+	trace_xen_mmu_set_pte_atomic(ptep, pte);
 	set_64bit((u64 *)ptep, native_pte_val(pte));
 }
 
 static void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
+	trace_xen_mmu_pte_clear(mm, addr, ptep);
 	if (!xen_batched_set_pte(ptep, native_make_pte(0)))
 		native_pte_clear(mm, addr, ptep);
 }
 
 static void xen_pmd_clear(pmd_t *pmdp)
 {
+	trace_xen_mmu_pmd_clear(pmdp);
 	set_pmd(pmdp, __pmd(0));
 }
 #endif	/* CONFIG_X86_PAE */
@@ -629,6 +667,8 @@ static void xen_set_pgd(pgd_t *ptr, pgd_t val)
 {
 	pgd_t *user_ptr = xen_get_user_pgd(ptr);
 
+	trace_xen_mmu_set_pgd(ptr, user_ptr, val);
+
 	/* If page is not pinned, we can just update the entry
 	   directly */
 	if (!xen_page_pinned(ptr)) {
@@ -788,14 +828,12 @@ static void xen_pte_unlock(void *v)
 
 static void xen_do_pin(unsigned level, unsigned long pfn)
 {
-	struct mmuext_op *op;
-	struct multicall_space mcs;
+	struct mmuext_op op;
 
-	mcs = __xen_mc_entry(sizeof(*op));
-	op = mcs.args;
-	op->cmd = level;
-	op->arg1.mfn = pfn_to_mfn(pfn);
-	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+	op.cmd = level;
+	op.arg1.mfn = pfn_to_mfn(pfn);
+
+	xen_extend_mmuext_op(&op);
 }
 
 static int xen_pin_page(struct mm_struct *mm, struct page *page,
@@ -863,6 +901,8 @@ static int xen_pin_page(struct mm_struct *mm, struct page *page,
    read-only, and can be pinned. */
 static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
 {
+	trace_xen_mmu_pgd_pin(mm, pgd);
+
 	xen_mc_batch();
 
 	if (__xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT)) {
@@ -988,6 +1028,8 @@ static int xen_unpin_page(struct mm_struct *mm, struct page *page,
 /* Release a pagetables pages back as normal RW */
 static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd)
 {
+	trace_xen_mmu_pgd_unpin(mm, pgd);
+
 	xen_mc_batch();
 
 	xen_do_pin(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
@@ -1196,6 +1238,8 @@ static void xen_flush_tlb(void)
 	struct mmuext_op *op;
 	struct multicall_space mcs;
 
+	trace_xen_mmu_flush_tlb(0);
+
 	preempt_disable();
 
 	mcs = xen_mc_entry(sizeof(*op));
@@ -1214,6 +1258,8 @@ static void xen_flush_tlb_single(unsigned long addr)
 	struct mmuext_op *op;
 	struct multicall_space mcs;
 
+	trace_xen_mmu_flush_tlb_single(addr);
+
 	preempt_disable();
 
 	mcs = xen_mc_entry(sizeof(*op));
@@ -1240,6 +1286,8 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
 	} *args;
 	struct multicall_space mcs;
 
+	trace_xen_mmu_flush_tlb_others(cpus, mm, va);
+
 	if (cpumask_empty(cpus))
 		return;		/* nothing to do */
 
@@ -1275,10 +1323,11 @@ static void set_current_cr3(void *v)
 
 static void __xen_write_cr3(bool kernel, unsigned long cr3)
 {
-	struct mmuext_op *op;
-	struct multicall_space mcs;
+	struct mmuext_op op;
 	unsigned long mfn;
 
+	trace_xen_mmu_write_cr3(kernel, cr3);
+
 	if (cr3)
 		mfn = pfn_to_mfn(PFN_DOWN(cr3));
 	else
@@ -1286,13 +1335,10 @@ static void __xen_write_cr3(bool kernel, unsigned long cr3)
 
 	WARN_ON(mfn == 0 && kernel);
 
-	mcs = __xen_mc_entry(sizeof(*op));
+	op.cmd = kernel ? MMUEXT_NEW_BASEPTR : MMUEXT_NEW_USER_BASEPTR;
+	op.arg1.mfn = mfn;
 
-	op = mcs.args;
-	op->cmd = kernel ? MMUEXT_NEW_BASEPTR : MMUEXT_NEW_USER_BASEPTR;
-	op->arg1.mfn = mfn;
-
-	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+	xen_extend_mmuext_op(&op);
 
 	if (kernel) {
 		percpu_write(xen_cr3, cr3);
@@ -1451,19 +1497,52 @@ static void __init xen_release_pmd_init(unsigned long pfn)
 	make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
 }
 
+static inline void __pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
+{
+	struct multicall_space mcs;
+	struct mmuext_op *op;
+
+	mcs = __xen_mc_entry(sizeof(*op));
+	op = mcs.args;
+	op->cmd = cmd;
+	op->arg1.mfn = pfn_to_mfn(pfn);
+
+	MULTI_mmuext_op(mcs.mc, mcs.args, 1, NULL, DOMID_SELF);
+}
+
+static inline void __set_pfn_prot(unsigned long pfn, pgprot_t prot)
+{
+	struct multicall_space mcs;
+	unsigned long addr = (unsigned long)__va(pfn << PAGE_SHIFT);
+
+	mcs = __xen_mc_entry(0);
+	MULTI_update_va_mapping(mcs.mc, (unsigned long)addr,
+				pfn_pte(pfn, prot), 0);
+}
+
 /* This needs to make sure the new pte page is pinned iff its being
    attached to a pinned pagetable. */
-static void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned level)
+static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,
+				    unsigned level)
 {
-	struct page *page = pfn_to_page(pfn);
+	bool pinned = PagePinned(virt_to_page(mm->pgd));
+
+	trace_xen_mmu_alloc_ptpage(mm, pfn, level, pinned);
+
+	if (pinned) {
+		struct page *page = pfn_to_page(pfn);
 
-	if (PagePinned(virt_to_page(mm->pgd))) {
 		SetPagePinned(page);
 
 		if (!PageHighMem(page)) {
-			make_lowmem_page_readonly(__va(PFN_PHYS((unsigned long)pfn)));
+			xen_mc_batch();
+
+			__set_pfn_prot(pfn, PAGE_KERNEL_RO);
+
 			if (level == PT_PTE && USE_SPLIT_PTLOCKS)
-				pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
+				__pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
+
+			xen_mc_issue(PARAVIRT_LAZY_MMU);
 		} else {
 			/* make sure there are no stray mappings of
 			   this page */
@@ -1483,15 +1562,23 @@ static void xen_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
 }
 
 /* This should never happen until we're OK to use struct page */
-static void xen_release_ptpage(unsigned long pfn, unsigned level)
+static inline void xen_release_ptpage(unsigned long pfn, unsigned level)
 {
 	struct page *page = pfn_to_page(pfn);
+	bool pinned = PagePinned(page);
 
-	if (PagePinned(page)) {
+	trace_xen_mmu_release_ptpage(pfn, level, pinned);
+
+	if (pinned) {
 		if (!PageHighMem(page)) {
+			xen_mc_batch();
+
 			if (level == PT_PTE && USE_SPLIT_PTLOCKS)
-				pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
-			make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
+				__pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
+
+			__set_pfn_prot(pfn, PAGE_KERNEL);
+
+			xen_mc_issue(PARAVIRT_LAZY_MMU);
 		}
 		ClearPagePinned(page);
 	}
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index 1b2b73ff0a6e..0d82003e76ad 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -30,12 +30,13 @@
 
 #define MC_BATCH	32
 
-#define MC_DEBUG	1
+#define MC_DEBUG	0
 
 #define MC_ARGS		(MC_BATCH * 16)
 
 
 struct mc_buffer {
+	unsigned mcidx, argidx, cbidx;
 	struct multicall_entry entries[MC_BATCH];
 #if MC_DEBUG
 	struct multicall_entry debug[MC_BATCH];
@@ -46,85 +47,15 @@ struct mc_buffer {
 		void (*fn)(void *);
 		void *data;
 	} callbacks[MC_BATCH];
-	unsigned mcidx, argidx, cbidx;
 };
 
 static DEFINE_PER_CPU(struct mc_buffer, mc_buffer);
 DEFINE_PER_CPU(unsigned long, xen_mc_irq_flags);
 
-/* flush reasons 0- slots, 1- args, 2- callbacks */
-enum flush_reasons
-{
-	FL_SLOTS,
-	FL_ARGS,
-	FL_CALLBACKS,
-
-	FL_N_REASONS
-};
-
-#ifdef CONFIG_XEN_DEBUG_FS
-#define NHYPERCALLS	40		/* not really */
-
-static struct {
-	unsigned histo[MC_BATCH+1];
-
-	unsigned issued;
-	unsigned arg_total;
-	unsigned hypercalls;
-	unsigned histo_hypercalls[NHYPERCALLS];
-
-	unsigned flush[FL_N_REASONS];
-} mc_stats;
-
-static u8 zero_stats;
-
-static inline void check_zero(void)
-{
-	if (unlikely(zero_stats)) {
-		memset(&mc_stats, 0, sizeof(mc_stats));
-		zero_stats = 0;
-	}
-}
-
-static void mc_add_stats(const struct mc_buffer *mc)
-{
-	int i;
-
-	check_zero();
-
-	mc_stats.issued++;
-	mc_stats.hypercalls += mc->mcidx;
-	mc_stats.arg_total += mc->argidx;
-
-	mc_stats.histo[mc->mcidx]++;
-	for(i = 0; i < mc->mcidx; i++) {
-		unsigned op = mc->entries[i].op;
-		if (op < NHYPERCALLS)
-			mc_stats.histo_hypercalls[op]++;
-	}
-}
-
-static void mc_stats_flush(enum flush_reasons idx)
-{
-	check_zero();
-
-	mc_stats.flush[idx]++;
-}
-
-#else  /* !CONFIG_XEN_DEBUG_FS */
-
-static inline void mc_add_stats(const struct mc_buffer *mc)
-{
-}
-
-static inline void mc_stats_flush(enum flush_reasons idx)
-{
-}
-#endif	/* CONFIG_XEN_DEBUG_FS */
-
 void xen_mc_flush(void)
 {
 	struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+	struct multicall_entry *mc;
 	int ret = 0;
 	unsigned long flags;
 	int i;
@@ -135,9 +66,26 @@ void xen_mc_flush(void)
 	   something in the middle */
 	local_irq_save(flags);
 
-	mc_add_stats(b);
+	trace_xen_mc_flush(b->mcidx, b->argidx, b->cbidx);
 
-	if (b->mcidx) {
+	switch (b->mcidx) {
+	case 0:
+		/* no-op */
+		BUG_ON(b->argidx != 0);
+		break;
+
+	case 1:
+		/* Singleton multicall - bypass multicall machinery
+		   and just do the call directly. */
+		mc = &b->entries[0];
+
+		mc->result = privcmd_call(mc->op,
+					  mc->args[0], mc->args[1], mc->args[2], 
+					  mc->args[3], mc->args[4]);
+		ret = mc->result < 0;
+		break;
+
+	default:
 #if MC_DEBUG
 		memcpy(b->debug, b->entries,
 		       b->mcidx * sizeof(struct multicall_entry));
@@ -164,11 +112,10 @@ void xen_mc_flush(void)
 			}
 		}
 #endif
+	}
 
-		b->mcidx = 0;
-		b->argidx = 0;
-	} else
-		BUG_ON(b->argidx != 0);
+	b->mcidx = 0;
+	b->argidx = 0;
 
 	for (i = 0; i < b->cbidx; i++) {
 		struct callback *cb = &b->callbacks[i];
@@ -188,18 +135,21 @@ struct multicall_space __xen_mc_entry(size_t args)
 	struct multicall_space ret;
 	unsigned argidx = roundup(b->argidx, sizeof(u64));
 
+	trace_xen_mc_entry_alloc(args);
+
 	BUG_ON(preemptible());
 	BUG_ON(b->argidx >= MC_ARGS);
 
-	if (b->mcidx == MC_BATCH ||
-	    (argidx + args) >= MC_ARGS) {
-		mc_stats_flush(b->mcidx == MC_BATCH ? FL_SLOTS : FL_ARGS);
+	if (unlikely(b->mcidx == MC_BATCH ||
+		     (argidx + args) >= MC_ARGS)) {
+		trace_xen_mc_flush_reason((b->mcidx == MC_BATCH) ?
+					  XEN_MC_FL_BATCH : XEN_MC_FL_ARGS);
 		xen_mc_flush();
 		argidx = roundup(b->argidx, sizeof(u64));
 	}
 
 	ret.mc = &b->entries[b->mcidx];
-#ifdef MC_DEBUG
+#if MC_DEBUG
 	b->caller[b->mcidx] = __builtin_return_address(0);
 #endif
 	b->mcidx++;
@@ -218,20 +168,25 @@ struct multicall_space xen_mc_extend_args(unsigned long op, size_t size)
 	BUG_ON(preemptible());
 	BUG_ON(b->argidx >= MC_ARGS);
 
-	if (b->mcidx == 0)
-		return ret;
+	if (unlikely(b->mcidx == 0 ||
+		     b->entries[b->mcidx - 1].op != op)) {
+		trace_xen_mc_extend_args(op, size, XEN_MC_XE_BAD_OP);
+		goto out;
+	}
 
-	if (b->entries[b->mcidx - 1].op != op)
-		return ret;
-
-	if ((b->argidx + size) >= MC_ARGS)
-		return ret;
+	if (unlikely((b->argidx + size) >= MC_ARGS)) {
+		trace_xen_mc_extend_args(op, size, XEN_MC_XE_NO_SPACE);
+		goto out;
+	}
 
 	ret.mc = &b->entries[b->mcidx - 1];
 	ret.args = &b->args[b->argidx];
 	b->argidx += size;
 
 	BUG_ON(b->argidx >= MC_ARGS);
+
+	trace_xen_mc_extend_args(op, size, XEN_MC_XE_OK);
+out:
 	return ret;
 }
 
@@ -241,43 +196,13 @@ void xen_mc_callback(void (*fn)(void *), void *data)
 	struct callback *cb;
 
 	if (b->cbidx == MC_BATCH) {
-		mc_stats_flush(FL_CALLBACKS);
+		trace_xen_mc_flush_reason(XEN_MC_FL_CALLBACK);
 		xen_mc_flush();
 	}
 
+	trace_xen_mc_callback(fn, data);
+
 	cb = &b->callbacks[b->cbidx++];
 	cb->fn = fn;
 	cb->data = data;
 }
-
-#ifdef CONFIG_XEN_DEBUG_FS
-
-static struct dentry *d_mc_debug;
-
-static int __init xen_mc_debugfs(void)
-{
-	struct dentry *d_xen = xen_init_debugfs();
-
-	if (d_xen == NULL)
-		return -ENOMEM;
-
-	d_mc_debug = debugfs_create_dir("multicalls", d_xen);
-
-	debugfs_create_u8("zero_stats", 0644, d_mc_debug, &zero_stats);
-
-	debugfs_create_u32("batches", 0444, d_mc_debug, &mc_stats.issued);
-	debugfs_create_u32("hypercalls", 0444, d_mc_debug, &mc_stats.hypercalls);
-	debugfs_create_u32("arg_total", 0444, d_mc_debug, &mc_stats.arg_total);
-
-	xen_debugfs_create_u32_array("batch_histo", 0444, d_mc_debug,
-				     mc_stats.histo, MC_BATCH);
-	xen_debugfs_create_u32_array("hypercall_histo", 0444, d_mc_debug,
-				     mc_stats.histo_hypercalls, NHYPERCALLS);
-	xen_debugfs_create_u32_array("flush_reasons", 0444, d_mc_debug,
-				     mc_stats.flush, FL_N_REASONS);
-
-	return 0;
-}
-fs_initcall(xen_mc_debugfs);
-
-#endif	/* CONFIG_XEN_DEBUG_FS */
diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h
index 4ec8035e3216..dee79b78a90f 100644
--- a/arch/x86/xen/multicalls.h
+++ b/arch/x86/xen/multicalls.h
@@ -1,6 +1,8 @@
 #ifndef _XEN_MULTICALLS_H
 #define _XEN_MULTICALLS_H
 
+#include <trace/events/xen.h>
+
 #include "xen-ops.h"
 
 /* Multicalls */
@@ -20,8 +22,10 @@ DECLARE_PER_CPU(unsigned long, xen_mc_irq_flags);
 static inline void xen_mc_batch(void)
 {
 	unsigned long flags;
+
 	/* need to disable interrupts until this entry is complete */
 	local_irq_save(flags);
+	trace_xen_mc_batch(paravirt_get_lazy_mode());
 	__this_cpu_write(xen_mc_irq_flags, flags);
 }
 
@@ -37,6 +41,8 @@ void xen_mc_flush(void);
 /* Issue a multicall if we're not in a lazy mode */
 static inline void xen_mc_issue(unsigned mode)
 {
+	trace_xen_mc_issue(mode);
+
 	if ((paravirt_get_lazy_mode() & mode) == 0)
 		xen_mc_flush();
 
diff --git a/arch/x86/xen/trace.c b/arch/x86/xen/trace.c
new file mode 100644
index 000000000000..734beba2a08c
--- /dev/null
+++ b/arch/x86/xen/trace.c
@@ -0,0 +1,61 @@
+#include <linux/ftrace.h>
+
+#define N(x)	[__HYPERVISOR_##x] = "("#x")"
+static const char *xen_hypercall_names[] = {
+	N(set_trap_table),
+	N(mmu_update),
+	N(set_gdt),
+	N(stack_switch),
+	N(set_callbacks),
+	N(fpu_taskswitch),
+	N(sched_op_compat),
+	N(dom0_op),
+	N(set_debugreg),
+	N(get_debugreg),
+	N(update_descriptor),
+	N(memory_op),
+	N(multicall),
+	N(update_va_mapping),
+	N(set_timer_op),
+	N(event_channel_op_compat),
+	N(xen_version),
+	N(console_io),
+	N(physdev_op_compat),
+	N(grant_table_op),
+	N(vm_assist),
+	N(update_va_mapping_otherdomain),
+	N(iret),
+	N(vcpu_op),
+	N(set_segment_base),
+	N(mmuext_op),
+	N(acm_op),
+	N(nmi_op),
+	N(sched_op),
+	N(callback_op),
+	N(xenoprof_op),
+	N(event_channel_op),
+	N(physdev_op),
+	N(hvm_op),
+
+/* Architecture-specific hypercall definitions. */
+	N(arch_0),
+	N(arch_1),
+	N(arch_2),
+	N(arch_3),
+	N(arch_4),
+	N(arch_5),
+	N(arch_6),
+	N(arch_7),
+};
+#undef N
+
+static const char *xen_hypercall_name(unsigned op)
+{
+	if (op < ARRAY_SIZE(xen_hypercall_names) && xen_hypercall_names[op] != NULL)
+		return xen_hypercall_names[op];
+
+	return "";
+}
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/xen.h>
diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h
new file mode 100644
index 000000000000..44d8decee09e
--- /dev/null
+++ b/include/trace/events/xen.h
@@ -0,0 +1,504 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM xen
+
+#if !defined(_TRACE_XEN_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_XEN_H
+
+#include <linux/tracepoint.h>
+#include <asm/paravirt_types.h>
+#include <asm/xen/trace_types.h>
+
+/* Multicalls */
+DECLARE_EVENT_CLASS(xen_mc__batch,
+	    TP_PROTO(enum paravirt_lazy_mode mode),
+	    TP_ARGS(mode),
+	    TP_STRUCT__entry(
+		    __field(enum paravirt_lazy_mode, mode)
+		    ),
+	    TP_fast_assign(__entry->mode = mode),
+	    TP_printk("start batch LAZY_%s",
+		      (__entry->mode == PARAVIRT_LAZY_MMU) ? "MMU" :
+		      (__entry->mode == PARAVIRT_LAZY_CPU) ? "CPU" : "NONE")
+	);
+#define DEFINE_XEN_MC_BATCH(name)			\
+	DEFINE_EVENT(xen_mc__batch, name,		\
+		TP_PROTO(enum paravirt_lazy_mode mode),	\
+		     TP_ARGS(mode))
+
+DEFINE_XEN_MC_BATCH(xen_mc_batch);
+DEFINE_XEN_MC_BATCH(xen_mc_issue);
+
+TRACE_EVENT(xen_mc_entry,
+	    TP_PROTO(struct multicall_entry *mc, unsigned nargs),
+	    TP_ARGS(mc, nargs),
+	    TP_STRUCT__entry(
+		    __field(unsigned int, op)
+		    __field(unsigned int, nargs)
+		    __array(unsigned long, args, 6)
+		    ),
+	    TP_fast_assign(__entry->op = mc->op;
+			   __entry->nargs = nargs;
+			   memcpy(__entry->args, mc->args, sizeof(unsigned long) * nargs);
+			   memset(__entry->args + nargs, 0, sizeof(unsigned long) * (6 - nargs));
+		    ),
+	    TP_printk("op %u%s args [%lx, %lx, %lx, %lx, %lx, %lx]",
+		      __entry->op, xen_hypercall_name(__entry->op),
+		      __entry->args[0], __entry->args[1], __entry->args[2],
+		      __entry->args[3], __entry->args[4], __entry->args[5])
+	);
+
+TRACE_EVENT(xen_mc_entry_alloc,
+	    TP_PROTO(size_t args),
+	    TP_ARGS(args),
+	    TP_STRUCT__entry(
+		    __field(size_t, args)
+		    ),
+	    TP_fast_assign(__entry->args = args),
+	    TP_printk("alloc entry %zu arg bytes", __entry->args)
+	);
+
+TRACE_EVENT(xen_mc_callback,
+	    TP_PROTO(xen_mc_callback_fn_t fn, void *data),
+	    TP_ARGS(fn, data),
+	    TP_STRUCT__entry(
+		    __field(xen_mc_callback_fn_t, fn)
+		    __field(void *, data)
+		    ),
+	    TP_fast_assign(
+		    __entry->fn = fn;
+		    __entry->data = data;
+		    ),
+	    TP_printk("callback %pf, data %p",
+		      __entry->fn, __entry->data)
+	);
+
+TRACE_EVENT(xen_mc_flush_reason,
+	    TP_PROTO(enum xen_mc_flush_reason reason),
+	    TP_ARGS(reason),
+	    TP_STRUCT__entry(
+		    __field(enum xen_mc_flush_reason, reason)
+		    ),
+	    TP_fast_assign(__entry->reason = reason),
+	    TP_printk("flush reason %s",
+		      (__entry->reason == XEN_MC_FL_NONE) ? "NONE" :
+		      (__entry->reason == XEN_MC_FL_BATCH) ? "BATCH" :
+		      (__entry->reason == XEN_MC_FL_ARGS) ? "ARGS" :
+		      (__entry->reason == XEN_MC_FL_CALLBACK) ? "CALLBACK" : "??")
+	);
+
+TRACE_EVENT(xen_mc_flush,
+	    TP_PROTO(unsigned mcidx, unsigned argidx, unsigned cbidx),
+	    TP_ARGS(mcidx, argidx, cbidx),
+	    TP_STRUCT__entry(
+		    __field(unsigned, mcidx)
+		    __field(unsigned, argidx)
+		    __field(unsigned, cbidx)
+		    ),
+	    TP_fast_assign(__entry->mcidx = mcidx;
+			   __entry->argidx = argidx;
+			   __entry->cbidx = cbidx),
+	    TP_printk("flushing %u hypercalls, %u arg bytes, %u callbacks",
+		      __entry->mcidx, __entry->argidx, __entry->cbidx)
+	);
+
+TRACE_EVENT(xen_mc_extend_args,
+	    TP_PROTO(unsigned long op, size_t args, enum xen_mc_extend_args res),
+	    TP_ARGS(op, args, res),
+	    TP_STRUCT__entry(
+		    __field(unsigned int, op)
+		    __field(size_t, args)
+		    __field(enum xen_mc_extend_args, res)
+		    ),
+	    TP_fast_assign(__entry->op = op;
+			   __entry->args = args;
+			   __entry->res = res),
+	    TP_printk("extending op %u%s by %zu bytes res %s",
+		      __entry->op, xen_hypercall_name(__entry->op),
+		      __entry->args,
+		      __entry->res == XEN_MC_XE_OK ? "OK" :
+		      __entry->res == XEN_MC_XE_BAD_OP ? "BAD_OP" :
+		      __entry->res == XEN_MC_XE_NO_SPACE ? "NO_SPACE" : "???")
+	);
+
+/* mmu */
+DECLARE_EVENT_CLASS(xen_mmu__set_pte,
+	    TP_PROTO(pte_t *ptep, pte_t pteval),
+	    TP_ARGS(ptep, pteval),
+	    TP_STRUCT__entry(
+		    __field(pte_t *, ptep)
+		    __field(pteval_t, pteval)
+		    ),
+	    TP_fast_assign(__entry->ptep = ptep;
+			   __entry->pteval = pteval.pte),
+	    TP_printk("ptep %p pteval %0*llx (raw %0*llx)",
+		      __entry->ptep,
+		      (int)sizeof(pteval_t) * 2, (unsigned long long)pte_val(native_make_pte(__entry->pteval)),
+		      (int)sizeof(pteval_t) * 2, (unsigned long long)__entry->pteval)
+	);
+
+#define DEFINE_XEN_MMU_SET_PTE(name)				\
+	DEFINE_EVENT(xen_mmu__set_pte, name,			\
+		     TP_PROTO(pte_t *ptep, pte_t pteval),	\
+		     TP_ARGS(ptep, pteval))
+
+DEFINE_XEN_MMU_SET_PTE(xen_mmu_set_pte);
+DEFINE_XEN_MMU_SET_PTE(xen_mmu_set_pte_atomic);
+
+TRACE_EVENT(xen_mmu_set_domain_pte,
+	    TP_PROTO(pte_t *ptep, pte_t pteval, unsigned domid),
+	    TP_ARGS(ptep, pteval, domid),
+	    TP_STRUCT__entry(
+		    __field(pte_t *, ptep)
+		    __field(pteval_t, pteval)
+		    __field(unsigned, domid)
+		    ),
+	    TP_fast_assign(__entry->ptep = ptep;
+			   __entry->pteval = pteval.pte;
+			   __entry->domid = domid),
+	    TP_printk("ptep %p pteval %0*llx (raw %0*llx) domid %u",
+		      __entry->ptep,
+		      (int)sizeof(pteval_t) * 2, (unsigned long long)pte_val(native_make_pte(__entry->pteval)),
+		      (int)sizeof(pteval_t) * 2, (unsigned long long)__entry->pteval,
+		      __entry->domid)
+	);
+
+TRACE_EVENT(xen_mmu_set_pte_at,
+	    TP_PROTO(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t pteval),
+	    TP_ARGS(mm, addr, ptep, pteval),
+	    TP_STRUCT__entry(
+		    __field(struct mm_struct *, mm)
+		    __field(unsigned long, addr)
+		    __field(pte_t *, ptep)
+		    __field(pteval_t, pteval)
+		    ),
+	    TP_fast_assign(__entry->mm = mm;
+			   __entry->addr = addr;
+			   __entry->ptep = ptep;
+			   __entry->pteval = pteval.pte),
+	    TP_printk("mm %p addr %lx ptep %p pteval %0*llx (raw %0*llx)",
+		      __entry->mm, __entry->addr, __entry->ptep,
+		      (int)sizeof(pteval_t) * 2, (unsigned long long)pte_val(native_make_pte(__entry->pteval)),
+		      (int)sizeof(pteval_t) * 2, (unsigned long long)__entry->pteval)
+	);
+
+TRACE_EVENT(xen_mmu_pte_clear,
+	    TP_PROTO(struct mm_struct *mm, unsigned long addr, pte_t *ptep),
+	    TP_ARGS(mm, addr, ptep),
+	    TP_STRUCT__entry(
+		    __field(struct mm_struct *, mm)
+		    __field(unsigned long, addr)
+		    __field(pte_t *, ptep)
+		    ),
+	    TP_fast_assign(__entry->mm = mm;
+			   __entry->addr = addr;
+			   __entry->ptep = ptep),
+	    TP_printk("mm %p addr %lx ptep %p",
+		      __entry->mm, __entry->addr, __entry->ptep)
+	);
+
+TRACE_EVENT(xen_mmu_set_pmd,
+	    TP_PROTO(pmd_t *pmdp, pmd_t pmdval),
+	    TP_ARGS(pmdp, pmdval),
+	    TP_STRUCT__entry(
+		    __field(pmd_t *, pmdp)
+		    __field(pmdval_t, pmdval)
+		    ),
+	    TP_fast_assign(__entry->pmdp = pmdp;
+			   __entry->pmdval = pmdval.pmd),
+	    TP_printk("pmdp %p pmdval %0*llx (raw %0*llx)",
+		      __entry->pmdp,
+		      (int)sizeof(pmdval_t) * 2, (unsigned long long)pmd_val(native_make_pmd(__entry->pmdval)),
+		      (int)sizeof(pmdval_t) * 2, (unsigned long long)__entry->pmdval)
+	);
+
+TRACE_EVENT(xen_mmu_pmd_clear,
+	    TP_PROTO(pmd_t *pmdp),
+	    TP_ARGS(pmdp),
+	    TP_STRUCT__entry(
+		    __field(pmd_t *, pmdp)
+		    ),
+	    TP_fast_assign(__entry->pmdp = pmdp),
+	    TP_printk("pmdp %p", __entry->pmdp)
+	);
+
+#if PAGETABLE_LEVELS >= 4
+
+TRACE_EVENT(xen_mmu_set_pud,
+	    TP_PROTO(pud_t *pudp, pud_t pudval),
+	    TP_ARGS(pudp, pudval),
+	    TP_STRUCT__entry(
+		    __field(pud_t *, pudp)
+		    __field(pudval_t, pudval)
+		    ),
+	    TP_fast_assign(__entry->pudp = pudp;
+			   __entry->pudval = native_pud_val(pudval)),
+	    TP_printk("pudp %p pudval %0*llx (raw %0*llx)",
+		      __entry->pudp,
+		      (int)sizeof(pudval_t) * 2, (unsigned long long)pud_val(native_make_pud(__entry->pudval)),
+		      (int)sizeof(pudval_t) * 2, (unsigned long long)__entry->pudval)
+	);
+
+TRACE_EVENT(xen_mmu_set_pgd,
+	    TP_PROTO(pgd_t *pgdp, pgd_t *user_pgdp, pgd_t pgdval),
+	    TP_ARGS(pgdp, user_pgdp, pgdval),
+	    TP_STRUCT__entry(
+		    __field(pgd_t *, pgdp)
+		    __field(pgd_t *, user_pgdp)
+		    __field(pgdval_t, pgdval)
+		    ),
+	    TP_fast_assign(__entry->pgdp = pgdp;
+			   __entry->user_pgdp = user_pgdp;
+			   __entry->pgdval = pgdval.pgd),
+	    TP_printk("pgdp %p user_pgdp %p pgdval %0*llx (raw %0*llx)",
+		      __entry->pgdp, __entry->user_pgdp,
+		      (int)sizeof(pgdval_t) * 2, (unsigned long long)pgd_val(native_make_pgd(__entry->pgdval)),
+		      (int)sizeof(pgdval_t) * 2, (unsigned long long)__entry->pgdval)
+	);
+
+TRACE_EVENT(xen_mmu_pud_clear,
+	    TP_PROTO(pud_t *pudp),
+	    TP_ARGS(pudp),
+	    TP_STRUCT__entry(
+		    __field(pud_t *, pudp)
+		    ),
+	    TP_fast_assign(__entry->pudp = pudp),
+	    TP_printk("pudp %p", __entry->pudp)
+	);
+#else
+
+TRACE_EVENT(xen_mmu_set_pud,
+	    TP_PROTO(pud_t *pudp, pud_t pudval),
+	    TP_ARGS(pudp, pudval),
+	    TP_STRUCT__entry(
+		    __field(pud_t *, pudp)
+		    __field(pudval_t, pudval)
+		    ),
+	    TP_fast_assign(__entry->pudp = pudp;
+			   __entry->pudval = native_pud_val(pudval)),
+	    TP_printk("pudp %p pudval %0*llx (raw %0*llx)",
+		      __entry->pudp,
+		      (int)sizeof(pudval_t) * 2, (unsigned long long)pgd_val(native_make_pgd(__entry->pudval)),
+		      (int)sizeof(pudval_t) * 2, (unsigned long long)__entry->pudval)
+	);
+
+#endif
+
+TRACE_EVENT(xen_mmu_pgd_clear,
+	    TP_PROTO(pgd_t *pgdp),
+	    TP_ARGS(pgdp),
+	    TP_STRUCT__entry(
+		    __field(pgd_t *, pgdp)
+		    ),
+	    TP_fast_assign(__entry->pgdp = pgdp),
+	    TP_printk("pgdp %p", __entry->pgdp)
+	);
+
+DECLARE_EVENT_CLASS(xen_mmu_ptep_modify_prot,
+	    TP_PROTO(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t pteval),
+	    TP_ARGS(mm, addr, ptep, pteval),
+	    TP_STRUCT__entry(
+		    __field(struct mm_struct *, mm)
+		    __field(unsigned long, addr)
+		    __field(pte_t *, ptep)
+		    __field(pteval_t, pteval)
+		    ),
+	    TP_fast_assign(__entry->mm = mm;
+			   __entry->addr = addr;
+			   __entry->ptep = ptep;
+			   __entry->pteval = pteval.pte),
+	    TP_printk("mm %p addr %lx ptep %p pteval %0*llx (raw %0*llx)",
+		      __entry->mm, __entry->addr, __entry->ptep,
+		      (int)sizeof(pteval_t) * 2, (unsigned long long)pte_val(native_make_pte(__entry->pteval)),
+		      (int)sizeof(pteval_t) * 2, (unsigned long long)__entry->pteval)
+	);
+#define DEFINE_XEN_MMU_PTEP_MODIFY_PROT(name)				\
+	DEFINE_EVENT(xen_mmu_ptep_modify_prot, name,			\
+		     TP_PROTO(struct mm_struct *mm, unsigned long addr,	\
+			      pte_t *ptep, pte_t pteval),		\
+		     TP_ARGS(mm, addr, ptep, pteval))
+
+DEFINE_XEN_MMU_PTEP_MODIFY_PROT(xen_mmu_ptep_modify_prot_start);
+DEFINE_XEN_MMU_PTEP_MODIFY_PROT(xen_mmu_ptep_modify_prot_commit);
+
+TRACE_EVENT(xen_mmu_alloc_ptpage,
+	    TP_PROTO(struct mm_struct *mm, unsigned long pfn, unsigned level, bool pinned),
+	    TP_ARGS(mm, pfn, level, pinned),
+	    TP_STRUCT__entry(
+		    __field(struct mm_struct *, mm)
+		    __field(unsigned long, pfn)
+		    __field(unsigned, level)
+		    __field(bool, pinned)
+		    ),
+	    TP_fast_assign(__entry->mm = mm;
+			   __entry->pfn = pfn;
+			   __entry->level = level;
+			   __entry->pinned = pinned),
+	    TP_printk("mm %p  pfn %lx  level %d  %spinned",
+		      __entry->mm, __entry->pfn, __entry->level,
+		      __entry->pinned ? "" : "un")
+	);
+
+TRACE_EVENT(xen_mmu_release_ptpage,
+	    TP_PROTO(unsigned long pfn, unsigned level, bool pinned),
+	    TP_ARGS(pfn, level, pinned),
+	    TP_STRUCT__entry(
+		    __field(unsigned long, pfn)
+		    __field(unsigned, level)
+		    __field(bool, pinned)
+		    ),
+	    TP_fast_assign(__entry->pfn = pfn;
+			   __entry->level = level;
+			   __entry->pinned = pinned),
+	    TP_printk("pfn %lx  level %d  %spinned",
+		      __entry->pfn, __entry->level,
+		      __entry->pinned ? "" : "un")
+	);
+
+DECLARE_EVENT_CLASS(xen_mmu_pgd,
+	    TP_PROTO(struct mm_struct *mm, pgd_t *pgd),
+	    TP_ARGS(mm, pgd),
+	    TP_STRUCT__entry(
+		    __field(struct mm_struct *, mm)
+		    __field(pgd_t *, pgd)
+		    ),
+	    TP_fast_assign(__entry->mm = mm;
+			   __entry->pgd = pgd),
+	    TP_printk("mm %p pgd %p", __entry->mm, __entry->pgd)
+	);
+#define DEFINE_XEN_MMU_PGD_EVENT(name)				\
+	DEFINE_EVENT(xen_mmu_pgd, name,				\
+		TP_PROTO(struct mm_struct *mm, pgd_t *pgd),	\
+		     TP_ARGS(mm, pgd))
+
+DEFINE_XEN_MMU_PGD_EVENT(xen_mmu_pgd_pin);
+DEFINE_XEN_MMU_PGD_EVENT(xen_mmu_pgd_unpin);
+
+TRACE_EVENT(xen_mmu_flush_tlb,
+	    TP_PROTO(int x),
+	    TP_ARGS(x),
+	    TP_STRUCT__entry(__array(char, x, 0)),
+	    TP_fast_assign((void)x),
+	    TP_printk("%s", "")
+	);
+
+TRACE_EVENT(xen_mmu_flush_tlb_single,
+	    TP_PROTO(unsigned long addr),
+	    TP_ARGS(addr),
+	    TP_STRUCT__entry(
+		    __field(unsigned long, addr)
+		    ),
+	    TP_fast_assign(__entry->addr = addr),
+	    TP_printk("addr %lx", __entry->addr)
+	);
+
+TRACE_EVENT(xen_mmu_flush_tlb_others,
+	    TP_PROTO(const struct cpumask *cpus, struct mm_struct *mm,
+		     unsigned long addr),
+	    TP_ARGS(cpus, mm, addr),
+	    TP_STRUCT__entry(
+		    __field(unsigned, ncpus)
+		    __field(struct mm_struct *, mm)
+		    __field(unsigned long, addr)
+		    ),
+	    TP_fast_assign(__entry->ncpus = cpumask_weight(cpus);
+			   __entry->mm = mm;
+			   __entry->addr = addr),
+	    TP_printk("ncpus %d mm %p addr %lx",
+		      __entry->ncpus, __entry->mm, __entry->addr)
+	);
+
+TRACE_EVENT(xen_mmu_write_cr3,
+	    TP_PROTO(bool kernel, unsigned long cr3),
+	    TP_ARGS(kernel, cr3),
+	    TP_STRUCT__entry(
+		    __field(bool, kernel)
+		    __field(unsigned long, cr3)
+		    ),
+	    TP_fast_assign(__entry->kernel = kernel;
+			   __entry->cr3 = cr3),
+	    TP_printk("%s cr3 %lx",
+		      __entry->kernel ? "kernel" : "user", __entry->cr3)
+	);
+
+
+/* CPU */
+TRACE_EVENT(xen_cpu_write_ldt_entry,
+	    TP_PROTO(struct desc_struct *dt, int entrynum, u64 desc),
+	    TP_ARGS(dt, entrynum, desc),
+	    TP_STRUCT__entry(
+		    __field(struct desc_struct *, dt)
+		    __field(int, entrynum)
+		    __field(u64, desc)
+		    ),
+	    TP_fast_assign(__entry->dt = dt;
+			   __entry->entrynum = entrynum;
+			   __entry->desc = desc;
+		    ),
+	    TP_printk("dt %p  entrynum %d  entry %016llx",
+		      __entry->dt, __entry->entrynum,
+		      (unsigned long long)__entry->desc)
+	);
+
+TRACE_EVENT(xen_cpu_write_idt_entry,
+	    TP_PROTO(gate_desc *dt, int entrynum, const gate_desc *ent),
+	    TP_ARGS(dt, entrynum, ent),
+	    TP_STRUCT__entry(
+		    __field(gate_desc *, dt)
+		    __field(int, entrynum)
+		    ),
+	    TP_fast_assign(__entry->dt = dt;
+			   __entry->entrynum = entrynum;
+		    ),
+	    TP_printk("dt %p  entrynum %d",
+		      __entry->dt, __entry->entrynum)
+	);
+
+TRACE_EVENT(xen_cpu_load_idt,
+	    TP_PROTO(const struct desc_ptr *desc),
+	    TP_ARGS(desc),
+	    TP_STRUCT__entry(
+		    __field(unsigned long, addr)
+		    ),
+	    TP_fast_assign(__entry->addr = desc->address),
+	    TP_printk("addr %lx", __entry->addr)
+	);
+
+TRACE_EVENT(xen_cpu_write_gdt_entry,
+	    TP_PROTO(struct desc_struct *dt, int entrynum, const void *desc, int type),
+	    TP_ARGS(dt, entrynum, desc, type),
+	    TP_STRUCT__entry(
+		    __field(u64, desc)
+		    __field(struct desc_struct *, dt)
+		    __field(int, entrynum)
+		    __field(int, type)
+		    ),
+	    TP_fast_assign(__entry->dt = dt;
+			   __entry->entrynum = entrynum;
+			   __entry->desc = *(u64 *)desc;
+			   __entry->type = type;
+		    ),
+	    TP_printk("dt %p  entrynum %d  type %d  desc %016llx",
+		      __entry->dt, __entry->entrynum, __entry->type,
+		      (unsigned long long)__entry->desc)
+	);
+
+TRACE_EVENT(xen_cpu_set_ldt,
+	    TP_PROTO(const void *addr, unsigned entries),
+	    TP_ARGS(addr, entries),
+	    TP_STRUCT__entry(
+		    __field(const void *, addr)
+		    __field(unsigned, entries)
+		    ),
+	    TP_fast_assign(__entry->addr = addr;
+			   __entry->entries = entries),
+	    TP_printk("addr %p  entries %u",
+		      __entry->addr, __entry->entries)
+	);
+
+
+#endif /*  _TRACE_XEN_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>