13 files changed, 409 insertions, 176 deletions
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 17c565de3d6..add2c2d729c 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -15,8 +15,10 @@ obj-y		:= enlighten.o setup.o multicalls.o mmu.o irq.o \
                        grant-table.o suspend.o platform-pci-unplug.o \
                        p2m.o
+obj-$(CONFIG_EVENT_TRACING) += trace.o
 obj-$(CONFIG_SMP)               += smp.o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
 obj-$(CONFIG_XEN_DEBUG_FS)      += debugfs.o
+obj-$(CONFIG_XEN_DOM0)          += vga.o
 obj-$(CONFIG_SWIOTLB_XEN)       += pci-swiotlb-xen.o
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 5525163a039..46c8069ae98 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -77,8 +77,8 @@ EXPORT_SYMBOL_GPL(xen_domain_type);
 unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START;
 EXPORT_SYMBOL(machine_to_phys_mapping);
-unsigned int   machine_to_phys_order;
+unsigned long  machine_to_phys_nr;
-EXPORT_SYMBOL(machine_to_phys_order);
+EXPORT_SYMBOL(machine_to_phys_nr);
 struct start_info *xen_start_info;
 EXPORT_SYMBOL_GPL(xen_start_info);
@@ -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);
 }
@@ -937,6 +951,10 @@ static const struct pv_info xen_info __initconst = {
        .paravirt_enabled = 1,
        .shared_kernel_pmd = 0,
+#ifdef CONFIG_X86_64
+        .extra_user_64bit_cs = FLAT_USER_CS64,
+#endif
        .name = "Xen",
 };
@@ -1248,6 +1266,14 @@ asmlinkage void __init xen_start_kernel(void)
                if (pci_xen)
                        x86_init.pci.arch_init = pci_xen_init;
        } else {
+                const struct dom0_vga_console_info *info =
+                        (void *)((char *)xen_start_info +
+                                 xen_start_info->console.dom0.info_off);
+                xen_init_vga(info, xen_start_info->console.dom0.info_size);
+                xen_start_info->console.domU.mfn = 0;
+                xen_start_info->console.domU.evtchn = 0;
                /* Make sure ACS will be enabled */
                pci_request_acs();
        }
@@ -1329,7 +1355,7 @@ static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self,
        int cpu = (long)hcpu;
        switch (action) {
        case CPU_UP_PREPARE:
-                per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
+                xen_vcpu_setup(cpu);
                if (xen_have_vector_callback)
                        xen_init_lock_cpu(cpu);
                break;
@@ -1359,7 +1385,6 @@ static void __init xen_hvm_guest_init(void)
        xen_hvm_smp_init();
        register_cpu_notifier(&xen_hvm_cpu_notifier);
        xen_unplug_emulated_devices();
-        have_vcpu_info_placement = 0;
        x86_init.irqs.intr_init = xen_init_IRQ;
        xen_hvm_init_time_ops();
        xen_hvm_init_mmu_ops();
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 0ccccb67a99..3dd53f997b1 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 mmuext_op op;
-        struct multicall_space mcs;
-        mcs = __xen_mc_entry(sizeof(*op));
+        op.cmd = level;
-        op = mcs.args;
+        op.arg1.mfn = pfn_to_mfn(pfn);
-        op->cmd = level;
-        op->arg1.mfn = pfn_to_mfn(pfn);
+        xen_extend_mmuext_op(&op);
-        MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 }
 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 mmuext_op op;
-        struct multicall_space mcs;
        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);
+                                __pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
-                        make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
+                        __set_pfn_prot(pfn, PAGE_KERNEL);
+                        xen_mc_issue(PARAVIRT_LAZY_MMU);
                }
                ClearPagePinned(page);
        }
@@ -1626,15 +1713,17 @@ static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
 void __init xen_setup_machphys_mapping(void)
 {
        struct xen_machphys_mapping mapping;
-        unsigned long machine_to_phys_nr_ents;
        if (HYPERVISOR_memory_op(XENMEM_machphys_mapping, &mapping) == 0) {
                machine_to_phys_mapping = (unsigned long *)mapping.v_start;
-                machine_to_phys_nr_ents = mapping.max_mfn + 1;
+                machine_to_phys_nr = mapping.max_mfn + 1;
        } else {
-                machine_to_phys_nr_ents = MACH2PHYS_NR_ENTRIES;
+                machine_to_phys_nr = MACH2PHYS_NR_ENTRIES;
        }
-        machine_to_phys_order = fls(machine_to_phys_nr_ents - 1);
+#ifdef CONFIG_X86_32
+        WARN_ON((machine_to_phys_mapping + (machine_to_phys_nr - 1))
+                < machine_to_phys_mapping);
+#endif
 }
 #ifdef CONFIG_X86_64
@@ -1829,6 +1918,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 # endif
 #else
        case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE:
+        case VVAR_PAGE:
 #endif
        case FIX_TEXT_POKE0:
        case FIX_TEXT_POKE1:
@@ -1869,7 +1959,8 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #ifdef CONFIG_X86_64
        /* Replicate changes to map the vsyscall page into the user
           pagetable vsyscall mapping. */
-        if (idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) {
+        if ((idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) ||
+            idx == VVAR_PAGE) {
                unsigned long vaddr = __fix_to_virt(idx);
                set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte);
        }
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index 1b2b73ff0a6..0d82003e76a 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);
+        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;
-        if (b->mcidx) {
+        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->mcidx = 0;
-                b->argidx = 0;
+        b->argidx = 0;
-        } else
-                BUG_ON(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 ||
+        if (unlikely(b->mcidx == MC_BATCH ||
-            (argidx + args) >= MC_ARGS) {
+                     (argidx + args) >= MC_ARGS)) {
-                mc_stats_flush(b->mcidx == MC_BATCH ? FL_SLOTS : FL_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)
+        if (unlikely(b->mcidx == 0 ||
-                return ret;
+                     b->entries[b->mcidx - 1].op != op)) {
+                trace_xen_mc_extend_args(op, size, XEN_MC_XE_BAD_OP);
-        if (b->entries[b->mcidx - 1].op != op)
+                goto out;
-                return ret;
+        }
-        if ((b->argidx + size) >= MC_ARGS)
+        if (unlikely((b->argidx + size) >= MC_ARGS)) {
-                return ret;
+                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 4ec8035e321..dee79b78a90 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/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c
index 25c52f94a27..ffcf2615640 100644
--- a/arch/x86/xen/platform-pci-unplug.c
+++ b/arch/x86/xen/platform-pci-unplug.c
@@ -35,7 +35,7 @@ EXPORT_SYMBOL_GPL(xen_platform_pci_unplug);
 #ifdef CONFIG_XEN_PVHVM
 static int xen_emul_unplug;
-static int __init check_platform_magic(void)
+static int check_platform_magic(void)
 {
        short magic;
        char protocol;
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 60aeeb56948..e1913024687 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -9,6 +9,7 @@
 #include <linux/mm.h>
 #include <linux/pm.h>
 #include <linux/memblock.h>
+#include <linux/cpuidle.h>
 #include <asm/elf.h>
 #include <asm/vdso.h>
@@ -92,8 +93,6 @@ static unsigned long __init xen_release_chunk(phys_addr_t start_addr,
        if (end <= start)
                return 0;
-        printk(KERN_INFO "xen_release_chunk: looking at area pfn %lx-%lx: ",
-               start, end);
        for(pfn = start; pfn < end; pfn++) {
                unsigned long mfn = pfn_to_mfn(pfn);
@@ -106,14 +105,14 @@ static unsigned long __init xen_release_chunk(phys_addr_t start_addr,
                ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
                                           &reservation);
-                WARN(ret != 1, "Failed to release memory %lx-%lx err=%d\n",
+                WARN(ret != 1, "Failed to release pfn %lx err=%d\n", pfn, ret);
-                     start, end, ret);
                if (ret == 1) {
                        __set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
                        len++;
                }
        }
-        printk(KERN_CONT "%ld pages freed\n", len);
+        printk(KERN_INFO "Freeing  %lx-%lx pfn range: %lu pages freed\n",
+               start, end, len);
        return len;
 }
@@ -139,7 +138,7 @@ static unsigned long __init xen_return_unused_memory(unsigned long max_pfn,
        if (last_end < max_addr)
                released += xen_release_chunk(last_end, max_addr);
-        printk(KERN_INFO "released %ld pages of unused memory\n", released);
+        printk(KERN_INFO "released %lu pages of unused memory\n", released);
        return released;
 }
@@ -185,6 +184,31 @@ static unsigned long __init xen_set_identity(const struct e820entry *list,
                                        PFN_UP(start_pci), PFN_DOWN(last));
        return identity;
 }
+static unsigned long __init xen_get_max_pages(void)
+{
+        unsigned long max_pages = MAX_DOMAIN_PAGES;
+        domid_t domid = DOMID_SELF;
+        int ret;
+        /*
+         * For the initial domain we use the maximum reservation as
+         * the maximum page.
+         *
+         * For guest domains the current maximum reservation reflects
+         * the current maximum rather than the static maximum. In this
+         * case the e820 map provided to us will cover the static
+         * maximum region.
+         */
+        if (xen_initial_domain()) {
+                ret = HYPERVISOR_memory_op(XENMEM_maximum_reservation, &domid);
+                if (ret > 0)
+                        max_pages = ret;
+        }
+        return min(max_pages, MAX_DOMAIN_PAGES);
+}
 /**
 * machine_specific_memory_setup - Hook for machine specific memory setup.
 **/
@@ -293,6 +317,14 @@ char * __init xen_memory_setup(void)
        sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+        extra_limit = xen_get_max_pages();
+        if (max_pfn + extra_pages > extra_limit) {
+                if (extra_limit > max_pfn)
+                        extra_pages = extra_limit - max_pfn;
+                else
+                        extra_pages = 0;
+        }
        extra_pages += xen_return_unused_memory(xen_start_info->nr_pages, &e820);
        /*
@@ -426,8 +458,8 @@ void __init xen_arch_setup(void)
 #ifdef CONFIG_X86_32
        boot_cpu_data.hlt_works_ok = 1;
 #endif
-        pm_idle = default_idle;
+        disable_cpuidle();
        boot_option_idle_override = IDLE_HALT;
+        WARN_ON(set_pm_idle_to_default());
        fiddle_vdso();
 }
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index b4533a86d7e..041d4fe9dfe 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -32,6 +32,7 @@
 #include <xen/page.h>
 #include <xen/events.h>
+#include <xen/hvc-console.h>
 #include "xen-ops.h"
 #include "mmu.h"
@@ -207,6 +208,15 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
        unsigned cpu;
        unsigned int i;
+        if (skip_ioapic_setup) {
+                char *m = (max_cpus == 0) ?
+                        "The nosmp parameter is incompatible with Xen; " \
+                        "use Xen dom0_max_vcpus=1 parameter" :
+                        "The noapic parameter is incompatible with Xen";
+                xen_raw_printk(m);
+                panic(m);
+        }
        xen_init_lock_cpu(0);
        smp_store_cpu_info(0);
@@ -521,10 +531,7 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
        native_smp_prepare_cpus(max_cpus);
        WARN_ON(xen_smp_intr_init(0));
-        if (!xen_have_vector_callback)
-                return;
        xen_init_lock_cpu(0);
-        xen_init_spinlocks();
 }
 static int __cpuinit xen_hvm_cpu_up(unsigned int cpu)
@@ -546,6 +553,8 @@ static void xen_hvm_cpu_die(unsigned int cpu)
 void __init xen_hvm_smp_init(void)
 {
+        if (!xen_have_vector_callback)
+                return;
        smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
        smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
        smp_ops.cpu_up = xen_hvm_cpu_up;
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 5158c505bef..163b4679556 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -168,9 +168,10 @@ cycle_t xen_clocksource_read(void)
        struct pvclock_vcpu_time_info *src;
        cycle_t ret;
-        src = &get_cpu_var(xen_vcpu)->time;
+        preempt_disable_notrace();
+        src = &__get_cpu_var(xen_vcpu)->time;
        ret = pvclock_clocksource_read(src);
-        put_cpu_var(xen_vcpu);
+        preempt_enable_notrace();
        return ret;
 }
diff --git a/arch/x86/xen/trace.c b/arch/x86/xen/trace.c
new file mode 100644
index 00000000000..520022d1a18
--- /dev/null
+++ b/arch/x86/xen/trace.c
@@ -0,0 +1,62 @@
+#include <linux/ftrace.h>
+#include <xen/interface/xen.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/arch/x86/xen/vga.c b/arch/x86/xen/vga.c
new file mode 100644
index 00000000000..1cd7f4d11e2
--- /dev/null
+++ b/arch/x86/xen/vga.c
@@ -0,0 +1,67 @@
+#include <linux/screen_info.h>
+#include <linux/init.h>
+#include <asm/bootparam.h>
+#include <asm/setup.h>
+#include <xen/interface/xen.h>
+#include "xen-ops.h"
+void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size)
+{
+        struct screen_info *screen_info = &boot_params.screen_info;
+        /* This is drawn from a dump from vgacon:startup in
+         * standard Linux. */
+        screen_info->orig_video_mode = 3;
+        screen_info->orig_video_isVGA = 1;
+        screen_info->orig_video_lines = 25;
+        screen_info->orig_video_cols = 80;
+        screen_info->orig_video_ega_bx = 3;
+        screen_info->orig_video_points = 16;
+        screen_info->orig_y = screen_info->orig_video_lines - 1;
+        switch (info->video_type) {
+        case XEN_VGATYPE_TEXT_MODE_3:
+                if (size < offsetof(struct dom0_vga_console_info, u.text_mode_3)
+                    + sizeof(info->u.text_mode_3))
+                        break;
+                screen_info->orig_video_lines = info->u.text_mode_3.rows;
+                screen_info->orig_video_cols = info->u.text_mode_3.columns;
+                screen_info->orig_x = info->u.text_mode_3.cursor_x;
+                screen_info->orig_y = info->u.text_mode_3.cursor_y;
+                screen_info->orig_video_points =
+                        info->u.text_mode_3.font_height;
+                break;
+        case XEN_VGATYPE_VESA_LFB:
+                if (size < offsetof(struct dom0_vga_console_info,
+                                    u.vesa_lfb.gbl_caps))
+                        break;
+                screen_info->orig_video_isVGA = VIDEO_TYPE_VLFB;
+                screen_info->lfb_width = info->u.vesa_lfb.width;
+                screen_info->lfb_height = info->u.vesa_lfb.height;
+                screen_info->lfb_depth = info->u.vesa_lfb.bits_per_pixel;
+                screen_info->lfb_base = info->u.vesa_lfb.lfb_base;
+                screen_info->lfb_size = info->u.vesa_lfb.lfb_size;
+                screen_info->lfb_linelength = info->u.vesa_lfb.bytes_per_line;
+                screen_info->red_size = info->u.vesa_lfb.red_size;
+                screen_info->red_pos = info->u.vesa_lfb.red_pos;
+                screen_info->green_size = info->u.vesa_lfb.green_size;
+                screen_info->green_pos = info->u.vesa_lfb.green_pos;
+                screen_info->blue_size = info->u.vesa_lfb.blue_size;
+                screen_info->blue_pos = info->u.vesa_lfb.blue_pos;
+                screen_info->rsvd_size = info->u.vesa_lfb.rsvd_size;
+                screen_info->rsvd_pos = info->u.vesa_lfb.rsvd_pos;
+                if (size >= offsetof(struct dom0_vga_console_info,
+                                     u.vesa_lfb.gbl_caps)
+                    + sizeof(info->u.vesa_lfb.gbl_caps))
+                        screen_info->capabilities = info->u.vesa_lfb.gbl_caps;
+                if (size >= offsetof(struct dom0_vga_console_info,
+                                     u.vesa_lfb.mode_attrs)
+                    + sizeof(info->u.vesa_lfb.mode_attrs))
+                        screen_info->vesa_attributes = info->u.vesa_lfb.mode_attrs;
+                break;
+        }
+}
diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S
index 22a2093b586..b040b0e518c 100644
--- a/arch/x86/xen/xen-asm_32.S
+++ b/arch/x86/xen/xen-asm_32.S
@@ -113,11 +113,13 @@ xen_iret_start_crit:
        /*
         * If there's something pending, mask events again so we can
-         * jump back into xen_hypervisor_callback
+         * jump back into xen_hypervisor_callback. Otherwise do not
+         * touch XEN_vcpu_info_mask.
         */
-        sete XEN_vcpu_info_mask(%eax)
+        jne 1f
+        movb $1, XEN_vcpu_info_mask(%eax)
-        popl %eax
+1:      popl %eax
        /*
         * From this point on the registers are restored and the stack
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 97dfdc8757b..b095739ccd4 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -88,6 +88,17 @@ static inline void xen_uninit_lock_cpu(int cpu)
 }
 #endif
+struct dom0_vga_console_info;
+#ifdef CONFIG_XEN_DOM0
+void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size);
+#else
+static inline void __init xen_init_vga(const struct dom0_vga_console_info *info,
+                                       size_t size)
+{
+}
+#endif
 /* Declare an asm function, along with symbols needed to make it
   inlineable */
 #define DECL_ASM(ret, name, ...)                \