14 files changed, 511 insertions, 201 deletions

diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 6c388e593bc8..c2cc99580871 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -12,3 +12,13 @@ config XEN
           This is the Linux Xen port.  Enabling this will allow the
           kernel to boot in a paravirtualized environment under the
           Xen hypervisor.
+
+config XEN_MAX_DOMAIN_MEMORY
+       int "Maximum allowed size of a domain in gigabytes"
+       default 8
+       depends on XEN
+       help
+         The pseudo-physical to machine address array is sized
+         according to the maximum possible memory size of a Xen
+         domain.  This array uses 1 page per gigabyte, so there's no
+         need to be too stingy here.
\ No newline at end of file
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 3d8df981d5fd..2ba2d1649131 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -1,4 +1,4 @@
 obj-y           := enlighten.o setup.o multicalls.o mmu.o \
-                        time.o manage.o xen-asm.o grant-table.o
+                        time.o xen-asm.o grant-table.o suspend.o
 
 obj-$(CONFIG_SMP)       += smp.o
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index f09c1c69c37a..bd74229081c3 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -75,13 +75,13 @@ DEFINE_PER_CPU(unsigned long, xen_current_cr3);	 /* actual vcpu cr3 */
 struct start_info *xen_start_info;
 EXPORT_SYMBOL_GPL(xen_start_info);
 
-static /* __initdata */ struct shared_info dummy_shared_info;
+struct shared_info xen_dummy_shared_info;
 
 /*
  * Point at some empty memory to start with. We map the real shared_info
  * page as soon as fixmap is up and running.
  */
-struct shared_info *HYPERVISOR_shared_info = (void *)&dummy_shared_info;
+struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info;
 
 /*
  * Flag to determine whether vcpu info placement is available on all
@@ -98,13 +98,13 @@ struct shared_info *HYPERVISOR_shared_info = (void *)&dummy_shared_info;
  */
 static int have_vcpu_info_placement = 1;
 
-static void __init xen_vcpu_setup(int cpu)
+static void xen_vcpu_setup(int cpu)
 {
         struct vcpu_register_vcpu_info info;
         int err;
         struct vcpu_info *vcpup;
 
-        BUG_ON(HYPERVISOR_shared_info == &dummy_shared_info);
+        BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
         per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
 
         if (!have_vcpu_info_placement)
@@ -136,11 +136,41 @@ static void __init xen_vcpu_setup(int cpu)
         }
 }
 
+/*
+ * On restore, set the vcpu placement up again.
+ * If it fails, then we're in a bad state, since
+ * we can't back out from using it...
+ */
+void xen_vcpu_restore(void)
+{
+        if (have_vcpu_info_placement) {
+                int cpu;
+
+                for_each_online_cpu(cpu) {
+                        bool other_cpu = (cpu != smp_processor_id());
+
+                        if (other_cpu &&
+                            HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL))
+                                BUG();
+
+                        xen_vcpu_setup(cpu);
+
+                        if (other_cpu &&
+                            HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL))
+                                BUG();
+                }
+
+                BUG_ON(!have_vcpu_info_placement);
+        }
+}
+
 static void __init xen_banner(void)
 {
         printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
                pv_info.name);
-        printk(KERN_INFO "Hypervisor signature: %s\n", xen_start_info->magic);
+        printk(KERN_INFO "Hypervisor signature: %s%s\n",
+               xen_start_info->magic,
+               xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
 }
 
 static void xen_cpuid(unsigned int *ax, unsigned int *bx,
@@ -235,13 +265,13 @@ static void xen_irq_enable(void)
 {
         struct vcpu_info *vcpu;
 
-        /* There's a one instruction preempt window here.  We need to
-           make sure we're don't switch CPUs between getting the vcpu
-           pointer and updating the mask. */
-        preempt_disable();
+        /* We don't need to worry about being preempted here, since
+           either a) interrupts are disabled, so no preemption, or b)
+           the caller is confused and is trying to re-enable interrupts
+           on an indeterminate processor. */
+
         vcpu = x86_read_percpu(xen_vcpu);
         vcpu->evtchn_upcall_mask = 0;
-        preempt_enable_no_resched();
 
         /* Doesn't matter if we get preempted here, because any
            pending event will get dealt with anyway. */
@@ -254,7 +284,7 @@ static void xen_irq_enable(void)
 static void xen_safe_halt(void)
 {
         /* Blocking includes an implicit local_irq_enable(). */
-        if (HYPERVISOR_sched_op(SCHEDOP_block, 0) != 0)
+        if (HYPERVISOR_sched_op(SCHEDOP_block, NULL) != 0)
                 BUG();
 }
 
@@ -607,6 +637,30 @@ static void xen_flush_tlb_others(const cpumask_t *cpus, struct mm_struct *mm,
         xen_mc_issue(PARAVIRT_LAZY_MMU);
 }
 
+static void xen_clts(void)
+{
+        struct multicall_space mcs;
+
+        mcs = xen_mc_entry(0);
+
+        MULTI_fpu_taskswitch(mcs.mc, 0);
+
+        xen_mc_issue(PARAVIRT_LAZY_CPU);
+}
+
+static void xen_write_cr0(unsigned long cr0)
+{
+        struct multicall_space mcs;
+
+        /* Only pay attention to cr0.TS; everything else is
+           ignored. */
+        mcs = xen_mc_entry(0);
+
+        MULTI_fpu_taskswitch(mcs.mc, (cr0 & X86_CR0_TS) != 0);
+
+        xen_mc_issue(PARAVIRT_LAZY_CPU);
+}
+
 static void xen_write_cr2(unsigned long cr2)
 {
         x86_read_percpu(xen_vcpu)->arch.cr2 = cr2;
@@ -624,8 +678,10 @@ static unsigned long xen_read_cr2_direct(void)
 
 static void xen_write_cr4(unsigned long cr4)
 {
-        /* Just ignore cr4 changes; Xen doesn't allow us to do
-           anything anyway. */
+        cr4 &= ~X86_CR4_PGE;
+        cr4 &= ~X86_CR4_PSE;
+
+        native_write_cr4(cr4);
 }
 
 static unsigned long xen_read_cr3(void)
@@ -831,7 +887,7 @@ static __init void xen_pagetable_setup_start(pgd_t *base)
                           PFN_DOWN(__pa(xen_start_info->pt_base)));
 }
 
-static __init void setup_shared_info(void)
+void xen_setup_shared_info(void)
 {
         if (!xen_feature(XENFEAT_auto_translated_physmap)) {
                 unsigned long addr = fix_to_virt(FIX_PARAVIRT_BOOTMAP);
@@ -854,6 +910,8 @@ static __init void setup_shared_info(void)
         /* In UP this is as good a place as any to set up shared info */
         xen_setup_vcpu_info_placement();
 #endif
+
+        xen_setup_mfn_list_list();
 }
 
 static __init void xen_pagetable_setup_done(pgd_t *base)
@@ -866,15 +924,23 @@ static __init void xen_pagetable_setup_done(pgd_t *base)
         pv_mmu_ops.release_pmd = xen_release_pmd;
         pv_mmu_ops.set_pte = xen_set_pte;
 
-        setup_shared_info();
+        xen_setup_shared_info();
 
         /* Actually pin the pagetable down, but we can't set PG_pinned
            yet because the page structures don't exist yet. */
         pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(base)));
 }
 
+static __init void xen_post_allocator_init(void)
+{
+        pv_mmu_ops.set_pmd = xen_set_pmd;
+        pv_mmu_ops.set_pud = xen_set_pud;
+
+        xen_mark_init_mm_pinned();
+}
+
 /* This is called once we have the cpu_possible_map */
-void __init xen_setup_vcpu_info_placement(void)
+void xen_setup_vcpu_info_placement(void)
 {
         int cpu;
 
@@ -960,7 +1026,7 @@ static const struct pv_init_ops xen_init_ops __initdata = {
         .banner = xen_banner,
         .memory_setup = xen_memory_setup,
         .arch_setup = xen_arch_setup,
-        .post_allocator_init = xen_mark_init_mm_pinned,
+        .post_allocator_init = xen_post_allocator_init,
 };
 
 static const struct pv_time_ops xen_time_ops __initdata = {
@@ -978,10 +1044,10 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = {
         .set_debugreg = xen_set_debugreg,
         .get_debugreg = xen_get_debugreg,
 
-        .clts = native_clts,
+        .clts = xen_clts,
 
         .read_cr0 = native_read_cr0,
-        .write_cr0 = native_write_cr0,
+        .write_cr0 = xen_write_cr0,
 
         .read_cr4 = native_read_cr4,
         .read_cr4_safe = native_read_cr4_safe,
@@ -1072,9 +1138,13 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 
         .set_pte = NULL,        /* see xen_pagetable_setup_* */
         .set_pte_at = xen_set_pte_at,
-        .set_pmd = xen_set_pmd,
+        .set_pmd = xen_set_pmd_hyper,
+
+        .ptep_modify_prot_start = __ptep_modify_prot_start,
+        .ptep_modify_prot_commit = __ptep_modify_prot_commit,
 
         .pte_val = xen_pte_val,
+        .pte_flags = native_pte_val,
         .pgd_val = xen_pgd_val,
 
         .make_pte = xen_make_pte,
@@ -1082,7 +1152,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 
         .set_pte_atomic = xen_set_pte_atomic,
         .set_pte_present = xen_set_pte_at,
-        .set_pud = xen_set_pud,
+        .set_pud = xen_set_pud_hyper,
         .pte_clear = xen_pte_clear,
         .pmd_clear = xen_pmd_clear,
 
@@ -1114,11 +1184,13 @@ static const struct smp_ops xen_smp_ops __initdata = {
 
 static void xen_reboot(int reason)
 {
+        struct sched_shutdown r = { .reason = reason };
+
 #ifdef CONFIG_SMP
         smp_send_stop();
 #endif
 
-        if (HYPERVISOR_sched_op(SCHEDOP_shutdown, reason))
+        if (HYPERVISOR_sched_op(SCHEDOP_shutdown, &r))
                 BUG();
 }
 
@@ -1173,6 +1245,8 @@ asmlinkage void __init xen_start_kernel(void)
 
         BUG_ON(memcmp(xen_start_info->magic, "xen-3", 5) != 0);
 
+        xen_setup_features();
+
         /* Install Xen paravirt ops */
         pv_info = xen_info;
         pv_init_ops = xen_init_ops;
@@ -1182,17 +1256,20 @@ asmlinkage void __init xen_start_kernel(void)
         pv_apic_ops = xen_apic_ops;
         pv_mmu_ops = xen_mmu_ops;
 
+        if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
+                pv_mmu_ops.ptep_modify_prot_start = xen_ptep_modify_prot_start;
+                pv_mmu_ops.ptep_modify_prot_commit = xen_ptep_modify_prot_commit;
+        }
+
         machine_ops = xen_machine_ops;
 
 #ifdef CONFIG_SMP
         smp_ops = xen_smp_ops;
 #endif
 
-        xen_setup_features();
-
         /* Get mfn list */
         if (!xen_feature(XENFEAT_auto_translated_physmap))
-                phys_to_machine_mapping = (unsigned long *)xen_start_info->mfn_list;
+                xen_build_dynamic_phys_to_machine();
 
         pgd = (pgd_t *)xen_start_info->pt_base;
 
@@ -1232,8 +1309,11 @@ asmlinkage void __init xen_start_kernel(void)
                 ? __pa(xen_start_info->mod_start) : 0;
         boot_params.hdr.ramdisk_size = xen_start_info->mod_len;
 
-        if (!is_initial_xendomain())
+        if (!is_initial_xendomain()) {
+                add_preferred_console("xenboot", 0, NULL);
+                add_preferred_console("tty", 0, NULL);
                 add_preferred_console("hvc", 0, NULL);
+        }
 
         /* Start the world */
         start_kernel();
diff --git a/arch/x86/xen/manage.c b/arch/x86/xen/manage.c
deleted file mode 100644
index aa7af9e6abc0..000000000000
--- a/arch/x86/xen/manage.c
+++ /dev/null
@@ -1,143 +0,0 @@
-/*
- * Handle extern requests for shutdown, reboot and sysrq
- */
-#include <linux/kernel.h>
-#include <linux/err.h>
-#include <linux/reboot.h>
-#include <linux/sysrq.h>
-
-#include <xen/xenbus.h>
-
-#define SHUTDOWN_INVALID  -1
-#define SHUTDOWN_POWEROFF  0
-#define SHUTDOWN_SUSPEND   2
-/* Code 3 is SHUTDOWN_CRASH, which we don't use because the domain can only
- * report a crash, not be instructed to crash!
- * HALT is the same as POWEROFF, as far as we're concerned.  The tools use
- * the distinction when we return the reason code to them.
- */
-#define SHUTDOWN_HALT      4
-
-/* Ignore multiple shutdown requests. */
-static int shutting_down = SHUTDOWN_INVALID;
-
-static void shutdown_handler(struct xenbus_watch *watch,
-                             const char **vec, unsigned int len)
-{
-        char *str;
-        struct xenbus_transaction xbt;
-        int err;
-
-        if (shutting_down != SHUTDOWN_INVALID)
-                return;
-
- again:
-        err = xenbus_transaction_start(&xbt);
-        if (err)
-                return;
-
-        str = (char *)xenbus_read(xbt, "control", "shutdown", NULL);
-        /* Ignore read errors and empty reads. */
-        if (XENBUS_IS_ERR_READ(str)) {
-                xenbus_transaction_end(xbt, 1);
-                return;
-        }
-
-        xenbus_write(xbt, "control", "shutdown", "");
-
-        err = xenbus_transaction_end(xbt, 0);
-        if (err == -EAGAIN) {
-                kfree(str);
-                goto again;
-        }
-
-        if (strcmp(str, "poweroff") == 0 ||
-            strcmp(str, "halt") == 0)
-                orderly_poweroff(false);
-        else if (strcmp(str, "reboot") == 0)
-                ctrl_alt_del();
-        else {
-                printk(KERN_INFO "Ignoring shutdown request: %s\n", str);
-                shutting_down = SHUTDOWN_INVALID;
-        }
-
-        kfree(str);
-}
-
-static void sysrq_handler(struct xenbus_watch *watch, const char **vec,
-                          unsigned int len)
-{
-        char sysrq_key = '\0';
-        struct xenbus_transaction xbt;
-        int err;
-
- again:
-        err = xenbus_transaction_start(&xbt);
-        if (err)
-                return;
-        if (!xenbus_scanf(xbt, "control", "sysrq", "%c", &sysrq_key)) {
-                printk(KERN_ERR "Unable to read sysrq code in "
-                       "control/sysrq\n");
-                xenbus_transaction_end(xbt, 1);
-                return;
-        }
-
-        if (sysrq_key != '\0')
-                xenbus_printf(xbt, "control", "sysrq", "%c", '\0');
-
-        err = xenbus_transaction_end(xbt, 0);
-        if (err == -EAGAIN)
-                goto again;
-
-        if (sysrq_key != '\0')
-                handle_sysrq(sysrq_key, NULL);
-}
-
-static struct xenbus_watch shutdown_watch = {
-        .node = "control/shutdown",
-        .callback = shutdown_handler
-};
-
-static struct xenbus_watch sysrq_watch = {
-        .node = "control/sysrq",
-        .callback = sysrq_handler
-};
-
-static int setup_shutdown_watcher(void)
-{
-        int err;
-
-        err = register_xenbus_watch(&shutdown_watch);
-        if (err) {
-                printk(KERN_ERR "Failed to set shutdown watcher\n");
-                return err;
-        }
-
-        err = register_xenbus_watch(&sysrq_watch);
-        if (err) {
-                printk(KERN_ERR "Failed to set sysrq watcher\n");
-                return err;
-        }
-
-        return 0;
-}
-
-static int shutdown_event(struct notifier_block *notifier,
-                          unsigned long event,
-                          void *data)
-{
-        setup_shutdown_watcher();
-        return NOTIFY_DONE;
-}
-
-static int __init setup_shutdown_event(void)
-{
-        static struct notifier_block xenstore_notifier = {
-                .notifier_call = shutdown_event
-        };
-        register_xenstore_notifier(&xenstore_notifier);
-
-        return 0;
-}
-
-subsys_initcall(setup_shutdown_event);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index df40bf74ea75..42b3b9ed641d 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -56,6 +56,131 @@
 #include "multicalls.h"
 #include "mmu.h"
 
+#define P2M_ENTRIES_PER_PAGE    (PAGE_SIZE / sizeof(unsigned long))
+#define TOP_ENTRIES             (MAX_DOMAIN_PAGES / P2M_ENTRIES_PER_PAGE)
+
+/* Placeholder for holes in the address space */
+static unsigned long p2m_missing[P2M_ENTRIES_PER_PAGE]
+        __attribute__((section(".data.page_aligned"))) =
+                { [ 0 ... P2M_ENTRIES_PER_PAGE-1 ] = ~0UL };
+
+ /* Array of pointers to pages containing p2m entries */
+static unsigned long *p2m_top[TOP_ENTRIES]
+        __attribute__((section(".data.page_aligned"))) =
+                { [ 0 ... TOP_ENTRIES - 1] = &p2m_missing[0] };
+
+/* Arrays of p2m arrays expressed in mfns used for save/restore */
+static unsigned long p2m_top_mfn[TOP_ENTRIES]
+        __attribute__((section(".bss.page_aligned")));
+
+static unsigned long p2m_top_mfn_list[
+                        PAGE_ALIGN(TOP_ENTRIES / P2M_ENTRIES_PER_PAGE)]
+        __attribute__((section(".bss.page_aligned")));
+
+static inline unsigned p2m_top_index(unsigned long pfn)
+{
+        BUG_ON(pfn >= MAX_DOMAIN_PAGES);
+        return pfn / P2M_ENTRIES_PER_PAGE;
+}
+
+static inline unsigned p2m_index(unsigned long pfn)
+{
+        return pfn % P2M_ENTRIES_PER_PAGE;
+}
+
+/* Build the parallel p2m_top_mfn structures */
+void xen_setup_mfn_list_list(void)
+{
+        unsigned pfn, idx;
+
+        for(pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_ENTRIES_PER_PAGE) {
+                unsigned topidx = p2m_top_index(pfn);
+
+                p2m_top_mfn[topidx] = virt_to_mfn(p2m_top[topidx]);
+        }
+
+        for(idx = 0; idx < ARRAY_SIZE(p2m_top_mfn_list); idx++) {
+                unsigned topidx = idx * P2M_ENTRIES_PER_PAGE;
+                p2m_top_mfn_list[idx] = virt_to_mfn(&p2m_top_mfn[topidx]);
+        }
+
+        BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
+
+        HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list =
+                virt_to_mfn(p2m_top_mfn_list);
+        HYPERVISOR_shared_info->arch.max_pfn = xen_start_info->nr_pages;
+}
+
+/* Set up p2m_top to point to the domain-builder provided p2m pages */
+void __init xen_build_dynamic_phys_to_machine(void)
+{
+        unsigned long *mfn_list = (unsigned long *)xen_start_info->mfn_list;
+        unsigned long max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages);
+        unsigned pfn;
+
+        for(pfn = 0; pfn < max_pfn; pfn += P2M_ENTRIES_PER_PAGE) {
+                unsigned topidx = p2m_top_index(pfn);
+
+                p2m_top[topidx] = &mfn_list[pfn];
+        }
+}
+
+unsigned long get_phys_to_machine(unsigned long pfn)
+{
+        unsigned topidx, idx;
+
+        if (unlikely(pfn >= MAX_DOMAIN_PAGES))
+                return INVALID_P2M_ENTRY;
+
+        topidx = p2m_top_index(pfn);
+        idx = p2m_index(pfn);
+        return p2m_top[topidx][idx];
+}
+EXPORT_SYMBOL_GPL(get_phys_to_machine);
+
+static void alloc_p2m(unsigned long **pp, unsigned long *mfnp)
+{
+        unsigned long *p;
+        unsigned i;
+
+        p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL);
+        BUG_ON(p == NULL);
+
+        for(i = 0; i < P2M_ENTRIES_PER_PAGE; i++)
+                p[i] = INVALID_P2M_ENTRY;
+
+        if (cmpxchg(pp, p2m_missing, p) != p2m_missing)
+                free_page((unsigned long)p);
+        else
+                *mfnp = virt_to_mfn(p);
+}
+
+void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
+{
+        unsigned topidx, idx;
+
+        if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
+                BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
+                return;
+        }
+
+        if (unlikely(pfn >= MAX_DOMAIN_PAGES)) {
+                BUG_ON(mfn != INVALID_P2M_ENTRY);
+                return;
+        }
+
+        topidx = p2m_top_index(pfn);
+        if (p2m_top[topidx] == p2m_missing) {
+                /* no need to allocate a page to store an invalid entry */
+                if (mfn == INVALID_P2M_ENTRY)
+                        return;
+                alloc_p2m(&p2m_top[topidx], &p2m_top_mfn[topidx]);
+        }
+
+        idx = p2m_index(pfn);
+        p2m_top[topidx][idx] = mfn;
+}
+
 xmaddr_t arbitrary_virt_to_machine(unsigned long address)
 {
         unsigned int level;
@@ -98,24 +223,60 @@ void make_lowmem_page_readwrite(void *vaddr)
 }
 
 
-void xen_set_pmd(pmd_t *ptr, pmd_t val)
+static bool page_pinned(void *ptr)
+{
+        struct page *page = virt_to_page(ptr);
+
+        return PagePinned(page);
+}
+
+static void extend_mmu_update(const struct mmu_update *update)
 {
         struct multicall_space mcs;
         struct mmu_update *u;
 
-        preempt_disable();
+        mcs = xen_mc_extend_args(__HYPERVISOR_mmu_update, sizeof(*u));
+
+        if (mcs.mc != NULL)
+                mcs.mc->args[1]++;
+        else {
+                mcs = __xen_mc_entry(sizeof(*u));
+                MULTI_mmu_update(mcs.mc, mcs.args, 1, NULL, DOMID_SELF);
+        }
 
-        mcs = xen_mc_entry(sizeof(*u));
         u = mcs.args;
-        u->ptr = virt_to_machine(ptr).maddr;
-        u->val = pmd_val_ma(val);
-        MULTI_mmu_update(mcs.mc, u, 1, NULL, DOMID_SELF);
+        *u = *update;
+}
+
+void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
+{
+        struct mmu_update u;
+
+        preempt_disable();
+
+        xen_mc_batch();
+
+        u.ptr = virt_to_machine(ptr).maddr;
+        u.val = pmd_val_ma(val);
+        extend_mmu_update(&u);
 
         xen_mc_issue(PARAVIRT_LAZY_MMU);
 
         preempt_enable();
 }
 
+void xen_set_pmd(pmd_t *ptr, pmd_t val)
+{
+        /* If page is not pinned, we can just update the entry
+           directly */
+        if (!page_pinned(ptr)) {
+                *ptr = val;
+                return;
+        }
+
+        xen_set_pmd_hyper(ptr, val);
+}
+
 /*
  * Associate a virtual page frame with a given physical page frame
  * and protection flags for that frame.
@@ -179,13 +340,33 @@ out:
                 preempt_enable();
 }
 
+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 */
+        return *ptep;
+}
+
+void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
+                                 pte_t *ptep, pte_t pte)
+{
+        struct mmu_update u;
+
+        xen_mc_batch();
+
+        u.ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;
+        u.val = pte_val_ma(pte);
+        extend_mmu_update(&u);
+
+        xen_mc_issue(PARAVIRT_LAZY_MMU);
+}
+
 /* Assume pteval_t is equivalent to all the other *val_t types. */
 static pteval_t pte_mfn_to_pfn(pteval_t val)
 {
         if (val & _PAGE_PRESENT) {
                 unsigned long mfn = (val & PTE_MASK) >> PAGE_SHIFT;
                 pteval_t flags = val & ~PTE_MASK;
-                val = (mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
+                val = ((pteval_t)mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
         }
 
         return val;
@@ -196,7 +377,7 @@ static pteval_t pte_pfn_to_mfn(pteval_t val)
         if (val & _PAGE_PRESENT) {
                 unsigned long pfn = (val & PTE_MASK) >> PAGE_SHIFT;
                 pteval_t flags = val & ~PTE_MASK;
-                val = (pfn_to_mfn(pfn) << PAGE_SHIFT) | flags;
+                val = ((pteval_t)pfn_to_mfn(pfn) << PAGE_SHIFT) | flags;
         }
 
         return val;
@@ -229,24 +410,35 @@ pmdval_t xen_pmd_val(pmd_t pmd)
         return pte_mfn_to_pfn(pmd.pmd);
 }
 
-void xen_set_pud(pud_t *ptr, pud_t val)
+void xen_set_pud_hyper(pud_t *ptr, pud_t val)
 {
-        struct multicall_space mcs;
-        struct mmu_update *u;
+        struct mmu_update u;
 
         preempt_disable();
 
-        mcs = xen_mc_entry(sizeof(*u));
-        u = mcs.args;
-        u->ptr = virt_to_machine(ptr).maddr;
-        u->val = pud_val_ma(val);
-        MULTI_mmu_update(mcs.mc, u, 1, NULL, DOMID_SELF);
+        xen_mc_batch();
+
+        u.ptr = virt_to_machine(ptr).maddr;
+        u.val = pud_val_ma(val);
+        extend_mmu_update(&u);
 
         xen_mc_issue(PARAVIRT_LAZY_MMU);
 
         preempt_enable();
 }
 
+void xen_set_pud(pud_t *ptr, pud_t val)
+{
+        /* If page is not pinned, we can just update the entry
+           directly */
+        if (!page_pinned(ptr)) {
+                *ptr = val;
+                return;
+        }
+
+        xen_set_pud_hyper(ptr, val);
+}
+
 void xen_set_pte(pte_t *ptep, pte_t pte)
 {
         ptep->pte_high = pte.pte_high;
@@ -268,7 +460,7 @@ void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 
 void xen_pmd_clear(pmd_t *pmdp)
 {
-        xen_set_pmd(pmdp, __pmd(0));
+        set_pmd(pmdp, __pmd(0));
 }
 
 pmd_t xen_make_pmd(pmdval_t pmd)
@@ -441,6 +633,29 @@ void xen_pgd_pin(pgd_t *pgd)
         xen_mc_issue(0);
 }
 
+/*
+ * On save, we need to pin all pagetables to make sure they get their
+ * mfns turned into pfns.  Search the list for any unpinned pgds and pin
+ * them (unpinned pgds are not currently in use, probably because the
+ * process is under construction or destruction).
+ */
+void xen_mm_pin_all(void)
+{
+        unsigned long flags;
+        struct page *page;
+
+        spin_lock_irqsave(&pgd_lock, flags);
+
+        list_for_each_entry(page, &pgd_list, lru) {
+                if (!PagePinned(page)) {
+                        xen_pgd_pin((pgd_t *)page_address(page));
+                        SetPageSavePinned(page);
+                }
+        }
+
+        spin_unlock_irqrestore(&pgd_lock, flags);
+}
+
 /* The init_mm pagetable is really pinned as soon as its created, but
    that's before we have page structures to store the bits.  So do all
    the book-keeping now. */
@@ -498,6 +713,29 @@ static void xen_pgd_unpin(pgd_t *pgd)
         xen_mc_issue(0);
 }
 
+/*
+ * On resume, undo any pinning done at save, so that the rest of the
+ * kernel doesn't see any unexpected pinned pagetables.
+ */
+void xen_mm_unpin_all(void)
+{
+        unsigned long flags;
+        struct page *page;
+
+        spin_lock_irqsave(&pgd_lock, flags);
+
+        list_for_each_entry(page, &pgd_list, lru) {
+                if (PageSavePinned(page)) {
+                        BUG_ON(!PagePinned(page));
+                        printk("unpinning pinned %p\n", page_address(page));
+                        xen_pgd_unpin((pgd_t *)page_address(page));
+                        ClearPageSavePinned(page);
+                }
+        }
+
+        spin_unlock_irqrestore(&pgd_lock, flags);
+}
+
 void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next)
 {
         spin_lock(&next->page_table_lock);
@@ -591,7 +829,7 @@ void xen_exit_mmap(struct mm_struct *mm)
         spin_lock(&mm->page_table_lock);
 
         /* pgd may not be pinned in the error exit path of execve */
-        if (PagePinned(virt_to_page(mm->pgd)))
+        if (page_pinned(mm->pgd))
                 xen_pgd_unpin(mm->pgd);
 
         spin_unlock(&mm->page_table_lock);
diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h
index 5fe961caffd4..297bf9f5b8bc 100644
--- a/arch/x86/xen/mmu.h
+++ b/arch/x86/xen/mmu.h
@@ -25,10 +25,6 @@ enum pt_level {
 
 void set_pte_mfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
 
-void xen_set_pte(pte_t *ptep, pte_t pteval);
-void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
-                    pte_t *ptep, pte_t pteval);
-void xen_set_pmd(pmd_t *pmdp, pmd_t pmdval);
 
 void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next);
 void xen_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm);
@@ -45,11 +41,19 @@ pte_t xen_make_pte(pteval_t);
 pmd_t xen_make_pmd(pmdval_t);
 pgd_t xen_make_pgd(pgdval_t);
 
+void xen_set_pte(pte_t *ptep, pte_t pteval);
 void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
                     pte_t *ptep, pte_t pteval);
 void xen_set_pte_atomic(pte_t *ptep, pte_t pte);
+void xen_set_pmd(pmd_t *pmdp, pmd_t pmdval);
 void xen_set_pud(pud_t *ptr, pud_t val);
+void xen_set_pmd_hyper(pmd_t *pmdp, pmd_t pmdval);
+void xen_set_pud_hyper(pud_t *ptr, pud_t val);
 void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 void xen_pmd_clear(pmd_t *pmdp);
 
+pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+void  xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
+                                  pte_t *ptep, pte_t pte);
+
 #endif  /* _XEN_MMU_H */
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index 5791eb2e3750..3c63c4da7ed1 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -29,14 +29,14 @@
 #define MC_DEBUG        1
 
 #define MC_BATCH        32
-#define MC_ARGS         (MC_BATCH * 16 / sizeof(u64))
+#define MC_ARGS         (MC_BATCH * 16)
 
 struct mc_buffer {
         struct multicall_entry entries[MC_BATCH];
 #if MC_DEBUG
         struct multicall_entry debug[MC_BATCH];
 #endif
-        u64 args[MC_ARGS];
+        unsigned char args[MC_ARGS];
         struct callback {
                 void (*fn)(void *);
                 void *data;
@@ -107,20 +107,48 @@ struct multicall_space __xen_mc_entry(size_t args)
 {
         struct mc_buffer *b = &__get_cpu_var(mc_buffer);
         struct multicall_space ret;
-        unsigned argspace = (args + sizeof(u64) - 1) / sizeof(u64);
+        unsigned argidx = roundup(b->argidx, sizeof(u64));
 
         BUG_ON(preemptible());
-        BUG_ON(argspace > MC_ARGS);
+        BUG_ON(b->argidx > MC_ARGS);
 
         if (b->mcidx == MC_BATCH ||
-            (b->argidx + argspace) > MC_ARGS)
+            (argidx + args) > MC_ARGS) {
                 xen_mc_flush();
+                argidx = roundup(b->argidx, sizeof(u64));
+        }
 
         ret.mc = &b->entries[b->mcidx];
         b->mcidx++;
+        ret.args = &b->args[argidx];
+        b->argidx = argidx + args;
+
+        BUG_ON(b->argidx > MC_ARGS);
+        return ret;
+}
+
+struct multicall_space xen_mc_extend_args(unsigned long op, size_t size)
+{
+        struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+        struct multicall_space ret = { NULL, NULL };
+
+        BUG_ON(preemptible());
+        BUG_ON(b->argidx > MC_ARGS);
+
+        if (b->mcidx == 0)
+                return ret;
+
+        if (b->entries[b->mcidx - 1].op != op)
+                return ret;
+
+        if ((b->argidx + size) > MC_ARGS)
+                return ret;
+
+        ret.mc = &b->entries[b->mcidx - 1];
         ret.args = &b->args[b->argidx];
-        b->argidx += argspace;
+        b->argidx += size;
 
+        BUG_ON(b->argidx > MC_ARGS);
         return ret;
 }
 
diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h
index 8bae996d99a3..858938241616 100644
--- a/arch/x86/xen/multicalls.h
+++ b/arch/x86/xen/multicalls.h
@@ -45,4 +45,16 @@ static inline void xen_mc_issue(unsigned mode)
 /* Set up a callback to be called when the current batch is flushed */
 void xen_mc_callback(void (*fn)(void *), void *data);
 
+/*
+ * Try to extend the arguments of the previous multicall command.  The
+ * previous command's op must match.  If it does, then it attempts to
+ * extend the argument space allocated to the multicall entry by
+ * arg_size bytes.
+ *
+ * The returned multicall_space will return with mc pointing to the
+ * command on success, or NULL on failure, and args pointing to the
+ * newly allocated space.
+ */
+struct multicall_space xen_mc_extend_args(unsigned long op, size_t arg_size);
+
 #endif /* _XEN_MULTICALLS_H */
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 82517e4a752a..488447878a9d 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -16,6 +16,7 @@
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 
+#include <xen/page.h>
 #include <xen/interface/callback.h>
 #include <xen/interface/physdev.h>
 #include <xen/features.h>
@@ -27,8 +28,6 @@
 extern const char xen_hypervisor_callback[];
 extern const char xen_failsafe_callback[];
 
-unsigned long *phys_to_machine_mapping;
-EXPORT_SYMBOL(phys_to_machine_mapping);
 
 /**
  * machine_specific_memory_setup - Hook for machine specific memory setup.
@@ -38,6 +37,8 @@ char * __init xen_memory_setup(void)
 {
         unsigned long max_pfn = xen_start_info->nr_pages;
 
+        max_pfn = min(MAX_DOMAIN_PAGES, max_pfn);
+
         e820.nr_map = 0;
         add_memory_region(0, LOWMEMSIZE(), E820_RAM);
         add_memory_region(HIGH_MEMORY, PFN_PHYS(max_pfn)-HIGH_MEMORY, E820_RAM);
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 94e69000f982..d2e3c20127d7 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -35,7 +35,7 @@
 #include "xen-ops.h"
 #include "mmu.h"
 
-static cpumask_t xen_cpu_initialized_map;
+cpumask_t xen_cpu_initialized_map;
 static DEFINE_PER_CPU(int, resched_irq) = -1;
 static DEFINE_PER_CPU(int, callfunc_irq) = -1;
 static DEFINE_PER_CPU(int, debug_irq) = -1;
@@ -65,6 +65,12 @@ static struct call_data_struct *call_data;
  */
 static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
 {
+#ifdef CONFIG_X86_32
+        __get_cpu_var(irq_stat).irq_resched_count++;
+#else
+        add_pda(irq_resched_count, 1);
+#endif
+
         return IRQ_HANDLED;
 }
 
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
new file mode 100644
index 000000000000..251669a932d4
--- /dev/null
+++ b/arch/x86/xen/suspend.c
@@ -0,0 +1,45 @@
+#include <linux/types.h>
+
+#include <xen/interface/xen.h>
+#include <xen/grant_table.h>
+#include <xen/events.h>
+
+#include <asm/xen/hypercall.h>
+#include <asm/xen/page.h>
+
+#include "xen-ops.h"
+#include "mmu.h"
+
+void xen_pre_suspend(void)
+{
+        xen_start_info->store_mfn = mfn_to_pfn(xen_start_info->store_mfn);
+        xen_start_info->console.domU.mfn =
+                mfn_to_pfn(xen_start_info->console.domU.mfn);
+
+        BUG_ON(!irqs_disabled());
+
+        HYPERVISOR_shared_info = &xen_dummy_shared_info;
+        if (HYPERVISOR_update_va_mapping(fix_to_virt(FIX_PARAVIRT_BOOTMAP),
+                                         __pte_ma(0), 0))
+                BUG();
+}
+
+void xen_post_suspend(int suspend_cancelled)
+{
+        xen_setup_shared_info();
+
+        if (suspend_cancelled) {
+                xen_start_info->store_mfn =
+                        pfn_to_mfn(xen_start_info->store_mfn);
+                xen_start_info->console.domU.mfn =
+                        pfn_to_mfn(xen_start_info->console.domU.mfn);
+        } else {
+#ifdef CONFIG_SMP
+                xen_cpu_initialized_map = cpu_online_map;
+#endif
+                xen_vcpu_restore();
+                xen_timer_resume();
+        }
+
+}
+
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 41e217503c96..64f0038b9558 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -459,6 +459,19 @@ void xen_setup_cpu_clockevents(void)
         clockevents_register_device(&__get_cpu_var(xen_clock_events));
 }
 
+void xen_timer_resume(void)
+{
+        int cpu;
+
+        if (xen_clockevent != &xen_vcpuop_clockevent)
+                return;
+
+        for_each_online_cpu(cpu) {
+                if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL))
+                        BUG();
+        }
+}
+
 __init void xen_time_init(void)
 {
         int cpu = smp_processor_id();
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 6ec3b4f7719b..7c0cf6320a0a 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -7,6 +7,7 @@
 #include <linux/init.h>
 #include <asm/boot.h>
 #include <xen/interface/elfnote.h>
+#include <asm/xen/interface.h>
 
         __INIT
 ENTRY(startup_xen)
@@ -32,5 +33,9 @@ ENTRY(hypercall_page)
         ELFNOTE(Xen, XEN_ELFNOTE_FEATURES,       .asciz "!writable_page_tables|pae_pgdir_above_4gb")
         ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE,       .asciz "yes")
         ELFNOTE(Xen, XEN_ELFNOTE_LOADER,         .asciz "generic")
+        ELFNOTE(Xen, XEN_ELFNOTE_L1_MFN_VALID,
+                .quad _PAGE_PRESENT; .quad _PAGE_PRESENT)
+        ELFNOTE(Xen, XEN_ELFNOTE_SUSPEND_CANCEL, .long 1)
+        ELFNOTE(Xen, XEN_ELFNOTE_HV_START_LOW,   .long __HYPERVISOR_VIRT_START)
 
 #endif /*CONFIG_XEN */
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index f1063ae08037..9a055592a307 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -9,18 +9,26 @@
 extern const char xen_hypervisor_callback[];
 extern const char xen_failsafe_callback[];
 
+struct trap_info;
 void xen_copy_trap_info(struct trap_info *traps);
 
 DECLARE_PER_CPU(unsigned long, xen_cr3);
 DECLARE_PER_CPU(unsigned long, xen_current_cr3);
 
 extern struct start_info *xen_start_info;
+extern struct shared_info xen_dummy_shared_info;
 extern struct shared_info *HYPERVISOR_shared_info;
 
+void xen_setup_mfn_list_list(void);
+void xen_setup_shared_info(void);
+
 char * __init xen_memory_setup(void);
 void __init xen_arch_setup(void);
 void __init xen_init_IRQ(void);
 void xen_enable_sysenter(void);
+void xen_vcpu_restore(void);
+
+void __init xen_build_dynamic_phys_to_machine(void);
 
 void xen_setup_timer(int cpu);
 void xen_setup_cpu_clockevents(void);
@@ -29,6 +37,7 @@ void __init xen_time_init(void);
 unsigned long xen_get_wallclock(void);
 int xen_set_wallclock(unsigned long time);
 unsigned long long xen_sched_clock(void);
+void xen_timer_resume(void);
 
 irqreturn_t xen_debug_interrupt(int irq, void *dev_id);
 
@@ -54,6 +63,8 @@ int xen_smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 int xen_smp_call_function_mask(cpumask_t mask, void (*func)(void *),
                                void *info, int wait);
 
+extern cpumask_t xen_cpu_initialized_map;
+
 
 /* Declare an asm function, along with symbols needed to make it
    inlineable */