9 files changed, 205 insertions, 54 deletions

diff --git a/arch/arm/include/asm/xen/interface.h b/arch/arm/include/asm/xen/interface.h
index 5000397134b4..1151188bcd83 100644
--- a/arch/arm/include/asm/xen/interface.h
+++ b/arch/arm/include/asm/xen/interface.h
@@ -49,6 +49,7 @@ DEFINE_GUEST_HANDLE(void);
 DEFINE_GUEST_HANDLE(uint64_t);
 DEFINE_GUEST_HANDLE(uint32_t);
 DEFINE_GUEST_HANDLE(xen_pfn_t);
+DEFINE_GUEST_HANDLE(xen_ulong_t);
 
 /* Maximum number of virtual CPUs in multi-processor guests. */
 #define MAX_VIRT_CPUS 1
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index f57609275449..41a6a27128a2 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -8,6 +8,8 @@
 #include <xen/features.h>
 #include <xen/platform_pci.h>
 #include <xen/xenbus.h>
+#include <xen/page.h>
+#include <xen/xen-ops.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 #include <linux/interrupt.h>
@@ -17,6 +19,8 @@
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
 
+#include <linux/mm.h>
+
 struct start_info _xen_start_info;
 struct start_info *xen_start_info = &_xen_start_info;
 EXPORT_SYMBOL_GPL(xen_start_info);
@@ -29,6 +33,10 @@ struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info;
 
 DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
 
+/* These are unused until we support booting "pre-ballooned" */
+unsigned long xen_released_pages;
+struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
+
 /* TODO: to be removed */
 __read_mostly int xen_have_vector_callback;
 EXPORT_SYMBOL_GPL(xen_have_vector_callback);
@@ -38,15 +46,106 @@ EXPORT_SYMBOL_GPL(xen_platform_pci_unplug);
 
 static __read_mostly int xen_events_irq = -1;
 
+/* map fgmfn of domid to lpfn in the current domain */
+static int map_foreign_page(unsigned long lpfn, unsigned long fgmfn,
+                            unsigned int domid)
+{
+        int rc;
+        struct xen_add_to_physmap_range xatp = {
+                .domid = DOMID_SELF,
+                .foreign_domid = domid,
+                .size = 1,
+                .space = XENMAPSPACE_gmfn_foreign,
+        };
+        xen_ulong_t idx = fgmfn;
+        xen_pfn_t gpfn = lpfn;
+
+        set_xen_guest_handle(xatp.idxs, &idx);
+        set_xen_guest_handle(xatp.gpfns, &gpfn);
+
+        rc = HYPERVISOR_memory_op(XENMEM_add_to_physmap_range, &xatp);
+        if (rc) {
+                pr_warn("Failed to map pfn to mfn rc:%d pfn:%lx mfn:%lx\n",
+                        rc, lpfn, fgmfn);
+                return 1;
+        }
+        return 0;
+}
+
+struct remap_data {
+        xen_pfn_t fgmfn; /* foreign domain's gmfn */
+        pgprot_t prot;
+        domid_t  domid;
+        struct vm_area_struct *vma;
+        int index;
+        struct page **pages;
+        struct xen_remap_mfn_info *info;
+};
+
+static int remap_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr,
+                        void *data)
+{
+        struct remap_data *info = data;
+        struct page *page = info->pages[info->index++];
+        unsigned long pfn = page_to_pfn(page);
+        pte_t pte = pfn_pte(pfn, info->prot);
+
+        if (map_foreign_page(pfn, info->fgmfn, info->domid))
+                return -EFAULT;
+        set_pte_at(info->vma->vm_mm, addr, ptep, pte);
+
+        return 0;
+}
+
 int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
                                unsigned long addr,
-                               unsigned long mfn, int nr,
-                               pgprot_t prot, unsigned domid)
+                               xen_pfn_t mfn, int nr,
+                               pgprot_t prot, unsigned domid,
+                               struct page **pages)
 {
-        return -ENOSYS;
+        int err;
+        struct remap_data data;
+
+        /* TBD: Batching, current sole caller only does page at a time */
+        if (nr > 1)
+                return -EINVAL;
+
+        data.fgmfn = mfn;
+        data.prot = prot;
+        data.domid = domid;
+        data.vma = vma;
+        data.index = 0;
+        data.pages = pages;
+        err = apply_to_page_range(vma->vm_mm, addr, nr << PAGE_SHIFT,
+                                  remap_pte_fn, &data);
+        return err;
 }
 EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range);
 
+int xen_unmap_domain_mfn_range(struct vm_area_struct *vma,
+                               int nr, struct page **pages)
+{
+        int i;
+
+        for (i = 0; i < nr; i++) {
+                struct xen_remove_from_physmap xrp;
+                unsigned long rc, pfn;
+
+                pfn = page_to_pfn(pages[i]);
+
+                xrp.domid = DOMID_SELF;
+                xrp.gpfn = pfn;
+                rc = HYPERVISOR_memory_op(XENMEM_remove_from_physmap, &xrp);
+                if (rc) {
+                        pr_warn("Failed to unmap pfn:%lx rc:%ld\n",
+                                pfn, rc);
+                        return rc;
+                }
+        }
+        return 0;
+}
+EXPORT_SYMBOL_GPL(xen_unmap_domain_mfn_range);
+
 /*
  * see Documentation/devicetree/bindings/arm/xen.txt for the
  * documentation of the Xen Device Tree format.
@@ -149,23 +248,6 @@ static int __init xen_init_events(void)
 }
 postcore_initcall(xen_init_events);
 
-/* XXX: only until balloon is properly working */
-int alloc_xenballooned_pages(int nr_pages, struct page **pages, bool highmem)
-{
-        *pages = alloc_pages(highmem ? GFP_HIGHUSER : GFP_KERNEL,
-                        get_order(nr_pages));
-        if (*pages == NULL)
-                return -ENOMEM;
-        return 0;
-}
-EXPORT_SYMBOL_GPL(alloc_xenballooned_pages);
-
-void free_xenballooned_pages(int nr_pages, struct page **pages)
-{
-        kfree(*pages);
-        *pages = NULL;
-}
-EXPORT_SYMBOL_GPL(free_xenballooned_pages);
 
 /* In the hypervisor.S file. */
 EXPORT_SYMBOL_GPL(HYPERVISOR_event_channel_op);
@@ -176,4 +258,4 @@ EXPORT_SYMBOL_GPL(HYPERVISOR_sched_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_hvm_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_memory_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_physdev_op);
-EXPORT_SYMBOL_GPL(privcmd_call);
+EXPORT_SYMBOL_GPL(privcmd_call);
\ No newline at end of file
diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
index 54d52ff1304a..fd9cb7695b5f 100644
--- a/arch/x86/include/asm/xen/interface.h
+++ b/arch/x86/include/asm/xen/interface.h
@@ -63,6 +63,7 @@ DEFINE_GUEST_HANDLE(void);
 DEFINE_GUEST_HANDLE(uint64_t);
 DEFINE_GUEST_HANDLE(uint32_t);
 DEFINE_GUEST_HANDLE(xen_pfn_t);
+DEFINE_GUEST_HANDLE(xen_ulong_t);
 #endif
 
 #ifndef HYPERVISOR_VIRT_START
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index fdce49c7aff6..c31ee77e1ec1 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -6,6 +6,7 @@ config XEN
         bool "Xen guest support"
         select PARAVIRT
         select PARAVIRT_CLOCK
+        select XEN_HAVE_PVMMU
         depends on X86_64 || (X86_32 && X86_PAE && !X86_VISWS)
         depends on X86_CMPXCHG && X86_TSC
         help
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 586d83812b67..138e5667409a 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -193,10 +193,11 @@ void xen_vcpu_restore(void)
 {
         int cpu;
 
-        for_each_online_cpu(cpu) {
+        for_each_possible_cpu(cpu) {
                 bool other_cpu = (cpu != smp_processor_id());
+                bool is_up = HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL);
 
-                if (other_cpu &&
+                if (other_cpu && is_up &&
                     HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL))
                         BUG();
 
@@ -205,7 +206,7 @@ void xen_vcpu_restore(void)
                 if (have_vcpu_info_placement)
                         xen_vcpu_setup(cpu);
 
-                if (other_cpu &&
+                if (other_cpu && is_up &&
                     HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL))
                         BUG();
         }
@@ -223,6 +224,21 @@ static void __init xen_banner(void)
                version >> 16, version & 0xffff, extra.extraversion,
                xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
 }
+/* Check if running on Xen version (major, minor) or later */
+bool
+xen_running_on_version_or_later(unsigned int major, unsigned int minor)
+{
+        unsigned int version;
+
+        if (!xen_domain())
+                return false;
+
+        version = HYPERVISOR_xen_version(XENVER_version, NULL);
+        if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) ||
+                ((version >> 16) > major))
+                return true;
+        return false;
+}
 
 #define CPUID_THERM_POWER_LEAF 6
 #define APERFMPERF_PRESENT 0
@@ -287,8 +303,7 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
 
 static bool __init xen_check_mwait(void)
 {
-#if defined(CONFIG_ACPI) && !defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR) && \
-        !defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR_MODULE)
+#ifdef CONFIG_ACPI
         struct xen_platform_op op = {
                 .cmd                    = XENPF_set_processor_pminfo,
                 .u.set_pminfo.id        = -1,
@@ -309,6 +324,13 @@ static bool __init xen_check_mwait(void)
         if (!xen_initial_domain())
                 return false;
 
+        /*
+         * When running under platform earlier than Xen4.2, do not expose
+         * mwait, to avoid the risk of loading native acpi pad driver
+         */
+        if (!xen_running_on_version_or_later(4, 2))
+                return false;
+
         ax = 1;
         cx = 0;
 
@@ -1495,51 +1517,72 @@ asmlinkage void __init xen_start_kernel(void)
 #endif
 }
 
-void __ref xen_hvm_init_shared_info(void)
+#ifdef CONFIG_XEN_PVHVM
+#define HVM_SHARED_INFO_ADDR 0xFE700000UL
+static struct shared_info *xen_hvm_shared_info;
+static unsigned long xen_hvm_sip_phys;
+static int xen_major, xen_minor;
+
+static void xen_hvm_connect_shared_info(unsigned long pfn)
 {
-        int cpu;
         struct xen_add_to_physmap xatp;
-        static struct shared_info *shared_info_page = 0;
 
-        if (!shared_info_page)
-                shared_info_page = (struct shared_info *)
-                        extend_brk(PAGE_SIZE, PAGE_SIZE);
         xatp.domid = DOMID_SELF;
         xatp.idx = 0;
         xatp.space = XENMAPSPACE_shared_info;
-        xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT;
+        xatp.gpfn = pfn;
         if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
                 BUG();
 
-        HYPERVISOR_shared_info = (struct shared_info *)shared_info_page;
+}
+static void __init xen_hvm_set_shared_info(struct shared_info *sip)
+{
+        int cpu;
+
+        HYPERVISOR_shared_info = sip;
 
         /* xen_vcpu is a pointer to the vcpu_info struct in the shared_info
          * page, we use it in the event channel upcall and in some pvclock
          * related functions. We don't need the vcpu_info placement
          * optimizations because we don't use any pv_mmu or pv_irq op on
-         * HVM.
-         * When xen_hvm_init_shared_info is run at boot time only vcpu 0 is
-         * online but xen_hvm_init_shared_info is run at resume time too and
-         * in that case multiple vcpus might be online. */
-        for_each_online_cpu(cpu) {
+         * HVM. */
+        for_each_online_cpu(cpu)
                 per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
+}
+
+/* Reconnect the shared_info pfn to a (new) mfn */
+void xen_hvm_resume_shared_info(void)
+{
+        xen_hvm_connect_shared_info(xen_hvm_sip_phys >> PAGE_SHIFT);
+}
+
+/* Xen tools prior to Xen 4 do not provide a E820_Reserved area for guest usage.
+ * On these old tools the shared info page will be placed in E820_Ram.
+ * Xen 4 provides a E820_Reserved area at 0xFC000000, and this code expects
+ * that nothing is mapped up to HVM_SHARED_INFO_ADDR.
+ * Xen 4.3+ provides an explicit 1MB area at HVM_SHARED_INFO_ADDR which is used
+ * here for the shared info page. */
+static void __init xen_hvm_init_shared_info(void)
+{
+        if (xen_major < 4) {
+                xen_hvm_shared_info = extend_brk(PAGE_SIZE, PAGE_SIZE);
+                xen_hvm_sip_phys = __pa(xen_hvm_shared_info);
+        } else {
+                xen_hvm_sip_phys = HVM_SHARED_INFO_ADDR;
+                set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_hvm_sip_phys);
+                xen_hvm_shared_info =
+                (struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
         }
+        xen_hvm_connect_shared_info(xen_hvm_sip_phys >> PAGE_SHIFT);
+        xen_hvm_set_shared_info(xen_hvm_shared_info);
 }
 
-#ifdef CONFIG_XEN_PVHVM
 static void __init init_hvm_pv_info(void)
 {
-        int major, minor;
-        uint32_t eax, ebx, ecx, edx, pages, msr, base;
+        uint32_t ecx, edx, pages, msr, base;
         u64 pfn;
 
         base = xen_cpuid_base();
-        cpuid(base + 1, &eax, &ebx, &ecx, &edx);
-
-        major = eax >> 16;
-        minor = eax & 0xffff;
-        printk(KERN_INFO "Xen version %d.%d.\n", major, minor);
-
         cpuid(base + 2, &pages, &msr, &ecx, &edx);
 
         pfn = __pa(hypercall_page);
@@ -1590,12 +1633,22 @@ static void __init xen_hvm_guest_init(void)
 
 static bool __init xen_hvm_platform(void)
 {
+        uint32_t eax, ebx, ecx, edx, base;
+
         if (xen_pv_domain())
                 return false;
 
-        if (!xen_cpuid_base())
+        base = xen_cpuid_base();
+        if (!base)
                 return false;
 
+        cpuid(base + 1, &eax, &ebx, &ecx, &edx);
+
+        xen_major = eax >> 16;
+        xen_minor = eax & 0xffff;
+
+        printk(KERN_INFO "Xen version %d.%d.\n", xen_major, xen_minor);
+
         return true;
 }
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index dcf5f2dd91ec..01de35c77221 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -2497,8 +2497,10 @@ static int remap_area_mfn_pte_fn(pte_t *ptep, pgtable_t token,
 
 int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
                                unsigned long addr,
-                               unsigned long mfn, int nr,
-                               pgprot_t prot, unsigned domid)
+                               xen_pfn_t mfn, int nr,
+                               pgprot_t prot, unsigned domid,
+                               struct page **pages)
+
 {
         struct remap_data rmd;
         struct mmu_update mmu_update[REMAP_BATCH_SIZE];
@@ -2542,3 +2544,14 @@ out:
         return err;
 }
 EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range);
+
+/* Returns: 0 success */
+int xen_unmap_domain_mfn_range(struct vm_area_struct *vma,
+                               int numpgs, struct page **pages)
+{
+        if (!pages || !xen_feature(XENFEAT_auto_translated_physmap))
+                return 0;
+
+        return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(xen_unmap_domain_mfn_range);
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 353c50f18702..4f7d2599b484 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -254,7 +254,7 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
         }
         xen_init_lock_cpu(0);
 
-        smp_store_cpu_info(0);
+        smp_store_boot_cpu_info();
         cpu_data(0).x86_max_cores = 1;
 
         for_each_possible_cpu(i) {
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 45329c8c226e..ae8a00c39de4 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -30,7 +30,7 @@ void xen_arch_hvm_post_suspend(int suspend_cancelled)
 {
 #ifdef CONFIG_XEN_PVHVM
         int cpu;
-        xen_hvm_init_shared_info();
+        xen_hvm_resume_shared_info();
         xen_callback_vector();
         xen_unplug_emulated_devices();
         if (xen_feature(XENFEAT_hvm_safe_pvclock)) {
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index a95b41744ad0..d2e73d19d366 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -40,7 +40,7 @@ void xen_enable_syscall(void);
 void xen_vcpu_restore(void);
 
 void xen_callback_vector(void);
-void xen_hvm_init_shared_info(void);
+void xen_hvm_resume_shared_info(void);
 void xen_unplug_emulated_devices(void);
 
 void __init xen_build_dynamic_phys_to_machine(void);