11 files changed, 246 insertions, 33 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 59bcb96ac369..f28fc1ac8760 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.
@@ -148,21 +247,3 @@ static int __init xen_init_events(void)
         return 0;
 }
 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);
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/mmu.c b/arch/x86/xen/mmu.c
index 6226c99729b9..fd8393f55069 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -2478,8 +2478,10 @@ 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];
@@ -2523,3 +2525,14 @@ 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/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 126d8ce591ce..cabfa97f4674 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -206,4 +206,7 @@ config XEN_MCE_LOG
           Allow kernel fetching MCE error from Xen platform and
           converting it into Linux mcelog format for mcelog tools
 
+config XEN_HAVE_PVMMU
+       bool
+
 endmenu
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index 3c397170f39c..3ee2b91ca4e0 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -1,8 +1,8 @@
 ifneq ($(CONFIG_ARM),y)
-obj-y   += manage.o balloon.o
+obj-y   += manage.o
 obj-$(CONFIG_HOTPLUG_CPU)               += cpu_hotplug.o
 endif
-obj-y   += grant-table.o features.o events.o
+obj-y   += grant-table.o features.o events.o balloon.o
 obj-y   += xenbus/
 
 nostackp := $(call cc-option, -fno-stack-protector)
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index d6886d90ccfd..a56776dbe095 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -359,6 +359,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 
                 set_phys_to_machine(pfn, frame_list[i]);
 
+#ifdef CONFIG_XEN_HAVE_PVMMU
                 /* Link back into the page tables if not highmem. */
                 if (xen_pv_domain() && !PageHighMem(page)) {
                         int ret;
@@ -368,6 +369,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
                                 0);
                         BUG_ON(ret);
                 }
+#endif
 
                 /* Relinquish the page back to the allocator. */
                 ClearPageReserved(page);
@@ -416,13 +418,14 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 
                 scrub_page(page);
 
+#ifdef CONFIG_XEN_HAVE_PVMMU
                 if (xen_pv_domain() && !PageHighMem(page)) {
                         ret = HYPERVISOR_update_va_mapping(
                                 (unsigned long)__va(pfn << PAGE_SHIFT),
                                 __pte_ma(0), 0);
                         BUG_ON(ret);
                 }
-
+#endif
         }
 
         /* Ensure that ballooned highmem pages don't have kmaps. */
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 8adb9cc267f9..b9d08987a5a5 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -33,11 +33,14 @@
 #include <xen/features.h>
 #include <xen/page.h>
 #include <xen/xen-ops.h>
+#include <xen/balloon.h>
 
 #include "privcmd.h"
 
 MODULE_LICENSE("GPL");
 
+#define PRIV_VMA_LOCKED ((void *)1)
+
 #ifndef HAVE_ARCH_PRIVCMD_MMAP
 static int privcmd_enforce_singleshot_mapping(struct vm_area_struct *vma);
 #endif
@@ -178,7 +181,7 @@ static int mmap_mfn_range(void *data, void *state)
                                         msg->va & PAGE_MASK,
                                         msg->mfn, msg->npages,
                                         vma->vm_page_prot,
-                                        st->domain);
+                                        st->domain, NULL);
         if (rc < 0)
                 return rc;
 
@@ -199,6 +202,10 @@ static long privcmd_ioctl_mmap(void __user *udata)
         if (!xen_initial_domain())
                 return -EPERM;
 
+        /* We only support privcmd_ioctl_mmap_batch for auto translated. */
+        if (xen_feature(XENFEAT_auto_translated_physmap))
+                return -ENOSYS;
+
         if (copy_from_user(&mmapcmd, udata, sizeof(mmapcmd)))
                 return -EFAULT;
 
@@ -246,6 +253,7 @@ struct mmap_batch_state {
         domid_t domain;
         unsigned long va;
         struct vm_area_struct *vma;
+        int index;
         /* A tristate:
          *      0 for no errors
          *      1 if at least one error has happened (and no
@@ -260,14 +268,24 @@ struct mmap_batch_state {
         xen_pfn_t __user *user_mfn;
 };
 
+/* auto translated dom0 note: if domU being created is PV, then mfn is
+ * mfn(addr on bus). If it's auto xlated, then mfn is pfn (input to HAP).
+ */
 static int mmap_batch_fn(void *data, void *state)
 {
         xen_pfn_t *mfnp = data;
         struct mmap_batch_state *st = state;
+        struct vm_area_struct *vma = st->vma;
+        struct page **pages = vma->vm_private_data;
+        struct page *cur_page = NULL;
         int ret;
 
+        if (xen_feature(XENFEAT_auto_translated_physmap))
+                cur_page = pages[st->index++];
+
         ret = xen_remap_domain_mfn_range(st->vma, st->va & PAGE_MASK, *mfnp, 1,
-                                         st->vma->vm_page_prot, st->domain);
+                                         st->vma->vm_page_prot, st->domain,
+                                         &cur_page);
 
         /* Store error code for second pass. */
         *(st->err++) = ret;
@@ -303,6 +321,32 @@ static int mmap_return_errors_v1(void *data, void *state)
         return __put_user(*mfnp, st->user_mfn++);
 }
 
+/* Allocate pfns that are then mapped with gmfns from foreign domid. Update
+ * the vma with the page info to use later.
+ * Returns: 0 if success, otherwise -errno
+ */
+static int alloc_empty_pages(struct vm_area_struct *vma, int numpgs)
+{
+        int rc;
+        struct page **pages;
+
+        pages = kcalloc(numpgs, sizeof(pages[0]), GFP_KERNEL);
+        if (pages == NULL)
+                return -ENOMEM;
+
+        rc = alloc_xenballooned_pages(numpgs, pages, 0);
+        if (rc != 0) {
+                pr_warn("%s Could not alloc %d pfns rc:%d\n", __func__,
+                        numpgs, rc);
+                kfree(pages);
+                return -ENOMEM;
+        }
+        BUG_ON(vma->vm_private_data != PRIV_VMA_LOCKED);
+        vma->vm_private_data = pages;
+
+        return 0;
+}
+
 static struct vm_operations_struct privcmd_vm_ops;
 
 static long privcmd_ioctl_mmap_batch(void __user *udata, int version)
@@ -370,10 +414,18 @@ static long privcmd_ioctl_mmap_batch(void __user *udata, int version)
                 up_write(&mm->mmap_sem);
                 goto out;
         }
+        if (xen_feature(XENFEAT_auto_translated_physmap)) {
+                ret = alloc_empty_pages(vma, m.num);
+                if (ret < 0) {
+                        up_write(&mm->mmap_sem);
+                        goto out;
+                }
+        }
 
         state.domain        = m.dom;
         state.vma           = vma;
         state.va            = m.addr;
+        state.index         = 0;
         state.global_error  = 0;
         state.err           = err_array;
 
@@ -438,6 +490,19 @@ static long privcmd_ioctl(struct file *file,
         return ret;
 }
 
+static void privcmd_close(struct vm_area_struct *vma)
+{
+        struct page **pages = vma->vm_private_data;
+        int numpgs = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+
+        if (!xen_feature(XENFEAT_auto_translated_physmap || !numpgs || !pages))
+                return;
+
+        xen_unmap_domain_mfn_range(vma, numpgs, pages);
+        free_xenballooned_pages(numpgs, pages);
+        kfree(pages);
+}
+
 static int privcmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
         printk(KERN_DEBUG "privcmd_fault: vma=%p %lx-%lx, pgoff=%lx, uv=%p\n",
@@ -448,6 +513,7 @@ static int privcmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 }
 
 static struct vm_operations_struct privcmd_vm_ops = {
+        .close = privcmd_close,
         .fault = privcmd_fault
 };
 
@@ -465,7 +531,7 @@ static int privcmd_mmap(struct file *file, struct vm_area_struct *vma)
 
 static int privcmd_enforce_singleshot_mapping(struct vm_area_struct *vma)
 {
-        return (xchg(&vma->vm_private_data, (void *)1) == NULL);
+        return !cmpxchg(&vma->vm_private_data, NULL, PRIV_VMA_LOCKED);
 }
 
 const struct file_operations xen_privcmd_fops = {
diff --git a/include/xen/interface/memory.h b/include/xen/interface/memory.h
index 90712e2072d5..b40a4315cb8b 100644
--- a/include/xen/interface/memory.h
+++ b/include/xen/interface/memory.h
@@ -153,6 +153,14 @@ struct xen_machphys_mapping {
 };
 DEFINE_GUEST_HANDLE_STRUCT(xen_machphys_mapping_t);
 
+#define XENMAPSPACE_shared_info  0 /* shared info page */
+#define XENMAPSPACE_grant_table  1 /* grant table page */
+#define XENMAPSPACE_gmfn         2 /* GMFN */
+#define XENMAPSPACE_gmfn_range   3 /* GMFN range, XENMEM_add_to_physmap only. */
+#define XENMAPSPACE_gmfn_foreign 4 /* GMFN from another dom,
+                                    * XENMEM_add_to_physmap_range only.
+                                    */
+
 /*
  * Sets the GPFN at which a particular page appears in the specified guest's
  * pseudophysical address space.
@@ -167,8 +175,6 @@ struct xen_add_to_physmap {
     uint16_t    size;
 
     /* Source mapping space. */
-#define XENMAPSPACE_shared_info 0 /* shared info page */
-#define XENMAPSPACE_grant_table 1 /* grant table page */
     unsigned int space;
 
     /* Index into source mapping space. */
@@ -182,6 +188,24 @@ DEFINE_GUEST_HANDLE_STRUCT(xen_add_to_physmap);
 /*** REMOVED ***/
 /*#define XENMEM_translate_gpfn_list  8*/
 
+#define XENMEM_add_to_physmap_range 23
+struct xen_add_to_physmap_range {
+    /* Which domain to change the mapping for. */
+    domid_t domid;
+    uint16_t space; /* => enum phys_map_space */
+
+    /* Number of pages to go through */
+    uint16_t size;
+    domid_t foreign_domid; /* IFF gmfn_foreign */
+
+    /* Indexes into space being mapped. */
+    GUEST_HANDLE(xen_ulong_t) idxs;
+
+    /* GPFN in domid where the source mapping page should appear. */
+    GUEST_HANDLE(xen_pfn_t) gpfns;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_add_to_physmap_range);
+
 /*
  * Returns the pseudo-physical memory map as it was when the domain
  * was started (specified by XENMEM_set_memory_map).
@@ -217,4 +241,20 @@ DEFINE_GUEST_HANDLE_STRUCT(xen_memory_map);
  * during a driver critical region.
  */
 extern spinlock_t xen_reservation_lock;
+
+/*
+ * Unmaps the page appearing at a particular GPFN from the specified guest's
+ * pseudophysical address space.
+ * arg == addr of xen_remove_from_physmap_t.
+ */
+#define XENMEM_remove_from_physmap      15
+struct xen_remove_from_physmap {
+    /* Which domain to change the mapping for. */
+    domid_t domid;
+
+    /* GPFN of the current mapping of the page. */
+    xen_pfn_t gpfn;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_remove_from_physmap);
+
 #endif /* __XEN_PUBLIC_MEMORY_H__ */
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 6170abd53d0b..d6fe062cad6b 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -2,6 +2,7 @@
 #define INCLUDE_XEN_OPS_H
 
 #include <linux/percpu.h>
+#include <asm/xen/interface.h>
 
 DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
 
@@ -26,8 +27,11 @@ void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order);
 struct vm_area_struct;
 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);
+int xen_unmap_domain_mfn_range(struct vm_area_struct *vma,
+                               int numpgs, struct page **pages);
 
 bool xen_running_on_version_or_later(unsigned int major, unsigned int minor);
 #endif /* INCLUDE_XEN_OPS_H */