xen/xenpaging.HVMCOPY_gfn_paged_out.patch

Subject: xenpaging: handle HVMCOPY_gfn_paged_out in copy_from/to_user

copy_from_user_hvm can fail when __hvm_copy returns
HVMCOPY_gfn_paged_out for a referenced gfn, for example during guests
pagetable walk.  This has to be handled in some way.  One hypercall that
failed was do_memory_op/XENMEM_decrease_reservation which lead to a
BUG_ON balloon.c.  Since do_memory_op already has restart support for
the hypercall, copy_from_guest uses this existing retry code.  In
addition, cleanup on error was added to increase_reservation and
populate_physmap.

Signed-off-by: Olaf Hering <olaf@aepfle.de>

---
 xen/arch/x86/hvm/hvm.c |    4 ++++
 xen/common/memory.c    |   44 +++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 43 insertions(+), 5 deletions(-)

--- xen-4.0.1-testing.orig/xen/arch/x86/hvm/hvm.c
+++ xen-4.0.1-testing/xen/arch/x86/hvm/hvm.c
@@ -1853,6 +1853,8 @@ unsigned long copy_to_user_hvm(void *to,
 
     rc = hvm_copy_to_guest_virt_nofault((unsigned long)to, (void *)from,
                                         len, 0);
+    if ( rc == HVMCOPY_gfn_paged_out )
+        return -EAGAIN;
     return rc ? len : 0; /* fake a copy_to_user() return code */
 }
 
@@ -1869,6 +1871,8 @@ unsigned long copy_from_user_hvm(void *t
 #endif
 
     rc = hvm_copy_from_guest_virt_nofault(to, (unsigned long)from, len, 0);
+    if ( rc == HVMCOPY_gfn_paged_out )
+        return -EAGAIN;
     return rc ? len : 0; /* fake a copy_from_user() return code */
 }
 
--- xen-4.0.1-testing.orig/xen/common/memory.c
+++ xen-4.0.1-testing/xen/common/memory.c
@@ -47,6 +47,7 @@ static void increase_reservation(struct
 {
     struct page_info *page;
     unsigned long i;
+    unsigned long ctg_ret;
     xen_pfn_t mfn;
     struct domain *d = a->domain;
 
@@ -80,8 +81,14 @@ static void increase_reservation(struct
         if ( !guest_handle_is_null(a->extent_list) )
         {
             mfn = page_to_mfn(page);
-            if ( unlikely(__copy_to_guest_offset(a->extent_list, i, &mfn, 1)) )
+            ctg_ret = __copy_to_guest_offset(a->extent_list, i, &mfn, 1);
+            if ( unlikely(ctg_ret) )
+            {
+                free_domheap_pages(page, a->extent_order);
+                if ( (long)ctg_ret == -EAGAIN )
+                    a->preempted = 1;
                 goto out;
+            }
         }
     }
 
@@ -93,6 +100,7 @@ static void populate_physmap(struct memo
 {
     struct page_info *page;
     unsigned long i, j;
+    unsigned long cftg_ret;
     xen_pfn_t gpfn, mfn;
     struct domain *d = a->domain;
 
@@ -111,8 +119,13 @@ static void populate_physmap(struct memo
             goto out;
         }
 
-        if ( unlikely(__copy_from_guest_offset(&gpfn, a->extent_list, i, 1)) )
+        cftg_ret = __copy_from_guest_offset(&gpfn, a->extent_list, i, 1);
+        if ( unlikely(cftg_ret) )
+        {
+            if ( (long)cftg_ret == -EAGAIN )
+                a->preempted = 1;
             goto out;
+        }
 
         if ( a->memflags & MEMF_populate_on_demand )
         {
@@ -142,8 +155,17 @@ static void populate_physmap(struct memo
                     set_gpfn_from_mfn(mfn + j, gpfn + j);
 
                 /* Inform the domain of the new page's machine address. */ 
-                if ( unlikely(__copy_to_guest_offset(a->extent_list, i, &mfn, 1)) )
+                cftg_ret = __copy_to_guest_offset(a->extent_list, i, &mfn, 1);
+                if ( unlikely(cftg_ret) )
+                {
+                    for ( j = 0; j < (1 << a->extent_order); j++ )
+                        set_gpfn_from_mfn(mfn + j, INVALID_M2P_ENTRY);
+                    guest_physmap_remove_page(d, gpfn, mfn, a->extent_order);
+                    free_domheap_pages(page, a->extent_order);
+                    if ( (long)cftg_ret == -EAGAIN )
+                        a->preempted = 1;
                     goto out;
+                }
             }
         }
     }
@@ -212,6 +234,7 @@ int guest_remove_page(struct domain *d,
 static void decrease_reservation(struct memop_args *a)
 {
     unsigned long i, j;
+    unsigned long cfg_ret;
     xen_pfn_t gmfn;
 
     if ( !guest_handle_subrange_okay(a->extent_list, a->nr_done,
@@ -226,8 +249,13 @@ static void decrease_reservation(struct
             goto out;
         }
 
-        if ( unlikely(__copy_from_guest_offset(&gmfn, a->extent_list, i, 1)) )
+        cfg_ret = __copy_from_guest_offset(&gmfn, a->extent_list, i, 1);
+        if ( unlikely(cfg_ret) )
+        {
+            if ( (long)cfg_ret == -EAGAIN )
+                a->preempted = 1;
             goto out;
+        }
 
         if ( tb_init_done )
         {
@@ -511,6 +539,7 @@ long do_memory_op(unsigned long cmd, XEN
     int rc, op;
     unsigned int address_bits;
     unsigned long start_extent;
+    unsigned long cfg_ret;
     struct xen_memory_reservation reservation;
     struct memop_args args;
     domid_t domid;
@@ -524,8 +553,13 @@ long do_memory_op(unsigned long cmd, XEN
     case XENMEM_populate_physmap:
         start_extent = cmd >> MEMOP_EXTENT_SHIFT;
 
-        if ( copy_from_guest(&reservation, arg, 1) )
+        cfg_ret = copy_from_guest(&reservation, arg, 1);
+        if ( unlikely(cfg_ret) )
+        {
+            if ( (long)cfg_ret == -EAGAIN )
+                return hypercall_create_continuation(__HYPERVISOR_memory_op, "lh", cmd, arg);
             return start_extent;
+        }
 
         /* Is size too large for us to encode a continuation? */
         if ( reservation.nr_extents > (ULONG_MAX >> MEMOP_EXTENT_SHIFT) )