xc: use XENMEM_claim_pages hypercall during guest creation.

We add an extra parameter to the structures passed to the
PV routine (arch_setup_meminit) and HVM routine (setup_guest)
that determines whether the claim hypercall is to be done.

The contents of the 'claim_enabled' is defined as an 'int'
in case the hypercall expands in the future with extra
flags (for example for per-NUMA allocation). For right now
the proper values are: 0 to disable it or 1 to enable
it.

If the hypervisor does not support this function, the
xc_domain_claim_pages and xc_domain_get_outstanding_pages
will silently return 0 (and set errno to zero).

Signed-off-by: Dan Magenheimer <dan.magenheimer@oracle.com>
[v2: Updated per Ian's recommendations]
[v3: Added support for out-of-sync hypervisor]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Ian Jackson <ian.jackson@eu.citrix.com>

tools/libxc/xc_dom.h

@@ -135,6 +135,7 @@ struct xc_dom_image {
     domid_t guest_domid;
     int8_t vhpt_size_log2; /* for IA64 */
     int8_t superpages;
+    int claim_enabled; /* 0 by default, 1 enables it */
     int shadow_enabled;
 
     int xen_version;

tools/libxc/xc_dom_x86.c

@@ -706,6 +706,13 @@ int arch_setup_meminit(struct xc_dom_image *dom)
     }
     else
     {
+        /* try to claim pages for early warning of insufficient memory avail */
+        if ( dom->claim_enabled ) {
+            rc = xc_domain_claim_pages(dom->xch, dom->guest_domid,
+                                       dom->total_pages);
+            if ( rc )
+                return rc;
+        }
         /* setup initial p2m */
         for ( pfn = 0; pfn < dom->total_pages; pfn++ )
             dom->p2m_host[pfn] = pfn;
@@ -722,6 +729,11 @@ int arch_setup_meminit(struct xc_dom_image *dom)
                 dom->xch, dom->guest_domid, allocsz,
                 0, 0, &dom->p2m_host[i]);
         }
+
+        /* Ensure no unclaimed pages are left unused.
+         * OK to call if hadn't done the earlier claim call. */
+        (void)xc_domain_claim_pages(dom->xch, dom->guest_domid,
+                                    0 /* cancels the claim */);
     }
 
     return rc;

tools/libxc/xc_domain.c

@@ -775,6 +775,36 @@ int xc_domain_add_to_physmap(xc_interface *xch,
     return do_memory_op(xch, XENMEM_add_to_physmap, &xatp, sizeof(xatp));
 }
 
+int xc_domain_claim_pages(xc_interface *xch,
+                               uint32_t domid,
+                               unsigned long nr_pages)
+{
+    int err;
+    struct xen_memory_reservation reservation = {
+        .nr_extents   = nr_pages,
+        .extent_order = 0,
+        .mem_flags    = 0, /* no flags */
+        .domid        = domid
+    };
+
+    set_xen_guest_handle(reservation.extent_start, HYPERCALL_BUFFER_NULL);
+
+    err = do_memory_op(xch, XENMEM_claim_pages, &reservation, sizeof(reservation));
+    /* Ignore it if the hypervisor does not support the call. */
+    if (err == -1 && errno == ENOSYS)
+        err = errno = 0;
+    return err;
+}
+unsigned long xc_domain_get_outstanding_pages(xc_interface *xch)
+{
+    long ret = do_memory_op(xch, XENMEM_get_outstanding_pages, NULL, 0);
+
+    /* Ignore it if the hypervisor does not support the call. */
+    if (ret == -1 && errno == ENOSYS)
+        ret = errno = 0;
+    return ret;
+}
+
 int xc_domain_populate_physmap(xc_interface *xch,
                                uint32_t domid,
                                unsigned long nr_extents,

tools/libxc/xc_hvm_build_x86.c

@@ -252,6 +252,7 @@ static int setup_guest(xc_interface *xch,
     unsigned long stat_normal_pages = 0, stat_2mb_pages = 0, 
         stat_1gb_pages = 0;
     int pod_mode = 0;
+    int claim_enabled = args->claim_enabled;
 
     if ( nr_pages > target_pages )
         pod_mode = XENMEMF_populate_on_demand;
@@ -329,6 +330,16 @@ static int setup_guest(xc_interface *xch,
         xch, dom, 0xa0, 0, pod_mode, &page_array[0x00]);
     cur_pages = 0xc0;
     stat_normal_pages = 0xc0;
+
+    /* try to claim pages for early warning of insufficient memory available */
+    if ( claim_enabled ) {
+        rc = xc_domain_claim_pages(xch, dom, nr_pages - cur_pages);
+        if ( rc != 0 )
+        {
+            PERROR("Could not allocate memory for HVM guest as we cannot claim memory!");
+            goto error_out;
+        }
+    }
     while ( (rc == 0) && (nr_pages > cur_pages) )
     {
         /* Clip count to maximum 1GB extent. */
@@ -506,12 +517,16 @@ static int setup_guest(xc_interface *xch,
         munmap(page0, PAGE_SIZE);
     }
 
-    free(page_array);
-    return 0;
-
+    rc = 0;
+    goto out;
  error_out:
+    rc = -1;
+ out:
+    /* ensure no unclaimed pages are left unused */
+    xc_domain_claim_pages(xch, dom, 0 /* cancels the claim */);
+
     free(page_array);
-    return -1;
+    return rc;
 }
 
 /* xc_hvm_build:

tools/libxc/xenctrl.h

@@ -1133,6 +1133,12 @@ int xc_domain_populate_physmap_exact(xc_interface *xch,
                                      unsigned int mem_flags,
                                      xen_pfn_t *extent_start);
 
+int xc_domain_claim_pages(xc_interface *xch,
+                               uint32_t domid,
+                               unsigned long nr_pages);
+
+unsigned long xc_domain_get_outstanding_pages(xc_interface *xch);
+
 int xc_domain_memory_exchange_pages(xc_interface *xch,
                                     int domid,
                                     unsigned long nr_in_extents,

tools/libxc/xenguest.h

@@ -231,6 +231,8 @@ struct xc_hvm_build_args {
 
     /* Extra SMBIOS structures passed to HVMLOADER */
     struct xc_hvm_firmware_module smbios_module;
+    /* Whether to use claim hypercall (1 - enable, 0 - disable). */
+    int claim_enabled;
 };
 
 /**