tools: VM generation ID save/restore and migrate.

Add code to track the address of the VM generation ID buffer across a
save/restore or migrate, and increment it as necessary.
The address of the buffer is written into xenstore by hvmloader at
boot time. It must be read from xenstore by the caller of
xc_domain_save() and then written back again by the caller of
xc_domain_restore().

Note that the changes to xc_save.c and xc_restore.c are merely
sufficient for them to build.

Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Committed-by: Ian Jackson <ian.jackson.citrix.com>

tools/libxc/ia64/xc_ia64_linux_restore.c

@@ -548,7 +548,9 @@ int
 xc_domain_restore(xc_interface *xch, int io_fd, uint32_t dom,
                   unsigned int store_evtchn, unsigned long *store_mfn,
                   unsigned int console_evtchn, unsigned long *console_mfn,
-                  unsigned int hvm, unsigned int pae, int superpages)
+                  unsigned int hvm, unsigned int pae, int superpages,
+                  int no_incr_generationid,
+                  unsigned long *vm_generationid_addr)
 {
     DECLARE_DOMCTL;
     int rc = 1;

tools/libxc/ia64/xc_ia64_linux_save.c

@@ -382,7 +382,8 @@ out:
 int
 xc_domain_save(xc_interface *xch, int io_fd, uint32_t dom, uint32_t max_iters,
                uint32_t max_factor, uint32_t flags,
-               struct save_callbacks* callbacks, int hvm)
+               struct save_callbacks* callbacks, int hvm,
+               unsigned long vm_generationid_addr)
 {
     DECLARE_DOMCTL;
     xc_dominfo_t info;

tools/libxc/xc_domain_restore.c

@@ -681,6 +681,7 @@ typedef struct {
     uint64_t console_pfn;
     uint64_t acpi_ioport_location;
     uint64_t viridian;
+    uint64_t vm_generationid_addr;
 } pagebuf_t;
 
 static int pagebuf_init(pagebuf_t* buf)
@@ -860,6 +861,17 @@ static int pagebuf_get_one(xc_interface *xch, struct restore_ctx *ctx,
         }
         return compbuf_size;
 
+    case XC_SAVE_ID_HVM_GENERATION_ID_ADDR:
+        /* Skip padding 4 bytes then read the generation id buffer location. */
+        if ( RDEXACT(fd, &buf->vm_generationid_addr, sizeof(uint32_t)) ||
+             RDEXACT(fd, &buf->vm_generationid_addr, sizeof(uint64_t)) )
+        {
+            PERROR("error read the generation id buffer location");
+            return -1;
+        }
+        DPRINTF("read generation id buffer address");
+        return pagebuf_get_one(xch, ctx, buf, fd, dom);
+
     default:
         if ( (count > MAX_BATCH_SIZE) || (count < 0) ) {
             ERROR("Max batch size exceeded (%d). Giving up.", count);
@@ -1248,7 +1260,9 @@ static int apply_batch(xc_interface *xch, uint32_t dom, struct restore_ctx *ctx,
 int xc_domain_restore(xc_interface *xch, int io_fd, uint32_t dom,
                       unsigned int store_evtchn, unsigned long *store_mfn,
                       unsigned int console_evtchn, unsigned long *console_mfn,
-                      unsigned int hvm, unsigned int pae, int superpages)
+                      unsigned int hvm, unsigned int pae, int superpages,
+                      int no_incr_generationid,
+                      unsigned long *vm_generationid_addr)
 {
     DECLARE_DOMCTL;
     int rc = 1, frc, i, j, n, m, pae_extended_cr3 = 0, ext_vcpucontext = 0;
@@ -1449,6 +1463,39 @@ int xc_domain_restore(xc_interface *xch, int io_fd, uint32_t dom,
                 xc_set_hvm_param(xch, dom, HVM_PARAM_VM86_TSS, pagebuf.vm86_tss);
             if ( pagebuf.console_pfn )
                 console_pfn = pagebuf.console_pfn;
+            if ( pagebuf.vm_generationid_addr ) {
+                if ( !no_incr_generationid ) {
+                    unsigned int offset;
+                    unsigned char *buf;
+                    unsigned long long generationid;
+
+                    /*
+                     * Map the VM generation id buffer and inject the new value.
+                     */
+
+                    pfn = pagebuf.vm_generationid_addr >> PAGE_SHIFT;
+                    offset = pagebuf.vm_generationid_addr & (PAGE_SIZE - 1);
+                
+                    if ( (pfn >= dinfo->p2m_size) ||
+                         (pfn_type[pfn] != XEN_DOMCTL_PFINFO_NOTAB) )
+                    {
+                        ERROR("generation id buffer frame is bad");
+                        goto out;
+                    }
+
+                    mfn = ctx->p2m[pfn];
+                    buf = xc_map_foreign_range(xch, dom, PAGE_SIZE,
+                                               PROT_READ | PROT_WRITE, mfn);
+
+                    generationid = *(unsigned long long *)(buf + offset);
+                    *(unsigned long long *)(buf + offset) = generationid + 1;
+
+                    munmap(buf, PAGE_SIZE);
+                }
+
+                *vm_generationid_addr = pagebuf.vm_generationid_addr;
+            }
+
             break;  /* our work here is done */
         }
 

tools/libxc/xc_domain_save.c

@@ -804,7 +804,8 @@ static int save_tsc_info(xc_interface *xch, uint32_t dom, int io_fd)
 
 int xc_domain_save(xc_interface *xch, int io_fd, uint32_t dom, uint32_t max_iters,
                    uint32_t max_factor, uint32_t flags,
-                   struct save_callbacks* callbacks, int hvm)
+                   struct save_callbacks* callbacks, int hvm,
+                   unsigned long vm_generationid_addr)
 {
     xc_dominfo_t info;
     DECLARE_DOMCTL;
@@ -1616,6 +1617,16 @@ int xc_domain_save(xc_interface *xch, int io_fd, uint32_t dom, uint32_t max_iter
             uint64_t data;
         } chunk = { 0, };
 
+        chunk.id = XC_SAVE_ID_HVM_GENERATION_ID_ADDR;
+        chunk.data = vm_generationid_addr;
+
+        if ( (chunk.data != 0) &&
+             wrexact(io_fd, &chunk, sizeof(chunk)) )
+        {
+            PERROR("Error when writing the generation id buffer location for guest");
+            goto out;
+        }
+
         chunk.id = XC_SAVE_ID_HVM_IDENT_PT;
         chunk.data = 0;
         xc_get_hvm_param(xch, dom, HVM_PARAM_IDENT_PT,

tools/libxc/xenguest.h

@@ -58,7 +58,8 @@ struct save_callbacks {
  */
 int xc_domain_save(xc_interface *xch, int io_fd, uint32_t dom, uint32_t max_iters,
                    uint32_t max_factor, uint32_t flags /* XCFLAGS_xxx */,
-                   struct save_callbacks* callbacks, int hvm);
+                   struct save_callbacks* callbacks, int hvm,
+                   unsigned long vm_generationid_addr);
 
 
 /**
@@ -72,12 +73,16 @@ int xc_domain_save(xc_interface *xch, int io_fd, uint32_t dom, uint32_t max_iter
  * @parm hvm non-zero if this is a HVM restore
  * @parm pae non-zero if this HVM domain has PAE support enabled
  * @parm superpages non-zero to allocate guest memory with superpages
+ * @parm no_incr_generationid non-zero if generation id is NOT to be incremented
+ * @parm vm_generationid_addr returned with the address of the generation id buffer
  * @return 0 on success, -1 on failure
  */
 int xc_domain_restore(xc_interface *xch, int io_fd, uint32_t dom,
                       unsigned int store_evtchn, unsigned long *store_mfn,
                       unsigned int console_evtchn, unsigned long *console_mfn,
-                      unsigned int hvm, unsigned int pae, int superpages);
+                      unsigned int hvm, unsigned int pae, int superpages,
+                      int no_incr_generationid,
+		      unsigned long *vm_generationid_addr);
 /**
  * xc_domain_restore writes a file to disk that contains the device
  * model saved state.

tools/libxc/xg_save_restore.h

@@ -253,6 +253,7 @@
 #define XC_SAVE_ID_HVM_VIRIDIAN       -11
 #define XC_SAVE_ID_COMPRESSED_DATA    -12 /* Marker to indicate arrival of compressed data */
 #define XC_SAVE_ID_ENABLE_COMPRESSION -13 /* Marker to enable compression logic at receiver side */
+#define XC_SAVE_ID_HVM_GENERATION_ID_ADDR -14
 
 /*
 ** We process save/restore/migrate in batches of pages; the below

tools/libxl/libxl_create.c

@@ -99,6 +99,7 @@ int libxl_init_build_info(libxl_ctx *ctx,
         b_info->u.hvm.vpt_align = 1;
         b_info->u.hvm.timer_mode = 1;
         b_info->u.hvm.nested_hvm = 0;
+        b_info->u.hvm.no_incr_generationid = 0;
         break;
     case LIBXL_DOMAIN_TYPE_PV:
         b_info->u.pv.slack_memkb = 8 * 1024;

tools/libxl/libxl_dom.c

@@ -106,6 +106,7 @@ int libxl__build_pre(libxl__gc *gc, uint32_t domid,
 
     state->store_port = xc_evtchn_alloc_unbound(ctx->xch, domid, 0);
     state->console_port = xc_evtchn_alloc_unbound(ctx->xch, domid, 0);
+    state->vm_generationid_addr = 0;
     return 0;
 }
 
@@ -117,7 +118,7 @@ int libxl__build_post(libxl__gc *gc, uint32_t domid,
     libxl_ctx *ctx = libxl__gc_owner(gc);
     char *dom_path, *vm_path;
     xs_transaction_t t;
-    char **ents;
+    char **ents, **hvm_ents;
     int i;
 
     libxl_cpuid_apply_policy(ctx, domid);
@@ -143,6 +144,13 @@ int libxl__build_post(libxl__gc *gc, uint32_t domid,
                             ? "offline" : "online";
     }
 
+    hvm_ents = NULL;
+    if (info->type == LIBXL_DOMAIN_TYPE_HVM) {
+        hvm_ents = libxl__calloc(gc, 3, sizeof(char *));
+        hvm_ents[0] = "hvmloader/generation-id-address";
+        hvm_ents[1] = libxl__sprintf(gc, "0x%lx", state->vm_generationid_addr);
+    }
+
     dom_path = libxl__xs_get_dompath(gc, domid);
     if (!dom_path) {
         return ERROR_FAIL;
@@ -153,6 +161,9 @@ retry_transaction:
     t = xs_transaction_start(ctx->xsh);
 
     libxl__xs_writev(gc, t, dom_path, ents);
+    if (info->type == LIBXL_DOMAIN_TYPE_HVM)
+        libxl__xs_writev(gc, t, dom_path, hvm_ents);
+
     libxl__xs_writev(gc, t, dom_path, local_ents);
     libxl__xs_writev(gc, t, vm_path, vms_ents);
 
@@ -356,16 +367,19 @@ int libxl__domain_restore_common(libxl__gc *gc, uint32_t domid,
     /* read signature */
     int rc;
     int hvm, pae, superpages;
+    int no_incr_generationid;
     switch (info->type) {
     case LIBXL_DOMAIN_TYPE_HVM:
         hvm = 1;
         superpages = 1;
         pae = info->u.hvm.pae;
+        no_incr_generationid = info->u.hvm.no_incr_generationid;
         break;
     case LIBXL_DOMAIN_TYPE_PV:
         hvm = 0;
         superpages = 0;
         pae = 1;
+        no_incr_generationid = 0;
         break;
     default:
         return ERROR_INVAL;
@@ -373,7 +387,8 @@ int libxl__domain_restore_common(libxl__gc *gc, uint32_t domid,
     rc = xc_domain_restore(ctx->xch, fd, domid,
                            state->store_port, &state->store_mfn,
                            state->console_port, &state->console_mfn,
-                           hvm, pae, superpages);
+                           hvm, pae, superpages, no_incr_generationid,
+                           &state->vm_generationid_addr);
     if ( rc ) {
         LIBXL__LOG_ERRNO(ctx, LIBXL__LOG_ERROR, "restoring domain");
         return ERROR_FAIL;
@@ -538,12 +553,23 @@ int libxl__domain_suspend_common(libxl__gc *gc, uint32_t domid, int fd,
     struct save_callbacks callbacks;
     struct suspendinfo si;
     int hvm, rc = ERROR_FAIL;
+    unsigned long vm_generationid_addr;
 
     switch (type) {
-    case LIBXL_DOMAIN_TYPE_HVM:
+    case LIBXL_DOMAIN_TYPE_HVM: {
+        char *path;
+        char *addr;
+
+        path = libxl__sprintf(gc, "%s/hvmloader/generation-id-address",
+                              libxl__xs_get_dompath(gc, domid));
+        addr = libxl__xs_read(gc, XBT_NULL, path);
+
+        vm_generationid_addr = (addr) ? strtoul(addr, NULL, 0) : 0;
         hvm = 1;
         break;
+    }
     case LIBXL_DOMAIN_TYPE_PV:
+        vm_generationid_addr = 0;
         hvm = 0;
         break;
     default:
@@ -581,7 +607,8 @@ int libxl__domain_suspend_common(libxl__gc *gc, uint32_t domid, int fd,
     callbacks.switch_qemu_logdirty = libxl__domain_suspend_common_switch_qemu_logdirty;
     callbacks.data = &si;
 
-    rc = xc_domain_save(ctx->xch, fd, domid, 0, 0, flags, &callbacks, hvm);
+    rc = xc_domain_save(ctx->xch, fd, domid, 0, 0, flags, &callbacks,
+                        hvm, vm_generationid_addr);
     if ( rc ) {
         LIBXL__LOG_ERRNO(ctx, LIBXL__LOG_ERROR, "saving domain: %s",
                          si.guest_responded ?

tools/libxl/libxl_internal.h

@@ -223,6 +223,7 @@ typedef struct {
 
     uint32_t console_port;
     unsigned long console_mfn;
+    unsigned long vm_generationid_addr;
 } libxl__domain_build_state;
 
 _hidden int libxl__build_pre(libxl__gc *gc, uint32_t domid,

tools/libxl/libxl_types.idl

@@ -184,6 +184,7 @@ libxl_domain_build_info = Struct("domain_build_info",[
                                        ("vpt_align", bool),
                                        ("timer_mode", integer),
                                        ("nested_hvm", bool),
+                                       ("no_incr_generationid", bool),
                                        ])),
                  ("pv", Struct(None, [("kernel", libxl_file_reference),
                                       ("slack_memkb", uint32),

tools/libxl/xl_cmdimpl.c

@@ -360,6 +360,8 @@ static void printf_info(int domid,
         printf("\t\t\t(vpt_align %d)\n", b_info->u.hvm.vpt_align);
         printf("\t\t\t(timer_mode %d)\n", b_info->u.hvm.timer_mode);
         printf("\t\t\t(nestedhvm %d)\n", b_info->u.hvm.nested_hvm);
+        printf("\t\t\t(no_incr_generationid %d)\n",
+                    b_info->u.hvm.no_incr_generationid);
 
         printf("\t\t\t(device_model %s)\n", dm_info->device_model ? : "default");
         printf("\t\t\t(videoram %d)\n", dm_info->videoram);
@@ -1364,6 +1366,7 @@ struct domain_create {
     const char *restore_file;
     int migrate_fd; /* -1 means none */
     char **migration_domname_r; /* from malloc */
+    int no_incr_generationid;
 };
 
 static int freemem(libxl_domain_build_info *b_info, libxl_device_model_info *dm_info)
@@ -1577,6 +1580,8 @@ static int create_domain(struct domain_create *dom_info)
         }
     }
 
+    d_config.b_info.u.hvm.no_incr_generationid = dom_info->no_incr_generationid;
+
     if (debug || dom_info->dryrun)
         printf_info(-1, &d_config, &d_config.dm_info);
 
@@ -2817,6 +2822,7 @@ static void migrate_receive(int debug, int daemonize, int monitor)
     dom_info.restore_file = "incoming migration stream";
     dom_info.migrate_fd = 0; /* stdin */
     dom_info.migration_domname_r = &migration_domname;
+    dom_info.no_incr_generationid = 1;
 
     rc = create_domain(&dom_info);
     if (rc < 0) {

tools/python/xen/lowlevel/checkpoint/libcheckpoint.c

@@ -175,6 +175,7 @@ int checkpoint_start(checkpoint_state* s, int fd,
 {
     int hvm, rc;
     int flags = XCFLAGS_LIVE;
+    unsigned long vm_generationid_addr;
 
     if (!s->domid) {
        s->errstr = "checkpoint state not opened";
@@ -185,16 +186,28 @@ int checkpoint_start(checkpoint_state* s, int fd,
 
     hvm = s->domtype > dt_pv;
     if (hvm) {
+       char path[128];
+       char *addr;
+
+       sprintf(path, "/local/domain/%u/hvmloader/generation-id-address", s->domid);
+       addr = xs_read(s->xsh, XBT_NULL, path, NULL);
+
+       vm_generationid_addr = (addr) ? strtoul(addr, NULL, 0) : 0;
+       free(addr);
+
        flags |= XCFLAGS_HVM;
        if (switch_qemu_logdirty(s, 1))
            return -1;
+    } else {
+       vm_generationid_addr = 0;
     }
     if (remus_flags & CHECKPOINT_FLAGS_COMPRESSION)
       flags |= XCFLAGS_CHECKPOINT_COMPRESS;
 
     callbacks->switch_qemu_logdirty = noop_switch_logdirty;
 
-    rc = xc_domain_save(s->xch, fd, s->domid, 0, 0, flags, callbacks, hvm);
+    rc = xc_domain_save(s->xch, fd, s->domid, 0, 0, flags, callbacks, hvm,
+                        vm_generationid_addr);
 
     if (hvm)
        switch_qemu_logdirty(s, 0);

tools/xcutils/xc_restore.c

@@ -46,7 +46,8 @@ main(int argc, char **argv)
 	    superpages = !!hvm;
 
     ret = xc_domain_restore(xch, io_fd, domid, store_evtchn, &store_mfn,
-                            console_evtchn, &console_mfn, hvm, pae, superpages);
+                            console_evtchn, &console_mfn, hvm, pae, superpages,
+                            0, NULL);
 
     if ( ret == 0 )
     {

tools/xcutils/xc_save.c

@@ -208,7 +208,7 @@ main(int argc, char **argv)
     callbacks.suspend = suspend;
     callbacks.switch_qemu_logdirty = switch_qemu_logdirty;
     ret = xc_domain_save(si.xch, io_fd, si.domid, maxit, max_f, si.flags, 
-                         &callbacks, !!(si.flags & XCFLAGS_HVM));
+                         &callbacks, !!(si.flags & XCFLAGS_HVM), 0);
 
     if (si.suspend_evtchn > 0)
 	 xc_suspend_evtchn_release(si.xch, si.xce, si.domid, si.suspend_evtchn);