[PATCH 17/29] tools/libxc: x86 HVM restore code

[Andrew Cooper <andrew.cooper3@citrix.com>]

Restore the x86 HVM specific parts of a domain.  This is the HVM_CONTEXT and
HVM_PARAMS records.

There is no need for any page localisation.

This also includes writing the trailing qemu save record to a file because
this is what libxc currently does.  This is intended to be moved into libxl
proper in the future.

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
---
 tools/libxc/saverestore/common.h          |    1 +
 tools/libxc/saverestore/restore_x86_hvm.c |  355 +++++++++++++++++++++++++++++
 2 files changed, 356 insertions(+)
 create mode 100644 tools/libxc/saverestore/restore_x86_hvm.c

diff --git a/tools/libxc/saverestore/common.h b/tools/libxc/saverestore/common.h
index de7063e..193dd0e 100644
--- a/tools/libxc/saverestore/common.h
+++ b/tools/libxc/saverestore/common.h
@@ -286,6 +286,7 @@ extern struct xc_sr_save_ops save_ops_x86_pv;
 extern struct xc_sr_save_ops save_ops_x86_hvm;
 
 extern struct xc_sr_restore_ops restore_ops_x86_pv;
+extern struct xc_sr_restore_ops restore_ops_x86_hvm;
 
 struct xc_sr_record
 {
diff --git a/tools/libxc/saverestore/restore_x86_hvm.c b/tools/libxc/saverestore/restore_x86_hvm.c
new file mode 100644
index 0000000..c65f9ac
--- /dev/null
+++ b/tools/libxc/saverestore/restore_x86_hvm.c
@@ -0,0 +1,355 @@
+#include <assert.h>
+#include <arpa/inet.h>
+
+#include "common_x86.h"
+
+/* TODO: remove */
+static int handle_toolstack(struct xc_sr_context *ctx, struct xc_sr_record *rec)
+{
+    xc_interface *xch = ctx->xch;
+    int rc;
+
+    if ( !ctx->restore.callbacks || !ctx->restore.callbacks->toolstack_restore )
+        return 0;
+
+    rc = ctx->restore.callbacks->toolstack_restore(ctx->domid, rec->data, rec->length,
+                                                   ctx->restore.callbacks->data);
+    if ( rc < 0 )
+        PERROR("restoring toolstack");
+    return rc;
+}
+
+/*
+ * Process an HVM_CONTEXT record from the stream.
+ */
+static int handle_hvm_context(struct xc_sr_context *ctx, struct xc_sr_record *rec)
+{
+    xc_interface *xch = ctx->xch;
+    void *p;
+
+    p = malloc(rec->length);
+    if ( !p )
+    {
+        ERROR("Unable to allocate %u bytes for hvm context", rec->length);
+        return -1;
+    }
+
+    free(ctx->x86_hvm.restore.context);
+
+    ctx->x86_hvm.restore.context = memcpy(p, rec->data, rec->length);
+    ctx->x86_hvm.restore.contextsz = rec->length;
+
+    return 0;
+}
+
+/*
+ * Process an HVM_PARAMS record from the stream.
+ */
+static int handle_hvm_params(struct xc_sr_context *ctx, struct xc_sr_record *rec)
+{
+    xc_interface *xch = ctx->xch;
+    struct xc_sr_rec_hvm_params *hdr = rec->data;
+    struct xc_sr_rec_hvm_params_entry *entry = hdr->param;
+    unsigned int i;
+    int rc;
+
+    if ( rec->length < sizeof(*hdr)
+         || rec->length < sizeof(*hdr) + hdr->count * sizeof(*entry) )
+    {
+        ERROR("hvm_params record is too short");
+        return -1;
+    }
+
+    for ( i = 0; i < hdr->count; i++, entry++ )
+    {
+        switch ( entry->index )
+        {
+        case HVM_PARAM_CONSOLE_PFN:
+            ctx->restore.console_mfn = entry->value;
+            xc_clear_domain_page(xch, ctx->domid, entry->value);
+            break;
+        case HVM_PARAM_STORE_PFN:
+            ctx->restore.xenstore_mfn = entry->value;
+            xc_clear_domain_page(xch, ctx->domid, entry->value);
+            break;
+        case HVM_PARAM_IOREQ_PFN:
+        case HVM_PARAM_BUFIOREQ_PFN:
+            xc_clear_domain_page(xch, ctx->domid, entry->value);
+            break;
+        }
+
+        rc = xc_set_hvm_param(xch, ctx->domid, entry->index, entry->value);
+        if ( rc < 0 )
+        {
+            PERROR("set HVM param %"PRId64" = 0x%016"PRIx64,
+                   entry->index, entry->value);
+            return rc;
+        }
+    }
+    return 0;
+}
+
+/* TODO: remove */
+static __attribute__((unused)) int dump_qemu(struct xc_sr_context *ctx)
+{
+#ifdef XG_DUMP_QEMU
+    xc_interface *xch = ctx->xch;
+    char qemusig[21], path[256];
+    uint32_t qlen;
+    void *qbuf = NULL;
+    int rc = -1;
+    FILE *fp = NULL;
+
+    if ( read_exact(ctx->fd, qemusig, sizeof(qemusig)) )
+    {
+        PERROR("Error reading QEMU signature");
+        goto out;
+    }
+
+    if ( !memcmp(qemusig, "DeviceModelRecord0002", sizeof(qemusig)) )
+    {
+        if ( read_exact(ctx->fd, &qlen, sizeof(qlen)) )
+        {
+            PERROR("Error reading QEMU record length");
+            goto out;
+        }
+
+        qbuf = malloc(qlen);
+        if ( !qbuf )
+        {
+            PERROR("no memory for device model state");
+            goto out;
+        }
+
+        if ( read_exact(ctx->fd, qbuf, qlen) )
+        {
+            PERROR("Error reading device model state");
+            goto out;
+        }
+    }
+    /* XenServer hack, until Xapi compatibility code is written. */
+    else if ( !memcmp(qemusig, "QemuDeviceModelRecord", sizeof(qemusig)) )
+    {
+        char head[9];
+
+        if ( read_exact(ctx->fd, &head, sizeof(head)) )
+        {
+            PERROR("Error reading QEMU record head");
+            goto out;
+        }
+
+        if ( head[0] == '\n' && !memcmp(&head[5], "QEVM", 4) )
+            qlen = ntohl(*((uint32_t*)&head[1])) - 4;
+        else
+        {
+            ERROR("Unrecongised data following %s", qemusig);
+            goto out;
+        }
+
+        qbuf = malloc(qlen);
+        if ( !qbuf )
+        {
+            PERROR("no memory for device model state");
+            goto out;
+        }
+
+        memcpy(qbuf, "QEVM", 4);
+        if ( read_exact(ctx->fd, &((uint8_t*)qbuf)[4], qlen - 4) )
+        {
+            PERROR("Error reading device model state");
+            goto out;
+        }
+    }
+    else
+    {
+        ERROR("Invalid device model state signature '%*.*s'",
+              (int)sizeof(qemusig), (int)sizeof(qemusig), qemusig);
+        goto out;
+    }
+
+    sprintf(path, XC_DEVICE_MODEL_RESTORE_FILE".%u", ctx->domid);
+    fp = fopen(path, "wb");
+    if ( !fp )
+    {
+        PERROR("Failed to open '%s' for writing", path);
+        goto out;
+    }
+
+    DPRINTF("Writing %u bytes of QEMU data", qlen);
+    if ( fwrite(qbuf, 1, qlen, fp) != qlen )
+    {
+        PERROR("Failed to write %u bytes of QEMU data", qlen);
+        goto out;
+    }
+
+    rc = 0;
+
+ out:
+    if ( fp )
+        fclose(fp);
+    free(qbuf);
+
+    return rc;
+#else
+    return 0;
+#endif
+}
+
+/* restore_ops function. */
+static bool x86_hvm_pfn_is_valid(const struct xc_sr_context *ctx, xen_pfn_t pfn)
+{
+    return true;
+}
+
+/* restore_ops function. */
+static xen_pfn_t x86_hvm_pfn_to_gfn(const struct xc_sr_context *ctx, xen_pfn_t pfn)
+{
+    return pfn;
+}
+
+/* restore_ops function. */
+static void x86_hvm_set_gfn(struct xc_sr_context *ctx, xen_pfn_t pfn,
+                            xen_pfn_t gfn)
+{
+    /* no op */
+}
+
+/* restore_ops function. */
+static void x86_hvm_set_page_type(struct xc_sr_context *ctx, xen_pfn_t pfn, xen_pfn_t type)
+{
+    /* no-op */
+}
+
+/* restore_ops function. */
+static int x86_hvm_localise_page(struct xc_sr_context *ctx, uint32_t type, void *page)
+{
+    /* no-op */
+    return 0;
+}
+
+/*
+ * restore_ops function. Confirms the stream matches the domain.
+ */
+static int x86_hvm_setup(struct xc_sr_context *ctx)
+{
+    xc_interface *xch = ctx->xch;
+
+    if ( ctx->restore.guest_type != DHDR_TYPE_X86_HVM )
+    {
+        ERROR("Unable to restore %s domain into an x86_hvm domain",
+              dhdr_type_to_str(ctx->restore.guest_type));
+        return -1;
+    }
+    else if ( ctx->restore.guest_page_size != PAGE_SIZE )
+    {
+        ERROR("Invalid page size %d for x86_hvm domains",
+              ctx->restore.guest_page_size);
+        return -1;
+    }
+
+    return 0;
+}
+
+/*
+ * restore_ops function.
+ */
+static int x86_hvm_process_record(struct xc_sr_context *ctx, struct xc_sr_record *rec)
+{
+    switch ( rec->type )
+    {
+    case REC_TYPE_TSC_INFO:
+        return handle_tsc_info(ctx, rec);
+
+    case REC_TYPE_HVM_CONTEXT:
+        return handle_hvm_context(ctx, rec);
+
+    case REC_TYPE_HVM_PARAMS:
+        return handle_hvm_params(ctx, rec);
+
+    case REC_TYPE_TOOLSTACK:
+        return handle_toolstack(ctx, rec);
+
+    default:
+        return RECORD_NOT_PROCESSED;
+    }
+}
+
+/*
+ * restore_ops function.  Sets extra hvm parameters and seeds the grant table.
+ */
+static int x86_hvm_stream_complete(struct xc_sr_context *ctx)
+{
+    xc_interface *xch = ctx->xch;
+    int rc;
+
+    rc = xc_set_hvm_param(xch, ctx->domid, HVM_PARAM_STORE_EVTCHN,
+                          ctx->restore.xenstore_evtchn);
+    if ( rc )
+    {
+        PERROR("Failed to set HVM_PARAM_STORE_EVTCHN");
+        return rc;
+    }
+
+    rc = xc_domain_hvm_setcontext(xch, ctx->domid,
+                                  ctx->x86_hvm.restore.context,
+                                  ctx->x86_hvm.restore.contextsz);
+    if ( rc < 0 )
+    {
+        PERROR("Unable to restore HVM context");
+        return rc;
+    }
+
+    rc = xc_dom_gnttab_hvm_seed(xch, ctx->domid,
+                                ctx->restore.console_mfn,
+                                ctx->restore.xenstore_mfn,
+                                ctx->restore.console_domid,
+                                ctx->restore.xenstore_domid);
+    if ( rc )
+    {
+        PERROR("Failed to seed grant table");
+        return rc;
+    }
+
+    /*
+     * FIXME: reading the device model state from the stream should be
+     * done by libxl.
+     */
+    rc = dump_qemu(ctx);
+    if ( rc )
+    {
+        ERROR("Failed to dump qemu");
+        return rc;
+    }
+
+    return rc;
+}
+
+static int x86_hvm_cleanup(struct xc_sr_context *ctx)
+{
+    free(ctx->x86_hvm.restore.context);
+
+    return 0;
+}
+
+struct xc_sr_restore_ops restore_ops_x86_hvm =
+{
+    .pfn_is_valid    = x86_hvm_pfn_is_valid,
+    .pfn_to_gfn      = x86_hvm_pfn_to_gfn,
+    .set_gfn         = x86_hvm_set_gfn,
+    .set_page_type   = x86_hvm_set_page_type,
+    .localise_page   = x86_hvm_localise_page,
+    .setup           = x86_hvm_setup,
+    .process_record  = x86_hvm_process_record,
+    .stream_complete = x86_hvm_stream_complete,
+    .cleanup         = x86_hvm_cleanup,
+};
+
+/*
+ * Local variables:
+ * mode: C
+ * c-file-style: "BSD"
+ * c-basic-offset: 4
+ * tab-width: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
-- 
1.7.10.4