xen/libxc-sr-restore-handle_buffered_page_data.patch

From: Olaf Hering <olaf@aepfle.de>
Date: Tue, 27 Oct 2020 19:21:50 +0100
Subject: libxc sr restore handle_buffered_page_data

tools: restore: split handle_page_data

handle_page_data must be able to read directly into mapped guest memory.
This will avoid unneccesary memcpy calls for data that can be consumed verbatim.

Split the various steps of record processing:
- move processing to handle_buffered_page_data
- adjust xenforeignmemory_map to set errno in case of failure
- adjust verify mode to set errno in case of failure

This change is preparation for future changes in handle_page_data,
no change in behavior is intended.

Signed-off-by: Olaf Hering <olaf@aepfle.de>
---
 tools/libs/guest/xg_sr_common.h  |   4 +
 tools/libs/guest/xg_sr_restore.c | 320 ++++++++++++++++++++-----------
 2 files changed, 207 insertions(+), 117 deletions(-)

--- a/tools/libs/guest/xg_sr_common.h
+++ b/tools/libs/guest/xg_sr_common.h
@@ -262,6 +262,10 @@ struct xc_sr_context
             int *map_errs;
             xen_pfn_t *pp_pfns;
             xen_pfn_t *pp_mfns;
+            void **guest_data;
+
+            void *guest_mapping;
+            uint32_t nr_mapped_pages;
 
             int send_back_fd;
             unsigned long p2m_size;
--- a/tools/libs/guest/xg_sr_restore.c
+++ b/tools/libs/guest/xg_sr_restore.c
@@ -183,121 +183,18 @@ int populate_pfns(struct xc_sr_context *
     return rc;
 }
 
-/*
- * Given a list of pfns, their types, and a block of page data from the
- * stream, populate and record their types, map the relevant subset and copy
- * the data into the guest.
- */
-static int process_page_data(struct xc_sr_context *ctx, unsigned int count,
-                             xen_pfn_t *pfns, uint32_t *types, void *page_data)
+static int handle_static_data_end_v2(struct xc_sr_context *ctx)
 {
-    xc_interface *xch = ctx->xch;
-    int rc;
-    void *mapping = NULL, *guest_page = NULL;
-    unsigned int i, /* i indexes the pfns from the record. */
-        j,          /* j indexes the subset of pfns we decide to map. */
-        nr_pages = 0;
-
-    rc = populate_pfns(ctx, count, pfns, types);
-    if ( rc )
-    {
-        ERROR("Failed to populate pfns for batch of %u pages", count);
-        goto err;
-    }
-
-    for ( i = 0; i < count; ++i )
-    {
-        ctx->restore.ops.set_page_type(ctx, pfns[i], types[i]);
-
-        if ( page_type_has_stream_data(types[i]) )
-            ctx->restore.mfns[nr_pages++] = ctx->restore.ops.pfn_to_gfn(ctx, pfns[i]);
-    }
-
-    /* Nothing to do? */
-    if ( nr_pages == 0 )
-        goto done;
-
-    mapping = guest_page = xenforeignmemory_map(
-        xch->fmem, ctx->domid, PROT_READ | PROT_WRITE,
-        nr_pages, ctx->restore.mfns, ctx->restore.map_errs);
-    if ( !mapping )
-    {
-        rc = -1;
-        PERROR("Unable to map %u mfns for %u pages of data",
-               nr_pages, count);
-        goto err;
-    }
-
-    for ( i = 0, j = 0; i < count; ++i )
-    {
-        if ( !page_type_has_stream_data(types[i]) )
-            continue;
-
-        if ( ctx->restore.map_errs[j] )
-        {
-            rc = -1;
-            ERROR("Mapping pfn %#"PRIpfn" (mfn %#"PRIpfn", type %#"PRIx32") failed with %d",
-                  pfns[i], ctx->restore.mfns[j], types[i], ctx->restore.map_errs[j]);
-            goto err;
-        }
-
-        /* Undo page normalisation done by the saver. */
-        rc = ctx->restore.ops.localise_page(ctx, types[i], page_data);
-        if ( rc )
-        {
-            ERROR("Failed to localise pfn %#"PRIpfn" (type %#"PRIx32")",
-                  pfns[i], types[i] >> XEN_DOMCTL_PFINFO_LTAB_SHIFT);
-            goto err;
-        }
-
-        if ( ctx->restore.verify )
-        {
-            /* Verify mode - compare incoming data to what we already have. */
-            if ( memcmp(guest_page, page_data, PAGE_SIZE) )
-                ERROR("verify pfn %#"PRIpfn" failed (type %#"PRIx32")",
-                      pfns[i], types[i] >> XEN_DOMCTL_PFINFO_LTAB_SHIFT);
-        }
-        else
-        {
-            /* Regular mode - copy incoming data into place. */
-            memcpy(guest_page, page_data, PAGE_SIZE);
-        }
-
-        ++j;
-        guest_page += PAGE_SIZE;
-        page_data += PAGE_SIZE;
-    }
-
- done:
-    rc = 0;
-
- err:
-    if ( mapping )
-        xenforeignmemory_unmap(xch->fmem, mapping, nr_pages);
-
-    return rc;
-}
+    int rc = 0;
 
-/*
- * Validate a PAGE_DATA record from the stream, and pass the results to
- * process_page_data() to actually perform the legwork.
- */
-static int handle_page_data(struct xc_sr_context *ctx, struct xc_sr_record *rec)
-{
+#if defined(__i386__) || defined(__x86_64__)
     xc_interface *xch = ctx->xch;
-    struct xc_sr_rec_page_data_header *pages = rec->data;
-    unsigned int i, pages_of_data = 0;
-    int rc = -1;
-
-    xen_pfn_t pfn;
-    uint32_t type;
-
     /*
      * v2 compatibility only exists for x86 streams.  This is a bit of a
      * bodge, but it is less bad than duplicating handle_page_data() between
      * different architectures.
      */
-#if defined(__i386__) || defined(__x86_64__)
+
     /* v2 compat.  Infer the position of STATIC_DATA_END. */
     if ( ctx->restore.format_version < 3 && !ctx->restore.seen_static_data_end )
     {
@@ -315,12 +212,26 @@ static int handle_page_data(struct xc_sr
         ERROR("No STATIC_DATA_END seen");
         goto err;
     }
+
+    rc = 0;
+err:
 #endif
 
-    if ( rec->length < sizeof(*pages) )
+    return rc;
+}
+
+static bool verify_rec_page_hdr(struct xc_sr_context *ctx, uint32_t rec_length,
+                                 struct xc_sr_rec_page_data_header *pages)
+{
+    xc_interface *xch = ctx->xch;
+    bool ret = false;
+
+    errno = EINVAL;
+
+    if ( rec_length < sizeof(*pages) )
     {
         ERROR("PAGE_DATA record truncated: length %u, min %zu",
-              rec->length, sizeof(*pages));
+              rec_length, sizeof(*pages));
         goto err;
     }
 
@@ -330,13 +241,28 @@ static int handle_page_data(struct xc_sr
         goto err;
     }
 
-    if ( rec->length < sizeof(*pages) + (pages->count * sizeof(uint64_t)) )
+    if ( rec_length < sizeof(*pages) + (pages->count * sizeof(uint64_t)) )
     {
         ERROR("PAGE_DATA record (length %u) too short to contain %u"
-              " pfns worth of information", rec->length, pages->count);
+              " pfns worth of information", rec_length, pages->count);
         goto err;
     }
 
+    ret = true;
+
+err:
+    return ret;
+}
+
+static bool verify_rec_page_pfns(struct xc_sr_context *ctx, uint32_t rec_length,
+                                 struct xc_sr_rec_page_data_header *pages)
+{
+    xc_interface *xch = ctx->xch;
+    uint32_t i, pages_of_data = 0;
+    xen_pfn_t pfn;
+    uint32_t type;
+    bool ret = false;
+
     for ( i = 0; i < pages->count; ++i )
     {
         pfn = pages->pfn[i] & PAGE_DATA_PFN_MASK;
@@ -363,19 +289,177 @@ static int handle_page_data(struct xc_sr
         ctx->restore.types[i] = type;
     }
 
-    if ( rec->length != (sizeof(*pages) +
+    if ( rec_length != (sizeof(*pages) +
                          (sizeof(uint64_t) * pages->count) +
                          (PAGE_SIZE * pages_of_data)) )
     {
         ERROR("PAGE_DATA record wrong size: length %u, expected "
-              "%zu + %zu + %lu", rec->length, sizeof(*pages),
+              "%zu + %zu + %lu", rec_length, sizeof(*pages),
               (sizeof(uint64_t) * pages->count), (PAGE_SIZE * pages_of_data));
         goto err;
     }
 
-    rc = process_page_data(ctx, pages->count, ctx->restore.pfns,
-                           ctx->restore.types, &pages->pfn[pages->count]);
+    ret = true;
+
+err:
+    return ret;
+}
+
+/*
+ * Populate pfns, if required
+ * Fill guest_data with either mapped address or NULL
+ * The caller must unmap guest_mapping
+ */
+static int map_guest_pages(struct xc_sr_context *ctx,
+                           struct xc_sr_rec_page_data_header *pages)
+{
+    xc_interface *xch = ctx->xch;
+    uint32_t i, p;
+    int rc;
+
+    rc = populate_pfns(ctx, pages->count, ctx->restore.pfns, ctx->restore.types);
+    if ( rc )
+    {
+        ERROR("Failed to populate pfns for batch of %u pages", pages->count);
+        goto err;
+    }
+
+    ctx->restore.nr_mapped_pages = 0;
+
+    for ( i = 0; i < pages->count; i++ )
+    {
+        ctx->restore.ops.set_page_type(ctx, ctx->restore.pfns[i], ctx->restore.types[i]);
+
+        if ( page_type_has_stream_data(ctx->restore.types[i]) == false )
+        {
+            ctx->restore.guest_data[i] = NULL;
+            continue;
+        }
+
+        ctx->restore.mfns[ctx->restore.nr_mapped_pages++] = ctx->restore.ops.pfn_to_gfn(ctx, ctx->restore.pfns[i]);
+    }
+
+    /* Nothing to do? */
+    if ( ctx->restore.nr_mapped_pages == 0 )
+        goto done;
+
+    ctx->restore.guest_mapping = xenforeignmemory_map(xch->fmem, ctx->domid,
+            PROT_READ | PROT_WRITE, ctx->restore.nr_mapped_pages,
+            ctx->restore.mfns, ctx->restore.map_errs);
+    if ( !ctx->restore.guest_mapping )
+    {
+        rc = -1;
+        PERROR("Unable to map %u mfns for %u pages of data",
+               ctx->restore.nr_mapped_pages, pages->count);
+        goto err;
+    }
+
+    /* Verify mapping, and assign address to pfn data */
+    for ( i = 0, p = 0; i < pages->count; i++ )
+    {
+        if ( !page_type_has_stream_data(ctx->restore.types[i]) )
+            continue;
+
+        if ( ctx->restore.map_errs[p] == 0 )
+        {
+            ctx->restore.guest_data[i] = ctx->restore.guest_mapping + (p * PAGE_SIZE);
+            p++;
+            continue;
+        }
+
+        errno = ctx->restore.map_errs[p];
+        rc = -1;
+        PERROR("Mapping pfn %#"PRIpfn" (mfn %#"PRIpfn", type %#"PRIx32") failed",
+              ctx->restore.pfns[i], ctx->restore.mfns[p], ctx->restore.types[i]);
+        goto err;
+    }
+
+done:
+    rc = 0;
+
+err:
+    return rc;
+}
+
+/*
+ * Handle PAGE_DATA record from an existing buffer
+ * Given a list of pfns, their types, and a block of page data from the
+ * stream, populate and record their types, map the relevant subset and copy
+ * the data into the guest.
+ */
+static int handle_buffered_page_data(struct xc_sr_context *ctx,
+                                     struct xc_sr_record *rec)
+{
+    xc_interface *xch = ctx->xch;
+    struct xc_sr_rec_page_data_header *pages = rec->data;
+    void *p;
+    uint32_t i;
+    int rc = -1, idx;
+
+    rc = handle_static_data_end_v2(ctx);
+    if ( rc )
+        goto err;
+
+    /* First read and verify the header */
+    if ( !verify_rec_page_hdr(ctx, rec->length, pages) )
+    {
+        rc = -1;
+        goto err;
+    }
+
+    /* Then read and verify the pfn numbers */
+    if ( !verify_rec_page_pfns(ctx, rec->length, pages) )
+    {
+        rc = -1;
+        goto err;
+    }
+
+    /* Map the target pfn */
+    rc = map_guest_pages(ctx, pages);
+    if ( rc )
+        goto err;
+
+    for ( i = 0, idx = 0; i < pages->count; i++ )
+    {
+        if ( !ctx->restore.guest_data[i] )
+            continue;
+
+        p = &pages->pfn[pages->count] + (idx * PAGE_SIZE);
+        rc = ctx->restore.ops.localise_page(ctx, ctx->restore.types[i], p);
+        if ( rc )
+        {
+            ERROR("Failed to localise pfn %#"PRIpfn" (type %#"PRIx32")",
+                  ctx->restore.pfns[i], ctx->restore.types[i] >> XEN_DOMCTL_PFINFO_LTAB_SHIFT);
+            goto err;
+
+        }
+
+        if ( ctx->restore.verify )
+        {
+            if ( memcmp(ctx->restore.guest_data[i], p, PAGE_SIZE) )
+            {
+                errno = EIO;
+                ERROR("verify pfn %#"PRIpfn" failed (type %#"PRIx32")",
+                      ctx->restore.pfns[i], ctx->restore.types[i] >> XEN_DOMCTL_PFINFO_LTAB_SHIFT);
+                goto err;
+            }
+        }
+        else
+        {
+            memcpy(ctx->restore.guest_data[i], p, PAGE_SIZE);
+        }
+
+        idx++;
+    }
+
+    rc = 0;
+
  err:
+    if ( ctx->restore.guest_mapping )
+    {
+        xenforeignmemory_unmap(xch->fmem, ctx->restore.guest_mapping, ctx->restore.nr_mapped_pages);
+        ctx->restore.guest_mapping = NULL;
+    }
     return rc;
 }
 
@@ -623,7 +707,7 @@ static int process_buffered_record(struc
         break;
 
     case REC_TYPE_PAGE_DATA:
-        rc = handle_page_data(ctx, rec);
+        rc = handle_buffered_page_data(ctx, rec);
         break;
 
     case REC_TYPE_VERIFY:
@@ -703,9 +787,10 @@ static int setup(struct xc_sr_context *c
     ctx->restore.map_errs = malloc(MAX_BATCH_SIZE * sizeof(*ctx->restore.map_errs));
     ctx->restore.pp_pfns = malloc(MAX_BATCH_SIZE * sizeof(*ctx->restore.pp_pfns));
     ctx->restore.pp_mfns = malloc(MAX_BATCH_SIZE * sizeof(*ctx->restore.pp_mfns));
+    ctx->restore.guest_data = malloc(MAX_BATCH_SIZE * sizeof(*ctx->restore.guest_data));
     if ( !ctx->restore.pfns || !ctx->restore.types || !ctx->restore.mfns ||
          !ctx->restore.map_errs || !ctx->restore.pp_pfns ||
-         !ctx->restore.pp_mfns )
+         !ctx->restore.pp_mfns || !ctx->restore.guest_data )
     {
         ERROR("Unable to allocate memory");
         rc = -1;
@@ -742,6 +827,7 @@ static void cleanup(struct xc_sr_context
 
     free(ctx->restore.buffered_records);
     free(ctx->restore.populated_pfns);
+    free(ctx->restore.guest_data);
     free(ctx->restore.pp_mfns);
     free(ctx->restore.pp_pfns);
     free(ctx->restore.map_errs);