[PATCH v20210616 26/36] tools: restore: write data directly into guest

[Olaf Hering <olaf@aepfle.de>]

Read incoming migration stream directly into the guest memory.
This avoids the memory allocation and copying, and the resulting
performance penalty.

Signed-off-by: Olaf Hering <olaf@aepfle.de>
---
 tools/libs/saverestore/common.h  |   1 +
 tools/libs/saverestore/restore.c | 132 ++++++++++++++++++++++++++++++-
 2 files changed, 129 insertions(+), 4 deletions(-)

diff --git a/tools/libs/saverestore/common.h b/tools/libs/saverestore/common.h
index d479f1a918..5c440f28ec 100644
--- a/tools/libs/saverestore/common.h
+++ b/tools/libs/saverestore/common.h
@@ -243,6 +243,7 @@ struct sr_restore_arrays {
     xen_pfn_t mfns[MAX_BATCH_SIZE];
     int map_errs[MAX_BATCH_SIZE];
     void *guest_data[MAX_BATCH_SIZE];
+    struct iovec iov[MAX_BATCH_SIZE];
 
     /* populate_pfns */
     xen_pfn_t pp_mfns[MAX_BATCH_SIZE];
diff --git a/tools/libs/saverestore/restore.c b/tools/libs/saverestore/restore.c
index 877fd19a9b..d0148606bf 100644
--- a/tools/libs/saverestore/restore.c
+++ b/tools/libs/saverestore/restore.c
@@ -392,6 +392,122 @@ err:
     return rc;
 }
 
+/*
+ * Handle PAGE_DATA record from the stream.
+ * 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_incoming_page_data(struct xc_sr_context *ctx,
+                                     struct xc_sr_rhdr *rhdr)
+{
+    xc_interface *xch = ctx->xch;
+    struct sr_restore_arrays *m = ctx->restore.m;
+    struct xc_sr_rec_page_data_header *pages = &m->pages;
+    uint64_t *pfn_nums = m->pages.pfn;
+    uint32_t i;
+    int rc, iov_idx;
+
+    rc = handle_static_data_end_v2(ctx);
+    if ( rc )
+        goto err;
+
+    /* First read and verify the header */
+    rc = read_exact(ctx->fd, pages, sizeof(*pages));
+    if ( rc )
+    {
+        PERROR("Could not read rec_pfn header");
+        goto err;
+    }
+
+    if ( verify_rec_page_hdr(ctx, rhdr->length, pages) == false )
+    {
+        rc = -1;
+        goto err;
+    }
+
+    /* Then read and verify the incoming pfn numbers */
+    rc = read_exact(ctx->fd, pfn_nums, sizeof(*pfn_nums) * pages->count);
+    if ( rc )
+    {
+        PERROR("Could not read rec_pfn data");
+        goto err;
+    }
+
+    if ( verify_rec_page_pfns(ctx, rhdr->length, pages) == false )
+    {
+        rc = -1;
+        goto err;
+    }
+
+    /* Finally read and verify the incoming pfn data */
+    rc = map_guest_pages(ctx, pages);
+    if ( rc )
+        goto err;
+
+    /* Prepare read buffers, either guest or throw away memory */
+    for ( i = 0, iov_idx = 0; i < pages->count; i++ )
+    {
+        if ( !m->guest_data[i] )
+            continue;
+
+        m->iov[iov_idx].iov_len = PAGE_SIZE;
+        if ( ctx->restore.verify )
+            m->iov[iov_idx].iov_base = ctx->restore.verify_buf + i * PAGE_SIZE;
+        else
+            m->iov[iov_idx].iov_base = m->guest_data[i];
+        iov_idx++;
+    }
+
+    if ( !iov_idx )
+        goto done;
+
+    rc = readv_exact(ctx->fd, m->iov, iov_idx);
+    if ( rc )
+    {
+        PERROR("read of %d pages failed", iov_idx);
+        goto err;
+    }
+
+    /* Post-processing of pfn data */
+    for ( i = 0, iov_idx = 0; i < pages->count; i++ )
+    {
+        if ( !m->guest_data[i] )
+            continue;
+
+        rc = ctx->restore.ops.localise_page(ctx, m->types[i], m->iov[iov_idx].iov_base);
+        if ( rc )
+        {
+            ERROR("Failed to localise pfn %#"PRIpfn" (type %#"PRIx32")",
+                  m->pfns[i], m->types[i] >> XEN_DOMCTL_PFINFO_LTAB_SHIFT);
+            goto err;
+
+        }
+
+        if ( ctx->restore.verify )
+        {
+            if ( memcmp(m->guest_data[i], m->iov[iov_idx].iov_base, PAGE_SIZE) )
+            {
+                ERROR("verify pfn %#"PRIpfn" failed (type %#"PRIx32")",
+                      m->pfns[i], m->types[i] >> XEN_DOMCTL_PFINFO_LTAB_SHIFT);
+            }
+        }
+
+        iov_idx++;
+    }
+
+done:
+    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;
+}
+
 /*
  * Handle PAGE_DATA record from an existing buffer
  * Given a list of pfns, their types, and a block of page data from the
@@ -773,11 +889,19 @@ static int process_incoming_record_header(struct xc_sr_context *ctx, struct xc_s
     struct xc_sr_record rec;
     int rc;
 
-    rc = read_record_data(ctx, ctx->fd, rhdr, &rec);
-    if ( rc )
-        return rc;
+    switch ( rhdr->type )
+    {
+    case REC_TYPE_PAGE_DATA:
+        rc = handle_incoming_page_data(ctx, rhdr);
+        break;
+    default:
+        rc = read_record_data(ctx, ctx->fd, rhdr, &rec);
+        if ( rc == 0 )
+            rc = process_buffered_record(ctx, &rec);;
+        break;
+    }
 
-    return process_buffered_record(ctx, &rec);
+    return rc;
 }