All of lore.kernel.org
 help / color / mirror / Atom feed
From: Olaf Hering <olaf@aepfle.de>
To: xen-devel@lists.xenproject.org
Cc: Olaf Hering <olaf@aepfle.de>, Ian Jackson <iwj@xenproject.org>,
	Wei Liu <wl@xen.org>, Juergen Gross <jgross@suse.com>
Subject: [PATCH v20210616 25/36] tools: restore: split handle_page_data
Date: Wed, 16 Jun 2021 14:51:18 +0200	[thread overview]
Message-ID: <20210616125129.26563-26-olaf@aepfle.de> (raw)
In-Reply-To: <20210616125129.26563-1-olaf@aepfle.de>

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/saverestore/common.h  |   9 +
 tools/libs/saverestore/restore.c | 343 ++++++++++++++++++++-----------
 2 files changed, 231 insertions(+), 121 deletions(-)

diff --git a/tools/libs/saverestore/common.h b/tools/libs/saverestore/common.h
index 2ced6f100d..d479f1a918 100644
--- a/tools/libs/saverestore/common.h
+++ b/tools/libs/saverestore/common.h
@@ -242,9 +242,14 @@ struct sr_restore_arrays {
     /* process_page_data */
     xen_pfn_t mfns[MAX_BATCH_SIZE];
     int map_errs[MAX_BATCH_SIZE];
+    void *guest_data[MAX_BATCH_SIZE];
+
     /* populate_pfns */
     xen_pfn_t pp_mfns[MAX_BATCH_SIZE];
     xen_pfn_t pp_pfns[MAX_BATCH_SIZE];
+
+    /* Must be the last member */
+    struct xc_sr_rec_page_data_header pages;
 };
 
 struct xc_sr_context
@@ -335,7 +340,11 @@ struct xc_sr_context
 
             /* Sender has invoked verify mode on the stream. */
             bool verify;
+            void *verify_buf;
+
             struct sr_restore_arrays *m;
+            void *guest_mapping;
+            uint32_t nr_mapped_pages;
         } restore;
     };
 
diff --git a/tools/libs/saverestore/restore.c b/tools/libs/saverestore/restore.c
index 2409c8d603..877fd19a9b 100644
--- a/tools/libs/saverestore/restore.c
+++ b/tools/libs/saverestore/restore.c
@@ -186,123 +186,18 @@ int populate_pfns(struct xc_sr_context *ctx, unsigned int count,
     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;
-    xen_pfn_t *mfns = ctx->restore.m->mfns;
-    int *map_errs = ctx->restore.m->map_errs;
-    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]) == true )
-            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, mfns, 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]) == false )
-            continue;
-
-        if ( map_errs[j] )
-        {
-            rc = -1;
-            ERROR("Mapping pfn %#"PRIpfn" (mfn %#"PRIpfn", type %#"PRIx32") failed with %d",
-                  pfns[i], mfns[j], types[i], 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 *pfns = ctx->restore.m->pfns, pfn;
-    uint32_t *types = ctx->restore.m->types, 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 )
     {
@@ -320,12 +215,26 @@ static int handle_page_data(struct xc_sr_context *ctx, struct xc_sr_record *rec)
         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;
     }
 
@@ -335,13 +244,35 @@ static int handle_page_data(struct xc_sr_context *ctx, struct xc_sr_record *rec)
         goto err;
     }
 
-    if ( rec->length < sizeof(*pages) + (pages->count * sizeof(uint64_t)) )
+    if ( pages->count > MAX_BATCH_SIZE )
+    {
+        ERROR("pfn count %u in PAGE_DATA record too large", pages->count);
+        errno = E2BIG;
+        goto err;
+    }
+
+    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;
@@ -364,23 +295,183 @@ static int handle_page_data(struct xc_sr_context *ctx, struct xc_sr_record *rec)
              * have a page worth of data in the record. */
             pages_of_data++;
 
-        pfns[i] = pfn;
-        types[i] = type;
+        ctx->restore.m->pfns[i] = pfn;
+        ctx->restore.m->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, pfns, types,
-                           &pages->pfn[pages->count]);
+    ret = true;
+
+err:
+    return ret;
+}
+
+/*
+ * Populate pfns, if required
+ * Fill m->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;
+    struct sr_restore_arrays *m = ctx->restore.m;
+    uint32_t i, p;
+    int rc;
+
+    rc = populate_pfns(ctx, pages->count, m->pfns, m->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, m->pfns[i], m->types[i]);
+
+        if ( page_type_has_stream_data(m->types[i]) == false )
+        {
+            m->guest_data[i] = NULL;
+            continue;
+        }
+
+        m->mfns[ctx->restore.nr_mapped_pages++] = ctx->restore.ops.pfn_to_gfn(ctx, m->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,
+            m->mfns, m->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(m->types[i]) == false )
+            continue;
+
+        if ( m->map_errs[p] == 0 )
+        {
+            m->guest_data[i] = ctx->restore.guest_mapping + (p * PAGE_SIZE);
+            p++;
+            continue;
+        }
+
+        errno = m->map_errs[p];
+        rc = -1;
+        PERROR("Mapping pfn %#"PRIpfn" (mfn %#"PRIpfn", type %#"PRIx32") failed",
+              m->pfns[i], m->mfns[p], m->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;
+    struct sr_restore_arrays *m = ctx->restore.m;
+    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) == false )
+    {
+        rc = -1;
+        goto err;
+    }
+
+    /* Then read and verify the pfn numbers */
+    if ( verify_rec_page_pfns(ctx, rec->length, pages) == false )
+    {
+        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 ( !m->guest_data[i] )
+            continue;
+
+        p = &pages->pfn[pages->count] + (idx * PAGE_SIZE);
+        rc = ctx->restore.ops.localise_page(ctx, m->types[i], p);
+        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], p, PAGE_SIZE) )
+            {
+                errno = EIO;
+                ERROR("verify pfn %#"PRIpfn" failed (type %#"PRIx32")",
+                      m->pfns[i], m->types[i] >> XEN_DOMCTL_PFINFO_LTAB_SHIFT);
+                goto err;
+            }
+        }
+        else
+        {
+            memcpy(m->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;
 }
 
@@ -641,12 +732,21 @@ static int process_buffered_record(struct xc_sr_context *ctx, struct xc_sr_recor
         break;
 
     case REC_TYPE_PAGE_DATA:
-        rc = handle_page_data(ctx, rec);
+        rc = handle_buffered_page_data(ctx, rec);
         break;
 
     case REC_TYPE_VERIFY:
         DPRINTF("Verify mode enabled");
         ctx->restore.verify = true;
+        if ( !ctx->restore.verify_buf )
+        {
+            ctx->restore.verify_buf = malloc(MAX_BATCH_SIZE * PAGE_SIZE);
+            if ( !ctx->restore.verify_buf )
+            {
+                rc = -1;
+                PERROR("Unable to allocate verify_buf");
+            }
+        }
         break;
 
     case REC_TYPE_CHECKPOINT:
@@ -725,7 +825,8 @@ static int setup(struct xc_sr_context *ctx)
     }
     ctx->restore.allocated_rec_num = DEFAULT_BUF_RECORDS;
 
-    ctx->restore.m = malloc(sizeof(*ctx->restore.m));
+    ctx->restore.m = malloc(sizeof(*ctx->restore.m) +
+            (sizeof(*ctx->restore.m->pages.pfn) * MAX_BATCH_SIZE));
     if ( !ctx->restore.m ) {
         ERROR("Unable to allocate memory for arrays");
         rc = -1;


  parent reply	other threads:[~2021-06-16 13:08 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-16 12:50 [PATCH v20210616 00/36] leftover from 2020 Olaf Hering
2021-06-16 12:50 ` [PATCH v20210616 01/36] hotplug/Linux: fix starting of xenstored with restarting systemd Olaf Hering
2021-06-16 12:50 ` [PATCH v20210616 02/36] tools: add API to work with sevaral bits at once Olaf Hering
2021-06-16 12:50 ` [PATCH v20210616 03/36] xl: fix description of migrate --debug Olaf Hering
2021-06-16 12:50 ` [PATCH v20210616 04/36] tools: create libxensaverestore Olaf Hering
2021-06-16 15:17   ` Olaf Hering
2021-06-16 12:50 ` [PATCH v20210616 05/36] MAINTAINERS: add myself as saverestore maintainer Olaf Hering
2021-06-16 12:50 ` [PATCH v20210616 06/36] tools: add readv_exact to libxenctrl Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 07/36] tools: add sr_is_known_page_type to libsaverestore Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 08/36] tools: use sr_is_known_page_type Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 09/36] tools: unify type checking for data pfns in migration stream Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 10/36] tools: show migration transfer rate in send_dirty_pages Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 11/36] tools: prepare to allocate saverestore arrays once Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 12/36] tools: save: move mfns array Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 13/36] tools: save: move types array Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 14/36] tools: save: move errors array Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 15/36] tools: save: move iov array Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 16/36] tools: save: move rec_pfns array Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 17/36] tools: save: move guest_data array Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 18/36] tools: save: move local_pages array Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 19/36] tools: restore: move types array Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 20/36] tools: restore: move mfns array Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 21/36] tools: restore: move map_errs array Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 22/36] tools: restore: move mfns array in populate_pfns Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 23/36] tools: restore: move pfns " Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 24/36] tools: restore: split record processing Olaf Hering
2021-06-16 12:51 ` Olaf Hering [this message]
2021-06-16 12:51 ` [PATCH v20210616 26/36] tools: restore: write data directly into guest Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 27/36] tools: recognize LIBXL_API_VERSION for 4.16 Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 28/36] tools: adjust libxl_domain_suspend to receive a struct props Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 29/36] tools: change struct precopy_stats to precopy_stats_t Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 30/36] tools: add callback to libxl for precopy_policy and precopy_stats_t Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 31/36] tools: add --max_iters to libxl_domain_suspend Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 32/36] tools: add --min_remaining " Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 33/36] tools: add --abort_if_busy " Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 34/36] tools: add API for expandable bitmaps Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 35/36] tools: use sr_bitmap for populated_pfns Olaf Hering
2021-06-16 12:51 ` [PATCH v20210616 36/36] tools: use superpages during restore of HVM guest Olaf Hering
2021-06-16 14:50 ` [PATCH v20210616 00/36] leftover from 2020 Andrew Cooper
2021-06-16 15:02   ` Olaf Hering
2021-06-17 11:02     ` Julien Grall
2021-06-17 17:40       ` Olaf Hering
2021-06-16 15:38   ` Olaf Hering
2021-06-17 11:24     ` Andrew Cooper
2021-06-17 14:55       ` Olaf Hering
2021-06-17 15:05         ` Andrew Cooper

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210616125129.26563-26-olaf@aepfle.de \
    --to=olaf@aepfle.de \
    --cc=iwj@xenproject.org \
    --cc=jgross@suse.com \
    --cc=wl@xen.org \
    --cc=xen-devel@lists.xenproject.org \
    --subject='Re: [PATCH v20210616 25/36] tools: restore: split handle_page_data' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.