[Xen-devel] [RFC PATCH v2 08/14] Add basic live update stream creation

[David Woodhouse <dwmw2@xxxxxxxxxxxxx>]

From: David Woodhouse <dwmw@xxxxxxxxxxxx>

Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx>
---
 xen/common/Makefile    |   1 +
 xen/common/lu/Makefile |   1 +
 xen/common/lu/stream.c | 108 +++++++++++++++++++++++++++++++++++++++++
 xen/include/xen/lu.h   |  12 +++++
 4 files changed, 122 insertions(+)
 create mode 100644 xen/common/lu/Makefile
 create mode 100644 xen/common/lu/stream.c
 create mode 100644 xen/include/xen/lu.h

diff --git a/xen/common/Makefile b/xen/common/Makefile
index 62b34e69e9..36c824a99a 100644
--- a/xen/common/Makefile
+++ b/xen/common/Makefile
@@ -78,3 +78,4 @@ subdir-$(CONFIG_UBSAN) += ubsan
 
 subdir-$(CONFIG_NEEDS_LIBELF) += libelf
 subdir-$(CONFIG_HAS_DEVICE_TREE) += libfdt
+subdir-y += lu
diff --git a/xen/common/lu/Makefile b/xen/common/lu/Makefile
new file mode 100644
index 0000000000..68991b3ca4
--- /dev/null
+++ b/xen/common/lu/Makefile
@@ -0,0 +1 @@
+obj-y += stream.o
diff --git a/xen/common/lu/stream.c b/xen/common/lu/stream.c
new file mode 100644
index 0000000000..52030e8b2e
--- /dev/null
+++ b/xen/common/lu/stream.c
@@ -0,0 +1,108 @@
+/*
+ * Live update data stream handling.
+ *
+ * During live update, one version of Xen (Xen#1) performs a kexec into
+ * a new version of Xen (Xen#2), performing guest-transparent live
+ * migration of all existing domains.
+ *
+ * Xen#2 must avoid scribbling on any pages which may belong to existing
+ * domains. In order to achieve this, we reserve a contiguous area of
+ * physical memory to be used by the boot allocator in Xen#2. Xen must
+ * not allocate pages from that region which are later shared with
+ * guests or need to persist across live update.
+ *
+ * The live update bootmem region is reserved by the first Xen to boot,
+ * and userspace can obtain its address using KEXEC_CMD_kexec_get_range
+ * with the new KEXEC_RANGE_MA_LIVEUPDATE type. Userspace kexec(8)
+ * appends the appropriate 'liveupdate=' parameter to the command line
+ * of Xen#2 when setting up the kexec image.
+ *
+ * At the time of kexec, Xen#1 serialises the domain state into buffers
+ * allocated from its own heap., then creates a single physically
+ * contiguous scatter-gather list containing the MFNs of those data
+ * pages (which Xen#2 can then trivially vmap()). In a system with
+ * 4KiB pages, the MFN list for the live update data stream will fit
+ * into a single page until the total size of the live update data
+ * exceeds 2MiB.
+ *
+ * The physical address of the MFN list is passed to Xen#2 by placing
+ * it at the start of the reserved live update bootmem region, with a
+ * magic number to avoid false positives.
+ */
+
+#include <xen/types.h>
+#include <xen/vmap.h>
+#include <xen/lu.h>
+
+static int lu_stream_extend(struct lu_stream *stream, int nr_pages)
+{
+       int order = get_order_from_bytes((nr_pages + 1) * sizeof(mfn_t));
+       int old_order = get_order_from_bytes((stream->nr_pages + 1) * 
sizeof(mfn_t));
+
+       if (!stream->nr_pages || order > old_order) {
+               mfn_t *new_pglist = alloc_xenheap_pages(order, 0);
+               if (!new_pglist)
+                       return -ENOMEM;
+
+               if (stream->nr_pages) {
+                       memcpy(new_pglist, stream->pagelist,
+                              stream->nr_pages * sizeof(mfn_t));
+                       free_xenheap_pages(stream->pagelist, old_order);
+               }
+               stream->pagelist = new_pglist;
+       }
+       while (stream->nr_pages < nr_pages) {
+               struct page_info *pg = alloc_domheap_page(NULL, MEMF_no_owner);
+               if (!pg) {
+                       /* Ensure the cleanup frees the correct order of 
pagelist */
+                       stream->nr_pages++;
+                       return -ENOMEM;
+               }
+               stream->pagelist[stream->nr_pages++] = page_to_mfn(pg);
+               stream->pagelist[stream->nr_pages] = 0;
+       }
+
+       if (stream->data)
+               vunmap(stream->data);
+       stream->data = vmap(stream->pagelist, stream->nr_pages);
+       if (!stream->data)
+               return -ENOMEM;
+
+       return 0;
+}
+
+void *lu_stream_reserve(struct lu_stream *stream, size_t size)
+{
+       int nr_pages = (stream->len + size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+       if (stream->nr_pages < nr_pages && lu_stream_extend(stream, nr_pages))
+               return NULL;
+
+       return stream->data + stream->len;
+}
+
+void lu_stream_end_reservation(struct lu_stream *stream, size_t size)
+{
+       stream->len += size;
+}
+
+int lu_stream_append(struct lu_stream *stream, void *data, size_t size)
+{
+       void *p = lu_stream_reserve(stream, size);
+       if (!p)
+               return -ENOMEM;
+       memcpy(p, data, size);
+       lu_stream_end_reservation(stream, size);
+
+       return 0;
+}
+
+void lu_stream_free(struct lu_stream *stream)
+{
+       int order = get_order_from_bytes((stream->nr_pages + 1) * 
sizeof(mfn_t));
+
+       if (stream->pagelist)
+               free_xenheap_pages(stream->pagelist, order);
+       if (stream->data)
+               vunmap(stream->data);
+}
diff --git a/xen/include/xen/lu.h b/xen/include/xen/lu.h
new file mode 100644
index 0000000000..cb2f1dbe06
--- /dev/null
+++ b/xen/include/xen/lu.h
@@ -0,0 +1,12 @@
+
+struct lu_stream {
+       mfn_t *pagelist;
+       size_t len;
+       int nr_pages;
+       char *data;
+};
+
+void *lu_stream_reserve(struct lu_stream *stream, size_t size);
+void lu_stream_end_reservation(struct lu_stream *stream, size_t size);
+int lu_stream_append(struct lu_stream *stream, void *data, size_t size);
+void lu_stream_free(struct lu_stream *stream);
-- 
2.21.0


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel