xen-devel.lists.xenproject.org archive mirror
 help / color / mirror / Atom feed
From: Wen Congyang <wency@cn.fujitsu.com>
To: xen devel <xen-devel@lists.xen.org>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	Andrew Cooper <andrew.cooper3@citrix.com>,
	Ian Campbell <ian.campbell@citrix.com>,
	Ian Jackson <ian.jackson@eu.citrix.com>,
	Wei Liu <wei.liu2@citrix.com>
Cc: Lars Kurth <lars.kurth@citrix.com>,
	Changlong Xie <xiecl.fnst@cn.fujitsu.com>,
	Wen Congyang <wency@cn.fujitsu.com>,
	Gui Jianfeng <guijianfeng@cn.fujitsu.com>,
	Jiang Yunhong <yunhong.jiang@intel.com>,
	Dong Eddie <eddie.dong@intel.com>,
	Shriram Rajagopalan <rshriram@cs.ubc.ca>,
	Yang Hongyang <hongyang.yang@easystack.cn>
Subject: [PATCH v10 19/31] libxc/restore: send dirty pfn list to primary when checkpoint under colo
Date: Mon, 22 Feb 2016 10:52:23 +0800	[thread overview]
Message-ID: <1456109555-28299-20-git-send-email-wency@cn.fujitsu.com> (raw)
In-Reply-To: <1456109555-28299-1-git-send-email-wency@cn.fujitsu.com>

Send dirty pfn list to primary when checkpoint under colo.

Signed-off-by: Yang Hongyang <hongyang.yang@easystack.cn>
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
---
 tools/libxc/xc_sr_common.h  |   4 ++
 tools/libxc/xc_sr_restore.c | 120 +++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 123 insertions(+), 1 deletion(-)

diff --git a/tools/libxc/xc_sr_common.h b/tools/libxc/xc_sr_common.h
index a24a9ad..29ab4eb 100644
--- a/tools/libxc/xc_sr_common.h
+++ b/tools/libxc/xc_sr_common.h
@@ -226,6 +226,10 @@ struct xc_sr_context
             struct xc_sr_restore_ops ops;
             struct restore_callbacks *callbacks;
 
+            int send_back_fd;
+            unsigned long p2m_size;
+            xc_hypercall_buffer_t dirty_bitmap_hbuf;
+
             /* From Image Header. */
             uint32_t format_version;
 
diff --git a/tools/libxc/xc_sr_restore.c b/tools/libxc/xc_sr_restore.c
index 2ae8154..37c0416 100644
--- a/tools/libxc/xc_sr_restore.c
+++ b/tools/libxc/xc_sr_restore.c
@@ -411,6 +411,92 @@ static int handle_page_data(struct xc_sr_context *ctx, struct xc_sr_record *rec)
     return rc;
 }
 
+/*
+ * Send checkpoint dirty pfn list to primary.
+ */
+static int send_checkpoint_dirty_pfn_list(struct xc_sr_context *ctx)
+{
+    xc_interface *xch = ctx->xch;
+    int rc = -1;
+    unsigned count, written;
+    uint64_t i, *pfns = NULL;
+    struct iovec *iov = NULL;
+    xc_shadow_op_stats_t stats = { 0, ctx->restore.p2m_size };
+    struct xc_sr_record rec =
+    {
+        .type = REC_TYPE_CHECKPOINT_DIRTY_PFN_LIST,
+    };
+    DECLARE_HYPERCALL_BUFFER_SHADOW(unsigned long, dirty_bitmap,
+                                    &ctx->restore.dirty_bitmap_hbuf);
+
+    if ( xc_shadow_control(
+             xch, ctx->domid, XEN_DOMCTL_SHADOW_OP_CLEAN,
+             HYPERCALL_BUFFER(dirty_bitmap), ctx->restore.p2m_size,
+             NULL, 0, &stats) != ctx->restore.p2m_size )
+    {
+        PERROR("Failed to retrieve logdirty bitmap");
+        goto err;
+    }
+
+    for ( i = 0, count = 0; i < ctx->restore.p2m_size; i++ )
+    {
+        if ( test_bit(i, dirty_bitmap) )
+            count++;
+    }
+
+
+    pfns = malloc(count * sizeof(*pfns));
+    if ( !pfns )
+    {
+        ERROR("Unable to allocate %zu bytes of memory for dirty pfn list",
+              count * sizeof(*pfns));
+        goto err;
+    }
+
+    for ( i = 0, written = 0; i < ctx->restore.p2m_size; ++i )
+    {
+        if ( !test_bit(i, dirty_bitmap) )
+            continue;
+
+        if ( written > count )
+        {
+            ERROR("Dirty pfn list exceed");
+            goto err;
+        }
+
+        pfns[written++] = i;
+    }
+
+    /* iovec[] for writev(). */
+    iov = malloc(3 * sizeof(*iov));
+    if ( !iov )
+    {
+        ERROR("Unable to allocate memory for sending dirty bitmap");
+        goto err;
+    }
+
+    rec.length = count * sizeof(*pfns);
+
+    iov[0].iov_base = &rec.type;
+    iov[0].iov_len = sizeof(rec.type);
+
+    iov[1].iov_base = &rec.length;
+    iov[1].iov_len = sizeof(rec.length);
+
+    iov[2].iov_base = pfns;
+    iov[2].iov_len = count * sizeof(*pfns);
+
+    if ( writev_exact(ctx->restore.send_back_fd, iov, 3) )
+    {
+        PERROR("Failed to write dirty bitmap to stream");
+        goto err;
+    }
+
+    rc = 0;
+ err:
+    return rc;
+}
+
 static int process_record(struct xc_sr_context *ctx, struct xc_sr_record *rec);
 static int handle_checkpoint(struct xc_sr_context *ctx)
 {
@@ -500,7 +586,9 @@ static int handle_checkpoint(struct xc_sr_context *ctx)
 
 #undef HANDLE_CALLBACK_RETURN_VALUE
 
-        /* TODO: send dirty pfn list to primary */
+        rc = send_checkpoint_dirty_pfn_list(ctx);
+        if ( rc )
+            goto err;
     }
 
  err:
@@ -572,6 +660,21 @@ static int setup(struct xc_sr_context *ctx)
 {
     xc_interface *xch = ctx->xch;
     int rc;
+    DECLARE_HYPERCALL_BUFFER_SHADOW(unsigned long, dirty_bitmap,
+                                    &ctx->restore.dirty_bitmap_hbuf);
+
+    if ( ctx->restore.checkpointed == MIG_STREAM_COLO )
+    {
+        dirty_bitmap = xc_hypercall_buffer_alloc_pages(xch, dirty_bitmap,
+                                NRPAGES(bitmap_size(ctx->restore.p2m_size)));
+
+        if ( !dirty_bitmap )
+        {
+            ERROR("Unable to allocate memory for dirty bitmap");
+            rc = -1;
+            goto err;
+        }
+    }
 
     rc = ctx->restore.ops.setup(ctx);
     if ( rc )
@@ -605,10 +708,15 @@ static void cleanup(struct xc_sr_context *ctx)
 {
     xc_interface *xch = ctx->xch;
     unsigned i;
+    DECLARE_HYPERCALL_BUFFER_SHADOW(unsigned long, dirty_bitmap,
+                                    &ctx->restore.dirty_bitmap_hbuf);
 
     for ( i = 0; i < ctx->restore.buffered_rec_num; i++ )
         free(ctx->restore.buffered_records[i].data);
 
+    if ( ctx->restore.checkpointed == MIG_STREAM_COLO )
+        xc_hypercall_buffer_free_pages(xch, dirty_bitmap,
+                                   NRPAGES(bitmap_size(ctx->restore.p2m_size)));
     free(ctx->restore.buffered_records);
     free(ctx->restore.populated_pfns);
     if ( ctx->restore.ops.cleanup(ctx) )
@@ -719,6 +827,7 @@ int xc_domain_restore(xc_interface *xch, int io_fd, uint32_t dom,
                       int checkpointed_stream,
                       struct restore_callbacks *callbacks, int send_back_fd)
 {
+    xen_pfn_t nr_pfns;
     struct xc_sr_context ctx =
         {
             .xch = xch,
@@ -732,6 +841,7 @@ int xc_domain_restore(xc_interface *xch, int io_fd, uint32_t dom,
     ctx.restore.xenstore_domid = store_domid;
     ctx.restore.checkpointed = checkpointed_stream;
     ctx.restore.callbacks = callbacks;
+    ctx.restore.send_back_fd = send_back_fd;
 
     /* Sanity checks for callbacks. */
     if ( checkpointed_stream )
@@ -766,6 +876,14 @@ int xc_domain_restore(xc_interface *xch, int io_fd, uint32_t dom,
     if ( read_headers(&ctx) )
         return -1;
 
+    if ( xc_domain_nr_gpfns(xch, dom, &nr_pfns) < 0 )
+    {
+        PERROR("Unable to obtain the guest p2m size");
+        return -1;
+    }
+
+    ctx.restore.p2m_size = nr_pfns;
+
     if ( ctx.dominfo.hvm )
     {
         ctx.restore.ops = restore_ops_x86_hvm;
-- 
2.5.0

  parent reply	other threads:[~2016-02-22  2:52 UTC|newest]

Thread overview: 70+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-02-22  2:52 [PATCH v10 00/31] COarse-grain LOck-stepping Virtual Machines for Non-stop Service Wen Congyang
2016-02-22  2:52 ` [PATCH v10 01/31] tools/libxl: introduce libxl__domain_restore_device_model to load qemu state Wen Congyang
2016-02-25 15:53   ` Wei Liu
2016-02-26  1:55     ` Wen Congyang
2016-02-22  2:52 ` [PATCH v10 02/31] tools/libxl: introduce libxl__domain_common_switch_qemu_logdirty() Wen Congyang
2016-02-22  2:52 ` [PATCH v10 03/31] tools/libxl: Add back channel to allow migration target send data back Wen Congyang
2016-02-22  2:52 ` [PATCH v10 04/31] tools/libxl: Introduce new helper function dup_fd_helper() Wen Congyang
2016-02-25 15:53   ` Wei Liu
2016-02-22  2:52 ` [PATCH v10 05/31] tools/libx{l, c}: add back channel to libxc Wen Congyang
2016-02-25 15:54   ` Wei Liu
2016-02-22  2:52 ` [PATCH v10 06/31] docs: add colo readme Wen Congyang
2016-02-25 15:54   ` Wei Liu
2016-02-22  2:52 ` [PATCH v10 07/31] docs/libxl: Introduce CHECKPOINT_CONTEXT to support migration v2 colo streams Wen Congyang
2016-02-25 15:54   ` Wei Liu
2016-02-26  1:59     ` Wen Congyang
2016-02-22  2:52 ` [PATCH v10 08/31] libxc/migration: Specification update for DIRTY_PFN_LIST records Wen Congyang
2016-02-22  2:52 ` [PATCH v10 09/31] libxc/migration: export read_record for common use Wen Congyang
2016-02-22  2:52 ` [PATCH v10 10/31] tools/libxl: add back channel support to write stream Wen Congyang
2016-02-25 15:54   ` Wei Liu
2016-02-26  2:11     ` Wen Congyang
2016-03-02 15:02       ` Wei Liu
2016-03-03  1:25         ` Wen Congyang
2016-02-22  2:52 ` [PATCH v10 11/31] tools/libxl: write checkpoint_state records into the stream Wen Congyang
2016-02-22  2:52 ` [PATCH v10 12/31] tools/libxl: add back channel support to read stream Wen Congyang
2016-02-25 15:54   ` Wei Liu
2016-02-26  2:16     ` Wen Congyang
2016-03-02 15:03       ` Wei Liu
2016-02-22  2:52 ` [PATCH v10 13/31] tools/libxl: handle checkpoint_state records in a libxl migration v2 " Wen Congyang
2016-02-22  2:52 ` [PATCH v10 14/31] tools/libx{l, c}: introduce wait_checkpoint callback Wen Congyang
2016-02-22  2:52 ` [PATCH v10 15/31] tools/libx{l, c}: add postcopy/suspend callback to restore side Wen Congyang
2016-02-22  2:52 ` [PATCH v10 16/31] secondary vm suspend/resume/checkpoint code Wen Congyang
2016-02-25 15:56   ` Wei Liu
2016-02-26  2:30     ` Wen Congyang
2016-03-01 10:06     ` Wen Congyang
2016-02-22  2:52 ` [PATCH v10 17/31] primary " Wen Congyang
2016-02-25 15:57   ` Wei Liu
2016-02-26  2:32     ` Wen Congyang
2016-02-22  2:52 ` [PATCH v10 18/31] libxc/restore: support COLO restore Wen Congyang
2016-02-25 15:57   ` Wei Liu
2016-02-26  2:33     ` Wen Congyang
2016-02-22  2:52 ` Wen Congyang [this message]
2016-02-22  2:52 ` [PATCH v10 20/31] send store gfn and console gfn to xl before resuming secondary vm Wen Congyang
2016-02-22  2:52 ` [PATCH v10 21/31] libxc/save: support COLO save Wen Congyang
2016-02-25 15:58   ` Wei Liu
2016-02-26  2:35     ` Wen Congyang
2016-02-22  2:52 ` [PATCH v10 22/31] implement the cmdline for COLO Wen Congyang
2016-03-02 15:03   ` Wei Liu
2016-03-03  1:30     ` Wen Congyang
2016-02-22  2:52 ` [PATCH v10 23/31] COLO: introduce new API to prepare/start/do/get_error/stop replication Wen Congyang
2016-03-02 15:03   ` Wei Liu
2016-02-22  2:52 ` [PATCH v10 24/31] Support colo mode for qemu disk Wen Congyang
2016-03-02 15:04   ` Wei Liu
2016-03-03  1:40     ` Wen Congyang
2016-02-22  2:52 ` [PATCH v10 25/31] COLO: use qemu block replication Wen Congyang
2016-03-02 15:03   ` Wei Liu
2016-02-22  2:52 ` [PATCH v10 26/31] COLO proxy: implement setup/teardown of COLO proxy module Wen Congyang
2016-03-02 15:04   ` Wei Liu
2016-03-11 22:25   ` Konrad Rzeszutek Wilk
2016-03-14  9:13     ` Wen Congyang
2016-03-22  3:40       ` Changlong Xie
2016-02-22  2:52 ` [PATCH v10 27/31] COLO proxy: preresume, postresume and checkpoint Wen Congyang
2016-03-02 15:04   ` Wei Liu
2016-02-22  2:52 ` [PATCH v10 28/31] COLO nic: implement COLO nic subkind Wen Congyang
2016-03-02 15:04   ` Wei Liu
2016-02-22  2:52 ` [PATCH v10 29/31] setup and control colo proxy on primary side Wen Congyang
2016-02-22  2:52 ` [PATCH v10 30/31] setup and control colo proxy on secondary side Wen Congyang
2016-02-22  2:52 ` [PATCH v10 31/31] cmdline switches and config vars to control colo-proxy Wen Congyang
2016-03-02 15:05   ` Wei Liu
2016-03-03  1:41     ` Wen Congyang
2016-02-25 16:05 ` [PATCH v10 00/31] COarse-grain LOck-stepping Virtual Machines for Non-stop Service Wei Liu

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=1456109555-28299-20-git-send-email-wency@cn.fujitsu.com \
    --to=wency@cn.fujitsu.com \
    --cc=andrew.cooper3@citrix.com \
    --cc=eddie.dong@intel.com \
    --cc=guijianfeng@cn.fujitsu.com \
    --cc=hongyang.yang@easystack.cn \
    --cc=ian.campbell@citrix.com \
    --cc=ian.jackson@eu.citrix.com \
    --cc=konrad.wilk@oracle.com \
    --cc=lars.kurth@citrix.com \
    --cc=rshriram@cs.ubc.ca \
    --cc=wei.liu2@citrix.com \
    --cc=xen-devel@lists.xen.org \
    --cc=xiecl.fnst@cn.fujitsu.com \
    --cc=yunhong.jiang@intel.com \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).