qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Dr. David Alan Gilbert (git)" <dgilbert@redhat.com>
To: qemu-devel@nongnu.org
Cc: quintela@redhat.com, lvivier@redhat.com,
	marcandre.lureau@redhat.com, vsementsov@virtuozzo.com,
	danielhb@linux.vnet.ibm.com, pasic@linux.vnet.ibm.com,
	ashijeetacharya@gmail.com
Subject: [Qemu-devel] [PULL 19/27] postcopy: Use temporary for placing zero huge pages
Date: Tue, 28 Feb 2017 12:40:48 +0000	[thread overview]
Message-ID: <20170228124056.5074-20-dgilbert@redhat.com> (raw)
In-Reply-To: <20170228124056.5074-1-dgilbert@redhat.com>

From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>

The kernel can't do UFFDIO_ZEROPAGE for huge pages, so we have
to allocate a temporary (always zero) page and use UFFDIO_COPYPAGE
on it.

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Laurent Vivier <lvivier@redhat.com>
Message-Id: <20170224182844.32452-9-dgilbert@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
 include/migration/migration.h |  1 +
 migration/postcopy-ram.c      | 23 +++++++++++++++++++++--
 2 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/include/migration/migration.h b/include/migration/migration.h
index 08b98e9..5720c88 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -109,6 +109,7 @@ struct MigrationIncomingState {
     QEMUFile *to_src_file;
     QemuMutex rp_mutex;    /* We send replies from multiple threads */
     void     *postcopy_tmp_page;
+    void     *postcopy_tmp_zero_page;
 
     QEMUBH *bh;
 
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index a8b7fed..4c736d2 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -324,6 +324,10 @@ int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis)
         munmap(mis->postcopy_tmp_page, mis->largest_page_size);
         mis->postcopy_tmp_page = NULL;
     }
+    if (mis->postcopy_tmp_zero_page) {
+        munmap(mis->postcopy_tmp_zero_page, mis->largest_page_size);
+        mis->postcopy_tmp_zero_page = NULL;
+    }
     trace_postcopy_ram_incoming_cleanup_exit();
     return 0;
 }
@@ -593,8 +597,23 @@ int postcopy_place_page_zero(MigrationIncomingState *mis, void *host,
             return -e;
         }
     } else {
-        /* TODO: The kernel can't use UFFDIO_ZEROPAGE for hugepages */
-        assert(0);
+        /* The kernel can't use UFFDIO_ZEROPAGE for hugepages */
+        if (!mis->postcopy_tmp_zero_page) {
+            mis->postcopy_tmp_zero_page = mmap(NULL, mis->largest_page_size,
+                                               PROT_READ | PROT_WRITE,
+                                               MAP_PRIVATE | MAP_ANONYMOUS,
+                                               -1, 0);
+            if (mis->postcopy_tmp_zero_page == MAP_FAILED) {
+                int e = errno;
+                mis->postcopy_tmp_zero_page = NULL;
+                error_report("%s: %s mapping large zero page",
+                             __func__, strerror(e));
+                return -e;
+            }
+            memset(mis->postcopy_tmp_zero_page, '\0', mis->largest_page_size);
+        }
+        return postcopy_place_page(mis, host, mis->postcopy_tmp_zero_page,
+                                   pagesize);
     }
 
     return 0;
-- 
2.9.3

  parent reply	other threads:[~2017-02-28 12:41 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-02-28 12:40 [Qemu-devel] [PULL 00/27] migration queue Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 01/27] Changing error message of QMP 'migrate_set_downtime' to seconds Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 02/27] migration/vmstate: renames in (load|save)_state Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 03/27] migration/vmstate: split up vmstate_base_addr Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 04/27] migration/vmstate: fix array of ptr with nullptrs Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 05/27] tests/test-vmstate.c: test array of ptr with null Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 06/27] tests/test-vmstate.c: test array of ptr to primitive Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 07/27] vmstate-static-checker: update white list with spapr_pci Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 08/27] migrate: Introduce a 'dc->vmsd' check to avoid segfault for --only-migratable Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 09/27] migration: fix id leak regression Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 10/27] migration: Update docs to discourage version bumps Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 11/27] migration: fix use-after-free of to_dst_file Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 12/27] postcopy: Transmit ram size summary word Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 13/27] postcopy: Transmit and compare individual page sizes Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 14/27] postcopy: Chunk discards for hugepages Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 15/27] exec: ram_block_discard_range Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 16/27] postcopy: enhance ram_block_discard_range for hugepages Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 17/27] postcopy: Record largest page size Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 18/27] postcopy: Plumb pagesize down into place helpers Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` Dr. David Alan Gilbert (git) [this message]
2017-02-28 12:40 ` [Qemu-devel] [PULL 20/27] postcopy: Load huge pages in one go Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 21/27] postcopy: Mask fault addresses to huge page boundary Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 22/27] postcopy: Send whole huge pages Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 23/27] postcopy: Allow hugepages Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 24/27] postcopy: Update userfaultfd.h header Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 25/27] postcopy: Check for userfault+hugepage feature Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 26/27] postcopy: Add doc about hugepages and postcopy Dr. David Alan Gilbert (git)
2017-02-28 12:40 ` [Qemu-devel] [PULL 27/27] postcopy: Add extra check for COPY function Dr. David Alan Gilbert (git)
2017-03-01 13:06 ` [Qemu-devel] [PULL 00/27] migration queue Peter Maydell
2017-03-01 13:13   ` Dr. David Alan Gilbert
2017-03-02 19:27 ` Peter Maydell

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=20170228124056.5074-20-dgilbert@redhat.com \
    --to=dgilbert@redhat.com \
    --cc=ashijeetacharya@gmail.com \
    --cc=danielhb@linux.vnet.ibm.com \
    --cc=lvivier@redhat.com \
    --cc=marcandre.lureau@redhat.com \
    --cc=pasic@linux.vnet.ibm.com \
    --cc=qemu-devel@nongnu.org \
    --cc=quintela@redhat.com \
    --cc=vsementsov@virtuozzo.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).