qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Fam Zheng <famz@redhat.com>
To: qemu-devel@nongnu.org
Cc: Paolo Bonzini <pbonzini@redhat.com>
Subject: [Qemu-devel] [PATCH v3 0/4] exec: Make bounce buffer thread safe
Date: Mon, 16 Mar 2015 13:31:46 +0800	[thread overview]
Message-ID: <1426483910-24597-1-git-send-email-famz@redhat.com> (raw)

v3: Address Paolo's comments:
    Use atomic_xchg for bounce buffer.
    Use mutex and BH for map_client_list.

The global bounce buffer used for non-direct memory access is not thread-safe:

 1) Access to "bounce" is not atomic.

 2) Access to "map_client_list" is not atomic.

 3) In dma_blk_cb, there is a race condition between:

        mem = dma_memory_map(...
    and
        cpu_register_map_client(...

    Bounce may become available after dma_memory_map failed but before
    cpu_register_map_client is called.

 4) The reschedule_dma is not in the right AioContext;
    continue_after_map_failure called from other threads will race with
    dma_aio_cancel.

This series fixes these issues respectively.


Fam Zheng (4):
  exec: Atomic access to bounce buffer
  exec: Protect map_client_list with mutex
  exec: Notify cpu_register_map_client caller if the bounce buffer is
    available
  dma-helpers: Fix race condition of continue_after_map_failure and
    dma_aio_cancel

 dma-helpers.c             | 17 +++++------
 exec.c                    | 77 ++++++++++++++++++++++++++++++++---------------
 include/exec/cpu-common.h |  3 +-
 3 files changed, 62 insertions(+), 35 deletions(-)

-- 
1.9.3

             reply	other threads:[~2015-03-16  5:32 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-03-16  5:31 Fam Zheng [this message]
2015-03-16  5:31 ` [Qemu-devel] [PATCH v3 1/4] exec: Atomic access to bounce buffer Fam Zheng
2015-03-16  7:30   ` Paolo Bonzini
2015-03-16  7:42     ` Fam Zheng
2015-03-16  5:31 ` [Qemu-devel] [PATCH v3 2/4] exec: Protect map_client_list with mutex Fam Zheng
2015-03-16  7:33   ` Paolo Bonzini
2015-03-16  7:55     ` Fam Zheng
2015-03-16  5:31 ` [Qemu-devel] [PATCH v3 3/4] exec: Notify cpu_register_map_client caller if the bounce buffer is available Fam Zheng
2015-03-16  7:34   ` Paolo Bonzini
2015-03-16  7:44     ` Fam Zheng
2015-03-16  5:31 ` [Qemu-devel] [PATCH v3 4/4] dma-helpers: Fix race condition of continue_after_map_failure and dma_aio_cancel Fam Zheng
2015-03-16  7:36   ` Paolo Bonzini

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=1426483910-24597-1-git-send-email-famz@redhat.com \
    --to=famz@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    /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).