qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Paolo Bonzini <pbonzini@redhat.com>
To: qemu-devel@nongnu.org
Cc: famz@redhat.com, stefanha@redhat.com, mst@redhat.com
Subject: [Qemu-devel] [PATCH v2 00/29] Dirty bitmap atomic access and optimizations
Date: Mon, 27 Apr 2015 18:28:08 +0200	[thread overview]
Message-ID: <1430152117-100558-1-git-send-email-pbonzini@redhat.com> (raw)

QEMU is currently accessing the dirty bitmaps very liberally,
which is understandable since the accesses are cheap.  This is
however not good for squeezing maximum performance out of dataplane,
and is also not good if the accesses become more expensive---as is
the case when they use atomic primitives.

This patch series does the following optimizations and cleanups:

1) it lets KVM code treat migration as "just another dirty bitmap
client" instead of needing the special global_log_start/stop callbacks.
These remain in use in Xen and vhost.  This removes code and avoids
bugs such as the one fixed in commit 4cc856f (kvm-all: Sync dirty-bitmap
from kvm before kvm destroy the corresponding dirty_bitmap, 2015-04-02).

2) it avoids modifications to unused dirty bitmaps: code if TCG
is disabled, migration if no migration is in progress, VGA for
regions other than VRAM.

and on top of this makes dirty bitmap access atomic.  I'm not including
the patch to make the migration thread synchronize the bitmap outside
the big QEMU lock (thus removing the last source of jitter during the
RAM copy phase of migration) but it is also enabled by these patches.

Patches 1-4 are cleanups to DIRTY_MEMORY_VGA users.

Patches 5-12 are the first cleanup (KVM treats migration as just
another client).  Patches 13-14 are a simple optimization that is enabled
by these patches.

Patches 15-18 are bonus cleanups to translate-all.c's dirty memory
tracking for TCG.

Patches 19-22 are the second cleanup (avoid modifications to unused
dirty bitmaps).

Patches 23-28 are Stefan's patches for atomic access to the dirty
bitmap, which has no performance impact in the common case thanks to
the previous work.

Patch 29 is an unrelated strengthening of assertions, that mst spotted
while reviewing v1.

v1->v2: completed work on removing global_start/global_stop from KVM
	listener

        extra spelunking of TCG history so that the exec.c code
	makes more sense

        extra splitting of patches (Stefan)

        keep memory_region_is_logging and memory_region_get_dirty_log_mask
	APIs separate (mst)

Paolo Bonzini (23):
  memory: the only dirty memory flag for users is DIRTY_MEMORY_VGA
  g364fb: remove pointless call to memory_region_set_coalescing
  display: enable DIRTY_MEMORY_VGA tracking explicitly
  display: add memory_region_sync_dirty_bitmap calls
  memory: differentiate memory_region_is_logging and
    memory_region_get_dirty_log_mask
  memory: prepare for multiple bits in the dirty log mask
  framebuffer: check memory_region_is_logging
  ui/console: remove dpy_gfx_update_dirty
  memory: track DIRTY_MEMORY_CODE in mr->dirty_log_mask
  kvm: accept non-mapped memory in kvm_dirty_pages_log_change
  memory: include DIRTY_MEMORY_MIGRATION in the dirty log mask
  kvm: remove special handling of DIRTY_MEMORY_MIGRATION in the dirty
    log mask
  ram_addr: tweaks to xen_modified_memory
  exec: use memory_region_get_dirty_log_mask to optimize dirty tracking
  exec: move functions to translate-all.h
  translate-all: remove unnecessary argument to tb_invalidate_phys_range
  cputlb: remove useless arguments to tlb_unprotect_code_phys, rename
  translate-all: make less of tb_invalidate_phys_page_range depend on
    is_cpu_write_access
  exec: pass client mask to cpu_physical_memory_set_dirty_range
  exec: invert return value of cpu_physical_memory_get_clean, rename
  exec: only check relevant bitmaps for cleanliness
  memory: do not touch code dirty bitmap unless TCG is enabled
  memory: strengthen assertions on mr->terminates

Stefan Hajnoczi (6):
  bitmap: add atomic set functions
  bitmap: add atomic test and clear
  memory: use atomic ops for setting dirty memory bits
  migration: move dirty bitmap sync to ram_addr.h
  memory: replace cpu_physical_memory_reset_dirty() with test-and-clear
  memory: make cpu_physical_memory_sync_dirty_bitmap() fully atomic

 arch_init.c                  |  46 +--------------
 cputlb.c                     |   7 +--
 exec.c                       |  99 +++++++++++++++----------------
 hw/display/cg3.c             |   2 +
 hw/display/exynos4210_fimd.c |  20 ++++---
 hw/display/framebuffer.c     |   4 ++
 hw/display/g364fb.c          |   3 +-
 hw/display/sm501.c           |   2 +
 hw/display/tcx.c             |   2 +
 hw/display/vmware_vga.c      |   2 +-
 hw/virtio/dataplane/vring.c  |   2 +-
 hw/virtio/vhost.c            |   9 ++-
 include/exec/cputlb.h        |   3 +-
 include/exec/exec-all.h      |   6 +-
 include/exec/memory.h        |  25 ++++++--
 include/exec/ram_addr.h      | 138 ++++++++++++++++++++++++++++---------------
 include/qemu/bitmap.h        |   4 ++
 include/qemu/bitops.h        |  14 +++++
 include/ui/console.h         |   4 --
 kvm-all.c                    |  77 ++++++------------------
 linux-user/mmap.c            |   7 ++-
 memory.c                     |  76 ++++++++++++++++--------
 translate-all.c              |  20 +++----
 translate-all.h              |   7 +++
 ui/console.c                 |  61 -------------------
 user-exec.c                  |   1 +
 util/bitmap.c                |  81 +++++++++++++++++++++++++
 xen-hvm.c                    |  22 ++++---
 28 files changed, 401 insertions(+), 343 deletions(-)

-- 
1.8.3.1

             reply	other threads:[~2015-04-27 16:37 UTC|newest]

Thread overview: 88+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-04-27 16:28 Paolo Bonzini [this message]
2015-04-27 16:28 ` [Qemu-devel] [PATCH 01/29] memory: the only dirty memory flag for users is DIRTY_MEMORY_VGA Paolo Bonzini
2015-05-26  7:00   ` Fam Zheng
2015-04-27 16:28 ` [Qemu-devel] [PATCH 02/29] g364fb: remove pointless call to memory_region_set_coalescing Paolo Bonzini
2015-05-26 12:53   ` Fam Zheng
2015-04-27 16:28 ` [Qemu-devel] [PATCH 03/29] display: enable DIRTY_MEMORY_VGA tracking explicitly Paolo Bonzini
2015-05-26  7:13   ` Fam Zheng
2015-05-26  8:14     ` Paolo Bonzini
2015-05-26 11:24   ` Paolo Bonzini
2015-05-26 11:52     ` Peter Maydell
2015-05-26 11:56       ` Paolo Bonzini
2015-05-26 12:08         ` Peter Maydell
2015-05-26 12:10           ` Paolo Bonzini
2015-05-26 12:16             ` Peter Maydell
2015-05-31 20:32         ` Mark Cave-Ayland
2015-04-27 16:28 ` [Qemu-devel] [PATCH 04/29] display: add memory_region_sync_dirty_bitmap calls Paolo Bonzini
2015-05-26  7:36   ` Fam Zheng
2015-05-26  8:14     ` Paolo Bonzini
2015-04-27 16:28 ` [Qemu-devel] [PATCH 05/29] memory: differentiate memory_region_is_logging and memory_region_get_dirty_log_mask Paolo Bonzini
2015-05-26  7:46   ` Fam Zheng
2015-05-26 11:35     ` Paolo Bonzini
2015-04-27 16:28 ` [Qemu-devel] [PATCH 06/29] memory: prepare for multiple bits in the dirty log mask Paolo Bonzini
2015-05-26  7:55   ` Fam Zheng
2015-04-27 16:28 ` [Qemu-devel] [PATCH 07/29] framebuffer: check memory_region_is_logging Paolo Bonzini
2015-05-26  8:02   ` Fam Zheng
2015-05-26 11:16     ` Paolo Bonzini
2015-04-27 16:28 ` [Qemu-devel] [PATCH 08/29] ui/console: remove dpy_gfx_update_dirty Paolo Bonzini
2015-05-26  8:03   ` Fam Zheng
2015-04-27 16:28 ` [Qemu-devel] [PATCH 09/29] memory: track DIRTY_MEMORY_CODE in mr->dirty_log_mask Paolo Bonzini
2015-05-26  8:06   ` Fam Zheng
2015-04-27 16:28 ` [Qemu-devel] [PATCH 10/29] kvm: accept non-mapped memory in kvm_dirty_pages_log_change Paolo Bonzini
2015-05-26  8:10   ` Fam Zheng
2015-05-26  8:16     ` Paolo Bonzini
2015-05-26  8:22       ` Fam Zheng
2015-04-27 16:28 ` [Qemu-devel] [PATCH 11/29] memory: include DIRTY_MEMORY_MIGRATION in the dirty log mask Paolo Bonzini
2015-05-26  8:40   ` Fam Zheng
2015-05-26  9:07     ` Paolo Bonzini
2015-05-26  9:22       ` Fam Zheng
2015-05-26  9:26         ` Paolo Bonzini
2015-05-26  9:48           ` Fam Zheng
2015-05-26  9:07     ` Paolo Bonzini
2015-04-27 16:28 ` [Qemu-devel] [PATCH 12/29] kvm: remove special handling of " Paolo Bonzini
2015-05-26  8:56   ` Fam Zheng
2015-04-27 16:28 ` [Qemu-devel] [PATCH 13/29] ram_addr: tweaks to xen_modified_memory Paolo Bonzini
2015-05-26 12:52   ` Fam Zheng
2015-04-27 16:28 ` [Qemu-devel] [PATCH 14/29] exec: use memory_region_get_dirty_log_mask to optimize dirty tracking Paolo Bonzini
2015-05-26 10:42   ` Fam Zheng
2015-05-26 10:58     ` Paolo Bonzini
2015-05-26 11:12       ` Fam Zheng
2015-04-27 16:28 ` [Qemu-devel] [PATCH 15/29] exec: move functions to translate-all.h Paolo Bonzini
2015-05-26 10:50   ` Fam Zheng
2015-04-27 16:28 ` [Qemu-devel] [PATCH 16/29] translate-all: remove unnecessary argument to tb_invalidate_phys_range Paolo Bonzini
2015-05-26 10:51   ` Fam Zheng
2015-04-27 16:28 ` [Qemu-devel] [PATCH 17/29] cputlb: remove useless arguments to tlb_unprotect_code_phys, rename Paolo Bonzini
2015-05-26 10:53   ` Fam Zheng
2015-04-27 16:28 ` [Qemu-devel] [PATCH 18/29] translate-all: make less of tb_invalidate_phys_page_range depend on is_cpu_write_access Paolo Bonzini
2015-04-27 16:28 ` [Qemu-devel] [PATCH 19/29] exec: pass client mask to cpu_physical_memory_set_dirty_range Paolo Bonzini
2015-05-26 11:08   ` Fam Zheng
2015-05-26 11:28     ` Paolo Bonzini
2015-04-27 16:28 ` [Qemu-devel] [PATCH 20/29] exec: invert return value of cpu_physical_memory_get_clean, rename Paolo Bonzini
2015-05-26 11:26   ` Fam Zheng
2015-04-27 16:28 ` [Qemu-devel] [PATCH 21/29] exec: only check relevant bitmaps for cleanliness Paolo Bonzini
2015-05-26 11:31   ` Fam Zheng
2015-04-27 16:28 ` [Qemu-devel] [PATCH 22/29] memory: do not touch code dirty bitmap unless TCG is enabled Paolo Bonzini
2015-05-26 11:33   ` Fam Zheng
2015-04-27 16:28 ` [Qemu-devel] [PATCH 23/29] bitmap: add atomic set functions Paolo Bonzini
2015-05-26 11:54   ` Fam Zheng
2015-05-26 11:58     ` Paolo Bonzini
2015-05-26 12:36     ` Fam Zheng
2015-04-27 16:28 ` [Qemu-devel] [PATCH 24/29] bitmap: add atomic test and clear Paolo Bonzini
2015-05-26 12:27   ` Fam Zheng
2015-05-26 12:32     ` Fam Zheng
2015-05-26 12:33     ` Paolo Bonzini
2015-04-27 16:28 ` [Qemu-devel] [PATCH 25/29] memory: use atomic ops for setting dirty memory bits Paolo Bonzini
2015-05-26 12:29   ` Fam Zheng
2015-04-27 16:28 ` [Qemu-devel] [PATCH 26/29] migration: move dirty bitmap sync to ram_addr.h Paolo Bonzini
2015-05-26 12:34   ` Fam Zheng
2015-04-27 16:28 ` [Qemu-devel] [PATCH 27/29] memory: replace cpu_physical_memory_reset_dirty() with test-and-clear Paolo Bonzini
2015-05-26 12:42   ` Fam Zheng
2015-05-26 12:45     ` Paolo Bonzini
2015-04-27 16:28 ` [Qemu-devel] [PATCH 28/29] memory: make cpu_physical_memory_sync_dirty_bitmap() fully atomic Paolo Bonzini
2015-05-26 12:45   ` Fam Zheng
2015-04-27 16:28 ` [Qemu-devel] [PATCH 29/29] memory: strengthen assertions on mr->terminates Paolo Bonzini
2015-05-26 12:49   ` Fam Zheng
2015-05-26 12:52     ` Paolo Bonzini
2015-05-26 12:56       ` Fam Zheng
2015-05-25 21:50 ` [Qemu-devel] [PATCH v2 00/29] Dirty bitmap atomic access and optimizations Paolo Bonzini
2015-05-26 12:58 ` Fam Zheng

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=1430152117-100558-1-git-send-email-pbonzini@redhat.com \
    --to=pbonzini@redhat.com \
    --cc=famz@redhat.com \
    --cc=mst@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=stefanha@redhat.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).