Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 11 7月, 2013 18 次提交
  3. 10 7月, 2013 22 次提交
    • M
      xilinx systemace: Fix sparse warnings · 4937a269
      由 Michal Simek 提交于 
      Fix sysace sparse warnings.
Signed-off-by: NMichal Simek <michal.simek@xilinx.com>
      4937a269
    • M
      microblaze: Move __NR_syscalls from uapi · 40c2702a
      由 Michal Simek 提交于 
      The reason is that other applications like strace
think that every __NR_xx is syscall.
Also __NR_syscalls is not used by user applications/libs.
Signed-off-by: NMichal Simek <michal.simek@xilinx.com>
      40c2702a
    • L
      Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next · 496322bc
      由 Linus Torvalds 提交于 
      Pull networking updates from David Miller:
 "This is a re-do of the net-next pull request for the current merge
  window.  The only difference from the one I made the other day is that
  this has Eliezer's interface renames and the timeout handling changes
  made based upon your feedback, as well as a few bug fixes that have
  trickeled in.

  Highlights:

   1) Low latency device polling, eliminating the cost of interrupt
      handling and context switches.  Allows direct polling of a network
      device from socket operations, such as recvmsg() and poll().

      Currently ixgbe, mlx4, and bnx2x support this feature.

      Full high level description, performance numbers, and design in
      commit 0a4db187 ("Merge branch 'll_poll'")

      From Eliezer Tamir.

   2) With the routing cache removed, ip_check_mc_rcu() gets exercised
      more than ever before in the case where we have lots of multicast
      addresses.  Use a hash table instead of a simple linked list, from
      Eric Dumazet.

   3) Add driver for Atheros CQA98xx 802.11ac wireless devices, from
      Bartosz Markowski, Janusz Dziedzic, Kalle Valo, Marek Kwaczynski,
      Marek Puzyniak, Michal Kazior, and Sujith Manoharan.

   4) Support reporting the TUN device persist flag to userspace, from
      Pavel Emelyanov.

   5) Allow controlling network device VF link state using netlink, from
      Rony Efraim.

   6) Support GRE tunneling in openvswitch, from Pravin B Shelar.

   7) Adjust SOCK_MIN_RCVBUF and SOCK_MIN_SNDBUF for modern times, from
      Daniel Borkmann and Eric Dumazet.

   8) Allow controlling of TCP quickack behavior on a per-route basis,
      from Cong Wang.

   9) Several bug fixes and improvements to vxlan from Stephen
      Hemminger, Pravin B Shelar, and Mike Rapoport.  In particular,
      support receiving on multiple UDP ports.

  10) Major cleanups, particular in the area of debugging and cookie
      lifetime handline, to the SCTP protocol code.  From Daniel
      Borkmann.

  11) Allow packets to cross network namespaces when traversing tunnel
      devices.  From Nicolas Dichtel.

  12) Allow monitoring netlink traffic via AF_PACKET sockets, in a
      manner akin to how we monitor real network traffic via ptype_all.
      From Daniel Borkmann.

  13) Several bug fixes and improvements for the new alx device driver,
      from Johannes Berg.

  14) Fix scalability issues in the netem packet scheduler's time queue,
      by using an rbtree.  From Eric Dumazet.

  15) Several bug fixes in TCP loss recovery handling, from Yuchung
      Cheng.

  16) Add support for GSO segmentation of MPLS packets, from Simon
      Horman.

  17) Make network notifiers have a real data type for the opaque
      pointer that's passed into them.  Use this to properly handle
      network device flag changes in arp_netdev_event().  From Jiri
      Pirko and Timo Teräs.

  18) Convert several drivers over to module_pci_driver(), from Peter
      Huewe.

  19) tcp_fixup_rcvbuf() can loop 500 times over loopback, just use a
      O(1) calculation instead.  From Eric Dumazet.

  20) Support setting of explicit tunnel peer addresses in ipv6, just
      like ipv4.  From Nicolas Dichtel.

  21) Protect x86 BPF JIT against spraying attacks, from Eric Dumazet.

  22) Prevent a single high rate flow from overruning an individual cpu
      during RX packet processing via selective flow shedding.  From
      Willem de Bruijn.

  23) Don't use spinlocks in TCP md5 signing fast paths, from Eric
      Dumazet.

  24) Don't just drop GSO packets which are above the TBF scheduler's
      burst limit, chop them up so they are in-bounds instead.  Also
      from Eric Dumazet.

  25) VLAN offloads are missed when configured on top of a bridge, fix
      from Vlad Yasevich.

  26) Support IPV6 in ping sockets.  From Lorenzo Colitti.

  27) Receive flow steering targets should be updated at poll() time
      too, from David Majnemer.

  28) Fix several corner case regressions in PMTU/redirect handling due
      to the routing cache removal, from Timo Teräs.

  29) We have to be mindful of ipv4 mapped ipv6 sockets in
      upd_v6_push_pending_frames().  From Hannes Frederic Sowa.

  30) Fix L2TP sequence number handling bugs, from James Chapman."

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1214 commits)
  drivers/net: caif: fix wrong rtnl_is_locked() usage
  drivers/net: enic: release rtnl_lock on error-path
  vhost-net: fix use-after-free in vhost_net_flush
  net: mv643xx_eth: do not use port number as platform device id
  net: sctp: confirm route during forward progress
  virtio_net: fix race in RX VQ processing
  virtio: support unlocked queue poll
  net/cadence/macb: fix bug/typo in extracting gem_irq_read_clear bit
  Documentation: Fix references to defunct linux-net@vger.kernel.org
  net/fs: change busy poll time accounting
  net: rename low latency sockets functions to busy poll
  bridge: fix some kernel warning in multicast timer
  sfc: Fix memory leak when discarding scattered packets
  sit: fix tunnel update via netlink
  dt:net:stmmac: Add dt specific phy reset callback support.
  dt:net:stmmac: Add support to dwmac version 3.610 and 3.710
  dt:net:stmmac: Allocate platform data only if its NULL.
  net:stmmac: fix memleak in the open method
  ipv6: rt6_check_neigh should successfully verify neigh if no NUD information are available
  net: ipv6: fix wrong ping_v6_sendmsg return value
  ...
      496322bc
    • L
      Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linux · 2e17c5a9
      由 Linus Torvalds 提交于 
      Pull drm updates from Dave Airlie:
 "Okay this is the big one, I was stalled on the fbdev pull req as I
  stupidly let fbdev guys merge a patch I required to fix a warning with
  some patches I had, they ended up merging the patch from the wrong
  place, but the warning should be fixed.  In future I'll just take the
  patch myself!

  Outside drm:

  There are some snd changes for the HDMI audio interactions on haswell,
  they've been acked for inclusion via my tree.  This relies on the
  wound/wait tree from Ingo which is already merged.

  Major changes:

  AMD finally released the dynamic power management code for all their
  GPUs from r600->present day, this is great, off by default for now but
  also a huge amount of code, in fact it is most of this pull request.

  Since it landed there has been a lot of community testing and Alex has
  sent a lot of fixes for any bugs found so far.  I suspect radeon might
  now be the biggest kernel driver ever :-P p.s.  radeon.dpm=1 to enable
  dynamic powermanagement for anyone.

  New drivers:

  Renesas r-car display unit.

  Other highlights:

   - core: GEM CMA prime support, use new w/w mutexs for TTM
     reservations, cursor hotspot, doc updates
   - dvo chips: chrontel 7010B support
   - i915: Haswell (fbc, ips, vecs, watermarks, audio powerwell),
     Valleyview (enabled by default, rc6), lots of pll reworking, 30bpp
     support (this time for sure)
   - nouveau: async buffer object deletion, context/register init
     updates, kernel vp2 engine support, GF117 support, GK110 accel
     support (with external nvidia ucode), context cleanups.
   - exynos: memory leak fixes, Add S3C64XX SoC series support, device
     tree updates, common clock framework support,
   - qxl: cursor hotspot support, multi-monitor support, suspend/resume
     support
   - mgag200: hw cursor support, g200 mode limiting
   - shmobile: prime support
   - tegra: fixes mostly

  I've been banging on this quite a lot due to the size of it, and it
  seems to okay on everything I've tested it on."

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (811 commits)
  drm/radeon/dpm: implement vblank_too_short callback for si
  drm/radeon/dpm: implement vblank_too_short callback for cayman
  drm/radeon/dpm: implement vblank_too_short callback for btc
  drm/radeon/dpm: implement vblank_too_short callback for evergreen
  drm/radeon/dpm: implement vblank_too_short callback for 7xx
  drm/radeon/dpm: add checks against vblank time
  drm/radeon/dpm: add helper to calculate vblank time
  drm/radeon: remove stray line in old pm code
  drm/radeon/dpm: fix display_gap programming on rv7xx
  drm/nvc0/gr: fix gpc firmware regression
  drm/nouveau: fix minor thinko causing bo moves to not be async on kepler
  drm/radeon/dpm: implement force performance level for TN
  drm/radeon/dpm: implement force performance level for ON/LN
  drm/radeon/dpm: implement force performance level for SI
  drm/radeon/dpm: implement force performance level for cayman
  drm/radeon/dpm: implement force performance levels for 7xx/eg/btc
  drm/radeon/dpm: add infrastructure to force performance levels
  drm/radeon: fix surface setup on r1xx
  drm/radeon: add support for 3d perf states on older asics
  drm/radeon: set default clocks for SI when DPM is disabled
  ...
      2e17c5a9
    • L
      Merge tag 'fbdev-for-3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/plagnioj/linux-fbdev · 5f097cd2
      由 Linus Torvalds 提交于 
      Pull fbdev update from Jean-Christophe PLAGNIOL-VILLARD:
 "Various fbdev changes for 3.11
   - xilinxfb updates
   - Small cleanups and fixes to multiple drivers
   - OMAP display subsystem bug updates
   - imxfb dt support"

* tag 'fbdev-for-3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/plagnioj/linux-fbdev: (95 commits)
  video: imxfb: Add DT support
  video: i740fb: Make i740fb_init static
  fb: make fp_get_options name argument const
  video: mmp: fix graphics/video layer enable/mask swap issue
  video: mmp: fix memcpy wrong size for mmp_addr issue
  radeon: use pdev->pm_cap instead of pci_find_capability(..,PCI_CAP_ID_PM)
  aty128fb: use pdev->pm_cap instead of pci_find_capability(..,PCI_CAP_ID_PM)
  video: of_display_timing.h: Declare 'display_timing'
  fbdev: bfin-lq035q1-fb: Use dev_pm_ops
  fbmem: return -EFAULT on copy_to_user() failure
  OMAPDSS: DPI: Fix wrong pixel clock limit
  video: replace strict_strtoul() with kstrtoul()
  uvesafb: Correct/simplify warning message
  fb: fix atyfb unused data warnings
  fb: fix atyfb build warning
  video: imxfb: Make local symbols static
  video: udlfb: Make local symbol static
  video: udlfb: Use NULL instead of 0
  video: smscufx: Use NULL instead of 0
  video: remove unnecessary platform_set_drvdata()
  ...
      5f097cd2
    • L
      Merge branch 'akpm' (updates from Andrew Morton) · a82a729f
      由 Linus Torvalds 提交于 
      Merge second patch-bomb from Andrew Morton:
 - misc fixes
 - audit stuff
 - fanotify/inotify/dnotify things
 - most of the rest of MM.  The new cache shrinker code from Glauber and
   Dave Chinner probably isn't quite stabilized yet.
 - ptrace
 - ipc
 - partitions
 - reboot cleanups
 - add LZ4 decompressor, use it for kernel compression

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (118 commits)
  lib/scatterlist: error handling in __sg_alloc_table()
  scsi_debug: fix do_device_access() with wrap around range
  crypto: talitos: use sg_pcopy_to_buffer()
  lib/scatterlist: introduce sg_pcopy_from_buffer() and sg_pcopy_to_buffer()
  lib/scatterlist: factor out sg_miter_get_next_page() from sg_miter_next()
  crypto: add lz4 Cryptographic API
  lib: add lz4 compressor module
  arm: add support for LZ4-compressed kernel
  lib: add support for LZ4-compressed kernel
  decompressor: add LZ4 decompressor module
  lib: add weak clz/ctz functions
  reboot: move arch/x86 reboot= handling to generic kernel
  reboot: arm: change reboot_mode to use enum reboot_mode
  reboot: arm: prepare reboot_mode for moving to generic kernel code
  reboot: arm: remove unused restart_mode fields from some arm subarchs
  reboot: unicore32: prepare reboot_mode for moving to generic kernel code
  reboot: x86: prepare reboot_mode for moving to generic kernel code
  reboot: checkpatch.pl the new kernel/reboot.c file
  reboot: move shutdown/reboot related functions to kernel/reboot.c
  reboot: remove -stable friendly PF_THREAD_BOUND define
  ...
      a82a729f
    • H
      parisc: Fix gcc miscompilation in pa_memcpy() · 5b879d78
      由 Helge Deller 提交于 
      When running the LTP testsuite one may hit this kernel BUG() with the
write06 testcase:

kernel BUG at mm/filemap.c:2023!
CPU: 1 PID: 8614 Comm: writev01 Not tainted 3.10.0-rc7-64bit-c3000+ #6
IASQ: 0000000000000000 0000000000000000 IAOQ: 00000000401e6e84 00000000401e6e88
 IIR: 03ffe01f    ISR: 0000000010340000  IOR: 000001fbe0380820
 CPU:        1   CR30: 00000000bef80000 CR31: ffffffffffffffff
 ORIG_R28: 00000000bdc192c0
 IAOQ[0]: iov_iter_advance+0x3c/0xc0
 IAOQ[1]: iov_iter_advance+0x40/0xc0
 RP(r2): generic_file_buffered_write+0x204/0x3f0
Backtrace:
 [<00000000401e764c>] generic_file_buffered_write+0x204/0x3f0
 [<00000000401eab24>] __generic_file_aio_write+0x244/0x448
 [<00000000401eadc0>] generic_file_aio_write+0x98/0x150
 [<000000004024f460>] do_sync_readv_writev+0xc0/0x130
 [<000000004025037c>] compat_do_readv_writev+0x12c/0x340
 [<00000000402505f8>] compat_writev+0x68/0xa0
 [<0000000040251d88>] compat_SyS_writev+0x98/0xf8

Reason for this crash is a gcc miscompilation in the fault handlers of
pa_memcpy() which return the fault address instead of the copied bytes.
Since this seems to be a generic problem with gcc-4.7.x (and below), it's
better to simplify the fault handlers in pa_memcpy to avoid this problem.

Here is a simple reproducer for the problem:

int main(int argc, char **argv)
{
	int fd, nbytes;
	struct iovec wr_iovec[] = {
		{ "TEST STRING                     ",32},
		{ (char*)0x40005000,32} }; // random memory.
	fd = open(DATA_FILE, O_RDWR | O_CREAT, 0666);
	nbytes = writev(fd, wr_iovec, 2);
	printf("return value = %d, errno %d (%s)\n",
		nbytes, errno, strerror(errno));
	return 0;
}

In addition, John David Anglin wrote:
There is no gcc PR as pa_memcpy is not legitimate C code. There is an
implicit assumption that certain variables will contain correct values
when an exception occurs and the code randomly jumps to one of the
exception blocks.  There is no guarantee of this.  If a PR was filed, it
would likely be marked as invalid.
Signed-off-by: NHelge Deller <deller@gmx.de>
Signed-off-by: NJohn David Anglin <dave.anglin@bell.net>
Cc: <stable@vger.kernel.org> # 3.8+
Signed-off-by: NHelge Deller <deller@gmx.de>
      5b879d78
    • J
      parisc: Ensure volatile space register %sr1 is not clobbered · e8d8fc21
      由 John David Anglin 提交于 
      I still see the occasional random segv on rp3440.  Looking at one of
these (a code 15), it appeared the problem must be with the cache
handling of anonymous pages.  Reviewing this, I noticed that the space
register %sr1 might be being clobbered when we flush an anonymous page.

Register %sr1 is used for TLB purges in a couple of places.  These
purges are needed on PA8800 and PA8900 processors to ensure cache
consistency of flushed cache lines.

The solution here is simply to move the %sr1 load into the TLB lock
region needed to ensure that one purge executes at a time on SMP
systems.  This was already the case for one use.  After a few days of
operation, I haven't had a random segv on my rp3440.
Signed-off-by: NJohn David Anglin <dave.anglin@bell.net>
Cc: <stable@vger.kernel.org> # 3.10
Signed-off-by: NHelge Deller <deller@gmx.de>
      e8d8fc21
    • H
      parisc: optimize mtsp(0,sr) inline assembly · 92b59929
      由 Helge Deller 提交于 
      If the value which should be moved into a space register is zero, we can
optimize the inline assembly to become "mtsp %r0,%srX".
Signed-off-by: NHelge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org> # 3.10
      92b59929
    • H
      parisc: switch to gzip-compressed vmlinuz kernel · 594174d8
      由 Helge Deller 提交于 
      The latest PA-RISC Boot Loader (palo) allows loading of gzip compressed
vmlinuz kernels. So let's now switch to build a vmlinuz file when we
build a palo boot image.

PALO version 1.9 (or higher) is required for this which is available at
git://git.kernel.org/pub/scm/linux/kernel/git/deller/palo.gitSigned-off-by: NHelge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org> # 3.10
      594174d8
    • H
      parisc: document the shadow registers · a83f58bc
      由 Helge Deller 提交于 
      Signed-off-by: NHelge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org> # 3.10
      a83f58bc
    • H
      parisc: more capabilities info in /proc/cpuinfo · 30a9f0b2
      由 Helge Deller 提交于 
      Signed-off-by: NHelge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org> # 3.10
      30a9f0b2
    • H
      parisc: fix LMMIO mismatch between PAT length and MASK register · dac76f1b
      由 Helge Deller 提交于 
      The LMMIO length reported by PAT and the length given by the LBA MASK
register are not consistent. This leads e.g. to a not-working ATI FireGL
card with the radeon DRM driver since the memory can't be mapped.

Fix this by correctly adjusting the resource sizes.
Signed-off-by: NHelge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org> # 3.10
      dac76f1b
    • K
      drivers/net: caif: fix wrong rtnl_is_locked() usage · 56e0ef52
      由 Konstantin Khlebnikov 提交于 
      rtnl_is_locked() doesn't check who holds this lock, it just tells that it's
locked right now. if caif::ldisc_close really can be called under rtrnl_lock
then it should release net device in other context because there is no way
to grab rtnl_lock without deadlock.

This patch adds work which releases these devices. Also this patch fixes calling
dev_close/unregister_netdevice without rtnl_lock from caif_ser_exit().
Signed-off-by: NKonstantin Khlebnikov <khlebnikov@openvz.org>
Cc: Dmitry Tarnyagin <dmitry.tarnyagin@lockless.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      56e0ef52
    • K
      drivers/net: enic: release rtnl_lock on error-path · e057590b
      由 Konstantin Khlebnikov 提交于 
      enic_change_mtu_work() must call rtnl_unlock() on all exiting paths.
Signed-off-by: NKonstantin Khlebnikov <khlebnikov@openvz.org>
Cc: Christian Benvenuti <benve@cisco.com>
Cc: Roopa Prabhu <roprabhu@cisco.com>
Cc: Neel Patel <neepatel@cisco.com>
Cc: Nishank Trivedi <nistrive@cisco.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      e057590b
    • M
      vhost-net: fix use-after-free in vhost_net_flush · dd7633ec
      由 Michael S. Tsirkin 提交于 
      vhost_net_ubuf_put_and_wait has a confusing name:
it will actually also free it's argument.
Thus since commit 1280c27f
    "vhost-net: flush outstanding DMAs on memory change"
vhost_net_flush tries to use the argument after passing it
to vhost_net_ubuf_put_and_wait, this results
in use after free.
To fix, don't free the argument in vhost_net_ubuf_put_and_wait,
add an new API for callers that want to free ubufs.
Acked-by: NAsias He <asias@redhat.com>
Acked-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      dd7633ec
    • L
      Merge tag 'for-linus-3.11-merge-window-part-1' of... · 899dd388
      由 Linus Torvalds 提交于 
      Merge tag 'for-linus-3.11-merge-window-part-1' of git://git.kernel.org/pub/scm/linux/kernel/git/ericvh/v9fs

Pull 9p update from Eric Van Hensbergen:
 "Grab bag of little fixes and enhancements:
  - optional security enhancements
  - fix path coverage in MAINTAINERS
  - switch to using most used protocol and transport as default
  - clean up buffer dumps in trace code

  Held off on RDMA patches as they need to be cleaned up a bit, but will
  try to get the cleaned, checked, and pushed by mid-week"

* tag 'for-linus-3.11-merge-window-part-1' of git://git.kernel.org/pub/scm/linux/kernel/git/ericvh/v9fs:
  9p: Add rest of 9p files to MAINTAINERS entry
  9p: trace: use %*ph to dump buffer
  net/9p: Handle error in zero copy request correctly for 9p2000.u
  net/9p: Use virtio transpart as the default transport
  net/9p: Make 9P2000.L the default protocol for 9p file system
      899dd388
    • J
      net: mv643xx_eth: do not use port number as platform device id · 785bf6f7
      由 Jonas Gorski 提交于 
      The port number is only local to the ethernet block, not global, so
there can be two ethernet blocks both using the same port, like
kirkwood with both using port 0.

Fix this by using the array index offset for the allocated platform
devices as the id.
Signed-off-by: NJonas Gorski <jogo@openwrt.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      785bf6f7
    • D
      net: sctp: confirm route during forward progress · 8c2f414a
      由 Daniel Borkmann 提交于 
      This fix has been proposed originally by Vlad Yasevich. He says:

  When SCTP makes forward progress (receives a SACK that acks new chunks,
  renegs, or answeres 0-window probes) or when HB-ACK arrives, mark
  the route as confirmed so we don't unnecessarily send NUD probes.

Having a simple SCTP client/server that exchange data chunks every 1sec,
without this patch ARP requests are sent periodically every 40-60sec.
With this fix applied, an ARP request is only done once right at the
"session" beginning. Also, when clearing the related ARP cache entry
manually during the session, a new request is correctly done. I have
only "backported" this to net-next and tested that it works, so full
credit goes to Vlad.
Signed-off-by: NVlad Yasevich <vyasevich@gmail.com>
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Acked-by: NNeil Horman <nhorman@tuxdriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      8c2f414a
    • D
      virtio_net: fix race in RX VQ processing · e1d6fbc3
      由 David S. Miller 提交于 
      Michael S. Tsirkin says:

====================
Jason Wang reported a race in RX VQ processing:
virtqueue_enable_cb is called outside napi lock,
violating virtio serialization rules.
The race has been there from day 1, but it got especially nasty in 3.0
when commit a5c262c5
"virtio_ring: support event idx feature"
added more dependency on vq state.

Please review, and consider for 3.11 and stable.

Changes from v1:
	- Added Jason's Tested-by tag
	- minor coding style fix
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      e1d6fbc3
    • M
      virtio_net: fix race in RX VQ processing · cbdadbbf
      由 Michael S. Tsirkin 提交于 
      virtio net called virtqueue_enable_cq on RX path after napi_complete, so
with NAPI_STATE_SCHED clear - outside the implicit napi lock.
This violates the requirement to synchronize virtqueue_enable_cq wrt
virtqueue_add_buf.  In particular, used event can move backwards,
causing us to lose interrupts.
In a debug build, this can trigger panic within START_USE.

Jason Wang reports that he can trigger the races artificially,
by adding udelay() in virtqueue_enable_cb() after virtio_mb().

However, we must call napi_complete to clear NAPI_STATE_SCHED before
polling the virtqueue for used buffers, otherwise napi_schedule_prep in
a callback will fail, causing us to lose RX events.

To fix, call virtqueue_enable_cb_prepare with NAPI_STATE_SCHED
set (under napi lock), later call virtqueue_poll with
NAPI_STATE_SCHED clear (outside the lock).
Reported-by: NJason Wang <jasowang@redhat.com>
Tested-by: NJason Wang <jasowang@redhat.com>
Acked-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      cbdadbbf
    • M
      virtio: support unlocked queue poll · cc229884
      由 Michael S. Tsirkin 提交于 
      This adds a way to check ring empty state after enable_cb outside any
locks. Will be used by virtio_net.

Note: there's room for more optimization: caller is likely to have a
memory barrier already, which means we might be able to get rid of a
barrier here.  Deferring this optimization until we do some
benchmarking.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      cc229884