Commit graph

299,176 commits

Author SHA1 Message Date
K. Y. Srinivasan
ae2a0b42bf Staging: hv: util: Forcefully shutdown when shutdown is requested
When the host requests a "shutdown", make sure we shutdown!

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:05:29 -07:00
K. Y. Srinivasan
70691ec666 Staging: hv: storvsc: No need to copy from bounce buffer in case of a failure
No need to copy from bounce buffer in case of a failure; cleanup the code
accordingly.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:09 -07:00
K. Y. Srinivasan
2544b79437 Staging: hv: storvsc: In case of scsi errors offline the device
When we do get fatal errors from the host, offline the device since the
host has already tried all possible recovery actions.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:09 -07:00
K. Y. Srinivasan
b8de73df1b Staging: hv: storvsc: Fix a typo
Fix a typo in a function name.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:09 -07:00
K. Y. Srinivasan
4ed51a21c0 Staging: hv: storvsc: Fixup srb and scsi status for INQUIRY and MODE_SENSE
The current VHD handler on the Windows Host does not correctly handle
INQUIRY and MODE_SENSE commands with some options. Fixup srb_status
in these cases since the failure is not fatal.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:08 -07:00
K. Y. Srinivasan
c1b3d067e4 Staging: hv: storvsc: Cleanup storvsc_drv.c after adding the contents of hyperv_storage.h
Cleanup storvsc_drv.c after adding the contents of hyperv_storage.h.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:08 -07:00
K. Y. Srinivasan
f0d79fe9c5 Staging: hv: storvsc: Add the contents of hyperv_storage.h to storvsc_drv.c
As part of further cleanup of storvsc, add the contents of hyperv_storage.h
to storvsc_drv.c and do the necessary adjustments.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:08 -07:00
K. Y. Srinivasan
a1be1706ed Staging: hv: storvsc: Cleanup storvsc_drv.c after adding the contents of storvsc.c
Cleanup storvsc_drv.c after adding the contents of storvsc.c.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:07 -07:00
K. Y. Srinivasan
8dcf37d446 Staging: hv: storvsc: Include storvsc.c in storvsc_drv.c
As part of further cleanup of our storage drivers, include the content
of storvsc.c into storvsc_drv.c and delete storvsc.c and do the necessary
adjustments.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:07 -07:00
K. Y. Srinivasan
fa23b8c78f Staging: hv: storvsc: Optimize the bounce buffer handling in the "read" case
Optimize the bounce buffer handling in the "read" case.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:07 -07:00
K. Y. Srinivasan
3612ef99b0 Staging: hv: storvsc: Optimize bounce buffer handling for the "write" case
Optimize bounce buffer handling for the "write" case.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:06 -07:00
K. Y. Srinivasan
b38cc43432 Staging: hv: blkvsc: Get rid of blkvsc_drv.c as this code is not used
Now that blkvsc driver is no longer needed, remove blkvsc_drv.c

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:06 -07:00
K. Y. Srinivasan
21e3774236 Staging: hv: storvsc: Handle IDE devices using the storvsc driver
Now, enable handling of all IDE devices by extending the storvsc
device id table to handle IDE guid. As part of this cleanup Kconfig
and Hyper-V Makefile to not build the IDE driver (blkvsc).

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:06 -07:00
K. Y. Srinivasan
bd1f5d6a00 Staging: hv: storvsc: Add code to handle IDE devices using the storvsc driver
Add code to handle IDE devices using the storvsc driver. The storvsc_probe()
is modified so that the storvsc driver can surface all disks presented to the
guest as scsi devices using generic upper level Linux scsi drivers.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:06 -07:00
K. Y. Srinivasan
9d88f33a15 Staging: hv: netvsc: Get rid of the refcnt field in struct netvsc_device
Get rid of the refcnt field in struct netvsc_device. We implement the following
logic to manage the life cycle of the device: If the device is being destroyed,
we do not allow any outgoing traffic. Furthermore, if the device is being
destroyed, we allow incoming traffic only to drain outgoing traffic. Note that
the driver may send some book keeping messages to the host not known to
upper level Linux code.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:05 -07:00
K. Y. Srinivasan
124f506dc1 Staging: hv: netvsc: Get rid of release_inbound_net_device() by inlining the code
Get rid of release_inbound_net_device() by inlining the code.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:05 -07:00
K. Y. Srinivasan
3852409b88 Staging: hv: netvsc: Get rid of release_outbound_net_device() by inlining the code
Get rid of release_outbound_net_device() by inlining the code.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:05 -07:00
K. Y. Srinivasan
2ef7714397 Staging: hv: netvsc: Prevent outgoing traffic when netvsc dev is destroyed
Prevent outgoing traffic when netvsc dev is destroyed.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:05 -07:00
K. Y. Srinivasan
c38b9c7118 Staging: hv: netvsc: Introduce state to manage the lifecycle of net device
Introduce state to manage the lifecycle of net device.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:04 -07:00
K. Y. Srinivasan
509ee3878b Staging: hv: netvsc: Cleanup alloc_net_device()
Cleanup alloc_net_device(); we can directly set the refcnt.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:04 -07:00
K. Y. Srinivasan
356c465719 Staging: hv: netvsc: Inline the code for free_net_device()
Inline the code for free_net_device().

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:04 -07:00
K. Y. Srinivasan
5e6f4d069f Staging: hv: storvsc: Get rid of the reference counting in struct storvsc_device
Get rid of the reference counting in struct storvsc_device. We manage the lifecycle with
the following logic: If the device is marked for destruction, we dot allow any
outgoing traffic on the device. Incoming traffic is allowed only to drain pending
outgoing traffic. Note that while the upper level code in Linux deals with outstanding
I/Os, we may have situations on Hyper-V where some book keeping messages are sent out
that the upper level Linux code may not be aware of.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:04 -07:00
K. Y. Srinivasan
a5b2359b05 Staging: hv: storvsc: Get rid of final_release_stor_device() by inlining code
Get rid of final_release_stor_device() by inlining code.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:03 -07:00
K. Y. Srinivasan
c352ee8f61 Staging: hv: storvsc: Get rid of release_stor_device() by inlining the code
Get rid of release_stor_device() by inlining the code.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:03 -07:00
K. Y. Srinivasan
582f445fde Staging: hv: storvsc: Prevent outgoing traffic when stor dev is being destroyed
Prevent outgoing traffic when stor dev is destroyed.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:03 -07:00
K. Y. Srinivasan
f6c17484eb Staging: hv: storvsc: Introduce state to manage the lifecycle of stor device
Introduce state to manage the lifecycle of stor device. This would be the
basis for managing the references on the stor object.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:02 -07:00
K. Y. Srinivasan
df977d6c90 Staging: hv: storvsc: Cleanup alloc_stor_device()
Cleanup alloc_stor_device(), we can set the ref_count directly.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:02 -07:00
K. Y. Srinivasan
1eaaddf938 Staging: hv: storvsc: Rename get_stor_device()
In preparation for cleaning up how we manage reference counts on the stor
device, clearly distinguish why we are attempting to acquire a reference.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:02 -07:00
K. Y. Srinivasan
bf49e80998 Staging: hv: storvsc: Rename must_get_stor_device()
In preparation for cleaning up how we manage reference counts on the stor
device, clearly distinguish why we are attempting to acquire a reference.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:02 -07:00
K. Y. Srinivasan
bdbc49706b Staging: hv: storvsc: Do not aquire an unnecessary reference on stor_device
On entry into storvsc_on_io_completion() we have already acquired a reference
on the stor_device; there is no need to acquire an additional reference here.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:01 -07:00
K. Y. Srinivasan
0fb07a87ec Staging: hv: storvsc: Inline free_stor_device()
Inline the code for  free_stor_device() and get rid of the function.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 11:01:01 -07:00
Larry Finger
a504de3a1e staging: rtl8192e: Fix array overrun
Smatch outputs the following message:

drivers/staging/rtl8192e/r8192E_cmdpkt.c +412 cmpk_message_handle_rx(70)
	error: buffer overflow 'priv->stats.rxcmdpkt' 4 <= 7

   407                          RT_TRACE(COMP_CMDPKT, "---->cmpk_message_handle_rx():"
   408                                   "unknow CMD Element\n");
   409                          return 1;
   410                  }
   411
   412                  priv->stats.rxcmdpkt[element_id]++;
                                             ^^^^^^^^^^
->stats.rxcmdpkt[] only has 4 elements, but from the switch statement
in the section before we can see that element_id can go up to 7
(RX_TX_RATE_HISTORY).

Reported-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Larry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 10:58:00 -07:00
Florian Tobias Schandinat
f9557a4477 MAINTAINERS: change framebuffer maintainer
As Paul has not much time for it I take over maintaining the
framebuffer subsystem.

Signed-off-by: Florian Tobias Schandinat <FlorianSchandinat@gmx.de>
Acked-by: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-08-29 10:13:29 -07:00
Kjetil Oftedal
38f7f8f05e sparc32,sun4d: Change IPI IRQ level to prevent collision between IPI and timer interrupt
On Sun4d systems running in SMP mode, IRQ 14 is used for timer interrupts
and has a specialized interrupt handler. IPI is currently set to use IRQ 14
as well, which causes it to trigger the timer interrupt handler, and not the
IPI interrupt handler.

The IPI interrupt is therefore changed to IRQ 13, which is the highest
normally handled interrupt. This IRQ is also used for SBUS interrupts,
however there is nothing in the IPI/SBUS interrupt handlers that indicate
that they will not handle sharing the interrupt.
(IRQ 13 is indicated as audio interrupt, which is unlikely to be found in a
sun4d system)

Signed-off-by: Kjetil Oftedal <oftedal@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-08-29 09:20:40 -07:00
Stephen Rothwell
2ee04a1069 sparc: Remove another reference to nfsservctl
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-08-29 09:19:24 -07:00
Greg Kroah-Hartman
6ed962a208 Merge 3.1-rc4 into usb-next
This was done to resolve a conflict in this file:
	drivers/usb/host/xhci-ring.c

Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 08:56:17 -07:00
Greg Kroah-Hartman
6eafa4604c Merge 3.1-rc4 into staging-next
This resolves a conflict with:
	drivers/staging/brcm80211/brcmsmac/types.h

Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-29 08:47:46 -07:00
Sakari Ailus
69d232ae8e [media] omap3isp: ccdc: Use generic frame sync event instead of private HS_VS event
The ccdc block in the omap3isp produces events whenever it starts receiving
a new frame. A private HS_VS event was used for this previously. Now, the
generic V4L2_EVENT_FRAME_SYNC event is being used for the purpose.

This patch also provides the frame sequence number to user space.

Signed-off-by: Sakari Ailus <sakari.ailus@iki.fi>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2011-08-29 12:38:51 -03:00
Sakari Ailus
eab00a0da2 [media] v4l: events: Define V4L2_EVENT_FRAME_SYNC
Define a frame sync event to tell user space when the reception of a frame
starts.

Signed-off-by: Sakari Ailus <sakari.ailus@iki.fi>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2011-08-29 12:37:15 -03:00
Sascha Hauer
7b4b88e067 dmaengine i.MX SDMA: use request_firmware_nowait
The firmware blob may not be available when the driver
probes. Instead of blocking the whole kernel use
request_firmware_nowait() and continue without firmware.
The ROM scripts can already be used then if available.
For the devicetree case the ROM scripts are not available,
still the probe function should not block. The driver
will be unusable in this case, but we have no way of
detecting this properly. The configuration of the dma
channels will fail, so nothing bad should happen.

Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
2011-08-29 20:08:53 +05:30
Sascha Hauer
36e2f21ab4 dmaengine i.MX SDMA: set firmware scripts addresses to negative value initially
If we do not have a firmare script for a given transfer,
the setup of this channel must fail. For this the script
addresses have to be < 0 initially, not 0.

Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
2011-08-29 20:08:37 +05:30
Sascha Hauer
73eab978ad dmaengine i.MX SDMA: lock channel 0
channel0 of the sdma engine is the configuration channel. It
is a shared resource and thus must be protected by a mutex.

Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
2011-08-29 20:08:26 +05:30
Mark Brown
59ec6da2e3 MAINTAINERS: Add some missed Wolfson files
Mostly input related.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
2011-08-29 14:00:26 +01:00
Guennadi Liakhovetski
981ed70d8e dmatest: make dmatest threads freezable
Making dmatest threads freezable allows its use for system PM testing.

Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
2011-08-29 18:01:27 +05:30
Joonyoung Shim
6380c50921 drm: Fix the number of connector and encoder to cleanup functions
It is left out the code to decrease the number of connector and encoder
to the cleanup functions.

Signed-off-by: Joonyoung Shim <jy0922.shim@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-08-29 11:47:35 +01:00
Ohad Ben-Cohen
024ae884a6 iommu: omap: add Kconfig OMAP dependency
Make CONFIG_OMAP_IOMMU depend on CONFIG_ARCH_OMAP so other
allmodconfig builds won't fail.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Ohad Ben-Cohen <ohad@wizery.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2011-08-29 12:38:19 +02:00
Stephane Eranian
a8d757ef07 perf events: Fix slow and broken cgroup context switch code
The current cgroup context switch code was incorrect leading
to bogus counts. Furthermore, as soon as there was an active
cgroup event on a CPU, the context switch cost on that CPU
would increase by a significant amount as demonstrated by a
simple ping/pong example:

 $ ./pong
 Both processes pinned to CPU1, running for 10s
 10684.51 ctxsw/s

Now start a cgroup perf stat:
 $ perf stat -e cycles,cycles -A -a -G test  -C 1 -- sleep 100

$ ./pong
 Both processes pinned to CPU1, running for 10s
 6674.61 ctxsw/s

That's a 37% penalty.

Note that pong is not even in the monitored cgroup.

The results shown by perf stat are bogus:
 $ perf stat -e cycles,cycles -A -a -G test  -C 1 -- sleep 100

 Performance counter stats for 'sleep 100':

 CPU1 <not counted> cycles   test
 CPU1 16,984,189,138 cycles  #    0.000 GHz

The second 'cycles' event should report a count @ CPU clock
(here 2.4GHz) as it is counting across all cgroups.

The patch below fixes the bogus accounting and bypasses any
cgroup switches in case the outgoing and incoming tasks are
in the same cgroup.

With this patch the same test now yields:
 $ ./pong
 Both processes pinned to CPU1, running for 10s
 10775.30 ctxsw/s

Start perf stat with cgroup:

 $ perf stat -e cycles,cycles -A -a -G test  -C 1 -- sleep 10

Run pong outside the cgroup:
 $ /pong
 Both processes pinned to CPU1, running for 10s
 10687.80 ctxsw/s

The penalty is now less than 2%.

And the results for perf stat are correct:

$ perf stat -e cycles,cycles -A -a -G test  -C 1 -- sleep 10

 Performance counter stats for 'sleep 10':

 CPU1 <not counted> cycles test #    0.000 GHz
 CPU1 23,933,981,448 cycles      #    0.000 GHz

Now perf stat reports the correct counts for
for the non cgroup event.

If we run pong inside the cgroup, then we also get the
correct counts:

$ perf stat -e cycles,cycles -A -a -G test  -C 1 -- sleep 10

 Performance counter stats for 'sleep 10':

 CPU1 22,297,726,205 cycles test #    0.000 GHz
 CPU1 23,933,981,448 cycles      #    0.000 GHz

      10.001457237 seconds time elapsed

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20110825135803.GA4697@quad
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-08-29 12:28:33 +02:00
WANG Cong
feff8fa007 sched: Fix a memory leak in __sdt_free()
This patch fixes the following memory leak:

unreferenced object 0xffff880107266800 (size 512):
  comm "sched-powersave", pid 3718, jiffies 4323097853 (age 27495.450s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<ffffffff81133940>] create_object+0x187/0x28b
    [<ffffffff814ac103>] kmemleak_alloc+0x73/0x98
    [<ffffffff811232ba>] __kmalloc_node+0x104/0x159
    [<ffffffff81044b98>] kzalloc_node.clone.97+0x15/0x17
    [<ffffffff8104cb90>] build_sched_domains+0xb7/0x7f3
    [<ffffffff8104d4df>] partition_sched_domains+0x1db/0x24a
    [<ffffffff8109ee4a>] do_rebuild_sched_domains+0x3b/0x47
    [<ffffffff810a00c7>] rebuild_sched_domains+0x10/0x12
    [<ffffffff8104d5ba>] sched_power_savings_store+0x6c/0x7b
    [<ffffffff8104d5df>] sched_mc_power_savings_store+0x16/0x18
    [<ffffffff8131322c>] sysdev_class_store+0x20/0x22
    [<ffffffff81193876>] sysfs_write_file+0x108/0x144
    [<ffffffff81135b10>] vfs_write+0xaf/0x102
    [<ffffffff81135d23>] sys_write+0x4d/0x74
    [<ffffffff814c8a42>] system_call_fastpath+0x16/0x1b
    [<ffffffffffffffff>] 0xffffffffffffffff

Signed-off-by: WANG Cong <amwang@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: stable@kernel.org # 3.0
Link: http://lkml.kernel.org/r/1313671017-4112-1-git-send-email-amwang@redhat.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-08-29 12:27:01 +02:00
Thomas Gleixner
9c40cef2b7 sched: Move blk_schedule_flush_plug() out of __schedule()
There is no real reason to run blk_schedule_flush_plug() with
interrupts and preemption disabled.

Move it into schedule() and call it when the task is going voluntarily
to sleep. There might be false positives when the task is woken
between that call and actually scheduling, but that's not really
different from being woken immediately after switching away.

This fixes a deadlock in the scheduler where the
blk_schedule_flush_plug() callchain enables interrupts and thereby
allows a wakeup to happen of the task that's going to sleep.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Tejun Heo <tj@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: stable@kernel.org # 2.6.39+
Link: http://lkml.kernel.org/n/tip-dwfxtra7yg1b5r65m32ywtct@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-08-29 12:26:59 +02:00
Thomas Gleixner
c259e01a1e sched: Separate the scheduler entry for preemption
Block-IO and workqueues call into notifier functions from the
scheduler core code with interrupts and preemption disabled. These
calls should be made before entering the scheduler core.

To simplify this, separate the scheduler core code into
__schedule(). __schedule() is directly called from the places which
set PREEMPT_ACTIVE and from schedule(). This allows us to add the work
checks into schedule(), so they are only called when a task voluntary
goes to sleep.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Tejun Heo <tj@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: stable@kernel.org # 2.6.39+
Link: http://lkml.kernel.org/r/20110622174918.813258321@linutronix.de
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-08-29 12:26:57 +02:00