During allocator-intensive workloads, kswapd will be woken frequently
causing free memory to oscillate between the high and min watermark. This
is expected behaviour. Unfortunately, if the highest zone is small, a
problem occurs.
When balance_pgdat() returns, it may be at a lower classzone_idx than it
started because the highest zone was unreclaimable. Before checking if it
should go to sleep though, it checks pgdat->classzone_idx which when there
is no other activity will be MAX_NR_ZONES-1. It interprets this as it has
been woken up while reclaiming, skips scheduling and reclaims again. As
there is no useful reclaim work to do, it enters into a loop of shrinking
slab consuming loads of CPU until the highest zone becomes reclaimable for
a long period of time.
There are two problems here. 1) If the returned classzone or order is
lower, it'll continue reclaiming without scheduling. 2) if the highest
zone was marked unreclaimable but balance_pgdat() returns immediately at
DEF_PRIORITY, the new lower classzone is not communicated back to kswapd()
for sleeping.
This patch does two things that are related. If the end_zone is
unreclaimable, this information is communicated back. Second, if the
classzone or order was reduced due to failing to reclaim, new information
is not read from pgdat and instead an attempt is made to go to sleep. Due
to this, it is also necessary that pgdat->classzone_idx be initialised
each time to pgdat->nr_zones - 1 to avoid re-reads being interpreted as
wakeups.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Andrew Lutomirski <luto@mit.edu>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When deciding if kswapd is sleeping prematurely, the classzone is taken
into account but this is different to what balance_pgdat() and the
allocator are doing. Specifically, the DMA zone will be checked based on
the classzone used when waking kswapd which could be for a GFP_KERNEL or
GFP_HIGHMEM request. The lowmem reserve limit kicks in, the watermark is
not met and kswapd thinks it's sleeping prematurely keeping kswapd awake in
error.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Andrew Lutomirski <luto@mit.edu>
Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
During allocator-intensive workloads, kswapd will be woken frequently
causing free memory to oscillate between the high and min watermark. This
is expected behaviour.
When kswapd applies pressure to zones during node balancing, it checks if
the zone is above a high+balance_gap threshold. If it is, it does not
apply pressure but it unconditionally shrinks slab on a global basis which
is excessive. In the event kswapd is being kept awake due to a high small
unreclaimable zone, it skips zone shrinking but still calls shrink_slab().
Once pressure has been applied, the check for zone being unreclaimable is
being made before the check is made if all_unreclaimable should be set.
This miss of unreclaimable can cause has_under_min_watermark_zone to be
set due to an unreclaimable zone preventing kswapd backing off on
congestion_wait().
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Andrew Lutomirski <luto@mit.edu>
Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
During allocator-intensive workloads, kswapd will be woken frequently
causing free memory to oscillate between the high and min watermark. This
is expected behaviour. Unfortunately, if the highest zone is small, a
problem occurs.
This seems to happen most with recent sandybridge laptops but it's
probably a co-incidence as some of these laptops just happen to have a
small Normal zone. The reproduction case is almost always during copying
large files that kswapd pegs at 100% CPU until the file is deleted or
cache is dropped.
The problem is mostly down to sleeping_prematurely() keeping kswapd awake
when the highest zone is small and unreclaimable and compounded by the
fact we shrink slabs even when not shrinking zones causing a lot of time
to be spent in shrinkers and a lot of memory to be reclaimed.
Patch 1 corrects sleeping_prematurely to check the zones matching
the classzone_idx instead of all zones.
Patch 2 avoids shrinking slab when we are not shrinking a zone.
Patch 3 notes that sleeping_prematurely is checking lower zones against
a high classzone which is not what allocators or balance_pgdat()
is doing leading to an artifical belief that kswapd should be
still awake.
Patch 4 notes that when balance_pgdat() gives up on a high zone that the
decision is not communicated to sleeping_prematurely()
This problem affects 2.6.38.8 for certain and is expected to affect 2.6.39
and 3.0-rc4 as well. If accepted, they need to go to -stable to be picked
up by distros and this series is against 3.0-rc4. I've cc'd people that
reported similar problems recently to see if they still suffer from the
problem and if this fixes it.
This patch: correct the check for kswapd sleeping in sleeping_prematurely()
During allocator-intensive workloads, kswapd will be woken frequently
causing free memory to oscillate between the high and min watermark. This
is expected behaviour.
A problem occurs if the highest zone is small. balance_pgdat() only
considers unreclaimable zones when priority is DEF_PRIORITY but
sleeping_prematurely considers all zones. It's possible for this sequence
to occur
1. kswapd wakes up and enters balance_pgdat()
2. At DEF_PRIORITY, marks highest zone unreclaimable
3. At DEF_PRIORITY-1, ignores highest zone setting end_zone
4. At DEF_PRIORITY-1, calls shrink_slab freeing memory from
highest zone, clearing all_unreclaimable. Highest zone
is still unbalanced
5. kswapd returns and calls sleeping_prematurely
6. sleeping_prematurely looks at *all* zones, not just the ones
being considered by balance_pgdat. The highest small zone
has all_unreclaimable cleared but the zone is not
balanced. all_zones_ok is false so kswapd stays awake
This patch corrects the behaviour of sleeping_prematurely to check the
zones balance_pgdat() checked.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Andrew Lutomirski <luto@mit.edu>
Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The LM95241 driver accepts every chip ID equal to or larger than 0xA4 as its
own, and other chips such as LM95245 use chip IDs in the accepted ID range.
This results in false chip detection.
Fix problem by accepting only the known LM95241 chip ID.
Signed-off-by: Guenter Roeck <guenter.roeck@ericsson.com>
Acked-by: Jean Delvare <khali@linux-fr.org>
Cc: stable@kernel.org # 2.6.30+
Multiple attempts to dynamically reallocate pci resources have
unfortunately lead to regressions. Though we continue to fix the
regressions and fine tune the dynamic-reallocation behavior, we have not
reached a acceptable state yet.
This patch provides a interim solution. It disables dynamic reallocation
by default, but adds the ability to enable it through pci=realloc kernel
command line parameter.
Tested-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
The ramp_delay variable can be set lower than the desired value.
This patch fixes it.
Signed-off-by: Donggeun Kim <dg77.kim@samsung.com>
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Signed-off-by: KyungMin Park <kyungmin.park@samsung.com>
Acked-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Liam Girdwood <lrg@slimlogic.co.uk>
Small cleanups for better readability.
Signed-off-by: Axel Lin <axel.lin@gmail.com>
Acked-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Liam Girdwood <lrg@slimlogic.co.uk>
The platform_data (pdata) may be pointing to __initdata section, which
may be free'd from the memory. The dependency on pdata in non-init
functions is removed in this patch to allow platform to declare
__initdata for platform data.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Acked-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Liam Girdwood <lrg@slimlogic.co.uk>
Currently, ramp_delay variable is used uninitialzed in
max8997_set_voltage_ldobuck which gets called through
regulator_register calls.
To fix the problem, in max8997_pmic_probe, ramp_delay initialization
code is moved before calls to regulator_register.
Cc: Liam Girdwood <lrg@ti.com>
Cc: Mark Brown <broonie@opensource.wolfsonmicro.com>
Cc: MyungJoo Ham <myungjoo.ham@samsung.com>
Cc: Kyungmin Park <kyungmin.park@samsung.com>
Cc: Samuel Ortiz <sameo@linux.intel.com>
Signed-off-by: Tushar Behera <tushar.behera@linaro.org>
Acked-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Acked-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Liam Girdwood <lrg@slimlogic.co.uk>
evergreen+ asics have 2-6 crtcs. Don't access crtc registers
for crtc regs that don't exist as they have very high latency
and may cause problems on some asics. The previous code missed
a few cases and was not fine grained enough (missed the 4 crtc
case for example).
Fixes:
https://bugs.freedesktop.org/show_bug.cgi?id=38800
v2: fix typo noticed by Chris Bandy <cbandy@jbandy.com>
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Reviewed-by: Michel Dänzer <michel@daenzer.net>
Tested-by: Simon Farnsworth <simon.farnsworth@onelan.co.uk>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Trigger user ABORT if application closes a socket which has data
queued on the socket receive queue or chunks waiting on the
reassembly or ordering queue as this would imply data being lost
which defeats the point of a graceful shutdown.
This behavior is already practiced in TCP.
We do not check the input queue because that would mean to parse
all chunks on it to look for unacknowledged data which seems too
much of an effort. Control chunks or duplicated chunks may also
be in the input queue and should not be stopping a graceful
shutdown.
Signed-off-by: Thomas Graf <tgraf@infradead.org>
Acked-by: Vlad Yasevich <vladislav.yasevich@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Some workloads need some headroom (NET_SKB_PAD) to avoid expensive
reallocations.
Using netdev_alloc_skb_ip_align() instead of bare skb_alloc() brings the
NET_IP_ALIGN and the NET_SKB_PAD headroom.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Rasesh Mody <rmody@brocade.com>
CC: Debashis Dutt <ddutt@brocade.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The macro FILL_RX_POOLS_IN_BH is never been used, in order to avoid
the compiler reports error because of the usage of function INIT_WORK,
we just delete the marco.
Cc: Chas Williams <chas@cmf.nrl.navy.mil>
Cc: linux-atm-general@lists.sourceforge.net
Signed-off-by: Wang Shaoyan <wangshaoyan.pt@taobao.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The third parameter of module_param is supposed to represent sysfs
file permissions. A value of "1" leads to the following:
$ ls -l /sys/module/natsemi/parameters/
total 0
---------x 1 root root 4096 Jul 8 09:46 dspcfg_workaround
I am changing it to "0" to align with the other module parameters in
this driver.
Signed-off-by: Jean Delvare <jdelvare@suse.de>
Cc: Tim Hockin <thockin@hockin.org>
Cc: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is no need to check for the address being a multicast address in
the netdev_for_each_mc_addr loop, so remove it. This patch covers all
remaining network drivers still containing such a check.
Cc: Joe Perches <joe@perches.com>
Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
We need to release "dcb_lock" which we took on the previous line.
Signed-off-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
* 'omap-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap-2.6:
omap: drop __initdata tags from static struct platform_device declarations
* 'drm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6:
drm/kms: allow drm_mode_group with no objects
drm/radeon/kms: free ib pool on module unloading
drm/radeon/kms: fix typo in evergreen disp int status register
drm/radeon/kms: fix typo in IH_CNTL swap bitfield
Upon "ip xfrm state update ..", xfrm_add_sa() takes an extra reference on
the user-supplied SA and forgets to drop the reference when
xfrm_state_update() returns 0. This leads to a memory leak as the
parameter SA is never freed. This change attempts to fix the leak by
calling __xfrm_state_put() when xfrm_state_update() updates a valid SA
(err = 0). The parameter SA is added to the gc list when the final
reference is dropped by xfrm_add_sa() upon completion.
Signed-off-by: Tushar Gohad <tgohad@mvista.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Change references to SysKonnect in Kconfig to Marvell since
SysKonnect was acquired by Marvell back in 2002.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since new hardware chip support was added bump version.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is a backport from the vendor driver of support for the newer Optima
(Prime and 2) chipsets. It also includes some setup changes for the
current Optima chip as well. The code and comments intentionally
mirror the vendor sk98lin driver to allow for easier maintenance.
Although this adds support for new chip id's, these chip id's are not
used by any of the current PCI device id's listed in the driver.
The patch is just to get initial infrastructure in place to handle them
when they come.
I don't have access to any of this hardware to actually test it yet.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is another fix picked out of the vendor driver. The IPG value
in the serial mode register is supposed to be programmed differently
at lower speeds.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Found when reviewing the vendor driver. Apparently some chip versions
require receive checksumming to be enabled in order for RSS to work.
Also, if fix_features has to change some settings; put in message
in log in similar manner to netdev_fix_features.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The wrong bit was masked when acking langwell gpio interrupts.
Reason for maskig the wrong bit was probably because__ffs() and ffs() functions
return bit indexes differently (0..31 vs 1..32)
This fixes langwell based devices from hanging when a gpio interrupt is
triggered and undoes the breakage which occurred in change set
732063b92b
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Signed-off-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
If mini2440_init() is in __init, mini2440_parse_features() should also
be in __init. Fixes:
(.text+0x9adc): Section mismatch in reference from the function mini2440_parse_features.clone.0() to the
(unknown reference) .init.data:(unknown)
The function mini2440_parse_features.clone.0() references the (unknown reference) __initdata (unknown).
Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
Cc: Michel Pollet <buserror@gmail.com>
Signed-off-by: Kukjin Kim <kgene.kim@samsung.com>
Commit bb072c3c (ARM / Samsung: Use struct syscore_ops for "core" power
management) turned s3c2410_dma_resume_chan() from int to void. So, drop
the actual return values, too. Fixes:
arch/arm/plat-s3c24xx/dma.c: In function 's3c2410_dma_resume_chan':
arch/arm/plat-s3c24xx/dma.c:1238:3: warning: 'return' with a value, in function returning void
arch/arm/plat-s3c24xx/dma.c:1250:2: warning: 'return' with a value, in function returning void
Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
Acked-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Kukjin Kim <kgene.kim@samsung.com>
Commit 8970ef47 (S3C24XX: Remove hardware specific registers from DMA
calls) removed the parameter dcon in s3c2410_dma_config() and calculates
it on its own. So the debug-output for the old parameter can go, too.
Fixes:
arch/arm/plat-s3c24xx/dma.c: In function 's3c2410_dma_config':
arch/arm/plat-s3c24xx/dma.c:1030:2: warning: 'dcon' is used uninitialized in this function
Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
Cc: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: Kukjin Kim <kgene.kim@samsung.com>
Since rpc_killall_tasks may modify the rpc_task's tk_action field
without any locking, we need to be careful when dereferencing it.
Reported-by: Ben Greear <greearb@candelatech.com>
Tested-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: stable@kernel.org
* 'for-30-rc5/all-i2c' of git://git.fluff.org/bjdooks/linux:
i2c-bfin-twi: abort transfer is MEM bit is reset unexpectedly
i2c-s3c2410: Remove useless break code
i2c-s3c2410: Fix typo 'i2s' -> 'i2c'
i2c: tegra: Assign unused slave address
According to the hardware documentation, GDRST is exactly the same as on
Sandybridge. So simply enable the existing code.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Keith Packard <keithp@keithp.com>
When initiating a graceful shutdown while having data chunks
on the retransmission queue with a peer which is in zero
window mode the shutdown is never completed because the
retransmission error count is reset periodically by the
following two rules:
- Do not timeout association while doing zero window probe.
- Reset overall error count when a heartbeat request has
been acknowledged.
The graceful shutdown will wait for all outstanding TSN to
be acknowledged before sending the SHUTDOWN request. This
never happens due to the peer's zero window not acknowledging
the continuously retransmitted data chunks. Although the
error counter is incremented for each failed retransmission,
the receiving of the SACK announcing the zero window clears
the error count again immediately. Also heartbeat requests
continue to be sent periodically. The peer acknowledges these
requests causing the error counter to be reset as well.
This patch changes behaviour to only reset the overall error
counter for the above rules while not in shutdown. After
reaching the maximum number of retransmission attempts, the
T5 shutdown guard timer is scheduled to give the receiver
some additional time to recover. The timer is stopped as soon
as the receiver acknowledges any data.
The issue can be easily reproduced by establishing a sctp
association over the loopback device, constantly queueing
data at the sender while not reading any at the receiver.
Wait for the window to reach zero, then initiate a shutdown
by killing both processes simultaneously. The association
will never be freed and the chunks on the retransmission
queue will be retransmitted indefinitely.
Signed-off-by: Thomas Graf <tgraf@infradead.org>
Acked-by: Vlad Yasevich <vladislav.yasevich@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On sinks with a DPCD rev of 1.1 or greater, we can send sink power
management commands to address 0x600 per section 5.1.5 of the
DisplayPort 1.1a spec.
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Keith Packard <keithp@keithp.com>
Signed-off-by: Keith Packard <keithp@keithp.com>
When checking link status during a hot plug event or detecting sink
presence, we need to retry 3 times per the spec (section 9.1 of the 1.1a
DisplayPort spec). Consolidate the retry code into a
native_aux_read_retry function for use by get_link_status and _detect.
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Keith Packard <keithp@keithp.com>
Signed-off-by: Keith Packard <keithp@keithp.com>
We currently use this when a hot plug event is received, only checking
the link status and re-training if we had previously configured a link.
However if we want to preserve the DP configuration across both hot plug
and DPMS events (which we do for userspace apps that don't respond to
hot plug uevents), we need to unconditionally check the link and try to
bring it up on hot plug.
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Keith Packard <keithp@keithp.com>
Signed-off-by: Keith Packard <keithp@keithp.com>
If ->detect is called too soon after a hot plug event, the sink may not
be ready yet. So try up to 3 times with 1ms sleeps in between tries to
get the data (spec dictates that receivers must be ready to respond within
1ms and that sources should try 3 times).
See section 9.1 of the 1.1a DisplayPort spec.
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Keith Packard <keithp@keithp.com>
Signed-off-by: Keith Packard <keithp@keithp.com>
When a hotplug event is received, we need to check the receiver cap bits
in case they've changed (as they might with a hub or chain config).
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Keith Packard <keithp@keithp.com>
Signed-off-by: Keith Packard <keithp@keithp.com>
