SCSI marks internal commands with REQ_PREEMPT and push it at the front
of the request queue using blk_execute_rq(). When entering suspended
or frozen state, SCSI devices are quiesced using
scsi_device_quiesce(). In quiesced state, only REQ_PREEMPT requests
are processed. This is how SCSI blocks other requests out while
suspending and resuming. As all internal commands are pushed at the
front of the queue, this usually works.
Unfortunately, this interacts badly with ordered requeueing. To
preserve request order on requeueing (due to busy device, active EH or
other failures), requests are sorted according to ordered sequence on
requeue if IO barrier is in progress.
The following sequence deadlocks.
1. IO barrier sequence issues.
2. Suspend requested. Queue is quiesced with part or all of IO
barrier sequence at the front.
3. During suspending or resuming, SCSI issues internal command which
gets deferred and requeued for some reason. As the command is
issued after the IO barrier in #1, ordered requeueing code puts the
request after IO barrier sequence.
4. The device is ready to process requests again but still is in
quiesced state and the first request of the queue isn't
REQ_PREEMPT, so command processing is deadlocked -
suspending/resuming waits for the issued request to complete while
the request can't be processed till device is put back into
running state by resuming.
This can be fixed by always putting !fs requests at the front when
requeueing.
The following thread reports this deadlock.
http://thread.gmane.org/gmane.linux.kernel/537473
Signed-off-by: Tejun Heo <htejun@gmail.com>
Acked-by: David Greaves <david@dgreaves.com>
Acked-by: Jeff Garzik <jeff@garzik.org>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch fixes a NULL dereference spotted by the Coverity checker.
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 6f74651ae6 is found guilty
of breaking DSACK counting, which should be done only for the
SACK block reported by the DSACK instead of every SACK block
that is received along with DSACK information.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 164891aadf broke RTT
sampling of congestion control modules. Inaccurate timestamps
could be fed to them without providing any way for them to
identify such cases. Previously RTT sampler was called only if
FLAG_RETRANS_DATA_ACKED was not set filtering inaccurate
timestamps nicely. In addition, the new behavior could give an
invalid timestamp (zero) to RTT sampler if only skbs with
TCPCB_RETRANS were ACKed. This solves both problems.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
We only ever set do_wakeup to non-zero if the pipe has an inode
backing, so it's pointless to check outside the pipe->inode
check.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
If the destination pipe is full and we already transferred
data, we break out instead of waiting for more pipe room.
The exit logic looks at spd->nr_pages to see if we moved
everything inside the spd container, but we decrement that
variable in the loop to decide when spd has emptied.
Instead we want to compare to the original page count in
the spd, so cache that in a local variable.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
As we have potentially dirtied more than 1 page, we should indicate as
such to the dirty page balancing. So call
balance_dirty_pages_ratelimited_nr() and pass in the approximate number
of pages we dirtied.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
The lazy fpu changes did not take into account that some vmexit handlers
can sleep. Move loading the guest state into the inner loop so that it
can be reloaded if necessary, and move loading the host state into
vmx_vcpu_put() so it can be performed whenever we relinquish the vcpu.
Signed-off-by: Avi Kivity <avi@qumranet.com>
* 'drm-patches' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6:
drm: fix radeon setparam on 32/64 bit systems.
drm/i915: Add support for the G33, Q33, and Q35 chipsets.
i915: add new pciids for 945GME, 965GME/GLE
* master.kernel.org:/pub/scm/linux/kernel/git/kyle/parisc-2.6: (30 commits)
[PARISC] remove global_ack_eiem
[PARISC] Fix kernel panic in check_ivt
[PARISC] Fix bug when syscall nr is __NR_Linux_syscalls
[PARISC] be more defensive in process.c::get_wchan
[PARISC] fix "reduce size of task_struct on 64-bit machines" fallout
[PARISC] fix null ptr deref in unwind.c
[PARISC] fix trivial spelling nit in asm/linkage.h
[PARISC] remove remnants of parisc-specific softirq code
[PARISC] fix section mismatch in smp.c
[PARISC] fix "ENTRY" macro redefinition
[PARISC] Wire up utimensat/signalfd/timerfd/eventfd syscalls
[PARISC] fix section mismatch in superio serial drivers
[PARISC] fix section mismatch in parisc eisa driver
[PARISC] fix section mismatches in arch/parisc/kernel
[PARISC] fix section mismatch in ccio-dma
[PARISC] fix section mismatch in parisc STI video drivers
[PARISC] fix section mismatch in parport_gsc
[PARISC] fix lasi_82596 build
[PARISC] Build fixes for power.c
[PARISC] kobject is embedded in subsys, not kset
...
* 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/sparc-2.6:
[SPARC64]: Fix args to sun4v_ldc_revoke().
[SPARC64]: Really fix parport.
[SPARC64]: Fix IO/MEM space sizing for PCI.
[SPARC64]: Wire up cookie based sun4v interrupt registry.
This patch trys to fix device probe in two cases. First we should
correctly detect device if integrated graphics device is not enabled
or exists, like an add-in card is plugged. Second on some type of intel
GMCH, it might have multiple graphic chip models, like 945GME case, so
we should be sure the detect works through the whole table.
Signed-off-by: Wang Zhenyu <zhenyu.z.wang@intel.com>
Signed-off-by: Dave Jones <davej@redhat.com>
* 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6:
[IPV6] addrconf: Fix IPv6 on tuntap tunnels
[TCP]: Add missing break to TCP option parsing code
[SCTP] Don't disable PMTU discovery when mtu is small
[SCTP] Flag a pmtu change request
[SCTP] Update pmtu handling to be similar to tcp
[SCTP] Fix leak in sctp_getsockopt_local_addrs when copy_to_user fails
[SCTP]: Allow unspecified port in sctp_bindx()
[SCTP]: Correctly set daddr for IPv6 sockets during peeloff
[TCP]: Set initial_ssthresh default to zero in Cubic and BIC.
[TCP]: Fix left_out setting during FRTO
[TCP]: Disable TSO if MD5SIG is enabled.
[PPP_MPPE]: Fix "osize too small" check.
[PATCH] mac80211: Don't stop tx queue on master device while scanning.
[PATCH] mac80211: fix debugfs tx power reduction output
[PATCH] cfg80211: fix signed macaddress in sysfs
[IrDA]: f-timer reloading when sending rejected frames.
[IrDA]: Fix Rx/Tx path race.
The recent patch that added ipv6_hwtype is broken on tuntap tunnels.
Indeed, it's broken on any device that does not pass the ipv6_hwtype
test.
The reason is that the original test only applies to autoconfiguration,
not IPv6 support. IPv6 support is allowed on any device. In fact,
even with the ipv6_hwtype patch applied you can still add IPv6 addresses
to any interface that doesn't pass thw ipv6_hwtype test provided that
they have a sufficiently large MTU. This is a serious problem because
come deregistration time these devices won't be cleaned up properly.
I've gone back and looked at the rationale for the patch. It appears
that the real problem is that we were creating IPv6 devices even if the
MTU was too small. So here's a patch which fixes that and reverts the
ipv6_hwtype stuff.
Thanks to Kanru Chen for reporting this issue.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Support for performance counter overflow interrupt that is on a separate
interrupt from the timer.
Signed-off-by: Chris Dearman <chris@mips.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
And an attempt to tidy up the core/controller differences.
Signed-off-by: Chris Dearman <chris@mips.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
This allows SLUB debugging to be used without fear of messing up DMA
transfers. SPI is one example that easily breaks without this patch.
Signed-off-by: Haavard Skinnemoen <hskinnemoen@atmel.com>
In the latest incarnation of the ltv350qv driver the call to
spi_setup() has been removed. So we need to initialize things more
carefully in the board info struct.
Signed-off-by: Haavard Skinnemoen <hskinnemoen@atmel.com>
Tejun Heo
Adrian Bunk
Ilpo Järvinen
Linus Torvalds
Jens Axboe
Avi Kivity
Wang Zhenyu
David S. Miller
Herbert Xu
Chris Dearman
Haavard Skinnemoen