When the PMU is enabled it is valid to have unhandled nmis, two
events could trigger 'simultaneously' raising two back-to-back
NMIs. If the first NMI handles both, the latter will be empty
and daze the CPU.
The solution to avoid an 'unknown nmi' massage in this case was
simply to stop the nmi handler chain when the PMU is enabled by
stating the nmi was handled. This has the drawback that a) we
can not detect unknown nmis anymore, and b) subsequent nmi
handlers are not called.
This patch addresses this. Now, we check this unknown NMI if it
could be a PMU back-to-back NMI. Otherwise we pass it and let
the kernel handle the unknown nmi.
This is a debug log:
cpu #6, nmi #32333, skip_nmi #32330, handled = 1, time = 1934364430
cpu #6, nmi #32334, skip_nmi #32330, handled = 1, time = 1934704616
cpu #6, nmi #32335, skip_nmi #32336, handled = 2, time = 1936032320
cpu #6, nmi #32336, skip_nmi #32336, handled = 0, time = 1936034139
cpu #6, nmi #32337, skip_nmi #32336, handled = 1, time = 1936120100
cpu #6, nmi #32338, skip_nmi #32336, handled = 1, time = 1936404607
cpu #6, nmi #32339, skip_nmi #32336, handled = 1, time = 1937983416
cpu #6, nmi #32340, skip_nmi #32341, handled = 2, time = 1938201032
cpu #6, nmi #32341, skip_nmi #32341, handled = 0, time = 1938202830
cpu #6, nmi #32342, skip_nmi #32341, handled = 1, time = 1938443743
cpu #6, nmi #32343, skip_nmi #32341, handled = 1, time = 1939956552
cpu #6, nmi #32344, skip_nmi #32341, handled = 1, time = 1940073224
cpu #6, nmi #32345, skip_nmi #32341, handled = 1, time = 1940485677
cpu #6, nmi #32346, skip_nmi #32347, handled = 2, time = 1941947772
cpu #6, nmi #32347, skip_nmi #32347, handled = 1, time = 1941949818
cpu #6, nmi #32348, skip_nmi #32347, handled = 0, time = 1941951591
Uhhuh. NMI received for unknown reason 00 on CPU 6.
Do you have a strange power saving mode enabled?
Dazed and confused, but trying to continue
Deltas:
nmi #32334 340186
nmi #32335 1327704
nmi #32336 1819 <<<< back-to-back nmi [1]
nmi #32337 85961
nmi #32338 284507
nmi #32339 1578809
nmi #32340 217616
nmi #32341 1798 <<<< back-to-back nmi [2]
nmi #32342 240913
nmi #32343 1512809
nmi #32344 116672
nmi #32345 412453
nmi #32346 1462095 <<<< 1st nmi (standard) handling 2 counters
nmi #32347 2046 <<<< 2nd nmi (back-to-back) handling one
counter nmi #32348 1773 <<<< 3rd nmi (back-to-back)
handling no counter! [3]
For back-to-back nmi detection there are the following rules:
The PMU nmi handler was handling more than one counter and no
counter was handled in the subsequent nmi (see [1] and [2]
above).
There is another case if there are two subsequent back-to-back
nmis [3]. The 2nd is detected as back-to-back because the first
handled more than one counter. If the second handles one counter
and the 3rd handles nothing, we drop the 3rd nmi because it
could be a back-to-back nmi.
Signed-off-by: Robert Richter <robert.richter@amd.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
[ renamed nmi variable to pmu_nmi to avoid clash with .nmi in entry.S ]
Signed-off-by: Don Zickus <dzickus@redhat.com>
Cc: peterz@infradead.org
Cc: gorcunov@gmail.com
Cc: fweisbec@gmail.com
Cc: ying.huang@intel.com
Cc: ming.m.lin@intel.com
Cc: eranian@google.com
LKML-Reference: <1283454469-1909-3-git-send-email-dzickus@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
During testing of a patch to stop having the perf subsytem
swallow nmis, it was uncovered that Nehalem boxes were randomly
getting unknown nmis when using the perf tool.
Moving the ack'ing of the PMI closer to when we get the status
allows the hardware to properly re-set the PMU bit signaling
another PMI was triggered during the processing of the first
PMI. This allows the new logic for dealing with the
shortcomings of multiple PMIs to handle the extra NMI by
'eat'ing it later.
Now one can wonder why are we getting a second PMI when we
disable all the PMUs in the begining of the NMI handler to
prevent such a case, for that I do not know. But I know the fix
below helps deal with this quirk.
Tested on multiple Nehalems where the problem was occuring.
With the patch, the code now loops a second time to handle the
second PMI (whereas before it was not).
Signed-off-by: Don Zickus <dzickus@redhat.com>
Cc: peterz@infradead.org
Cc: robert.richter@amd.com
Cc: gorcunov@gmail.com
Cc: fweisbec@gmail.com
Cc: ying.huang@intel.com
Cc: ming.m.lin@intel.com
Cc: eranian@google.com
LKML-Reference: <1283454469-1909-2-git-send-email-dzickus@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'nouveau/for-airlied' of /ssd/git/drm-nouveau-next:
drm/nv50: initialize ramht_refs list for faked 0 channel
drm/nouveau: Don't take struct_mutex around the pushbuf IOCTL.
drm/nouveau: Take fence spinlock before reading the last sequence.
If we attempt to preallocate more than 2^32 blocks of space in a
single syscall, the transaction block reservation will overflow
leading to a hangs in the superblock block accounting code. This
is trivially reproduced with xfs_io. Fix the problem by capping the
allocation reservation to the maximum number of blocks a single
xfs_bmapi() call can allocate (2^21 blocks).
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
We need it for PFIFO_INTR_CACHE_ERROR interrupt handling,
because nouveau_fifo_swmthd looks for matching gpuobj in
ramht_refs list.
It fixes kernel panic in nouveau_gpuobj_ref_find.
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
We don't need it and it can lead to lock order inversions with respect
to drm_global_mutex, potentially causing dead locks.
Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
It fixes a race between the TTM delayed work queue and the GEM IOCTLs
(fdo bug 29583) uncovered by the BKL removal.
Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
The max depth supported by T3 is 64K entries. This fixes a bug
introduced in commit 9918b28d ("RDMA/cxgb3: Increase the max CQ
depth") that causes stalls and possibly crashes in large MPI clusters.
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Cc: <stable@kernel.org>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
This patch fixes a lockdep warning:
[ 516.287584] =========================================================
[ 516.288386] [ INFO: possible irq lock inversion dependency detected ]
[ 516.288386] 2.6.35b #7
[ 516.288386] ---------------------------------------------------------
[ 516.288386] swapper/0 just changed the state of lock:
[ 516.288386] (&qdisc_tx_lock){+.-...}, at: [<c12eacda>] est_timer+0x62/0x1b4
[ 516.288386] but this lock took another, SOFTIRQ-unsafe lock in the past:
[ 516.288386] (est_tree_lock){+.+...}
[ 516.288386]
[ 516.288386] and interrupts could create inverse lock ordering between them.
...
So, est_tree_lock needs BH protection because it's taken by
qdisc_tx_lock, which is used both in BH and process contexts.
(Full warning with this patch at netdev, 02 Sep 2010.)
Fixes commit: ae638c47dc
("pkt_sched: gen_estimator: add a new lock")
Signed-off-by: Jarek Poplawski <jarkao2@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix Passive FTP problem in ip_vs_ftp:
- Do not oops in nf_nat_set_seq_adjust (adjust_tcp_sequence) when
iptable_nat module is not loaded
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
This reverts commit de6be6c1f7.
After some discussion with Jarek Poplawski and Eric Dumazet, we've
decided that this change is incorrect.
Signed-off-by: David S. Miller <davem@davemloft.net>
The validate_event function in the ARM perf events backend has the
following problems:
1.) Events that are disabled count towards the cost.
2.) Events associated with other PMUs [for example, software events or
breakpoints] do not count towards the cost, but do fail validation,
causing the group to fail.
This patch changes validate_event so that it ignores events in the
PERF_EVENT_STATE_OFF state or that are scheduled for other PMUs.
Reported-by: Pawel Moll <pawel.moll@arm.com>
Acked-by: Jamie Iles <jamie.iles@picochip.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Currently on-disk structure is able to keep only 16bit project quota
id, so disallow 32bit ones. This fixes a problem where parts of
kernel structures holding project quota id are 32bit while parts
(on-disk) are 16bit variables which causes project quota member
files to be inaccessible for some operations (like mv/rm).
Signed-off-by: Arkadiusz Mi?kiewicz <arekm@maven.pl>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alex Elder <aelder@sgi.com>
CPU_32v6K is selected by CPU_V7 but it only depends on CPU_V6.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
When doing large parallel file creates on a 16p machines, large amounts of
time is being spent in _xfs_buf_find(). A system wide profile with perf top
shows this:
1134740.00 19.3% _xfs_buf_find
733142.00 12.5% __ticket_spin_lock
The problem is that the hash contains 45,000 buffers, and the hash table width
is only 256 buffers. That means we've got around 200 buffers per chain, and
searching it is quite expensive. The hash table size needs to increase.
Secondly, every time we do a lookup, we promote the buffer we find to the head
of the hash chain. This is causing cachelines to be dirtied and causes
invalidation of cachelines across all CPUs that may have walked the hash chain
recently. hence every walk of the hash chain is effectively a cold cache walk.
Remove the promotion to avoid this invalidation.
The results are:
1045043.00 21.2% __ticket_spin_lock
326184.00 6.6% _xfs_buf_find
A 70% drop in the CPU usage when looking up buffers. Unfortunately that does
not result in an increase in performance underthis workload as contention on
the inode_lock soaks up most of the reduction in CPU usage.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
The 7th entry in a lot of evergreen i2c gpio tables is partially
zeroed. Fix the entry.
Should fix the missing ddc entry in:
https://bugs.freedesktop.org/show_bug.cgi?id=29255
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Packets entering GRO might have different headrooms, even for a given
flow (because of implementation details in drivers, like copybreak).
We cant force drivers to deliver packets with a fixed headroom.
1) fix skb_segment()
skb_segment() makes the false assumption headrooms of fragments are same
than the head. When CHECKSUM_PARTIAL is used, this can give csum_start
errors, and crash later in skb_copy_and_csum_dev()
2) allocate a minimal skb for head of frag_list
skb_gro_receive() uses netdev_alloc_skb(headroom + skb_gro_offset(p)) to
allocate a fresh skb. This adds NET_SKB_PAD to a padding already
provided by netdevice, depending on various things, like copybreak.
Use alloc_skb() to allocate an exact padding, to reduce cache line
needs:
NET_SKB_PAD + NET_IP_ALIGN
bugzilla : https://bugzilla.kernel.org/show_bug.cgi?id=16626
Many thanks to Plamen Petrov, testing many debugging patches !
With help of Jarek Poplawski.
Reported-by: Plamen Petrov <pvp-lsts@fs.uni-ruse.bg>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Jarek Poplawski <jarkao2@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In a similar vain to commit 17762060c2
("bridge: Clear IPCB before possible entry into IP stack")
Any time we call into the IP stack we have to make sure the state
there is as expected by the ipv4 code.
With help from Eric Dumazet and Herbert Xu.
Reported-by: Bandan Das <bandan.das@stratus.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The tv parameter was added to disable the tv-out connector,
however, it caused a crash if it was set to 0 due to
drm_connector_init not getting called. If tv=0, don't
attempt to add the connector.
Might fix:
https://bugzilla.kernel.org/show_bug.cgi?id=17241
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
There has been periodic evidence that LVDS, on at least some
panels, prefers the dividers selected by the legacy pll algo.
This patch forces the use of the legacy pll algo on RV515
LVDS panels. The old behavior (new pll algo) can be selected
by setting the new_pll module parameter to 1.
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Cc: stable@kernel.org
Signed-off-by: Dave Airlie <airlied@redhat.com>
This code was originally for forcing some clocks on certain asics.
However, this code was later moved to asic specific functions
for all of the affected asics. The only users of the original
code at this point were r600, rv770, and evergreen and the code
was not relevant for those asics. So, remove it.
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
vortex_ioctl() was grabbing vortex_private::lock around its call to
generic_mii_ioctl(). This is no longer necessary since there are more
specific locks which the mdio_{read,write}() functions will obtain.
Worse, those functions do not save and restore IRQ flags when locking
the MII state, so interrupts will be enabled when generic_mii_ioctl()
returns.
Since there is currently no need for any function to call
mdio_{read,write}() while holding another spinlock, do not change them
to save and restore IRQ flags but remove the specification of ordering
between vortex_private::lock and vortex_private::mii_lock.
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
The dlpar code can cause a deadlock to occur when making the RTAS
configure-connector call. This occurs because we make kmalloc calls,
which can block, while parsing the rtas_data_buf and holding the
rtas_data_buf_lock. This an cause issues if someone else attempts
to grab the rtas_data_bug_lock.
This patch alleviates this issue by copying the contents of the rtas_data_buf
to a local buffer before parsing. This allows us to only hold the
rtas_data_buf_lock around the RTAS configure-connector calls.
Signed-off-by: Nathan Fontenot <nfont@austin.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
fixes the warning:
.config:369:warning: symbol value '' invalid for ZRELADDR
and the prompt for ZRELADDR on make
Signed-off-by: Erik Gilling <konkers@android.com>
There's something very important I forgot to tell you.
What?
Don't cross the GRO streams.
Why?
It would be bad.
I'm fuzzy on the whole good/bad thing. What do you mean, "bad"?
Try to imagine all the Internet as you know it stopping instantaneously
and every bit in every packet swapping at the speed of light.
Total packet reordering.
Right. That's bad. Okay. All right. Important safety tip. Thanks, Hubert
The simplest way to stop this is just avoid doing GRO on the second port.
Very few Marvell boards support two ports per ring, and GRO is just
an optimization.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Attached is a small patch to remove a warning ("warning: ISO C90 forbids
mixed declarations and code" with gcc 4.3.2).
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes init_vf() function, so on each new backlog period parent's
cl_cfmin is properly updated (including further propgation towards the root),
even if the activated leaf has no upperlimit curve defined.
Signed-off-by: Michal Soltys <soltys@ziu.info>
Signed-off-by: David S. Miller <davem@davemloft.net>
mdiobus resources must be released on exit
Signed-off-by: Denis Kirjanov <dkirjanov@kernel.org>
Acked-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While reviewing commit 1c40be12f7, I
audited other users of tc_action_ops->dump for information leaks.
That commit covered almost all of them but act_police still had a leak.
opt.limit and opt.capab aren't zeroed out before the structure is
passed out.
This patch uses the C99 initializers to zero everything unused out.
Signed-off-by: Jeff Mahoney <jeffm@suse.com>
Acked-by: Jeff Mahoney <jeffm@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Its currently illegal to call kthread_stop(NULL)
Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change just add the IBM eHEA 10Gb network drivers as supported.
Signed-off-by: Breno Leitao <leitao@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The use of the return value of init_sysfs() with commit
10f0412 oprofile, x86: fix init_sysfs error handling
discovered the following build error for !CONFIG_PM:
.../linux/arch/x86/oprofile/nmi_int.c: In function ‘op_nmi_init’:
.../linux/arch/x86/oprofile/nmi_int.c:784: error: expected expression before ‘do’
make[2]: *** [arch/x86/oprofile/nmi_int.o] Error 1
make[1]: *** [arch/x86/oprofile] Error 2
This patch fixes this.
Reported-by: Ingo Molnar <mingo@elte.hu>
Cc: stable@kernel.org
Signed-off-by: Robert Richter <robert.richter@amd.com>
When compiling alpha generic build get errors such as:
arch/alpha/kernel/err_marvel.c: In function ‘marvel_print_err_cyc’:
arch/alpha/kernel/err_marvel.c:119: error: format ‘%ld’ expects type ‘long int’, but argument 6 has type ‘u64’
Replaced a number of %ld format specifiers with %lld since u64
is unsigned long long.
Signed-off-by: Michael Cree <mcree@orcon.net.nz>
Signed-off-by: Matt Turner <mattst88@gmail.com>
The 2.6.36-rc kernel added three new system calls:
fanotify_init, fanotify_mark, and prlimit64. This patch
wires them up on ARM.
The only non-trivial issue here is the u64 argument to
sys_fanotify_mark(), but it is the 3rd argument and thus
passed in r2/r3 in both kernel and user space, so it causes
no problems.
Tested with a 2.6.36-rc2 EABI kernel on an ixp4xx machine.
Tested-by: Anand Gadiyar <gadiyar@ti.com>
Signed-off-by: Mikael Pettersson <mikpe@it.uu.se>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
This is purely a cosmetic change to the ARM perf backend because the current
comments about the relationship between NMIs, interrupt context and
perf_event_do_pending are misleading.
This patch updates the comments so that they reflect what the code
actually does (which is in line with other architectures).
Acked-by: Jamie Iles <jamie.iles@picochip.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
During my rewrite, the semantics of touch_nmi_watchdog and
touch_softlockup_watchdog changed enough to break some drivers
(mostly over preemptable regions).
These are cases where long delays on one CPU (due to
print_delay for example) can cause long delays on other
CPUs - so we must 'touch' the nmi_watchdog flag of those
other CPUs as well.
This change brings those touch_*_watchdog() functions back in line
with to how they used to work.
Signed-off-by: Don Zickus <dzickus@redhat.com>
Acked-by: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: peterz@infradead.org
Cc: fweisbec@gmail.com
LKML-Reference: <1283310009-22168-2-git-send-email-dzickus@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Updates the Alpha perf_event code to match the changes
recently made to the core perf_event code in commit
e78505958c.
Signed-off-by: Michael Cree <mcree@orcon.net.nz>
Signed-off-by: Matt Turner <mattst88@gmail.com>
This patch fixes the failure to compile Alpha Generic because of
previously overlooked calls to ns87312_enable_ide(). The function has
been replaced by newer SuperIO code.
Tested-by: Michael Cree <mcree@orcon.net.nz>
Signed-off-by: Morten H. Larsen <m-larsen@post6.tele.dk>
Signed-off-by: Matt Turner <mattst88@gmail.com>
Let's use the standard L1_CACHE_ALIGN macro instead.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: Matt Turner <mattst88@gmail.com>
We need to call platform_device_unregister(i8042_platform_device)
before calling platform_driver_unregister() because i8042_remove()
resets i8042_platform_device to NULL. This leaves the platform device
instance behind and prevents driver reload.
Fixes https://bugzilla.kernel.org/show_bug.cgi?id=16613
Reported-by: Seryodkin Victor <vvscore@gmail.com>
Cc: stable@kernel.org
Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
By visual inspection, the reported touch_major and touch_minor axes
are a factor of two too small. Presumably the device actually reports
the semi-major and semi-minor axes. Corrected with this patch.
Signed-off-by: Henrik Rydberg <rydberg@euromail.se>
Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
Robert Richter