Pull RCU updates from Paul E. McKenney:
* Documentation updates, including fixes to the design-level
requirements documentation and a fixed version of the design-level
data-structure documentation. These fixes include removing
cartoons and getting rid of the html/htmlx duplication.
* Further improvements to the new-age expedited grace periods.
* Miscellaneous fixes.
* Torture-test changes, including a new rcuperf module for measuring
RCU grace-period performance and scalability, which is useful for
the expedited-grace-period changes.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Nothing outside of the tracing directory calls filter_check_discard() or
check_filter_check_discard(). They should not be called by modules. Move
their prototypes into the local tracing header and remove their
EXPORT_SYMBOL() macros.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
The default remains 127, which is good for most cases, and not even hit
most of the time, but then for some cases, as reported by Brendan, 1024+
deep frames are appearing on the radar for things like groovy, ruby.
And in some workloads putting a _lower_ cap on this may make sense. One
that is per event still needs to be put in place tho.
The new file is:
# cat /proc/sys/kernel/perf_event_max_stack
127
Chaging it:
# echo 256 > /proc/sys/kernel/perf_event_max_stack
# cat /proc/sys/kernel/perf_event_max_stack
256
But as soon as there is some event using callchains we get:
# echo 512 > /proc/sys/kernel/perf_event_max_stack
-bash: echo: write error: Device or resource busy
#
Because we only allocate the callchain percpu data structures when there
is a user, which allows for changing the max easily, its just a matter
of having no callchain users at that point.
Reported-and-Tested-by: Brendan Gregg <brendan.d.gregg@gmail.com>
Reviewed-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Zefan Li <lizefan@huawei.com>
Link: http://lkml.kernel.org/r/20160426002928.GB16708@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The functions event_trigger_unlock_commit() and
event_trigger_unlock_commit_regs() are no longer used outside the tracing
system. Move them out of the generic headers and into the local one.
Along with __event_trigger_test_discard() that is only used by them.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
In the ppc64 big endian ABI, function symbols point to function
descriptors. The symbols which point to the function entry points
have a dot in front of the function name. Consequently, when the
ftrace filter mechanism searches for the symbol corresponding to
an entry point address, it gets the dot symbol.
As a result, ftrace filter users have to be aware of this ABI detail on
ppc64 and prepend a dot to the function name when setting the filter.
The perf probe command insulates the user from this by ignoring the dot
in front of the symbol name when matching function names to symbols,
but the sysfs interface does not. This patch makes the ftrace filter
mechanism do the same when searching symbols.
Fixes the following failure in ftracetest's kprobe_ftrace.tc:
.../kprobe_ftrace.tc: line 9: echo: write error: Invalid argument
That failure is on this line of kprobe_ftrace.tc:
echo _do_fork > set_ftrace_filter
This is because there's no _do_fork entry in the functions list:
# cat available_filter_functions | grep _do_fork
._do_fork
This change introduces no regressions on the perf and ftracetest
testsuite results.
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Pull networking fixes from David Miller:
1) Handle v4/v6 mixed sockets properly in soreuseport, from Craig
Gallak.
2) Bug fixes for the new macsec facility (missing kmalloc NULL checks,
missing locking around netdev list traversal, etc.) from Sabrina
Dubroca.
3) Fix handling of host routes on ifdown in ipv6, from David Ahern.
4) Fix double-fdput in bpf verifier. From Jann Horn.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (31 commits)
bpf: fix double-fdput in replace_map_fd_with_map_ptr()
net: ipv6: Delete host routes on an ifdown
Revert "ipv6: Revert optional address flusing on ifdown."
net/mlx4_en: fix spurious timestamping callbacks
net: dummy: remove note about being Y by default
cxgbi: fix uninitialized flowi6
ipv6: Revert optional address flusing on ifdown.
ipv4/fib: don't warn when primary address is missing if in_dev is dead
net/mlx5: Add pci shutdown callback
net/mlx5_core: Remove static from local variable
net/mlx5e: Use vport MTU rather than physical port MTU
net/mlx5e: Fix minimum MTU
net/mlx5e: Device's mtu field is u16 and not int
net/mlx5_core: Add ConnectX-5 to list of supported devices
net/mlx5e: Fix MLX5E_100BASE_T define
net/mlx5_core: Fix soft lockup in steering error flow
qlcnic: Update version to 5.3.64
net: stmmac: socfpga: Remove re-registration of reset controller
macsec: fix netlink attribute validation
macsec: add missing macsec prefix in uapi
...
When bpf(BPF_PROG_LOAD, ...) was invoked with a BPF program whose bytecode
references a non-map file descriptor as a map file descriptor, the error
handling code called fdput() twice instead of once (in __bpf_map_get() and
in replace_map_fd_with_map_ptr()). If the file descriptor table of the
current task is shared, this causes f_count to be decremented too much,
allowing the struct file to be freed while it is still in use
(use-after-free). This can be exploited to gain root privileges by an
unprivileged user.
This bug was introduced in
commit 0246e64d9a ("bpf: handle pseudo BPF_LD_IMM64 insn"), but is only
exploitable since
commit 1be7f75d16 ("bpf: enable non-root eBPF programs") because
previously, CAP_SYS_ADMIN was required to reach the vulnerable code.
(posted publicly according to request by maintainer)
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The tty field was missing from AUDIT_LOGIN events.
Refactor code to create a new function audit_get_tty(), using it to
replace the call in audit_log_task_info() and to add it to
audit_log_set_loginuid(). Lock and bump the kref to protect it, adding
audit_put_tty() alias to decrement it.
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
With the following code snippet:
...
char buf[64];
...
if (copy_from_user(&buf, ubuf, cnt))
...
Even though the value of "&buf" equals "buf", but there is no need
to get the address of the "buf" again. Use "buf" instead of "&buf".
Link: http://lkml.kernel.org/r/20160418152329.18b72bea@debian
Signed-off-by: Wang Xiaoqiang <wangxq10@lzu.edu.cn>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
The bug in a workqueue leads to a stalled IO request in MQ ctx->rq_list
with the following backtrace:
[ 601.347452] INFO: task kworker/u129:5:1636 blocked for more than 120 seconds.
[ 601.347574] Tainted: G O 4.4.5-1-storage+ #6
[ 601.347651] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 601.348142] kworker/u129:5 D ffff880803077988 0 1636 2 0x00000000
[ 601.348519] Workqueue: ibnbd_server_fileio_wq ibnbd_dev_file_submit_io_worker [ibnbd_server]
[ 601.348999] ffff880803077988 ffff88080466b900 ffff8808033f9c80 ffff880803078000
[ 601.349662] ffff880807c95000 7fffffffffffffff ffffffff815b0920 ffff880803077ad0
[ 601.350333] ffff8808030779a0 ffffffff815b01d5 0000000000000000 ffff880803077a38
[ 601.350965] Call Trace:
[ 601.351203] [<ffffffff815b0920>] ? bit_wait+0x60/0x60
[ 601.351444] [<ffffffff815b01d5>] schedule+0x35/0x80
[ 601.351709] [<ffffffff815b2dd2>] schedule_timeout+0x192/0x230
[ 601.351958] [<ffffffff812d43f7>] ? blk_flush_plug_list+0xc7/0x220
[ 601.352208] [<ffffffff810bd737>] ? ktime_get+0x37/0xa0
[ 601.352446] [<ffffffff815b0920>] ? bit_wait+0x60/0x60
[ 601.352688] [<ffffffff815af784>] io_schedule_timeout+0xa4/0x110
[ 601.352951] [<ffffffff815b3a4e>] ? _raw_spin_unlock_irqrestore+0xe/0x10
[ 601.353196] [<ffffffff815b093b>] bit_wait_io+0x1b/0x70
[ 601.353440] [<ffffffff815b056d>] __wait_on_bit+0x5d/0x90
[ 601.353689] [<ffffffff81127bd0>] wait_on_page_bit+0xc0/0xd0
[ 601.353958] [<ffffffff81096db0>] ? autoremove_wake_function+0x40/0x40
[ 601.354200] [<ffffffff81127cc4>] __filemap_fdatawait_range+0xe4/0x140
[ 601.354441] [<ffffffff81127d34>] filemap_fdatawait_range+0x14/0x30
[ 601.354688] [<ffffffff81129a9f>] filemap_write_and_wait_range+0x3f/0x70
[ 601.354932] [<ffffffff811ced3b>] blkdev_fsync+0x1b/0x50
[ 601.355193] [<ffffffff811c82d9>] vfs_fsync_range+0x49/0xa0
[ 601.355432] [<ffffffff811cf45a>] blkdev_write_iter+0xca/0x100
[ 601.355679] [<ffffffff81197b1a>] __vfs_write+0xaa/0xe0
[ 601.355925] [<ffffffff81198379>] vfs_write+0xa9/0x1a0
[ 601.356164] [<ffffffff811c59d8>] kernel_write+0x38/0x50
The underlying device is a null_blk, with default parameters:
queue_mode = MQ
submit_queues = 1
Verification that nullb0 has something inflight:
root@pserver8:~# cat /sys/block/nullb0/inflight
0 1
root@pserver8:~# find /sys/block/nullb0/mq/0/cpu* -name rq_list -print -exec cat {} \;
...
/sys/block/nullb0/mq/0/cpu2/rq_list
CTX pending:
ffff8838038e2400
...
During debug it became clear that stalled request is always inserted in
the rq_list from the following path:
save_stack_trace_tsk + 34
blk_mq_insert_requests + 231
blk_mq_flush_plug_list + 281
blk_flush_plug_list + 199
wait_on_page_bit + 192
__filemap_fdatawait_range + 228
filemap_fdatawait_range + 20
filemap_write_and_wait_range + 63
blkdev_fsync + 27
vfs_fsync_range + 73
blkdev_write_iter + 202
__vfs_write + 170
vfs_write + 169
kernel_write + 56
So blk_flush_plug_list() was called with from_schedule == true.
If from_schedule is true, that means that finally blk_mq_insert_requests()
offloads execution of __blk_mq_run_hw_queue() and uses kblockd workqueue,
i.e. it calls kblockd_schedule_delayed_work_on().
That means, that we race with another CPU, which is about to execute
__blk_mq_run_hw_queue() work.
Further debugging shows the following traces from different CPUs:
CPU#0 CPU#1
---------------------------------- -------------------------------
reqeust A inserted
STORE hctx->ctx_map[0] bit marked
kblockd_schedule...() returns 1
<schedule to kblockd workqueue>
request B inserted
STORE hctx->ctx_map[1] bit marked
kblockd_schedule...() returns 0
*** WORK PENDING bit is cleared ***
flush_busy_ctxs() is executed, but
bit 1, set by CPU#1, is not observed
As a result request B pended forever.
This behaviour can be explained by speculative LOAD of hctx->ctx_map on
CPU#0, which is reordered with clear of PENDING bit and executed _before_
actual STORE of bit 1 on CPU#1.
The proper fix is an explicit full barrier <mfence>, which guarantees
that clear of PENDING bit is to be executed before all possible
speculative LOADS or STORES inside actual work function.
Signed-off-by: Roman Pen <roman.penyaev@profitbricks.com>
Cc: Gioh Kim <gi-oh.kim@profitbricks.com>
Cc: Michael Wang <yun.wang@profitbricks.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Tejun Heo <tj@kernel.org>
In ext4, there is a race condition between changing inode journal mode
and ext4_writepages(). While ext4_writepages() is executed on a
non-journalled mode inode, the inode's journal mode could be enabled
by ioctl() and then, some pages dirtied after switching the journal
mode will be still exposed to ext4_writepages() in non-journaled mode.
To resolve this problem, we use fs-wide per-cpu rw semaphore by Jan
Kara's suggestion because we don't want to waste ext4_inode_info's
space for this extra rare case.
Signed-off-by: Daeho Jeong <daeho.jeong@samsung.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Jan Kara <jack@suse.cz>
As the event-fork option requires doing work when enabled and disabled, it
can not be passed down to created instances. The instance must clear this
flag when it is created, and must clear it when its removed.
As more options may be created with this need, a macro ZEROED_TRACE_FLAGS is
created that holds the flags that must not be inherited by the top level
instance, and must be cleared on removal of instances.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Since e93ad19d05 ("cpuset: make mm migration asynchronous"), cpuset
kicks off asynchronous NUMA node migration if necessary during task
migration and flushes it from cpuset_post_attach_flush() which is
called at the end of __cgroup_procs_write(). This is to avoid
performing migration with cgroup_threadgroup_rwsem write-locked which
can lead to deadlock through dependency on kworker creation.
memcg has a similar issue with charge moving, so let's convert it to
an official callback rather than the current one-off cpuset specific
function. This patch adds cgroup_subsys->post_attach callback and
makes cpuset register cpuset_post_attach_flush() as its ->post_attach.
The conversion is mostly one-to-one except that the new callback is
called under cgroup_mutex. This is to guarantee that no other
migration operations are started before ->post_attach callbacks are
finished. cgroup_mutex is one of the outermost mutex in the system
and has never been and shouldn't be a problem. We can add specialized
synchronization around __cgroup_procs_write() but I don't think
there's any noticeable benefit.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: <stable@vger.kernel.org> # 4.4+ prerequisite for the next patch
Goal of this patch is to use the new libnl API to align netlink attribute
when needed.
The layout of the netlink message will be a bit different after the patch,
because the padattr (TASKSTATS_TYPE_STATS) will be inside the nested
attribute instead of before it.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts were two cases of simple overlapping changes,
nothing serious.
In the UDP case, we need to add a hlist_add_tail_rcu()
to linux/rculist.h, because we've moved UDP socket handling
away from using nulls lists.
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull perf, cpu hotplug and timer fixes from Ingo Molnar:
"perf:
- A single tooling fix for a user-triggerable segfault.
CPU hotplug:
- Fix a CPU hotplug corner case regression, introduced by the recent
hotplug rework
timers:
- Fix a boot hang in the ARM based Tango SoC clocksource driver"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf intel-pt: Fix segfault tracing transactions
* 'smp-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
cpu/hotplug: Fix rollback during error-out in __cpu_disable()
* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
clocksource/drivers/tango-xtal: Fix boot hang due to incorrect test
Pull locking fixes from Ingo Molnar:
"Misc fixes:
pvqspinlocks:
- an instrumentation fix
futexes:
- preempt-count vs pagefault_disable decouple corner case fix
- futex requeue plist race window fix
- futex UNLOCK_PI transaction fix for a corner case"
* 'locking-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
asm-generic/futex: Re-enable preemption in futex_atomic_cmpxchg_inatomic()
futex: Acknowledge a new waiter in counter before plist
futex: Handle unlock_pi race gracefully
locking/pvqspinlock: Fix division by zero in qstat_read()
Pull irq fixes from Ingo Molnar:
"A core irq affinity masks related fix and a MIPS irqchip driver fix"
* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
irqchip/mips-gic: Don't overrun pcpu_masks array
genirq: Dont allow affinity mask to be updated on IPIs
I got a minus(very big) dl_b->total_bw during my deadline tests.
# grep dl /proc/sched_debug
dl_rq[0]:
.dl_nr_running : 0
.dl_bw->bw : 996147
.dl_bw->total_bw : -222297900
Something unusual must have happened.
After some digging, I finally noticed that when changing a deadline
task to normal(cfs), and changing it back to deadline immediately,
after it died, we will got the wrong dl_bw->total_bw.
The root cause is in dl_overflow(), it has:
if (new_bw == p->dl.dl_bw)
return 0;
1) When a deadline task is changed to !deadline task, it will start
dl timer in switched_from_dl(), and retain previous deadline parameter
till the timer expires.
2) If we change it back to deadline with the same bandwidth parameter
before the timer expires, as it keeps the old bandwidth although it
is not a deadline task. dl_overflow() simply returns success without
updating the right data, and got the wrong dl_bw->total_bw.
The solution is simple, if @p is not deadline, don't return.
Signed-off-by: Xunlei Pang <xlpang@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Juri Lelli <juri.lelli@arm.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1460636368-1993-1-git-send-email-xlpang@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Ticks can happen while the CPU is in dynticks-idle or dynticks-singletask
mode. In fact "nohz" or "dynticks" only mean that we exit the periodic
mode and we try to minimize the ticks as much as possible. The nohz
subsystem uses a confusing terminology with the internal state
"ts->tick_stopped" which is also available through its public interface
with tick_nohz_tick_stopped(). This is a misnomer as the tick is instead
reduced with the best effort rather than stopped. In the best case the
tick can indeed be actually stopped but there is no guarantee about that.
If a timer needs to fire one second later, a tick will fire while the
CPU is in nohz mode and this is a very common scenario.
Now this confusion happens to be a problem with CPU load updates:
cpu_load_update_active() doesn't handle nohz ticks correctly because it
assumes that ticks are completely stopped in nohz mode and that
cpu_load_update_active() can't be called in dynticks mode. When that
happens, the whole previous tickless load is ignored and the function
just records the load for the current tick, ignoring potentially long
idle periods behind.
In order to solve this, we could account the current load for the
previous nohz time but there is a risk that we account the load of a
task that got freshly enqueued for the whole nohz period.
So instead, lets record the dynticks load on nohz frame entry so we know
what to record in case of nohz ticks, then use this record to account
the tickless load on nohz ticks and nohz frame end.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Byungchul Park <byungchul.park@lge.com>
Cc: Chris Metcalf <cmetcalf@ezchip.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Luiz Capitulino <lcapitulino@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul E . McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1460555812-25375-3-git-send-email-fweisbec@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When asymmetric packing is set in the sched_domain and target CPU is
busy, update_sd_pick_busiest() may not select the busiest runqueue.
When target CPU is busy, find_busiest_group() will ignore checks for
asym packing and may continue to load balance using the currently
selected not-the-busiest runqueue as source runqueue.
Selecting the busiest runqueue as source when the target CPU is busy,
should result in achieving much better load balance.
Also when target CPU is not busy and asymmetric packing is set in sd,
select higher CPU as source CPU for load balancing.
While doing this change, move the check to see if target CPU is busy
into check_asym_packing().
The extent of performance benefit from this change decreases with the
increasing load. However there is benefit in undercommit as well as
overcommit conditions.
1. Record per second ebizzy (32 threads) on a 64 CPU power 7 box. (5 iterations)
4.6.0-rc2
Testcase: Min Max Avg StdDev
ebizzy: 5223767.00 10368236.00 7946971.00 1753094.76
4.6.0-rc2+asym-changes
Testcase: Min Max Avg StdDev %Change
ebizzy: 8617191.00 13872356.00 11383980.00 1783400.89 +24.78%
2. Record per second ebizzy (64 threads) on a 64 CPU power 7 box. (5 iterations)
4.6.0-rc2
Testcase: Min Max Avg StdDev
ebizzy: 6497666.00 18399783.00 10818093.20 4051452.08
4.6.0-rc2+asym-changes
Testcase: Min Max Avg StdDev %Change
ebizzy: 7567365.00 19456937.00 11674063.60 4295407.48 +4.40%
3. Record per second ebizzy (128 threads) on a 64 CPU power 7 box. (5 iterations)
4.6.0-rc2
Testcase: Min Max Avg StdDev
ebizzy: 37073983.00 40341911.00 38776241.80 1259766.82
4.6.0-rc2+asym-changes
Testcase: Min Max Avg StdDev %Change
ebizzy: 38030399.00 41333378.00 39827404.40 1255001.86 +2.54%
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Gautham R Shenoy <ego@linux.vnet.ibm.com>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1459948660-16073-1-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch introduces 'write_backward' bit to perf_event_attr, which
controls the direction of a ring buffer. After set, the corresponding
ring buffer is written from end to beginning. This feature is design to
support reading from overwritable ring buffer.
Ring buffer can be created by mapping a perf event fd. Kernel puts event
records into ring buffer, user tooling like perf fetch them from
address returned by mmap(). To prevent racing between kernel and tooling,
they communicate to each other through 'head' and 'tail' pointers.
Kernel maintains 'head' pointer, points it to the next free area (tail
of the last record). Tooling maintains 'tail' pointer, points it to the
tail of last consumed record (record has already been fetched). Kernel
determines the available space in a ring buffer using these two
pointers to avoid overwrite unfetched records.
By mapping without 'PROT_WRITE', an overwritable ring buffer is created.
Different from normal ring buffer, tooling is unable to maintain 'tail'
pointer because writing is forbidden. Therefore, for this type of ring
buffers, kernel overwrite old records unconditionally, works like flight
recorder. This feature would be useful if reading from overwritable ring
buffer were as easy as reading from normal ring buffer. However,
there's an obscure problem.
The following figure demonstrates a full overwritable ring buffer. In
this figure, the 'head' pointer points to the end of last record, and a
long record 'E' is pending. For a normal ring buffer, a 'tail' pointer
would have pointed to position (X), so kernel knows there's no more
space in the ring buffer. However, for an overwritable ring buffer,
kernel ignore the 'tail' pointer.
(X) head
. |
. V
+------+-------+----------+------+---+
|A....A|B.....B|C........C|D....D| |
+------+-------+----------+------+---+
Record 'A' is overwritten by event 'E':
head
|
V
+--+---+-------+----------+------+---+
|.E|..A|B.....B|C........C|D....D|E..|
+--+---+-------+----------+------+---+
Now tooling decides to read from this ring buffer. However, none of these
two natural positions, 'head' and the start of this ring buffer, are
pointing to the head of a record. Even the full ring buffer can be
accessed by tooling, it is unable to find a position to start decoding.
The first attempt tries to solve this problem AFAIK can be found from
[1]. It makes kernel to maintain 'tail' pointer: updates it when ring
buffer is half full. However, this approach introduces overhead to
fast path. Test result shows a 1% overhead [2]. In addition, this method
utilizes no more tham 50% records.
Another attempt can be found from [3], which allows putting the size of
an event at the end of each record. This approach allows tooling to find
records in a backward manner from 'head' pointer by reading size of a
record from its tail. However, because of alignment requirement, it
needs 8 bytes to record the size of a record, which is a huge waste. Its
performance is also not good, because more data need to be written.
This approach also introduces some extra branch instructions to fast
path.
'write_backward' is a better solution to this problem.
Following figure demonstrates the state of the overwritable ring buffer
when 'write_backward' is set before overwriting:
head
|
V
+---+------+----------+-------+------+
| |D....D|C........C|B.....B|A....A|
+---+------+----------+-------+------+
and after overwriting:
head
|
V
+---+------+----------+-------+---+--+
|..E|D....D|C........C|B.....B|A..|E.|
+---+------+----------+-------+---+--+
In each situation, 'head' points to the beginning of the newest record.
From this record, tooling can iterate over the full ring buffer and fetch
records one by one.
The only limitation that needs to be considered is back-to-back reading.
Due to the non-deterministic of user programs, it is impossible to ensure
the ring buffer keeps stable during reading. Consider an extreme situation:
tooling is scheduled out after reading record 'D', then a burst of events
come, eat up the whole ring buffer (one or multiple rounds). When the
tooling process comes back, reading after 'D' is incorrect now.
To prevent this problem, we need to find a way to ensure the ring buffer
is stable during reading. ioctl(PERF_EVENT_IOC_PAUSE_OUTPUT) is
suggested because its overhead is lower than
ioctl(PERF_EVENT_IOC_ENABLE).
By carefully verifying 'header' pointer, reader can avoid pausing the
ring-buffer. For example:
/* A union of all possible events */
union perf_event event;
p = head = perf_mmap__read_head();
while (true) {
/* copy header of next event */
fetch(&event.header, p, sizeof(event.header));
/* read 'head' pointer */
head = perf_mmap__read_head();
/* check overwritten: is the header good? */
if (!verify(sizeof(event.header), p, head))
break;
/* copy the whole event */
fetch(&event, p, event.header.size);
/* read 'head' pointer again */
head = perf_mmap__read_head();
/* is the whole event good? */
if (!verify(event.header.size, p, head))
break;
p += event.header.size;
}
However, the overhead is high because:
a) In-place decoding is not safe.
Copying-verifying-decoding is required.
b) Fetching 'head' pointer requires additional synchronization.
(From Alexei Starovoitov:
Even when this trick works, pause is needed for more than stability of
reading. When we collect the events into overwrite buffer we're waiting
for some other trigger (like all cpu utilization spike or just one cpu
running and all others are idle) and when it happens the buffer has
valuable info from the past. At this point new events are no longer
interesting and buffer should be paused, events read and unpaused until
next trigger comes.)
This patch utilizes event's default overflow_handler introduced
previously. perf_event_output_backward() is created as the default
overflow handler for backward ring buffers. To avoid extra overhead to
fast path, original perf_event_output() becomes __perf_event_output()
and marked '__always_inline'. In theory, there's no extra overhead
introduced to fast path.
Performance testing:
Calling 3000000 times of 'close(-1)', use gettimeofday() to check
duration. Use 'perf record -o /dev/null -e raw_syscalls:*' to capture
system calls. In ns.
Testing environment:
CPU : Intel(R) Core(TM) i7-4790 CPU @ 3.60GHz
Kernel : v4.5.0
MEAN STDVAR
BASE 800214.950 2853.083
PRE1 2253846.700 9997.014
PRE2 2257495.540 8516.293
POST 2250896.100 8933.921
Where 'BASE' is pure performance without capturing. 'PRE1' is test
result of pure 'v4.5.0' kernel. 'PRE2' is test result before this
patch. 'POST' is test result after this patch. See [4] for the detailed
experimental setup.
Considering the stdvar, this patch doesn't introduce performance
overhead to the fast path.
[1] http://lkml.iu.edu/hypermail/linux/kernel/1304.1/04584.html
[2] http://lkml.iu.edu/hypermail/linux/kernel/1307.1/00535.html
[3] http://lkml.iu.edu/hypermail/linux/kernel/1512.0/01265.html
[4] http://lkml.kernel.org/g/56F89DCD.1040202@huawei.com
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: <acme@kernel.org>
Cc: <pi3orama@163.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: Zefan Li <lizefan@huawei.com>
Link: http://lkml.kernel.org/r/1459865478-53413-1-git-send-email-wangnan0@huawei.com
[ Fixed the changelog some more. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The do_sys_settimeofday() function uses a timespec, which is not year
2038 safe on 32bit systems.
Thus this patch introduces do_sys_settimeofday64(), which allows us to
transition users of do_sys_settimeofday() to using 64bit time types.
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Baolin Wang <baolin.wang@linaro.org>
[jstultz: Include errno-base.h to avoid build issue on some arches]
Signed-off-by: John Stultz <john.stultz@linaro.org>
The recent introduction of the hotplug thread which invokes the callbacks on
the plugged cpu, cased the following regression:
If takedown_cpu() fails, then we run into several issues:
1) The rollback of the target cpu states is not invoked. That leaves the smp
threads and the hotplug thread in disabled state.
2) notify_online() is executed due to a missing skip_onerr flag. That causes
that both CPU_DOWN_FAILED and CPU_ONLINE notifications are invoked which
confuses quite some notifiers.
3) The CPU_DOWN_FAILED notification is not invoked on the target CPU. That's
not an issue per se, but it is inconsistent and in consequence blocks the
patches which rely on these states being invoked on the target CPU and not
on the controlling cpu. It also does not preserve the strict call order on
rollback which is problematic for the ongoing state machine conversion as
well.
To fix this we add a rollback flag to the remote callback machinery and invoke
the rollback including the CPU_DOWN_FAILED notification on the remote
cpu. Further mark the notify online state with 'skip_onerr' so we don't get a
double invokation.
This workaround will go away once we moved the unplug invocation to the target
cpu itself.
[ tglx: Massaged changelog and moved the CPU_DOWN_FAILED notifiaction to the
target cpu ]
Fixes: 4cb28ced23 ("cpu/hotplug: Create hotplug threads")
Reported-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: linux-s390@vger.kernel.org
Cc: rt@linutronix.de
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Anna-Maria Gleixner <anna-maria@linutronix.de>
Link: http://lkml.kernel.org/r/20160408124015.GA21960@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Mutation testing carried out by Iftekhar Ahmed of Oregon State
University showed that rcutorture is failing to test invocations
of call_rcu() having interrupts disabled. This commit therefore
adds interrupt disabling around one of the existing invocations
of call_rcu() (and friends).
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
When running from the scripts, rcutorture is completely headless,
so there is no way to to manually dump the trace buffer. This commit
therefore unconditionally dumps the trace buffer upon timed shutdown.
However, if you are using rmmod to end the test, it is still up to you
to manually dump the trace buffer.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Pull networking fixes from David Miller:
1) Fix memory leak in iwlwifi, from Matti Gottlieb.
2) Add missing registration of netfilter arp_tables into initial
namespace, from Florian Westphal.
3) Fix potential NULL deref in DecNET routing code.
4) Restrict NETLINK_URELEASE to truly bound sockets only, from Dmitry
Ivanov.
5) Fix dst ref counting in VRF, from David Ahern.
6) Fix TSO segmenting limits in i40e driver, from Alexander Duyck.
7) Fix heap leak in PACKET_DIAG_MCLIST, from Mathias Krause.
8) Ravalidate IPV6 datagram socket cached routes properly, particularly
with UDP, from Martin KaFai Lau.
9) Fix endian bug in RDS dp_ack_seq handling, from Qing Huang.
10) Fix stats typing in bcmgenet driver, from Eric Dumazet.
11) Openvswitch needs to orphan SKBs before ipv6 fragmentation handing,
from Joe Stringer.
12) SPI device reference leak in spi_ks8895 PHY driver, from Mark Brown.
13) atl2 doesn't actually support scatter-gather, so don't advertise the
feature. From Ben Hucthings.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (72 commits)
openvswitch: use flow protocol when recalculating ipv6 checksums
Driver: Vmxnet3: set CHECKSUM_UNNECESSARY for IPv6 packets
atl2: Disable unimplemented scatter/gather feature
net/mlx4_en: Split SW RX dropped counter per RX ring
net/mlx4_core: Don't allow to VF change global pause settings
net/mlx4_core: Avoid repeated calls to pci enable/disable
net/mlx4_core: Implement pci_resume callback
net: phy: spi_ks8895: Don't leak references to SPI devices
net: ethernet: davinci_emac: Fix platform_data overwrite
net: ethernet: davinci_emac: Fix Unbalanced pm_runtime_enable
qede: Fix single MTU sized packet from firmware GRO flow
qede: Fix setting Skb network header
qede: Fix various memory allocation error flows for fastpath
tcp: Merge tx_flags and tskey in tcp_shifted_skb
tcp: Merge tx_flags and tskey in tcp_collapse_retrans
drivers: net: cpsw: fix wrong regs access in cpsw_ndo_open
tcp: Fix SOF_TIMESTAMPING_TX_ACK when handling dup acks
openvswitch: Orphan skbs before IPv6 defrag
Revert "Prevent NUll pointer dereference with two PHYs on cpsw"
VSOCK: Only check error on skb_recv_datagram when skb is NULL
...
move trace_call_bpf() into helper function to minimize the size
of perf_trace_*() tracepoint handlers.
text data bss dec hex filename
10541679 5526646 2945024 19013349 1221ee5 vmlinux_before
10509422 5526646 2945024 18981092 121a0e4 vmlinux_after
It may seem that perf_fetch_caller_regs() can also be moved,
but that is incorrect, since ip/sp will be wrong.
bpf+tracepoint performance is not affected, since
perf_swevent_put_recursion_context() is now inlined.
export_symbol_gpl can also be dropped.
No measurable change in normal perf tracepoints.
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
If userspace calls UNLOCK_PI unconditionally without trying the TID -> 0
transition in user space first then the user space value might not have the
waiters bit set. This opens the following race:
CPU0 CPU1
uval = get_user(futex)
lock(hb)
lock(hb)
futex |= FUTEX_WAITERS
....
unlock(hb)
cmpxchg(futex, uval, newval)
So the cmpxchg fails and returns -EINVAL to user space, which is wrong because
the futex value is valid.
To handle this (yes, yet another) corner case gracefully, check for a flag
change and retry.
[ tglx: Massaged changelog and slightly reworked implementation ]
Fixes: ccf9e6a80d ("futex: Make unlock_pi more robust")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: stable@vger.kernel.org
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Darren Hart <dvhart@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1460723739-5195-1-git-send-email-bigeasy@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
This series wires up the generic memremap() function for ARM in a way
that allows it to be used as intended, i.e., without regard for whether
the region being mapped is covered by a struct page and/or the linear
mapping (lowmem)
This patch adds a new helper for cls/act programs that can push events
to user space applications. For networking, this can be f.e. for sampling,
debugging, logging purposes or pushing of arbitrary wake-up events. The
idea is similar to a43eec3042 ("bpf: introduce bpf_perf_event_output()
helper") and 39111695b1 ("samples: bpf: add bpf_perf_event_output example").
The eBPF program utilizes a perf event array map that user space populates
with fds from perf_event_open(), the eBPF program calls into the helper
f.e. as skb_event_output(skb, &my_map, BPF_F_CURRENT_CPU, raw, sizeof(raw))
so that the raw data is pushed into the fd f.e. at the map index of the
current CPU.
User space can poll/mmap/etc on this and has a data channel for receiving
events that can be post-processed. The nice thing is that since the eBPF
program and user space application making use of it are tightly coupled,
they can define their own arbitrary raw data format and what/when they
want to push.
While f.e. packet headers could be one part of the meta data that is being
pushed, this is not a substitute for things like packet sockets as whole
packet is not being pushed and push is only done in a single direction.
Intention is more of a generically usable, efficient event pipe to applications.
Workflow is that tc can pin the map and applications can attach themselves
e.g. after cls/act setup to one or multiple map slots, demuxing is done by
the eBPF program.
Adding this facility is with minimal effort, it reuses the helper
introduced in a43eec3042 ("bpf: introduce bpf_perf_event_output() helper")
and we get its functionality for free by overloading its BPF_FUNC_ identifier
for cls/act programs, ctx is currently unused, but will be made use of in
future. Example will be added to iproute2's BPF example files.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a BPF_F_CURRENT_CPU flag to optimize the use-case where user space has
per-CPU ring buffers and the eBPF program pushes the data into the current
CPU's ring buffer which saves us an extra helper function call in eBPF.
Also, make sure to properly reserve the remaining flags which are not used.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fengguang Wu's bot found two comparisons of unsigned integers to zero. These
were real bugs, as it would miss error conditions returned to zero.
trace_events_hist.c:426:6-9: WARNING: Unsigned expression compared with zero: idx < 0
trace_events_hist.c:568:5-14: WARNING: Unsigned expression compared with zero: n_entries < 0
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
