* pm-sleep:
PM / hibernate: Fix rtree_next_node() to avoid walking off list ends
x86/power/64: Use __pa() for physical address computation
PM / sleep: Update some system sleep documentation
Pull networking fixes from David Miller:
1) Buffers powersave frame test is reversed in cfg80211, fix from Felix
Fietkau.
2) Remove bogus WARN_ON in openvswitch, from Jarno Rajahalme.
3) Fix some tg3 ethtool logic bugs, and one that would cause no
interrupts to be generated when rx-coalescing is set to 0. From
Satish Baddipadige and Siva Reddy Kallam.
4) QLCNIC mailbox corruption and napi budget handling fix from Manish
Chopra.
5) Fix fib_trie logic when walking the trie during /proc/net/route
output than can access a stale node pointer. From David Forster.
6) Several sctp_diag fixes from Phil Sutter.
7) PAUSE frame handling fixes in mlxsw driver from Ido Schimmel.
8) Checksum fixup fixes in bpf from Daniel Borkmann.
9) Memork leaks in nfnetlink, from Liping Zhang.
10) Use after free in rxrpc, from David Howells.
11) Use after free in new skb_array code of macvtap driver, from Jason
Wang.
12) Calipso resource leak, from Colin Ian King.
13) mediatek bug fixes (missing stats sync init, etc.) from Sean Wang.
14) Fix bpf non-linear packet write helpers, from Daniel Borkmann.
15) Fix lockdep splats in macsec, from Sabrina Dubroca.
16) hv_netvsc bug fixes from Vitaly Kuznetsov, mostly to do with VF
handling.
17) Various tc-action bug fixes, from CONG Wang.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (116 commits)
net_sched: allow flushing tc police actions
net_sched: unify the init logic for act_police
net_sched: convert tcf_exts from list to pointer array
net_sched: move tc offload macros to pkt_cls.h
net_sched: fix a typo in tc_for_each_action()
net_sched: remove an unnecessary list_del()
net_sched: remove the leftover cleanup_a()
mlxsw: spectrum: Allow packets to be trapped from any PG
mlxsw: spectrum: Unmap 802.1Q FID before destroying it
mlxsw: spectrum: Add missing rollbacks in error path
mlxsw: reg: Fix missing op field fill-up
mlxsw: spectrum: Trap loop-backed packets
mlxsw: spectrum: Add missing packet traps
mlxsw: spectrum: Mark port as active before registering it
mlxsw: spectrum: Create PVID vPort before registering netdevice
mlxsw: spectrum: Remove redundant errors from the code
mlxsw: spectrum: Don't return upon error in removal path
i40e: check for and deal with non-contiguous TCs
ixgbe: Re-enable ability to toggle VLAN filtering
ixgbe: Force VLNCTRL.VFE to be set in all VMDq paths
...
cgroup_threadgroup_rwsem is acquired in read mode during process exit
and fork. It is also grabbed in write mode during
__cgroups_proc_write(). I've recently run into a scenario with lots
of memory pressure and OOM and I am beginning to see
systemd
__switch_to+0x1f8/0x350
__schedule+0x30c/0x990
schedule+0x48/0xc0
percpu_down_write+0x114/0x170
__cgroup_procs_write.isra.12+0xb8/0x3c0
cgroup_file_write+0x74/0x1a0
kernfs_fop_write+0x188/0x200
__vfs_write+0x6c/0xe0
vfs_write+0xc0/0x230
SyS_write+0x6c/0x110
system_call+0x38/0xb4
This thread is waiting on the reader of cgroup_threadgroup_rwsem to
exit. The reader itself is under memory pressure and has gone into
reclaim after fork. There are times the reader also ends up waiting on
oom_lock as well.
__switch_to+0x1f8/0x350
__schedule+0x30c/0x990
schedule+0x48/0xc0
jbd2_log_wait_commit+0xd4/0x180
ext4_evict_inode+0x88/0x5c0
evict+0xf8/0x2a0
dispose_list+0x50/0x80
prune_icache_sb+0x6c/0x90
super_cache_scan+0x190/0x210
shrink_slab.part.15+0x22c/0x4c0
shrink_zone+0x288/0x3c0
do_try_to_free_pages+0x1dc/0x590
try_to_free_pages+0xdc/0x260
__alloc_pages_nodemask+0x72c/0xc90
alloc_pages_current+0xb4/0x1a0
page_table_alloc+0xc0/0x170
__pte_alloc+0x58/0x1f0
copy_page_range+0x4ec/0x950
copy_process.isra.5+0x15a0/0x1870
_do_fork+0xa8/0x4b0
ppc_clone+0x8/0xc
In the meanwhile, all processes exiting/forking are blocked almost
stalling the system.
This patch moves the threadgroup_change_begin from before
cgroup_fork() to just before cgroup_canfork(). There is no nee to
worry about threadgroup changes till the task is actually added to the
threadgroup. This avoids having to call reclaim with
cgroup_threadgroup_rwsem held.
tj: Subject and description edits.
Signed-off-by: Balbir Singh <bsingharora@gmail.com>
Acked-by: Zefan Li <lizefan@huawei.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: stable@vger.kernel.org # v4.2+
Signed-off-by: Tejun Heo <tj@kernel.org>
Commit 1e2a7d7849 ("irqdomain: Don't set type when mapping an IRQ")
moved the trigger configuration call from the irqdomain mapping to
the interrupt being actually requested.
This patch failed to handle the case where we configure a chained
interrupt, which doesn't get requested through the usual path.
In order to solve this, let's call __irq_set_trigger just before
starting the cascade interrupt. Special care must be taken to
make the flow handler stick, as the .irq_set_type method could
have reset it (it doesn't know we're dealing with a chained
interrupt).
Based on an initial patch by Jon Hunter.
Fixes: 1e2a7d7849 ("irqdomain: Don't set type when mapping an IRQ")
Reported-by: John Stultz <john.stultz@linaro.org>
Reported-by: Linus Walleij <linus.walleij@linaro.org>
Tested-by: John Stultz <john.stultz@linaro.org>
Acked-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
All of the callers of cpufreq_update_util() pass rq_clock(rq) to it
as the time argument and some of them check whether or not cpu_of(rq)
is equal to smp_processor_id() before calling it, so rework it to
take a runqueue pointer as the argument and move the rq_clock(rq)
evaluation into it.
Additionally, provide a wrapper checking cpu_of(rq) against
smp_processor_id() for the cpufreq_update_util() callers that
need it.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
It is useful to know the reason why cpufreq_update_util() has just
been called and that can be passed as flags to cpufreq_update_util()
and to the ->func() callback in struct update_util_data. However,
doing that in addition to passing the util and max arguments they
already take would be clumsy, so avoid it.
Instead, use the observation that the schedutil governor is part
of the scheduler proper, so it can access scheduler data directly.
This allows the util and max arguments of cpufreq_update_util()
and the ->func() callback in struct update_util_data to be replaced
with a flags one, but schedutil has to be modified to follow.
Thus make the schedutil governor obtain the CFS utilization
information from the scheduler and use the "RT" and "DL" flags
instead of the special utilization value of ULONG_MAX to track
updates from the RT and DL sched classes. Make it non-modular
too to avoid having to export scheduler variables to modules at
large.
Next, update all of the other users of cpufreq_update_util()
and the ->func() callback in struct update_util_data accordingly.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Commit 288dab8a35 ("block: add a separate operation type for secure
erase") split REQ_OP_SECURE_ERASE from REQ_OP_DISCARD without considering
all the places REQ_OP_DISCARD was being used to mean either. Fix those.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Fixes: 288dab8a35 ("block: add a separate operation type for secure erase")
Signed-off-by: Jens Axboe <axboe@fb.com>
rtree_next_node() walks the linked list of leaf nodes to find the next
block of pages in the struct memory_bitmap. If it walks off the end of
the list of nodes, it walks the list of memory zones to find the next
region of memory. If it walks off the end of the list of zones, it
returns false.
This leaves the struct bm_position's node and zone pointers pointing
at their respective struct list_heads in struct mem_zone_bm_rtree.
memory_bm_find_bit() uses struct bm_position's node and zone pointers
to avoid walking lists and trees if the next bit appears in the same
node/zone. It handles these values being stale.
Swap rtree_next_node()s 'step then test' to 'test-next then step',
this means if we reach the end of memory we return false and leave
the node and zone pointers as they were.
This fixes a panic on resume using AMD Seattle with 64K pages:
[ 6.868732] Freezing user space processes ... (elapsed 0.000 seconds) done.
[ 6.875753] Double checking all user space processes after OOM killer disable... (elapsed 0.000 seconds)
[ 6.896453] PM: Using 3 thread(s) for decompression.
[ 6.896453] PM: Loading and decompressing image data (5339 pages)...
[ 7.318890] PM: Image loading progress: 0%
[ 7.323395] Unable to handle kernel paging request at virtual address 00800040
[ 7.330611] pgd = ffff000008df0000
[ 7.334003] [00800040] *pgd=00000083fffe0003, *pud=00000083fffe0003, *pmd=00000083fffd0003, *pte=0000000000000000
[ 7.344266] Internal error: Oops: 96000005 [#1] PREEMPT SMP
[ 7.349825] Modules linked in:
[ 7.352871] CPU: 2 PID: 1 Comm: swapper/0 Tainted: G W I 4.8.0-rc1 #4737
[ 7.360512] Hardware name: AMD Overdrive/Supercharger/Default string, BIOS ROD1002C 04/08/2016
[ 7.369109] task: ffff8003c0220000 task.stack: ffff8003c0280000
[ 7.375020] PC is at set_bit+0x18/0x30
[ 7.378758] LR is at memory_bm_set_bit+0x24/0x30
[ 7.383362] pc : [<ffff00000835bbc8>] lr : [<ffff0000080faf18>] pstate: 60000045
[ 7.390743] sp : ffff8003c0283b00
[ 7.473551]
[ 7.475031] Process swapper/0 (pid: 1, stack limit = 0xffff8003c0280020)
[ 7.481718] Stack: (0xffff8003c0283b00 to 0xffff8003c0284000)
[ 7.800075] Call trace:
[ 7.887097] [<ffff00000835bbc8>] set_bit+0x18/0x30
[ 7.891876] [<ffff0000080fb038>] duplicate_memory_bitmap.constprop.38+0x54/0x70
[ 7.899172] [<ffff0000080fcc40>] snapshot_write_next+0x22c/0x47c
[ 7.905166] [<ffff0000080fe1b4>] load_image_lzo+0x754/0xa88
[ 7.910725] [<ffff0000080ff0a8>] swsusp_read+0x144/0x230
[ 7.916025] [<ffff0000080fa338>] load_image_and_restore+0x58/0x90
[ 7.922105] [<ffff0000080fa660>] software_resume+0x2f0/0x338
[ 7.927752] [<ffff000008083350>] do_one_initcall+0x38/0x11c
[ 7.933314] [<ffff000008b40cc0>] kernel_init_freeable+0x14c/0x1ec
[ 7.939395] [<ffff0000087ce564>] kernel_init+0x10/0xfc
[ 7.944520] [<ffff000008082e90>] ret_from_fork+0x10/0x40
[ 7.949820] Code: d2800022 8b400c21 f9800031 9ac32043 (c85f7c22)
[ 7.955909] ---[ end trace 0024a5986e6ff323 ]---
[ 7.960529] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b
Here struct mem_zone_bm_rtree's start_pfn has been returned instead of
struct rtree_node's addr as the node/zone pointers are corrupt after
we walked off the end of the lists during mark_unsafe_pages().
This behaviour was exposed by commit 6dbecfd345 ("PM / hibernate:
Simplify mark_unsafe_pages()"), which caused mark_unsafe_pages() to call
duplicate_memory_bitmap(), which uses memory_bm_find_bit() after walking
off the end of the memory bitmap.
Fixes: 3a20cb1779 (PM / Hibernate: Implement position keeping in radix tree)
Signed-off-by: James Morse <james.morse@arm.com>
[ rjw: Subject ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
bpf_get_prandom_u32() was initially introduced for socket filters
and later requested numberous times to be added to tracing bpf programs
for the same reason as in socket filters: to be able to randomly
select incoming events.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The helper functions like bpf_map_lookup_elem(map, key) were only
allowing 'key' to point to the initialized stack area.
That is causing performance degradation when programs need to process
millions of packets per second and need to copy contents of the packet
into the stack just to pass the stack pointer into the lookup() function.
Allow such helpers read from the packet directly.
All helpers that expect ARG_PTR_TO_MAP_KEY, ARG_PTR_TO_MAP_VALUE,
ARG_PTR_TO_STACK assume byte aligned pointer, so no alignment concerns,
only need to check that helper will not be accessing beyond
the packet range verified by the prior 'if (ptr < data_end)' condition.
For now allow this feature for XDP programs only. Later it can be
relaxed for the clsact programs as well.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
While hashing out BPF's current_task_under_cgroup helper bits, it came
to discussion that the skb_in_cgroup helper name was suboptimally chosen.
Tejun says:
So, I think in_cgroup should mean that the object is in that
particular cgroup while under_cgroup in the subhierarchy of that
cgroup. Let's rename the other subhierarchy test to under too. I
think that'd be a lot less confusing going forward.
[...]
It's more intuitive and gives us the room to implement the real
"in" test if ever necessary in the future.
Since this touches uapi bits, we need to change this as long as v4.8
is not yet officially released. Thus, change the helper enum and rename
related bits.
Fixes: 4a482f34af ("cgroup: bpf: Add bpf_skb_in_cgroup_proto")
Reference: http://patchwork.ozlabs.org/patch/658500/
Suggested-by: Sargun Dhillon <sargun@sargun.me>
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
This adds a bpf helper that's similar to the skb_in_cgroup helper to check
whether the probe is currently executing in the context of a specific
subset of the cgroupsv2 hierarchy. It does this based on membership test
for a cgroup arraymap. It is invalid to call this in an interrupt, and
it'll return an error. The helper is primarily to be used in debugging
activities for containers, where you may have multiple programs running in
a given top-level "container".
Signed-off-by: Sargun Dhillon <sargun@sargun.me>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Tejun Heo <tj@kernel.org>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull power management fixes from Rafael Wysocki:
"Two hibernation fixes allowing it to work with the recently added
randomization of the kernel identity mapping base on x86-64 and one
cpufreq driver regression fix.
Specifics:
- Fix the x86 identity mapping creation helpers to avoid the
assumption that the base address of the mapping will always be
aligned at the PGD level, as it may be aligned at the PUD level if
address space randomization is enabled (Rafael Wysocki).
- Fix the hibernation core to avoid executing tracing functions
before restoring the processor state completely during resume
(Thomas Garnier).
- Fix a recently introduced regression in the powernv cpufreq driver
that causes it to crash due to an out-of-bounds array access
(Akshay Adiga)"
* tag 'pm-4.8-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
PM / hibernate: Restore processor state before using per-CPU variables
x86/power/64: Always create temporary identity mapping correctly
cpufreq: powernv: Fix crash in gpstate_timer_handler()
Pull timer fixes from Ingo Molnar:
"Misc fixes: a /dev/rtc regression fix, two APIC timer period
calibration fixes, an ARM clocksource driver fix and a NOHZ
power use regression fix"
* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/hpet: Fix /dev/rtc breakage caused by RTC cleanup
x86/timers/apic: Inform TSC deadline clockevent device about recalibration
x86/timers/apic: Fix imprecise timer interrupts by eliminating TSC clockevents frequency roundoff error
timers: Fix get_next_timer_interrupt() computation
clocksource/arm_arch_timer: Force per-CPU interrupt to be level-triggered
Pull scheduler fixes from Ingo Molnar:
"Misc fixes: cputime fixes, two deadline scheduler fixes and a cgroups
scheduling fix"
* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/cputime: Fix omitted ticks passed in parameter
sched/cputime: Fix steal time accounting
sched/deadline: Fix lock pinning warning during CPU hotplug
sched/cputime: Mitigate performance regression in times()/clock_gettime()
sched/fair: Fix typo in sync_throttle()
sched/deadline: Fix wrap-around in DL heap
Restore the processor state before calling any other functions to
ensure per-CPU variables can be used with KASLR memory randomization.
Tracing functions use per-CPU variables (GS based on x86) and one was
called just before restoring the processor state fully. It resulted
in a double fault when both the tracing & the exception handler
functions tried to use a per-CPU variable.
Fixes: bb3632c610 (PM / sleep: trace events for suspend/resume)
Reported-and-tested-by: Borislav Petkov <bp@suse.de>
Reported-by: Jiri Kosina <jikos@kernel.org>
Tested-by: Rafael J. Wysocki <rafael@kernel.org>
Tested-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Thomas Garnier <thgarnie@google.com>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Pull perf fixes from Ingo Molnar:
"Mostly tooling fixes, plus two uncore-PMU fixes, an uprobes fix, a
perf-cgroups fix and an AUX events fix"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86/intel/uncore: Add enable_box for client MSR uncore
perf/x86/intel/uncore: Fix uncore num_counters
uprobes/x86: Fix RIP-relative handling of EVEX-encoded instructions
perf/core: Set cgroup in CPU contexts for new cgroup events
perf/core: Fix sideband list-iteration vs. event ordering NULL pointer deference crash
perf probe ppc64le: Fix probe location when using DWARF
perf probe: Add function to post process kernel trace events
tools: Sync cpufeatures headers with the kernel
toops: Sync tools/include/uapi/linux/bpf.h with the kernel
tools: Sync cpufeatures.h and vmx.h with the kernel
perf probe: Support signedness casting
perf stat: Avoid skew when reading events
perf probe: Fix module name matching
perf probe: Adjust map->reloc offset when finding kernel symbol from map
perf hists: Trim libtraceevent trace_seq buffers
perf script: Add 'bpf-output' field to usage message
Pull locking fixes from Ingo Molnar:
"Misc fixes: lockstat fix, futex fix on !MMU systems, big endian fix
for qrwlocks and a race fix for pvqspinlocks"
* 'locking-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
locking/pvqspinlock: Fix a bug in qstat_read()
locking/pvqspinlock: Fix double hash race
locking/qrwlock: Fix write unlock bug on big endian systems
futex: Assume all mappings are private on !MMU systems
Pull irq fix from Ingo Molnar:
"A fix for an MSI regression"
* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
genirq/msi: Make sure PCI MSIs are activated early
Debugging what goes wrong with cgroup setup can get hairy. Add
tracepoints for cgroup hierarchy mount, cgroup creation/destruction
and task migration operations for better visibility.
Signed-off-by: Tejun Heo <tj@kernel.org>
cgroup_path() and friends used to format the path from the end and
thus the resulting path usually didn't start at the start of the
passed in buffer. Also, when the buffer was too small, the partial
result was truncated from the head rather than tail and there was no
way to tell how long the full path would be. These make the functions
less robust and more awkward to use.
With recent updates to kernfs_path(), cgroup_path() and friends can be
made to behave in strlcpy() style.
* cgroup_path(), cgroup_path_ns[_locked]() and task_cgroup_path() now
always return the length of the full path. If buffer is too small,
it contains nul terminated truncated output.
* All users updated accordingly.
v2: cgroup_path() usage in kernel/sched/debug.c converted.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Serge Hallyn <serge.hallyn@ubuntu.com>
Cc: Peter Zijlstra <peterz@infradead.org>
This message is currently really useless since it always prints a value
that comes from the printk() we just did, e.g.:
BUG: sleeping function called from invalid context at mm/slab.h:388
in_atomic(): 0, irqs_disabled(): 0, pid: 31996, name: trinity-c1
Preemption disabled at:[<ffffffff8119db33>] down_trylock+0x13/0x80
BUG: sleeping function called from invalid context at include/linux/freezer.h:56
in_atomic(): 0, irqs_disabled(): 0, pid: 31996, name: trinity-c1
Preemption disabled at:[<ffffffff811aaa37>] console_unlock+0x2f7/0x930
Here, both down_trylock() and console_unlock() is somewhere in the
printk() path.
We should save the value before calling printk() and use the saved value
instead. That immediately reveals the offending callsite:
BUG: sleeping function called from invalid context at mm/slab.h:388
in_atomic(): 0, irqs_disabled(): 0, pid: 14971, name: trinity-c2
Preemption disabled at:[<ffffffff819bcd46>] rhashtable_walk_start+0x46/0x150
Bug report:
http://marc.info/?l=linux-netdev&m=146925979821849&w=2
Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rusty Russel <rusty@rustcorp.com.au>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Currently the percpu-rwsem switches to (global) atomic ops while a
writer is waiting; which could be quite a while and slows down
releasing the readers.
This patch cures this problem by ordering the reader-state vs
reader-count (see the comments in __percpu_down_read() and
percpu_down_write()). This changes a global atomic op into a full
memory barrier, which doesn't have the global cacheline contention.
This also enables using the percpu-rwsem with rcu_sync disabled in order
to bias the implementation differently, reducing the writer latency by
adding some cost to readers.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Paul McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
[ Fixed modular build. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Currently there are overlap in the pvqspinlock wait_again and
spurious_wakeup stat counters. Because of lock stealing, it is
no longer possible to accurately determine if spurious wakeup has
happened in the queue head. As they track both the queue node and
queue head status, it is also hard to tell how many of those comes
from the queue head and how many from the queue node.
This patch changes the accounting rules so that spurious wakeup is
only tracked in the queue node. The wait_again count, however, is
only tracked in the queue head when the vCPU failed to acquire the
lock after a vCPU kick. This should give a much better indication of
the wait-kick dynamics in the queue node and the queue head.
Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Douglas Hatch <doug.hatch@hpe.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Pan Xinhui <xinhui@linux.vnet.ibm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1464713631-1066-2-git-send-email-Waiman.Long@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
setup_new_dl_entity() takes two parameters, but it only actually uses
one of them, under a different name, to setup a new dl_entity, after:
2f9f3fdc928 "sched/deadline: Remove dl_new from struct sched_dl_entity"
as we currently do:
setup_new_dl_entity(&p->dl, &p->dl)
However, before Luca's change we were doing:
setup_new_dl_entity(dl_se, pi_se)
in update_dl_entity() for a dl_se->new entity: we were using pi_se's
parameters (the potential PI donor) for setting up a new entity.
This change removes the useless second parameter of setup_new_dl_entity().
While we are at it we also optimize things further calling setup_new_dl_
entity() only for already queued tasks, since (as pointed out by Xunlei)
we already do the very same update at tasks wakeup time anyway. By doing
so, we don't need to worry about a potential PI donor anymore, as
rt_mutex_setprio() takes care of that already for us.
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@unitn.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Xunlei Pang <xpang@redhat.com>
Link: http://lkml.kernel.org/r/1470409675-20935-1-git-send-email-juri.lelli@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Vincent noted that the update_tg_load_avg() usage in commit:
3d30544f02 ("sched/fair: Apply more PELT fixes")
isn't entirely sufficient. We need to call this function every time
cfs_rq->avg.load changes, this includes when update_cfs_rq_load_avg()
returns true, but {attach,detach}_entity_load_avg() themselves also
change it. This means we need to unconditionally call
update_tg_load_avg().
Also, add more comments.
Reported-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The following warning can be triggered by hot-unplugging the CPU
on which an active SCHED_DEADLINE task is running on:
WARNING: CPU: 0 PID: 0 at kernel/locking/lockdep.c:3531 lock_release+0x690/0x6a0
releasing a pinned lock
Call Trace:
dump_stack+0x99/0xd0
__warn+0xd1/0xf0
? dl_task_timer+0x1a1/0x2b0
warn_slowpath_fmt+0x4f/0x60
? sched_clock+0x13/0x20
lock_release+0x690/0x6a0
? enqueue_pushable_dl_task+0x9b/0xa0
? enqueue_task_dl+0x1ca/0x480
_raw_spin_unlock+0x1f/0x40
dl_task_timer+0x1a1/0x2b0
? push_dl_task.part.31+0x190/0x190
WARNING: CPU: 0 PID: 0 at kernel/locking/lockdep.c:3649 lock_unpin_lock+0x181/0x1a0
unpinning an unpinned lock
Call Trace:
dump_stack+0x99/0xd0
__warn+0xd1/0xf0
warn_slowpath_fmt+0x4f/0x60
lock_unpin_lock+0x181/0x1a0
dl_task_timer+0x127/0x2b0
? push_dl_task.part.31+0x190/0x190
As per the comment before this code, its safe to drop the RQ lock
here, and since we (potentially) change rq, unpin and repin to avoid
the splat.
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
[ Rewrote changelog. ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@unitn.it>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1470274940-17976-1-git-send-email-wanpeng.li@hotmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit:
6e998916df ("sched/cputime: Fix clock_nanosleep()/clock_gettime() inconsistency")
fixed a problem whereby clock_nanosleep() followed by clock_gettime() could
allow a task to wake early. It addressed the problem by calling the scheduling
classes update_curr() when the cputimer starts.
Said change induced a considerable performance regression on the syscalls
times() and clock_gettimes(CLOCK_PROCESS_CPUTIME_ID). There are some
debuggers and applications that monitor their own performance that
accidentally depend on the performance of these specific calls.
This patch mitigates the performace loss by prefetching data in the CPU
cache, as stalls due to cache misses appear to be where most time is spent
in our benchmarks.
Here are the performance gain of this patch over v4.7-rc7 on a Sandy Bridge
box with 32 logical cores and 2 NUMA nodes. The test is repeated with a
variable number of threads, from 2 to 4*num_cpus; the results are in
seconds and correspond to the average of 10 runs; the percentage gain is
computed with (before-after)/before so a positive value is an improvement
(it's faster). The improvement varies between a few percents for 5-20
threads and more than 10% for 2 or >20 threads.
pound_clock_gettime:
threads 4.7-rc7 patched 4.7-rc7
[num] [secs] [secs (percent)]
2 3.48 3.06 ( 11.83%)
5 3.33 3.25 ( 2.40%)
8 3.37 3.26 ( 3.30%)
12 3.32 3.37 ( -1.60%)
21 4.01 3.90 ( 2.74%)
30 3.63 3.36 ( 7.41%)
48 3.71 3.11 ( 16.27%)
79 3.75 3.16 ( 15.74%)
110 3.81 3.25 ( 14.80%)
128 3.88 3.31 ( 14.76%)
pound_times:
threads 4.7-rc7 patched 4.7-rc7
[num] [secs] [secs (percent)]
2 3.65 3.25 ( 11.03%)
5 3.45 3.17 ( 7.92%)
8 3.52 3.22 ( 8.69%)
12 3.29 3.36 ( -2.04%)
21 4.07 3.92 ( 3.78%)
30 3.87 3.40 ( 12.17%)
48 3.79 3.16 ( 16.61%)
79 3.88 3.28 ( 15.42%)
110 3.90 3.38 ( 13.35%)
128 4.00 3.38 ( 15.45%)
pound_clock_gettime and pound_clock_gettime are two benchmarks included in
the MMTests framework. They launch a given number of threads which
repeatedly call times() or clock_gettimes(). The results above can be
reproduced with cloning MMTests from github.com and running the "poundtime"
workload:
$ git clone https://github.com/gormanm/mmtests.git
$ cd mmtests
$ cp configs/config-global-dhp__workload_poundtime config
$ ./run-mmtests.sh --run-monitor $(uname -r)
The above will run "poundtime" measuring the kernel currently running on
the machine; Once a new kernel is installed and the machine rebooted,
running again
$ cd mmtests
$ ./run-mmtests.sh --run-monitor $(uname -r)
will produce results to compare with. A comparison table will be output
with:
$ cd mmtests/work/log
$ ../../compare-kernels.sh
the table will contain a lot of entries; grepping for "Amean" (as in
"arithmetic mean") will give the tables presented above. The source code
for the two benchmarks is reported at the end of this changelog for
clairity.
The cache misses addressed by this patch were found using a combination of
`perf top`, `perf record` and `perf annotate`. The incriminated lines were
found to be
struct sched_entity *curr = cfs_rq->curr;
and
delta_exec = now - curr->exec_start;
in the function update_curr() from kernel/sched/fair.c. This patch
prefetches the data from memory just before update_curr is called in the
interested execution path.
A comparison of the total number of cycles before and after the patch
follows; the data is obtained using `perf stat -r 10 -ddd <program>`
running over the same sequence of number of threads used above (a positive
gain is an improvement):
threads cycles before cycles after gain
2 19,699,563,964 +-1.19% 17,358,917,517 +-1.85% 11.88%
5 47,401,089,566 +-2.96% 45,103,730,829 +-0.97% 4.85%
8 80,923,501,004 +-3.01% 71,419,385,977 +-0.77% 11.74%
12 112,326,485,473 +-0.47% 110,371,524,403 +-0.47% 1.74%
21 193,455,574,299 +-0.72% 180,120,667,904 +-0.36% 6.89%
30 315,073,519,013 +-1.64% 271,222,225,950 +-1.29% 13.92%
48 321,969,515,332 +-1.48% 273,353,977,321 +-1.16% 15.10%
79 337,866,003,422 +-0.97% 289,462,481,538 +-1.05% 14.33%
110 338,712,691,920 +-0.78% 290,574,233,170 +-0.77% 14.21%
128 348,384,794,006 +-0.50% 292,691,648,206 +-0.66% 15.99%
A comparison of cache miss vs total cache loads ratios, before and after
the patch (again from the `perf stat -r 10 -ddd <program>` tables):
threads L1 misses/total*100 L1 misses/total*100 gain
before after
2 7.43 +-4.90% 7.36 +-4.70% 0.94%
5 13.09 +-4.74% 13.52 +-3.73% -3.28%
8 13.79 +-5.61% 12.90 +-3.27% 6.45%
12 11.57 +-2.44% 8.71 +-1.40% 24.72%
21 12.39 +-3.92% 9.97 +-1.84% 19.53%
30 13.91 +-2.53% 11.73 +-2.28% 15.67%
48 13.71 +-1.59% 12.32 +-1.97% 10.14%
79 14.44 +-0.66% 13.40 +-1.06% 7.20%
110 15.86 +-0.50% 14.46 +-0.59% 8.83%
128 16.51 +-0.32% 15.06 +-0.78% 8.78%
As a final note, the following shows the evolution of performance figures
in the "poundtime" benchmark and pinpoints commit 6e998916df
("sched/cputime: Fix clock_nanosleep()/clock_gettime() inconsistency") as a
major source of degradation, mostly unaddressed to this day (figures
expressed in seconds).
pound_clock_gettime:
threads parent of 6e998916df 4.7-rc7
6e998916df itself
2 2.23 3.68 ( -64.56%) 3.48 (-55.48%)
5 2.83 3.78 ( -33.42%) 3.33 (-17.43%)
8 2.84 4.31 ( -52.12%) 3.37 (-18.76%)
12 3.09 3.61 ( -16.74%) 3.32 ( -7.17%)
21 3.14 4.63 ( -47.36%) 4.01 (-27.71%)
30 3.28 5.75 ( -75.37%) 3.63 (-10.80%)
48 3.02 6.05 (-100.56%) 3.71 (-22.99%)
79 2.88 6.30 (-118.90%) 3.75 (-30.26%)
110 2.95 6.46 (-119.00%) 3.81 (-29.24%)
128 3.05 6.42 (-110.08%) 3.88 (-27.04%)
pound_times:
threads parent of 6e998916df 4.7-rc7
6e998916df itself
2 2.27 3.73 ( -64.71%) 3.65 (-61.14%)
5 2.78 3.77 ( -35.56%) 3.45 (-23.98%)
8 2.79 4.41 ( -57.71%) 3.52 (-26.05%)
12 3.02 3.56 ( -17.94%) 3.29 ( -9.08%)
21 3.10 4.61 ( -48.74%) 4.07 (-31.34%)
30 3.33 5.75 ( -72.53%) 3.87 (-16.01%)
48 2.96 6.06 (-105.04%) 3.79 (-28.10%)
79 2.88 6.24 (-116.83%) 3.88 (-34.81%)
110 2.98 6.37 (-114.08%) 3.90 (-31.12%)
128 3.10 6.35 (-104.61%) 4.00 (-28.87%)
The source code of the two benchmarks follows. To compile the two:
NR_THREADS=42
for FILE in pound_times pound_clock_gettime; do
gcc -lrt -O2 -lpthread -DNUM_THREADS=$NR_THREADS $FILE.c -o $FILE
done
==== BEGIN pound_times.c ====
struct tms start;
void *pound (void *threadid)
{
struct tms end;
int oldutime = 0;
int utime;
int i;
for (i = 0; i < 5000000 / NUM_THREADS; i++) {
times(&end);
utime = ((int)end.tms_utime - (int)start.tms_utime);
if (oldutime > utime) {
printf("utime decreased, was %d, now %d!\n", oldutime, utime);
}
oldutime = utime;
}
pthread_exit(NULL);
}
int main()
{
pthread_t th[NUM_THREADS];
long i;
times(&start);
for (i = 0; i < NUM_THREADS; i++) {
pthread_create (&th[i], NULL, pound, (void *)i);
}
pthread_exit(NULL);
return 0;
}
==== END pound_times.c ====
==== BEGIN pound_clock_gettime.c ====
void *pound (void *threadid)
{
struct timespec ts;
int rc, i;
unsigned long prev = 0, this = 0;
for (i = 0; i < 5000000 / NUM_THREADS; i++) {
rc = clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &ts);
if (rc < 0)
perror("clock_gettime");
this = (ts.tv_sec * 1000000000) + ts.tv_nsec;
if (0 && this < prev)
printf("%lu ns timewarp at iteration %d\n", prev - this, i);
prev = this;
}
pthread_exit(NULL);
}
int main()
{
pthread_t th[NUM_THREADS];
long rc, i;
pid_t pgid;
for (i = 0; i < NUM_THREADS; i++) {
rc = pthread_create(&th[i], NULL, pound, (void *)i);
if (rc < 0)
perror("pthread_create");
}
pthread_exit(NULL);
return 0;
}
==== END pound_clock_gettime.c ====
Suggested-by: Mike Galbraith <mgalbraith@suse.de>
Signed-off-by: Giovanni Gherdovich <ggherdovich@suse.cz>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1470385316-15027-2-git-send-email-ggherdovich@suse.cz
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Current code in cpudeadline.c has a bug in re-heapifying when adding a
new element at the end of the heap, because a deadline value of 0 is
temporarily set in the new elem, then cpudl_change_key() is called
with the actual elem deadline as param.
However, the function compares the new deadline to set with the one
previously in the elem, which is 0. So, if current absolute deadlines
grew so much to have negative values as s64, the comparison in
cpudl_change_key() makes the wrong decision. Instead, as from
dl_time_before(), the kernel should handle correctly abs deadlines
wrap-arounds.
This patch fixes the problem with a minimally invasive change that
forces cpudl_change_key() to heapify up in this case.
Signed-off-by: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Luca Abeni <luca.abeni@unitn.it>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1468921493-10054-2-git-send-email-tommaso.cucinotta@sssup.it
Signed-off-by: Ingo Molnar <mingo@kernel.org>
For perf record -b, which requires the pmu::sched_task callback the
current code is rather expensive:
7.68% sched-pipe [kernel.vmlinux] [k] perf_pmu_sched_task
5.95% sched-pipe [kernel.vmlinux] [k] __switch_to
5.20% sched-pipe [kernel.vmlinux] [k] __intel_pmu_disable_all
3.95% sched-pipe perf [.] worker_thread
The problem is that it will iterate all registered PMUs, most of which
will not have anything to do. Avoid this by keeping an explicit list
of PMUs that have requested the callback.
The perf_sched_cb_{inc,dec}() functions already takes the required pmu
argument, and now that these functions are no longer called from NMI
context we can use them to manage a list.
With this patch applied the function doesn't show up in the top 4
anymore (it dropped to 18th place).
6.67% sched-pipe [kernel.vmlinux] [k] __switch_to
6.18% sched-pipe [kernel.vmlinux] [k] __intel_pmu_disable_all
3.92% sched-pipe [kernel.vmlinux] [k] switch_mm_irqs_off
3.71% sched-pipe perf [.] worker_thread
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.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: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In order to allow optimizing perf_pmu_sched_task() we must ensure
perf_sched_cb_{inc,dec}() are no longer called from NMI context; this
means that pmu::{start,stop}() can no longer use them.
Prepare for this by reworking the whole large PEBS setup code.
The current code relied on the cpuc->pebs_enabled state, however since
that reflects the current active state as per pmu::{start,stop}() we
can no longer rely on this.
Introduce two counters: cpuc->n_pebs and cpuc->n_large_pebs which
count the total number of PEBS events and the number of PEBS events
that have FREERUNNING set, resp.. With this we can tell if the current
setup requires a single record interrupt threshold or can use a larger
buffer.
This also improves the code in that it re-enables the large threshold
once the PEBS event that required single record gets removed.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.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: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Groups of events are supposed to be scheduled atomically, such that it
is possible to derive meaningful ratios between their values.
We take great pains to achieve this when scheduling event groups to a
PMU in group_sched_in(), calling {start,commit}_txn() (which fall back
to perf_pmu_{disable,enable}() if necessary) to provide this guarantee.
However we don't mirror this in group_sched_out(), and in some cases
events will not be scheduled out atomically.
For example, if we disable an event group with PERF_EVENT_IOC_DISABLE,
we'll cross-call __perf_event_disable() for the group leader, and will
call group_sched_out() without having first disabled the relevant PMU.
We will disable/enable the PMU around each pmu->del() call, but between
each call the PMU will be enabled and events may count.
Avoid this by explicitly disabling and enabling the PMU around event
removal in group_sched_out(), mirroring what we do in group_sched_in().
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.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>
Link: http://lkml.kernel.org/r/1469553141-28314-1-git-send-email-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There's a perf stat bug easy to observer on a machine with only one cgroup:
$ perf stat -e cycles -I 1000 -C 0 -G /
# time counts unit events
1.000161699 <not counted> cycles /
2.000355591 <not counted> cycles /
3.000565154 <not counted> cycles /
4.000951350 <not counted> cycles /
We'd expect some output there.
The underlying problem is that there is an optimization in
perf_cgroup_sched_{in,out}() that skips the switch of cgroup events
if the old and new cgroups in a task switch are the same.
This optimization interacts with the current code in two ways
that cause a CPU context's cgroup (cpuctx->cgrp) to be NULL even if a
cgroup event matches the current task. These are:
1. On creation of the first cgroup event in a CPU: In current code,
cpuctx->cpu is only set in perf_cgroup_sched_in, but due to the
aforesaid optimization, perf_cgroup_sched_in will run until the next
cgroup switches in that CPU. This may happen late or never happen,
depending on system's number of cgroups, CPU load, etc.
2. On deletion of the last cgroup event in a cpuctx: In list_del_event,
cpuctx->cgrp is set NULL. Any new cgroup event will not be sched in
because cpuctx->cgrp == NULL until a cgroup switch occurs and
perf_cgroup_sched_in is executed (updating cpuctx->cgrp).
This patch fixes both problems by setting cpuctx->cgrp in list_add_event,
mirroring what list_del_event does when removing a cgroup event from CPU
context, as introduced in:
commit 68cacd2916 ("perf_events: Fix stale ->cgrp pointer in update_cgrp_time_from_cpuctx()")
With this patch, cpuctx->cgrp is always set/clear when installing/removing
the first/last cgroup event in/from the CPU context. With cpuctx->cgrp
correctly set, event_filter_match works as intended when events are
sched in/out.
After the fix, the output is as expected:
$ perf stat -e cycles -I 1000 -a -G /
# time counts unit events
1.004699159 627342882 cycles /
2.007397156 615272690 cycles /
3.010019057 616726074 cycles /
Signed-off-by: David Carrillo-Cisneros <davidcc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Turner <pjt@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vegard Nossum <vegard.nossum@gmail.com>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Link: http://lkml.kernel.org/r/1470124092-113192-1-git-send-email-davidcc@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Vegard Nossum reported that perf fuzzing generates a NULL
pointer dereference crash:
> Digging a bit deeper into this, it seems the event itself is getting
> created by perf_event_open() and it gets added to the pmu_event_list
> through:
>
> perf_event_open()
> - perf_event_alloc()
> - account_event()
> - account_pmu_sb_event()
> - attach_sb_event()
>
> so at this point the event is being attached but its ->ctx is still
> NULL. It seems like ->ctx is set just a bit later in
> perf_event_open(), though.
>
> But before that, __schedule() comes along and creates a stack trace
> similar to the one above:
>
> __schedule()
> - __perf_event_task_sched_out()
> - perf_iterate_sb()
> - perf_iterate_sb_cpu()
> - event_filter_match()
> - perf_cgroup_match()
> - __get_cpu_context()
> - (dereference ctx which is NULL)
>
> So I guess the question is... should the event be attached (= put on
> the list) before ->ctx gets set? Or should the cgroup code check for a
> NULL ->ctx?
The latter seems like the simplest solution. Moving the list-add later
creates a bit of a mess.
Reported-by: Vegard Nossum <vegard.nossum@gmail.com>
Tested-by: Vegard Nossum <vegard.nossum@gmail.com>
Tested-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: f2fb6bef92 ("perf/core: Optimize side-band event delivery")
Link: http://lkml.kernel.org/r/20160804123724.GN6862@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
