Skip to content

L
linux
Switch branch/tag
  1. 14 Jan, 2017 2 commits
    • Peter Zijlstra's avatar
      perf/core: Fix concurrent sys_perf_event_open() vs. 'move_group' race · 321027c1
      Peter Zijlstra authored 
      Di Shen reported a race between two concurrent sys_perf_event_open()
calls where both try and move the same pre-existing software group
into a hardware context.

The problem is exactly that described in commit:

  f63a8daa ("perf: Fix event->ctx locking")

... where, while we wait for a ctx->mutex acquisition, the event->ctx
relation can have changed under us.

That very same commit failed to recognise sys_perf_event_context() as an
external access vector to the events and thereby didn't apply the
established locking rules correctly.

So while one sys_perf_event_open() call is stuck waiting on
mutex_lock_double(), the other (which owns said locks) moves the group
about. So by the time the former sys_perf_event_open() acquires the
locks, the context we've acquired is stale (and possibly dead).

Apply the established locking rules as per perf_event_ctx_lock_nested()
to the mutex_lock_double() for the 'move_group' case. This obviously means
we need to validate state after we acquire the locks.

Reported-by: Di Shen (Keen Lab)
Tested-by: default avatarJohn Dias <joaodias@google.com>
Signed-off-by: default avatarPeter 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: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Min Chong <mchong@google.com>
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>
Fixes: f63a8daa ("perf: Fix event->ctx locking")
Link: http://lkml.kernel.org/r/20170106131444.GZ3174@twins.programming.kicks-ass.netSigned-off-by: default avatarIngo Molnar <mingo@kernel.org>
      321027c1
    • Peter Zijlstra's avatar
      perf/core: Fix sys_perf_event_open() vs. hotplug · 63cae12b
      Peter Zijlstra authored 
      There is problem with installing an event in a task that is 'stuck' on
an offline CPU.

Blocked tasks are not dis-assosciated from offlined CPUs, after all, a
blocked task doesn't run and doesn't require a CPU etc.. Only on
wakeup do we ammend the situation and place the task on a available
CPU.

If we hit such a task with perf_install_in_context() we'll loop until
either that task wakes up or the CPU comes back online, if the task
waking depends on the event being installed, we're stuck.

While looking into this issue, I also spotted another problem, if we
hit a task with perf_install_in_context() that is in the middle of
being migrated, that is we observe the old CPU before sending the IPI,
but run the IPI (on the old CPU) while the task is already running on
the new CPU, things also go sideways.

Rework things to rely on task_curr() -- outside of rq->lock -- which
is rather tricky. Imagine the following scenario where we're trying to
install the first event into our task 't':

CPU0            CPU1            CPU2

                (current == t)

t->perf_event_ctxp[] = ctx;
smp_mb();
cpu = task_cpu(t);

                switch(t, n);
                                migrate(t, 2);
                                switch(p, t);

                                ctx = t->perf_event_ctxp[]; // must not be NULL

smp_function_call(cpu, ..);

                generic_exec_single()
                  func();
                    spin_lock(ctx->lock);
                    if (task_curr(t)) // false

                    add_event_to_ctx();
                    spin_unlock(ctx->lock);

                                perf_event_context_sched_in();
                                  spin_lock(ctx->lock);
                                  // sees event

So its CPU0's store of t->perf_event_ctxp[] that must not go 'missing'.
Because if CPU2's load of that variable were to observe NULL, it would
not try to schedule the ctx and we'd have a task running without its
counter, which would be 'bad'.

As long as we observe !NULL, we'll acquire ctx->lock. If we acquire it
first and not see the event yet, then CPU0 must observe task_curr()
and retry. If the install happens first, then we must see the event on
sched-in and all is well.

I think we can translate the first part (until the 'must not be NULL')
of the scenario to a litmus test like:

  C C-peterz

  {
  }

  P0(int *x, int *y)
  {
          int r1;

          WRITE_ONCE(*x, 1);
          smp_mb();
          r1 = READ_ONCE(*y);
  }

  P1(int *y, int *z)
  {
          WRITE_ONCE(*y, 1);
          smp_store_release(z, 1);
  }

  P2(int *x, int *z)
  {
          int r1;
          int r2;

          r1 = smp_load_acquire(z);
	  smp_mb();
          r2 = READ_ONCE(*x);
  }

  exists
  (0:r1=0 /\ 2:r1=1 /\ 2:r2=0)

Where:
  x is perf_event_ctxp[],
  y is our tasks's CPU, and
  z is our task being placed on the rq of CPU2.

The P0 smp_mb() is the one added by this patch, ordering the store to
perf_event_ctxp[] from find_get_context() and the load of task_cpu()
in task_function_call().

The smp_store_release/smp_load_acquire model the RCpc locking of the
rq->lock and the smp_mb() of P2 is the context switch switching from
whatever CPU2 was running to our task 't'.

This litmus test evaluates into:

  Test C-peterz Allowed
  States 7
  0:r1=0; 2:r1=0; 2:r2=0;
  0:r1=0; 2:r1=0; 2:r2=1;
  0:r1=0; 2:r1=1; 2:r2=1;
  0:r1=1; 2:r1=0; 2:r2=0;
  0:r1=1; 2:r1=0; 2:r2=1;
  0:r1=1; 2:r1=1; 2:r2=0;
  0:r1=1; 2:r1=1; 2:r2=1;
  No
  Witnesses
  Positive: 0 Negative: 7
  Condition exists (0:r1=0 /\ 2:r1=1 /\ 2:r2=0)
  Observation C-peterz Never 0 7
  Hash=e427f41d9146b2a5445101d3e2fcaa34

And the strong and weak model agree.
Reported-by: default avatarMark Rutland <mark.rutland@arm.com>
Tested-by: default avatarMark Rutland <mark.rutland@arm.com>
Signed-off-by: default avatarPeter 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: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: jeremy.linton@arm.com
Link: http://lkml.kernel.org/r/20161209135900.GU3174@twins.programming.kicks-ass.netSigned-off-by: default avatarIngo Molnar <mingo@kernel.org>
      63cae12b
  3. 11 Jan, 2017 2 commits
  5. 05 Jan, 2017 2 commits
    • David Carrillo-Cisneros's avatar
      perf/x86: Set pmu->module in Intel PMU modules · 74545f63
      David Carrillo-Cisneros authored 
      The conversion of Intel PMU drivers into modules did not include reference
counting. The machine will crash when attempting to  access deleted code
if an event from a module PMU is started and the module removed before the
event is destroyed.

i.e. this crashes the machine:

	$ insmod intel-rapl-perf.ko
	$ perf stat -e power/energy-cores/ -C 0 &
	$ rmmod intel-rapl-perf.ko

Set THIS_MODULE to pmu->module in Intel module PMUs so that generic code
can handle reference counting and deny rmmod while an event still exists.
Signed-off-by: default avatarDavid Carrillo-Cisneros <davidcc@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Dave Hansen <dave.hansen@linux.intel.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: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1482455860-116269-1-git-send-email-davidcc@google.comSigned-off-by: default avatarIngo Molnar <mingo@kernel.org>
      74545f63
    • Ingo Molnar's avatar
      Merge tag 'perf-urgent-for-mingo-4.10-20170104' of... · 4e06d4f0
      Ingo Molnar authored 
      Merge tag 'perf-urgent-for-mingo-4.10-20170104' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/urgent fixes and one improvement from Arnaldo Carvalho de Melo:

Fixes:

  - Fix prev/next_prio formatting for deadline tasks in libtraceevent (Daniel Bristot de Oliveira)

  - Robustify reading of build-ids from /sys/kernel/note (Arnaldo Carvalho de Melo)

  - Fix building some sample/bpf in Alpine Linux 3.4 (Arnaldo Carvalho de Melo)

  - Fix 'make install-bin' to install libtraceevent plugins (Arnaldo Carvalho de Melo)

  - Fix 'perf record --switch-output' documentation and comment (Jiri Olsa)

  - Fix 'perf probe' for cross arch probing (Masami Hiramatsu)

Improvement:

  - Show total scheduling time in 'perf sched timehist' (Namhyumg Kim)
Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      4e06d4f0
  7. 04 Jan, 2017 2 commits
  9. 03 Jan, 2017 6 commits
  11. 02 Jan, 2017 1 commit
    • Masami Hiramatsu's avatar
      perf probe: Fix to get correct modname from elf header · 1f2ed153
      Masami Hiramatsu authored 
      Since 'perf probe' supports cross-arch probes, it is possible to analyze
different arch kernel image which has different bits-per-long.

In that case, it fails to get the module name because it uses the
MOD_NAME_OFFSET macro based on the host machine bits-per-long, instead
of the target arch bits-per-long.

This fixes above issue by changing modname-offset based on the target
archs bit width. This is ok because linux kernel uses LP64 model on
64bit arch.

E.g. without this (on x86_64, and target module is arm32):

  $ perf probe -m build-arm/fs/configfs/configfs.ko -D configfs_lookup
  p:probe/configfs_lookup :configfs_lookup+0
                          ^-Here is an empty module name.

With this fix, you can see correct module name:

  $ perf probe -m build-arm/fs/configfs/configfs.ko -D configfs_lookup
  p:probe/configfs_lookup configfs:configfs_lookup+0
Signed-off-by: default avatarMasami Hiramatsu <mhiramat@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/148337043836.6752.383495516397005695.stgit@devboxSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      1f2ed153
  13. 01 Jan, 2017 2 commits
    • Linus Torvalds's avatar
      Linux 4.10-rc2 · 0c744ea4
      Linus Torvalds authored
      0c744ea4
    • Linus Torvalds's avatar
      Merge branch 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm · 4759d386
      Linus Torvalds authored 
      Pull DAX updates from Dan Williams:
 "The completion of Jan's DAX work for 4.10.

  As I mentioned in the libnvdimm-for-4.10 pull request, these are some
  final fixes for the DAX dirty-cacheline-tracking invalidation work
  that was merged through the -mm, ext4, and xfs trees in -rc1. These
  patches were prepared prior to the merge window, but we waited for
  4.10-rc1 to have a stable merge base after all the prerequisites were
  merged.

  Quoting Jan on the overall changes in these patches:

     "So I'd like all these 6 patches to go for rc2. The first three
      patches fix invalidation of exceptional DAX entries (a bug which
      is there for a long time) - without these patches data loss can
      occur on power failure even though user called fsync(2). The other
      three patches change locking of DAX faults so that ->iomap_begin()
      is called in a more relaxed locking context and we are safe to
      start a transaction there for ext4"

  These have received a build success notification from the kbuild
  robot, and pass the latest libnvdimm unit tests. There have not been
  any -next releases since -rc1, so they have not appeared there"

* 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
  ext4: Simplify DAX fault path
  dax: Call ->iomap_begin without entry lock during dax fault
  dax: Finish fault completely when loading holes
  dax: Avoid page invalidation races and unnecessary radix tree traversals
  mm: Invalidate DAX radix tree entries only if appropriate
  ext2: Return BH_New buffers for zeroed blocks
      4759d386
  15. 30 Dec, 2016 2 commits
  17. 29 Dec, 2016 2 commits
    • Olof Johansson's avatar
      mm/filemap: fix parameters to test_bit() · 98473f9f
      Olof Johansson authored 
       mm/filemap.c: In function 'clear_bit_unlock_is_negative_byte':
  mm/filemap.c:933:9: error: too few arguments to function 'test_bit'
    return test_bit(PG_waiters);
         ^~~~~~~~

Fixes: b91e1302 ('mm: optimize PageWaiters bit use for unlock_page()')
Signed-off-by: default avatarOlof Johansson <olof@lixom.net>
Brown-paper-bag-by: default avatarLinus Torvalds <dummy@duh.com>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
      98473f9f
    • Linus Torvalds's avatar
      mm: optimize PageWaiters bit use for unlock_page() · b91e1302
      Linus Torvalds authored 
      In commit 62906027 ("mm: add PageWaiters indicating tasks are
waiting for a page bit") Nick Piggin made our page locking no longer
unconditionally touch the hashed page waitqueue, which not only helps
performance in general, but is particularly helpful on NUMA machines
where the hashed wait queues can bounce around a lot.

However, the "clear lock bit atomically and then test the waiters bit"
sequence turns out to be much more expensive than it needs to be,
because you get a nasty stall when trying to access the same word that
just got updated atomically.

On architectures where locking is done with LL/SC, this would be trivial
to fix with a new primitive that clears one bit and tests another
atomically, but that ends up not working on x86, where the only atomic
operations that return the result end up being cmpxchg and xadd.  The
atomic bit operations return the old value of the same bit we changed,
not the value of an unrelated bit.

On x86, we could put the lock bit in the high bit of the byte, and use
"xadd" with that bit (where the overflow ends up not touching other
bits), and look at the other bits of the result.  However, an even
simpler model is to just use a regular atomic "and" to clear the lock
bit, and then the sign bit in eflags will indicate the resulting state
of the unrelated bit #7.

So by moving the PageWaiters bit up to bit #7, we can atomically clear
the lock bit and test the waiters bit on x86 too.  And architectures
with LL/SC (which is all the usual RISC suspects), the particular bit
doesn't matter, so they are fine with this approach too.

This avoids the extra access to the same atomic word, and thus avoids
the costly stall at page unlock time.

The only downside is that the interface ends up being a bit odd and
specialized: clear a bit in a byte, and test the sign bit.  Nick doesn't
love the resulting name of the new primitive, but I'd rather make the
name be descriptive and very clear about the limitation imposed by
trying to work across all relevant architectures than make it be some
generic thing that doesn't make the odd semantics explicit.

So this introduces the new architecture primitive

    clear_bit_unlock_is_negative_byte();

and adds the trivial implementation for x86.  We have a generic
non-optimized fallback (that just does a "clear_bit()"+"test_bit(7)"
combination) which can be overridden by any architecture that can do
better.  According to Nick, Power has the same hickup x86 has, for
example, but some other architectures may not even care.

All these optimizations mean that my page locking stress-test (which is
just executing a lot of small short-lived shell scripts: "make test" in
the git source tree) no longer makes our page locking look horribly bad.
Before all these optimizations, just the unlock_page() costs were just
over 3% of all CPU overhead on "make test".  After this, it's down to
0.66%, so just a quarter of the cost it used to be.

(The difference on NUMA is bigger, but there this micro-optimization is
likely less noticeable, since the big issue on NUMA was not the accesses
to 'struct page', but the waitqueue accesses that were already removed
by Nick's earlier commit).
Acked-by: default avatarNick Piggin <npiggin@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Bob Peterson <rpeterso@redhat.com>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Andrew Lutomirski <luto@kernel.org>
Cc: Andreas Gruenbacher <agruenba@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
      b91e1302
  19. 28 Dec, 2016 5 commits
    • Arnaldo Carvalho de Melo's avatar
      samples/bpf trace_output_user: Remove duplicate sys/ioctl.h include · b6f4c667
      Arnaldo Carvalho de Melo authored 
      Cc: Alexei Starovoitov <ast@fb.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Joe Stringer <joe@ovn.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-3awp0nv8tpnblatojmwjww7z@git.kernel.orgSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      b6f4c667
    • Linus Torvalds's avatar
      Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6 · 2d706e79
      Linus Torvalds authored 
      Pull crypto fix from Herbert Xu:
 "This fixes a hash corruption bug in the marvell driver"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6:
  crypto: marvell - Copy IVDIG before launching partial DMA ahash requests
      2d706e79
    • Arnaldo Carvalho de Melo's avatar
      samples/bpf sock_example: Avoid getting ethhdr from two includes · ee12996c
      Arnaldo Carvalho de Melo authored 
      To avoid the following build failure on Alpine Linux 3.4, that has
clang-3.8 with the bpf target:

    HOSTCC  samples/bpf/sock_example.o
  In file included from /usr/include/net/ethernet.h:10:0,
                   from /git/linux/samples/bpf/sock_example.h:7,
                   from /git/linux/samples/bpf/sock_example.c:30:
  /usr/include/netinet/if_ether.h:96:8: error: redefinition of 'struct
  ethhdr'
   struct ethhdr {
          ^
  In file included from /git/linux/samples/bpf/sock_example.c:26:0:
  ./usr/include/linux/if_ether.h:144:8: note: originally defined here
   struct ethhdr {
          ^
  scripts/Makefile.host:124: recipe for target
  'samples/bpf/sock_example.o' failed
  make[2]: *** [samples/bpf/sock_example.o] Error 1
  /git/linux/Makefile:1658: recipe for target 'samples/bpf/' failed

So include net/if_ether.h for the needs of sock_example.h, using the
same include that sock_example.c uses.

Cc: Alexei Starovoitov <ast@fb.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Joe Stringer <joe@ovn.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-m9avekl1b651qe1r1zd5tzz9@git.kernel.orgSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      ee12996c
    • Namhyung Kim's avatar
      perf sched timehist: Show total scheduling time · 9396c9cb
      Namhyung Kim authored 
      Show length of analyzed sample time and rate of idle task running.
This also takes care of time range given by --time option.

  $ perf sched timehist -sI | tail
  Samples do not have callchains.
  Idle stats:
      CPU  0 idle for    930.316  msec  ( 92.93%)
      CPU  1 idle for    963.614  msec  ( 96.25%)
      CPU  2 idle for    885.482  msec  ( 88.45%)
      CPU  3 idle for    938.635  msec  ( 93.76%)

      Total number of unique tasks: 118
  Total number of context switches: 2337
             Total run time (msec): 3718.048
      Total scheduling time (msec): 1001.131  (x 4)
Suggested-by: default avatarDavid Ahern <dsahern@gmail.com>
Signed-off-by: default avatarNamhyung Kim <namhyung@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20161222060350.17655-3-namhyung@kernel.orgSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      9396c9cb
    • Linus Torvalds's avatar
      Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net · 8f18e4d0
      Linus Torvalds authored 
      Pull networking fixes from David Miller:

 1) Various ipvlan fixes from Eric Dumazet and Mahesh Bandewar.

    The most important is to not assume the packet is RX just because
    the destination address matches that of the device. Such an
    assumption causes problems when an interface is put into loopback
    mode.

 2) If we retry when creating a new tc entry (because we dropped the
    RTNL mutex in order to load a module, for example) we end up with
    -EAGAIN and then loop trying to replay the request. But we didn't
    reset some state when looping back to the top like this, and if
    another thread meanwhile inserted the same tc entry we were trying
    to, we re-link it creating an enless loop in the tc chain. Fix from
    Daniel Borkmann.

 3) There are two different WRITE bits in the MDIO address register for
    the stmmac chip, depending upon the chip variant. Due to a bug we
    could set them both, fix from Hock Leong Kweh.

 4) Fix mlx4 bug in XDP_TX handling, from Tariq Toukan.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
  net: stmmac: fix incorrect bit set in gmac4 mdio addr register
  r8169: add support for RTL8168 series add-on card.
  net: xdp: remove unused bfp_warn_invalid_xdp_buffer()
  openvswitch: upcall: Fix vlan handling.
  ipv4: Namespaceify tcp_tw_reuse knob
  net: korina: Fix NAPI versus resources freeing
  net, sched: fix soft lockup in tc_classify
  net/mlx4_en: Fix user prio field in XDP forward
  tipc: don't send FIN message from connectionless socket
  ipvlan: fix multicast processing
  ipvlan: fix various issues in ipvlan_process_multicast()
      8f18e4d0
  21. 27 Dec, 2016 14 commits
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7