Pull tracing updates from Steven Rostedt:
"New features:
- Tom Zanussi's extended histogram work.
This adds the synthetic events to have histograms from multiple
event data Adds triggers "onmatch" and "onmax" to call the
synthetic events Several updates to the histogram code from this
- Allow way to nest ring buffer calls in the same context
- Allow absolute time stamps in ring buffer
- Rewrite of filter code parsing based on Al Viro's suggestions
- Setting of trace_clock to global if TSC is unstable (on boot)
- Better OOM handling when allocating large ring buffers
- Added initcall tracepoints (consolidated initcall_debug code with
them)
And other various fixes and clean ups"
* tag 'trace-v4.17' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (68 commits)
init: Have initcall_debug still work without CONFIG_TRACEPOINTS
init, tracing: Have printk come through the trace events for initcall_debug
init, tracing: instrument security and console initcall trace events
init, tracing: Add initcall trace events
tracing: Add rcu dereference annotation for test func that touches filter->prog
tracing: Add rcu dereference annotation for filter->prog
tracing: Fixup logic inversion on setting trace_global_clock defaults
tracing: Hide global trace clock from lockdep
ring-buffer: Add set/clear_current_oom_origin() during allocations
ring-buffer: Check if memory is available before allocation
lockdep: Add print_irqtrace_events() to __warn
vsprintf: Do not preprocess non-dereferenced pointers for bprintf (%px and %pK)
tracing: Uninitialized variable in create_tracing_map_fields()
tracing: Make sure variable string fields are NULL-terminated
tracing: Add action comparisons when testing matching hist triggers
tracing: Don't add flag strings when displaying variable references
tracing: Fix display of hist trigger expressions containing timestamps
ftrace: Drop a VLA in module_exists()
tracing: Mention trace_clock=global when warning about unstable clocks
tracing: Default to using trace_global_clock if sched_clock is unstable
...
A boot up test function update_pred_fn() dereferences filter->prog without
the proper rcu annotation.
To do this, we must also take the event_mutex first. Normally, this isn't
needed because this test function can not race with other use cases that
touch the event filters (it is disabled if any events are enabled).
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Fixes: 80765597bc ("tracing: Rewrite filter logic to be simpler and faster")
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
ftrace_function_set_filter() referenences filter->prog without annotation
and sparse complains about it. It needs a rcu_dereference_protected()
wrapper.
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Fixes: 80765597bc ("tracing: Rewrite filter logic to be simpler and faster")
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
In commit 932066a15335 ("tracing: Default to using trace_global_clock if
sched_clock is unstable"), the logic for deciding to override the
default clock if unstable was reversed from the earlier posting. I was
trying to reduce the width of the message by using an early return
rather than a if-block, but reverted back to using the if-block and
accidentally left the predicate inverted.
Link: http://lkml.kernel.org/r/20180404212450.26646-1-chris@chris-wilson.co.uk
Fixes: 932066a15335 ("tracing: Default to using trace_global_clock if sched_clock is unstable")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Function tracing can trace in NMIs and such. If the TSC is determined
to be unstable, the tracing clock will switch to the global clock on
boot up, unless "trace_clock" is specified on the kernel command line.
The global clock disables interrupts to access sched_clock_cpu(), and in
doing so can be done within lockdep internals (because of function
tracing and NMIs). This can trigger false lockdep splats.
The trace_clock_global() is special, best not to trace the irq logic
within it.
Link: http://lkml.kernel.org/r/20180404145015.77bde42d@gandalf.local.home
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
As si_mem_available() can say there is enough memory even though the memory
available is not useable by the ring buffer, it is best to not kill innocent
applications because the ring buffer is taking up all the memory while it is
trying to allocate a great deal of memory.
If the allocator is user space (because kernel threads can also increase the
size of the kernel ring buffer on boot up), then after si_mem_available()
says there is enough memory, set the OOM killer to kill the current task if
an OOM triggers during the allocation.
Link: http://lkml.kernel.org/r/20180404062340.GD6312@dhcp22.suse.cz
Suggested-by: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
The ring buffer is made up of a link list of pages. When making the ring
buffer bigger, it will allocate all the pages it needs before adding to the
ring buffer, and if it fails, it frees them and returns an error. This makes
increasing the ring buffer size an all or nothing action. When this was
first created, the pages were allocated with "NORETRY". This was to not
cause any Out-Of-Memory (OOM) actions from allocating the ring buffer. But
NORETRY was too strict, as the ring buffer would fail to expand even when
there's memory available, but was taken up in the page cache.
Commit 848618857d ("tracing/ring_buffer: Try harder to allocate") changed
the allocating from NORETRY to RETRY_MAYFAIL. The RETRY_MAYFAIL would
allocate from the page cache, but if there was no memory available, it would
simple fail the allocation and not trigger an OOM.
This worked fine, but had one problem. As the ring buffer would allocate one
page at a time, it could take up all memory in the system before it failed
to allocate and free that memory. If the allocation is happening and the
ring buffer allocates all memory and then tries to take more than available,
its allocation will not trigger an OOM, but if there's any allocation that
happens someplace else, that could trigger an OOM, even though once the ring
buffer's allocation fails, it would free up all the previous memory it tried
to allocate, and allow other memory allocations to succeed.
Commit d02bd27bd3 ("mm/page_alloc.c: calculate 'available' memory in a
separate function") separated out si_mem_availble() as a separate function
that could be used to see how much memory is available in the system. Using
this function to make sure that the ring buffer could be allocated before it
tries to allocate pages we can avoid allocating all memory in the system and
making it vulnerable to OOMs if other allocations are taking place.
Link: http://lkml.kernel.org/r/1522320104-6573-1-git-send-email-zhaoyang.huang@spreadtrum.com
CC: stable@vger.kernel.org
Cc: linux-mm@kvack.org
Fixes: 848618857d ("tracing/ring_buffer: Try harder to allocate")
Requires: d02bd27bd3 ("mm/page_alloc.c: calculate 'available' memory in a separate function")
Reported-by: Zhaoyang Huang <huangzhaoyang@gmail.com>
Tested-by: Joel Fernandes <joelaf@google.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Smatch complains that idx can be used uninitialized when we check if
(idx < 0). It has to be the first iteration through the loop and the
HIST_FIELD_FL_STACKTRACE bit has to be clear and the HIST_FIELD_FL_VAR
bit has to be set to reach the bug.
Link: http://lkml.kernel.org/r/20180328114815.GC29050@mwanda
Fixes: 30350d65ac ("tracing: Add variable support to hist triggers")
Acked-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Actions also need to be considered when checking for matching triggers
- triggers differing only by action should be allowed, but currently
aren't because the matching check ignores the action and erroneously
returns -EEXIST.
Add and call an actions_match() function to address that.
Here's an example using onmatch() actions. The first -EEXIST shouldn't
occur because the onmatch() is different in the second wakeup_latency()
param. The second -EEXIST shouldn't occur because it's a different
action (in this case, it doesn't have an action, so shouldn't be seen
as being the same and therefore rejected).
In the after case, both are correctly accepted (and trying to add one of
them again returns -EEXIST as it should).
before:
# echo 'wakeup_latency u64 lat; pid_t pid' >> /sys/kernel/debug/tracing/synthetic_events
# echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="cyclictest"' >> /sys/kernel/debug/tracing/events/sched/sched_wakeup/trigger
# echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0 if next_comm=="cyclictest"' >> /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
# echo 'hist:keys=next_pid:onmatch(sched.sched_wakeup).wakeup_latency(sched.sched_switch.$wakeup_lat,next_pid) if next_comm=="cyclictest"' >> /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
# echo 'hist:keys=next_pid:onmatch(sched.sched_wakeup).wakeup_latency(sched.sched_switch.$wakeup_lat,prev_pid) if next_comm=="cyclictest"' >> /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
-su: echo: write error: File exists
# echo 'hist:keys=next_pid if next_comm=="cyclictest"' >> /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
-su: echo: write error: File exists
after:
# echo 'wakeup_latency u64 lat; pid_t pid' >> /sys/kernel/debug/tracing/synthetic_events
# echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="cyclictest"' >> /sys/kernel/debug/tracing/events/sched/sched_wakeup/trigger
# echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0 if next_comm=="cyclictest"' >> /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
# echo 'hist:keys=next_pid:onmatch(sched.sched_wakeup).wakeup_latency(sched.sched_switch.$wakeup_lat,next_pid) if next_comm=="cyclictest"' >> /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
# echo 'hist:keys=next_pid:onmatch(sched.sched_wakeup).wakeup_latency(sched.sched_switch.$wakeup_lat,prev_pid) if next_comm=="cyclictest"' >> /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
# echo 'hist:keys=next_pid if next_comm=="cyclictest"' >> /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
Link: http://lkml.kernel.org/r/a7fd668b87ec10736c8f016ac4279c8480d50c2b.1522256721.git.tom.zanussi@linux.intel.com
Tested-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
When displaying hist triggers, variable references that have the
timestamp field flag set are erroneously displayed as common_timestamp
rather than the variable reference. Additionally, timestamp
expressions are displayed in the same way. Fix this by forcing the
timestamp flag handling to follow variable reference and expression
handling.
Before:
# cat /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
hist:keys=next_pid:vals=hitcount:wakeup_lat=common_timestamp.usecs:...
After:
# cat /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
hist:keys=next_pid:vals=hitcount:wakeup_lat=common_timestamp.usecs-$ts0.usecs:...
Link: http://lkml.kernel.org/r/92746b06be67499c2a6217bd55395b350ad18fad.1522256721.git.tom.zanussi@linux.intel.com
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Across suspend, we may see a very large drift in timestamps if the sched
clock is unstable, prompting the global trace's ringbuffer code to warn
and suggest switching to the global clock. Preempt this request by
detecting when the sched clock is unstable (determined during
late_initcall) and automatically switching the default clock over to
trace_global_clock.
This should prevent requiring user interaction to resolve warnings such
as:
Delta way too big! 18446743856563626466 ts=18446744054496180323 write stamp = 197932553857
If you just came from a suspend/resume,
please switch to the trace global clock:
echo global > /sys/kernel/debug/tracing/trace_clock
Link: http://lkml.kernel.org/r/20180330150132.16903-1-chris@chris-wilson.co.uk
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Pull trivial tree updates from Jiri Kosina.
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial:
kfifo: fix inaccurate comment
tools/thermal: tmon: fix for segfault
net: Spelling s/stucture/structure/
edd: don't spam log if no EDD information is present
Documentation: Fix early-microcode.txt references after file rename
tracing: Block comments should align the * on each line
treewide: Fix typos in printk
GenWQE: Fix a typo in two comments
treewide: Align function definition open/close braces
Pull time(r) updates from Thomas Gleixner:
"A small set of updates for timers and timekeeping:
- The most interesting change is the consolidation of clock MONOTONIC
and clock BOOTTIME.
Clock MONOTONIC behaves now exactly like clock BOOTTIME and does
not longer ignore the time spent in suspend. A new clock
MONOTONIC_ACTIVE is provived which behaves like clock MONOTONIC in
kernels before this change. This allows applications to
programmatically check for the clock MONOTONIC behaviour.
As discussed in the review thread, this has the potential of
breaking user space and we might have to revert this. Knock on wood
that we can avoid that exercise.
- Updates to the NTP mechanism to improve accuracy
- A new kernel internal data structure to aid the ongoing Y2038 work.
- Cleanups and simplifications of the clocksource code.
- Make the alarmtimer code play nicely with debugobjects"
* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
alarmtimer: Init nanosleep alarm timer on stack
y2038: Introduce struct __kernel_old_timeval
tracing: Unify the "boot" and "mono" tracing clocks
hrtimer: Unify MONOTONIC and BOOTTIME clock behavior
posix-timers: Unify MONOTONIC and BOOTTIME clock behavior
timekeeping: Remove boot time specific code
Input: Evdev - unify MONOTONIC and BOOTTIME clock behavior
timekeeping: Make the MONOTONIC clock behave like the BOOTTIME clock
timekeeping: Add the new CLOCK_MONOTONIC_ACTIVE clock
timekeeping/ntp: Determine the multiplier directly from NTP tick length
timekeeping/ntp: Don't align NTP frequency adjustments to ticks
clocksource: Use ATTRIBUTE_GROUPS
clocksource: Use DEVICE_ATTR_RW/RO/WO to define device attributes
clocksource: Don't walk the clocksource list for empty override
Pull networking updates from David Miller:
1) Support offloading wireless authentication to userspace via
NL80211_CMD_EXTERNAL_AUTH, from Srinivas Dasari.
2) A lot of work on network namespace setup/teardown from Kirill Tkhai.
Setup and cleanup of namespaces now all run asynchronously and thus
performance is significantly increased.
3) Add rx/tx timestamping support to mv88e6xxx driver, from Brandon
Streiff.
4) Support zerocopy on RDS sockets, from Sowmini Varadhan.
5) Use denser instruction encoding in x86 eBPF JIT, from Daniel
Borkmann.
6) Support hw offload of vlan filtering in mvpp2 dreiver, from Maxime
Chevallier.
7) Support grafting of child qdiscs in mlxsw driver, from Nogah
Frankel.
8) Add packet forwarding tests to selftests, from Ido Schimmel.
9) Deal with sub-optimal GSO packets better in BBR congestion control,
from Eric Dumazet.
10) Support 5-tuple hashing in ipv6 multipath routing, from David Ahern.
11) Add path MTU tests to selftests, from Stefano Brivio.
12) Various bits of IPSEC offloading support for mlx5, from Aviad
Yehezkel, Yossi Kuperman, and Saeed Mahameed.
13) Support RSS spreading on ntuple filters in SFC driver, from Edward
Cree.
14) Lots of sockmap work from John Fastabend. Applications can use eBPF
to filter sendmsg and sendpage operations.
15) In-kernel receive TLS support, from Dave Watson.
16) Add XDP support to ixgbevf, this is significant because it should
allow optimized XDP usage in various cloud environments. From Tony
Nguyen.
17) Add new Intel E800 series "ice" ethernet driver, from Anirudh
Venkataramanan et al.
18) IP fragmentation match offload support in nfp driver, from Pieter
Jansen van Vuuren.
19) Support XDP redirect in i40e driver, from Björn Töpel.
20) Add BPF_RAW_TRACEPOINT program type for accessing the arguments of
tracepoints in their raw form, from Alexei Starovoitov.
21) Lots of striding RQ improvements to mlx5 driver with many
performance improvements, from Tariq Toukan.
22) Use rhashtable for inet frag reassembly, from Eric Dumazet.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1678 commits)
net: mvneta: improve suspend/resume
net: mvneta: split rxq/txq init and txq deinit into SW and HW parts
ipv6: frags: fix /proc/sys/net/ipv6/ip6frag_low_thresh
net: bgmac: Fix endian access in bgmac_dma_tx_ring_free()
net: bgmac: Correctly annotate register space
route: check sysctl_fib_multipath_use_neigh earlier than hash
fix typo in command value in drivers/net/phy/mdio-bitbang.
sky2: Increase D3 delay to sky2 stops working after suspend
net/mlx5e: Set EQE based as default TX interrupt moderation mode
ibmvnic: Disable irqs before exiting reset from closed state
net: sched: do not emit messages while holding spinlock
vlan: also check phy_driver ts_info for vlan's real device
Bluetooth: Mark expected switch fall-throughs
Bluetooth: Set HCI_QUIRK_SIMULTANEOUS_DISCOVERY for BTUSB_QCA_ROME
Bluetooth: btrsi: remove unused including <linux/version.h>
Bluetooth: hci_bcm: Remove DMI quirk for the MINIX Z83-4
sh_eth: kill useless check in __sh_eth_get_regs()
sh_eth: add sh_eth_cpu_data::no_xdfar flag
ipv6: factorize sk_wmem_alloc updates done by __ip6_append_data()
ipv4: factorize sk_wmem_alloc updates done by __ip_append_data()
...
Minor conflicts in drivers/net/ethernet/mellanox/mlx5/core/en_rep.c,
we had some overlapping changes:
1) In 'net' MLX5E_PARAMS_LOG_{SQ,RQ}_SIZE -->
MLX5E_REP_PARAMS_LOG_{SQ,RQ}_SIZE
2) In 'net-next' params->log_rq_size is renamed to be
params->log_rq_mtu_frames.
3) In 'net-next' params->hard_mtu is added.
Signed-off-by: David S. Miller <davem@davemloft.net>
== The problem ==
There are use-cases when a program of some type can be attached to
multiple attach points and those attach points must have different
permissions to access context or to call helpers.
E.g. context structure may have fields for both IPv4 and IPv6 but it
doesn't make sense to read from / write to IPv6 field when attach point
is somewhere in IPv4 stack.
Same applies to BPF-helpers: it may make sense to call some helper from
some attach point, but not from other for same prog type.
== The solution ==
Introduce `expected_attach_type` field in in `struct bpf_attr` for
`BPF_PROG_LOAD` command. If scenario described in "The problem" section
is the case for some prog type, the field will be checked twice:
1) At load time prog type is checked to see if attach type for it must
be known to validate program permissions correctly. Prog will be
rejected with EINVAL if it's the case and `expected_attach_type` is
not specified or has invalid value.
2) At attach time `attach_type` is compared with `expected_attach_type`,
if prog type requires to have one, and, if they differ, attach will
be rejected with EINVAL.
The `expected_attach_type` is now available as part of `struct bpf_prog`
in both `bpf_verifier_ops->is_valid_access()` and
`bpf_verifier_ops->get_func_proto()` () and can be used to check context
accesses and calls to helpers correspondingly.
Initially the idea was discussed by Alexei Starovoitov <ast@fb.com> and
Daniel Borkmann <daniel@iogearbox.net> here:
https://marc.info/?l=linux-netdev&m=152107378717201&w=2
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Introduce BPF_PROG_TYPE_RAW_TRACEPOINT bpf program type to access
kernel internal arguments of the tracepoints in their raw form.
>From bpf program point of view the access to the arguments look like:
struct bpf_raw_tracepoint_args {
__u64 args[0];
};
int bpf_prog(struct bpf_raw_tracepoint_args *ctx)
{
// program can read args[N] where N depends on tracepoint
// and statically verified at program load+attach time
}
kprobe+bpf infrastructure allows programs access function arguments.
This feature allows programs access raw tracepoint arguments.
Similar to proposed 'dynamic ftrace events' there are no abi guarantees
to what the tracepoints arguments are and what their meaning is.
The program needs to type cast args properly and use bpf_probe_read()
helper to access struct fields when argument is a pointer.
For every tracepoint __bpf_trace_##call function is prepared.
In assembler it looks like:
(gdb) disassemble __bpf_trace_xdp_exception
Dump of assembler code for function __bpf_trace_xdp_exception:
0xffffffff81132080 <+0>: mov %ecx,%ecx
0xffffffff81132082 <+2>: jmpq 0xffffffff811231f0 <bpf_trace_run3>
where
TRACE_EVENT(xdp_exception,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp, u32 act),
The above assembler snippet is casting 32-bit 'act' field into 'u64'
to pass into bpf_trace_run3(), while 'dev' and 'xdp' args are passed as-is.
All of ~500 of __bpf_trace_*() functions are only 5-10 byte long
and in total this approach adds 7k bytes to .text.
This approach gives the lowest possible overhead
while calling trace_xdp_exception() from kernel C code and
transitioning into bpf land.
Since tracepoint+bpf are used at speeds of 1M+ events per second
this is valuable optimization.
The new BPF_RAW_TRACEPOINT_OPEN sys_bpf command is introduced
that returns anon_inode FD of 'bpf-raw-tracepoint' object.
The user space looks like:
// load bpf prog with BPF_PROG_TYPE_RAW_TRACEPOINT type
prog_fd = bpf_prog_load(...);
// receive anon_inode fd for given bpf_raw_tracepoint with prog attached
raw_tp_fd = bpf_raw_tracepoint_open("xdp_exception", prog_fd);
Ctrl-C of tracing daemon or cmdline tool that uses this feature
will automatically detach bpf program, unload it and
unregister tracepoint probe.
On the kernel side the __bpf_raw_tp_map section of pointers to
tracepoint definition and to __bpf_trace_*() probe function is used
to find a tracepoint with "xdp_exception" name and
corresponding __bpf_trace_xdp_exception() probe function
which are passed to tracepoint_probe_register() to connect probe
with tracepoint.
Addition of bpf_raw_tracepoint doesn't interfere with ftrace and perf
tracepoint mechanisms. perf_event_open() can be used in parallel
on the same tracepoint.
Multiple bpf_raw_tracepoint_open("xdp_exception", prog_fd) are permitted.
Each with its own bpf program. The kernel will execute
all tracepoint probes and all attached bpf programs.
In the future bpf_raw_tracepoints can be extended with
query/introspection logic.
__bpf_raw_tp_map section logic was contributed by Steven Rostedt
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Pull kprobe fixes from Steven Rostedt:
"The documentation for kprobe events says that symbol offets can take
both a + and - sign to get to befor and after the symbol address.
But in actuality, the code does not support the minus. This fixes that
issue, and adds a few more selftests to kprobe events"
* tag 'trace-v4.16-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
selftests: ftrace: Add a testcase for probepoint
selftests: ftrace: Add a testcase for string type with kprobe_event
selftests: ftrace: Add probe event argument syntax testcase
tracing: probeevent: Fix to support minus offset from symbol
Linus Torvalds
Steven Rostedt (VMware)
Chris Wilson
Dan Carpenter
Tom Zanussi
Salvatore Mesoraca
David S. Miller
Andrey Ignatov
Ingo Molnar
Alexei Starovoitov
Rohit Visavalia
Joe Perches