09 Mar, 2016
7 commits
-
performance tests for hash map and per-cpu hash map
with and without pre-allocationSigned-off-by: Alexei Starovoitov
Signed-off-by: David S. Miller -
increase stress by also calling bpf_get_stackid() from
various *spin* functionsSigned-off-by: Alexei Starovoitov
Signed-off-by: David S. Miller -
this test calls bpf programs from different contexts:
from inside of slub, from rcu, from pretty much everywhere,
since it kprobes all spin_lock functions.
It stresses the bpf hash and percpu map pre-allocation,
deallocation logic and call_rcu mechanisms.
User space part adding more stress by walking and deleting map elements.Note that due to nature bpf_load.c the earlier kprobe+bpf programs are
already active while loader loads new programs, creates new kprobes and
attaches them.Signed-off-by: Alexei Starovoitov
Signed-off-by: David S. Miller -
extend test coveraged to include pre-allocated and run-time alloc maps
Signed-off-by: Alexei Starovoitov
Signed-off-by: David S. Miller -
note old loader is compatible with new kernel.
map_flags are optionalSigned-off-by: Alexei Starovoitov
Signed-off-by: David S. Miller -
move ksym search from offwaketime into library to be reused
in other testsSigned-off-by: Alexei Starovoitov
Signed-off-by: David S. Miller -
map creation is typically the first one to fail when rlimits are
too low, not enough memory, etc
Make this failure scenario more verboseSigned-off-by: Alexei Starovoitov
Signed-off-by: David S. Miller
20 Feb, 2016
1 commit
-
This is simplified version of Brendan Gregg's offwaketime:
This program shows kernel stack traces and task names that were blocked and
"off-CPU", along with the stack traces and task names for the threads that woke
them, and the total elapsed time from when they blocked to when they were woken
up. The combined stacks, task names, and total time is summarized in kernel
context for efficiency.Example:
$ sudo ./offwaketime | flamegraph.pl > demo.svg
Open demo.svg in the browser as FlameGraph visualization.Signed-off-by: Alexei Starovoitov
Signed-off-by: David S. Miller
06 Feb, 2016
3 commits
-
Signed-off-by: Alexei Starovoitov
Signed-off-by: David S. Miller -
A sanity test for BPF_MAP_TYPE_PERCPU_ARRAY
Signed-off-by: Ming Lei
Signed-off-by: Alexei Starovoitov
Signed-off-by: David S. Miller -
A sanity test for BPF_MAP_TYPE_PERCPU_HASH.
Signed-off-by: Martin KaFai Lau
Signed-off-by: Alexei Starovoitov
Signed-off-by: David S. Miller
18 Nov, 2015
1 commit
-
Pull networking fixes from David Miller:
1) Fix list tests in netfilter ingress support, from Florian Westphal.
2) Fix reversal of input and output interfaces in ingress hook
invocation, from Pablo Neira Ayuso.3) We have a use after free in r8169, caught by Dave Jones, fixed by
Francois Romieu.4) Splice use-after-free fix in AF_UNIX frmo Hannes Frederic Sowa.
5) Three ipv6 route handling bug fixes from Martin KaFai Lau:
a) Don't create clone routes not managed by the fib6 tree
b) Don't forget to check expiration of DST_NOCACHE routes.
c) Handle rt->dst.from == NULL properly.6) Several AF_PACKET fixes wrt transport header setting and SKB
protocol setting, from Daniel Borkmann.7) Fix thunder driver crash on shutdown, from Pavel Fedin.
8) Several Mellanox driver fixes (max MTU calculations, use of correct
DMA unmap in TX path, etc.) from Saeed Mahameed, Tariq Toukan, Doron
Tsur, Achiad Shochat, Eran Ben Elisha, and Noa Osherovich.9) Several mv88e6060 DSA driver fixes (wrong bit definitions for
certain registers, etc.) from Neil Armstrong.10) Make sure to disable preemption while updating per-cpu stats of ip
tunnels, from Jason A. Donenfeld.11) Various ARM64 bpf JIT fixes, from Yang Shi.
12) Flush icache properly in ARM JITs, from Daniel Borkmann.
13) Fix masking of RX and TX interrupts in ravb driver, from Masaru
Nagai.14) Fix netdev feature propagation for devices not implementing
->ndo_set_features(). From Nikolay Aleksandrov.15) Big endian fix in vmxnet3 driver, from Shrikrishna Khare.
16) RAW socket code increments incorrect SNMP counters, fix from Ben
Cartwright-Cox.17) IPv6 multicast SNMP counters are bumped twice, fix from Neil Horman.
18) Fix handling of VLAN headers on stacked devices when REORDER is
disabled. From Vlad Yasevich.19) Fix SKB leaks and use-after-free in ipvlan and macvlan drivers, from
Sabrina Dubroca.* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (83 commits)
MAINTAINERS: Update Mellanox's Eth NIC driver entries
net/core: revert "net: fix __netdev_update_features return.." and add comment
af_unix: take receive queue lock while appending new skb
rtnetlink: fix frame size warning in rtnl_fill_ifinfo
net: use skb_clone to avoid alloc_pages failure.
packet: Use PAGE_ALIGNED macro
packet: Don't check frames_per_block against negative values
net: phy: Use interrupts when available in NOLINK state
phy: marvell: Add support for 88E1540 PHY
arm64: bpf: make BPF prologue and epilogue align with ARM64 AAPCS
macvlan: fix leak in macvlan_handle_frame
ipvlan: fix use after free of skb
ipvlan: fix leak in ipvlan_rcv_frame
vlan: Do not put vlan headers back on bridge and macvlan ports
vlan: Fix untag operations of stacked vlans with REORDER_HEADER off
via-velocity: unconditionally drop frames with bad l2 length
ipg: Remove ipg driver
dl2k: Add support for IP1000A-based cards
snmp: Remove duplicate OUTMCAST stat increment
net: thunder: Check for driver data in nicvf_remove()
...
17 Nov, 2015
1 commit
-
commit 338d4f49d6f7114a017d294ccf7374df4f998edc
("arm64: kernel: Add support for Privileged Access Never") includes sysreg.h
into futex.h and uaccess.h. But, the inline assembly used by asm/sysreg.h is
incompatible with llvm so it will cause BPF samples build failure for ARM64.
Since sysreg.h is useless for BPF samples, just exclude it from Makefile via
defining __ASM_SYSREG_H.Signed-off-by: Yang Shi
Acked-by: Alexei Starovoitov
Signed-off-by: David S. Miller
14 Nov, 2015
1 commit
-
Pull SCSI target updates from Nicholas Bellinger:
"This series contains HCH's changes to absorb configfs attribute
->show() + ->store() function pointer usage from it's original
tree-wide consumers, into common configfs code.It includes usb-gadget, target w/ drivers, netconsole and ocfs2
changes to realize the improved simplicity, that now renders the
original include/target/configfs_macros.h CPP magic for fabric drivers
and others, unnecessary and obsolete.And with common code in place, new configfs attributes can be added
easier than ever before.Note, there are further improvements in-flight from other folks for
v4.5 code in configfs land, plus number of target fixes for post -rc1
code"In the meantime, a new user of the now-removed old configfs API came in
through the char/misc tree in commit 7bd1d4093c2f ("stm class: Introduce
an abstraction for System Trace Module devices").This merge resolution comes from Alexander Shishkin, who updated his stm
class tracing abstraction to account for the removal of the old
show_attribute and store_attribute methods in commit 517982229f78
("configfs: remove old API") from this pull. As Alexander says about
that patch:"There's no need to keep an extra wrapper structure per item and the
awkward show_attribute/store_attribute item ops are no longer needed.This patch converts policy code to the new api, all the while making
the code quite a bit smaller and easier on the eyes.Signed-off-by: Alexander Shishkin "
That patch was folded into the merge so that the tree should be fully
bisectable.* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending: (23 commits)
configfs: remove old API
ocfs2/cluster: use per-attribute show and store methods
ocfs2/cluster: move locking into attribute store methods
netconsole: use per-attribute show and store methods
target: use per-attribute show and store methods
spear13xx_pcie_gadget: use per-attribute show and store methods
dlm: use per-attribute show and store methods
usb-gadget/f_serial: use per-attribute show and store methods
usb-gadget/f_phonet: use per-attribute show and store methods
usb-gadget/f_obex: use per-attribute show and store methods
usb-gadget/f_uac2: use per-attribute show and store methods
usb-gadget/f_uac1: use per-attribute show and store methods
usb-gadget/f_mass_storage: use per-attribute show and store methods
usb-gadget/f_sourcesink: use per-attribute show and store methods
usb-gadget/f_printer: use per-attribute show and store methods
usb-gadget/f_midi: use per-attribute show and store methods
usb-gadget/f_loopback: use per-attribute show and store methods
usb-gadget/ether: use per-attribute show and store methods
usb-gadget/f_acm: use per-attribute show and store methods
usb-gadget/f_hid: use per-attribute show and store methods
...
07 Nov, 2015
1 commit
-
Pull tracking updates from Steven Rostedt:
"Most of the changes are clean ups and small fixes. Some of them have
stable tags to them. I searched through my INBOX just as the merge
window opened and found lots of patches to pull. I ran them through
all my tests and they were in linux-next for a few days.Features added this release:
----------------------------- Module globbing. You can now filter function tracing to several
modules. # echo '*:mod:*snd*' > set_ftrace_filter (Dmitry Safonov)- Tracer specific options are now visible even when the tracer is not
active. It was rather annoying that you can only see and modify
tracer options after enabling the tracer. Now they are in the
options/ directory even when the tracer is not active. Although
they are still only visible when the tracer is active in the
trace_options file.- Trace options are now per instance (although some of the tracer
specific options are global)- New tracefs file: set_event_pid. If any pid is added to this file,
then all events in the instance will filter out events that are not
part of this pid. sched_switch and sched_wakeup events handle next
and the wakee pids"* tag 'trace-v4.4' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (68 commits)
tracefs: Fix refcount imbalance in start_creating()
tracing: Put back comma for empty fields in boot string parsing
tracing: Apply tracer specific options from kernel command line.
tracing: Add some documentation about set_event_pid
ring_buffer: Remove unneeded smp_wmb() before wakeup of reader benchmark
tracing: Allow dumping traces without tracking trace started cpus
ring_buffer: Fix more races when terminating the producer in the benchmark
ring_buffer: Do no not complete benchmark reader too early
tracing: Remove redundant TP_ARGS redefining
tracing: Rename max_stack_lock to stack_trace_max_lock
tracing: Allow arch-specific stack tracer
recordmcount: arm64: Replace the ignored mcount call into nop
recordmcount: Fix endianness handling bug for nop_mcount
tracepoints: Fix documentation of RCU lockdep checks
tracing: ftrace_event_is_function() can return boolean
tracing: is_legal_op() can return boolean
ring-buffer: rb_event_is_commit() can return boolean
ring-buffer: rb_per_cpu_empty() can return boolean
ring_buffer: ring_buffer_empty{cpu}() can return boolean
ring-buffer: rb_is_reader_page() can return boolean
...
03 Nov, 2015
2 commits
-
This patch adds a couple of stand-alone examples on how BPF_OBJ_PIN
and BPF_OBJ_GET commands can be used.Example with maps:
# ./fds_example -F /sys/fs/bpf/m -P -m -k 1 -v 42
bpf: map fd:3 (Success)
bpf: pin ret:(0,Success)
bpf: fd:3 u->(1:42) ret:(0,Success)
# ./fds_example -F /sys/fs/bpf/m -G -m -k 1
bpf: get fd:3 (Success)
bpf: fd:3 l->(1):42 ret:(0,Success)
# ./fds_example -F /sys/fs/bpf/m -G -m -k 1 -v 24
bpf: get fd:3 (Success)
bpf: fd:3 u->(1:24) ret:(0,Success)
# ./fds_example -F /sys/fs/bpf/m -G -m -k 1
bpf: get fd:3 (Success)
bpf: fd:3 l->(1):24 ret:(0,Success)# ./fds_example -F /sys/fs/bpf/m2 -P -m
bpf: map fd:3 (Success)
bpf: pin ret:(0,Success)
# ./fds_example -F /sys/fs/bpf/m2 -G -m -k 1
bpf: get fd:3 (Success)
bpf: fd:3 l->(1):0 ret:(0,Success)
# ./fds_example -F /sys/fs/bpf/m2 -G -m
bpf: get fd:3 (Success)Example with progs:
# ./fds_example -F /sys/fs/bpf/p -P -p
bpf: prog fd:3 (Success)
bpf: pin ret:(0,Success)
bpf sock:4
Acked-by: Alexei Starovoitov
Signed-off-by: David S. Miller -
The commit 889204278ccf ("tracing: Update trace-event-sample with
TRACE_SYSTEM_VAR documentation") changed TRACE_SYSTEM to 'sample-trace',
but didn't make the according change of its name in the comments.Link: http://lkml.kernel.org/r/1443599650-23680-1-git-send-email-zhang.chunyan@linaro.org
Signed-off-by: Chunyan Zhang
Signed-off-by: Steven Rostedt
01 Nov, 2015
1 commit
28 Oct, 2015
1 commit
-
Define aarch64 specific registers for building bpf samples correctly.
Signed-off-by: Yang Shi
Acked-by: Alexei Starovoitov
Signed-off-by: David S. Miller
22 Oct, 2015
1 commit
-
Performance test and example of bpf_perf_event_output().
kprobe is attached to sys_write() and trivial bpf program streams
pid+cookie into userspace via PERF_COUNT_SW_BPF_OUTPUT event.Usage:
$ sudo ./bld_x64/samples/bpf/trace_output
recv 2968913 events per secSigned-off-by: Alexei Starovoitov
Signed-off-by: David S. Miller
14 Oct, 2015
1 commit
-
Remove the old show_attribute and store_attribute methods and update
the documentation. Also replace the two C samples with a single new
one in the proper samples directory where people expect to find it.Signed-off-by: Christoph Hellwig
Signed-off-by: Nicholas Bellinger
13 Oct, 2015
1 commit
-
Add new tests samples/bpf/test_verifier:
unpriv: return pointer
checks that pointer cannot be returned from the eBPF programunpriv: add const to pointer
unpriv: add pointer to pointer
unpriv: neg pointer
checks that pointer arithmetic is disallowedunpriv: cmp pointer with const
unpriv: cmp pointer with pointer
checks that comparison of pointers is disallowed
Only one case allowed 'void *value = bpf_map_lookup_elem(..); if (value == 0) ...'unpriv: check that printk is disallowed
since bpf_trace_printk is not available to unprivilegedunpriv: pass pointer to helper function
checks that pointers cannot be passed to functions that expect integers
If function expects a pointer the verifier allows only that type of pointer.
Like 1st argument of bpf_map_lookup_elem() must be pointer to map.
(applies to non-root as well)unpriv: indirectly pass pointer on stack to helper function
checks that pointer stored into stack cannot be used as part of key
passed into bpf_map_lookup_elem()unpriv: mangle pointer on stack 1
unpriv: mangle pointer on stack 2
checks that writing into stack slot that already contains a pointer
is disallowedunpriv: read pointer from stack in small chunks
checks that < 8 byte read from stack slot that contains a pointer is
disallowedunpriv: write pointer into ctx
checks that storing pointers into skb->fields is disallowedunpriv: write pointer into map elem value
checks that storing pointers into element values is disallowed
For example:
int bpf_prog(struct __sk_buff *skb)
{
u32 key = 0;
u64 *value = bpf_map_lookup_elem(&map, &key);
if (value)
*value = (u64) skb;
}
will be rejected.unpriv: partial copy of pointer
checks that doing 32-bit register mov from register containing
a pointer is disallowedunpriv: pass pointer to tail_call
checks that passing pointer as an index into bpf_tail_call
is disallowedunpriv: cmp map pointer with zero
checks that comparing map pointer with constant is disallowedunpriv: write into frame pointer
checks that frame pointer is read-only (applies to root too)unpriv: cmp of frame pointer
checks that R10 cannot be using in comparisonunpriv: cmp of stack pointer
checks that Rx = R10 - imm is ok, but comparing Rx is notunpriv: obfuscate stack pointer
checks that Rx = R10 - imm is ok, but Rx -= imm is notSigned-off-by: Alexei Starovoitov
Signed-off-by: David S. Miller
02 Oct, 2015
2 commits
-
Conflicts:
net/dsa/slave.cnet/dsa/slave.c simply had overlapping changes.
Signed-off-by: David S. Miller
-
Commit 3033f14ab78c ("clone: support passing tls argument via C rather
than pt_regs magic") introduced _do_fork() that allowed to pass @tls
parameter.The old do_fork() is defined only for architectures that are not ready
to use this way and do not define HAVE_COPY_THREAD_TLS.Let's use _do_fork() in the kprobe examples to make them work again on
all architectures.Signed-off-by: Petr Mladek
Cc: Ingo Molnar
Cc: Masami Hiramatsu
Cc: Andy Lutomirski
Cc: Peter Zijlstra
Cc: "H. Peter Anvin"
Cc: Thomas Gleixner
Cc: Thiago Macieira
Cc: Jiri Kosina
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
18 Sep, 2015
1 commit
-
Existing bpf_clone_redirect() helper clones skb before redirecting
it to RX or TX of destination netdev.
Introduce bpf_redirect() helper that does that without cloning.Benchmarked with two hosts using 10G ixgbe NICs.
One host is doing line rate pktgen.
Another host is configured as:
$ tc qdisc add dev $dev ingress
$ tc filter add dev $dev root pref 10 u32 match u32 0 0 flowid 1:2 \
action bpf run object-file tcbpf1_kern.o section clone_redirect_xmit drop
so it receives the packet on $dev and immediately xmits it on $dev + 1
The section 'clone_redirect_xmit' in tcbpf1_kern.o file has the program
that does bpf_clone_redirect() and performance is 2.0 Mpps$ tc filter add dev $dev root pref 10 u32 match u32 0 0 flowid 1:2 \
action bpf run object-file tcbpf1_kern.o section redirect_xmit drop
which is using bpf_redirect() - 2.4 Mppsand using cls_bpf with integrated actions as:
$ tc filter add dev $dev root pref 10 \
bpf run object-file tcbpf1_kern.o section redirect_xmit integ_act classid 1
performance is 2.5 MppsTo summarize:
u32+act_bpf using clone_redirect - 2.0 Mpps
u32+act_bpf using redirect - 2.4 Mpps
cls_bpf using redirect - 2.5 MppsFor comparison linux bridge in this setup is doing 2.1 Mpps
and ixgbe rx + drop in ip_rcv - 7.8 MppsSigned-off-by: Alexei Starovoitov
Acked-by: Daniel Borkmann
Acked-by: John Fastabend
Signed-off-by: David S. Miller
13 Aug, 2015
1 commit
-
There are two improvements in this patch:
1. Fix the build warnings;
2. Add function read_trace_pipe() to print the result on
the screen;Before this patch, we can get the result through /sys/kernel/de
bug/tracing/trace_pipe and get nothing on the screen.
By applying this patch, the result can be printed on the screen.
$ ./tracex6
...
tracex6-705 [003] d..1 131.428593: : CPU-3 19981414
sshd-683 [000] d..1 131.428727: : CPU-0 221682321
sshd-683 [000] d..1 131.428821: : CPU-0 221808766
sshd-683 [000] d..1 131.428950: : CPU-0 221982984
sshd-683 [000] d..1 131.429045: : CPU-0 222111851
tracex6-705 [003] d..1 131.429168: : CPU-3 20757551
sshd-683 [000] d..1 131.429170: : CPU-0 222281240
sshd-683 [000] d..1 131.429261: : CPU-0 222403340
sshd-683 [000] d..1 131.429378: : CPU-0 222561024
...Signed-off-by: Kaixu Xia
Acked-by: Alexei Starovoitov
Signed-off-by: David S. Miller
10 Aug, 2015
1 commit
-
This is a simple example and shows how to use the new ability
to get the selected Hardware PMU counter value.Signed-off-by: Kaixu Xia
Signed-off-by: David S. Miller
27 Jul, 2015
1 commit
-
mov %rsp, %r1 ; r1 = rsp
add $-8, %r1 ; r1 = rsp - 8
store_q $123, -8(%rsp) ; *(u64*)r1 = 123
Acked-by: Alexei Starovoitov
Signed-off-by: David S. Miller
23 Jul, 2015
1 commit
-
Conflicts:
net/bridge/br_mdb.cbr_mdb.c conflict was a function call being removed to fix a bug in
'net' but whose signature was changed in 'net-next'.Signed-off-by: David S. Miller
18 Jul, 2015
1 commit
-
He Kuang noticed that the trace event samples for arrays was broken:
"The output result of trace_foo_bar event in traceevent samples is
wrong. This problem can be reproduced as following:(Build kernel with SAMPLE_TRACE_EVENTS=m)
$ insmod trace-events-sample.ko
$ echo 1 > /sys/kernel/debug/tracing/events/sample-trace/foo_bar/enable
$ cat /sys/kernel/debug/tracing/trace
event-sample-980 [000] .... 43.649559: foo_bar: foo hello 21 0x15
BIT1|BIT3|0x10 {0x1,0x6f6f6e53,0xff007970,0xffffffff} Snoopy
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
The array length is not right, should be {0x1}.
(ffffffff,ffffffff)event-sample-980 [000] .... 44.653827: foo_bar: foo hello 22 0x16
BIT2|BIT3|0x10
{0x1,0x2,0x646e6147,0x666c61,0xffffffff,0xffffffff,0x750aeffe,0x7}
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
The array length is not right, should be {0x1,0x2}.
Gandalf (ffffffff,ffffffff)"This was caused by an update to have __print_array()'s second parameter
be the count of items in the array and not the size of the array.As there is already users of __print_array(), it can not change. But
the sample code can and we can also improve on the documentation about
__print_array() and __get_dynamic_array_len().Link: http://lkml.kernel.org/r/1436839171-31527-2-git-send-email-hekuang@huawei.com
Fixes: ac01ce1410fc2 ("tracing: Make ftrace_print_array_seq compute buf_len")
Reported-by: He Kuang
Signed-off-by: Steven Rostedt
09 Jul, 2015
1 commit
-
The trace bpf samples do not compile on s390x because they use x86
specific fields from the "pt_regs" structure.Fix this and access the fields via new PT_REGS macros.
Signed-off-by: Michael Holzheu
Acked-by: Alexei Starovoitov
Signed-off-by: David S. Miller
23 Jun, 2015
1 commit
-
BPF offers another way to generate latency histograms. We attach
kprobes at trace_preempt_off and trace_preempt_on and calculate the
time it takes to from seeing the off/on transition.The first array is used to store the start time stamp. The key is the
CPU id. The second array stores the log2(time diff). We need to use
static allocation here (array and not hash tables). The kprobes
hooking into trace_preempt_on|off should not calling any dynamic
memory allocation or free path. We need to avoid recursivly
getting called. Besides that, it reduces jitter in the measurement.CPU 0
latency : count distribution
1 -> 1 : 0 | |
2 -> 3 : 0 | |
4 -> 7 : 0 | |
8 -> 15 : 0 | |
16 -> 31 : 0 | |
32 -> 63 : 0 | |
64 -> 127 : 0 | |
128 -> 255 : 0 | |
256 -> 511 : 0 | |
512 -> 1023 : 0 | |
1024 -> 2047 : 0 | |
2048 -> 4095 : 166723 |*************************************** |
4096 -> 8191 : 19870 |*** |
8192 -> 16383 : 6324 | |
16384 -> 32767 : 1098 | |
32768 -> 65535 : 190 | |
65536 -> 131071 : 179 | |
131072 -> 262143 : 18 | |
262144 -> 524287 : 4 | |
524288 -> 1048575 : 1363 | |
CPU 1
latency : count distribution
1 -> 1 : 0 | |
2 -> 3 : 0 | |
4 -> 7 : 0 | |
8 -> 15 : 0 | |
16 -> 31 : 0 | |
32 -> 63 : 0 | |
64 -> 127 : 0 | |
128 -> 255 : 0 | |
256 -> 511 : 0 | |
512 -> 1023 : 0 | |
1024 -> 2047 : 0 | |
2048 -> 4095 : 114042 |*************************************** |
4096 -> 8191 : 9587 |** |
8192 -> 16383 : 4140 | |
16384 -> 32767 : 673 | |
32768 -> 65535 : 179 | |
65536 -> 131071 : 29 | |
131072 -> 262143 : 4 | |
262144 -> 524287 : 1 | |
524288 -> 1048575 : 364 | |
CPU 2
latency : count distribution
1 -> 1 : 0 | |
2 -> 3 : 0 | |
4 -> 7 : 0 | |
8 -> 15 : 0 | |
16 -> 31 : 0 | |
32 -> 63 : 0 | |
64 -> 127 : 0 | |
128 -> 255 : 0 | |
256 -> 511 : 0 | |
512 -> 1023 : 0 | |
1024 -> 2047 : 0 | |
2048 -> 4095 : 40147 |*************************************** |
4096 -> 8191 : 2300 |* |
8192 -> 16383 : 828 | |
16384 -> 32767 : 178 | |
32768 -> 65535 : 59 | |
65536 -> 131071 : 2 | |
131072 -> 262143 : 0 | |
262144 -> 524287 : 1 | |
524288 -> 1048575 : 174 | |
CPU 3
latency : count distribution
1 -> 1 : 0 | |
2 -> 3 : 0 | |
4 -> 7 : 0 | |
8 -> 15 : 0 | |
16 -> 31 : 0 | |
32 -> 63 : 0 | |
64 -> 127 : 0 | |
128 -> 255 : 0 | |
256 -> 511 : 0 | |
512 -> 1023 : 0 | |
1024 -> 2047 : 0 | |
2048 -> 4095 : 29626 |*************************************** |
4096 -> 8191 : 2704 |** |
8192 -> 16383 : 1090 | |
16384 -> 32767 : 160 | |
32768 -> 65535 : 72 | |
65536 -> 131071 : 32 | |
131072 -> 262143 : 26 | |
262144 -> 524287 : 12 | |
524288 -> 1048575 : 298 | |All this is based on the trace3 examples written by
Alexei Starovoitov .Signed-off-by: Daniel Wagner
Cc: Alexei Starovoitov
Cc: Alexei Starovoitov
Cc: "David S. Miller"
Cc: Daniel Borkmann
Cc: Ingo Molnar
Cc: linux-kernel@vger.kernel.org
Cc: netdev@vger.kernel.org
Acked-by: Alexei Starovoitov
Acked-by: Daniel Borkmann
Signed-off-by: David S. Miller
16 Jun, 2015
1 commit
-
eBPF programs attached to kprobes need to filter based on
current->pid, uid and other fields, so introduce helper functions:u64 bpf_get_current_pid_tgid(void)
Return: current->tgid << 32 | current->pidu64 bpf_get_current_uid_gid(void)
Return: current_gid << 32 | current_uidbpf_get_current_comm(char *buf, int size_of_buf)
stores current->comm into bufThey can be used from the programs attached to TC as well to classify packets
based on current task fields.Update tracex2 example to print histogram of write syscalls for each process
instead of aggregated for all.Signed-off-by: Alexei Starovoitov
Signed-off-by: David S. Miller
07 Jun, 2015
2 commits
-
allow programs read/write skb->mark, tc_index fields and
((struct qdisc_skb_cb *)cb)->data.mark and tc_index are generically useful in TC.
cb[0]-cb[4] are primarily used to pass arguments from one
program to another called via bpf_tail_call() which can
be seen in sockex3_kern.c example.All fields of 'struct __sk_buff' are readable to socket and tc_cls_act progs.
mark, tc_index are writeable from tc_cls_act only.
cb[0]-cb[4] are writeable by both sockets and tc_cls_act.Add verifier tests and improve sample code.
Signed-off-by: Alexei Starovoitov
Signed-off-by: David S. Miller -
eBPF programs attached to ingress and egress qdiscs see inconsistent skb->data.
For ingress L2 header is already pulled, whereas for egress it's present.
This is known to program writers which are currently forced to use
BPF_LL_OFF workaround.
Since programs don't change skb internal pointers it is safe to do
pull/push right around invocation of the program and earlier taps and
later pt->func() will not be affected.
Multiple taps via packet_rcv(), tpacket_rcv() are doing the same trick
around run_filter/BPF_PROG_RUN even if skb_shared.This fix finally allows programs to use optimized LD_ABS/IND instructions
without BPF_LL_OFF for higher performance.
tc ingress + cls_bpf + samples/bpf/tcbpf1_kern.o
w/o JIT w/JIT
before 20.5 23.6 Mpps
after 21.8 26.6 MppsOld programs with BPF_LL_OFF will still work as-is.
We can now undo most of the earlier workaround commit:
a166151cbe33 ("bpf: fix bpf helpers to use skb->mac_header relative offsets")Signed-off-by: Alexei Starovoitov
Acked-by: Jamal Hadi Salim
Signed-off-by: David S. Miller
23 May, 2015
5 commits
-
This script pktgen_bench_xmit_mode_netif_receive.sh is a benchmark
script, which can be used for benchmarking part of the network stack.
This can be used for performance improving or catching regression in
that area.The script is developed for benchmarking ingress qdisc path, original
idea by Alexei Starovoitov. This script don't really need any
hardware. This is achieved via the recently introduced stack inject
feature "xmit_mode netif_receive". See commit 62f64aed622b6 ("pktgen:
introduce xmit_mode ''").Signed-off-by: Jesper Dangaard Brouer
Signed-off-by: David S. Miller -
Add the pktgen samples script pktgen_sample03_burst_single_flow.sh
that demonstrates how to acheive maximum performance.If correctly tuned[1] single CPU 10Gbit/s wirespeed small pkts is
possible[2] which is 14.88Mpps. The trick is to take advantage of the
"burst" feature introduced in commit 38b2cf2982dc73 ("net: pktgen:
packet bursting via skb->xmit_more").[1] http://netoptimizer.blogspot.dk/2014/06/pktgen-for-network-overload-testing.html
[2] http://netoptimizer.blogspot.dk/2014/10/unlocked-10gbps-tx-wirespeed-smallest.htmlSigned-off-by: Jesper Dangaard Brouer
Signed-off-by: David S. Miller -
Add the pktgen samples script pktgen_sample02_multiqueue.sh that
demonstrates generating packets on multiqueue NICs.Specifically notice the options "-t" that specifies how many
kernel threads to activate. Also notice the flag QUEUE_MAP_CPU,
which cause the SKB TX queue to be mapped to the CPU running the
kernel thread. For best scalability people are also encourage to
map NIC IRQ /proc/irq/*/smp_affinity to CPU number.Usage example with "-t" 4 threads and help:
./pktgen_sample02_multiqueue.sh -i eth4 -m 00:1B:21:3C:9D:F8 -t 4Usage: ./pktgen_sample02_multiqueue.sh [-vx] -i ethX
-i : ($DEV) output interface/device (required)
-s : ($PKT_SIZE) packet size
-d : ($DEST_IP) destination IP
-m : ($DST_MAC) destination MAC-addr
-t : ($THREADS) threads to start
-c : ($SKB_CLONE) SKB clones send before alloc new SKB
-b : ($BURST) HW level bursting of SKBs
-v : ($VERBOSE) verbose
-x : ($DEBUG) debugRemoving pktgen.conf-2-1 and pktgen.conf-2-2 as these examples
should be covered now.Signed-off-by: Jesper Dangaard Brouer
Signed-off-by: David S. Miller -
Add the first basic pktgen samples script pktgen_sample01_simple.sh,
which demonstrates the a simple use of the helper functions.
Removing pktgen.conf-1-1 as that example should be covered now.The naming scheme pktgen_sampleNN, where NN is a number, should encourage
reading the samples in a specific order.Script cause pktgen sending with a single thread and single interface,
and introduce flow variation via random UDP source port.Usage example and help:
./pktgen_sample01_simple.sh -i eth4 -m 00:1B:21:3C:9D:F8 -d 192.168.8.2Usage: ./pktgen_sample01_simple.sh [-vx] -i ethX
-i : ($DEV) output interface/device (required)
-s : ($PKT_SIZE) packet size
-d : ($DEST_IP) destination IP
-m : ($DST_MAC) destination MAC-addr
-c : ($SKB_CLONE) SKB clones send before alloc new SKB
-v : ($VERBOSE) verbose
-x : ($DEBUG) debugSigned-off-by: Jesper Dangaard Brouer
Signed-off-by: David S. Miller -
Preparing for removing existing samples/pktgen/ scripts, and
replacing these with easier to use samples.This commit provides two helper shell files, that can
be "included" by shell source'ing. Namely "functions.sh"
and "parameters.sh".The parameters.sh file support easy and consistant parameter
parsing across the sample scripts. Usage example is printed on
errors.The functions.sh file provides, three new shell functions for
configuring the different components of pktgen: pg_ctrl(),
pg_thread() and pg_set(). A slightly improved version of the old
pgset() function is also provided for backwards compat.The new functions correspond to pktgens different components.
* pg_ctrl() control "pgctrl" (/proc/net/pktgen/pgctrl)
* pg_thread() control the kernel threads and binding to devices
* pg_set() control setup of individual devicesThese changes are borrowed from:
https://github.com/netoptimizer/network-testing/tree/master/pktgenSigned-off-by: Jesper Dangaard Brouer
Signed-off-by: David S. Miller
