linux/kernel/trace
Daniel Borkmann 555c8a8623 bpf: avoid stack copy and use skb ctx for event output
This work addresses a couple of issues bpf_skb_event_output()
helper currently has: i) We need two copies instead of just a
single one for the skb data when it should be part of a sample.
The data can be non-linear and thus needs to be extracted via
bpf_skb_load_bytes() helper first, and then copied once again
into the ring buffer slot. ii) Since bpf_skb_load_bytes()
currently needs to be used first, the helper needs to see a
constant size on the passed stack buffer to make sure BPF
verifier can do sanity checks on it during verification time.
Thus, just passing skb->len (or any other non-constant value)
wouldn't work, but changing bpf_skb_load_bytes() is also not
the proper solution, since the two copies are generally still
needed. iii) bpf_skb_load_bytes() is just for rather small
buffers like headers, since they need to sit on the limited
BPF stack anyway. Instead of working around in bpf_skb_load_bytes(),
this work improves the bpf_skb_event_output() helper to address
all 3 at once.

We can make use of the passed in skb context that we have in
the helper anyway, and use some of the reserved flag bits as
a length argument. The helper will use the new __output_custom()
facility from perf side with bpf_skb_copy() as callback helper
to walk and extract the data. It will pass the data for setup
to bpf_event_output(), which generates and pushes the raw record
with an additional frag part. The linear data used in the first
frag of the record serves as programmatically defined meta data
passed along with the appended sample.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-15 14:23:56 -07:00
..
blktrace.c blktrace: add missed mask name 2016-05-10 08:41:36 -06:00
bpf_trace.c bpf: avoid stack copy and use skb ctx for event output 2016-07-15 14:23:56 -07:00
ftrace.c Three more changes. 2016-05-22 19:40:39 -07:00
Kconfig tracing: Add 'hist' event trigger command 2016-04-19 12:16:14 -04:00
Makefile tracing: Add 'hist' event trigger command 2016-04-19 12:16:14 -04:00
power-traces.c cpufreq: schedutil: New governor based on scheduler utilization data 2016-04-02 01:09:12 +02:00
ring_buffer_benchmark.c ring_buffer: Remove unneeded smp_wmb() before wakeup of reader benchmark 2015-11-03 16:19:02 -05:00
ring_buffer.c ring-buffer: Prevent overflow of size in ring_buffer_resize() 2016-05-13 16:44:20 -04:00
rpm-traces.c
trace_benchmark.c tracing: Only benchmark the time tracepoints take if tracing is on 2015-11-02 13:34:58 -05:00
trace_benchmark.h tracing: Add tracepoint benchmark tracepoint 2014-05-29 22:49:54 -04:00
trace_branch.c tracing: Remove {start,stop}_branch_trace 2015-10-21 10:10:09 -04:00
trace_clock.c tracing: Export tracing clock functions 2015-05-12 15:56:57 -04:00
trace_entries.h tracing: %pF is only for function pointers 2015-03-25 08:57:22 -04:00
trace_event_perf.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next 2016-05-17 16:26:30 -07:00
trace_events_filter_test.h
trace_events_filter.c tracing: Use temp buffer when filtering events 2016-05-03 17:59:24 -04:00
trace_events_hist.c tracing: Add check for NULL event field when creating hist field 2016-04-26 09:40:29 -04:00
trace_events_trigger.c tracing: Add support for named triggers 2016-04-19 18:56:00 -04:00
trace_events.c This includes two new updates for the ftrace infrastructure. 2016-05-18 18:55:19 -07:00
trace_export.c tracing: ftrace_event_is_function() can return boolean 2015-11-02 14:28:05 -05:00
trace_functions_graph.c arch, ftrace: for KASAN put hard/soft IRQ entries into separate sections 2016-03-25 16:37:42 -07:00
trace_functions.c tracing: Make tracer_flags use the right set_flag callback 2016-03-08 11:19:08 -05:00
trace_irqsoff.c tracing: Remove redundant reset per-CPU buff in irqsoff tracer 2016-03-18 16:39:11 -04:00
trace_kdb.c tracing: Move trace_flags from global to a trace_array field 2015-09-30 15:22:55 -04:00
trace_kprobe.c perf: split perf_trace_buf_prepare into alloc and update parts 2016-04-07 21:04:26 -04:00
trace_mmiotrace.c kernel/...: convert pr_warning to pr_warn 2016-03-22 15:36:02 -07:00
trace_nop.c tracing: Fix typoes in code comment and printk in trace_nop.c 2016-03-08 11:23:57 -05:00
trace_output.c tracing: Record and show NMI state 2016-03-22 18:04:10 -04:00
trace_output.h tracing: Turn seq_print_user_ip() into a static function 2015-09-28 10:16:12 -04:00
trace_printk.c tracing: Handle NULL formats in hold_module_trace_bprintk_format() 2016-06-20 09:46:12 -04:00
trace_probe.c kernel/...: convert pr_warning to pr_warn 2016-03-22 15:36:02 -07:00
trace_probe.h kernel/trace_probe: is_good_name can be boolean 2015-09-22 13:11:30 -04:00
trace_sched_switch.c sched/core: Fix trace_sched_switch() 2015-10-06 17:08:15 +02:00
trace_sched_wakeup.c Most of the changes are clean ups and small fixes. Some of them have 2015-11-06 13:30:20 -08:00
trace_selftest_dynamic.c
trace_selftest.c Seems that Peter Zijlstra added a new check that is making old 2014-10-12 07:28:55 -04:00
trace_seq.c tracing: use %*pb[l] to print bitmaps including cpumasks and nodemasks 2015-02-13 21:21:37 -08:00
trace_stack.c tracing, kasan: Silence Kasan warning in check_stack of stack_tracer 2016-02-19 12:36:44 -05:00
trace_stat.c kernel/...: convert pr_warning to pr_warn 2016-03-22 15:36:02 -07:00
trace_stat.h
trace_syscalls.c perf: split perf_trace_buf_prepare into alloc and update parts 2016-04-07 21:04:26 -04:00
trace_uprobe.c perf: split perf_trace_buf_prepare into alloc and update parts 2016-04-07 21:04:26 -04:00
trace.c tracing: Use temp buffer when filtering events 2016-05-03 17:59:24 -04:00
trace.h tracing: Use temp buffer when filtering events 2016-05-03 17:59:24 -04:00
tracing_map.c tracing: Handle tracing_map_alloc_elts() error path correctly 2016-04-26 09:40:30 -04:00
tracing_map.h tracing: Update some tracing_map constants and comments 2016-04-19 12:16:06 -04:00