korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2025-01-26 15:54:18 +08:00
Code Issues Packages Projects Releases Wiki Activity
1,153,849 Commits 116 Branches 5,373 Tags 4.7 GiB
6012b82020
Commit Graph

22 Commits

Author SHA1 Message Date
Andrii Nakryiko
eb6af4ceda selftests/bpf: fix veristat's singular file-or-prog filter 
Fix the bug of filtering out filename too early, before we know the
program name, if using unified file-or-prog filter (i.e., -f
<any-glob>). Because we try to filter BPF object file early without
opening and parsing it, if any_glob (file-or-prog) filter is used we
have to accept any filename just to get program name, which might match
any_glob.

Fixes: 10b1b3f3e5 ("selftests/bpf: consolidate and improve file/prog filtering in veristat")
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20221111181242.2101192-1-andrii@kernel.org
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
 2022-11-11 14:06:20 -08:00
Andrii Nakryiko
d5ce4b8923 selftests/bpf: support stat filtering in comparison mode in veristat 
Finally add support for filtering stats values, similar to
non-comparison mode filtering. For comparison mode 4 variants of stats
are important for filtering, as they allow to filter either A or B side,
but even more importantly they allow to filter based on value
difference, and for verdict stat value difference is MATCH/MISMATCH
classification. So with these changes it's finally possible to easily
check if there were any mismatches between failure/success outcomes on
two separate data sets. Like in an example below:

  $ ./veristat -e file,prog,verdict,insns -C ~/baseline-results.csv ~/shortest-results.csv -f verdict_diff=mismatch
  File                                   Program                Verdict (A)  Verdict (B)  Verdict (DIFF)  Insns (A)  Insns (B)  Insns        (DIFF)
  -------------------------------------  ---------------------  -----------  -----------  --------------  ---------  ---------  -------------------
  dynptr_success.bpf.linked1.o           test_data_slice        success      failure      MISMATCH               85          0       -85 (-100.00%)
  dynptr_success.bpf.linked1.o           test_read_write        success      failure      MISMATCH             1992          0     -1992 (-100.00%)
  dynptr_success.bpf.linked1.o           test_ringbuf           success      failure      MISMATCH               74          0       -74 (-100.00%)
  kprobe_multi.bpf.linked1.o             test_kprobe            failure      success      MISMATCH                0        246      +246 (+100.00%)
  kprobe_multi.bpf.linked1.o             test_kprobe_manual     failure      success      MISMATCH                0        246      +246 (+100.00%)
  kprobe_multi.bpf.linked1.o             test_kretprobe         failure      success      MISMATCH                0        248      +248 (+100.00%)
  kprobe_multi.bpf.linked1.o             test_kretprobe_manual  failure      success      MISMATCH                0        248      +248 (+100.00%)
  kprobe_multi.bpf.linked1.o             trigger                failure      success      MISMATCH                0          2        +2 (+100.00%)
  netcnt_prog.bpf.linked1.o              bpf_nextcnt            failure      success      MISMATCH                0         56       +56 (+100.00%)
  pyperf600_nounroll.bpf.linked1.o       on_event               success      failure      MISMATCH           568128    1000001    +431873 (+76.02%)
  ringbuf_bench.bpf.linked1.o            bench_ringbuf          success      failure      MISMATCH                8          0        -8 (-100.00%)
  strobemeta.bpf.linked1.o               on_event               success      failure      MISMATCH           557149    1000001    +442852 (+79.49%)
  strobemeta_nounroll1.bpf.linked1.o     on_event               success      failure      MISMATCH            57240    1000001  +942761 (+1647.03%)
  strobemeta_nounroll2.bpf.linked1.o     on_event               success      failure      MISMATCH           501725    1000001    +498276 (+99.31%)
  strobemeta_subprogs.bpf.linked1.o      on_event               success      failure      MISMATCH            65420    1000001  +934581 (+1428.59%)
  test_map_in_map_invalid.bpf.linked1.o  xdp_noop0              success      failure      MISMATCH                2          0        -2 (-100.00%)
  test_mmap.bpf.linked1.o                test_mmap              success      failure      MISMATCH               46          0       -46 (-100.00%)
  test_verif_scale3.bpf.linked1.o        balancer_ingress       success      failure      MISMATCH           845499    1000001    +154502 (+18.27%)
  -------------------------------------  ---------------------  -----------  -----------  --------------  ---------  ---------  -------------------

Note that by filtering on verdict_diff=mismatch, it's now extremely easy and
fast to see any changes in verdict. Example above showcases both failure ->
success transitions (which are generally surprising) and success -> failure
transitions (which are expected if bugs are present).

Given veristat allows to query relative percent difference values, internal
logic for comparison mode is based on floating point numbers, so requires a bit
of epsilon precision logic, deviating from typical integer simple handling
rules.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20221103055304.2904589-11-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-11-03 21:54:14 -07:00
Andrii Nakryiko
fa9bb590c2 selftests/bpf: support stats ordering in comparison mode in veristat 
Introduce the concept of "stat variant", by which it's possible to
specify whether to use the value from A (baseline) side, B (comparison
or control) side, the absolute difference value or relative (percentage)
difference value.

To support specifying this, veristat recognizes `_a`, `_b`, `_diff`,
`_pct` suffixes, which can be appended to stat name(s). In
non-comparison mode variants are ignored (there is only `_a` variant
effectively), if no variant suffix is provided, `_b` is assumed, as
control group is of primary interest in comparison mode.

These stat variants can be flexibly combined with asc/desc orders.

Here's an example of ordering results first by verdict match/mismatch (or n/a
if one of the sides is missing; n/a is always considered to be the lowest
value), and within each match/mismatch/n/a group further sort by number of
instructions in B side. In this case we don't have MISMATCH cases, but N/A are
split from MATCH, demonstrating this custom ordering.

  $ ./veristat -e file,prog,verdict,insns -s verdict_diff,insns_b_ -C ~/base.csv ~/comp.csv
  File                Program                         Verdict (A)  Verdict (B)  Verdict (DIFF)  Insns (A)  Insns (B)  Insns   (DIFF)
  ------------------  ------------------------------  -----------  -----------  --------------  ---------  ---------  --------------
  bpf_xdp.o           tail_lb_ipv6                    N/A          success      N/A                   N/A     151895             N/A
  bpf_xdp.o           tail_nodeport_nat_egress_ipv4   N/A          success      N/A                   N/A      15619             N/A
  bpf_xdp.o           tail_nodeport_ipv6_dsr          N/A          success      N/A                   N/A       1206             N/A
  bpf_xdp.o           tail_nodeport_ipv4_dsr          N/A          success      N/A                   N/A       1162             N/A
  bpf_alignchecker.o  tail_icmp6_send_echo_reply      N/A          failure      N/A                   N/A         74             N/A
  bpf_alignchecker.o  __send_drop_notify              success      N/A          N/A                    53        N/A             N/A
  bpf_host.o          __send_drop_notify              success      N/A          N/A                    53        N/A             N/A
  bpf_host.o          cil_from_host                   success      N/A          N/A                   762        N/A             N/A
  bpf_xdp.o           tail_lb_ipv4                    success      success      MATCH               71736      73430  +1694 (+2.36%)
  bpf_xdp.o           tail_handle_nat_fwd_ipv4        success      success      MATCH               21547      20920   -627 (-2.91%)
  bpf_xdp.o           tail_rev_nodeport_lb6           success      success      MATCH               17954      17905    -49 (-0.27%)
  bpf_xdp.o           tail_handle_nat_fwd_ipv6        success      success      MATCH               16974      17039    +65 (+0.38%)
  bpf_xdp.o           tail_nodeport_nat_ingress_ipv4  success      success      MATCH                7658       7713    +55 (+0.72%)
  bpf_xdp.o           tail_rev_nodeport_lb4           success      success      MATCH                7126       6934   -192 (-2.69%)
  bpf_xdp.o           tail_nodeport_nat_ingress_ipv6  success      success      MATCH                6405       6397     -8 (-0.12%)
  bpf_xdp.o           tail_nodeport_nat_ipv6_egress   failure      failure      MATCH                 752        752     +0 (+0.00%)
  bpf_xdp.o           cil_xdp_entry                   success      success      MATCH                 423        423     +0 (+0.00%)
  bpf_xdp.o           __send_drop_notify              success      success      MATCH                 151        151     +0 (+0.00%)
  bpf_alignchecker.o  tail_icmp6_handle_ns            failure      failure      MATCH                  33         33     +0 (+0.00%)
  ------------------  ------------------------------  -----------  -----------  --------------  ---------  ---------  --------------

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20221103055304.2904589-10-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-11-03 21:54:14 -07:00
Andrii Nakryiko
a5710848d8 selftests/bpf: handle missing records in comparison mode better in veristat 
When comparing two datasets, if either side is missing corresponding
record with the same file and prog name, currently veristat emits
misleading zeros/failures, and even tried to calculate a difference,
even though there is no data to compare against.

This patch improves internal logic of handling such situations. Now
we'll emit "N/A" in places where data is missing and comparison is
non-sensical.

As an example, in an artificially truncated and mismatched Cilium
results, the output looks like below:

  $ ./veristat -e file,prog,verdict,insns -C ~/base.csv ~/comp.csv
  File                Program                         Verdict (A)  Verdict (B)  Verdict (DIFF)  Insns (A)  Insns (B)  Insns   (DIFF)
  ------------------  ------------------------------  -----------  -----------  --------------  ---------  ---------  --------------
  bpf_alignchecker.o  __send_drop_notify              success      N/A          N/A                    53        N/A             N/A
  bpf_alignchecker.o  tail_icmp6_handle_ns            failure      failure      MATCH                  33         33     +0 (+0.00%)
  bpf_alignchecker.o  tail_icmp6_send_echo_reply      N/A          failure      N/A                   N/A         74             N/A
  bpf_host.o          __send_drop_notify              success      N/A          N/A                    53        N/A             N/A
  bpf_host.o          cil_from_host                   success      N/A          N/A                   762        N/A             N/A
  bpf_xdp.o           __send_drop_notify              success      success      MATCH                 151        151     +0 (+0.00%)
  bpf_xdp.o           cil_xdp_entry                   success      success      MATCH                 423        423     +0 (+0.00%)
  bpf_xdp.o           tail_handle_nat_fwd_ipv4        success      success      MATCH               21547      20920   -627 (-2.91%)
  bpf_xdp.o           tail_handle_nat_fwd_ipv6        success      success      MATCH               16974      17039    +65 (+0.38%)
  bpf_xdp.o           tail_lb_ipv4                    success      success      MATCH               71736      73430  +1694 (+2.36%)
  bpf_xdp.o           tail_lb_ipv6                    N/A          success      N/A                   N/A     151895             N/A
  bpf_xdp.o           tail_nodeport_ipv4_dsr          N/A          success      N/A                   N/A       1162             N/A
  bpf_xdp.o           tail_nodeport_ipv6_dsr          N/A          success      N/A                   N/A       1206             N/A
  bpf_xdp.o           tail_nodeport_nat_egress_ipv4   N/A          success      N/A                   N/A      15619             N/A
  bpf_xdp.o           tail_nodeport_nat_ingress_ipv4  success      success      MATCH                7658       7713    +55 (+0.72%)
  bpf_xdp.o           tail_nodeport_nat_ingress_ipv6  success      success      MATCH                6405       6397     -8 (-0.12%)
  bpf_xdp.o           tail_nodeport_nat_ipv6_egress   failure      failure      MATCH                 752        752     +0 (+0.00%)
  bpf_xdp.o           tail_rev_nodeport_lb4           success      success      MATCH                7126       6934   -192 (-2.69%)
  bpf_xdp.o           tail_rev_nodeport_lb6           success      success      MATCH               17954      17905    -49 (-0.27%)
  ------------------  ------------------------------  -----------  -----------  --------------  ---------  ---------  --------------

Internally veristat now separates joining two datasets and remembering the
join, and actually emitting a comparison view. This will come handy when we add
support for filtering and custom ordering in comparison mode.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20221103055304.2904589-9-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-11-03 21:54:13 -07:00
Andrii Nakryiko
77534401d6 selftests/bpf: make veristat emit all stats in CSV mode by default 
Make veristat distinguish between table and CSV output formats and use
different default set of stats (columns) that are emitted. While for
human-readable table output it doesn't make sense to output all known
stats, it is very useful for CSV mode to record all possible data, so
that it can later be queried and filtered in replay or comparison mode.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20221103055304.2904589-8-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-11-03 21:54:13 -07:00
Andrii Nakryiko
1bb4ec8150 selftests/bpf: support simple filtering of stats in veristat 
Define simple expressions to filter not just by file and program name,
but also by resulting values of collected stats. Support usual
equality and inequality operators. Verdict, which is a boolean-like
field can be also filtered either as 0/1, failure/success (with f/s,
fail/succ, and failure/success aliases) symbols, or as false/true (f/t).
Aliases are case insensitive.

Currently this filtering is honored only in verification and replay
modes. Comparison mode support will be added in next patch.

Here's an example of verifying a bunch of BPF object files and emitting
only results for successfully validated programs that have more than 100
total instructions processed by BPF verifier, sorted by number of
instructions in ascending order:

  $ sudo ./veristat *.bpf.o -s insns^ -f 'insns>100'

There can be many filters (both allow and deny flavors), all of them are
combined.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20221103055304.2904589-7-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-11-03 21:54:13 -07:00
Andrii Nakryiko
d68c07e2dd selftests/bpf: allow to define asc/desc ordering for sort specs in veristat 
Allow to specify '^' at the end of stat name to designate that it should
be sorted in ascending order. Similarly, allow any of 'v', 'V', '.',
'!', or '_' suffix "symbols" to designate descending order. It's such
a zoo for descending order because there is no single intuitive symbol
that could be used (using 'v' looks pretty weird in practice), so few
symbols that are "downwards leaning or pointing" were chosen. Either
way, it shouldn't cause any troubles in practice.

This new feature allows to customize sortering order to match user's
needs.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20221103055304.2904589-6-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-11-03 21:54:13 -07:00
Andrii Nakryiko
b9670b904a selftests/bpf: ensure we always have non-ambiguous sorting in veristat 
Always fall back to unique file/prog comparison if user's custom order
specs are ambiguous. This ensures stable output no matter what.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20221103055304.2904589-5-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-11-03 21:54:13 -07:00
Andrii Nakryiko
10b1b3f3e5 selftests/bpf: consolidate and improve file/prog filtering in veristat 
Slightly change rules of specifying file/prog glob filters. In practice
it's quite often inconvenient to do `*/<prog-glob>` if that program glob
is unique enough and won't accidentally match any file names.

This patch changes the rules so that `-f <glob>` will apply specified
glob to both file and program names. User still has all the control by
doing '*/<prog-only-glob>' or '<file-only-glob/*'. We also now allow
'/<prog-glob>' and '<file-glob/' (all matching wildcard is assumed if
missing).

Also, internally unify file-only and file+prog checks
(should_process_file and should_process_prog are now
should_process_file_prog that can handle prog name as optional). This
makes maintaining and extending this code easier.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20221103055304.2904589-4-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-11-03 21:54:13 -07:00
Andrii Nakryiko
62d2c08bb9 selftests/bpf: shorten "Total insns/states" column names in veristat 
In comparison mode the "Total " part is pretty useless, but takes
a considerable amount of horizontal space. Drop the "Total " parts.

Also make sure that table headers for numerical columns are aligned in
the same fashion as integer values in those columns. This looks better
and is now more obvious with shorter "Insns" and "States" column
headers.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20221103055304.2904589-3-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-11-03 21:54:13 -07:00
Andrii Nakryiko
9b5e3536c8 selftests/bpf: add veristat replay mode 
Replay mode allow to parse previously stored CSV file with verification
results and present it in desired output (presumable human-readable
table, but CSV to CSV convertion is supported as well). While doing
that, it's possible to use veristat's sorting rules, specify subset of
columns, and filter by file and program name.

In subsequent patches veristat's filtering capabilities will just grow
making replay mode even more useful in practice for post-processing
results.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20221103055304.2904589-2-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-11-03 21:54:13 -07:00
Andrii Nakryiko
60df8c4d32 selftests/bpf: add BPF object fixup step to veristat 
Add a step to attempt to "fix up" BPF object file to make it possible to
successfully load it. E.g., set non-zero size for BPF maps that expect
max_entries set, but BPF object file itself doesn't have declarative
max_entries values specified.

Another issue was with automatic map pinning. Pinning has no effect on
BPF verification process itself but can interfere when validating
multiple related programs and object files, so veristat disabled all the
pinning explicitly.

In the future more such fix up heuristics could be added to accommodate
common patterns encountered in practice.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20221005161450.1064469-3-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-10-05 16:55:12 -07:00
Andrii Nakryiko
6df2eb45e3 selftests/bpf: avoid reporting +100% difference in veristat for actual 0% 
In special case when both base and comparison values are 0, veristat
currently reports "+0 (+100%)" difference, which is quite confusing. Fix
it up to be "+0 (+0%)".

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20221005161450.1064469-2-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-10-05 16:55:11 -07:00
Andrii Nakryiko
e310efc5dd selftests/bpf: allow to adjust BPF verifier log level in veristat 
Add -l (--log-level) flag to override default BPF verifier log lever.
This only matters in verbose mode, which is the mode in which veristat
emits verifier log for each processed BPF program.

This is important because for successfully verified BPF programs
log_level 1 is empty, as BPF verifier truncates all the successfully
verified paths. So -l2 is the only way to actually get BPF verifier log
in practice. It looks sometihng like this:

  [vmuser@archvm bpf]$ sudo ./veristat xdp_tx.bpf.o -vl2
  Processing 'xdp_tx.bpf.o'...
  PROCESSING xdp_tx.bpf.o/xdp_tx, DURATION US: 19, VERDICT: success, VERIFIER LOG:
  func#0 @0
  0: R1=ctx(off=0,imm=0) R10=fp0
  ; return XDP_TX;
  0: (b4) w0 = 3                        ; R0_w=3
  1: (95) exit
  verification time 19 usec
  stack depth 0
  processed 2 insns (limit 1000000) max_states_per_insn 0 total_states 0 peak_states 0 mark_read 0

  File          Program  Verdict  Duration (us)  Total insns  Total states  Peak states
  ------------  -------  -------  -------------  -----------  ------------  -----------
  xdp_tx.bpf.o  xdp_tx   success             19            2             0            0
  ------------  -------  -------  -------------  -----------  ------------  -----------
  Done. Processed 1 files, 0 programs. Skipped 1 files, 0 programs.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20220923175913.3272430-6-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-09-23 18:14:45 -07:00
Andrii Nakryiko
c511d009ce selftests/bpf: emit processing progress and add quiet mode to veristat 
Emit "Processing <filepath>..." for each BPF object file to be
processed, to show progress. But also add -q (--quiet) flag to silence
such messages. Doing something more clever (like overwriting same output
line) is to cumbersome and easily breakable if there is any other
console output (e.g., errors from libbpf).

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20220923175913.3272430-5-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-09-23 18:14:45 -07:00
Andrii Nakryiko
518fee8bfa selftests/bpf: make veristat skip non-BPF and failing-to-open BPF objects 
Make veristat ignore non-BPF object files. This allows simpler
mass-verification (e.g., `sudo ./veristat *.bpf.o` in selftests/bpf
directory). Note that `sudo ./veristat *.o` would also work, but with
selftests's multiple copies of BPF object files (.bpf.o and
.bpf.linked{1,2,3}.o) it's 4x slower.

Also, given some of BPF object files could be incomplete in the sense
that they are meant to be statically linked into final BPF object file
(like linked_maps, linked_funcs, linked_vars), note such instances in
stderr, but proceed anyways. This seems like a better trade off between
completely silently ignoring BPF object file and aborting
mass-verification altogether.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20220923175913.3272430-4-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-09-23 18:14:45 -07:00
Andrii Nakryiko
c2488d70ce selftests/bpf: make veristat's verifier log parsing faster and more robust 
Make sure veristat doesn't spend ridiculous amount of time parsing
verifier stats from verifier log, especially for very large logs or
truncated logs (e.g., when verifier returns -ENOSPC due to too small
buffer). For this, parse lines from the end of the log and make sure we
parse only up to 100 last lines, where stats should be, if at all.

Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20220923175913.3272430-3-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-09-23 18:14:44 -07:00
Andrii Nakryiko
bde4a96cdc selftests/bpf: add ability to filter programs in veristat 
Add -f (--filter) argument which accepts glob-based filters for
narrowing down what BPF object files and programs within them should be
processed by veristat. This filtering applies both to comparison and
main (verification) mode.

Filter can be of two forms:
  - file (object) filter: 'strobemeta*'; in this case all the programs
    within matching files are implicitly allowed (or denied, depending
    if it's positive or negative rule, see below);
  - file and prog filter: 'strobemeta*/*unroll*' will further filter
    programs within matching files to only allow those program names that
    match '*unroll*' glob.

As mentioned, filters can be positive (allowlisting) and negative
(denylisting). Negative filters should start with '!': '!strobemeta*'
will deny any filename which basename starts with "strobemeta".

Further, one extra special syntax is supported to allow more convenient
use in practice. Instead of specifying rule on the command line,
veristat allows to specify file that contains rules, both positive and
negative, one line per one filter. This is achieved with -f @<filepath>
use, where <filepath> points to a text file containing rules (negative
and positive rules can be mixed). For convenience empty lines and lines
starting with '#' are ignored. This feature is useful to have some
pre-canned list of object files and program names that are tested
repeatedly, allowing to check in a list of rules and quickly specify
them on the command line.

As a demonstration (and a short cut for nearest future), create a small
list of "interesting" BPF object files from selftests/bpf and commit it
as veristat.cfg. It currently includes 73 programs, most of which are
the most complex and largest BPF programs in selftests, as judged by
total verified instruction count and verifier states total.

If there is overlap between positive or negative filters, negative
filter takes precedence (denylisting is stronger than allowlisting). If
no allow filter is specified, veristat implicitly assumes '*/*' rule. If
no deny rule is specified, veristat (logically) assumes no negative
filters.

Also note that -f (just like -e and -s) can be specified multiple times
and their effect is cumulative.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20220921164254.3630690-5-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-09-21 19:41:37 -07:00
Andrii Nakryiko
394169b079 selftests/bpf: add comparison mode to veristat 
Add ability to compare and contrast two veristat runs, previously
recorded with veristat using CSV output format.

When veristat is called with -C (--compare) flag, veristat expects
exactly two input files specified, both should be in CSV format.
Expectation is that it's output from previous veristat runs, but as long
as column names and formats match, it should just work. First CSV file
is designated as a "baseline" provided, and the second one is
comparison (experiment) data set. Establishing baseline matters later
when calculating difference percentages, see below.

Veristat parses these two CSV files and "reconstructs" verifier stats
(it could be just a subset of all possible stats). File and program
names are mandatory as they are used as joining key (these two "stats"
are designated as "key stats" in the code).

Veristat currently enforces that the set of stats recorded in both CSV
has to exactly match, down to exact order. This is just a simplifying
condition which can be lifted with a bit of additional pre-processing to
reorded stat specs internally, which I didn't bother doing, yet.

For all the non-key stats, veristat will output three columns: one for
baseline data, one for comparison data, and one with an absolute and
relative percentage difference. If either baseline or comparison values
are missing (that is, respective CSV file doesn't have a row with
*exactly* matching file and program name), those values are assumed to
be empty or zero. In such case relative percentages are forced to +100%
or -100% output, for consistency with a typical case.

Veristat's -e (--emit) and -s (--sort) specs still apply, so even if CSV
contains lots of stats, user can request to compare only a subset of
them (and specify desired column order as well). Similarly, both CSV and
human-readable table output is honored. Note that input is currently
always expected to be CSV.

Here's an example shell session, recording data for biosnoop tool on two
different kernels and comparing them afterwards, outputting data in table
format.

  # on slightly older production kernel
  $ sudo ./veristat biosnoop_bpf.o
  File            Program                   Verdict  Duration (us)  Total insns  Total states  Peak states
  --------------  ------------------------  -------  -------------  -----------  ------------  -----------
  biosnoop_bpf.o  blk_account_io_merge_bio  success             37           24             1            1
  biosnoop_bpf.o  blk_account_io_start      failure              0            0             0            0
  biosnoop_bpf.o  block_rq_complete         success             76          104             6            6
  biosnoop_bpf.o  block_rq_insert           success             83           85             7            7
  biosnoop_bpf.o  block_rq_issue            success             79           85             7            7
  --------------  ------------------------  -------  -------------  -----------  ------------  -----------
  Done. Processed 1 object files, 5 programs.
  $ sudo ./veristat ~/local/tmp/fbcode-bpf-objs/biosnoop_bpf.o -o csv > baseline.csv
  $ cat baseline.csv
  file_name,prog_name,verdict,duration,total_insns,total_states,peak_states
  biosnoop_bpf.o,blk_account_io_merge_bio,success,36,24,1,1
  biosnoop_bpf.o,blk_account_io_start,failure,0,0,0,0
  biosnoop_bpf.o,block_rq_complete,success,82,104,6,6
  biosnoop_bpf.o,block_rq_insert,success,78,85,7,7
  biosnoop_bpf.o,block_rq_issue,success,74,85,7,7

  # on latest bpf-next kernel
  $ sudo ./veristat biosnoop_bpf.o
  File            Program                   Verdict  Duration (us)  Total insns  Total states  Peak states
  --------------  ------------------------  -------  -------------  -----------  ------------  -----------
  biosnoop_bpf.o  blk_account_io_merge_bio  success             31           24             1            1
  biosnoop_bpf.o  blk_account_io_start      failure              0            0             0            0
  biosnoop_bpf.o  block_rq_complete         success             76          104             6            6
  biosnoop_bpf.o  block_rq_insert           success             83           91             7            7
  biosnoop_bpf.o  block_rq_issue            success             74           91             7            7
  --------------  ------------------------  -------  -------------  -----------  ------------  -----------
  Done. Processed 1 object files, 5 programs.
  $ sudo ./veristat biosnoop_bpf.o -o csv > comparison.csv
  $ cat comparison.csv
  file_name,prog_name,verdict,duration,total_insns,total_states,peak_states
  biosnoop_bpf.o,blk_account_io_merge_bio,success,71,24,1,1
  biosnoop_bpf.o,blk_account_io_start,failure,0,0,0,0
  biosnoop_bpf.o,block_rq_complete,success,82,104,6,6
  biosnoop_bpf.o,block_rq_insert,success,83,91,7,7
  biosnoop_bpf.o,block_rq_issue,success,87,91,7,7

  # now let's compare with human-readable output (note that no sudo needed)
  # we also ignore verification duration in this case to shortned output
  $ ./veristat -C baseline.csv comparison.csv -e file,prog,verdict,insns
  File            Program                   Verdict (A)  Verdict (B)  Verdict (DIFF)  Total insns (A)  Total insns (B)  Total insns (DIFF)
  --------------  ------------------------  -----------  -----------  --------------  ---------------  ---------------  ------------------
  biosnoop_bpf.o  blk_account_io_merge_bio  success      success      MATCH                        24               24         +0 (+0.00%)
  biosnoop_bpf.o  blk_account_io_start      failure      failure      MATCH                         0                0       +0 (+100.00%)
  biosnoop_bpf.o  block_rq_complete         success      success      MATCH                       104              104         +0 (+0.00%)
  biosnoop_bpf.o  block_rq_insert           success      success      MATCH                        91               85         -6 (-6.59%)
  biosnoop_bpf.o  block_rq_issue            success      success      MATCH                        91               85         -6 (-6.59%)
  --------------  ------------------------  -----------  -----------  --------------  ---------------  ---------------  ------------------

While not particularly exciting example (it turned out to be kind of hard to
quickly find a nice example with significant difference just because of kernel
version bump), it should demonstrate main features.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20220921164254.3630690-4-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-09-21 19:41:37 -07:00
Andrii Nakryiko
e5eb08d8fe selftests/bpf: add CSV output mode for veristat 
Teach veristat to output results as CSV table for easier programmatic
processing. Change what was --output/-o argument to now be --emit/-e.
And then use --output-format/-o <fmt> to specify output format.
Currently "table" and "csv" is supported, table being default.

For CSV output mode veristat is using spec identifiers as column names.
E.g., instead of "Total states" veristat uses "total_states" as a CSV
header name.

Internally veristat recognizes three formats, one of them
(RESFMT_TABLE_CALCLEN) is a special format instructing veristat to
calculate column widths for table output. This felt a bit cleaner and
more uniform than either creating separate functions just for this.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20220921164254.3630690-3-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-09-21 19:41:37 -07:00
Andrii Nakryiko
f338ac9105 selftests/bpf: fix double bpf_object__close() in veristate 
bpf_object__close(obj) is called twice for BPF object files with single
BPF program in it. This causes crash. Fix this by not calling
bpf_object__close() unnecessarily.

Fixes: c8bc5e0509 ("selftests/bpf: Add veristat tool for mass-verifying BPF object files")
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20220921164254.3630690-2-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
 2022-09-21 19:41:37 -07:00
Andrii Nakryiko
c8bc5e0509 selftests/bpf: Add veristat tool for mass-verifying BPF object files 
Add a small tool, veristat, that allows mass-verification of
a set of *libbpf-compatible* BPF ELF object files. For each such object
file, veristat will attempt to verify each BPF program *individually*.
Regardless of success or failure, it parses BPF verifier stats and
outputs them in human-readable table format. In the future we can also
add CSV and JSON output for more scriptable post-processing, if necessary.

veristat allows to specify a set of stats that should be output and
ordering between multiple objects and files (e.g., so that one can
easily order by total instructions processed, instead of default file
name, prog name, verdict, total instructions order).

This tool should be useful for validating various BPF verifier changes
or even validating different kernel versions for regressions.

Here's an example for some of the heaviest selftests/bpf BPF object
files:

  $ sudo ./veristat -s insns,file,prog {pyperf,loop,test_verif_scale,strobemeta,test_cls_redirect,profiler}*.linked3.o
  File                                  Program                               Verdict  Duration, us  Total insns  Total states  Peak states
  ------------------------------------  ------------------------------------  -------  ------------  -----------  ------------  -----------
  loop3.linked3.o                       while_true                            failure        350990      1000001          9663         9663
  test_verif_scale3.linked3.o           balancer_ingress                      success        115244       845499          8636         2141
  test_verif_scale2.linked3.o           balancer_ingress                      success         77688       773445          3048          788
  pyperf600.linked3.o                   on_event                              success       2079872       624585         30335        30241
  pyperf600_nounroll.linked3.o          on_event                              success        353972       568128         37101         2115
  strobemeta.linked3.o                  on_event                              success        455230       557149         15915        13537
  test_verif_scale1.linked3.o           balancer_ingress                      success         89880       554754          8636         2141
  strobemeta_nounroll2.linked3.o        on_event                              success        433906       501725         17087         1912
  loop6.linked3.o                       trace_virtqueue_add_sgs               success        282205       398057          8717          919
  loop1.linked3.o                       nested_loops                          success        125630       361349          5504         5504
  pyperf180.linked3.o                   on_event                              success       2511740       160398         11470        11446
  pyperf100.linked3.o                   on_event                              success        744329        87681          6213         6191
  test_cls_redirect.linked3.o           cls_redirect                          success         54087        78925          4782          903
  strobemeta_subprogs.linked3.o         on_event                              success         57898        65420          1954          403
  test_cls_redirect_subprogs.linked3.o  cls_redirect                          success         54522        64965          4619          958
  strobemeta_nounroll1.linked3.o        on_event                              success         43313        57240          1757          382
  pyperf50.linked3.o                    on_event                              success        194355        46378          3263         3241
  profiler2.linked3.o                   tracepoint__syscalls__sys_enter_kill  success         23869        43372          1423          542
  pyperf_subprogs.linked3.o             on_event                              success         29179        36358          2499         2499
  profiler1.linked3.o                   tracepoint__syscalls__sys_enter_kill  success         13052        27036          1946          936
  profiler3.linked3.o                   tracepoint__syscalls__sys_enter_kill  success         21023        26016          2186          915
  profiler2.linked3.o                   kprobe__vfs_link                      success          5255        13896           303          271
  profiler1.linked3.o                   kprobe__vfs_link                      success          7792        12687          1042         1041
  profiler3.linked3.o                   kprobe__vfs_link                      success          7332        10601           865          865
  profiler2.linked3.o                   kprobe_ret__do_filp_open              success          3417         8900           216          199
  profiler2.linked3.o                   kprobe__vfs_symlink                   success          3548         8775           203          186
  pyperf_global.linked3.o               on_event                              success         10007         7563           520          520
  profiler3.linked3.o                   kprobe_ret__do_filp_open              success          4708         6464           532          532
  profiler1.linked3.o                   kprobe_ret__do_filp_open              success          3090         6445           508          508
  profiler3.linked3.o                   kprobe__vfs_symlink                   success          4477         6358           521          521
  profiler1.linked3.o                   kprobe__vfs_symlink                   success          3381         6347           507          507
  profiler2.linked3.o                   raw_tracepoint__sched_process_exec    success          2464         5874           292          189
  profiler3.linked3.o                   raw_tracepoint__sched_process_exec    success          2677         4363           397          283
  profiler2.linked3.o                   kprobe__proc_sys_write                success          1800         4355           143          138
  profiler1.linked3.o                   raw_tracepoint__sched_process_exec    success          1649         4019           333          240
  pyperf600_bpf_loop.linked3.o          on_event                              success          2711         3966           306          306
  profiler2.linked3.o                   raw_tracepoint__sched_process_exit    success          1234         3138            83           66
  profiler3.linked3.o                   kprobe__proc_sys_write                success          1755         2623           223          223
  profiler1.linked3.o                   kprobe__proc_sys_write                success          1222         2456           193          193
  loop2.linked3.o                       while_true                            success           608         1783            57           30
  profiler3.linked3.o                   raw_tracepoint__sched_process_exit    success           789         1680           146          146
  profiler1.linked3.o                   raw_tracepoint__sched_process_exit    success           592         1526           133          133
  strobemeta_bpf_loop.linked3.o         on_event                              success          1015         1512           106          106
  loop4.linked3.o                       combinations                          success           165          524            18           17
  profiler3.linked3.o                   raw_tracepoint__sched_process_fork    success           196          299            25           25
  profiler1.linked3.o                   raw_tracepoint__sched_process_fork    success           109          265            19           19
  profiler2.linked3.o                   raw_tracepoint__sched_process_fork    success           111          265            19           19
  loop5.linked3.o                       while_true                            success            47           84             9            9
  ------------------------------------  ------------------------------------  -------  ------------  -----------  ------------  -----------

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220909193053.577111-4-andrii@kernel.org
 2022-09-16 22:41:41 +02:00