All of lore.kernel.org
 help / color / mirror / Atom feed
From: Eduard Zingerman <eddyz87@gmail.com>
To: bpf@vger.kernel.org, ast@kernel.org
Cc: andrii@kernel.org, daniel@iogearbox.net, martin.lau@linux.dev,
	kernel-team@fb.com, yonghong.song@linux.dev, tj@kernel.org,
	patsomaru@meta.com, Eduard Zingerman <eddyz87@gmail.com>
Subject: [PATCH bpf-next v1 03/10] bpf: don't do clean_live_states when state->loop_entry->branches > 0
Date: Sat, 15 Feb 2025 03:03:54 -0800	[thread overview]
Message-ID: <20250215110411.3236773-4-eddyz87@gmail.com> (raw)
In-Reply-To: <20250215110411.3236773-1-eddyz87@gmail.com>

verifier.c:is_state_visited() uses RANGE_WITHIN states comparison rules
for cached states that have loop_entry with non-zero branches count
(meaning that loop_entry's verification is not yet done).

The RANGE_WITHIN rules in regsafe()/stacksafe() require register and
stack objects types to be identical in current and old states.

verifier.c:clean_live_states() replaces registers and stack spills
with NOT_INIT/STACK_INVALID marks, if these registers/stack spills are
not read in any child state. This means that clean_live_states() works
against loop convergence logic under some conditions. See selftest in
the next patch for a specific example.

Mitigate this by prohibiting clean_verifier_state() when
state->loop_entry->branches > 0.

This undoes negative verification performance impact of the
copy_verifier_state() fix from the previous patch.
Below is comparison between master and current patch.

selftests:

File                                Program                       Insns (A)  Insns (B)  Insns    (DIFF)  States (A)  States (B)  States  (DIFF)
----------------------------------  ----------------------------  ---------  ---------  ---------------  ----------  ----------  --------------
arena_htab.bpf.o                    arena_htab_llvm                     717        423   -294 (-41.00%)          57          37   -20 (-35.09%)
arena_htab_asm.bpf.o                arena_htab_asm                      597        445   -152 (-25.46%)          47          37   -10 (-21.28%)
arena_list.bpf.o                    arena_list_add                     1493       1822   +329 (+22.04%)          30          37    +7 (+23.33%)
arena_list.bpf.o                    arena_list_del                      309        261    -48 (-15.53%)          23          15    -8 (-34.78%)
iters.bpf.o                         checkpoint_states_deletion        18125      22154  +4029 (+22.23%)         818         918  +100 (+12.22%)
iters.bpf.o                         iter_nested_deeply_iters            593        367   -226 (-38.11%)          67          43   -24 (-35.82%)
iters.bpf.o                         iter_nested_iters                   813        772     -41 (-5.04%)          79          72     -7 (-8.86%)
iters.bpf.o                         iter_subprog_check_stacksafe        155        135    -20 (-12.90%)          15          14     -1 (-6.67%)
iters.bpf.o                         iter_subprog_iters                 1094        808   -286 (-26.14%)          88          68   -20 (-22.73%)
iters.bpf.o                         loop_state_deps2                    479        356   -123 (-25.68%)          46          35   -11 (-23.91%)
iters.bpf.o                         triple_continue                      35         31     -4 (-11.43%)           3           3     +0 (+0.00%)
kmem_cache_iter.bpf.o               open_coded_iter                      63         59      -4 (-6.35%)           7           6    -1 (-14.29%)
mptcp_subflow.bpf.o                 _getsockopt_subflow                 501        446    -55 (-10.98%)          25          23     -2 (-8.00%)
pyperf600_iter.bpf.o                on_event                          12339       6379  -5960 (-48.30%)         441         286  -155 (-35.15%)
verifier_bits_iter.bpf.o            max_words                            92         84      -8 (-8.70%)           8           7    -1 (-12.50%)
verifier_iterating_callbacks.bpf.o  cond_break2                         113        192    +79 (+69.91%)          12          21    +9 (+75.00%)

sched_ext:

File               Program                 Insns (A)  Insns (B)  Insns      (DIFF)  States (A)  States (B)  States    (DIFF)
-----------------  ----------------------  ---------  ---------  -----------------  ----------  ----------  ----------------
bpf.bpf.o          layered_dispatch            11485       9039    -2446 (-21.30%)         848         662    -186 (-21.93%)
bpf.bpf.o          layered_dump                 7422       5022    -2400 (-32.34%)         681         298    -383 (-56.24%)
bpf.bpf.o          layered_enqueue             16854      13753    -3101 (-18.40%)        1611        1308    -303 (-18.81%)
bpf.bpf.o          layered_init              1000001       5549  -994452 (-99.45%)       84672         523  -84149 (-99.38%)
bpf.bpf.o          layered_runnable             3149       1899    -1250 (-39.70%)         288         151    -137 (-47.57%)
bpf.bpf.o          p2dq_init                    2343       1936     -407 (-17.37%)         201         170     -31 (-15.42%)
bpf.bpf.o          refresh_layer_cpumasks      16487       1285   -15202 (-92.21%)        1770         120   -1650 (-93.22%)
bpf.bpf.o          rusty_select_cpu             1937       1386     -551 (-28.45%)         177         125     -52 (-29.38%)
scx_central.bpf.o  central_dispatch              636        600       -36 (-5.66%)          63          59       -4 (-6.35%)
scx_central.bpf.o  central_init                  913        632     -281 (-30.78%)          48          39      -9 (-18.75%)
scx_nest.bpf.o     nest_init                     636        601       -35 (-5.50%)          60          58       -2 (-3.33%)
scx_pair.bpf.o     pair_dispatch             1000001       1914  -998087 (-99.81%)       58169         142  -58027 (-99.76%)
scx_qmap.bpf.o     qmap_dispatch                2393       2187      -206 (-8.61%)         196         174     -22 (-11.22%)
scx_qmap.bpf.o     qmap_init                   16367      22777    +6410 (+39.16%)         603         768    +165 (+27.36%)

'layered_init' and 'pair_dispatch' hit 1M on master, but are verified
ok with this patch.

Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
---
 kernel/bpf/verifier.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 01b31b718f4f..945a13b2cfeb 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -17814,12 +17814,16 @@ static void clean_verifier_state(struct bpf_verifier_env *env,
 static void clean_live_states(struct bpf_verifier_env *env, int insn,
 			      struct bpf_verifier_state *cur)
 {
+	struct bpf_verifier_state *loop_entry;
 	struct bpf_verifier_state_list *sl;
 
 	sl = *explored_state(env, insn);
 	while (sl) {
 		if (sl->state.branches)
 			goto next;
+		loop_entry = get_loop_entry(&sl->state);
+		if (loop_entry && loop_entry->branches)
+			goto next;
 		if (sl->state.insn_idx != insn ||
 		    !same_callsites(&sl->state, cur))
 			goto next;
-- 
2.48.1


  parent reply	other threads:[~2025-02-15 11:04 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-02-15 11:03 [PATCH bpf-next v1 00/10] bpf: copy_verifier_state() should copy 'loop_entry' field Eduard Zingerman
2025-02-15 11:03 ` [PATCH bpf-next v1 01/10] " Eduard Zingerman
2025-02-24 18:56   ` Andrii Nakryiko
2025-02-24 22:28     ` Eduard Zingerman
2025-02-15 11:03 ` [PATCH bpf-next v1 02/10] selftests/bpf: test correct loop_entry update in copy_verifier_state Eduard Zingerman
2025-02-15 11:03 ` Eduard Zingerman [this message]
2025-02-15 11:03 ` [PATCH bpf-next v1 04/10] selftests/bpf: check states pruning for deeply nested iterator Eduard Zingerman
2025-02-15 11:03 ` [PATCH bpf-next v1 05/10] bpf: detect infinite loop in get_loop_entry() Eduard Zingerman
2025-02-15 11:03 ` [PATCH bpf-next v1 06/10] bpf: make state->dfs_depth < state->loop_entry->dfs_depth an invariant Eduard Zingerman
2025-02-15 11:03 ` [PATCH bpf-next v1 07/10] bpf: do not update state->loop_entry in get_loop_entry() Eduard Zingerman
2025-02-15 11:03 ` [PATCH bpf-next v1 08/10] bpf: use list_head to track explored states and free list Eduard Zingerman
2025-02-15 11:04 ` [PATCH bpf-next v1 09/10] bpf: free verifier states when they are no longer referenced Eduard Zingerman
2025-02-15 11:04 ` [PATCH bpf-next v1 10/10] bpf: fix env->peak_states computation Eduard Zingerman

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250215110411.3236773-4-eddyz87@gmail.com \
    --to=eddyz87@gmail.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=kernel-team@fb.com \
    --cc=martin.lau@linux.dev \
    --cc=patsomaru@meta.com \
    --cc=tj@kernel.org \
    --cc=yonghong.song@linux.dev \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.