From 33a154a96e71a34a1bcca9f40da343dbbf7b38b4 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 1 Oct 2026 14:52:55 +0000 Subject: selftests/bpf: Test packet range of pointers sharing an id Add tests where two packet pointers share an id and tightening one pointer's umax from its var_off would put it less than their constant distance from the other's umax: with an index & 0x38 capped at 50, the base pointer keeps umax 50, so the pointer 8 bytes further on must keep umax 58, even though its known bits allow at most 56. These refused a valid program or accepted an out-of-bounds access before the fix: - check the advanced copy, load through the base: valid, was refused; - check the base, load the byte at base + 1 through a copy advanced by 8: was accepted; - check base + 4, load 4 bytes at base + 2 through base + 8: reads two bytes past the checked range, was accepted; - the same as the second with data_meta pointers checked against data: was accepted. These pass with and without the fix and cover nearby paths: - subtract an unknown scalar from a checked pointer and load below it (the range is kept across a new id); - reach a load through two paths whose checks cover 8 and 7 bytes after the loaded pointer; the second path must not be pruned by the first; - spill a copy of a pointer, check the pointer, fill the copy and load one byte past the checked range: the load is refused, and the copy has the range of the check. Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20261001145255.855630-2-alexei.starovoitov@gmail.com Signed-off-by: Kumar Kartikeya Dwivedi --- samples/workqueue/stall_detector/Makefile | 1 + samples/workqueue/stall_detector/wq_stall.c | 98 +++++++++++++++++++++++++++++ 2 files changed, 99 insertions(+) create mode 100644 samples/workqueue/stall_detector/Makefile create mode 100644 samples/workqueue/stall_detector/wq_stall.c (limited to 'samples/workqueue') diff --git a/samples/workqueue/stall_detector/Makefile b/samples/workqueue/stall_detector/Makefile new file mode 100644 index 000000000..8849e85e9 --- /dev/null +++ b/samples/workqueue/stall_detector/Makefile @@ -0,0 +1 @@ +obj-m += wq_stall.o diff --git a/samples/workqueue/stall_detector/wq_stall.c b/samples/workqueue/stall_detector/wq_stall.c new file mode 100644 index 000000000..6f4a497b1 --- /dev/null +++ b/samples/workqueue/stall_detector/wq_stall.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * wq_stall - Test module for the workqueue stall detector. + * + * Deliberately creates a workqueue stall so the watchdog fires and + * prints diagnostic output. Useful for verifying that the stall + * detector correctly identifies stuck workers and produces useful + * backtraces. + * + * The stall is triggered by clearing PF_WQ_WORKER before sleeping, + * which hides the worker from the concurrency manager. A second + * work item queued on the same pool then sits in the worklist with + * no worker available to process it. + * + * After ~30s the workqueue watchdog fires: + * BUG: workqueue lockup - pool cpus=N ... + * + * Build: + * make -C M=samples/workqueue/stall_detector modules + * + * Copyright (c) 2026 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2026 Breno Leitao + */ + +#include +#include +#include +#include +#include + +static DECLARE_WAIT_QUEUE_HEAD(stall_wq_head); +static atomic_t wake_condition = ATOMIC_INIT(0); +static struct work_struct stall_work1; +static struct work_struct stall_work2; + +static void stall_work2_fn(struct work_struct *work) +{ + pr_info("wq_stall: second work item finally ran\n"); +} + +static void stall_work1_fn(struct work_struct *work) +{ + pr_info("wq_stall: first work item running on cpu %d\n", + raw_smp_processor_id()); + + /* + * Queue second item while we're still counted as running + * (pool->nr_running > 0). Since schedule_work() on a per-CPU + * workqueue targets raw_smp_processor_id(), item 2 lands on the + * same pool. __queue_work -> kick_pool -> need_more_worker() + * sees nr_running > 0 and does NOT wake a new worker. + */ + schedule_work(&stall_work2); + + /* + * Hide from the workqueue concurrency manager. Without + * PF_WQ_WORKER, schedule() won't call wq_worker_sleeping(), + * so nr_running is never decremented and no replacement + * worker is created. Item 2 stays stuck in pool->worklist. + */ + current->flags &= ~PF_WQ_WORKER; + + pr_info("wq_stall: entering wait_event_idle (PF_WQ_WORKER cleared)\n"); + pr_info("wq_stall: expect 'BUG: workqueue lockup' in ~30-60s\n"); + wait_event_idle(stall_wq_head, atomic_read(&wake_condition) != 0); + + /* Restore so process_one_work() cleanup works correctly */ + current->flags |= PF_WQ_WORKER; + pr_info("wq_stall: woke up, PF_WQ_WORKER restored\n"); +} + +static int __init wq_stall_init(void) +{ + pr_info("wq_stall: loading\n"); + + INIT_WORK(&stall_work1, stall_work1_fn); + INIT_WORK(&stall_work2, stall_work2_fn); + schedule_work(&stall_work1); + + return 0; +} + +static void __exit wq_stall_exit(void) +{ + pr_info("wq_stall: unloading\n"); + atomic_set(&wake_condition, 1); + wake_up(&stall_wq_head); + flush_work(&stall_work1); + flush_work(&stall_work2); + pr_info("wq_stall: all work flushed, module unloaded\n"); +} + +module_init(wq_stall_init); +module_exit(wq_stall_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Reproduce workqueue stall caused by PF_WQ_WORKER misuse"); +MODULE_AUTHOR("Breno Leitao "); -- cgit v1.3.1