From a5f7a5bb3b7f28ba7e4fa246775b29a0e5537255 Mon Sep 17 00:00:00 2001 From: Jinke Han Date: Tue, 8 Sep 2026 15:37:42 +0800 Subject: x86/kprobes: Fix crash when probing CS CALL instructions When using eBPF to probe CS CALL instructions within a function, a crash can be triggered. The eBPF tool probes offset 257 of the __hrtimer_run_queues() function: <__hrtimer_run_queues+249>: nopl 0x0(%rax,%rax,1) <__hrtimer_run_queues+254>: mov %r14,%rdi <__hrtimer_run_queues+257>: cs call <__x86_indirect_thunk_r12> <__hrtimer_run_queues+263>: mov %eax,%r12d <__hrtimer_run_queues+266>: xchg %ax,%ax <__hrtimer_run_queues+268>: mov %r13,%rdi Which triggers this crash: BUG: unable to handle page fault for address: 00000000000f41c9 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] SMP NOPTI CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P RIP: 0010:__hrtimer_run_queues+0x106/0x230 Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is at the 6th byte of the above CS CALL instruction. Since the CS CALL instruction occupies 6 bytes, the exception occurred in the middle of that call instruction. The root cause is that when using eBPF tools to probe in the middle of a function, a kprobe with INT3 is used as the underlying implementation. During single-step emulation of the original CALL instruction, int3_emulate_call() assumes that the probed CALL instruction is 5 bytes long. However, the actual CS-prefixed CALL instruction occupies 6 bytes, so it constructs an incorrect exception return address. When the CPU returns from the kprobe handler, the next instruction to be executed is at the address of the last byte of that CS CALL instruction. Coincidentally, starting from that address, the CPU fetches and decodes a completely different instruction, which ultimately triggers a kernel crash. Fix the issue by using the actual instruction length obtained from the instruction decoder when constructing the exception return address, rather than relying on the hardcoded CALL_INSN_SIZE macro. [ mingo: Refined the changelog ] Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step") Suggested-by: Masami Hiramatsu (Google) Signed-off-by: Jinke Han Signed-off-by: Ingo Molnar Reviewed-by: Masami Hiramatsu (Google) Acked-by: Yafang Shao Acked-by: Borislav Petkov Cc: Peter Zijlstra Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000 --- lib/dynamic_queue_limits.c | 217 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 217 insertions(+) create mode 100644 lib/dynamic_queue_limits.c (limited to 'lib/dynamic_queue_limits.c') diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c new file mode 100644 index 000000000..f97a752e9 --- /dev/null +++ b/lib/dynamic_queue_limits.c @@ -0,0 +1,217 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Dynamic byte queue limits. See include/linux/dynamic_queue_limits.h + * + * Copyright (c) 2011, Tom Herbert + */ +#include +#include +#include +#include +#include +#include +#include + +#define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0) +#define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0) + +static void dql_check_stall(struct dql *dql, unsigned short stall_thrs) +{ + unsigned long now; + + if (!stall_thrs) + return; + + now = jiffies; + /* Check for a potential stall */ + if (time_after_eq(now, dql->last_reap + stall_thrs)) { + unsigned long hist_head, t, start, end; + + /* We are trying to detect a period of at least @stall_thrs + * jiffies without any Tx completions, but during first half + * of which some Tx was posted. + */ +dqs_again: + hist_head = READ_ONCE(dql->history_head); + /* pairs with smp_wmb() in dql_queued() */ + smp_rmb(); + + /* Get the previous entry in the ring buffer, which is the + * oldest sample. + */ + start = (hist_head - DQL_HIST_LEN + 1) * BITS_PER_LONG; + + /* Advance start to continue from the last reap time */ + if (time_before(start, dql->last_reap + 1)) + start = dql->last_reap + 1; + + /* Newest sample we should have already seen a completion for */ + end = hist_head * BITS_PER_LONG + (BITS_PER_LONG - 1); + + /* Shrink the search space to [start, (now - start_thrs/2)] if + * `end` is beyond the stall zone + */ + if (time_before(now, end + stall_thrs / 2)) + end = now - stall_thrs / 2; + + /* Search for the queued time in [t, end] */ + for (t = start; time_before_eq(t, end); t++) + if (test_bit(t % (DQL_HIST_LEN * BITS_PER_LONG), + dql->history)) + break; + + /* Variable t contains the time of the queue */ + if (!time_before_eq(t, end)) + goto no_stall; + + /* The ring buffer was modified in the meantime, retry */ + if (hist_head != READ_ONCE(dql->history_head)) + goto dqs_again; + + dql->stall_cnt++; + dql->stall_max = max_t(unsigned short, dql->stall_max, now - t); + + trace_dql_stall_detected(dql->stall_thrs, now - t, + dql->last_reap, dql->history_head, + now, dql->history); + } +no_stall: + dql->last_reap = now; +} + +/* Records completed count and recalculates the queue limit */ +void dql_completed(struct dql *dql, unsigned int count) +{ + unsigned int inprogress, prev_inprogress, limit; + unsigned int ovlimit, completed, num_queued; + unsigned short stall_thrs; + bool all_prev_completed; + + num_queued = READ_ONCE(dql->num_queued); + /* Read stall_thrs in advance since it belongs to the same (first) + * cache line as ->num_queued. This way, dql_check_stall() does not + * need to touch the first cache line again later, reducing the window + * of possible false sharing. + */ + stall_thrs = READ_ONCE(dql->stall_thrs); + + /* Can't complete more than what's in queue */ + BUG_ON(count > num_queued - dql->num_completed); + + completed = dql->num_completed + count; + limit = dql->limit; + ovlimit = POSDIFF(num_queued - dql->num_completed, limit); + inprogress = num_queued - completed; + prev_inprogress = dql->prev_num_queued - dql->num_completed; + all_prev_completed = AFTER_EQ(completed, dql->prev_num_queued); + + if ((ovlimit && !inprogress) || + (dql->prev_ovlimit && all_prev_completed)) { + /* + * Queue considered starved if: + * - The queue was over-limit in the last interval, + * and there is no more data in the queue. + * OR + * - The queue was over-limit in the previous interval and + * when enqueuing it was possible that all queued data + * had been consumed. This covers the case when queue + * may have becomes starved between completion processing + * running and next time enqueue was scheduled. + * + * When queue is starved increase the limit by the amount + * of bytes both sent and completed in the last interval, + * plus any previous over-limit. + */ + limit += POSDIFF(completed, dql->prev_num_queued) + + dql->prev_ovlimit; + dql->slack_start_time = jiffies; + dql->lowest_slack = UINT_MAX; + } else if (inprogress && prev_inprogress && !all_prev_completed) { + /* + * Queue was not starved, check if the limit can be decreased. + * A decrease is only considered if the queue has been busy in + * the whole interval (the check above). + * + * If there is slack, the amount of excess data queued above + * the amount needed to prevent starvation, the queue limit + * can be decreased. To avoid hysteresis we consider the + * minimum amount of slack found over several iterations of the + * completion routine. + */ + unsigned int slack, slack_last_objs; + + /* + * Slack is the maximum of + * - The queue limit plus previous over-limit minus twice + * the number of objects completed. Note that two times + * number of completed bytes is a basis for an upper bound + * of the limit. + * - Portion of objects in the last queuing operation that + * was not part of non-zero previous over-limit. That is + * "round down" by non-overlimit portion of the last + * queueing operation. + */ + slack = POSDIFF(limit + dql->prev_ovlimit, + 2 * (completed - dql->num_completed)); + slack_last_objs = dql->prev_ovlimit ? + POSDIFF(dql->prev_last_obj_cnt, dql->prev_ovlimit) : 0; + + slack = max(slack, slack_last_objs); + + if (slack < dql->lowest_slack) + dql->lowest_slack = slack; + + if (time_after(jiffies, + dql->slack_start_time + dql->slack_hold_time)) { + limit = POSDIFF(limit, dql->lowest_slack); + dql->slack_start_time = jiffies; + dql->lowest_slack = UINT_MAX; + } + } + + /* Enforce bounds on limit */ + limit = clamp(limit, dql->min_limit, dql->max_limit); + + if (limit != dql->limit) { + dql->limit = limit; + ovlimit = 0; + } + + dql->adj_limit = limit + completed; + dql->prev_ovlimit = ovlimit; + dql->prev_last_obj_cnt = READ_ONCE(dql->last_obj_cnt); + dql->num_completed = completed; + dql->prev_num_queued = num_queued; + + dql_check_stall(dql, stall_thrs); +} +EXPORT_SYMBOL(dql_completed); + +void dql_reset(struct dql *dql) +{ + /* Reset all dynamic values */ + dql->limit = dql->min_limit; + dql->num_queued = 0; + dql->num_completed = 0; + dql->last_obj_cnt = 0; + dql->prev_num_queued = 0; + dql->prev_last_obj_cnt = 0; + dql->prev_ovlimit = 0; + dql->lowest_slack = UINT_MAX; + dql->slack_start_time = jiffies; + + dql->last_reap = jiffies; + dql->history_head = jiffies / BITS_PER_LONG; + memset(dql->history, 0, sizeof(dql->history)); +} +EXPORT_SYMBOL(dql_reset); + +void dql_init(struct dql *dql, unsigned int hold_time) +{ + dql->max_limit = DQL_MAX_LIMIT; + dql->min_limit = 0; + dql->slack_hold_time = hold_time; + dql->stall_thrs = 0; + dql_reset(dql); +} +EXPORT_SYMBOL(dql_init); -- cgit v1.3.1