When multiple threads are stopped at the same breakpoint, LLDB currently steps each thread over the breakpoint one at a time. Each step requires disabling the breakpoint, single-stepping one thread, and re-enabling it, resulting in N disable/enable cycles and N individual vCont packets for N threads. This is a common scenario for hot breakpoints in multithreaded programs and scales poorly. This patch batches the step-over so that all threads at the same breakpoint site are stepped together in a single vCont packet, with the breakpoint disabled once at the start and re-enabled once after the last thread finishes. At the top of WillResume, any leftover StepOverBreakpoint plans from a previous cycle are popped with their re-enable side effect suppressed via SetReenabledBreakpointSite, giving a clean slate. SetupToStepOverBreakpointIfNeeded then creates fresh plans for all threads that still need to step over a breakpoint, and these are grouped by breakpoint address. For groups with multiple threads, each plan is set to defer its re-enable through SetDeferReenableBreakpointSite. Instead of re-enabling the breakpoint directly when a plan completes, it calls ThreadFinishedSteppingOverBreakpoint, which decrements a per-address tracking count. The breakpoint is only re-enabled when the count reaches zero. All threads in the largest group are resumed together in a single batched vCont packet. If some threads don't complete their step in one cycle, the pop-and-recreate logic naturally re-batches the remaining threads on the next WillResume call. For 10 threads at the same breakpoint, this reduces the operation from 10 z0/Z0 pairs and 10 vCont packets to 1 z0 + 1 Z0 and a few progressively smaller batched vCont packets. EDIT: Tried to merge this PR twice, the first time the test was flaky so we had to revert. The second time, we broke 2 tests on windows machine: https://lab.llvm.org/buildbot/#/builders/141/builds/15798 The tests that were failing were failing because the cleanup code in `WillResume` was popping **ALL** `StepOverBreakpoint` plans, including non-deferred ones from incomplete single-steps. The issue was: 1) Multiple threads hit the same breakpoint. One thread's breakpoint condition evaluates to false, so it needs to auto-continue. 2) A `StepOverBreakpoint` plan is created for that thread (non-deferred). 3) On the next WillResume, the cleanup pops that non-deferred plan. 4) Now the `StopOthers` scan finds no thread with a StopOthers() plan, so thread_to_run stays null. 5) The else branch runs, calling `SetupToStepOverBreakpointIfNeeded` on **ALL** threads, including the thread that legitimately hit the breakpoint with a true condition. 6) That thread gets a new `StepOverBreakpoint` plan pushed, which overwrites its breakpoint stop reason with trace when the step completes. The error `trace (2) != breakpoint (3)` confirms this, the thread that should have reported breakpoint as its stop reason instead reports trace, because an unwanted `StepOverBreakpoint` plan was pushed on it and completed. The newly added code fixes it by only popping plans that have `GetDeferReenableBreakpointSite() == true` Co-authored-by: Bar Soloveychik <barsolo@fb.com>
189 lines
6.9 KiB
C++
189 lines
6.9 KiB
C++
//===-- ThreadPlanStepOverBreakpoint.cpp ----------------------------------===//
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "lldb/Target/ThreadPlanStepOverBreakpoint.h"
|
|
|
|
#include "lldb/Target/Process.h"
|
|
#include "lldb/Target/RegisterContext.h"
|
|
#include "lldb/Target/ThreadList.h"
|
|
#include "lldb/Utility/LLDBLog.h"
|
|
#include "lldb/Utility/Log.h"
|
|
#include "lldb/Utility/Stream.h"
|
|
|
|
using namespace lldb;
|
|
using namespace lldb_private;
|
|
|
|
// ThreadPlanStepOverBreakpoint: Single steps over a breakpoint bp_site_sp at
|
|
// the pc.
|
|
|
|
ThreadPlanStepOverBreakpoint::ThreadPlanStepOverBreakpoint(Thread &thread)
|
|
: ThreadPlan(ThreadPlan::eKindStepOverBreakpoint,
|
|
"Step over breakpoint trap", thread, eVoteNo,
|
|
eVoteNoOpinion), // We need to report the run since this
|
|
// happens first in the thread plan stack when
|
|
// stepping over a breakpoint
|
|
m_breakpoint_addr(LLDB_INVALID_ADDRESS), m_auto_continue(false),
|
|
m_reenabled_breakpoint_site(false),
|
|
m_defer_reenable_breakpoint_site(false)
|
|
|
|
{
|
|
m_breakpoint_addr = thread.GetRegisterContext()->GetPC();
|
|
m_breakpoint_site_id =
|
|
thread.GetProcess()->GetBreakpointSiteList().FindIDByAddress(
|
|
m_breakpoint_addr);
|
|
}
|
|
|
|
ThreadPlanStepOverBreakpoint::~ThreadPlanStepOverBreakpoint() = default;
|
|
|
|
void ThreadPlanStepOverBreakpoint::GetDescription(
|
|
Stream *s, lldb::DescriptionLevel level) {
|
|
s->Printf("Single stepping past breakpoint site %" PRIu64 " at 0x%" PRIx64,
|
|
m_breakpoint_site_id, (uint64_t)m_breakpoint_addr);
|
|
}
|
|
|
|
bool ThreadPlanStepOverBreakpoint::ValidatePlan(Stream *error) { return true; }
|
|
|
|
bool ThreadPlanStepOverBreakpoint::DoPlanExplainsStop(Event *event_ptr) {
|
|
StopInfoSP stop_info_sp = GetPrivateStopInfo();
|
|
if (stop_info_sp) {
|
|
StopReason reason = stop_info_sp->GetStopReason();
|
|
|
|
Log *log = GetLog(LLDBLog::Step);
|
|
LLDB_LOG(log, "Step over breakpoint stopped for reason: {0}.",
|
|
Thread::StopReasonAsString(reason));
|
|
|
|
switch (reason) {
|
|
case eStopReasonTrace:
|
|
case eStopReasonNone:
|
|
return true;
|
|
case eStopReasonBreakpoint:
|
|
{
|
|
// It's a little surprising that we stop here for a breakpoint hit.
|
|
// However, when you single step ONTO a breakpoint we still want to call
|
|
// that a breakpoint hit, and trigger the actions, etc. Otherwise you
|
|
// would see the PC at the breakpoint without having triggered the
|
|
// actions, then you'd continue, the PC wouldn't change, and you'd see
|
|
// the breakpoint hit, which would be odd. So the lower levels fake
|
|
// "step onto breakpoint address" and return that as a breakpoint hit.
|
|
// So our trace step COULD appear as a breakpoint hit if the next
|
|
// instruction also contained a breakpoint. We don't want to handle
|
|
// that, since we really don't know what to do with breakpoint hits.
|
|
// But make sure we don't set ourselves to auto-continue or we'll wrench
|
|
// control away from the plans that can deal with this.
|
|
// Be careful, however, as we may have "seen a breakpoint under the PC
|
|
// because we stopped without changing the PC, in which case we do want
|
|
// to re-claim this stop so we'll try again.
|
|
lldb::addr_t pc_addr = GetThread().GetRegisterContext()->GetPC();
|
|
|
|
if (pc_addr == m_breakpoint_addr) {
|
|
LLDB_LOGF(log,
|
|
"Got breakpoint stop reason but pc: 0x%" PRIx64
|
|
"hasn't changed.",
|
|
pc_addr);
|
|
return true;
|
|
}
|
|
|
|
SetAutoContinue(false);
|
|
return false;
|
|
}
|
|
default:
|
|
return false;
|
|
}
|
|
}
|
|
return false;
|
|
}
|
|
|
|
bool ThreadPlanStepOverBreakpoint::ShouldStop(Event *event_ptr) {
|
|
return !ShouldAutoContinue(event_ptr);
|
|
}
|
|
|
|
bool ThreadPlanStepOverBreakpoint::StopOthers() { return true; }
|
|
|
|
// This thread plan does a single instruction step over a breakpoint instruction
|
|
// and needs to not resume other threads, so return false to stop the
|
|
// ThreadPlanSingleThreadTimeout from timing out and trying to resume all
|
|
// threads. If all threads gets resumed before we disable, single step and
|
|
// re-enable the breakpoint, we can miss breakpoints on other threads.
|
|
bool ThreadPlanStepOverBreakpoint::SupportsResumeOthers() { return false; }
|
|
|
|
StateType ThreadPlanStepOverBreakpoint::GetPlanRunState() {
|
|
return eStateStepping;
|
|
}
|
|
|
|
bool ThreadPlanStepOverBreakpoint::DoWillResume(StateType resume_state,
|
|
bool current_plan) {
|
|
if (current_plan) {
|
|
BreakpointSiteSP bp_site_sp(
|
|
m_process.GetBreakpointSiteList().FindByAddress(m_breakpoint_addr));
|
|
if (bp_site_sp && bp_site_sp->IsEnabled()) {
|
|
m_process.DisableBreakpointSite(bp_site_sp.get());
|
|
m_reenabled_breakpoint_site = false;
|
|
}
|
|
}
|
|
return true;
|
|
}
|
|
|
|
bool ThreadPlanStepOverBreakpoint::WillStop() {
|
|
ReenableBreakpointSite();
|
|
return true;
|
|
}
|
|
|
|
void ThreadPlanStepOverBreakpoint::DidPop() { ReenableBreakpointSite(); }
|
|
|
|
bool ThreadPlanStepOverBreakpoint::MischiefManaged() {
|
|
lldb::addr_t pc_addr = GetThread().GetRegisterContext()->GetPC();
|
|
|
|
if (pc_addr == m_breakpoint_addr) {
|
|
// If we are still at the PC of our breakpoint, then for some reason we
|
|
// didn't get a chance to run.
|
|
return false;
|
|
} else {
|
|
Log *log = GetLog(LLDBLog::Step);
|
|
LLDB_LOGF(log, "Completed step over breakpoint plan.");
|
|
// Otherwise, re-enable the breakpoint we were stepping over, and we're
|
|
// done.
|
|
ReenableBreakpointSite();
|
|
ThreadPlan::MischiefManaged();
|
|
return true;
|
|
}
|
|
}
|
|
|
|
void ThreadPlanStepOverBreakpoint::ReenableBreakpointSite() {
|
|
if (!m_reenabled_breakpoint_site) {
|
|
m_reenabled_breakpoint_site = true;
|
|
|
|
if (m_defer_reenable_breakpoint_site) {
|
|
// Let ThreadList track all threads stepping over this breakpoint.
|
|
// It will re-enable the breakpoint only when ALL threads have finished.
|
|
m_process.GetThreadList().ThreadFinishedSteppingOverBreakpoint(
|
|
m_breakpoint_addr, GetThread().GetID());
|
|
} else {
|
|
// Default behavior: re-enable the breakpoint directly.
|
|
if (BreakpointSiteSP bp_site_sp =
|
|
m_process.GetBreakpointSiteList().FindByAddress(
|
|
m_breakpoint_addr))
|
|
m_process.EnableBreakpointSite(bp_site_sp.get());
|
|
}
|
|
}
|
|
}
|
|
void ThreadPlanStepOverBreakpoint::ThreadDestroyed() {
|
|
ReenableBreakpointSite();
|
|
}
|
|
|
|
void ThreadPlanStepOverBreakpoint::SetAutoContinue(bool do_it) {
|
|
m_auto_continue = do_it;
|
|
}
|
|
|
|
bool ThreadPlanStepOverBreakpoint::ShouldAutoContinue(Event *event_ptr) {
|
|
return m_auto_continue;
|
|
}
|
|
|
|
bool ThreadPlanStepOverBreakpoint::IsPlanStale() {
|
|
return GetThread().GetRegisterContext()->GetPC() != m_breakpoint_addr;
|
|
}
|