Android Input流程分析(四):InputDispatcher

本文详细解析了Android系统中按键事件从硬件输入到View接收的整个处理流程,包括InputDispatcher的角色与职责、按键事件的拦截与分发机制、以及InputChannel在窗口与系统间通信中的作用。

  之前提到,InputReader将Key的信息封装成一个NotifyKeyArgs对象,调用InputDispatcher的notifyKey来处理。再进行一些初步的处理后,将个NotifyKeyArgs对象拆包,得到的信息构成一个KeyEvent,并调用interceptKeyBeforeQueueing进行第一次事件拦截,该函数最终会调到java层PhoneWindowManager的interceptKeyBeforeQueueing函数,对一些系统特殊按键进行处理。该函数会返回一个result,如果result带有ACTION_PASS_TO_USER标志位,说明在这次的事件拦截中没有被过滤;如果没有ACTION_PASS_TO_USER标志位,则说明按键在这次事件拦截中被过滤处理掉了。这个ACTION_PASS_TO_USER标志位将被记录在Native层interceptKeyBeforeQueueing函数第二个参数policyFlags中。接下来构造一个KeyEntry,将这个KeyEntry通过enqueueInboundEventLocked加入到mInboundQueue这个Queue< EventEntry>中。每次InputReader推送NotifyKeyArgs对象过来而且mInboundQueue为空时,就会调用wake函数唤醒mLooper,wake函数就是往mWakeEventFd表示的fd写入一个数字进行唤醒。

/frameworks/native/services/inputflinger/InputDispatcher.cpp

void InputDispatcher::notifyKey(const NotifyKeyArgs* args) {
#if DEBUG_INBOUND_EVENT_DETAILS
    ALOGD("notifyKey - eventTime=%lld, deviceId=%d, source=0x%x, policyFlags=0x%x, action=0x%x, "
            "flags=0x%x, keyCode=0x%x, scanCode=0x%x, metaState=0x%x, downTime=%lld",
            args->eventTime, args->deviceId, args->source, args->policyFlags,
            args->action, args->flags, args->keyCode, args->scanCode,
            args->metaState, args->downTime);
#endif
    if (!validateKeyEvent(args->action)) {
        return;
    }

    uint32_t policyFlags = args->policyFlags;
    int32_t flags = args->flags;
    int32_t metaState = args->metaState;
    if ((policyFlags & POLICY_FLAG_VIRTUAL) || (flags & AKEY_EVENT_FLAG_VIRTUAL_HARD_KEY)) {
        policyFlags |= POLICY_FLAG_VIRTUAL;
        flags |= AKEY_EVENT_FLAG_VIRTUAL_HARD_KEY;
    }
    if (policyFlags & POLICY_FLAG_FUNCTION) {
        metaState |= AMETA_FUNCTION_ON;
    }

    policyFlags |= POLICY_FLAG_TRUSTED;

    int32_t keyCode = args->keyCode;
    if (metaState & AMETA_META_ON && args->action == AKEY_EVENT_ACTION_DOWN) {
        int32_t newKeyCode = AKEYCODE_UNKNOWN;
        if (keyCode == AKEYCODE_DEL) {
            newKeyCode = AKEYCODE_BACK;
        } else if (keyCode == AKEYCODE_ENTER) {
            newKeyCode = AKEYCODE_HOME;
        }
        if (newKeyCode != AKEYCODE_UNKNOWN) {
            AutoMutex _l(mLock);
            struct KeyReplacement replacement = {keyCode, args->deviceId};
            mReplacedKeys.add(replacement, newKeyCode);
            keyCode = newKeyCode;
            metaState &= ~AMETA_META_ON;
        }
    } else if (args->action == AKEY_EVENT_ACTION_UP) {
        // In order to maintain a consistent stream of up and down events, check to see if the key
        // going up is one we've replaced in a down event and haven't yet replaced in an up event,
        // even if the modifier was released between the down and the up events.
        AutoMutex _l(mLock);
        struct KeyReplacement replacement = {keyCode, args->deviceId};
        ssize_t index = mReplacedKeys.indexOfKey(replacement);
        if (index >= 0) {
            keyCode = mReplacedKeys.valueAt(index);
            mReplacedKeys.removeItemsAt(index);
            metaState &= ~AMETA_META_ON;
        }
    }

    KeyEvent event;
    event.initialize(args->deviceId, args->source, args->action,
            flags, keyCode, args->scanCode, metaState, 0,
            args->downTime, args->eventTime);

    mPolicy->interceptKeyBeforeQueueing(&event, /*byref*/ policyFlags);

    bool needWake;
    { // acquire lock
        mLock.lock();

        if (shouldSendKeyToInputFilterLocked(args)) {
            mLock.unlock();

            policyFlags |= POLICY_FLAG_FILTERED;
            if (!mPolicy->filterInputEvent(&event, policyFlags)) {
                return; // event was consumed by the filter
            }

            mLock.lock();
        }

        int32_t repeatCount = 0;
        KeyEntry* newEntry = new KeyEntry(args->eventTime,
                args->deviceId, args->source, policyFlags,
                args->action, flags, keyCode, args->scanCode,
                metaState, repeatCount, args->downTime);

        needWake = enqueueInboundEventLocked(newEntry);
        mLock.unlock();
    } // release lock

    if (needWake) {
        mLooper->wake();
    }
}

  InputDispatcher是在一个threadLoop循环中执行dispatchOnce函数的。haveCommandsLocked判断mCommandQueue是否不为空。这里假设是在首次执行dispatchOnce函数时,mCommandQueue理应为空,dispatchOnceInnerLocked函数会被执行。

/frameworks/native/services/inputflinger/InputDispatcher.cpp

void InputDispatcher::dispatchOnce() {
    nsecs_t nextWakeupTime = LONG_LONG_MAX;
    { // acquire lock
        AutoMutex _l(mLock);
        mDispatcherIsAliveCondition.broadcast();

        // Run a dispatch loop if there are no pending commands.
        // The dispatch loop might enqueue commands to run afterwards.
        if (!haveCommandsLocked()) {
            dispatchOnceInnerLocked(&nextWakeupTime);
        }

        // Run all pending commands if there are any.
        // If any commands were run then force the next poll to wake up immediately.
        if (runCommandsLockedInterruptible()) {
            nextWakeupTime = LONG_LONG_MIN;
        }
    } // release lock

    // Wait for callback or timeout or wake.  (make sure we round up, not down)
    nsecs_t currentTime = now();
    int timeoutMillis = toMillisecondTimeoutDelay(currentTime, nextWakeupTime);
    mLooper->pollOnce(timeoutMillis);
}

  这里会取出mInboundQueue队列头的KeyEntry作为mPendingEvent继续往后处理。随后通过pokeUserActivityLocked将InputDispatcher::doPokeUserActivityLockedInterruptible函数推入到mCommandQueue里面。
  接下来根据情况设置按键丢弃标志。凡是在第一次事件拦截中没有被加上POLICY_FLAG_PASS_TO_USER的Key,其dropReason会被设为DROP_REASON_POLICY。还有一些规则可以细看一下。

/frameworks/native/services/inputflinger/InputDispatcher.cpp

void InputDispatcher::dispatchOnceInnerLocked(nsecs_t* nextWakeupTime) {
    nsecs_t currentTime = now();

    // Reset the key repeat timer whenever normal dispatch is suspended while the
    // device is in a non-interactive state.  This is to ensure that we abort a key
    // repeat if the device is just coming out of sleep.
    if (!mDispatchEnabled) {
        resetKeyRepeatLocked();
    }

    // If dispatching is frozen, do not process timeouts or try to deliver any new events.
    if (mDispatchFrozen) {
#if DEBUG_FOCUS
        ALOGD("Dispatch frozen.  Waiting some more.");
#endif
        return;
    }

    // Optimize latency of app switches.
    // Essentially we start a short timeout when an app switch key (HOME / ENDCALL) has
    // been pressed.  When it expires, we preempt dispatch and drop all other pending events.
    bool isAppSwitchDue = mAppSwitchDueTime <= currentTime;
    if (mAppSwitchDueTime < *nextWakeupTime) {
        *nextWakeupTime = mAppSwitchDueTime;
    }

    // Ready to start a new event.
    // If we don't already have a pending event, go grab one.
    if (! mPendingEvent) {
        if (mInboundQueue.isEmpty()) {
            if (isAppSwitchDue) {
                // The inbound queue is empty so the app switch key we were waiting
                // for will never arrive.  Stop waiting for it.
                resetPendingAppSwitchLocked(false);
                isAppSwitchDue = false;
            }

            // Synthesize a key repeat if appropriate.
            if (mKeyRepeatState.lastKeyEntry) {
                if (currentTime >= mKeyRepeatState.nextRepeatTime) {
                    mPendingEvent = synthesizeKeyRepeatLocked(currentTime);
                } else {
                    if (mKeyRepeatState.nextRepeatTime < *nextWakeupTime) {
                        *nextWakeupTime = mKeyRepeatState.nextRepeatTime;
                    }
                }
            }

            // Nothing to do if there is no pending event.
            if (!mPendingEvent) {
                return;
            }
        } else {
            // Inbound queue has at least one entry.
            mPendingEvent = mInboundQueue.dequeueAtHead();
            traceInboundQueueLengthLocked();
        }

        // Poke user activity for this event.
        if (mPendingEvent->policyFlags & POLICY_FLAG_PASS_TO_USER) {
            pokeUserActivityLocked(mPendingEvent);
        }

        // Get ready to dispatch the event.
        resetANRTimeoutsLocked();
    }

    // Now we have an event to dispatch.
    // All events are eventually dequeued and processed this way, even if we intend to drop them.
    ALOG_ASSERT(mPendingEvent != NULL);
    bool done = false;
    DropReason dropReason = DROP_REASON_NOT_DROPPED;
    if (!(mPendingEvent->policyFlags & POLICY_FLAG_PASS_TO_USER)) {
        dropReason = DROP_REASON_POLICY;
    } else if (!mDispatchEnabled) {
        dropReason = DROP_REASON_DISABLED;
    }

    if (mNextUnblockedEvent == mPendingEvent) {
        mNextUnblockedEvent = NULL;
    }

    switch (mPendingEvent->type) {
    case EventEntry::TYPE_CONFIGURATION_CHANGED: {
        ConfigurationChangedEntry* typedEntry =
                static_cast<ConfigurationChangedEntry*>(mPendingEvent);
        done = dispatchConfigurationChangedLocked(currentTime, typedEntry);
        dropReason = DROP_REASON_NOT_DROPPED; // configuration changes are never dropped
        break;
    }

    case EventEntry::TYPE_DEVICE_RESET: {
        DeviceResetEntry* typedEntry =
                static_cast<DeviceResetEntry*>(mPendingEvent);
        done = dispatchDeviceResetLocked(currentTime, typedEntry);
        dropReason = DROP_REASON_NOT_DROPPED; // device resets are never dropped
        break;
    }

    case EventEntry::TYPE_KEY: {
        KeyEntry* typedEntry = static_cast<KeyEntry*>(mPendingEvent);
        if (isAppSwitchDue) {
            if (isAppSwitchKeyEventLocked(typedEntry)) {
                resetPendingAppSwitchLocked(true);
                isAppSwitchDue = false;
            } else if (dropReason == DROP_REASON_NOT_DROPPED) {
                dropReason = DROP_REASON_APP_SWITCH;
            }
        }
        if (dropReason == DROP_REASON_NOT_DROPPED
                && isStaleEventLocked(currentTime, typedEntry)) {
            dropReason = DROP_REASON_STALE;
        }
        if (dropReason == DROP_REASON_NOT_DROPPED && mNextUnblockedEvent) {
            dropReason = DROP_REASON_BLOCKED;
        }
        done = dispatchKeyLocked(currentTime, typedEntry, &dropReason, nextWakeupTime);
        break;
    }

    case EventEntry::TYPE_MOTION: {
        MotionEntry* typedEntry = static_cast<MotionEntry*>(mPendingEvent);
        if (dropReason == DROP_REASON_NOT_DROPPED && isAppSwitchDue) {
            dropReason = DROP_REASON_APP_SWITCH;
        }
        if (dropReason == DROP_REASON_NOT_DROPPED
                && isStaleEventLocked(currentTime, typedEntry)) {
            dropReason = DROP_REASON_STALE;
        }
        if (dropReason == DROP_REASON_NOT_DROPPED && mNextUnblockedEvent) {
            dropReason = DROP_REASON_BLOCKED;
        }
        done = dispatchMotionLocked(currentTime, typedEntry,
                &dropReason, nextWakeupTime);
        break;
    }

    default:
        ALOG_ASSERT(false);
        break;
    }

    if (done) {
        if (dropReason != DROP_REASON_NOT_DROPPED) {
            dropInboundEventLocked(mPendingEvent, dropReason);
        }
        mLastDropReason = dropReason;

        releasePendingEventLocked();
        *nextWakeupTime = LONG_LONG_MIN;  // force next poll to wake up immediately
    }
}

  不管是会被丢弃的按键还是保留的按键,都会进入到dispatchKeyLocked函数中。前面是生成重复按键事件,在 mConfig.keyRepeatTimeout时间内同一个按键被按下会被视为重复按键事件,即是长按事件,通过其repeatCount成员是否大于1体现。接着会将doInterceptKeyBeforeDispatchingLockedInterruptible推入到mCommandQueue中,这是第二次执行时间拦截的函数。findFocusedWindowTargetsLocked接受当前焦点窗口句柄mFocusedWindowHandle为参数,构造出一个InputTarget,push到inputTargets中去。

/frameworks/native/services/inputflinger/InputDispatcher.cpp

bool InputDispatcher::dispatchKeyLocked(nsecs_t currentTime, KeyEntry* entry,
        DropReason* dropReason, nsecs_t* nextWakeupTime) {
    // Preprocessing.
    if (! entry->dispatchInProgress) {
        if (entry->repeatCount == 0
                && entry->action == AKEY_EVENT_ACTION_DOWN
                && (entry->policyFlags & POLICY_FLAG_TRUSTED)
                && (!(entry->policyFlags & POLICY_FLAG_DISABLE_KEY_REPEAT))) {
            if (mKeyRepeatState.lastKeyEntry
                    && mKeyRepeatState.lastKeyEntry->keyCode == entry->keyCode) {
                // We have seen two identical key downs in a row which indicates that the device
                // driver is automatically generating key repeats itself.  We take note of the
                // repeat here, but we disable our own next key repeat timer since it is clear that
                // we will not need to synthesize key repeats ourselves.
                entry->repeatCount = mKeyRepeatState.lastKeyEntry->repeatCount + 1;
                resetKeyRepeatLocked();
                mKeyRepeatState.nextRepeatTime = LONG_LONG_MAX; // don't generate repeats ourselves
            } else {
                // Not a repeat.  Save key down state in case we do see a repeat later.
                resetKeyRepeatLocked();
                mKeyRepeatState.nextRepeatTime = entry->eventTime + mConfig.keyRepeatTimeout;
            }
            mKeyRepeatState.lastKeyEntry = entry;
            entry->refCount += 1;
        } else if (! entry->syntheticRepeat) {
            resetKeyRepeatLocked();
        }

        if (entry->repeatCount == 1) {
            entry->flags |= AKEY_EVENT_FLAG_LONG_PRESS;
        } else {
            entry->flags &= ~AKEY_EVENT_FLAG_LONG_PRESS;
        }

        entry->dispatchInProgress = true;

        logOutboundKeyDetailsLocked("dispatchKey - ", entry);
    }

    // Handle case where the policy asked us to try again later last time.
    if (entry->interceptKeyResult == KeyEntry::INTERCEPT_KEY_RESULT_TRY_AGAIN_LATER) {
        if (currentTime < entry->interceptKeyWakeupTime) {
            if (entry->interceptKeyWakeupTime < *nextWakeupTime) {
                *nextWakeupTime = entry->interceptKeyWakeupTime;
            }
            return false; // wait until next wakeup
        }
        entry->interceptKeyResult = KeyEntry::INTERCEPT_KEY_RESULT_UNKNOWN;
        entry->interceptKeyWakeupTime = 0;
    }

    // Give the policy a chance to intercept the key.
    if (entry->interceptKeyResult == KeyEntry::INTERCEPT_KEY_RESULT_UNKNOWN) {
        if (entry->policyFlags & POLICY_FLAG_PASS_TO_USER) {
            CommandEntry* commandEntry = postCommandLocked(
                    & InputDispatcher::doInterceptKeyBeforeDispatchingLockedInterruptible);
            if (mFocusedWindowHandle != NULL) {
                commandEntry->inputWindowHandle = mFocusedWindowHandle;
            }
            commandEntry->keyEntry = entry;
            entry->refCount += 1;
            return false; // wait for the command to run
        } else {
            entry->interceptKeyResult = KeyEntry::INTERCEPT_KEY_RESULT_CONTINUE;
        }
    } else if (entry->interceptKeyResult == KeyEntry::INTERCEPT_KEY_RESULT_SKIP) {
        if (*dropReason == DROP_REASON_NOT_DROPPED) {
            *dropReason = DROP_REASON_POLICY;
        }
    }

    // Clean up if dropping the event.
    if (*dropReason != DROP_REASON_NOT_DROPPED) {
        setInjectionResultLocked(entry, *dropReason == DROP_REASON_POLICY
                ? INPUT_EVENT_INJECTION_SUCCEEDED : INPUT_EVENT_INJECTION_FAILED);
        return true;
    }

    // Identify targets.
    Vector<InputTarget> inputTargets;
    int32_t injectionResult = findFocusedWindowTargetsLocked(currentTime,
            entry, inputTargets, nextWakeupTime);
    if (injectionResult == INPUT_EVENT_INJECTION_PENDING) {
        return false;
    }

    setInjectionResultLocked(entry, injectionResult);
    if (injectionResult != INPUT_EVENT_INJECTION_SUCCEEDED) {
        return true;
    }

    addMonitoringTargetsLocked(inputTargets);

    // Dispatch the key.
    dispatchEventLocked(currentTime, entry, inputTargets);
    return true;
}

  dispatchEventLocked会遍历inputTargets中所有InputTarget,每个InputTarget都对应着一个InputChannel,每个InputChannel对应着一个Connection,代表着InputDispatcher和Window的联系纽带。

/frameworks/native/services/inputflinger/InputDispatcher.cpp

void InputDispatcher::dispatchEventLocked(nsecs_t currentTime,
        EventEntry* eventEntry, const Vector<InputTarget>& inputTargets) {
#if DEBUG_DISPATCH_CYCLE
    ALOGD("dispatchEventToCurrentInputTargets");
#endif

    ALOG_ASSERT(eventEntry->dispatchInProgress); // should already have been set to true

    pokeUserActivityLocked(eventEntry);

    for (size_t i = 0; i < inputTargets.size(); i++) {
        const InputTarget& inputTarget = inputTargets.itemAt(i);

        ssize_t connectionIndex = getConnectionIndexLocked(inputTarget.inputChannel);
        if (connectionIndex >= 0) {
            sp<Connection> connection = mConnectionsByFd.valueAt(connectionIndex);
            prepareDispatchCycleLocked(currentTime, connection, eventEntry, &inputTarget);
        } else {
#if DEBUG_FOCUS
            ALOGD("Dropping event delivery to target with channel '%s' because it "
                    "is no longer registered with the input dispatcher.",
                    inputTarget.inputChannel->getName().string());
#endif
        }
    }
}

  直接看enqueueDispatchEntriesLocked。

/frameworks/native/services/inputflinger/InputDispatcher.cpp

void InputDispatcher::prepareDispatchCycleLocked(nsecs_t currentTime,
        const sp<Connection>& connection, EventEntry* eventEntry, const InputTarget* inputTarget) {
#if DEBUG_DISPATCH_CYCLE
    ALOGD("channel '%s' ~ prepareDispatchCycle - flags=0x%08x, "
            "xOffset=%f, yOffset=%f, scaleFactor=%f, "
            "pointerIds=0x%x",
            connection->getInputChannelName(), inputTarget->flags,
            inputTarget->xOffset, inputTarget->yOffset,
            inputTarget->scaleFactor, inputTarget->pointerIds.value);
#endif

    // Skip this event if the connection status is not normal.
    // We don't want to enqueue additional outbound events if the connection is broken.
    if (connection->status != Connection::STATUS_NORMAL) {
#if DEBUG_DISPATCH_CYCLE
        ALOGD("channel '%s' ~ Dropping event because the channel status is %s",
                connection->getInputChannelName(), connection->getStatusLabel());
#endif
        return;
    }

    // Split a motion event if needed.
    if (inputTarget->flags & InputTarget::FLAG_SPLIT) {
        ALOG_ASSERT(eventEntry->type == EventEntry::TYPE_MOTION);

        MotionEntry* originalMotionEntry = static_cast<MotionEntry*>(eventEntry);
        if (inputTarget->pointerIds.count() != originalMotionEntry->pointerCount) {
            MotionEntry* splitMotionEntry = splitMotionEvent(
                    originalMotionEntry, inputTarget->pointerIds);
            if (!splitMotionEntry) {
                return; // split event was dropped
            }
#if DEBUG_FOCUS
            ALOGD("channel '%s' ~ Split motion event.",
                    connection->getInputChannelName());
            logOutboundMotionDetailsLocked("  ", splitMotionEntry);
#endif
            enqueueDispatchEntriesLocked(currentTime, connection,
                    splitMotionEntry, inputTarget);
            splitMotionEntry->release();
            return;
        }
    }

    // Not splitting.  Enqueue dispatch entries for the event as is.
    enqueueDispatchEntriesLocked(currentTime, connection, eventEntry, inputTarget);
}

  enqueueDispatchEntriesLocked将构建一个DispatchEntry,push到Connection的outboundQueue队列中。如果Connection对应的outboundQueue之前为空,现在不为空的话,调用startDispatchCycleLocked进入推送过程。

/frameworks/native/services/inputflinger/InputDispatcher.cpp

void InputDispatcher::enqueueDispatchEntriesLocked(nsecs_t currentTime,
        const sp<Connection>& connection, EventEntry* eventEntry, const InputTarget* inputTarget) {
    bool wasEmpty = connection->outboundQueue.isEmpty();

    // Enqueue dispatch entries for the requested modes.
    enqueueDispatchEntryLocked(connection, eventEntry, inputTarget,
            InputTarget::FLAG_DISPATCH_AS_HOVER_EXIT);
    enqueueDispatchEntryLocked(connection, eventEntry, inputTarget,
            InputTarget::FLAG_DISPATCH_AS_OUTSIDE);
    enqueueDispatchEntryLocked(connection, eventEntry, inputTarget,
            InputTarget::FLAG_DISPATCH_AS_HOVER_ENTER);
    enqueueDispatchEntryLocked(connection, eventEntry, inputTarget,
            InputTarget::FLAG_DISPATCH_AS_IS);
    enqueueDispatchEntryLocked(connection, eventEntry, inputTarget,
            InputTarget::FLAG_DISPATCH_AS_SLIPPERY_EXIT);
    enqueueDispatchEntryLocked(connection, eventEntry, inputTarget,
            InputTarget::FLAG_DISPATCH_AS_SLIPPERY_ENTER);

    // If the outbound queue was previously empty, start the dispatch cycle going.
    if (wasEmpty && !connection->outboundQueue.isEmpty()) {
        startDispatchCycleLocked(currentTime, connection);
    }
}

/frameworks/native/services/inputflinger/InputDispatcher.cpp

void InputDispatcher::enqueueDispatchEntryLocked(
        const sp<Connection>& connection, EventEntry* eventEntry, const InputTarget* inputTarget,
        int32_t dispatchMode) {
    int32_t inputTargetFlags = inputTarget->flags;
    if (!(inputTargetFlags & dispatchMode)) {
        return;
    }
    inputTargetFlags = (inputTargetFlags & ~InputTarget::FLAG_DISPATCH_MASK) | dispatchMode;

    // This is a new event.
    // Enqueue a new dispatch entry onto the outbound queue for this connection.
    DispatchEntry* dispatchEntry = new DispatchEntry(eventEntry, // increments ref
            inputTargetFlags, inputTarget->xOffset, inputTarget->yOffset,
            inputTarget->scaleFactor);

    // Apply target flags and update the connection's input state.
    switch (eventEntry->type) {
    case EventEntry::TYPE_KEY: {
        KeyEntry* keyEntry = static_cast<KeyEntry*>(eventEntry);
        dispatchEntry->resolvedAction = keyEntry->action;
        dispatchEntry->resolvedFlags = keyEntry->flags;

        if (!connection->inputState.trackKey(keyEntry,
                dispatchEntry->resolvedAction, dispatchEntry->resolvedFlags)) {
#if DEBUG_DISPATCH_CYCLE
            ALOGD("channel '%s' ~ enqueueDispatchEntryLocked: skipping inconsistent key event",
                    connection->getInputChannelName());
#endif
            delete dispatchEntry;
            return; // skip the inconsistent event
        }
        break;
    }

    case EventEntry::TYPE_MOTION: {
        MotionEntry* motionEntry = static_cast<MotionEntry*>(eventEntry);
        if (dispatchMode & InputTarget::FLAG_DISPATCH_AS_OUTSIDE) {
            dispatchEntry->resolvedAction = AMOTION_EVENT_ACTION_OUTSIDE;
        } else if (dispatchMode & InputTarget::FLAG_DISPATCH_AS_HOVER_EXIT) {
            dispatchEntry->resolvedAction = AMOTION_EVENT_ACTION_HOVER_EXIT;
        } else if (dispatchMode & InputTarget::FLAG_DISPATCH_AS_HOVER_ENTER) {
            dispatchEntry->resolvedAction = AMOTION_EVENT_ACTION_HOVER_ENTER;
        } else if (dispatchMode & InputTarget::FLAG_DISPATCH_AS_SLIPPERY_EXIT) {
            dispatchEntry->resolvedAction = AMOTION_EVENT_ACTION_CANCEL;
        } else if (dispatchMode & InputTarget::FLAG_DISPATCH_AS_SLIPPERY_ENTER) {
            dispatchEntry->resolvedAction = AMOTION_EVENT_ACTION_DOWN;
        } else {
            dispatchEntry->resolvedAction = motionEntry->action;
        }
        if (dispatchEntry->resolvedAction == AMOTION_EVENT_ACTION_HOVER_MOVE
                && !connection->inputState.isHovering(
                        motionEntry->deviceId, motionEntry->source, motionEntry->displayId)) {
#if DEBUG_DISPATCH_CYCLE
        ALOGD("channel '%s' ~ enqueueDispatchEntryLocked: filling in missing hover enter event",
                connection->getInputChannelName());
#endif
            dispatchEntry->resolvedAction = AMOTION_EVENT_ACTION_HOVER_ENTER;
        }

        dispatchEntry->resolvedFlags = motionEntry->flags;
        if (dispatchEntry->targetFlags & InputTarget::FLAG_WINDOW_IS_OBSCURED) {
            dispatchEntry->resolvedFlags |= AMOTION_EVENT_FLAG_WINDOW_IS_OBSCURED;
        }

        if (!connection->inputState.trackMotion(motionEntry,
                dispatchEntry->resolvedAction, dispatchEntry->resolvedFlags)) {
#if DEBUG_DISPATCH_CYCLE
            ALOGD("channel '%s' ~ enqueueDispatchEntryLocked: skipping inconsistent motion event",
                    connection->getInputChannelName());
#endif
            delete dispatchEntry;
            return; // skip the inconsistent event
        }
        break;
    }
    }

    // Remember that we are waiting for this dispatch to complete.
    if (dispatchEntry->hasForegroundTarget()) {
        incrementPendingForegroundDispatchesLocked(eventEntry);
    }

    // Enqueue the dispatch entry.
    connection->outboundQueue.enqueueAtTail(dispatchEntry);
    traceOutboundQueueLengthLocked(connection);

  startDispatchCycleLocked会取出outboundQueue中的每一个对应的DispatchEntry,使用Connection的InputPublisher的publishKeyEvent函数将这个DispatchEntry携带的信息组合成一个InputMessage,推送到InputChannel中。

/frameworks/native/services/inputflinger/InputDispatcher.cpp

void InputDispatcher::startDispatchCycleLocked(nsecs_t currentTime,
        const sp<Connection>& connection) {
#if DEBUG_DISPATCH_CYCLE
    ALOGD("channel '%s' ~ startDispatchCycle",
            connection->getInputChannelName());
#endif

    while (connection->status == Connection::STATUS_NORMAL
            && !connection->outboundQueue.isEmpty()) {
        DispatchEntry* dispatchEntry = connection->outboundQueue.head;
        dispatchEntry->deliveryTime = currentTime;

        // Publish the event.
        status_t status;
        EventEntry* eventEntry = dispatchEntry->eventEntry;
        switch (eventEntry->type) {
        case EventEntry::TYPE_KEY: {
            KeyEntry* keyEntry = static_cast<KeyEntry*>(eventEntry);

            // Publish the key event.
            status = connection->inputPublisher.publishKeyEvent(dispatchEntry->seq,
                    keyEntry->deviceId, keyEntry->source,
                    dispatchEntry->resolvedAction, dispatchEntry->resolvedFlags,
                    keyEntry->keyCode, keyEntry->scanCode,
                    keyEntry->metaState, keyEntry->repeatCount, keyEntry->downTime,
                    keyEntry->eventTime);
            break;
        }

        case EventEntry::TYPE_MOTION: {
            MotionEntry* motionEntry = static_cast<MotionEntry*>(eventEntry);

            PointerCoords scaledCoords[MAX_POINTERS];
            const PointerCoords* usingCoords = motionEntry->pointerCoords;

            // Set the X and Y offset depending on the input source.
            float xOffset, yOffset, scaleFactor;
            if ((motionEntry->source & AINPUT_SOURCE_CLASS_POINTER)
                    && !(dispatchEntry->targetFlags & InputTarget::FLAG_ZERO_COORDS)) {
                scaleFactor = dispatchEntry->scaleFactor;
                xOffset = dispatchEntry->xOffset * scaleFactor;
                yOffset = dispatchEntry->yOffset * scaleFactor;
                if (scaleFactor != 1.0f) {
                    for (uint32_t i = 0; i < motionEntry->pointerCount; i++) {
                        scaledCoords[i] = motionEntry->pointerCoords[i];
                        scaledCoords[i].scale(scaleFactor);
                    }
                    usingCoords = scaledCoords;
                }
            } else {
                xOffset = 0.0f;
                yOffset = 0.0f;
                scaleFactor = 1.0f;

                // We don't want the dispatch target to know.
                if (dispatchEntry->targetFlags & InputTarget::FLAG_ZERO_COORDS) {
                    for (uint32_t i = 0; i < motionEntry->pointerCount; i++) {
                        scaledCoords[i].clear();
                    }
                    usingCoords = scaledCoords;
                }
            }

            // Publish the motion event.
            status = connection->inputPublisher.publishMotionEvent(dispatchEntry->seq,
                    motionEntry->deviceId, motionEntry->source,
                    dispatchEntry->resolvedAction, motionEntry->actionButton,
                    dispatchEntry->resolvedFlags, motionEntry->edgeFlags,
                    motionEntry->metaState, motionEntry->buttonState,
                    xOffset, yOffset, motionEntry->xPrecision, motionEntry->yPrecision,
                    motionEntry->downTime, motionEntry->eventTime,
                    motionEntry->pointerCount, motionEntry->pointerProperties,
                    usingCoords);
            break;
        }

        default:
            ALOG_ASSERT(false);
            return;
        }

        // Check the result.
        if (status) {
            if (status == WOULD_BLOCK) {
                if (connection->waitQueue.isEmpty()) {
                    ALOGE("channel '%s' ~ Could not publish event because the pipe is full. "
                            "This is unexpected because the wait queue is empty, so the pipe "
                            "should be empty and we shouldn't have any problems writing an "
                            "event to it, status=%d", connection->getInputChannelName(), status);
                    abortBrokenDispatchCycleLocked(currentTime, connection, true /*notify*/);
                } else {
                    // Pipe is full and we are waiting for the app to finish process some events
                    // before sending more events to it.
#if DEBUG_DISPATCH_CYCLE
                    ALOGD("channel '%s' ~ Could not publish event because the pipe is full, "
                            "waiting for the application to catch up",
                            connection->getInputChannelName());
#endif
                    connection->inputPublisherBlocked = true;
                }
            } else {
                ALOGE("channel '%s' ~ Could not publish event due to an unexpected error, "
                        "status=%d", connection->getInputChannelName(), status);
                abortBrokenDispatchCycleLocked(currentTime, connection, true /*notify*/);
            }
            return;
        }

        // Re-enqueue the event on the wait queue.
        connection->outboundQueue.dequeue(dispatchEntry);
        traceOutboundQueueLengthLocked(connection);
        connection->waitQueue.enqueueAtTail(dispatchEntry);
        traceWaitQueueLengthLocked(connection);
    }
}

  在窗口的创建过程中,会通过openInputChannelPair创建一对UNIX域套接字。client端即窗口端保存的是inputChannels[0],server端即应用程序端View保存的inputChannels[1]。这些java层的InputChannel在native有着对应的InputChannel。
  registerInputChannel的作用是注册InputChanel。在往下调注册InputChannel的时候,会new一个Connection,标示一对连接,并且会将对应的fd和Connection作为键值对保存到mConnectionsByFd中。Connection的构造函数会new一个inputPublisher。所以Connection含有输入窗口句柄InputWindowHandle,连接纽带InputChannel,推送工具InputPublisher,Key保存队列Queue< DispatchEntry>和Key等待队列Queue< DispatchEntry>等成员。

/frameworks/base/services/core/java/com/android/server/wm/WindowManagerService.java

    public int addWindow(Session session, IWindow client, int seq,
            WindowManager.LayoutParams attrs, int viewVisibility, int displayId,
            Rect outContentInsets, Rect outStableInsets, Rect outOutsets,
            InputChannel outInputChannel) {
            ...
            if (outInputChannel != null && (attrs.inputFeatures
                    & WindowManager.LayoutParams.INPUT_FEATURE_NO_INPUT_CHANNEL) == 0) {
                String name = win.makeInputChannelName();
                InputChannel[] inputChannels = InputChannel.openInputChannelPair(name);
                win.setInputChannel(inputChannels[0]);
                inputChannels[1].transferTo(outInputChannel);

                mInputManager.registerInputChannel(win.mInputChannel, win.mInputWindowHandle);
            }

/frameworks/native/services/inputflinger/InputDispatcher.cpp

status_t InputDispatcher::registerInputChannel(const sp<InputChannel>& inputChannel,
        const sp<InputWindowHandle>& inputWindowHandle, bool monitor) {
#if DEBUG_REGISTRATION
    ALOGD("channel '%s' ~ registerInputChannel - monitor=%s", inputChannel->getName().string(),
            toString(monitor));
#endif

    { // acquire lock
        AutoMutex _l(mLock);

        if (getConnectionIndexLocked(inputChannel) >= 0) {
            ALOGW("Attempted to register already registered input channel '%s'",
                    inputChannel->getName().string());
            return BAD_VALUE;
        }

        sp<Connection> connection = new Connection(inputChannel, inputWindowHandle, monitor);

        int fd = inputChannel->getFd();
        mConnectionsByFd.add(fd, connection);

        if (monitor) {
            mMonitoringChannels.push(inputChannel);
        }

        mLooper->addFd(fd, 0, ALOOPER_EVENT_INPUT, handleReceiveCallback, this);
    } // release lock

    // Wake the looper because some connections have changed.
    mLooper->wake();
    return OK;
}

 &emsp;现在已经了解了Connection的内部构造。看看Connection内部InputPublisher::publishKeyEvent实现。

/frameworks/native/services/inputflinger/InputDispatcher.cpp

status_t InputPublisher::publishKeyEvent(
        uint32_t seq,
        int32_t deviceId,
        int32_t source,
        int32_t action,
        int32_t flags,
        int32_t keyCode,
        int32_t scanCode,
        int32_t metaState,
        int32_t repeatCount,
        nsecs_t downTime,
        nsecs_t eventTime) {
#if DEBUG_TRANSPORT_ACTIONS
    ALOGD("channel '%s' publisher ~ publishKeyEvent: seq=%u, deviceId=%d, source=0x%x, "
            "action=0x%x, flags=0x%x, keyCode=%d, scanCode=%d, metaState=0x%x, repeatCount=%d,"
            "downTime=%lld, eventTime=%lld",
            mChannel->getName().string(), seq,
            deviceId, source, action, flags, keyCode, scanCode, metaState, repeatCount,
            downTime, eventTime);
#endif

    if (!seq) {
        ALOGE("Attempted to publish a key event with sequence number 0.");
        return BAD_VALUE;
    }

    InputMessage msg;
    msg.header.type = InputMessage::TYPE_KEY;
    msg.body.key.seq = seq;
    msg.body.key.deviceId = deviceId;
    msg.body.key.source = source;
    msg.body.key.action = action;
    msg.body.key.flags = flags;
    msg.body.key.keyCode = keyCode;
    msg.body.key.scanCode = scanCode;
    msg.body.key.metaState = metaState;
    msg.body.key.repeatCount = repeatCount;
    msg.body.key.downTime = downTime;
    msg.body.key.eventTime = eventTime;
    return mChannel->sendMessage(&msg);
}

  InputChannel::sendMessage就是将封装好的InputMessage通过send推送到mFd中去。那么,在server端的InputChannel会接收到这个InputMessage。

/frameworks/native/services/inputflinger/InputDispatcher.cpp

status_t InputChannel::sendMessage(const InputMessage* msg) {
    size_t msgLength = msg->size();
    ssize_t nWrite;
    do {
        nWrite = ::send(mFd, msg, msgLength, MSG_DONTWAIT | MSG_NOSIGNAL);
    } while (nWrite == -1 && errno == EINTR);

    if (nWrite < 0) {
        int error = errno;
#if DEBUG_CHANNEL_MESSAGES
        ALOGD("channel '%s' ~ error sending message of type %d, errno=%d", mName.string(),
                msg->header.type, error);
#endif
        if (error == EAGAIN || error == EWOULDBLOCK) {
            return WOULD_BLOCK;
        }
        if (error == EPIPE || error == ENOTCONN || error == ECONNREFUSED || error == ECONNRESET) {
            return DEAD_OBJECT;
        }
        return -error;
    }

    if (size_t(nWrite) != msgLength) {
#if DEBUG_CHANNEL_MESSAGES
        ALOGD("channel '%s' ~ error sending message type %d, send was incomplete",
                mName.string(), msg->header.type);
#endif
        return DEAD_OBJECT;
    }

#if DEBUG_CHANNEL_MESSAGES
    ALOGD("channel '%s' ~ sent message of type %d", mName.string(), msg->header.type);
#endif
    return OK;
}

  至此,派发流程从InputDispatcher的派发中走到了View的逻辑中。

<think> 嗯,用户正在处理一个Android输入系统的棘手问题:InputDispatcher报告"Could not find connection for..."错误。从引用内容看,用户已经研究了InputDispatcher的工作机制,特别是事件分发流程和焦点窗口处理。用户提供的引用[3]和[4]尤其关键,它们揭示了事件分发依赖的两个核心要素:有效的窗口连接(inputChannel)和正确的焦点状态。 用户的问题描述很专业,直接指向了连接丢失的具体错误日志,说明ta可能是个Android系统开发者或框架工程师。考虑到这类错误通常发生在复杂场景(如多窗口切换或动态窗口创建销毁),需要排查几个关键点: 首先想到焦点窗口失效的可能性。引用[4]明确提到当focusedWindowHandle和focusedApplicationHandle同时为空时,事件会被丢弃。这提示用户需要确认两点:窗口是否成功注册InputChannel(检查ViewRootImpl的setView流程),以及WMS是否正常更新焦点窗口(可通过adb shell dumpsys window | grep mCurrentFocus验证)。 连接管理也不容忽视。引用[3]显示dispatchEventLocked()通过inputChannel查找connectionIndex,若返回负数就会触发这个错误。常见情况是窗口销毁时connection被移除但事件队列仍有残留事件。建议用户检查InputDispatcher的mConnectionsByFd状态(adb shell dumpsys input可查看),特别注意目标连接的disposition状态是否为DISCONNECTED。 解决方案设计需要分层推进:最简单的验证是强制焦点切换(如adb命令重启导航栏),系统性方案则包括添加窗口生命周期日志(跟踪onResume/onPause与InputChannel注册的时序),以及捕获InputDispatcher的详细分发轨迹(需DEBUG级别日志)。用户若是ROM开发者,还可以在prepareDispatchCycleLocked()前插入连接有效性断言。 考虑到用户能提供具体错误日志,应该建议ta先过滤"InputDispatcher:Focused"和"InputDispatcher:findConnection"日志,对比窗口token与连接记录中的token是否一致——这能快速区分是焦点错误还是连接泄漏。对于Xposed模块开发者,还要特别注意HOOK机制可能破坏InputChannel映射关系。 最后要提醒风险操作:直接修改InputDispatcher.cpp需要重新编译内核,普通应用开发者应该优先排查自身页面生命周期问题。有趣的是,引用[5]虽然讲的是TCP协议栈,但提到"精妙的算法和机制",这暗示连接可靠性设计是系统级组件的共性——或许用户未来解决类似问题时可以借鉴网络模块的设计思想。 </think> 基于Android输入子系统的工作原理和常见错误场景,以下是解决"InputDispatcher: Could not find connection for ..."错误的完整方案: --- ### **问题原因分析** 此错误表明InputDispatcher无法找到目标窗口的`InputChannel`连接,通常由以下原因导致: 1. **窗口连接未注册** 窗口销毁时未正确注销InputChannel,或创建时未注册(引用[3]) 2. **焦点窗口异常** 当前无有效焦点窗口(`focusedWindowHandle == nullptr`)或焦点应用(引用[4]) 3. **跨进程通信故障** `InputChannel`对应的文件描述符(fd)意外关闭或损坏 4. **窗口生命周期问题** 窗口已销毁但事件仍在分发队列中未被清理 --- ### **解决方案步骤** #### **1. 验证焦点窗口状态** ```bash adb shell dumpsys window | grep mCurrentFocus ``` - ✅ 正常应显示当前前台窗口(如 `ActivityRecord{...}`) - ❌ 若输出为空,检查: - 应用主线程是否阻塞(ANR) - 窗口是否未调用`ViewRootImpl.setView()`注册InputChannel #### **2. 排查连接泄漏** ```bash adb shell dumpsys input | grep "Connection" -A 15 ``` 检查目标窗口的Connection状态: - **STATUS_ZOMBIE**:连接已废弃但未清理(需强制GC) - **STATUS_BROKEN**:Socket通道损坏(需重启应用) #### **3. 关键代码修复点** **窗口销毁时注销连接(Java层)** ```java // 在Activity.onDestroy()或Fragment.onDestroyView() @Override protected void onDestroy() { getWindow().getDecorView().getViewRootImpl().die(); // 触发InputChannel注销 super.onDestroy(); } ``` **Native层事件过滤(C++)** 在`InputDispatcher.cpp`添加连接有效性检查: ```cpp // 修改 dispatchEventLocked() 函数 for (size_t i = 0; i < inputTargets.size(); i++) { const InputTarget& target = inputTargets.itemAt(i); ssize_t connIndex = getConnectionIndexLocked(target.inputChannel); if (connIndex < 0) { ALOGW("Skip event: Invalid connection for channel %s", target.inputChannel->getName().c_str()); continue; // 跳过无效连接而非报错 } ... } ``` #### **4. 高级调试手段** - **开启InputDispatcher详细日志** 修改`frameworks/native/services/inputflinger/InputDispatcher.cpp`: ```cpp #define DEBUG_DISPATCH_CYCLE 1 // 强制开启事件分发跟踪 ``` - **监控连接生命周期** 注入日志到关键函数: ```cpp // InputDispatcher::registerInputChannel() ALOGI("+++ CONN REG: channel=%s, pid=%d", channel->getName().c_str(), pid); // InputDispatcher::unregisterInputChannel() ALOGI("--- CONN UNREG: channel=%s", channel->getName().c_str()); ``` --- ### **预防措施** 1. **异步事件清理** 在窗口销毁后延迟100ms清除InputDispatcher队列(避免事件残留): ```cpp mDispatcher->postTimeoutAtTime(CLEAR_EVENTS, now + 100000000); ``` 2. **InputChannel健康检查** 在`prepareDispatchCycleLocked()`中添加: ```cpp if (!connection->inputChannel->isValid()) { ALOGE("Channel fd %d invalid!", connection->inputChannel->getFd()); removeConnectionLocked(connection); } ``` > **根本矛盾**:窗口销毁与事件分发的时序竞争。建议在WMS(WindowManagerService)侧增加**窗口Token双重验证机制**,确保InputDispatcher收到的token必然对应有效窗口。 --- ### **典型修复案例** 某系统级输入法因未注销InputChannel导致错误: 1. 现象:切换输入法时频繁触发错误 2. 根因:输入法窗口`onDetachedFromWindow()`未调用`die()` 3. 修复: ```java // 在InputMethodService.onDestroy() public void onDestroy() { if (mRootView != null) { mRootView.getViewRootImpl().die(true); // 强制注销 } } ``` ---
评论
成就一亿技术人!
拼手气红包6.0元
还能输入1000个字符
 
红包 添加红包
表情包 插入表情
 条评论被折叠 查看
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

Invoker123

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值