Android的守护进程ServiceManager

ServiceManager是Android系统中的一个重要守护进程，它负责管理系统服务的注册、查找和启动。

1.守护进程ServiceManager的作用

1） 提供服务注册和查找：ServiceManager充当了一个中央注册表的角色，它允许应用程序和系统组件将自己注册为服务，并提供一个唯一的服务名称。其他应用程序可以通过ServiceManager查找并获取已注册的服务，从而实现进程间通信。

2） 启动和管理系统进程：ServiceManager还负责启动和管理一些重要的系统进程，例如系统服务（如Telephony服务、Media服务等），以及其他一些重要的系统组件。

3）实现Binder机制：Android系统采用Binder作为进程间通信（IPC）的机制，ServiceManager是Binder通信的关键组件之一。它维护了一个Binder对象的表格，用于存储已注册的Binder服务，并提供了一些方法供其他进程通过Binder跨进程进行通信和交互。

总之，ServiceManager在Android系统中扮演着重要的角色，它提供了一种机制让不同的组件和应用程序能够进行通信和交互，实现了Android系统的高效运行和各个组件之间的协作。

2.ServiceManager启动

具体启动流程如下：

1. 引导加载器（Bootloader）加载并启动Linux内核。
2. Linux内核启动后，会创建一个init进程（进程号为1），init进程的主要责任是启动Android系统的各个组件。
3. init进程首先会读取init.rc配置文件，根据配置文件的内容启动各个进程和服务。
4. 在配置文件中，init进程会启动Zygote进程，Zygote是Android系统的孵化器进程，用于创建其他应用程序进程。
5. Zygote进程启动后，会加载系统的核心库和一些基础的系统服务，其中就包括了ServiceManager进程。
6. ServiceManager进程被启动后，会负责管理和提供系统服务的注册和访问功能。

service servicemanager /system/bin/servicemanager
    class core animation
    user system
    group system readproc
    critical
    onrestart restart healthd
    onrestart restart zygote
    onrestart restart audioserver
    onrestart restart media
    onrestart restart surfaceflinger
    onrestart restart inputflinger
    onrestart restart drm
    onrestart restart cameraserver
    onrestart restart keystore
    onrestart restart gatekeeperd
    onrestart restart thermalservice
    writepid /dev/cpuset/system-background/tasks
    shutdown critical
    rlimit rtprio 10 10

3.ServiceManager源码分析

ServiceManager是一个可执行的二进制ELF文件，源码位于frameworks\native\cmds\servicemanager下面

Android.pb

cc_binary {
    name: "servicemanager",
    defaults: ["servicemanager_flags"],
    srcs: [
        "service_manager.c",
        "binder.c",
    ],
    shared_libs: ["libcutils", "libselinux"],
    init_rc: ["servicemanager.rc"],
}

cc_binary {
    name: "vndservicemanager",
    defaults: ["servicemanager_flags"],
    vendor: true,
    srcs: [
        "service_manager.c",
        "binder.c",
    ],
    cflags: [
        "-DVENDORSERVICEMANAGER=1",
    ],
    shared_libs: ["libcutils", "libselinux"],
    init_rc: ["vndservicemanager.rc"],
}

可以看到vndservicemanager与servicemanager其实是同样的代码编译出来的二进制文件，只是在启动的时候参数不一样，out出来的目录也不一样。

service vndservicemanager /vendor/bin/vndservicemanager /dev/vndbinder
    class core
    user system
    group system readproc
    writepid /dev/cpuset/system-background/tasks
    shutdown critical

可以见，传参是不一样的。

int main(int argc, char** argv)
{
    struct binder_state *bs;
    union selinux_callback cb;
    char *driver;

    if (argc > 1) {
        driver = argv[1];
    } else {
        driver = "/dev/binder";
    }

    bs = binder_open(driver, 128*1024);
    if (!bs) {
#ifdef VENDORSERVICEMANAGER
        ALOGW("failed to open binder driver %s\n", driver);
        while (true) {
            sleep(UINT_MAX);
        }
#else
        ALOGE("failed to open binder driver %s\n", driver);
#endif
        return -1;
    }

    if (binder_become_context_manager(bs)) {
        ALOGE("cannot become context manager (%s)\n", strerror(errno));
        return -1;
    }

    cb.func_audit = audit_callback;
    selinux_set_callback(SELINUX_CB_AUDIT, cb);
#ifdef VENDORSERVICEMANAGER
    cb.func_log = selinux_vendor_log_callback;
#else
    cb.func_log = selinux_log_callback;
#endif
    selinux_set_callback(SELINUX_CB_LOG, cb);

#ifdef VENDORSERVICEMANAGER
    sehandle = selinux_android_vendor_service_context_handle();
#else
    sehandle = selinux_android_service_context_handle();
#endif
    selinux_status_open(true);

    if (sehandle == NULL) {
        ALOGE("SELinux: Failed to acquire sehandle. Aborting.\n");
        abort();
    }

    if (getcon(&service_manager_context) != 0) {
        ALOGE("SELinux: Failed to acquire service_manager context. Aborting.\n");
        abort();
    }


    binder_loop(bs, svcmgr_handler);

    return 0;
}

打开底层的binder驱动节点

struct binder_state *binder_open(const char* driver, size_t mapsize)
{
    struct binder_state *bs;
    struct binder_version vers;

    bs = malloc(sizeof(*bs));
    if (!bs) {
        errno = ENOMEM;
        return NULL;
    }

    bs->fd = open(driver, O_RDWR | O_CLOEXEC);
    if (bs->fd < 0) {
        fprintf(stderr,"binder: cannot open %s (%s)\n",
                driver, strerror(errno));
        goto fail_open;
    }

    if ((ioctl(bs->fd, BINDER_VERSION, &vers) == -1) ||
        (vers.protocol_version != BINDER_CURRENT_PROTOCOL_VERSION)) {
        fprintf(stderr,
                "binder: kernel driver version (%d) differs from user space version (%d)\n",
                vers.protocol_version, BINDER_CURRENT_PROTOCOL_VERSION);
        goto fail_open;
    }

    bs->mapsize = mapsize;
    bs->mapped = mmap(NULL, mapsize, PROT_READ, MAP_PRIVATE, bs->fd, 0);
    if (bs->mapped == MAP_FAILED) {
        fprintf(stderr,"binder: cannot map device (%s)\n",
                strerror(errno));
        goto fail_map;
    }

    return bs;

fail_map:
    close(bs->fd);
fail_open:
    free(bs);
    return NULL;
}

申请一块物理内存，并把它映射到虚拟空间中来

    bs->mapsize = mapsize;
    bs->mapped = mmap(NULL, mapsize, PROT_READ, MAP_PRIVATE, bs->fd, 0);

使得自己成为服务管理者

int binder_become_context_manager(struct binder_state *bs)
{
    struct flat_binder_object obj;
    memset(&obj, 0, sizeof(obj));
    obj.flags = FLAT_BINDER_FLAG_TXN_SECURITY_CTX | 0x800;

    int result = ioctl(bs->fd, BINDER_SET_CONTEXT_MGR_EXT, &obj);

    // fallback to original method
    if (result != 0) {
        android_errorWriteLog(0x534e4554, "121035042");

        result = ioctl(bs->fd, BINDER_SET_CONTEXT_MGR, 0);
    }
    return result;
}

设置SeAndroid上下文的

    cb.func_audit = audit_callback;
    selinux_set_callback(SELINUX_CB_AUDIT, cb);
#ifdef VENDORSERVICEMANAGER
    cb.func_log = selinux_vendor_log_callback;
#else
    cb.func_log = selinux_log_callback;
#endif
    selinux_set_callback(SELINUX_CB_LOG, cb);

#ifdef VENDORSERVICEMANAGER
    sehandle = selinux_android_vendor_service_context_handle();
#else
    sehandle = selinux_android_service_context_handle();
#endif
    selinux_status_open(true);

进入循环等待服务请求

void binder_loop(struct binder_state *bs, binder_handler func)
{
    int res;
    struct binder_write_read bwr;
    uint32_t readbuf[32];

    bwr.write_size = 0;
    bwr.write_consumed = 0;
    bwr.write_buffer = 0;

    readbuf[0] = BC_ENTER_LOOPER;
    binder_write(bs, readbuf, sizeof(uint32_t));

    for (;;) {
        bwr.read_size = sizeof(readbuf);
        bwr.read_consumed = 0;
        bwr.read_buffer = (uintptr_t) readbuf;

        res = ioctl(bs->fd, BINDER_WRITE_READ, &bwr);

        if (res < 0) {
            ALOGE("binder_loop: ioctl failed (%s)\n", strerror(errno));
            break;
        }

        res = binder_parse(bs, 0, (uintptr_t) readbuf, bwr.read_consumed, func);
        if (res == 0) {
            ALOGE("binder_loop: unexpected reply?!\n");
            break;
        }
        if (res < 0) {
            ALOGE("binder_loop: io error %d %s\n", res, strerror(errno));
            break;
        }
    }
}

解释参数

int binder_parse(struct binder_state *bs, struct binder_io *bio,
                 uintptr_t ptr, size_t size, binder_handler func)
{
    int r = 1;
    uintptr_t end = ptr + (uintptr_t) size;

    while (ptr < end) {
        uint32_t cmd = *(uint32_t *) ptr;
        ptr += sizeof(uint32_t);
#if TRACE
        fprintf(stderr,"%s:\n", cmd_name(cmd));
#endif
        switch(cmd) {
        case BR_NOOP:
            break;
        case BR_TRANSACTION_COMPLETE:
            break;
        case BR_INCREFS:
        case BR_ACQUIRE:
        case BR_RELEASE:
        case BR_DECREFS:
#if TRACE
            fprintf(stderr,"  %p, %p\n", (void *)ptr, (void *)(ptr + sizeof(void *)));
#endif
            ptr += sizeof(struct binder_ptr_cookie);
            break;
        case BR_TRANSACTION_SEC_CTX:
        case BR_TRANSACTION: {
            struct binder_transaction_data_secctx txn;
            if (cmd == BR_TRANSACTION_SEC_CTX) {
                if ((end - ptr) < sizeof(struct binder_transaction_data_secctx)) {
                    ALOGE("parse: txn too small (binder_transaction_data_secctx)!\n");
                    return -1;
                }
                memcpy(&txn, (void*) ptr, sizeof(struct binder_transaction_data_secctx));
                ptr += sizeof(struct binder_transaction_data_secctx);
            } else /* BR_TRANSACTION */ {
                if ((end - ptr) < sizeof(struct binder_transaction_data)) {
                    ALOGE("parse: txn too small (binder_transaction_data)!\n");
                    return -1;
                }
                memcpy(&txn.transaction_data, (void*) ptr, sizeof(struct binder_transaction_data));
                ptr += sizeof(struct binder_transaction_data);

                txn.secctx = 0;
            }

            binder_dump_txn(&txn.transaction_data);
            if (func) {
                unsigned rdata[256/4];
                struct binder_io msg;
                struct binder_io reply;
                int res;

                bio_init(&reply, rdata, sizeof(rdata), 4);
                bio_init_from_txn(&msg, &txn.transaction_data);
                res = func(bs, &txn, &msg, &reply);
                if (txn.transaction_data.flags & TF_ONE_WAY) {
                    binder_free_buffer(bs, txn.transaction_data.data.ptr.buffer);
                } else {
                    binder_send_reply(bs, &reply, txn.transaction_data.data.ptr.buffer, res);
                }
            }
            break;
        }
        case BR_REPLY: {
            struct binder_transaction_data *txn = (struct binder_transaction_data *) ptr;
            if ((end - ptr) < sizeof(*txn)) {
                ALOGE("parse: reply too small!\n");
                return -1;
            }
            binder_dump_txn(txn);
            if (bio) {
                bio_init_from_txn(bio, txn);
                bio = 0;
            } else {
                /* todo FREE BUFFER */
            }
            ptr += sizeof(*txn);
            r = 0;
            break;
        }
        case BR_DEAD_BINDER: {
            struct binder_death *death = (struct binder_death *)(uintptr_t) *(binder_uintptr_t *)ptr;
            ptr += sizeof(binder_uintptr_t);
            death->func(bs, death->ptr);
            break;
        }
        case BR_FAILED_REPLY:
            r = -1;
            break;
        case BR_DEAD_REPLY:
            r = -1;
            break;
        default:
            ALOGE("parse: OOPS %d\n", cmd);
            return -1;
        }
    }

    return r;
}

查找服务与注册服务

int svcmgr_handler(struct binder_state *bs,
                   struct binder_transaction_data_secctx *txn_secctx,
                   struct binder_io *msg,
                   struct binder_io *reply)
{
    struct svcinfo *si;
    uint16_t *s;
    size_t len;
    uint32_t handle;
    uint32_t strict_policy;
    int allow_isolated;
    uint32_t dumpsys_priority;

    struct binder_transaction_data *txn = &txn_secctx->transaction_data;

    //ALOGI("target=%p code=%d pid=%d uid=%d\n",
    //      (void*) txn->target.ptr, txn->code, txn->sender_pid, txn->sender_euid);

    if (txn->target.ptr != BINDER_SERVICE_MANAGER)
        return -1;

    if (txn->code == PING_TRANSACTION)
        return 0;

    // Equivalent to Parcel::enforceInterface(), reading the RPC
    // header with the strict mode policy mask and the interface name.
    // Note that we ignore the strict_policy and don't propagate it
    // further (since we do no outbound RPCs anyway).
    strict_policy = bio_get_uint32(msg);
    bio_get_uint32(msg);  // Ignore worksource header.
    s = bio_get_string16(msg, &len);
    if (s == NULL) {
        return -1;
    }

    if ((len != (sizeof(svcmgr_id) / 2)) ||
        memcmp(svcmgr_id, s, sizeof(svcmgr_id))) {
        fprintf(stderr,"invalid id %s\n", str8(s, len));
        return -1;
    }

    if (sehandle && selinux_status_updated() > 0) {
#ifdef VENDORSERVICEMANAGER
        struct selabel_handle *tmp_sehandle = selinux_android_vendor_service_context_handle();
#else
        struct selabel_handle *tmp_sehandle = selinux_android_service_context_handle();
#endif
        if (tmp_sehandle) {
            selabel_close(sehandle);
            sehandle = tmp_sehandle;
        }
    }

    switch(txn->code) {
    case SVC_MGR_GET_SERVICE:
    case SVC_MGR_CHECK_SERVICE:
        s = bio_get_string16(msg, &len);
        if (s == NULL) {
            return -1;
        }
        handle = do_find_service(s, len, txn->sender_euid, txn->sender_pid,
                                 (const char*) txn_secctx->secctx);
        if (!handle)
            break;
        bio_put_ref(reply, handle);
        return 0;

    case SVC_MGR_ADD_SERVICE:
        s = bio_get_string16(msg, &len);
        if (s == NULL) {
            return -1;
        }
        handle = bio_get_ref(msg);
        allow_isolated = bio_get_uint32(msg) ? 1 : 0;
        dumpsys_priority = bio_get_uint32(msg);
        if (do_add_service(bs, s, len, handle, txn->sender_euid, allow_isolated, dumpsys_priority,
                           txn->sender_pid, (const char*) txn_secctx->secctx))
            return -1;
        break;

    case SVC_MGR_LIST_SERVICES: {
        uint32_t n = bio_get_uint32(msg);
        uint32_t req_dumpsys_priority = bio_get_uint32(msg);

        if (!svc_can_list(txn->sender_pid, (const char*) txn_secctx->secctx, txn->sender_euid)) {
            ALOGE("list_service() uid=%d - PERMISSION DENIED\n",
                    txn->sender_euid);
            return -1;
        }
        si = svclist;
        // walk through the list of services n times skipping services that
        // do not support the requested priority
        while (si) {
            if (si->dumpsys_priority & req_dumpsys_priority) {
                if (n == 0) break;
                n--;
            }
            si = si->next;
        }
        if (si) {
            bio_put_string16(reply, si->name);
            return 0;
        }
        return -1;
    }
    default:
        ALOGE("unknown code %d\n", txn->code);
        return -1;
    }

    bio_put_uint32(reply, 0);
    return 0;
}

查找服务

    case SVC_MGR_CHECK_SERVICE:
        s = bio_get_string16(msg, &len);
        if (s == NULL) {
            return -1;
        }
        handle = do_find_service(s, len, txn->sender_euid, txn->sender_pid,
                                 (const char*) txn_secctx->secctx);
        if (!handle)
            break;
        bio_put_ref(reply, handle);
        return 0;

添加服务

    case SVC_MGR_ADD_SERVICE:
        s = bio_get_string16(msg, &len);
        if (s == NULL) {
            return -1;
        }
        handle = bio_get_ref(msg);
        allow_isolated = bio_get_uint32(msg) ? 1 : 0;
        dumpsys_priority = bio_get_uint32(msg);
        if (do_add_service(bs, s, len, handle, txn->sender_euid, allow_isolated, dumpsys_priority,
                           txn->sender_pid, (const char*) txn_secctx->secctx))
            return -1;
        break;

这就是上层C/C++层源码分析，后续我们继续分析上层Java是如何与它进行进程通讯的，底层驱动又是如何实现增加进程节点，寻找对应的进程通讯的。