1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
int main(int argc __unused, char **argv __unused) {
    struct sched_param param = {
            .sched_priority = 1,
    };

    /* By default disable low level vmpressure events */
    level_oomadj[VMPRESS_LEVEL_LOW] =
        property_get_int32("ro.lmk.low", OOM_SCORE_ADJ_MAX + 1);
    level_oomadj[VMPRESS_LEVEL_MEDIUM] =
        property_get_int32("ro.lmk.medium", 800);
    level_oomadj[VMPRESS_LEVEL_CRITICAL] =
        property_get_int32("ro.lmk.critical", 0);
    debug_process_killing = property_get_bool("ro.lmk.debug", false);

    /* By default disable upgrade/downgrade logic */
    enable_pressure_upgrade =
        property_get_bool("ro.lmk.critical_upgrade", false);
    upgrade_pressure =
        (int64_t)property_get_int32("ro.lmk.upgrade_pressure", 100);
    downgrade_pressure =
        (int64_t)property_get_int32("ro.lmk.downgrade_pressure", 100);
    kill_heaviest_task =
        property_get_bool("ro.lmk.kill_heaviest_task", false);
    low_ram_device = property_get_bool("ro.config.low_ram", false);
    kill_timeout_ms =
        (unsigned long)property_get_int32("ro.lmk.kill_timeout_ms", 0);
    use_minfree_levels =
        property_get_bool("ro.lmk.use_minfree_levels", false);
...
    //将该进程当前使用的以及未来使用的内存都锁住在物理内存中，放置内存被交换
    if (mlockall(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT) && errno != EINVAL)
        ALOGW("mlockall failed: errno=%d", errno);
    //设置调度策略
    sched_setscheduler(0, SCHED_FIFO, &param);
    if (!init())
        mainloop();
...
    ALOGI("exiting");
    return 0;

1
2
if (mlockall(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT) && errno != EINVAL)
        ALOGW("mlockall failed: errno=%d", errno);

1
sched_setscheduler(0, SCHED_FIFO, &param);

1
2
3
4
struct adjslot_list {
    struct adjslot_list *next;
    struct adjslot_list *prev;
};

1
2
3
4
5
6
7
8
9
10
static void proc_insert(struct proc *procp) {
    //根据pid计算hash值
    int hval = pid_hashfn(procp->pid);
    //维护一个哈希链表，用于快速找到该进程,每次都放在该位置的头部
    procp->pidhash_next = pidhash[hval];
    pidhash[hval] = procp;
    //用procadjslot_list中放置该进程
    proc_slot(procp);
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
static void proc_slot(struct proc *procp) {
    //计算进程需要放置的位置，将oomadj增加1000.
    int adjslot = ADJTOSLOT(procp->oomadj);
    //根据adjslot值，插入到procadjslot_list中，其实是类似一个优先队列的链表．优先级最高的放在头部，低的放在尾部．
    adjslot_insert(&procadjslot_list[adjslot], &procp->asl);
}
//将new插入到head位置之后
static void adjslot_insert(struct adjslot_list *head, struct adjslot_list *new)
{
    struct adjslot_list *next = head->next;
    new->prev = head;
    new->next = next;
    next->prev = new;
    head->next = new;
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
static void mainloop(void) {
    struct event_handler_info* handler_info;
    struct epoll_event *evt;

    while (1) {
        struct epoll_event events[maxevents];
        int nevents;
        int i;
        //阻塞等待epoll_event
        nevents = epoll_wait(epollfd, events, maxevents, -1);

        if (nevents == -1) {
            if (errno == EINTR)
                continue;
            ALOGE("epoll_wait failed (errno=%d)", errno);
            continue;
        }

        /*
         * First pass to see if any data socket connections were dropped.
         * Dropped connection should be handled before any other events
         * to deallocate data connection and correctly handle cases when
         * connection gets dropped and reestablished in the same epoll cycle.
         * In such cases it's essential to handle connection closures first.
         */
        for (i = 0, evt = &events[0]; i < nevents; ++i, evt++) {
            if ((evt->events & EPOLLHUP) && evt->data.ptr) {
                ALOGI("lmkd data connection dropped");
                handler_info = (struct event_handler_info*)evt->data.ptr;
                ctrl_data_close(handler_info->data);
            }
        }

        /* Second pass to handle all other events */
        for (i = 0, evt = &events[0]; i < nevents; ++i, evt++) {
            if (evt->events & EPOLLERR)
                ALOGD("EPOLLERR on event #%d", i);
            if (evt->events & EPOLLHUP) {
                /* This case was handled in the first pass */
                continue;
            }
            if (evt->data.ptr) {
                handler_info = (struct event_handler_info*)evt->data.ptr;
                handler_info->handler(handler_info->data, evt->events);
            }
        }
    }
}

1
2
3
4
5
static void ctrl_data_handler(int data, uint32_t events) {
    if (events & EPOLLIN) {
        ctrl_command_handler(data);
    }
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
static void ctrl_command_handler(int dsock_idx) {
    LMKD_CTRL_PACKET packet;
    int len;
    enum lmk_cmd cmd;
    int nargs;
    int targets;

    len = ctrl_data_read(dsock_idx, (char *)packet, CTRL_PACKET_MAX_SIZE);
    if (len <= 0)
        return;

    if (len < (int)sizeof(int)) {
        ALOGE("Wrong control socket read length len=%d", len);
        return;
    }

    cmd = lmkd_pack_get_cmd(packet);
    nargs = len / sizeof(int) - 1;
    if (nargs < 0)
        goto wronglen;

    switch(cmd) {
    case LMK_TARGET:
        targets = nargs / 2;
        if (nargs & 0x1 || targets > (int)ARRAY_SIZE(lowmem_adj))
            goto wronglen;
        cmd_target(targets, packet);
        break;
    case LMK_PROCPRIO:
        if (nargs != 3)
            goto wronglen;
        cmd_procprio(packet);
        break;
    case LMK_PROCREMOVE:
        if (nargs != 1)
            goto wronglen;
        cmd_procremove(packet);
        break;
    default:
        ALOGE("Received unknown command code %d", cmd);
        return;
    }

    return;

wronglen:
    ALOGE("Wrong control socket read length cmd=%d len=%d", cmd, len);
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
static void cmd_target(int ntargets, LMKD_CTRL_PACKET packet) {
    int i;
    struct lmk_target target;

    if (ntargets > (int)ARRAY_SIZE(lowmem_adj))
        return;

    for (i = 0; i < ntargets; i++) {
        lmkd_pack_get_target(packet, i, &target);
        lowmem_minfree[i] = target.minfree;
        lowmem_adj[i] = target.oom_adj_score;
    }

    lowmem_targets_size = ntargets;

    if (has_inkernel_module) {
        char minfreestr[128];
        char killpriostr[128];

        minfreestr[0] = '\0';
        killpriostr[0] = '\0';

        for (i = 0; i < lowmem_targets_size; i++) {
            char val[40];

            if (i) {
                strlcat(minfreestr, ",", sizeof(minfreestr));
                strlcat(killpriostr, ",", sizeof(killpriostr));
            }

            snprintf(val, sizeof(val), "%d", use_inkernel_interface ? lowmem_minfree[i] : 0);
            strlcat(minfreestr, val, sizeof(minfreestr));
            snprintf(val, sizeof(val), "%d", use_inkernel_interface ? lowmem_adj[i] : 0);
            strlcat(killpriostr, val, sizeof(killpriostr));
        }

        writefilestring(INKERNEL_MINFREE_PATH, minfreestr);
        writefilestring(INKERNEL_ADJ_PATH, killpriostr);
    }
}

1
2
3
4
5
6
7
8
//drivers/staging/android/lowmemorykiller.c
static short lowmem_oom_adj_to_oom_score_adj(short oom_adj)
{
	if (oom_adj == OOM_ADJUST_MAX)
		return OOM_SCORE_ADJ_MAX;
	else
		return (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE;
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
static void cmd_procprio(LMKD_CTRL_PACKET packet) {
    struct proc *procp;
    char path[80];
    char val[20];
    int soft_limit_mult;
    struct lmk_procprio params;

    lmkd_pack_get_procprio(packet, &params);

    if (params.oomadj < OOM_SCORE_ADJ_MIN ||
        params.oomadj > OOM_SCORE_ADJ_MAX) {
        ALOGE("Invalid PROCPRIO oomadj argument %d", params.oomadj);
        return;
    }

    snprintf(path, sizeof(path), "/proc/%d/oom_score_adj", params.pid);
    snprintf(val, sizeof(val), "%d", params.oomadj);
    writefilestring(path, val);

    if (use_inkernel_interface)
        return;

    if (low_ram_device) {
        if (params.oomadj >= 900) {
            soft_limit_mult = 0;
        } else if (params.oomadj >= 800) {
            soft_limit_mult = 0;
        } else if (params.oomadj >= 700) {
            soft_limit_mult = 0;
        } else if (params.oomadj >= 600) {
            // Launcher should be perceptible, don't kill it.
            params.oomadj = 200;
            soft_limit_mult = 1;
        } else if (params.oomadj >= 500) {
            soft_limit_mult = 0;
        } else if (params.oomadj >= 400) {
            soft_limit_mult = 0;
        } else if (params.oomadj >= 300) {
            soft_limit_mult = 1;
        } else if (params.oomadj >= 200) {
            soft_limit_mult = 2;
        } else if (params.oomadj >= 100) {
            soft_limit_mult = 10;
        } else if (params.oomadj >=   0) {
            soft_limit_mult = 20;
        } else {
            // Persistent processes will have a large
            // soft limit 512MB.
            soft_limit_mult = 64;
        }
        //当使用low_ram_device时，会根据进程的oomadj进行分级，从而确定soft_limit_multi的值
        //最后将soft_limit_multi * EIGHT_MEGA(8MB)的值写入到memory.soft_limit_in_bytes，
        //soft_limit_in_bytes不会像limit_in_bytes组织进程使用超过限额的内存，但会在系统内存不足时，
        //有限回收超过限额的进程占用的内存．
        snprintf(path, sizeof(path),
             "/dev/memcg/apps/uid_%d/pid_%d/memory.soft_limit_in_bytes",
             params.uid, params.pid);
        snprintf(val, sizeof(val), "%d", soft_limit_mult * EIGHT_MEGA);
        writefilestring(path, val);
    }
    //当不使用内核空间lowmemorykiller时，将该进程加入到链表中
    procp = pid_lookup(params.pid);
    if (!procp) {
            procp = malloc(sizeof(struct proc));
            if (!procp) {
                // Oh, the irony.  May need to rebuild our state.
                return;
            }
            procp->pid = params.pid;
            procp->uid = params.uid;
            procp->oomadj = params.oomadj;
            proc_insert(procp);
    } else {
        proc_unslot(procp);
        procp->oomadj = params.oomadj;
        proc_slot(procp);
    }
}

1
2
3
4
5
6
7
8
9
static void cmd_procremove(LMKD_CTRL_PACKET packet) {
    struct lmk_procremove params;

    if (use_inkernel_interface)
        return;

    lmkd_pack_get_procremove(packet, &params);
    pid_remove(params.pid);
}

1
2
3
4
5
6
7
8
9
if (use_inkernel_interface) {
    ALOGI("Using in-kernel low memory killer interface");
} else {
    if (!init_mp_common(VMPRESS_LEVEL_LOW) ||
        !init_mp_common(VMPRESS_LEVEL_MEDIUM) ||
        !init_mp_common(VMPRESS_LEVEL_CRITICAL)) {
        ALOGE("Kernel does not support memory pressure events or in-kernel low memory killer");
        return -1;
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
static bool init_mp_common(enum vmpressure_level level) {
    int mpfd;
    int evfd;
    int evctlfd;
    char buf[256];
    struct epoll_event epev;
    int ret;
    int level_idx = (int)level;
    const char *levelstr = level_name[level_idx];
    //打开pressure_level节点
    mpfd = open(MEMCG_SYSFS_PATH "memory.pressure_level", O_RDONLY | O_CLOEXEC);
    if (mpfd < 0) {
        ALOGI("No kernel memory.pressure_level support (errno=%d)", errno);
        goto err_open_mpfd;
    }
    //打开cgroup.event_controll节点
    evctlfd = open(MEMCG_SYSFS_PATH "cgroup.event_control", O_WRONLY | O_CLOEXEC);
    if (evctlfd < 0) {
        ALOGI("No kernel memory cgroup event control (errno=%d)", errno);
        goto err_open_evctlfd;
    }

    evfd = eventfd(0, EFD_NONBLOCK | EFD_CLOEXEC);
    if (evfd < 0) {
        ALOGE("eventfd failed for level %s; errno=%d", levelstr, errno);
        goto err_eventfd;
    }

    ret = snprintf(buf, sizeof(buf), "%d %d %s", evfd, mpfd, levelstr);
    if (ret >= (ssize_t)sizeof(buf)) {
        ALOGE("cgroup.event_control line overflow for level %s", levelstr);
        goto err;
    }

    ret = TEMP_FAILURE_RETRY(write(evctlfd, buf, strlen(buf) + 1));
    if (ret == -1) {
        ALOGE("cgroup.event_control write failed for level %s; errno=%d",
              levelstr, errno);
        goto err;
    }

    epev.events = EPOLLIN;
    /* use data to store event level */
    vmpressure_hinfo[level_idx].data = level_idx;
    vmpressure_hinfo[level_idx].handler = mp_event_common;
    epev.data.ptr = (void *)&vmpressure_hinfo[level_idx];
    ret = epoll_ctl(epollfd, EPOLL_CTL_ADD, evfd, &epev);
    if (ret == -1) {
        ALOGE("epoll_ctl for level %s failed; errno=%d", levelstr, errno);
        goto err;
    }
    maxevents++;
    mpevfd[level] = evfd;
    close(evctlfd);
    return true;

err:
    close(evfd);
err_eventfd:
    close(evctlfd);
err_open_evctlfd:
    close(mpfd);
err_open_mpfd:
    return false;
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
static void mp_event_common(int data, uint32_t events __unused) {
    int ret;
    unsigned long long evcount;
    int64_t mem_usage, memsw_usage;
    int64_t mem_pressure;
    enum vmpressure_level lvl;
    union meminfo mi;
    union zoneinfo zi;
    static struct timeval last_report_tm;
    static unsigned long skip_count = 0;
    enum vmpressure_level level = (enum vmpressure_level)data;
    long other_free = 0, other_file = 0;
    int min_score_adj;
    int pages_to_free = 0;
    int minfree = 0;
    static struct reread_data mem_usage_file_data = {
        .filename = MEMCG_MEMORY_USAGE,
        .fd = -1,
    };
    static struct reread_data memsw_usage_file_data = {
        .filename = MEMCG_MEMORYSW_USAGE,
        .fd = -1,
    };

    /*
    从低到高读取mpevfd，更新其计数器.
    */ 
    for (lvl = VMPRESS_LEVEL_LOW; lvl < VMPRESS_LEVEL_COUNT; lvl++) {
        if (mpevfd[lvl] != -1 &&
            TEMP_FAILURE_RETRY(read(mpevfd[lvl],
                               &evcount, sizeof(evcount))) > 0 &&
            evcount > 0 && lvl > level) {
            level = lvl;
        }
    }
   
   //假如设置了`kill_timeout_ms`,那么计算当前时间到上次调用`mp_event_common`时记录的时间差和`kill_timeout_ms`进行对比，
   //如果没到达该时间,则递增`skip_count`并自增后返回,注意`skip_count`是静态量．
   if (kill_timeout_ms) {
        struct timeval curr_tm;
        gettimeofday(&curr_tm, NULL);
        if (get_time_diff_ms(&last_report_tm, &curr_tm) < kill_timeout_ms) {
            skip_count++;
            return;
        }
    }
    //超过了`kill_timeout_ms`时间，重新清零．
    if (skip_count > 0) {
        ALOGI("%lu memory pressure events were skipped after a kill!",
              skip_count);
        skip_count = 0;
    }
   
   /*
    meminfo_parse解析/proc/meminfo的内容，并获取如下数据：
    "MemFree:": 系统尚未使用的内存,LowFree和HightFree的总和
    "Cached:": 被高速缓冲存储器用的内存大小
    "SwapCached:": 被高速缓冲存储器用的交换空间的大小 
    "Buffers:": 用来给文件做缓冲大小
    "Shmem:": 共享内存
    "Unevictable:",不能够pageout/swapout的内存页
    "SwapFree:"：未被使用交换空间的大小
    "Dirty: 等待被写回到磁盘的内存大小
    
    zoneinfo_parse解析"/proc/zoneinfo"的内容，并获取如下数据
   "nr_free_pages",
    "nr_file_pages",
    "nr_shmem",
    "nr_unevictable",
    "workingset_refault",
    "high",`
   */
    if (meminfo_parse(&mi) < 0 || zoneinfo_parse(&zi) < 0) {
        ALOGE("Failed to get free memory!");
        return;
    }
    //use_minfree_levels的逻辑和内核相同
    //该模式下，需要借助可用内存和文件换存阈值来决定何时终止
    if (use_minfree_levels) {
        int i;
        //other_free为可用内存，为MemFree(meminfo)的值减去计算出来的totalreserve_pages（page_high）
        other_free = mi.field.nr_free_pages - zi.field.totalreserve_pages;
        if (mi.field.nr_file_pages > (mi.field.shmem + mi.field.unevictable + mi.field.swap_cached)) {
            //other_file为文件换存阈值，为MemTotal-Shemem-unevictable-swapcached
            other_file = (mi.field.nr_file_pages - mi.field.shmem -
                          mi.field.unevictable - mi.field.swap_cached);
        } else {
            other_file = 0;
        }
        //从低到高遍历，当other_free和other_file均满足小于minfree时，跳出
        //找到对应lowmem_adj数组的min_score_adj.
        min_score_adj = OOM_SCORE_ADJ_MAX + 1;
        for (i = 0; i < lowmem_targets_size; i++) {
            minfree = lowmem_minfree[i];
            if (other_free < minfree && other_file < minfree) {
                min_score_adj = lowmem_adj[i];
                break;
            }
        }

        if (min_score_adj == OOM_SCORE_ADJ_MAX + 1) {
            if (debug_process_killing) {
                ALOGI("Ignore %s memory pressure event "
                      "(free memory=%ldkB, cache=%ldkB, limit=%ldkB)",
                      level_name[level], other_free * page_k, other_file * page_k,
                      (long)lowmem_minfree[lowmem_targets_size - 1] * page_k);
            }
            return;
        }
        //计算出需要释放的内存大小
        /* Free up enough pages to push over the highest minfree level */
        pages_to_free = lowmem_minfree[lowmem_targets_size - 1] -
            ((other_free < other_file) ? other_free : other_file);
        goto do_kill;
    }
    
    if (level == VMPRESS_LEVEL_LOW) {
        record_low_pressure_levels(&mi);
    }

    if (level_oomadj[level] > OOM_SCORE_ADJ_MAX) {
        /* Do not monitor this pressure level */
        return;
    }
    //从/dev/memcg/memory.usage_in_bytes获取已用的内存
    if ((mem_usage = get_memory_usage(&mem_usage_file_data)) < 0) {
        goto do_kill;
    }
    //从/dev/memcg/memory.memsw.usage_in_bytes获取已用的内存
    if ((memsw_usage = get_memory_usage(&memsw_usage_file_data)) < 0) {
        goto do_kill;
    }
    // Calculate percent for swappinness.
    //计算出交换率
    mem_pressure = (mem_usage * 100) / memsw_usage;

    if (enable_pressure_upgrade && level != VMPRESS_LEVEL_CRITICAL) {
        // We are swapping too much.
        if (mem_pressure < upgrade_pressure) {
            level = upgrade_level(level);
            if (debug_process_killing) {
                ALOGI("Event upgraded to %s", level_name[level]);
            }
        }
    }

    // If the pressure is larger than downgrade_pressure lmk will not
    // kill any process, since enough memory is available.
    if (mem_pressure > downgrade_pressure) {
        if (debug_process_killing) {
            ALOGI("Ignore %s memory pressure", level_name[level]);
        }
        return;
    } else if (level == VMPRESS_LEVEL_CRITICAL &&
               mem_pressure > upgrade_pressure) {
        if (debug_process_killing) {
            ALOGI("Downgrade critical memory pressure");
        }
        // Downgrade event, since enough memory available.
        level = downgrade_level(level);
    }
...

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
static struct proc *proc_get_heaviest(int oomadj) {
    struct adjslot_list *head = &procadjslot_list[ADJTOSLOT(oomadj)];
    struct adjslot_list *curr = head->next;
    struct proc *maxprocp = NULL;
    int maxsize = 0;
    while (curr != head) {
        int pid = ((struct proc *)curr)->pid;
        int tasksize = proc_get_size(pid);
        if (tasksize <= 0) {
            struct adjslot_list *next = curr->next;
            pid_remove(pid);
            curr = next;
        } else {
            if (tasksize > maxsize) {
                maxsize = tasksize;
                maxprocp = (struct proc *)curr;
            }
            curr = curr->next;
        }
    }
    return maxprocp;
}

static int proc_get_size(int pid) {
    char path[PATH_MAX];
    char line[LINE_MAX];
    int fd;
    int rss = 0;
    int total;
    ssize_t ret;

    snprintf(path, PATH_MAX, "/proc/%d/statm", pid);
    fd = open(path, O_RDONLY | O_CLOEXEC);
    if (fd == -1)
        return -1;

    ret = read_all(fd, line, sizeof(line) - 1);
    if (ret < 0) {
        close(fd);
        return -1;
    }

    sscanf(line, "%d %d ", &total, &rss);
    close(fd);
    return rss;
}

1
2
3
static struct proc *proc_adj_lru(int oomadj) {
    return (struct proc *)adjslot_tail(&procadjslot_list[ADJTOSLOT(oomadj)]);
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
static int kill_one_process(struct proc* procp, int min_score_adj,
                            enum vmpressure_level level) {
    int pid = procp->pid;
    uid_t uid = procp->uid;
    char *taskname;
    int tasksize;
    int r;

    taskname = proc_get_name(pid);
    if (!taskname) {
        pid_remove(pid);
        return -1;
    }

    tasksize = proc_get_size(pid);
    if (tasksize <= 0) {
        pid_remove(pid);
        return -1;
    }

    TRACE_KILL_START(pid);

    r = kill(pid, SIGKILL);
    ... 
    pid_remove(pid);

    if (r) {
        ALOGE("kill(%d): errno=%d", pid, errno);
        return -1;
    } else {
        return tasksize;
    }
    return tasksize;
}

1
2
3
4
5
6
7
8
9
10
11
12
static struct shrinker lowmem_shrinker = {
	.scan_objects = lowmem_scan,
	.count_objects = lowmem_count,
	.seeks = DEFAULT_SEEKS * 16
};

static int __init lowmem_init(void)
{
	register_shrinker(&lowmem_shrinker);
	return 0;
}
device_initcall(lowmem_init);

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc)
{
	struct task_struct *tsk;
	struct task_struct *selected = NULL;
	unsigned long rem = 0;
	int tasksize;
	int i;
	short min_score_adj = OOM_SCORE_ADJ_MAX + 1;
	int minfree = 0;
	int selected_tasksize = 0;
	short selected_oom_score_adj;
	int array_size = ARRAY_SIZE(lowmem_adj);
	//获取当前系统剩余内存和文件缓存阈值，与用户空间开启use_min_freelevel逻辑相同
	int other_free = global_page_state(NR_FREE_PAGES) - totalreserve_pages;
	int other_file = global_node_page_state(NR_FILE_PAGES) -
				global_node_page_state(NR_SHMEM) -
				global_node_page_state(NR_UNEVICTABLE) -
				total_swapcache_pages();

	if (lowmem_adj_size < array_size)
		array_size = lowmem_adj_size;
	if (lowmem_minfree_size < array_size)
		array_size = lowmem_minfree_size;
    //从小到大递增计算minfree，当临界点minfree大于剩余内存other_free时，计算出对应的adj
    //保存到min_score_adj中
	for (i = 0; i < array_size; i++) {
		minfree = lowmem_minfree[i];
		if (other_free < minfree && other_file < minfree) {
			min_score_adj = lowmem_adj[i];
			break;
		}
	}
    ...
	if (min_score_adj == OOM_SCORE_ADJ_MAX + 1) {
		lowmem_print(5, "lowmem_scan %lu, %x, return 0\n",
			     sc->nr_to_scan, sc->gfp_mask);
		return 0;
	}

	selected_oom_score_adj = min_score_adj;

	rcu_read_lock();
	//遍历所有进程
	for_each_process(tsk) {
		struct task_struct *p;
		short oom_score_adj;
        //内核线程跳过
		if (tsk->flags & PF_KTHREAD)
			continue;

		p = find_lock_task_mm(tsk);
		if (!p)
			continue;

		if (task_lmk_waiting(p) &&
		    time_before_eq(jiffies, lowmem_deathpending_timeout)) {
			task_unlock(p);
			rcu_read_unlock();
			return 0;
		}
		oom_score_adj = p->signal->oom_score_adj;
		if (oom_score_adj < min_score_adj) {
			task_unlock(p);
			continue;
		}
		tasksize = get_mm_rss(p->mm);
		task_unlock(p);
		if (tasksize <= 0)
			continue;
		if (selected) {
		    //当selected不为空，即选择了进程，会比较该进程的oom_score_adj
		    //如果当前进程的oom_score_adj与选中的进程的oom_score_adj相比较小，则跳过．说明当前进程优先级较高
		    //或者相同时，如果tasksize更小时，也跳过．
			if (oom_score_adj < selected_oom_score_adj)
				continue;
			if (oom_score_adj == selected_oom_score_adj &&
			    tasksize <= selected_tasksize)
				continue;
		}
		selected = p;
		selected_tasksize = tasksize;
		selected_oom_score_adj = oom_score_adj;
		lowmem_print(2, "select '%s' (%d), adj %hd, size %d, to kill\n",
			     p->comm, p->pid, oom_score_adj, tasksize);
	}
	if (selected) {
		long cache_size = other_file * (long)(PAGE_SIZE / 1024);
		long cache_limit = minfree * (long)(PAGE_SIZE / 1024);
		long free = other_free * (long)(PAGE_SIZE / 1024);

		task_lock(selected);
		//发送kill信号给进程
		send_sig(SIGKILL, selected, 0);
		if (selected->mm)
			task_set_lmk_waiting(selected);
		task_unlock(selected);
		trace_lowmemory_kill(selected, cache_size, cache_limit, free);
		lowmem_print(1, "Killing '%s' (%d) (tgid %d), adj %hd,\n"
				 "   to free %ldkB on behalf of '%s' (%d) because\n"
				 "   cache %ldkB is below limit %ldkB for oom_score_adj %hd\n"
				 "   Free memory is %ldkB above reserved\n",
			     selected->comm, selected->pid, selected->tgid,
			     selected_oom_score_adj,
			     selected_tasksize * (long)(PAGE_SIZE / 1024),
			     current->comm, current->pid,
			     cache_size, cache_limit,
			     min_score_adj,
			     free);
		lowmem_deathpending_timeout = jiffies + HZ;
		rem += selected_tasksize;
	}

	lowmem_print(4, "lowmem_scan %lu, %x, return %lu\n",
		     sc->nr_to_scan, sc->gfp_mask, rem);
	rcu_read_unlock();
	return rem;
}