当前位置：首页 > news >正文

rt-linux下的D状态的堆栈抓取及TASK_RTLOCK_WAIT状态

news 来源：原创 2025/4/28 5:48:43

一、背景

在之前的博客缺页异常导致的iowait打印出相关文件的绝对路径-CSDN博客里的 2.1 一节里的代码，我们已经有了一个比较强大的抓取D状态和等IO状态超过阈值的waker和wakee的堆栈状态的内核模块。在之前的博客增加等IO状态的唤醒堆栈打印及缺页异常导致iowait分析-CSDN博客里的 2.3 一节，我们也针对了一些特殊的情况，即在in_iowait状态下的非TASK_UNINTERRUPTIBLE状态的情况也考虑到并进行了超阈值的堆栈打印：

对于iowait的情形，这样的监控程序和上面提到的考虑已经是足够了，针对iowait情形，我们还打印了waker和wakee的堆栈。而对于D状态的超时而言，我们当前的程序并没有覆盖全场景，我们并没有打印D状态的waker堆栈，我们也没有考虑TASK_UNINTERRUPTIBLE这个bit是1但是其他bit也是1的情况。另外，在这篇博客里，我们也会讲到，对于rt-linux内核而言，还有一种特殊的D状态，即TASK_RTLOCK_WAIT状态，这个TASK_RTLOCK_WAIT状态在rt-linux里也是一个很普遍存在的情况，不抓取这样的情况就漏了很多D状态。

下面第二章里，我们给出更新后的源码（源码里去掉iowait的抓取，因为iowait的抓取之前的程序已经足够了，这篇博客只关注rt-linux下的D状态的抓取，注意这里说的D状态是一个广义的D状态，即在perfetto里显示出是D状态那就被视为是D状态，并不应该理解成是__state == TASK_UNINTERRUPTIBLE，也不应该理解成是__state的里TASK_UNINTERRUPTIBLE的mask是TASK_UNINTERRUPTIBLE，具体在下面第三章里展开说明）。

然后在第三章里，我们讲解这次源码的改动的部分和与TASK_RTLOCK_WAIT相关的细节。

二、源码及抓取效果

2.1 源码

#include <linux/module.h>
#include <linux/capability.h>
#include <linux/sched.h>
#include <linux/uaccess.h>
#include <linux/proc_fs.h>
#include <linux/ctype.h>
#include <linux/seq_file.h>
#include <linux/poll.h>
#include <linux/types.h>
#include <linux/ioctl.h>
#include <linux/errno.h>
#include <linux/stddef.h>
#include <linux/lockdep.h>
#include <linux/kthread.h>
#include <linux/sched.h>
#include <linux/delay.h>
#include <linux/wait.h>
#include <linux/init.h>
#include <asm/atomic.h>
#include <trace/events/workqueue.h>
#include <linux/sched/clock.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/tracepoint.h>
#include <trace/events/osmonitor.h>
#include <trace/events/sched.h>
#include <trace/events/irq.h>
#include <trace/events/kmem.h>
#include <linux/ptrace.h>
#include <linux/uaccess.h>
#include <asm/processor.h>
#include <linux/sched/task_stack.h>
#include <linux/nmi.h>
#include <linux/version.h>
#include <linux/sched/mm.h>
#include <asm/irq_regs.h>
#include <linux/kallsyms.h>
#include <linux/kprobes.h>
#include <linux/stop_machine.h>MODULE_LICENSE("GPL");
MODULE_AUTHOR("zhaoxin");
MODULE_DESCRIPTION("Module for monitor D tasks.");
MODULE_VERSION("1.0");static unsigned long ns = 5000000ull;module_param(ns, ulong, S_IRUGO);
MODULE_PARM_DESC(ns, "threshold nano second");#define IODELAY_TRACEPOINT_ENABLE#define TEST_STACK_TRACE_ENTRIES   32typedef unsigned int (*stack_trace_save_tsk_func)(struct task_struct *task,unsigned long *store, unsigned int size,unsigned int skipnr);
stack_trace_save_tsk_func _stack_trace_save_tsk;typedef int (*get_cmdline_func)(struct task_struct *task, char *buffer, int buflen);
get_cmdline_func _get_cmdline_func;#define TESTDIOMONITOR_SAMPLEDESC_SWDSTART  "swDstart"
#define TESTDIOMONITOR_SAMPLEDESC_WADSTOP    "waDstop"
#define TESTDIOMONITOR_SAMPLEDESC_SWDIOSTART "swDiostart"
#define TESTDIOMONITOR_SAMPLEDESC_WADIOSTOP  "waDiostop"
#define TESTDIOMONITOR_SAMPLEDESC_DEXCEED    "Dexceed"
#define TESTDIOMONITOR_SAMPLEDESC_DIOEXCEED  "Dioexceed"
#define TESTDIOMONITOR_SAMPLEDESC_IOEXCEED   "Ioexceed"#define TESTDIOMONITOR_SIMPLE#ifdef TESTDIOMONITOR_SIMPLE
#define TESTDIOMONITOR_SIMPLE_THRESHOLDNS   (ns)//5000000ull
#endif// 1ms
//#define TESTDIOMONITOR_DEXCEED_THRESHOLD     1000ull//1000000ull#ifdef CONFIG_UCLAMP_TASK
struct uclamp_bucket {unsigned long value : bits_per(SCHED_CAPACITY_SCALE);unsigned long tasks : BITS_PER_LONG - bits_per(SCHED_CAPACITY_SCALE);
};struct uclamp_rq {unsigned int value;struct uclamp_bucket bucket[UCLAMP_BUCKETS];
};
#endif/* CFS-related fields in a runqueue */
struct cfs_rq {struct load_weight	load;unsigned int		nr_running;unsigned int		h_nr_running;      /* SCHED_{NORMAL,BATCH,IDLE} */unsigned int		idle_nr_running;   /* SCHED_IDLE */unsigned int		idle_h_nr_running; /* SCHED_IDLE */u64			exec_clock;u64			min_vruntime;
#ifdef CONFIG_SCHED_COREunsigned int		forceidle_seq;u64			min_vruntime_fi;
#endif#ifndef CONFIG_64BITu64			min_vruntime_copy;
#endifstruct rb_root_cached	tasks_timeline;/** 'curr' points to currently running entity on this cfs_rq.* It is set to NULL otherwise (i.e when none are currently running).*/struct sched_entity	*curr;struct sched_entity	*next;struct sched_entity	*last;struct sched_entity	*skip;#ifdef	CONFIG_SCHED_DEBUGunsigned int		nr_spread_over;
#endif#ifdef CONFIG_SMP/** CFS load tracking*/struct sched_avg	avg;
#ifndef CONFIG_64BITu64			last_update_time_copy;
#endifstruct {raw_spinlock_t	lock ____cacheline_aligned;int		nr;unsigned long	load_avg;unsigned long	util_avg;unsigned long	runnable_avg;} removed;#ifdef CONFIG_FAIR_GROUP_SCHEDunsigned long		tg_load_avg_contrib;long			propagate;long			prop_runnable_sum;/**   h_load = weight * f(tg)** Where f(tg) is the recursive weight fraction assigned to* this group.*/unsigned long		h_load;u64			last_h_load_update;struct sched_entity	*h_load_next;
#endif /* CONFIG_FAIR_GROUP_SCHED */
#endif /* CONFIG_SMP */#ifdef CONFIG_FAIR_GROUP_SCHEDstruct rq		*rq;	/* CPU runqueue to which this cfs_rq is attached *//** leaf cfs_rqs are those that hold tasks (lowest schedulable entity in* a hierarchy). Non-leaf lrqs hold other higher schedulable entities* (like users, containers etc.)** leaf_cfs_rq_list ties together list of leaf cfs_rq's in a CPU.* This list is used during load balance.*/int			on_list;struct list_head	leaf_cfs_rq_list;struct task_group	*tg;	/* group that "owns" this runqueue *//* Locally cached copy of our task_group's idle value */int			idle;#ifdef CONFIG_CFS_BANDWIDTHint			runtime_enabled;s64			runtime_remaining;u64			throttled_pelt_idle;
#ifndef CONFIG_64BITu64                     throttled_pelt_idle_copy;
#endifu64			throttled_clock;u64			throttled_clock_pelt;u64			throttled_clock_pelt_time;int			throttled;int			throttle_count;struct list_head	throttled_list;
#endif /* CONFIG_CFS_BANDWIDTH */
#endif /* CONFIG_FAIR_GROUP_SCHED */
};/** This is the priority-queue data structure of the RT scheduling class:*/
struct rt_prio_array {DECLARE_BITMAP(bitmap, MAX_RT_PRIO+1); /* include 1 bit for delimiter */struct list_head queue[MAX_RT_PRIO];
};/* Real-Time classes' related field in a runqueue: */
struct rt_rq {struct rt_prio_array	active;unsigned int		rt_nr_running;unsigned int		rr_nr_running;
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHEDstruct {int		curr; /* highest queued rt task prio */
#ifdef CONFIG_SMPint		next; /* next highest */
#endif} highest_prio;
#endif
#ifdef CONFIG_SMPunsigned int		rt_nr_migratory;unsigned int		rt_nr_total;int			overloaded;struct plist_head	pushable_tasks;#endif /* CONFIG_SMP */int			rt_queued;int			rt_throttled;u64			rt_time;u64			rt_runtime;/* Nests inside the rq lock: */raw_spinlock_t		rt_runtime_lock;#ifdef CONFIG_RT_GROUP_SCHEDunsigned int		rt_nr_boosted;struct rq		*rq;struct task_group	*tg;
#endif
};/* Deadline class' related fields in a runqueue */
struct dl_rq {/* runqueue is an rbtree, ordered by deadline */struct rb_root_cached	root;unsigned int		dl_nr_running;#ifdef CONFIG_SMP/** Deadline values of the currently executing and the* earliest ready task on this rq. Caching these facilitates* the decision whether or not a ready but not running task* should migrate somewhere else.*/struct {u64		curr;u64		next;} earliest_dl;unsigned int		dl_nr_migratory;int			overloaded;/** Tasks on this rq that can be pushed away. They are kept in* an rb-tree, ordered by tasks' deadlines, with caching* of the leftmost (earliest deadline) element.*/struct rb_root_cached	pushable_dl_tasks_root;
#elsestruct dl_bw		dl_bw;
#endif/** "Active utilization" for this runqueue: increased when a* task wakes up (becomes TASK_RUNNING) and decreased when a* task blocks*/u64			running_bw;/** Utilization of the tasks "assigned" to this runqueue (including* the tasks that are in runqueue and the tasks that executed on this* CPU and blocked). Increased when a task moves to this runqueue, and* decreased when the task moves away (migrates, changes scheduling* policy, or terminates).* This is needed to compute the "inactive utilization" for the* runqueue (inactive utilization = this_bw - running_bw).*/u64			this_bw;u64			extra_bw;/** Inverse of the fraction of CPU utilization that can be reclaimed* by the GRUB algorithm.*/u64			bw_ratio;
};/** This is the main, per-CPU runqueue data structure.** Locking rule: those places that want to lock multiple runqueues* (such as the load balancing or the thread migration code), lock* acquire operations must be ordered by ascending &runqueue.*/
struct rq {/* runqueue lock: */raw_spinlock_t		__lock;/** nr_running and cpu_load should be in the same cacheline because* remote CPUs use both these fields when doing load calculation.*/unsigned int		nr_running;
#ifdef CONFIG_NUMA_BALANCINGunsigned int		nr_numa_running;unsigned int		nr_preferred_running;unsigned int		numa_migrate_on;
#endif
#ifdef CONFIG_NO_HZ_COMMON
#ifdef CONFIG_SMPunsigned long		last_blocked_load_update_tick;unsigned int		has_blocked_load;call_single_data_t	nohz_csd;
#endif /* CONFIG_SMP */unsigned int		nohz_tick_stopped;atomic_t		nohz_flags;
#endif /* CONFIG_NO_HZ_COMMON */#ifdef CONFIG_SMPunsigned int		ttwu_pending;
#endifu64			nr_switches;#ifdef CONFIG_UCLAMP_TASK/* Utilization clamp values based on CPU's RUNNABLE tasks */struct uclamp_rq	uclamp[UCLAMP_CNT] ____cacheline_aligned;unsigned int		uclamp_flags;
#define UCLAMP_FLAG_IDLE 0x01
#endifstruct cfs_rq		cfs;struct rt_rq		rt;struct dl_rq		dl;#ifdef CONFIG_FAIR_GROUP_SCHED/* list of leaf cfs_rq on this CPU: */struct list_head	leaf_cfs_rq_list;struct list_head	*tmp_alone_branch;
#endif /* CONFIG_FAIR_GROUP_SCHED *//** This is part of a global counter where only the total sum* over all CPUs matters. A task can increase this counter on* one CPU and if it got migrated afterwards it may decrease* it on another CPU. Always updated under the runqueue lock:*/unsigned int		nr_uninterruptible;struct task_struct __rcu	*curr;struct task_struct	*idle;struct task_struct	*stop;unsigned long		next_balance;struct mm_struct	*prev_mm;unsigned int		clock_update_flags;u64			clock;/* Ensure that all clocks are in the same cache line */u64			clock_task ____cacheline_aligned;u64			clock_pelt;unsigned long		lost_idle_time;u64			clock_pelt_idle;u64			clock_idle;
#ifndef CONFIG_64BITu64			clock_pelt_idle_copy;u64			clock_idle_copy;
#endifatomic_t		nr_iowait;#ifdef CONFIG_SCHED_DEBUGu64 last_seen_need_resched_ns;int ticks_without_resched;
#endif#ifdef CONFIG_MEMBARRIERint membarrier_state;
#endif#ifdef CONFIG_SMPstruct root_domain		*rd;struct sched_domain __rcu	*sd;unsigned long		cpu_capacity;unsigned long		cpu_capacity_orig;struct balance_callback *balance_callback;unsigned char		nohz_idle_balance;unsigned char		idle_balance;unsigned long		misfit_task_load;/* For active balancing */int			active_balance;int			push_cpu;struct cpu_stop_work	active_balance_work;/* CPU of this runqueue: */int			cpu;int			online;struct list_head cfs_tasks;struct sched_avg	avg_rt;struct sched_avg	avg_dl;
#ifdef CONFIG_HAVE_SCHED_AVG_IRQstruct sched_avg	avg_irq;
#endif
#ifdef CONFIG_SCHED_THERMAL_PRESSUREstruct sched_avg	avg_thermal;
#endifu64			idle_stamp;u64			avg_idle;unsigned long		wake_stamp;u64			wake_avg_idle;/* This is used to determine avg_idle's max value */u64			max_idle_balance_cost;#ifdef CONFIG_HOTPLUG_CPUstruct rcuwait		hotplug_wait;
#endif
#endif /* CONFIG_SMP */#ifdef CONFIG_IRQ_TIME_ACCOUNTINGu64			prev_irq_time;u64			psi_irq_time;
#endif
#ifdef CONFIG_PARAVIRTu64			prev_steal_time;
#endif
#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTINGu64			prev_steal_time_rq;
#endif/* calc_load related fields */unsigned long		calc_load_update;long			calc_load_active;#ifdef CONFIG_SCHED_HRTICK
#ifdef CONFIG_SMPcall_single_data_t	hrtick_csd;
#endifstruct hrtimer		hrtick_timer;ktime_t 		hrtick_time;
#endif#ifdef CONFIG_SCHEDSTATS/* latency stats */struct sched_info	rq_sched_info;unsigned long long	rq_cpu_time;/* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? *//* sys_sched_yield() stats */unsigned int		yld_count;/* schedule() stats */unsigned int		sched_count;unsigned int		sched_goidle;/* try_to_wake_up() stats */unsigned int		ttwu_count;unsigned int		ttwu_local;
#endif#ifdef CONFIG_CPU_IDLE/* Must be inspected within a rcu lock section */struct cpuidle_state	*idle_state;
#endif#ifdef CONFIG_SMPunsigned int		nr_pinned;
#endifunsigned int		push_busy;struct cpu_stop_work	push_work;#ifdef CONFIG_SCHED_CORE/* per rq */struct rq		*core;struct task_struct	*core_pick;unsigned int		core_enabled;unsigned int		core_sched_seq;struct rb_root		core_tree;/* shared state -- careful with sched_core_cpu_deactivate() */unsigned int		core_task_seq;unsigned int		core_pick_seq;unsigned long		core_cookie;unsigned int		core_forceidle_count;unsigned int		core_forceidle_seq;unsigned int		core_forceidle_occupation;u64			core_forceidle_start;
#endif
};// runqueues (not export symbol)
struct rq* _prq = NULL;struct rq* my_cpu_rq(int i_cpu)
{return per_cpu_ptr(_prq, i_cpu);
}u64 my_rq_clock_task(void)
{struct rq* prq = my_cpu_rq(smp_processor_id());return prq->clock_task;
}#define TESTDIOMONITOR_FILE_MAXLEN  1024typedef struct testdiomonitor_sample {struct timespec64 time;int cpu;int pid;int tgid;int ppid;char comm[TASK_COMM_LEN];char ppidcomm[TASK_COMM_LEN];// 0 or 1int bin_iowait;/** "swDstart" // 在sched_switch里* "waDstop"  // 在sched_waking里* "swDiostart" // 在sched_switch里* "waDiostop"  // 在sched_waking里* "Dexceed"    // 超出阈值，非iowait* "Dioexceed"  // 超出阈值，iowait*/const char* desc;u64 dtimens;    // 纳秒单位，D状态持续的时间u64 iowaittimens;   // 纳秒单位，等待io的时间int stackn;void* parray_stack[TEST_STACK_TRACE_ENTRIES];int wakercpu;int wakerpid;int wakertgid;int wakerppid;char wakercomm[TASK_COMM_LEN];char wakerppidcomm[TASK_COMM_LEN];int wakerstackn;void* parray_wakerstack[TEST_STACK_TRACE_ENTRIES];char filepath[TESTDIOMONITOR_FILE_MAXLEN];u32 __state;u64 exec_start_begin;u64 exec_start_end;u64 local_clock_now;u64 clock_task_curr;u32 writedone;  // 0 or 1
} testdiomonitor_sample;#define TESTDIOMONITOR_SAMPLE_RINGBUFF_MAXCOUNT  8192*4typedef struct testdiomonitor_sample_ringbuff {testdiomonitor_sample* parray_sample;volatile u64 wp;    // Index is wp & (TESTDIOMONITOR_SAMPLE_RINGBUFF_MAXCOUNT - 1).volatile u64 rp;    // Index is rp & (TESTDIOMONITOR_SAMPLE_RINGBUFF_MAXCOUNT - 1).u32 skipcount;  // 0 means no skip any abnormal event
} testdiomonitor_sample_ringbuff;#define TESTDIOMONITOR_LINEBUFF  1024typedef struct testdiomonitor_env {struct file* file;char file_linebuff[TESTDIOMONITOR_LINEBUFF];int headoffset;loff_t file_pos;testdiomonitor_sample_ringbuff ringbuff;
} testdiomonitor_env;static testdiomonitor_env _env;static struct delayed_work work_write_file;
static struct workqueue_struct *wq_write_file;#define FILENAME        "test_new_j6_full.txt"void init_file(void)
{_env.file = filp_open(FILENAME, O_WRONLY | O_CREAT | O_TRUNC, 0644);if (IS_ERR(_env.file)) {_env.file = NULL;}
}void exit_file(void)
{if (_env.file) {filp_close(_env.file, NULL);}
}void testdiomonitor_write_file(char* i_pchar, int i_size)
{if (_env.file) {kernel_write(_env.file, i_pchar, i_size, &_env.file_pos);}
}void testdiomonitor_write_file_emptyline(void)
{testdiomonitor_write_file("\n", strlen("\n"));
}void testdiomonitor_file_oneline(const char* i_format, ...)
{char* pcontent = &_env.file_linebuff[_env.headoffset];va_list args;va_start(args, i_format);vsnprintf(pcontent, TESTDIOMONITOR_LINEBUFF - _env.headoffset, i_format, args);va_end(args);testdiomonitor_write_file(_env.file_linebuff, strlen(_env.file_linebuff));
}void testdiomonitor_replace_null_with_space(char *str, int n) {for (int i = 0; i < n - 1; i++) {if (str[i] == '\0') {str[i] = ' ';}}
}void testdiomonitor_set_cmdline(char* i_pbuff, int i_buffsize, struct task_struct* i_ptask)
{int ret = _get_cmdline_func(i_ptask, i_pbuff, i_buffsize);if (ret <= 0) {i_pbuff[0] = '\0';return;}testdiomonitor_replace_null_with_space(i_pbuff, ret);i_pbuff[ret - 1] = '\0';
}void testdiomonitor_checkget_parentinfo_and_cmdline(testdiomonitor_sample* io_psample, struct task_struct* i_ptask)
{struct task_struct* parent;rcu_read_lock();parent = rcu_dereference(i_ptask->real_parent);io_psample->ppid = parent->pid;strlcpy(io_psample->ppidcomm, parent->comm, TASK_COMM_LEN);rcu_read_unlock();
}void testdiomonitor_checkget_parentinfo_and_cmdline_waker(testdiomonitor_sample* io_psample, struct task_struct* i_ptask)
{struct task_struct* parent;rcu_read_lock();parent = rcu_dereference(i_ptask->real_parent);io_psample->wakerppid = parent->pid;strlcpy(io_psample->wakerppidcomm, parent->comm, TASK_COMM_LEN);rcu_read_unlock();
}#define TESTDIOMONITOR_COMMANDLINE_MAX 128int contains_ls(char *str) {const char *substr = "ls";size_t len = strlen(substr); // 获取子字符串的长度const char *p = str;while ((p = strchr(p, substr[0])) != NULL) { // 查找第一个字符 'l'if (strncmp(p, substr, len) == 0) { // 比较后续的字符return 1; // 找到了}p++; // 移动到下一个字符}return 0; // 没有找到
}static void write_file(struct work_struct *w)
{//ssize_t ret;u32 index;testdiomonitor_sample* psample;struct tm t;char timestr[64];char exceedstr[64];char temp_commandline[TESTDIOMONITOR_COMMANDLINE_MAX];struct pid* pid_struct;struct task_struct* ptask;int stacki;while (_env.ringbuff.rp != _env.ringbuff.wp) {index = (_env.ringbuff.rp & (TESTDIOMONITOR_SAMPLE_RINGBUFF_MAXCOUNT - 1));psample = &_env.ringbuff.parray_sample[index];if (psample->writedone != 1) {break;}testdiomonitor_write_file_emptyline();_env.headoffset = sprintf(_env.file_linebuff, "[%llu][%s] ", _env.ringbuff.rp, psample->desc);time64_to_tm(psample->time.tv_sec + 8 * 60 * 60, 0, &t);snprintf(timestr, 64, "%04ld-%02d-%02d-%02d_%02d_%02d.%09ld",1900 + t.tm_year, t.tm_mon + 1, t.tm_mday, t.tm_hour, t.tm_min, t.tm_sec, psample->time.tv_nsec);if (psample->desc == (const char*)TESTDIOMONITOR_SAMPLEDESC_DEXCEED) {snprintf(exceedstr, 64, "dtimens[%llu]", psample->dtimens);}else if (psample->desc == (const char*)TESTDIOMONITOR_SAMPLEDESC_DIOEXCEED) {snprintf(exceedstr, 64, "iowaittimens[%llu]", psample->iowaittimens);}else if (psample->desc == (const char*)TESTDIOMONITOR_SAMPLEDESC_IOEXCEED) {snprintf(exceedstr, 64, "delayacct_iowaittimens[%llu]", psample->iowaittimens);}else {exceedstr[0] = '\0';}//if (psample->desc == (const char*)TESTDIOMONITOR_SAMPLEDESC_DIOEXCEED) {if (psample->desc == (const char*)TESTDIOMONITOR_SAMPLEDESC_DEXCEED) {testdiomonitor_file_oneline("[skipcount:%u]begin...time[%s]wakercpu[%d]desc[%s]%s\n", _env.ringbuff.skipcount, timestr, psample->wakercpu, psample->desc, "wakerDexceed");testdiomonitor_file_oneline("wakertgid[%d]wakerpid[%d]wakercomm[%s]wakerppid[%d]wakerppidcomm[%s]\n",psample->wakertgid, psample->wakerpid, psample->wakercomm, psample->wakerppid, psample->wakerppidcomm);pid_struct = find_get_pid(psample->wakerpid);if (pid_struct) {ptask = get_pid_task(pid_struct, PIDTYPE_PID);if (ptask) {testdiomonitor_set_cmdline(temp_commandline, TESTDIOMONITOR_COMMANDLINE_MAX, ptask);put_task_struct(ptask);}else {temp_commandline[0] = '\0';}put_pid(pid_struct);}else {temp_commandline[0] = '\0';}testdiomonitor_file_oneline("wakercommandline[%s]\n", temp_commandline);pid_struct = find_get_pid(psample->wakerppid);if (pid_struct) {ptask = get_pid_task(pid_struct, PIDTYPE_PID);if (ptask) {testdiomonitor_set_cmdline(temp_commandline, TESTDIOMONITOR_COMMANDLINE_MAX, ptask);put_task_struct(ptask);}else {temp_commandline[0] = '\0';}put_pid(pid_struct);}else {temp_commandline[0] = '\0';}testdiomonitor_file_oneline("wakerppid_commandline[%s]\n", temp_commandline);testdiomonitor_file_oneline("stack[%d]:\n", psample->wakerstackn);for (stacki = 0; stacki < psample->wakerstackn; stacki++) {testdiomonitor_file_oneline("%*c%pS\n", 5, ' ', (void *)psample->parray_wakerstack[stacki]);}testdiomonitor_file_oneline("cpu[%d]desc[%s]%s\n", psample->cpu, psample->desc, exceedstr);}else {testdiomonitor_file_oneline("begin...time[%s]cpu[%d]desc[%s]%s\n", timestr, psample->cpu, psample->desc, exceedstr);}testdiomonitor_file_oneline("tgid[%d]pid[%d]comm[%s]ppid[%d]ppidcomm[%s]\n",psample->tgid, psample->pid, psample->comm, psample->ppid, psample->ppidcomm);{const char *desc = "NA";if (psample->__state == TASK_UNINTERRUPTIBLE) {desc = "D";}else if (psample->__state == TASK_KILLABLE) {desc = "K";}testdiomonitor_file_oneline("iniowait[%u]__state[%u][%s]exec_start_begin[%llu]exec_start_end[%llu]local_clock[%llu]clock_task_curr[%llu]\n",psample->bin_iowait ? 1 : 0, psample->__state, desc, psample->exec_start_begin, psample->exec_start_end, psample->local_clock_now, psample->clock_task_curr);}pid_struct = find_get_pid(psample->pid);if (pid_struct) {ptask = get_pid_task(pid_struct, PIDTYPE_PID);if (ptask) {testdiomonitor_set_cmdline(temp_commandline, TESTDIOMONITOR_COMMANDLINE_MAX, ptask);put_task_struct(ptask);}else {temp_commandline[0] = '\0';}put_pid(pid_struct);}else {temp_commandline[0] = '\0';}testdiomonitor_file_oneline("commandline[%s]\n", temp_commandline);pid_struct = find_get_pid(psample->ppid);if (pid_struct) {ptask = get_pid_task(pid_struct, PIDTYPE_PID);if (ptask) {testdiomonitor_set_cmdline(temp_commandline, TESTDIOMONITOR_COMMANDLINE_MAX, ptask);put_task_struct(ptask);}else {temp_commandline[0] = '\0';}put_pid(pid_struct);}else {temp_commandline[0] = '\0';}testdiomonitor_file_oneline("ppid_commandline[%s]\n", temp_commandline);//testdiomonitor_file_oneline("filepath[%s]\n", psample->filepath);testdiomonitor_file_oneline("stack[%d]:\n", psample->stackn);for (stacki = 0; stacki < psample->stackn; stacki++) {testdiomonitor_file_oneline("%*c%pS\n", 5, ' ', (void *)psample->parray_stack[stacki]);}testdiomonitor_write_file_emptyline();smp_wmb();psample->writedone = 0;_env.ringbuff.rp ++;}queue_delayed_work_on(nr_cpu_ids - 1, wq_write_file,&work_write_file, 1);
}static void init_write_file(void)
{init_file();wq_write_file = alloc_workqueue("testdiomonitor_write_file", WQ_MEM_RECLAIM, 0);INIT_DELAYED_WORK(&work_write_file, write_file);queue_delayed_work_on(nr_cpu_ids - 1, wq_write_file,&work_write_file, 3);
}static void exit_write_file(void)
{cancel_delayed_work_sync(&work_write_file);destroy_workqueue(wq_write_file);exit_file();
}void init_testdiomonitor_sample_ringbuff(void) 
{//testdiomonitor_sample* psample;_env.ringbuff.parray_sample = kvzalloc(sizeof(testdiomonitor_sample) * TESTDIOMONITOR_SAMPLE_RINGBUFF_MAXCOUNT, GFP_KERNEL);
}void exit_testdiomonitor_sample_ringbuff(void)
{kvfree(_env.ringbuff.parray_sample);
}testdiomonitor_sample* testdiomonitor_get_psample(void)
{u64 windex_raw, windex_raw_old;u32 windex;while (1) {windex_raw = _env.ringbuff.wp;if (windex_raw - _env.ringbuff.rp >= (u64)(TESTDIOMONITOR_SAMPLE_RINGBUFF_MAXCOUNT)) {_env.ringbuff.skipcount ++;return NULL;}// atomic_cmpxchg return old valuewindex_raw_old = atomic64_cmpxchg((atomic64_t*)&_env.ringbuff.wp,windex_raw, windex_raw + 1);if (windex_raw_old == windex_raw) {break;}}windex = (u32)(windex_raw & (u64)(TESTDIOMONITOR_SAMPLE_RINGBUFF_MAXCOUNT - 1));return &_env.ringbuff.parray_sample[windex];
}static u64 _magic_number = 0xABCDEFull;void* _dl_sched_class = NULL;int get_file_dir_by_folio(struct folio *i_fo, char* i_path, int i_len);void testdiomonitor_add_sample(const char* i_desc, struct task_struct* i_task, u64 i_timens, u32 i_state, u64 i_exec_start_begin, u64 i_exec_start_end, u64 i_local_clock, u64 i_clock_task_curr)
{testdiomonitor_sample* psample = testdiomonitor_get_psample();if (!psample) {return;}ktime_get_real_ts64(&psample->time);psample->cpu = task_cpu(i_task);psample->pid = i_task->pid;psample->tgid = i_task->tgid;strlcpy(psample->comm, i_task->comm, TASK_COMM_LEN);testdiomonitor_checkget_parentinfo_and_cmdline(psample, i_task);psample->bin_iowait = i_task->in_iowait;psample->desc = i_desc;if (i_desc == (const char*)TESTDIOMONITOR_SAMPLEDESC_DEXCEED) {psample->dtimens = i_timens;}else if (i_desc == (const char*)TESTDIOMONITOR_SAMPLEDESC_DIOEXCEED || i_desc == (const char*)TESTDIOMONITOR_SAMPLEDESC_IOEXCEED) {psample->iowaittimens = i_timens;}psample->stackn = _stack_trace_save_tsk(i_task, (unsigned long*)psample->parray_stack, TEST_STACK_TRACE_ENTRIES, 0);//if (i_desc == (const char*)TESTDIOMONITOR_SAMPLEDESC_DIOEXCEED) {if (i_desc == (const char*)TESTDIOMONITOR_SAMPLEDESC_DEXCEED) {psample->__state = i_state;psample->exec_start_begin = i_exec_start_begin;psample->exec_start_end = i_exec_start_end;psample->local_clock_now = i_local_clock;psample->clock_task_curr = i_clock_task_curr;psample->wakercpu = smp_processor_id();psample->wakerpid = current->pid;psample->wakertgid = current->tgid;strlcpy(psample->wakercomm, current->comm, TASK_COMM_LEN);testdiomonitor_checkget_parentinfo_and_cmdline_waker(psample, current);psample->wakerstackn = _stack_trace_save_tsk(current, (unsigned long*)psample->parray_wakerstack, TEST_STACK_TRACE_ENTRIES, 0);// psample->filepath[0] = '\0';// if ((void*)i_task->sched_class != (void*)&_dl_sched_class) {//     if (i_task->dl.dl_runtime == _magic_number) {//         //if (sched_clock() - i_task->dl.dl_deadline >= TESTDIOMONITOR_SIMPLE_THRESHOLDNS) //         {//             //printk("__folio_lock_killable wait %llu ns\n", sched_clock() - current->dl.dl_deadline);//             //dump_stack();//             if (get_file_dir_by_folio((struct folio*)i_task->dl.dl_period, psample->filepath, TESTDIOMONITOR_FILE_MAXLEN) < 0) {//                 //printk("get_file_dir_by_folio fail!\n");//             }//         }//         current->dl.dl_runtime = 0;//     }// }}smp_wmb();psample->writedone = 1;
}static void cb_sched_switch(void *i_data, bool i_preempt,struct task_struct *i_prev,struct task_struct *i_next,unsigned int i_prev_state)
{
#ifndef TESTDIOMONITOR_SIMPLEvoid* parray_stack[TEST_STACK_TRACE_ENTRIES];int num_stack;int stacki;if (i_prev_state == TASK_UNINTERRUPTIBLE) {if (i_prev->in_iowait) {testdiomonitor_add_sample(TESTDIOMONITOR_SAMPLEDESC_SWDIOSTART, i_prev, 0);}else {testdiomonitor_add_sample(TESTDIOMONITOR_SAMPLEDESC_SWDSTART, i_prev, 0);}}else if (i_prev->in_iowait) {testdiomonitor_add_sample(TESTDIOMONITOR_SAMPLEDESC_SWDIOSTART, i_prev, 0);}
#endif
}const char* getstatstr_bystate(u32 i_state) {switch (i_state) {case TASK_RUNNING:return "TASK_RUNNING";case TASK_INTERRUPTIBLE:return "TASK_INTERRUPTIBLE";case TASK_UNINTERRUPTIBLE:return "TASK_UNINTERRUPTIBLE";default:return "other";}
}static void cb_sched_waking(void *i_data, struct task_struct *i_p) {if ((i_p->__state & TASK_UNINTERRUPTIBLE) == TASK_UNINTERRUPTIBLE) {//u64 currns = my_rq_clock_task();struct rq* prq = my_cpu_rq(task_cpu(i_p));struct rq* prq_curr = my_cpu_rq(smp_processor_id());u64 currns = prq->clock_task;u64 currns_curr = prq_curr->clock_task;//u64 local_c = local_clock();//int cpuid = smp_processor_id();//if (i_p->in_iowait) {
#ifndef TESTDIOMONITOR_SIMPLEtestdiomonitor_add_sample(TESTDIOMONITOR_SAMPLEDESC_WADIOSTOP, i_p, 0);
#endif
#ifdef TESTDIOMONITOR_SIMPLE//if (currns - i_p->se.exec_start >= TESTDIOMONITOR_SIMPLE_THRESHOLDNS)
#endif//testdiomonitor_add_sample(TESTDIOMONITOR_SAMPLEDESC_DIOEXCEED, i_p, currns - i_p->se.exec_start);
#ifndef TESTDIOMONITOR_SIMPLEif (i_p->se.exec_start > currns) {//if (task_cpu(i_p) == cpuid) {printk("comm[%s]pid[%d]exec_start[%llu]currns[%llu]local_clock[%llu]last_cpu[%d]cpuid[%d]\n", i_p->comm, i_p->pid, i_p->se.exec_start, currns, local_c, task_cpu(i_p), cpuid);}}// if (printk_ratelimit()) {//     printk("waking dump_stack[D]:\n");//     dump_stack();// }
#endif}
//#ifndef TESTDIOMONITOR_SIMPLE//else {//testdiomonitor_add_sample(TESTDIOMONITOR_SAMPLEDESC_WADSTOP, i_p, 0);if (currns - i_p->se.exec_start >= TESTDIOMONITOR_SIMPLE_THRESHOLDNS) {//if (strcmp(current->comm, "ls") == 0) {//if (strcmp(i_p->comm, "hobot-log") != 0) {testdiomonitor_add_sample(TESTDIOMONITOR_SAMPLEDESC_DEXCEED, i_p, currns - i_p->se.exec_start, i_p->__state, i_p->se.exec_start, currns, local_clock(), currns_curr);}return;//}}if (i_p->se.exec_start > currns) {//if (task_cpu(i_p) == cpuid) // {//     printk("comm[%s]pid[%d]exec_start[%llu]currns[%llu]local_clock[%llu]last_cpu[%d]cpuid[%d]\n", //         i_p->comm, i_p->pid, i_p->se.exec_start, currns, local_c, task_cpu(i_p), cpuid);// }}}
//#endif}if (strcmp(current->comm, "ls") == 0|| strcmp(current->comm, "wc") == 0|| strcmp(current->comm, "grep") == 0|| strcmp(current->comm, "awk") == 0) {if (strcmp(i_p->comm, "hobot-log") != 0&& strcmp(i_p->comm, "kthreadd") != 0) {struct rq* prq = my_cpu_rq(task_cpu(i_p));struct rq* prq_curr = my_cpu_rq(smp_processor_id());u64 currns = prq->clock_task;u64 currns_curr = prq_curr->clock_task;testdiomonitor_add_sample(TESTDIOMONITOR_SAMPLEDESC_DEXCEED, i_p, currns - i_p->se.exec_start, i_p->__state, i_p->se.exec_start, currns, local_clock(), currns_curr);}}//else if (i_p->in_iowait) {//struct rq* prq = my_cpu_rq(task_cpu(i_p));//u64 currns = prq->clock_task;//u64 local_c = local_clock();//int cpuid = smp_processor_id();//if (printk_ratelimit()) // {//     printk("i_p->__state=[%u][%s]\n", i_p->__state, getstatstr_bystate(i_p->__state));//     printk("waking dump_stack[K]:\n");//     dump_stack();// }
#ifndef TESTDIOMONITOR_SIMPLEtestdiomonitor_add_sample(TESTDIOMONITOR_SAMPLEDESC_WADIOSTOP, i_p, 0);
#endif
#ifdef TESTDIOMONITOR_SIMPLE//if (currns - i_p->se.exec_start >= TESTDIOMONITOR_SIMPLE_THRESHOLDNS)
#endif//testdiomonitor_add_sample(TESTDIOMONITOR_SAMPLEDESC_DIOEXCEED, i_p, currns - i_p->se.exec_start);}
}static void cb_iodelay_account(void *i_data, struct task_struct *i_curr,unsigned long long i_delta)
{
#ifdef TESTDIOMONITOR_SIMPLE//if (i_delta >= TESTDIOMONITOR_SIMPLE_THRESHOLDNS)
#endif//testdiomonitor_add_sample(TESTDIOMONITOR_SAMPLEDESC_IOEXCEED, i_curr, i_delta);
}struct kern_tracepoint {void *callback;struct tracepoint *ptr;bool bregister;
};
static void clear_kern_tracepoint(struct kern_tracepoint *tp)
{if (tp->bregister) {tracepoint_probe_unregister(tp->ptr, tp->callback, NULL);}
}#define INIT_KERN_TRACEPOINT(tracepoint_name) \static struct kern_tracepoint mykern_##tracepoint_name = {.callback = NULL, .ptr = NULL, .bregister = false};#define TRACEPOINT_CHECK_AND_SET(tracepoint_name)                                             \static void tracepoint_name##_tracepoint_check_and_set(struct tracepoint *tp, void *priv) \{                                                                                \if (!strcmp(#tracepoint_name, tp->name))                                     \{                                                                            \((struct kern_tracepoint *)priv)->ptr = tp;                          \return;                                                                  \}                                                                            \}INIT_KERN_TRACEPOINT(sched_switch)
TRACEPOINT_CHECK_AND_SET(sched_switch)
INIT_KERN_TRACEPOINT(sched_waking)
TRACEPOINT_CHECK_AND_SET(sched_waking)
#ifdef IODELAY_TRACEPOINT_ENABLE
INIT_KERN_TRACEPOINT(iodelay_account)
TRACEPOINT_CHECK_AND_SET(iodelay_account)
#endiftypedef unsigned long (*kallsyms_lookup_name_func)(const char *name);
kallsyms_lookup_name_func _kallsyms_lookup_name_func;void* get_func_by_symbol_name_kallsyms_lookup_name(void)
{int ret;void* pfunc = NULL;struct kprobe kp;memset(&kp, 0, sizeof(kp));kp.symbol_name = "kallsyms_lookup_name";kp.pre_handler = NULL;kp.addr = NULL;	// 作为强调，提示使用symbol_nameret = register_kprobe(&kp);if (ret < 0) {printk("register_kprobe fail!\n");return NULL;}printk("register_kprobe succeed!\n");pfunc = (void*)kp.addr;unregister_kprobe(&kp);return pfunc;
}void* get_func_by_symbol_name(const char* i_symbol)
{if (_kallsyms_lookup_name_func == NULL) {return NULL;}return (void*)_kallsyms_lookup_name_func(i_symbol);
}enum behavior {EXCLUSIVE,	/* Hold ref to page and take the bit when woken, like* __folio_lock() waiting on then setting PG_locked.*/SHARED,		/* Hold ref to page and check the bit when woken, like* folio_wait_writeback() waiting on PG_writeback.*/DROP,		/* Drop ref to page before wait, no check when woken,* like folio_put_wait_locked() on PG_locked.*/
};int kprobecb_folio_lock_killable_pre(struct kprobe* i_k, struct pt_regs* i_p)
{if ((void*)current->sched_class != (void*)&_dl_sched_class) {struct folio *fo = (struct folio*) i_p->regs[0];//i_p->di;int bit_nr = (int)i_p->regs[1];//i_p->si;int state = (int)i_p->regs[2];//i_p->dx;enum behavior beh = (enum behavior)i_p->regs[3];//i_p->cx;if (bit_nr != PG_locked || state != TASK_KILLABLE|| beh != EXCLUSIVE) {return 0;}current->dl.dl_runtime = _magic_number;current->dl.dl_deadline = sched_clock();current->dl.dl_period = (u64)fo;}return 0;
}int getfullpath(struct inode *inode,char* i_buffer,int i_len)
{struct dentry *dentry;//printk("inode = %ld\n", inode->i_ino);//spin_lock(&inode->i_lock);hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {char *buffer, *path;buffer = (char *)__get_free_page(GFP_KERNEL);if (!buffer)return -ENOMEM;path = dentry_path_raw(dentry, buffer, PAGE_SIZE);if (IS_ERR(path)){continue;   }strlcpy(i_buffer, path, i_len);//printk("dentry name = %s , path = %s", dentry->d_name.name, path);free_page((unsigned long)buffer);}//spin_unlock(&inode->i_lock);return 0;
}int get_file_dir_by_folio(struct folio *i_fo, char* i_path, int i_len)
{if (i_fo->mapping) {struct inode *inode = i_fo->mapping->host;if (inode) {// struct dentry *dentry = inode->i_dentry;// if (!dentry) {//     return -1;// }{//char path_buf[256];int ret = 0;if ((ret = getfullpath(inode, i_path, i_len)) < 0) {return ret;}// struct path path;// //dentry_lock(dentry);// path.dentry = dentry;// path.mnt = dget(dentry->d_sb->s_root);// if (dentry_path_raw(dentry, path_buf, sizeof(path_buf)) >= 0) {//     pr_info("File path: %s\n", path_buf);// }//dentry_unlock(dentry);}return 0;}}return -1;
}struct kprobe _kp1;void kprobecb_folio_lock_killable_post(struct kprobe *p, struct pt_regs *regs,unsigned long flags)
{// if (current->sched_class != &_dl_sched_class) {//     if (current->dl.dl_runtime == _magic_number) {//         if (sched_clock() - current->dl.dl_deadline >= TESTDIOMONITOR_SIMPLE_THRESHOLDNS) {//             //printk("__folio_lock_killable wait %llu ns\n", sched_clock() - current->dl.dl_deadline);//             //dump_stack();//             if (get_file_dir_by_folio((struct folio*)current->dl.dl_period) < 0) {//                 printk("get_file_dir_by_folio fail!\n");//             }//         }//         current->dl.dl_runtime = 0;//     }// }
}int kprobe_register_func_folio_lock_killable(void)
{// int ret;// memset(&_kp1, 0, sizeof(_kp1));// _kp1.symbol_name = "folio_wait_bit_common";// _kp1.pre_handler = kprobecb_folio_lock_killable_pre;// _kp1.post_handler = kprobecb_folio_lock_killable_post;// ret = register_kprobe(&_kp1);// if (ret < 0) {// 	printk("register_kprobe fail!\n");// 	return -1;// }// printk("register_kprobe success!\n");return 0;
}void kprobe_unregister_func_folio_lock_killable(void)
{// unregister_kprobe(&_kp1);
}extern void* get_dl_sched_class_pointer(void);
extern struct rq* get_runqueues(void);static int __init testdiomonitor_full_init(void)
{printk(KERN_INFO "ns=%lu\n", ns);//printk("offset of mmap_lock in mm_struct [%d]\n", offsetof(struct mm_struct, mmap_lock));_kallsyms_lookup_name_func = get_func_by_symbol_name_kallsyms_lookup_name();// _dl_sched_class = (void*)_kallsyms_lookup_name_func("dl_sched_class");// if (_dl_sched_class == NULL) {//     printk(KERN_ERR "get_func_by_symbol_name _dl_sched_class failed!\n");//     return -1;// }_dl_sched_class = get_dl_sched_class_pointer();// _prq = get_func_by_symbol_name("runqueues");// if (_prq == NULL) {//     printk(KERN_ERR "get_func_by_symbol_name runqueues failed!\n");//     return -1;// }_prq = get_runqueues();init_testdiomonitor_sample_ringbuff();init_write_file();_stack_trace_save_tsk = get_func_by_symbol_name("stack_trace_save_tsk");if (_stack_trace_save_tsk == NULL) {printk(KERN_ERR "get_func_by_symbol_name stack_trace_save_tsk failed!\n");return -1;}_get_cmdline_func = get_func_by_symbol_name("get_cmdline");if (_get_cmdline_func == NULL) {printk(KERN_ERR "get_func_by_symbol_name get_cmdline failed!\n");return -1;}mykern_sched_switch.callback = cb_sched_switch;for_each_kernel_tracepoint(sched_switch_tracepoint_check_and_set, &mykern_sched_switch);if (!mykern_sched_switch.ptr) {printk(KERN_ERR "mykern_sched_switch register failed!\n");return -1;}else {printk(KERN_INFO "mykern_sched_switch register succeeded!\n");}tracepoint_probe_register(mykern_sched_switch.ptr, mykern_sched_switch.callback, NULL);mykern_sched_switch.bregister = 1;mykern_sched_waking.callback = cb_sched_waking;for_each_kernel_tracepoint(sched_waking_tracepoint_check_and_set, &mykern_sched_waking);if (!mykern_sched_waking.ptr) {printk(KERN_ERR "mykern_sched_waking register failed!\n");return -1;}else {printk(KERN_INFO "mykern_sched_waking register succeeded!\n");}tracepoint_probe_register(mykern_sched_waking.ptr, mykern_sched_waking.callback, NULL);mykern_sched_waking.bregister = 1;#ifdef IODELAY_TRACEPOINT_ENABLEmykern_iodelay_account.callback = cb_iodelay_account;for_each_kernel_tracepoint(iodelay_account_tracepoint_check_and_set, &mykern_iodelay_account);if (!mykern_iodelay_account.ptr) {printk(KERN_ERR "mykern_iodelay_account register failed!\n");return -1;}else {printk(KERN_INFO "mykern_iodelay_account register succeeded!\n");}tracepoint_probe_register(mykern_iodelay_account.ptr, mykern_iodelay_account.callback, NULL);mykern_iodelay_account.bregister = 1;
#endifkprobe_register_func_folio_lock_killable();return 0;
}static void __exit testdiomonitor_fullexit(void)
{kprobe_unregister_func_folio_lock_killable();clear_kern_tracepoint(&mykern_sched_switch);clear_kern_tracepoint(&mykern_sched_waking);
#ifdef IODELAY_TRACEPOINT_ENABLEclear_kern_tracepoint(&mykern_iodelay_account);
#endiftracepoint_synchronize_unregister();exit_write_file();exit_testdiomonitor_sample_ringbuff();
}module_init(testdiomonitor_full_init);
module_exit(testdiomonitor_fullexit);

2.2 抓取效果展示

抓取到的waker唤醒wakee的堆栈如下：

三、源码改动部分解释及TASK_RTLOCK_WAIT相关细节

3.1 TASK_RTLOCK_WAIT状态在perfetto的视角里是Uninterruptible Sleep状态，即通常意义上的D状态

如下图，抓自perfetto里：

如下图可以看到，这个3626线程是被ls 16492唤醒：

3.1.1 但是从抓到的堆栈里可以看到__state里的TASK_UNINTERRUPTIBLE的这个bit并不是1

下图是抓到的waker和wakee的堆栈：

从上图里的被唤醒者，线程3626的状态信息：__state[4096]可以得知，在trace_sched_waking时被唤醒者线程的状态是4096，即0x1000，而TASK_UNINTERRUPTIBLE是2，所以__state & TASK_UNINTERRUPTIBLE并不等于TASK_UNINTERRUPTIBLE。

所以这种特殊的peretto认为的D状态，在底层逻辑里不能通过__state & TASK_UNINTERRUPTIBLE是否等于TASK_UNINTERRUPTIBLE来判断。

3.1.2 TASK_RTLOCK_WAIT是0x1000

在kernel/include/linux/sched.h里有TASK_RTLOCK_WAIT的定义

3.2 rt-linux系统里用到的rtmutex和spinlock_rt会设置这个TASK_RTLOCK_WAIT状态

TASK_RTLOCK_WAIT状态会设置到__state里，在如下图在rtlock_slowlock_locked有设置：

另外，在current_save_and_set_rtlock_wait_state宏里有如下设置：

而current_save_and_set_rtlock_wait_state宏在rtlock_slowlock_locked（rtmutex.c）和spinlock_rt.c里都有使用：

上图里的rwbase_set_and_save_current_state宏在rwbase_write_lock里使用：

在使能CONFIG_PREEMPT_RT宏之后，struct mutex被定义成：

而rt_mutex_base有关的函数即在上面已经展示过的rtmutex.c里的rtlock_slowlock_locked等函数所关联使用。

3.3 源码改动部分解释

在 2.1 一节里展示的源码，展示的是在调试过程中抓到问题情况堆栈的一份源码，但是从原理上，是可以进行进一步改进的。我们在下面的最后一节 3.3.5 里提及如何进一步改进。我们先说明一下源码里和之前的缺页异常导致的iowait打印出相关文件的绝对路径-CSDN博客博客里的 2.1 一节里的源码的差异改动部分的内容的原理。

3.3.1 针对arm64平台需要调整kprobe的callback里的实现

我们的这次实例代码是针对的arm64的rt-linux平台，针对kprobe的callback的实现，需要针对不同的平台做不同的调整，如果是arm64平台，则要如下方式使用参数，即由原来的x86下的di/si/dx/cx改成regs[0]/regs[1]/regs[2]/regs[3]这样来得到入参：

3.3.2 内核里增加两个函数，为了适配当前的arm64内核版本

当前使用arm64内核版本无法拿到runqueues和dl_sched_class这两个符号。

所以直接在内核里增加两个export symbol的函数，如下实现：

3.3.3 为了让抓取的堆栈更加聚焦D状态，去掉了iowait情况的抓取

去掉iowait情形，只打印非iowait时的D状态的堆栈：

打印唤醒者和被唤醒者的堆栈的逻辑和抓iowait时堆栈的逻辑是基本一样的。

相应地，在采样时，也只转换非iowait的D状态的情况：

为了清楚的显示任务在被waking时的状态，写了一个状态转换函数：

这部分倒是可以在优化一下，增加TASK_RTLOCK_WAIT的情况，还有的情况，这里1026即TASK_RTLOCK_WAIT | TASK_UNINTERRUPTIBLE的状态。

这个增加TASK_RTLOCK_WAIT等其他状态在调试到问题情况前是不预知，即并不知道会出现这样的状态，所以真正在调试一些corner case时，还得加一些额外的如下面 3.3.3 里类似的逻辑去增加一些打印，但是肯定得考虑增加的打印的量不能过大而导致引入别的问题或者引入因为打印过大而导致的问题。