/*
 * Kernel pointers have redundant information, so we can use a
 * scheme where we can return either an error code or a normal
 * pointer with the same return value.
 *
 * This should be a per-architecture thing, to allow different
 * error and pointer decisions.
 */
#define MAX_ERRNO	4095

#ifndef __ASSEMBLY__

#define IS_ERR_VALUE(x) unlikely((unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO)

 * <__x64_sys_recv>:		<-- syscall with 4 parameters
 *	callq	<__fentry__>
 *
 *	mov	0x70(%rdi),%rdi	<-- decode regs->di
 *	mov	0x68(%rdi),%rsi	<-- decode regs->si
 *	mov	0x60(%rdi),%rdx	<-- decode regs->dx
 *	mov	0x38(%rdi),%rcx	<-- decode regs->r10
 *
 *	xor	%r9d,%r9d	<-- clear %r9
 *	xor	%r8d,%r8d	<-- clear %r8
 *
 *	callq	__sys_recvfrom	<-- do the actual work in __sys_recvfrom()
 *				    which takes 6 arguments
 *
 *	cltq			<-- extend return value to 64-bit
 *	retq			<-- return
 *

	wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
	wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);

SYM_CODE_START(entry_SYSCALL_64)
	UNWIND_HINT_EMPTY

	swapgs
	/* tss.sp2 is scratch space. */
	movq	%rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp

SYM_INNER_LABEL(entry_SYSCALL_64_safe_stack, SYM_L_GLOBAL)

	/* Construct struct pt_regs on stack */
	pushq	$__USER_DS				/* pt_regs->ss */
	pushq	PER_CPU_VAR(cpu_tss_rw + TSS_sp2)	/* pt_regs->sp */
	pushq	%r11					/* pt_regs->flags */
	pushq	$__USER_CS				/* pt_regs->cs */
	pushq	%rcx					/* pt_regs->ip */
SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
	pushq	%rax					/* pt_regs->orig_ax */

	PUSH_AND_CLEAR_REGS rax=$-ENOSYS

	/* IRQs are off. */
	movq	%rsp, %rdi
	/* Sign extend the lower 32bit as syscall numbers are treated as int */
	movslq	%eax, %rsi
	call	do_syscall_64		/* returns with IRQs disabled */

__visible noinstr void do_syscall_64(struct pt_regs *regs, int nr)
{
	add_random_kstack_offset();
	nr = syscall_enter_from_user_mode(regs, nr);
	/* syscall_enter_from_user_mode里面会检查一些权限, 比如是否满足SECCOMP. 对系统调用的审计也在这里 
	 * 如果返回-1, 则不会执行下面的函数, 最终给用户态程序返回 -ENOSYS
	*/

	instrumentation_begin();

	if (!do_syscall_x64(regs, nr) && !do_syscall_x32(regs, nr) && nr != -1) {
		/* Invalid system call, but still a system call. */
		regs->ax = __x64_sys_ni_syscall(regs);
	}

	instrumentation_end();
	syscall_exit_to_user_mode(regs);
}

crash> whatis sys_call_table
const sys_call_ptr_t sys_call_table[];
crash> p sys_call_table[0]
$9 = (const sys_call_ptr_t) 0xffffffffb9b19c30
crash> sym 0xffffffffb9b19c30
ffffffffb9b19c30 (T) __x64_sys_read /usr/src/debug/kernel-4.18.0-305.3.1.el8_4/linux-4.18.0-305.3.1.el8.x86_64/fs/read_write.c: 586
crash>

struct task_struct {
u64        utime;//用户态消耗的CPU时间
u64        stime;//内核态消耗的CPU时间
unsigned long      nvcsw;//自愿(voluntary)上下文切换计数
unsigned long      nivcsw;//非自愿(involuntary)上下文切换计数
u64        start_time;//进程启动时间，不包含睡眠时间
u64        real_start_time;//进程启动时间，包含睡眠时间
}

/* TICK_NSEC is the time between ticks in nsec assuming SHIFTED_HZ */
#define TICK_NSEC ((NSEC_PER_SEC+HZ/2)/HZ)

/*
 * Account a tick to a process and cpustat
 * @p: the process that the CPU time gets accounted to
 * @user_tick: is the tick from userspace
 * @rq: the pointer to rq
 *
 * Tick demultiplexing follows the order
 * - pending hardirq update
 * - pending softirq update
 * - user_time
 * - idle_time
 * - system time
 *   - check for guest_time
 *   - else account as system_time
 *
 * Check for hardirq is done both for system and user time as there is
 * no timer going off while we are on hardirq and hence we may never get an
 * opportunity to update it solely in system time.
 * p->stime and friends are only updated on system time and not on irq
 * softirq as those do not count in task exec_runtime any more.
 */
static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
					 int ticks)
{
	u64 other, cputime = TICK_NSEC * ticks;

	/*
	 * When returning from idle, many ticks can get accounted at
	 * once, including some ticks of steal, irq, and softirq time.
	 * Subtract those ticks from the amount of time accounted to
	 * idle, or potentially user or system time. Due to rounding,
	 * other time can exceed ticks occasionally.
	 */
	other = account_other_time(ULONG_MAX);
	if (other >= cputime)
		return;

	cputime -= other;

	if (this_cpu_ksoftirqd() == p) {
		/*
		 * ksoftirqd time do not get accounted in cpu_softirq_time.
		 * So, we have to handle it separately here.
		 * Also, p->stime needs to be updated for ksoftirqd.
		 */
		account_system_index_time(p, cputime, CPUTIME_SOFTIRQ);
	} else if (user_tick) {
		account_user_time(p, cputime);
	} else if (p == this_rq()->idle) {
		account_idle_time(cputime);
	} else if (p->flags & PF_VCPU) { /* System time or guest time */
		account_guest_time(p, cputime);
	} else {
		account_system_index_time(p, cputime, CPUTIME_SYSTEM);
	}
}

update_process_times
	irqtime_account_process_tick     /* 更新cpu信息 */
	scheduler_tick                   /* 更新调度相关的信息, 比如 vruntime */

u64 nsec_to_clock_t(u64 x)
{
#if (NSEC_PER_SEC % USER_HZ) == 0
	return div_u64(x, NSEC_PER_SEC / USER_HZ);
#elif (USER_HZ % 512) == 0
	return div_u64(x * USER_HZ / 512, NSEC_PER_SEC / 512);
#else
	/*
         * max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024,
         * overflow after 64.99 years.
         * exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ...
         */
	return div_u64(x * 9, (9ull * NSEC_PER_SEC + (USER_HZ / 2)) / USER_HZ);
#endif
}

	seq_put_decimal_ull(m, " ", nsec_to_clock_t(utime));
	seq_put_decimal_ull(m, " ", nsec_to_clock_t(stime));

static inline void account_softirq_enter(struct task_struct *tsk)
{
	vtime_account_irq(tsk, SOFTIRQ_OFFSET);
	irqtime_account_irq(tsk, SOFTIRQ_OFFSET);      /*更新starttime, 但第二个参数不让计算差值*/
}

static inline void account_softirq_exit(struct task_struct *tsk)
{
	vtime_account_softirq(tsk);
	irqtime_account_irq(tsk, 0);                   /*更新starttime, 并将差值(now-starttime)统计进去*/
}

static inline void account_hardirq_enter(struct task_struct *tsk)
{
	vtime_account_irq(tsk, HARDIRQ_OFFSET);
	irqtime_account_irq(tsk, HARDIRQ_OFFSET);     /*更新starttime, 但第二个参数不让计算差值*/
}

static inline void account_hardirq_exit(struct task_struct *tsk)
{
	vtime_account_hardirq(tsk);
	irqtime_account_irq(tsk, 0);                  /*更新starttime, 并将差值(now-starttime)统计进去*/
}

#ifdef CONFIG_KASAN
#define KASAN_STACK_ORDER 1
#else
#define KASAN_STACK_ORDER 0
#endif

#define THREAD_SIZE_ORDER	(2 + KASAN_STACK_ORDER)
#define THREAD_SIZE  (PAGE_SIZE << THREAD_SIZE_ORDER)


#define task_pt_regs(task) \
({									\
	unsigned long __ptr = (unsigned long)task_stack_page(task);	\
	__ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;		\
	((struct pt_regs *)__ptr) - 1;					\
})

#ifdef CONFIG_X86_32
# ifdef CONFIG_VM86
#  define TOP_OF_KERNEL_STACK_PADDING 16
# else
#  define TOP_OF_KERNEL_STACK_PADDING 8
# endif
#else
# define TOP_OF_KERNEL_STACK_PADDING 0
#endif

void __init pid_idr_init(void)
{
	/* Verify no one has done anything silly: */
	BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_ADDING);

	/* bump default and minimum pid_max based on number of cpus */
	pid_max = min(pid_max_max, max_t(int, pid_max,
				PIDS_PER_CPU_DEFAULT * num_possible_cpus()));
	pid_max_min = max_t(int, pid_max_min,
				PIDS_PER_CPU_MIN * num_possible_cpus());
	pr_info("pid_max: default: %u minimum: %u\n", pid_max, pid_max_min);

	idr_init(&init_pid_ns.idr);

	init_pid_ns.pid_cachep = KMEM_CACHE(pid,
			SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT);
}

/*
 * A maximum of 4 million PIDs should be enough for a while.
 * [NOTE: PID/TIDs are limited to 2^29 ~= 500+ million, see futex.h.]
 */
#define PID_MAX_LIMIT (CONFIG_BASE_SMALL ? PAGE_SIZE * 8 : \
	(sizeof(long) > 4 ? 4 * 1024 * 1024 : PID_MAX_DEFAULT))

	if (is_ucounts_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) {
		if (p->real_cred->user != INIT_USER &&
		    !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN))
			goto bad_fork_free;
	}

	/*
	 * If multiple threads are within copy_process(), then this check
	 * triggers too late. This doesn't hurt, the check is only there
	 * to stop root fork bombs.
	 */
	retval = -EAGAIN;
	if (data_race(nr_threads >= max_threads))
		goto bad_fork_cleanup_count;

	if (pid != &init_struct_pid) {
		pid = alloc_pid(p->nsproxy->pid_ns_for_children, args->set_tid,
				args->set_tid_size);
		if (IS_ERR(pid)) {
			retval = PTR_ERR(pid);
			goto bad_fork_cleanup_thread;
		}
	}

	/*
	 * Ensure that the cgroup subsystem policies allow the new process to be
	 * forked. It should be noted that the new process's css_set can be changed
	 * between here and cgroup_post_fork() if an organisation operation is in
	 * progress.
	 */
	retval = cgroup_can_fork(p, args);
	if (retval)
		goto bad_fork_put_pidfd;

unsigned int sysctl_nr_open __read_mostly = 1024*1024;   //默认值
unsigned int sysctl_nr_open_min = BITS_PER_LONG;
/* our min() is unusable in constant expressions ;-/ */
#define __const_min(x, y) ((x) < (y) ? (x) : (y))
unsigned int sysctl_nr_open_max =
	__const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG;  //最大值

struct file *alloc_empty_file(int flags, const struct cred *cred)
{
	static long old_max;
	struct file *f;

	/*
	 * Privileged users can go above max_files
	 */
	if (get_nr_files() >= files_stat.max_files && !capable(CAP_SYS_ADMIN)) {
		/*
		 * percpu_counters are inaccurate.  Do an expensive check before
		 * we go and fail.
		 */
		if (percpu_counter_sum_positive(&nr_files) >= files_stat.max_files)
			goto over;
	}

	f = __alloc_file(flags, cred);
	if (!IS_ERR(f))
		percpu_counter_inc(&nr_files);

	return f;

over:
	/* Ran out of filps - report that */
	if (get_nr_files() > old_max) {
		pr_info("VFS: file-max limit %lu reached\n", get_max_files());
		old_max = get_nr_files();
	}
	return ERR_PTR(-ENFILE);
}

	/*
	 * Allocated stacks are cached and later reused by new threads,
	 * so memcg accounting is performed manually on assigning/releasing
	 * stacks to tasks. Drop __GFP_ACCOUNT.
	 */
	stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN,
				     VMALLOC_START, VMALLOC_END,
				     THREADINFO_GFP & ~__GFP_ACCOUNT,
				     PAGE_KERNEL,
				     0, node, __builtin_return_address(0));

	/*
	 * We can't call find_vm_area() in interrupt context, and
	 * free_thread_stack() can be called in interrupt context,
	 * so cache the vm_struct.
	 */
	if (stack) {
		tsk->stack_vm_area = find_vm_area(stack);
		tsk->stack = stack;
	}

DECLARE_PER_CPU(struct task_struct *, current_task);

static __always_inline struct task_struct *get_current(void)
{
	return this_cpu_read_stable(current_task);
}

#define current get_current()

#define MAX_NICE	19
#define MIN_NICE	-20
#define NICE_WIDTH	(MAX_NICE - MIN_NICE + 1)

/*
 * Priority of a process goes from 0..MAX_PRIO-1, valid RT
 * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
 * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority
 * values are inverted: lower p->prio value means higher priority.
 *
 * The MAX_USER_RT_PRIO value allows the actual maximum
 * RT priority to be separate from the value exported to
 * user-space.  This allows kernel threads to set their
 * priority to a value higher than any user task. Note:
 * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
 */

#define MAX_USER_RT_PRIO	100
#define MAX_RT_PRIO		MAX_USER_RT_PRIO

#define MAX_PRIO		(MAX_RT_PRIO + NICE_WIDTH)
#define DEFAULT_PRIO		(MAX_RT_PRIO + NICE_WIDTH / 2)

/*
 * Convert user-nice values [ -20 ... 0 ... 19 ]
 * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
 * and back.
 */
#define NICE_TO_PRIO(nice)	((nice) + DEFAULT_PRIO)
#define PRIO_TO_NICE(prio)	((prio) - DEFAULT_PRIO)

/*
 * 'User priority' is the nice value converted to something we
 * can work with better when scaling various scheduler parameters,
 * it's a [ 0 ... 39 ] range.
 */
#define USER_PRIO(p)		((p)-MAX_RT_PRIO)
#define TASK_USER_PRIO(p)	USER_PRIO((p)->static_prio)
#define MAX_USER_PRIO		(USER_PRIO(MAX_PRIO))

/*
 * Convert nice value [19,-20] to rlimit style value [1,40].
 */
static inline long nice_to_rlimit(long nice)
{
	return (MAX_NICE - nice + 1);
}


/**
 * task_nice - return the nice value of a given task.
 * @p: the task in question.
 *
 * Return: The nice value [ -20 ... 0 ... 19 ].
 */
static inline int task_nice(const struct task_struct *p)
{
	return PRIO_TO_NICE((p)->static_prio);
}
```普通进程的nice值是优先级. 用户态显示的范围为 [-20 ~ 19], 值越低,优先级越高.对应的task_struct的字段为static_prio, 取值为[100～139]

``` c

#define MAX_NICE	19
#define MIN_NICE	-20
#define NICE_WIDTH	(MAX_NICE - MIN_NICE + 1)

/*
 * Priority of a process goes from 0..MAX_PRIO-1, valid RT
 * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
 * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority
 * values are inverted: lower p->prio value means higher priority.
 *
 * The MAX_USER_RT_PRIO value allows the actual maximum
 * RT priority to be separate from the value exported to
 * user-space.  This allows kernel threads to set their
 * priority to a value higher than any user task. Note:
 * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
 */

#define MAX_USER_RT_PRIO	100
#define MAX_RT_PRIO		MAX_USER_RT_PRIO

#define MAX_PRIO		(MAX_RT_PRIO + NICE_WIDTH)
#define DEFAULT_PRIO		(MAX_RT_PRIO + NICE_WIDTH / 2)

/*
 * Convert user-nice values [ -20 ... 0 ... 19 ]
 * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
 * and back.
 */
#define NICE_TO_PRIO(nice)	((nice) + DEFAULT_PRIO)
#define PRIO_TO_NICE(prio)	((prio) - DEFAULT_PRIO)

/*
 * 'User priority' is the nice value converted to something we
 * can work with better when scaling various scheduler parameters,
 * it's a [ 0 ... 39 ] range.
 */
#define USER_PRIO(p)		((p)-MAX_RT_PRIO)
#define TASK_USER_PRIO(p)	USER_PRIO((p)->static_prio)
#define MAX_USER_PRIO		(USER_PRIO(MAX_PRIO))

/*
 * Convert nice value [19,-20] to rlimit style value [1,40].
 */
static inline long nice_to_rlimit(long nice)
{
	return (MAX_NICE - nice + 1);
}


/**
 * task_nice - return the nice value of a given task.
 * @p: the task in question.
 *
 * Return: The nice value [ -20 ... 0 ... 19 ].
 */
static inline int task_nice(const struct task_struct *p)
{
	return PRIO_TO_NICE((p)->static_prio);
}

/*
 * The order of the sched class addresses are important, as they are
 * used to determine the order of the priority of each sched class in
 * relation to each other.
 */
#define SCHED_DATA				\
	STRUCT_ALIGN();				\
	__begin_sched_classes = .;		\
	*(__idle_sched_class)			\
	*(__fair_sched_class)			\
	*(__rt_sched_class)			\
	*(__dl_sched_class)			\
	*(__stop_sched_class)			\
	__end_sched_classes = .;

#define switch_to(prev, next, last)					\
do {									\
	((last) = __switch_to_asm((prev), (next)));			\
} while (0)

SYM_FUNC_START(__switch_to_asm)
	/*
	 * Save callee-saved registers
	 * This must match the order in inactive_task_frame
	 */
	pushq	%rbp
	pushq	%rbx
	pushq	%r12
	pushq	%r13
	pushq	%r14
	pushq	%r15

	/* switch stack */
	movq	%rsp, TASK_threadsp(%rdi)
	movq	TASK_threadsp(%rsi), %rsp    
	/* 执行完这个命令之后, 后续操作都是在next这个进程的内核栈进行了 */

#ifdef CONFIG_STACKPROTECTOR
	movq	TASK_stack_canary(%rsi), %rbx
	movq	%rbx, PER_CPU_VAR(fixed_percpu_data) + stack_canary_offset
#endif

#ifdef CONFIG_RETPOLINE
	/*
	 * When switching from a shallower to a deeper call stack
	 * the RSB may either underflow or use entries populated
	 * with userspace addresses. On CPUs where those concerns
	 * exist, overwrite the RSB with entries which capture
	 * speculative execution to prevent attack.
	 */
	FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
#endif

	/* restore callee-saved registers */
	popq	%r15
	popq	%r14
	popq	%r13
	popq	%r12
	popq	%rbx
	popq	%rbp

	jmp	__switch_to
SYM_FUNC_END(__switch_to_asm)