2022q1 Homework5 (quiz8)

contributed by < Xx-oX >

測驗 1

#include <stddef.h>
#include <stdint.h>
#include <limits.h>
#include <string.h>

/* Nonzero if either X or Y is not aligned on a "long" boundary */
#define UNALIGNED(X) ((long) X & (sizeof(long) - 1))

/* How many bytes are loaded each iteration of the word copy loop */
#define LBLOCKSIZE (sizeof(long))

/* Threshhold for punting to the bytewise iterator */
#define TOO_SMALL(LEN) ((LEN) < LBLOCKSIZE)

#if LONG_MAX == 2147483647L
#define DETECT_NULL(X) (((X) -0x01010101) & ~(X) & 0x80808080)
#else
#if LONG_MAX == 9223372036854775807L
/* Nonzero if X (a long int) contains a NULL byte. */
#define DETECT_NULL(X) (((X) -0x0101010101010101) & ~(X) & 0x8080808080808080)
#else
#error long int is not a 32bit or 64bit type.
#endif
#endif

/* @return nonzero if (long)X contains the byte used to fill MASK. */
#define DETECT_CHAR(X, MASK) (DETECT_NULL(X ^ MASK))

void *memchr_opt(const void *src_void, int c, size_t length)
{
    const unsigned char *src = (const unsigned char *) src_void;
    unsigned char d = c;

    while (UNALIGNED(src)) {
        if (!length--)
            return NULL;
        if (*src == d)
            return (void *) src;
        src++;
    }

    if (!TOO_SMALL(length)) {
        /* If we get this far, we know that length is large and
         * src is word-aligned.
         */

        /* The fast code reads the source one word at a time and only performs
         * the bytewise search on word-sized segments if they contain the search
         * character, which is detected by XORing the word-sized segment with a
         * word-sized block of the search character and then detecting for the
         * presence of NULL in the result.
         */
        unsigned long *asrc = (unsigned long *) src;
        unsigned long mask = d << 8 | d;
        mask = mask << 16 | mask;
        for (unsigned int i = 32; i < LBLOCKSIZE * 8; i <<= 1)
            mask = (mask << i) | mask;

        while (length >= LBLOCKSIZE) {
            /* character detected => do the bytewise search */
            if (DETECT_CHAR(*asrc, mask)) {
                break;
            }
            /* moving to the next block */
            asrc++;
            length -= 8;
        }

        /* If there are fewer than LBLOCKSIZE characters left, then we resort to
         * the bytewise loop.
         */
        src = (unsigned char *) asrc;
    }

    while (length--) {
        if (*src == d)
            return (void *) src;
        src++;
    }

    return NULL;
}

testing main function

#include <stdio.h>
int main()
{
    // const char str[] = "http://wiki.csie.ncku.edu.tw";
    // const char ch = '.';

    char str[64], ch;
    scanf("%s %c", str, &ch);
    
    char *ret = memchr_opt(str, ch, strlen(str));
    printf("String after |%c| is - |%s|\n", ch, ret);
    return 0;
}

測驗 2

static inline ringidx_t cond_reload(ringidx_t idx, const ringidx_t *loc)
{
    ringidx_t fresh = __atomic_load_n(loc, __ATOMIC_RELAXED);
    if (before(idx, fresh)) { /* fresh is after idx, use this instead */
        idx = fresh;
    } else { /* Continue with next slot */
	    /* moving to the next slot, DDD */ idx++;
    }
    return idx;
}

static inline ringidx_t find_tail(lfring_t *lfr, ringidx_t head, ringidx_t tail)
{
    if (lfr->flags & LFRING_FLAG_SP) /* single-producer enqueue */
        return __atomic_load_n(&lfr->tail, __ATOMIC_ACQUIRE);

    /* Multi-producer enqueue.
     * Scan ring for new elements that have been written but not released.
     */
    ringidx_t mask = lfr->mask;
    ringidx_t size = /* lfr->mask = ringsz - 1, KKK */ mask + 1;
    while (before(tail, head + size) &&
           __atomic_load_n(/* atomic load tail, TTT */ &lfr->tail, __ATOMIC_ACQUIRE) ==
               tail)
        tail++;
    tail = cond_update(&lfr->tail, tail);
    return tail;
}

uint32_t lfring_dequeue(lfring_t *lfr,
                        void **restrict elems,
                        uint32_t n_elems,
                        uint32_t *index)
{
    ringidx_t mask = lfr->mask;
    intptr_t actual;
    ringidx_t head = __atomic_load_n(&lfr->head, __ATOMIC_RELAXED);
    ringidx_t tail = __atomic_load_n(&lfr->tail, __ATOMIC_ACQUIRE);
    do { /* skipped */
    } while (!__atomic_compare_exchange_n(
        &lfr->head, &head, /* Updated on failure */
        /* desired, HHH */ head + actual,
        /* weak */ false, __ATOMIC_RELAXED, __ATOMIC_RELAXED));
    *index = (uint32_t) head;
    return (uint32_t) actual;
}

DDD: 將 idx 往前移動 1 byte

KKK: 從 lfring.c 中的第 52 行 lfr->mask = ringsz - 1; 可以得知 size = mask + 1;

HHH: 將 lfr->head 與 head 比較，如果相同就將 lfr->head 更改成 head + actual

Built-in Function: bool __atomic_compare_exchange_n (type *ptr, type *expected, type desired, bool weak, int success_memorder, int failure_memorder)

Description

This built-in function implements an atomic compare and exchange operation. This compares the contents of *ptr with the contents of *expected. If equal, the operation is a read-modify-write operation that writes desired into *ptr. If they are not equal, the operation is a read and the current contents of *ptr are written into *expected. weak is true for weak compare_exchange, which may fail spuriously, and false for the strong variation, which never fails spuriously. Many targets only offer the strong variation and ignore the parameter. When in doubt, use the strong variation.
If desired is written into *ptr then true is returned and memory is affected according to the memory order specified by success_memorder. There are no restrictions on what memory order can be used here.
Otherwise, false is returned and memory is affected according to failure_memorder. This memory order cannot be __ATOMIC_RELEASE nor __ATOMIC_ACQ_REL. It also cannot be a stronger order than that specified by success_memorder.

測驗 3

static void periodic_routine(struct work_struct *ws)
{
    if (likely(loaded))
        check();
    queue_delayed_work(wq, &dont_trace_task, JIFFIES_DELAY);
}

Once the module is attached to the kernel, the module’s “core” function will run periodically through the advantage of workqueues. Specifically, the module runs every JIFFIES_DELAY, which is set to 1. That is, the module will run every one jiffy. This can be changed through modifying the macro JIFFIES_DELAY defined in the module.

每過 JIFFIES_DELAY 就跑一次 => 每次檢查完就利用 queue_delayed_work 延遲 JIFFIES_DELAY

Full code

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/list.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/sched/signal.h>
#include <linux/workqueue.h>

MODULE_AUTHOR("National Cheng Kung University, Taiwan");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_DESCRIPTION("A kernel module that kills ptrace tracer and its tracees");

#define JIFFIES_DELAY 1
#define DONT_TRACE_WQ_NAME "dont_trace_worker"

static void periodic_routine(struct work_struct *);
static DECLARE_DELAYED_WORK(dont_trace_task, periodic_routine);
static struct workqueue_struct *wq;
static bool loaded;

/* Send SIGKILL from kernel space */
static void kill_task(struct task_struct *task)
{
    send_sig(SIGKILL, task, 1);
}

/* @return true if the process has tracees */
static bool is_tracer(struct list_head *children)
{
    struct list_head *list;
    list_for_each (list, children) {
        struct task_struct *task =
            list_entry(list, struct task_struct, ptrace_entry);
        if (task)
            return true;
    }
    return false;
}

/* Traverse the element in the linked list of the ptraced proccesses and
 * finally kills them.
 */
static void kill_tracee(struct list_head *children)
{
    struct list_head *list;
    list_for_each (list, children) {
        struct task_struct *task_ptraced =
            list_entry(list, struct task_struct, ptrace_entry);
        pr_info("ptracee -> comm: %s, pid: %d, gid: %d, ptrace: %d\n",
                task_ptraced->comm, task_ptraced->pid, task_ptraced->tgid,
                task_ptraced->ptrace);
        kill_task(task_ptraced);
    }
}

static void check(void)
{
    struct task_struct *task;
    for_each_process (task) {
        if (!is_tracer(&task->ptraced))
            continue;

        kill_tracee(&task->ptraced);
        kill_task(task); /* Kill the tracer once all tracees are killed */
    }
}

static void periodic_routine(struct work_struct *ws)
{
    if (likely(loaded))
        check();
    queue_delayed_work(wq, &dont_trace_task, JIFFIES_DELAY);
}

static int __init dont_trace_init(void)
{
    wq = create_workqueue(DONT_TRACE_WQ_NAME);
    queue_delayed_work(wq, &dont_trace_task, JIFFIES_DELAY);

    loaded = true;
    pr_info("Loaded!\n");
    return 0;
}

static void __exit dont_trace_exit(void)
{
    loaded = false;

    /* No new routines will be queued */
    cancel_delayed_work(&dont_trace_task);

    /* Wait for the completion of all routines */
    flush_workqueue(wq);
    destroy_workqueue(wq);

    pr_info("Unloaded.\n");
}

module_init(dont_trace_init);
module_exit(dont_trace_exit);