C++ raw_smp_processor_id函数代码示例

/**
 * set_mtrr - update mtrrs on all processors
 * @reg:	mtrr in question
 * @base:	mtrr base
 * @size:	mtrr size
 * @type:	mtrr type
 *
 * This is kinda tricky, but fortunately, Intel spelled it out for us cleanly:
 *
 * 1. Queue work to do the following on all processors:
 * 2. Disable Interrupts
 * 3. Wait for all procs to do so
 * 4. Enter no-fill cache mode
 * 5. Flush caches
 * 6. Clear PGE bit
 * 7. Flush all TLBs
 * 8. Disable all range registers
 * 9. Update the MTRRs
 * 10. Enable all range registers
 * 11. Flush all TLBs and caches again
 * 12. Enter normal cache mode and reenable caching
 * 13. Set PGE
 * 14. Wait for buddies to catch up
 * 15. Enable interrupts.
 *
 * What does that mean for us? Well, first we set data.count to the number
 * of CPUs. As each CPU announces that it started the rendezvous handler by
 * decrementing the count, We reset data.count and set the data.gate flag
 * allowing all the cpu's to proceed with the work. As each cpu disables
 * interrupts, it'll decrement data.count once. We wait until it hits 0 and
 * proceed. We clear the data.gate flag and reset data.count. Meanwhile, they
 * are waiting for that flag to be cleared. Once it's cleared, each
 * CPU goes through the transition of updating MTRRs.
 * The CPU vendors may each do it differently,
 * so we call mtrr_if->set() callback and let them take care of it.
 * When they're done, they again decrement data->count and wait for data.gate
 * to be set.
 * When we finish, we wait for data.count to hit 0 and toggle the data.gate flag
 * Everyone then enables interrupts and we all continue on.
 *
 * Note that the mechanism is the same for UP systems, too; all the SMP stuff
 * becomes nops.
 */
static void
set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type type)
{
	struct set_mtrr_data data;
	unsigned long flags;
	int cpu;

#ifdef CONFIG_SMP
	/*
	 * If this cpu is not yet active, we are in the cpu online path. There
	 * can be no stop_machine() in parallel, as stop machine ensures this
	 * by using get_online_cpus(). We can skip taking the stop_cpus_mutex,
	 * as we don't need it and also we can't afford to block while waiting
	 * for the mutex.
	 *
	 * If this cpu is active, we need to prevent stop_machine() happening
	 * in parallel by taking the stop cpus mutex.
	 *
	 * Also, this is called in the context of cpu online path or in the
	 * context where cpu hotplug is prevented. So checking the active status
	 * of the raw_smp_processor_id() is safe.
	 */
	if (cpu_active(raw_smp_processor_id()))
		mutex_lock(&stop_cpus_mutex);
#endif

	preempt_disable();

	data.smp_reg = reg;
	data.smp_base = base;
	data.smp_size = size;
	data.smp_type = type;
	atomic_set(&data.count, num_booting_cpus() - 1);

	/* Make sure data.count is visible before unleashing other CPUs */
	smp_wmb();
	atomic_set(&data.gate, 0);

	/* Start the ball rolling on other CPUs */
	for_each_online_cpu(cpu) {
		struct cpu_stop_work *work = &per_cpu(mtrr_work, cpu);

		if (cpu == smp_processor_id())
			continue;

		stop_one_cpu_nowait(cpu, mtrr_work_handler, &data, work);
	}


	while (atomic_read(&data.count))
		cpu_relax();

	/* Ok, reset count and toggle gate */
	atomic_set(&data.count, num_booting_cpus() - 1);
	smp_wmb();
	atomic_set(&data.gate, 1);

//.........这里部分代码省略.........

/*
 * Report back to the Boot Processor.
 * Running on AP.
 */
static void __cpuinit smp_callin(void)
{
	int cpuid, phys_id;
	unsigned long timeout;

	/*
	 * If waken up by an INIT in an 82489DX configuration
	 * we may get here before an INIT-deassert IPI reaches
	 * our local APIC.  We have to wait for the IPI or we'll
	 * lock up on an APIC access.
	 */
	if (apic->wait_for_init_deassert)
		apic->wait_for_init_deassert(&init_deasserted);

	/*
	 * (This works even if the APIC is not enabled.)
	 */
	phys_id = read_apic_id();
	cpuid = smp_processor_id();
	if (cpumask_test_cpu(cpuid, cpu_callin_mask)) {
		panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__,
					phys_id, cpuid);
	}
	pr_debug("CPU#%d (phys ID: %d) waiting for CALLOUT\n", cpuid, phys_id);

	/*
	 * STARTUP IPIs are fragile beasts as they might sometimes
	 * trigger some glue motherboard logic. Complete APIC bus
	 * silence for 1 second, this overestimates the time the
	 * boot CPU is spending to send the up to 2 STARTUP IPIs
	 * by a factor of two. This should be enough.
	 */

	/*
	 * Waiting 2s total for startup (udelay is not yet working)
	 */
	timeout = jiffies + 2*HZ;
	while (time_before(jiffies, timeout)) {
		/*
		 * Has the boot CPU finished it's STARTUP sequence?
		 */
		if (cpumask_test_cpu(cpuid, cpu_callout_mask))
			break;
		cpu_relax();
	}

	if (!time_before(jiffies, timeout)) {
		panic("%s: CPU%d started up but did not get a callout!\n",
		      __func__, cpuid);
	}

	/*
	 * the boot CPU has finished the init stage and is spinning
	 * on callin_map until we finish. We are free to set up this
	 * CPU, first the APIC. (this is probably redundant on most
	 * boards)
	 */

	pr_debug("CALLIN, before setup_local_APIC().\n");
	if (apic->smp_callin_clear_local_apic)
		apic->smp_callin_clear_local_apic();
	setup_local_APIC();
	end_local_APIC_setup();

	/*
	 * Need to setup vector mappings before we enable interrupts.
	 */
	setup_vector_irq(smp_processor_id());

	/*
	 * Save our processor parameters. Note: this information
	 * is needed for clock calibration.
	 */
	smp_store_cpu_info(cpuid);

	/*
	 * Get our bogomips.
	 * Update loops_per_jiffy in cpu_data. Previous call to
	 * smp_store_cpu_info() stored a value that is close but not as
	 * accurate as the value just calculated.
	 */
	calibrate_delay();
	cpu_data(cpuid).loops_per_jiffy = loops_per_jiffy;
	pr_debug("Stack at about %p\n", &cpuid);

	/*
	 * This must be done before setting cpu_online_mask
	 * or calling notify_cpu_starting.
	 */
	set_cpu_sibling_map(raw_smp_processor_id());
	wmb();

	notify_cpu_starting(cpuid);

	/*
	 * Allow the master to continue.
//.........这里部分代码省略.........

/**
 * round_jiffies_up - function to round jiffies up to a full second
 * @j: the time in (absolute) jiffies that should be rounded
 *
 * This is the same as round_jiffies() except that it will never
 * round down.  This is useful for timeouts for which the exact time
 * of firing does not matter too much, as long as they don't fire too
 * early.
 */
unsigned long round_jiffies_up(unsigned long j)
{
	return round_jiffies_common(j, raw_smp_processor_id(), true);
}

static void cpu_vsyscall_init(void *arg)
{
	/* preemption should be already off */
	vsyscall_set_cpu(raw_smp_processor_id());
}

static inline void debug_write_lock_after(rwlock_t *lock)
{
	lock->owner_cpu = raw_smp_processor_id();
	lock->owner = current;
}

static u64 nps_clksrc_read(struct clocksource *clksrc)
{
	int cluster = raw_smp_processor_id() >> NPS_CLUSTER_OFFSET;

	return (u64)ioread32be(nps_msu_reg_low_addr[cluster]);
}

static int wait_slt_scu_state_sync(unsigned long state, int wait)
{

    int ret = 0, i;
    unsigned long retry = 0;
    static volatile int get_exit = 0;
    static volatile int cpu_num = 0;
    unsigned long all_cpu_mask = 0;

    int cpu = raw_smp_processor_id();

    //printk("wait_slt_scu_state_sync, cpu%d wait state=%d\n", cpu, state);

    if(cpu_num & (0x1 << cpu))
    {
        //printk(KERN_ERR, "cpu%d already waitting\n", cpu);
        return 0;
    }

    while(cpu_num && get_exit)
    {
        //printk(KERN_INFO, "wait other cpu to finish waiting loop\n");
        mdelay(10);
    }

    spin_lock(&scu_wait_sync_lock);
    cpu_num  |= 0x1 << cpu;
    get_exit = 0;
    __cpuc_flush_dcache_area(&get_exit, sizeof(int));
    __cpuc_flush_dcache_area(&cpu_num, sizeof(int));
    spin_unlock(&scu_wait_sync_lock);

    for(i = 0; i < NR_CPUS; i++)
    {
        all_cpu_mask |= (0x1 << i);
    }

    /* wait all cpu in sync loop */
    while(cpu_num != all_cpu_mask)
    {
        retry++;

        if(retry > 0x10000)
        {
            //printk(KERN_INFO, "scu wait sync state (%d) timeout\n", state);
            goto wait_sync_out;
        }

        if(get_exit)
            break;

        //printk(KERN_INFO, "\n\nretry=0x%08x wait state = %d\n", retry, state);
        //slt_scu_print_state();
        mdelay(1);
    }

    spin_lock(&scu_wait_sync_lock);
    get_exit |= 0x1 << cpu;
    __cpuc_flush_dcache_area(&get_exit, sizeof(int));
    spin_unlock(&scu_wait_sync_lock);


    ret = is_slt_scu_state_sync(state);

    /* make sure all cpu exit wait sync loop
     * check cpu_num is for the case retry timeout
     */
    while(1)
    {
        //printk(KERN_INFO, "wait exit retry\n");
        if(!get_exit ||
           get_exit == all_cpu_mask ||
           cpu_num != all_cpu_mask)
        {
            break;
        }
        mdelay(1);
    }

wait_sync_out:
    spin_lock(&scu_wait_sync_lock);
    cpu_num &= ~(0x01 << cpu);
    __cpuc_flush_dcache_area(&cpu_num, sizeof(int));
    spin_unlock(&scu_wait_sync_lock);

    //printk("cpu%d exit fun, ret=%s\n", cpu, ret ? "pass" : "fail");
    return ret;
}

static int slt_scu_test_func(void *data)
{
    int ret = 0, loop, pass;
    int cpu = raw_smp_processor_id();
    unsigned long irq_flag;
    int cpu_cnt;

    unsigned long buf;
    unsigned long *mem_buf = (unsigned long *)data;
    unsigned long retry;

    //spin_lock(&scu_thread_lock[cpu]);
    //local_irq_save(irq_flag);
#if 0
    if(cpu == 0)
    {
        mtk_wdt_enable(WK_WDT_DIS);
    }
#endif

    if(!mem_buf)
    {
        printk(KERN_ERR, "allocate memory fail for cpu scu test\n");
        g_iCPU_PassFail = -1;
        goto scu_thread_out;
    }

    printk("\n>>slt_scu_test_func -- cpu id = %d, mem_buf = 0x%08x <<\n", cpu, mem_buf);

    msleep(50);

    if(!wait_slt_scu_state_sync(SCU_STATE_START, 1))
    {
        printk("cpu%d wait SCU_STATE_START timeout\n", cpu);

        goto scu_thread_out;
    }
    g_iCPU_PassFail = 0;
    g_iSCU_PassFail[cpu] = 1;

    for (loop = 0; loop < g_iScuLoopCount; loop++) {

        slt_scu_write_state(cpu, SCU_STATE_EXECUTE);
        spin_lock_irqsave(&scu_thread_irq_lock[cpu], irq_flag);
        if(!wait_slt_scu_state_sync(SCU_STATE_EXECUTE, 1))
        {
            spin_unlock_irqrestore(&scu_thread_irq_lock[cpu], irq_flag);
            printk("cpu%d wait SCU_STATE_EXECUTE timeout\n", cpu);
            goto scu_thread_out;
        }

        g_iSCU_PassFail[cpu] = fp6_scu_start(mem_buf);
        spin_unlock_irqrestore(&scu_thread_irq_lock[cpu], irq_flag);

        __cpuc_flush_dcache_area(g_iSCU_PassFail, 2*sizeof(int));

        printk("\n>>cpu%d scu : fp6_scu_start %s ret=0x%x<<\n", cpu, g_iSCU_PassFail[cpu] != 0xA? "fail" : "pass", g_iSCU_PassFail[cpu]);

        slt_scu_write_state(cpu, SCU_STATE_EXEEND);

        if(!wait_slt_scu_state_sync(SCU_STATE_EXEEND, 1))
        {
            printk("cpu%d wait SCU_STATE_EXEEND timeout\n", cpu);
            goto scu_thread_out;

        }

        if(cpu == 0)
        {
            pass = 1;
            for(cpu_cnt = 0; cpu_cnt < NR_CPUS; cpu_cnt++)
            {
                if(g_iSCU_PassFail[cpu_cnt] != 0xA)
                {
                    pass = 0;
                }
            }

            if(pass)
            {
                g_iCPU_PassFail += 1;
            }
        }
    }

scu_thread_out:

    slt_scu_write_state(cpu, SCU_STATE_IDEL);

    if(cpu == 0)
    {
        if (g_iCPU_PassFail == g_iScuLoopCount) {
            printk("\n>> CPU scu test pass <<\n\n");
        }else {
            printk("\n>> CPU scu test fail (loop count = %d)<<\n\n", g_iCPU_PassFail);
        }
        //mtk_wdt_enable(WK_WDT_EN);
    }

    wait_slt_scu_state_sync(SCU_STATE_IDEL, 1);
//.........这里部分代码省略.........

/*---------------------------------------------------------------------------*/
int priv_ev_loop_run(void *loop_hndl)
{
	struct xio_ev_loop	*loop = loop_hndl;
	struct xio_ev_data	*tev;
	struct llist_node	*node;
	int cpu;

	clear_bit(XIO_EV_LOOP_STOP, &loop->states);

	switch (loop->flags) {
	case XIO_LOOP_GIVEN_THREAD:
		if (loop->ctx->worker != (uint64_t) get_current()) {
			ERROR_LOG("worker kthread(%p) is not current(%p).\n",
				  (void *) loop->ctx->worker, get_current());
			goto cleanup0;
		}
		/* no need to disable preemption */
		cpu = raw_smp_processor_id();
		if (loop->ctx->cpuid != cpu) {
			TRACE_LOG("worker on core(%d) scheduled to(%d).\n",
				  cpu, loop->ctx->cpuid);
			set_cpus_allowed_ptr(get_current(),
					     cpumask_of(loop->ctx->cpuid));
		}
		break;
	case XIO_LOOP_TASKLET:
		/* were events added to list while in STOP state ? */
		if (!llist_empty(&loop->ev_llist))
			priv_kick_tasklet(loop_hndl);
		return 0;
	case XIO_LOOP_WORKQUEUE:
		/* were events added to list while in STOP state ? */
		while ((node = llist_del_all(&loop->ev_llist)) != NULL) {
			node = llist_reverse_order(node);
			while (node) {
				tev = llist_entry(node, struct xio_ev_data,
						  ev_llist);
				node = llist_next(node);
				tev->work.func = priv_ev_loop_run_work;
				queue_work_on(loop->ctx->cpuid, loop->workqueue,
					      &tev->work);
			}
		}
		return 0;
	default:
		/* undo */
		set_bit(XIO_EV_LOOP_STOP, &loop->states);
		return -1;
	}

retry_wait:
	wait_event_interruptible(loop->wait,
				 test_bit(XIO_EV_LOOP_WAKE, &loop->states));

retry_dont_wait:

	while ((node = llist_del_all(&loop->ev_llist)) != NULL) {
		node = llist_reverse_order(node);
		while (node) {
			tev = llist_entry(node, struct xio_ev_data, ev_llist);
			node = llist_next(node);
			tev->handler(tev->data);
		}
	}

	/* "race point" */
	clear_bit(XIO_EV_LOOP_WAKE, &loop->states);

	if (unlikely(test_bit(XIO_EV_LOOP_STOP, &loop->states)))
		return 0;

	/* if a new entry was added while we were at "race point"
	 * than wait event might block forever as condition is false */
	if (llist_empty(&loop->ev_llist))
		goto retry_wait;

	/* race detected */
	if (!test_and_set_bit(XIO_EV_LOOP_WAKE, &loop->states))
		goto retry_dont_wait;

	/* was one wakeup was called */
	goto retry_wait;

cleanup0:
	set_bit(XIO_EV_LOOP_STOP, &loop->states);
	return -1;
}

static struct kvm_para_state *kvm_para_state(void)
{
	return &per_cpu(para_state, raw_smp_processor_id());
}

static int cpu_request_microcode(int cpu, const void *buf, size_t bufsize)
{
    struct microcode_amd *mc_amd, *mc_old;
    size_t offset = bufsize;
    size_t last_offset, applied_offset = 0;
    int error = 0;
    struct ucode_cpu_info *uci = &per_cpu(ucode_cpu_info, cpu);

    /* We should bind the task to the CPU */
    BUG_ON(cpu != raw_smp_processor_id());

    if ( *(const uint32_t *)buf != UCODE_MAGIC )
    {
        printk(KERN_ERR "microcode: Wrong microcode patch file magic\n");
        error = -EINVAL;
        goto out;
    }

    mc_amd = xmalloc(struct microcode_amd);
    if ( !mc_amd )
    {
        printk(KERN_ERR "microcode: Cannot allocate memory for microcode patch\n");
        error = -ENOMEM;
        goto out;
    }

    error = install_equiv_cpu_table(mc_amd, buf, &offset);
    if ( error )
    {
        xfree(mc_amd);
        printk(KERN_ERR "microcode: installing equivalent cpu table failed\n");
        error = -EINVAL;
        goto out;
    }

    mc_old = uci->mc.mc_amd;
    /* implicitely validates uci->mc.mc_valid */
    uci->mc.mc_amd = mc_amd;

    /*
     * It's possible the data file has multiple matching ucode,
     * lets keep searching till the latest version
     */
    mc_amd->mpb = NULL;
    mc_amd->mpb_size = 0;
    last_offset = offset;
    while ( (error = get_ucode_from_buffer_amd(mc_amd, buf, bufsize,
                                               &offset)) == 0 )
    {
        if ( microcode_fits(mc_amd, cpu) )
        {
            error = apply_microcode(cpu);
            if ( error )
                break;
            applied_offset = last_offset;
        }

        last_offset = offset;

        if ( offset >= bufsize )
            break;
    }

    /* On success keep the microcode patch for
     * re-apply on resume.
     */
    if ( applied_offset )
    {
        int ret = get_ucode_from_buffer_amd(mc_amd, buf, bufsize,
                                            &applied_offset);
        if ( ret == 0 )
            xfree(mc_old);
        else
            error = ret;
    }

    if ( !applied_offset || error )
    {
        xfree(mc_amd);
        uci->mc.mc_amd = mc_old;
    }

  out:
    svm_host_osvw_init();

    /*
     * In some cases we may return an error even if processor's microcode has
     * been updated. For example, the first patch in a container file is loaded
     * successfully but subsequent container file processing encounters a
     * failure.
     */
    return error;
}

void dump_bfin_trace_buffer(void)
{
#ifdef CONFIG_DEBUG_BFIN_HWTRACE_ON
	int tflags, i = 0, fault = 0;
	char buf[150];
	unsigned short *addr;
	unsigned int cpu = raw_smp_processor_id();
#ifdef CONFIG_DEBUG_BFIN_HWTRACE_EXPAND
	int j, index;
#endif

	trace_buffer_save(tflags);

	pr_notice("Hardware Trace:\n");

#ifdef CONFIG_DEBUG_BFIN_HWTRACE_EXPAND
	pr_notice("WARNING: Expanded trace turned on - can not trace exceptions\n");
#endif

	if (likely(bfin_read_TBUFSTAT() & TBUFCNT)) {
		for (; bfin_read_TBUFSTAT() & TBUFCNT; i++) {
			addr = (unsigned short *)bfin_read_TBUF();
			decode_address(buf, (unsigned long)addr);
			pr_notice("%4i Target : %s\n", i, buf);
			if (!fault && addr == ((unsigned short *)evt_ivhw)) {
				addr = (unsigned short *)bfin_read_TBUF();
				decode_address(buf, (unsigned long)addr);
				pr_notice("      FAULT : %s ", buf);
				decode_instruction(addr);
				pr_cont("\n");
				fault = 1;
				continue;
			}
			if (!fault && addr == (unsigned short *)trap &&
				(cpu_pda[cpu].seqstat & SEQSTAT_EXCAUSE) > VEC_EXCPT15) {
				decode_address(buf, cpu_pda[cpu].icplb_fault_addr);
				pr_notice("      FAULT : %s ", buf);
				decode_instruction((unsigned short *)cpu_pda[cpu].icplb_fault_addr);
				pr_cont("\n");
				fault = 1;
			}
			addr = (unsigned short *)bfin_read_TBUF();
			decode_address(buf, (unsigned long)addr);
			pr_notice("     Source : %s ", buf);
			decode_instruction(addr);
			pr_cont("\n");
		}
	}

#ifdef CONFIG_DEBUG_BFIN_HWTRACE_EXPAND
	if (trace_buff_offset)
		index = trace_buff_offset / 4;
	else
		index = EXPAND_LEN;

	j = (1 << CONFIG_DEBUG_BFIN_HWTRACE_EXPAND_LEN) * 128;
	while (j) {
		decode_address(buf, software_trace_buff[index]);
		pr_notice("%4i Target : %s\n", i, buf);
		index -= 1;
		if (index < 0)
			index = EXPAND_LEN;
		decode_address(buf, software_trace_buff[index]);
		pr_notice("     Source : %s ", buf);
		decode_instruction((unsigned short *)software_trace_buff[index]);
		pr_cont("\n");
		index -= 1;
		if (index < 0)
			index = EXPAND_LEN;
		j--;
		i++;
	}
#endif

	trace_buffer_restore(tflags);
#endif
}

inline void __const_udelay(unsigned long xloops)
{
	__delay(xloops * (HZ * cpu_data[raw_smp_processor_id()].loops_per_jiffy));
}

void nft_meta_get_eval(const struct nft_expr *expr,
		       struct nft_regs *regs,
		       const struct nft_pktinfo *pkt)
{
	const struct nft_meta *priv = nft_expr_priv(expr);
	const struct sk_buff *skb = pkt->skb;
	const struct net_device *in = pkt->in, *out = pkt->out;
	u32 *dest = &regs->data[priv->dreg];

	switch (priv->key) {
	case NFT_META_LEN:
		*dest = skb->len;
		break;
	case NFT_META_PROTOCOL:
		*dest = 0;
		*(__be16 *)dest = skb->protocol;
		break;
	case NFT_META_NFPROTO:
		*dest = pkt->ops->pf;
		break;
	case NFT_META_L4PROTO:
		*dest = pkt->tprot;
		break;
	case NFT_META_PRIORITY:
		*dest = skb->priority;
		break;
	case NFT_META_MARK:
		*dest = skb->mark;
		break;
	case NFT_META_IIF:
		if (in == NULL)
			goto err;
		*dest = in->ifindex;
		break;
	case NFT_META_OIF:
		if (out == NULL)
			goto err;
		*dest = out->ifindex;
		break;
	case NFT_META_IIFNAME:
		if (in == NULL)
			goto err;
		strncpy((char *)dest, in->name, IFNAMSIZ);
		break;
	case NFT_META_OIFNAME:
		if (out == NULL)
			goto err;
		strncpy((char *)dest, out->name, IFNAMSIZ);
		break;
	case NFT_META_IIFTYPE:
		if (in == NULL)
			goto err;
		*dest = 0;
		*(u16 *)dest = in->type;
		break;
	case NFT_META_OIFTYPE:
		if (out == NULL)
			goto err;
		*dest = 0;
		*(u16 *)dest = out->type;
		break;
	case NFT_META_SKUID:
		if (skb->sk == NULL || !sk_fullsock(skb->sk))
			goto err;

		read_lock_bh(&skb->sk->sk_callback_lock);
		if (skb->sk->sk_socket == NULL ||
		    skb->sk->sk_socket->file == NULL) {
			read_unlock_bh(&skb->sk->sk_callback_lock);
			goto err;
		}

		*dest =	from_kuid_munged(&init_user_ns,
				skb->sk->sk_socket->file->f_cred->fsuid);
		read_unlock_bh(&skb->sk->sk_callback_lock);
		break;
	case NFT_META_SKGID:
		if (skb->sk == NULL || !sk_fullsock(skb->sk))
			goto err;

		read_lock_bh(&skb->sk->sk_callback_lock);
		if (skb->sk->sk_socket == NULL ||
		    skb->sk->sk_socket->file == NULL) {
			read_unlock_bh(&skb->sk->sk_callback_lock);
			goto err;
		}
		*dest =	from_kgid_munged(&init_user_ns,
				 skb->sk->sk_socket->file->f_cred->fsgid);
		read_unlock_bh(&skb->sk->sk_callback_lock);
		break;
#ifdef CONFIG_IP_ROUTE_CLASSID
	case NFT_META_RTCLASSID: {
		const struct dst_entry *dst = skb_dst(skb);

		if (dst == NULL)
			goto err;
		*dest = dst->tclassid;
		break;
	}
#endif
//.........这里部分代码省略.........

//.........这里部分代码省略.........
	if (fixup_exception(regs)) {
		current->thread.cp0_baduaddr = address;
		return;
	}

	/*
	 * Oops. The kernel tried to access some bad page. We'll have to
	 * terminate things with extreme prejudice.
	 */
	bust_spinlocks(1);

	printk(KERN_ALERT "CPU %d Unable to handle kernel paging request at "
	       "virtual address %0*lx, epc == %0*lx, ra == %0*lx\n",
	       smp_processor_id(), field, address, field, regs->cp0_epc,
	       field,  regs->regs[31]);
	die("Oops", regs);

/*
 * We ran out of memory, or some other thing happened to us that made
 * us unable to handle the page fault gracefully.
 */
out_of_memory:
	up_read(&mm->mmap_sem);
	if (tsk->pid == 1) {
		yield();
		down_read(&mm->mmap_sem);
		goto survive;
	}
	printk("VM: killing process %s\n", tsk->comm);
	if (user_mode(regs))
		do_exit(SIGKILL);
	goto no_context;

do_sigbus:
	up_read(&mm->mmap_sem);

	/* Kernel mode? Handle exceptions or die */
	if (!user_mode(regs))
		goto no_context;
	else
	/*
	 * Send a sigbus, regardless of whether we were in kernel
	 * or user mode.
	 */
#if 0
		printk("do_page_fault() #3: sending SIGBUS to %s for "
		       "invalid %s\n%0*lx (epc == %0*lx, ra == %0*lx)\n",
		       tsk->comm,
		       write ? "write access to" : "read access from",
		       field, address,
		       field, (unsigned long) regs->cp0_epc,
		       field, (unsigned long) regs->regs[31]);
#endif
	tsk->thread.cp0_badvaddr = address;
	info.si_signo = SIGBUS;
	info.si_errno = 0;
	info.si_code = BUS_ADRERR;
	info.si_addr = (void __user *) address;
	force_sig_info(SIGBUS, &info, tsk);

	return;
vmalloc_fault:
	{
		/*
		 * Synchronize this task's top level page-table
		 * with the 'reference' page table.
		 *
		 * Do _not_ use "tsk" here. We might be inside
		 * an interrupt in the middle of a task switch..
		 */
		int offset = __pgd_offset(address);
		pgd_t *pgd, *pgd_k;
		pud_t *pud, *pud_k;
		pmd_t *pmd, *pmd_k;
		pte_t *pte_k;

		pgd = (pgd_t *) pgd_current[raw_smp_processor_id()] + offset;
		pgd_k = init_mm.pgd + offset;

		if (!pgd_present(*pgd_k))
			goto no_context;
		set_pgd(pgd, *pgd_k);

		pud = pud_offset(pgd, address);
		pud_k = pud_offset(pgd_k, address);
		if (!pud_present(*pud_k))
			goto no_context;

		pmd = pmd_offset(pud, address);
		pmd_k = pmd_offset(pud_k, address);
		if (!pmd_present(*pmd_k))
			goto no_context;
		set_pmd(pmd, *pmd_k);

		pte_k = pte_offset_kernel(pmd_k, address);
		if (!pte_present(*pte_k))
			goto no_context;
		return;
	}
}