吐血整理 | 肝翻 Linux 中断所有知识点

<group of groups>. <group of processors>.<processor>.<core>
<group of processors>.<processor>.<core>.<thread>

gic: interrupt-controller@51a00000 {
        compatible = "arm,gic-v3";
        reg = <0x0 0x51a00000 0 0x10000>, /* GIC Dist */
              <0x0 0x51b00000 0 0xC0000>, /* GICR */
              <0x0 0x52000000 0 0x2000>,  /* GICC */
              <0x0 0x52010000 0 0x1000>,  /* GICH */
              <0x0 0x52020000 0 0x20000>; /* GICV */
        #interrupt-cells = <3>;
        interrupt-controller;
        interrupts = <GIC_PPI 9
                (GIC_CPU_MASK_SIMPLE(6) | IRQ_TYPE_LEVEL_HIGH)>;
        interrupt-parent = <&gic>;
};

IRQCHIP_DECLARE(gic_v3, "arm,gic-v3", gic_of_init);

#define IRQCHIP_DECLARE(name, compat, fn) OF_DECLARE_2(irqchip, name, compat, fn)

#define OF_DECLARE_2(table, name, compat, fn) \ 
        _OF_DECLARE(table, name, compat, fn, of_init_fn_2)

#define _OF_DECLARE(table, name, compat, fn, fn_type)            \ 
    static const struct of_device_id __of_table_##name        \ 
        __used __section(__##table##_of_table)            \ 
         = { .compatible = compat,                \ 
             .data = (fn == (fn_type)NULL) ? fn : fn  }

#ifdef CONFIG_IRQCHIP
    #define IRQCHIP_OF_MATCH_TABLE()                    \
        . = ALIGN(8);                           \
        VMLINUX_SYMBOL(__irqchip_begin) = .;                \
        *(__irqchip_of_table)                       \
        *(__irqchip_of_end)
#endif

static int __init gic_of_init(struct device_node *node, struct device_node *parent)
{
  ......
 dist_base = of_iomap(node, 0);                                           ------(1)
 if (!dist_base) {
  pr_err("%pOF: unable to map gic dist registers\n", node);
  return -ENXIO;
 }

 err = gic_validate_dist_version(dist_base);                              ------(2)
 if (err) {
  pr_err("%pOF: no distributor detected, giving up\n", node);
  goto out_unmap_dist;
 }

 if (of_property_read_u32(node, "#redistributor-regions", &nr_redist_regions))  ------(3)
  nr_redist_regions = 1;

 rdist_regs = kzalloc(sizeof(*rdist_regs) * nr_redist_regions, GFP_KERNEL);
 if (!rdist_regs) {
  err = -ENOMEM;
  goto out_unmap_dist;
 }

 for (i = 0; i < nr_redist_regions; i++) {                                ------(4)
  struct resource res;
  int ret;

  ret = of_address_to_resource(node, 1 + i, &res);
  rdist_regs[i].redist_base = of_iomap(node, 1 + i);
  if (ret || !rdist_regs[i].redist_base) {
   pr_err("%pOF: couldn't map region %d\n", node, i);
   err = -ENODEV;
   goto out_unmap_rdist;
  }
  rdist_regs[i].phys_base = res.start;
 }
 
 if (of_property_read_u64(node, "redistributor-stride", &redist_stride))  ------(5)
  redist_stride = 0;

 err = gic_init_bases(dist_base, rdist_regs, nr_redist_regions,           ------(6)
        redist_stride, &node->fwnode);
 if (err)
  goto out_unmap_rdist;

 gic_populate_ppi_partitions(node);                                       ------(7)
 gic_of_setup_kvm_info(node);
 return 0;
  ......
 return err;
}

static int __init gic_init_bases(void __iomem *dist_base,
     struct redist_region *rdist_regs,
     u32 nr_redist_regions,
     u64 redist_stride,
     struct fwnode_handle *handle)
{
  ......
 typer = readl_relaxed(gic_data.dist_base + GICD_TYPER);                ------(1)
 gic_data.rdists.id_bits = GICD_TYPER_ID_BITS(typer);
 gic_irqs = GICD_TYPER_IRQS(typer);
 if (gic_irqs > 1020)
  gic_irqs = 1020;
 gic_data.irq_nr = gic_irqs;

 gic_data.domain = irq_domain_create_tree(handle, &gic_irq_domain_ops,  ------(2)
       &gic_data);
 gic_data.rdists.rdist = alloc_percpu(typeof(*gic_data.rdists.rdist));
 gic_data.rdists.has_vlpis = true;
 gic_data.rdists.has_direct_lpi = true;
  ......
 set_handle_irq(gic_handle_irq);                                        ------(3)

 gic_update_vlpi_properties();                                          ------(4)

 if (IS_ENABLED(CONFIG_ARM_GIC_V3_ITS) && gic_dist_supports_lpis())
  its_init(handle, &gic_data.rdists, gic_data.domain);                  ------(5)

 gic_smp_init();                                                        ------(6)
 gic_dist_init();                                                       ------(7)
 gic_cpu_init();                                                        ------(8)
 gic_cpu_pm_init();                                                     ------(9)

 return 0;
  ......
}

struct irq_desc {
 struct irq_common_data irq_common_data;
 struct irq_data  irq_data;  
 unsigned int __percpu *kstat_irqs;
 irq_flow_handler_t handle_irq;  
  ......
 struct irqaction *action; 
 ......
} ____cacheline_internodealigned_in_smp;

struct irq_data {
 u32   mask;
 unsigned int  irq;
 unsigned long  hwirq;
 struct irq_common_data *common;
 struct irq_chip  *chip;
 struct irq_domain *domain;
#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
 struct irq_data  *parent_data;
#endif
 void   *chip_data;
};

struct irq_chip {
 struct device *parent_device;
 const char *name;
 unsigned int (*irq_startup)(struct irq_data *data);
 void  (*irq_shutdown)(struct irq_data *data);
 void  (*irq_enable)(struct irq_data *data);
 void  (*irq_disable)(struct irq_data *data);

 void  (*irq_ack)(struct irq_data *data);
 void  (*irq_mask)(struct irq_data *data);
 void  (*irq_mask_ack)(struct irq_data *data);
 void  (*irq_unmask)(struct irq_data *data);
 void  (*irq_eoi)(struct irq_data *data);

 int  (*irq_set_affinity)(struct irq_data *data, const struct cpumask *dest, bool force);
 int  (*irq_retrigger)(struct irq_data *data);
 int  (*irq_set_type)(struct irq_data *data, unsigned int flow_type);
 int  (*irq_set_wake)(struct irq_data *data, unsigned int on);

 void  (*irq_bus_lock)(struct irq_data *data);
 void  (*irq_bus_sync_unlock)(struct irq_data *data);
 ......
};

struct irq_domain {
 struct list_head link;
 const char *name;
 const struct irq_domain_ops *ops;
 void *host_data;
 unsigned int flags;
 unsigned int mapcount;

 /* Optional data */
 struct fwnode_handle *fwnode;
 enum irq_domain_bus_token bus_token;
 struct irq_domain_chip_generic *gc;
#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
 struct irq_domain *parent;
#endif
#ifdef CONFIG_GENERIC_IRQ_DEBUGFS
 struct dentry  *debugfs_file;
#endif

 /* reverse map data. The linear map gets appended to the irq_domain */
 irq_hw_number_t hwirq_max;
 unsigned int revmap_direct_max_irq;
 unsigned int revmap_size;
 struct radix_tree_root revmap_tree;
 unsigned int linear_revmap[];
};

struct irq_domain_ops {
 int (*match)(struct irq_domain *d, struct device_node *node,
       enum irq_domain_bus_token bus_token);
 int (*select)(struct irq_domain *d, struct irq_fwspec *fwspec,
        enum irq_domain_bus_token bus_token);
 int (*map)(struct irq_domain *d, unsigned int virq, irq_hw_number_t hw);
 void (*unmap)(struct irq_domain *d, unsigned int virq);
 int (*xlate)(struct irq_domain *d, struct device_node *node,
       const u32 *intspec, unsigned int intsize,
       unsigned long *out_hwirq, unsigned int *out_type);
 ......
};

struct irqaction {
 irq_handler_t  handler; 
 void   *dev_id;  
  ......
 unsigned int  irq;  
 unsigned int  flags;  
  ......
 const char  *name;   
 struct proc_dir_entry *dir;
} ____cacheline_internodealigned_in_smp;

static inline int __must_check
request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags,
        const char *name, void *dev)
{
    return request_threaded_irq(irq, handler, NULL, flags, name, dev);
}

#define IRQF_SHARED  0x00000080              //多个设备共享一个中断号，需要外设硬件支持
#define IRQF_PROBE_SHARED 0x00000100              //中断处理程序允许sharing mismatch发生
#define __IRQF_TIMER  0x00000200               //时钟中断
#define IRQF_PERCPU  0x00000400               //属于特定CPU的中断
#define IRQF_NOBALANCING 0x00000800               //禁止在CPU之间进行中断均衡处理
#define IRQF_IRQPOLL  0x00001000              //中断被用作轮训
#define IRQF_ONESHOT  0x00002000              //一次性触发的中断，不能嵌套，1）在硬件中断处理完成后才能打开中断；2）在中断线程化中保持关闭状态，直到该中断源上的所有thread_fn函数都执行完
#define IRQF_NO_SUSPEND  0x00004000      //系统休眠唤醒操作中，不关闭该中断
#define IRQF_FORCE_RESUME 0x00008000              //系统唤醒过程中必须强制打开该中断
#define IRQF_NO_THREAD  0x00010000      //禁止中断线程化
#define IRQF_EARLY_RESUME 0x00020000      //系统唤醒过程中在syscore阶段resume，而不用等到设备resume阶段
#define IRQF_COND_SUSPEND 0x00040000      //与NO_SUSPEND的用户共享中断时，执行本设备的中断处理函数

# ps -A | grep "irq/"
root          1749     2       0      0 irq_thread          0 S [irq/433-imx_drm]
root          1750     2       0      0 irq_thread          0 S [irq/439-imx_drm]
root          1751     2       0      0 irq_thread          0 S [irq/445-imx_drm]
root          1752     2       0      0 irq_thread          0 S [irq/451-imx_drm]
root          2044     2       0      0 irq_thread          0 S [irq/279-isl2902]
root          2192     2       0      0 irq_thread          0 S [irq/114-mmc0]
root          2199     2       0      0 irq_thread          0 S [irq/115-mmc1]
root          2203     2       0      0 irq_thread          0 S [irq/322-5b02000]
root          2361     2       0      0 irq_thread          0 S [irq/294-4-0051]

/*
 * Exception vectors.
 */
        .pushsection ".entry.text", "ax"

        .align  11
SYM_CODE_START(vectors)
        ......
        
        kernel_ventry   1, sync                         // el1 下的同步异常，例如指令执行异常、缺页中断等
        kernel_ventry   1, irq                          // el1 下的异步异常，硬件中断。1代表异常等级
        kernel_ventry   1, fiq_invalid                  // FIQ EL1h
        kernel_ventry   1, error                        // Error EL1h

        kernel_ventry   0, sync                         // el0 下的同步异常，例如指令执行异常、缺页中断（跳转地址或者取地址）、系统调用等
        kernel_ventry   0, irq                          // el0 下的异步异常，硬件中断。0代表异常等级
        kernel_ventry   0, fiq_invalid                  // FIQ 64-bit EL0
        kernel_ventry   0, error                        // Error 64-bit EL0

        ......
#endif
SYM_CODE_END(vectors)

.macro  kernel_entry, el, regsize = 64
.if     \regsize == 32
mov     w0, w0                          // zero upper 32 bits of x0
.endif
stp     x0, x1, [sp, #16 * 0]
stp     x2, x3, [sp, #16 * 1]
stp     x4, x5, [sp, #16 * 2]
stp     x6, x7, [sp, #16 * 3]
stp     x8, x9, [sp, #16 * 4]
stp     x10, x11, [sp, #16 * 5]
stp     x12, x13, [sp, #16 * 6]
stp     x14, x15, [sp, #16 * 7]
stp     x16, x17, [sp, #16 * 8]
stp     x18, x19, [sp, #16 * 9]
stp     x20, x21, [sp, #16 * 10]
stp     x22, x23, [sp, #16 * 11]
stp     x24, x25, [sp, #16 * 12]
stp     x26, x27, [sp, #16 * 13]
stp     x28, x29, [sp, #16 * 14]

.if     \el == 0
clear_gp_regs
mrs     x21, sp_el0
ldr_this_cpu    tsk, __entry_task, x20
msr     sp_el0, tsk

/* IRQ is the lowest priority flag, unconditionally unmask the rest. */
.macro enable_da_f
msr     daifclr, #(8 | 4 | 1)
.endm

/*
 * Interrupt handling.
 */
        .macro  irq_handler
        ldr_l   x1, handle_arch_irq
        mov     x0, sp
        irq_stack_entry      //进入中断栈
        blr     x1           //执行 handle_arch_irq
        irq_stack_exit       //退出中断栈
        .endm

void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
{
 if (handle_arch_irq)
  return;

 handle_arch_irq = handle_irq;
}

static int __init gic_init_bases(void __iomem *dist_base,
     struct redist_region *rdist_regs,
     u32 nr_redist_regions,
     u64 redist_stride,
     struct fwnode_handle *handle)
{
 set_handle_irq(gic_handle_irq);
}

static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
{
 u32 irqnr;

 do {
  irqnr = gic_read_iar();                                     ------(1)

  if (likely(irqnr > 15 && irqnr < 1020) || irqnr >= 8192) {  ------(2)
   int err;

   if (static_key_true(&supports_deactivate))
    gic_write_eoir(irqnr);
   else
    isb();

   err = handle_domain_irq(gic_data.domain, irqnr, regs);    ------(3)
   if (err) {
    WARN_ONCE(true, "Unexpected interrupt received!\n");
    if (static_key_true(&supports_deactivate)) {
     if (irqnr < 8192)
      gic_write_dir(irqnr);
    } else {
     gic_write_eoir(irqnr);
    }
   }
   continue;
  }
  if (irqnr < 16) {                                          ------(4)
   gic_write_eoir(irqnr);
   if (static_key_true(&supports_deactivate))
    gic_write_dir(irqnr);
#ifdef CONFIG_SMP
   /*
    * Unlike GICv2, we don't need an smp_rmb() here.
    * The control dependency from gic_read_iar to
    * the ISB in gic_write_eoir is enough to ensure
    * that any shared data read by handle_IPI will
    * be read after the ACK.
    */
   handle_IPI(irqnr, regs);                                ------(5)
#else
   WARN_ONCE(true, "Unexpected SGI received!\n");
#endif
   continue;
  }
 } while (irqnr != ICC_IAR1_EL1_SPURIOUS);
}

int __handle_domain_irq(struct irq_domain *domain, unsigned int hwirq,
   bool lookup, struct pt_regs *regs)
{
 struct pt_regs *old_regs = set_irq_regs(regs);        
 unsigned int irq = hwirq;
 int ret = 0;

 irq_enter();                               ------(1)

#ifdef CONFIG_IRQ_DOMAIN
 if (lookup)
  irq = irq_find_mapping(domain, hwirq);    ------(2)
#endif

 /*
  * Some hardware gives randomly wrong interrupts.  Rather
  * than crashing, do something sensible.
  */
 if (unlikely(!irq || irq >= nr_irqs)) {
  ack_bad_irq(irq);
  ret = -EINVAL;
 } else {
  generic_handle_irq(irq);                  ------(3)
 }

 irq_exit();                                ------(4)
 set_irq_regs(old_regs);
 return ret;
}

static inline void generic_handle_irq_desc(struct irq_desc *desc)
{
 desc->handle_irq(desc);            
}

SYM_CODE_START_LOCAL(ret_to_user)
        disable_daif                      //D A I F 分别为PSTAT中的四个异常屏蔽标志位，此处屏蔽这4中异常
        gic_prio_kentry_setup tmp=x3
#ifdef CONFIG_TRACE_IRQFLAGS
        bl      trace_hardirqs_off
#endif
        ldr     x19, [tsk, #TSK_TI_FLAGS]  //获取 thread_info 中的flags变量的值
        and     x2, x19, #_TIF_WORK_MASK
        cbnz    x2, work_pending
finish_ret_to_user:
        user_enter_irqoff
        /* Ignore asynchronous tag check faults in the uaccess routines */
        clear_mte_async_tcf
        enable_step_tsk x19, x2
#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
        bl      stackleak_erase
#endif
        kernel_exit 0                      //恢复 pt_regs 中的寄存器上下文

struct work_struct {
 atomic_long_t data;     
 struct list_head entry; 
 work_func_t func;       
#ifdef CONFIG_LOCKDEP
 struct lockdep_map lockdep_map;
#endif
};

struct workqueue_struct {
 struct list_head pwqs;  /* WR: all pwqs of this wq */   
 struct list_head list;  /* PR: list of all workqueues */  

 struct list_head maydays; /* MD: pwqs requesting rescue */    
 struct worker  *rescuer; /* I: rescue worker */  

 struct pool_workqueue *dfl_pwq; /* PW: only for unbound wqs */

 char   name[WQ_NAME_LEN]; /* I: workqueue name */

 /* hot fields used during command issue, aligned to cacheline */
 unsigned int  flags ____cacheline_aligned; /* WQ: WQ_* flags */
 struct pool_workqueue __percpu *cpu_pwqs; /* I: per-cpu pwqs */    
 struct pool_workqueue __rcu *numa_pwq_tbl[]; /* PWR: unbound pwqs indexed by node */    //Per-Node创建pool_workqueue
    ...
};

struct pool_workqueue {
 struct worker_pool *pool;  /* I: the associated pool */    
 struct workqueue_struct *wq;  /* I: the owning workqueue */   

 int   nr_active; /* L: nr of active works */    
 int   max_active; /* L: max active works */   
 struct list_head delayed_works; /* L: delayed works */     
 struct list_head pwqs_node; /* WR: node on wq->pwqs */    
 struct list_head mayday_node; /* MD: node on wq->maydays */   //用于添加到workqueue链表中
    ...
} __aligned(1 << WORK_STRUCT_FLAG_BITS);

struct worker_pool {
 spinlock_t  lock;  /* the pool lock */
 int   cpu;  /* I: the associated cpu */     
 int   node;  /* I: the associated node ID */ 
 int   id;  /* I: pool ID */
 unsigned int  flags;  /* X: flags */

 unsigned long  watchdog_ts; /* L: watchdog timestamp */

 struct list_head worklist; /* L: list of pending works */  
 int   nr_workers; /* L: total number of workers */   

 /* nr_idle includes the ones off idle_list for rebinding */
 int   nr_idle; /* L: currently idle ones */

 struct list_head idle_list; /* X: list of idle workers */  
 struct timer_list idle_timer; /* L: worker idle timeout */
 struct timer_list mayday_timer; /* L: SOS timer for workers */

 /* a workers is either on busy_hash or idle_list, or the manager */
 DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER);   /* L: hash of busy workers */

 /* see manage_workers() for details on the two manager mutexes */
 struct worker  *manager; /* L: purely informational */
 struct mutex  attach_mutex; /* attach/detach exclusion */
 struct list_head workers; /* A: attached workers */   
 struct completion *detach_completion; /* all workers detached */

 struct ida  worker_ida; /* worker IDs for task name */

 struct workqueue_attrs *attrs;  /* I: worker attributes */
 struct hlist_node hash_node; /* PL: unbound_pool_hash node */    
    ...
} ____cacheline_aligned_in_smp;

struct worker {
 /* on idle list while idle, on busy hash table while busy */
 union {
  struct list_head entry; /* L: while idle */     
  struct hlist_node hentry; /* L: while busy */ 
 };

 struct work_struct *current_work; /* L: work being processed */  
 work_func_t  current_func; /* L: current_work's fn */                
 struct pool_workqueue *current_pwq; /* L: current_work's pwq */   

 struct list_head scheduled; /* L: scheduled works */   
  
 /* 64 bytes boundary on 64bit, 32 on 32bit */

 struct task_struct *task;  /* I: worker task */   
 struct worker_pool *pool;  /* I: the associated pool */   
      /* L: for rescuers */
 struct list_head node;  /* A: anchored at pool->workers */  //添加到worker_pool->workers链表中
      /* A: runs through worker->node */
    ...
};

#define INIT_WORK(_work, _func)      \
 __INIT_WORK((_work), (_func), 0)
  
#define __INIT_WORK(_work, _func, _onstack)    \
 do {        \
  __init_work((_work), _onstack);    \
  (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \
  INIT_LIST_HEAD(&(_work)->entry);   \
  (_work)->func = (_func);    \
 } while (0)