xpc.h

LINUX 2.6.17.4的源码

 *  E - Messages that have been copied and delivered, but have not yet been
 *	acknowledged by the recipient as having been received.
 *
 *  F - Messages that have been acknowledged, but XPC has not yet notified the
 *	sender that the message was received by its intended recipient.
 *	This is also an area that needs to be prepared for the allocating of
 *	new messages, by the clearing of the message flags of the acknowledged
 *	messages.
 */
struct xpc_channel {
	partid_t partid;		/* ID of remote partition connected */
	spinlock_t lock;		/* lock for updating this structure */
	u32 flags;			/* general flags */

	enum xpc_retval reason;		/* reason why channel is disconnect'g */
	int reason_line;		/* line# disconnect initiated from */

	u16 number;			/* channel # */

	u16 msg_size;			/* sizeof each msg entry */
	u16 local_nentries;		/* #of msg entries in local msg queue */
	u16 remote_nentries;		/* #of msg entries in remote msg queue*/

	void *local_msgqueue_base;	/* base address of kmalloc'd space */
	struct xpc_msg *local_msgqueue;	/* local message queue */
	void *remote_msgqueue_base;	/* base address of kmalloc'd space */
	struct xpc_msg *remote_msgqueue;/* cached copy of remote partition's */
					/* local message queue */
	u64 remote_msgqueue_pa;		/* phys addr of remote partition's */
					/* local message queue */

	atomic_t references;		/* #of external references to queues */

	atomic_t n_on_msg_allocate_wq;   /* #on msg allocation wait queue */
	wait_queue_head_t msg_allocate_wq; /* msg allocation wait queue */

	u8 delayed_IPI_flags;		/* IPI flags received, but delayed */
					/* action until channel disconnected */

	/* queue of msg senders who want to be notified when msg received */

	atomic_t n_to_notify;		/* #of msg senders to notify */
	struct xpc_notify *notify_queue;/* notify queue for messages sent */

	xpc_channel_func func;		/* user's channel function */
	void *key;			/* pointer to user's key */

	struct mutex msg_to_pull_mutex;	/* next msg to pull serialization */
	struct completion wdisconnect_wait; /* wait for channel disconnect */

	struct xpc_openclose_args *local_openclose_args; /* args passed on */
					/* opening or closing of channel */

	/* various flavors of local and remote Get/Put values */

	struct xpc_gp *local_GP;	/* local Get/Put values */
	struct xpc_gp remote_GP;	/* remote Get/Put values */
	struct xpc_gp w_local_GP;	/* working local Get/Put values */
	struct xpc_gp w_remote_GP;	/* working remote Get/Put values */
	s64 next_msg_to_pull;		/* Put value of next msg to pull */

	/* kthread management related fields */

// >>> rethink having kthreads_assigned_limit and kthreads_idle_limit; perhaps
// >>> allow the assigned limit be unbounded and let the idle limit be dynamic
// >>> dependent on activity over the last interval of time
	atomic_t kthreads_assigned;	/* #of kthreads assigned to channel */
	u32 kthreads_assigned_limit; 	/* limit on #of kthreads assigned */
	atomic_t kthreads_idle;		/* #of kthreads idle waiting for work */
	u32 kthreads_idle_limit;	/* limit on #of kthreads idle */
	atomic_t kthreads_active;	/* #of kthreads actively working */
	// >>> following field is temporary
	u32 kthreads_created;		/* total #of kthreads created */

	wait_queue_head_t idle_wq;	/* idle kthread wait queue */

} ____cacheline_aligned;


/* struct xpc_channel flags */

#define	XPC_C_WASCONNECTED	0x00000001 /* channel was connected */

#define	XPC_C_ROPENREPLY	0x00000002 /* remote open channel reply */
#define	XPC_C_OPENREPLY		0x00000004 /* local open channel reply */
#define	XPC_C_ROPENREQUEST	0x00000008 /* remote open channel request */
#define	XPC_C_OPENREQUEST	0x00000010 /* local open channel request */

#define	XPC_C_SETUP		0x00000020 /* channel's msgqueues are alloc'd */
#define	XPC_C_CONNECTEDCALLOUT	0x00000040 /* connected callout initiated */
#define	XPC_C_CONNECTEDCALLOUT_MADE \
				0x00000080 /* connected callout completed */
#define	XPC_C_CONNECTED		0x00000100 /* local channel is connected */
#define	XPC_C_CONNECTING	0x00000200 /* channel is being connected */

#define	XPC_C_RCLOSEREPLY	0x00000400 /* remote close channel reply */
#define	XPC_C_CLOSEREPLY	0x00000800 /* local close channel reply */
#define	XPC_C_RCLOSEREQUEST	0x00001000 /* remote close channel request */
#define	XPC_C_CLOSEREQUEST	0x00002000 /* local close channel request */

#define	XPC_C_DISCONNECTED	0x00004000 /* channel is disconnected */
#define	XPC_C_DISCONNECTING	0x00008000 /* channel is being disconnected */
#define	XPC_C_DISCONNECTINGCALLOUT \
				0x00010000 /* disconnecting callout initiated */
#define	XPC_C_DISCONNECTINGCALLOUT_MADE \
				0x00020000 /* disconnecting callout completed */
#define	XPC_C_WDISCONNECT	0x00040000 /* waiting for channel disconnect */



/*
 * Manages channels on a partition basis. There is one of these structures
 * for each partition (a partition will never utilize the structure that
 * represents itself).
 */
struct xpc_partition {

	/* XPC HB infrastructure */

	u8 remote_rp_version;		/* version# of partition's rsvd pg */
	struct timespec remote_rp_stamp;/* time when rsvd pg was initialized */
	u64 remote_rp_pa;		/* phys addr of partition's rsvd pg */
	u64 remote_vars_pa;		/* phys addr of partition's vars */
	u64 remote_vars_part_pa;	/* phys addr of partition's vars part */
	u64 last_heartbeat;		/* HB at last read */
	u64 remote_amos_page_pa;	/* phys addr of partition's amos page */
	int remote_act_nasid;		/* active part's act/deact nasid */
	int remote_act_phys_cpuid;	/* active part's act/deact phys cpuid */
	u32 act_IRQ_rcvd;		/* IRQs since activation */
	spinlock_t act_lock;		/* protect updating of act_state */
	u8 act_state;			/* from XPC HB viewpoint */
	u8 remote_vars_version;		/* version# of partition's vars */
	enum xpc_retval reason;		/* reason partition is deactivating */
	int reason_line;		/* line# deactivation initiated from */
	int reactivate_nasid;		/* nasid in partition to reactivate */

	unsigned long disengage_request_timeout; /* timeout in jiffies */
	struct timer_list disengage_request_timer;


	/* XPC infrastructure referencing and teardown control */

	volatile u8 setup_state;	/* infrastructure setup state */
	wait_queue_head_t teardown_wq;	/* kthread waiting to teardown infra */
	atomic_t references;		/* #of references to infrastructure */


	/*
	 * NONE OF THE PRECEDING FIELDS OF THIS STRUCTURE WILL BE CLEARED WHEN
	 * XPC SETS UP THE NECESSARY INFRASTRUCTURE TO SUPPORT CROSS PARTITION
	 * COMMUNICATION. ALL OF THE FOLLOWING FIELDS WILL BE CLEARED. (THE
	 * 'nchannels' FIELD MUST BE THE FIRST OF THE FIELDS TO BE CLEARED.)
	 */


	u8 nchannels;		   /* #of defined channels supported */
	atomic_t nchannels_active; /* #of channels that are not DISCONNECTED */
	atomic_t nchannels_engaged;/* #of channels engaged with remote part */
	struct xpc_channel *channels;/* array of channel structures */

	void *local_GPs_base;	  /* base address of kmalloc'd space */
	struct xpc_gp *local_GPs; /* local Get/Put values */
	void *remote_GPs_base;    /* base address of kmalloc'd space */
	struct xpc_gp *remote_GPs;/* copy of remote partition's local Get/Put */
				  /* values */
	u64 remote_GPs_pa;	  /* phys address of remote partition's local */
				  /* Get/Put values */


	/* fields used to pass args when opening or closing a channel */

	void *local_openclose_args_base;  /* base address of kmalloc'd space */
	struct xpc_openclose_args *local_openclose_args;  /* local's args */
	void *remote_openclose_args_base; /* base address of kmalloc'd space */
	struct xpc_openclose_args *remote_openclose_args; /* copy of remote's */
					  /* args */
	u64 remote_openclose_args_pa;	  /* phys addr of remote's args */


	/* IPI sending, receiving and handling related fields */

	int remote_IPI_nasid;	    /* nasid of where to send IPIs */
	int remote_IPI_phys_cpuid;  /* phys CPU ID of where to send IPIs */
	AMO_t *remote_IPI_amo_va;   /* address of remote IPI AMO_t structure */

	AMO_t *local_IPI_amo_va;    /* address of IPI AMO_t structure */
	u64 local_IPI_amo;	    /* IPI amo flags yet to be handled */
	char IPI_owner[8];	    /* IPI owner's name */
	struct timer_list dropped_IPI_timer; /* dropped IPI timer */

	spinlock_t IPI_lock;	    /* IPI handler lock */


	/* channel manager related fields */

	atomic_t channel_mgr_requests;	/* #of requests to activate chan mgr */
	wait_queue_head_t channel_mgr_wq; /* channel mgr's wait queue */

} ____cacheline_aligned;


/* struct xpc_partition act_state values (for XPC HB) */

#define	XPC_P_INACTIVE		0x00	/* partition is not active */
#define XPC_P_ACTIVATION_REQ	0x01	/* created thread to activate */
#define XPC_P_ACTIVATING	0x02	/* activation thread started */
#define XPC_P_ACTIVE		0x03	/* xpc_partition_up() was called */
#define XPC_P_DEACTIVATING	0x04	/* partition deactivation initiated */


#define XPC_DEACTIVATE_PARTITION(_p, _reason) \
			xpc_deactivate_partition(__LINE__, (_p), (_reason))


/* struct xpc_partition setup_state values */

#define XPC_P_UNSET		0x00	/* infrastructure was never setup */
#define XPC_P_SETUP		0x01	/* infrastructure is setup */
#define XPC_P_WTEARDOWN		0x02	/* waiting to teardown infrastructure */
#define XPC_P_TORNDOWN		0x03	/* infrastructure is torndown */



/*
 * struct xpc_partition IPI_timer #of seconds to wait before checking for
 * dropped IPIs. These occur whenever an IPI amo write doesn't complete until
 * after the IPI was received.
 */
#define XPC_P_DROPPED_IPI_WAIT	(0.25 * HZ)


/* number of seconds to wait for other partitions to disengage */
#define XPC_DISENGAGE_REQUEST_DEFAULT_TIMELIMIT	90

/* interval in seconds to print 'waiting disengagement' messages */
#define XPC_DISENGAGE_PRINTMSG_INTERVAL		10


#define XPC_PARTID(_p)	((partid_t) ((_p) - &xpc_partitions[0]))



/* found in xp_main.c */
extern struct xpc_registration xpc_registrations[];


/* found in xpc_main.c */
extern struct device *xpc_part;
extern struct device *xpc_chan;
extern int xpc_disengage_request_timelimit;
extern int xpc_disengage_request_timedout;
extern irqreturn_t xpc_notify_IRQ_handler(int, void *, struct pt_regs *);
extern void xpc_dropped_IPI_check(struct xpc_partition *);
extern void xpc_activate_partition(struct xpc_partition *);
extern void xpc_activate_kthreads(struct xpc_channel *, int);
extern void xpc_create_kthreads(struct xpc_channel *, int);
extern void xpc_disconnect_wait(int);


/* found in xpc_partition.c */
extern int xpc_exiting;
extern struct xpc_vars *xpc_vars;
extern struct xpc_rsvd_page *xpc_rsvd_page;
extern struct xpc_vars_part *xpc_vars_part;
extern struct xpc_partition xpc_partitions[XP_MAX_PARTITIONS + 1];
extern char *xpc_remote_copy_buffer;
extern void *xpc_remote_copy_buffer_base;
extern void *xpc_kmalloc_cacheline_aligned(size_t, gfp_t, void **);
extern struct xpc_rsvd_page *xpc_rsvd_page_init(void);
extern void xpc_allow_IPI_ops(void);
extern void xpc_restrict_IPI_ops(void);
extern int xpc_identify_act_IRQ_sender(void);
extern int xpc_partition_disengaged(struct xpc_partition *);
extern enum xpc_retval xpc_mark_partition_active(struct xpc_partition *);
extern void xpc_mark_partition_inactive(struct xpc_partition *);
extern void xpc_discovery(void);
extern void xpc_check_remote_hb(void);
extern void xpc_deactivate_partition(const int, struct xpc_partition *,
						enum xpc_retval);
extern enum xpc_retval xpc_initiate_partid_to_nasids(partid_t, void *);


/* found in xpc_channel.c */
extern void xpc_initiate_connect(int);
extern void xpc_initiate_disconnect(int);
extern enum xpc_retval xpc_initiate_allocate(partid_t, int, u32, void **);
extern enum xpc_retval xpc_initiate_send(partid_t, int, void *);
extern enum xpc_retval xpc_initiate_send_notify(partid_t, int, void *,
						xpc_notify_func, void *);
extern void xpc_initiate_received(partid_t, int, void *);
extern enum xpc_retval xpc_setup_infrastructure(struct xpc_partition *);
extern enum xpc_retval xpc_pull_remote_vars_part(struct xpc_partition *);
extern void xpc_process_channel_activity(struct xpc_partition *);
extern void xpc_connected_callout(struct xpc_channel *);
extern void xpc_deliver_msg(struct xpc_channel *);
extern void xpc_disconnect_channel(const int, struct xpc_channel *,
					enum xpc_retval, unsigned long *);
extern void xpc_disconnect_callout(struct xpc_channel *, enum xpc_retval);
extern void xpc_partition_going_down(struct xpc_partition *, enum xpc_retval);
extern void xpc_teardown_infrastructure(struct xpc_partition *);



static inline void
xpc_wakeup_channel_mgr(struct xpc_partition *part)
{
	if (atomic_inc_return(&part->channel_mgr_requests) == 1) {
		wake_up(&part->channel_mgr_wq);
	}
}



/*
 * These next two inlines are used to keep us from tearing down a channel's
 * msg queues while a thread may be referencing them.
 */
static inline void
xpc_msgqueue_ref(struct xpc_channel *ch)
{
	atomic_inc(&ch->references);
}

static inline void
xpc_msgqueue_deref(struct xpc_channel *ch)
{
	s32 refs = atomic_dec_return(&ch->references);

	DBUG_ON(refs < 0);
	if (refs == 0) {
		xpc_wakeup_channel_mgr(&xpc_partitions[ch->partid]);
	}
}



#define XPC_DISCONNECT_CHANNEL(_ch, _reason, _irqflgs) \
		xpc_disconnect_channel(__LINE__, _ch, _reason, _irqflgs)


/*
 * These two inlines are used to keep us from tearing down a partition's
 * setup infrastructure while a thread may be referencing it.
 */
static inline void
xpc_part_deref(struct xpc_partition *part)
{
	s32 refs = atomic_dec_return(&part->references);


	DBUG_ON(refs < 0);
	if (refs == 0 && part->setup_state == XPC_P_WTEARDOWN) {
		wake_up(&part->teardown_wq);
	}
}

static inline int
xpc_part_ref(struct xpc_partition *part)
{
	int setup;


	atomic_inc(&part->references);
	setup = (part->setup_state == XPC_P_SETUP);
	if (!setup) {
		xpc_part_deref(part);
	}
	return setup;
}



/*
 * The following macro is to be used for the setting of the reason and
 * reason_line fields in both the struct xpc_channel and struct xpc_partition
 * structures.
 */
#define XPC_SET_REASON(_p, _reason, _line) \
	{ \
		(_p)->reason = _reason; \
		(_p)->reason_line = _line; \
	}



/*
 * This next set of inlines are used to keep track of when a partition is
 * potentially engaged in accessing memory belonging to another partition.
 */

static inline void
xpc_mark_partition_engaged(struct xpc_partition *part)
{
	unsigned long irq_flags;
	AMO_t *amo = (AMO_t *) __va(part->remote_amos_page_pa +
				(XPC_ENGAGED_PARTITIONS_AMO * sizeof(AMO_t)));


	local_irq_save(irq_flags);

	/* set bit corresponding to our partid in remote partition's AMO */
	FETCHOP_STORE_OP(TO_AMO((u64) &amo->variable), FETCHOP_OR,
						(1UL << sn_partition_id));
	/*
	 * We must always use the nofault function regardless of whether we
	 * are on a Shub 1.1 system or a Shub 1.2 slice 0xc processor. If we
	 * didn't, we'd never know that the other partition is down and would
	 * keep sending IPIs and AMOs to it until the heartbeat times out.
	 */
	(void) xp_nofault_PIOR((u64 *) GLOBAL_MMR_ADDR(NASID_GET(&amo->
				variable), xp_nofault_PIOR_target));

	local_irq_restore(irq_flags);
}

static inline void
xpc_mark_partition_disengaged(struct xpc_partition *part)
{
	unsigned long irq_flags;
	AMO_t *amo = (AMO_t *) __va(part->remote_amos_page_pa +
				(XPC_ENGAGED_PARTITIONS_AMO * sizeof(AMO_t)));