Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1762740AbYFFQzh (ORCPT ); Fri, 6 Jun 2008 12:55:37 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754529AbYFFQz2 (ORCPT ); Fri, 6 Jun 2008 12:55:28 -0400 Received: from relay1.sgi.com ([192.48.171.29]:40059 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1752422AbYFFQzZ (ORCPT ); Fri, 6 Jun 2008 12:55:25 -0400 Date: Fri, 6 Jun 2008 11:55:23 -0500 From: Dean Nelson To: akpm@linux-foundation.org Cc: linux-kernel@vger.kernel.org Subject: [Patch 12/18] isolate additional sn2 specific code Message-ID: <20080606165523.GM13695@sgi.com> References: <20080606164034.GA13695@sgi.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20080606164034.GA13695@sgi.com> User-Agent: Mutt/1.5.13 (2006-08-11) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 95647 Lines: 2771 Move additional sn2 specific code into xpc_sn2.c. Signed-off-by: Dean Nelson --- drivers/misc/sgi-xp/xpc.h | 173 +++--- drivers/misc/sgi-xp/xpc_channel.c | 214 -------- drivers/misc/sgi-xp/xpc_main.c | 278 +++------- drivers/misc/sgi-xp/xpc_partition.c | 61 +- drivers/misc/sgi-xp/xpc_sn2.c | 853 ++++++++++++++++++++------------ drivers/misc/sgi-xp/xpc_uv.c | 15 6 files changed, 786 insertions(+), 808 deletions(-) Index: linux-2.6/drivers/misc/sgi-xp/xpc.h =================================================================== --- linux-2.6.orig/drivers/misc/sgi-xp/xpc.h 2008-06-05 12:51:17.175807359 -0500 +++ linux-2.6/drivers/misc/sgi-xp/xpc.h 2008-06-06 08:10:50.969262778 -0500 @@ -122,9 +122,6 @@ struct xpc_rsvd_page { #define XPC_RP_VERSION _XPC_VERSION(2, 0) /* version 2.0 of the reserved page */ -#define XPC_SUPPORTS_RP_STAMP(_version) \ - (_version >= _XPC_VERSION(1, 1)) - /* * Define the structures by which XPC variables can be exported to other * partitions. (There are two: struct xpc_vars and struct xpc_vars_part) @@ -144,8 +141,8 @@ struct xpc_vars_sn2 { u64 heartbeat; DECLARE_BITMAP(heartbeating_to_mask, XP_MAX_NPARTITIONS_SN2); u64 heartbeat_offline; /* if 0, heartbeat should be changing */ - int act_nasid; - int act_phys_cpuid; + int activate_IRQ_nasid; + int activate_IRQ_phys_cpuid; u64 vars_part_pa; u64 amos_page_pa; /* paddr of page of AMOs from MSPEC driver */ AMO_t *amos_page; /* vaddr of page of AMOs from MSPEC driver */ @@ -153,9 +150,6 @@ struct xpc_vars_sn2 { #define XPC_V_VERSION _XPC_VERSION(3, 1) /* version 3.1 of the cross vars */ -#define XPC_SUPPORTS_DISENGAGE_REQUEST(_version) \ - (_version >= _XPC_VERSION(3, 1)) - /* * The following pertains to ia64-sn2 only. * @@ -167,14 +161,14 @@ struct xpc_vars_sn2 { * a PI FSB Protocol error to be generated by the SHUB. For XPC, we need 64 * AMO variables (based on XP_MAX_NPARTITIONS_SN2) to identify the senders of * NOTIFY IRQs, 128 AMO variables (based on XP_NASID_MASK_WORDS) to identify - * the senders of ACTIVATE IRQs, and 2 AMO variables to identify which remote + * the senders of ACTIVATE IRQs, 1 AMO variable to identify which remote * partitions (i.e., XPCs) consider themselves currently engaged with the - * local XPC. + * local XPC and 1 AMO variable to request partition deactivation. */ #define XPC_NOTIFY_IRQ_AMOS 0 #define XPC_ACTIVATE_IRQ_AMOS (XPC_NOTIFY_IRQ_AMOS + XP_MAX_NPARTITIONS_SN2) #define XPC_ENGAGED_PARTITIONS_AMO (XPC_ACTIVATE_IRQ_AMOS + XP_NASID_MASK_WORDS) -#define XPC_DISENGAGE_REQUEST_AMO (XPC_ENGAGED_PARTITIONS_AMO + 1) +#define XPC_DEACTIVATE_REQUEST_AMO (XPC_ENGAGED_PARTITIONS_AMO + 1) /* * The following structure describes the per partition specific variables. @@ -369,6 +363,23 @@ struct xpc_notify { * new messages, by the clearing of the message flags of the acknowledged * messages. */ +struct xpc_channel_sn2 { + + /* 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 */ + + struct mutex msg_to_pull_mutex; /* next msg to pull serialization */ +}; + +struct xpc_channel_uv { + /* >>> code is coming */ +}; + struct xpc_channel { short partid; /* ID of remote partition connected */ spinlock_t lock; /* lock for updating this structure */ @@ -407,20 +418,11 @@ struct xpc_channel { 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 */ atomic_t kthreads_assigned; /* #of kthreads assigned to channel */ @@ -431,6 +433,11 @@ struct xpc_channel { wait_queue_head_t idle_wq; /* idle kthread wait queue */ + union { + struct xpc_channel_sn2 sn2; + struct xpc_channel_uv uv; + } sn; + } ____cacheline_aligned; /* struct xpc_channel flags */ @@ -467,6 +474,40 @@ struct xpc_channel { * for each partition (a partition will never utilize the structure that * represents itself). */ + +struct xpc_partition_sn2 { + u64 remote_amos_page_pa; /* phys addr of partition's amos page */ + int activate_IRQ_nasid; /* active partition's act/deact nasid */ + int activate_IRQ_phys_cpuid; /* active part's act/deact phys cpuid */ + + u64 remote_vars_pa; /* phys addr of partition's vars */ + u64 remote_vars_part_pa; /* phys addr of partition's vars part */ + u8 remote_vars_version; /* version# of partition's vars */ + + 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 */ + + u64 remote_openclose_args_pa; /* phys addr of remote's args */ + + int remote_IPI_nasid; /* nasid of where to send IPIs */ + int remote_IPI_phys_cpuid; /* phys CPU ID of where to send IPIs */ + char IPI_owner[8]; /* IPI owner's name */ + + 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 */ + + struct timer_list dropped_notify_IRQ_timer; /* dropped IRQ timer */ +}; + +struct xpc_partition_uv { + /* >>> code is coming */ +}; + struct xpc_partition { /* XPC HB infrastructure */ @@ -474,22 +515,15 @@ struct xpc_partition { u8 remote_rp_version; /* version# of partition's rsvd pg */ unsigned long 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 activate_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 xp_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; + unsigned long disengage_timeout; /* timeout in jiffies */ + struct timer_list disengage_timer; /* XPC infrastructure referencing and teardown control */ @@ -502,14 +536,6 @@ struct xpc_partition { 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 */ @@ -517,19 +543,10 @@ struct xpc_partition { 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 */ @@ -537,6 +554,11 @@ struct xpc_partition { atomic_t channel_mgr_requests; /* #of requests to activate chan mgr */ wait_queue_head_t channel_mgr_wq; /* channel mgr's wait queue */ + union { + struct xpc_partition_sn2 sn2; + struct xpc_partition_uv uv; + } sn; + } ____cacheline_aligned; /* struct xpc_partition act_state values (for XPC HB) */ @@ -565,10 +587,10 @@ struct xpc_partition { #define XPC_P_DROPPED_IPI_WAIT_INTERVAL (0.25 * HZ) /* number of seconds to wait for other partitions to disengage */ -#define XPC_DISENGAGE_REQUEST_DEFAULT_TIMELIMIT 90 +#define XPC_DISENGAGE_DEFAULT_TIMELIMIT 90 -/* interval in seconds to print 'waiting disengagement' messages */ -#define XPC_DISENGAGE_PRINTMSG_INTERVAL 10 +/* interval in seconds to print 'waiting deactivation' messages */ +#define XPC_DEACTIVATE_PRINTMSG_INTERVAL 10 #define XPC_PARTID(_p) ((short)((_p) - &xpc_partitions[0])) @@ -578,13 +600,11 @@ extern struct xpc_registration xpc_regis /* 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 int xpc_disengage_timelimit; +extern int xpc_disengage_timedout; extern atomic_t xpc_activate_IRQ_rcvd; extern wait_queue_head_t xpc_activate_IRQ_wq; extern void *xpc_heartbeating_to_mask; -extern irqreturn_t xpc_notify_IRQ_handler(int, void *); -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, int); @@ -598,31 +618,34 @@ extern void (*xpc_online_heartbeat) (voi extern void (*xpc_check_remote_hb) (void); extern enum xp_retval (*xpc_make_first_contact) (struct xpc_partition *); extern u64 (*xpc_get_IPI_flags) (struct xpc_partition *); +extern void (*xpc_notify_senders_of_disconnect) (struct xpc_channel *); +extern void (*xpc_process_msg_IPI) (struct xpc_partition *, int); +extern int (*xpc_n_of_deliverable_msgs) (struct xpc_channel *); extern struct xpc_msg *(*xpc_get_deliverable_msg) (struct xpc_channel *); -extern void (*xpc_initiate_partition_activation) (struct xpc_rsvd_page *, u64, - int); +extern void (*xpc_request_partition_activation) (struct xpc_rsvd_page *, u64, + int); +extern void (*xpc_request_partition_reactivation) (struct xpc_partition *); +extern void (*xpc_request_partition_deactivation) (struct xpc_partition *); +extern void (*xpc_cancel_partition_deactivation_request) ( + struct xpc_partition *); extern void (*xpc_process_activate_IRQ_rcvd) (int); extern enum xp_retval (*xpc_setup_infrastructure) (struct xpc_partition *); extern void (*xpc_teardown_infrastructure) (struct xpc_partition *); -extern void (*xpc_mark_partition_engaged) (struct xpc_partition *); -extern void (*xpc_mark_partition_disengaged) (struct xpc_partition *); -extern void (*xpc_request_partition_disengage) (struct xpc_partition *); -extern void (*xpc_cancel_partition_disengage_request) (struct xpc_partition *); -extern u64 (*xpc_partition_engaged) (u64); -extern u64 (*xpc_partition_disengage_requested) (u64);; -extern void (*xpc_clear_partition_engaged) (u64); -extern void (*xpc_clear_partition_disengage_request) (u64); - -extern void (*xpc_IPI_send_local_activate) (int); -extern void (*xpc_IPI_send_activated) (struct xpc_partition *); -extern void (*xpc_IPI_send_local_reactivate) (int); -extern void (*xpc_IPI_send_disengage) (struct xpc_partition *); - -extern void (*xpc_IPI_send_closerequest) (struct xpc_channel *, - unsigned long *); -extern void (*xpc_IPI_send_closereply) (struct xpc_channel *, unsigned long *); -extern void (*xpc_IPI_send_openrequest) (struct xpc_channel *, unsigned long *); -extern void (*xpc_IPI_send_openreply) (struct xpc_channel *, unsigned long *); + +extern void (*xpc_indicate_partition_engaged) (struct xpc_partition *); +extern int (*xpc_partition_engaged) (short); +extern int (*xpc_any_partition_engaged) (void); +extern void (*xpc_indicate_partition_disengaged) (struct xpc_partition *); +extern void (*xpc_assume_partition_disengaged) (short); + +extern void (*xpc_send_channel_closerequest) (struct xpc_channel *, + unsigned long *); +extern void (*xpc_send_channel_closereply) (struct xpc_channel *, + unsigned long *); +extern void (*xpc_send_channel_openrequest) (struct xpc_channel *, + unsigned long *); +extern void (*xpc_send_channel_openreply) (struct xpc_channel *, + unsigned long *); extern enum xp_retval (*xpc_send_msg) (struct xpc_channel *, u32, void *, u16, u8, xpc_notify_func, void *); @@ -646,8 +669,6 @@ 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_setup_rsvd_page(void); -extern void xpc_allow_IPI_ops(void); -extern void xpc_restrict_IPI_ops(void); extern int xpc_identify_activate_IRQ_sender(void); extern int xpc_partition_disengaged(struct xpc_partition *); extern enum xp_retval xpc_mark_partition_active(struct xpc_partition *); Index: linux-2.6/drivers/misc/sgi-xp/xpc_channel.c =================================================================== --- linux-2.6.orig/drivers/misc/sgi-xp/xpc_channel.c 2008-06-05 12:51:17.075794869 -0500 +++ linux-2.6/drivers/misc/sgi-xp/xpc_channel.c 2008-06-06 08:08:28.696424737 -0500 @@ -201,7 +201,7 @@ xpc_process_connect(struct xpc_channel * if (!(ch->flags & XPC_C_OPENREPLY)) { ch->flags |= XPC_C_OPENREPLY; - xpc_IPI_send_openreply(ch, irq_flags); + xpc_send_channel_openreply(ch, irq_flags); } if (!(ch->flags & XPC_C_ROPENREPLY)) @@ -220,52 +220,6 @@ xpc_process_connect(struct xpc_channel * } /* - * Notify those who wanted to be notified upon delivery of their message. - */ -static void -xpc_notify_senders(struct xpc_channel *ch, enum xp_retval reason, s64 put) -{ - struct xpc_notify *notify; - u8 notify_type; - s64 get = ch->w_remote_GP.get - 1; - - while (++get < put && atomic_read(&ch->n_to_notify) > 0) { - - notify = &ch->notify_queue[get % ch->local_nentries]; - - /* - * See if the notify entry indicates it was associated with - * a message who's sender wants to be notified. It is possible - * that it is, but someone else is doing or has done the - * notification. - */ - notify_type = notify->type; - if (notify_type == 0 || - cmpxchg(¬ify->type, notify_type, 0) != notify_type) { - continue; - } - - DBUG_ON(notify_type != XPC_N_CALL); - - atomic_dec(&ch->n_to_notify); - - if (notify->func != NULL) { - dev_dbg(xpc_chan, "notify->func() called, notify=0x%p, " - "msg_number=%ld, partid=%d, channel=%d\n", - (void *)notify, get, ch->partid, ch->number); - - notify->func(reason, ch->partid, ch->number, - notify->key); - - dev_dbg(xpc_chan, "notify->func() returned, " - "notify=0x%p, msg_number=%ld, partid=%d, " - "channel=%d\n", (void *)notify, get, - ch->partid, ch->number); - } - } -} - -/* * Free up message queues and other stuff that were allocated for the specified * channel. * @@ -275,6 +229,8 @@ xpc_notify_senders(struct xpc_channel *c static void xpc_free_msgqueues(struct xpc_channel *ch) { + struct xpc_channel_sn2 *ch_sn2 = &ch->sn.sn2; + DBUG_ON(!spin_is_locked(&ch->lock)); DBUG_ON(atomic_read(&ch->n_to_notify) != 0); @@ -287,15 +243,15 @@ xpc_free_msgqueues(struct xpc_channel *c ch->kthreads_assigned_limit = 0; ch->kthreads_idle_limit = 0; - ch->local_GP->get = 0; - ch->local_GP->put = 0; - ch->remote_GP.get = 0; - ch->remote_GP.put = 0; - ch->w_local_GP.get = 0; - ch->w_local_GP.put = 0; - ch->w_remote_GP.get = 0; - ch->w_remote_GP.put = 0; - ch->next_msg_to_pull = 0; + ch_sn2->local_GP->get = 0; + ch_sn2->local_GP->put = 0; + ch_sn2->remote_GP.get = 0; + ch_sn2->remote_GP.put = 0; + ch_sn2->w_local_GP.get = 0; + ch_sn2->w_local_GP.put = 0; + ch_sn2->w_remote_GP.get = 0; + ch_sn2->w_remote_GP.put = 0; + ch_sn2->next_msg_to_pull = 0; if (ch->flags & XPC_C_SETUP) { ch->flags &= ~XPC_C_SETUP; @@ -339,7 +295,7 @@ xpc_process_disconnect(struct xpc_channe if (part->act_state == XPC_P_DEACTIVATING) { /* can't proceed until the other side disengages from us */ - if (xpc_partition_engaged(1UL << ch->partid)) + if (xpc_partition_engaged(ch->partid)) return; } else { @@ -351,7 +307,7 @@ xpc_process_disconnect(struct xpc_channe if (!(ch->flags & XPC_C_CLOSEREPLY)) { ch->flags |= XPC_C_CLOSEREPLY; - xpc_IPI_send_closereply(ch, irq_flags); + xpc_send_channel_closereply(ch, irq_flags); } if (!(ch->flags & XPC_C_RCLOSEREPLY)) @@ -361,7 +317,7 @@ xpc_process_disconnect(struct xpc_channe /* wake those waiting for notify completion */ if (atomic_read(&ch->n_to_notify) > 0) { /* >>> we do callout while holding ch->lock */ - xpc_notify_senders(ch, ch->reason, ch->w_local_GP.put); + xpc_notify_senders_of_disconnect(ch); } /* both sides are disconnected now */ @@ -734,7 +690,7 @@ xpc_connect_channel(struct xpc_channel * /* initiate the connection */ ch->flags |= (XPC_C_OPENREQUEST | XPC_C_CONNECTING); - xpc_IPI_send_openrequest(ch, &irq_flags); + xpc_send_channel_openrequest(ch, &irq_flags); xpc_process_connect(ch, &irq_flags); @@ -743,142 +699,6 @@ xpc_connect_channel(struct xpc_channel * return xpSuccess; } -/* - * Clear some of the msg flags in the local message queue. - */ -static inline void -xpc_clear_local_msgqueue_flags(struct xpc_channel *ch) -{ - struct xpc_msg *msg; - s64 get; - - get = ch->w_remote_GP.get; - do { - msg = (struct xpc_msg *)((u64)ch->local_msgqueue + - (get % ch->local_nentries) * - ch->msg_size); - msg->flags = 0; - } while (++get < ch->remote_GP.get); -} - -/* - * Clear some of the msg flags in the remote message queue. - */ -static inline void -xpc_clear_remote_msgqueue_flags(struct xpc_channel *ch) -{ - struct xpc_msg *msg; - s64 put; - - put = ch->w_remote_GP.put; - do { - msg = (struct xpc_msg *)((u64)ch->remote_msgqueue + - (put % ch->remote_nentries) * - ch->msg_size); - msg->flags = 0; - } while (++put < ch->remote_GP.put); -} - -static void -xpc_process_msg_IPI(struct xpc_partition *part, int ch_number) -{ - struct xpc_channel *ch = &part->channels[ch_number]; - int nmsgs_sent; - - ch->remote_GP = part->remote_GPs[ch_number]; - - /* See what, if anything, has changed for each connected channel */ - - xpc_msgqueue_ref(ch); - - if (ch->w_remote_GP.get == ch->remote_GP.get && - ch->w_remote_GP.put == ch->remote_GP.put) { - /* nothing changed since GPs were last pulled */ - xpc_msgqueue_deref(ch); - return; - } - - if (!(ch->flags & XPC_C_CONNECTED)) { - xpc_msgqueue_deref(ch); - return; - } - - /* - * First check to see if messages recently sent by us have been - * received by the other side. (The remote GET value will have - * changed since we last looked at it.) - */ - - if (ch->w_remote_GP.get != ch->remote_GP.get) { - - /* - * We need to notify any senders that want to be notified - * that their sent messages have been received by their - * intended recipients. We need to do this before updating - * w_remote_GP.get so that we don't allocate the same message - * queue entries prematurely (see xpc_allocate_msg()). - */ - if (atomic_read(&ch->n_to_notify) > 0) { - /* - * Notify senders that messages sent have been - * received and delivered by the other side. - */ - xpc_notify_senders(ch, xpMsgDelivered, - ch->remote_GP.get); - } - - /* - * Clear msg->flags in previously sent messages, so that - * they're ready for xpc_allocate_msg(). - */ - xpc_clear_local_msgqueue_flags(ch); - - ch->w_remote_GP.get = ch->remote_GP.get; - - dev_dbg(xpc_chan, "w_remote_GP.get changed to %ld, partid=%d, " - "channel=%d\n", ch->w_remote_GP.get, ch->partid, - ch->number); - - /* - * If anyone was waiting for message queue entries to become - * available, wake them up. - */ - if (atomic_read(&ch->n_on_msg_allocate_wq) > 0) - wake_up(&ch->msg_allocate_wq); - } - - /* - * Now check for newly sent messages by the other side. (The remote - * PUT value will have changed since we last looked at it.) - */ - - if (ch->w_remote_GP.put != ch->remote_GP.put) { - /* - * Clear msg->flags in previously received messages, so that - * they're ready for xpc_get_deliverable_msg(). - */ - xpc_clear_remote_msgqueue_flags(ch); - - ch->w_remote_GP.put = ch->remote_GP.put; - - dev_dbg(xpc_chan, "w_remote_GP.put changed to %ld, partid=%d, " - "channel=%d\n", ch->w_remote_GP.put, ch->partid, - ch->number); - - nmsgs_sent = ch->w_remote_GP.put - ch->w_local_GP.get; - if (nmsgs_sent > 0) { - dev_dbg(xpc_chan, "msgs waiting to be copied and " - "delivered=%d, partid=%d, channel=%d\n", - nmsgs_sent, ch->partid, ch->number); - - if (ch->flags & XPC_C_CONNECTEDCALLOUT_MADE) - xpc_activate_kthreads(ch, nmsgs_sent); - } - } - - xpc_msgqueue_deref(ch); -} - void xpc_process_channel_activity(struct xpc_partition *part) { @@ -1117,7 +937,7 @@ xpc_disconnect_channel(const int line, s XPC_C_ROPENREQUEST | XPC_C_ROPENREPLY | XPC_C_CONNECTING | XPC_C_CONNECTED); - xpc_IPI_send_closerequest(ch, irq_flags); + xpc_send_channel_closerequest(ch, irq_flags); if (channel_was_connected) ch->flags |= XPC_C_WASCONNECTED; Index: linux-2.6/drivers/misc/sgi-xp/xpc_main.c =================================================================== --- linux-2.6.orig/drivers/misc/sgi-xp/xpc_main.c 2008-06-05 12:51:17.111799366 -0500 +++ linux-2.6/drivers/misc/sgi-xp/xpc_main.c 2008-06-06 08:10:50.969262778 -0500 @@ -26,7 +26,7 @@ * Caveats: * * . We currently have no way to determine which nasid an IPI came - * from. Thus, xpc_IPI_send() does a remote AMO write followed by + * from. Thus, >>> xpc_IPI_send() does a remote AMO write followed by * an IPI. The AMO indicates where data is to be pulled from, so * after the IPI arrives, the remote partition checks the AMO word. * The IPI can actually arrive before the AMO however, so other code @@ -89,9 +89,9 @@ static int xpc_hb_check_interval = XPC_H static int xpc_hb_check_min_interval = 10; static int xpc_hb_check_max_interval = 120; -int xpc_disengage_request_timelimit = XPC_DISENGAGE_REQUEST_DEFAULT_TIMELIMIT; -static int xpc_disengage_request_min_timelimit; /* = 0 */ -static int xpc_disengage_request_max_timelimit = 120; +int xpc_disengage_timelimit = XPC_DISENGAGE_DEFAULT_TIMELIMIT; +static int xpc_disengage_min_timelimit; /* = 0 */ +static int xpc_disengage_max_timelimit = 120; static ctl_table xpc_sys_xpc_hb_dir[] = { { @@ -124,14 +124,14 @@ static ctl_table xpc_sys_xpc_dir[] = { .child = xpc_sys_xpc_hb_dir}, { .ctl_name = CTL_UNNUMBERED, - .procname = "disengage_request_timelimit", - .data = &xpc_disengage_request_timelimit, + .procname = "disengage_timelimit", + .data = &xpc_disengage_timelimit, .maxlen = sizeof(int), .mode = 0644, .proc_handler = &proc_dointvec_minmax, .strategy = &sysctl_intvec, - .extra1 = &xpc_disengage_request_min_timelimit, - .extra2 = &xpc_disengage_request_max_timelimit}, + .extra1 = &xpc_disengage_min_timelimit, + .extra2 = &xpc_disengage_max_timelimit}, {} }; static ctl_table xpc_sys_dir[] = { @@ -144,8 +144,8 @@ static ctl_table xpc_sys_dir[] = { }; static struct ctl_table_header *xpc_sysctl; -/* non-zero if any remote partition disengage request was timed out */ -int xpc_disengage_request_timedout; +/* non-zero if any remote partition disengage was timed out */ +int xpc_disengage_timedout; /* #of activate IRQs received */ atomic_t xpc_activate_IRQ_rcvd = ATOMIC_INIT(0); @@ -184,38 +184,36 @@ void (*xpc_online_heartbeat) (void); void (*xpc_check_remote_hb) (void); enum xp_retval (*xpc_make_first_contact) (struct xpc_partition *part); +void (*xpc_notify_senders_of_disconnect) (struct xpc_channel *ch); u64 (*xpc_get_IPI_flags) (struct xpc_partition *part); +void (*xpc_process_msg_IPI) (struct xpc_partition *part, int ch_number); +int (*xpc_n_of_deliverable_msgs) (struct xpc_channel *ch); struct xpc_msg *(*xpc_get_deliverable_msg) (struct xpc_channel *ch); -void (*xpc_initiate_partition_activation) (struct xpc_rsvd_page *remote_rp, - u64 remote_rp_pa, int nasid); +void (*xpc_request_partition_activation) (struct xpc_rsvd_page *remote_rp, + u64 remote_rp_pa, int nasid); +void (*xpc_request_partition_reactivation) (struct xpc_partition *part); +void (*xpc_request_partition_deactivation) (struct xpc_partition *part); +void (*xpc_cancel_partition_deactivation_request) (struct xpc_partition *part); void (*xpc_process_activate_IRQ_rcvd) (int n_IRQs_expected); enum xp_retval (*xpc_setup_infrastructure) (struct xpc_partition *part); void (*xpc_teardown_infrastructure) (struct xpc_partition *part); -void (*xpc_mark_partition_engaged) (struct xpc_partition *part); -void (*xpc_mark_partition_disengaged) (struct xpc_partition *part); -void (*xpc_request_partition_disengage) (struct xpc_partition *part); -void (*xpc_cancel_partition_disengage_request) (struct xpc_partition *part); -u64 (*xpc_partition_engaged) (u64 partid_mask); -u64 (*xpc_partition_disengage_requested) (u64 partid_mask); -void (*xpc_clear_partition_engaged) (u64 partid_mask); -void (*xpc_clear_partition_disengage_request) (u64 partid_mask); - -void (*xpc_IPI_send_local_activate) (int from_nasid); -void (*xpc_IPI_send_activated) (struct xpc_partition *part); -void (*xpc_IPI_send_local_reactivate) (int from_nasid); -void (*xpc_IPI_send_disengage) (struct xpc_partition *part); - -void (*xpc_IPI_send_closerequest) (struct xpc_channel *ch, - unsigned long *irq_flags); -void (*xpc_IPI_send_closereply) (struct xpc_channel *ch, - unsigned long *irq_flags); -void (*xpc_IPI_send_openrequest) (struct xpc_channel *ch, - unsigned long *irq_flags); -void (*xpc_IPI_send_openreply) (struct xpc_channel *ch, - unsigned long *irq_flags); +void (*xpc_indicate_partition_engaged) (struct xpc_partition *part); +int (*xpc_partition_engaged) (short partid); +int (*xpc_any_partition_engaged) (void); +void (*xpc_indicate_partition_disengaged) (struct xpc_partition *part); +void (*xpc_assume_partition_disengaged) (short partid); + +void (*xpc_send_channel_closerequest) (struct xpc_channel *ch, + unsigned long *irq_flags); +void (*xpc_send_channel_closereply) (struct xpc_channel *ch, + unsigned long *irq_flags); +void (*xpc_send_channel_openrequest) (struct xpc_channel *ch, + unsigned long *irq_flags); +void (*xpc_send_channel_openreply) (struct xpc_channel *ch, + unsigned long *irq_flags); enum xp_retval (*xpc_send_msg) (struct xpc_channel *ch, u32 flags, void *payload, u16 payload_size, u8 notify_type, @@ -223,19 +221,19 @@ enum xp_retval (*xpc_send_msg) (struct x void (*xpc_received_msg) (struct xpc_channel *ch, struct xpc_msg *msg); /* - * Timer function to enforce the timelimit on the partition disengage request. + * Timer function to enforce the timelimit on the partition disengage. */ static void -xpc_timeout_partition_disengage_request(unsigned long data) +xpc_timeout_partition_disengage(unsigned long data) { struct xpc_partition *part = (struct xpc_partition *)data; - DBUG_ON(time_is_after_jiffies(part->disengage_request_timeout)); + DBUG_ON(time_is_after_jiffies(part->disengage_timeout)); (void)xpc_partition_disengaged(part); - DBUG_ON(part->disengage_request_timeout != 0); - DBUG_ON(xpc_partition_engaged(1UL << XPC_PARTID(part)) != 0); + DBUG_ON(part->disengage_timeout != 0); + DBUG_ON(xpc_partition_engaged(XPC_PARTID(part))); } /* @@ -464,7 +462,7 @@ xpc_activating(void *__partid) if (part->reason == xpReactivating) { /* interrupting ourselves results in activating partition */ - xpc_IPI_send_local_reactivate(part->reactivate_nasid); + xpc_request_partition_reactivation(part); } return 0; @@ -496,82 +494,6 @@ xpc_activate_partition(struct xpc_partit } } -/* - * Check to see if there is any channel activity to/from the specified - * partition. - */ -static void -xpc_check_for_channel_activity(struct xpc_partition *part) -{ - u64 IPI_amo; - unsigned long irq_flags; - -/* this needs to be uncommented, but I'm thinking this function and the */ -/* ones that call it need to be moved into xpc_sn2.c... */ - IPI_amo = 0; /* = xpc_IPI_receive(part->local_IPI_amo_va); */ - if (IPI_amo == 0) - return; - - spin_lock_irqsave(&part->IPI_lock, irq_flags); - part->local_IPI_amo |= IPI_amo; - spin_unlock_irqrestore(&part->IPI_lock, irq_flags); - - dev_dbg(xpc_chan, "received IPI from partid=%d, IPI_amo=0x%lx\n", - XPC_PARTID(part), IPI_amo); - - xpc_wakeup_channel_mgr(part); -} - -/* - * Handle the receipt of a SGI_XPC_NOTIFY IRQ by seeing whether the specified - * partition actually sent it. Since SGI_XPC_NOTIFY IRQs may be shared by more - * than one partition, we use an AMO_t structure per partition to indicate - * whether a partition has sent an IPI or not. If it has, then wake up the - * associated kthread to handle it. - * - * All SGI_XPC_NOTIFY IRQs received by XPC are the result of IPIs sent by XPC - * running on other partitions. - * - * Noteworthy Arguments: - * - * irq - Interrupt ReQuest number. NOT USED. - * - * dev_id - partid of IPI's potential sender. - */ -irqreturn_t -xpc_notify_IRQ_handler(int irq, void *dev_id) -{ - short partid = (short)(u64)dev_id; - struct xpc_partition *part = &xpc_partitions[partid]; - - DBUG_ON(partid < 0 || partid >= xp_max_npartitions); - - if (xpc_part_ref(part)) { - xpc_check_for_channel_activity(part); - - xpc_part_deref(part); - } - return IRQ_HANDLED; -} - -/* - * Check to see if xpc_notify_IRQ_handler() dropped any IPIs on the floor - * because the write to their associated IPI amo completed after the IRQ/IPI - * was received. - */ -void -xpc_dropped_IPI_check(struct xpc_partition *part) -{ - if (xpc_part_ref(part)) { - xpc_check_for_channel_activity(part); - - part->dropped_IPI_timer.expires = jiffies + - XPC_P_DROPPED_IPI_WAIT_INTERVAL; - add_timer(&part->dropped_IPI_timer); - xpc_part_deref(part); - } -} - void xpc_activate_kthreads(struct xpc_channel *ch, int needed) { @@ -616,7 +538,7 @@ xpc_kthread_waitmsgs(struct xpc_partitio do { /* deliver messages to their intended recipients */ - while (ch->w_local_GP.get < ch->w_remote_GP.put && + while (xpc_n_of_deliverable_msgs(ch) > 0 && !(ch->flags & XPC_C_DISCONNECTING)) { xpc_deliver_msg(ch); } @@ -632,7 +554,7 @@ xpc_kthread_waitmsgs(struct xpc_partitio "wait_event_interruptible_exclusive()\n"); (void)wait_event_interruptible_exclusive(ch->idle_wq, - (ch->w_local_GP.get < ch->w_remote_GP.put || + (xpc_n_of_deliverable_msgs(ch) > 0 || (ch->flags & XPC_C_DISCONNECTING))); atomic_dec(&ch->kthreads_idle); @@ -677,7 +599,7 @@ xpc_kthread_start(void *args) * additional kthreads to help deliver them. We only * need one less than total #of messages to deliver. */ - n_needed = ch->w_remote_GP.put - ch->w_local_GP.get - 1; + n_needed = xpc_n_of_deliverable_msgs(ch) - 1; if (n_needed > 0 && !(ch->flags & XPC_C_DISCONNECTING)) xpc_activate_kthreads(ch, n_needed); @@ -703,11 +625,9 @@ xpc_kthread_start(void *args) } spin_unlock_irqrestore(&ch->lock, irq_flags); - if (atomic_dec_return(&ch->kthreads_assigned) == 0) { - if (atomic_dec_return(&part->nchannels_engaged) == 0) { - xpc_mark_partition_disengaged(part); - xpc_IPI_send_disengage(part); - } + if (atomic_dec_return(&ch->kthreads_assigned) == 0 && + atomic_dec_return(&part->nchannels_engaged) == 0) { + xpc_indicate_partition_disengaged(part); } xpc_msgqueue_deref(ch); @@ -758,9 +678,9 @@ xpc_create_kthreads(struct xpc_channel * } else if (ch->flags & XPC_C_DISCONNECTING) { break; - } else if (atomic_inc_return(&ch->kthreads_assigned) == 1) { - if (atomic_inc_return(&part->nchannels_engaged) == 1) - xpc_mark_partition_engaged(part); + } else if (atomic_inc_return(&ch->kthreads_assigned) == 1 && + atomic_inc_return(&part->nchannels_engaged) == 1) { + xpc_indicate_partition_engaged(part); } (void)xpc_part_ref(part); xpc_msgqueue_ref(ch); @@ -782,8 +702,7 @@ xpc_create_kthreads(struct xpc_channel * if (atomic_dec_return(&ch->kthreads_assigned) == 0 && atomic_dec_return(&part->nchannels_engaged) == 0) { - xpc_mark_partition_disengaged(part); - xpc_IPI_send_disengage(part); + xpc_indicate_partition_disengaged(part); } xpc_msgqueue_deref(ch); xpc_part_deref(part); @@ -862,7 +781,7 @@ xpc_do_exit(enum xp_retval reason) short partid; int active_part_count, printed_waiting_msg = 0; struct xpc_partition *part; - unsigned long printmsg_time, disengage_request_timeout = 0; + unsigned long printmsg_time, disengage_timeout = 0; /* a 'rmmod XPC' and a 'reboot' cannot both end up here together */ DBUG_ON(xpc_exiting == 1); @@ -886,8 +805,8 @@ xpc_do_exit(enum xp_retval reason) /* wait for all partitions to become inactive */ - printmsg_time = jiffies + (XPC_DISENGAGE_PRINTMSG_INTERVAL * HZ); - xpc_disengage_request_timedout = 0; + printmsg_time = jiffies + (XPC_DEACTIVATE_PRINTMSG_INTERVAL * HZ); + xpc_disengage_timedout = 0; do { active_part_count = 0; @@ -904,36 +823,32 @@ xpc_do_exit(enum xp_retval reason) XPC_DEACTIVATE_PARTITION(part, reason); - if (part->disengage_request_timeout > - disengage_request_timeout) { - disengage_request_timeout = - part->disengage_request_timeout; - } + if (part->disengage_timeout > disengage_timeout) + disengage_timeout = part->disengage_timeout; } - if (xpc_partition_engaged(-1UL)) { + if (xpc_any_partition_engaged()) { if (time_is_before_jiffies(printmsg_time)) { dev_info(xpc_part, "waiting for remote " - "partitions to disengage, timeout in " - "%ld seconds\n", - (disengage_request_timeout - jiffies) - / HZ); + "partitions to deactivate, timeout in " + "%ld seconds\n", (disengage_timeout - + jiffies) / HZ); printmsg_time = jiffies + - (XPC_DISENGAGE_PRINTMSG_INTERVAL * HZ); + (XPC_DEACTIVATE_PRINTMSG_INTERVAL * HZ); printed_waiting_msg = 1; } } else if (active_part_count > 0) { if (printed_waiting_msg) { dev_info(xpc_part, "waiting for local partition" - " to disengage\n"); + " to deactivate\n"); printed_waiting_msg = 0; } } else { - if (!xpc_disengage_request_timedout) { + if (!xpc_disengage_timedout) { dev_info(xpc_part, "all partitions have " - "disengaged\n"); + "deactivated\n"); } break; } @@ -943,7 +858,7 @@ xpc_do_exit(enum xp_retval reason) } while (1); - DBUG_ON(xpc_partition_engaged(-1UL)); + DBUG_ON(xpc_any_partition_engaged()); DBUG_ON(xpc_any_hbs_allowed() != 0); /* indicate to others that our reserved page is uninitialized */ @@ -996,15 +911,16 @@ xpc_system_reboot(struct notifier_block } /* - * Notify other partitions to disengage from all references to our memory. + * Notify other partitions to deactivate from us by first disengaging from all + * references to our memory. */ static void -xpc_die_disengage(void) +xpc_die_deactivate(void) { struct xpc_partition *part; short partid; - unsigned long engaged; - long time, printmsg_time, disengage_request_timeout; + int any_engaged; + long time, printmsg_time, disengage_timeout; /* keep xpc_hb_checker thread from doing anything (just in case) */ xpc_exiting = 1; @@ -1014,43 +930,37 @@ xpc_die_disengage(void) for (partid = 0; partid < xp_max_npartitions; partid++) { part = &xpc_partitions[partid]; - if (!XPC_SUPPORTS_DISENGAGE_REQUEST(part-> - remote_vars_version)) { - - /* just in case it was left set by an earlier XPC */ - xpc_clear_partition_engaged(1UL << partid); - continue; - } - - if (xpc_partition_engaged(1UL << partid) || + if (xpc_partition_engaged(partid) || part->act_state != XPC_P_INACTIVE) { - xpc_request_partition_disengage(part); - xpc_mark_partition_disengaged(part); - xpc_IPI_send_disengage(part); + xpc_request_partition_deactivation(part); + xpc_indicate_partition_disengaged(part); } } time = rtc_time(); printmsg_time = time + - (XPC_DISENGAGE_PRINTMSG_INTERVAL * sn_rtc_cycles_per_second); - disengage_request_timeout = time + - (xpc_disengage_request_timelimit * sn_rtc_cycles_per_second); + (XPC_DEACTIVATE_PRINTMSG_INTERVAL * sn_rtc_cycles_per_second); + disengage_timeout = time + + (xpc_disengage_timelimit * sn_rtc_cycles_per_second); - /* wait for all other partitions to disengage from us */ + /* + * Though we requested that all other partitions deactivate from us, + * we only wait until they've all disengaged. + */ while (1) { - engaged = xpc_partition_engaged(-1UL); - if (!engaged) { - dev_info(xpc_part, "all partitions have disengaged\n"); + any_engaged = xpc_any_partition_engaged(); + if (!any_engaged) { + dev_info(xpc_part, "all partitions have deactivated\n"); break; } time = rtc_time(); - if (time >= disengage_request_timeout) { + if (time >= disengage_timeout) { for (partid = 0; partid < xp_max_npartitions; partid++) { - if (engaged & (1UL << partid)) { - dev_info(xpc_part, "disengage from " + if (xpc_partition_engaged(partid)) { + dev_info(xpc_part, "deactivate from " "remote partition %d timed " "out\n", partid); } @@ -1060,11 +970,11 @@ xpc_die_disengage(void) if (time >= printmsg_time) { dev_info(xpc_part, "waiting for remote partitions to " - "disengage, timeout in %ld seconds\n", - (disengage_request_timeout - time) / + "deactivate, timeout in %ld seconds\n", + (disengage_timeout - time) / sn_rtc_cycles_per_second); printmsg_time = time + - (XPC_DISENGAGE_PRINTMSG_INTERVAL * + (XPC_DEACTIVATE_PRINTMSG_INTERVAL * sn_rtc_cycles_per_second); } } @@ -1084,7 +994,7 @@ xpc_system_die(struct notifier_block *nb switch (event) { case DIE_MACHINE_RESTART: case DIE_MACHINE_HALT: - xpc_die_disengage(); + xpc_die_deactivate(); break; case DIE_KDEBUG_ENTER: @@ -1183,10 +1093,10 @@ xpc_init(void) part->act_state = XPC_P_INACTIVE; XPC_SET_REASON(part, 0, 0); - init_timer(&part->disengage_request_timer); - part->disengage_request_timer.function = - xpc_timeout_partition_disengage_request; - part->disengage_request_timer.data = (unsigned long)part; + init_timer(&part->disengage_timer); + part->disengage_timer.function = + xpc_timeout_partition_disengage; + part->disengage_timer.data = (unsigned long)part; part->setup_state = XPC_P_UNSET; init_waitqueue_head(&part->teardown_wq); @@ -1295,9 +1205,9 @@ module_param(xpc_hb_check_interval, int, MODULE_PARM_DESC(xpc_hb_check_interval, "Number of seconds between " "heartbeat checks."); -module_param(xpc_disengage_request_timelimit, int, 0); -MODULE_PARM_DESC(xpc_disengage_request_timelimit, "Number of seconds to wait " - "for disengage request to complete."); +module_param(xpc_disengage_timelimit, int, 0); +MODULE_PARM_DESC(xpc_disengage_timelimit, "Number of seconds to wait " + "for disengage to complete."); module_param(xpc_kdebug_ignore, int, 0); MODULE_PARM_DESC(xpc_kdebug_ignore, "Should lack of heartbeat be ignored by " Index: linux-2.6/drivers/misc/sgi-xp/xpc_sn2.c =================================================================== --- linux-2.6.orig/drivers/misc/sgi-xp/xpc_sn2.c 2008-06-05 12:51:17.151804361 -0500 +++ linux-2.6/drivers/misc/sgi-xp/xpc_sn2.c 2008-06-06 08:10:50.973263248 -0500 @@ -196,37 +196,85 @@ xpc_activate_IRQ_send_local_sn2(int from wake_up_interruptible(&xpc_activate_IRQ_wq); } -static void -xpc_IPI_send_local_activate_sn2(int from_nasid) -{ - xpc_activate_IRQ_send_local_sn2(from_nasid); -} +/* + * IPIs associated with SGI_XPC_NOTIFY IRQ. + */ +/* + * Check to see if there is any channel activity to/from the specified + * partition. + */ static void -xpc_IPI_send_activated_sn2(struct xpc_partition *part) +xpc_check_for_channel_activity_sn2(struct xpc_partition *part) { - xpc_activate_IRQ_send_sn2(part->remote_amos_page_pa, - cnodeid_to_nasid(0), part->remote_act_nasid, - part->remote_act_phys_cpuid); -} + u64 IPI_amo; + unsigned long irq_flags; -static void -xpc_IPI_send_local_reactivate_sn2(int from_nasid) -{ - xpc_activate_IRQ_send_local_sn2(from_nasid); + IPI_amo = xpc_IPI_receive_sn2(part->sn.sn2.local_IPI_amo_va); + if (IPI_amo == 0) + return; + + spin_lock_irqsave(&part->IPI_lock, irq_flags); + part->local_IPI_amo |= IPI_amo; + spin_unlock_irqrestore(&part->IPI_lock, irq_flags); + + dev_dbg(xpc_chan, "received IPI from partid=%d, IPI_amo=0x%lx\n", + XPC_PARTID(part), IPI_amo); + + xpc_wakeup_channel_mgr(part); } -static void -xpc_IPI_send_disengage_sn2(struct xpc_partition *part) +/* + * Handle the receipt of a SGI_XPC_NOTIFY IRQ by seeing whether the specified + * partition actually sent it. Since SGI_XPC_NOTIFY IRQs may be shared by more + * than one partition, we use an AMO_t structure per partition to indicate + * whether a partition has sent an IPI or not. If it has, then wake up the + * associated kthread to handle it. + * + * All SGI_XPC_NOTIFY IRQs received by XPC are the result of IPIs sent by XPC + * running on other partitions. + * + * Noteworthy Arguments: + * + * irq - Interrupt ReQuest number. NOT USED. + * + * dev_id - partid of IPI's potential sender. + */ +static irqreturn_t +xpc_handle_notify_IRQ_sn2(int irq, void *dev_id) { - xpc_activate_IRQ_send_sn2(part->remote_amos_page_pa, - cnodeid_to_nasid(0), part->remote_act_nasid, - part->remote_act_phys_cpuid); + short partid = (short)(u64)dev_id; + struct xpc_partition *part = &xpc_partitions[partid]; + + DBUG_ON(partid < 0 || partid >= xp_max_npartitions); + + if (xpc_part_ref(part)) { + xpc_check_for_channel_activity_sn2(part); + + xpc_part_deref(part); + } + return IRQ_HANDLED; } /* - * IPIs associated with SGI_XPC_NOTIFY IRQ. + * Check to see if xpc_handle_notify_IRQ_sn2() dropped any IPIs on the floor + * because the write to their associated IPI amo completed after the IRQ/IPI + * was received. */ +static void +xpc_dropped_notify_IRQ_check_sn2(struct xpc_partition *part) +{ + struct xpc_partition_sn2 *part_sn2 = &part->sn.sn2; + + if (xpc_part_ref(part)) { + xpc_check_for_channel_activity_sn2(part); + + part_sn2->dropped_notify_IRQ_timer.expires = jiffies + + XPC_P_DROPPED_IPI_WAIT_INTERVAL; + add_timer(&part_sn2->dropped_notify_IRQ_timer); + xpc_part_deref(part); + } +} /* * Send an IPI to the remote partition that is associated with the @@ -237,13 +285,14 @@ xpc_notify_IRQ_send_sn2(struct xpc_chann char *ipi_flag_string, unsigned long *irq_flags) { struct xpc_partition *part = &xpc_partitions[ch->partid]; + struct xpc_partition_sn2 *part_sn2 = &part->sn.sn2; enum xp_retval ret; if (likely(part->act_state != XPC_P_DEACTIVATING)) { - ret = xpc_IPI_send_sn2(part->remote_IPI_amo_va, + ret = xpc_IPI_send_sn2(part_sn2->remote_IPI_amo_va, (u64)ipi_flag << (ch->number * 8), - part->remote_IPI_nasid, - part->remote_IPI_phys_cpuid, + part_sn2->remote_IPI_nasid, + part_sn2->remote_IPI_phys_cpuid, SGI_XPC_NOTIFY); dev_dbg(xpc_chan, "%s sent to partid=%d, channel=%d, ret=%d\n", ipi_flag_string, ch->partid, ch->number, ret); @@ -263,7 +312,7 @@ xpc_notify_IRQ_send_sn2(struct xpc_chann /* * Make it look like the remote partition, which is associated with the * specified channel, sent us an IPI. This faked IPI will be handled - * by xpc_dropped_IPI_check(). + * by xpc_dropped_notify_IRQ_check_sn2(). */ static void xpc_notify_IRQ_send_local_sn2(struct xpc_channel *ch, u8 ipi_flag, @@ -271,7 +320,7 @@ xpc_notify_IRQ_send_local_sn2(struct xpc { struct xpc_partition *part = &xpc_partitions[ch->partid]; - FETCHOP_STORE_OP(TO_AMO((u64)&part->local_IPI_amo_va->variable), + FETCHOP_STORE_OP(TO_AMO((u64)&part->sn.sn2.local_IPI_amo_va->variable), FETCHOP_OR, ((u64)ipi_flag << (ch->number * 8))); dev_dbg(xpc_chan, "%s sent local from partid=%d, channel=%d\n", ipi_flag_string, ch->partid, ch->number); @@ -281,7 +330,8 @@ xpc_notify_IRQ_send_local_sn2(struct xpc xpc_notify_IRQ_send_local_sn2(_ch, _ipi_f, #_ipi_f) static void -xpc_IPI_send_closerequest_sn2(struct xpc_channel *ch, unsigned long *irq_flags) +xpc_send_channel_closerequest_sn2(struct xpc_channel *ch, + unsigned long *irq_flags) { struct xpc_openclose_args *args = ch->local_openclose_args; @@ -290,13 +340,15 @@ xpc_IPI_send_closerequest_sn2(struct xpc } static void -xpc_IPI_send_closereply_sn2(struct xpc_channel *ch, unsigned long *irq_flags) +xpc_send_channel_closereply_sn2(struct xpc_channel *ch, + unsigned long *irq_flags) { XPC_NOTIFY_IRQ_SEND_SN2(ch, XPC_IPI_CLOSEREPLY, irq_flags); } static void -xpc_IPI_send_openrequest_sn2(struct xpc_channel *ch, unsigned long *irq_flags) +xpc_send_channel_openrequest_sn2(struct xpc_channel *ch, + unsigned long *irq_flags) { struct xpc_openclose_args *args = ch->local_openclose_args; @@ -306,7 +358,7 @@ xpc_IPI_send_openrequest_sn2(struct xpc_ } static void -xpc_IPI_send_openreply_sn2(struct xpc_channel *ch, unsigned long *irq_flags) +xpc_send_channel_openreply_sn2(struct xpc_channel *ch, unsigned long *irq_flags) { struct xpc_openclose_args *args = ch->local_openclose_args; @@ -317,13 +369,13 @@ xpc_IPI_send_openreply_sn2(struct xpc_ch } static void -xpc_IPI_send_msgrequest_sn2(struct xpc_channel *ch) +xpc_send_channel_msgrequest_sn2(struct xpc_channel *ch) { XPC_NOTIFY_IRQ_SEND_SN2(ch, XPC_IPI_MSGREQUEST, NULL); } static void -xpc_IPI_send_local_msgrequest_sn2(struct xpc_channel *ch) +xpc_send_channel_local_msgrequest_sn2(struct xpc_channel *ch) { XPC_NOTIFY_IRQ_SEND_LOCAL_SN2(ch, XPC_IPI_MSGREQUEST); } @@ -334,10 +386,10 @@ xpc_IPI_send_local_msgrequest_sn2(struct */ static void -xpc_mark_partition_engaged_sn2(struct xpc_partition *part) +xpc_indicate_partition_engaged_sn2(struct xpc_partition *part) { unsigned long irq_flags; - AMO_t *amo = (AMO_t *)__va(part->remote_amos_page_pa + + AMO_t *amo = (AMO_t *)__va(part->sn.sn2.remote_amos_page_pa + (XPC_ENGAGED_PARTITIONS_AMO * sizeof(AMO_t))); @@ -360,10 +412,11 @@ xpc_mark_partition_engaged_sn2(struct xp } static void -xpc_mark_partition_disengaged_sn2(struct xpc_partition *part) +xpc_indicate_partition_disengaged_sn2(struct xpc_partition *part) { + struct xpc_partition_sn2 *part_sn2 = &part->sn.sn2; unsigned long irq_flags; - AMO_t *amo = (AMO_t *)__va(part->remote_amos_page_pa + + AMO_t *amo = (AMO_t *)__va(part_sn2->remote_amos_page_pa + (XPC_ENGAGED_PARTITIONS_AMO * sizeof(AMO_t))); @@ -383,96 +436,44 @@ xpc_mark_partition_disengaged_sn2(struct xp_nofault_PIOR_target)); local_irq_restore(irq_flags); -} - -static void -xpc_request_partition_disengage_sn2(struct xpc_partition *part) -{ - unsigned long irq_flags; - AMO_t *amo = (AMO_t *)__va(part->remote_amos_page_pa + - (XPC_DISENGAGE_REQUEST_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 void -xpc_cancel_partition_disengage_request_sn2(struct xpc_partition *part) -{ - unsigned long irq_flags; - AMO_t *amo = (AMO_t *)__va(part->remote_amos_page_pa + - (XPC_DISENGAGE_REQUEST_AMO * sizeof(AMO_t))); - - local_irq_save(irq_flags); - - /* clear bit corresponding to our partid in remote partition's AMO */ - FETCHOP_STORE_OP(TO_AMO((u64)&amo->variable), FETCHOP_AND, - ~(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. + * Send activate IRQ to get other side to see that we've cleared our + * bit in their engaged partitions AMO. */ - (void)xp_nofault_PIOR((u64 *)GLOBAL_MMR_ADDR(NASID_GET(&amo-> - variable), - xp_nofault_PIOR_target)); - - local_irq_restore(irq_flags); + xpc_activate_IRQ_send_sn2(part_sn2->remote_amos_page_pa, + cnodeid_to_nasid(0), + part_sn2->activate_IRQ_nasid, + part_sn2->activate_IRQ_phys_cpuid); } -static u64 -xpc_partition_engaged_sn2(u64 partid_mask) +static int +xpc_partition_engaged_sn2(short partid) { AMO_t *amo = xpc_vars->amos_page + XPC_ENGAGED_PARTITIONS_AMO; - /* return our partition's AMO variable ANDed with partid_mask */ + /* our partition's AMO variable ANDed with partid mask */ return (FETCHOP_LOAD_OP(TO_AMO((u64)&amo->variable), FETCHOP_LOAD) & - partid_mask); + (1UL << partid)) != 0; } -static u64 -xpc_partition_disengage_requested_sn2(u64 partid_mask) -{ - AMO_t *amo = xpc_vars->amos_page + XPC_DISENGAGE_REQUEST_AMO; - - /* return our partition's AMO variable ANDed with partid_mask */ - return (FETCHOP_LOAD_OP(TO_AMO((u64)&amo->variable), FETCHOP_LOAD) & - partid_mask); -} - -static void -xpc_clear_partition_engaged_sn2(u64 partid_mask) +static int +xpc_any_partition_engaged_sn2(void) { AMO_t *amo = xpc_vars->amos_page + XPC_ENGAGED_PARTITIONS_AMO; - /* clear bit(s) based on partid_mask in our partition's AMO */ - FETCHOP_STORE_OP(TO_AMO((u64)&amo->variable), FETCHOP_AND, - ~partid_mask); + /* our partition's AMO variable */ + return FETCHOP_LOAD_OP(TO_AMO((u64)&amo->variable), FETCHOP_LOAD) != 0; } static void -xpc_clear_partition_disengage_request_sn2(u64 partid_mask) +xpc_assume_partition_disengaged_sn2(short partid) { - AMO_t *amo = xpc_vars->amos_page + XPC_DISENGAGE_REQUEST_AMO; + AMO_t *amo = xpc_vars->amos_page + XPC_ENGAGED_PARTITIONS_AMO; - /* clear bit(s) based on partid_mask in our partition's AMO */ + /* clear bit(s) based on partid mask in our partition's AMO */ FETCHOP_STORE_OP(TO_AMO((u64)&amo->variable), FETCHOP_AND, - ~partid_mask); + ~(1UL << partid)); } /* original protection values for each node */ @@ -545,7 +546,6 @@ xpc_rsvd_page_init_sn2(struct xpc_rsvd_p xpc_vars_part = (struct xpc_vars_part_sn2 *)((u8 *)XPC_RP_VARS(rp) + XPC_RP_VARS_SIZE); - /* * Before clearing xpc_vars, see if a page of AMOs had been previously * allocated. If not we'll need to allocate one and set permissions @@ -583,8 +583,8 @@ xpc_rsvd_page_init_sn2(struct xpc_rsvd_p memset(xpc_vars, 0, sizeof(struct xpc_vars_sn2)); xpc_vars->version = XPC_V_VERSION; - xpc_vars->act_nasid = cpuid_to_nasid(0); - xpc_vars->act_phys_cpuid = cpu_physical_id(0); + xpc_vars->activate_IRQ_nasid = cpuid_to_nasid(0); + xpc_vars->activate_IRQ_phys_cpuid = cpu_physical_id(0); xpc_vars->vars_part_pa = __pa(xpc_vars_part); xpc_vars->amos_page_pa = ia64_tpa((u64)amos_page); xpc_vars->amos_page = amos_page; /* save for next load of XPC */ @@ -599,7 +599,7 @@ xpc_rsvd_page_init_sn2(struct xpc_rsvd_p /* initialize the engaged remote partitions related AMO variables */ (void)xpc_IPI_init_sn2(XPC_ENGAGED_PARTITIONS_AMO); - (void)xpc_IPI_init_sn2(XPC_DISENGAGE_REQUEST_AMO); + (void)xpc_IPI_init_sn2(XPC_DEACTIVATE_REQUEST_AMO); return xpSuccess; } @@ -671,7 +671,7 @@ xpc_check_remote_hb_sn2(void) /* pull the remote_hb cache line */ ret = xp_remote_memcpy(remote_vars, - (void *)part->remote_vars_pa, + (void *)part->sn.sn2.remote_vars_pa, XPC_RP_VARS_SIZE); if (ret != xpSuccess) { XPC_DEACTIVATE_PARTITION(part, ret); @@ -726,10 +726,86 @@ xpc_get_remote_vars_sn2(u64 remote_vars_ } static void -xpc_initiate_partition_activation_sn2(struct xpc_rsvd_page *remote_rp, - u64 remote_rp_pa, int nasid) +xpc_request_partition_activation_sn2(struct xpc_rsvd_page *remote_rp, + u64 remote_rp_pa, int nasid) { - xpc_IPI_send_local_activate(nasid); + xpc_activate_IRQ_send_local_sn2(nasid); +} + +static void +xpc_request_partition_reactivation_sn2(struct xpc_partition *part) +{ + xpc_activate_IRQ_send_local_sn2(part->sn.sn2.activate_IRQ_nasid); +} + +static void +xpc_request_partition_deactivation_sn2(struct xpc_partition *part) +{ + struct xpc_partition_sn2 *part_sn2 = &part->sn.sn2; + unsigned long irq_flags; + AMO_t *amo = (AMO_t *)__va(part_sn2->remote_amos_page_pa + + (XPC_DEACTIVATE_REQUEST_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); + + /* + * Send activate IRQ to get other side to see that we've set our + * bit in their deactivate request AMO. + */ + xpc_activate_IRQ_send_sn2(part_sn2->remote_amos_page_pa, + cnodeid_to_nasid(0), + part_sn2->activate_IRQ_nasid, + part_sn2->activate_IRQ_phys_cpuid); +} + +static void +xpc_cancel_partition_deactivation_request_sn2(struct xpc_partition *part) +{ + unsigned long irq_flags; + AMO_t *amo = (AMO_t *)__va(part->sn.sn2.remote_amos_page_pa + + (XPC_DEACTIVATE_REQUEST_AMO * sizeof(AMO_t))); + + local_irq_save(irq_flags); + + /* clear bit corresponding to our partid in remote partition's AMO */ + FETCHOP_STORE_OP(TO_AMO((u64)&amo->variable), FETCHOP_AND, + ~(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 int +xpc_partition_deactivation_requested_sn2(short partid) +{ + AMO_t *amo = xpc_vars->amos_page + XPC_DEACTIVATE_REQUEST_AMO; + + /* our partition's AMO variable ANDed with partid mask */ + return (FETCHOP_LOAD_OP(TO_AMO((u64)&amo->variable), FETCHOP_LOAD) & + (1UL << partid)) != 0; } /* @@ -741,6 +817,8 @@ xpc_update_partition_info_sn2(struct xpc u64 remote_vars_pa, struct xpc_vars_sn2 *remote_vars) { + struct xpc_partition_sn2 *part_sn2 = &part->sn.sn2; + part->remote_rp_version = remote_rp_version; dev_dbg(xpc_part, " remote_rp_version = 0x%016x\n", part->remote_rp_version); @@ -752,33 +830,34 @@ xpc_update_partition_info_sn2(struct xpc part->remote_rp_pa = remote_rp_pa; dev_dbg(xpc_part, " remote_rp_pa = 0x%016lx\n", part->remote_rp_pa); - part->remote_vars_pa = remote_vars_pa; + part_sn2->remote_vars_pa = remote_vars_pa; dev_dbg(xpc_part, " remote_vars_pa = 0x%016lx\n", - part->remote_vars_pa); + part_sn2->remote_vars_pa); part->last_heartbeat = remote_vars->heartbeat; dev_dbg(xpc_part, " last_heartbeat = 0x%016lx\n", part->last_heartbeat); - part->remote_vars_part_pa = remote_vars->vars_part_pa; + part_sn2->remote_vars_part_pa = remote_vars->vars_part_pa; dev_dbg(xpc_part, " remote_vars_part_pa = 0x%016lx\n", - part->remote_vars_part_pa); + part_sn2->remote_vars_part_pa); - part->remote_act_nasid = remote_vars->act_nasid; - dev_dbg(xpc_part, " remote_act_nasid = 0x%x\n", - part->remote_act_nasid); + part_sn2->activate_IRQ_nasid = remote_vars->activate_IRQ_nasid; + dev_dbg(xpc_part, " activate_IRQ_nasid = 0x%x\n", + part_sn2->activate_IRQ_nasid); + + part_sn2->activate_IRQ_phys_cpuid = + remote_vars->activate_IRQ_phys_cpuid; + dev_dbg(xpc_part, " activate_IRQ_phys_cpuid = 0x%x\n", + part_sn2->activate_IRQ_phys_cpuid); - part->remote_act_phys_cpuid = remote_vars->act_phys_cpuid; - dev_dbg(xpc_part, " remote_act_phys_cpuid = 0x%x\n", - part->remote_act_phys_cpuid); - - part->remote_amos_page_pa = remote_vars->amos_page_pa; + part_sn2->remote_amos_page_pa = remote_vars->amos_page_pa; dev_dbg(xpc_part, " remote_amos_page_pa = 0x%lx\n", - part->remote_amos_page_pa); + part_sn2->remote_amos_page_pa); - part->remote_vars_version = remote_vars->version; + part_sn2->remote_vars_version = remote_vars->version; dev_dbg(xpc_part, " remote_vars_version = 0x%x\n", - part->remote_vars_version); + part_sn2->remote_vars_version); } /* @@ -807,6 +886,7 @@ xpc_identify_activate_IRQ_req_sn2(int na unsigned long remote_rp_stamp = 0; short partid; struct xpc_partition *part; + struct xpc_partition_sn2 *part_sn2; enum xp_retval ret; /* pull over the reserved page structure */ @@ -822,11 +902,11 @@ xpc_identify_activate_IRQ_req_sn2(int na remote_vars_pa = remote_rp->sn.vars_pa; remote_rp_version = remote_rp->version; - if (XPC_SUPPORTS_RP_STAMP(remote_rp_version)) - remote_rp_stamp = remote_rp->stamp; + remote_rp_stamp = remote_rp->stamp; partid = remote_rp->SAL_partid; part = &xpc_partitions[partid]; + part_sn2 = &part->sn.sn2; /* pull over the cross partition variables */ @@ -834,7 +914,6 @@ xpc_identify_activate_IRQ_req_sn2(int na ret = xpc_get_remote_vars_sn2(remote_vars_pa, remote_vars); if (ret != xpSuccess) { - dev_warn(xpc_part, "unable to get XPC variables from nasid %d, " "which sent interrupt, reason=%d\n", nasid, ret); @@ -855,18 +934,12 @@ xpc_identify_activate_IRQ_req_sn2(int na &remote_rp_stamp, remote_rp_pa, remote_vars_pa, remote_vars); - if (XPC_SUPPORTS_DISENGAGE_REQUEST(part->remote_vars_version)) { - if (xpc_partition_disengage_requested(1UL << partid)) { - /* - * Other side is waiting on us to disengage, - * even though we already have. - */ - return; - } - - } else { - /* other side doesn't support disengage requests */ - xpc_clear_partition_disengage_request(1UL << partid); + if (xpc_partition_deactivation_requested_sn2(partid)) { + /* + * Other side is waiting on us to deactivate even though + * we already have. + */ + return; } xpc_activate_partition(part); @@ -874,93 +947,30 @@ xpc_identify_activate_IRQ_req_sn2(int na } DBUG_ON(part->remote_rp_version == 0); - DBUG_ON(part->remote_vars_version == 0); + DBUG_ON(part_sn2->remote_vars_version == 0); - if (!XPC_SUPPORTS_RP_STAMP(part->remote_rp_version)) { - DBUG_ON(XPC_SUPPORTS_DISENGAGE_REQUEST(part-> - remote_vars_version)); - - if (!XPC_SUPPORTS_RP_STAMP(remote_rp_version)) { - DBUG_ON(XPC_SUPPORTS_DISENGAGE_REQUEST(remote_vars-> - version)); - /* see if the other side rebooted */ - if (part->remote_amos_page_pa == - remote_vars->amos_page_pa && - xpc_hb_allowed(sn_partition_id, - &remote_vars->heartbeating_to_mask)) { - /* doesn't look that way, so ignore the IPI */ - return; - } - } + if (remote_rp_stamp != part->remote_rp_stamp) { - /* - * Other side rebooted and previous XPC didn't support the - * disengage request, so we don't need to do anything special. - */ - - xpc_update_partition_info_sn2(part, remote_rp_version, - &remote_rp_stamp, remote_rp_pa, - remote_vars_pa, remote_vars); - part->reactivate_nasid = nasid; - XPC_DEACTIVATE_PARTITION(part, xpReactivating); - return; - } - - DBUG_ON(!XPC_SUPPORTS_DISENGAGE_REQUEST(part->remote_vars_version)); + /* the other side rebooted */ - if (!XPC_SUPPORTS_RP_STAMP(remote_rp_version)) { - DBUG_ON(!XPC_SUPPORTS_DISENGAGE_REQUEST(remote_vars->version)); - - /* - * Other side rebooted and previous XPC did support the - * disengage request, but the new one doesn't. - */ - - xpc_clear_partition_engaged(1UL << partid); - xpc_clear_partition_disengage_request(1UL << partid); + DBUG_ON(xpc_partition_engaged_sn2(partid)); + DBUG_ON(xpc_partition_deactivation_requested_sn2(partid)); xpc_update_partition_info_sn2(part, remote_rp_version, &remote_rp_stamp, remote_rp_pa, remote_vars_pa, remote_vars); reactivate = 1; - - } else { - DBUG_ON(!XPC_SUPPORTS_DISENGAGE_REQUEST(remote_vars->version)); - - if (remote_rp_stamp != part->remote_rp_stamp) { - - /* - * Other side rebooted and the previous XPC did support - * the disengage request, as does the new one. - */ - - DBUG_ON(xpc_partition_engaged(1UL << partid)); - DBUG_ON(xpc_partition_disengage_requested(1UL << - partid)); - - xpc_update_partition_info_sn2(part, remote_rp_version, - &remote_rp_stamp, - remote_rp_pa, - remote_vars_pa, - remote_vars); - reactivate = 1; - } } - if (part->disengage_request_timeout > 0 && - !xpc_partition_disengaged(part)) { + if (part->disengage_timeout > 0 && !xpc_partition_disengaged(part)) { /* still waiting on other side to disengage from us */ return; } - if (reactivate) { - part->reactivate_nasid = nasid; + if (reactivate) XPC_DEACTIVATE_PARTITION(part, xpReactivating); - - } else if (XPC_SUPPORTS_DISENGAGE_REQUEST(part->remote_vars_version) && - xpc_partition_disengage_requested(1UL << partid)) { + else if (xpc_partition_deactivation_requested_sn2(partid)) XPC_DEACTIVATE_PARTITION(part, xpOtherGoingDown); - } } /* @@ -1038,6 +1048,7 @@ xpc_process_activate_IRQ_rcvd_sn2(int n_ static enum xp_retval xpc_setup_infrastructure_sn2(struct xpc_partition *part) { + struct xpc_partition_sn2 *part_sn2 = &part->sn.sn2; enum xp_retval retval; int ret; int cpuid; @@ -1060,28 +1071,29 @@ xpc_setup_infrastructure_sn2(struct xpc_ /* allocate all the required GET/PUT values */ - part->local_GPs = xpc_kzalloc_cacheline_aligned(XPC_GP_SIZE, - GFP_KERNEL, - &part->local_GPs_base); - if (part->local_GPs == NULL) { + part_sn2->local_GPs = xpc_kzalloc_cacheline_aligned(XPC_GP_SIZE, + GFP_KERNEL, + &part_sn2-> + local_GPs_base); + if (part_sn2->local_GPs == NULL) { dev_err(xpc_chan, "can't get memory for local get/put " "values\n"); retval = xpNoMemory; goto out_1; } - part->remote_GPs = xpc_kzalloc_cacheline_aligned(XPC_GP_SIZE, - GFP_KERNEL, - &part-> - remote_GPs_base); - if (part->remote_GPs == NULL) { + part_sn2->remote_GPs = xpc_kzalloc_cacheline_aligned(XPC_GP_SIZE, + GFP_KERNEL, + &part_sn2-> + remote_GPs_base); + if (part_sn2->remote_GPs == NULL) { dev_err(xpc_chan, "can't get memory for remote get/put " "values\n"); retval = xpNoMemory; goto out_2; } - part->remote_GPs_pa = 0; + part_sn2->remote_GPs_pa = 0; /* allocate all the required open and close args */ @@ -1103,22 +1115,23 @@ xpc_setup_infrastructure_sn2(struct xpc_ goto out_4; } - part->remote_openclose_args_pa = 0; + part_sn2->remote_openclose_args_pa = 0; - part->local_IPI_amo_va = xpc_IPI_init_sn2(partid); + part_sn2->local_IPI_amo_va = xpc_IPI_init_sn2(partid); part->local_IPI_amo = 0; spin_lock_init(&part->IPI_lock); - part->remote_IPI_nasid = 0; - part->remote_IPI_phys_cpuid = 0; - part->remote_IPI_amo_va = NULL; + part_sn2->remote_IPI_nasid = 0; + part_sn2->remote_IPI_phys_cpuid = 0; + part_sn2->remote_IPI_amo_va = NULL; atomic_set(&part->channel_mgr_requests, 1); init_waitqueue_head(&part->channel_mgr_wq); - sprintf(part->IPI_owner, "xpc%02d", partid); - ret = request_irq(SGI_XPC_NOTIFY, xpc_notify_IRQ_handler, IRQF_SHARED, - part->IPI_owner, (void *)(u64)partid); + sprintf(part_sn2->IPI_owner, "xpc%02d", partid); + ret = request_irq(SGI_XPC_NOTIFY, xpc_handle_notify_IRQ_sn2, + IRQF_SHARED, part_sn2->IPI_owner, + (void *)(u64)partid); if (ret != 0) { dev_err(xpc_chan, "can't register NOTIFY IRQ handler, " "errno=%d\n", -ret); @@ -1127,9 +1140,10 @@ xpc_setup_infrastructure_sn2(struct xpc_ } /* Setup a timer to check for dropped IPIs */ - timer = &part->dropped_IPI_timer; + timer = &part_sn2->dropped_notify_IRQ_timer; init_timer(timer); - timer->function = (void (*)(unsigned long))xpc_dropped_IPI_check; + timer->function = + (void (*)(unsigned long))xpc_dropped_notify_IRQ_check_sn2; timer->data = (unsigned long)part; timer->expires = jiffies + XPC_P_DROPPED_IPI_WAIT_INTERVAL; add_timer(timer); @@ -1146,7 +1160,7 @@ xpc_setup_infrastructure_sn2(struct xpc_ ch->number = ch_number; ch->flags = XPC_C_DISCONNECTED; - ch->local_GP = &part->local_GPs[ch_number]; + ch->sn.sn2.local_GP = &part_sn2->local_GPs[ch_number]; ch->local_openclose_args = &part->local_openclose_args[ch_number]; @@ -1158,7 +1172,7 @@ xpc_setup_infrastructure_sn2(struct xpc_ atomic_set(&ch->n_to_notify, 0); spin_lock_init(&ch->lock); - mutex_init(&ch->msg_to_pull_mutex); + mutex_init(&ch->sn.sn2.msg_to_pull_mutex); init_completion(&ch->wdisconnect_wait); atomic_set(&ch->n_on_msg_allocate_wq, 0); @@ -1179,10 +1193,10 @@ xpc_setup_infrastructure_sn2(struct xpc_ * The setting of the magic # indicates that these per partition * specific variables are ready to be used. */ - xpc_vars_part[partid].GPs_pa = __pa(part->local_GPs); + xpc_vars_part[partid].GPs_pa = __pa(part_sn2->local_GPs); xpc_vars_part[partid].openclose_args_pa = __pa(part->local_openclose_args); - xpc_vars_part[partid].IPI_amo_pa = __pa(part->local_IPI_amo_va); + xpc_vars_part[partid].IPI_amo_pa = __pa(part_sn2->local_IPI_amo_va); cpuid = raw_smp_processor_id(); /* any CPU in this partition will do */ xpc_vars_part[partid].IPI_nasid = cpuid_to_nasid(cpuid); xpc_vars_part[partid].IPI_phys_cpuid = cpu_physical_id(cpuid); @@ -1199,11 +1213,11 @@ out_4: kfree(part->local_openclose_args_base); part->local_openclose_args = NULL; out_3: - kfree(part->remote_GPs_base); - part->remote_GPs = NULL; + kfree(part_sn2->remote_GPs_base); + part_sn2->remote_GPs = NULL; out_2: - kfree(part->local_GPs_base); - part->local_GPs = NULL; + kfree(part_sn2->local_GPs_base); + part_sn2->local_GPs = NULL; out_1: kfree(part->channels); part->channels = NULL; @@ -1217,6 +1231,7 @@ out_1: static void xpc_teardown_infrastructure_sn2(struct xpc_partition *part) { + struct xpc_partition_sn2 *part_sn2 = &part->sn.sn2; short partid = XPC_PARTID(part); /* @@ -1248,19 +1263,19 @@ xpc_teardown_infrastructure_sn2(struct x part->setup_state = XPC_P_TORNDOWN; /* in case we've still got outstanding timers registered... */ - del_timer_sync(&part->dropped_IPI_timer); + del_timer_sync(&part_sn2->dropped_notify_IRQ_timer); kfree(part->remote_openclose_args_base); part->remote_openclose_args = NULL; kfree(part->local_openclose_args_base); part->local_openclose_args = NULL; - kfree(part->remote_GPs_base); - part->remote_GPs = NULL; - kfree(part->local_GPs_base); - part->local_GPs = NULL; + kfree(part_sn2->remote_GPs_base); + part_sn2->remote_GPs = NULL; + kfree(part_sn2->local_GPs_base); + part_sn2->local_GPs = NULL; kfree(part->channels); part->channels = NULL; - part->local_IPI_amo_va = NULL; + part_sn2->local_IPI_amo_va = NULL; } /* @@ -1300,6 +1315,7 @@ xpc_pull_remote_cachelines_sn2(struct xp static enum xp_retval xpc_pull_remote_vars_part_sn2(struct xpc_partition *part) { + struct xpc_partition_sn2 *part_sn2 = &part->sn.sn2; u8 buffer[L1_CACHE_BYTES * 2]; struct xpc_vars_part_sn2 *pulled_entry_cacheline = (struct xpc_vars_part_sn2 *)L1_CACHE_ALIGN((u64)buffer); @@ -1310,11 +1326,11 @@ xpc_pull_remote_vars_part_sn2(struct xpc /* pull the cacheline that contains the variables we're interested in */ - DBUG_ON(part->remote_vars_part_pa != - L1_CACHE_ALIGN(part->remote_vars_part_pa)); + DBUG_ON(part_sn2->remote_vars_part_pa != + L1_CACHE_ALIGN(part_sn2->remote_vars_part_pa)); DBUG_ON(sizeof(struct xpc_vars_part_sn2) != L1_CACHE_BYTES / 2); - remote_entry_pa = part->remote_vars_part_pa + + remote_entry_pa = part_sn2->remote_vars_part_pa + sn_partition_id * sizeof(struct xpc_vars_part_sn2); remote_entry_cacheline_pa = (remote_entry_pa & ~(L1_CACHE_BYTES - 1)); @@ -1364,13 +1380,13 @@ xpc_pull_remote_vars_part_sn2(struct xpc /* the variables we imported look to be valid */ - part->remote_GPs_pa = pulled_entry->GPs_pa; - part->remote_openclose_args_pa = + part_sn2->remote_GPs_pa = pulled_entry->GPs_pa; + part_sn2->remote_openclose_args_pa = pulled_entry->openclose_args_pa; - part->remote_IPI_amo_va = + part_sn2->remote_IPI_amo_va = (AMO_t *)__va(pulled_entry->IPI_amo_pa); - part->remote_IPI_nasid = pulled_entry->IPI_nasid; - part->remote_IPI_phys_cpuid = pulled_entry->IPI_phys_cpuid; + part_sn2->remote_IPI_nasid = pulled_entry->IPI_nasid; + part_sn2->remote_IPI_phys_cpuid = pulled_entry->IPI_phys_cpuid; if (part->nchannels > pulled_entry->nchannels) part->nchannels = pulled_entry->nchannels; @@ -1394,6 +1410,7 @@ xpc_pull_remote_vars_part_sn2(struct xpc static enum xp_retval xpc_make_first_contact_sn2(struct xpc_partition *part) { + struct xpc_partition_sn2 *part_sn2 = &part->sn.sn2; enum xp_retval ret; /* @@ -1406,7 +1423,7 @@ xpc_make_first_contact_sn2(struct xpc_pa * we should get the same page for remote_amos_page_pa after module * reloads and system reboots. */ - if (sn_register_xp_addr_region(part->remote_amos_page_pa, + if (sn_register_xp_addr_region(part_sn2->remote_amos_page_pa, PAGE_SIZE, 1) < 0) { dev_warn(xpc_part, "xpc_activating(%d) failed to register " "xp_addr region\n", XPC_PARTID(part)); @@ -1416,7 +1433,14 @@ xpc_make_first_contact_sn2(struct xpc_pa return ret; } - xpc_IPI_send_activated(part); + /* + * Send activate IRQ to get other side to activate if they've not + * already begun to do so. + */ + xpc_activate_IRQ_send_sn2(part_sn2->remote_amos_page_pa, + cnodeid_to_nasid(0), + part_sn2->activate_IRQ_nasid, + part_sn2->activate_IRQ_phys_cpuid); while ((ret = xpc_pull_remote_vars_part_sn2(part)) != xpSuccess) { if (ret != xpRetry) { @@ -1443,6 +1467,7 @@ xpc_make_first_contact_sn2(struct xpc_pa static u64 xpc_get_IPI_flags_sn2(struct xpc_partition *part) { + struct xpc_partition_sn2 *part_sn2 = &part->sn.sn2; unsigned long irq_flags; u64 IPI_amo; enum xp_retval ret; @@ -1459,9 +1484,9 @@ xpc_get_IPI_flags_sn2(struct xpc_partiti spin_unlock_irqrestore(&part->IPI_lock, irq_flags); if (XPC_ANY_OPENCLOSE_IPI_FLAGS_SET(IPI_amo)) { - ret = xpc_pull_remote_cachelines_sn2(part, - part->remote_openclose_args, - (void *)part-> + ret = xpc_pull_remote_cachelines_sn2(part, part-> + remote_openclose_args, + (void *)part_sn2-> remote_openclose_args_pa, XPC_OPENCLOSE_ARGS_SIZE); if (ret != xpSuccess) { @@ -1477,8 +1502,8 @@ xpc_get_IPI_flags_sn2(struct xpc_partiti } if (XPC_ANY_MSG_IPI_FLAGS_SET(IPI_amo)) { - ret = xpc_pull_remote_cachelines_sn2(part, part->remote_GPs, - (void *)part->remote_GPs_pa, + ret = xpc_pull_remote_cachelines_sn2(part, part_sn2->remote_GPs, + (void *)part_sn2->remote_GPs_pa, XPC_GP_SIZE); if (ret != xpSuccess) { XPC_DEACTIVATE_PARTITION(part, ret); @@ -1494,28 +1519,220 @@ xpc_get_IPI_flags_sn2(struct xpc_partiti return IPI_amo; } +/* + * Notify those who wanted to be notified upon delivery of their message. + */ +static void +xpc_notify_senders_sn2(struct xpc_channel *ch, enum xp_retval reason, s64 put) +{ + struct xpc_notify *notify; + u8 notify_type; + s64 get = ch->sn.sn2.w_remote_GP.get - 1; + + while (++get < put && atomic_read(&ch->n_to_notify) > 0) { + + notify = &ch->notify_queue[get % ch->local_nentries]; + + /* + * See if the notify entry indicates it was associated with + * a message who's sender wants to be notified. It is possible + * that it is, but someone else is doing or has done the + * notification. + */ + notify_type = notify->type; + if (notify_type == 0 || + cmpxchg(¬ify->type, notify_type, 0) != notify_type) { + continue; + } + + DBUG_ON(notify_type != XPC_N_CALL); + + atomic_dec(&ch->n_to_notify); + + if (notify->func != NULL) { + dev_dbg(xpc_chan, "notify->func() called, notify=0x%p, " + "msg_number=%ld, partid=%d, channel=%d\n", + (void *)notify, get, ch->partid, ch->number); + + notify->func(reason, ch->partid, ch->number, + notify->key); + + dev_dbg(xpc_chan, "notify->func() returned, " + "notify=0x%p, msg_number=%ld, partid=%d, " + "channel=%d\n", (void *)notify, get, + ch->partid, ch->number); + } + } +} + +static void +xpc_notify_senders_of_disconnect_sn2(struct xpc_channel *ch) +{ + xpc_notify_senders_sn2(ch, ch->reason, ch->sn.sn2.w_local_GP.put); +} + +/* + * Clear some of the msg flags in the local message queue. + */ +static inline void +xpc_clear_local_msgqueue_flags_sn2(struct xpc_channel *ch) +{ + struct xpc_channel_sn2 *ch_sn2 = &ch->sn.sn2; + struct xpc_msg *msg; + s64 get; + + get = ch_sn2->w_remote_GP.get; + do { + msg = (struct xpc_msg *)((u64)ch->local_msgqueue + + (get % ch->local_nentries) * + ch->msg_size); + msg->flags = 0; + } while (++get < ch_sn2->remote_GP.get); +} + +/* + * Clear some of the msg flags in the remote message queue. + */ +static inline void +xpc_clear_remote_msgqueue_flags_sn2(struct xpc_channel *ch) +{ + struct xpc_channel_sn2 *ch_sn2 = &ch->sn.sn2; + struct xpc_msg *msg; + s64 put; + + put = ch_sn2->w_remote_GP.put; + do { + msg = (struct xpc_msg *)((u64)ch->remote_msgqueue + + (put % ch->remote_nentries) * + ch->msg_size); + msg->flags = 0; + } while (++put < ch_sn2->remote_GP.put); +} + +static void +xpc_process_msg_IPI_sn2(struct xpc_partition *part, int ch_number) +{ + struct xpc_channel *ch = &part->channels[ch_number]; + struct xpc_channel_sn2 *ch_sn2 = &ch->sn.sn2; + int nmsgs_sent; + + ch_sn2->remote_GP = part->sn.sn2.remote_GPs[ch_number]; + + /* See what, if anything, has changed for each connected channel */ + + xpc_msgqueue_ref(ch); + + if (ch_sn2->w_remote_GP.get == ch_sn2->remote_GP.get && + ch_sn2->w_remote_GP.put == ch_sn2->remote_GP.put) { + /* nothing changed since GPs were last pulled */ + xpc_msgqueue_deref(ch); + return; + } + + if (!(ch->flags & XPC_C_CONNECTED)) { + xpc_msgqueue_deref(ch); + return; + } + + /* + * First check to see if messages recently sent by us have been + * received by the other side. (The remote GET value will have + * changed since we last looked at it.) + */ + + if (ch_sn2->w_remote_GP.get != ch_sn2->remote_GP.get) { + + /* + * We need to notify any senders that want to be notified + * that their sent messages have been received by their + * intended recipients. We need to do this before updating + * w_remote_GP.get so that we don't allocate the same message + * queue entries prematurely (see xpc_allocate_msg()). + */ + if (atomic_read(&ch->n_to_notify) > 0) { + /* + * Notify senders that messages sent have been + * received and delivered by the other side. + */ + xpc_notify_senders_sn2(ch, xpMsgDelivered, + ch_sn2->remote_GP.get); + } + + /* + * Clear msg->flags in previously sent messages, so that + * they're ready for xpc_allocate_msg(). + */ + xpc_clear_local_msgqueue_flags_sn2(ch); + + ch_sn2->w_remote_GP.get = ch_sn2->remote_GP.get; + + dev_dbg(xpc_chan, "w_remote_GP.get changed to %ld, partid=%d, " + "channel=%d\n", ch_sn2->w_remote_GP.get, ch->partid, + ch->number); + + /* + * If anyone was waiting for message queue entries to become + * available, wake them up. + */ + if (atomic_read(&ch->n_on_msg_allocate_wq) > 0) + wake_up(&ch->msg_allocate_wq); + } + + /* + * Now check for newly sent messages by the other side. (The remote + * PUT value will have changed since we last looked at it.) + */ + + if (ch_sn2->w_remote_GP.put != ch_sn2->remote_GP.put) { + /* + * Clear msg->flags in previously received messages, so that + * they're ready for xpc_get_deliverable_msg(). + */ + xpc_clear_remote_msgqueue_flags_sn2(ch); + + ch_sn2->w_remote_GP.put = ch_sn2->remote_GP.put; + + dev_dbg(xpc_chan, "w_remote_GP.put changed to %ld, partid=%d, " + "channel=%d\n", ch_sn2->w_remote_GP.put, ch->partid, + ch->number); + + nmsgs_sent = ch_sn2->w_remote_GP.put - ch_sn2->w_local_GP.get; + if (nmsgs_sent > 0) { + dev_dbg(xpc_chan, "msgs waiting to be copied and " + "delivered=%d, partid=%d, channel=%d\n", + nmsgs_sent, ch->partid, ch->number); + + if (ch->flags & XPC_C_CONNECTEDCALLOUT_MADE) + xpc_activate_kthreads(ch, nmsgs_sent); + } + } + + xpc_msgqueue_deref(ch); +} + static struct xpc_msg * xpc_pull_remote_msg_sn2(struct xpc_channel *ch, s64 get) { struct xpc_partition *part = &xpc_partitions[ch->partid]; + struct xpc_channel_sn2 *ch_sn2 = &ch->sn.sn2; struct xpc_msg *remote_msg, *msg; u32 msg_index, nmsgs; u64 msg_offset; enum xp_retval ret; - if (mutex_lock_interruptible(&ch->msg_to_pull_mutex) != 0) { + if (mutex_lock_interruptible(&ch_sn2->msg_to_pull_mutex) != 0) { /* we were interrupted by a signal */ return NULL; } - while (get >= ch->next_msg_to_pull) { + while (get >= ch_sn2->next_msg_to_pull) { /* pull as many messages as are ready and able to be pulled */ - msg_index = ch->next_msg_to_pull % ch->remote_nentries; + msg_index = ch_sn2->next_msg_to_pull % ch->remote_nentries; - DBUG_ON(ch->next_msg_to_pull >= ch->w_remote_GP.put); - nmsgs = ch->w_remote_GP.put - ch->next_msg_to_pull; + DBUG_ON(ch_sn2->next_msg_to_pull >= ch_sn2->w_remote_GP.put); + nmsgs = ch_sn2->w_remote_GP.put - ch_sn2->next_msg_to_pull; if (msg_index + nmsgs > ch->remote_nentries) { /* ignore the ones that wrap the msg queue for now */ nmsgs = ch->remote_nentries - msg_index; @@ -1532,19 +1749,19 @@ xpc_pull_remote_msg_sn2(struct xpc_chann dev_dbg(xpc_chan, "failed to pull %d msgs starting with" " msg %ld from partition %d, channel=%d, " - "ret=%d\n", nmsgs, ch->next_msg_to_pull, + "ret=%d\n", nmsgs, ch_sn2->next_msg_to_pull, ch->partid, ch->number, ret); XPC_DEACTIVATE_PARTITION(part, ret); - mutex_unlock(&ch->msg_to_pull_mutex); + mutex_unlock(&ch_sn2->msg_to_pull_mutex); return NULL; } - ch->next_msg_to_pull += nmsgs; + ch_sn2->next_msg_to_pull += nmsgs; } - mutex_unlock(&ch->msg_to_pull_mutex); + mutex_unlock(&ch_sn2->msg_to_pull_mutex); /* return the message we were looking for */ msg_offset = (get % ch->remote_nentries) * ch->msg_size; @@ -1553,12 +1770,19 @@ xpc_pull_remote_msg_sn2(struct xpc_chann return msg; } +static int +xpc_n_of_deliverable_msgs_sn2(struct xpc_channel *ch) +{ + return ch->sn.sn2.w_remote_GP.put - ch->sn.sn2.w_local_GP.get; +} + /* * Get a message to be delivered. */ static struct xpc_msg * xpc_get_deliverable_msg_sn2(struct xpc_channel *ch) { + struct xpc_channel_sn2 *ch_sn2 = &ch->sn.sn2; struct xpc_msg *msg = NULL; s64 get; @@ -1566,9 +1790,9 @@ xpc_get_deliverable_msg_sn2(struct xpc_c if (ch->flags & XPC_C_DISCONNECTING) break; - get = ch->w_local_GP.get; + get = ch_sn2->w_local_GP.get; rmb(); /* guarantee that .get loads before .put */ - if (get == ch->w_remote_GP.put) + if (get == ch_sn2->w_remote_GP.put) break; /* There are messages waiting to be pulled and delivered. @@ -1578,7 +1802,7 @@ xpc_get_deliverable_msg_sn2(struct xpc_c * to try again for the next one. */ - if (cmpxchg(&ch->w_local_GP.get, get, get + 1) == get) { + if (cmpxchg(&ch_sn2->w_local_GP.get, get, get + 1) == get) { /* we got the entry referenced by get */ dev_dbg(xpc_chan, "w_local_GP.get changed to %ld, " @@ -1609,6 +1833,7 @@ xpc_get_deliverable_msg_sn2(struct xpc_c static void xpc_send_msgs_sn2(struct xpc_channel *ch, s64 initial_put) { + struct xpc_channel_sn2 *ch_sn2 = &ch->sn.sn2; struct xpc_msg *msg; s64 put = initial_put + 1; int send_IPI = 0; @@ -1616,7 +1841,7 @@ xpc_send_msgs_sn2(struct xpc_channel *ch while (1) { while (1) { - if (put == ch->w_local_GP.put) + if (put == ch_sn2->w_local_GP.put) break; msg = (struct xpc_msg *)((u64)ch->local_msgqueue + @@ -1634,10 +1859,10 @@ xpc_send_msgs_sn2(struct xpc_channel *ch break; } - if (cmpxchg_rel(&ch->local_GP->put, initial_put, put) != + if (cmpxchg_rel(&ch_sn2->local_GP->put, initial_put, put) != initial_put) { /* someone else beat us to it */ - DBUG_ON(ch->local_GP->put < initial_put); + DBUG_ON(ch_sn2->local_GP->put < initial_put); break; } @@ -1657,7 +1882,7 @@ xpc_send_msgs_sn2(struct xpc_channel *ch } if (send_IPI) - xpc_IPI_send_msgrequest_sn2(ch); + xpc_send_channel_msgrequest_sn2(ch); } /* @@ -1668,6 +1893,7 @@ static enum xp_retval xpc_allocate_msg_sn2(struct xpc_channel *ch, u32 flags, struct xpc_msg **address_of_msg) { + struct xpc_channel_sn2 *ch_sn2 = &ch->sn.sn2; struct xpc_msg *msg; enum xp_retval ret; s64 put; @@ -1681,9 +1907,9 @@ xpc_allocate_msg_sn2(struct xpc_channel while (1) { - put = ch->w_local_GP.put; + put = ch_sn2->w_local_GP.put; rmb(); /* guarantee that .put loads before .get */ - if (put - ch->w_remote_GP.get < ch->local_nentries) { + if (put - ch_sn2->w_remote_GP.get < ch->local_nentries) { /* There are available message entries. We need to try * to secure one for ourselves. We'll do this by trying @@ -1691,7 +1917,8 @@ xpc_allocate_msg_sn2(struct xpc_channel * doesn't beat us to it. If they do, we'll have to * try again. */ - if (cmpxchg(&ch->w_local_GP.put, put, put + 1) == put) { + if (cmpxchg(&ch_sn2->w_local_GP.put, put, put + 1) == + put) { /* we got the entry referenced by put */ break; } @@ -1708,7 +1935,7 @@ xpc_allocate_msg_sn2(struct xpc_channel * GP values as if an IPI was sent by the other side. */ if (ret == xpTimeout) - xpc_IPI_send_local_msgrequest_sn2(ch); + xpc_send_channel_local_msgrequest_sn2(ch); if (flags & XPC_NOWAIT) return xpNoWait; @@ -1810,13 +2037,13 @@ xpc_send_msg_sn2(struct xpc_channel *ch, /* * The preceding store of msg->flags must occur before the following - * load of ch->local_GP->put. + * load of local_GP->put. */ mb(); /* see if the message is next in line to be sent, if so send it */ - put = ch->local_GP->put; + put = ch->sn.sn2.local_GP->put; if (put == msg_number) xpc_send_msgs_sn2(ch, put); @@ -1833,6 +2060,7 @@ out_1: static void xpc_acknowledge_msgs_sn2(struct xpc_channel *ch, s64 initial_get, u8 msg_flags) { + struct xpc_channel_sn2 *ch_sn2 = &ch->sn.sn2; struct xpc_msg *msg; s64 get = initial_get + 1; int send_IPI = 0; @@ -1840,7 +2068,7 @@ xpc_acknowledge_msgs_sn2(struct xpc_chan while (1) { while (1) { - if (get == ch->w_local_GP.get) + if (get == ch_sn2->w_local_GP.get) break; msg = (struct xpc_msg *)((u64)ch->remote_msgqueue + @@ -1859,10 +2087,10 @@ xpc_acknowledge_msgs_sn2(struct xpc_chan break; } - if (cmpxchg_rel(&ch->local_GP->get, initial_get, get) != + if (cmpxchg_rel(&ch_sn2->local_GP->get, initial_get, get) != initial_get) { /* someone else beat us to it */ - DBUG_ON(ch->local_GP->get <= initial_get); + DBUG_ON(ch_sn2->local_GP->get <= initial_get); break; } @@ -1882,7 +2110,7 @@ xpc_acknowledge_msgs_sn2(struct xpc_chan } if (send_IPI) - xpc_IPI_send_msgrequest_sn2(ch); + xpc_send_channel_msgrequest_sn2(ch); } static void @@ -1902,7 +2130,7 @@ xpc_received_msg_sn2(struct xpc_channel /* * The preceding store of msg->flags must occur before the following - * load of ch->local_GP->get. + * load of local_GP->get. */ mb(); @@ -1910,7 +2138,7 @@ xpc_received_msg_sn2(struct xpc_channel * See if this message is next in line to be acknowledged as having * been delivered. */ - get = ch->local_GP->get; + get = ch->sn.sn2.local_GP->get; if (get == msg_number) xpc_acknowledge_msgs_sn2(ch, get, msg->flags); } @@ -1928,36 +2156,35 @@ xpc_init_sn2(void) xpc_heartbeat_exit = xpc_heartbeat_exit_sn2; xpc_check_remote_hb = xpc_check_remote_hb_sn2; - xpc_initiate_partition_activation = - xpc_initiate_partition_activation_sn2; + xpc_request_partition_activation = xpc_request_partition_activation_sn2; + xpc_request_partition_reactivation = + xpc_request_partition_reactivation_sn2; + xpc_request_partition_deactivation = + xpc_request_partition_deactivation_sn2; + xpc_cancel_partition_deactivation_request = + xpc_cancel_partition_deactivation_request_sn2; + xpc_process_activate_IRQ_rcvd = xpc_process_activate_IRQ_rcvd_sn2; xpc_setup_infrastructure = xpc_setup_infrastructure_sn2; xpc_teardown_infrastructure = xpc_teardown_infrastructure_sn2; xpc_make_first_contact = xpc_make_first_contact_sn2; xpc_get_IPI_flags = xpc_get_IPI_flags_sn2; + xpc_notify_senders_of_disconnect = xpc_notify_senders_of_disconnect_sn2; + xpc_process_msg_IPI = xpc_process_msg_IPI_sn2; + xpc_n_of_deliverable_msgs = xpc_n_of_deliverable_msgs_sn2; xpc_get_deliverable_msg = xpc_get_deliverable_msg_sn2; - xpc_mark_partition_engaged = xpc_mark_partition_engaged_sn2; - xpc_mark_partition_disengaged = xpc_mark_partition_disengaged_sn2; - xpc_request_partition_disengage = xpc_request_partition_disengage_sn2; - xpc_cancel_partition_disengage_request = - xpc_cancel_partition_disengage_request_sn2; + xpc_indicate_partition_engaged = xpc_indicate_partition_engaged_sn2; xpc_partition_engaged = xpc_partition_engaged_sn2; - xpc_partition_disengage_requested = - xpc_partition_disengage_requested_sn2; - xpc_clear_partition_engaged = xpc_clear_partition_engaged_sn2; - xpc_clear_partition_disengage_request = - xpc_clear_partition_disengage_request_sn2; - - xpc_IPI_send_local_activate = xpc_IPI_send_local_activate_sn2; - xpc_IPI_send_activated = xpc_IPI_send_activated_sn2; - xpc_IPI_send_local_reactivate = xpc_IPI_send_local_reactivate_sn2; - xpc_IPI_send_disengage = xpc_IPI_send_disengage_sn2; - - xpc_IPI_send_closerequest = xpc_IPI_send_closerequest_sn2; - xpc_IPI_send_closereply = xpc_IPI_send_closereply_sn2; - xpc_IPI_send_openrequest = xpc_IPI_send_openrequest_sn2; - xpc_IPI_send_openreply = xpc_IPI_send_openreply_sn2; + xpc_any_partition_engaged = xpc_any_partition_engaged_sn2; + xpc_indicate_partition_disengaged = + xpc_indicate_partition_disengaged_sn2; + xpc_assume_partition_disengaged = xpc_assume_partition_disengaged_sn2; + + xpc_send_channel_closerequest = xpc_send_channel_closerequest_sn2; + xpc_send_channel_closereply = xpc_send_channel_closereply_sn2; + xpc_send_channel_openrequest = xpc_send_channel_openrequest_sn2; + xpc_send_channel_openreply = xpc_send_channel_openreply_sn2; xpc_send_msg = xpc_send_msg_sn2; xpc_received_msg = xpc_received_msg_sn2; Index: linux-2.6/drivers/misc/sgi-xp/xpc_partition.c =================================================================== --- linux-2.6.orig/drivers/misc/sgi-xp/xpc_partition.c 2008-06-05 12:51:17.127801364 -0500 +++ linux-2.6/drivers/misc/sgi-xp/xpc_partition.c 2008-06-06 08:10:50.969262778 -0500 @@ -242,7 +242,7 @@ xpc_get_remote_rp(int nasid, u64 *discov return xpBadVersion; } - /* check that both local and remote partids are valid for each side */ + /* check that both remote and local partids are valid for each side */ if (remote_rp->SAL_partid < 0 || remote_rp->SAL_partid >= xp_max_npartitions || remote_rp->max_npartitions <= sn_partition_id) { @@ -256,8 +256,9 @@ xpc_get_remote_rp(int nasid, u64 *discov } /* - * See if the other side has responded to a partition disengage request - * from us. + * See if the other side has responded to a partition deactivate request + * from us. Though we requested the remote partition to deactivate with regard + * to us, we really only need to wait for the other side to disengage from us. */ int xpc_partition_disengaged(struct xpc_partition *part) @@ -265,41 +266,37 @@ xpc_partition_disengaged(struct xpc_part short partid = XPC_PARTID(part); int disengaged; - disengaged = (xpc_partition_engaged(1UL << partid) == 0); - if (part->disengage_request_timeout) { + disengaged = !xpc_partition_engaged(partid); + if (part->disengage_timeout) { if (!disengaged) { - if (time_is_after_jiffies(part-> - disengage_request_timeout)) { + if (time_is_after_jiffies(part->disengage_timeout)) { /* timelimit hasn't been reached yet */ return 0; } /* - * Other side hasn't responded to our disengage + * Other side hasn't responded to our deactivate * request in a timely fashion, so assume it's dead. */ - dev_info(xpc_part, "disengage from remote partition %d " - "timed out\n", partid); - xpc_disengage_request_timedout = 1; - xpc_clear_partition_engaged(1UL << partid); + dev_info(xpc_part, "deactivate request to remote " + "partition %d timed out\n", partid); + xpc_disengage_timedout = 1; + xpc_assume_partition_disengaged(partid); disengaged = 1; } - part->disengage_request_timeout = 0; + part->disengage_timeout = 0; /* cancel the timer function, provided it's not us */ - if (!in_interrupt()) { - del_singleshot_timer_sync(&part-> - disengage_request_timer); - } + if (!in_interrupt()) + del_singleshot_timer_sync(&part->disengage_timer); DBUG_ON(part->act_state != XPC_P_DEACTIVATING && part->act_state != XPC_P_INACTIVE); if (part->act_state != XPC_P_INACTIVE) xpc_wakeup_channel_mgr(part); - if (XPC_SUPPORTS_DISENGAGE_REQUEST(part->remote_vars_version)) - xpc_cancel_partition_disengage_request(part); + xpc_cancel_partition_deactivation_request(part); } return disengaged; } @@ -329,7 +326,7 @@ xpc_mark_partition_active(struct xpc_par } /* - * Notify XPC that the partition is down. + * Start the process of deactivating the specified partition. */ void xpc_deactivate_partition(const int line, struct xpc_partition *part, @@ -344,7 +341,7 @@ xpc_deactivate_partition(const int line, spin_unlock_irqrestore(&part->act_lock, irq_flags); if (reason == xpReactivating) { /* we interrupt ourselves to reactivate partition */ - xpc_IPI_send_local_reactivate(part->reactivate_nasid); + xpc_request_partition_reactivation(part); } return; } @@ -362,17 +359,13 @@ xpc_deactivate_partition(const int line, spin_unlock_irqrestore(&part->act_lock, irq_flags); - if (XPC_SUPPORTS_DISENGAGE_REQUEST(part->remote_vars_version)) { - xpc_request_partition_disengage(part); - xpc_IPI_send_disengage(part); - - /* set a timelimit on the disengage request */ - part->disengage_request_timeout = jiffies + - (xpc_disengage_request_timelimit * HZ); - part->disengage_request_timer.expires = - part->disengage_request_timeout; - add_timer(&part->disengage_request_timer); - } + /* ask remote partition to deactivate with regard to us */ + xpc_request_partition_deactivation(part); + + /* set a timelimit on the disengage phase of the deactivation request */ + part->disengage_timeout = jiffies + (xpc_disengage_timelimit * HZ); + part->disengage_timer.expires = part->disengage_timeout; + add_timer(&part->disengage_timer); dev_dbg(xpc_part, "bringing partition %d down, reason = %d\n", XPC_PARTID(part), reason); @@ -505,8 +498,8 @@ xpc_discovery(void) continue; } - xpc_initiate_partition_activation(remote_rp, - remote_rp_pa, nasid); + xpc_request_partition_activation(remote_rp, + remote_rp_pa, nasid); } } Index: linux-2.6/drivers/misc/sgi-xp/xpc_uv.c =================================================================== --- linux-2.6.orig/drivers/misc/sgi-xp/xpc_uv.c 2008-06-05 12:51:16.767756403 -0500 +++ linux-2.6/drivers/misc/sgi-xp/xpc_uv.c 2008-06-06 08:08:28.700425233 -0500 @@ -63,8 +63,8 @@ xpc_heartbeat_exit_uv(void) } static void -xpc_initiate_partition_activation_uv(struct xpc_rsvd_page *remote_rp, - u64 remote_rp_pa, int nasid) +xpc_request_partition_activation_uv(struct xpc_rsvd_page *remote_rp, + u64 remote_rp_pa, int nasid) { short partid = remote_rp->SAL_partid; struct xpc_partition *part = &xpc_partitions[partid]; @@ -78,6 +78,12 @@ xpc_initiate_partition_activation_uv(str xpc_IPI_send_local_activate_uv(part); } +static void +xpc_request_partition_reactivation_uv(struct xpc_partition *part) +{ + xpc_IPI_send_local_activate_uv(part); +} + /* * Setup the infrastructure necessary to support XPartition Communication * between the specified remote partition and the local one. @@ -128,8 +134,9 @@ xpc_init_uv(void) xpc_increment_heartbeat = xpc_increment_heartbeat_uv; xpc_heartbeat_init = xpc_heartbeat_init_uv; xpc_heartbeat_exit = xpc_heartbeat_exit_uv; - xpc_initiate_partition_activation = - xpc_initiate_partition_activation_uv; + xpc_request_partition_activation = xpc_request_partition_activation_uv; + xpc_request_partition_reactivation = + xpc_request_partition_reactivation_uv; xpc_setup_infrastructure = xpc_setup_infrastructure_uv; xpc_teardown_infrastructure = xpc_teardown_infrastructure_uv; xpc_make_first_contact = xpc_make_first_contact_uv; -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/