diff options
Diffstat (limited to 'drivers/infiniband/hw/ehca')
| -rw-r--r-- | drivers/infiniband/hw/ehca/Kconfig | 8 | ||||
| -rw-r--r-- | drivers/infiniband/hw/ehca/ehca_classes.h | 26 | ||||
| -rw-r--r-- | drivers/infiniband/hw/ehca/ehca_cq.c | 16 | ||||
| -rw-r--r-- | drivers/infiniband/hw/ehca/ehca_eq.c | 1 | ||||
| -rw-r--r-- | drivers/infiniband/hw/ehca/ehca_hca.c | 58 | ||||
| -rw-r--r-- | drivers/infiniband/hw/ehca/ehca_irq.c | 336 | ||||
| -rw-r--r-- | drivers/infiniband/hw/ehca/ehca_irq.h | 1 | ||||
| -rw-r--r-- | drivers/infiniband/hw/ehca/ehca_main.c | 37 | ||||
| -rw-r--r-- | drivers/infiniband/hw/ehca/hcp_if.c | 24 | ||||
| -rw-r--r-- | drivers/infiniband/hw/ehca/hcp_if.h | 4 | ||||
| -rw-r--r-- | drivers/infiniband/hw/ehca/ipz_pt_fn.h | 11 |
11 files changed, 365 insertions, 157 deletions
diff --git a/drivers/infiniband/hw/ehca/Kconfig b/drivers/infiniband/hw/ehca/Kconfig index 727b10d89686..1a854598e0e6 100644 --- a/drivers/infiniband/hw/ehca/Kconfig +++ b/drivers/infiniband/hw/ehca/Kconfig @@ -7,11 +7,3 @@ config INFINIBAND_EHCA To compile the driver as a module, choose M here. The module will be called ib_ehca. -config INFINIBAND_EHCA_SCALING - bool "Scaling support (EXPERIMENTAL)" - depends on IBMEBUS && INFINIBAND_EHCA && HOTPLUG_CPU && EXPERIMENTAL - default y - ---help--- - eHCA scaling support schedules the CQ callbacks to different CPUs. - - To enable this feature choose Y here. diff --git a/drivers/infiniband/hw/ehca/ehca_classes.h b/drivers/infiniband/hw/ehca/ehca_classes.h index cf95ee474b0f..10fb8fbafa0c 100644 --- a/drivers/infiniband/hw/ehca/ehca_classes.h +++ b/drivers/infiniband/hw/ehca/ehca_classes.h @@ -42,8 +42,6 @@ #ifndef __EHCA_CLASSES_H__ #define __EHCA_CLASSES_H__ -#include "ehca_classes.h" -#include "ipz_pt_fn.h" struct ehca_module; struct ehca_qp; @@ -54,15 +52,25 @@ struct ehca_mw; struct ehca_pd; struct ehca_av; -#ifdef CONFIG_PPC64 -#include "ehca_classes_pSeries.h" -#endif +#include <linux/wait.h> #include <rdma/ib_verbs.h> #include <rdma/ib_user_verbs.h> +#ifdef CONFIG_PPC64 +#include "ehca_classes_pSeries.h" +#endif +#include "ipz_pt_fn.h" +#include "ehca_qes.h" #include "ehca_irq.h" +#define EHCA_EQE_CACHE_SIZE 20 + +struct ehca_eqe_cache_entry { + struct ehca_eqe *eqe; + struct ehca_cq *cq; +}; + struct ehca_eq { u32 length; struct ipz_queue ipz_queue; @@ -74,6 +82,8 @@ struct ehca_eq { spinlock_t spinlock; struct tasklet_struct interrupt_task; u32 ist; + spinlock_t irq_spinlock; + struct ehca_eqe_cache_entry eqe_cache[EHCA_EQE_CACHE_SIZE]; }; struct ehca_sport { @@ -96,6 +106,7 @@ struct ehca_shca { struct ehca_mr *maxmr; struct ehca_pd *pd; struct h_galpas galpas; + struct mutex modify_mutex; }; struct ehca_pd { @@ -145,7 +156,9 @@ struct ehca_cq { spinlock_t cb_lock; struct hlist_head qp_hashtab[QP_HASHTAB_LEN]; struct list_head entry; - u32 nr_callbacks; + u32 nr_callbacks; /* #events assigned to cpu by scaling code */ + u32 nr_events; /* #events seen */ + wait_queue_head_t wait_completion; spinlock_t task_lock; u32 ownpid; /* mmap counter for resources mapped into user space */ @@ -269,6 +282,7 @@ extern struct idr ehca_cq_idr; extern int ehca_static_rate; extern int ehca_port_act_time; extern int ehca_use_hp_mr; +extern int ehca_scaling_code; struct ipzu_queue_resp { u32 qe_size; /* queue entry size */ diff --git a/drivers/infiniband/hw/ehca/ehca_cq.c b/drivers/infiniband/hw/ehca/ehca_cq.c index 6ebfa27e4e16..e2cdc1a16fe9 100644 --- a/drivers/infiniband/hw/ehca/ehca_cq.c +++ b/drivers/infiniband/hw/ehca/ehca_cq.c @@ -146,6 +146,7 @@ struct ib_cq *ehca_create_cq(struct ib_device *device, int cqe, spin_lock_init(&my_cq->spinlock); spin_lock_init(&my_cq->cb_lock); spin_lock_init(&my_cq->task_lock); + init_waitqueue_head(&my_cq->wait_completion); my_cq->ownpid = current->tgid; cq = &my_cq->ib_cq; @@ -302,6 +303,16 @@ create_cq_exit1: return cq; } +static int get_cq_nr_events(struct ehca_cq *my_cq) +{ + int ret; + unsigned long flags; + spin_lock_irqsave(&ehca_cq_idr_lock, flags); + ret = my_cq->nr_events; + spin_unlock_irqrestore(&ehca_cq_idr_lock, flags); + return ret; +} + int ehca_destroy_cq(struct ib_cq *cq) { u64 h_ret; @@ -329,10 +340,11 @@ int ehca_destroy_cq(struct ib_cq *cq) } spin_lock_irqsave(&ehca_cq_idr_lock, flags); - while (my_cq->nr_callbacks) { + while (my_cq->nr_events) { spin_unlock_irqrestore(&ehca_cq_idr_lock, flags); - yield(); + wait_event(my_cq->wait_completion, !get_cq_nr_events(my_cq)); spin_lock_irqsave(&ehca_cq_idr_lock, flags); + /* recheck nr_events to assure no cqe has just arrived */ } idr_remove(&ehca_cq_idr, my_cq->token); diff --git a/drivers/infiniband/hw/ehca/ehca_eq.c b/drivers/infiniband/hw/ehca/ehca_eq.c index 24ceab0bae4a..4961eb88827c 100644 --- a/drivers/infiniband/hw/ehca/ehca_eq.c +++ b/drivers/infiniband/hw/ehca/ehca_eq.c @@ -61,6 +61,7 @@ int ehca_create_eq(struct ehca_shca *shca, struct ib_device *ib_dev = &shca->ib_device; spin_lock_init(&eq->spinlock); + spin_lock_init(&eq->irq_spinlock); eq->is_initialized = 0; if (type != EHCA_EQ && type != EHCA_NEQ) { diff --git a/drivers/infiniband/hw/ehca/ehca_hca.c b/drivers/infiniband/hw/ehca/ehca_hca.c index b7be950ab47c..32b55a4f0e5b 100644 --- a/drivers/infiniband/hw/ehca/ehca_hca.c +++ b/drivers/infiniband/hw/ehca/ehca_hca.c @@ -147,6 +147,7 @@ int ehca_query_port(struct ib_device *ibdev, break; } + props->port_cap_flags = rblock->capability_mask; props->gid_tbl_len = rblock->gid_tbl_len; props->max_msg_sz = rblock->max_msg_sz; props->bad_pkey_cntr = rblock->bad_pkey_cntr; @@ -162,6 +163,9 @@ int ehca_query_port(struct ib_device *ibdev, props->active_width = IB_WIDTH_12X; props->active_speed = 0x1; + /* at the moment (logical) link state is always LINK_UP */ + props->phys_state = 0x5; + query_port1: ehca_free_fw_ctrlblock(rblock); @@ -233,10 +237,60 @@ query_gid1: return ret; } +const u32 allowed_port_caps = ( + IB_PORT_SM | IB_PORT_LED_INFO_SUP | IB_PORT_CM_SUP | + IB_PORT_SNMP_TUNNEL_SUP | IB_PORT_DEVICE_MGMT_SUP | + IB_PORT_VENDOR_CLASS_SUP); + int ehca_modify_port(struct ib_device *ibdev, u8 port, int port_modify_mask, struct ib_port_modify *props) { - /* Not implemented yet */ - return -EFAULT; + int ret = 0; + struct ehca_shca *shca = container_of(ibdev, struct ehca_shca, ib_device); + struct hipz_query_port *rblock; + u32 cap; + u64 hret; + + if ((props->set_port_cap_mask | props->clr_port_cap_mask) + & ~allowed_port_caps) { + ehca_err(&shca->ib_device, "Non-changeable bits set in masks " + "set=%x clr=%x allowed=%x", props->set_port_cap_mask, + props->clr_port_cap_mask, allowed_port_caps); + return -EINVAL; + } + + if (mutex_lock_interruptible(&shca->modify_mutex)) + return -ERESTARTSYS; + + rblock = ehca_alloc_fw_ctrlblock(GFP_KERNEL); + if (!rblock) { + ehca_err(&shca->ib_device, "Can't allocate rblock memory."); + ret = -ENOMEM; + goto modify_port1; + } + + if (hipz_h_query_port(shca->ipz_hca_handle, port, rblock) != H_SUCCESS) { + ehca_err(&shca->ib_device, "Can't query port properties"); + ret = -EINVAL; + goto modify_port2; + } + + cap = (rblock->capability_mask | props->set_port_cap_mask) + & ~props->clr_port_cap_mask; + + hret = hipz_h_modify_port(shca->ipz_hca_handle, port, + cap, props->init_type, port_modify_mask); + if (hret != H_SUCCESS) { + ehca_err(&shca->ib_device, "Modify port failed hret=%lx", hret); + ret = -EINVAL; + } + +modify_port2: + ehca_free_fw_ctrlblock(rblock); + +modify_port1: + mutex_unlock(&shca->modify_mutex); + + return ret; } diff --git a/drivers/infiniband/hw/ehca/ehca_irq.c b/drivers/infiniband/hw/ehca/ehca_irq.c index 6c4f9f91b15d..f284be1c9166 100644 --- a/drivers/infiniband/hw/ehca/ehca_irq.c +++ b/drivers/infiniband/hw/ehca/ehca_irq.c @@ -63,13 +63,11 @@ #define ERROR_DATA_LENGTH EHCA_BMASK_IBM(52,63) #define ERROR_DATA_TYPE EHCA_BMASK_IBM(0,7) -#ifdef CONFIG_INFINIBAND_EHCA_SCALING - static void queue_comp_task(struct ehca_cq *__cq); static struct ehca_comp_pool* pool; +#ifdef CONFIG_HOTPLUG_CPU static struct notifier_block comp_pool_callback_nb; - #endif static inline void comp_event_callback(struct ehca_cq *cq) @@ -206,7 +204,7 @@ static void qp_event_callback(struct ehca_shca *shca, } static void cq_event_callback(struct ehca_shca *shca, - u64 eqe) + u64 eqe) { struct ehca_cq *cq; unsigned long flags; @@ -318,7 +316,7 @@ static void parse_ec(struct ehca_shca *shca, u64 eqe) "disruptive port %x configuration change", port); ehca_info(&shca->ib_device, - "port %x is inactive.", port); + "port %x is inactive.", port); event.device = &shca->ib_device; event.event = IB_EVENT_PORT_ERR; event.element.port_num = port; @@ -326,7 +324,7 @@ static void parse_ec(struct ehca_shca *shca, u64 eqe) ib_dispatch_event(&event); ehca_info(&shca->ib_device, - "port %x is active.", port); + "port %x is active.", port); event.device = &shca->ib_device; event.event = IB_EVENT_PORT_ACTIVE; event.element.port_num = port; @@ -401,200 +399,274 @@ irqreturn_t ehca_interrupt_eq(int irq, void *dev_id) return IRQ_HANDLED; } -void ehca_tasklet_eq(unsigned long data) + +static inline void process_eqe(struct ehca_shca *shca, struct ehca_eqe *eqe) { - struct ehca_shca *shca = (struct ehca_shca*)data; - struct ehca_eqe *eqe; - int int_state; - int query_cnt = 0; + u64 eqe_value; + u32 token; + unsigned long flags; + struct ehca_cq *cq; - do { - eqe = (struct ehca_eqe *)ehca_poll_eq(shca, &shca->eq); + eqe_value = eqe->entry; + ehca_dbg(&shca->ib_device, "eqe_value=%lx", eqe_value); + if (EHCA_BMASK_GET(EQE_COMPLETION_EVENT, eqe_value)) { + ehca_dbg(&shca->ib_device, "Got completion event"); + token = EHCA_BMASK_GET(EQE_CQ_TOKEN, eqe_value); + spin_lock_irqsave(&ehca_cq_idr_lock, flags); + cq = idr_find(&ehca_cq_idr, token); + if (cq == NULL) { + spin_unlock_irqrestore(&ehca_cq_idr_lock, flags); + ehca_err(&shca->ib_device, + "Invalid eqe for non-existing cq token=%x", + token); + return; + } + reset_eq_pending(cq); + cq->nr_events++; + spin_unlock_irqrestore(&ehca_cq_idr_lock, flags); + if (ehca_scaling_code) + queue_comp_task(cq); + else { + comp_event_callback(cq); + spin_lock_irqsave(&ehca_cq_idr_lock, flags); + cq->nr_events--; + if (!cq->nr_events) + wake_up(&cq->wait_completion); + spin_unlock_irqrestore(&ehca_cq_idr_lock, flags); + } + } else { + ehca_dbg(&shca->ib_device, "Got non completion event"); + parse_identifier(shca, eqe_value); + } +} - if ((shca->hw_level >= 2) && eqe) - int_state = 1; - else - int_state = 0; - - while ((int_state == 1) || eqe) { - while (eqe) { - u64 eqe_value = eqe->entry; - - ehca_dbg(&shca->ib_device, - "eqe_value=%lx", eqe_value); - - /* TODO: better structure */ - if (EHCA_BMASK_GET(EQE_COMPLETION_EVENT, - eqe_value)) { - unsigned long flags; - u32 token; - struct ehca_cq *cq; - - ehca_dbg(&shca->ib_device, - "... completion event"); - token = - EHCA_BMASK_GET(EQE_CQ_TOKEN, - eqe_value); - spin_lock_irqsave(&ehca_cq_idr_lock, - flags); - cq = idr_find(&ehca_cq_idr, token); - - if (cq == NULL) { - spin_unlock_irqrestore(&ehca_cq_idr_lock, - flags); - break; - } - - reset_eq_pending(cq); -#ifdef CONFIG_INFINIBAND_EHCA_SCALING - queue_comp_task(cq); - spin_unlock_irqrestore(&ehca_cq_idr_lock, - flags); -#else - spin_unlock_irqrestore(&ehca_cq_idr_lock, - flags); - comp_event_callback(cq); -#endif - } else { - ehca_dbg(&shca->ib_device, - "... non completion event"); - parse_identifier(shca, eqe_value); - } - eqe = - (struct ehca_eqe *)ehca_poll_eq(shca, - &shca->eq); - } +void ehca_process_eq(struct ehca_shca *shca, int is_irq) +{ + struct ehca_eq *eq = &shca->eq; + struct ehca_eqe_cache_entry *eqe_cache = eq->eqe_cache; + u64 eqe_value; + unsigned long flags; + int eqe_cnt, i; + int eq_empty = 0; + + spin_lock_irqsave(&eq->irq_spinlock, flags); + if (is_irq) { + const int max_query_cnt = 100; + int query_cnt = 0; + int int_state = 1; + do { + int_state = hipz_h_query_int_state( + shca->ipz_hca_handle, eq->ist); + query_cnt++; + iosync(); + } while (int_state && query_cnt < max_query_cnt); + if (unlikely((query_cnt == max_query_cnt))) + ehca_dbg(&shca->ib_device, "int_state=%x query_cnt=%x", + int_state, query_cnt); + } - if (shca->hw_level >= 2) { - int_state = - hipz_h_query_int_state(shca->ipz_hca_handle, - shca->eq.ist); - query_cnt++; - iosync(); - if (query_cnt >= 100) { - query_cnt = 0; - int_state = 0; - } + /* read out all eqes */ + eqe_cnt = 0; + do { + u32 token; + eqe_cache[eqe_cnt].eqe = + (struct ehca_eqe *)ehca_poll_eq(shca, eq); + if (!eqe_cache[eqe_cnt].eqe) + break; + eqe_value = eqe_cache[eqe_cnt].eqe->entry; + if (EHCA_BMASK_GET(EQE_COMPLETION_EVENT, eqe_value)) { + token = EHCA_BMASK_GET(EQE_CQ_TOKEN, eqe_value); + spin_lock(&ehca_cq_idr_lock); + eqe_cache[eqe_cnt].cq = idr_find(&ehca_cq_idr, token); + if (!eqe_cache[eqe_cnt].cq) { + spin_unlock(&ehca_cq_idr_lock); + ehca_err(&shca->ib_device, + "Invalid eqe for non-existing cq " + "token=%x", token); + continue; } - eqe = (struct ehca_eqe *)ehca_poll_eq(shca, &shca->eq); - + eqe_cache[eqe_cnt].cq->nr_events++; + spin_unlock(&ehca_cq_idr_lock); + } else + eqe_cache[eqe_cnt].cq = NULL; + eqe_cnt++; + } while (eqe_cnt < EHCA_EQE_CACHE_SIZE); + if (!eqe_cnt) { + if (is_irq) + ehca_dbg(&shca->ib_device, + "No eqe found for irq event"); + goto unlock_irq_spinlock; + } else if (!is_irq) + ehca_dbg(&shca->ib_device, "deadman found %x eqe", eqe_cnt); + if (unlikely(eqe_cnt == EHCA_EQE_CACHE_SIZE)) + ehca_dbg(&shca->ib_device, "too many eqes for one irq event"); + /* enable irq for new packets */ + for (i = 0; i < eqe_cnt; i++) { + if (eq->eqe_cache[i].cq) + reset_eq_pending(eq->eqe_cache[i].cq); + } + /* check eq */ + spin_lock(&eq->spinlock); + eq_empty = (!ipz_eqit_eq_peek_valid(&shca->eq.ipz_queue)); + spin_unlock(&eq->spinlock); + /* call completion handler for cached eqes */ + for (i = 0; i < eqe_cnt; i++) + if (eq->eqe_cache[i].cq) { + if (ehca_scaling_code) + queue_comp_task(eq->eqe_cache[i].cq); + else { + struct ehca_cq *cq = eq->eqe_cache[i].cq; + comp_event_callback(cq); + spin_lock_irqsave(&ehca_cq_idr_lock, flags); + cq->nr_events--; + if (!cq->nr_events) + wake_up(&cq->wait_completion); + spin_unlock_irqrestore(&ehca_cq_idr_lock, + flags); + } + } else { + ehca_dbg(&shca->ib_device, "Got non completion event"); + parse_identifier(shca, eq->eqe_cache[i].eqe->entry); } - } while (int_state != 0); + /* poll eq if not empty */ + if (eq_empty) + goto unlock_irq_spinlock; + do { + struct ehca_eqe *eqe; + eqe = (struct ehca_eqe *)ehca_poll_eq(shca, &shca->eq); + if (!eqe) + break; + process_eqe(shca, eqe); + } while (1); - return; +unlock_irq_spinlock: + spin_unlock_irqrestore(&eq->irq_spinlock, flags); } -#ifdef CONFIG_INFINIBAND_EHCA_SCALING +void ehca_tasklet_eq(unsigned long data) +{ + ehca_process_eq((struct ehca_shca*)data, 1); +} static inline int find_next_online_cpu(struct ehca_comp_pool* pool) { - unsigned long flags_last_cpu; + int cpu; + unsigned long flags; + WARN_ON_ONCE(!in_interrupt()); if (ehca_debug_level) ehca_dmp(&cpu_online_map, sizeof(cpumask_t), ""); - spin_lock_irqsave(&pool->last_cpu_lock, flags_last_cpu); - pool->last_cpu = next_cpu(pool->last_cpu, cpu_online_map); - if (pool->last_cpu == NR_CPUS) - pool->last_cpu = first_cpu(cpu_online_map); - spin_unlock_irqrestore(&pool->last_cpu_lock, flags_last_cpu); + spin_lock_irqsave(&pool->last_cpu_lock, flags); + cpu = next_cpu(pool->last_cpu, cpu_online_map); + if (cpu == NR_CPUS) + cpu = first_cpu(cpu_online_map); + pool->last_cpu = cpu; + spin_unlock_irqrestore(&pool->last_cpu_lock, flags); - return pool->last_cpu; + return cpu; } static void __queue_comp_task(struct ehca_cq *__cq, struct ehca_cpu_comp_task *cct) { - unsigned long flags_cct; - unsigned long flags_cq; + unsigned long flags; - spin_lock_irqsave(&cct->task_lock, flags_cct); - spin_lock_irqsave(&__cq->task_lock, flags_cq); + spin_lock_irqsave(&cct->task_lock, flags); + spin_lock(&__cq->task_lock); if (__cq->nr_callbacks == 0) { __cq->nr_callbacks++; list_add_tail(&__cq->entry, &cct->cq_list); cct->cq_jobs++; wake_up(&cct->wait_queue); - } - else + } else __cq->nr_callbacks++; - spin_unlock_irqrestore(&__cq->task_lock, flags_cq); - spin_unlock_irqrestore(&cct->task_lock, flags_cct); + spin_unlock(&__cq->task_lock); + spin_unlock_irqrestore(&cct->task_lock, flags); } static void queue_comp_task(struct ehca_cq *__cq) { - int cpu; int cpu_id; struct ehca_cpu_comp_task *cct; + int cq_jobs; + unsigned long flags; - cpu = get_cpu(); cpu_id = find_next_online_cpu(pool); - BUG_ON(!cpu_online(cpu_id)); cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu_id); + BUG_ON(!cct); - if (cct->cq_jobs > 0) { + spin_lock_irqsave(&cct->task_lock, flags); + cq_jobs = cct->cq_jobs; + spin_unlock_irqrestore(&cct->task_lock, flags); + if (cq_jobs > 0) { cpu_id = find_next_online_cpu(pool); cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu_id); + BUG_ON(!cct); } __queue_comp_task(__cq, cct); - - put_cpu(); - - return; } static void run_comp_task(struct ehca_cpu_comp_task* cct) { struct ehca_cq *cq; - unsigned long flags_cct; - unsigned long flags_cq; + unsigned long flags; - spin_lock_irqsave(&cct->task_lock, flags_cct); + spin_lock_irqsave(&cct->task_lock, flags); while (!list_empty(&cct->cq_list)) { cq = list_entry(cct->cq_list.next, struct ehca_cq, entry); - spin_unlock_irqrestore(&cct->task_lock, flags_cct); + spin_unlock_irqrestore(&cct->task_lock, flags); comp_event_callback(cq); - spin_lock_irqsave(&cct->task_lock, flags_cct); - spin_lock_irqsave(&cq->task_lock, flags_cq); + spin_lock_irqsave(&ehca_cq_idr_lock, flags); + cq->nr_events--; + if (!cq->nr_events) + wake_up(&cq->wait_completion); + spin_unlock_irqrestore(&ehca_cq_idr_lock, flags); + + spin_lock_irqsave(&cct->task_lock, flags); + spin_lock(&cq->task_lock); cq->nr_callbacks--; - if (cq->nr_callbacks == 0) { + if (!cq->nr_callbacks) { list_del_init(cct->cq_list.next); cct->cq_jobs--; } - spin_unlock_irqrestore(&cq->task_lock, flags_cq); - + spin_unlock(&cq->task_lock); } - spin_unlock_irqrestore(&cct->task_lock, flags_cct); - - return; + spin_unlock_irqrestore(&cct->task_lock, flags); } static int comp_task(void *__cct) { struct ehca_cpu_comp_task* cct = __cct; + int cql_empty; DECLARE_WAITQUEUE(wait, current); set_current_state(TASK_INTERRUPTIBLE); while(!kthread_should_stop()) { add_wait_queue(&cct->wait_queue, &wait); - if (list_empty(&cct->cq_list)) + spin_lock_irq(&cct->task_lock); + cql_empty = list_empty(&cct->cq_list); + spin_unlock_irq(&cct->task_lock); + if (cql_empty) schedule(); else __set_current_state(TASK_RUNNING); remove_wait_queue(&cct->wait_queue, &wait); - if (!list_empty(&cct->cq_list)) + spin_lock_irq(&cct->task_lock); + cql_empty = list_empty(&cct->cq_list); + spin_unlock_irq(&cct->task_lock); + if (!cql_empty) run_comp_task(__cct); set_current_state(TASK_INTERRUPTIBLE); @@ -637,8 +709,6 @@ static void destroy_comp_task(struct ehca_comp_pool *pool, if (task) kthread_stop(task); - - return; } static void take_over_work(struct ehca_comp_pool *pool, @@ -654,17 +724,18 @@ static void take_over_work(struct ehca_comp_pool *pool, list_splice_init(&cct->cq_list, &list); while(!list_empty(&list)) { - cq = list_entry(cct->cq_list.next, struct ehca_cq, entry); + cq = list_entry(cct->cq_list.next, struct ehca_cq, entry); - list_del(&cq->entry); - __queue_comp_task(cq, per_cpu_ptr(pool->cpu_comp_tasks, - smp_processor_id())); + list_del(&cq->entry); + __queue_comp_task(cq, per_cpu_ptr(pool->cpu_comp_tasks, + smp_processor_id())); } spin_unlock_irqrestore(&cct->task_lock, flags_cct); } +#ifdef CONFIG_HOTPLUG_CPU static int comp_pool_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) @@ -707,15 +778,16 @@ static int comp_pool_callback(struct notifier_block *nfb, return NOTIFY_OK; } - #endif int ehca_create_comp_pool(void) { -#ifdef CONFIG_INFINIBAND_EHCA_SCALING int cpu; struct task_struct *task; + if (!ehca_scaling_code) + return 0; + pool = kzalloc(sizeof(struct ehca_comp_pool), GFP_KERNEL); if (pool == NULL) return -ENOMEM; @@ -737,20 +809,27 @@ int ehca_create_comp_pool(void) } } +#ifdef CONFIG_HOTPLUG_CPU comp_pool_callback_nb.notifier_call = comp_pool_callback; comp_pool_callback_nb.priority =0; register_cpu_notifier(&comp_pool_callback_nb); #endif + printk(KERN_INFO "eHCA scaling code enabled\n"); + return 0; } void ehca_destroy_comp_pool(void) { -#ifdef CONFIG_INFINIBAND_EHCA_SCALING int i; + if (!ehca_scaling_code) + return; + +#ifdef CONFIG_HOTPLUG_CPU unregister_cpu_notifier(&comp_pool_callback_nb); +#endif for (i = 0; i < NR_CPUS; i++) { if (cpu_online(i)) @@ -758,7 +837,4 @@ void ehca_destroy_comp_pool(void) } free_percpu(pool->cpu_comp_tasks); kfree(pool); -#endif - - return; } diff --git a/drivers/infiniband/hw/ehca/ehca_irq.h b/drivers/infiniband/hw/ehca/ehca_irq.h index be579cc0adf6..6ed06ee033ed 100644 --- a/drivers/infiniband/hw/ehca/ehca_irq.h +++ b/drivers/infiniband/hw/ehca/ehca_irq.h @@ -56,6 +56,7 @@ void ehca_tasklet_neq(unsigned long data); irqreturn_t ehca_interrupt_eq(int irq, void *dev_id); void ehca_tasklet_eq(unsigned long data); +void ehca_process_eq(struct ehca_shca *shca, int is_irq); struct ehca_cpu_comp_task { wait_queue_head_t wait_queue; diff --git a/drivers/infiniband/hw/ehca/ehca_main.c b/drivers/infiniband/hw/ehca/ehca_main.c index 1155bcf48212..4700085ba834 100644 --- a/drivers/infiniband/hw/ehca/ehca_main.c +++ b/drivers/infiniband/hw/ehca/ehca_main.c @@ -52,7 +52,7 @@ MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Christoph Raisch <raisch@de.ibm.com>"); MODULE_DESCRIPTION("IBM eServer HCA InfiniBand Device Driver"); -MODULE_VERSION("SVNEHCA_0020"); +MODULE_VERSION("SVNEHCA_0022"); int ehca_open_aqp1 = 0; int ehca_debug_level = 0; @@ -62,6 +62,7 @@ int ehca_use_hp_mr = 0; int ehca_port_act_time = 30; int ehca_poll_all_eqs = 1; int ehca_static_rate = -1; +int ehca_scaling_code = 1; module_param_named(open_aqp1, ehca_open_aqp1, int, 0); module_param_named(debug_level, ehca_debug_level, int, 0); @@ -71,6 +72,7 @@ module_param_named(use_hp_mr, ehca_use_hp_mr, int, 0); module_param_named(port_act_time, ehca_port_act_time, int, 0); module_param_named(poll_all_eqs, ehca_poll_all_eqs, int, 0); module_param_named(static_rate, ehca_static_rate, int, 0); +module_param_named(scaling_code, ehca_scaling_code, int, 0); MODULE_PARM_DESC(open_aqp1, "AQP1 on startup (0: no (default), 1: yes)"); @@ -91,6 +93,8 @@ MODULE_PARM_DESC(poll_all_eqs, " (0: no, 1: yes (default))"); MODULE_PARM_DESC(static_rate, "set permanent static rate (default: disabled)"); +MODULE_PARM_DESC(scaling_code, + "set scaling code (0: disabled, 1: enabled/default)"); spinlock_t ehca_qp_idr_lock; spinlock_t ehca_cq_idr_lock; @@ -432,8 +436,8 @@ static int ehca_destroy_aqp1(struct ehca_sport *sport) static ssize_t ehca_show_debug_level(struct device_driver *ddp, char *buf) { - return snprintf(buf, PAGE_SIZE, "%d\n", - ehca_debug_level); + return snprintf(buf, PAGE_SIZE, "%d\n", + ehca_debug_level); } static ssize_t ehca_store_debug_level(struct device_driver *ddp, @@ -561,11 +565,11 @@ static int __devinit ehca_probe(struct ibmebus_dev *dev, const struct of_device_id *id) { struct ehca_shca *shca; - u64 *handle; + const u64 *handle; struct ib_pd *ibpd; int ret; - handle = (u64 *)get_property(dev->ofdev.node, "ibm,hca-handle", NULL); + handle = get_property(dev->ofdev.node, "ibm,hca-handle", NULL); if (!handle) { ehca_gen_err("Cannot get eHCA handle for adapter: %s.", dev->ofdev.node->full_name); @@ -583,6 +587,7 @@ static int __devinit ehca_probe(struct ibmebus_dev *dev, ehca_gen_err("Cannot allocate shca memory."); return -ENOMEM; } + mutex_init(&shca->modify_mutex); shca->ibmebus_dev = dev; shca->ipz_hca_handle.handle = *handle; @@ -778,8 +783,24 @@ void ehca_poll_eqs(unsigned long data) spin_lock(&shca_list_lock); list_for_each_entry(shca, &shca_list, shca_list) { - if (shca->eq.is_initialized) - ehca_tasklet_eq((unsigned long)(void*)shca); + if (shca->eq.is_initialized) { + /* call deadman proc only if eq ptr does not change */ + struct ehca_eq *eq = &shca->eq; + int max = 3; + volatile u64 q_ofs, q_ofs2; + u64 flags; + spin_lock_irqsave(&eq->spinlock, flags); + q_ofs = eq->ipz_queue.current_q_offset; + spin_unlock_irqrestore(&eq->spinlock, flags); + do { + spin_lock_irqsave(&eq->spinlock, flags); + q_ofs2 = eq->ipz_queue.current_q_offset; + spin_unlock_irqrestore(&eq->spinlock, flags); + max--; + } while (q_ofs == q_ofs2 && max > 0); + if (q_ofs == q_ofs2) + ehca_process_eq(shca, 0); + } } mod_timer(&poll_eqs_timer, jiffies + HZ); spin_unlock(&shca_list_lock); @@ -790,7 +811,7 @@ int __init ehca_module_init(void) int ret; printk(KERN_INFO "eHCA Infiniband Device Driver " - "(Rel.: SVNEHCA_0020)\n"); + "(Rel.: SVNEHCA_0022)\n"); idr_init(&ehca_qp_idr); idr_init(&ehca_cq_idr); spin_lock_init(&ehca_qp_idr_lock); diff --git a/drivers/infiniband/hw/ehca/hcp_if.c b/drivers/infiniband/hw/ehca/hcp_if.c index 3fb46e67df87..b564fcd3b282 100644 --- a/drivers/infiniband/hw/ehca/hcp_if.c +++ b/drivers/infiniband/hw/ehca/hcp_if.c @@ -70,6 +70,10 @@ #define H_ALL_RES_QP_SQUEUE_SIZE_PAGES EHCA_BMASK_IBM(0, 31) #define H_ALL_RES_QP_RQUEUE_SIZE_PAGES EHCA_BMASK_IBM(32, 63) +#define H_MP_INIT_TYPE EHCA_BMASK_IBM(44, 47) +#define H_MP_SHUTDOWN EHCA_BMASK_IBM(48, 48) +#define H_MP_RESET_QKEY_CTR EHCA_BMASK_IBM(49, 49) + /* direct access qp controls */ #define DAQP_CTRL_ENABLE 0x01 #define DAQP_CTRL_SEND_COMP 0x20 @@ -364,6 +368,26 @@ u64 hipz_h_query_port(const struct ipz_adapter_handle adapter_handle, return ret; } +u64 hipz_h_modify_port(const struct ipz_adapter_handle adapter_handle, + const u8 port_id, const u32 port_cap, + const u8 init_type, const int modify_mask) +{ + u64 port_attributes = port_cap; + + if (modify_mask & IB_PORT_SHUTDOWN) + port_attributes |= EHCA_BMASK_SET(H_MP_SHUTDOWN, 1); + if (modify_mask & IB_PORT_INIT_TYPE) + port_attributes |= EHCA_BMASK_SET(H_MP_INIT_TYPE, init_type); + if (modify_mask & IB_PORT_RESET_QKEY_CNTR) + port_attributes |= EHCA_BMASK_SET(H_MP_RESET_QKEY_CTR, 1); + + return ehca_plpar_hcall_norets(H_MODIFY_PORT, + adapter_handle.handle, /* r4 */ + port_id, /* r5 */ + port_attributes, /* r6 */ + 0, 0, 0, 0); +} + u64 hipz_h_query_hca(const struct ipz_adapter_handle adapter_handle, struct hipz_query_hca *query_hca_rblock) { diff --git a/drivers/infiniband/hw/ehca/hcp_if.h b/drivers/infiniband/hw/ehca/hcp_if.h index 587ebd470959..2869f7dd6196 100644 --- a/drivers/infiniband/hw/ehca/hcp_if.h +++ b/drivers/infiniband/hw/ehca/hcp_if.h @@ -85,6 +85,10 @@ u64 hipz_h_query_port(const struct ipz_adapter_handle adapter_handle, const u8 port_id, struct hipz_query_port *query_port_response_block); +u64 hipz_h_modify_port(const struct ipz_adapter_handle adapter_handle, + const u8 port_id, const u32 port_cap, + const u8 init_type, const int modify_mask); + u64 hipz_h_query_hca(const struct ipz_adapter_handle adapter_handle, struct hipz_query_hca *query_hca_rblock); diff --git a/drivers/infiniband/hw/ehca/ipz_pt_fn.h b/drivers/infiniband/hw/ehca/ipz_pt_fn.h index dc3bda2634b7..8199c45768a3 100644 --- a/drivers/infiniband/hw/ehca/ipz_pt_fn.h +++ b/drivers/infiniband/hw/ehca/ipz_pt_fn.h @@ -79,7 +79,7 @@ static inline void *ipz_qeit_calc(struct ipz_queue *queue, u64 q_offset) if (q_offset >= queue->queue_length) return NULL; current_page = (queue->queue_pages)[q_offset >> EHCA_PAGESHIFT]; - return ¤t_page->entries[q_offset & (EHCA_PAGESIZE - 1)]; + return ¤t_page->entries[q_offset & (EHCA_PAGESIZE - 1)]; } /* @@ -247,6 +247,15 @@ static inline void *ipz_eqit_eq_get_inc_valid(struct ipz_queue *queue) return ret; } +static inline void *ipz_eqit_eq_peek_valid(struct ipz_queue *queue) +{ + void *ret = ipz_qeit_get(queue); + u32 qe = *(u8 *) ret; + if ((qe >> 7) != (queue->toggle_state & 1)) + return NULL; + return ret; +} + /* returns address (GX) of first queue entry */ static inline u64 ipz_qpt_get_firstpage(struct ipz_qpt *qpt) { |