summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/infiniband')
-rw-r--r--drivers/infiniband/core/addr.c4
-rw-r--r--drivers/infiniband/core/mad.c16
-rw-r--r--drivers/infiniband/core/netlink.c2
-rw-r--r--drivers/infiniband/hw/cxgb4/cm.c2
-rw-r--r--drivers/infiniband/hw/cxgb4/qp.c2
-rw-r--r--drivers/infiniband/hw/ehca/ehca_irq.c250
-rw-r--r--drivers/infiniband/hw/ehca/ehca_irq.h6
-rw-r--r--drivers/infiniband/hw/mthca/mthca_reset.c8
-rw-r--r--drivers/infiniband/hw/nes/nes_hw.c6
-rw-r--r--drivers/infiniband/hw/nes/nes_nic.c5
-rw-r--r--drivers/infiniband/hw/ocrdma/ocrdma_verbs.c8
-rw-r--r--drivers/infiniband/hw/qib/qib.h2
-rw-r--r--drivers/infiniband/hw/qib/qib_fs.c4
-rw-r--r--drivers/infiniband/hw/qib/qib_mad.c3
-rw-r--r--drivers/infiniband/hw/qib/qib_pcie.c40
-rw-r--r--drivers/infiniband/ulp/ipoib/Makefile3
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib.h21
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_cm.c34
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_main.c134
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_multicast.c2
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_netlink.c172
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_vlan.c124
22 files changed, 498 insertions, 350 deletions
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 28058ae33d3..eaec8d7a3b7 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -152,13 +152,11 @@ static void set_timeout(unsigned long time)
{
unsigned long delay;
- cancel_delayed_work(&work);
-
delay = time - jiffies;
if ((long)delay <= 0)
delay = 1;
- queue_delayed_work(addr_wq, &work, delay);
+ mod_delayed_work(addr_wq, &work, delay);
}
static void queue_req(struct addr_req *req)
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index b0d0bc8a6fb..dc3fd1e8af0 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -2004,7 +2004,7 @@ static void adjust_timeout(struct ib_mad_agent_private *mad_agent_priv)
unsigned long delay;
if (list_empty(&mad_agent_priv->wait_list)) {
- __cancel_delayed_work(&mad_agent_priv->timed_work);
+ cancel_delayed_work(&mad_agent_priv->timed_work);
} else {
mad_send_wr = list_entry(mad_agent_priv->wait_list.next,
struct ib_mad_send_wr_private,
@@ -2013,13 +2013,11 @@ static void adjust_timeout(struct ib_mad_agent_private *mad_agent_priv)
if (time_after(mad_agent_priv->timeout,
mad_send_wr->timeout)) {
mad_agent_priv->timeout = mad_send_wr->timeout;
- __cancel_delayed_work(&mad_agent_priv->timed_work);
delay = mad_send_wr->timeout - jiffies;
if ((long)delay <= 0)
delay = 1;
- queue_delayed_work(mad_agent_priv->qp_info->
- port_priv->wq,
- &mad_agent_priv->timed_work, delay);
+ mod_delayed_work(mad_agent_priv->qp_info->port_priv->wq,
+ &mad_agent_priv->timed_work, delay);
}
}
}
@@ -2052,11 +2050,9 @@ static void wait_for_response(struct ib_mad_send_wr_private *mad_send_wr)
list_add(&mad_send_wr->agent_list, list_item);
/* Reschedule a work item if we have a shorter timeout */
- if (mad_agent_priv->wait_list.next == &mad_send_wr->agent_list) {
- __cancel_delayed_work(&mad_agent_priv->timed_work);
- queue_delayed_work(mad_agent_priv->qp_info->port_priv->wq,
- &mad_agent_priv->timed_work, delay);
- }
+ if (mad_agent_priv->wait_list.next == &mad_send_wr->agent_list)
+ mod_delayed_work(mad_agent_priv->qp_info->port_priv->wq,
+ &mad_agent_priv->timed_work, delay);
}
void ib_reset_mad_timeout(struct ib_mad_send_wr_private *mad_send_wr,
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 3ae2bfd3101..fe10a949aef 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -177,7 +177,7 @@ int __init ibnl_init(void)
.input = ibnl_rcv,
};
- nls = netlink_kernel_create(&init_net, NETLINK_RDMA, THIS_MODULE, &cfg);
+ nls = netlink_kernel_create(&init_net, NETLINK_RDMA, &cfg);
if (!nls) {
pr_warn("Failed to create netlink socket\n");
return -ENOMEM;
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 51f42061dae..6cfd4d8fd0b 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -1361,11 +1361,11 @@ static int abort_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
struct tid_info *t = dev->rdev.lldi.tids;
ep = lookup_tid(t, tid);
- PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
if (!ep) {
printk(KERN_WARNING MOD "Abort rpl to freed endpoint\n");
return 0;
}
+ PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
mutex_lock(&ep->com.mutex);
switch (ep->com.state) {
case ABORTING:
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index 45aedf1d933..5213bab2d19 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -1155,7 +1155,7 @@ static int ring_kernel_db(struct c4iw_qp *qhp, u32 qid, u16 inc)
*/
if (cxgb4_dbfifo_count(qhp->rhp->rdev.lldi.ports[0], 1) <
(qhp->rhp->rdev.lldi.dbfifo_int_thresh << 5)) {
- writel(V_QID(qid) | V_PIDX(inc), qhp->wq.db);
+ writel(QID(qid) | PIDX(inc), qhp->wq.db);
break;
}
set_current_state(TASK_UNINTERRUPTIBLE);
diff --git a/drivers/infiniband/hw/ehca/ehca_irq.c b/drivers/infiniband/hw/ehca/ehca_irq.c
index 53589000fd0..8615d7cf7e0 100644
--- a/drivers/infiniband/hw/ehca/ehca_irq.c
+++ b/drivers/infiniband/hw/ehca/ehca_irq.c
@@ -42,6 +42,7 @@
*/
#include <linux/slab.h>
+#include <linux/smpboot.h>
#include "ehca_classes.h"
#include "ehca_irq.h"
@@ -652,7 +653,7 @@ 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)
+static int find_next_online_cpu(struct ehca_comp_pool *pool)
{
int cpu;
unsigned long flags;
@@ -662,17 +663,20 @@ static inline int find_next_online_cpu(struct ehca_comp_pool *pool)
ehca_dmp(cpu_online_mask, cpumask_size(), "");
spin_lock_irqsave(&pool->last_cpu_lock, flags);
- cpu = cpumask_next(pool->last_cpu, cpu_online_mask);
- if (cpu >= nr_cpu_ids)
- cpu = cpumask_first(cpu_online_mask);
- pool->last_cpu = cpu;
+ do {
+ cpu = cpumask_next(pool->last_cpu, cpu_online_mask);
+ if (cpu >= nr_cpu_ids)
+ cpu = cpumask_first(cpu_online_mask);
+ pool->last_cpu = cpu;
+ } while (!per_cpu_ptr(pool->cpu_comp_tasks, cpu)->active);
spin_unlock_irqrestore(&pool->last_cpu_lock, flags);
return cpu;
}
static void __queue_comp_task(struct ehca_cq *__cq,
- struct ehca_cpu_comp_task *cct)
+ struct ehca_cpu_comp_task *cct,
+ struct task_struct *thread)
{
unsigned long flags;
@@ -683,7 +687,7 @@ static void __queue_comp_task(struct ehca_cq *__cq,
__cq->nr_callbacks++;
list_add_tail(&__cq->entry, &cct->cq_list);
cct->cq_jobs++;
- wake_up(&cct->wait_queue);
+ wake_up_process(thread);
} else
__cq->nr_callbacks++;
@@ -695,6 +699,7 @@ static void queue_comp_task(struct ehca_cq *__cq)
{
int cpu_id;
struct ehca_cpu_comp_task *cct;
+ struct task_struct *thread;
int cq_jobs;
unsigned long flags;
@@ -702,7 +707,8 @@ static void queue_comp_task(struct ehca_cq *__cq)
BUG_ON(!cpu_online(cpu_id));
cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu_id);
- BUG_ON(!cct);
+ thread = *per_cpu_ptr(pool->cpu_comp_threads, cpu_id);
+ BUG_ON(!cct || !thread);
spin_lock_irqsave(&cct->task_lock, flags);
cq_jobs = cct->cq_jobs;
@@ -710,28 +716,25 @@ static void queue_comp_task(struct ehca_cq *__cq)
if (cq_jobs > 0) {
cpu_id = find_next_online_cpu(pool);
cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu_id);
- BUG_ON(!cct);
+ thread = *per_cpu_ptr(pool->cpu_comp_threads, cpu_id);
+ BUG_ON(!cct || !thread);
}
-
- __queue_comp_task(__cq, cct);
+ __queue_comp_task(__cq, cct, thread);
}
static void run_comp_task(struct ehca_cpu_comp_task *cct)
{
struct ehca_cq *cq;
- unsigned long flags;
-
- 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);
+ spin_unlock_irq(&cct->task_lock);
comp_event_callback(cq);
if (atomic_dec_and_test(&cq->nr_events))
wake_up(&cq->wait_completion);
- spin_lock_irqsave(&cct->task_lock, flags);
+ spin_lock_irq(&cct->task_lock);
spin_lock(&cq->task_lock);
cq->nr_callbacks--;
if (!cq->nr_callbacks) {
@@ -740,159 +743,76 @@ static void run_comp_task(struct ehca_cpu_comp_task *cct)
}
spin_unlock(&cq->task_lock);
}
-
- spin_unlock_irqrestore(&cct->task_lock, flags);
}
-static int comp_task(void *__cct)
+static void comp_task_park(unsigned int cpu)
{
- 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);
-
- 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);
+ struct ehca_cpu_comp_task *cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
+ struct ehca_cpu_comp_task *target;
+ struct task_struct *thread;
+ struct ehca_cq *cq, *tmp;
+ LIST_HEAD(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);
+ spin_lock_irq(&cct->task_lock);
+ cct->cq_jobs = 0;
+ cct->active = 0;
+ list_splice_init(&cct->cq_list, &list);
+ spin_unlock_irq(&cct->task_lock);
- set_current_state(TASK_INTERRUPTIBLE);
+ cpu = find_next_online_cpu(pool);
+ target = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
+ thread = *per_cpu_ptr(pool->cpu_comp_threads, cpu);
+ spin_lock_irq(&target->task_lock);
+ list_for_each_entry_safe(cq, tmp, &list, entry) {
+ list_del(&cq->entry);
+ __queue_comp_task(cq, target, thread);
}
- __set_current_state(TASK_RUNNING);
-
- return 0;
-}
-
-static struct task_struct *create_comp_task(struct ehca_comp_pool *pool,
- int cpu)
-{
- struct ehca_cpu_comp_task *cct;
-
- cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
- spin_lock_init(&cct->task_lock);
- INIT_LIST_HEAD(&cct->cq_list);
- init_waitqueue_head(&cct->wait_queue);
- cct->task = kthread_create_on_node(comp_task, cct, cpu_to_node(cpu),
- "ehca_comp/%d", cpu);
-
- return cct->task;
+ spin_unlock_irq(&target->task_lock);
}
-static void destroy_comp_task(struct ehca_comp_pool *pool,
- int cpu)
+static void comp_task_stop(unsigned int cpu, bool online)
{
- struct ehca_cpu_comp_task *cct;
- struct task_struct *task;
- unsigned long flags_cct;
-
- cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
-
- spin_lock_irqsave(&cct->task_lock, flags_cct);
+ struct ehca_cpu_comp_task *cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
- task = cct->task;
- cct->task = NULL;
+ spin_lock_irq(&cct->task_lock);
cct->cq_jobs = 0;
-
- spin_unlock_irqrestore(&cct->task_lock, flags_cct);
-
- if (task)
- kthread_stop(task);
+ cct->active = 0;
+ WARN_ON(!list_empty(&cct->cq_list));
+ spin_unlock_irq(&cct->task_lock);
}
-static void __cpuinit take_over_work(struct ehca_comp_pool *pool, int cpu)
+static int comp_task_should_run(unsigned int cpu)
{
struct ehca_cpu_comp_task *cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
- LIST_HEAD(list);
- struct ehca_cq *cq;
- unsigned long flags_cct;
-
- spin_lock_irqsave(&cct->task_lock, flags_cct);
-
- list_splice_init(&cct->cq_list, &list);
-
- while (!list_empty(&list)) {
- cq = list_entry(cct->cq_list.next, struct ehca_cq, entry);
-
- list_del(&cq->entry);
- __queue_comp_task(cq, this_cpu_ptr(pool->cpu_comp_tasks));
- }
-
- spin_unlock_irqrestore(&cct->task_lock, flags_cct);
+ return cct->cq_jobs;
}
-static int __cpuinit comp_pool_callback(struct notifier_block *nfb,
- unsigned long action,
- void *hcpu)
+static void comp_task(unsigned int cpu)
{
- unsigned int cpu = (unsigned long)hcpu;
- struct ehca_cpu_comp_task *cct;
+ struct ehca_cpu_comp_task *cct = this_cpu_ptr(pool->cpu_comp_tasks);
+ int cql_empty;
- switch (action) {
- case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
- ehca_gen_dbg("CPU: %x (CPU_PREPARE)", cpu);
- if (!create_comp_task(pool, cpu)) {
- ehca_gen_err("Can't create comp_task for cpu: %x", cpu);
- return notifier_from_errno(-ENOMEM);
- }
- break;
- case CPU_UP_CANCELED:
- case CPU_UP_CANCELED_FROZEN:
- ehca_gen_dbg("CPU: %x (CPU_CANCELED)", cpu);
- cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
- kthread_bind(cct->task, cpumask_any(cpu_online_mask));
- destroy_comp_task(pool, cpu);
- break;
- case CPU_ONLINE:
- case CPU_ONLINE_FROZEN:
- ehca_gen_dbg("CPU: %x (CPU_ONLINE)", cpu);
- cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
- kthread_bind(cct->task, cpu);
- wake_up_process(cct->task);
- break;
- case CPU_DOWN_PREPARE:
- case CPU_DOWN_PREPARE_FROZEN:
- ehca_gen_dbg("CPU: %x (CPU_DOWN_PREPARE)", cpu);
- break;
- case CPU_DOWN_FAILED:
- case CPU_DOWN_FAILED_FROZEN:
- ehca_gen_dbg("CPU: %x (CPU_DOWN_FAILED)", cpu);
- break;
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
- ehca_gen_dbg("CPU: %x (CPU_DEAD)", cpu);
- destroy_comp_task(pool, cpu);
- take_over_work(pool, cpu);
- break;
+ spin_lock_irq(&cct->task_lock);
+ cql_empty = list_empty(&cct->cq_list);
+ if (!cql_empty) {
+ __set_current_state(TASK_RUNNING);
+ run_comp_task(cct);
}
-
- return NOTIFY_OK;
+ spin_unlock_irq(&cct->task_lock);
}
-static struct notifier_block comp_pool_callback_nb __cpuinitdata = {
- .notifier_call = comp_pool_callback,
- .priority = 0,
+static struct smp_hotplug_thread comp_pool_threads = {
+ .thread_should_run = comp_task_should_run,
+ .thread_fn = comp_task,
+ .thread_comm = "ehca_comp/%u",
+ .cleanup = comp_task_stop,
+ .park = comp_task_park,
};
int ehca_create_comp_pool(void)
{
- int cpu;
- struct task_struct *task;
+ int cpu, ret = -ENOMEM;
if (!ehca_scaling_code)
return 0;
@@ -905,38 +825,46 @@ int ehca_create_comp_pool(void)
pool->last_cpu = cpumask_any(cpu_online_mask);
pool->cpu_comp_tasks = alloc_percpu(struct ehca_cpu_comp_task);
- if (pool->cpu_comp_tasks == NULL) {
- kfree(pool);
- return -EINVAL;
- }
+ if (!pool->cpu_comp_tasks)
+ goto out_pool;
- for_each_online_cpu(cpu) {
- task = create_comp_task(pool, cpu);
- if (task) {
- kthread_bind(task, cpu);
- wake_up_process(task);
- }
+ pool->cpu_comp_threads = alloc_percpu(struct task_struct *);
+ if (!pool->cpu_comp_threads)
+ goto out_tasks;
+
+ for_each_present_cpu(cpu) {
+ struct ehca_cpu_comp_task *cct;
+
+ cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
+ spin_lock_init(&cct->task_lock);
+ INIT_LIST_HEAD(&cct->cq_list);
}
- register_hotcpu_notifier(&comp_pool_callback_nb);
+ comp_pool_threads.store = pool->cpu_comp_threads;
+ ret = smpboot_register_percpu_thread(&comp_pool_threads);
+ if (ret)
+ goto out_threads;
- printk(KERN_INFO "eHCA scaling code enabled\n");
+ pr_info("eHCA scaling code enabled\n");
+ return ret;
- return 0;
+out_threads:
+ free_percpu(pool->cpu_comp_threads);
+out_tasks:
+ free_percpu(pool->cpu_comp_tasks);
+out_pool:
+ kfree(pool);
+ return ret;
}
void ehca_destroy_comp_pool(void)
{
- int i;
-
if (!ehca_scaling_code)
return;
- unregister_hotcpu_notifier(&comp_pool_callback_nb);
-
- for_each_online_cpu(i)
- destroy_comp_task(pool, i);
+ smpboot_unregister_percpu_thread(&comp_pool_threads);
+ free_percpu(pool->cpu_comp_threads);
free_percpu(pool->cpu_comp_tasks);
kfree(pool);
}
diff --git a/drivers/infiniband/hw/ehca/ehca_irq.h b/drivers/infiniband/hw/ehca/ehca_irq.h
index 3346cb06cea..5370199f08c 100644
--- a/drivers/infiniband/hw/ehca/ehca_irq.h
+++ b/drivers/infiniband/hw/ehca/ehca_irq.h
@@ -58,15 +58,15 @@ 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;
struct list_head cq_list;
- struct task_struct *task;
spinlock_t task_lock;
int cq_jobs;
+ int active;
};
struct ehca_comp_pool {
- struct ehca_cpu_comp_task *cpu_comp_tasks;
+ struct ehca_cpu_comp_task __percpu *cpu_comp_tasks;
+ struct task_struct * __percpu *cpu_comp_threads;
int last_cpu;
spinlock_t last_cpu_lock;
};
diff --git a/drivers/infiniband/hw/mthca/mthca_reset.c b/drivers/infiniband/hw/mthca/mthca_reset.c
index 4fa3534ec23..74c6a942604 100644
--- a/drivers/infiniband/hw/mthca/mthca_reset.c
+++ b/drivers/infiniband/hw/mthca/mthca_reset.c
@@ -241,16 +241,16 @@ good:
if (hca_pcie_cap) {
devctl = hca_header[(hca_pcie_cap + PCI_EXP_DEVCTL) / 4];
- if (pci_write_config_word(mdev->pdev, hca_pcie_cap + PCI_EXP_DEVCTL,
- devctl)) {
+ if (pcie_capability_write_word(mdev->pdev, PCI_EXP_DEVCTL,
+ devctl)) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA PCI Express "
"Device Control register, aborting.\n");
goto out;
}
linkctl = hca_header[(hca_pcie_cap + PCI_EXP_LNKCTL) / 4];
- if (pci_write_config_word(mdev->pdev, hca_pcie_cap + PCI_EXP_LNKCTL,
- linkctl)) {
+ if (pcie_capability_write_word(mdev->pdev, PCI_EXP_LNKCTL,
+ linkctl)) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA PCI Express "
"Link control register, aborting.\n");
diff --git a/drivers/infiniband/hw/nes/nes_hw.c b/drivers/infiniband/hw/nes/nes_hw.c
index d42c9f435b1..9e0895b45eb 100644
--- a/drivers/infiniband/hw/nes/nes_hw.c
+++ b/drivers/infiniband/hw/nes/nes_hw.c
@@ -2679,11 +2679,9 @@ static void nes_process_mac_intr(struct nes_device *nesdev, u32 mac_number)
}
}
if (nesadapter->phy_type[mac_index] == NES_PHY_TYPE_SFP_D) {
- if (nesdev->link_recheck)
- cancel_delayed_work(&nesdev->work);
nesdev->link_recheck = 1;
- schedule_delayed_work(&nesdev->work,
- NES_LINK_RECHECK_DELAY);
+ mod_delayed_work(system_wq, &nesdev->work,
+ NES_LINK_RECHECK_DELAY);
}
}
diff --git a/drivers/infiniband/hw/nes/nes_nic.c b/drivers/infiniband/hw/nes/nes_nic.c
index f3a3ecf8d09..e43f6e41a6b 100644
--- a/drivers/infiniband/hw/nes/nes_nic.c
+++ b/drivers/infiniband/hw/nes/nes_nic.c
@@ -243,10 +243,9 @@ static int nes_netdev_open(struct net_device *netdev)
spin_lock_irqsave(&nesdev->nesadapter->phy_lock, flags);
if (nesdev->nesadapter->phy_type[nesdev->mac_index] == NES_PHY_TYPE_SFP_D) {
- if (nesdev->link_recheck)
- cancel_delayed_work(&nesdev->work);
nesdev->link_recheck = 1;
- schedule_delayed_work(&nesdev->work, NES_LINK_RECHECK_DELAY);
+ mod_delayed_work(system_wq, &nesdev->work,
+ NES_LINK_RECHECK_DELAY);
}
spin_unlock_irqrestore(&nesdev->nesadapter->phy_lock, flags);
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index cb5b7f7d4d3..b29a4246ef4 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -2219,7 +2219,6 @@ static bool ocrdma_poll_success_scqe(struct ocrdma_qp *qp,
u32 wqe_idx;
if (!qp->wqe_wr_id_tbl[tail].signaled) {
- expand = true; /* CQE cannot be consumed yet */
*polled = false; /* WC cannot be consumed yet */
} else {
ibwc->status = IB_WC_SUCCESS;
@@ -2227,10 +2226,11 @@ static bool ocrdma_poll_success_scqe(struct ocrdma_qp *qp,
ibwc->qp = &qp->ibqp;
ocrdma_update_wc(qp, ibwc, tail);
*polled = true;
- wqe_idx = le32_to_cpu(cqe->wq.wqeidx) & OCRDMA_CQE_WQEIDX_MASK;
- if (tail != wqe_idx)
- expand = true; /* Coalesced CQE can't be consumed yet */
}
+ wqe_idx = le32_to_cpu(cqe->wq.wqeidx) & OCRDMA_CQE_WQEIDX_MASK;
+ if (tail != wqe_idx)
+ expand = true; /* Coalesced CQE can't be consumed yet */
+
ocrdma_hwq_inc_tail(&qp->sq);
return expand;
}
diff --git a/drivers/infiniband/hw/qib/qib.h b/drivers/infiniband/hw/qib/qib.h
index 7b1b8669002..4d11575c201 100644
--- a/drivers/infiniband/hw/qib/qib.h
+++ b/drivers/infiniband/hw/qib/qib.h
@@ -87,7 +87,7 @@ struct qlogic_ib_stats {
};
extern struct qlogic_ib_stats qib_stats;
-extern struct pci_error_handlers qib_pci_err_handler;
+extern const struct pci_error_handlers qib_pci_err_handler;
extern struct pci_driver qib_driver;
#define QIB_CHIP_SWVERSION QIB_CHIP_VERS_MAJ
diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c
index cff8a6c3216..65a2a23f6f8 100644
--- a/drivers/infiniband/hw/qib/qib_fs.c
+++ b/drivers/infiniband/hw/qib/qib_fs.c
@@ -61,8 +61,8 @@ static int qibfs_mknod(struct inode *dir, struct dentry *dentry,
inode->i_ino = get_next_ino();
inode->i_mode = mode;
- inode->i_uid = 0;
- inode->i_gid = 0;
+ inode->i_uid = GLOBAL_ROOT_UID;
+ inode->i_gid = GLOBAL_ROOT_GID;
inode->i_blocks = 0;
inode->i_atime = CURRENT_TIME;
inode->i_mtime = inode->i_atime;
diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c
index 19f1e6c45fb..ccb119143d2 100644
--- a/drivers/infiniband/hw/qib/qib_mad.c
+++ b/drivers/infiniband/hw/qib/qib_mad.c
@@ -471,9 +471,10 @@ static int subn_get_portinfo(struct ib_smp *smp, struct ib_device *ibdev,
if (port_num != port) {
ibp = to_iport(ibdev, port_num);
ret = check_mkey(ibp, smp, 0);
- if (ret)
+ if (ret) {
ret = IB_MAD_RESULT_FAILURE;
goto bail;
+ }
}
}
diff --git a/drivers/infiniband/hw/qib/qib_pcie.c b/drivers/infiniband/hw/qib/qib_pcie.c
index 062c301ebf5..c574ec7c85e 100644
--- a/drivers/infiniband/hw/qib/qib_pcie.c
+++ b/drivers/infiniband/hw/qib/qib_pcie.c
@@ -273,10 +273,9 @@ int qib_pcie_params(struct qib_devdata *dd, u32 minw, u32 *nent,
struct qib_msix_entry *entry)
{
u16 linkstat, speed;
- int pos = 0, pose, ret = 1;
+ int pos = 0, ret = 1;
- pose = pci_pcie_cap(dd->pcidev);
- if (!pose) {
+ if (!pci_is_pcie(dd->pcidev)) {
qib_dev_err(dd, "Can't find PCI Express capability!\n");
/* set up something... */
dd->lbus_width = 1;
@@ -298,7 +297,7 @@ int qib_pcie_params(struct qib_devdata *dd, u32 minw, u32 *nent,
if (!pos)
qib_enable_intx(dd->pcidev);
- pci_read_config_word(dd->pcidev, pose + PCI_EXP_LNKSTA, &linkstat);
+ pcie_capability_read_word(dd->pcidev, PCI_EXP_LNKSTA, &linkstat);
/*
* speed is bits 0-3, linkwidth is bits 4-8
* no defines for them in headers
@@ -516,7 +515,6 @@ static int qib_tune_pcie_coalesce(struct qib_devdata *dd)
{
int r;
struct pci_dev *parent;
- int ppos;
u16 devid;
u32 mask, bits, val;
@@ -529,8 +527,7 @@ static int qib_tune_pcie_coalesce(struct qib_devdata *dd)
qib_devinfo(dd->pcidev, "Parent not root\n");
return 1;
}
- ppos = pci_pcie_cap(parent);
- if (!ppos)
+ if (!pci_is_pcie(parent))
return 1;
if (parent->vendor != 0x8086)
return 1;
@@ -587,7 +584,6 @@ static int qib_tune_pcie_caps(struct qib_devdata *dd)
{
int ret = 1; /* Assume the worst */
struct pci_dev *parent;
- int ppos, epos;
u16 pcaps, pctl, ecaps, ectl;
int rc_sup, ep_sup;
int rc_cur, ep_cur;
@@ -598,19 +594,15 @@ static int qib_tune_pcie_caps(struct qib_devdata *dd)
qib_devinfo(dd->pcidev, "Parent not root\n");
goto bail;
}
- ppos = pci_pcie_cap(parent);
- if (ppos) {
- pci_read_config_word(parent, ppos + PCI_EXP_DEVCAP, &pcaps);
- pci_read_config_word(parent, ppos + PCI_EXP_DEVCTL, &pctl);
- } else
+
+ if (!pci_is_pcie(parent) || !pci_is_pcie(dd->pcidev))
goto bail;
+ pcie_capability_read_word(parent, PCI_EXP_DEVCAP, &pcaps);
+ pcie_capability_read_word(parent, PCI_EXP_DEVCTL, &pctl);
/* Find out supported and configured values for endpoint (us) */
- epos = pci_pcie_cap(dd->pcidev);
- if (epos) {
- pci_read_config_word(dd->pcidev, epos + PCI_EXP_DEVCAP, &ecaps);
- pci_read_config_word(dd->pcidev, epos + PCI_EXP_DEVCTL, &ectl);
- } else
- goto bail;
+ pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCAP, &ecaps);
+ pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL, &ectl);
+
ret = 0;
/* Find max payload supported by root, endpoint */
rc_sup = fld2val(pcaps, PCI_EXP_DEVCAP_PAYLOAD);
@@ -629,14 +621,14 @@ static int qib_tune_pcie_caps(struct qib_devdata *dd)
rc_cur = rc_sup;
pctl = (pctl & ~PCI_EXP_DEVCTL_PAYLOAD) |
val2fld(rc_cur, PCI_EXP_DEVCTL_PAYLOAD);
- pci_write_config_word(parent, ppos + PCI_EXP_DEVCTL, pctl);
+ pcie_capability_write_word(parent, PCI_EXP_DEVCTL, pctl);
}
/* If less than (allowed, supported), bump endpoint payload */
if (rc_sup > ep_cur) {
ep_cur = rc_sup;
ectl = (ectl & ~PCI_EXP_DEVCTL_PAYLOAD) |
val2fld(ep_cur, PCI_EXP_DEVCTL_PAYLOAD);
- pci_write_config_word(dd->pcidev, epos + PCI_EXP_DEVCTL, ectl);
+ pcie_capability_write_word(dd->pcidev, PCI_EXP_DEVCTL, ectl);
}
/*
@@ -654,13 +646,13 @@ static int qib_tune_pcie_caps(struct qib_devdata *dd)
rc_cur = rc_sup;
pctl = (pctl & ~PCI_EXP_DEVCTL_READRQ) |
val2fld(rc_cur, PCI_EXP_DEVCTL_READRQ);
- pci_write_config_word(parent, ppos + PCI_EXP_DEVCTL, pctl);
+ pcie_capability_write_word(parent, PCI_EXP_DEVCTL, pctl);
}
if (rc_sup > ep_cur) {
ep_cur = rc_sup;
ectl = (ectl & ~PCI_EXP_DEVCTL_READRQ) |
val2fld(ep_cur, PCI_EXP_DEVCTL_READRQ);
- pci_write_config_word(dd->pcidev, epos + PCI_EXP_DEVCTL, ectl);
+ pcie_capability_write_word(dd->pcidev, PCI_EXP_DEVCTL, ectl);
}
bail:
return ret;
@@ -753,7 +745,7 @@ qib_pci_resume(struct pci_dev *pdev)
qib_init(dd, 1); /* same as re-init after reset */
}
-struct pci_error_handlers qib_pci_err_handler = {
+const struct pci_error_handlers qib_pci_err_handler = {
.error_detected = qib_pci_error_detected,
.mmio_enabled = qib_pci_mmio_enabled,
.link_reset = qib_pci_link_reset,
diff --git a/drivers/infiniband/ulp/ipoib/Makefile b/drivers/infiniband/ulp/ipoib/Makefile
index 3090100f0de..e5430dd5076 100644
--- a/drivers/infiniband/ulp/ipoib/Makefile
+++ b/drivers/infiniband/ulp/ipoib/Makefile
@@ -5,7 +5,8 @@ ib_ipoib-y := ipoib_main.o \
ipoib_multicast.o \
ipoib_verbs.o \
ipoib_vlan.o \
- ipoib_ethtool.o
+ ipoib_ethtool.o \
+ ipoib_netlink.o
ib_ipoib-$(CONFIG_INFINIBAND_IPOIB_CM) += ipoib_cm.o
ib_ipoib-$(CONFIG_INFINIBAND_IPOIB_DEBUG) += ipoib_fs.o
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index ca43901ed86..196eb52f003 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -104,6 +104,10 @@ enum {
MAX_SEND_CQE = 16,
IPOIB_CM_COPYBREAK = 256,
+
+ IPOIB_NON_CHILD = 0,
+ IPOIB_LEGACY_CHILD = 1,
+ IPOIB_RTNL_CHILD = 2,
};
#define IPOIB_OP_RECV (1ul << 31)
@@ -262,7 +266,10 @@ struct ipoib_ethtool_st {
u16 max_coalesced_frames;
};
+struct ipoib_neigh_table;
+
struct ipoib_neigh_hash {
+ struct ipoib_neigh_table *ntbl;
struct ipoib_neigh __rcu **buckets;
struct rcu_head rcu;
u32 mask;
@@ -271,9 +278,9 @@ struct ipoib_neigh_hash {
struct ipoib_neigh_table {
struct ipoib_neigh_hash __rcu *htbl;
- rwlock_t rwlock;
atomic_t entries;
struct completion flushed;
+ struct completion deleted;
};
/*
@@ -350,6 +357,7 @@ struct ipoib_dev_priv {
struct net_device *parent;
struct list_head child_intfs;
struct list_head list;
+ int child_type;
#ifdef CONFIG_INFINIBAND_IPOIB_CM
struct ipoib_cm_dev_priv cm;
@@ -509,6 +517,17 @@ void ipoib_event(struct ib_event_handler *handler,
int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey);
int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey);
+int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
+ u16 pkey, int child_type);
+
+int __init ipoib_netlink_init(void);
+void __exit ipoib_netlink_fini(void);
+
+void ipoib_set_umcast(struct net_device *ndev, int umcast_val);
+int ipoib_set_mode(struct net_device *dev, const char *buf);
+
+void ipoib_setup(struct net_device *dev);
+
void ipoib_pkey_poll(struct work_struct *work);
int ipoib_pkey_dev_delay_open(struct net_device *dev);
void ipoib_drain_cq(struct net_device *dev);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 24683fda8e2..175581cf478 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -1448,15 +1448,10 @@ static ssize_t show_mode(struct device *d, struct device_attribute *attr,
return sprintf(buf, "datagram\n");
}
-static ssize_t set_mode(struct device *d, struct device_attribute *attr,
- const char *buf, size_t count)
+int ipoib_set_mode(struct net_device *dev, const char *buf)
{
- struct net_device *dev = to_net_dev(d);
struct ipoib_dev_priv *priv = netdev_priv(dev);
- if (!rtnl_trylock())
- return restart_syscall();
-
/* flush paths if we switch modes so that connections are restarted */
if (IPOIB_CM_SUPPORTED(dev->dev_addr) && !strcmp(buf, "connected\n")) {
set_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
@@ -1467,7 +1462,8 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr,
priv->tx_wr.send_flags &= ~IB_SEND_IP_CSUM;
ipoib_flush_paths(dev);
- return count;
+ rtnl_lock();
+ return 0;
}
if (!strcmp(buf, "datagram\n")) {
@@ -1476,14 +1472,32 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr,
dev_set_mtu(dev, min(priv->mcast_mtu, dev->mtu));
rtnl_unlock();
ipoib_flush_paths(dev);
-
- return count;
+ rtnl_lock();
+ return 0;
}
- rtnl_unlock();
return -EINVAL;
}
+static ssize_t set_mode(struct device *d, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct net_device *dev = to_net_dev(d);
+ int ret;
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ ret = ipoib_set_mode(dev, buf);
+
+ rtnl_unlock();
+
+ if (!ret)
+ return count;
+
+ return ret;
+}
+
static DEVICE_ATTR(mode, S_IWUSR | S_IRUGO, show_mode, set_mode);
int ipoib_cm_add_mode_attr(struct net_device *dev)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 3e2085a3ee4..3f9a9ba2f9e 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -173,6 +173,11 @@ static int ipoib_stop(struct net_device *dev)
return 0;
}
+static void ipoib_uninit(struct net_device *dev)
+{
+ ipoib_dev_cleanup(dev);
+}
+
static netdev_features_t ipoib_fix_features(struct net_device *dev, netdev_features_t features)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
@@ -546,15 +551,15 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
struct ipoib_neigh *neigh;
unsigned long flags;
+ spin_lock_irqsave(&priv->lock, flags);
neigh = ipoib_neigh_alloc(daddr, dev);
if (!neigh) {
+ spin_unlock_irqrestore(&priv->lock, flags);
++dev->stats.tx_dropped;
dev_kfree_skb_any(skb);
return;
}
- spin_lock_irqsave(&priv->lock, flags);
-
path = __path_find(dev, daddr + 4);
if (!path) {
path = path_rec_create(dev, daddr + 4);
@@ -863,10 +868,10 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
if (test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags))
return;
- write_lock_bh(&ntbl->rwlock);
+ spin_lock_irqsave(&priv->lock, flags);
htbl = rcu_dereference_protected(ntbl->htbl,
- lockdep_is_held(&ntbl->rwlock));
+ lockdep_is_held(&priv->lock));
if (!htbl)
goto out_unlock;
@@ -883,16 +888,14 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
struct ipoib_neigh __rcu **np = &htbl->buckets[i];
while ((neigh = rcu_dereference_protected(*np,
- lockdep_is_held(&ntbl->rwlock))) != NULL) {
+ lockdep_is_held(&priv->lock))) != NULL) {
/* was the neigh idle for two GC periods */
if (time_after(neigh_obsolete, neigh->alive)) {
rcu_assign_pointer(*np,
rcu_dereference_protected(neigh->hnext,
- lockdep_is_held(&ntbl->rwlock)));
+ lockdep_is_held(&priv->lock)));
/* remove from path/mc list */
- spin_lock_irqsave(&priv->lock, flags);
list_del(&neigh->list);
- spin_unlock_irqrestore(&priv->lock, flags);
call_rcu(&neigh->rcu, ipoib_neigh_reclaim);
} else {
np = &neigh->hnext;
@@ -902,7 +905,7 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
}
out_unlock:
- write_unlock_bh(&ntbl->rwlock);
+ spin_unlock_irqrestore(&priv->lock, flags);
}
static void ipoib_reap_neigh(struct work_struct *work)
@@ -947,10 +950,8 @@ struct ipoib_neigh *ipoib_neigh_alloc(u8 *daddr,
struct ipoib_neigh *neigh;
u32 hash_val;
- write_lock_bh(&ntbl->rwlock);
-
htbl = rcu_dereference_protected(ntbl->htbl,
- lockdep_is_held(&ntbl->rwlock));
+ lockdep_is_held(&priv->lock));
if (!htbl) {
neigh = NULL;
goto out_unlock;
@@ -961,10 +962,10 @@ struct ipoib_neigh *ipoib_neigh_alloc(u8 *daddr,
*/
hash_val = ipoib_addr_hash(htbl, daddr);
for (neigh = rcu_dereference_protected(htbl->buckets[hash_val],
- lockdep_is_held(&ntbl->rwlock));
+ lockdep_is_held(&priv->lock));
neigh != NULL;
neigh = rcu_dereference_protected(neigh->hnext,
- lockdep_is_held(&ntbl->rwlock))) {
+ lockdep_is_held(&priv->lock))) {
if (memcmp(daddr, neigh->daddr, INFINIBAND_ALEN) == 0) {
/* found, take one ref on behalf of the caller */
if (!atomic_inc_not_zero(&neigh->refcnt)) {
@@ -987,12 +988,11 @@ struct ipoib_neigh *ipoib_neigh_alloc(u8 *daddr,
/* put in hash */
rcu_assign_pointer(neigh->hnext,
rcu_dereference_protected(htbl->buckets[hash_val],
- lockdep_is_held(&ntbl->rwlock)));
+ lockdep_is_held(&priv->lock)));
rcu_assign_pointer(htbl->buckets[hash_val], neigh);
atomic_inc(&ntbl->entries);
out_unlock:
- write_unlock_bh(&ntbl->rwlock);
return neigh;
}
@@ -1040,35 +1040,29 @@ void ipoib_neigh_free(struct ipoib_neigh *neigh)
struct ipoib_neigh *n;
u32 hash_val;
- write_lock_bh(&ntbl->rwlock);
-
htbl = rcu_dereference_protected(ntbl->htbl,
- lockdep_is_held(&ntbl->rwlock));
+ lockdep_is_held(&priv->lock));
if (!htbl)
- goto out_unlock;
+ return;
hash_val = ipoib_addr_hash(htbl, neigh->daddr);
np = &htbl->buckets[hash_val];
for (n = rcu_dereference_protected(*np,
- lockdep_is_held(&ntbl->rwlock));
+ lockdep_is_held(&priv->lock));
n != NULL;
n = rcu_dereference_protected(*np,
- lockdep_is_held(&ntbl->rwlock))) {
+ lockdep_is_held(&priv->lock))) {
if (n == neigh) {
/* found */
rcu_assign_pointer(*np,
rcu_dereference_protected(neigh->hnext,
- lockdep_is_held(&ntbl->rwlock)));
+ lockdep_is_held(&priv->lock)));
call_rcu(&neigh->rcu, ipoib_neigh_reclaim);
- goto out_unlock;
+ return;
} else {
np = &n->hnext;
}
}
-
-out_unlock:
- write_unlock_bh(&ntbl->rwlock);
-
}
static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv)
@@ -1080,7 +1074,6 @@ static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv)
clear_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags);
ntbl->htbl = NULL;
- rwlock_init(&ntbl->rwlock);
htbl = kzalloc(sizeof(*htbl), GFP_KERNEL);
if (!htbl)
return -ENOMEM;
@@ -1095,6 +1088,7 @@ static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv)
htbl->mask = (size - 1);
htbl->buckets = buckets;
ntbl->htbl = htbl;
+ htbl->ntbl = ntbl;
atomic_set(&ntbl->entries, 0);
/* start garbage collection */
@@ -1111,9 +1105,11 @@ static void neigh_hash_free_rcu(struct rcu_head *head)
struct ipoib_neigh_hash,
rcu);
struct ipoib_neigh __rcu **buckets = htbl->buckets;
+ struct ipoib_neigh_table *ntbl = htbl->ntbl;
kfree(buckets);
kfree(htbl);
+ complete(&ntbl->deleted);
}
void ipoib_del_neighs_by_gid(struct net_device *dev, u8 *gid)
@@ -1125,10 +1121,10 @@ void ipoib_del_neighs_by_gid(struct net_device *dev, u8 *gid)
int i;
/* remove all neigh connected to a given path or mcast */
- write_lock_bh(&ntbl->rwlock);
+ spin_lock_irqsave(&priv->lock, flags);
htbl = rcu_dereference_protected(ntbl->htbl,
- lockdep_is_held(&ntbl->rwlock));
+ lockdep_is_held(&priv->lock));
if (!htbl)
goto out_unlock;
@@ -1138,16 +1134,14 @@ void ipoib_del_neighs_by_gid(struct net_device *dev, u8 *gid)
struct ipoib_neigh __rcu **np = &htbl->buckets[i];
while ((neigh = rcu_dereference_protected(*np,
- lockdep_is_held(&ntbl->rwlock))) != NULL) {
+ lockdep_is_held(&priv->lock))) != NULL) {
/* delete neighs belong to this parent */
if (!memcmp(gid, neigh->daddr + 4, sizeof (union ib_gid))) {
rcu_assign_pointer(*np,
rcu_dereference_protected(neigh->hnext,
- lockdep_is_held(&ntbl->rwlock)));
+ lockdep_is_held(&priv->lock)));
/* remove from parent list */
- spin_lock_irqsave(&priv->lock, flags);
list_del(&neigh->list);
- spin_unlock_irqrestore(&priv->lock, flags);
call_rcu(&neigh->rcu, ipoib_neigh_reclaim);
} else {
np = &neigh->hnext;
@@ -1156,7 +1150,7 @@ void ipoib_del_neighs_by_gid(struct net_device *dev, u8 *gid)
}
}
out_unlock:
- write_unlock_bh(&ntbl->rwlock);
+ spin_unlock_irqrestore(&priv->lock, flags);
}
static void ipoib_flush_neighs(struct ipoib_dev_priv *priv)
@@ -1164,37 +1158,44 @@ static void ipoib_flush_neighs(struct ipoib_dev_priv *priv)
struct ipoib_neigh_table *ntbl = &priv->ntbl;
struct ipoib_neigh_hash *htbl;
unsigned long flags;
- int i;
+ int i, wait_flushed = 0;
- write_lock_bh(&ntbl->rwlock);
+ init_completion(&priv->ntbl.flushed);
+
+ spin_lock_irqsave(&priv->lock, flags);
htbl = rcu_dereference_protected(ntbl->htbl,
- lockdep_is_held(&ntbl->rwlock));
+ lockdep_is_held(&priv->lock));
if (!htbl)
goto out_unlock;
+ wait_flushed = atomic_read(&priv->ntbl.entries);
+ if (!wait_flushed)
+ goto free_htbl;
+
for (i = 0; i < htbl->size; i++) {
struct ipoib_neigh *neigh;
struct ipoib_neigh __rcu **np = &htbl->buckets[i];
while ((neigh = rcu_dereference_protected(*np,
- lockdep_is_held(&ntbl->rwlock))) != NULL) {
+ lockdep_is_held(&priv->lock))) != NULL) {
rcu_assign_pointer(*np,
rcu_dereference_protected(neigh->hnext,
- lockdep_is_held(&ntbl->rwlock)));
+ lockdep_is_held(&priv->lock)));
/* remove from path/mc list */
- spin_lock_irqsave(&priv->lock, flags);
list_del(&neigh->list);
- spin_unlock_irqrestore(&priv->lock, flags);
call_rcu(&neigh->rcu, ipoib_neigh_reclaim);
}
}
+free_htbl:
rcu_assign_pointer(ntbl->htbl, NULL);
call_rcu(&htbl->rcu, neigh_hash_free_rcu);
out_unlock:
- write_unlock_bh(&ntbl->rwlock);
+ spin_unlock_irqrestore(&priv->lock, flags);
+ if (wait_flushed)
+ wait_for_completion(&priv->ntbl.flushed);
}
static void ipoib_neigh_hash_uninit(struct net_device *dev)
@@ -1203,7 +1204,7 @@ static void ipoib_neigh_hash_uninit(struct net_device *dev)
int stopped;
ipoib_dbg(priv, "ipoib_neigh_hash_uninit\n");
- init_completion(&priv->ntbl.flushed);
+ init_completion(&priv->ntbl.deleted);
set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags);
/* Stop GC if called at init fail need to cancel work */
@@ -1211,10 +1212,9 @@ static void ipoib_neigh_hash_uninit(struct net_device *dev)
if (!stopped)
cancel_delayed_work(&priv->neigh_reap_task);
- if (atomic_read(&priv->ntbl.entries)) {
- ipoib_flush_neighs(priv);
- wait_for_completion(&priv->ntbl.flushed);
- }
+ ipoib_flush_neighs(priv);
+
+ wait_for_completion(&priv->ntbl.deleted);
}
@@ -1262,6 +1262,9 @@ out:
void ipoib_dev_cleanup(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev), *cpriv, *tcpriv;
+ LIST_HEAD(head);
+
+ ASSERT_RTNL();
ipoib_delete_debug_files(dev);
@@ -1270,10 +1273,9 @@ void ipoib_dev_cleanup(struct net_device *dev)
/* Stop GC on child */
set_bit(IPOIB_STOP_NEIGH_GC, &cpriv->flags);
cancel_delayed_work(&cpriv->neigh_reap_task);
- unregister_netdev(cpriv->dev);
- ipoib_dev_cleanup(cpriv->dev);
- free_netdev(cpriv->dev);
+ unregister_netdevice_queue(cpriv->dev, &head);
}
+ unregister_netdevice_many(&head);
ipoib_ib_dev_cleanup(dev);
@@ -1291,6 +1293,7 @@ static const struct header_ops ipoib_header_ops = {
};
static const struct net_device_ops ipoib_netdev_ops = {
+ .ndo_uninit = ipoib_uninit,
.ndo_open = ipoib_open,
.ndo_stop = ipoib_stop,
.ndo_change_mtu = ipoib_change_mtu,
@@ -1300,7 +1303,7 @@ static const struct net_device_ops ipoib_netdev_ops = {
.ndo_set_rx_mode = ipoib_set_mcast_list,
};
-static void ipoib_setup(struct net_device *dev)
+void ipoib_setup(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
@@ -1378,12 +1381,9 @@ static ssize_t show_umcast(struct device *dev,
return sprintf(buf, "%d\n", test_bit(IPOIB_FLAG_UMCAST, &priv->flags));
}
-static ssize_t set_umcast(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
+void ipoib_set_umcast(struct net_device *ndev, int umcast_val)
{
- struct ipoib_dev_priv *priv = netdev_priv(to_net_dev(dev));
- unsigned long umcast_val = simple_strtoul(buf, NULL, 0);
+ struct ipoib_dev_priv *priv = netdev_priv(ndev);
if (umcast_val > 0) {
set_bit(IPOIB_FLAG_UMCAST, &priv->flags);
@@ -1391,6 +1391,15 @@ static ssize_t set_umcast(struct device *dev,
"by userspace\n");
} else
clear_bit(IPOIB_FLAG_UMCAST, &priv->flags);
+}
+
+static ssize_t set_umcast(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ unsigned long umcast_val = simple_strtoul(buf, NULL, 0);
+
+ ipoib_set_umcast(to_net_dev(dev), umcast_val);
return count;
}
@@ -1662,7 +1671,6 @@ static void ipoib_remove_one(struct ib_device *device)
flush_workqueue(ipoib_workqueue);
unregister_netdev(priv->dev);
- ipoib_dev_cleanup(priv->dev);
free_netdev(priv->dev);
}
@@ -1714,8 +1722,15 @@ static int __init ipoib_init_module(void)
if (ret)
goto err_sa;
+ ret = ipoib_netlink_init();
+ if (ret)
+ goto err_client;
+
return 0;
+err_client:
+ ib_unregister_client(&ipoib_client);
+
err_sa:
ib_sa_unregister_client(&ipoib_sa_client);
destroy_workqueue(ipoib_workqueue);
@@ -1728,6 +1743,7 @@ err_fs:
static void __exit ipoib_cleanup_module(void)
{
+ ipoib_netlink_fini();
ib_unregister_client(&ipoib_client);
ib_sa_unregister_client(&ipoib_sa_client);
ipoib_unregister_debugfs();
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 13f4aa7593c..75367249f44 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -707,9 +707,7 @@ out:
neigh = ipoib_neigh_get(dev, daddr);
spin_lock_irqsave(&priv->lock, flags);
if (!neigh) {
- spin_unlock_irqrestore(&priv->lock, flags);
neigh = ipoib_neigh_alloc(daddr, dev);
- spin_lock_irqsave(&priv->lock, flags);
if (neigh) {
kref_get(&mcast->ah->ref);
neigh->ah = mcast->ah;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
new file mode 100644
index 00000000000..74685936c94
--- /dev/null
+++ b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
@@ -0,0 +1,172 @@
+/*
+ * Copyright (c) 2012 Mellanox Technologies. - All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/netdevice.h>
+#include <linux/module.h>
+#include <net/rtnetlink.h>
+#include "ipoib.h"
+
+static const struct nla_policy ipoib_policy[IFLA_IPOIB_MAX + 1] = {
+ [IFLA_IPOIB_PKEY] = { .type = NLA_U16 },
+ [IFLA_IPOIB_MODE] = { .type = NLA_U16 },
+ [IFLA_IPOIB_UMCAST] = { .type = NLA_U16 },
+};
+
+static int ipoib_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+ struct ipoib_dev_priv *priv = netdev_priv(dev);
+ u16 val;
+
+ if (nla_put_u16(skb, IFLA_IPOIB_PKEY, priv->pkey))
+ goto nla_put_failure;
+
+ val = test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
+ if (nla_put_u16(skb, IFLA_IPOIB_MODE, val))
+ goto nla_put_failure;
+
+ val = test_bit(IPOIB_FLAG_UMCAST, &priv->flags);
+ if (nla_put_u16(skb, IFLA_IPOIB_UMCAST, val))
+ goto nla_put_failure;
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
+static int ipoib_changelink(struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[])
+{
+ u16 mode, umcast;
+ int ret = 0;
+
+ if (data[IFLA_IPOIB_MODE]) {
+ mode = nla_get_u16(data[IFLA_IPOIB_MODE]);
+ if (mode == IPOIB_MODE_DATAGRAM)
+ ret = ipoib_set_mode(dev, "datagram\n");
+ else if (mode == IPOIB_MODE_CONNECTED)
+ ret = ipoib_set_mode(dev, "connected\n");
+ else
+ ret = -EINVAL;
+
+ if (ret < 0)
+ goto out_err;
+ }
+
+ if (data[IFLA_IPOIB_UMCAST]) {
+ umcast = nla_get_u16(data[IFLA_IPOIB_UMCAST]);
+ ipoib_set_umcast(dev, umcast);
+ }
+
+out_err:
+ return ret;
+}
+
+static int ipoib_new_child_link(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[])
+{
+ struct net_device *pdev;
+ struct ipoib_dev_priv *ppriv;
+ u16 child_pkey;
+ int err;
+
+ if (!tb[IFLA_LINK])
+ return -EINVAL;
+
+ pdev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
+ if (!pdev)
+ return -ENODEV;
+
+ ppriv = netdev_priv(pdev);
+
+ if (test_bit(IPOIB_FLAG_SUBINTERFACE, &ppriv->flags)) {
+ ipoib_warn(ppriv, "child creation disallowed for child devices\n");
+ return -EINVAL;
+ }
+
+ if (!data || !data[IFLA_IPOIB_PKEY]) {
+ ipoib_dbg(ppriv, "no pkey specified, using parent pkey\n");
+ child_pkey = ppriv->pkey;
+ } else
+ child_pkey = nla_get_u16(data[IFLA_IPOIB_PKEY]);
+
+ err = __ipoib_vlan_add(ppriv, netdev_priv(dev), child_pkey, IPOIB_RTNL_CHILD);
+
+ if (!err && data)
+ err = ipoib_changelink(dev, tb, data);
+ return err;
+}
+
+static void ipoib_unregister_child_dev(struct net_device *dev, struct list_head *head)
+{
+ struct ipoib_dev_priv *priv, *ppriv;
+
+ priv = netdev_priv(dev);
+ ppriv = netdev_priv(priv->parent);
+
+ mutex_lock(&ppriv->vlan_mutex);
+ unregister_netdevice_queue(dev, head);
+ list_del(&priv->list);
+ mutex_unlock(&ppriv->vlan_mutex);
+}
+
+static size_t ipoib_get_size(const struct net_device *dev)
+{
+ return nla_total_size(2) + /* IFLA_IPOIB_PKEY */
+ nla_total_size(2) + /* IFLA_IPOIB_MODE */
+ nla_total_size(2); /* IFLA_IPOIB_UMCAST */
+}
+
+static struct rtnl_link_ops ipoib_link_ops __read_mostly = {
+ .kind = "ipoib",
+ .maxtype = IFLA_IPOIB_MAX,
+ .policy = ipoib_policy,
+ .priv_size = sizeof(struct ipoib_dev_priv),
+ .setup = ipoib_setup,
+ .newlink = ipoib_new_child_link,
+ .changelink = ipoib_changelink,
+ .dellink = ipoib_unregister_child_dev,
+ .get_size = ipoib_get_size,
+ .fill_info = ipoib_fill_info,
+};
+
+int __init ipoib_netlink_init(void)
+{
+ return rtnl_link_register(&ipoib_link_ops);
+}
+
+void __exit ipoib_netlink_fini(void)
+{
+ rtnl_link_unregister(&ipoib_link_ops);
+}
+
+MODULE_ALIAS_RTNL_LINK("ipoib");
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index d7e9740c724..8292554bccb 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -49,47 +49,11 @@ static ssize_t show_parent(struct device *d, struct device_attribute *attr,
}
static DEVICE_ATTR(parent, S_IRUGO, show_parent, NULL);
-int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
+int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
+ u16 pkey, int type)
{
- struct ipoib_dev_priv *ppriv, *priv;
- char intf_name[IFNAMSIZ];
int result;
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
-
- ppriv = netdev_priv(pdev);
-
- if (!rtnl_trylock())
- return restart_syscall();
- mutex_lock(&ppriv->vlan_mutex);
-
- /*
- * First ensure this isn't a duplicate. We check the parent device and
- * then all of the child interfaces to make sure the Pkey doesn't match.
- */
- if (ppriv->pkey == pkey) {
- result = -ENOTUNIQ;
- priv = NULL;
- goto err;
- }
-
- list_for_each_entry(priv, &ppriv->child_intfs, list) {
- if (priv->pkey == pkey) {
- result = -ENOTUNIQ;
- priv = NULL;
- goto err;
- }
- }
-
- snprintf(intf_name, sizeof intf_name, "%s.%04x",
- ppriv->dev->name, pkey);
- priv = ipoib_intf_alloc(intf_name);
- if (!priv) {
- result = -ENOMEM;
- goto err;
- }
-
priv->max_ib_mtu = ppriv->max_ib_mtu;
/* MTU will be reset when mcast join happens */
priv->dev->mtu = IPOIB_UD_MTU(priv->max_ib_mtu);
@@ -124,24 +88,27 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
ipoib_create_debug_files(priv->dev);
- if (ipoib_cm_add_mode_attr(priv->dev))
- goto sysfs_failed;
- if (ipoib_add_pkey_attr(priv->dev))
- goto sysfs_failed;
- if (ipoib_add_umcast_attr(priv->dev))
- goto sysfs_failed;
-
- if (device_create_file(&priv->dev->dev, &dev_attr_parent))
- goto sysfs_failed;
+ /* RTNL childs don't need proprietary sysfs entries */
+ if (type == IPOIB_LEGACY_CHILD) {
+ if (ipoib_cm_add_mode_attr(priv->dev))
+ goto sysfs_failed;
+ if (ipoib_add_pkey_attr(priv->dev))
+ goto sysfs_failed;
+ if (ipoib_add_umcast_attr(priv->dev))
+ goto sysfs_failed;
+
+ if (device_create_file(&priv->dev->dev, &dev_attr_parent))
+ goto sysfs_failed;
+ }
+ priv->child_type = type;
+ priv->dev->iflink = ppriv->dev->ifindex;
list_add_tail(&priv->list, &ppriv->child_intfs);
- mutex_unlock(&ppriv->vlan_mutex);
- rtnl_unlock();
-
return 0;
sysfs_failed:
+ result = -ENOMEM;
ipoib_delete_debug_files(priv->dev);
unregister_netdevice(priv->dev);
@@ -149,11 +116,60 @@ register_failed:
ipoib_dev_cleanup(priv->dev);
err:
+ return result;
+}
+
+int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
+{
+ struct ipoib_dev_priv *ppriv, *priv;
+ char intf_name[IFNAMSIZ];
+ struct ipoib_dev_priv *tpriv;
+ int result;
+
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
+ ppriv = netdev_priv(pdev);
+
+ snprintf(intf_name, sizeof intf_name, "%s.%04x",
+ ppriv->dev->name, pkey);
+ priv = ipoib_intf_alloc(intf_name);
+ if (!priv)
+ return -ENOMEM;
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ mutex_lock(&ppriv->vlan_mutex);
+
+ /*
+ * First ensure this isn't a duplicate. We check the parent device and
+ * then all of the legacy child interfaces to make sure the Pkey
+ * doesn't match.
+ */
+ if (ppriv->pkey == pkey) {
+ result = -ENOTUNIQ;
+ goto out;
+ }
+
+ list_for_each_entry(tpriv, &ppriv->child_intfs, list) {
+ if (tpriv->pkey == pkey &&
+ tpriv->child_type == IPOIB_LEGACY_CHILD) {
+ result = -ENOTUNIQ;
+ goto out;
+ }
+ }
+
+ result = __ipoib_vlan_add(ppriv, priv, pkey, IPOIB_LEGACY_CHILD);
+
+out:
mutex_unlock(&ppriv->vlan_mutex);
- rtnl_unlock();
- if (priv)
+
+ if (result)
free_netdev(priv->dev);
+ rtnl_unlock();
+
return result;
}
@@ -171,9 +187,9 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
return restart_syscall();
mutex_lock(&ppriv->vlan_mutex);
list_for_each_entry_safe(priv, tpriv, &ppriv->child_intfs, list) {
- if (priv->pkey == pkey) {
+ if (priv->pkey == pkey &&
+ priv->child_type == IPOIB_LEGACY_CHILD) {
unregister_netdevice(priv->dev);
- ipoib_dev_cleanup(priv->dev);
list_del(&priv->list);
dev = priv->dev;
break;