7 files changed, 135 insertions, 60 deletions

diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index ecc3fa28f666..b7091d5ca2f8 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -18,11 +18,7 @@
 
 #include "internals.h"
 
-/**
- *      dynamic_irq_init - initialize a dynamically allocated irq
- *      @irq:   irq number to initialize
- */
-void dynamic_irq_init(unsigned int irq)
+static void dynamic_irq_init_x(unsigned int irq, bool keep_chip_data)
 {
         struct irq_desc *desc;
         unsigned long flags;
@@ -41,7 +37,8 @@ void dynamic_irq_init(unsigned int irq)
         desc->depth = 1;
         desc->msi_desc = NULL;
         desc->handler_data = NULL;
-        desc->chip_data = NULL;
+        if (!keep_chip_data)
+                desc->chip_data = NULL;
         desc->action = NULL;
         desc->irq_count = 0;
         desc->irqs_unhandled = 0;
@@ -55,10 +52,26 @@ void dynamic_irq_init(unsigned int irq)
 }
 
 /**
- *      dynamic_irq_cleanup - cleanup a dynamically allocated irq
+ *      dynamic_irq_init - initialize a dynamically allocated irq
  *      @irq:   irq number to initialize
  */
-void dynamic_irq_cleanup(unsigned int irq)
+void dynamic_irq_init(unsigned int irq)
+{
+        dynamic_irq_init_x(irq, false);
+}
+
+/**
+ *      dynamic_irq_init_keep_chip_data - initialize a dynamically allocated irq
+ *      @irq:   irq number to initialize
+ *
+ *      does not set irq_to_desc(irq)->chip_data to NULL
+ */
+void dynamic_irq_init_keep_chip_data(unsigned int irq)
+{
+        dynamic_irq_init_x(irq, true);
+}
+
+static void dynamic_irq_cleanup_x(unsigned int irq, bool keep_chip_data)
 {
         struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
@@ -77,7 +90,8 @@ void dynamic_irq_cleanup(unsigned int irq)
         }
         desc->msi_desc = NULL;
         desc->handler_data = NULL;
-        desc->chip_data = NULL;
+        if (!keep_chip_data)
+                desc->chip_data = NULL;
         desc->handle_irq = handle_bad_irq;
         desc->chip = &no_irq_chip;
         desc->name = NULL;
@@ -85,6 +99,26 @@ void dynamic_irq_cleanup(unsigned int irq)
         raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
 
+/**
+ *      dynamic_irq_cleanup - cleanup a dynamically allocated irq
+ *      @irq:   irq number to initialize
+ */
+void dynamic_irq_cleanup(unsigned int irq)
+{
+        dynamic_irq_cleanup_x(irq, false);
+}
+
+/**
+ *      dynamic_irq_cleanup_keep_chip_data - cleanup a dynamically allocated irq
+ *      @irq:   irq number to initialize
+ *
+ *      does not set irq_to_desc(irq)->chip_data to NULL
+ */
+void dynamic_irq_cleanup_keep_chip_data(unsigned int irq)
+{
+        dynamic_irq_cleanup_x(irq, true);
+}
+
 
 /**
  *      set_irq_chip - set the irq chip for an irq
@@ -325,6 +359,23 @@ static inline void mask_ack_irq(struct irq_desc *desc, int irq)
                 if (desc->chip->ack)
                         desc->chip->ack(irq);
         }
+        desc->status |= IRQ_MASKED;
+}
+
+static inline void mask_irq(struct irq_desc *desc, int irq)
+{
+        if (desc->chip->mask) {
+                desc->chip->mask(irq);
+                desc->status |= IRQ_MASKED;
+        }
+}
+
+static inline void unmask_irq(struct irq_desc *desc, int irq)
+{
+        if (desc->chip->unmask) {
+                desc->chip->unmask(irq);
+                desc->status &= ~IRQ_MASKED;
+        }
 }
 
 /*
@@ -450,10 +501,8 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
         raw_spin_lock(&desc->lock);
         desc->status &= ~IRQ_INPROGRESS;
 
-        if (unlikely(desc->status & IRQ_ONESHOT))
-                desc->status |= IRQ_MASKED;
-        else if (!(desc->status & IRQ_DISABLED) && desc->chip->unmask)
-                desc->chip->unmask(irq);
+        if (!(desc->status & (IRQ_DISABLED | IRQ_ONESHOT)))
+                unmask_irq(desc, irq);
 out_unlock:
         raw_spin_unlock(&desc->lock);
 }
@@ -490,8 +539,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
         action = desc->action;
         if (unlikely(!action || (desc->status & IRQ_DISABLED))) {
                 desc->status |= IRQ_PENDING;
-                if (desc->chip->mask)
-                        desc->chip->mask(irq);
+                mask_irq(desc, irq);
                 goto out;
         }
 
@@ -520,7 +568,7 @@ out:
  *      signal. The occurence is latched into the irq controller hardware
  *      and must be acked in order to be reenabled. After the ack another
  *      interrupt can happen on the same source even before the first one
- *      is handled by the assosiacted event handler. If this happens it
+ *      is handled by the associated event handler. If this happens it
  *      might be necessary to disable (mask) the interrupt depending on the
  *      controller hardware. This requires to reenable the interrupt inside
  *      of the loop which handles the interrupts which have arrived while
@@ -559,7 +607,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
                 irqreturn_t action_ret;
 
                 if (unlikely(!action)) {
-                        desc->chip->mask(irq);
+                        mask_irq(desc, irq);
                         goto out_unlock;
                 }
 
@@ -571,8 +619,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
                 if (unlikely((desc->status &
                                (IRQ_PENDING | IRQ_MASKED | IRQ_DISABLED)) ==
                               (IRQ_PENDING | IRQ_MASKED))) {
-                        desc->chip->unmask(irq);
-                        desc->status &= ~IRQ_MASKED;
+                        unmask_irq(desc, irq);
                 }
 
                 desc->status &= ~IRQ_PENDING;
@@ -682,7 +729,7 @@ set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
         __set_irq_handler(irq, handle, 0, name);
 }
 
-void __init set_irq_noprobe(unsigned int irq)
+void set_irq_noprobe(unsigned int irq)
 {
         struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
@@ -697,7 +744,7 @@ void __init set_irq_noprobe(unsigned int irq)
         raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
 
-void __init set_irq_probe(unsigned int irq)
+void set_irq_probe(unsigned int irq)
 {
         struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c
index d06df9c41cba..1ef4ffcdfa55 100644
--- a/kernel/irq/devres.c
+++ b/kernel/irq/devres.c
@@ -42,7 +42,7 @@ static int devm_irq_match(struct device *dev, void *res, void *data)
  *      automatically freed on driver detach.
  *
  *      If an IRQ allocated with this function needs to be freed
- *      separately, dev_free_irq() must be used.
+ *      separately, devm_free_irq() must be used.
  */
 int devm_request_threaded_irq(struct device *dev, unsigned int irq,
                               irq_handler_t handler, irq_handler_t thread_fn,
@@ -81,7 +81,7 @@ EXPORT_SYMBOL(devm_request_threaded_irq);
  *      Except for the extra @dev argument, this function takes the
  *      same arguments and performs the same function as free_irq().
  *      This function instead of free_irq() should be used to manually
- *      free IRQs allocated with dev_request_irq().
+ *      free IRQs allocated with devm_request_irq().
  */
 void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id)
 {
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 814940e7f485..76d5a671bfe1 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -19,7 +19,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/rculist.h>
 #include <linux/hash.h>
-#include <linux/bootmem.h>
+#include <linux/radix-tree.h>
 #include <trace/events/irq.h>
 
 #include "internals.h"
@@ -87,12 +87,8 @@ void __ref init_kstat_irqs(struct irq_desc *desc, int node, int nr)
 {
         void *ptr;
 
-        if (slab_is_available())
-                ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs),
-                                   GFP_ATOMIC, node);
-        else
-                ptr = alloc_bootmem_node(NODE_DATA(node),
-                                nr * sizeof(*desc->kstat_irqs));
+        ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs),
+                           GFP_ATOMIC, node);
 
         /*
          * don't overwite if can not get new one
@@ -132,7 +128,26 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int node)
  */
 DEFINE_RAW_SPINLOCK(sparse_irq_lock);
 
-struct irq_desc **irq_desc_ptrs __read_mostly;
+static RADIX_TREE(irq_desc_tree, GFP_ATOMIC);
+
+static void set_irq_desc(unsigned int irq, struct irq_desc *desc)
+{
+        radix_tree_insert(&irq_desc_tree, irq, desc);
+}
+
+struct irq_desc *irq_to_desc(unsigned int irq)
+{
+        return radix_tree_lookup(&irq_desc_tree, irq);
+}
+
+void replace_irq_desc(unsigned int irq, struct irq_desc *desc)
+{
+        void **ptr;
+
+        ptr = radix_tree_lookup_slot(&irq_desc_tree, irq);
+        if (ptr)
+                radix_tree_replace_slot(ptr, desc);
+}
 
 static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = {
         [0 ... NR_IRQS_LEGACY-1] = {
@@ -164,9 +179,6 @@ int __init early_irq_init(void)
         legacy_count = ARRAY_SIZE(irq_desc_legacy);
         node = first_online_node;
 
-        /* allocate irq_desc_ptrs array based on nr_irqs */
-        irq_desc_ptrs = kcalloc(nr_irqs, sizeof(void *), GFP_NOWAIT);
-
         /* allocate based on nr_cpu_ids */
         kstat_irqs_legacy = kzalloc_node(NR_IRQS_LEGACY * nr_cpu_ids *
                                           sizeof(int), GFP_NOWAIT, node);
@@ -180,23 +192,12 @@ int __init early_irq_init(void)
                 lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
                 alloc_desc_masks(&desc[i], node, true);
                 init_desc_masks(&desc[i]);
-                irq_desc_ptrs[i] = desc + i;
+                set_irq_desc(i, &desc[i]);
         }
 
-        for (i = legacy_count; i < nr_irqs; i++)
-                irq_desc_ptrs[i] = NULL;
-
         return arch_early_irq_init();
 }
 
-struct irq_desc *irq_to_desc(unsigned int irq)
-{
-        if (irq_desc_ptrs && irq < nr_irqs)
-                return irq_desc_ptrs[irq];
-
-        return NULL;
-}
-
 struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
 {
         struct irq_desc *desc;
@@ -208,21 +209,18 @@ struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
                 return NULL;
         }
 
-        desc = irq_desc_ptrs[irq];
+        desc = irq_to_desc(irq);
         if (desc)
                 return desc;
 
         raw_spin_lock_irqsave(&sparse_irq_lock, flags);
 
         /* We have to check it to avoid races with another CPU */
-        desc = irq_desc_ptrs[irq];
+        desc = irq_to_desc(irq);
         if (desc)
                 goto out_unlock;
 
-        if (slab_is_available())
-                desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
-        else
-                desc = alloc_bootmem_node(NODE_DATA(node), sizeof(*desc));
+        desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
 
         printk(KERN_DEBUG "  alloc irq_desc for %d on node %d\n", irq, node);
         if (!desc) {
@@ -231,7 +229,7 @@ struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
         }
         init_one_irq_desc(irq, desc, node);
 
-        irq_desc_ptrs[irq] = desc;
+        set_irq_desc(irq, desc);
 
 out_unlock:
         raw_spin_unlock_irqrestore(&sparse_irq_lock, flags);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index b2821f070a3d..c63f3bc88f0b 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -21,11 +21,7 @@ extern void clear_kstat_irqs(struct irq_desc *desc);
 extern raw_spinlock_t sparse_irq_lock;
 
 #ifdef CONFIG_SPARSE_IRQ
-/* irq_desc_ptrs allocated at boot time */
-extern struct irq_desc **irq_desc_ptrs;
-#else
-/* irq_desc_ptrs is a fixed size array */
-extern struct irq_desc *irq_desc_ptrs[NR_IRQS];
+void replace_irq_desc(unsigned int irq, struct irq_desc *desc);
 #endif
 
 #ifdef CONFIG_PROC_FS
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index eb6078ca60c7..704e488730a5 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -382,6 +382,7 @@ int can_request_irq(unsigned int irq, unsigned long irqflags)
 {
         struct irq_desc *desc = irq_to_desc(irq);
         struct irqaction *action;
+        unsigned long flags;
 
         if (!desc)
                 return 0;
@@ -389,11 +390,14 @@ int can_request_irq(unsigned int irq, unsigned long irqflags)
         if (desc->status & IRQ_NOREQUEST)
                 return 0;
 
+        raw_spin_lock_irqsave(&desc->lock, flags);
         action = desc->action;
         if (action)
                 if (irqflags & action->flags & IRQF_SHARED)
                         action = NULL;
 
+        raw_spin_unlock_irqrestore(&desc->lock, flags);
+
         return !action;
 }
 
@@ -483,8 +487,26 @@ static int irq_wait_for_interrupt(struct irqaction *action)
  */
 static void irq_finalize_oneshot(unsigned int irq, struct irq_desc *desc)
 {
+again:
         chip_bus_lock(irq, desc);
         raw_spin_lock_irq(&desc->lock);
+
+        /*
+         * Implausible though it may be we need to protect us against
+         * the following scenario:
+         *
+         * The thread is faster done than the hard interrupt handler
+         * on the other CPU. If we unmask the irq line then the
+         * interrupt can come in again and masks the line, leaves due
+         * to IRQ_INPROGRESS and the irq line is masked forever.
+         */
+        if (unlikely(desc->status & IRQ_INPROGRESS)) {
+                raw_spin_unlock_irq(&desc->lock);
+                chip_bus_sync_unlock(irq, desc);
+                cpu_relax();
+                goto again;
+        }
+
         if (!(desc->status & IRQ_DISABLED) && (desc->status & IRQ_MASKED)) {
                 desc->status &= ~IRQ_MASKED;
                 desc->chip->unmask(irq);
@@ -735,6 +757,16 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
                 if (new->flags & IRQF_ONESHOT)
                         desc->status |= IRQ_ONESHOT;
 
+                /*
+                 * Force MSI interrupts to run with interrupts
+                 * disabled. The multi vector cards can cause stack
+                 * overflows due to nested interrupts when enough of
+                 * them are directed to a core and fire at the same
+                 * time.
+                 */
+                if (desc->msi_desc)
+                        new->flags |= IRQF_DISABLED;
+
                 if (!(desc->status & IRQ_NOAUTOEN)) {
                         desc->depth = 0;
                         desc->status &= ~IRQ_DISABLED;
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index 26bac9d8f860..65d3845665ac 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/irq.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/interrupt.h>
@@ -70,7 +71,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
         raw_spin_lock_irqsave(&sparse_irq_lock, flags);
 
         /* We have to check it to avoid races with another CPU */
-        desc = irq_desc_ptrs[irq];
+        desc = irq_to_desc(irq);
 
         if (desc && old_desc != desc)
                 goto out_unlock;
@@ -90,7 +91,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
                 goto out_unlock;
         }
 
-        irq_desc_ptrs[irq] = desc;
+        replace_irq_desc(irq, desc);
         raw_spin_unlock_irqrestore(&sparse_irq_lock, flags);
 
         /* free the old one */
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 6f50eccc79c0..7a6eb04ef6b5 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/irq.h>
+#include <linux/gfp.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>