Merge branch 'next' (accumulated 3.16 merge window patches) into master

Now that 3.15 is released, this merges the 'next' branch into 'master',
bringing us to the normal situation where my 'master' branch is the
merge window.

* accumulated work in next: (6809 commits)
  ufs: sb mutex merge + mutex_destroy
  powerpc: update comments for generic idle conversion
  cris: update comments for generic idle conversion
  idle: remove cpu_idle() forward declarations
  nbd: zero from and len fields in NBD_CMD_DISCONNECT.
  mm: convert some level-less printks to pr_*
  MAINTAINERS: adi-buildroot-devel is moderated
  MAINTAINERS: add linux-api for review of API/ABI changes
  mm/kmemleak-test.c: use pr_fmt for logging
  fs/dlm/debug_fs.c: replace seq_printf by seq_puts
  fs/dlm/lockspace.c: convert simple_str to kstr
  fs/dlm/config.c: convert simple_str to kstr
  mm: mark remap_file_pages() syscall as deprecated
  mm: memcontrol: remove unnecessary memcg argument from soft limit functions
  mm: memcontrol: clean up memcg zoneinfo lookup
  mm/memblock.c: call kmemleak directly from memblock_(alloc|free)
  mm/mempool.c: update the kmemleak stack trace for mempool allocations
  lib/radix-tree.c: update the kmemleak stack trace for radix tree allocations
  mm: introduce kmemleak_update_trace()
  mm/kmemleak.c: use %u to print ->checksum
  ...

7 files changed, 188 insertions, 45 deletions

diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 07cbdfea9ae2..d269cecdfbf0 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -5,6 +5,10 @@ menu "IRQ subsystem"
 config MAY_HAVE_SPARSE_IRQ
        bool
 
+# Legacy support, required for itanic
+config GENERIC_IRQ_LEGACY
+       bool
+
 # Enable the generic irq autoprobe mechanism
 config GENERIC_IRQ_PROBE
 	bool
@@ -17,6 +21,11 @@ config GENERIC_IRQ_SHOW
 config GENERIC_IRQ_SHOW_LEVEL
        bool
 
+# Facility to allocate a hardware interrupt. This is legacy support
+# and should not be used in new code. Use irq domains instead.
+config GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
+       bool
+
 # Support for delayed migration from interrupt context
 config GENERIC_PENDING_IRQ
 	bool
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 6397df2d6945..a2b28a2fd7b1 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -40,10 +40,9 @@ int irq_set_chip(unsigned int irq, struct irq_chip *chip)
 	irq_put_desc_unlock(desc, flags);
 	/*
 	 * For !CONFIG_SPARSE_IRQ make the irq show up in
-	 * allocated_irqs. For the CONFIG_SPARSE_IRQ case, it is
-	 * already marked, and this call is harmless.
+	 * allocated_irqs.
 	 */
-	irq_reserve_irq(irq);
+	irq_mark_irq(irq);
 	return 0;
 }
 EXPORT_SYMBOL(irq_set_chip);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index ddf1ffeb79f1..099ea2e0eb88 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -33,7 +33,7 @@ enum {
 };
 
 /*
- * Bit masks for desc->state
+ * Bit masks for desc->core_internal_state__do_not_mess_with_it
  *
  * IRQS_AUTODETECT		- autodetection in progress
  * IRQS_SPURIOUS_DISABLED	- was disabled due to spurious interrupt
@@ -76,6 +76,12 @@ extern void mask_irq(struct irq_desc *desc);
 extern void unmask_irq(struct irq_desc *desc);
 extern void unmask_threaded_irq(struct irq_desc *desc);
 
+#ifdef CONFIG_SPARSE_IRQ
+static inline void irq_mark_irq(unsigned int irq) { }
+#else
+extern void irq_mark_irq(unsigned int irq);
+#endif
+
 extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
 
 irqreturn_t handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index bb07f2928f4b..7339e42a85ab 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -278,7 +278,12 @@ EXPORT_SYMBOL(irq_to_desc);
 
 static void free_desc(unsigned int irq)
 {
-	dynamic_irq_cleanup(irq);
+	struct irq_desc *desc = irq_to_desc(irq);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+	desc_set_defaults(irq, desc, desc_node(desc), NULL);
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
 
 static inline int alloc_descs(unsigned int start, unsigned int cnt, int node,
@@ -299,6 +304,20 @@ static int irq_expand_nr_irqs(unsigned int nr)
 	return -ENOMEM;
 }
 
+void irq_mark_irq(unsigned int irq)
+{
+	mutex_lock(&sparse_irq_lock);
+	bitmap_set(allocated_irqs, irq, 1);
+	mutex_unlock(&sparse_irq_lock);
+}
+
+#ifdef CONFIG_GENERIC_IRQ_LEGACY
+void irq_init_desc(unsigned int irq)
+{
+	free_desc(irq);
+}
+#endif
+
 #endif /* !CONFIG_SPARSE_IRQ */
 
 /**
@@ -396,30 +415,56 @@ err:
 }
 EXPORT_SYMBOL_GPL(__irq_alloc_descs);
 
+#ifdef CONFIG_GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
 /**
- * irq_reserve_irqs - mark irqs allocated
- * @from:	mark from irq number
- * @cnt:	number of irqs to mark
+ * irq_alloc_hwirqs - Allocate an irq descriptor and initialize the hardware
+ * @cnt:	number of interrupts to allocate
+ * @node:	node on which to allocate
  *
- * Returns 0 on success or an appropriate error code
+ * Returns an interrupt number > 0 or 0, if the allocation fails.
  */
-int irq_reserve_irqs(unsigned int from, unsigned int cnt)
+unsigned int irq_alloc_hwirqs(int cnt, int node)
 {
-	unsigned int start;
-	int ret = 0;
+	int i, irq = __irq_alloc_descs(-1, 0, cnt, node, NULL);
 
-	if (!cnt || (from + cnt) > nr_irqs)
-		return -EINVAL;
+	if (irq < 0)
+		return 0;
 
-	mutex_lock(&sparse_irq_lock);
-	start = bitmap_find_next_zero_area(allocated_irqs, nr_irqs, from, cnt, 0);
-	if (start == from)
-		bitmap_set(allocated_irqs, start, cnt);
-	else
-		ret = -EEXIST;
-	mutex_unlock(&sparse_irq_lock);
-	return ret;
+	for (i = irq; cnt > 0; i++, cnt--) {
+		if (arch_setup_hwirq(i, node))
+			goto err;
+		irq_clear_status_flags(i, _IRQ_NOREQUEST);
+	}
+	return irq;
+
+err:
+	for (i--; i >= irq; i--) {
+		irq_set_status_flags(i, _IRQ_NOREQUEST | _IRQ_NOPROBE);
+		arch_teardown_hwirq(i);
+	}
+	irq_free_descs(irq, cnt);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(irq_alloc_hwirqs);
+
+/**
+ * irq_free_hwirqs - Free irq descriptor and cleanup the hardware
+ * @from:	Free from irq number
+ * @cnt:	number of interrupts to free
+ *
+ */
+void irq_free_hwirqs(unsigned int from, int cnt)
+{
+	int i;
+
+	for (i = from; cnt > 0; i++, cnt--) {
+		irq_set_status_flags(i, _IRQ_NOREQUEST | _IRQ_NOPROBE);
+		arch_teardown_hwirq(i);
+	}
+	irq_free_descs(from, cnt);
 }
+EXPORT_SYMBOL_GPL(irq_free_hwirqs);
+#endif
 
 /**
  * irq_get_next_irq - get next allocated irq number
@@ -482,20 +527,6 @@ int irq_set_percpu_devid(unsigned int irq)
 	return 0;
 }
 
-/**
- * dynamic_irq_cleanup - cleanup a dynamically allocated irq
- * @irq:	irq number to initialize
- */
-void dynamic_irq_cleanup(unsigned int irq)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc_set_defaults(irq, desc, desc_node(desc), NULL);
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-}
-
 void kstat_incr_irq_this_cpu(unsigned int irq)
 {
 	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index f14033700c25..eb5e10e32e05 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -27,14 +27,14 @@ static struct irq_domain *irq_default_domain;
  * __irq_domain_add() - Allocate a new irq_domain data structure
  * @of_node: optional device-tree node of the interrupt controller
  * @size: Size of linear map; 0 for radix mapping only
+ * @hwirq_max: Maximum number of interrupts supported by controller
  * @direct_max: Maximum value of direct maps; Use ~0 for no limit; 0 for no
  *              direct mapping
  * @ops: map/unmap domain callbacks
  * @host_data: Controller private data pointer
  *
- * Allocates and initialize and irq_domain structure.  Caller is expected to
- * register allocated irq_domain with irq_domain_register().  Returns pointer
- * to IRQ domain, or NULL on failure.
+ * Allocates and initialize and irq_domain structure.
+ * Returns pointer to IRQ domain, or NULL on failure.
  */
 struct irq_domain *__irq_domain_add(struct device_node *of_node, int size,
 				    irq_hw_number_t hwirq_max, int direct_max,
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index d34131ca372b..3dc6a61bf06a 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -886,8 +886,8 @@ static int irq_thread(void *data)
 		irq_thread_check_affinity(desc, action);
 
 		action_ret = handler_fn(desc, action);
-		if (!noirqdebug)
-			note_interrupt(action->irq, desc, action_ret);
+		if (action_ret == IRQ_HANDLED)
+			atomic_inc(&desc->threads_handled);
 
 		wake_threads_waitq(desc);
 	}
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index a1d8cc63b56e..e2514b0e439e 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -270,6 +270,8 @@ try_misrouted_irq(unsigned int irq, struct irq_desc *desc,
 	return action && (action->flags & IRQF_IRQPOLL);
 }
 
+#define SPURIOUS_DEFERRED	0x80000000
+
 void note_interrupt(unsigned int irq, struct irq_desc *desc,
 		    irqreturn_t action_ret)
 {
@@ -277,15 +279,111 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc,
 	    irq_settings_is_polled(desc))
 		return;
 
-	/* we get here again via the threaded handler */
-	if (action_ret == IRQ_WAKE_THREAD)
-		return;
-
 	if (bad_action_ret(action_ret)) {
 		report_bad_irq(irq, desc, action_ret);
 		return;
 	}
 
+	/*
+	 * We cannot call note_interrupt from the threaded handler
+	 * because we need to look at the compound of all handlers
+	 * (primary and threaded). Aside of that in the threaded
+	 * shared case we have no serialization against an incoming
+	 * hardware interrupt while we are dealing with a threaded
+	 * result.
+	 *
+	 * So in case a thread is woken, we just note the fact and
+	 * defer the analysis to the next hardware interrupt.
+	 *
+	 * The threaded handlers store whether they sucessfully
+	 * handled an interrupt and we check whether that number
+	 * changed versus the last invocation.
+	 *
+	 * We could handle all interrupts with the delayed by one
+	 * mechanism, but for the non forced threaded case we'd just
+	 * add pointless overhead to the straight hardirq interrupts
+	 * for the sake of a few lines less code.
+	 */
+	if (action_ret & IRQ_WAKE_THREAD) {
+		/*
+		 * There is a thread woken. Check whether one of the
+		 * shared primary handlers returned IRQ_HANDLED. If
+		 * not we defer the spurious detection to the next
+		 * interrupt.
+		 */
+		if (action_ret == IRQ_WAKE_THREAD) {
+			int handled;
+			/*
+			 * We use bit 31 of thread_handled_last to
+			 * denote the deferred spurious detection
+			 * active. No locking necessary as
+			 * thread_handled_last is only accessed here
+			 * and we have the guarantee that hard
+			 * interrupts are not reentrant.
+			 */
+			if (!(desc->threads_handled_last & SPURIOUS_DEFERRED)) {
+				desc->threads_handled_last |= SPURIOUS_DEFERRED;
+				return;
+			}
+			/*
+			 * Check whether one of the threaded handlers
+			 * returned IRQ_HANDLED since the last
+			 * interrupt happened.
+			 *
+			 * For simplicity we just set bit 31, as it is
+			 * set in threads_handled_last as well. So we
+			 * avoid extra masking. And we really do not
+			 * care about the high bits of the handled
+			 * count. We just care about the count being
+			 * different than the one we saw before.
+			 */
+			handled = atomic_read(&desc->threads_handled);
+			handled |= SPURIOUS_DEFERRED;
+			if (handled != desc->threads_handled_last) {
+				action_ret = IRQ_HANDLED;
+				/*
+				 * Note: We keep the SPURIOUS_DEFERRED
+				 * bit set. We are handling the
+				 * previous invocation right now.
+				 * Keep it for the current one, so the
+				 * next hardware interrupt will
+				 * account for it.
+				 */
+				desc->threads_handled_last = handled;
+			} else {
+				/*
+				 * None of the threaded handlers felt
+				 * responsible for the last interrupt
+				 *
+				 * We keep the SPURIOUS_DEFERRED bit
+				 * set in threads_handled_last as we
+				 * need to account for the current
+				 * interrupt as well.
+				 */
+				action_ret = IRQ_NONE;
+			}
+		} else {
+			/*
+			 * One of the primary handlers returned
+			 * IRQ_HANDLED. So we don't care about the
+			 * threaded handlers on the same line. Clear
+			 * the deferred detection bit.
+			 *
+			 * In theory we could/should check whether the
+			 * deferred bit is set and take the result of
+			 * the previous run into account here as
+			 * well. But it's really not worth the
+			 * trouble. If every other interrupt is
+			 * handled we never trigger the spurious
+			 * detector. And if this is just the one out
+			 * of 100k unhandled ones which is handled
+			 * then we merily delay the spurious detection
+			 * by one hard interrupt. Not a real problem.
+			 */
+			desc->threads_handled_last &= ~SPURIOUS_DEFERRED;
+		}
+	}
+
 	if (unlikely(action_ret == IRQ_NONE)) {
 		/*
 		 * If we are seeing only the odd spurious IRQ caused by