Merge branch 'for-rmk/perf' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux into devel-stable

  * Support for Qualcomm Krait processors (run perf on your phone!)
  * Support for Cortex-A12 (run perf stat on your FPGA!)
  * Support for perf_sample_event_took, allowing us to automatically decrease
    the sample rate if we can't handle the PMU interrupts quickly enough
    (run perf record on your FPGA!).

As part of the Krait support, we also gain support for PPI generation by
the PMU.

15 files changed, 181 insertions, 92 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 70654521dab6..5a4d39b4686b 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -250,6 +250,17 @@ static inline unsigned bio_segments(struct bio *bio)
 	struct bio_vec bv;
 	struct bvec_iter iter;
 
+	/*
+	 * We special case discard/write same, because they interpret bi_size
+	 * differently:
+	 */
+
+	if (bio->bi_rw & REQ_DISCARD)
+		return 1;
+
+	if (bio->bi_rw & REQ_WRITE_SAME)
+		return 1;
+
 	bio_for_each_segment(bv, bio, iter)
 		segs++;
 
@@ -332,6 +343,7 @@ extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *);
 extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs);
 
 extern struct bio_set *fs_bio_set;
+unsigned int bio_integrity_tag_size(struct bio *bio);
 
 static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
 {
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 161b23105b1e..18ba8a627f46 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -83,6 +83,8 @@ struct blk_mq_ops {
 	 */
 	rq_timed_out_fn		*timeout;
 
+	softirq_done_fn		*complete;
+
 	/*
 	 * Override for hctx allocations (should probably go)
 	 */
@@ -119,11 +121,12 @@ void blk_mq_init_commands(struct request_queue *, void (*init)(void *data, struc
 
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
 
-void blk_mq_insert_request(struct request_queue *, struct request *, bool);
+void blk_mq_insert_request(struct request_queue *, struct request *,
+		bool, bool);
 void blk_mq_run_queues(struct request_queue *q, bool async);
 void blk_mq_free_request(struct request *rq);
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
-struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp, bool reserved);
+struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp);
 struct request *blk_mq_alloc_reserved_request(struct request_queue *q, int rw, gfp_t gfp);
 struct request *blk_mq_rq_from_tag(struct request_queue *q, unsigned int tag);
 
@@ -133,6 +136,8 @@ void blk_mq_free_single_hw_queue(struct blk_mq_hw_ctx *, unsigned int);
 
 void blk_mq_end_io(struct request *rq, int error);
 
+void blk_mq_complete_request(struct request *rq);
+
 void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
 void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx);
 void blk_mq_stop_hw_queues(struct request_queue *q);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8678c4322b44..4afa4f8f6090 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -98,7 +98,7 @@ struct request {
 	struct list_head queuelist;
 	union {
 		struct call_single_data csd;
-		struct work_struct mq_flush_data;
+		struct work_struct mq_flush_work;
 	};
 
 	struct request_queue *q;
@@ -448,13 +448,8 @@ struct request_queue {
 	unsigned long		flush_pending_since;
 	struct list_head	flush_queue[2];
 	struct list_head	flush_data_in_flight;
-	union {
-		struct request	flush_rq;
-		struct {
-			spinlock_t mq_flush_lock;
-			struct work_struct mq_flush_work;
-		};
-	};
+	struct request		*flush_rq;
+	spinlock_t		mq_flush_lock;
 
 	struct mutex		sysfs_lock;
 
diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h
index 2f0543f7510c..f9bbbb472663 100644
--- a/include/linux/can/skb.h
+++ b/include/linux/can/skb.h
@@ -11,7 +11,9 @@
 #define CAN_SKB_H
 
 #include <linux/types.h>
+#include <linux/skbuff.h>
 #include <linux/can.h>
+#include <net/sock.h>
 
 /*
  * The struct can_skb_priv is used to transport additional information along
@@ -42,4 +44,40 @@ static inline void can_skb_reserve(struct sk_buff *skb)
 	skb_reserve(skb, sizeof(struct can_skb_priv));
 }
 
+static inline void can_skb_destructor(struct sk_buff *skb)
+{
+	sock_put(skb->sk);
+}
+
+static inline void can_skb_set_owner(struct sk_buff *skb, struct sock *sk)
+{
+	if (sk) {
+		sock_hold(sk);
+		skb->destructor = can_skb_destructor;
+		skb->sk = sk;
+	}
+}
+
+/*
+ * returns an unshared skb owned by the original sock to be echo'ed back
+ */
+static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb)
+{
+	if (skb_shared(skb)) {
+		struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+
+		if (likely(nskb)) {
+			can_skb_set_owner(nskb, skb->sk);
+			consume_skb(skb);
+			return nskb;
+		} else {
+			kfree_skb(skb);
+			return NULL;
+		}
+	}
+
+	/* we can assume to have an unshared skb with proper owner */
+	return skb;
+}
+
 #endif /* CAN_SKB_H */
diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h
index ded429966c1f..2507fd2a1eb4 100644
--- a/include/linux/compiler-gcc4.h
+++ b/include/linux/compiler-gcc4.h
@@ -75,11 +75,7 @@
  *
  * (asm goto is automatically volatile - the naming reflects this.)
  */
-#if GCC_VERSION <= 40801
-# define asm_volatile_goto(x...)	do { asm goto(x); asm (""); } while (0)
-#else
-# define asm_volatile_goto(x...)	do { asm goto(x); } while (0)
-#endif
+#define asm_volatile_goto(x...)	do { asm goto(x); asm (""); } while (0)
 
 #ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP
 #if GCC_VERSION >= 40400
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index 4d34dbbbad4d..7a8144fef406 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -4,8 +4,6 @@
 #include <linux/err.h>
 #include <linux/kernel.h>
 
-#ifdef CONFIG_GPIOLIB
-
 struct device;
 struct gpio_chip;
 
@@ -18,6 +16,8 @@ struct gpio_chip;
  */
 struct gpio_desc;
 
+#ifdef CONFIG_GPIOLIB
+
 /* Acquire and dispose GPIOs */
 struct gpio_desc *__must_check gpiod_get(struct device *dev,
 					 const char *con_id);
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 15da677478dd..344883dce584 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -875,7 +875,7 @@ struct vmbus_channel_relid_released {
 struct vmbus_channel_initiate_contact {
 	struct vmbus_channel_message_header header;
 	u32 vmbus_version_requested;
-	u32 padding2;
+	u32 target_vcpu; /* The VCPU the host should respond to */
 	u64 interrupt_page;
 	u64 monitor_page1;
 	u64 monitor_page2;
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 0053adde0ed9..a2678d35b5a2 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -158,6 +158,11 @@ devm_request_irq(struct device *dev, unsigned int irq, irq_handler_t handler,
 					 devname, dev_id);
 }
 
+extern int __must_check
+devm_request_any_context_irq(struct device *dev, unsigned int irq,
+		 irq_handler_t handler, unsigned long irqflags,
+		 const char *devname, void *dev_id);
+
 extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id);
 
 /*
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 554548cd3dd4..130bc8d77fa5 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -38,8 +38,10 @@
 #include <linux/pci.h>
 #include <linux/spinlock_types.h>
 #include <linux/semaphore.h>
+#include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/radix-tree.h>
+
 #include <linux/mlx5/device.h>
 #include <linux/mlx5/doorbell.h>
 
@@ -227,6 +229,7 @@ struct mlx5_uuar_info {
 	 * protect uuar allocation data structs
 	 */
 	struct mutex		lock;
+	u32			ver;
 };
 
 struct mlx5_bf {
diff --git a/include/linux/of.h b/include/linux/of.h
index 70c64ba17fa5..435cb995904d 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -169,35 +169,15 @@ static inline const char *of_node_full_name(const struct device_node *np)
 
 extern struct device_node *of_find_node_by_name(struct device_node *from,
 	const char *name);
-#define for_each_node_by_name(dn, name) \
-	for (dn = of_find_node_by_name(NULL, name); dn; \
-	     dn = of_find_node_by_name(dn, name))
 extern struct device_node *of_find_node_by_type(struct device_node *from,
 	const char *type);
-#define for_each_node_by_type(dn, type) \
-	for (dn = of_find_node_by_type(NULL, type); dn; \
-	     dn = of_find_node_by_type(dn, type))
 extern struct device_node *of_find_compatible_node(struct device_node *from,
 	const char *type, const char *compat);
-#define for_each_compatible_node(dn, type, compatible) \
-	for (dn = of_find_compatible_node(NULL, type, compatible); dn; \
-	     dn = of_find_compatible_node(dn, type, compatible))
 extern struct device_node *of_find_matching_node_and_match(
 	struct device_node *from,
 	const struct of_device_id *matches,
 	const struct of_device_id **match);
-static inline struct device_node *of_find_matching_node(
-	struct device_node *from,
-	const struct of_device_id *matches)
-{
-	return of_find_matching_node_and_match(from, matches, NULL);
-}
-#define for_each_matching_node(dn, matches) \
-	for (dn = of_find_matching_node(NULL, matches); dn; \
-	     dn = of_find_matching_node(dn, matches))
-#define for_each_matching_node_and_match(dn, matches, match) \
-	for (dn = of_find_matching_node_and_match(NULL, matches, match); \
-	     dn; dn = of_find_matching_node_and_match(dn, matches, match))
+
 extern struct device_node *of_find_node_by_path(const char *path);
 extern struct device_node *of_find_node_by_phandle(phandle handle);
 extern struct device_node *of_get_parent(const struct device_node *node);
@@ -209,43 +189,11 @@ extern struct device_node *of_get_next_available_child(
 
 extern struct device_node *of_get_child_by_name(const struct device_node *node,
 					const char *name);
-#define for_each_child_of_node(parent, child) \
-	for (child = of_get_next_child(parent, NULL); child != NULL; \
-	     child = of_get_next_child(parent, child))
-
-#define for_each_available_child_of_node(parent, child) \
-	for (child = of_get_next_available_child(parent, NULL); child != NULL; \
-	     child = of_get_next_available_child(parent, child))
-
-static inline int of_get_child_count(const struct device_node *np)
-{
-	struct device_node *child;
-	int num = 0;
-
-	for_each_child_of_node(np, child)
-		num++;
-
-	return num;
-}
-
-static inline int of_get_available_child_count(const struct device_node *np)
-{
-	struct device_node *child;
-	int num = 0;
-
-	for_each_available_child_of_node(np, child)
-		num++;
-
-	return num;
-}
 
 /* cache lookup */
 extern struct device_node *of_find_next_cache_node(const struct device_node *);
 extern struct device_node *of_find_node_with_property(
 	struct device_node *from, const char *prop_name);
-#define for_each_node_with_property(dn, prop_name) \
-	for (dn = of_find_node_with_property(NULL, prop_name); dn; \
-	     dn = of_find_node_with_property(dn, prop_name))
 
 extern struct property *of_find_property(const struct device_node *np,
 					 const char *name,
@@ -367,42 +315,53 @@ static inline struct device_node *of_find_node_by_name(struct device_node *from,
 	return NULL;
 }
 
-static inline struct device_node *of_get_parent(const struct device_node *node)
+static inline struct device_node *of_find_node_by_type(struct device_node *from,
+	const char *type)
 {
 	return NULL;
 }
 
-static inline bool of_have_populated_dt(void)
+static inline struct device_node *of_find_matching_node_and_match(
+	struct device_node *from,
+	const struct of_device_id *matches,
+	const struct of_device_id **match)
 {
-	return false;
+	return NULL;
 }
 
-/* Kill an unused variable warning on a device_node pointer */
-static inline void __of_use_dn(const struct device_node *np)
+static inline struct device_node *of_get_parent(const struct device_node *node)
 {
+	return NULL;
 }
 
-#define for_each_child_of_node(parent, child) \
-	while (__of_use_dn(parent), __of_use_dn(child), 0)
+static inline struct device_node *of_get_next_child(
+	const struct device_node *node, struct device_node *prev)
+{
+	return NULL;
+}
 
-#define for_each_available_child_of_node(parent, child) \
-	while (0)
+static inline struct device_node *of_get_next_available_child(
+	const struct device_node *node, struct device_node *prev)
+{
+	return NULL;
+}
 
-static inline struct device_node *of_get_child_by_name(
-					const struct device_node *node,
-					const char *name)
+static inline struct device_node *of_find_node_with_property(
+	struct device_node *from, const char *prop_name)
 {
 	return NULL;
 }
 
-static inline int of_get_child_count(const struct device_node *np)
+static inline bool of_have_populated_dt(void)
 {
-	return 0;
+	return false;
 }
 
-static inline int of_get_available_child_count(const struct device_node *np)
+static inline struct device_node *of_get_child_by_name(
+					const struct device_node *node,
+					const char *name)
 {
-	return 0;
+	return NULL;
 }
 
 static inline int of_device_is_compatible(const struct device_node *device,
@@ -569,6 +528,13 @@ extern int of_node_to_nid(struct device_node *np);
 static inline int of_node_to_nid(struct device_node *device) { return 0; }
 #endif
 
+static inline struct device_node *of_find_matching_node(
+	struct device_node *from,
+	const struct of_device_id *matches)
+{
+	return of_find_matching_node_and_match(from, matches, NULL);
+}
+
 /**
  * of_property_read_bool - Findfrom a property
  * @np:		device node from which the property value is to be read.
@@ -618,6 +584,55 @@ static inline int of_property_read_u32(const struct device_node *np,
 		s;						\
 		s = of_prop_next_string(prop, s))
 
+#define for_each_node_by_name(dn, name) \
+	for (dn = of_find_node_by_name(NULL, name); dn; \
+	     dn = of_find_node_by_name(dn, name))
+#define for_each_node_by_type(dn, type) \
+	for (dn = of_find_node_by_type(NULL, type); dn; \
+	     dn = of_find_node_by_type(dn, type))
+#define for_each_compatible_node(dn, type, compatible) \
+	for (dn = of_find_compatible_node(NULL, type, compatible); dn; \
+	     dn = of_find_compatible_node(dn, type, compatible))
+#define for_each_matching_node(dn, matches) \
+	for (dn = of_find_matching_node(NULL, matches); dn; \
+	     dn = of_find_matching_node(dn, matches))
+#define for_each_matching_node_and_match(dn, matches, match) \
+	for (dn = of_find_matching_node_and_match(NULL, matches, match); \
+	     dn; dn = of_find_matching_node_and_match(dn, matches, match))
+
+#define for_each_child_of_node(parent, child) \
+	for (child = of_get_next_child(parent, NULL); child != NULL; \
+	     child = of_get_next_child(parent, child))
+#define for_each_available_child_of_node(parent, child) \
+	for (child = of_get_next_available_child(parent, NULL); child != NULL; \
+	     child = of_get_next_available_child(parent, child))
+
+#define for_each_node_with_property(dn, prop_name) \
+	for (dn = of_find_node_with_property(NULL, prop_name); dn; \
+	     dn = of_find_node_with_property(dn, prop_name))
+
+static inline int of_get_child_count(const struct device_node *np)
+{
+	struct device_node *child;
+	int num = 0;
+
+	for_each_child_of_node(np, child)
+		num++;
+
+	return num;
+}
+
+static inline int of_get_available_child_count(const struct device_node *np)
+{
+	struct device_node *child;
+	int num = 0;
+
+	for_each_available_child_of_node(np, child)
+		num++;
+
+	return num;
+}
+
 #if defined(CONFIG_PROC_FS) && defined(CONFIG_PROC_DEVICETREE)
 extern void proc_device_tree_add_node(struct device_node *, struct proc_dir_entry *);
 extern void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop);
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 8d7dd6768cb7..ef370210ffb2 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -78,11 +78,13 @@ static inline int of_device_uevent_modalias(struct device *dev,
 
 static inline void of_device_node_put(struct device *dev) { }
 
-static inline const struct of_device_id *of_match_device(
+static inline const struct of_device_id *__of_match_device(
 		const struct of_device_id *matches, const struct device *dev)
 {
 	return NULL;
 }
+#define of_match_device(matches, dev)	\
+	__of_match_device(of_match_ptr(matches), (dev))
 
 static inline struct device_node *of_cpu_device_node_get(int cpu)
 {
diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
index e273e5ac19c9..3f83459dbb20 100644
--- a/include/linux/phy/phy.h
+++ b/include/linux/phy/phy.h
@@ -146,7 +146,9 @@ static inline void phy_set_bus_width(struct phy *phy, int bus_width)
 	phy->attrs.bus_width = bus_width;
 }
 struct phy *phy_get(struct device *dev, const char *string);
+struct phy *phy_optional_get(struct device *dev, const char *string);
 struct phy *devm_phy_get(struct device *dev, const char *string);
+struct phy *devm_phy_optional_get(struct device *dev, const char *string);
 void phy_put(struct phy *phy);
 void devm_phy_put(struct device *dev, struct phy *phy);
 struct phy *of_phy_simple_xlate(struct device *dev,
@@ -232,11 +234,23 @@ static inline struct phy *phy_get(struct device *dev, const char *string)
 	return ERR_PTR(-ENOSYS);
 }
 
+static inline struct phy *phy_optional_get(struct device *dev,
+					   const char *string)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
 static inline struct phy *devm_phy_get(struct device *dev, const char *string)
 {
 	return ERR_PTR(-ENOSYS);
 }
 
+static inline struct phy *devm_phy_optional_get(struct device *dev,
+						const char *string)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
 static inline void phy_put(struct phy *phy)
 {
 }
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 3834f43f9993..6ae004e437ea 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -188,6 +188,9 @@ static inline void kick_all_cpus_sync(void) {  }
  */
 extern void arch_disable_smp_support(void);
 
+extern void arch_enable_nonboot_cpus_begin(void);
+extern void arch_enable_nonboot_cpus_end(void);
+
 void smp_setup_processor_id(void);
 
 #endif /* __LINUX_SMP_H */
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index a1d4ca290862..4203c66d8803 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -273,7 +273,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  *	message while queuing transfers that arrive in the meantime. When the
  *	driver is finished with this message, it must call
  *	spi_finalize_current_message() so the subsystem can issue the next
- *	transfer
+ *	message
  * @unprepare_transfer_hardware: there are currently no more messages on the
  *	queue so the subsystem notifies the driver that it may relax the
  *	hardware by issuing this call
@@ -287,7 +287,10 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  *                  - return 1 if the transfer is still in progress. When
  *                    the driver is finished with this transfer it must
  *                    call spi_finalize_current_transfer() so the subsystem
- *                    can issue the next transfer
+ *                    can issue the next transfer. Note: transfer_one and
+ *                    transfer_one_message are mutually exclusive; when both
+ *                    are set, the generic subsystem does not call your
+ *                    transfer_one callback.
  * @unprepare_message: undo any work done by prepare_message().
  * @cs_gpios: Array of GPIOs to use as chip select lines; one per CS
  *	number. Any individual value may be -ENOENT for CS lines that
diff --git a/include/linux/usb.h b/include/linux/usb.h
index c716da18c668..7f6eb859873e 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1265,8 +1265,6 @@ typedef void (*usb_complete_t)(struct urb *);
  * @sg: scatter gather buffer list, the buffer size of each element in
  * 	the list (except the last) must be divisible by the endpoint's
  * 	max packet size if no_sg_constraint isn't set in 'struct usb_bus'
- * 	(FIXME: scatter-gather under xHCI is broken for periodic transfers.
- * 	Do not use urb->sg for interrupt endpoints for now, only bulk.)
  * @num_mapped_sgs: (internal) number of mapped sg entries
  * @num_sgs: number of entries in the sg list
  * @transfer_buffer_length: How big is transfer_buffer.  The transfer may