23 files changed, 422 insertions, 54 deletions

diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index f5c40b0fadc2..e6a83d712ef6 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -66,8 +66,8 @@
 #define smp_read_barrier_depends()	do { } while (0)
 #endif
 
-#ifndef set_mb
-#define set_mb(var, value)  do { (var) = (value); mb(); } while (0)
+#ifndef smp_store_mb
+#define smp_store_mb(var, value)  do { WRITE_ONCE(var, value); mb(); } while (0)
 #endif
 
 #ifndef smp_mb__before_atomic
diff --git a/include/asm-generic/cmpxchg.h b/include/asm-generic/cmpxchg.h
index 811fb1e9b061..3766ab34aa45 100644
--- a/include/asm-generic/cmpxchg.h
+++ b/include/asm-generic/cmpxchg.h
@@ -86,9 +86,6 @@ unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
 
 /*
  * Atomic compare and exchange.
- *
- * Do not define __HAVE_ARCH_CMPXCHG because we want to use it to check whether
- * a cmpxchg primitive faster than repeated local irq save/restore exists.
  */
 #include <asm-generic/cmpxchg-local.h>
 
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
new file mode 100644
index 000000000000..83bfb87f5bf1
--- /dev/null
+++ b/include/asm-generic/qspinlock.h
@@ -0,0 +1,139 @@
+/*
+ * Queued spinlock
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
+ *
+ * Authors: Waiman Long <waiman.long@hp.com>
+ */
+#ifndef __ASM_GENERIC_QSPINLOCK_H
+#define __ASM_GENERIC_QSPINLOCK_H
+
+#include <asm-generic/qspinlock_types.h>
+
+/**
+ * queued_spin_is_locked - is the spinlock locked?
+ * @lock: Pointer to queued spinlock structure
+ * Return: 1 if it is locked, 0 otherwise
+ */
+static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
+{
+	return atomic_read(&lock->val);
+}
+
+/**
+ * queued_spin_value_unlocked - is the spinlock structure unlocked?
+ * @lock: queued spinlock structure
+ * Return: 1 if it is unlocked, 0 otherwise
+ *
+ * N.B. Whenever there are tasks waiting for the lock, it is considered
+ *      locked wrt the lockref code to avoid lock stealing by the lockref
+ *      code and change things underneath the lock. This also allows some
+ *      optimizations to be applied without conflict with lockref.
+ */
+static __always_inline int queued_spin_value_unlocked(struct qspinlock lock)
+{
+	return !atomic_read(&lock.val);
+}
+
+/**
+ * queued_spin_is_contended - check if the lock is contended
+ * @lock : Pointer to queued spinlock structure
+ * Return: 1 if lock contended, 0 otherwise
+ */
+static __always_inline int queued_spin_is_contended(struct qspinlock *lock)
+{
+	return atomic_read(&lock->val) & ~_Q_LOCKED_MASK;
+}
+/**
+ * queued_spin_trylock - try to acquire the queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ * Return: 1 if lock acquired, 0 if failed
+ */
+static __always_inline int queued_spin_trylock(struct qspinlock *lock)
+{
+	if (!atomic_read(&lock->val) &&
+	   (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) == 0))
+		return 1;
+	return 0;
+}
+
+extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+
+/**
+ * queued_spin_lock - acquire a queued spinlock
+ * @lock: Pointer to queued spinlock structure
+ */
+static __always_inline void queued_spin_lock(struct qspinlock *lock)
+{
+	u32 val;
+
+	val = atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL);
+	if (likely(val == 0))
+		return;
+	queued_spin_lock_slowpath(lock, val);
+}
+
+#ifndef queued_spin_unlock
+/**
+ * queued_spin_unlock - release a queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ */
+static __always_inline void queued_spin_unlock(struct qspinlock *lock)
+{
+	/*
+	 * smp_mb__before_atomic() in order to guarantee release semantics
+	 */
+	smp_mb__before_atomic_dec();
+	atomic_sub(_Q_LOCKED_VAL, &lock->val);
+}
+#endif
+
+/**
+ * queued_spin_unlock_wait - wait until current lock holder releases the lock
+ * @lock : Pointer to queued spinlock structure
+ *
+ * There is a very slight possibility of live-lock if the lockers keep coming
+ * and the waiter is just unfortunate enough to not see any unlock state.
+ */
+static inline void queued_spin_unlock_wait(struct qspinlock *lock)
+{
+	while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
+		cpu_relax();
+}
+
+#ifndef virt_queued_spin_lock
+static __always_inline bool virt_queued_spin_lock(struct qspinlock *lock)
+{
+	return false;
+}
+#endif
+
+/*
+ * Initializier
+ */
+#define	__ARCH_SPIN_LOCK_UNLOCKED	{ ATOMIC_INIT(0) }
+
+/*
+ * Remapping spinlock architecture specific functions to the corresponding
+ * queued spinlock functions.
+ */
+#define arch_spin_is_locked(l)		queued_spin_is_locked(l)
+#define arch_spin_is_contended(l)	queued_spin_is_contended(l)
+#define arch_spin_value_unlocked(l)	queued_spin_value_unlocked(l)
+#define arch_spin_lock(l)		queued_spin_lock(l)
+#define arch_spin_trylock(l)		queued_spin_trylock(l)
+#define arch_spin_unlock(l)		queued_spin_unlock(l)
+#define arch_spin_lock_flags(l, f)	queued_spin_lock(l)
+#define arch_spin_unlock_wait(l)	queued_spin_unlock_wait(l)
+
+#endif /* __ASM_GENERIC_QSPINLOCK_H */
diff --git a/include/asm-generic/qspinlock_types.h b/include/asm-generic/qspinlock_types.h
new file mode 100644
index 000000000000..85f888e86761
--- /dev/null
+++ b/include/asm-generic/qspinlock_types.h
@@ -0,0 +1,79 @@
+/*
+ * Queued spinlock
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
+ *
+ * Authors: Waiman Long <waiman.long@hp.com>
+ */
+#ifndef __ASM_GENERIC_QSPINLOCK_TYPES_H
+#define __ASM_GENERIC_QSPINLOCK_TYPES_H
+
+/*
+ * Including atomic.h with PARAVIRT on will cause compilation errors because
+ * of recursive header file incluson via paravirt_types.h. So don't include
+ * it if PARAVIRT is on.
+ */
+#ifndef CONFIG_PARAVIRT
+#include <linux/types.h>
+#include <linux/atomic.h>
+#endif
+
+typedef struct qspinlock {
+	atomic_t	val;
+} arch_spinlock_t;
+
+/*
+ * Bitfields in the atomic value:
+ *
+ * When NR_CPUS < 16K
+ *  0- 7: locked byte
+ *     8: pending
+ *  9-15: not used
+ * 16-17: tail index
+ * 18-31: tail cpu (+1)
+ *
+ * When NR_CPUS >= 16K
+ *  0- 7: locked byte
+ *     8: pending
+ *  9-10: tail index
+ * 11-31: tail cpu (+1)
+ */
+#define	_Q_SET_MASK(type)	(((1U << _Q_ ## type ## _BITS) - 1)\
+				      << _Q_ ## type ## _OFFSET)
+#define _Q_LOCKED_OFFSET	0
+#define _Q_LOCKED_BITS		8
+#define _Q_LOCKED_MASK		_Q_SET_MASK(LOCKED)
+
+#define _Q_PENDING_OFFSET	(_Q_LOCKED_OFFSET + _Q_LOCKED_BITS)
+#if CONFIG_NR_CPUS < (1U << 14)
+#define _Q_PENDING_BITS		8
+#else
+#define _Q_PENDING_BITS		1
+#endif
+#define _Q_PENDING_MASK		_Q_SET_MASK(PENDING)
+
+#define _Q_TAIL_IDX_OFFSET	(_Q_PENDING_OFFSET + _Q_PENDING_BITS)
+#define _Q_TAIL_IDX_BITS	2
+#define _Q_TAIL_IDX_MASK	_Q_SET_MASK(TAIL_IDX)
+
+#define _Q_TAIL_CPU_OFFSET	(_Q_TAIL_IDX_OFFSET + _Q_TAIL_IDX_BITS)
+#define _Q_TAIL_CPU_BITS	(32 - _Q_TAIL_CPU_OFFSET)
+#define _Q_TAIL_CPU_MASK	_Q_SET_MASK(TAIL_CPU)
+
+#define _Q_TAIL_OFFSET		_Q_TAIL_IDX_OFFSET
+#define _Q_TAIL_MASK		(_Q_TAIL_IDX_MASK | _Q_TAIL_CPU_MASK)
+
+#define _Q_LOCKED_VAL		(1U << _Q_LOCKED_OFFSET)
+#define _Q_PENDING_VAL		(1U << _Q_PENDING_OFFSET)
+
+#endif /* __ASM_GENERIC_QSPINLOCK_TYPES_H */
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index ae2982c0f7a6..656da2a12ffe 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -17,7 +17,7 @@
 #define PHY_ID_BCM7250			0xae025280
 #define PHY_ID_BCM7364			0xae025260
 #define PHY_ID_BCM7366			0x600d8490
-#define PHY_ID_BCM7425			0x03625e60
+#define PHY_ID_BCM7425			0x600d86b0
 #define PHY_ID_BCM7429			0x600d8730
 #define PHY_ID_BCM7439			0x600d8480
 #define PHY_ID_BCM7439_2		0xae025080
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 867722591be2..03e227ba481c 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -250,7 +250,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 	({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
 
 #define WRITE_ONCE(x, val) \
-	({ typeof(x) __val = (val); __write_once_size(&(x), &__val, sizeof(__val)); __val; })
+	({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
 
 #endif /* __KERNEL__ */
 
@@ -450,7 +450,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
  * with an explicit memory barrier or atomic instruction that provides the
  * required ordering.
  *
- * If possible use READ_ONCE/ASSIGN_ONCE instead.
+ * If possible use READ_ONCE()/WRITE_ONCE() instead.
  */
 #define __ACCESS_ONCE(x) ({ \
 	 __maybe_unused typeof(x) __var = (__force typeof(x)) 0; \
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 27e285b92b5f..59915ea5373c 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -151,10 +151,8 @@ static inline unsigned int cpumask_any_but(const struct cpumask *mask,
 	return 1;
 }
 
-static inline int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp)
+static inline unsigned int cpumask_local_spread(unsigned int i, int node)
 {
-	set_bit(0, cpumask_bits(dstp));
-
 	return 0;
 }
 
@@ -208,7 +206,7 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
 
 int cpumask_next_and(int n, const struct cpumask *, const struct cpumask *);
 int cpumask_any_but(const struct cpumask *mask, unsigned int cpu);
-int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp);
+unsigned int cpumask_local_spread(unsigned int i, int node);
 
 /**
  * for_each_cpu - iterate over every cpu in a mask
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 30624954dec5..e9bc9292bd3a 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -185,33 +185,85 @@ static inline int dmar_device_remove(void *handle)
 
 struct irte {
 	union {
+		/* Shared between remapped and posted mode*/
 		struct {
-			__u64	present 	: 1,
-				fpd		: 1,
-				dst_mode	: 1,
-				redir_hint	: 1,
-				trigger_mode	: 1,
-				dlvry_mode	: 3,
-				avail		: 4,
-				__reserved_1	: 4,
-				vector		: 8,
-				__reserved_2	: 8,
-				dest_id		: 32;
+			__u64	present		: 1,  /*  0      */
+				fpd		: 1,  /*  1      */
+				__res0		: 6,  /*  2 -  6 */
+				avail		: 4,  /*  8 - 11 */
+				__res1		: 3,  /* 12 - 14 */
+				pst		: 1,  /* 15      */
+				vector		: 8,  /* 16 - 23 */
+				__res2		: 40; /* 24 - 63 */
+		};
+
+		/* Remapped mode */
+		struct {
+			__u64	r_present	: 1,  /*  0      */
+				r_fpd		: 1,  /*  1      */
+				dst_mode	: 1,  /*  2      */
+				redir_hint	: 1,  /*  3      */
+				trigger_mode	: 1,  /*  4      */
+				dlvry_mode	: 3,  /*  5 -  7 */
+				r_avail		: 4,  /*  8 - 11 */
+				r_res0		: 4,  /* 12 - 15 */
+				r_vector	: 8,  /* 16 - 23 */
+				r_res1		: 8,  /* 24 - 31 */
+				dest_id		: 32; /* 32 - 63 */
+		};
+
+		/* Posted mode */
+		struct {
+			__u64	p_present	: 1,  /*  0      */
+				p_fpd		: 1,  /*  1      */
+				p_res0		: 6,  /*  2 -  7 */
+				p_avail		: 4,  /*  8 - 11 */
+				p_res1		: 2,  /* 12 - 13 */
+				p_urgent	: 1,  /* 14      */
+				p_pst		: 1,  /* 15      */
+				p_vector	: 8,  /* 16 - 23 */
+				p_res2		: 14, /* 24 - 37 */
+				pda_l		: 26; /* 38 - 63 */
 		};
 		__u64 low;
 	};
 
 	union {
+		/* Shared between remapped and posted mode*/
 		struct {
-			__u64	sid		: 16,
-				sq		: 2,
-				svt		: 2,
-				__reserved_3	: 44;
+			__u64	sid		: 16,  /* 64 - 79  */
+				sq		: 2,   /* 80 - 81  */
+				svt		: 2,   /* 82 - 83  */
+				__res3		: 44;  /* 84 - 127 */
+		};
+
+		/* Posted mode*/
+		struct {
+			__u64	p_sid		: 16,  /* 64 - 79  */
+				p_sq		: 2,   /* 80 - 81  */
+				p_svt		: 2,   /* 82 - 83  */
+				p_res3		: 12,  /* 84 - 95  */
+				pda_h		: 32;  /* 96 - 127 */
 		};
 		__u64 high;
 	};
 };
 
+static inline void dmar_copy_shared_irte(struct irte *dst, struct irte *src)
+{
+	dst->present	= src->present;
+	dst->fpd	= src->fpd;
+	dst->avail	= src->avail;
+	dst->pst	= src->pst;
+	dst->vector	= src->vector;
+	dst->sid	= src->sid;
+	dst->sq		= src->sq;
+	dst->svt	= src->svt;
+}
+
+#define PDA_LOW_BIT    26
+#define PDA_HIGH_BIT   32
+
 enum {
 	IRQ_REMAP_XAPIC_MODE,
 	IRQ_REMAP_X2APIC_MODE,
@@ -227,6 +279,7 @@ extern void dmar_msi_read(int irq, struct msi_msg *msg);
 extern void dmar_msi_write(int irq, struct msi_msg *msg);
 extern int dmar_set_interrupt(struct intel_iommu *iommu);
 extern irqreturn_t dmar_fault(int irq, void *dev_id);
-extern int arch_setup_dmar_msi(unsigned int irq);
+extern int dmar_alloc_hwirq(int id, int node, void *arg);
+extern void dmar_free_hwirq(int irq);
 
 #endif /* __DMAR_H__ */
diff --git a/include/linux/htirq.h b/include/linux/htirq.h
index 70a1dbbf2093..d4a527e58434 100644
--- a/include/linux/htirq.h
+++ b/include/linux/htirq.h
@@ -1,24 +1,38 @@
 #ifndef LINUX_HTIRQ_H
 #define LINUX_HTIRQ_H
 
+struct pci_dev;
+struct irq_data;
+
 struct ht_irq_msg {
 	u32	address_lo;	/* low 32 bits of the ht irq message */
 	u32	address_hi;	/* high 32 bits of the it irq message */
 };
 
+typedef void (ht_irq_update_t)(struct pci_dev *dev, int irq,
+			       struct ht_irq_msg *msg);
+
+struct ht_irq_cfg {
+	struct pci_dev *dev;
+	 /* Update callback used to cope with buggy hardware */
+	ht_irq_update_t *update;
+	unsigned pos;
+	unsigned idx;
+	struct ht_irq_msg msg;
+};
+
 /* Helper functions.. */
 void fetch_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg);
 void write_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg);
-struct irq_data;
 void mask_ht_irq(struct irq_data *data);
 void unmask_ht_irq(struct irq_data *data);
 
 /* The arch hook for getting things started */
-int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev);
+int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev,
+		      ht_irq_update_t *update);
+void arch_teardown_ht_irq(unsigned int irq);
 
 /* For drivers of buggy hardware */
-typedef void (ht_irq_update_t)(struct pci_dev *dev, int irq,
-			       struct ht_irq_msg *msg);
 int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update);
 
 #endif /* LINUX_HTIRQ_H */
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 796ef9645827..0c251be39836 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -87,6 +87,7 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 /*
  * Decoding Capability Register
  */
+#define cap_pi_support(c)	(((c) >> 59) & 1)
 #define cap_read_drain(c)	(((c) >> 55) & 1)
 #define cap_write_drain(c)	(((c) >> 54) & 1)
 #define cap_max_amask_val(c)	(((c) >> 48) & 0x3f)
@@ -298,6 +299,8 @@ struct q_inval {
 
 #define INTR_REMAP_TABLE_ENTRIES	65536
 
+struct irq_domain;
+
 struct ir_table {
 	struct irte *base;
 	unsigned long *bitmap;
@@ -347,6 +350,8 @@ struct intel_iommu {
 
 #ifdef CONFIG_IRQ_REMAP
 	struct ir_table *ir_table;	/* Interrupt remapping info */
+	struct irq_domain *ir_domain;
+	struct irq_domain *ir_msi_domain;
 #endif
 	struct device	*iommu_dev; /* IOMMU-sysfs device */
 	int		node;
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 62c6901cab55..48cb7d1aa58f 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -327,6 +327,7 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
  * @irq_write_msi_msg:	optional to write message content for MSI
  * @irq_get_irqchip_state:	return the internal state of an interrupt
  * @irq_set_irqchip_state:	set the internal state of a interrupt
+ * @irq_set_vcpu_affinity:	optional to target a vCPU in a virtual machine
  * @flags:		chip specific flags
  */
 struct irq_chip {
@@ -369,6 +370,8 @@ struct irq_chip {
 	int		(*irq_get_irqchip_state)(struct irq_data *data, enum irqchip_irq_state which, bool *state);
 	int		(*irq_set_irqchip_state)(struct irq_data *data, enum irqchip_irq_state which, bool state);
 
+	int		(*irq_set_vcpu_affinity)(struct irq_data *data, void *vcpu_info);
+
 	unsigned long	flags;
 };
 
@@ -422,6 +425,7 @@ extern void irq_cpu_online(void);
 extern void irq_cpu_offline(void);
 extern int irq_set_affinity_locked(struct irq_data *data,
 				   const struct cpumask *cpumask, bool force);
+extern int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info);
 
 #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
 void irq_move_irq(struct irq_data *data);
@@ -467,6 +471,8 @@ extern int irq_chip_set_affinity_parent(struct irq_data *data,
 					const struct cpumask *dest,
 					bool force);
 extern int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on);
+extern int irq_chip_set_vcpu_affinity_parent(struct irq_data *data,
+					     void *vcpu_info);
 #endif
 
 /* Handling of unhandled and spurious interrupts: */
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index dd1109fb241e..a113a8dc7438 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -93,6 +93,15 @@ struct irq_desc {
 extern struct irq_desc irq_desc[NR_IRQS];
 #endif
 
+static inline struct irq_desc *irq_data_to_desc(struct irq_data *data)
+{
+#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
+	return irq_to_desc(data->irq);
+#else
+	return container_of(data, struct irq_desc, irq_data);
+#endif
+}
+
 static inline struct irq_data *irq_desc_get_irq_data(struct irq_desc *desc)
 {
 	return &desc->irq_data;
diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h
index 3a6490e81b28..703ea5c30a33 100644
--- a/include/linux/osq_lock.h
+++ b/include/linux/osq_lock.h
@@ -32,4 +32,9 @@ static inline void osq_lock_init(struct optimistic_spin_queue *lock)
 extern bool osq_lock(struct optimistic_spin_queue *lock);
 extern void osq_unlock(struct optimistic_spin_queue *lock);
 
+static inline bool osq_is_locked(struct optimistic_spin_queue *lock)
+{
+	return atomic_read(&lock->tail) != OSQ_UNLOCKED_VAL;
+}
+
 #endif
diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index 50e50095c8d1..84a109449610 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -41,7 +41,12 @@ void percpu_counter_destroy(struct percpu_counter *fbc);
 void percpu_counter_set(struct percpu_counter *fbc, s64 amount);
 void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch);
 s64 __percpu_counter_sum(struct percpu_counter *fbc);
-int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs);
+int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch);
+
+static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
+{
+	return __percpu_counter_compare(fbc, rhs, percpu_counter_batch);
+}
 
 static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 {
@@ -116,6 +121,12 @@ static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
 		return 0;
 }
 
+static inline int
+__percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch)
+{
+	return percpu_counter_compare(fbc, rhs);
+}
+
 static inline void
 percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 {
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 26a2e6122734..18f197223ebd 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -252,7 +252,7 @@ extern char ___assert_task_state[1 - 2*!!(
 #define set_task_state(tsk, state_value)			\
 	do {							\
 		(tsk)->task_state_change = _THIS_IP_;		\
-		set_mb((tsk)->state, (state_value));		\
+		smp_store_mb((tsk)->state, (state_value));		\
 	} while (0)
 
 /*
@@ -274,7 +274,7 @@ extern char ___assert_task_state[1 - 2*!!(
 #define set_current_state(state_value)				\
 	do {							\
 		current->task_state_change = _THIS_IP_;		\
-		set_mb(current->state, (state_value));		\
+		smp_store_mb(current->state, (state_value));		\
 	} while (0)
 
 #else
@@ -282,7 +282,7 @@ extern char ___assert_task_state[1 - 2*!!(
 #define __set_task_state(tsk, state_value)		\
 	do { (tsk)->state = (state_value); } while (0)
 #define set_task_state(tsk, state_value)		\
-	set_mb((tsk)->state, (state_value))
+	smp_store_mb((tsk)->state, (state_value))
 
 /*
  * set_current_state() includes a barrier so that the write of current->state
@@ -298,7 +298,7 @@ extern char ___assert_task_state[1 - 2*!!(
 #define __set_current_state(state_value)		\
 	do { current->state = (state_value); } while (0)
 #define set_current_state(state_value)			\
-	set_mb(current->state, (state_value))
+	smp_store_mb(current->state, (state_value))
 
 #endif
 
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 497bc14cdb85..0320bbb7d7b5 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -98,7 +98,8 @@ struct inet_connection_sock {
 	const struct tcp_congestion_ops *icsk_ca_ops;
 	const struct inet_connection_sock_af_ops *icsk_af_ops;
 	unsigned int		  (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
-	__u8			  icsk_ca_state:7,
+	__u8			  icsk_ca_state:6,
+				  icsk_ca_setsockopt:1,
 				  icsk_ca_dst_locked:1;
 	__u8			  icsk_retransmits;
 	__u8			  icsk_pending;
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 8e3668b44c29..fc57f6b82fc5 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -354,7 +354,7 @@ enum ieee80211_rssi_event_data {
 };
 
 /**
- * enum ieee80211_rssi_event - data attached to an %RSSI_EVENT
+ * struct ieee80211_rssi_event - data attached to an %RSSI_EVENT
  * @data: See &enum ieee80211_rssi_event_data
  */
 struct ieee80211_rssi_event {
@@ -388,7 +388,7 @@ enum ieee80211_mlme_event_status {
 };
 
 /**
- * enum ieee80211_mlme_event - data attached to an %MLME_EVENT
+ * struct ieee80211_mlme_event - data attached to an %MLME_EVENT
  * @data: See &enum ieee80211_mlme_event_data
  * @status: See &enum ieee80211_mlme_event_status
  * @reason: the reason code if applicable
@@ -401,9 +401,10 @@ struct ieee80211_mlme_event {
 
 /**
  * struct ieee80211_event - event to be sent to the driver
- * @type The event itself. See &enum ieee80211_event_type.
+ * @type: The event itself. See &enum ieee80211_event_type.
  * @rssi: relevant if &type is %RSSI_EVENT
  * @mlme: relevant if &type is %AUTH_EVENT
+ * @u:    union holding the above two fields
  */
 struct ieee80211_event {
 	enum ieee80211_event_type type;
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index c56a438c3a1e..ce13cf20f625 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -574,11 +574,14 @@ static inline void sctp_v6_map_v4(union sctp_addr *addr)
 /* Map v4 address to v4-mapped v6 address */
 static inline void sctp_v4_map_v6(union sctp_addr *addr)
 {
+	__be16 port;
+
+	port = addr->v4.sin_port;
+	addr->v6.sin6_addr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
+	addr->v6.sin6_port = port;
 	addr->v6.sin6_family = AF_INET6;
 	addr->v6.sin6_flowinfo = 0;
 	addr->v6.sin6_scope_id = 0;
-	addr->v6.sin6_port = addr->v4.sin_port;
-	addr->v6.sin6_addr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
 	addr->v6.sin6_addr.s6_addr32[0] = 0;
 	addr->v6.sin6_addr.s6_addr32[1] = 0;
 	addr->v6.sin6_addr.s6_addr32[2] = htonl(0x0000ffff);
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index d61be7297b2c..5f1225706993 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -1,9 +1,7 @@
 #ifndef TARGET_CORE_BACKEND_H
 #define TARGET_CORE_BACKEND_H
 
-#define TRANSPORT_PLUGIN_PHBA_PDEV		1
-#define TRANSPORT_PLUGIN_VHBA_PDEV		2
-#define TRANSPORT_PLUGIN_VHBA_VDEV		3
+#define TRANSPORT_FLAG_PASSTHROUGH		1
 
 struct target_backend_cits {
 	struct config_item_type tb_dev_cit;
@@ -22,7 +20,7 @@ struct se_subsystem_api {
 	char inquiry_rev[4];
 	struct module *owner;
 
-	u8 transport_type;
+	u8 transport_flags;
 
 	int (*attach_hba)(struct se_hba *, u32);
 	void (*detach_hba)(struct se_hba *);
@@ -138,5 +136,7 @@ int	se_dev_set_queue_depth(struct se_device *, u32);
 int	se_dev_set_max_sectors(struct se_device *, u32);
 int	se_dev_set_optimal_sectors(struct se_device *, u32);
 int	se_dev_set_block_size(struct se_device *, u32);
+sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd,
+	sense_reason_t (*exec_cmd)(struct se_cmd *cmd));
 
 #endif /* TARGET_CORE_BACKEND_H */
diff --git a/include/target/target_core_configfs.h b/include/target/target_core_configfs.h
index 25bb04c4209e..b99c01170392 100644
--- a/include/target/target_core_configfs.h
+++ b/include/target/target_core_configfs.h
@@ -40,8 +40,6 @@ struct target_fabric_configfs {
 	struct config_item	*tf_fabric;
 	/* Passed from fabric modules */
 	struct config_item_type	*tf_fabric_cit;
-	/* Pointer to target core subsystem */
-	struct configfs_subsystem *tf_subsys;
 	/* Pointer to fabric's struct module */
 	struct module *tf_module;
 	struct target_core_fabric_ops tf_ops;
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index 17c7f5ac7ea0..0f4dc3768587 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -4,7 +4,6 @@
 struct target_core_fabric_ops {
 	struct module *module;
 	const char *name;
-	struct configfs_subsystem *tf_subsys;
 	char *(*get_fabric_name)(void);
 	u8 (*get_fabric_proto_ident)(struct se_portal_group *);
 	char *(*tpg_get_wwn)(struct se_portal_group *);
@@ -109,6 +108,9 @@ struct target_core_fabric_ops {
 int target_register_template(const struct target_core_fabric_ops *fo);
 void target_unregister_template(const struct target_core_fabric_ops *fo);
 
+int target_depend_item(struct config_item *item);
+void target_undepend_item(struct config_item *item);
+
 struct se_session *transport_init_session(enum target_prot_op);
 int transport_alloc_session_tags(struct se_session *, unsigned int,
 		unsigned int);
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index 81ea59812117..f7554fd7fc62 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -140,19 +140,42 @@ DEFINE_EVENT(kmem_free, kfree,
 	TP_ARGS(call_site, ptr)
 );
 
-DEFINE_EVENT(kmem_free, kmem_cache_free,
+DEFINE_EVENT_CONDITION(kmem_free, kmem_cache_free,
 
 	TP_PROTO(unsigned long call_site, const void *ptr),
 
-	TP_ARGS(call_site, ptr)
+	TP_ARGS(call_site, ptr),
+
+	/*
+	 * This trace can be potentially called from an offlined cpu.
+	 * Since trace points use RCU and RCU should not be used from
+	 * offline cpus, filter such calls out.
+	 * While this trace can be called from a preemptable section,
+	 * it has no impact on the condition since tasks can migrate
+	 * only from online cpus to other online cpus. Thus its safe
+	 * to use raw_smp_processor_id.
+	 */
+	TP_CONDITION(cpu_online(raw_smp_processor_id()))
 );
 
-TRACE_EVENT(mm_page_free,
+TRACE_EVENT_CONDITION(mm_page_free,
 
 	TP_PROTO(struct page *page, unsigned int order),
 
 	TP_ARGS(page, order),
 
+
+	/*
+	 * This trace can be potentially called from an offlined cpu.
+	 * Since trace points use RCU and RCU should not be used from
+	 * offline cpus, filter such calls out.
+	 * While this trace can be called from a preemptable section,
+	 * it has no impact on the condition since tasks can migrate
+	 * only from online cpus to other online cpus. Thus its safe
+	 * to use raw_smp_processor_id.
+	 */
+	TP_CONDITION(cpu_online(raw_smp_processor_id())),
+
 	TP_STRUCT__entry(
 		__field(	unsigned long,	pfn		)
 		__field(	unsigned int,	order		)
@@ -253,12 +276,35 @@ DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked,
 	TP_ARGS(page, order, migratetype)
 );
 
-DEFINE_EVENT_PRINT(mm_page, mm_page_pcpu_drain,
+TRACE_EVENT_CONDITION(mm_page_pcpu_drain,
 
 	TP_PROTO(struct page *page, unsigned int order, int migratetype),
 
 	TP_ARGS(page, order, migratetype),
 
+	/*
+	 * This trace can be potentially called from an offlined cpu.
+	 * Since trace points use RCU and RCU should not be used from
+	 * offline cpus, filter such calls out.
+	 * While this trace can be called from a preemptable section,
+	 * it has no impact on the condition since tasks can migrate
+	 * only from online cpus to other online cpus. Thus its safe
+	 * to use raw_smp_processor_id.
+	 */
+	TP_CONDITION(cpu_online(raw_smp_processor_id())),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	pfn		)
+		__field(	unsigned int,	order		)
+		__field(	int,		migratetype	)
+	),
+
+	TP_fast_assign(
+		__entry->pfn		= page ? page_to_pfn(page) : -1UL;
+		__entry->order		= order;
+		__entry->migratetype	= migratetype;
+	),
+
 	TP_printk("page=%p pfn=%lu order=%d migratetype=%d",
 		pfn_to_page(__entry->pfn), __entry->pfn,
 		__entry->order, __entry->migratetype)
diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h
index 984169a819ee..d7f1cbc3766c 100644
--- a/include/uapi/linux/virtio_balloon.h
+++ b/include/uapi/linux/virtio_balloon.h
@@ -26,6 +26,7 @@
  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  * SUCH DAMAGE. */
 #include <linux/types.h>
+#include <linux/virtio_types.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>