Merge tag 'arm-perf-4.1' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux into next/drivers

Merge "arm-cci PMU updates for 4.1" from Will Deacon:

CCI-400 PMU updates

This series reworks some of the CCI-400 PMU code so that it can be used
on both ARM and ARM64-based systems, without the need to boot in secure
mode on the latter. This paves the way for CCI-500 support in future.

* tag 'arm-perf-4.1' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux:
  arm-cci: Fix CCI PMU event validation
  arm-cci: Split the code for PMU vs driver support
  arm-cci: Get rid of secure transactions for PMU driver
  arm-cci: Abstract the CCI400 PMU specific definitions
  arm-cci: Rearrange code for splitting PMU vs driver code
  drivers: cci: reject groups spanning multiple HW PMUs
  + Linux 4.0-rc4

Signed-off-by: Olof Johansson <olof@lixom.net>

19 files changed, 92 insertions, 41 deletions

diff --git a/include/linux/arm-cci.h b/include/linux/arm-cci.h
index 79d6edf446d5..521ec1f2e6bc 100644
--- a/include/linux/arm-cci.h
+++ b/include/linux/arm-cci.h
@@ -24,16 +24,22 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 
+#include <asm/arm-cci.h>
+
 struct device_node;
 
 #ifdef CONFIG_ARM_CCI
 extern bool cci_probed(void);
+#else
+static inline bool cci_probed(void) { return false; }
+#endif
+
+#ifdef CONFIG_ARM_CCI400_PORT_CTRL
 extern int cci_ace_get_port(struct device_node *dn);
 extern int cci_disable_port_by_cpu(u64 mpidr);
 extern int __cci_control_port_by_device(struct device_node *dn, bool enable);
 extern int __cci_control_port_by_index(u32 port, bool enable);
 #else
-static inline bool cci_probed(void) { return false; }
 static inline int cci_ace_get_port(struct device_node *dn)
 {
 	return -ENODEV;
@@ -49,6 +55,7 @@ static inline int __cci_control_port_by_index(u32 port, bool enable)
 	return -ENODEV;
 }
 #endif
+
 #define cci_disable_port_by_device(dev) \
 	__cci_control_port_by_device(dev, false)
 #define cci_enable_port_by_device(dev) \
diff --git a/include/linux/clk.h b/include/linux/clk.h
index 8381bbfbc308..68c16a6bedb3 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -125,6 +125,19 @@ int clk_set_phase(struct clk *clk, int degrees);
  */
 int clk_get_phase(struct clk *clk);
 
+/**
+ * clk_is_match - check if two clk's point to the same hardware clock
+ * @p: clk compared against q
+ * @q: clk compared against p
+ *
+ * Returns true if the two struct clk pointers both point to the same hardware
+ * clock node. Put differently, returns true if struct clk *p and struct clk *q
+ * share the same struct clk_core object.
+ *
+ * Returns false otherwise. Note that two NULL clks are treated as matching.
+ */
+bool clk_is_match(const struct clk *p, const struct clk *q);
+
 #else
 
 static inline long clk_get_accuracy(struct clk *clk)
@@ -142,6 +155,11 @@ static inline long clk_get_phase(struct clk *clk)
 	return -ENOTSUPP;
 }
 
+static inline bool clk_is_match(const struct clk *p, const struct clk *q)
+{
+	return p == q;
+}
+
 #endif
 
 /**
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index f551a9299ac9..306178d7309f 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -126,6 +126,8 @@ struct cpuidle_driver {
 
 #ifdef CONFIG_CPU_IDLE
 extern void disable_cpuidle(void);
+extern bool cpuidle_not_available(struct cpuidle_driver *drv,
+				  struct cpuidle_device *dev);
 
 extern int cpuidle_select(struct cpuidle_driver *drv,
 			  struct cpuidle_device *dev);
@@ -150,11 +152,17 @@ extern void cpuidle_resume(void);
 extern int cpuidle_enable_device(struct cpuidle_device *dev);
 extern void cpuidle_disable_device(struct cpuidle_device *dev);
 extern int cpuidle_play_dead(void);
-extern void cpuidle_enter_freeze(void);
+extern int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
+				      struct cpuidle_device *dev);
+extern int cpuidle_enter_freeze(struct cpuidle_driver *drv,
+				struct cpuidle_device *dev);
 
 extern struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev);
 #else
 static inline void disable_cpuidle(void) { }
+static inline bool cpuidle_not_available(struct cpuidle_driver *drv,
+					 struct cpuidle_device *dev)
+{return true; }
 static inline int cpuidle_select(struct cpuidle_driver *drv,
 				 struct cpuidle_device *dev)
 {return -ENODEV; }
@@ -183,7 +191,12 @@ static inline int cpuidle_enable_device(struct cpuidle_device *dev)
 {return -ENODEV; }
 static inline void cpuidle_disable_device(struct cpuidle_device *dev) { }
 static inline int cpuidle_play_dead(void) {return -ENODEV; }
-static inline void cpuidle_enter_freeze(void) { }
+static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
+					     struct cpuidle_device *dev)
+{return -ENODEV; }
+static inline int cpuidle_enter_freeze(struct cpuidle_driver *drv,
+				       struct cpuidle_device *dev)
+{return -ENODEV; }
 static inline struct cpuidle_driver *cpuidle_get_cpu_driver(
 	struct cpuidle_device *dev) {return NULL; }
 #endif
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index d9b05b5bf8c7..2e88580194f0 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -52,11 +52,17 @@
  * IRQF_ONESHOT - Interrupt is not reenabled after the hardirq handler finished.
  *                Used by threaded interrupts which need to keep the
  *                irq line disabled until the threaded handler has been run.
- * IRQF_NO_SUSPEND - Do not disable this IRQ during suspend
+ * IRQF_NO_SUSPEND - Do not disable this IRQ during suspend.  Does not guarantee
+ *                   that this interrupt will wake the system from a suspended
+ *                   state.  See Documentation/power/suspend-and-interrupts.txt
  * IRQF_FORCE_RESUME - Force enable it on resume even if IRQF_NO_SUSPEND is set
  * IRQF_NO_THREAD - Interrupt cannot be threaded
  * IRQF_EARLY_RESUME - Resume IRQ early during syscore instead of at device
  *                resume time.
+ * IRQF_COND_SUSPEND - If the IRQ is shared with a NO_SUSPEND user, execute this
+ *                interrupt handler after suspending interrupts. For system
+ *                wakeup devices users need to implement wakeup detection in
+ *                their interrupt handlers.
  */
 #define IRQF_DISABLED		0x00000020
 #define IRQF_SHARED		0x00000080
@@ -70,6 +76,7 @@
 #define IRQF_FORCE_RESUME	0x00008000
 #define IRQF_NO_THREAD		0x00010000
 #define IRQF_EARLY_RESUME	0x00020000
+#define IRQF_COND_SUSPEND	0x00040000
 
 #define IRQF_TIMER		(__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD)
 
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 800544bc7bfd..781974afff9f 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -166,6 +166,11 @@
 
 #define GITS_TRANSLATER			0x10040
 
+#define GITS_CTLR_ENABLE		(1U << 0)
+#define GITS_CTLR_QUIESCENT		(1U << 31)
+
+#define GITS_TYPER_DEVBITS_SHIFT	13
+#define GITS_TYPER_DEVBITS(r)		((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1)
 #define GITS_TYPER_PTA			(1UL << 19)
 
 #define GITS_CBASER_VALID		(1UL << 63)
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index faf433af425e..dd1109fb241e 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -78,6 +78,7 @@ struct irq_desc {
 #ifdef CONFIG_PM_SLEEP
 	unsigned int		nr_actions;
 	unsigned int		no_suspend_depth;
+	unsigned int		cond_suspend_depth;
 	unsigned int		force_resume_depth;
 #endif
 #ifdef CONFIG_PROC_FS
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 72ba725ddf9c..5bb074431eb0 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -5,6 +5,7 @@
 
 struct kmem_cache;
 struct page;
+struct vm_struct;
 
 #ifdef CONFIG_KASAN
 
@@ -49,15 +50,11 @@ void kasan_krealloc(const void *object, size_t new_size);
 void kasan_slab_alloc(struct kmem_cache *s, void *object);
 void kasan_slab_free(struct kmem_cache *s, void *object);
 
-#define MODULE_ALIGN (PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT)
-
 int kasan_module_alloc(void *addr, size_t size);
-void kasan_module_free(void *addr);
+void kasan_free_shadow(const struct vm_struct *vm);
 
 #else /* CONFIG_KASAN */
 
-#define MODULE_ALIGN 1
-
 static inline void kasan_unpoison_shadow(const void *address, size_t size) {}
 
 static inline void kasan_enable_current(void) {}
@@ -82,7 +79,7 @@ static inline void kasan_slab_alloc(struct kmem_cache *s, void *object) {}
 static inline void kasan_slab_free(struct kmem_cache *s, void *object) {}
 
 static inline int kasan_module_alloc(void *addr, size_t size) { return 0; }
-static inline void kasan_module_free(void *addr) {}
+static inline void kasan_free_shadow(const struct vm_struct *vm) {}
 
 #endif /* CONFIG_KASAN */
 
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index 2bbc62aa818a..551f85456c11 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -427,7 +427,7 @@ struct mlx4_wqe_inline_seg {
 
 enum mlx4_update_qp_attr {
 	MLX4_UPDATE_QP_SMAC		= 1 << 0,
-	MLX4_UPDATE_QP_VSD		= 1 << 2,
+	MLX4_UPDATE_QP_VSD		= 1 << 1,
 	MLX4_UPDATE_QP_SUPPORTED_ATTRS	= (1 << 2) - 1
 };
 
diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h
index f7556261fe3c..4d0cb9bba93e 100644
--- a/include/linux/moduleloader.h
+++ b/include/linux/moduleloader.h
@@ -84,4 +84,12 @@ void module_arch_cleanup(struct module *mod);
 
 /* Any cleanup before freeing mod->module_init */
 void module_arch_freeing_init(struct module *mod);
+
+#ifdef CONFIG_KASAN
+#include <linux/kasan.h>
+#define MODULE_ALIGN (PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT)
+#else
+#define MODULE_ALIGN PAGE_SIZE
+#endif
+
 #endif
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5897b4ea5a3f..429d1790a27e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2342,6 +2342,7 @@ struct gro_remcsum {
 
 static inline void skb_gro_remcsum_init(struct gro_remcsum *grc)
 {
+	grc->offset = 0;
 	grc->delta = 0;
 }
 
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 2f77e0c651c8..b01ccf371fdc 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -343,6 +343,7 @@ extern struct inode *nfs_fhget(struct super_block *, struct nfs_fh *,
 extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *);
 extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr);
 extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr);
+extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr);
 extern int nfs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
 extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *);
 extern void nfs_access_set_mask(struct nfs_access_entry *, u32);
@@ -355,8 +356,9 @@ extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode);
 extern int nfs_revalidate_inode_rcu(struct nfs_server *server, struct inode *inode);
 extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *);
 extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping);
+extern int nfs_revalidate_mapping_protected(struct inode *inode, struct address_space *mapping);
 extern int nfs_setattr(struct dentry *, struct iattr *);
-extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr);
+extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *);
 extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
 				struct nfs4_label *label);
 extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx);
@@ -369,6 +371,7 @@ extern struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ct
 extern void nfs_put_lock_context(struct nfs_lock_context *l_ctx);
 extern u64 nfs_compat_user_ino64(u64 fileid);
 extern void nfs_fattr_init(struct nfs_fattr *fattr);
+extern void nfs_fattr_set_barrier(struct nfs_fattr *fattr);
 extern unsigned long nfs_inc_attr_generation_counter(void);
 
 extern struct nfs_fattr *nfs_alloc_fattr(void);
diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h
index 8a860f096c35..611a691145c4 100644
--- a/include/linux/of_platform.h
+++ b/include/linux/of_platform.h
@@ -84,7 +84,7 @@ static inline int of_platform_populate(struct device_node *root,
 static inline void of_platform_depopulate(struct device *parent) { }
 #endif
 
-#ifdef CONFIG_OF_DYNAMIC
+#if defined(CONFIG_OF_DYNAMIC) && defined(CONFIG_OF_ADDRESS)
 extern void of_platform_register_reconfig_notifier(void);
 #else
 static inline void of_platform_register_reconfig_notifier(void) { }
diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 58851275fed9..d438eeb08bff 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -54,10 +54,11 @@ struct rhash_head {
  * @buckets: size * hash buckets
  */
 struct bucket_table {
-	size_t				size;
-	unsigned int			locks_mask;
-	spinlock_t			*locks;
-	struct rhash_head __rcu		*buckets[];
+	size_t			size;
+	unsigned int		locks_mask;
+	spinlock_t		*locks;
+
+	struct rhash_head __rcu	*buckets[] ____cacheline_aligned_in_smp;
 };
 
 typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed);
@@ -78,12 +79,6 @@ struct rhashtable;
  * @locks_mul: Number of bucket locks to allocate per cpu (default: 128)
  * @hashfn: Function to hash key
  * @obj_hashfn: Function to hash object
- * @grow_decision: If defined, may return true if table should expand
- * @shrink_decision: If defined, may return true if table should shrink
- *
- * Note: when implementing the grow and shrink decision function, min/max
- * shift must be enforced, otherwise, resizing watermarks they set may be
- * useless.
  */
 struct rhashtable_params {
 	size_t			nelem_hint;
@@ -97,10 +92,6 @@ struct rhashtable_params {
 	size_t			locks_mul;
 	rht_hashfn_t		hashfn;
 	rht_obj_hashfn_t	obj_hashfn;
-	bool			(*grow_decision)(const struct rhashtable *ht,
-						 size_t new_size);
-	bool			(*shrink_decision)(const struct rhashtable *ht,
-						   size_t new_size);
 };
 
 /**
@@ -192,9 +183,6 @@ int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params);
 void rhashtable_insert(struct rhashtable *ht, struct rhash_head *node);
 bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *node);
 
-bool rht_grow_above_75(const struct rhashtable *ht, size_t new_size);
-bool rht_shrink_below_30(const struct rhashtable *ht, size_t new_size);
-
 int rhashtable_expand(struct rhashtable *ht);
 int rhashtable_shrink(struct rhashtable *ht);
 
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index baf3e1d08416..d10965f0d8a4 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -143,13 +143,13 @@ struct uart_port {
 	unsigned char		iotype;			/* io access style */
 	unsigned char		unused1;
 
-#define UPIO_PORT		(0)			/* 8b I/O port access */
-#define UPIO_HUB6		(1)			/* Hub6 ISA card */
-#define UPIO_MEM		(2)			/* 8b MMIO access */
-#define UPIO_MEM32		(3)			/* 32b little endian */
-#define UPIO_MEM32BE		(4)			/* 32b big endian */
-#define UPIO_AU			(5)			/* Au1x00 and RT288x type IO */
-#define UPIO_TSI		(6)			/* Tsi108/109 type IO */
+#define UPIO_PORT		(SERIAL_IO_PORT)	/* 8b I/O port access */
+#define UPIO_HUB6		(SERIAL_IO_HUB6)	/* Hub6 ISA card */
+#define UPIO_MEM		(SERIAL_IO_MEM)		/* 8b MMIO access */
+#define UPIO_MEM32		(SERIAL_IO_MEM32)	/* 32b little endian */
+#define UPIO_AU			(SERIAL_IO_AU)		/* Au1x00 and RT288x type IO */
+#define UPIO_TSI		(SERIAL_IO_TSI)		/* Tsi108/109 type IO */
+#define UPIO_MEM32BE		(SERIAL_IO_MEM32BE)	/* 32b big endian */
 
 	unsigned int		read_status_mask;	/* driver specific */
 	unsigned int		ignore_status_mask;	/* driver specific */
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index ed9489d893a4..856d34dde79b 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -649,7 +649,7 @@ struct spi_transfer {
  * sequence completes.  On some systems, many such sequences can execute as
  * as single programmed DMA transfer.  On all systems, these messages are
  * queued, and might complete after transactions to other devices.  Messages
- * sent to a given spi_device are alway executed in FIFO order.
+ * sent to a given spi_device are always executed in FIFO order.
  *
  * The code that submits an spi_message (and its spi_transfers)
  * to the lower layers is responsible for managing its memory.
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 07a022641996..71880299ed48 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -98,6 +98,8 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages,
 			size_t maxsize, size_t *start);
 int iov_iter_npages(const struct iov_iter *i, int maxpages);
 
+const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags);
+
 static inline size_t iov_iter_count(struct iov_iter *i)
 {
 	return i->count;
diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h
index 9bb547c7bce7..704a1ab8240c 100644
--- a/include/linux/usb/serial.h
+++ b/include/linux/usb/serial.h
@@ -190,8 +190,7 @@ static inline void usb_set_serial_data(struct usb_serial *serial, void *data)
  * @num_ports: the number of different ports this device will have.
  * @bulk_in_size: minimum number of bytes to allocate for bulk-in buffer
  *	(0 = end-point size)
- * @bulk_out_size: minimum number of bytes to allocate for bulk-out buffer
- *	(0 = end-point size)
+ * @bulk_out_size: bytes to allocate for bulk-out buffer (0 = end-point size)
  * @calc_num_ports: pointer to a function to determine how many ports this
  *	device has dynamically.  It will be called after the probe()
  *	callback is called, but before attach()
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 7d7acb35603d..0ec598381f97 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -17,6 +17,7 @@ struct vm_area_struct;		/* vma defining user mapping in mm_types.h */
 #define VM_VPAGES		0x00000010	/* buffer for pages was vmalloc'ed */
 #define VM_UNINITIALIZED	0x00000020	/* vm_struct is not fully initialized */
 #define VM_NO_GUARD		0x00000040      /* don't add guard page */
+#define VM_KASAN		0x00000080      /* has allocated kasan shadow memory */
 /* bits [20..32] reserved for arch specific ioremap internals */
 
 /*
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 74db135f9957..f597846ff605 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -70,7 +70,8 @@ enum {
 	/* data contains off-queue information when !WORK_STRUCT_PWQ */
 	WORK_OFFQ_FLAG_BASE	= WORK_STRUCT_COLOR_SHIFT,
 
-	WORK_OFFQ_CANCELING	= (1 << WORK_OFFQ_FLAG_BASE),
+	__WORK_OFFQ_CANCELING	= WORK_OFFQ_FLAG_BASE,
+	WORK_OFFQ_CANCELING	= (1 << __WORK_OFFQ_CANCELING),
 
 	/*
 	 * When a work item is off queue, its high bits point to the last