Merge branch 'master' into sh/hwblk

29 files changed, 392 insertions, 138 deletions

diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h
index 3e798593b17b..ab0b85cf21f3 100644
--- a/include/acpi/acpiosxf.h
+++ b/include/acpi/acpiosxf.h
@@ -242,6 +242,10 @@ acpi_os_derive_pci_id(acpi_handle rhandle,
 acpi_status acpi_os_validate_interface(char *interface);
 acpi_status acpi_osi_invalidate(char* interface);
 
+acpi_status
+acpi_os_validate_address(u8 space_id, acpi_physical_address address,
+			 acpi_size length, char *name);
+
 u64 acpi_os_get_timer(void);
 
 acpi_status acpi_os_signal(u32 function, void *info);
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 7174818c2c13..853508499d20 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -257,9 +257,12 @@
 	{0x1002, 0x940F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R600|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x94A0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x94A1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x94A3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x94B1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x94B3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x94B4, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x94B5, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x94B9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x9440, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV770|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x9441, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV770|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x9442, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV770|RADEON_NEW_MEMMAP}, \
@@ -288,6 +291,7 @@
 	{0x1002, 0x948F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x9490, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x9491, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x9495, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x9498, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x949C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x949E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \
@@ -325,6 +329,7 @@
 	{0x1002, 0x9552, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV710|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x9553, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV710|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x9555, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV710|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x9557, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV710|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x9580, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV630|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x9581, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV630|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x9583, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV630|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
@@ -365,6 +370,11 @@
 	{0x1002, 0x9614, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS780|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9615, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS780|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9616, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS780|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9710, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9711, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9712, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9713, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9714, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0, 0, 0}
 
 #define r128_PCI_IDS \
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index e7cb5dbf6c26..69103e053c92 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -913,6 +913,7 @@ extern void blk_queue_logical_block_size(struct request_queue *, unsigned short)
 extern void blk_queue_physical_block_size(struct request_queue *, unsigned short);
 extern void blk_queue_alignment_offset(struct request_queue *q,
 				       unsigned int alignment);
+extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
 extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
 extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt);
 extern void blk_set_default_limits(struct queue_limits *lim);
diff --git a/include/linux/cb710.h b/include/linux/cb710.h
index 63bc9a4d2926..8cc10411bab2 100644
--- a/include/linux/cb710.h
+++ b/include/linux/cb710.h
@@ -140,29 +140,6 @@ void cb710_dump_regs(struct cb710_chip *chip, unsigned dump);
 #include <linux/highmem.h>
 #include <linux/scatterlist.h>
 
-/**
- * cb710_sg_miter_stop_writing - stop mapping iteration after writing
- * @miter: sg mapping iter to be stopped
- *
- * Description:
- *   Stops mapping iterator @miter.  @miter should have been started
- *   started using sg_miter_start().  A stopped iteration can be
- *   resumed by calling sg_miter_next() on it.  This is useful when
- *   resources (kmap) need to be released during iteration.
- *
- *   This is a convenience wrapper that will be optimized out for arches
- *   that don't need flush_kernel_dcache_page().
- *
- * Context:
- *   IRQ disabled if the SG_MITER_ATOMIC is set.  Don't care otherwise.
- */
-static inline void cb710_sg_miter_stop_writing(struct sg_mapping_iter *miter)
-{
-	if (miter->page)
-		flush_kernel_dcache_page(miter->page);
-	sg_miter_stop(miter);
-}
-
 /*
  * 32-bit PIO mapping sg iterator
  *
@@ -171,12 +148,12 @@ static inline void cb710_sg_miter_stop_writing(struct sg_mapping_iter *miter)
  * without DMA support).
  *
  * Best-case reading (transfer from device):
- *   sg_miter_start();
+ *   sg_miter_start(, SG_MITER_TO_SG);
  *   cb710_sg_dwiter_write_from_io();
- *   cb710_sg_miter_stop_writing();
+ *   sg_miter_stop();
  *
  * Best-case writing (transfer to device):
- *   sg_miter_start();
+ *   sg_miter_start(, SG_MITER_FROM_SG);
  *   cb710_sg_dwiter_read_to_io();
  *   sg_miter_stop();
  */
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index c56457c8334e..1219be4fb42e 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -293,7 +293,12 @@ static inline int clocksource_enable(struct clocksource *cs)
 	if (cs->enable)
 		ret = cs->enable(cs);
 
-	/* save mult_orig on enable */
+	/*
+	 * The frequency may have changed while the clocksource
+	 * was disabled. If so the code in ->enable() must update
+	 * the mult value to reflect the new frequency. Make sure
+	 * mult_orig follows this change.
+	 */
 	cs->mult_orig = cs->mult;
 
 	return ret;
@@ -309,6 +314,13 @@ static inline int clocksource_enable(struct clocksource *cs)
  */
 static inline void clocksource_disable(struct clocksource *cs)
 {
+	/*
+	 * Save mult_orig in mult so clocksource_enable() can
+	 * restore the value regardless if ->enable() updates
+	 * the value of mult or not.
+	 */
+	cs->mult = cs->mult_orig;
+
 	if (cs->disable)
 		cs->disable(cs);
 }
diff --git a/include/linux/decompress/generic.h b/include/linux/decompress/generic.h
index 6dfb856327bb..0c7111a55a1a 100644
--- a/include/linux/decompress/generic.h
+++ b/include/linux/decompress/generic.h
@@ -1,31 +1,37 @@
 #ifndef DECOMPRESS_GENERIC_H
 #define DECOMPRESS_GENERIC_H
 
-/* Minimal chunksize to be read.
- *Bzip2 prefers at least 4096
- *Lzma prefers 0x10000 */
-#define COMPR_IOBUF_SIZE	4096
-
 typedef int (*decompress_fn) (unsigned char *inbuf, int len,
 			      int(*fill)(void*, unsigned int),
-			      int(*writebb)(void*, unsigned int),
-			      unsigned char *output,
+			      int(*flush)(void*, unsigned int),
+			      unsigned char *outbuf,
 			      int *posp,
 			      void(*error)(char *x));
 
 /* inbuf   - input buffer
  *len     - len of pre-read data in inbuf
- *fill    - function to fill inbuf if empty
- *writebb - function to write out outbug
+ *fill    - function to fill inbuf when empty
+ *flush   - function to write out outbuf
+ *outbuf  - output buffer
  *posp    - if non-null, input position (number of bytes read) will be
  *	  returned here
  *
- *If len != 0, the inbuf is initialized (with as much data), and fill
- *should not be called
- *If len = 0, the inbuf is allocated, but empty. Its size is IOBUF_SIZE
- *fill should be called (repeatedly...) to read data, at most IOBUF_SIZE
+ *If len != 0, inbuf should contain all the necessary input data, and fill
+ *should be NULL
+ *If len = 0, inbuf can be NULL, in which case the decompressor will allocate
+ *the input buffer.  If inbuf != NULL it must be at least XXX_IOBUF_SIZE bytes.
+ *fill will be called (repeatedly...) to read data, at most XXX_IOBUF_SIZE
+ *bytes should be read per call.  Replace XXX with the appropriate decompressor
+ *name, i.e. LZMA_IOBUF_SIZE.
+ *
+ *If flush = NULL, outbuf must be large enough to buffer all the expected
+ *output.  If flush != NULL, the output buffer will be allocated by the
+ *decompressor (outbuf = NULL), and the flush function will be called to
+ *flush the output buffer at the appropriate time (decompressor and stream
+ *dependent).
  */
 
+
 /* Utility routine to detect the decompression method */
 decompress_fn decompress_method(const unsigned char *inbuf, int len,
 				const char **name);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a36ffa5a77a4..67888a9e0655 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2137,7 +2137,7 @@ extern loff_t default_llseek(struct file *file, loff_t offset, int origin);
 
 extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin);
 
-extern struct inode * inode_init_always(struct super_block *, struct inode *);
+extern int inode_init_always(struct super_block *, struct inode *);
 extern void inode_init_once(struct inode *);
 extern void inode_add_to_lists(struct super_block *, struct inode *);
 extern void iput(struct inode *);
@@ -2164,6 +2164,7 @@ extern void __iget(struct inode * inode);
 extern void iget_failed(struct inode *);
 extern void clear_inode(struct inode *);
 extern void destroy_inode(struct inode *);
+extern void __destroy_inode(struct inode *);
 extern struct inode *new_inode(struct super_block *);
 extern int should_remove_suid(struct dentry *);
 extern int file_remove_suid(struct file *);
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 5c093ffc655b..a81170de7f6b 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -89,7 +89,9 @@ enum print_line_t {
 	TRACE_TYPE_NO_CONSUME	= 3	/* Handled but ask to not consume */
 };
 
-
+void tracing_generic_entry_update(struct trace_entry *entry,
+				  unsigned long flags,
+				  int pc);
 struct ring_buffer_event *
 trace_current_buffer_lock_reserve(int type, unsigned long len,
 				  unsigned long flags, int pc);
@@ -119,11 +121,9 @@ struct ftrace_event_call {
 	void			*filter;
 	void			*mod;
 
-#ifdef CONFIG_EVENT_PROFILE
-	atomic_t	profile_count;
-	int		(*profile_enable)(struct ftrace_event_call *);
-	void		(*profile_disable)(struct ftrace_event_call *);
-#endif
+	atomic_t		profile_count;
+	int			(*profile_enable)(struct ftrace_event_call *);
+	void			(*profile_disable)(struct ftrace_event_call *);
 };
 
 #define MAX_FILTER_PRED		32
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index acef2a770b6b..ad27c7da8798 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -82,7 +82,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev)
 
 #define IN_DEV_FORWARD(in_dev)		IN_DEV_CONF_GET((in_dev), FORWARDING)
 #define IN_DEV_MFORWARD(in_dev)		IN_DEV_ANDCONF((in_dev), MC_FORWARDING)
-#define IN_DEV_RPFILTER(in_dev)		IN_DEV_ANDCONF((in_dev), RP_FILTER)
+#define IN_DEV_RPFILTER(in_dev)		IN_DEV_MAXCONF((in_dev), RP_FILTER)
 #define IN_DEV_SOURCE_ROUTE(in_dev)	IN_DEV_ANDCONF((in_dev), \
 						       ACCEPT_SOURCE_ROUTE)
 #define IN_DEV_BOOTP_RELAY(in_dev)	IN_DEV_ANDCONF((in_dev), BOOTP_RELAY)
diff --git a/include/linux/input/matrix_keypad.h b/include/linux/input/matrix_keypad.h
index 7964516c6954..15d5903af2dd 100644
--- a/include/linux/input/matrix_keypad.h
+++ b/include/linux/input/matrix_keypad.h
@@ -15,12 +15,13 @@
 #define KEY_COL(k)		(((k) >> 16) & 0xff)
 #define KEY_VAL(k)		((k) & 0xffff)
 
+#define MATRIX_SCAN_CODE(row, col, row_shift)	(((row) << (row_shift)) + (col))
+
 /**
  * struct matrix_keymap_data - keymap for matrix keyboards
  * @keymap: pointer to array of uint32 values encoded with KEY() macro
  *	representing keymap
  * @keymap_size: number of entries (initialized) in this keymap
- * @max_keymap_size: maximum size of keymap supported by the device
  *
  * This structure is supposed to be used by platform code to supply
  * keymaps to drivers that implement matrix-like keypads/keyboards.
@@ -28,14 +29,13 @@
 struct matrix_keymap_data {
 	const uint32_t *keymap;
 	unsigned int	keymap_size;
-	unsigned int	max_keymap_size;
 };
 
 /**
  * struct matrix_keypad_platform_data - platform-dependent keypad data
  * @keymap_data: pointer to &matrix_keymap_data
- * @row_gpios: array of gpio numbers reporesenting rows
- * @col_gpios: array of gpio numbers reporesenting colums
+ * @row_gpios: pointer to array of gpio numbers representing rows
+ * @col_gpios: pointer to array of gpio numbers reporesenting colums
  * @num_row_gpios: actual number of row gpios used by device
  * @num_col_gpios: actual number of col gpios used by device
  * @col_scan_delay_us: delay, measured in microseconds, that is
@@ -48,8 +48,9 @@ struct matrix_keymap_data {
 struct matrix_keypad_platform_data {
 	const struct matrix_keymap_data *keymap_data;
 
-	unsigned int	row_gpios[MATRIX_MAX_ROWS];
-	unsigned int	col_gpios[MATRIX_MAX_COLS];
+	const unsigned int *row_gpios;
+	const unsigned int *col_gpios;
+
 	unsigned int	num_row_gpios;
 	unsigned int	num_col_gpios;
 
diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index dd05434fa45f..4da4a75c3f1e 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -92,7 +92,7 @@ static inline struct io_context *ioc_task_link(struct io_context *ioc)
 	 * a race).
 	 */
 	if (ioc && atomic_long_inc_not_zero(&ioc->refcount)) {
-		atomic_long_inc(&ioc->refcount);
+		atomic_inc(&ioc->nr_tasks);
 		return ioc;
 	}
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 16713dc672e4..3060bdc35ffe 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -110,6 +110,7 @@ struct kvm_memory_slot {
 
 struct kvm_kernel_irq_routing_entry {
 	u32 gsi;
+	u32 type;
 	int (*set)(struct kvm_kernel_irq_routing_entry *e,
 		    struct kvm *kvm, int level);
 	union {
diff --git a/include/linux/lguest.h b/include/linux/lguest.h
index dbf2479e808e..2fb1dcbcb5aa 100644
--- a/include/linux/lguest.h
+++ b/include/linux/lguest.h
@@ -1,5 +1,7 @@
-/* Things the lguest guest needs to know.  Note: like all lguest interfaces,
- * this is subject to wild and random change between versions. */
+/*
+ * Things the lguest guest needs to know.  Note: like all lguest interfaces,
+ * this is subject to wild and random change between versions.
+ */
 #ifndef _LINUX_LGUEST_H
 #define _LINUX_LGUEST_H
 
@@ -11,32 +13,41 @@
 #define LG_CLOCK_MIN_DELTA	100UL
 #define LG_CLOCK_MAX_DELTA	ULONG_MAX
 
-/*G:031 The second method of communicating with the Host is to via "struct
+/*G:031
+ * The second method of communicating with the Host is to via "struct
  * lguest_data".  Once the Guest's initialization hypercall tells the Host where
- * this is, the Guest and Host both publish information in it. :*/
-struct lguest_data
-{
-	/* 512 == enabled (same as eflags in normal hardware).  The Guest
-	 * changes interrupts so often that a hypercall is too slow. */
+ * this is, the Guest and Host both publish information in it.
+:*/
+struct lguest_data {
+	/*
+	 * 512 == enabled (same as eflags in normal hardware).  The Guest
+	 * changes interrupts so often that a hypercall is too slow.
+	 */
 	unsigned int irq_enabled;
 	/* Fine-grained interrupt disabling by the Guest */
 	DECLARE_BITMAP(blocked_interrupts, LGUEST_IRQS);
 
-	/* The Host writes the virtual address of the last page fault here,
+	/*
+	 * The Host writes the virtual address of the last page fault here,
 	 * which saves the Guest a hypercall.  CR2 is the native register where
-	 * this address would normally be found. */
+	 * this address would normally be found.
+	 */
 	unsigned long cr2;
 
 	/* Wallclock time set by the Host. */
 	struct timespec time;
 
-	/* Interrupt pending set by the Host.  The Guest should do a hypercall
-	 * if it re-enables interrupts and sees this set (to X86_EFLAGS_IF). */
+	/*
+	 * Interrupt pending set by the Host.  The Guest should do a hypercall
+	 * if it re-enables interrupts and sees this set (to X86_EFLAGS_IF).
+	 */
 	int irq_pending;
 
-	/* Async hypercall ring.  Instead of directly making hypercalls, we can
+	/*
+	 * Async hypercall ring.  Instead of directly making hypercalls, we can
 	 * place them in here for processing the next time the Host wants.
-	 * This batching can be quite efficient. */
+	 * This batching can be quite efficient.
+	 */
 
 	/* 0xFF == done (set by Host), 0 == pending (set by Guest). */
 	u8 hcall_status[LHCALL_RING_SIZE];
diff --git a/include/linux/lguest_launcher.h b/include/linux/lguest_launcher.h
index bfefbdf7498a..495203ff221c 100644
--- a/include/linux/lguest_launcher.h
+++ b/include/linux/lguest_launcher.h
@@ -29,8 +29,10 @@ struct lguest_device_desc {
 	__u8 type;
 	/* The number of virtqueues (first in config array) */
 	__u8 num_vq;
-	/* The number of bytes of feature bits.  Multiply by 2: one for host
-	 * features and one for Guest acknowledgements. */
+	/*
+	 * The number of bytes of feature bits.  Multiply by 2: one for host
+	 * features and one for Guest acknowledgements.
+	 */
 	__u8 feature_len;
 	/* The number of bytes of the config array after virtqueues. */
 	__u8 config_len;
@@ -39,8 +41,10 @@ struct lguest_device_desc {
 	__u8 config[0];
 };
 
-/*D:135 This is how we expect the device configuration field for a virtqueue
- * to be laid out in config space. */
+/*D:135
+ * This is how we expect the device configuration field for a virtqueue
+ * to be laid out in config space.
+ */
 struct lguest_vqconfig {
 	/* The number of entries in the virtio_ring */
 	__u16 num;
@@ -61,7 +65,9 @@ enum lguest_req
 	LHREQ_EVENTFD, /* + address, fd. */
 };
 
-/* The alignment to use between consumer and producer parts of vring.
- * x86 pagesize for historical reasons. */
+/*
+ * The alignment to use between consumer and producer parts of vring.
+ * x86 pagesize for historical reasons.
+ */
 #define LGUEST_VRING_ALIGN	4096
 #endif /* _LINUX_LGUEST_LAUNCHER */
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index 5675b63a0631..0f32a9b6ff55 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -251,7 +251,7 @@ struct mtd_info {
 
 static inline struct mtd_info *dev_to_mtd(struct device *dev)
 {
-	return dev ? container_of(dev, struct mtd_info, dev) : NULL;
+	return dev ? dev_get_drvdata(dev) : NULL;
 }
 
 static inline uint32_t mtd_div_by_eb(uint64_t sz, struct mtd_info *mtd)
diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h
index af6dcb992bc3..b70313d33ff8 100644
--- a/include/linux/mtd/partitions.h
+++ b/include/linux/mtd/partitions.h
@@ -47,6 +47,8 @@ struct mtd_partition {
 #define MTDPART_SIZ_FULL	(0)
 
 
+struct mtd_info;
+
 int add_mtd_partitions(struct mtd_info *, const struct mtd_partition *, int);
 int del_mtd_partitions(struct mtd_info *);
 
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index fdffb413b192..f6b90240dd41 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -473,7 +473,6 @@ extern int  nfs_writepages(struct address_space *, struct writeback_control *);
 extern int  nfs_flush_incompatible(struct file *file, struct page *page);
 extern int  nfs_updatepage(struct file *, struct page *, unsigned int, unsigned int);
 extern int nfs_writeback_done(struct rpc_task *, struct nfs_write_data *);
-extern void nfs_writedata_release(void *);
 
 /*
  * Try to write back everything synchronously (but check the
@@ -488,7 +487,6 @@ extern int nfs_wb_page_cancel(struct inode *inode, struct page* page);
 extern int  nfs_commit_inode(struct inode *, int);
 extern struct nfs_write_data *nfs_commitdata_alloc(void);
 extern void nfs_commit_free(struct nfs_write_data *wdata);
-extern void nfs_commitdata_release(void *wdata);
 #else
 static inline int
 nfs_commit_inode(struct inode *inode, int how)
@@ -507,6 +505,7 @@ nfs_have_writebacks(struct inode *inode)
  * Allocate nfs_write_data structures
  */
 extern struct nfs_write_data *nfs_writedata_alloc(unsigned int npages);
+extern void nfs_writedata_free(struct nfs_write_data *);
 
 /*
  * linux/fs/nfs/read.c
@@ -515,7 +514,6 @@ extern int  nfs_readpage(struct file *, struct page *);
 extern int  nfs_readpages(struct file *, struct address_space *,
 		struct list_head *, unsigned);
 extern int  nfs_readpage_result(struct rpc_task *, struct nfs_read_data *);
-extern void nfs_readdata_release(void *data);
 extern int  nfs_readpage_async(struct nfs_open_context *, struct inode *,
 			       struct page *);
 
@@ -523,6 +521,7 @@ extern int  nfs_readpage_async(struct nfs_open_context *, struct inode *,
  * Allocate nfs_read_data structures
  */
 extern struct nfs_read_data *nfs_readdata_alloc(unsigned int npages);
+extern void nfs_readdata_free(struct nfs_read_data *);
 
 /*
  * linux/fs/nfs3proc.c
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 829b94b156f2..b359c4a9ec9e 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -82,6 +82,12 @@
  *    to generate slightly worse code.  So use a simple one-line #define
  *    for node_isset(), instead of wrapping an inline inside a macro, the
  *    way we do the other calls.
+ *
+ * NODEMASK_SCRATCH
+ * When doing above logical AND, OR, XOR, Remap operations the callers tend to
+ * need temporary nodemask_t's on the stack. But if NODES_SHIFT is large,
+ * nodemask_t's consume too much stack space.  NODEMASK_SCRATCH is a helper
+ * for such situations. See below and CPUMASK_ALLOC also.
  */
 
 #include <linux/kernel.h>
@@ -473,4 +479,26 @@ static inline int num_node_state(enum node_states state)
 #define for_each_node(node)	   for_each_node_state(node, N_POSSIBLE)
 #define for_each_online_node(node) for_each_node_state(node, N_ONLINE)
 
+/*
+ * For nodemask scrach area.(See CPUMASK_ALLOC() in cpumask.h)
+ */
+
+#if NODES_SHIFT > 8 /* nodemask_t > 64 bytes */
+#define NODEMASK_ALLOC(x, m) struct x *m = kmalloc(sizeof(*m), GFP_KERNEL)
+#define NODEMASK_FREE(m) kfree(m)
+#else
+#define NODEMASK_ALLOC(x, m) struct x _m, *m = &_m
+#define NODEMASK_FREE(m)
+#endif
+
+/* A example struture for using NODEMASK_ALLOC, used in mempolicy. */
+struct nodemask_scratch {
+	nodemask_t	mask1;
+	nodemask_t	mask2;
+};
+
+#define NODEMASK_SCRATCH(x) NODEMASK_ALLOC(nodemask_scratch, x)
+#define NODEMASK_SCRATCH_FREE(x)  NODEMASK_FREE(x)
+
+
 #endif /* __LINUX_NODEMASK_H */
diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index bd15d7a5f5ce..b53f7006cc4e 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -115,27 +115,44 @@ enum perf_counter_sample_format {
 	PERF_SAMPLE_TID				= 1U << 1,
 	PERF_SAMPLE_TIME			= 1U << 2,
 	PERF_SAMPLE_ADDR			= 1U << 3,
-	PERF_SAMPLE_GROUP			= 1U << 4,
+	PERF_SAMPLE_READ			= 1U << 4,
 	PERF_SAMPLE_CALLCHAIN			= 1U << 5,
 	PERF_SAMPLE_ID				= 1U << 6,
 	PERF_SAMPLE_CPU				= 1U << 7,
 	PERF_SAMPLE_PERIOD			= 1U << 8,
 	PERF_SAMPLE_STREAM_ID			= 1U << 9,
+	PERF_SAMPLE_RAW				= 1U << 10,
 
-	PERF_SAMPLE_MAX = 1U << 10,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 11,		/* non-ABI */
 };
 
 /*
- * Bits that can be set in attr.read_format to request that
- * reads on the counter should return the indicated quantities,
- * in increasing order of bit value, after the counter value.
+ * The format of the data returned by read() on a perf counter fd,
+ * as specified by attr.read_format:
+ *
+ * struct read_format {
+ * 	{ u64		value;
+ * 	  { u64		time_enabled; } && PERF_FORMAT_ENABLED
+ * 	  { u64		time_running; } && PERF_FORMAT_RUNNING
+ * 	  { u64		id;           } && PERF_FORMAT_ID
+ * 	} && !PERF_FORMAT_GROUP
+ *
+ * 	{ u64		nr;
+ * 	  { u64		time_enabled; } && PERF_FORMAT_ENABLED
+ * 	  { u64		time_running; } && PERF_FORMAT_RUNNING
+ * 	  { u64		value;
+ * 	    { u64	id;           } && PERF_FORMAT_ID
+ * 	  }		cntr[nr];
+ * 	} && PERF_FORMAT_GROUP
+ * };
  */
 enum perf_counter_read_format {
 	PERF_FORMAT_TOTAL_TIME_ENABLED		= 1U << 0,
 	PERF_FORMAT_TOTAL_TIME_RUNNING		= 1U << 1,
 	PERF_FORMAT_ID				= 1U << 2,
+	PERF_FORMAT_GROUP			= 1U << 3,
 
-	PERF_FORMAT_MAX = 1U << 3, 		/* non-ABI */
+	PERF_FORMAT_MAX = 1U << 4, 		/* non-ABI */
 };
 
 #define PERF_ATTR_SIZE_VER0	64	/* sizeof first published struct */
@@ -181,8 +198,9 @@ struct perf_counter_attr {
 				freq           :  1, /* use freq, not period  */
 				inherit_stat   :  1, /* per task counts       */
 				enable_on_exec :  1, /* next exec enables     */
+				task           :  1, /* trace fork/exit       */
 
-				__reserved_1   : 51;
+				__reserved_1   : 50;
 
 	__u32			wakeup_events;	/* wakeup every n events */
 	__u32			__reserved_2;
@@ -311,6 +329,15 @@ enum perf_event_type {
 	/*
 	 * struct {
 	 *	struct perf_event_header	header;
+	 *	u32				pid, ppid;
+	 *	u32				tid, ptid;
+	 * };
+	 */
+	PERF_EVENT_EXIT			= 4,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
 	 *	u64				time;
 	 *	u64				id;
 	 *	u64				stream_id;
@@ -323,6 +350,7 @@ enum perf_event_type {
 	 * struct {
 	 *	struct perf_event_header	header;
 	 *	u32				pid, ppid;
+	 *	u32				tid, ptid;
 	 * };
 	 */
 	PERF_EVENT_FORK			= 7,
@@ -331,10 +359,8 @@ enum perf_event_type {
 	 * struct {
 	 * 	struct perf_event_header	header;
 	 * 	u32				pid, tid;
-	 * 	u64				value;
-	 * 	{ u64		time_enabled; 	} && PERF_FORMAT_ENABLED
-	 * 	{ u64		time_running; 	} && PERF_FORMAT_RUNNING
-	 * 	{ u64		parent_id;	} && PERF_FORMAT_ID
+	 *
+	 * 	struct read_format		values;
 	 * };
 	 */
 	PERF_EVENT_READ			= 8,
@@ -352,11 +378,24 @@ enum perf_event_type {
 	 *	{ u32			cpu, res; } && PERF_SAMPLE_CPU
 	 * 	{ u64			period;   } && PERF_SAMPLE_PERIOD
 	 *
-	 *	{ u64			nr;
-	 *	  { u64 id, val; }	cnt[nr];  } && PERF_SAMPLE_GROUP
+	 *	{ struct read_format	values;	  } && PERF_SAMPLE_READ
 	 *
 	 *	{ u64			nr,
 	 *	  u64			ips[nr];  } && PERF_SAMPLE_CALLCHAIN
+	 *
+	 * 	#
+	 * 	# The RAW record below is opaque data wrt the ABI
+	 * 	#
+	 * 	# That is, the ABI doesn't make any promises wrt to
+	 * 	# the stability of its content, it may vary depending
+	 * 	# on event, hardware, kernel version and phase of
+	 * 	# the moon.
+	 * 	#
+	 * 	# In other words, PERF_SAMPLE_RAW contents are not an ABI.
+	 * 	#
+	 *
+	 *	{ u32			size;
+	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
 	 * };
 	 */
 	PERF_EVENT_SAMPLE		= 9,
@@ -402,6 +441,11 @@ struct perf_callchain_entry {
 	__u64				ip[PERF_MAX_STACK_DEPTH];
 };
 
+struct perf_raw_record {
+	u32				size;
+	void				*data;
+};
+
 struct task_struct;
 
 /**
@@ -670,10 +714,13 @@ struct perf_sample_data {
 	struct pt_regs			*regs;
 	u64				addr;
 	u64				period;
+	struct perf_raw_record		*raw;
 };
 
 extern int perf_counter_overflow(struct perf_counter *counter, int nmi,
 				 struct perf_sample_data *data);
+extern void perf_counter_output(struct perf_counter *counter, int nmi,
+				struct perf_sample_data *data);
 
 /*
  * Return 1 for a software counter, 0 for a hardware counter
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index e5996984ddd0..9aaf5bfdad1a 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -242,6 +242,8 @@ size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents,
  */
 
 #define SG_MITER_ATOMIC		(1 << 0)	 /* use kmap_atomic */
+#define SG_MITER_TO_SG		(1 << 1)	/* flush back to phys on unmap */
+#define SG_MITER_FROM_SG	(1 << 2)	/* nop */
 
 struct sg_mapping_iter {
 	/* the following three fields can be accessed directly */
diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h
index 40f38d896777..0c4ee9b88f85 100644
--- a/include/linux/tty_ldisc.h
+++ b/include/linux/tty_ldisc.h
@@ -144,7 +144,7 @@ struct tty_ldisc_ops {
 
 struct tty_ldisc {
 	struct tty_ldisc_ops *ops;
-	int refcount;
+	atomic_t users;
 };
 
 #define TTY_LDISC_MAGIC	0x5403
diff --git a/include/linux/virtio_blk.h b/include/linux/virtio_blk.h
index be7d255fc7cf..8dab9f2b8832 100644
--- a/include/linux/virtio_blk.h
+++ b/include/linux/virtio_blk.h
@@ -20,8 +20,7 @@
 
 #define VIRTIO_BLK_ID_BYTES	(sizeof(__u16[256]))	/* IDENTIFY DATA */
 
-struct virtio_blk_config
-{
+struct virtio_blk_config {
 	/* The capacity (in 512-byte sectors). */
 	__u64 capacity;
 	/* The maximum segment size (if VIRTIO_BLK_F_SIZE_MAX) */
@@ -50,8 +49,7 @@ struct virtio_blk_config
 #define VIRTIO_BLK_T_BARRIER	0x80000000
 
 /* This is the first element of the read scatter-gather list. */
-struct virtio_blk_outhdr
-{
+struct virtio_blk_outhdr {
 	/* VIRTIO_BLK_T* */
 	__u32 type;
 	/* io priority. */
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 99f514575f6a..e547e3c8ee9a 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -79,8 +79,7 @@
  *	the dev->feature bits if it wants.
  */
 typedef void vq_callback_t(struct virtqueue *);
-struct virtio_config_ops
-{
+struct virtio_config_ops {
 	void (*get)(struct virtio_device *vdev, unsigned offset,
 		    void *buf, unsigned len);
 	void (*set)(struct virtio_device *vdev, unsigned offset,
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 9c543d6ac535..d8dd539c9f48 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -31,8 +31,7 @@
 
 #define VIRTIO_NET_S_LINK_UP	1	/* Link is up */
 
-struct virtio_net_config
-{
+struct virtio_net_config {
 	/* The config defining mac address (if VIRTIO_NET_F_MAC) */
 	__u8 mac[6];
 	/* See VIRTIO_NET_F_STATUS and VIRTIO_NET_S_* above */
@@ -41,8 +40,7 @@ struct virtio_net_config
 
 /* This is the first element of the scatter-gather list.  If you don't
  * specify GSO or CSUM features, you can simply ignore the header. */
-struct virtio_net_hdr
-{
+struct virtio_net_hdr {
 #define VIRTIO_NET_HDR_F_NEEDS_CSUM	1	// Use csum_start, csum_offset
 	__u8 flags;
 #define VIRTIO_NET_HDR_GSO_NONE		0	// Not a GSO frame
diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
index 693e0ec5afa6..e4d144b132b5 100644
--- a/include/linux/virtio_ring.h
+++ b/include/linux/virtio_ring.h
@@ -30,8 +30,7 @@
 #define VIRTIO_RING_F_INDIRECT_DESC	28
 
 /* Virtio ring descriptors: 16 bytes.  These can chain together via "next". */
-struct vring_desc
-{
+struct vring_desc {
 	/* Address (guest-physical). */
 	__u64 addr;
 	/* Length. */
@@ -42,24 +41,21 @@ struct vring_desc
 	__u16 next;
 };
 
-struct vring_avail
-{
+struct vring_avail {
 	__u16 flags;
 	__u16 idx;
 	__u16 ring[];
 };
 
 /* u32 is used here for ids for padding reasons. */
-struct vring_used_elem
-{
+struct vring_used_elem {
 	/* Index of start of used descriptor chain. */
 	__u32 id;
 	/* Total length of the descriptor chain which was used (written to) */
 	__u32 len;
 };
 
-struct vring_used
-{
+struct vring_used {
 	__u16 flags;
 	__u16 idx;
 	struct vring_used_elem ring[];
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 6788e1a4d4ca..cf3c2f5dba51 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -77,7 +77,14 @@ struct task_struct;
 #define __WAIT_BIT_KEY_INITIALIZER(word, bit)				\
 	{ .flags = word, .bit_nr = bit, }
 
-extern void init_waitqueue_head(wait_queue_head_t *q);
+extern void __init_waitqueue_head(wait_queue_head_t *q, struct lock_class_key *);
+
+#define init_waitqueue_head(q)				\
+	do {						\
+		static struct lock_class_key __key;	\
+							\
+		__init_waitqueue_head((q), &__key);	\
+	} while (0)
 
 #ifdef CONFIG_LOCKDEP
 # define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \
diff --git a/include/net/bluetooth/rfcomm.h b/include/net/bluetooth/rfcomm.h
index 80072611d26a..c274993234e3 100644
--- a/include/net/bluetooth/rfcomm.h
+++ b/include/net/bluetooth/rfcomm.h
@@ -355,7 +355,17 @@ struct rfcomm_dev_list_req {
 };
 
 int  rfcomm_dev_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
+
+#ifdef CONFIG_BT_RFCOMM_TTY
 int  rfcomm_init_ttys(void);
 void rfcomm_cleanup_ttys(void);
-
+#else
+static inline int rfcomm_init_ttys(void)
+{
+	return 0;
+}
+static inline void rfcomm_cleanup_ttys(void)
+{
+}
+#endif
 #endif /* __RFCOMM_H */
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 1a21895b732b..d1892d66701a 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -979,6 +979,10 @@ struct cfg80211_ops {
  * 	channels at a later time. This can be used for devices which do not
  * 	have calibration information gauranteed for frequencies or settings
  * 	outside of its regulatory domain.
+ * @disable_beacon_hints: enable this if your driver needs to ensure that
+ *	passive scan flags and beaconing flags may not be lifted by cfg80211
+ *	due to regulatory beacon hints. For more information on beacon
+ *	hints read the documenation for regulatory_hint_found_beacon()
  * @reg_notifier: the driver's regulatory notification callback
  * @regd: the driver's regulatory domain, if one was requested via
  * 	the regulatory_hint() API. This can be used by the driver
@@ -1004,6 +1008,7 @@ struct wiphy {
 
 	bool custom_regulatory;
 	bool strict_regulatory;
+	bool disable_beacon_hints;
 
 	enum cfg80211_signal_type signal_type;
 
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 1867553c61e5..f64fbaae781a 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -144,6 +144,9 @@
 #undef TP_fast_assign
 #define TP_fast_assign(args...) args
 
+#undef TP_perf_assign
+#define TP_perf_assign(args...)
+
 #undef TRACE_EVENT
 #define TRACE_EVENT(call, proto, args, tstruct, func, print)		\
 static int								\
@@ -345,6 +348,56 @@ static inline int ftrace_get_offsets_##call(				\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
+#ifdef CONFIG_EVENT_PROFILE
+
+/*
+ * Generate the functions needed for tracepoint perf_counter support.
+ *
+ * NOTE: The insertion profile callback (ftrace_profile_<call>) is defined later
+ *
+ * static int ftrace_profile_enable_<call>(struct ftrace_event_call *event_call)
+ * {
+ * 	int ret = 0;
+ *
+ * 	if (!atomic_inc_return(&event_call->profile_count))
+ * 		ret = register_trace_<call>(ftrace_profile_<call>);
+ *
+ * 	return ret;
+ * }
+ *
+ * static void ftrace_profile_disable_<call>(struct ftrace_event_call *event_call)
+ * {
+ * 	if (atomic_add_negative(-1, &event->call->profile_count))
+ * 		unregister_trace_<call>(ftrace_profile_<call>);
+ * }
+ *
+ */
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+									\
+static void ftrace_profile_##call(proto);				\
+									\
+static int ftrace_profile_enable_##call(struct ftrace_event_call *event_call) \
+{									\
+	int ret = 0;							\
+									\
+	if (!atomic_inc_return(&event_call->profile_count))		\
+		ret = register_trace_##call(ftrace_profile_##call);	\
+									\
+	return ret;							\
+}									\
+									\
+static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
+{									\
+	if (atomic_add_negative(-1, &event_call->profile_count))	\
+		unregister_trace_##call(ftrace_profile_##call);		\
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#endif
+
 /*
  * Stage 4 of the trace events.
  *
@@ -447,28 +500,6 @@ static inline int ftrace_get_offsets_##call(				\
 #define TP_FMT(fmt, args...)	fmt "\n", ##args
 
 #ifdef CONFIG_EVENT_PROFILE
-#define _TRACE_PROFILE(call, proto, args)				\
-static void ftrace_profile_##call(proto)				\
-{									\
-	extern void perf_tpcounter_event(int);				\
-	perf_tpcounter_event(event_##call.id);				\
-}									\
-									\
-static int ftrace_profile_enable_##call(struct ftrace_event_call *event_call) \
-{									\
-	int ret = 0;							\
-									\
-	if (!atomic_inc_return(&event_call->profile_count))		\
-		ret = register_trace_##call(ftrace_profile_##call);	\
-									\
-	return ret;							\
-}									\
-									\
-static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
-{									\
-	if (atomic_add_negative(-1, &event_call->profile_count))	\
-		unregister_trace_##call(ftrace_profile_##call);		\
-}
 
 #define _TRACE_PROFILE_INIT(call)					\
 	.profile_count = ATOMIC_INIT(-1),				\
@@ -476,7 +507,6 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
 	.profile_disable = ftrace_profile_disable_##call,
 
 #else
-#define _TRACE_PROFILE(call, proto, args)
 #define _TRACE_PROFILE_INIT(call)
 #endif
 
@@ -502,7 +532,6 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
 
 #undef TRACE_EVENT
 #define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
-_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args))			\
 									\
 static struct ftrace_event_call event_##call;				\
 									\
@@ -586,6 +615,110 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-#undef _TRACE_PROFILE
+/*
+ * Define the insertion callback to profile events
+ *
+ * The job is very similar to ftrace_raw_event_<call> except that we don't
+ * insert in the ring buffer but in a perf counter.
+ *
+ * static void ftrace_profile_<call>(proto)
+ * {
+ *	struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
+ *	struct ftrace_event_call *event_call = &event_<call>;
+ *	extern void perf_tpcounter_event(int, u64, u64, void *, int);
+ *	struct ftrace_raw_##call *entry;
+ *	u64 __addr = 0, __count = 1;
+ *	unsigned long irq_flags;
+ *	int __entry_size;
+ *	int __data_size;
+ *	int pc;
+ *
+ *	local_save_flags(irq_flags);
+ *	pc = preempt_count();
+ *
+ *	__data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
+ *
+ *	// Below we want to get the aligned size by taking into account
+ *	// the u32 field that will later store the buffer size
+ *	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),
+ *			     sizeof(u64));
+ *	__entry_size -= sizeof(u32);
+ *
+ *	do {
+ *		char raw_data[__entry_size]; <- allocate our sample in the stack
+ *		struct trace_entry *ent;
+ *
+ *		zero dead bytes from alignment to avoid stack leak to userspace:
+ *
+ *		*(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL;
+ *		entry = (struct ftrace_raw_<call> *)raw_data;
+ *		ent = &entry->ent;
+ *		tracing_generic_entry_update(ent, irq_flags, pc);
+ *		ent->type = event_call->id;
+ *
+ *		<tstruct> <- do some jobs with dynamic arrays
+ *
+ *		<assign>  <- affect our values
+ *
+ *		perf_tpcounter_event(event_call->id, __addr, __count, entry,
+ *			     __entry_size);  <- submit them to perf counter
+ *	} while (0);
+ *
+ * }
+ */
+
+#ifdef CONFIG_EVENT_PROFILE
+
+#undef __perf_addr
+#define __perf_addr(a) __addr = (a)
+
+#undef __perf_count
+#define __perf_count(c) __count = (c)
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+static void ftrace_profile_##call(proto)				\
+{									\
+	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
+	struct ftrace_event_call *event_call = &event_##call;		\
+	extern void perf_tpcounter_event(int, u64, u64, void *, int);	\
+	struct ftrace_raw_##call *entry;				\
+	u64 __addr = 0, __count = 1;					\
+	unsigned long irq_flags;					\
+	int __entry_size;						\
+	int __data_size;						\
+	int pc;								\
+									\
+	local_save_flags(irq_flags);					\
+	pc = preempt_count();						\
+									\
+	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
+	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
+			     sizeof(u64));				\
+	__entry_size -= sizeof(u32);					\
+									\
+	do {								\
+		char raw_data[__entry_size];				\
+		struct trace_entry *ent;				\
+									\
+		*(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL;	\
+		entry = (struct ftrace_raw_##call *)raw_data;		\
+		ent = &entry->ent;					\
+		tracing_generic_entry_update(ent, irq_flags, pc);	\
+		ent->type = event_call->id;				\
+									\
+		tstruct							\
+									\
+		{ assign; }						\
+									\
+		perf_tpcounter_event(event_call->id, __addr, __count, entry,\
+			     __entry_size);				\
+	} while (0);							\
+									\
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+#endif /* CONFIG_EVENT_PROFILE */
+
 #undef _TRACE_PROFILE_INIT