Merge branch 'oprofile/urgent' (early part) into oprofile/perf

39 files changed, 258 insertions, 98 deletions

diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index baacd98e7cc6..4de84ce3a927 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -377,9 +377,6 @@ struct acpi_pci_root {
 
 	u32 osc_support_set;	/* _OSC state of support bits */
 	u32 osc_control_set;	/* _OSC state of control bits */
-	u32 osc_control_qry;	/* the latest _OSC query result */
-
-	u32 osc_queried:1;	/* has _OSC control been queried? */
 };
 
 /* helper */
diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h
index c7376bf80b06..8ca18e26d7e3 100644
--- a/include/asm-generic/gpio.h
+++ b/include/asm-generic/gpio.h
@@ -16,15 +16,27 @@
  * While the GPIO programming interface defines valid GPIO numbers
  * to be in the range 0..MAX_INT, this library restricts them to the
  * smaller range 0..ARCH_NR_GPIOS-1.
+ *
+ * ARCH_NR_GPIOS is somewhat arbitrary; it usually reflects the sum of
+ * builtin/SoC GPIOs plus a number of GPIOs on expanders; the latter is
+ * actually an estimate of a board-specific value.
  */
 
 #ifndef ARCH_NR_GPIOS
 #define ARCH_NR_GPIOS		256
 #endif
 
+/*
+ * "valid" GPIO numbers are nonnegative and may be passed to
+ * setup routines like gpio_request().  only some valid numbers
+ * can successfully be requested and used.
+ *
+ * Invalid GPIO numbers are useful for indicating no-such-GPIO in
+ * platform data and other tables.
+ */
+
 static inline int gpio_is_valid(int number)
 {
-	/* only some non-negative numbers are valid */
 	return ((unsigned)number) < ARCH_NR_GPIOS;
 }
 
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index b5043a9890d8..08923b684768 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -70,11 +70,16 @@ extern void setup_per_cpu_areas(void);
 
 #else /* ! SMP */
 
-#define per_cpu(var, cpu)			(*((void)(cpu), &(var)))
-#define __get_cpu_var(var)			(var)
-#define __raw_get_cpu_var(var)			(var)
-#define this_cpu_ptr(ptr) per_cpu_ptr(ptr, 0)
-#define __this_cpu_ptr(ptr) this_cpu_ptr(ptr)
+#define VERIFY_PERCPU_PTR(__p) ({			\
+	__verify_pcpu_ptr((__p));			\
+	(typeof(*(__p)) __kernel __force *)(__p);	\
+})
+
+#define per_cpu(var, cpu)	(*((void)(cpu), VERIFY_PERCPU_PTR(&(var))))
+#define __get_cpu_var(var)	(*VERIFY_PERCPU_PTR(&(var)))
+#define __raw_get_cpu_var(var)	(*VERIFY_PERCPU_PTR(&(var)))
+#define this_cpu_ptr(ptr)	per_cpu_ptr(ptr, 0)
+#define __this_cpu_ptr(ptr)	this_cpu_ptr(ptr)
 
 #endif	/* SMP */
 
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index c9f3cc5949a8..3e5a51af757c 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -386,7 +386,15 @@ struct drm_connector_funcs {
 	void (*dpms)(struct drm_connector *connector, int mode);
 	void (*save)(struct drm_connector *connector);
 	void (*restore)(struct drm_connector *connector);
-	enum drm_connector_status (*detect)(struct drm_connector *connector);
+
+	/* Check to see if anything is attached to the connector.
+	 * @force is set to false whilst polling, true when checking the
+	 * connector due to user request. @force can be used by the driver
+	 * to avoid expensive, destructive operations during automated
+	 * probing.
+	 */
+	enum drm_connector_status (*detect)(struct drm_connector *connector,
+					    bool force);
 	int (*fill_modes)(struct drm_connector *connector, uint32_t max_width, uint32_t max_height);
 	int (*set_property)(struct drm_connector *connector, struct drm_property *property,
 			     uint64_t val);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index ccf94dc5acdf..c227757feb06 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -304,8 +304,8 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context);
 				OSC_PCI_EXPRESS_PME_CONTROL |		\
 				OSC_PCI_EXPRESS_AER_CONTROL |		\
 				OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL)
-
-extern acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 flags);
+extern acpi_status acpi_pci_osc_control_set(acpi_handle handle,
+					     u32 *mask, u32 req);
 extern void acpi_early_init(void);
 
 #else	/* !CONFIG_ACPI */
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index ed3e92e41c6e..0c991023ee47 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -578,7 +578,12 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
 void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it);
 int cgroup_scan_tasks(struct cgroup_scanner *scan);
 int cgroup_attach_task(struct cgroup *, struct task_struct *);
-int cgroup_attach_task_current_cg(struct task_struct *);
+int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
+
+static inline int cgroup_attach_task_current_cg(struct task_struct *tsk)
+{
+	return cgroup_attach_task_all(current, tsk);
+}
 
 /*
  * CSS ID is ID for cgroup_subsys_state structs under subsys. This only works
@@ -636,6 +641,11 @@ static inline int cgroupstats_build(struct cgroupstats *stats,
 }
 
 /* No cgroups - nothing to do */
+static inline int cgroup_attach_task_all(struct task_struct *from,
+					 struct task_struct *t)
+{
+	return 0;
+}
 static inline int cgroup_attach_task_current_cg(struct task_struct *t)
 {
 	return 0;
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 9ddc8780e8db..5778b559d59c 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -360,5 +360,8 @@ extern ssize_t compat_rw_copy_check_uvector(int type,
 		const struct compat_iovec __user *uvector, unsigned long nr_segs,
 		unsigned long fast_segs, struct iovec *fast_pointer,
 		struct iovec **ret_pointer);
+
+extern void __user *compat_alloc_user_space(unsigned long len);
+
 #endif /* CONFIG_COMPAT */
 #endif /* _LINUX_COMPAT_H */
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 2c958f4fce1e..926b50322a46 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -136,6 +136,7 @@ extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t);
 
 extern int elevator_init(struct request_queue *, char *);
 extern void elevator_exit(struct elevator_queue *);
+extern int elevator_change(struct request_queue *, const char *);
 extern int elv_rq_merge_ok(struct request *, struct bio *);
 
 /*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 76041b614758..63d069bd80b7 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1093,6 +1093,10 @@ struct file_lock {
 
 #include <linux/fcntl.h>
 
+/* temporary stubs for BKL removal */
+#define lock_flocks() lock_kernel()
+#define unlock_flocks() unlock_kernel()
+
 extern void send_sigio(struct fown_struct *fown, int fd, int band);
 
 #ifdef CONFIG_FILE_LOCKING
diff --git a/include/linux/gpio.h b/include/linux/gpio.h
index 03f616b78cfa..e41f7dd1ae67 100644
--- a/include/linux/gpio.h
+++ b/include/linux/gpio.h
@@ -13,6 +13,7 @@
 #include <linux/errno.h>
 
 struct device;
+struct gpio_chip;
 
 /*
  * Some platforms don't support the GPIO programming interface.
diff --git a/include/linux/i2c/sx150x.h b/include/linux/i2c/sx150x.h
index ee3049cb9ba5..52baa79d69a7 100644
--- a/include/linux/i2c/sx150x.h
+++ b/include/linux/i2c/sx150x.h
@@ -63,6 +63,9 @@
  *            IRQ lines will appear.  Similarly to gpio_base, the expander
  *            will create a block of irqs beginning at this number.
  *            This value is ignored if irq_summary is < 0.
+ * @reset_during_probe: If set to true, the driver will trigger a full
+ *                      reset of the chip at the beginning of the probe
+ *                      in order to place it in a known state.
  */
 struct sx150x_platform_data {
 	unsigned gpio_base;
@@ -73,6 +76,7 @@ struct sx150x_platform_data {
 	u16      io_polarity;
 	int      irq_summary;
 	unsigned irq_base;
+	bool     reset_during_probe;
 };
 
 #endif /* __LINUX_I2C_SX150X_H */
diff --git a/include/linux/intel-gtt.h b/include/linux/intel-gtt.h
new file mode 100644
index 000000000000..1d19ab2afa39
--- /dev/null
+++ b/include/linux/intel-gtt.h
@@ -0,0 +1,20 @@
+/*
+ * Common Intel AGPGART and GTT definitions.
+ */
+#ifndef _INTEL_GTT_H
+#define _INTEL_GTT_H
+
+#include <linux/agp_backend.h>
+
+/* This is for Intel only GTT controls.
+ *
+ * Sandybridge: AGP_USER_CACHED_MEMORY default to LLC only
+ */
+
+#define AGP_USER_CACHED_MEMORY_LLC_MLC (AGP_USER_TYPES + 2)
+#define AGP_USER_UNCACHED_MEMORY (AGP_USER_TYPES + 4)
+
+/* flag for GFDT type */
+#define AGP_USER_CACHED_MEMORY_GFDT (1 << 3)
+
+#endif
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index 0a6b3d5c490c..7fb592793738 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -79,7 +79,7 @@ io_mapping_free(struct io_mapping *mapping)
 }
 
 /* Atomic map/unmap */
-static inline void *
+static inline void __iomem *
 io_mapping_map_atomic_wc(struct io_mapping *mapping,
 			 unsigned long offset,
 			 int slot)
@@ -94,12 +94,12 @@ io_mapping_map_atomic_wc(struct io_mapping *mapping,
 }
 
 static inline void
-io_mapping_unmap_atomic(void *vaddr, int slot)
+io_mapping_unmap_atomic(void __iomem *vaddr, int slot)
 {
 	iounmap_atomic(vaddr, slot);
 }
 
-static inline void *
+static inline void __iomem *
 io_mapping_map_wc(struct io_mapping *mapping, unsigned long offset)
 {
 	resource_size_t phys_addr;
@@ -111,7 +111,7 @@ io_mapping_map_wc(struct io_mapping *mapping, unsigned long offset)
 }
 
 static inline void
-io_mapping_unmap(void *vaddr)
+io_mapping_unmap(void __iomem *vaddr)
 {
 	iounmap(vaddr);
 }
@@ -125,38 +125,38 @@ struct io_mapping;
 static inline struct io_mapping *
 io_mapping_create_wc(resource_size_t base, unsigned long size)
 {
-	return (struct io_mapping *) ioremap_wc(base, size);
+	return (struct io_mapping __force *) ioremap_wc(base, size);
 }
 
 static inline void
 io_mapping_free(struct io_mapping *mapping)
 {
-	iounmap(mapping);
+	iounmap((void __force __iomem *) mapping);
 }
 
 /* Atomic map/unmap */
-static inline void *
+static inline void __iomem *
 io_mapping_map_atomic_wc(struct io_mapping *mapping,
 			 unsigned long offset,
 			 int slot)
 {
-	return ((char *) mapping) + offset;
+	return ((char __force __iomem *) mapping) + offset;
 }
 
 static inline void
-io_mapping_unmap_atomic(void *vaddr, int slot)
+io_mapping_unmap_atomic(void __iomem *vaddr, int slot)
 {
 }
 
 /* Non-atomic map/unmap */
-static inline void *
+static inline void __iomem *
 io_mapping_map_wc(struct io_mapping *mapping, unsigned long offset)
 {
-	return ((char *) mapping) + offset;
+	return ((char __force __iomem *) mapping) + offset;
 }
 
 static inline void
-io_mapping_unmap(void *vaddr)
+io_mapping_unmap(void __iomem *vaddr)
 {
 }
 
diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h
index 4aa95f203f3e..62dbee554f60 100644
--- a/include/linux/kfifo.h
+++ b/include/linux/kfifo.h
@@ -214,7 +214,7 @@ __kfifo_must_check_helper(unsigned int val)
  */
 #define kfifo_reset(fifo) \
 (void)({ \
-	typeof(fifo + 1) __tmp = (fifo); \
+	typeof((fifo) + 1) __tmp = (fifo); \
 	__tmp->kfifo.in = __tmp->kfifo.out = 0; \
 })
 
@@ -228,7 +228,7 @@ __kfifo_must_check_helper(unsigned int val)
  */
 #define kfifo_reset_out(fifo)	\
 (void)({ \
-	typeof(fifo + 1) __tmp = (fifo); \
+	typeof((fifo) + 1) __tmp = (fifo); \
 	__tmp->kfifo.out = __tmp->kfifo.in; \
 })
 
@@ -238,7 +238,7 @@ __kfifo_must_check_helper(unsigned int val)
  */
 #define kfifo_len(fifo) \
 ({ \
-	typeof(fifo + 1) __tmpl = (fifo); \
+	typeof((fifo) + 1) __tmpl = (fifo); \
 	__tmpl->kfifo.in - __tmpl->kfifo.out; \
 })
 
@@ -248,7 +248,7 @@ __kfifo_must_check_helper(unsigned int val)
  */
 #define	kfifo_is_empty(fifo) \
 ({ \
-	typeof(fifo + 1) __tmpq = (fifo); \
+	typeof((fifo) + 1) __tmpq = (fifo); \
 	__tmpq->kfifo.in == __tmpq->kfifo.out; \
 })
 
@@ -258,7 +258,7 @@ __kfifo_must_check_helper(unsigned int val)
  */
 #define	kfifo_is_full(fifo) \
 ({ \
-	typeof(fifo + 1) __tmpq = (fifo); \
+	typeof((fifo) + 1) __tmpq = (fifo); \
 	kfifo_len(__tmpq) > __tmpq->kfifo.mask; \
 })
 
@@ -269,7 +269,7 @@ __kfifo_must_check_helper(unsigned int val)
 #define	kfifo_avail(fifo) \
 __kfifo_must_check_helper( \
 ({ \
-	typeof(fifo + 1) __tmpq = (fifo); \
+	typeof((fifo) + 1) __tmpq = (fifo); \
 	const size_t __recsize = sizeof(*__tmpq->rectype); \
 	unsigned int __avail = kfifo_size(__tmpq) - kfifo_len(__tmpq); \
 	(__recsize) ? ((__avail <= __recsize) ? 0 : \
@@ -284,7 +284,7 @@ __kfifo_must_check_helper( \
  */
 #define	kfifo_skip(fifo) \
 (void)({ \
-	typeof(fifo + 1) __tmp = (fifo); \
+	typeof((fifo) + 1) __tmp = (fifo); \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
 	if (__recsize) \
@@ -302,7 +302,7 @@ __kfifo_must_check_helper( \
 #define kfifo_peek_len(fifo) \
 __kfifo_must_check_helper( \
 ({ \
-	typeof(fifo + 1) __tmp = (fifo); \
+	typeof((fifo) + 1) __tmp = (fifo); \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
 	(!__recsize) ? kfifo_len(__tmp) * sizeof(*__tmp->type) : \
@@ -325,7 +325,7 @@ __kfifo_must_check_helper( \
 #define kfifo_alloc(fifo, size, gfp_mask) \
 __kfifo_must_check_helper( \
 ({ \
-	typeof(fifo + 1) __tmp = (fifo); \
+	typeof((fifo) + 1) __tmp = (fifo); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
 	__is_kfifo_ptr(__tmp) ? \
 	__kfifo_alloc(__kfifo, size, sizeof(*__tmp->type), gfp_mask) : \
@@ -339,7 +339,7 @@ __kfifo_must_check_helper( \
  */
 #define kfifo_free(fifo) \
 ({ \
-	typeof(fifo + 1) __tmp = (fifo); \
+	typeof((fifo) + 1) __tmp = (fifo); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
 	if (__is_kfifo_ptr(__tmp)) \
 		__kfifo_free(__kfifo); \
@@ -358,7 +358,7 @@ __kfifo_must_check_helper( \
  */
 #define kfifo_init(fifo, buffer, size) \
 ({ \
-	typeof(fifo + 1) __tmp = (fifo); \
+	typeof((fifo) + 1) __tmp = (fifo); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
 	__is_kfifo_ptr(__tmp) ? \
 	__kfifo_init(__kfifo, buffer, size, sizeof(*__tmp->type)) : \
@@ -379,8 +379,8 @@ __kfifo_must_check_helper( \
  */
 #define	kfifo_put(fifo, val) \
 ({ \
-	typeof(fifo + 1) __tmp = (fifo); \
-	typeof(val + 1) __val = (val); \
+	typeof((fifo) + 1) __tmp = (fifo); \
+	typeof((val) + 1) __val = (val); \
 	unsigned int __ret; \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
@@ -421,8 +421,8 @@ __kfifo_must_check_helper( \
 #define	kfifo_get(fifo, val) \
 __kfifo_must_check_helper( \
 ({ \
-	typeof(fifo + 1) __tmp = (fifo); \
-	typeof(val + 1) __val = (val); \
+	typeof((fifo) + 1) __tmp = (fifo); \
+	typeof((val) + 1) __val = (val); \
 	unsigned int __ret; \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
@@ -462,8 +462,8 @@ __kfifo_must_check_helper( \
 #define	kfifo_peek(fifo, val) \
 __kfifo_must_check_helper( \
 ({ \
-	typeof(fifo + 1) __tmp = (fifo); \
-	typeof(val + 1) __val = (val); \
+	typeof((fifo) + 1) __tmp = (fifo); \
+	typeof((val) + 1) __val = (val); \
 	unsigned int __ret; \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
@@ -501,8 +501,8 @@ __kfifo_must_check_helper( \
  */
 #define	kfifo_in(fifo, buf, n) \
 ({ \
-	typeof(fifo + 1) __tmp = (fifo); \
-	typeof(buf + 1) __buf = (buf); \
+	typeof((fifo) + 1) __tmp = (fifo); \
+	typeof((buf) + 1) __buf = (buf); \
 	unsigned long __n = (n); \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
@@ -554,8 +554,8 @@ __kfifo_must_check_helper( \
 #define	kfifo_out(fifo, buf, n) \
 __kfifo_must_check_helper( \
 ({ \
-	typeof(fifo + 1) __tmp = (fifo); \
-	typeof(buf + 1) __buf = (buf); \
+	typeof((fifo) + 1) __tmp = (fifo); \
+	typeof((buf) + 1) __buf = (buf); \
 	unsigned long __n = (n); \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
@@ -611,7 +611,7 @@ __kfifo_must_check_helper( \
 #define	kfifo_from_user(fifo, from, len, copied) \
 __kfifo_must_check_helper( \
 ({ \
-	typeof(fifo + 1) __tmp = (fifo); \
+	typeof((fifo) + 1) __tmp = (fifo); \
 	const void __user *__from = (from); \
 	unsigned int __len = (len); \
 	unsigned int *__copied = (copied); \
@@ -639,7 +639,7 @@ __kfifo_must_check_helper( \
 #define	kfifo_to_user(fifo, to, len, copied) \
 __kfifo_must_check_helper( \
 ({ \
-	typeof(fifo + 1) __tmp = (fifo); \
+	typeof((fifo) + 1) __tmp = (fifo); \
 	void __user *__to = (to); \
 	unsigned int __len = (len); \
 	unsigned int *__copied = (copied); \
@@ -666,7 +666,7 @@ __kfifo_must_check_helper( \
  */
 #define	kfifo_dma_in_prepare(fifo, sgl, nents, len) \
 ({ \
-	typeof(fifo + 1) __tmp = (fifo); \
+	typeof((fifo) + 1) __tmp = (fifo); \
 	struct scatterlist *__sgl = (sgl); \
 	int __nents = (nents); \
 	unsigned int __len = (len); \
@@ -690,7 +690,7 @@ __kfifo_must_check_helper( \
  */
 #define kfifo_dma_in_finish(fifo, len) \
 (void)({ \
-	typeof(fifo + 1) __tmp = (fifo); \
+	typeof((fifo) + 1) __tmp = (fifo); \
 	unsigned int __len = (len); \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
@@ -717,7 +717,7 @@ __kfifo_must_check_helper( \
  */
 #define	kfifo_dma_out_prepare(fifo, sgl, nents, len) \
 ({ \
-	typeof(fifo + 1) __tmp = (fifo); \
+	typeof((fifo) + 1) __tmp = (fifo);  \
 	struct scatterlist *__sgl = (sgl); \
 	int __nents = (nents); \
 	unsigned int __len = (len); \
@@ -741,7 +741,7 @@ __kfifo_must_check_helper( \
  */
 #define kfifo_dma_out_finish(fifo, len) \
 (void)({ \
-	typeof(fifo + 1) __tmp = (fifo); \
+	typeof((fifo) + 1) __tmp = (fifo); \
 	unsigned int __len = (len); \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
@@ -766,8 +766,8 @@ __kfifo_must_check_helper( \
 #define	kfifo_out_peek(fifo, buf, n) \
 __kfifo_must_check_helper( \
 ({ \
-	typeof(fifo + 1) __tmp = (fifo); \
-	typeof(buf + 1) __buf = (buf); \
+	typeof((fifo) + 1) __tmp = (fifo); \
+	typeof((buf) + 1) __buf = (buf); \
 	unsigned long __n = (n); \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 74d691ee9121..3319a6967626 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -16,6 +16,9 @@
 struct stable_node;
 struct mem_cgroup;
 
+struct page *ksm_does_need_to_copy(struct page *page,
+			struct vm_area_struct *vma, unsigned long address);
+
 #ifdef CONFIG_KSM
 int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 		unsigned long end, int advice, unsigned long *vm_flags);
@@ -70,19 +73,14 @@ static inline void set_page_stable_node(struct page *page,
  * We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE,
  * but what if the vma was unmerged while the page was swapped out?
  */
-struct page *ksm_does_need_to_copy(struct page *page,
-			struct vm_area_struct *vma, unsigned long address);
-static inline struct page *ksm_might_need_to_copy(struct page *page,
+static inline int ksm_might_need_to_copy(struct page *page,
 			struct vm_area_struct *vma, unsigned long address)
 {
 	struct anon_vma *anon_vma = page_anon_vma(page);
 
-	if (!anon_vma ||
-	    (anon_vma->root == vma->anon_vma->root &&
-	     page->index == linear_page_index(vma, address)))
-		return page;
-
-	return ksm_does_need_to_copy(page, vma, address);
+	return anon_vma &&
+		(anon_vma->root != vma->anon_vma->root ||
+		 page->index != linear_page_index(vma, address));
 }
 
 int page_referenced_ksm(struct page *page,
@@ -115,10 +113,10 @@ static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 	return 0;
 }
 
-static inline struct page *ksm_might_need_to_copy(struct page *page,
+static inline int ksm_might_need_to_copy(struct page *page,
 			struct vm_area_struct *vma, unsigned long address)
 {
-	return page;
+	return 0;
 }
 
 static inline int page_referenced_ksm(struct page *page,
diff --git a/include/linux/lglock.h b/include/linux/lglock.h
index b288cb713b90..f549056fb20b 100644
--- a/include/linux/lglock.h
+++ b/include/linux/lglock.h
@@ -150,7 +150,7 @@
 	int i;								\
 	preempt_disable();						\
 	rwlock_acquire(&name##_lock_dep_map, 0, 0, _RET_IP_);		\
-	for_each_online_cpu(i) {					\
+	for_each_possible_cpu(i) {					\
 		arch_spinlock_t *lock;					\
 		lock = &per_cpu(name##_lock, i);			\
 		arch_spin_lock(lock);					\
@@ -161,7 +161,7 @@
  void name##_global_unlock(void) {					\
 	int i;								\
 	rwlock_release(&name##_lock_dep_map, 1, _RET_IP_);		\
-	for_each_online_cpu(i) {					\
+	for_each_possible_cpu(i) {					\
 		arch_spinlock_t *lock;					\
 		lock = &per_cpu(name##_lock, i);			\
 		arch_spin_unlock(lock);					\
diff --git a/include/linux/libata.h b/include/linux/libata.h
index f010f18a0f86..45fb2967b66d 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -335,6 +335,7 @@ enum {
 	ATA_EHI_HOTPLUGGED	= (1 << 0),  /* could have been hotplugged */
 	ATA_EHI_NO_AUTOPSY	= (1 << 2),  /* no autopsy */
 	ATA_EHI_QUIET		= (1 << 3),  /* be quiet */
+	ATA_EHI_NO_RECOVERY	= (1 << 4),  /* no recovery */
 
 	ATA_EHI_DID_SOFTRESET	= (1 << 16), /* already soft-reset this port */
 	ATA_EHI_DID_HARDRESET	= (1 << 17), /* already soft-reset this port */
@@ -723,6 +724,7 @@ struct ata_port {
 	struct ata_ioports	ioaddr;	/* ATA cmd/ctl/dma register blocks */
 	u8			ctl;	/* cache of ATA control register */
 	u8			last_ctl;	/* Cache last written value */
+	struct ata_link*	sff_pio_task_link; /* link currently used */
 	struct delayed_work	sff_pio_task;
 #ifdef CONFIG_ATA_BMDMA
 	struct ata_bmdma_prd	*bmdma_prd;	/* BMDMA SG list */
@@ -1594,7 +1596,7 @@ extern void ata_sff_irq_on(struct ata_port *ap);
 extern void ata_sff_irq_clear(struct ata_port *ap);
 extern int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc,
 			    u8 status, int in_wq);
-extern void ata_sff_queue_pio_task(struct ata_port *ap, unsigned long delay);
+extern void ata_sff_queue_pio_task(struct ata_link *link, unsigned long delay);
 extern unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc);
 extern bool ata_sff_qc_fill_rtf(struct ata_queued_cmd *qc);
 extern unsigned int ata_sff_port_intr(struct ata_port *ap,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e6b1210772ce..74949fbef8c6 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -864,6 +864,12 @@ int set_page_dirty(struct page *page);
 int set_page_dirty_lock(struct page *page);
 int clear_page_dirty_for_io(struct page *page);
 
+/* Is the vma a continuation of the stack vma above it? */
+static inline int vma_stack_continue(struct vm_area_struct *vma, unsigned long addr)
+{
+	return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN);
+}
+
 extern unsigned long move_page_tables(struct vm_area_struct *vma,
 		unsigned long old_addr, struct vm_area_struct *new_vma,
 		unsigned long new_addr, unsigned long len);
diff --git a/include/linux/mmc/sdio.h b/include/linux/mmc/sdio.h
index 329a8faa6e37..245cdacee544 100644
--- a/include/linux/mmc/sdio.h
+++ b/include/linux/mmc/sdio.h
@@ -38,6 +38,8 @@
  *      [8:0] Byte/block count
  */
 
+#define R4_MEMORY_PRESENT (1 << 27)
+
 /*
   SDIO status in R5
   Type
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 6e6e62648a4d..3984c4eb41fd 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -284,6 +284,13 @@ struct zone {
 	unsigned long watermark[NR_WMARK];
 
 	/*
+	 * When free pages are below this point, additional steps are taken
+	 * when reading the number of free pages to avoid per-cpu counter
+	 * drift allowing watermarks to be breached
+	 */
+	unsigned long percpu_drift_mark;
+
+	/*
 	 * We don't know if the memory that we're going to allocate will be freeable
 	 * or/and it will be released eventually, so to avoid totally wasting several
 	 * GB of ram we must reserve some of the lower zone memory (otherwise we risk
@@ -441,6 +448,12 @@ static inline int zone_is_oom_locked(const struct zone *zone)
 	return test_bit(ZONE_OOM_LOCKED, &zone->flags);
 }
 
+#ifdef CONFIG_SMP
+unsigned long zone_nr_free_pages(struct zone *zone);
+#else
+#define zone_nr_free_pages(zone) zone_page_state(zone, NR_FREE_PAGES)
+#endif /* CONFIG_SMP */
+
 /*
  * The "priority" of VM scanning is how much of the queues we will scan in one
  * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 878cab4f5fcc..f363bc8fdc74 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -78,6 +78,14 @@ struct mutex_waiter {
 # include <linux/mutex-debug.h>
 #else
 # define __DEBUG_MUTEX_INITIALIZER(lockname)
+/**
+ * mutex_init - initialize the mutex
+ * @mutex: the mutex to be initialized
+ *
+ * Initialize the mutex to unlocked state.
+ *
+ * It is not allowed to initialize an already locked mutex.
+ */
 # define mutex_init(mutex) \
 do {							\
 	static struct lock_class_key __key;		\
diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index 791d5109f34c..50d8009be86c 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -63,20 +63,20 @@ static inline bool netpoll_rx(struct sk_buff *skb)
 	unsigned long flags;
 	bool ret = false;
 
-	rcu_read_lock_bh();
+	local_irq_save(flags);
 	npinfo = rcu_dereference_bh(skb->dev->npinfo);
 
 	if (!npinfo || (list_empty(&npinfo->rx_np) && !npinfo->rx_flags))
 		goto out;
 
-	spin_lock_irqsave(&npinfo->rx_lock, flags);
+	spin_lock(&npinfo->rx_lock);
 	/* check rx_flags again with the lock held */
 	if (npinfo->rx_flags && __netpoll_rx(skb))
 		ret = true;
-	spin_unlock_irqrestore(&npinfo->rx_lock, flags);
+	spin_unlock(&npinfo->rx_lock);
 
 out:
-	rcu_read_unlock_bh();
+	local_irq_restore(flags);
 	return ret;
 }
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index b1d17956a153..c8d95e369ff4 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1214,6 +1214,9 @@ static inline struct pci_dev *pci_get_bus_and_slot(unsigned int bus,
 						unsigned int devfn)
 { return NULL; }
 
+static inline int pci_domain_nr(struct pci_bus *bus)
+{ return 0; }
+
 #define dev_is_pci(d) (false)
 #define dev_is_pf(d) (false)
 #define dev_num_vf(d) (0)
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index f6a3b2d36cad..10d33309e9a6 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2300,6 +2300,8 @@
 #define PCI_DEVICE_ID_P2010		0x0079
 #define PCI_DEVICE_ID_P1020E		0x0100
 #define PCI_DEVICE_ID_P1020		0x0101
+#define PCI_DEVICE_ID_P1021E		0x0102
+#define PCI_DEVICE_ID_P1021		0x0103
 #define PCI_DEVICE_ID_P1011E		0x0108
 #define PCI_DEVICE_ID_P1011		0x0109
 #define PCI_DEVICE_ID_P1022E		0x0110
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index b8b9084527b1..49466b13c5c6 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -149,7 +149,7 @@ extern void __init percpu_init_late(void);
 
 #else /* CONFIG_SMP */
 
-#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); })
+#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); VERIFY_PERCPU_PTR((ptr)); })
 
 /* can't distinguish from other static vars, always false */
 static inline bool is_kernel_percpu_address(unsigned long addr)
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index d50ba858cfe0..d1a9193960f1 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -274,8 +274,14 @@ static inline int dquot_alloc_space(struct inode *inode, qsize_t nr)
 	int ret;
 
 	ret = dquot_alloc_space_nodirty(inode, nr);
-	if (!ret)
-		mark_inode_dirty_sync(inode);
+	if (!ret) {
+		/*
+		 * Mark inode fully dirty. Since we are allocating blocks, inode
+		 * would become fully dirty soon anyway and it reportedly
+		 * reduces inode_lock contention.
+		 */
+		mark_inode_dirty(inode);
+	}
 	return ret;
 }
 
diff --git a/include/linux/semaphore.h b/include/linux/semaphore.h
index 7415839ac890..5310d27abd2a 100644
--- a/include/linux/semaphore.h
+++ b/include/linux/semaphore.h
@@ -26,6 +26,9 @@ struct semaphore {
 	.wait_list	= LIST_HEAD_INIT((name).wait_list),		\
 }
 
+#define DEFINE_SEMAPHORE(name)	\
+	struct semaphore name = __SEMAPHORE_INITIALIZER(name, 1)
+
 #define DECLARE_MUTEX(name)	\
 	struct semaphore name = __SEMAPHORE_INITIALIZER(name, 1)
 
diff --git a/include/linux/serial.h b/include/linux/serial.h
index 1ebc694a6d52..ef914061511e 100644
--- a/include/linux/serial.h
+++ b/include/linux/serial.h
@@ -77,8 +77,7 @@ struct serial_struct {
 #define PORT_16654	11
 #define PORT_16850	12
 #define PORT_RSA	13	/* RSA-DV II/S card */
-#define PORT_U6_16550A	14
-#define PORT_MAX	14
+#define PORT_MAX	13
 
 #define SERIAL_IO_PORT	0
 #define SERIAL_IO_HUB6	1
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 64458a9a8938..563e23400913 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -44,7 +44,8 @@
 #define PORT_RM9000	16	/* PMC-Sierra RM9xxx internal UART */
 #define PORT_OCTEON	17	/* Cavium OCTEON internal UART */
 #define PORT_AR7	18	/* Texas Instruments AR7 internal UART */
-#define PORT_MAX_8250	18	/* max port ID */
+#define PORT_U6_16550A	19	/* ST-Ericsson U6xxx internal UART */
+#define PORT_MAX_8250	19	/* max port ID */
 
 /*
  * ARM specific type numbers.  These are not currently guaranteed
diff --git a/include/linux/spi/dw_spi.h b/include/linux/spi/dw_spi.h
index cc813f95a2f2..c91302f3a257 100644
--- a/include/linux/spi/dw_spi.h
+++ b/include/linux/spi/dw_spi.h
@@ -14,7 +14,9 @@
 #define SPI_MODE_OFFSET			6
 #define SPI_SCPH_OFFSET			6
 #define SPI_SCOL_OFFSET			7
+
 #define SPI_TMOD_OFFSET			8
+#define SPI_TMOD_MASK			(0x3 << SPI_TMOD_OFFSET)
 #define	SPI_TMOD_TR			0x0		/* xmit & recv */
 #define SPI_TMOD_TO			0x1		/* xmit only */
 #define SPI_TMOD_RO			0x2		/* recv only */
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 569dc722a600..85f38a63f098 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -30,7 +30,7 @@ struct rpc_inode;
  * The high-level client handle
  */
 struct rpc_clnt {
-	struct kref		cl_kref;	/* Number of references */
+	atomic_t		cl_count;	/* Number of references */
 	struct list_head	cl_clients;	/* Global list of clients */
 	struct list_head	cl_tasks;	/* List of tasks */
 	spinlock_t		cl_lock;	/* spinlock */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 2fee51a11b73..7cdd63366f88 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -19,6 +19,7 @@ struct bio;
 #define SWAP_FLAG_PREFER	0x8000	/* set if swap priority specified */
 #define SWAP_FLAG_PRIO_MASK	0x7fff
 #define SWAP_FLAG_PRIO_SHIFT	0
+#define SWAP_FLAG_DISCARD	0x10000 /* discard swap cluster after use */
 
 static inline int current_is_kswapd(void)
 {
@@ -142,7 +143,7 @@ struct swap_extent {
 enum {
 	SWP_USED	= (1 << 0),	/* is slot in swap_info[] used? */
 	SWP_WRITEOK	= (1 << 1),	/* ok to write to this swap?	*/
-	SWP_DISCARDABLE = (1 << 2),	/* blkdev supports discard */
+	SWP_DISCARDABLE = (1 << 2),	/* swapon+blkdev support discard */
 	SWP_DISCARDING	= (1 << 3),	/* now discarding a free cluster */
 	SWP_SOLIDSTATE	= (1 << 4),	/* blkdev seeks are cheap */
 	SWP_CONTINUED	= (1 << 5),	/* swap_map has count continuation */
@@ -315,6 +316,7 @@ extern long nr_swap_pages;
 extern long total_swap_pages;
 extern void si_swapinfo(struct sysinfo *);
 extern swp_entry_t get_swap_page(void);
+extern swp_entry_t get_swap_page_of_type(int);
 extern int valid_swaphandles(swp_entry_t, unsigned long *);
 extern int add_swap_count_continuation(swp_entry_t, gfp_t);
 extern void swap_shmem_alloc(swp_entry_t);
@@ -331,13 +333,6 @@ extern int reuse_swap_page(struct page *);
 extern int try_to_free_swap(struct page *);
 struct backing_dev_info;
 
-#ifdef CONFIG_HIBERNATION
-void hibernation_freeze_swap(void);
-void hibernation_thaw_swap(void);
-swp_entry_t get_swap_for_hibernation(int type);
-void swap_free_for_hibernation(swp_entry_t val);
-#endif
-
 /* linux/mm/thrash.c */
 extern struct mm_struct *swap_token_mm;
 extern void grab_swap_token(struct mm_struct *);
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 7f43ccdc1d38..eaaea37b3b75 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -170,6 +170,28 @@ static inline unsigned long zone_page_state(struct zone *zone,
 	return x;
 }
 
+/*
+ * More accurate version that also considers the currently pending
+ * deltas. For that we need to loop over all cpus to find the current
+ * deltas. There is no synchronization so the result cannot be
+ * exactly accurate either.
+ */
+static inline unsigned long zone_page_state_snapshot(struct zone *zone,
+					enum zone_stat_item item)
+{
+	long x = atomic_long_read(&zone->vm_stat[item]);
+
+#ifdef CONFIG_SMP
+	int cpu;
+	for_each_online_cpu(cpu)
+		x += per_cpu_ptr(zone->pageset, cpu)->vm_stat_diff[item];
+
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
+}
+
 extern unsigned long global_reclaimable_pages(void);
 extern unsigned long zone_reclaimable_pages(struct zone *zone);
 
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 4f9d277bcd9a..25e02c941bac 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -25,18 +25,20 @@ typedef void (*work_func_t)(struct work_struct *work);
 
 enum {
 	WORK_STRUCT_PENDING_BIT	= 0,	/* work item is pending execution */
-	WORK_STRUCT_CWQ_BIT	= 1,	/* data points to cwq */
-	WORK_STRUCT_LINKED_BIT	= 2,	/* next work is linked to this one */
+	WORK_STRUCT_DELAYED_BIT	= 1,	/* work item is delayed */
+	WORK_STRUCT_CWQ_BIT	= 2,	/* data points to cwq */
+	WORK_STRUCT_LINKED_BIT	= 3,	/* next work is linked to this one */
 #ifdef CONFIG_DEBUG_OBJECTS_WORK
-	WORK_STRUCT_STATIC_BIT	= 3,	/* static initializer (debugobjects) */
-	WORK_STRUCT_COLOR_SHIFT	= 4,	/* color for workqueue flushing */
+	WORK_STRUCT_STATIC_BIT	= 4,	/* static initializer (debugobjects) */
+	WORK_STRUCT_COLOR_SHIFT	= 5,	/* color for workqueue flushing */
 #else
-	WORK_STRUCT_COLOR_SHIFT	= 3,	/* color for workqueue flushing */
+	WORK_STRUCT_COLOR_SHIFT	= 4,	/* color for workqueue flushing */
 #endif
 
 	WORK_STRUCT_COLOR_BITS	= 4,
 
 	WORK_STRUCT_PENDING	= 1 << WORK_STRUCT_PENDING_BIT,
+	WORK_STRUCT_DELAYED	= 1 << WORK_STRUCT_DELAYED_BIT,
 	WORK_STRUCT_CWQ		= 1 << WORK_STRUCT_CWQ_BIT,
 	WORK_STRUCT_LINKED	= 1 << WORK_STRUCT_LINKED_BIT,
 #ifdef CONFIG_DEBUG_OBJECTS_WORK
@@ -59,8 +61,8 @@ enum {
 
 	/*
 	 * Reserve 7 bits off of cwq pointer w/ debugobjects turned
-	 * off.  This makes cwqs aligned to 128 bytes which isn't too
-	 * excessive while allowing 15 workqueue flush colors.
+	 * off.  This makes cwqs aligned to 256 bytes and allows 15
+	 * workqueue flush colors.
 	 */
 	WORK_STRUCT_FLAG_BITS	= WORK_STRUCT_COLOR_SHIFT +
 				  WORK_STRUCT_COLOR_BITS,
@@ -233,6 +235,10 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; }
 #define work_clear_pending(work) \
 	clear_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))
 
+/*
+ * Workqueue flags and constants.  For details, please refer to
+ * Documentation/workqueue.txt.
+ */
 enum {
 	WQ_NON_REENTRANT	= 1 << 0, /* guarantee non-reentrance */
 	WQ_UNBOUND		= 1 << 1, /* not bound to any cpu */
@@ -241,6 +247,8 @@ enum {
 	WQ_HIGHPRI		= 1 << 4, /* high priority */
 	WQ_CPU_INTENSIVE	= 1 << 5, /* cpu instensive workqueue */
 
+	WQ_DYING		= 1 << 6, /* internal: workqueue is dying */
+
 	WQ_MAX_ACTIVE		= 512,	  /* I like 512, better ideas? */
 	WQ_MAX_UNBOUND_PER_CPU	= 4,	  /* 4 * #cpus for unbound wq */
 	WQ_DFL_ACTIVE		= WQ_MAX_ACTIVE / 2,
diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h
index 726cc3536409..ef6c24a529e1 100644
--- a/include/net/cls_cgroup.h
+++ b/include/net/cls_cgroup.h
@@ -27,11 +27,17 @@ struct cgroup_cls_state
 #ifdef CONFIG_NET_CLS_CGROUP
 static inline u32 task_cls_classid(struct task_struct *p)
 {
+	int classid;
+
 	if (in_interrupt())
 		return 0;
 
-	return container_of(task_subsys_state(p, net_cls_subsys_id),
-			    struct cgroup_cls_state, css)->classid;
+	rcu_read_lock();
+	classid = container_of(task_subsys_state(p, net_cls_subsys_id),
+			       struct cgroup_cls_state, css)->classid;
+	rcu_read_unlock();
+
+	return classid;
 }
 #else
 extern int net_cls_subsys_id;
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index a4747a0f7303..f976885f686f 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -955,6 +955,9 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum)
 	return csum_partial(diff, sizeof(diff), oldsum);
 }
 
+extern void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp,
+				   int outin);
+
 #endif /* __KERNEL__ */
 
 #endif	/* _NET_IP_VS_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index ac53bfbdfe16..adab9dc58183 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -752,6 +752,7 @@ struct proto {
 	/* Keeping track of sk's, looking them up, and port selection methods. */
 	void			(*hash)(struct sock *sk);
 	void			(*unhash)(struct sock *sk);
+	void			(*rehash)(struct sock *sk);
 	int			(*get_port)(struct sock *sk, unsigned short snum);
 
 	/* Keeping track of sockets in use */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index eaa9582779d0..3e4b33e36602 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -475,8 +475,22 @@ extern unsigned int tcp_current_mss(struct sock *sk);
 /* Bound MSS / TSO packet size with the half of the window */
 static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize)
 {
-	if (tp->max_window && pktsize > (tp->max_window >> 1))
-		return max(tp->max_window >> 1, 68U - tp->tcp_header_len);
+	int cutoff;
+
+	/* When peer uses tiny windows, there is no use in packetizing
+	 * to sub-MSS pieces for the sake of SWS or making sure there
+	 * are enough packets in the pipe for fast recovery.
+	 *
+	 * On the other hand, for extremely large MSS devices, handling
+	 * smaller than MSS windows in this way does make sense.
+	 */
+	if (tp->max_window >= 512)
+		cutoff = (tp->max_window >> 1);
+	else
+		cutoff = tp->max_window;
+
+	if (cutoff && pktsize > cutoff)
+		return max_t(int, cutoff, 68U - tp->tcp_header_len);
 	else
 		return pktsize;
 }
diff --git a/include/net/udp.h b/include/net/udp.h
index 7abdf305da50..a184d3496b13 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -151,6 +151,7 @@ static inline void udp_lib_hash(struct sock *sk)
 }
 
 extern void udp_lib_unhash(struct sock *sk);
+extern void udp_lib_rehash(struct sock *sk, u16 new_hash);
 
 static inline void udp_lib_close(struct sock *sk, long timeout)
 {