Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Mostly simple overlapping changes.

For example, David Ahern's adjacency list revamp in 'net-next'
conflicted with an adjacency list traversal bug fix in 'net'.

Signed-off-by: David S. Miller <davem@davemloft.net>

65 files changed, 2156 insertions, 372 deletions

diff --git a/include/acpi/pcc.h b/include/acpi/pcc.h
index 17a940a14477..8caa79c61703 100644
--- a/include/acpi/pcc.h
+++ b/include/acpi/pcc.h
@@ -21,7 +21,7 @@ extern void pcc_mbox_free_channel(struct mbox_chan *chan);
 static inline struct mbox_chan *pcc_mbox_request_channel(struct mbox_client *cl,
 							 int subspace_id)
 {
-	return NULL;
+	return ERR_PTR(-ENODEV);
 }
 static inline void pcc_mbox_free_channel(struct mbox_chan *chan) { }
 #endif
diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h
new file mode 100644
index 000000000000..63554e9f6e0c
--- /dev/null
+++ b/include/asm-generic/export.h
@@ -0,0 +1,94 @@
+#ifndef __ASM_GENERIC_EXPORT_H
+#define __ASM_GENERIC_EXPORT_H
+
+#ifndef KSYM_FUNC
+#define KSYM_FUNC(x) x
+#endif
+#ifdef CONFIG_64BIT
+#define __put .quad
+#ifndef KSYM_ALIGN
+#define KSYM_ALIGN 8
+#endif
+#ifndef KCRC_ALIGN
+#define KCRC_ALIGN 8
+#endif
+#else
+#define __put .long
+#ifndef KSYM_ALIGN
+#define KSYM_ALIGN 4
+#endif
+#ifndef KCRC_ALIGN
+#define KCRC_ALIGN 4
+#endif
+#endif
+
+#ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX
+#define KSYM(name) _##name
+#else
+#define KSYM(name) name
+#endif
+
+/*
+ * note on .section use: @progbits vs %progbits nastiness doesn't matter,
+ * since we immediately emit into those sections anyway.
+ */
+.macro ___EXPORT_SYMBOL name,val,sec
+#ifdef CONFIG_MODULES
+	.globl KSYM(__ksymtab_\name)
+	.section ___ksymtab\sec+\name,"a"
+	.balign KSYM_ALIGN
+KSYM(__ksymtab_\name):
+	__put \val, KSYM(__kstrtab_\name)
+	.previous
+	.section __ksymtab_strings,"a"
+KSYM(__kstrtab_\name):
+#ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX
+	.asciz "_\name"
+#else
+	.asciz "\name"
+#endif
+	.previous
+#ifdef CONFIG_MODVERSIONS
+	.section ___kcrctab\sec+\name,"a"
+	.balign KCRC_ALIGN
+KSYM(__kcrctab_\name):
+	__put KSYM(__crc_\name)
+	.weak KSYM(__crc_\name)
+	.previous
+#endif
+#endif
+.endm
+#undef __put
+
+#if defined(__KSYM_DEPS__)
+
+#define __EXPORT_SYMBOL(sym, val, sec)	=== __KSYM_##sym ===
+
+#elif defined(CONFIG_TRIM_UNUSED_KSYMS)
+
+#include <linux/kconfig.h>
+#include <generated/autoksyms.h>
+
+#define __EXPORT_SYMBOL(sym, val, sec)				\
+	__cond_export_sym(sym, val, sec, __is_defined(__KSYM_##sym))
+#define __cond_export_sym(sym, val, sec, conf)			\
+	___cond_export_sym(sym, val, sec, conf)
+#define ___cond_export_sym(sym, val, sec, enabled)		\
+	__cond_export_sym_##enabled(sym, val, sec)
+#define __cond_export_sym_1(sym, val, sec) ___EXPORT_SYMBOL sym, val, sec
+#define __cond_export_sym_0(sym, val, sec) /* nothing */
+
+#else
+#define __EXPORT_SYMBOL(sym, val, sec) ___EXPORT_SYMBOL sym, val, sec
+#endif
+
+#define EXPORT_SYMBOL(name)					\
+	__EXPORT_SYMBOL(name, KSYM_FUNC(KSYM(name)),)
+#define EXPORT_SYMBOL_GPL(name) 				\
+	__EXPORT_SYMBOL(name, KSYM_FUNC(KSYM(name)), _gpl)
+#define EXPORT_DATA_SYMBOL(name)				\
+	__EXPORT_SYMBOL(name, KSYM(name),)
+#define EXPORT_DATA_SYMBOL_GPL(name)				\
+	__EXPORT_SYMBOL(name, KSYM(name),_gpl)
+
+#endif
diff --git a/include/asm-generic/libata-portmap.h b/include/asm-generic/libata-portmap.h
deleted file mode 100644
index cf14f2ff40b6..000000000000
--- a/include/asm-generic/libata-portmap.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __ASM_GENERIC_LIBATA_PORTMAP_H
-#define __ASM_GENERIC_LIBATA_PORTMAP_H
-
-#define ATA_PRIMARY_IRQ(dev)	14
-#define ATA_SECONDARY_IRQ(dev)	15
-
-#endif
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 4d9f233c4ba8..40e887068da2 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -65,6 +65,11 @@ extern void setup_per_cpu_areas(void);
 #define PER_CPU_DEF_ATTRIBUTES
 #endif
 
+#define raw_cpu_generic_read(pcp)					\
+({									\
+	*raw_cpu_ptr(&(pcp));						\
+})
+
 #define raw_cpu_generic_to_op(pcp, val, op)				\
 do {									\
 	*raw_cpu_ptr(&(pcp)) op val;					\
@@ -72,34 +77,39 @@ do {									\
 
 #define raw_cpu_generic_add_return(pcp, val)				\
 ({									\
-	raw_cpu_add(pcp, val);						\
-	raw_cpu_read(pcp);						\
+	typeof(&(pcp)) __p = raw_cpu_ptr(&(pcp));			\
+									\
+	*__p += val;							\
+	*__p;								\
 })
 
 #define raw_cpu_generic_xchg(pcp, nval)					\
 ({									\
+	typeof(&(pcp)) __p = raw_cpu_ptr(&(pcp));			\
 	typeof(pcp) __ret;						\
-	__ret = raw_cpu_read(pcp);					\
-	raw_cpu_write(pcp, nval);					\
+	__ret = *__p;							\
+	*__p = nval;							\
 	__ret;								\
 })
 
 #define raw_cpu_generic_cmpxchg(pcp, oval, nval)			\
 ({									\
+	typeof(&(pcp)) __p = raw_cpu_ptr(&(pcp));			\
 	typeof(pcp) __ret;						\
-	__ret = raw_cpu_read(pcp);					\
+	__ret = *__p;							\
 	if (__ret == (oval))						\
-		raw_cpu_write(pcp, nval);				\
+		*__p = nval;						\
 	__ret;								\
 })
 
 #define raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
 ({									\
+	typeof(&(pcp1)) __p1 = raw_cpu_ptr(&(pcp1));			\
+	typeof(&(pcp2)) __p2 = raw_cpu_ptr(&(pcp2));			\
 	int __ret = 0;							\
-	if (raw_cpu_read(pcp1) == (oval1) &&				\
-			 raw_cpu_read(pcp2)  == (oval2)) {		\
-		raw_cpu_write(pcp1, nval1);				\
-		raw_cpu_write(pcp2, nval2);				\
+	if (*__p1 == (oval1) && *__p2  == (oval2)) {			\
+		*__p1 = nval1;						\
+		*__p2 = nval2;						\
 		__ret = 1;						\
 	}								\
 	(__ret);							\
@@ -109,7 +119,7 @@ do {									\
 ({									\
 	typeof(pcp) __ret;						\
 	preempt_disable();						\
-	__ret = *this_cpu_ptr(&(pcp));					\
+	__ret = raw_cpu_generic_read(pcp);				\
 	preempt_enable();						\
 	__ret;								\
 })
@@ -118,17 +128,17 @@ do {									\
 do {									\
 	unsigned long __flags;						\
 	raw_local_irq_save(__flags);					\
-	*raw_cpu_ptr(&(pcp)) op val;					\
+	raw_cpu_generic_to_op(pcp, val, op);				\
 	raw_local_irq_restore(__flags);					\
 } while (0)
 
+
 #define this_cpu_generic_add_return(pcp, val)				\
 ({									\
 	typeof(pcp) __ret;						\
 	unsigned long __flags;						\
 	raw_local_irq_save(__flags);					\
-	raw_cpu_add(pcp, val);						\
-	__ret = raw_cpu_read(pcp);					\
+	__ret = raw_cpu_generic_add_return(pcp, val);			\
 	raw_local_irq_restore(__flags);					\
 	__ret;								\
 })
@@ -138,8 +148,7 @@ do {									\
 	typeof(pcp) __ret;						\
 	unsigned long __flags;						\
 	raw_local_irq_save(__flags);					\
-	__ret = raw_cpu_read(pcp);					\
-	raw_cpu_write(pcp, nval);					\
+	__ret = raw_cpu_generic_xchg(pcp, nval);			\
 	raw_local_irq_restore(__flags);					\
 	__ret;								\
 })
@@ -149,9 +158,7 @@ do {									\
 	typeof(pcp) __ret;						\
 	unsigned long __flags;						\
 	raw_local_irq_save(__flags);					\
-	__ret = raw_cpu_read(pcp);					\
-	if (__ret == (oval))						\
-		raw_cpu_write(pcp, nval);				\
+	__ret = raw_cpu_generic_cmpxchg(pcp, oval, nval);		\
 	raw_local_irq_restore(__flags);					\
 	__ret;								\
 })
@@ -168,16 +175,16 @@ do {									\
 })
 
 #ifndef raw_cpu_read_1
-#define raw_cpu_read_1(pcp)		(*raw_cpu_ptr(&(pcp)))
+#define raw_cpu_read_1(pcp)		raw_cpu_generic_read(pcp)
 #endif
 #ifndef raw_cpu_read_2
-#define raw_cpu_read_2(pcp)		(*raw_cpu_ptr(&(pcp)))
+#define raw_cpu_read_2(pcp)		raw_cpu_generic_read(pcp)
 #endif
 #ifndef raw_cpu_read_4
-#define raw_cpu_read_4(pcp)		(*raw_cpu_ptr(&(pcp)))
+#define raw_cpu_read_4(pcp)		raw_cpu_generic_read(pcp)
 #endif
 #ifndef raw_cpu_read_8
-#define raw_cpu_read_8(pcp)		(*raw_cpu_ptr(&(pcp)))
+#define raw_cpu_read_8(pcp)		raw_cpu_generic_read(pcp)
 #endif
 
 #ifndef raw_cpu_write_1
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 3e42bcdd014b..30747960bc54 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -196,9 +196,14 @@
 	*(.dtb.init.rodata)						\
 	VMLINUX_SYMBOL(__dtb_end) = .;
 
-/* .data section */
+/*
+ * .data section
+ * LD_DEAD_CODE_DATA_ELIMINATION option enables -fdata-sections generates
+ * .data.identifier which needs to be pulled in with .data, but don't want to
+ * pull in .data..stuff which has its own requirements. Same for bss.
+ */
 #define DATA_DATA							\
-	*(.data)							\
+	*(.data .data.[0-9a-zA-Z_]*)					\
 	*(.ref.data)							\
 	*(.data..shared_aligned) /* percpu related */			\
 	MEM_KEEP(init.data)						\
@@ -320,76 +325,76 @@
 	/* Kernel symbol table: Normal symbols */			\
 	__ksymtab         : AT(ADDR(__ksymtab) - LOAD_OFFSET) {		\
 		VMLINUX_SYMBOL(__start___ksymtab) = .;			\
-		*(SORT(___ksymtab+*))					\
+		KEEP(*(SORT(___ksymtab+*)))				\
 		VMLINUX_SYMBOL(__stop___ksymtab) = .;			\
 	}								\
 									\
 	/* Kernel symbol table: GPL-only symbols */			\
 	__ksymtab_gpl     : AT(ADDR(__ksymtab_gpl) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__start___ksymtab_gpl) = .;		\
-		*(SORT(___ksymtab_gpl+*))				\
+		KEEP(*(SORT(___ksymtab_gpl+*)))				\
 		VMLINUX_SYMBOL(__stop___ksymtab_gpl) = .;		\
 	}								\
 									\
 	/* Kernel symbol table: Normal unused symbols */		\
 	__ksymtab_unused  : AT(ADDR(__ksymtab_unused) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__start___ksymtab_unused) = .;		\
-		*(SORT(___ksymtab_unused+*))				\
+		KEEP(*(SORT(___ksymtab_unused+*)))			\
 		VMLINUX_SYMBOL(__stop___ksymtab_unused) = .;		\
 	}								\
 									\
 	/* Kernel symbol table: GPL-only unused symbols */		\
 	__ksymtab_unused_gpl : AT(ADDR(__ksymtab_unused_gpl) - LOAD_OFFSET) { \
 		VMLINUX_SYMBOL(__start___ksymtab_unused_gpl) = .;	\
-		*(SORT(___ksymtab_unused_gpl+*))			\
+		KEEP(*(SORT(___ksymtab_unused_gpl+*)))			\
 		VMLINUX_SYMBOL(__stop___ksymtab_unused_gpl) = .;	\
 	}								\
 									\
 	/* Kernel symbol table: GPL-future-only symbols */		\
 	__ksymtab_gpl_future : AT(ADDR(__ksymtab_gpl_future) - LOAD_OFFSET) { \
 		VMLINUX_SYMBOL(__start___ksymtab_gpl_future) = .;	\
-		*(SORT(___ksymtab_gpl_future+*))			\
+		KEEP(*(SORT(___ksymtab_gpl_future+*)))			\
 		VMLINUX_SYMBOL(__stop___ksymtab_gpl_future) = .;	\
 	}								\
 									\
 	/* Kernel symbol table: Normal symbols */			\
 	__kcrctab         : AT(ADDR(__kcrctab) - LOAD_OFFSET) {		\
 		VMLINUX_SYMBOL(__start___kcrctab) = .;			\
-		*(SORT(___kcrctab+*))					\
+		KEEP(*(SORT(___kcrctab+*)))				\
 		VMLINUX_SYMBOL(__stop___kcrctab) = .;			\
 	}								\
 									\
 	/* Kernel symbol table: GPL-only symbols */			\
 	__kcrctab_gpl     : AT(ADDR(__kcrctab_gpl) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__start___kcrctab_gpl) = .;		\
-		*(SORT(___kcrctab_gpl+*))				\
+		KEEP(*(SORT(___kcrctab_gpl+*)))				\
 		VMLINUX_SYMBOL(__stop___kcrctab_gpl) = .;		\
 	}								\
 									\
 	/* Kernel symbol table: Normal unused symbols */		\
 	__kcrctab_unused  : AT(ADDR(__kcrctab_unused) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__start___kcrctab_unused) = .;		\
-		*(SORT(___kcrctab_unused+*))				\
+		KEEP(*(SORT(___kcrctab_unused+*)))			\
 		VMLINUX_SYMBOL(__stop___kcrctab_unused) = .;		\
 	}								\
 									\
 	/* Kernel symbol table: GPL-only unused symbols */		\
 	__kcrctab_unused_gpl : AT(ADDR(__kcrctab_unused_gpl) - LOAD_OFFSET) { \
 		VMLINUX_SYMBOL(__start___kcrctab_unused_gpl) = .;	\
-		*(SORT(___kcrctab_unused_gpl+*))			\
+		KEEP(*(SORT(___kcrctab_unused_gpl+*)))			\
 		VMLINUX_SYMBOL(__stop___kcrctab_unused_gpl) = .;	\
 	}								\
 									\
 	/* Kernel symbol table: GPL-future-only symbols */		\
 	__kcrctab_gpl_future : AT(ADDR(__kcrctab_gpl_future) - LOAD_OFFSET) { \
 		VMLINUX_SYMBOL(__start___kcrctab_gpl_future) = .;	\
-		*(SORT(___kcrctab_gpl_future+*))			\
+		KEEP(*(SORT(___kcrctab_gpl_future+*)))			\
 		VMLINUX_SYMBOL(__stop___kcrctab_gpl_future) = .;	\
 	}								\
 									\
 	/* Kernel symbol table: strings */				\
         __ksymtab_strings : AT(ADDR(__ksymtab_strings) - LOAD_OFFSET) {	\
-		*(__ksymtab_strings)					\
+		KEEP(*(__ksymtab_strings))				\
 	}								\
 									\
 	/* __*init sections */						\
@@ -424,12 +429,17 @@
 #define SECURITY_INIT							\
 	.security_initcall.init : AT(ADDR(.security_initcall.init) - LOAD_OFFSET) { \
 		VMLINUX_SYMBOL(__security_initcall_start) = .;		\
-		*(.security_initcall.init) 				\
+		KEEP(*(.security_initcall.init))			\
 		VMLINUX_SYMBOL(__security_initcall_end) = .;		\
 	}
 
 /* .text section. Map to function alignment to avoid address changes
- * during second ld run in second ld pass when generating System.map */
+ * during second ld run in second ld pass when generating System.map
+ * LD_DEAD_CODE_DATA_ELIMINATION option enables -ffunction-sections generates
+ * .text.identifier which needs to be pulled in with .text , but some
+ * architectures define .text.foo which is not intended to be pulled in here.
+ * Those enabling LD_DEAD_CODE_DATA_ELIMINATION must ensure they don't have
+ * conflicting section names, and must pull in .text.[0-9a-zA-Z_]* */
 #define TEXT_TEXT							\
 		ALIGN_FUNCTION();					\
 		*(.text.hot .text .text.fixup .text.unlikely)		\
@@ -533,6 +543,7 @@
 
 /* init and exit section handling */
 #define INIT_DATA							\
+	KEEP(*(SORT(___kentry+*)))					\
 	*(.init.data)							\
 	MEM_DISCARD(init.data)						\
 	KERNEL_CTORS()							\
@@ -599,7 +610,7 @@
 		BSS_FIRST_SECTIONS					\
 		*(.bss..page_aligned)					\
 		*(.dynbss)						\
-		*(.bss)							\
+		*(.bss .bss.[0-9a-zA-Z_]*)				\
 		*(COMMON)						\
 	}
 
@@ -682,12 +693,12 @@
 
 #define INIT_CALLS_LEVEL(level)						\
 		VMLINUX_SYMBOL(__initcall##level##_start) = .;		\
-		*(.initcall##level##.init)				\
-		*(.initcall##level##s.init)				\
+		KEEP(*(.initcall##level##.init))			\
+		KEEP(*(.initcall##level##s.init))			\
 
 #define INIT_CALLS							\
 		VMLINUX_SYMBOL(__initcall_start) = .;			\
-		*(.initcallearly.init)					\
+		KEEP(*(.initcallearly.init))				\
 		INIT_CALLS_LEVEL(0)					\
 		INIT_CALLS_LEVEL(1)					\
 		INIT_CALLS_LEVEL(2)					\
@@ -701,21 +712,21 @@
 
 #define CON_INITCALL							\
 		VMLINUX_SYMBOL(__con_initcall_start) = .;		\
-		*(.con_initcall.init)					\
+		KEEP(*(.con_initcall.init))				\
 		VMLINUX_SYMBOL(__con_initcall_end) = .;
 
 #define SECURITY_INITCALL						\
 		VMLINUX_SYMBOL(__security_initcall_start) = .;		\
-		*(.security_initcall.init)				\
+		KEEP(*(.security_initcall.init))			\
 		VMLINUX_SYMBOL(__security_initcall_end) = .;
 
 #ifdef CONFIG_BLK_DEV_INITRD
 #define INIT_RAM_FS							\
 	. = ALIGN(4);							\
 	VMLINUX_SYMBOL(__initramfs_start) = .;				\
-	*(.init.ramfs)							\
+	KEEP(*(.init.ramfs))						\
 	. = ALIGN(8);							\
-	*(.init.ramfs.info)
+	KEEP(*(.init.ramfs.info))
 #else
 #define INIT_RAM_FS
 #endif
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 94afcb2c384c..689a8b9b9c8f 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -326,6 +326,7 @@ struct pci_dev;
 int acpi_pci_irq_enable (struct pci_dev *dev);
 void acpi_penalize_isa_irq(int irq, int active);
 bool acpi_isa_irq_available(int irq);
+void acpi_penalize_sci_irq(int irq, int trigger, int polarity);
 void acpi_pci_irq_disable (struct pci_dev *dev);
 
 extern int ec_read(u8 addr, u8 *val);
@@ -946,9 +947,17 @@ struct acpi_reference_args {
 #ifdef CONFIG_ACPI
 int acpi_dev_get_property(struct acpi_device *adev, const char *name,
 			  acpi_object_type type, const union acpi_object **obj);
-int acpi_node_get_property_reference(struct fwnode_handle *fwnode,
-				     const char *name, size_t index,
-				     struct acpi_reference_args *args);
+int __acpi_node_get_property_reference(struct fwnode_handle *fwnode,
+				const char *name, size_t index, size_t num_args,
+				struct acpi_reference_args *args);
+
+static inline int acpi_node_get_property_reference(struct fwnode_handle *fwnode,
+				const char *name, size_t index,
+				struct acpi_reference_args *args)
+{
+	return __acpi_node_get_property_reference(fwnode, name, index,
+		MAX_ACPI_REFERENCE_ARGS, args);
+}
 
 int acpi_node_prop_get(struct fwnode_handle *fwnode, const char *propname,
 		       void **valptr);
@@ -1024,6 +1033,14 @@ static inline int acpi_dev_get_property(struct acpi_device *adev,
 	return -ENXIO;
 }
 
+static inline int
+__acpi_node_get_property_reference(struct fwnode_handle *fwnode,
+				const char *name, size_t index, size_t num_args,
+				struct acpi_reference_args *args)
+{
+	return -ENXIO;
+}
+
 static inline int acpi_node_get_property_reference(struct fwnode_handle *fwnode,
 				const char *name, size_t index,
 				struct acpi_reference_args *args)
diff --git a/include/linux/ata.h b/include/linux/ata.h
index adbc812c009b..fdb180367ba1 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -105,6 +105,7 @@ enum {
 	ATA_ID_CFA_KEY_MGMT	= 162,
 	ATA_ID_CFA_MODES	= 163,
 	ATA_ID_DATA_SET_MGMT	= 169,
+	ATA_ID_SCT_CMD_XPORT	= 206,
 	ATA_ID_ROT_SPEED	= 217,
 	ATA_ID_PIO4		= (1 << 1),
 
@@ -789,6 +790,48 @@ static inline bool ata_id_sense_reporting_enabled(const u16 *id)
 }
 
 /**
+ *
+ * Word: 206 - SCT Command Transport
+ *    15:12 - Vendor Specific
+ *     11:6 - Reserved
+ *        5 - SCT Command Transport Data Tables supported
+ *        4 - SCT Command Transport Features Control supported
+ *        3 - SCT Command Transport Error Recovery Control supported
+ *        2 - SCT Command Transport Write Same supported
+ *        1 - SCT Command Transport Long Sector Access supported
+ *        0 - SCT Command Transport supported
+ */
+static inline bool ata_id_sct_data_tables(const u16 *id)
+{
+	return id[ATA_ID_SCT_CMD_XPORT] & (1 << 5) ? true : false;
+}
+
+static inline bool ata_id_sct_features_ctrl(const u16 *id)
+{
+	return id[ATA_ID_SCT_CMD_XPORT] & (1 << 4) ? true : false;
+}
+
+static inline bool ata_id_sct_error_recovery_ctrl(const u16 *id)
+{
+	return id[ATA_ID_SCT_CMD_XPORT] & (1 << 3) ? true : false;
+}
+
+static inline bool ata_id_sct_write_same(const u16 *id)
+{
+	return id[ATA_ID_SCT_CMD_XPORT] & (1 << 2) ? true : false;
+}
+
+static inline bool ata_id_sct_long_sector_access(const u16 *id)
+{
+	return id[ATA_ID_SCT_CMD_XPORT] & (1 << 1) ? true : false;
+}
+
+static inline bool ata_id_sct_supported(const u16 *id)
+{
+	return id[ATA_ID_SCT_CMD_XPORT] & (1 << 0) ? true : false;
+}
+
+/**
  *	ata_id_major_version	-	get ATA level of drive
  *	@id: Identify data
  *
@@ -1071,32 +1114,6 @@ static inline void ata_id_to_hd_driveid(u16 *id)
 #endif
 }
 
-/*
- * Write LBA Range Entries to the buffer that will cover the extent from
- * sector to sector + count.  This is used for TRIM and for ADD LBA(S)
- * TO NV CACHE PINNED SET.
- */
-static inline unsigned ata_set_lba_range_entries(void *_buffer,
-		unsigned num, u64 sector, unsigned long count)
-{
-	__le64 *buffer = _buffer;
-	unsigned i = 0, used_bytes;
-
-	while (i < num) {
-		u64 entry = sector |
-			((u64)(count > 0xffff ? 0xffff : count) << 48);
-		buffer[i++] = __cpu_to_le64(entry);
-		if (count <= 0xffff)
-			break;
-		count -= 0xffff;
-		sector += 0xffff;
-	}
-
-	used_bytes = ALIGN(i * 8, 512);
-	memset(buffer + i, 0, used_bytes - i * 8);
-	return used_bytes;
-}
-
 static inline bool ata_ok(u8 status)
 {
 	return ((status & (ATA_BUSY | ATA_DRDY | ATA_DF | ATA_DRQ | ATA_ERR))
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index cbdbf34de5b6..3bf5d33800ab 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -343,16 +343,7 @@ static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd)
  */
 static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen)
 {
-	char *p;
-
-	p = cgroup_path(blkg->blkcg->css.cgroup, buf, buflen);
-	if (!p) {
-		strncpy(buf, "<unavailable>", buflen);
-		return -ENAMETOOLONG;
-	}
-
-	memmove(buf, p, buf + buflen - p);
-	return 0;
+	return cgroup_path(blkg->blkcg->css.cgroup, buf, buflen);
 }
 
 /**
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 440a72164a11..c83c23f0577b 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -97,7 +97,7 @@ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
 int cgroup_rm_cftypes(struct cftype *cfts);
 void cgroup_file_notify(struct cgroup_file *cfile);
 
-char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
+int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
 int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry);
 int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 		     struct pid *pid, struct task_struct *tsk);
@@ -555,8 +555,7 @@ static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen)
 	return kernfs_name(cgrp->kn, buf, buflen);
 }
 
-static inline char * __must_check cgroup_path(struct cgroup *cgrp, char *buf,
-					      size_t buflen)
+static inline int cgroup_path(struct cgroup *cgrp, char *buf, size_t buflen)
 {
 	return kernfs_path(cgrp->kn, buf, buflen);
 }
@@ -658,8 +657,8 @@ struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
 					struct user_namespace *user_ns,
 					struct cgroup_namespace *old_ns);
 
-char *cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
-		     struct cgroup_namespace *ns);
+int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
+		   struct cgroup_namespace *ns);
 
 #else /* !CONFIG_CGROUPS */
 
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index af596381fa0f..a428aec36ace 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -785,7 +785,7 @@ extern struct of_device_id __clk_of_table;
  * routines, one at of_clk_init(), and one at platform device probe
  */
 #define CLK_OF_DECLARE_DRIVER(name, compat, fn) \
-	static void name##_of_clk_init_driver(struct device_node *np)	\
+	static void __init name##_of_clk_init_driver(struct device_node *np) \
 	{								\
 		of_node_clear_flag(np, OF_POPULATED);			\
 		fn(np);							\
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 573c5a18908f..432f5c97e18f 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -188,6 +188,13 @@
 #endif /* GCC_VERSION >= 40300 */
 
 #if GCC_VERSION >= 40500
+
+#ifndef __CHECKER__
+#ifdef LATENT_ENTROPY_PLUGIN
+#define __latent_entropy __attribute__((latent_entropy))
+#endif
+#endif
+
 /*
  * Mark a position in code as unreachable.  This can be used to
  * suppress control flow warnings after asm blocks that transfer
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 668569844d37..cf0fa5d86059 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -182,6 +182,29 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
 # define unreachable() do { } while (1)
 #endif
 
+/*
+ * KENTRY - kernel entry point
+ * This can be used to annotate symbols (functions or data) that are used
+ * without their linker symbol being referenced explicitly. For example,
+ * interrupt vector handlers, or functions in the kernel image that are found
+ * programatically.
+ *
+ * Not required for symbols exported with EXPORT_SYMBOL, or initcalls. Those
+ * are handled in their own way (with KEEP() in linker scripts).
+ *
+ * KENTRY can be avoided if the symbols in question are marked as KEEP() in the
+ * linker script. For example an architecture could KEEP() its entire
+ * boot/exception vector code rather than annotate each function and data.
+ */
+#ifndef KENTRY
+# define KENTRY(sym)						\
+	extern typeof(sym) sym;					\
+	static const unsigned long __kentry_##sym		\
+	__used							\
+	__attribute__((section("___kentry" "+" #sym ), used))	\
+	= (unsigned long)&sym;
+#endif
+
 #ifndef RELOC_HIDE
 # define RELOC_HIDE(ptr, off)					\
   ({ unsigned long __ptr;					\
@@ -406,6 +429,10 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 # define __attribute_const__	/* unimplemented */
 #endif
 
+#ifndef __latent_entropy
+# define __latent_entropy
+#endif
+
 /*
  * Tell gcc if a function is cold. The compiler will assume any path
  * directly leading to the call is unlikely.
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 631ba33bbe9f..32dc0cbd51ca 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -639,19 +639,19 @@ static inline int cpufreq_table_find_index_al(struct cpufreq_policy *policy,
 					      unsigned int target_freq)
 {
 	struct cpufreq_frequency_table *table = policy->freq_table;
+	struct cpufreq_frequency_table *pos, *best = table - 1;
 	unsigned int freq;
-	int i, best = -1;
 
-	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
-		freq = table[i].frequency;
+	cpufreq_for_each_valid_entry(pos, table) {
+		freq = pos->frequency;
 
 		if (freq >= target_freq)
-			return i;
+			return pos - table;
 
-		best = i;
+		best = pos;
 	}
 
-	return best;
+	return best - table;
 }
 
 /* Find lowest freq at or above target in a table in descending order */
@@ -659,28 +659,28 @@ static inline int cpufreq_table_find_index_dl(struct cpufreq_policy *policy,
 					      unsigned int target_freq)
 {
 	struct cpufreq_frequency_table *table = policy->freq_table;
+	struct cpufreq_frequency_table *pos, *best = table - 1;
 	unsigned int freq;
-	int i, best = -1;
 
-	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
-		freq = table[i].frequency;
+	cpufreq_for_each_valid_entry(pos, table) {
+		freq = pos->frequency;
 
 		if (freq == target_freq)
-			return i;
+			return pos - table;
 
 		if (freq > target_freq) {
-			best = i;
+			best = pos;
 			continue;
 		}
 
 		/* No freq found above target_freq */
-		if (best == -1)
-			return i;
+		if (best == table - 1)
+			return pos - table;
 
-		return best;
+		return best - table;
 	}
 
-	return best;
+	return best - table;
 }
 
 /* Works only on sorted freq-tables */
@@ -700,28 +700,28 @@ static inline int cpufreq_table_find_index_ah(struct cpufreq_policy *policy,
 					      unsigned int target_freq)
 {
 	struct cpufreq_frequency_table *table = policy->freq_table;
+	struct cpufreq_frequency_table *pos, *best = table - 1;
 	unsigned int freq;
-	int i, best = -1;
 
-	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
-		freq = table[i].frequency;
+	cpufreq_for_each_valid_entry(pos, table) {
+		freq = pos->frequency;
 
 		if (freq == target_freq)
-			return i;
+			return pos - table;
 
 		if (freq < target_freq) {
-			best = i;
+			best = pos;
 			continue;
 		}
 
 		/* No freq found below target_freq */
-		if (best == -1)
-			return i;
+		if (best == table - 1)
+			return pos - table;
 
-		return best;
+		return best - table;
 	}
 
-	return best;
+	return best - table;
 }
 
 /* Find highest freq at or below target in a table in descending order */
@@ -729,19 +729,19 @@ static inline int cpufreq_table_find_index_dh(struct cpufreq_policy *policy,
 					      unsigned int target_freq)
 {
 	struct cpufreq_frequency_table *table = policy->freq_table;
+	struct cpufreq_frequency_table *pos, *best = table - 1;
 	unsigned int freq;
-	int i, best = -1;
 
-	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
-		freq = table[i].frequency;
+	cpufreq_for_each_valid_entry(pos, table) {
+		freq = pos->frequency;
 
 		if (freq <= target_freq)
-			return i;
+			return pos - table;
 
-		best = i;
+		best = pos;
 	}
 
-	return best;
+	return best - table;
 }
 
 /* Works only on sorted freq-tables */
@@ -761,32 +761,32 @@ static inline int cpufreq_table_find_index_ac(struct cpufreq_policy *policy,
 					      unsigned int target_freq)
 {
 	struct cpufreq_frequency_table *table = policy->freq_table;
+	struct cpufreq_frequency_table *pos, *best = table - 1;
 	unsigned int freq;
-	int i, best = -1;
 
-	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
-		freq = table[i].frequency;
+	cpufreq_for_each_valid_entry(pos, table) {
+		freq = pos->frequency;
 
 		if (freq == target_freq)
-			return i;
+			return pos - table;
 
 		if (freq < target_freq) {
-			best = i;
+			best = pos;
 			continue;
 		}
 
 		/* No freq found below target_freq */
-		if (best == -1)
-			return i;
+		if (best == table - 1)
+			return pos - table;
 
 		/* Choose the closest freq */
-		if (target_freq - table[best].frequency > freq - target_freq)
-			return i;
+		if (target_freq - best->frequency > freq - target_freq)
+			return pos - table;
 
-		return best;
+		return best - table;
 	}
 
-	return best;
+	return best - table;
 }
 
 /* Find closest freq to target in a table in descending order */
@@ -794,32 +794,32 @@ static inline int cpufreq_table_find_index_dc(struct cpufreq_policy *policy,
 					      unsigned int target_freq)
 {
 	struct cpufreq_frequency_table *table = policy->freq_table;
+	struct cpufreq_frequency_table *pos, *best = table - 1;
 	unsigned int freq;
-	int i, best = -1;
 
-	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
-		freq = table[i].frequency;
+	cpufreq_for_each_valid_entry(pos, table) {
+		freq = pos->frequency;
 
 		if (freq == target_freq)
-			return i;
+			return pos - table;
 
 		if (freq > target_freq) {
-			best = i;
+			best = pos;
 			continue;
 		}
 
 		/* No freq found above target_freq */
-		if (best == -1)
-			return i;
+		if (best == table - 1)
+			return pos - table;
 
 		/* Choose the closest freq */
-		if (table[best].frequency - target_freq > target_freq - freq)
-			return i;
+		if (best->frequency - target_freq > target_freq - freq)
+			return pos - table;
 
-		return best;
+		return best - table;
 	}
 
-	return best;
+	return best - table;
 }
 
 /* Works only on sorted freq-tables */
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 9b207a8c5af3..afe641c02dca 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -81,6 +81,7 @@ enum cpuhp_state {
 	CPUHP_AP_ARM_ARCH_TIMER_STARTING,
 	CPUHP_AP_ARM_GLOBAL_TIMER_STARTING,
 	CPUHP_AP_DUMMY_TIMER_STARTING,
+	CPUHP_AP_JCORE_TIMER_STARTING,
 	CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING,
 	CPUHP_AP_ARM_TWD_STARTING,
 	CPUHP_AP_METAG_TIMER_STARTING,
diff --git a/include/linux/export.h b/include/linux/export.h
index d7df4922da1d..2a0f61fbc731 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -1,5 +1,6 @@
 #ifndef _LINUX_EXPORT_H
 #define _LINUX_EXPORT_H
+
 /*
  * Export symbols from the kernel to modules.  Forked from module.h
  * to reduce the amount of pointless cruft we feed to gcc when only
@@ -42,27 +43,26 @@ extern struct module __this_module;
 #ifdef CONFIG_MODVERSIONS
 /* Mark the CRC weak since genksyms apparently decides not to
  * generate a checksums for some symbols */
-#define __CRC_SYMBOL(sym, sec)					\
-	extern __visible void *__crc_##sym __attribute__((weak));		\
-	static const unsigned long __kcrctab_##sym		\
-	__used							\
-	__attribute__((section("___kcrctab" sec "+" #sym), unused))	\
+#define __CRC_SYMBOL(sym, sec)						\
+	extern __visible void *__crc_##sym __attribute__((weak));	\
+	static const unsigned long __kcrctab_##sym			\
+	__used								\
+	__attribute__((section("___kcrctab" sec "+" #sym), used))	\
 	= (unsigned long) &__crc_##sym;
 #else
 #define __CRC_SYMBOL(sym, sec)
 #endif
 
 /* For every exported symbol, place a struct in the __ksymtab section */
-#define ___EXPORT_SYMBOL(sym, sec)				\
-	extern typeof(sym) sym;					\
-	__CRC_SYMBOL(sym, sec)					\
-	static const char __kstrtab_##sym[]			\
-	__attribute__((section("__ksymtab_strings"), aligned(1))) \
-	= VMLINUX_SYMBOL_STR(sym);				\
-	extern const struct kernel_symbol __ksymtab_##sym;	\
-	__visible const struct kernel_symbol __ksymtab_##sym	\
-	__used							\
-	__attribute__((section("___ksymtab" sec "+" #sym), unused))	\
+#define ___EXPORT_SYMBOL(sym, sec)					\
+	extern typeof(sym) sym;						\
+	__CRC_SYMBOL(sym, sec)						\
+	static const char __kstrtab_##sym[]				\
+	__attribute__((section("__ksymtab_strings"), aligned(1)))	\
+	= VMLINUX_SYMBOL_STR(sym);					\
+	static const struct kernel_symbol __ksymtab_##sym		\
+	__used								\
+	__attribute__((section("___ksymtab" sec "+" #sym), used))	\
 	= { (unsigned long)&sym, __kstrtab_##sym }
 
 #if defined(__KSYM_DEPS__)
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index aca2a6a1d035..6e84b2cae6ad 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -105,7 +105,7 @@ struct files_struct *get_files_struct(struct task_struct *);
 void put_files_struct(struct files_struct *fs);
 void reset_files_struct(struct files_struct *);
 int unshare_files(struct files_struct **);
-struct files_struct *dup_fd(struct files_struct *, int *);
+struct files_struct *dup_fd(struct files_struct *, int *) __latent_entropy;
 void do_close_on_exec(struct files_struct *);
 int iterate_fd(struct files_struct *, unsigned,
 		int (*)(const void *, struct file *, unsigned),
diff --git a/include/linux/fs.h b/include/linux/fs.h
index bc65d5918140..16d2b6e874d6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2934,6 +2934,7 @@ extern int vfs_stat(const char __user *, struct kstat *);
 extern int vfs_lstat(const char __user *, struct kstat *);
 extern int vfs_fstat(unsigned int, struct kstat *);
 extern int vfs_fstatat(int , const char __user *, struct kstat *, int);
+extern const char *vfs_get_link(struct dentry *, struct delayed_call *);
 
 extern int __generic_block_fiemap(struct inode *inode,
 				  struct fiemap_extent_info *fieinfo,
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 1dbf52f9c24b..e0341af6950e 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -437,7 +437,7 @@ extern void disk_flush_events(struct gendisk *disk, unsigned int mask);
 extern unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask);
 
 /* drivers/char/random.c */
-extern void add_disk_randomness(struct gendisk *disk);
+extern void add_disk_randomness(struct gendisk *disk) __latent_entropy;
 extern void rand_initialize_disk(struct gendisk *disk);
 
 static inline sector_t get_start_sect(struct block_device *bdev)
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 6824556d37ed..cd184bdca58f 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1169,13 +1169,6 @@ int __must_check __vmbus_driver_register(struct hv_driver *hv_driver,
 					 const char *mod_name);
 void vmbus_driver_unregister(struct hv_driver *hv_driver);
 
-static inline const char *vmbus_dev_name(const struct hv_device *device_obj)
-{
-	const struct kobject *kobj = &device_obj->device.kobj;
-
-	return kobj->name;
-}
-
 void vmbus_hvsock_device_unregister(struct vmbus_channel *channel);
 
 int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj,
diff --git a/include/linux/init.h b/include/linux/init.h
index 5a3321a7909b..e30104ceb86d 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -39,7 +39,7 @@
 
 /* These are for everybody (although not all archs will actually
    discard it in modules) */
-#define __init		__section(.init.text) __cold notrace
+#define __init		__section(.init.text) __cold notrace __latent_entropy
 #define __initdata	__section(.init.data)
 #define __initconst	__section(.init.rodata)
 #define __exitdata	__section(.exit.data)
@@ -75,7 +75,8 @@
 #define __exit          __section(.exit.text) __exitused __cold notrace
 
 /* Used for MEMORY_HOTPLUG */
-#define __meminit        __section(.meminit.text) __cold notrace
+#define __meminit        __section(.meminit.text) __cold notrace \
+						  __latent_entropy
 #define __meminitdata    __section(.meminit.data)
 #define __meminitconst   __section(.meminit.rodata)
 #define __memexit        __section(.memexit.text) __exitused __cold notrace
@@ -139,24 +140,8 @@ extern bool initcall_debug;
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_LTO
-/* Work around a LTO gcc problem: when there is no reference to a variable
- * in a module it will be moved to the end of the program. This causes
- * reordering of initcalls which the kernel does not like.
- * Add a dummy reference function to avoid this. The function is
- * deleted by the linker.
- */
-#define LTO_REFERENCE_INITCALL(x) \
-	; /* yes this is needed */			\
-	static __used __exit void *reference_##x(void)	\
-	{						\
-		return &x;				\
-	}
-#else
-#define LTO_REFERENCE_INITCALL(x)
-#endif
-
-/* initcalls are now grouped by functionality into separate 
+/*
+ * initcalls are now grouped by functionality into separate
  * subsections. Ordering inside the subsections is determined
  * by link order. 
  * For backwards compatibility, initcall() puts the call in 
@@ -164,12 +149,16 @@ extern bool initcall_debug;
  *
  * The `id' arg to __define_initcall() is needed so that multiple initcalls
  * can point at the same handler without causing duplicate-symbol build errors.
+ *
+ * Initcalls are run by placing pointers in initcall sections that the
+ * kernel iterates at runtime. The linker can do dead code / data elimination
+ * and remove that completely, so the initcall sections have to be marked
+ * as KEEP() in the linker script.
  */
 
 #define __define_initcall(fn, id) \
 	static initcall_t __initcall_##fn##id __used \
-	__attribute__((__section__(".initcall" #id ".init"))) = fn; \
-	LTO_REFERENCE_INITCALL(__initcall_##fn##id)
+	__attribute__((__section__(".initcall" #id ".init"))) = fn;
 
 /*
  * Early initcalls run before initializing SMP.
@@ -205,15 +194,15 @@ extern bool initcall_debug;
 
 #define __initcall(fn) device_initcall(fn)
 
-#define __exitcall(fn) \
+#define __exitcall(fn)						\
 	static exitcall_t __exitcall_##fn __exit_call = fn
 
-#define console_initcall(fn) \
-	static initcall_t __initcall_##fn \
+#define console_initcall(fn)					\
+	static initcall_t __initcall_##fn			\
 	__used __section(.con_initcall.init) = fn
 
-#define security_initcall(fn) \
-	static initcall_t __initcall_##fn \
+#define security_initcall(fn)					\
+	static initcall_t __initcall_##fn			\
 	__used __section(.security_initcall.init) = fn
 
 struct obs_kernel_param {
diff --git a/include/linux/io.h b/include/linux/io.h
index e2c8419278c1..82ef36eac8a1 100644
--- a/include/linux/io.h
+++ b/include/linux/io.h
@@ -141,4 +141,26 @@ enum {
 void *memremap(resource_size_t offset, size_t size, unsigned long flags);
 void memunmap(void *addr);
 
+/*
+ * On x86 PAT systems we have memory tracking that keeps track of
+ * the allowed mappings on memory ranges. This tracking works for
+ * all the in-kernel mapping APIs (ioremap*), but where the user
+ * wishes to map a range from a physical device into user memory
+ * the tracking won't be updated. This API is to be used by
+ * drivers which remap physical device pages into userspace,
+ * and wants to make sure they are mapped WC and not UC.
+ */
+#ifndef arch_io_reserve_memtype_wc
+static inline int arch_io_reserve_memtype_wc(resource_size_t base,
+					     resource_size_t size)
+{
+	return 0;
+}
+
+static inline void arch_io_free_memtype_wc(resource_size_t base,
+					   resource_size_t size)
+{
+}
+#endif
+
 #endif /* _LINUX_IO_H */
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index e63e288dee83..7892f55a1866 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -19,11 +19,15 @@ struct vm_fault;
 #define IOMAP_UNWRITTEN	0x04	/* blocks allocated @blkno in unwritten state */
 
 /*
- * Flags for iomap mappings:
+ * Flags for all iomap mappings:
  */
-#define IOMAP_F_MERGED	0x01	/* contains multiple blocks/extents */
-#define IOMAP_F_SHARED	0x02	/* block shared with another file */
-#define IOMAP_F_NEW	0x04	/* blocks have been newly allocated */
+#define IOMAP_F_NEW	0x01	/* blocks have been newly allocated */
+
+/*
+ * Flags that only need to be reported for IOMAP_REPORT requests:
+ */
+#define IOMAP_F_MERGED	0x10	/* contains multiple blocks/extents */
+#define IOMAP_F_SHARED	0x20	/* block shared with another file */
 
 /*
  * Magic value for blkno:
@@ -42,8 +46,9 @@ struct iomap {
 /*
  * Flags for iomap_begin / iomap_end.  No flag implies a read.
  */
-#define IOMAP_WRITE		(1 << 0)
-#define IOMAP_ZERO		(1 << 1)
+#define IOMAP_WRITE		(1 << 0) /* writing, must allocate blocks */
+#define IOMAP_ZERO		(1 << 1) /* zeroing operation, may skip holes */
+#define IOMAP_REPORT		(1 << 2) /* report extent status, e.g. FIEMAP */
 
 struct iomap_ops {
 	/*
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 7e9a789be5e0..ca1ad9ebbc92 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -123,12 +123,12 @@ struct inet6_skb_parm {
 };
 
 #if defined(CONFIG_NET_L3_MASTER_DEV)
-static inline bool skb_l3mdev_slave(__u16 flags)
+static inline bool ipv6_l3mdev_skb(__u16 flags)
 {
 	return flags & IP6SKB_L3SLAVE;
 }
 #else
-static inline bool skb_l3mdev_slave(__u16 flags)
+static inline bool ipv6_l3mdev_skb(__u16 flags)
 {
 	return false;
 }
@@ -139,11 +139,22 @@ static inline bool skb_l3mdev_slave(__u16 flags)
 
 static inline int inet6_iif(const struct sk_buff *skb)
 {
-	bool l3_slave = skb_l3mdev_slave(IP6CB(skb)->flags);
+	bool l3_slave = ipv6_l3mdev_skb(IP6CB(skb)->flags);
 
 	return l3_slave ? skb->skb_iif : IP6CB(skb)->iif;
 }
 
+/* can not be used in TCP layer after tcp_v6_fill_cb */
+static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb)
+{
+#if defined(CONFIG_NET_L3_MASTER_DEV)
+	if (!net->ipv4.sysctl_tcp_l3mdev_accept &&
+	    ipv6_l3mdev_skb(IP6CB(skb)->flags))
+		return true;
+#endif
+	return false;
+}
+
 struct tcp6_request_sock {
 	struct tcp_request_sock	  tcp6rsk_tcp;
 };
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 8361c8d3edd1..b7e34313cdfe 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -290,7 +290,7 @@
 #define GITS_BASER_TYPE_SHIFT			(56)
 #define GITS_BASER_TYPE(r)		(((r) >> GITS_BASER_TYPE_SHIFT) & 7)
 #define GITS_BASER_ENTRY_SIZE_SHIFT		(48)
-#define GITS_BASER_ENTRY_SIZE(r)	((((r) >> GITS_BASER_ENTRY_SIZE_SHIFT) & 0xff) + 1)
+#define GITS_BASER_ENTRY_SIZE(r)	((((r) >> GITS_BASER_ENTRY_SIZE_SHIFT) & 0x1f) + 1)
 #define GITS_BASER_SHAREABILITY_SHIFT	(10)
 #define GITS_BASER_InnerShareable					\
 	GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable)
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index d600303306eb..820c0ad54a01 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -44,6 +44,7 @@ static inline void kasan_disable_current(void)
 void kasan_unpoison_shadow(const void *address, size_t size);
 
 void kasan_unpoison_task_stack(struct task_struct *task);
+void kasan_unpoison_stack_above_sp_to(const void *watermark);
 
 void kasan_alloc_pages(struct page *page, unsigned int order);
 void kasan_free_pages(struct page *page, unsigned int order);
@@ -85,6 +86,7 @@ size_t kasan_metadata_size(struct kmem_cache *cache);
 static inline void kasan_unpoison_shadow(const void *address, size_t size) {}
 
 static inline void kasan_unpoison_task_stack(struct task_struct *task) {}
+static inline void kasan_unpoison_stack_above_sp_to(const void *watermark) {}
 
 static inline void kasan_enable_current(void) {}
 static inline void kasan_disable_current(void) {}
diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h
index 15ec117ec537..8f2e059e4d45 100644
--- a/include/linux/kconfig.h
+++ b/include/linux/kconfig.h
@@ -31,7 +31,6 @@
  * When CONFIG_BOOGER is not defined, we generate a (... 1, 0) pair, and when
  * the last step cherry picks the 2nd arg, we get a zero.
  */
-#define config_enabled(cfg)		___is_defined(cfg)
 #define __is_defined(x)			___is_defined(x)
 #define ___is_defined(val)		____is_defined(__ARG_PLACEHOLDER_##val)
 #define ____is_defined(arg1_or_junk)	__take_second_arg(arg1_or_junk 1, 0)
@@ -41,13 +40,13 @@
  * otherwise. For boolean options, this is equivalent to
  * IS_ENABLED(CONFIG_FOO).
  */
-#define IS_BUILTIN(option) config_enabled(option)
+#define IS_BUILTIN(option) __is_defined(option)
 
 /*
  * IS_MODULE(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'm', 0
  * otherwise.
  */
-#define IS_MODULE(option) config_enabled(option##_MODULE)
+#define IS_MODULE(option) __is_defined(option##_MODULE)
 
 /*
  * IS_REACHABLE(CONFIG_FOO) evaluates to 1 if the currently compiled
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 96356ef012de..7056238fd9f5 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -269,10 +269,8 @@ static inline bool kernfs_ns_enabled(struct kernfs_node *kn)
 }
 
 int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen);
-size_t kernfs_path_len(struct kernfs_node *kn);
 int kernfs_path_from_node(struct kernfs_node *root_kn, struct kernfs_node *kn,
 			  char *buf, size_t buflen);
-char *kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen);
 void pr_cont_kernfs_name(struct kernfs_node *kn);
 void pr_cont_kernfs_path(struct kernfs_node *kn);
 struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn);
@@ -341,12 +339,10 @@ static inline bool kernfs_ns_enabled(struct kernfs_node *kn)
 static inline int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen)
 { return -ENOSYS; }
 
-static inline size_t kernfs_path_len(struct kernfs_node *kn)
-{ return 0; }
-
-static inline char *kernfs_path(struct kernfs_node *kn, char *buf,
-				size_t buflen)
-{ return NULL; }
+static inline int kernfs_path_from_node(struct kernfs_node *root_kn,
+					struct kernfs_node *kn,
+					char *buf, size_t buflen)
+{ return -ENOSYS; }
 
 static inline void pr_cont_kernfs_name(struct kernfs_node *kn) { }
 static inline void pr_cont_kernfs_path(struct kernfs_node *kn) { }
@@ -436,6 +432,22 @@ static inline void kernfs_init(void) { }
 
 #endif	/* CONFIG_KERNFS */
 
+/**
+ * kernfs_path - build full path of a given node
+ * @kn: kernfs_node of interest
+ * @buf: buffer to copy @kn's name into
+ * @buflen: size of @buf
+ *
+ * Builds and returns the full path of @kn in @buf of @buflen bytes.  The
+ * path is built from the end of @buf so the returned pointer usually
+ * doesn't match @buf.  If @buf isn't long enough, @buf is nul terminated
+ * and %NULL is returned.
+ */
+static inline int kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen)
+{
+	return kernfs_path_from_node(kn, NULL, buf, buflen);
+}
+
 static inline struct kernfs_node *
 kernfs_find_and_get(struct kernfs_node *kn, const char *name)
 {
diff --git a/include/linux/libata.h b/include/linux/libata.h
index e37d4f99f510..616eef4d81ea 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -46,7 +46,8 @@
 #ifdef CONFIG_ATA_NONSTANDARD
 #include <asm/libata-portmap.h>
 #else
-#include <asm-generic/libata-portmap.h>
+#define ATA_PRIMARY_IRQ(dev)	14
+#define ATA_SECONDARY_IRQ(dev)	15
 #endif
 
 /*
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index f6a164297358..3be7abd6e722 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1399,7 +1399,8 @@ void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
 		    u32 *lkey, u32 *rkey);
 int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr);
 int mlx4_SYNC_TPT(struct mlx4_dev *dev);
-int mlx4_test_interrupts(struct mlx4_dev *dev);
+int mlx4_test_interrupt(struct mlx4_dev *dev, int vector);
+int mlx4_test_async(struct mlx4_dev *dev);
 int mlx4_query_diag_counters(struct mlx4_dev *dev, u8 op_modifier,
 			     const u32 offset[], u32 value[],
 			     size_t array_len, u8 port);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 85c4786427e4..ecc451d89ccd 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -418,8 +418,12 @@ struct mlx5_core_health {
 	u32				prev;
 	int				miss_counter;
 	bool				sick;
+	/* wq spinlock to synchronize draining */
+	spinlock_t			wq_lock;
 	struct workqueue_struct	       *wq;
+	unsigned long			flags;
 	struct work_struct		work;
+	struct delayed_work		recover_work;
 };
 
 struct mlx5_cq_table {
@@ -626,10 +630,6 @@ struct mlx5_db {
 };
 
 enum {
-	MLX5_DB_PER_PAGE = PAGE_SIZE / L1_CACHE_BYTES,
-};
-
-enum {
 	MLX5_COMP_EQ_SIZE = 1024,
 };
 
@@ -638,13 +638,6 @@ enum {
 	MLX5_PTYS_EN = 1 << 2,
 };
 
-struct mlx5_db_pgdir {
-	struct list_head	list;
-	DECLARE_BITMAP(bitmap, MLX5_DB_PER_PAGE);
-	__be32		       *db_page;
-	dma_addr_t		db_dma;
-};
-
 typedef void (*mlx5_cmd_cbk_t)(int status, void *context);
 
 struct mlx5_cmd_work_ent {
@@ -789,6 +782,7 @@ void mlx5_health_cleanup(struct mlx5_core_dev *dev);
 int mlx5_health_init(struct mlx5_core_dev *dev);
 void mlx5_start_health_poll(struct mlx5_core_dev *dev);
 void mlx5_stop_health_poll(struct mlx5_core_dev *dev);
+void mlx5_drain_health_wq(struct mlx5_core_dev *dev);
 int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 			struct mlx5_buf *buf, int node);
 int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e9caec6a51e9..a92c8d73aeaf 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1266,29 +1266,25 @@ static inline int fixup_user_fault(struct task_struct *tsk,
 }
 #endif
 
-extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write);
+extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len,
+		unsigned int gup_flags);
 extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
-		void *buf, int len, int write);
+		void *buf, int len, unsigned int gup_flags);
 
-long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-		      unsigned long start, unsigned long nr_pages,
-		      unsigned int foll_flags, struct page **pages,
-		      struct vm_area_struct **vmas, int *nonblocking);
 long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
 			    unsigned long start, unsigned long nr_pages,
-			    int write, int force, struct page **pages,
+			    unsigned int gup_flags, struct page **pages,
 			    struct vm_area_struct **vmas);
 long get_user_pages(unsigned long start, unsigned long nr_pages,
-			    int write, int force, struct page **pages,
+			    unsigned int gup_flags, struct page **pages,
 			    struct vm_area_struct **vmas);
 long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
-		    int write, int force, struct page **pages, int *locked);
+		    unsigned int gup_flags, struct page **pages, int *locked);
 long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
 			       unsigned long start, unsigned long nr_pages,
-			       int write, int force, struct page **pages,
-			       unsigned int gup_flags);
+			       struct page **pages, unsigned int gup_flags);
 long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
-		    int write, int force, struct page **pages);
+		    struct page **pages, unsigned int gup_flags);
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages);
 
@@ -1306,7 +1302,7 @@ struct frame_vector {
 struct frame_vector *frame_vector_create(unsigned int nr_frames);
 void frame_vector_destroy(struct frame_vector *vec);
 int get_vaddr_frames(unsigned long start, unsigned int nr_pfns,
-		     bool write, bool force, struct frame_vector *vec);
+		     unsigned int gup_flags, struct frame_vector *vec);
 void put_vaddr_frames(struct frame_vector *vec);
 int frame_vector_to_pages(struct frame_vector *vec);
 void frame_vector_to_pfns(struct frame_vector *vec);
@@ -1391,7 +1387,7 @@ static inline int stack_guard_page_end(struct vm_area_struct *vma,
 		!vma_growsup(vma->vm_next, addr);
 }
 
-int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t);
+int vma_is_stack_for_current(struct vm_area_struct *vma);
 
 extern unsigned long move_page_tables(struct vm_area_struct *vma,
 		unsigned long old_addr, struct vm_area_struct *new_vma,
@@ -2232,6 +2228,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma,
 #define FOLL_TRIED	0x800	/* a retry, previous pass started an IO */
 #define FOLL_MLOCK	0x1000	/* lock present pages */
 #define FOLL_REMOTE	0x2000	/* we are working on non-current tsk/mm */
+#define FOLL_COW	0x4000	/* internal GUP flag */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
 			void *data);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 7f2ae99e5daf..0f088f3a2fed 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -440,33 +440,7 @@ struct zone {
 	seqlock_t		span_seqlock;
 #endif
 
-	/*
-	 * wait_table		-- the array holding the hash table
-	 * wait_table_hash_nr_entries	-- the size of the hash table array
-	 * wait_table_bits	-- wait_table_size == (1 << wait_table_bits)
-	 *
-	 * The purpose of all these is to keep track of the people
-	 * waiting for a page to become available and make them
-	 * runnable again when possible. The trouble is that this
-	 * consumes a lot of space, especially when so few things
-	 * wait on pages at a given time. So instead of using
-	 * per-page waitqueues, we use a waitqueue hash table.
-	 *
-	 * The bucket discipline is to sleep on the same queue when
-	 * colliding and wake all in that wait queue when removing.
-	 * When something wakes, it must check to be sure its page is
-	 * truly available, a la thundering herd. The cost of a
-	 * collision is great, but given the expected load of the
-	 * table, they should be so rare as to be outweighed by the
-	 * benefits from the saved space.
-	 *
-	 * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the
-	 * primary users of these fields, and in mm/page_alloc.c
-	 * free_area_init_core() performs the initialization of them.
-	 */
-	wait_queue_head_t	*wait_table;
-	unsigned long		wait_table_hash_nr_entries;
-	unsigned long		wait_table_bits;
+	int initialized;
 
 	/* Write-intensive fields used from the page allocator */
 	ZONE_PADDING(_pad1_)
@@ -546,7 +520,7 @@ static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn)
 
 static inline bool zone_is_initialized(struct zone *zone)
 {
-	return !!zone->wait_table;
+	return zone->initialized;
 }
 
 static inline bool zone_is_empty(struct zone *zone)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 458c87631e7f..20ce8df115ac 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2167,7 +2167,10 @@ struct napi_gro_cb {
 	/* Used to determine if flush_id can be ignored */
 	u8	is_atomic:1;
 
-	/* 5 bit hole */
+	/* Number of gro_receive callbacks this packet already went through */
+	u8 recursion_counter:4;
+
+	/* 1 bit hole */
 
 	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
 	__wsum	csum;
@@ -2178,6 +2181,40 @@ struct napi_gro_cb {
 
 #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb)
 
+#define GRO_RECURSION_LIMIT 15
+static inline int gro_recursion_inc_test(struct sk_buff *skb)
+{
+	return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT;
+}
+
+typedef struct sk_buff **(*gro_receive_t)(struct sk_buff **, struct sk_buff *);
+static inline struct sk_buff **call_gro_receive(gro_receive_t cb,
+						struct sk_buff **head,
+						struct sk_buff *skb)
+{
+	if (unlikely(gro_recursion_inc_test(skb))) {
+		NAPI_GRO_CB(skb)->flush |= 1;
+		return NULL;
+	}
+
+	return cb(head, skb);
+}
+
+typedef struct sk_buff **(*gro_receive_sk_t)(struct sock *, struct sk_buff **,
+					     struct sk_buff *);
+static inline struct sk_buff **call_gro_receive_sk(gro_receive_sk_t cb,
+						   struct sock *sk,
+						   struct sk_buff **head,
+						   struct sk_buff *skb)
+{
+	if (unlikely(gro_recursion_inc_test(skb))) {
+		NAPI_GRO_CB(skb)->flush |= 1;
+		return NULL;
+	}
+
+	return cb(sk, head, skb);
+}
+
 struct packet_type {
 	__be16			type;	/* This is really htons(ether_type). */
 	struct net_device	*dev;	/* NULL is wildcarded here	     */
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 7676557ce357..fc3c24206593 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -16,7 +16,6 @@
 #define _LINUX_NVME_H
 
 #include <linux/types.h>
-#include <linux/uuid.h>
 
 /* NQN names in commands fields specified one size */
 #define NVMF_NQN_FIELD_LEN	256
@@ -182,7 +181,7 @@ struct nvme_id_ctrl {
 	char			fr[8];
 	__u8			rab;
 	__u8			ieee[3];
-	__u8			mic;
+	__u8			cmic;
 	__u8			mdts;
 	__le16			cntlid;
 	__le32			ver;
@@ -202,7 +201,13 @@ struct nvme_id_ctrl {
 	__u8			apsta;
 	__le16			wctemp;
 	__le16			cctemp;
-	__u8			rsvd270[50];
+	__le16			mtfa;
+	__le32			hmpre;
+	__le32			hmmin;
+	__u8			tnvmcap[16];
+	__u8			unvmcap[16];
+	__le32			rpmbs;
+	__u8			rsvd316[4];
 	__le16			kas;
 	__u8			rsvd322[190];
 	__u8			sqes;
@@ -267,7 +272,7 @@ struct nvme_id_ns {
 	__le16			nabo;
 	__le16			nabspf;
 	__u16			rsvd46;
-	__le64			nvmcap[2];
+	__u8			nvmcap[16];
 	__u8			rsvd64[40];
 	__u8			nguid[16];
 	__u8			eui64[8];
@@ -277,6 +282,16 @@ struct nvme_id_ns {
 };
 
 enum {
+	NVME_ID_CNS_NS			= 0x00,
+	NVME_ID_CNS_CTRL		= 0x01,
+	NVME_ID_CNS_NS_ACTIVE_LIST	= 0x02,
+	NVME_ID_CNS_NS_PRESENT_LIST	= 0x10,
+	NVME_ID_CNS_NS_PRESENT		= 0x11,
+	NVME_ID_CNS_CTRL_NS_LIST	= 0x12,
+	NVME_ID_CNS_CTRL_LIST		= 0x13,
+};
+
+enum {
 	NVME_NS_FEAT_THIN	= 1 << 0,
 	NVME_NS_FLBAS_LBA_MASK	= 0xf,
 	NVME_NS_FLBAS_META_EXT	= 0x10,
@@ -556,8 +571,10 @@ enum nvme_admin_opcode {
 	nvme_admin_set_features		= 0x09,
 	nvme_admin_get_features		= 0x0a,
 	nvme_admin_async_event		= 0x0c,
+	nvme_admin_ns_mgmt		= 0x0d,
 	nvme_admin_activate_fw		= 0x10,
 	nvme_admin_download_fw		= 0x11,
+	nvme_admin_ns_attach		= 0x15,
 	nvme_admin_keep_alive		= 0x18,
 	nvme_admin_format_nvm		= 0x80,
 	nvme_admin_security_send	= 0x81,
@@ -583,6 +600,7 @@ enum {
 	NVME_FEAT_WRITE_ATOMIC	= 0x0a,
 	NVME_FEAT_ASYNC_EVENT	= 0x0b,
 	NVME_FEAT_AUTO_PST	= 0x0c,
+	NVME_FEAT_HOST_MEM_BUF	= 0x0d,
 	NVME_FEAT_KATO		= 0x0f,
 	NVME_FEAT_SW_PROGRESS	= 0x80,
 	NVME_FEAT_HOST_ID	= 0x81,
@@ -745,7 +763,7 @@ struct nvmf_common_command {
 struct nvmf_disc_rsp_page_entry {
 	__u8		trtype;
 	__u8		adrfam;
-	__u8		nqntype;
+	__u8		subtype;
 	__u8		treq;
 	__le16		portid;
 	__le16		cntlid;
@@ -794,7 +812,7 @@ struct nvmf_connect_command {
 };
 
 struct nvmf_connect_data {
-	uuid_be		hostid;
+	__u8		hostid[16];
 	__le16		cntlid;
 	char		resv4[238];
 	char		subsysnqn[NVMF_NQN_FIELD_LEN];
@@ -905,12 +923,23 @@ enum {
 	NVME_SC_INVALID_VECTOR		= 0x108,
 	NVME_SC_INVALID_LOG_PAGE	= 0x109,
 	NVME_SC_INVALID_FORMAT		= 0x10a,
-	NVME_SC_FIRMWARE_NEEDS_RESET	= 0x10b,
+	NVME_SC_FW_NEEDS_CONV_RESET	= 0x10b,
 	NVME_SC_INVALID_QUEUE		= 0x10c,
 	NVME_SC_FEATURE_NOT_SAVEABLE	= 0x10d,
 	NVME_SC_FEATURE_NOT_CHANGEABLE	= 0x10e,
 	NVME_SC_FEATURE_NOT_PER_NS	= 0x10f,
-	NVME_SC_FW_NEEDS_RESET_SUBSYS	= 0x110,
+	NVME_SC_FW_NEEDS_SUBSYS_RESET	= 0x110,
+	NVME_SC_FW_NEEDS_RESET		= 0x111,
+	NVME_SC_FW_NEEDS_MAX_TIME	= 0x112,
+	NVME_SC_FW_ACIVATE_PROHIBITED	= 0x113,
+	NVME_SC_OVERLAPPING_RANGE	= 0x114,
+	NVME_SC_NS_INSUFFICENT_CAP	= 0x115,
+	NVME_SC_NS_ID_UNAVAILABLE	= 0x116,
+	NVME_SC_NS_ALREADY_ATTACHED	= 0x118,
+	NVME_SC_NS_IS_PRIVATE		= 0x119,
+	NVME_SC_NS_NOT_ATTACHED		= 0x11a,
+	NVME_SC_THIN_PROV_NOT_SUPP	= 0x11b,
+	NVME_SC_CTRL_LIST_INVALID	= 0x11c,
 
 	/*
 	 * I/O Command Set Specific - NVM commands:
@@ -941,6 +970,7 @@ enum {
 	NVME_SC_REFTAG_CHECK		= 0x284,
 	NVME_SC_COMPARE_FAILED		= 0x285,
 	NVME_SC_ACCESS_DENIED		= 0x286,
+	NVME_SC_UNWRITTEN_BLOCK		= 0x287,
 
 	NVME_SC_DNR			= 0x4000,
 };
@@ -960,6 +990,7 @@ struct nvme_completion {
 	__le16	status;		/* did the command fail, and if so, why? */
 };
 
-#define NVME_VS(major, minor) (((major) << 16) | ((minor) << 8))
+#define NVME_VS(major, minor, tertiary) \
+	(((major) << 16) | ((minor) << 8) | (tertiary))
 
 #endif /* _LINUX_NVME_H */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 060d0ede88df..4741ecdb9817 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1257,6 +1257,7 @@ extern u64 perf_swevent_set_period(struct perf_event *event);
 extern void perf_event_enable(struct perf_event *event);
 extern void perf_event_disable(struct perf_event *event);
 extern void perf_event_disable_local(struct perf_event *event);
+extern void perf_event_disable_inatomic(struct perf_event *event);
 extern void perf_event_task_tick(void);
 #else /* !CONFIG_PERF_EVENTS: */
 static inline void *
diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h
index e4c08c1ff0c5..a1bacf1150b2 100644
--- a/include/linux/pkeys.h
+++ b/include/linux/pkeys.h
@@ -25,7 +25,6 @@ static inline int mm_pkey_alloc(struct mm_struct *mm)
 
 static inline int mm_pkey_free(struct mm_struct *mm, int pkey)
 {
-	WARN_ONCE(1, "free of protection key when disabled");
 	return -EINVAL;
 }
 
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index f9ae903bbb84..8978a60371f4 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -146,6 +146,7 @@ enum qed_led_mode {
 #define DIRECT_REG_RD(reg_addr) readl((void __iomem *)(reg_addr))
 
 #define QED_COALESCE_MAX 0xFF
+#define QED_DEFAULT_RX_USECS 12
 
 /* forward */
 struct qed_dev;
diff --git a/include/linux/qed/qede_roce.h b/include/linux/qed/qede_roce.h
index 99fbe6d55acb..f48d64b0e2fb 100644
--- a/include/linux/qed/qede_roce.h
+++ b/include/linux/qed/qede_roce.h
@@ -68,7 +68,7 @@ void qede_roce_unregister_driver(struct qedr_driver *drv);
 
 bool qede_roce_supported(struct qede_dev *dev);
 
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
+#if IS_ENABLED(CONFIG_QED_RDMA)
 int qede_roce_dev_add(struct qede_dev *dev);
 void qede_roce_dev_event_open(struct qede_dev *dev);
 void qede_roce_dev_event_close(struct qede_dev *dev);
diff --git a/include/linux/random.h b/include/linux/random.h
index f7bb7a355cf7..7bd2403e4fef 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -18,9 +18,20 @@ struct random_ready_callback {
 };
 
 extern void add_device_randomness(const void *, unsigned int);
+
+#if defined(CONFIG_GCC_PLUGIN_LATENT_ENTROPY) && !defined(__CHECKER__)
+static inline void add_latent_entropy(void)
+{
+	add_device_randomness((const void *)&latent_entropy,
+			      sizeof(latent_entropy));
+}
+#else
+static inline void add_latent_entropy(void) {}
+#endif
+
 extern void add_input_randomness(unsigned int type, unsigned int code,
-				 unsigned int value);
-extern void add_interrupt_randomness(int irq, int irq_flags);
+				 unsigned int value) __latent_entropy;
+extern void add_interrupt_randomness(int irq, int irq_flags) __latent_entropy;
 
 extern void get_random_bytes(void *buf, int nbytes);
 extern int add_random_ready_callback(struct random_ready_callback *rdy);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 663fda2887f7..cc6e23eaac91 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -936,6 +936,7 @@ struct sk_buff_fclones {
 
 /**
  *	skb_fclone_busy - check if fclone is busy
+ *	@sk: socket
  *	@skb: buffer
  *
  * Returns true if skb is a fast clone, and its clone is not freed.
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 0d7abb8b7315..91a740f6b884 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -902,8 +902,5 @@ asmlinkage long sys_pkey_mprotect(unsigned long start, size_t len,
 				  unsigned long prot, int pkey);
 asmlinkage long sys_pkey_alloc(unsigned long flags, unsigned long init_val);
 asmlinkage long sys_pkey_free(int pkey);
-//asmlinkage long sys_pkey_get(int pkey, unsigned long flags);
-//asmlinkage long sys_pkey_set(int pkey, unsigned long access_rights,
-//			     unsigned long flags);
 
 #endif
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 45f004e9cc59..2873baf5372a 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -14,17 +14,6 @@ struct timespec;
 struct compat_timespec;
 
 #ifdef CONFIG_THREAD_INFO_IN_TASK
-struct thread_info {
-	unsigned long		flags;		/* low level flags */
-};
-
-#define INIT_THREAD_INFO(tsk)			\
-{						\
-	.flags		= 0,			\
-}
-#endif
-
-#ifdef CONFIG_THREAD_INFO_IN_TASK
 #define current_thread_info() ((struct thread_info *)current)
 #endif
 
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index f2d072787947..8f998afc1384 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -174,6 +174,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
 int ipv6_sock_mc_drop(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
+void __ipv6_sock_mc_close(struct sock *sk);
 void ipv6_sock_mc_close(struct sock *sk);
 bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr,
 		    const struct in6_addr *src_addr);
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index c575583b50fb..2019310cf135 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -820,9 +820,9 @@ enum station_parameters_apply_mask {
  *	(or NULL for no change)
  * @supported_rates_len: number of supported rates
  * @sta_flags_mask: station flags that changed
- *	(bitmask of BIT(NL80211_STA_FLAG_...))
+ *	(bitmask of BIT(%NL80211_STA_FLAG_...))
  * @sta_flags_set: station flags values
- *	(bitmask of BIT(NL80211_STA_FLAG_...))
+ *	(bitmask of BIT(%NL80211_STA_FLAG_...))
  * @listen_interval: listen interval or -1 for no change
  * @aid: AID or zero for no change
  * @peer_aid: mesh peer AID or zero for no change
@@ -3160,47 +3160,54 @@ struct ieee80211_iface_limit {
  *
  * 1. Allow #STA <= 1, #AP <= 1, matching BI, channels = 1, 2 total:
  *
- *  struct ieee80211_iface_limit limits1[] = {
- *	{ .max = 1, .types = BIT(NL80211_IFTYPE_STATION), },
- *	{ .max = 1, .types = BIT(NL80211_IFTYPE_AP}, },
- *  };
- *  struct ieee80211_iface_combination combination1 = {
- *	.limits = limits1,
- *	.n_limits = ARRAY_SIZE(limits1),
- *	.max_interfaces = 2,
- *	.beacon_int_infra_match = true,
- *  };
+ *    .. code-block:: c
+ *
+ *	struct ieee80211_iface_limit limits1[] = {
+ *		{ .max = 1, .types = BIT(NL80211_IFTYPE_STATION), },
+ *		{ .max = 1, .types = BIT(NL80211_IFTYPE_AP}, },
+ *	};
+ *	struct ieee80211_iface_combination combination1 = {
+ *		.limits = limits1,
+ *		.n_limits = ARRAY_SIZE(limits1),
+ *		.max_interfaces = 2,
+ *		.beacon_int_infra_match = true,
+ *	};
  *
  *
  * 2. Allow #{AP, P2P-GO} <= 8, channels = 1, 8 total:
  *
- *  struct ieee80211_iface_limit limits2[] = {
- *	{ .max = 8, .types = BIT(NL80211_IFTYPE_AP) |
- *			     BIT(NL80211_IFTYPE_P2P_GO), },
- *  };
- *  struct ieee80211_iface_combination combination2 = {
- *	.limits = limits2,
- *	.n_limits = ARRAY_SIZE(limits2),
- *	.max_interfaces = 8,
- *	.num_different_channels = 1,
- *  };
+ *    .. code-block:: c
+ *
+ *	struct ieee80211_iface_limit limits2[] = {
+ *		{ .max = 8, .types = BIT(NL80211_IFTYPE_AP) |
+ *				     BIT(NL80211_IFTYPE_P2P_GO), },
+ *	};
+ *	struct ieee80211_iface_combination combination2 = {
+ *		.limits = limits2,
+ *		.n_limits = ARRAY_SIZE(limits2),
+ *		.max_interfaces = 8,
+ *		.num_different_channels = 1,
+ *	};
  *
  *
  * 3. Allow #STA <= 1, #{P2P-client,P2P-GO} <= 3 on two channels, 4 total.
  *
- * This allows for an infrastructure connection and three P2P connections.
+ *    This allows for an infrastructure connection and three P2P connections.
+ *
+ *    .. code-block:: c
+ *
+ *	struct ieee80211_iface_limit limits3[] = {
+ *		{ .max = 1, .types = BIT(NL80211_IFTYPE_STATION), },
+ *		{ .max = 3, .types = BIT(NL80211_IFTYPE_P2P_GO) |
+ *				     BIT(NL80211_IFTYPE_P2P_CLIENT), },
+ *	};
+ *	struct ieee80211_iface_combination combination3 = {
+ *		.limits = limits3,
+ *		.n_limits = ARRAY_SIZE(limits3),
+ *		.max_interfaces = 4,
+ *		.num_different_channels = 2,
+ *	};
  *
- *  struct ieee80211_iface_limit limits3[] = {
- *	{ .max = 1, .types = BIT(NL80211_IFTYPE_STATION), },
- *	{ .max = 3, .types = BIT(NL80211_IFTYPE_P2P_GO) |
- *			     BIT(NL80211_IFTYPE_P2P_CLIENT), },
- *  };
- *  struct ieee80211_iface_combination combination3 = {
- *	.limits = limits3,
- *	.n_limits = ARRAY_SIZE(limits3),
- *	.max_interfaces = 4,
- *	.num_different_channels = 2,
- *  };
  */
 struct ieee80211_iface_combination {
 	const struct ieee80211_iface_limit *limits;
@@ -4120,14 +4127,29 @@ unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr);
  */
 
 /**
+ * ieee80211_data_to_8023_exthdr - convert an 802.11 data frame to 802.3
+ * @skb: the 802.11 data frame
+ * @ehdr: pointer to a &struct ethhdr that will get the header, instead
+ *	of it being pushed into the SKB
+ * @addr: the device MAC address
+ * @iftype: the virtual interface type
+ * Return: 0 on success. Non-zero on error.
+ */
+int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
+				  const u8 *addr, enum nl80211_iftype iftype);
+
+/**
  * ieee80211_data_to_8023 - convert an 802.11 data frame to 802.3
  * @skb: the 802.11 data frame
  * @addr: the device MAC address
  * @iftype: the virtual interface type
  * Return: 0 on success. Non-zero on error.
  */
-int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr,
-			   enum nl80211_iftype iftype);
+static inline int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr,
+					 enum nl80211_iftype iftype)
+{
+	return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype);
+}
 
 /**
  * ieee80211_data_from_8023 - convert an 802.3 frame to 802.11
@@ -4145,22 +4167,23 @@ int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr,
 /**
  * ieee80211_amsdu_to_8023s - decode an IEEE 802.11n A-MSDU frame
  *
- * Decode an IEEE 802.11n A-MSDU frame and convert it to a list of
- * 802.3 frames. The @list will be empty if the decode fails. The
- * @skb is consumed after the function returns.
+ * Decode an IEEE 802.11 A-MSDU and convert it to a list of 802.3 frames.
+ * The @list will be empty if the decode fails. The @skb must be fully
+ * header-less before being passed in here; it is freed in this function.
  *
- * @skb: The input IEEE 802.11n A-MSDU frame.
+ * @skb: The input A-MSDU frame without any headers.
  * @list: The output list of 802.3 frames. It must be allocated and
  *	initialized by by the caller.
  * @addr: The device MAC address.
  * @iftype: The device interface type.
  * @extra_headroom: The hardware extra headroom for SKBs in the @list.
- * @has_80211_header: Set it true if SKB is with IEEE 802.11 header.
+ * @check_da: DA to check in the inner ethernet header, or NULL
+ * @check_sa: SA to check in the inner ethernet header, or NULL
  */
 void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list,
 			      const u8 *addr, enum nl80211_iftype iftype,
 			      const unsigned int extra_headroom,
-			      bool has_80211_header);
+			      const u8 *check_da, const u8 *check_sa);
 
 /**
  * cfg80211_classify8021d - determine the 802.1p/1d tag for a data frame
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 515352c6280a..b0576cb2ab25 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -190,8 +190,8 @@ struct inet6_dev {
 	__u32			if_flags;
 	int			dead;
 
+	u32			desync_factor;
 	u8			rndid[8];
-	struct timer_list	regen_timer;
 	struct list_head	tempaddr_list;
 
 	struct in6_addr		token;
diff --git a/include/net/ip.h b/include/net/ip.h
index bc43c0fcae12..5413883ac47f 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -38,7 +38,7 @@ struct sock;
 struct inet_skb_parm {
 	int			iif;
 	struct ip_options	opt;		/* Compiled IP options		*/
-	unsigned char		flags;
+	u16			flags;
 
 #define IPSKB_FORWARDED		BIT(0)
 #define IPSKB_XFRM_TUNNEL_SIZE	BIT(1)
@@ -48,10 +48,16 @@ struct inet_skb_parm {
 #define IPSKB_DOREDIRECT	BIT(5)
 #define IPSKB_FRAG_PMTU		BIT(6)
 #define IPSKB_FRAG_SEGS		BIT(7)
+#define IPSKB_L3SLAVE		BIT(8)
 
 	u16			frag_max_size;
 };
 
+static inline bool ipv4_l3mdev_skb(u16 flags)
+{
+	return !!(flags & IPSKB_L3SLAVE);
+}
+
 static inline unsigned int ip_hdrlen(const struct sk_buff *skb)
 {
 	return ip_hdr(skb)->ihl * 4;
@@ -572,7 +578,7 @@ int ip_options_rcv_srr(struct sk_buff *skb);
  */
 
 void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb);
-void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int offset);
+void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int tlen, int offset);
 int ip_cmsg_send(struct sock *sk, struct msghdr *msg,
 		 struct ipcm_cookie *ipc, bool allow_ipv6);
 int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
@@ -594,7 +600,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport,
 
 static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
 {
-	ip_cmsg_recv_offset(msg, skb, 0);
+	ip_cmsg_recv_offset(msg, skb, 0, 0);
 }
 
 bool icmp_global_allow(void);
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index fb961a576abe..a74e2aa40ef4 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -230,6 +230,8 @@ struct fib6_table {
 	rwlock_t		tb6_lock;
 	struct fib6_node	tb6_root;
 	struct inet_peer_base	tb6_peers;
+	unsigned int		flags;
+#define RT6_TABLE_HAS_DFLT_ROUTER	BIT(0)
 };
 
 #define RT6_TABLE_UNSPEC	RT_TABLE_UNSPEC
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index e0cd318d5103..f83e78d071a3 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -32,6 +32,7 @@ struct route_info {
 #define RT6_LOOKUP_F_SRCPREF_TMP	0x00000008
 #define RT6_LOOKUP_F_SRCPREF_PUBLIC	0x00000010
 #define RT6_LOOKUP_F_SRCPREF_COA	0x00000020
+#define RT6_LOOKUP_F_IGNORE_LINKSTATE	0x00000040
 
 /* We do not (yet ?) support IPv6 jumbograms (RFC 2675)
  * Unlike IPv4, hdr->seg_len doesn't include the IPv6 header
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index b9b24abd9103..5345d358a510 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -811,14 +811,18 @@ enum mac80211_rate_control_flags {
  * in the control information, and it will be filled by the rate
  * control algorithm according to what should be sent. For example,
  * if this array contains, in the format { <idx>, <count> } the
- * information
+ * information::
+ *
  *    { 3, 2 }, { 2, 2 }, { 1, 4 }, { -1, 0 }, { -1, 0 }
+ *
  * then this means that the frame should be transmitted
  * up to twice at rate 3, up to twice at rate 2, and up to four
  * times at rate 1 if it doesn't get acknowledged. Say it gets
  * acknowledged by the peer after the fifth attempt, the status
- * information should then contain
+ * information should then contain::
+ *
  *   { 3, 2 }, { 2, 2 }, { 1, 1 }, { -1, 0 } ...
+ *
  * since it was transmitted twice at rate 3, twice at rate 2
  * and once at rate 1 after which we received an acknowledgement.
  */
@@ -1168,8 +1172,8 @@ enum mac80211_rx_vht_flags {
  * @rate_idx: index of data rate into band's supported rates or MCS index if
  *	HT or VHT is used (%RX_FLAG_HT/%RX_FLAG_VHT)
  * @vht_nss: number of streams (VHT only)
- * @flag: %RX_FLAG_*
- * @vht_flag: %RX_VHT_FLAG_*
+ * @flag: %RX_FLAG_\*
+ * @vht_flag: %RX_VHT_FLAG_\*
  * @rx_flags: internal RX flags for mac80211
  * @ampdu_reference: A-MPDU reference number, must be a different value for
  *	each A-MPDU but the same for each subframe within one A-MPDU
@@ -1432,7 +1436,7 @@ enum ieee80211_vif_flags {
  * @probe_req_reg: probe requests should be reported to mac80211 for this
  *	interface.
  * @drv_priv: data area for driver use, will always be aligned to
- *	sizeof(void *).
+ *	sizeof(void \*).
  * @txq: the multicast data TX queue (if driver uses the TXQ abstraction)
  */
 struct ieee80211_vif {
@@ -1743,7 +1747,7 @@ struct ieee80211_sta_rates {
  * @wme: indicates whether the STA supports QoS/WME (if local devices does,
  *	otherwise always false)
  * @drv_priv: data area for driver use, will always be aligned to
- *	sizeof(void *), size is determined in hw information.
+ *	sizeof(void \*), size is determined in hw information.
  * @uapsd_queues: bitmap of queues configured for uapsd. Only valid
  *	if wme is supported. The bits order is like in
  *	IEEE80211_WMM_IE_STA_QOSINFO_AC_*.
@@ -2152,12 +2156,12 @@ enum ieee80211_hw_flags {
  *
  * @radiotap_mcs_details: lists which MCS information can the HW
  *	reports, by default it is set to _MCS, _GI and _BW but doesn't
- *	include _FMT. Use %IEEE80211_RADIOTAP_MCS_HAVE_* values, only
+ *	include _FMT. Use %IEEE80211_RADIOTAP_MCS_HAVE_\* values, only
  *	adding _BW is supported today.
  *
  * @radiotap_vht_details: lists which VHT MCS information the HW reports,
  *	the default is _GI | _BANDWIDTH.
- *	Use the %IEEE80211_RADIOTAP_VHT_KNOWN_* values.
+ *	Use the %IEEE80211_RADIOTAP_VHT_KNOWN_\* values.
  *
  * @radiotap_timestamp: Information for the radiotap timestamp field; if the
  *	'units_pos' member is set to a non-negative value it must be set to
@@ -2492,6 +2496,7 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb);
  * in the software stack cares about, we will, in the future, have mac80211
  * tell the driver which information elements are interesting in the sense
  * that we want to see changes in them. This will include
+ *
  *  - a list of information element IDs
  *  - a list of OUIs for the vendor information element
  *
diff --git a/include/net/sock.h b/include/net/sock.h
index 276489553338..f13ac87a8015 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -252,6 +252,7 @@ struct sock_common {
   *	@sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler)
   *	@sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE)
   *	@sk_sndbuf: size of send buffer in bytes
+  *	@sk_padding: unused element for alignment
   *	@sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets
   *	@sk_no_check_rx: allow zero checksum in RX packets
   *	@sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
@@ -302,7 +303,8 @@ struct sock_common {
   *	@sk_backlog_rcv: callback to process the backlog
   *	@sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
   *	@sk_reuseport_cb: reuseport group container
- */
+  *	@sk_rcu: used during RCU grace period
+  */
 struct sock {
 	/*
 	 * Now struct inet_timewait_sock also uses sock_common, so please just
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f83b7f220a65..5b82d4d94834 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -794,12 +794,23 @@ struct tcp_skb_cb {
  */
 static inline int tcp_v6_iif(const struct sk_buff *skb)
 {
-	bool l3_slave = skb_l3mdev_slave(TCP_SKB_CB(skb)->header.h6.flags);
+	bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);
 
 	return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif;
 }
 #endif
 
+/* TCP_SKB_CB reference means this can not be used from early demux */
+static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+	if (!net->ipv4.sysctl_tcp_l3mdev_accept &&
+	    ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags))
+		return true;
+#endif
+	return false;
+}
+
 /* Due to TSO, an SKB can be composed of multiple actual
  * packets.  To keep these tracked properly, we use this.
  */
diff --git a/include/net/udp.h b/include/net/udp.h
index 18f1e6b91927..6134f37ba3ab 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -262,6 +262,7 @@ void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst);
 int udp_rcv(struct sk_buff *skb);
 int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
 int udp_init_sock(struct sock *sk);
+int __udp_disconnect(struct sock *sk, int flags);
 int udp_disconnect(struct sock *sk, int flags);
 unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait);
 struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 0255613a54a4..308adc4154f4 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -225,9 +225,9 @@ struct vxlan_config {
 struct vxlan_dev {
 	struct hlist_node hlist;	/* vni hash table */
 	struct list_head  next;		/* vxlan's per namespace list */
-	struct vxlan_sock *vn4_sock;	/* listening socket for IPv4 */
+	struct vxlan_sock __rcu *vn4_sock;	/* listening socket for IPv4 */
 #if IS_ENABLED(CONFIG_IPV6)
-	struct vxlan_sock *vn6_sock;	/* listening socket for IPv6 */
+	struct vxlan_sock __rcu *vn6_sock;	/* listening socket for IPv6 */
 #endif
 	struct net_device *dev;
 	struct net	  *net;		/* netns for packet i/o */
diff --git a/include/soc/fsl/bman.h b/include/soc/fsl/bman.h
new file mode 100644
index 000000000000..eaaf56df4086
--- /dev/null
+++ b/include/soc/fsl/bman.h
@@ -0,0 +1,129 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	 notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __FSL_BMAN_H
+#define __FSL_BMAN_H
+
+/* wrapper for 48-bit buffers */
+struct bm_buffer {
+	union {
+		struct {
+			__be16 bpid; /* hi 8-bits reserved */
+			__be16 hi; /* High 16-bits of 48-bit address */
+			__be32 lo; /* Low 32-bits of 48-bit address */
+		};
+		__be64 data;
+	};
+} __aligned(8);
+/*
+ * Restore the 48 bit address previously stored in BMan
+ * hardware pools as a dma_addr_t
+ */
+static inline dma_addr_t bm_buf_addr(const struct bm_buffer *buf)
+{
+	return be64_to_cpu(buf->data) & 0xffffffffffffLLU;
+}
+
+static inline u64 bm_buffer_get64(const struct bm_buffer *buf)
+{
+	return be64_to_cpu(buf->data) & 0xffffffffffffLLU;
+}
+
+static inline void bm_buffer_set64(struct bm_buffer *buf, u64 addr)
+{
+	buf->hi = cpu_to_be16(upper_32_bits(addr));
+	buf->lo = cpu_to_be32(lower_32_bits(addr));
+}
+
+static inline u8 bm_buffer_get_bpid(const struct bm_buffer *buf)
+{
+	return be16_to_cpu(buf->bpid) & 0xff;
+}
+
+static inline void bm_buffer_set_bpid(struct bm_buffer *buf, int bpid)
+{
+	buf->bpid = cpu_to_be16(bpid & 0xff);
+}
+
+/* Managed portal, high-level i/face */
+
+/* Portal and Buffer Pools */
+struct bman_portal;
+struct bman_pool;
+
+#define BM_POOL_MAX		64 /* max # of buffer pools */
+
+/**
+ * bman_new_pool - Allocates a Buffer Pool object
+ *
+ * Creates a pool object, and returns a reference to it or NULL on error.
+ */
+struct bman_pool *bman_new_pool(void);
+
+/**
+ * bman_free_pool - Deallocates a Buffer Pool object
+ * @pool: the pool object to release
+ */
+void bman_free_pool(struct bman_pool *pool);
+
+/**
+ * bman_get_bpid - Returns a pool object's BPID.
+ * @pool: the pool object
+ *
+ * The returned value is the index of the encapsulated buffer pool,
+ * in the range of [0, @BM_POOL_MAX-1].
+ */
+int bman_get_bpid(const struct bman_pool *pool);
+
+/**
+ * bman_release - Release buffer(s) to the buffer pool
+ * @pool: the buffer pool object to release to
+ * @bufs: an array of buffers to release
+ * @num: the number of buffers in @bufs (1-8)
+ *
+ * Adds the given buffers to RCR entries. If the RCR ring is unresponsive,
+ * the function will return -ETIMEDOUT. Otherwise, it returns zero.
+ */
+int bman_release(struct bman_pool *pool, const struct bm_buffer *bufs, u8 num);
+
+/**
+ * bman_acquire - Acquire buffer(s) from a buffer pool
+ * @pool: the buffer pool object to acquire from
+ * @bufs: array for storing the acquired buffers
+ * @num: the number of buffers desired (@bufs is at least this big)
+ *
+ * Issues an "Acquire" command via the portal's management command interface.
+ * The return value will be the number of buffers obtained from the pool, or a
+ * negative error code if a h/w error or pool starvation was encountered. In
+ * the latter case, the content of @bufs is undefined.
+ */
+int bman_acquire(struct bman_pool *pool, struct bm_buffer *bufs, u8 num);
+
+#endif	/* __FSL_BMAN_H */
diff --git a/include/soc/fsl/qman.h b/include/soc/fsl/qman.h
new file mode 100644
index 000000000000..37f3eb001a16
--- /dev/null
+++ b/include/soc/fsl/qman.h
@@ -0,0 +1,1074 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	 notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __FSL_QMAN_H
+#define __FSL_QMAN_H
+
+#include <linux/bitops.h>
+
+/* Hardware constants */
+#define QM_CHANNEL_SWPORTAL0 0
+#define QMAN_CHANNEL_POOL1 0x21
+#define QMAN_CHANNEL_POOL1_REV3 0x401
+extern u16 qm_channel_pool1;
+
+/* Portal processing (interrupt) sources */
+#define QM_PIRQ_CSCI	0x00100000	/* Congestion State Change */
+#define QM_PIRQ_EQCI	0x00080000	/* Enqueue Command Committed */
+#define QM_PIRQ_EQRI	0x00040000	/* EQCR Ring (below threshold) */
+#define QM_PIRQ_DQRI	0x00020000	/* DQRR Ring (non-empty) */
+#define QM_PIRQ_MRI	0x00010000	/* MR Ring (non-empty) */
+/*
+ * This mask contains all the interrupt sources that need handling except DQRI,
+ * ie. that if present should trigger slow-path processing.
+ */
+#define QM_PIRQ_SLOW	(QM_PIRQ_CSCI | QM_PIRQ_EQCI | QM_PIRQ_EQRI | \
+			 QM_PIRQ_MRI)
+
+/* For qman_static_dequeue_*** APIs */
+#define QM_SDQCR_CHANNELS_POOL_MASK	0x00007fff
+/* for n in [1,15] */
+#define QM_SDQCR_CHANNELS_POOL(n)	(0x00008000 >> (n))
+/* for conversion from n of qm_channel */
+static inline u32 QM_SDQCR_CHANNELS_POOL_CONV(u16 channel)
+{
+	return QM_SDQCR_CHANNELS_POOL(channel + 1 - qm_channel_pool1);
+}
+
+/* --- QMan data structures (and associated constants) --- */
+
+/* "Frame Descriptor (FD)" */
+struct qm_fd {
+	union {
+		struct {
+			u8 cfg8b_w1;
+			u8 bpid;	/* Buffer Pool ID */
+			u8 cfg8b_w3;
+			u8 addr_hi;	/* high 8-bits of 40-bit address */
+			__be32 addr_lo;	/* low 32-bits of 40-bit address */
+		} __packed;
+		__be64 data;
+	};
+	__be32 cfg;	/* format, offset, length / congestion */
+	union {
+		__be32 cmd;
+		__be32 status;
+	};
+} __aligned(8);
+
+#define QM_FD_FORMAT_SG		BIT(31)
+#define QM_FD_FORMAT_LONG	BIT(30)
+#define QM_FD_FORMAT_COMPOUND	BIT(29)
+#define QM_FD_FORMAT_MASK	GENMASK(31, 29)
+#define QM_FD_OFF_SHIFT		20
+#define QM_FD_OFF_MASK		GENMASK(28, 20)
+#define QM_FD_LEN_MASK		GENMASK(19, 0)
+#define QM_FD_LEN_BIG_MASK	GENMASK(28, 0)
+
+enum qm_fd_format {
+	/*
+	 * 'contig' implies a contiguous buffer, whereas 'sg' implies a
+	 * scatter-gather table. 'big' implies a 29-bit length with no offset
+	 * field, otherwise length is 20-bit and offset is 9-bit. 'compound'
+	 * implies a s/g-like table, where each entry itself represents a frame
+	 * (contiguous or scatter-gather) and the 29-bit "length" is
+	 * interpreted purely for congestion calculations, ie. a "congestion
+	 * weight".
+	 */
+	qm_fd_contig = 0,
+	qm_fd_contig_big = QM_FD_FORMAT_LONG,
+	qm_fd_sg = QM_FD_FORMAT_SG,
+	qm_fd_sg_big = QM_FD_FORMAT_SG | QM_FD_FORMAT_LONG,
+	qm_fd_compound = QM_FD_FORMAT_COMPOUND
+};
+
+static inline dma_addr_t qm_fd_addr(const struct qm_fd *fd)
+{
+	return be64_to_cpu(fd->data) & 0xffffffffffLLU;
+}
+
+static inline u64 qm_fd_addr_get64(const struct qm_fd *fd)
+{
+	return be64_to_cpu(fd->data) & 0xffffffffffLLU;
+}
+
+static inline void qm_fd_addr_set64(struct qm_fd *fd, u64 addr)
+{
+	fd->addr_hi = upper_32_bits(addr);
+	fd->addr_lo = cpu_to_be32(lower_32_bits(addr));
+}
+
+/*
+ * The 'format' field indicates the interpretation of the remaining
+ * 29 bits of the 32-bit word.
+ * If 'format' is _contig or _sg, 20b length and 9b offset.
+ * If 'format' is _contig_big or _sg_big, 29b length.
+ * If 'format' is _compound, 29b "congestion weight".
+ */
+static inline enum qm_fd_format qm_fd_get_format(const struct qm_fd *fd)
+{
+	return be32_to_cpu(fd->cfg) & QM_FD_FORMAT_MASK;
+}
+
+static inline int qm_fd_get_offset(const struct qm_fd *fd)
+{
+	return (be32_to_cpu(fd->cfg) & QM_FD_OFF_MASK) >> QM_FD_OFF_SHIFT;
+}
+
+static inline int qm_fd_get_length(const struct qm_fd *fd)
+{
+	return be32_to_cpu(fd->cfg) & QM_FD_LEN_MASK;
+}
+
+static inline int qm_fd_get_len_big(const struct qm_fd *fd)
+{
+	return be32_to_cpu(fd->cfg) & QM_FD_LEN_BIG_MASK;
+}
+
+static inline void qm_fd_set_param(struct qm_fd *fd, enum qm_fd_format fmt,
+				   int off, int len)
+{
+	fd->cfg = cpu_to_be32(fmt | (len & QM_FD_LEN_BIG_MASK) |
+			      ((off << QM_FD_OFF_SHIFT) & QM_FD_OFF_MASK));
+}
+
+#define qm_fd_set_contig(fd, off, len) \
+	qm_fd_set_param(fd, qm_fd_contig, off, len)
+#define qm_fd_set_sg(fd, off, len) qm_fd_set_param(fd, qm_fd_sg, off, len)
+#define qm_fd_set_contig_big(fd, len) \
+	qm_fd_set_param(fd, qm_fd_contig_big, 0, len)
+#define qm_fd_set_sg_big(fd, len) qm_fd_set_param(fd, qm_fd_sg_big, 0, len)
+
+static inline void qm_fd_clear_fd(struct qm_fd *fd)
+{
+	fd->data = 0;
+	fd->cfg = 0;
+	fd->cmd = 0;
+}
+
+/* Scatter/Gather table entry */
+struct qm_sg_entry {
+	union {
+		struct {
+			u8 __reserved1[3];
+			u8 addr_hi;	/* high 8-bits of 40-bit address */
+			__be32 addr_lo;	/* low 32-bits of 40-bit address */
+		};
+		__be64 data;
+	};
+	__be32 cfg;	/* E bit, F bit, length */
+	u8 __reserved2;
+	u8 bpid;
+	__be16 offset; /* 13-bit, _res[13-15]*/
+} __packed;
+
+#define QM_SG_LEN_MASK	GENMASK(29, 0)
+#define QM_SG_OFF_MASK	GENMASK(12, 0)
+#define QM_SG_FIN	BIT(30)
+#define QM_SG_EXT	BIT(31)
+
+static inline dma_addr_t qm_sg_addr(const struct qm_sg_entry *sg)
+{
+	return be64_to_cpu(sg->data) & 0xffffffffffLLU;
+}
+
+static inline u64 qm_sg_entry_get64(const struct qm_sg_entry *sg)
+{
+	return be64_to_cpu(sg->data) & 0xffffffffffLLU;
+}
+
+static inline void qm_sg_entry_set64(struct qm_sg_entry *sg, u64 addr)
+{
+	sg->addr_hi = upper_32_bits(addr);
+	sg->addr_lo = cpu_to_be32(lower_32_bits(addr));
+}
+
+static inline bool qm_sg_entry_is_final(const struct qm_sg_entry *sg)
+{
+	return be32_to_cpu(sg->cfg) & QM_SG_FIN;
+}
+
+static inline bool qm_sg_entry_is_ext(const struct qm_sg_entry *sg)
+{
+	return be32_to_cpu(sg->cfg) & QM_SG_EXT;
+}
+
+static inline int qm_sg_entry_get_len(const struct qm_sg_entry *sg)
+{
+	return be32_to_cpu(sg->cfg) & QM_SG_LEN_MASK;
+}
+
+static inline void qm_sg_entry_set_len(struct qm_sg_entry *sg, int len)
+{
+	sg->cfg = cpu_to_be32(len & QM_SG_LEN_MASK);
+}
+
+static inline void qm_sg_entry_set_f(struct qm_sg_entry *sg, int len)
+{
+	sg->cfg = cpu_to_be32(QM_SG_FIN | (len & QM_SG_LEN_MASK));
+}
+
+static inline int qm_sg_entry_get_off(const struct qm_sg_entry *sg)
+{
+	return be32_to_cpu(sg->offset) & QM_SG_OFF_MASK;
+}
+
+/* "Frame Dequeue Response" */
+struct qm_dqrr_entry {
+	u8 verb;
+	u8 stat;
+	u16 seqnum;	/* 15-bit */
+	u8 tok;
+	u8 __reserved2[3];
+	u32 fqid;	/* 24-bit */
+	u32 contextB;
+	struct qm_fd fd;
+	u8 __reserved4[32];
+} __packed;
+#define QM_DQRR_VERB_VBIT		0x80
+#define QM_DQRR_VERB_MASK		0x7f	/* where the verb contains; */
+#define QM_DQRR_VERB_FRAME_DEQUEUE	0x60	/* "this format" */
+#define QM_DQRR_STAT_FQ_EMPTY		0x80	/* FQ empty */
+#define QM_DQRR_STAT_FQ_HELDACTIVE	0x40	/* FQ held active */
+#define QM_DQRR_STAT_FQ_FORCEELIGIBLE	0x20	/* FQ was force-eligible'd */
+#define QM_DQRR_STAT_FD_VALID		0x10	/* has a non-NULL FD */
+#define QM_DQRR_STAT_UNSCHEDULED	0x02	/* Unscheduled dequeue */
+#define QM_DQRR_STAT_DQCR_EXPIRED	0x01	/* VDQCR or PDQCR expired*/
+
+/* "ERN Message Response" */
+/* "FQ State Change Notification" */
+union qm_mr_entry {
+	struct {
+		u8 verb;
+		u8 __reserved[63];
+	};
+	struct {
+		u8 verb;
+		u8 dca;
+		u16 seqnum;
+		u8 rc;		/* Rej Code: 8-bit */
+		u8 orp_hi;	/* ORP: 24-bit */
+		u16 orp_lo;
+		u32 fqid;	/* 24-bit */
+		u32 tag;
+		struct qm_fd fd;
+		u8 __reserved1[32];
+	} __packed ern;
+	struct {
+		u8 verb;
+		u8 fqs;		/* Frame Queue Status */
+		u8 __reserved1[6];
+		u32 fqid;	/* 24-bit */
+		u32 contextB;
+		u8 __reserved2[48];
+	} __packed fq;		/* FQRN/FQRNI/FQRL/FQPN */
+};
+#define QM_MR_VERB_VBIT			0x80
+/*
+ * ERNs originating from direct-connect portals ("dcern") use 0x20 as a verb
+ * which would be invalid as a s/w enqueue verb. A s/w ERN can be distinguished
+ * from the other MR types by noting if the 0x20 bit is unset.
+ */
+#define QM_MR_VERB_TYPE_MASK		0x27
+#define QM_MR_VERB_DC_ERN		0x20
+#define QM_MR_VERB_FQRN			0x21
+#define QM_MR_VERB_FQRNI		0x22
+#define QM_MR_VERB_FQRL			0x23
+#define QM_MR_VERB_FQPN			0x24
+#define QM_MR_RC_MASK			0xf0	/* contains one of; */
+#define QM_MR_RC_CGR_TAILDROP		0x00
+#define QM_MR_RC_WRED			0x10
+#define QM_MR_RC_ERROR			0x20
+#define QM_MR_RC_ORPWINDOW_EARLY	0x30
+#define QM_MR_RC_ORPWINDOW_LATE		0x40
+#define QM_MR_RC_FQ_TAILDROP		0x50
+#define QM_MR_RC_ORPWINDOW_RETIRED	0x60
+#define QM_MR_RC_ORP_ZERO		0x70
+#define QM_MR_FQS_ORLPRESENT		0x02	/* ORL fragments to come */
+#define QM_MR_FQS_NOTEMPTY		0x01	/* FQ has enqueued frames */
+
+/*
+ * An identical structure of FQD fields is present in the "Init FQ" command and
+ * the "Query FQ" result, it's suctioned out into the "struct qm_fqd" type.
+ * Within that, the 'stashing' and 'taildrop' pieces are also factored out, the
+ * latter has two inlines to assist with converting to/from the mant+exp
+ * representation.
+ */
+struct qm_fqd_stashing {
+	/* See QM_STASHING_EXCL_<...> */
+	u8 exclusive;
+	/* Numbers of cachelines */
+	u8 cl; /* _res[6-7], as[4-5], ds[2-3], cs[0-1] */
+};
+
+struct qm_fqd_oac {
+	/* "Overhead Accounting Control", see QM_OAC_<...> */
+	u8 oac; /* oac[6-7], _res[0-5] */
+	/* Two's-complement value (-128 to +127) */
+	s8 oal; /* "Overhead Accounting Length" */
+};
+
+struct qm_fqd {
+	/* _res[6-7], orprws[3-5], oa[2], olws[0-1] */
+	u8 orpc;
+	u8 cgid;
+	__be16 fq_ctrl;	/* See QM_FQCTRL_<...> */
+	__be16 dest_wq;	/* channel[3-15], wq[0-2] */
+	__be16 ics_cred; /* 15-bit */
+	/*
+	 * For "Initialize Frame Queue" commands, the write-enable mask
+	 * determines whether 'td' or 'oac_init' is observed. For query
+	 * commands, this field is always 'td', and 'oac_query' (below) reflects
+	 * the Overhead ACcounting values.
+	 */
+	union {
+		__be16 td; /* "Taildrop": _res[13-15], mant[5-12], exp[0-4] */
+		struct qm_fqd_oac oac_init;
+	};
+	__be32 context_b;
+	union {
+		/* Treat it as 64-bit opaque */
+		__be64 opaque;
+		struct {
+			__be32 hi;
+			__be32 lo;
+		};
+		/* Treat it as s/w portal stashing config */
+		/* see "FQD Context_A field used for [...]" */
+		struct {
+			struct qm_fqd_stashing stashing;
+			/*
+			 * 48-bit address of FQ context to
+			 * stash, must be cacheline-aligned
+			 */
+			__be16 context_hi;
+			__be32 context_lo;
+		} __packed;
+	} context_a;
+	struct qm_fqd_oac oac_query;
+} __packed;
+
+#define QM_FQD_CHAN_OFF		3
+#define QM_FQD_WQ_MASK		GENMASK(2, 0)
+#define QM_FQD_TD_EXP_MASK	GENMASK(4, 0)
+#define QM_FQD_TD_MANT_OFF	5
+#define QM_FQD_TD_MANT_MASK	GENMASK(12, 5)
+#define QM_FQD_TD_MAX		0xe0000000
+#define QM_FQD_TD_MANT_MAX	0xff
+#define QM_FQD_OAC_OFF		6
+#define QM_FQD_AS_OFF		4
+#define QM_FQD_DS_OFF		2
+#define QM_FQD_XS_MASK		0x3
+
+/* 64-bit converters for context_hi/lo */
+static inline u64 qm_fqd_stashing_get64(const struct qm_fqd *fqd)
+{
+	return be64_to_cpu(fqd->context_a.opaque) & 0xffffffffffffULL;
+}
+
+static inline dma_addr_t qm_fqd_stashing_addr(const struct qm_fqd *fqd)
+{
+	return be64_to_cpu(fqd->context_a.opaque) & 0xffffffffffffULL;
+}
+
+static inline u64 qm_fqd_context_a_get64(const struct qm_fqd *fqd)
+{
+	return qm_fqd_stashing_get64(fqd);
+}
+
+static inline void qm_fqd_stashing_set64(struct qm_fqd *fqd, u64 addr)
+{
+	fqd->context_a.context_hi = upper_32_bits(addr);
+	fqd->context_a.context_lo = lower_32_bits(addr);
+}
+
+static inline void qm_fqd_context_a_set64(struct qm_fqd *fqd, u64 addr)
+{
+	fqd->context_a.hi = cpu_to_be16(upper_32_bits(addr));
+	fqd->context_a.lo = cpu_to_be32(lower_32_bits(addr));
+}
+
+/* convert a threshold value into mant+exp representation */
+static inline int qm_fqd_set_taildrop(struct qm_fqd *fqd, u32 val,
+				      int roundup)
+{
+	u32 e = 0;
+	int td, oddbit = 0;
+
+	if (val > QM_FQD_TD_MAX)
+		return -ERANGE;
+
+	while (val > QM_FQD_TD_MANT_MAX) {
+		oddbit = val & 1;
+		val >>= 1;
+		e++;
+		if (roundup && oddbit)
+			val++;
+	}
+
+	td = (val << QM_FQD_TD_MANT_OFF) & QM_FQD_TD_MANT_MASK;
+	td |= (e & QM_FQD_TD_EXP_MASK);
+	fqd->td = cpu_to_be16(td);
+	return 0;
+}
+/* and the other direction */
+static inline int qm_fqd_get_taildrop(const struct qm_fqd *fqd)
+{
+	int td = be16_to_cpu(fqd->td);
+
+	return ((td & QM_FQD_TD_MANT_MASK) >> QM_FQD_TD_MANT_OFF)
+		<< (td & QM_FQD_TD_EXP_MASK);
+}
+
+static inline void qm_fqd_set_stashing(struct qm_fqd *fqd, u8 as, u8 ds, u8 cs)
+{
+	struct qm_fqd_stashing *st = &fqd->context_a.stashing;
+
+	st->cl = ((as & QM_FQD_XS_MASK) << QM_FQD_AS_OFF) |
+		 ((ds & QM_FQD_XS_MASK) << QM_FQD_DS_OFF) |
+		 (cs & QM_FQD_XS_MASK);
+}
+
+static inline u8 qm_fqd_get_stashing(const struct qm_fqd *fqd)
+{
+	return fqd->context_a.stashing.cl;
+}
+
+static inline void qm_fqd_set_oac(struct qm_fqd *fqd, u8 val)
+{
+	fqd->oac_init.oac = val << QM_FQD_OAC_OFF;
+}
+
+static inline void qm_fqd_set_oal(struct qm_fqd *fqd, s8 val)
+{
+	fqd->oac_init.oal = val;
+}
+
+static inline void qm_fqd_set_destwq(struct qm_fqd *fqd, int ch, int wq)
+{
+	fqd->dest_wq = cpu_to_be16((ch << QM_FQD_CHAN_OFF) |
+				   (wq & QM_FQD_WQ_MASK));
+}
+
+static inline int qm_fqd_get_chan(const struct qm_fqd *fqd)
+{
+	return be16_to_cpu(fqd->dest_wq) >> QM_FQD_CHAN_OFF;
+}
+
+static inline int qm_fqd_get_wq(const struct qm_fqd *fqd)
+{
+	return be16_to_cpu(fqd->dest_wq) & QM_FQD_WQ_MASK;
+}
+
+/* See "Frame Queue Descriptor (FQD)" */
+/* Frame Queue Descriptor (FQD) field 'fq_ctrl' uses these constants */
+#define QM_FQCTRL_MASK		0x07ff	/* 'fq_ctrl' flags; */
+#define QM_FQCTRL_CGE		0x0400	/* Congestion Group Enable */
+#define QM_FQCTRL_TDE		0x0200	/* Tail-Drop Enable */
+#define QM_FQCTRL_CTXASTASHING	0x0080	/* Context-A stashing */
+#define QM_FQCTRL_CPCSTASH	0x0040	/* CPC Stash Enable */
+#define QM_FQCTRL_FORCESFDR	0x0008	/* High-priority SFDRs */
+#define QM_FQCTRL_AVOIDBLOCK	0x0004	/* Don't block active */
+#define QM_FQCTRL_HOLDACTIVE	0x0002	/* Hold active in portal */
+#define QM_FQCTRL_PREFERINCACHE	0x0001	/* Aggressively cache FQD */
+#define QM_FQCTRL_LOCKINCACHE	QM_FQCTRL_PREFERINCACHE /* older naming */
+
+/* See "FQD Context_A field used for [...] */
+/* Frame Queue Descriptor (FQD) field 'CONTEXT_A' uses these constants */
+#define QM_STASHING_EXCL_ANNOTATION	0x04
+#define QM_STASHING_EXCL_DATA		0x02
+#define QM_STASHING_EXCL_CTX		0x01
+
+/* See "Intra Class Scheduling" */
+/* FQD field 'OAC' (Overhead ACcounting) uses these constants */
+#define QM_OAC_ICS		0x2 /* Accounting for Intra-Class Scheduling */
+#define QM_OAC_CG		0x1 /* Accounting for Congestion Groups */
+
+/*
+ * This struct represents the 32-bit "WR_PARM_[GYR]" parameters in CGR fields
+ * and associated commands/responses. The WRED parameters are calculated from
+ * these fields as follows;
+ *   MaxTH = MA * (2 ^ Mn)
+ *   Slope = SA / (2 ^ Sn)
+ *    MaxP = 4 * (Pn + 1)
+ */
+struct qm_cgr_wr_parm {
+	/* MA[24-31], Mn[19-23], SA[12-18], Sn[6-11], Pn[0-5] */
+	u32 word;
+};
+/*
+ * This struct represents the 13-bit "CS_THRES" CGR field. In the corresponding
+ * management commands, this is padded to a 16-bit structure field, so that's
+ * how we represent it here. The congestion state threshold is calculated from
+ * these fields as follows;
+ *   CS threshold = TA * (2 ^ Tn)
+ */
+struct qm_cgr_cs_thres {
+	/* _res[13-15], TA[5-12], Tn[0-4] */
+	u16 word;
+};
+/*
+ * This identical structure of CGR fields is present in the "Init/Modify CGR"
+ * commands and the "Query CGR" result. It's suctioned out here into its own
+ * struct.
+ */
+struct __qm_mc_cgr {
+	struct qm_cgr_wr_parm wr_parm_g;
+	struct qm_cgr_wr_parm wr_parm_y;
+	struct qm_cgr_wr_parm wr_parm_r;
+	u8 wr_en_g;	/* boolean, use QM_CGR_EN */
+	u8 wr_en_y;	/* boolean, use QM_CGR_EN */
+	u8 wr_en_r;	/* boolean, use QM_CGR_EN */
+	u8 cscn_en;	/* boolean, use QM_CGR_EN */
+	union {
+		struct {
+			u16 cscn_targ_upd_ctrl; /* use QM_CSCN_TARG_UDP_ */
+			u16 cscn_targ_dcp_low;	/* CSCN_TARG_DCP low-16bits */
+		};
+		u32 cscn_targ;	/* use QM_CGR_TARG_* */
+	};
+	u8 cstd_en;	/* boolean, use QM_CGR_EN */
+	u8 cs;		/* boolean, only used in query response */
+	struct qm_cgr_cs_thres cs_thres; /* use qm_cgr_cs_thres_set64() */
+	u8 mode;	/* QMAN_CGR_MODE_FRAME not supported in rev1.0 */
+} __packed;
+#define QM_CGR_EN		0x01 /* For wr_en_*, cscn_en, cstd_en */
+#define QM_CGR_TARG_UDP_CTRL_WRITE_BIT	0x8000 /* value written to portal bit*/
+#define QM_CGR_TARG_UDP_CTRL_DCP	0x4000 /* 0: SWP, 1: DCP */
+#define QM_CGR_TARG_PORTAL(n)	(0x80000000 >> (n)) /* s/w portal, 0-9 */
+#define QM_CGR_TARG_FMAN0	0x00200000 /* direct-connect portal: fman0 */
+#define QM_CGR_TARG_FMAN1	0x00100000 /*			   : fman1 */
+/* Convert CGR thresholds to/from "cs_thres" format */
+static inline u64 qm_cgr_cs_thres_get64(const struct qm_cgr_cs_thres *th)
+{
+	return ((th->word >> 5) & 0xff) << (th->word & 0x1f);
+}
+
+static inline int qm_cgr_cs_thres_set64(struct qm_cgr_cs_thres *th, u64 val,
+					int roundup)
+{
+	u32 e = 0;
+	int oddbit = 0;
+
+	while (val > 0xff) {
+		oddbit = val & 1;
+		val >>= 1;
+		e++;
+		if (roundup && oddbit)
+			val++;
+	}
+	th->word = ((val & 0xff) << 5) | (e & 0x1f);
+	return 0;
+}
+
+/* "Initialize FQ" */
+struct qm_mcc_initfq {
+	u8 __reserved1[2];
+	u16 we_mask;	/* Write Enable Mask */
+	u32 fqid;	/* 24-bit */
+	u16 count;	/* Initialises 'count+1' FQDs */
+	struct qm_fqd fqd; /* the FQD fields go here */
+	u8 __reserved2[30];
+} __packed;
+/* "Initialize/Modify CGR" */
+struct qm_mcc_initcgr {
+	u8 __reserve1[2];
+	u16 we_mask;	/* Write Enable Mask */
+	struct __qm_mc_cgr cgr;	/* CGR fields */
+	u8 __reserved2[2];
+	u8 cgid;
+	u8 __reserved3[32];
+} __packed;
+
+/* INITFQ-specific flags */
+#define QM_INITFQ_WE_MASK		0x01ff	/* 'Write Enable' flags; */
+#define QM_INITFQ_WE_OAC		0x0100
+#define QM_INITFQ_WE_ORPC		0x0080
+#define QM_INITFQ_WE_CGID		0x0040
+#define QM_INITFQ_WE_FQCTRL		0x0020
+#define QM_INITFQ_WE_DESTWQ		0x0010
+#define QM_INITFQ_WE_ICSCRED		0x0008
+#define QM_INITFQ_WE_TDTHRESH		0x0004
+#define QM_INITFQ_WE_CONTEXTB		0x0002
+#define QM_INITFQ_WE_CONTEXTA		0x0001
+/* INITCGR/MODIFYCGR-specific flags */
+#define QM_CGR_WE_MASK			0x07ff	/* 'Write Enable Mask'; */
+#define QM_CGR_WE_WR_PARM_G		0x0400
+#define QM_CGR_WE_WR_PARM_Y		0x0200
+#define QM_CGR_WE_WR_PARM_R		0x0100
+#define QM_CGR_WE_WR_EN_G		0x0080
+#define QM_CGR_WE_WR_EN_Y		0x0040
+#define QM_CGR_WE_WR_EN_R		0x0020
+#define QM_CGR_WE_CSCN_EN		0x0010
+#define QM_CGR_WE_CSCN_TARG		0x0008
+#define QM_CGR_WE_CSTD_EN		0x0004
+#define QM_CGR_WE_CS_THRES		0x0002
+#define QM_CGR_WE_MODE			0x0001
+
+#define QMAN_CGR_FLAG_USE_INIT	     0x00000001
+
+	/* Portal and Frame Queues */
+/* Represents a managed portal */
+struct qman_portal;
+
+/*
+ * This object type represents QMan frame queue descriptors (FQD), it is
+ * cacheline-aligned, and initialised by qman_create_fq(). The structure is
+ * defined further down.
+ */
+struct qman_fq;
+
+/*
+ * This object type represents a QMan congestion group, it is defined further
+ * down.
+ */
+struct qman_cgr;
+
+/*
+ * This enum, and the callback type that returns it, are used when handling
+ * dequeued frames via DQRR. Note that for "null" callbacks registered with the
+ * portal object (for handling dequeues that do not demux because contextB is
+ * NULL), the return value *MUST* be qman_cb_dqrr_consume.
+ */
+enum qman_cb_dqrr_result {
+	/* DQRR entry can be consumed */
+	qman_cb_dqrr_consume,
+	/* Like _consume, but requests parking - FQ must be held-active */
+	qman_cb_dqrr_park,
+	/* Does not consume, for DCA mode only. */
+	qman_cb_dqrr_defer,
+	/*
+	 * Stop processing without consuming this ring entry. Exits the current
+	 * qman_p_poll_dqrr() or interrupt-handling, as appropriate. If within
+	 * an interrupt handler, the callback would typically call
+	 * qman_irqsource_remove(QM_PIRQ_DQRI) before returning this value,
+	 * otherwise the interrupt will reassert immediately.
+	 */
+	qman_cb_dqrr_stop,
+	/* Like qman_cb_dqrr_stop, but consumes the current entry. */
+	qman_cb_dqrr_consume_stop
+};
+typedef enum qman_cb_dqrr_result (*qman_cb_dqrr)(struct qman_portal *qm,
+					struct qman_fq *fq,
+					const struct qm_dqrr_entry *dqrr);
+
+/*
+ * This callback type is used when handling ERNs, FQRNs and FQRLs via MR. They
+ * are always consumed after the callback returns.
+ */
+typedef void (*qman_cb_mr)(struct qman_portal *qm, struct qman_fq *fq,
+			   const union qm_mr_entry *msg);
+
+/*
+ * s/w-visible states. Ie. tentatively scheduled + truly scheduled + active +
+ * held-active + held-suspended are just "sched". Things like "retired" will not
+ * be assumed until it is complete (ie. QMAN_FQ_STATE_CHANGING is set until
+ * then, to indicate it's completing and to gate attempts to retry the retire
+ * command). Note, park commands do not set QMAN_FQ_STATE_CHANGING because it's
+ * technically impossible in the case of enqueue DCAs (which refer to DQRR ring
+ * index rather than the FQ that ring entry corresponds to), so repeated park
+ * commands are allowed (if you're silly enough to try) but won't change FQ
+ * state, and the resulting park notifications move FQs from "sched" to
+ * "parked".
+ */
+enum qman_fq_state {
+	qman_fq_state_oos,
+	qman_fq_state_parked,
+	qman_fq_state_sched,
+	qman_fq_state_retired
+};
+
+#define QMAN_FQ_STATE_CHANGING	     0x80000000 /* 'state' is changing */
+#define QMAN_FQ_STATE_NE	     0x40000000 /* retired FQ isn't empty */
+#define QMAN_FQ_STATE_ORL	     0x20000000 /* retired FQ has ORL */
+#define QMAN_FQ_STATE_BLOCKOOS	     0xe0000000 /* if any are set, no OOS */
+#define QMAN_FQ_STATE_CGR_EN	     0x10000000 /* CGR enabled */
+#define QMAN_FQ_STATE_VDQCR	     0x08000000 /* being volatile dequeued */
+
+/*
+ * Frame queue objects (struct qman_fq) are stored within memory passed to
+ * qman_create_fq(), as this allows stashing of caller-provided demux callback
+ * pointers at no extra cost to stashing of (driver-internal) FQ state. If the
+ * caller wishes to add per-FQ state and have it benefit from dequeue-stashing,
+ * they should;
+ *
+ * (a) extend the qman_fq structure with their state; eg.
+ *
+ *     // myfq is allocated and driver_fq callbacks filled in;
+ *     struct my_fq {
+ *	   struct qman_fq base;
+ *	   int an_extra_field;
+ *	   [ ... add other fields to be associated with each FQ ...]
+ *     } *myfq = some_my_fq_allocator();
+ *     struct qman_fq *fq = qman_create_fq(fqid, flags, &myfq->base);
+ *
+ *     // in a dequeue callback, access extra fields from 'fq' via a cast;
+ *     struct my_fq *myfq = (struct my_fq *)fq;
+ *     do_something_with(myfq->an_extra_field);
+ *     [...]
+ *
+ * (b) when and if configuring the FQ for context stashing, specify how ever
+ *     many cachelines are required to stash 'struct my_fq', to accelerate not
+ *     only the QMan driver but the callback as well.
+ */
+
+struct qman_fq_cb {
+	qman_cb_dqrr dqrr;	/* for dequeued frames */
+	qman_cb_mr ern;		/* for s/w ERNs */
+	qman_cb_mr fqs;		/* frame-queue state changes*/
+};
+
+struct qman_fq {
+	/* Caller of qman_create_fq() provides these demux callbacks */
+	struct qman_fq_cb cb;
+	/*
+	 * These are internal to the driver, don't touch. In particular, they
+	 * may change, be removed, or extended (so you shouldn't rely on
+	 * sizeof(qman_fq) being a constant).
+	 */
+	u32 fqid, idx;
+	unsigned long flags;
+	enum qman_fq_state state;
+	int cgr_groupid;
+};
+
+/*
+ * This callback type is used when handling congestion group entry/exit.
+ * 'congested' is non-zero on congestion-entry, and zero on congestion-exit.
+ */
+typedef void (*qman_cb_cgr)(struct qman_portal *qm,
+			    struct qman_cgr *cgr, int congested);
+
+struct qman_cgr {
+	/* Set these prior to qman_create_cgr() */
+	u32 cgrid; /* 0..255, but u32 to allow specials like -1, 256, etc.*/
+	qman_cb_cgr cb;
+	/* These are private to the driver */
+	u16 chan; /* portal channel this object is created on */
+	struct list_head node;
+};
+
+/* Flags to qman_create_fq() */
+#define QMAN_FQ_FLAG_NO_ENQUEUE	     0x00000001 /* can't enqueue */
+#define QMAN_FQ_FLAG_NO_MODIFY	     0x00000002 /* can only enqueue */
+#define QMAN_FQ_FLAG_TO_DCPORTAL     0x00000004 /* consumed by CAAM/PME/Fman */
+#define QMAN_FQ_FLAG_DYNAMIC_FQID    0x00000020 /* (de)allocate fqid */
+
+/* Flags to qman_init_fq() */
+#define QMAN_INITFQ_FLAG_SCHED	     0x00000001 /* schedule rather than park */
+#define QMAN_INITFQ_FLAG_LOCAL	     0x00000004 /* set dest portal */
+
+	/* Portal Management */
+/**
+ * qman_p_irqsource_add - add processing sources to be interrupt-driven
+ * @bits: bitmask of QM_PIRQ_**I processing sources
+ *
+ * Adds processing sources that should be interrupt-driven (rather than
+ * processed via qman_poll_***() functions).
+ */
+void qman_p_irqsource_add(struct qman_portal *p, u32 bits);
+
+/**
+ * qman_p_irqsource_remove - remove processing sources from being int-driven
+ * @bits: bitmask of QM_PIRQ_**I processing sources
+ *
+ * Removes processing sources from being interrupt-driven, so that they will
+ * instead be processed via qman_poll_***() functions.
+ */
+void qman_p_irqsource_remove(struct qman_portal *p, u32 bits);
+
+/**
+ * qman_affine_cpus - return a mask of cpus that have affine portals
+ */
+const cpumask_t *qman_affine_cpus(void);
+
+/**
+ * qman_affine_channel - return the channel ID of an portal
+ * @cpu: the cpu whose affine portal is the subject of the query
+ *
+ * If @cpu is -1, the affine portal for the current CPU will be used. It is a
+ * bug to call this function for any value of @cpu (other than -1) that is not a
+ * member of the mask returned from qman_affine_cpus().
+ */
+u16 qman_affine_channel(int cpu);
+
+/**
+ * qman_get_affine_portal - return the portal pointer affine to cpu
+ * @cpu: the cpu whose affine portal is the subject of the query
+ */
+struct qman_portal *qman_get_affine_portal(int cpu);
+
+/**
+ * qman_p_poll_dqrr - process DQRR (fast-path) entries
+ * @limit: the maximum number of DQRR entries to process
+ *
+ * Use of this function requires that DQRR processing not be interrupt-driven.
+ * The return value represents the number of DQRR entries processed.
+ */
+int qman_p_poll_dqrr(struct qman_portal *p, unsigned int limit);
+
+/**
+ * qman_p_static_dequeue_add - Add pool channels to the portal SDQCR
+ * @pools: bit-mask of pool channels, using QM_SDQCR_CHANNELS_POOL(n)
+ *
+ * Adds a set of pool channels to the portal's static dequeue command register
+ * (SDQCR). The requested pools are limited to those the portal has dequeue
+ * access to.
+ */
+void qman_p_static_dequeue_add(struct qman_portal *p, u32 pools);
+
+	/* FQ management */
+/**
+ * qman_create_fq - Allocates a FQ
+ * @fqid: the index of the FQD to encapsulate, must be "Out of Service"
+ * @flags: bit-mask of QMAN_FQ_FLAG_*** options
+ * @fq: memory for storing the 'fq', with callbacks filled in
+ *
+ * Creates a frame queue object for the given @fqid, unless the
+ * QMAN_FQ_FLAG_DYNAMIC_FQID flag is set in @flags, in which case a FQID is
+ * dynamically allocated (or the function fails if none are available). Once
+ * created, the caller should not touch the memory at 'fq' except as extended to
+ * adjacent memory for user-defined fields (see the definition of "struct
+ * qman_fq" for more info). NO_MODIFY is only intended for enqueuing to
+ * pre-existing frame-queues that aren't to be otherwise interfered with, it
+ * prevents all other modifications to the frame queue. The TO_DCPORTAL flag
+ * causes the driver to honour any contextB modifications requested in the
+ * qm_init_fq() API, as this indicates the frame queue will be consumed by a
+ * direct-connect portal (PME, CAAM, or Fman). When frame queues are consumed by
+ * software portals, the contextB field is controlled by the driver and can't be
+ * modified by the caller.
+ */
+int qman_create_fq(u32 fqid, u32 flags, struct qman_fq *fq);
+
+/**
+ * qman_destroy_fq - Deallocates a FQ
+ * @fq: the frame queue object to release
+ *
+ * The memory for this frame queue object ('fq' provided in qman_create_fq()) is
+ * not deallocated but the caller regains ownership, to do with as desired. The
+ * FQ must be in the 'out-of-service' or in the 'parked' state.
+ */
+void qman_destroy_fq(struct qman_fq *fq);
+
+/**
+ * qman_fq_fqid - Queries the frame queue ID of a FQ object
+ * @fq: the frame queue object to query
+ */
+u32 qman_fq_fqid(struct qman_fq *fq);
+
+/**
+ * qman_init_fq - Initialises FQ fields, leaves the FQ "parked" or "scheduled"
+ * @fq: the frame queue object to modify, must be 'parked' or new.
+ * @flags: bit-mask of QMAN_INITFQ_FLAG_*** options
+ * @opts: the FQ-modification settings, as defined in the low-level API
+ *
+ * The @opts parameter comes from the low-level portal API. Select
+ * QMAN_INITFQ_FLAG_SCHED in @flags to cause the frame queue to be scheduled
+ * rather than parked. NB, @opts can be NULL.
+ *
+ * Note that some fields and options within @opts may be ignored or overwritten
+ * by the driver;
+ * 1. the 'count' and 'fqid' fields are always ignored (this operation only
+ * affects one frame queue: @fq).
+ * 2. the QM_INITFQ_WE_CONTEXTB option of the 'we_mask' field and the associated
+ * 'fqd' structure's 'context_b' field are sometimes overwritten;
+ *   - if @fq was not created with QMAN_FQ_FLAG_TO_DCPORTAL, then context_b is
+ *     initialised to a value used by the driver for demux.
+ *   - if context_b is initialised for demux, so is context_a in case stashing
+ *     is requested (see item 4).
+ * (So caller control of context_b is only possible for TO_DCPORTAL frame queue
+ * objects.)
+ * 3. if @flags contains QMAN_INITFQ_FLAG_LOCAL, the 'fqd' structure's
+ * 'dest::channel' field will be overwritten to match the portal used to issue
+ * the command. If the WE_DESTWQ write-enable bit had already been set by the
+ * caller, the channel workqueue will be left as-is, otherwise the write-enable
+ * bit is set and the workqueue is set to a default of 4. If the "LOCAL" flag
+ * isn't set, the destination channel/workqueue fields and the write-enable bit
+ * are left as-is.
+ * 4. if the driver overwrites context_a/b for demux, then if
+ * QM_INITFQ_WE_CONTEXTA is set, the driver will only overwrite
+ * context_a.address fields and will leave the stashing fields provided by the
+ * user alone, otherwise it will zero out the context_a.stashing fields.
+ */
+int qman_init_fq(struct qman_fq *fq, u32 flags, struct qm_mcc_initfq *opts);
+
+/**
+ * qman_schedule_fq - Schedules a FQ
+ * @fq: the frame queue object to schedule, must be 'parked'
+ *
+ * Schedules the frame queue, which must be Parked, which takes it to
+ * Tentatively-Scheduled or Truly-Scheduled depending on its fill-level.
+ */
+int qman_schedule_fq(struct qman_fq *fq);
+
+/**
+ * qman_retire_fq - Retires a FQ
+ * @fq: the frame queue object to retire
+ * @flags: FQ flags (QMAN_FQ_STATE*) if retirement completes immediately
+ *
+ * Retires the frame queue. This returns zero if it succeeds immediately, +1 if
+ * the retirement was started asynchronously, otherwise it returns negative for
+ * failure. When this function returns zero, @flags is set to indicate whether
+ * the retired FQ is empty and/or whether it has any ORL fragments (to show up
+ * as ERNs). Otherwise the corresponding flags will be known when a subsequent
+ * FQRN message shows up on the portal's message ring.
+ *
+ * NB, if the retirement is asynchronous (the FQ was in the Truly Scheduled or
+ * Active state), the completion will be via the message ring as a FQRN - but
+ * the corresponding callback may occur before this function returns!! Ie. the
+ * caller should be prepared to accept the callback as the function is called,
+ * not only once it has returned.
+ */
+int qman_retire_fq(struct qman_fq *fq, u32 *flags);
+
+/**
+ * qman_oos_fq - Puts a FQ "out of service"
+ * @fq: the frame queue object to be put out-of-service, must be 'retired'
+ *
+ * The frame queue must be retired and empty, and if any order restoration list
+ * was released as ERNs at the time of retirement, they must all be consumed.
+ */
+int qman_oos_fq(struct qman_fq *fq);
+
+/**
+ * qman_enqueue - Enqueue a frame to a frame queue
+ * @fq: the frame queue object to enqueue to
+ * @fd: a descriptor of the frame to be enqueued
+ *
+ * Fills an entry in the EQCR of portal @qm to enqueue the frame described by
+ * @fd. The descriptor details are copied from @fd to the EQCR entry, the 'pid'
+ * field is ignored. The return value is non-zero on error, such as ring full.
+ */
+int qman_enqueue(struct qman_fq *fq, const struct qm_fd *fd);
+
+/**
+ * qman_alloc_fqid_range - Allocate a contiguous range of FQIDs
+ * @result: is set by the API to the base FQID of the allocated range
+ * @count: the number of FQIDs required
+ *
+ * Returns 0 on success, or a negative error code.
+ */
+int qman_alloc_fqid_range(u32 *result, u32 count);
+#define qman_alloc_fqid(result) qman_alloc_fqid_range(result, 1)
+
+/**
+ * qman_release_fqid - Release the specified frame queue ID
+ * @fqid: the FQID to be released back to the resource pool
+ *
+ * This function can also be used to seed the allocator with
+ * FQID ranges that it can subsequently allocate from.
+ * Returns 0 on success, or a negative error code.
+ */
+int qman_release_fqid(u32 fqid);
+
+	/* Pool-channel management */
+/**
+ * qman_alloc_pool_range - Allocate a contiguous range of pool-channel IDs
+ * @result: is set by the API to the base pool-channel ID of the allocated range
+ * @count: the number of pool-channel IDs required
+ *
+ * Returns 0 on success, or a negative error code.
+ */
+int qman_alloc_pool_range(u32 *result, u32 count);
+#define qman_alloc_pool(result) qman_alloc_pool_range(result, 1)
+
+/**
+ * qman_release_pool - Release the specified pool-channel ID
+ * @id: the pool-chan ID to be released back to the resource pool
+ *
+ * This function can also be used to seed the allocator with
+ * pool-channel ID ranges that it can subsequently allocate from.
+ * Returns 0 on success, or a negative error code.
+ */
+int qman_release_pool(u32 id);
+
+	/* CGR management */
+/**
+ * qman_create_cgr - Register a congestion group object
+ * @cgr: the 'cgr' object, with fields filled in
+ * @flags: QMAN_CGR_FLAG_* values
+ * @opts: optional state of CGR settings
+ *
+ * Registers this object to receiving congestion entry/exit callbacks on the
+ * portal affine to the cpu portal on which this API is executed. If opts is
+ * NULL then only the callback (cgr->cb) function is registered. If @flags
+ * contains QMAN_CGR_FLAG_USE_INIT, then an init hw command (which will reset
+ * any unspecified parameters) will be used rather than a modify hw hardware
+ * (which only modifies the specified parameters).
+ */
+int qman_create_cgr(struct qman_cgr *cgr, u32 flags,
+		    struct qm_mcc_initcgr *opts);
+
+/**
+ * qman_delete_cgr - Deregisters a congestion group object
+ * @cgr: the 'cgr' object to deregister
+ *
+ * "Unplugs" this CGR object from the portal affine to the cpu on which this API
+ * is executed. This must be excuted on the same affine portal on which it was
+ * created.
+ */
+int qman_delete_cgr(struct qman_cgr *cgr);
+
+/**
+ * qman_delete_cgr_safe - Deregisters a congestion group object from any CPU
+ * @cgr: the 'cgr' object to deregister
+ *
+ * This will select the proper CPU and run there qman_delete_cgr().
+ */
+void qman_delete_cgr_safe(struct qman_cgr *cgr);
+
+/**
+ * qman_query_cgr_congested - Queries CGR's congestion status
+ * @cgr: the 'cgr' object to query
+ * @result: returns 'cgr's congestion status, 1 (true) if congested
+ */
+int qman_query_cgr_congested(struct qman_cgr *cgr, bool *result);
+
+/**
+ * qman_alloc_cgrid_range - Allocate a contiguous range of CGR IDs
+ * @result: is set by the API to the base CGR ID of the allocated range
+ * @count: the number of CGR IDs required
+ *
+ * Returns 0 on success, or a negative error code.
+ */
+int qman_alloc_cgrid_range(u32 *result, u32 count);
+#define qman_alloc_cgrid(result) qman_alloc_cgrid_range(result, 1)
+
+/**
+ * qman_release_cgrid - Release the specified CGR ID
+ * @id: the CGR ID to be released back to the resource pool
+ *
+ * This function can also be used to seed the allocator with
+ * CGR ID ranges that it can subsequently allocate from.
+ * Returns 0 on success, or a negative error code.
+ */
+int qman_release_cgrid(u32 id);
+
+#endif	/* __FSL_QMAN_H */
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index fb8e3b6febdf..c2119008990a 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -177,6 +177,7 @@ enum tcm_sense_reason_table {
 	TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED	= R(0x15),
 	TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED	= R(0x16),
 	TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED	= R(0x17),
+	TCM_COPY_TARGET_DEVICE_NOT_REACHABLE	= R(0x18),
 #undef R
 };
 
diff --git a/include/trace/events/cgroup.h b/include/trace/events/cgroup.h
new file mode 100644
index 000000000000..ab68640a18d0
--- /dev/null
+++ b/include/trace/events/cgroup.h
@@ -0,0 +1,163 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM cgroup
+
+#if !defined(_TRACE_CGROUP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_CGROUP_H
+
+#include <linux/cgroup.h>
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(cgroup_root,
+
+	TP_PROTO(struct cgroup_root *root),
+
+	TP_ARGS(root),
+
+	TP_STRUCT__entry(
+		__field(	int,		root			)
+		__field(	u16,		ss_mask			)
+		__string(	name,		root->name		)
+	),
+
+	TP_fast_assign(
+		__entry->root = root->hierarchy_id;
+		__entry->ss_mask = root->subsys_mask;
+		__assign_str(name, root->name);
+	),
+
+	TP_printk("root=%d ss_mask=%#x name=%s",
+		  __entry->root, __entry->ss_mask, __get_str(name))
+);
+
+DEFINE_EVENT(cgroup_root, cgroup_setup_root,
+
+	TP_PROTO(struct cgroup_root *root),
+
+	TP_ARGS(root)
+);
+
+DEFINE_EVENT(cgroup_root, cgroup_destroy_root,
+
+	TP_PROTO(struct cgroup_root *root),
+
+	TP_ARGS(root)
+);
+
+DEFINE_EVENT(cgroup_root, cgroup_remount,
+
+	TP_PROTO(struct cgroup_root *root),
+
+	TP_ARGS(root)
+);
+
+DECLARE_EVENT_CLASS(cgroup,
+
+	TP_PROTO(struct cgroup *cgrp),
+
+	TP_ARGS(cgrp),
+
+	TP_STRUCT__entry(
+		__field(	int,		root			)
+		__field(	int,		id			)
+		__field(	int,		level			)
+		__dynamic_array(char,		path,
+				cgrp->kn ? cgroup_path(cgrp, NULL, 0) + 1
+					 : strlen("(null)"))
+	),
+
+	TP_fast_assign(
+		__entry->root = cgrp->root->hierarchy_id;
+		__entry->id = cgrp->id;
+		__entry->level = cgrp->level;
+		if (cgrp->kn)
+			cgroup_path(cgrp, __get_dynamic_array(path),
+				    __get_dynamic_array_len(path));
+		else
+			__assign_str(path, "(null)");
+	),
+
+	TP_printk("root=%d id=%d level=%d path=%s",
+		  __entry->root, __entry->id, __entry->level, __get_str(path))
+);
+
+DEFINE_EVENT(cgroup, cgroup_mkdir,
+
+	TP_PROTO(struct cgroup *cgroup),
+
+	TP_ARGS(cgroup)
+);
+
+DEFINE_EVENT(cgroup, cgroup_rmdir,
+
+	TP_PROTO(struct cgroup *cgroup),
+
+	TP_ARGS(cgroup)
+);
+
+DEFINE_EVENT(cgroup, cgroup_release,
+
+	TP_PROTO(struct cgroup *cgroup),
+
+	TP_ARGS(cgroup)
+);
+
+DEFINE_EVENT(cgroup, cgroup_rename,
+
+	TP_PROTO(struct cgroup *cgroup),
+
+	TP_ARGS(cgroup)
+);
+
+DECLARE_EVENT_CLASS(cgroup_migrate,
+
+	TP_PROTO(struct cgroup *dst_cgrp, struct task_struct *task, bool threadgroup),
+
+	TP_ARGS(dst_cgrp, task, threadgroup),
+
+	TP_STRUCT__entry(
+		__field(	int,		dst_root		)
+		__field(	int,		dst_id			)
+		__field(	int,		dst_level		)
+		__dynamic_array(char,		dst_path,
+				dst_cgrp->kn ? cgroup_path(dst_cgrp, NULL, 0) + 1
+					     : strlen("(null)"))
+		__field(	int,		pid			)
+		__string(	comm,		task->comm		)
+	),
+
+	TP_fast_assign(
+		__entry->dst_root = dst_cgrp->root->hierarchy_id;
+		__entry->dst_id = dst_cgrp->id;
+		__entry->dst_level = dst_cgrp->level;
+		if (dst_cgrp->kn)
+			cgroup_path(dst_cgrp, __get_dynamic_array(dst_path),
+				    __get_dynamic_array_len(dst_path));
+		else
+			__assign_str(dst_path, "(null)");
+		__entry->pid = task->pid;
+		__assign_str(comm, task->comm);
+	),
+
+	TP_printk("dst_root=%d dst_id=%d dst_level=%d dst_path=%s pid=%d comm=%s",
+		  __entry->dst_root, __entry->dst_id, __entry->dst_level,
+		  __get_str(dst_path), __entry->pid, __get_str(comm))
+);
+
+DEFINE_EVENT(cgroup_migrate, cgroup_attach_task,
+
+	TP_PROTO(struct cgroup *dst_cgrp, struct task_struct *task, bool threadgroup),
+
+	TP_ARGS(dst_cgrp, task, threadgroup)
+);
+
+DEFINE_EVENT(cgroup_migrate, cgroup_transfer_tasks,
+
+	TP_PROTO(struct cgroup *dst_cgrp, struct task_struct *task, bool threadgroup),
+
+	TP_ARGS(dst_cgrp, task, threadgroup)
+);
+
+#endif /* _TRACE_CGROUP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index dbfee7e86ba6..9b1462e38b82 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -730,10 +730,6 @@ __SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect)
 __SYSCALL(__NR_pkey_alloc,    sys_pkey_alloc)
 #define __NR_pkey_free 290
 __SYSCALL(__NR_pkey_free,     sys_pkey_free)
-#define __NR_pkey_get 291
-//__SYSCALL(__NR_pkey_get,      sys_pkey_get)
-#define __NR_pkey_set 292
-//__SYSCALL(__NR_pkey_set,      sys_pkey_set)
 
 #undef __NR_syscalls
 #define __NR_syscalls 291
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 6965d0909554..cd2be1c8e9fb 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -75,6 +75,7 @@ header-y += bpf_perf_event.h
 header-y += bpf.h
 header-y += bpqether.h
 header-y += bsg.h
+header-y += bt-bmc.h
 header-y += btrfs.h
 header-y += can.h
 header-y += capability.h
diff --git a/include/uapi/linux/bt-bmc.h b/include/uapi/linux/bt-bmc.h
new file mode 100644
index 000000000000..d9ec766a63d0
--- /dev/null
+++ b/include/uapi/linux/bt-bmc.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (c) 2015-2016, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _UAPI_LINUX_BT_BMC_H
+#define _UAPI_LINUX_BT_BMC_H
+
+#include <linux/ioctl.h>
+
+#define __BT_BMC_IOCTL_MAGIC	0xb1
+#define BT_BMC_IOCTL_SMS_ATN	_IO(__BT_BMC_IOCTL_MAGIC, 0x00)
+
+#endif /* _UAPI_LINUX_BT_BMC_H */
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index ac5eacd3055b..db4c253f8011 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -239,7 +239,17 @@ struct btrfs_ioctl_fs_info_args {
  * Used by:
  * struct btrfs_ioctl_feature_flags
  */
-#define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE	(1ULL << 0)
+#define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE		(1ULL << 0)
+/*
+ * Older kernels (< 4.9) on big-endian systems produced broken free space tree
+ * bitmaps, and btrfs-progs also used to corrupt the free space tree (versions
+ * < 4.7.3).  If this bit is clear, then the free space tree cannot be trusted.
+ * btrfs-progs can also intentionally clear this bit to ask the kernel to
+ * rebuild the free space tree, however this might not work on older kernels
+ * that do not know about this bit. If not sure, clear the cache manually on
+ * first mount when booting older kernel versions.
+ */
+#define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID	(1ULL << 1)
 
 #define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF	(1ULL << 0)
 #define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL	(1ULL << 1)
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 099a4200732c..8e547231c1b7 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -119,8 +119,7 @@ struct ethtool_cmd {
 static inline void ethtool_cmd_speed_set(struct ethtool_cmd *ep,
 					 __u32 speed)
 {
-
-	ep->speed = (__u16)speed;
+	ep->speed = (__u16)(speed & 0xFFFF);
 	ep->speed_hi = (__u16)(speed >> 16);
 }
 
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index d812172d1d7b..e5a2e68b2236 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -612,6 +612,8 @@
  */
 #define PCI_EXP_DEVCAP2		36	/* Device Capabilities 2 */
 #define  PCI_EXP_DEVCAP2_ARI		0x00000020 /* Alternative Routing-ID */
+#define  PCI_EXP_DEVCAP2_ATOMIC_ROUTE	0x00000040 /* Atomic Op routing */
+#define PCI_EXP_DEVCAP2_ATOMIC_COMP64	0x00000100 /* Atomic 64-bit compare */
 #define  PCI_EXP_DEVCAP2_LTR		0x00000800 /* Latency tolerance reporting */
 #define  PCI_EXP_DEVCAP2_OBFF_MASK	0x000c0000 /* OBFF support mechanism */
 #define  PCI_EXP_DEVCAP2_OBFF_MSG	0x00040000 /* New message signaling */
@@ -619,6 +621,7 @@
 #define PCI_EXP_DEVCTL2		40	/* Device Control 2 */
 #define  PCI_EXP_DEVCTL2_COMP_TIMEOUT	0x000f	/* Completion Timeout Value */
 #define  PCI_EXP_DEVCTL2_ARI		0x0020	/* Alternative Routing-ID */
+#define PCI_EXP_DEVCTL2_ATOMIC_REQ	0x0040	/* Set Atomic requests */
 #define  PCI_EXP_DEVCTL2_IDO_REQ_EN	0x0100	/* Allow IDO for requests */
 #define  PCI_EXP_DEVCTL2_IDO_CMP_EN	0x0200	/* Allow IDO for completions */
 #define  PCI_EXP_DEVCTL2_LTR_EN		0x0400	/* Enable LTR mechanism */
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 262f0379d83a..5a78be518101 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -350,7 +350,7 @@ struct rtnexthop {
 #define RTNH_F_OFFLOAD		8	/* offloaded route */
 #define RTNH_F_LINKDOWN		16	/* carrier-down on nexthop */
 
-#define RTNH_COMPARE_MASK	(RTNH_F_DEAD | RTNH_F_LINKDOWN)
+#define RTNH_COMPARE_MASK	(RTNH_F_DEAD | RTNH_F_LINKDOWN | RTNH_F_OFFLOAD)
 
 /* Macros to handle hexthops */
 
diff --git a/include/uapi/rdma/qedr-abi.h b/include/uapi/rdma/qedr-abi.h
new file mode 100644
index 000000000000..75c270d839c8
--- /dev/null
+++ b/include/uapi/rdma/qedr-abi.h
@@ -0,0 +1,106 @@
+/* QLogic qedr NIC Driver
+ * Copyright (c) 2015-2016  QLogic Corporation
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and /or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef __QEDR_USER_H__
+#define __QEDR_USER_H__
+
+#include <linux/types.h>
+
+#define QEDR_ABI_VERSION		(8)
+
+/* user kernel communication data structures. */
+
+struct qedr_alloc_ucontext_resp {
+	__u64 db_pa;
+	__u32 db_size;
+
+	__u32 max_send_wr;
+	__u32 max_recv_wr;
+	__u32 max_srq_wr;
+	__u32 sges_per_send_wr;
+	__u32 sges_per_recv_wr;
+	__u32 sges_per_srq_wr;
+	__u32 max_cqes;
+};
+
+struct qedr_alloc_pd_ureq {
+	__u64 rsvd1;
+};
+
+struct qedr_alloc_pd_uresp {
+	__u32 pd_id;
+};
+
+struct qedr_create_cq_ureq {
+	__u64 addr;
+	__u64 len;
+};
+
+struct qedr_create_cq_uresp {
+	__u32 db_offset;
+	__u16 icid;
+};
+
+struct qedr_create_qp_ureq {
+	__u32 qp_handle_hi;
+	__u32 qp_handle_lo;
+
+	/* SQ */
+	/* user space virtual address of SQ buffer */
+	__u64 sq_addr;
+
+	/* length of SQ buffer */
+	__u64 sq_len;
+
+	/* RQ */
+	/* user space virtual address of RQ buffer */
+	__u64 rq_addr;
+
+	/* length of RQ buffer */
+	__u64 rq_len;
+};
+
+struct qedr_create_qp_uresp {
+	__u32 qp_id;
+	__u32 atomic_supported;
+
+	/* SQ */
+	__u32 sq_db_offset;
+	__u16 sq_icid;
+
+	/* RQ */
+	__u32 rq_db_offset;
+	__u16 rq_icid;
+
+	__u32 rq_db2_offset;
+};
+
+#endif /* __QEDR_USER_H__ */