diff --git a/Makefile b/Makefile
index 607f1b19555f9..11acd6dd024a2 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 261
+SUBLEVEL = 262
 EXTRAVERSION =
 NAME = Blurry Fish Butt
 
diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index ffd9cf5ec8c40..bf8475ce85ee2 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -3,6 +3,7 @@
 generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
+generic-y += export.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
diff --git a/arch/alpha/include/asm/uaccess.h b/arch/alpha/include/asm/uaccess.h
index c0ddbbf73400e..89413a29cb079 100644
--- a/arch/alpha/include/asm/uaccess.h
+++ b/arch/alpha/include/asm/uaccess.h
@@ -341,45 +341,17 @@ __asm__ __volatile__("1: stb %r2,%1\n"				\
  * Complex access routines
  */
 
-/* This little bit of silliness is to get the GP loaded for a function
-   that ordinarily wouldn't.  Otherwise we could have it done by the macro
-   directly, which can be optimized the linker.  */
-#ifdef MODULE
-#define __module_address(sym)		"r"(sym),
-#define __module_call(ra, arg, sym)	"jsr $" #ra ",(%" #arg ")," #sym
-#else
-#define __module_address(sym)
-#define __module_call(ra, arg, sym)	"bsr $" #ra "," #sym " !samegp"
-#endif
-
-extern void __copy_user(void);
-
-extern inline long
-__copy_tofrom_user_nocheck(void *to, const void *from, long len)
-{
-	register void * __cu_to __asm__("$6") = to;
-	register const void * __cu_from __asm__("$7") = from;
-	register long __cu_len __asm__("$0") = len;
-
-	__asm__ __volatile__(
-		__module_call(28, 3, __copy_user)
-		: "=r" (__cu_len), "=r" (__cu_from), "=r" (__cu_to)
-		: __module_address(__copy_user)
-		  "0" (__cu_len), "1" (__cu_from), "2" (__cu_to)
-		: "$1", "$2", "$3", "$4", "$5", "$28", "memory");
-
-	return __cu_len;
-}
+extern long __copy_user(void *to, const void *from, long len);
 
-#define __copy_to_user(to, from, n)					\
-({									\
-	__chk_user_ptr(to);						\
-	__copy_tofrom_user_nocheck((__force void *)(to), (from), (n));	\
+#define __copy_to_user(to, from, n)			\
+({							\
+	__chk_user_ptr(to);				\
+	__copy_user((__force void *)(to), (from), (n));	\
 })
-#define __copy_from_user(to, from, n)					\
-({									\
-	__chk_user_ptr(from);						\
-	__copy_tofrom_user_nocheck((to), (__force void *)(from), (n));	\
+#define __copy_from_user(to, from, n)			\
+({							\
+	__chk_user_ptr(from);				\
+	__copy_user((to), (__force void *)(from), (n));	\
 })
 
 #define __copy_to_user_inatomic __copy_to_user
@@ -389,35 +361,22 @@ extern inline long
 copy_to_user(void __user *to, const void *from, long n)
 {
 	if (likely(__access_ok((unsigned long)to, n, get_fs())))
-		n = __copy_tofrom_user_nocheck((__force void *)to, from, n);
+		n = __copy_user((__force void *)to, from, n);
 	return n;
 }
 
 extern inline long
 copy_from_user(void *to, const void __user *from, long n)
 {
+	long res = n;
 	if (likely(__access_ok((unsigned long)from, n, get_fs())))
-		n = __copy_tofrom_user_nocheck(to, (__force void *)from, n);
-	else
-		memset(to, 0, n);
-	return n;
+		res = __copy_from_user_inatomic(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
 }
 
-extern void __do_clear_user(void);
-
-extern inline long
-__clear_user(void __user *to, long len)
-{
-	register void __user * __cl_to __asm__("$6") = to;
-	register long __cl_len __asm__("$0") = len;
-	__asm__ __volatile__(
-		__module_call(28, 2, __do_clear_user)
-		: "=r"(__cl_len), "=r"(__cl_to)
-		: __module_address(__do_clear_user)
-		  "0"(__cl_len), "1"(__cl_to)
-		: "$1", "$2", "$3", "$4", "$5", "$28", "memory");
-	return __cl_len;
-}
+extern long __clear_user(void __user *to, long len);
 
 extern inline long
 clear_user(void __user *to, long len)
@@ -427,9 +386,6 @@ clear_user(void __user *to, long len)
 	return len;
 }
 
-#undef __module_address
-#undef __module_call
-
 #define user_addr_max() \
         (segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
 
diff --git a/arch/alpha/kernel/Makefile b/arch/alpha/kernel/Makefile
index 3ecac0106c8a1..8ce13d7a2ad38 100644
--- a/arch/alpha/kernel/Makefile
+++ b/arch/alpha/kernel/Makefile
@@ -8,7 +8,7 @@ ccflags-y	:= -Wno-sign-compare
 
 obj-y    := entry.o traps.o process.o osf_sys.o irq.o \
 	    irq_alpha.o signal.o setup.o ptrace.o time.o \
-	    alpha_ksyms.o systbls.o err_common.o io.o
+	    systbls.o err_common.o io.o
 
 obj-$(CONFIG_VGA_HOSE)	+= console.o
 obj-$(CONFIG_SMP)	+= smp.o
diff --git a/arch/alpha/kernel/alpha_ksyms.c b/arch/alpha/kernel/alpha_ksyms.c
deleted file mode 100644
index f4c7ab6f43b0d..0000000000000
--- a/arch/alpha/kernel/alpha_ksyms.c
+++ /dev/null
@@ -1,102 +0,0 @@
-/*
- * linux/arch/alpha/kernel/alpha_ksyms.c
- *
- * Export the alpha-specific functions that are needed for loadable
- * modules.
- */
-
-#include <linux/module.h>
-#include <asm/console.h>
-#include <asm/uaccess.h>
-#include <asm/checksum.h>
-#include <asm/fpu.h>
-#include <asm/machvec.h>
-
-#include <linux/syscalls.h>
-
-/* these are C runtime functions with special calling conventions: */
-extern void __divl (void);
-extern void __reml (void);
-extern void __divq (void);
-extern void __remq (void);
-extern void __divlu (void);
-extern void __remlu (void);
-extern void __divqu (void);
-extern void __remqu (void);
-
-EXPORT_SYMBOL(alpha_mv);
-EXPORT_SYMBOL(callback_getenv);
-EXPORT_SYMBOL(callback_setenv);
-EXPORT_SYMBOL(callback_save_env);
-
-/* platform dependent support */
-EXPORT_SYMBOL(strcat);
-EXPORT_SYMBOL(strcpy);
-EXPORT_SYMBOL(strlen);
-EXPORT_SYMBOL(strncpy);
-EXPORT_SYMBOL(strncat);
-EXPORT_SYMBOL(strchr);
-EXPORT_SYMBOL(strrchr);
-EXPORT_SYMBOL(memmove);
-EXPORT_SYMBOL(__memcpy);
-EXPORT_SYMBOL(__memset);
-EXPORT_SYMBOL(___memset);
-EXPORT_SYMBOL(__memsetw);
-EXPORT_SYMBOL(__constant_c_memset);
-EXPORT_SYMBOL(copy_page);
-EXPORT_SYMBOL(clear_page);
-
-EXPORT_SYMBOL(alpha_read_fp_reg);
-EXPORT_SYMBOL(alpha_read_fp_reg_s);
-EXPORT_SYMBOL(alpha_write_fp_reg);
-EXPORT_SYMBOL(alpha_write_fp_reg_s);
-
-/* Networking helper routines. */
-EXPORT_SYMBOL(csum_tcpudp_magic);
-EXPORT_SYMBOL(ip_compute_csum);
-EXPORT_SYMBOL(ip_fast_csum);
-EXPORT_SYMBOL(csum_partial_copy_nocheck);
-EXPORT_SYMBOL(csum_partial_copy_from_user);
-EXPORT_SYMBOL(csum_ipv6_magic);
-
-#ifdef CONFIG_MATHEMU_MODULE
-extern long (*alpha_fp_emul_imprecise)(struct pt_regs *, unsigned long);
-extern long (*alpha_fp_emul) (unsigned long pc);
-EXPORT_SYMBOL(alpha_fp_emul_imprecise);
-EXPORT_SYMBOL(alpha_fp_emul);
-#endif
-
-/*
- * The following are specially called from the uaccess assembly stubs.
- */
-EXPORT_SYMBOL(__copy_user);
-EXPORT_SYMBOL(__do_clear_user);
-
-/* 
- * SMP-specific symbols.
- */
-
-#ifdef CONFIG_SMP
-EXPORT_SYMBOL(_atomic_dec_and_lock);
-#endif /* CONFIG_SMP */
-
-/*
- * The following are special because they're not called
- * explicitly (the C compiler or assembler generates them in
- * response to division operations).  Fortunately, their
- * interface isn't gonna change any time soon now, so it's OK
- * to leave it out of version control.
- */
-# undef memcpy
-# undef memset
-EXPORT_SYMBOL(__divl);
-EXPORT_SYMBOL(__divlu);
-EXPORT_SYMBOL(__divq);
-EXPORT_SYMBOL(__divqu);
-EXPORT_SYMBOL(__reml);
-EXPORT_SYMBOL(__remlu);
-EXPORT_SYMBOL(__remq);
-EXPORT_SYMBOL(__remqu);
-EXPORT_SYMBOL(memcpy);
-EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memchr);
diff --git a/arch/alpha/kernel/machvec_impl.h b/arch/alpha/kernel/machvec_impl.h
index f54bdf658cd0b..8c6516025efbc 100644
--- a/arch/alpha/kernel/machvec_impl.h
+++ b/arch/alpha/kernel/machvec_impl.h
@@ -144,9 +144,11 @@
    else beforehand.  Fine.  We'll do it ourselves.  */
 #if 0
 #define ALIAS_MV(system) \
-  struct alpha_machine_vector alpha_mv __attribute__((alias(#system "_mv")));
+  struct alpha_machine_vector alpha_mv __attribute__((alias(#system "_mv"))); \
+  EXPORT_SYMBOL(alpha_mv);
 #else
 #define ALIAS_MV(system) \
-  asm(".global alpha_mv\nalpha_mv = " #system "_mv");
+  asm(".global alpha_mv\nalpha_mv = " #system "_mv"); \
+  EXPORT_SYMBOL(alpha_mv);
 #endif
 #endif /* GENERIC */
diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c
index b20af76f12c1d..4811e54069fcf 100644
--- a/arch/alpha/kernel/setup.c
+++ b/arch/alpha/kernel/setup.c
@@ -115,6 +115,7 @@ unsigned long alpha_agpgart_size = DEFAULT_AGP_APER_SIZE;
 
 #ifdef CONFIG_ALPHA_GENERIC
 struct alpha_machine_vector alpha_mv;
+EXPORT_SYMBOL(alpha_mv);
 #endif
 
 #ifndef alpha_using_srm
diff --git a/arch/alpha/lib/Makefile b/arch/alpha/lib/Makefile
index 59660743237cc..a808159603645 100644
--- a/arch/alpha/lib/Makefile
+++ b/arch/alpha/lib/Makefile
@@ -20,12 +20,8 @@ lib-y =	__divqu.o __remqu.o __divlu.o __remlu.o \
 	checksum.o \
 	csum_partial_copy.o \
 	$(ev67-y)strlen.o \
-	$(ev67-y)strcat.o \
-	strcpy.o \
-	$(ev67-y)strncat.o \
-	strncpy.o \
-	$(ev6-y)stxcpy.o \
-	$(ev6-y)stxncpy.o \
+	stycpy.o \
+	styncpy.o \
 	$(ev67-y)strchr.o \
 	$(ev67-y)strrchr.o \
 	$(ev6-y)memchr.o \
@@ -46,11 +42,20 @@ AFLAGS___remqu.o =       -DREM
 AFLAGS___divlu.o = -DDIV       -DINTSIZE
 AFLAGS___remlu.o =       -DREM -DINTSIZE
 
-$(obj)/__divqu.o: $(obj)/$(ev6-y)divide.S
-	$(cmd_as_o_S)
-$(obj)/__remqu.o: $(obj)/$(ev6-y)divide.S
-	$(cmd_as_o_S)
-$(obj)/__divlu.o: $(obj)/$(ev6-y)divide.S
-	$(cmd_as_o_S)
-$(obj)/__remlu.o: $(obj)/$(ev6-y)divide.S
-	$(cmd_as_o_S)
+$(addprefix $(obj)/,__divqu.o __remqu.o __divlu.o __remlu.o): \
+						$(src)/$(ev6-y)divide.S FORCE
+	$(call if_changed_rule,as_o_S)
+
+# There are direct branches between {str*cpy,str*cat} and stx*cpy.
+# Ensure the branches are within range by merging these objects.
+
+LDFLAGS_stycpy.o := -r
+LDFLAGS_styncpy.o := -r
+
+$(obj)/stycpy.o: $(obj)/strcpy.o $(obj)/$(ev67-y)strcat.o \
+		 $(obj)/$(ev6-y)stxcpy.o FORCE
+	$(call if_changed,ld)
+
+$(obj)/styncpy.o: $(obj)/strncpy.o $(obj)/$(ev67-y)strncat.o \
+		 $(obj)/$(ev6-y)stxncpy.o FORCE
+	$(call if_changed,ld)
diff --git a/arch/alpha/lib/callback_srm.S b/arch/alpha/lib/callback_srm.S
index 8804bec2c6448..6093addc931a5 100644
--- a/arch/alpha/lib/callback_srm.S
+++ b/arch/alpha/lib/callback_srm.S
@@ -3,6 +3,7 @@
  */
 
 #include <asm/console.h>
+#include <asm/export.h>
 
 .text
 #define HWRPB_CRB_OFFSET 0xc0
@@ -92,6 +93,10 @@ CALLBACK(reset_env, CCB_RESET_ENV, 4)
 CALLBACK(save_env, CCB_SAVE_ENV, 1)
 CALLBACK(pswitch, CCB_PSWITCH, 3)
 CALLBACK(bios_emul, CCB_BIOS_EMUL, 5)
+
+EXPORT_SYMBOL(callback_getenv)
+EXPORT_SYMBOL(callback_setenv)
+EXPORT_SYMBOL(callback_save_env)
 	
 .data
 __alpha_using_srm:		# For use by bootpheader
diff --git a/arch/alpha/lib/checksum.c b/arch/alpha/lib/checksum.c
index 199f6efa83faa..65197c3c08451 100644
--- a/arch/alpha/lib/checksum.c
+++ b/arch/alpha/lib/checksum.c
@@ -50,6 +50,7 @@ __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
 		(__force u64)saddr + (__force u64)daddr +
 		(__force u64)sum + ((len + proto) << 8));
 }
+EXPORT_SYMBOL(csum_tcpudp_magic);
 
 __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
 				   unsigned short len,
@@ -148,6 +149,7 @@ __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 {
 	return (__force __sum16)~do_csum(iph,ihl*4);
 }
+EXPORT_SYMBOL(ip_fast_csum);
 
 /*
  * computes the checksum of a memory block at buff, length len,
@@ -182,3 +184,4 @@ __sum16 ip_compute_csum(const void *buff, int len)
 {
 	return (__force __sum16)~from64to16(do_csum(buff,len));
 }
+EXPORT_SYMBOL(ip_compute_csum);
diff --git a/arch/alpha/lib/clear_page.S b/arch/alpha/lib/clear_page.S
index a221ae266e290..263d7393c0e7a 100644
--- a/arch/alpha/lib/clear_page.S
+++ b/arch/alpha/lib/clear_page.S
@@ -3,7 +3,7 @@
  *
  * Zero an entire page.
  */
-
+#include <asm/export.h>
 	.text
 	.align 4
 	.global clear_page
@@ -37,3 +37,4 @@ clear_page:
 	nop
 
 	.end clear_page
+	EXPORT_SYMBOL(clear_page)
diff --git a/arch/alpha/lib/clear_user.S b/arch/alpha/lib/clear_user.S
index 8860316c19576..006f469fef73a 100644
--- a/arch/alpha/lib/clear_user.S
+++ b/arch/alpha/lib/clear_user.S
@@ -8,22 +8,8 @@
  * right "bytes left to zero" value (and that it is updated only _after_
  * a successful copy).  There is also some rather minor exception setup
  * stuff.
- *
- * NOTE! This is not directly C-callable, because the calling semantics
- * are different:
- *
- * Inputs:
- *	length in $0
- *	destination address in $6
- *	exception pointer in $7
- *	return address in $28 (exceptions expect it there)
- *
- * Outputs:
- *	bytes left to copy in $0
- *
- * Clobbers:
- *	$1,$2,$3,$4,$5,$6
  */
+#include <asm/export.h>
 
 /* Allow an exception for an insn; exit if we get one.  */
 #define EX(x,y...)			\
@@ -37,62 +23,63 @@
 	.set noreorder
 	.align 4
 
-	.globl __do_clear_user
-	.ent __do_clear_user
-	.frame	$30, 0, $28
+	.globl __clear_user
+	.ent __clear_user
+	.frame	$30, 0, $26
 	.prologue 0
 
 $loop:
 	and	$1, 3, $4	# e0    :
 	beq	$4, 1f		# .. e1 :
 
-0:	EX( stq_u $31, 0($6) )	# e0    : zero one word
+0:	EX( stq_u $31, 0($16) )	# e0    : zero one word
 	subq	$0, 8, $0	# .. e1 :
 	subq	$4, 1, $4	# e0    :
-	addq	$6, 8, $6	# .. e1 :
+	addq	$16, 8, $16	# .. e1 :
 	bne	$4, 0b		# e1    :
 	unop			#       :
 
 1:	bic	$1, 3, $1	# e0    :
 	beq	$1, $tail	# .. e1 :
 
-2:	EX( stq_u $31, 0($6) )	# e0    : zero four words
+2:	EX( stq_u $31, 0($16) )	# e0    : zero four words
 	subq	$0, 8, $0	# .. e1 :
-	EX( stq_u $31, 8($6) )	# e0    :
+	EX( stq_u $31, 8($16) )	# e0    :
 	subq	$0, 8, $0	# .. e1 :
-	EX( stq_u $31, 16($6) )	# e0    :
+	EX( stq_u $31, 16($16) )	# e0    :
 	subq	$0, 8, $0	# .. e1 :
-	EX( stq_u $31, 24($6) )	# e0    :
+	EX( stq_u $31, 24($16) )	# e0    :
 	subq	$0, 8, $0	# .. e1 :
 	subq	$1, 4, $1	# e0    :
-	addq	$6, 32, $6	# .. e1 :
+	addq	$16, 32, $16	# .. e1 :
 	bne	$1, 2b		# e1    :
 
 $tail:
 	bne	$2, 1f		# e1    : is there a tail to do?
-	ret	$31, ($28), 1	# .. e1 :
+	ret	$31, ($26), 1	# .. e1 :
 
-1:	EX( ldq_u $5, 0($6) )	# e0    :
+1:	EX( ldq_u $5, 0($16) )	# e0    :
 	clr	$0		# .. e1 :
 	nop			# e1    :
 	mskqh	$5, $0, $5	# e0    :
-	EX( stq_u $5, 0($6) )	# e0    :
-	ret	$31, ($28), 1	# .. e1 :
+	EX( stq_u $5, 0($16) )	# e0    :
+	ret	$31, ($26), 1	# .. e1 :
 
-__do_clear_user:
-	and	$6, 7, $4	# e0    : find dest misalignment
+__clear_user:
+	and	$17, $17, $0
+	and	$16, 7, $4	# e0    : find dest misalignment
 	beq	$0, $zerolength # .. e1 :
 	addq	$0, $4, $1	# e0    : bias counter
 	and	$1, 7, $2	# e1    : number of bytes in tail
 	srl	$1, 3, $1	# e0    :
 	beq	$4, $loop	# .. e1 :
 
-	EX( ldq_u $5, 0($6) )	# e0    : load dst word to mask back in
+	EX( ldq_u $5, 0($16) )	# e0    : load dst word to mask back in
 	beq	$1, $oneword	# .. e1 : sub-word store?
 
-	mskql	$5, $6, $5	# e0    : take care of misaligned head
-	addq	$6, 8, $6	# .. e1 :
-	EX( stq_u $5, -8($6) )	# e0    :
+	mskql	$5, $16, $5	# e0    : take care of misaligned head
+	addq	$16, 8, $16	# .. e1 :
+	EX( stq_u $5, -8($16) )	# e0    :
 	addq	$0, $4, $0	# .. e1 : bytes left -= 8 - misalignment
 	subq	$1, 1, $1	# e0    :
 	subq	$0, 8, $0	# .. e1 :
@@ -100,14 +87,15 @@ __do_clear_user:
 	unop			#       :
 
 $oneword:
-	mskql	$5, $6, $4	# e0    :
+	mskql	$5, $16, $4	# e0    :
 	mskqh	$5, $2, $5	# e0    :
 	or	$5, $4, $5	# e1    :
-	EX( stq_u $5, 0($6) )	# e0    :
+	EX( stq_u $5, 0($16) )	# e0    :
 	clr	$0		# .. e1 :
 
 $zerolength:
 $exception:
-	ret	$31, ($28), 1	# .. e1 :
+	ret	$31, ($26), 1	# .. e1 :
 
-	.end __do_clear_user
+	.end __clear_user
+	EXPORT_SYMBOL(__clear_user)
diff --git a/arch/alpha/lib/copy_page.S b/arch/alpha/lib/copy_page.S
index 9f3b97459cc64..2ee0bd0508c59 100644
--- a/arch/alpha/lib/copy_page.S
+++ b/arch/alpha/lib/copy_page.S
@@ -3,7 +3,7 @@
  *
  * Copy an entire page.
  */
-
+#include <asm/export.h>
 	.text
 	.align 4
 	.global copy_page
@@ -47,3 +47,4 @@ copy_page:
 	nop
 
 	.end copy_page
+	EXPORT_SYMBOL(copy_page)
diff --git a/arch/alpha/lib/copy_user.S b/arch/alpha/lib/copy_user.S
index 6f3fab9eb4344..159f1b7e6e495 100644
--- a/arch/alpha/lib/copy_user.S
+++ b/arch/alpha/lib/copy_user.S
@@ -9,23 +9,10 @@
  * contains the right "bytes left to copy" value (and that it is updated
  * only _after_ a successful copy). There is also some rather minor
  * exception setup stuff..
- *
- * NOTE! This is not directly C-callable, because the calling semantics are
- * different:
- *
- * Inputs:
- *	length in $0
- *	destination address in $6
- *	source address in $7
- *	return address in $28
- *
- * Outputs:
- *	bytes left to copy in $0
- *
- * Clobbers:
- *	$1,$2,$3,$4,$5,$6,$7
  */
 
+#include <asm/export.h>
+
 /* Allow an exception for an insn; exit if we get one.  */
 #define EXI(x,y...)			\
 	99: x,##y;			\
@@ -47,58 +34,59 @@
 	.ent __copy_user
 __copy_user:
 	.prologue 0
-	and $6,7,$3
+	and $18,$18,$0
+	and $16,7,$3
 	beq $0,$35
 	beq $3,$36
 	subq $3,8,$3
 	.align 4
 $37:
-	EXI( ldq_u $1,0($7) )
-	EXO( ldq_u $2,0($6) )
-	extbl $1,$7,$1
-	mskbl $2,$6,$2
-	insbl $1,$6,$1
+	EXI( ldq_u $1,0($17) )
+	EXO( ldq_u $2,0($16) )
+	extbl $1,$17,$1
+	mskbl $2,$16,$2
+	insbl $1,$16,$1
 	addq $3,1,$3
 	bis $1,$2,$1
-	EXO( stq_u $1,0($6) )
+	EXO( stq_u $1,0($16) )
 	subq $0,1,$0
-	addq $6,1,$6
-	addq $7,1,$7
+	addq $16,1,$16
+	addq $17,1,$17
 	beq $0,$41
 	bne $3,$37
 $36:
-	and $7,7,$1
+	and $17,7,$1
 	bic $0,7,$4
 	beq $1,$43
 	beq $4,$48
-	EXI( ldq_u $3,0($7) )
+	EXI( ldq_u $3,0($17) )
 	.align 4
 $50:
-	EXI( ldq_u $2,8($7) )
+	EXI( ldq_u $2,8($17) )
 	subq $4,8,$4
-	extql $3,$7,$3
-	extqh $2,$7,$1
+	extql $3,$17,$3
+	extqh $2,$17,$1
 	bis $3,$1,$1
-	EXO( stq $1,0($6) )
-	addq $7,8,$7
+	EXO( stq $1,0($16) )
+	addq $17,8,$17
 	subq $0,8,$0
-	addq $6,8,$6
+	addq $16,8,$16
 	bis $2,$2,$3
 	bne $4,$50
 $48:
 	beq $0,$41
 	.align 4
 $57:
-	EXI( ldq_u $1,0($7) )
-	EXO( ldq_u $2,0($6) )
-	extbl $1,$7,$1
-	mskbl $2,$6,$2
-	insbl $1,$6,$1
+	EXI( ldq_u $1,0($17) )
+	EXO( ldq_u $2,0($16) )
+	extbl $1,$17,$1
+	mskbl $2,$16,$2
+	insbl $1,$16,$1
 	bis $1,$2,$1
-	EXO( stq_u $1,0($6) )
+	EXO( stq_u $1,0($16) )
 	subq $0,1,$0
-	addq $6,1,$6
-	addq $7,1,$7
+	addq $16,1,$16
+	addq $17,1,$17
 	bne $0,$57
 	br $31,$41
 	.align 4
@@ -106,40 +94,27 @@ $43:
 	beq $4,$65
 	.align 4
 $66:
-	EXI( ldq $1,0($7) )
+	EXI( ldq $1,0($17) )
 	subq $4,8,$4
-	EXO( stq $1,0($6) )
-	addq $7,8,$7
+	EXO( stq $1,0($16) )
+	addq $17,8,$17
 	subq $0,8,$0
-	addq $6,8,$6
+	addq $16,8,$16
 	bne $4,$66
 $65:
 	beq $0,$41
-	EXI( ldq $2,0($7) )
-	EXO( ldq $1,0($6) )
+	EXI( ldq $2,0($17) )
+	EXO( ldq $1,0($16) )
 	mskql $2,$0,$2
 	mskqh $1,$0,$1
 	bis $2,$1,$2
-	EXO( stq $2,0($6) )
+	EXO( stq $2,0($16) )
 	bis $31,$31,$0
 $41:
 $35:
-$exitout:
-	ret $31,($28),1
-
 $exitin:
-	/* A stupid byte-by-byte zeroing of the rest of the output
-	   buffer.  This cures security holes by never leaving 
-	   random kernel data around to be copied elsewhere.  */
-
-	mov $0,$1
-$101:
-	EXO ( ldq_u $2,0($6) )
-	subq $1,1,$1
-	mskbl $2,$6,$2
-	EXO ( stq_u $2,0($6) )
-	addq $6,1,$6
-	bgt $1,$101
-	ret $31,($28),1
+$exitout:
+	ret $31,($26),1
 
 	.end __copy_user
+EXPORT_SYMBOL(__copy_user)
diff --git a/arch/alpha/lib/csum_ipv6_magic.S b/arch/alpha/lib/csum_ipv6_magic.S
index 2c2acb96deb68..e74b4544b0cce 100644
--- a/arch/alpha/lib/csum_ipv6_magic.S
+++ b/arch/alpha/lib/csum_ipv6_magic.S
@@ -12,6 +12,7 @@
  * added by Ivan Kokshaysky <ink@jurassic.park.msu.ru>
  */
 
+#include <asm/export.h>
 	.globl csum_ipv6_magic
 	.align 4
 	.ent csum_ipv6_magic
@@ -113,3 +114,4 @@ csum_ipv6_magic:
 	ret			# .. e1 :
 
 	.end csum_ipv6_magic
+	EXPORT_SYMBOL(csum_ipv6_magic)
diff --git a/arch/alpha/lib/csum_partial_copy.c b/arch/alpha/lib/csum_partial_copy.c
index 5675dca8dbb14..b4ff3b683bcd5 100644
--- a/arch/alpha/lib/csum_partial_copy.c
+++ b/arch/alpha/lib/csum_partial_copy.c
@@ -374,6 +374,7 @@ csum_partial_copy_from_user(const void __user *src, void *dst, int len,
 	}
 	return (__force __wsum)checksum;
 }
+EXPORT_SYMBOL(csum_partial_copy_from_user);
 
 __wsum
 csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
@@ -386,3 +387,4 @@ csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
 	set_fs(oldfs);
 	return checksum;
 }
+EXPORT_SYMBOL(csum_partial_copy_nocheck);
diff --git a/arch/alpha/lib/dec_and_lock.c b/arch/alpha/lib/dec_and_lock.c
index f9f5fe830e9f9..4221b40167eed 100644
--- a/arch/alpha/lib/dec_and_lock.c
+++ b/arch/alpha/lib/dec_and_lock.c
@@ -7,6 +7,7 @@
 
 #include <linux/spinlock.h>
 #include <linux/atomic.h>
+#include <linux/export.h>
 
   asm (".text					\n\
 	.global _atomic_dec_and_lock		\n\
@@ -39,3 +40,4 @@ static int __used atomic_dec_and_lock_1(atomic_t *atomic, spinlock_t *lock)
 	spin_unlock(lock);
 	return 0;
 }
+EXPORT_SYMBOL(_atomic_dec_and_lock);
diff --git a/arch/alpha/lib/divide.S b/arch/alpha/lib/divide.S
index 2d1a0484a99e0..1e33bd1276213 100644
--- a/arch/alpha/lib/divide.S
+++ b/arch/alpha/lib/divide.S
@@ -45,6 +45,7 @@
  *	$28 - compare status
  */
 
+#include <asm/export.h>
 #define halt .long 0
 
 /*
@@ -151,6 +152,7 @@ ufunction:
 	addq	$30,STACK,$30
 	ret	$31,($23),1
 	.end	ufunction
+EXPORT_SYMBOL(ufunction)
 
 /*
  * Uhh.. Ugly signed division. I'd rather not have it at all, but
@@ -193,3 +195,4 @@ sfunction:
 	addq	$30,STACK,$30
 	ret	$31,($23),1
 	.end	sfunction
+EXPORT_SYMBOL(sfunction)
diff --git a/arch/alpha/lib/ev6-clear_page.S b/arch/alpha/lib/ev6-clear_page.S
index adf4f7be0e2b6..abe99e69a1945 100644
--- a/arch/alpha/lib/ev6-clear_page.S
+++ b/arch/alpha/lib/ev6-clear_page.S
@@ -3,7 +3,7 @@
  *
  * Zero an entire page.
  */
-
+#include <asm/export.h>
         .text
         .align 4
         .global clear_page
@@ -52,3 +52,4 @@ clear_page:
 	nop
 
 	.end clear_page
+	EXPORT_SYMBOL(clear_page)
diff --git a/arch/alpha/lib/ev6-clear_user.S b/arch/alpha/lib/ev6-clear_user.S
index 4f42a16b7f53d..e179e4757ef89 100644
--- a/arch/alpha/lib/ev6-clear_user.S
+++ b/arch/alpha/lib/ev6-clear_user.S
@@ -9,21 +9,6 @@
  * a successful copy).  There is also some rather minor exception setup
  * stuff.
  *
- * NOTE! This is not directly C-callable, because the calling semantics
- * are different:
- *
- * Inputs:
- *	length in $0
- *	destination address in $6
- *	exception pointer in $7
- *	return address in $28 (exceptions expect it there)
- *
- * Outputs:
- *	bytes left to copy in $0
- *
- * Clobbers:
- *	$1,$2,$3,$4,$5,$6
- *
  * Much of the information about 21264 scheduling/coding comes from:
  *	Compiler Writer's Guide for the Alpha 21264
  *	abbreviated as 'CWG' in other comments here
@@ -43,6 +28,7 @@
  *	want to leave a hole (and we also want to avoid repeating lots of work)
  */
 
+#include <asm/export.h>
 /* Allow an exception for an insn; exit if we get one.  */
 #define EX(x,y...)			\
 	99: x,##y;			\
@@ -55,14 +41,15 @@
 	.set noreorder
 	.align 4
 
-	.globl __do_clear_user
-	.ent __do_clear_user
-	.frame	$30, 0, $28
+	.globl __clear_user
+	.ent __clear_user
+	.frame	$30, 0, $26
 	.prologue 0
 
 				# Pipeline info : Slotting & Comments
-__do_clear_user:
-	and	$6, 7, $4	# .. E  .. ..	: find dest head misalignment
+__clear_user:
+	and	$17, $17, $0
+	and	$16, 7, $4	# .. E  .. ..	: find dest head misalignment
 	beq	$0, $zerolength # U  .. .. ..	:  U L U L
 
 	addq	$0, $4, $1	# .. .. .. E	: bias counter
@@ -74,14 +61,14 @@ __do_clear_user:
 
 /*
  * Head is not aligned.  Write (8 - $4) bytes to head of destination
- * This means $6 is known to be misaligned
+ * This means $16 is known to be misaligned
  */
-	EX( ldq_u $5, 0($6) )	# .. .. .. L	: load dst word to mask back in
+	EX( ldq_u $5, 0($16) )	# .. .. .. L	: load dst word to mask back in
 	beq	$1, $onebyte	# .. .. U  ..	: sub-word store?
-	mskql	$5, $6, $5	# .. U  .. ..	: take care of misaligned head
-	addq	$6, 8, $6	# E  .. .. .. 	: L U U L
+	mskql	$5, $16, $5	# .. U  .. ..	: take care of misaligned head
+	addq	$16, 8, $16	# E  .. .. .. 	: L U U L
 
-	EX( stq_u $5, -8($6) )	# .. .. .. L	:
+	EX( stq_u $5, -8($16) )	# .. .. .. L	:
 	subq	$1, 1, $1	# .. .. E  ..	:
 	addq	$0, $4, $0	# .. E  .. ..	: bytes left -= 8 - misalignment
 	subq	$0, 8, $0	# E  .. .. ..	: U L U L
@@ -92,11 +79,11 @@ __do_clear_user:
  * values upon initial entry to the loop
  * $1 is number of quadwords to clear (zero is a valid value)
  * $2 is number of trailing bytes (0..7) ($2 never used...)
- * $6 is known to be aligned 0mod8
+ * $16 is known to be aligned 0mod8
  */
 $headalign:
 	subq	$1, 16, $4	# .. .. .. E	: If < 16, we can not use the huge loop
-	and	$6, 0x3f, $2	# .. .. E  ..	: Forward work for huge loop
+	and	$16, 0x3f, $2	# .. .. E  ..	: Forward work for huge loop
 	subq	$2, 0x40, $3	# .. E  .. ..	: bias counter (huge loop)
 	blt	$4, $trailquad	# U  .. .. ..	: U L U L
 
@@ -113,21 +100,21 @@ $headalign:
 	beq	$3, $bigalign	# U  .. .. ..	: U L U L : Aligned 0mod64
 
 $alignmod64:
-	EX( stq_u $31, 0($6) )	# .. .. .. L
+	EX( stq_u $31, 0($16) )	# .. .. .. L
 	addq	$3, 8, $3	# .. .. E  ..
 	subq	$0, 8, $0	# .. E  .. ..
 	nop			# E  .. .. ..	: U L U L
 
 	nop			# .. .. .. E
 	subq	$1, 1, $1	# .. .. E  ..
-	addq	$6, 8, $6	# .. E  .. ..
+	addq	$16, 8, $16	# .. E  .. ..
 	blt	$3, $alignmod64	# U  .. .. ..	: U L U L
 
 $bigalign:
 /*
  * $0 is the number of bytes left
  * $1 is the number of quads left
- * $6 is aligned 0mod64
+ * $16 is aligned 0mod64
  * we know that we'll be taking a minimum of one trip through
  * CWG Section 3.7.6: do not expect a sustained store rate of > 1/cycle
  * We are _not_ going to update $0 after every single store.  That
@@ -144,39 +131,39 @@ $bigalign:
 	nop			# E :
 	nop			# E :
 	nop			# E :
-	bis	$6,$6,$3	# E : U L U L : Initial wh64 address is dest
+	bis	$16,$16,$3	# E : U L U L : Initial wh64 address is dest
 	/* This might actually help for the current trip... */
 
 $do_wh64:
 	wh64	($3)		# .. .. .. L1	: memory subsystem hint
 	subq	$1, 16, $4	# .. .. E  ..	: Forward calculation - repeat the loop?
-	EX( stq_u $31, 0($6) )	# .. L  .. ..
+	EX( stq_u $31, 0($16) )	# .. L  .. ..
 	subq	$0, 8, $0	# E  .. .. ..	: U L U L
 
-	addq	$6, 128, $3	# E : Target address of wh64
-	EX( stq_u $31, 8($6) )	# L :
-	EX( stq_u $31, 16($6) )	# L :
+	addq	$16, 128, $3	# E : Target address of wh64
+	EX( stq_u $31, 8($16) )	# L :
+	EX( stq_u $31, 16($16) )	# L :
 	subq	$0, 16, $0	# E : U L L U
 
 	nop			# E :
-	EX( stq_u $31, 24($6) )	# L :
-	EX( stq_u $31, 32($6) )	# L :
+	EX( stq_u $31, 24($16) )	# L :
+	EX( stq_u $31, 32($16) )	# L :
 	subq	$0, 168, $5	# E : U L L U : two trips through the loop left?
 	/* 168 = 192 - 24, since we've already completed some stores */
 
 	subq	$0, 16, $0	# E :
-	EX( stq_u $31, 40($6) )	# L :
-	EX( stq_u $31, 48($6) )	# L :
-	cmovlt	$5, $6, $3	# E : U L L U : Latency 2, extra mapping cycle
+	EX( stq_u $31, 40($16) )	# L :
+	EX( stq_u $31, 48($16) )	# L :
+	cmovlt	$5, $16, $3	# E : U L L U : Latency 2, extra mapping cycle
 
 	subq	$1, 8, $1	# E :
 	subq	$0, 16, $0	# E :
-	EX( stq_u $31, 56($6) )	# L :
+	EX( stq_u $31, 56($16) )	# L :
 	nop			# E : U L U L
 
 	nop			# E :
 	subq	$0, 8, $0	# E :
-	addq	$6, 64, $6	# E :
+	addq	$16, 64, $16	# E :
 	bge	$4, $do_wh64	# U : U L U L
 
 $trailquad:
@@ -189,14 +176,14 @@ $trailquad:
 	beq	$1, $trailbytes	# U  .. .. ..	: U L U L : Only 0..7 bytes to go
 
 $onequad:
-	EX( stq_u $31, 0($6) )	# .. .. .. L
+	EX( stq_u $31, 0($16) )	# .. .. .. L
 	subq	$1, 1, $1	# .. .. E  ..
 	subq	$0, 8, $0	# .. E  .. ..
 	nop			# E  .. .. ..	: U L U L
 
 	nop			# .. .. .. E
 	nop			# .. .. E  ..
-	addq	$6, 8, $6	# .. E  .. ..
+	addq	$16, 8, $16	# .. E  .. ..
 	bgt	$1, $onequad	# U  .. .. ..	: U L U L
 
 	# We have an unknown number of bytes left to go.
@@ -210,9 +197,9 @@ $trailbytes:
 	# so we will use $0 as the loop counter
 	# We know for a fact that $0 > 0 zero due to previous context
 $onebyte:
-	EX( stb $31, 0($6) )	# .. .. .. L
+	EX( stb $31, 0($16) )	# .. .. .. L
 	subq	$0, 1, $0	# .. .. E  ..	:
-	addq	$6, 1, $6	# .. E  .. ..	:
+	addq	$16, 1, $16	# .. E  .. ..	:
 	bgt	$0, $onebyte	# U  .. .. ..	: U L U L
 
 $zerolength:
@@ -220,6 +207,6 @@ $exception:			# Destination for exception recovery(?)
 	nop			# .. .. .. E	:
 	nop			# .. .. E  ..	:
 	nop			# .. E  .. ..	:
-	ret	$31, ($28), 1	# L0 .. .. ..	: L U L U
-	.end __do_clear_user
-
+	ret	$31, ($26), 1	# L0 .. .. ..	: L U L U
+	.end __clear_user
+	EXPORT_SYMBOL(__clear_user)
diff --git a/arch/alpha/lib/ev6-copy_page.S b/arch/alpha/lib/ev6-copy_page.S
index b789db1927544..77935061bddbb 100644
--- a/arch/alpha/lib/ev6-copy_page.S
+++ b/arch/alpha/lib/ev6-copy_page.S
@@ -56,7 +56,7 @@
    destination pages are in the dcache, but it is my guess that this is
    less important than the dcache miss case.  */
 
-
+#include <asm/export.h>
 	.text
 	.align 4
 	.global copy_page
@@ -201,3 +201,4 @@ copy_page:
 	nop
 
 	.end copy_page
+	EXPORT_SYMBOL(copy_page)
diff --git a/arch/alpha/lib/ev6-copy_user.S b/arch/alpha/lib/ev6-copy_user.S
index db42ffe9c350b..35e6710d07005 100644
--- a/arch/alpha/lib/ev6-copy_user.S
+++ b/arch/alpha/lib/ev6-copy_user.S
@@ -12,21 +12,6 @@
  * only _after_ a successful copy). There is also some rather minor
  * exception setup stuff..
  *
- * NOTE! This is not directly C-callable, because the calling semantics are
- * different:
- *
- * Inputs:
- *	length in $0
- *	destination address in $6
- *	source address in $7
- *	return address in $28
- *
- * Outputs:
- *	bytes left to copy in $0
- *
- * Clobbers:
- *	$1,$2,$3,$4,$5,$6,$7
- *
  * Much of the information about 21264 scheduling/coding comes from:
  *	Compiler Writer's Guide for the Alpha 21264
  *	abbreviated as 'CWG' in other comments here
@@ -37,6 +22,7 @@
  *	L	- lower subcluster; L0 - subcluster L0; L1 - subcluster L1
  */
 
+#include <asm/export.h>
 /* Allow an exception for an insn; exit if we get one.  */
 #define EXI(x,y...)			\
 	99: x,##y;			\
@@ -59,10 +45,11 @@
 				# Pipeline info: Slotting & Comments
 __copy_user:
 	.prologue 0
-	subq $0, 32, $1		# .. E  .. ..	: Is this going to be a small copy?
+	andq $18, $18, $0
+	subq $18, 32, $1	# .. E  .. ..	: Is this going to be a small copy?
 	beq $0, $zerolength	# U  .. .. ..	: U L U L
 
-	and $6,7,$3		# .. .. .. E	: is leading dest misalignment
+	and $16,7,$3		# .. .. .. E	: is leading dest misalignment
 	ble $1, $onebyteloop	# .. .. U  ..	: 1st branch : small amount of data
 	beq $3, $destaligned	# .. U  .. ..	: 2nd (one cycle fetcher stall)
 	subq $3, 8, $3		# E  .. .. ..	: L U U L : trip counter
@@ -72,17 +59,17 @@ __copy_user:
  * We know we have at least one trip through this loop
  */
 $aligndest:
-	EXI( ldbu $1,0($7) )	# .. .. .. L	: Keep loads separate from stores
-	addq $6,1,$6		# .. .. E  ..	: Section 3.8 in the CWG
+	EXI( ldbu $1,0($17) )	# .. .. .. L	: Keep loads separate from stores
+	addq $16,1,$16		# .. .. E  ..	: Section 3.8 in the CWG
 	addq $3,1,$3		# .. E  .. ..	:
 	nop			# E  .. .. ..	: U L U L
 
 /*
- * the -1 is to compensate for the inc($6) done in a previous quadpack
+ * the -1 is to compensate for the inc($16) done in a previous quadpack
  * which allows us zero dependencies within either quadpack in the loop
  */
-	EXO( stb $1,-1($6) )	# .. .. .. L	:
-	addq $7,1,$7		# .. .. E  ..	: Section 3.8 in the CWG
+	EXO( stb $1,-1($16) )	# .. .. .. L	:
+	addq $17,1,$17		# .. .. E  ..	: Section 3.8 in the CWG
 	subq $0,1,$0		# .. E  .. ..	:
 	bne $3, $aligndest	# U  .. .. ..	: U L U L
 
@@ -91,29 +78,29 @@ $aligndest:
  * If we arrived via branch, we have a minimum of 32 bytes
  */
 $destaligned:
-	and $7,7,$1		# .. .. .. E	: Check _current_ source alignment
+	and $17,7,$1		# .. .. .. E	: Check _current_ source alignment
 	bic $0,7,$4		# .. .. E  ..	: number bytes as a quadword loop
-	EXI( ldq_u $3,0($7) )	# .. L  .. ..	: Forward fetch for fallthrough code
+	EXI( ldq_u $3,0($17) )	# .. L  .. ..	: Forward fetch for fallthrough code
 	beq $1,$quadaligned	# U  .. .. ..	: U L U L
 
 /*
- * In the worst case, we've just executed an ldq_u here from 0($7)
+ * In the worst case, we've just executed an ldq_u here from 0($17)
  * and we'll repeat it once if we take the branch
  */
 
 /* Misaligned quadword loop - not unrolled.  Leave it that way. */
 $misquad:
-	EXI( ldq_u $2,8($7) )	# .. .. .. L	:
+	EXI( ldq_u $2,8($17) )	# .. .. .. L	:
 	subq $4,8,$4		# .. .. E  ..	:
-	extql $3,$7,$3		# .. U  .. ..	:
-	extqh $2,$7,$1		# U  .. .. ..	: U U L L
+	extql $3,$17,$3		# .. U  .. ..	:
+	extqh $2,$17,$1		# U  .. .. ..	: U U L L
 
 	bis $3,$1,$1		# .. .. .. E	:
-	EXO( stq $1,0($6) )	# .. .. L  ..	:
-	addq $7,8,$7		# .. E  .. ..	:
+	EXO( stq $1,0($16) )	# .. .. L  ..	:
+	addq $17,8,$17		# .. E  .. ..	:
 	subq $0,8,$0		# E  .. .. ..	: U L L U
 
-	addq $6,8,$6		# .. .. .. E	:
+	addq $16,8,$16		# .. .. .. E	:
 	bis $2,$2,$3		# .. .. E  ..	:
 	nop			# .. E  .. ..	:
 	bne $4,$misquad		# U  .. .. ..	: U L U L
@@ -124,8 +111,8 @@ $misquad:
 	beq $0,$zerolength	# U  .. .. ..	: U L U L
 
 /* We know we have at least one trip through the byte loop */
-	EXI ( ldbu $2,0($7) )	# .. .. .. L	: No loads in the same quad
-	addq $6,1,$6		# .. .. E  ..	: as the store (Section 3.8 in CWG)
+	EXI ( ldbu $2,0($17) )	# .. .. .. L	: No loads in the same quad
+	addq $16,1,$16		# .. .. E  ..	: as the store (Section 3.8 in CWG)
 	nop			# .. E  .. ..	:
 	br $31, $dirtyentry	# L0 .. .. ..	: L U U L
 /* Do the trailing byte loop load, then hop into the store part of the loop */
@@ -135,8 +122,8 @@ $misquad:
  * Based upon the usage context, it's worth the effort to unroll this loop
  * $0 - number of bytes to be moved
  * $4 - number of bytes to move as quadwords
- * $6 is current destination address
- * $7 is current source address
+ * $16 is current destination address
+ * $17 is current source address
  */
 $quadaligned:
 	subq	$4, 32, $2	# .. .. .. E	: do not unroll for small stuff
@@ -154,29 +141,29 @@ $quadaligned:
  * instruction memory hint instruction).
  */
 $unroll4:
-	EXI( ldq $1,0($7) )	# .. .. .. L
-	EXI( ldq $2,8($7) )	# .. .. L  ..
+	EXI( ldq $1,0($17) )	# .. .. .. L
+	EXI( ldq $2,8($17) )	# .. .. L  ..
 	subq	$4,32,$4	# .. E  .. ..
 	nop			# E  .. .. ..	: U U L L
 
-	addq	$7,16,$7	# .. .. .. E
-	EXO( stq $1,0($6) )	# .. .. L  ..
-	EXO( stq $2,8($6) )	# .. L  .. ..
+	addq	$17,16,$17	# .. .. .. E
+	EXO( stq $1,0($16) )	# .. .. L  ..
+	EXO( stq $2,8($16) )	# .. L  .. ..
 	subq	$0,16,$0	# E  .. .. ..	: U L L U
 
-	addq	$6,16,$6	# .. .. .. E
-	EXI( ldq $1,0($7) )	# .. .. L  ..
-	EXI( ldq $2,8($7) )	# .. L  .. ..
+	addq	$16,16,$16	# .. .. .. E
+	EXI( ldq $1,0($17) )	# .. .. L  ..
+	EXI( ldq $2,8($17) )	# .. L  .. ..
 	subq	$4, 32, $3	# E  .. .. ..	: U U L L : is there enough for another trip?
 
-	EXO( stq $1,0($6) )	# .. .. .. L
-	EXO( stq $2,8($6) )	# .. .. L  ..
+	EXO( stq $1,0($16) )	# .. .. .. L
+	EXO( stq $2,8($16) )	# .. .. L  ..
 	subq	$0,16,$0	# .. E  .. ..
-	addq	$7,16,$7	# E  .. .. ..	: U L L U
+	addq	$17,16,$17	# E  .. .. ..	: U L L U
 
 	nop			# .. .. .. E
 	nop			# .. .. E  ..
-	addq	$6,16,$6	# .. E  .. ..
+	addq	$16,16,$16	# .. E  .. ..
 	bgt	$3,$unroll4	# U  .. .. ..	: U L U L
 
 	nop
@@ -185,14 +172,14 @@ $unroll4:
 	beq	$4, $noquads
 
 $onequad:
-	EXI( ldq $1,0($7) )
+	EXI( ldq $1,0($17) )
 	subq	$4,8,$4
-	addq	$7,8,$7
+	addq	$17,8,$17
 	nop
 
-	EXO( stq $1,0($6) )
+	EXO( stq $1,0($16) )
 	subq	$0,8,$0
-	addq	$6,8,$6
+	addq	$16,8,$16
 	bne	$4,$onequad
 
 $noquads:
@@ -206,54 +193,33 @@ $noquads:
  * There's no point in doing a lot of complex alignment calculations to try to
  * to quadword stuff for a small amount of data.
  *	$0 - remaining number of bytes left to copy
- *	$6 - current dest addr
- *	$7 - current source addr
+ *	$16 - current dest addr
+ *	$17 - current source addr
  */
 
 $onebyteloop:
-	EXI ( ldbu $2,0($7) )	# .. .. .. L	: No loads in the same quad
-	addq $6,1,$6		# .. .. E  ..	: as the store (Section 3.8 in CWG)
+	EXI ( ldbu $2,0($17) )	# .. .. .. L	: No loads in the same quad
+	addq $16,1,$16		# .. .. E  ..	: as the store (Section 3.8 in CWG)
 	nop			# .. E  .. ..	:
 	nop			# E  .. .. ..	: U L U L
 
 $dirtyentry:
 /*
- * the -1 is to compensate for the inc($6) done in a previous quadpack
+ * the -1 is to compensate for the inc($16) done in a previous quadpack
  * which allows us zero dependencies within either quadpack in the loop
  */
-	EXO ( stb $2,-1($6) )	# .. .. .. L	:
-	addq $7,1,$7		# .. .. E  ..	: quadpack as the load
+	EXO ( stb $2,-1($16) )	# .. .. .. L	:
+	addq $17,1,$17		# .. .. E  ..	: quadpack as the load
 	subq $0,1,$0		# .. E  .. ..	: change count _after_ copy
 	bgt $0,$onebyteloop	# U  .. .. ..	: U L U L
 
 $zerolength:
+$exitin:
 $exitout:			# Destination for exception recovery(?)
 	nop			# .. .. .. E
 	nop			# .. .. E  ..
 	nop			# .. E  .. ..
-	ret $31,($28),1		# L0 .. .. ..	: L U L U
-
-$exitin:
-
-	/* A stupid byte-by-byte zeroing of the rest of the output
-	   buffer.  This cures security holes by never leaving 
-	   random kernel data around to be copied elsewhere.  */
-
-	nop
-	nop
-	nop
-	mov	$0,$1
-
-$101:
-	EXO ( stb $31,0($6) )	# L
-	subq $1,1,$1		# E
-	addq $6,1,$6		# E
-	bgt $1,$101		# U
-
-	nop
-	nop
-	nop
-	ret $31,($28),1		# L0
+	ret $31,($26),1		# L0 .. .. ..	: L U L U
 
 	.end __copy_user
-
+	EXPORT_SYMBOL(__copy_user)
diff --git a/arch/alpha/lib/ev6-csum_ipv6_magic.S b/arch/alpha/lib/ev6-csum_ipv6_magic.S
index fc0bc399f872d..de62627ac4fe1 100644
--- a/arch/alpha/lib/ev6-csum_ipv6_magic.S
+++ b/arch/alpha/lib/ev6-csum_ipv6_magic.S
@@ -52,6 +52,7 @@
  * may cause additional delay in rare cases (load-load replay traps).
  */
 
+#include <asm/export.h>
 	.globl csum_ipv6_magic
 	.align 4
 	.ent csum_ipv6_magic
@@ -148,3 +149,4 @@ csum_ipv6_magic:
 	ret			# L0 : L U L U
 
 	.end csum_ipv6_magic
+	EXPORT_SYMBOL(csum_ipv6_magic)
diff --git a/arch/alpha/lib/ev6-divide.S b/arch/alpha/lib/ev6-divide.S
index 2a82b9be93fa2..d18dc0e96e3d7 100644
--- a/arch/alpha/lib/ev6-divide.S
+++ b/arch/alpha/lib/ev6-divide.S
@@ -55,6 +55,7 @@
  * Try not to change the actual algorithm if possible for consistency.
  */
 
+#include <asm/export.h>
 #define halt .long 0
 
 /*
@@ -205,6 +206,7 @@ ufunction:
 	addq	$30,STACK,$30		# E :
 	ret	$31,($23),1		# L0 : L U U L
 	.end	ufunction
+EXPORT_SYMBOL(ufunction)
 
 /*
  * Uhh.. Ugly signed division. I'd rather not have it at all, but
@@ -257,3 +259,4 @@ sfunction:
 	addq	$30,STACK,$30		# E :
 	ret	$31,($23),1		# L0 : L U U L
 	.end	sfunction
+EXPORT_SYMBOL(sfunction)
diff --git a/arch/alpha/lib/ev6-memchr.S b/arch/alpha/lib/ev6-memchr.S
index 1a5f71b9d8b10..419adc53ccb4e 100644
--- a/arch/alpha/lib/ev6-memchr.S
+++ b/arch/alpha/lib/ev6-memchr.S
@@ -27,7 +27,7 @@
  *	L	- lower subcluster; L0 - subcluster L0; L1 - subcluster L1
  * Try not to change the actual algorithm if possible for consistency.
  */
-
+#include <asm/export.h>
         .set noreorder
         .set noat
 
@@ -189,3 +189,4 @@ $not_found:
 	ret			# L0 :
 
         .end memchr
+	EXPORT_SYMBOL(memchr)
diff --git a/arch/alpha/lib/ev6-memcpy.S b/arch/alpha/lib/ev6-memcpy.S
index 52b37b0f2af51..b19798b2efc09 100644
--- a/arch/alpha/lib/ev6-memcpy.S
+++ b/arch/alpha/lib/ev6-memcpy.S
@@ -19,7 +19,7 @@
  * Temp usage notes:
  *	$1,$2,		- scratch
  */
-
+#include <asm/export.h>
 	.set noreorder
 	.set noat
 
@@ -242,6 +242,7 @@ $nomoredata:
 	nop				# E :
 
 	.end memcpy
+	EXPORT_SYMBOL(memcpy)
 
 /* For backwards module compatibility.  */
 __memcpy = memcpy
diff --git a/arch/alpha/lib/ev6-memset.S b/arch/alpha/lib/ev6-memset.S
index 356bb2fdd7056..fed21c6893e8e 100644
--- a/arch/alpha/lib/ev6-memset.S
+++ b/arch/alpha/lib/ev6-memset.S
@@ -26,7 +26,7 @@
  * as fixes will need to be made in multiple places.  The performance gain
  * is worth it.
  */
-
+#include <asm/export.h>
 	.set noat
 	.set noreorder
 .text
@@ -229,6 +229,7 @@ end_b:
 	nop
 	ret $31,($26),1		# L0 :
 	.end ___memset
+	EXPORT_SYMBOL(___memset)
 
 	/*
 	 * This is the original body of code, prior to replication and
@@ -406,6 +407,7 @@ end:
 	nop
 	ret $31,($26),1		# L0 :
 	.end __constant_c_memset
+	EXPORT_SYMBOL(__constant_c_memset)
 
 	/*
 	 * This is a replicant of the __constant_c_memset code, rescheduled
@@ -594,6 +596,9 @@ end_w:
 	ret $31,($26),1		# L0 :
 
 	.end __memsetw
+	EXPORT_SYMBOL(__memsetw)
 
 memset = ___memset
 __memset = ___memset
+	EXPORT_SYMBOL(memset)
+	EXPORT_SYMBOL(__memset)
diff --git a/arch/alpha/lib/ev67-strcat.S b/arch/alpha/lib/ev67-strcat.S
index c426fe3ed72f4..b69f60419be1b 100644
--- a/arch/alpha/lib/ev67-strcat.S
+++ b/arch/alpha/lib/ev67-strcat.S
@@ -19,7 +19,7 @@
  * string once.
  */
 
-
+#include <asm/export.h>
 	.text
 
 	.align 4
@@ -52,3 +52,4 @@ $found:	cttz	$2, $3		# U0 :
 	br	__stxcpy	# L0 :
 
 	.end strcat
+	EXPORT_SYMBOL(strcat)
diff --git a/arch/alpha/lib/ev67-strchr.S b/arch/alpha/lib/ev67-strchr.S
index fbb7b4ffade9e..ea8f2f35db9ce 100644
--- a/arch/alpha/lib/ev67-strchr.S
+++ b/arch/alpha/lib/ev67-strchr.S
@@ -15,7 +15,7 @@
  *	L	- lower subcluster; L0 - subcluster L0; L1 - subcluster L1
  * Try not to change the actual algorithm if possible for consistency.
  */
-
+#include <asm/export.h>
 #include <asm/regdef.h>
 
 	.set noreorder
@@ -86,3 +86,4 @@ $found:	negq    t0, t1		# E : clear all but least set bit
 	ret			# L0 :
 
 	.end strchr
+	EXPORT_SYMBOL(strchr)
diff --git a/arch/alpha/lib/ev67-strlen.S b/arch/alpha/lib/ev67-strlen.S
index 503928072523e..736fd41884a8c 100644
--- a/arch/alpha/lib/ev67-strlen.S
+++ b/arch/alpha/lib/ev67-strlen.S
@@ -17,7 +17,7 @@
  *	U	- upper subcluster; U0 - subcluster U0; U1 - subcluster U1
  *	L	- lower subcluster; L0 - subcluster L0; L1 - subcluster L1
  */
-
+#include <asm/export.h>
 	.set noreorder
 	.set noat
 
@@ -47,3 +47,4 @@ $found:
 	ret	$31, ($26)	# L0 :
 
 	.end	strlen
+	EXPORT_SYMBOL(strlen)
diff --git a/arch/alpha/lib/ev67-strncat.S b/arch/alpha/lib/ev67-strncat.S
index 4ae716cd2bfbf..cd35cbade73ae 100644
--- a/arch/alpha/lib/ev67-strncat.S
+++ b/arch/alpha/lib/ev67-strncat.S
@@ -20,7 +20,7 @@
  * Try not to change the actual algorithm if possible for consistency.
  */
 
-
+#include <asm/export.h>
 	.text
 
 	.align 4
@@ -92,3 +92,4 @@ $zerocount:
 	ret			# L0 :
 
 	.end strncat
+	EXPORT_SYMBOL(strncat)
diff --git a/arch/alpha/lib/ev67-strrchr.S b/arch/alpha/lib/ev67-strrchr.S
index dd0d8c6b9f59f..747455f0328cf 100644
--- a/arch/alpha/lib/ev67-strrchr.S
+++ b/arch/alpha/lib/ev67-strrchr.S
@@ -18,7 +18,7 @@
  *	L	- lower subcluster; L0 - subcluster L0; L1 - subcluster L1
  */
 
-
+#include <asm/export.h>
 #include <asm/regdef.h>
 
 	.set noreorder
@@ -107,3 +107,4 @@ $eos:
 	nop
 
 	.end strrchr
+	EXPORT_SYMBOL(strrchr)
diff --git a/arch/alpha/lib/fpreg.c b/arch/alpha/lib/fpreg.c
index 05017ba34c3cc..4aa6dbfa14eec 100644
--- a/arch/alpha/lib/fpreg.c
+++ b/arch/alpha/lib/fpreg.c
@@ -4,6 +4,9 @@
  * (C) Copyright 1998 Linus Torvalds
  */
 
+#include <linux/compiler.h>
+#include <linux/export.h>
+
 #if defined(CONFIG_ALPHA_EV6) || defined(CONFIG_ALPHA_EV67)
 #define STT(reg,val)  asm volatile ("ftoit $f"#reg",%0" : "=r"(val));
 #else
@@ -52,6 +55,7 @@ alpha_read_fp_reg (unsigned long reg)
 	}
 	return val;
 }
+EXPORT_SYMBOL(alpha_read_fp_reg);
 
 #if defined(CONFIG_ALPHA_EV6) || defined(CONFIG_ALPHA_EV67)
 #define LDT(reg,val)  asm volatile ("itoft %0,$f"#reg : : "r"(val));
@@ -97,6 +101,7 @@ alpha_write_fp_reg (unsigned long reg, unsigned long val)
 	      case 31: LDT(31, val); break;
 	}
 }
+EXPORT_SYMBOL(alpha_write_fp_reg);
 
 #if defined(CONFIG_ALPHA_EV6) || defined(CONFIG_ALPHA_EV67)
 #define STS(reg,val)  asm volatile ("ftois $f"#reg",%0" : "=r"(val));
@@ -146,6 +151,7 @@ alpha_read_fp_reg_s (unsigned long reg)
 	}
 	return val;
 }
+EXPORT_SYMBOL(alpha_read_fp_reg_s);
 
 #if defined(CONFIG_ALPHA_EV6) || defined(CONFIG_ALPHA_EV67)
 #define LDS(reg,val)  asm volatile ("itofs %0,$f"#reg : : "r"(val));
@@ -191,3 +197,4 @@ alpha_write_fp_reg_s (unsigned long reg, unsigned long val)
 	      case 31: LDS(31, val); break;
 	}
 }
+EXPORT_SYMBOL(alpha_write_fp_reg_s);
diff --git a/arch/alpha/lib/memchr.S b/arch/alpha/lib/memchr.S
index 14427eeb555e6..c13d3eca2e059 100644
--- a/arch/alpha/lib/memchr.S
+++ b/arch/alpha/lib/memchr.S
@@ -31,7 +31,7 @@ For correctness consider that:
       - only minimum number of quadwords may be accessed
       - the third argument is an unsigned long
 */
-
+#include <asm/export.h>
         .set noreorder
         .set noat
 
@@ -162,3 +162,4 @@ $not_found:
 	ret			# .. e1 :
 
         .end memchr
+	EXPORT_SYMBOL(memchr)
diff --git a/arch/alpha/lib/memcpy.c b/arch/alpha/lib/memcpy.c
index 64083fc732389..57d9291ad172c 100644
--- a/arch/alpha/lib/memcpy.c
+++ b/arch/alpha/lib/memcpy.c
@@ -16,6 +16,7 @@
  */
 
 #include <linux/types.h>
+#include <linux/export.h>
 
 /*
  * This should be done in one go with ldq_u*2/mask/stq_u. Do it
@@ -158,6 +159,4 @@ void * memcpy(void * dest, const void *src, size_t n)
 	__memcpy_unaligned_up ((unsigned long) dest, (unsigned long) src, n);
 	return dest;
 }
-
-/* For backward modules compatibility, define __memcpy.  */
-asm("__memcpy = memcpy; .globl __memcpy");
+EXPORT_SYMBOL(memcpy);
diff --git a/arch/alpha/lib/memmove.S b/arch/alpha/lib/memmove.S
index eb3b6e02242f4..ff6a39d38385c 100644
--- a/arch/alpha/lib/memmove.S
+++ b/arch/alpha/lib/memmove.S
@@ -6,7 +6,7 @@
  * This is hand-massaged output from the original memcpy.c.  We defer to
  * memcpy whenever possible; the backwards copy loops are not unrolled.
  */
-        
+#include <asm/export.h>
 	.set noat
 	.set noreorder
 	.text
@@ -179,3 +179,4 @@ $egress:
 	nop
 
 	.end memmove
+	EXPORT_SYMBOL(memmove)
diff --git a/arch/alpha/lib/memset.S b/arch/alpha/lib/memset.S
index 76ccc6d1f364d..89a26f5e89de3 100644
--- a/arch/alpha/lib/memset.S
+++ b/arch/alpha/lib/memset.S
@@ -13,7 +13,7 @@
  * The scheduling comments are according to the EV5 documentation (and done by 
  * hand, so they might well be incorrect, please do tell me about it..)
  */
-
+#include <asm/export.h>
 	.set noat
 	.set noreorder
 .text
@@ -106,6 +106,8 @@ within_one_quad:
 end:
 	ret $31,($26),1		/* E1 */
 	.end ___memset
+EXPORT_SYMBOL(___memset)
+EXPORT_SYMBOL(__constant_c_memset)
 
 	.align 5
 	.ent __memsetw
@@ -122,6 +124,9 @@ __memsetw:
 	br __constant_c_memset	/* .. E1 */
 
 	.end __memsetw
+EXPORT_SYMBOL(__memsetw)
 
 memset = ___memset
 __memset = ___memset
+	EXPORT_SYMBOL(memset)
+	EXPORT_SYMBOL(__memset)
diff --git a/arch/alpha/lib/strcat.S b/arch/alpha/lib/strcat.S
index 393f50384878f..249837b03d4b9 100644
--- a/arch/alpha/lib/strcat.S
+++ b/arch/alpha/lib/strcat.S
@@ -4,6 +4,7 @@
  *
  * Append a null-terminated string from SRC to DST.
  */
+#include <asm/export.h>
 
 	.text
 
@@ -50,3 +51,4 @@ $found:	negq    $2, $3		# clear all but least set bit
 	br	__stxcpy
 
 	.end strcat
+EXPORT_SYMBOL(strcat);
diff --git a/arch/alpha/lib/strchr.S b/arch/alpha/lib/strchr.S
index 011a175e83292..7412a173ea393 100644
--- a/arch/alpha/lib/strchr.S
+++ b/arch/alpha/lib/strchr.S
@@ -5,7 +5,7 @@
  * Return the address of a given character within a null-terminated
  * string, or null if it is not found.
  */
-
+#include <asm/export.h>
 #include <asm/regdef.h>
 
 	.set noreorder
@@ -68,3 +68,4 @@ $retnull:
 	ret			# .. e1 :
 
 	.end strchr
+	EXPORT_SYMBOL(strchr)
diff --git a/arch/alpha/lib/strcpy.S b/arch/alpha/lib/strcpy.S
index e0728e4ad21fd..98deae1e4d085 100644
--- a/arch/alpha/lib/strcpy.S
+++ b/arch/alpha/lib/strcpy.S
@@ -5,7 +5,7 @@
  * Copy a null-terminated string from SRC to DST.  Return a pointer
  * to the null-terminator in the source.
  */
-
+#include <asm/export.h>
 	.text
 
 	.align 3
@@ -21,3 +21,4 @@ strcpy:
 	br	__stxcpy	# do the copy
 
 	.end strcpy
+	EXPORT_SYMBOL(strcpy)
diff --git a/arch/alpha/lib/strlen.S b/arch/alpha/lib/strlen.S
index fe63353de152d..79c416f71bacd 100644
--- a/arch/alpha/lib/strlen.S
+++ b/arch/alpha/lib/strlen.S
@@ -11,7 +11,7 @@
  *	  do this instead of the 9 instructions that
  *	  binary search needs).
  */
-
+#include <asm/export.h>
 	.set noreorder
 	.set noat
 
@@ -55,3 +55,4 @@ done:	subq	$0, $16, $0
 	ret	$31, ($26)
 
 	.end	strlen
+	EXPORT_SYMBOL(strlen)
diff --git a/arch/alpha/lib/strncat.S b/arch/alpha/lib/strncat.S
index a8278163c9720..6c29ea60869ae 100644
--- a/arch/alpha/lib/strncat.S
+++ b/arch/alpha/lib/strncat.S
@@ -9,7 +9,7 @@
  * past count, whereas libc may write to count+1.  This follows the generic
  * implementation in lib/string.c and is, IMHO, more sensible.
  */
-
+#include <asm/export.h>
 	.text
 
 	.align 3
@@ -82,3 +82,4 @@ $zerocount:
 	ret
 
 	.end strncat
+	EXPORT_SYMBOL(strncat)
diff --git a/arch/alpha/lib/strncpy.S b/arch/alpha/lib/strncpy.S
index a46f7f3ad8c73..e102cf1567ddd 100644
--- a/arch/alpha/lib/strncpy.S
+++ b/arch/alpha/lib/strncpy.S
@@ -10,7 +10,7 @@
  * version has cropped that bit o' nastiness as well as assuming that
  * __stxncpy is in range of a branch.
  */
-
+#include <asm/export.h>
 	.set noat
 	.set noreorder
 
@@ -79,3 +79,4 @@ $zerolen:
 	ret
 
 	.end	strncpy
+	EXPORT_SYMBOL(strncpy)
diff --git a/arch/alpha/lib/strrchr.S b/arch/alpha/lib/strrchr.S
index 1970dc07cfd12..4bc6cb4b9812e 100644
--- a/arch/alpha/lib/strrchr.S
+++ b/arch/alpha/lib/strrchr.S
@@ -5,7 +5,7 @@
  * Return the address of the last occurrence of a given character
  * within a null-terminated string, or null if it is not found.
  */
-
+#include <asm/export.h>
 #include <asm/regdef.h>
 
 	.set noreorder
@@ -85,3 +85,4 @@ $retnull:
 	ret			# .. e1 :
 
 	.end strrchr
+	EXPORT_SYMBOL(strrchr)
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index edd392fdc14bb..b44fdee5cd6b2 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -1789,7 +1789,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	 * Prevent userspace from creating a memory region outside of the IPA
 	 * space addressable by the KVM guest IPA space.
 	 */
-	if (memslot->base_gfn + memslot->npages >=
+	if (memslot->base_gfn + memslot->npages >
 	    (KVM_PHYS_SIZE >> PAGE_SHIFT))
 		return -EFAULT;
 
diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h
index a734b4b34d26b..9c7eb907b1653 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/code-patching.h
@@ -45,7 +45,7 @@ void __patch_exception(int exc, unsigned long addr);
 #endif
 
 #define OP_RT_RA_MASK	0xffff0000UL
-#define LIS_R2		0x3c020000UL
+#define LIS_R2		0x3c400000UL
 #define ADDIS_R2_R12	0x3c4c0000UL
 #define ADDI_R2_R2	0x38420000UL
 
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index e593e7f856ed0..7a80e1cff6e2e 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2008,7 +2008,17 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			left += period;
 			if (left <= 0)
 				left = period;
-			record = siar_valid(regs);
+
+			/*
+			 * If address is not requested in the sample via
+			 * PERF_SAMPLE_IP, just record that sample irrespective
+			 * of SIAR valid check.
+			 */
+			if (event->attr.sample_type & PERF_SAMPLE_IP)
+				record = siar_valid(regs);
+			else
+				record = 1;
+
 			event->hw.last_period = event->hw.sample_period;
 		}
 		if (left < 0x80000000LL)
@@ -2026,9 +2036,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 	 * MMCR2. Check attr.exclude_kernel and address to drop the sample in
 	 * these cases.
 	 */
-	if (event->attr.exclude_kernel && record)
-		if (is_kernel_addr(mfspr(SPRN_SIAR)))
-			record = 0;
+	if (event->attr.exclude_kernel &&
+	    (event->attr.sample_type & PERF_SAMPLE_IP) &&
+	    is_kernel_addr(mfspr(SPRN_SIAR)))
+		record = 0;
 
 	/*
 	 * Finally record data if requested.
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index f113fcd781d87..486f0d4f9aee8 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -738,7 +738,7 @@ static int smp_add_core(struct sclp_core_entry *core, cpumask_t *avail,
 static int __smp_rescan_cpus(struct sclp_core_info *info, bool early)
 {
 	struct sclp_core_entry *core;
-	cpumask_t avail;
+	static cpumask_t avail;
 	bool configured;
 	u16 core_id;
 	int nr, i;
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 31bbe5410b180..ae6b798b76bb2 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -870,7 +870,7 @@ static void set_fdc(int drive)
 }
 
 /* locks the driver */
-static int lock_fdc(int drive, bool interruptible)
+static int lock_fdc(int drive)
 {
 	if (WARN(atomic_read(&usage_count) == 0,
 		 "Trying to lock fdc while usage count=0\n"))
@@ -2180,7 +2180,7 @@ static int do_format(int drive, struct format_descr *tmp_format_req)
 {
 	int ret;
 
-	if (lock_fdc(drive, true))
+	if (lock_fdc(drive))
 		return -EINTR;
 
 	set_floppy(drive);
@@ -2967,7 +2967,7 @@ static int user_reset_fdc(int drive, int arg, bool interruptible)
 {
 	int ret;
 
-	if (lock_fdc(drive, interruptible))
+	if (lock_fdc(drive))
 		return -EINTR;
 
 	if (arg == FD_RESET_ALWAYS)
@@ -3254,7 +3254,7 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g,
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 		mutex_lock(&open_lock);
-		if (lock_fdc(drive, true)) {
+		if (lock_fdc(drive)) {
 			mutex_unlock(&open_lock);
 			return -EINTR;
 		}
@@ -3274,7 +3274,7 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g,
 	} else {
 		int oldStretch;
 
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		if (cmd != FDDEFPRM) {
 			/* notice a disk change immediately, else
@@ -3360,7 +3360,7 @@ static int get_floppy_geometry(int drive, int type, struct floppy_struct **g)
 	if (type)
 		*g = &floppy_type[type];
 	else {
-		if (lock_fdc(drive, false))
+		if (lock_fdc(drive))
 			return -EINTR;
 		if (poll_drive(false, 0) == -EINTR)
 			return -EINTR;
@@ -3462,7 +3462,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		if (UDRS->fd_ref != 1)
 			/* somebody else has this drive open */
 			return -EBUSY;
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 
 		/* do the actual eject. Fails on
@@ -3474,7 +3474,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		process_fd_request();
 		return ret;
 	case FDCLRPRM:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		current_type[drive] = NULL;
 		floppy_sizes[drive] = MAX_DISK_SIZE << 1;
@@ -3499,7 +3499,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		UDP->flags &= ~FTD_MSG;
 		return 0;
 	case FDFMTBEG:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		if (poll_drive(true, FD_RAW_NEED_DISK) == -EINTR)
 			return -EINTR;
@@ -3516,7 +3516,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		return do_format(drive, &inparam.f);
 	case FDFMTEND:
 	case FDFLUSH:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		return invalidate_drive(bdev);
 	case FDSETEMSGTRESH:
@@ -3542,7 +3542,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		outparam = UDP;
 		break;
 	case FDPOLLDRVSTAT:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		if (poll_drive(true, FD_RAW_NEED_DISK) == -EINTR)
 			return -EINTR;
@@ -3565,7 +3565,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 	case FDRAWCMD:
 		if (type)
 			return -EINVAL;
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		set_floppy(drive);
 		i = raw_cmd_ioctl(cmd, (void __user *)param);
@@ -3574,7 +3574,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		process_fd_request();
 		return i;
 	case FDTWADDLE:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		twaddle();
 		process_fd_request();
@@ -3801,7 +3801,7 @@ static int compat_getdrvstat(int drive, bool poll,
 	mutex_lock(&floppy_mutex);
 
 	if (poll) {
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			goto Eintr;
 		if (poll_drive(true, FD_RAW_NEED_DISK) == -EINTR)
 			goto Eintr;
@@ -4109,7 +4109,8 @@ static unsigned int floppy_check_events(struct gendisk *disk,
 		return DISK_EVENT_MEDIA_CHANGE;
 
 	if (time_after(jiffies, UDRS->last_checked + UDP->checkfreq)) {
-		lock_fdc(drive, false);
+		if (lock_fdc(drive))
+			return -EINTR;
 		poll_drive(false, 0);
 		process_fd_request();
 	}
@@ -4208,7 +4209,9 @@ static int floppy_revalidate(struct gendisk *disk)
 			 "VFS: revalidate called on non-open device.\n"))
 			return -EFAULT;
 
-		lock_fdc(drive, false);
+		res = lock_fdc(drive);
+		if (res)
+			return res;
 		cf = (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags) ||
 		      test_bit(FD_VERIFY_BIT, &UDRS->flags));
 		if (!(cf || test_bit(drive, &fake_change) || drive_no_geom(drive))) {
diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c
index 0d9137408e3c8..a53271acc2a25 100644
--- a/drivers/block/rsxx/core.c
+++ b/drivers/block/rsxx/core.c
@@ -895,6 +895,7 @@ static int rsxx_pci_probe(struct pci_dev *dev,
 	card->event_wq = create_singlethread_workqueue(DRIVER_NAME"_event");
 	if (!card->event_wq) {
 		dev_err(CARD_TO_DEV(card), "Failed card event setup.\n");
+		st = -ENOMEM;
 		goto failed_event_handler;
 	}
 
diff --git a/drivers/iio/imu/adis16400_buffer.c b/drivers/iio/imu/adis16400_buffer.c
index 90c24a23c679b..c0eb9dfd1c454 100644
--- a/drivers/iio/imu/adis16400_buffer.c
+++ b/drivers/iio/imu/adis16400_buffer.c
@@ -37,8 +37,11 @@ int adis16400_update_scan_mode(struct iio_dev *indio_dev,
 		return -ENOMEM;
 
 	adis->buffer = kzalloc(burst_length + sizeof(u16), GFP_KERNEL);
-	if (!adis->buffer)
+	if (!adis->buffer) {
+		kfree(adis->xfer);
+		adis->xfer = NULL;
 		return -ENOMEM;
+	}
 
 	tx = adis->buffer + burst_length;
 	tx[0] = ADIS_READ_REG(ADIS16400_GLOB_CMD);
diff --git a/drivers/iio/imu/adis_buffer.c b/drivers/iio/imu/adis_buffer.c
index 36607d52fee06..9de553e8c214f 100644
--- a/drivers/iio/imu/adis_buffer.c
+++ b/drivers/iio/imu/adis_buffer.c
@@ -39,8 +39,11 @@ int adis_update_scan_mode(struct iio_dev *indio_dev,
 		return -ENOMEM;
 
 	adis->buffer = kzalloc(indio_dev->scan_bytes * 2, GFP_KERNEL);
-	if (!adis->buffer)
+	if (!adis->buffer) {
+		kfree(adis->xfer);
+		adis->xfer = NULL;
 		return -ENOMEM;
+	}
 
 	rx = adis->buffer;
 	tx = rx + scan_count;
diff --git a/drivers/media/usb/hdpvr/hdpvr-core.c b/drivers/media/usb/hdpvr/hdpvr-core.c
index 7b5c493f02b0a..9f95b048123dc 100644
--- a/drivers/media/usb/hdpvr/hdpvr-core.c
+++ b/drivers/media/usb/hdpvr/hdpvr-core.c
@@ -297,7 +297,7 @@ static int hdpvr_probe(struct usb_interface *interface,
 	/* register v4l2_device early so it can be used for printks */
 	if (v4l2_device_register(&interface->dev, &dev->v4l2_dev)) {
 		dev_err(&interface->dev, "v4l2_device_register failed\n");
-		goto error;
+		goto error_free_dev;
 	}
 
 	mutex_init(&dev->io_mutex);
@@ -306,7 +306,7 @@ static int hdpvr_probe(struct usb_interface *interface,
 	dev->usbc_buf = kmalloc(64, GFP_KERNEL);
 	if (!dev->usbc_buf) {
 		v4l2_err(&dev->v4l2_dev, "Out of memory\n");
-		goto error;
+		goto error_v4l2_unregister;
 	}
 
 	init_waitqueue_head(&dev->wait_buffer);
@@ -314,7 +314,7 @@ static int hdpvr_probe(struct usb_interface *interface,
 
 	dev->workqueue = create_singlethread_workqueue("hdpvr_buffer");
 	if (!dev->workqueue)
-		goto error;
+		goto err_free_usbc;
 
 	dev->options = hdpvr_default_options;
 
@@ -348,13 +348,13 @@ static int hdpvr_probe(struct usb_interface *interface,
 	}
 	if (!dev->bulk_in_endpointAddr) {
 		v4l2_err(&dev->v4l2_dev, "Could not find bulk-in endpoint\n");
-		goto error;
+		goto error_put_usb;
 	}
 
 	/* init the device */
 	if (hdpvr_device_init(dev)) {
 		v4l2_err(&dev->v4l2_dev, "device init failed\n");
-		goto error;
+		goto error_put_usb;
 	}
 
 	mutex_lock(&dev->io_mutex);
@@ -362,7 +362,7 @@ static int hdpvr_probe(struct usb_interface *interface,
 		mutex_unlock(&dev->io_mutex);
 		v4l2_err(&dev->v4l2_dev,
 			 "allocating transfer buffers failed\n");
-		goto error;
+		goto error_put_usb;
 	}
 	mutex_unlock(&dev->io_mutex);
 
@@ -370,7 +370,7 @@ static int hdpvr_probe(struct usb_interface *interface,
 	retval = hdpvr_register_i2c_adapter(dev);
 	if (retval < 0) {
 		v4l2_err(&dev->v4l2_dev, "i2c adapter register failed\n");
-		goto error;
+		goto error_free_buffers;
 	}
 
 	client = hdpvr_register_ir_rx_i2c(dev);
@@ -412,15 +412,20 @@ static int hdpvr_probe(struct usb_interface *interface,
 reg_fail:
 #if IS_ENABLED(CONFIG_I2C)
 	i2c_del_adapter(&dev->i2c_adapter);
+error_free_buffers:
 #endif
+	hdpvr_free_buffers(dev);
+error_put_usb:
+	usb_put_dev(dev->udev);
+	/* Destroy single thread */
+	destroy_workqueue(dev->workqueue);
+err_free_usbc:
+	kfree(dev->usbc_buf);
+error_v4l2_unregister:
+	v4l2_device_unregister(&dev->v4l2_dev);
+error_free_dev:
+	kfree(dev);
 error:
-	if (dev) {
-		/* Destroy single thread */
-		if (dev->workqueue)
-			destroy_workqueue(dev->workqueue);
-		/* this frees allocated memory */
-		hdpvr_delete(dev);
-	}
 	return retval;
 }
 
diff --git a/drivers/media/usb/usbtv/usbtv-audio.c b/drivers/media/usb/usbtv/usbtv-audio.c
index 5dab02432e821..17128340ea5da 100644
--- a/drivers/media/usb/usbtv/usbtv-audio.c
+++ b/drivers/media/usb/usbtv/usbtv-audio.c
@@ -384,7 +384,7 @@ void usbtv_audio_free(struct usbtv *usbtv)
 	cancel_work_sync(&usbtv->snd_trigger);
 
 	if (usbtv->snd && usbtv->udev) {
-		snd_card_free(usbtv->snd);
+		snd_card_free_when_closed(usbtv->snd);
 		usbtv->snd = NULL;
 	}
 }
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 7844baecf3060..1506152983139 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -400,10 +400,6 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
 
 		/* EXT_CSD value is in units of 10ms, but we store in ms */
 		card->ext_csd.part_time = 10 * ext_csd[EXT_CSD_PART_SWITCH_TIME];
-		/* Some eMMC set the value too low so set a minimum */
-		if (card->ext_csd.part_time &&
-		    card->ext_csd.part_time < MMC_MIN_PART_SWITCH_TIME)
-			card->ext_csd.part_time = MMC_MIN_PART_SWITCH_TIME;
 
 		/* Sleep / awake timeout in 100ns units */
 		if (sa_shift > 0 && sa_shift <= 0x17)
@@ -585,6 +581,17 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
 		card->ext_csd.data_sector_size = 512;
 	}
 
+	/*
+	 * GENERIC_CMD6_TIME is to be used "unless a specific timeout is defined
+	 * when accessing a specific field", so use it here if there is no
+	 * PARTITION_SWITCH_TIME.
+	 */
+	if (!card->ext_csd.part_time)
+		card->ext_csd.part_time = card->ext_csd.generic_cmd6_time;
+	/* Some eMMC set the value too low so set a minimum */
+	if (card->ext_csd.part_time < MMC_MIN_PART_SWITCH_TIME)
+		card->ext_csd.part_time = MMC_MIN_PART_SWITCH_TIME;
+
 	/* eMMC v5 or later */
 	if (card->ext_csd.rev >= 7) {
 		memcpy(card->ext_csd.fwrev, &ext_csd[EXT_CSD_FIRMWARE_VERSION],
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 5ef25463494f4..1770c8df9d1b8 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -720,13 +720,13 @@ static void msdc_track_cmd_data(struct msdc_host *host,
 static void msdc_request_done(struct msdc_host *host, struct mmc_request *mrq)
 {
 	unsigned long flags;
-	bool ret;
 
-	ret = cancel_delayed_work(&host->req_timeout);
-	if (!ret) {
-		/* delay work already running */
-		return;
-	}
+	/*
+	 * No need check the return value of cancel_delayed_work, as only ONE
+	 * path will go here!
+	 */
+	cancel_delayed_work(&host->req_timeout);
+
 	spin_lock_irqsave(&host->lock, flags);
 	host->mrq = NULL;
 	spin_unlock_irqrestore(&host->lock, flags);
@@ -747,7 +747,7 @@ static bool msdc_cmd_done(struct msdc_host *host, int events,
 	bool done = false;
 	bool sbc_error;
 	unsigned long flags;
-	u32 *rsp = cmd->resp;
+	u32 *rsp;
 
 	if (mrq->sbc && cmd == mrq->cmd &&
 	    (events & (MSDC_INT_ACMDRDY | MSDC_INT_ACMDCRCERR
@@ -768,6 +768,7 @@ static bool msdc_cmd_done(struct msdc_host *host, int events,
 
 	if (done)
 		return true;
+	rsp = cmd->resp;
 
 	sdr_clr_bits(host->base + MSDC_INTEN, cmd_ints_mask);
 
@@ -942,7 +943,7 @@ static void msdc_data_xfer_next(struct msdc_host *host,
 static bool msdc_data_xfer_done(struct msdc_host *host, u32 events,
 				struct mmc_request *mrq, struct mmc_data *data)
 {
-	struct mmc_command *stop = data->stop;
+	struct mmc_command *stop;
 	unsigned long flags;
 	bool done;
 	unsigned int check_data = events &
@@ -958,6 +959,7 @@ static bool msdc_data_xfer_done(struct msdc_host *host, u32 events,
 
 	if (done)
 		return true;
+	stop = data->stop;
 
 	if (check_data || (stop && stop->error)) {
 		dev_dbg(host->dev, "DMA status: 0x%8X\n",
diff --git a/drivers/mmc/host/mxs-mmc.c b/drivers/mmc/host/mxs-mmc.c
index c8b8ac66ff7e3..687fd68fbbcd1 100644
--- a/drivers/mmc/host/mxs-mmc.c
+++ b/drivers/mmc/host/mxs-mmc.c
@@ -651,7 +651,7 @@ static int mxs_mmc_probe(struct platform_device *pdev)
 
 	ret = mmc_of_parse(mmc);
 	if (ret)
-		goto out_clk_disable;
+		goto out_free_dma;
 
 	mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34;
 
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 6b866d0451b21..b18bb0334ded6 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -383,7 +383,7 @@ static int flexcan_chip_freeze(struct flexcan_priv *priv)
 	u32 reg;
 
 	reg = flexcan_read(&regs->mcr);
-	reg |= FLEXCAN_MCR_HALT;
+	reg |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_HALT;
 	flexcan_write(reg, &regs->mcr);
 
 	while (timeout-- && !(flexcan_read(&regs->mcr) & FLEXCAN_MCR_FRZ_ACK))
@@ -1098,10 +1098,14 @@ static int register_flexcandev(struct net_device *dev)
 	if (err)
 		goto out_chip_disable;
 
-	/* set freeze, halt and activate FIFO, restrict register access */
+	/* set freeze, halt */
+	err = flexcan_chip_freeze(priv);
+	if (err)
+		goto out_chip_disable;
+
+	/* activate FIFO, restrict register access */
 	reg = flexcan_read(&regs->mcr);
-	reg |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_HALT |
-		FLEXCAN_MCR_FEN | FLEXCAN_MCR_SUPV;
+	reg |=  FLEXCAN_MCR_FEN | FLEXCAN_MCR_SUPV;
 	flexcan_write(reg, &regs->mcr);
 
 	/* Currently we only support newer versions of this core
diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index cf94b72dbacd9..ab06cf36af083 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -144,6 +144,8 @@ struct board_info {
 	u32		wake_state;
 
 	int		ip_summed;
+
+	struct regulator *power_supply;
 };
 
 /* debug code */
@@ -1462,7 +1464,7 @@ dm9000_probe(struct platform_device *pdev)
 		if (ret) {
 			dev_err(dev, "failed to request reset gpio %d: %d\n",
 				reset_gpios, ret);
-			return -ENODEV;
+			goto out_regulator_disable;
 		}
 
 		/* According to manual PWRST# Low Period Min 1ms */
@@ -1474,8 +1476,10 @@ dm9000_probe(struct platform_device *pdev)
 
 	if (!pdata) {
 		pdata = dm9000_parse_dt(&pdev->dev);
-		if (IS_ERR(pdata))
-			return PTR_ERR(pdata);
+		if (IS_ERR(pdata)) {
+			ret = PTR_ERR(pdata);
+			goto out_regulator_disable;
+		}
 	}
 
 	/* Init network device */
@@ -1492,6 +1496,8 @@ dm9000_probe(struct platform_device *pdev)
 
 	db->dev = &pdev->dev;
 	db->ndev = ndev;
+	if (!IS_ERR(power))
+		db->power_supply = power;
 
 	spin_lock_init(&db->lock);
 	mutex_init(&db->addr_lock);
@@ -1710,6 +1716,10 @@ out:
 	dm9000_release_board(pdev, db);
 	free_netdev(ndev);
 
+out_regulator_disable:
+	if (!IS_ERR(power))
+		regulator_disable(power);
+
 	return ret;
 }
 
@@ -1769,10 +1779,13 @@ static int
 dm9000_drv_remove(struct platform_device *pdev)
 {
 	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct board_info *dm = to_dm9000_board(ndev);
 
 	unregister_netdev(ndev);
-	dm9000_release_board(pdev, netdev_priv(ndev));
+	dm9000_release_board(pdev, dm);
 	free_netdev(ndev);		/* free device structure */
+	if (dm->power_supply)
+		regulator_disable(dm->power_supply);
 
 	dev_dbg(&pdev->dev, "released and freed device\n");
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index b52491f09a4d0..14a3e9e601e8d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -47,7 +47,7 @@
 #define EN_ETHTOOL_SHORT_MASK cpu_to_be16(0xffff)
 #define EN_ETHTOOL_WORD_MASK  cpu_to_be32(0xffffffff)
 
-static int mlx4_en_moderation_update(struct mlx4_en_priv *priv)
+int mlx4_en_moderation_update(struct mlx4_en_priv *priv)
 {
 	int i;
 	int err = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index b7bde70a3e952..112ce16717cda 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -3188,6 +3188,8 @@ int mlx4_en_reset_config(struct net_device *dev,
 			en_err(priv, "Failed starting port\n");
 	}
 
+	if (!err)
+		err = mlx4_en_moderation_update(priv);
 out:
 	mutex_unlock(&mdev->state_lock);
 	netdev_features_change(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 440f1ab6d92e2..b6cd733791a81 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -839,6 +839,7 @@ void mlx4_en_ptp_overflow_check(struct mlx4_en_dev *mdev);
 #define DEV_FEATURE_CHANGED(dev, new_features, feature) \
 	((dev->features & feature) ^ (new_features & feature))
 
+int mlx4_en_moderation_update(struct mlx4_en_priv *priv);
 int mlx4_en_reset_config(struct net_device *dev,
 			 struct hwtstamp_config ts_config,
 			 netdev_features_t new_features);
diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c
index ef746ba74ab4c..666bbacb8cb49 100644
--- a/drivers/net/wan/lapbether.c
+++ b/drivers/net/wan/lapbether.c
@@ -286,7 +286,6 @@ static int lapbeth_open(struct net_device *dev)
 		return -ENODEV;
 	}
 
-	netif_start_queue(dev);
 	return 0;
 }
 
@@ -294,8 +293,6 @@ static int lapbeth_close(struct net_device *dev)
 {
 	int err;
 
-	netif_stop_queue(dev);
-
 	if ((err = lapb_unregister(dev)) != LAPB_OK)
 		pr_err("lapb_unregister error: %d\n", err);
 
diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h
index a660e40f2df1e..70b5dbe9de6aa 100644
--- a/drivers/net/wireless/ath/ath9k/ath9k.h
+++ b/drivers/net/wireless/ath/ath9k/ath9k.h
@@ -178,7 +178,8 @@ struct ath_frame_info {
 	s8 txq;
 	u8 keyix;
 	u8 rtscts_rate;
-	u8 retries : 7;
+	u8 retries : 6;
+	u8 dyn_smps : 1;
 	u8 baw_tracked : 1;
 	u8 tx_power;
 	enum ath9k_key_type keytype:2;
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index 3e3dac3d70604..94fac5dc1b4af 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -1228,6 +1228,11 @@ static void ath_buf_set_rate(struct ath_softc *sc, struct ath_buf *bf,
 				 is_40, is_sgi, is_sp);
 			if (rix < 8 && (tx_info->flags & IEEE80211_TX_CTL_STBC))
 				info->rates[i].RateFlags |= ATH9K_RATESERIES_STBC;
+			if (rix >= 8 && fi->dyn_smps) {
+				info->rates[i].RateFlags |=
+					ATH9K_RATESERIES_RTS_CTS;
+				info->flags |= ATH9K_TXDESC_CTSENA;
+			}
 
 			info->txpower[i] = ath_get_rate_txpower(sc, bf, rix,
 								is_40, false);
@@ -2114,6 +2119,7 @@ static void setup_frame_info(struct ieee80211_hw *hw,
 		fi->keyix = an->ps_key;
 	else
 		fi->keyix = ATH9K_TXKEYIX_INVALID;
+	fi->dyn_smps = sta && sta->smps_mode == IEEE80211_SMPS_DYNAMIC;
 	fi->keytype = keytype;
 	fi->framelen = framelen;
 	fi->tx_power = txpower;
diff --git a/drivers/net/wireless/libertas/if_sdio.c b/drivers/net/wireless/libertas/if_sdio.c
index 33ceda296c9c6..45d68ee682f6d 100644
--- a/drivers/net/wireless/libertas/if_sdio.c
+++ b/drivers/net/wireless/libertas/if_sdio.c
@@ -1229,6 +1229,10 @@ static int if_sdio_probe(struct sdio_func *func,
 
 	spin_lock_init(&card->lock);
 	card->workqueue = create_workqueue("libertas_sdio");
+	if (unlikely(!card->workqueue)) {
+		ret = -ENOMEM;
+		goto err_queue;
+	}
 	INIT_WORK(&card->packet_worker, if_sdio_host_to_card_worker);
 	init_waitqueue_head(&card->pwron_waitq);
 
@@ -1282,6 +1286,7 @@ err_activate_card:
 	lbs_remove_card(priv);
 free:
 	destroy_workqueue(card->workqueue);
+err_queue:
 	while (card->packets) {
 		packet = card->packets;
 		card->packets = card->packets->next;
diff --git a/drivers/pci/host/pci-xgene-msi.c b/drivers/pci/host/pci-xgene-msi.c
index a6456b5782692..b6a099371ad24 100644
--- a/drivers/pci/host/pci-xgene-msi.c
+++ b/drivers/pci/host/pci-xgene-msi.c
@@ -393,13 +393,9 @@ static int xgene_msi_hwirq_alloc(unsigned int cpu)
 		if (!msi_group->gic_irq)
 			continue;
 
-		irq_set_chained_handler(msi_group->gic_irq,
-					xgene_msi_isr);
-		err = irq_set_handler_data(msi_group->gic_irq, msi_group);
-		if (err) {
-			pr_err("failed to register GIC IRQ handler\n");
-			return -EINVAL;
-		}
+		irq_set_chained_handler_and_data(msi_group->gic_irq,
+			xgene_msi_isr, msi_group);
+
 		/*
 		 * Statically allocate MSI GIC IRQs to each CPU core.
 		 * With 8-core X-Gene v1, 2 MSI GIC IRQs are allocated
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index b76a85d14ef0c..aec25ea99d194 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -3286,8 +3286,6 @@ void dasd_generic_remove(struct ccw_device *cdev)
 	struct dasd_device *device;
 	struct dasd_block *block;
 
-	cdev->handler = NULL;
-
 	device = dasd_device_from_cdev(cdev);
 	if (IS_ERR(device)) {
 		dasd_remove_sysfs_files(cdev);
@@ -3306,6 +3304,7 @@ void dasd_generic_remove(struct ccw_device *cdev)
 	 * no quite down yet.
 	 */
 	dasd_set_target_state(device, DASD_STATE_NEW);
+	cdev->handler = NULL;
 	/* dasd_delete_device destroys the device reference. */
 	block = device->block;
 	dasd_delete_device(device);
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index ecf3950c44383..18b8d86ef74b2 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -1568,14 +1568,9 @@ check_mgmt:
 		}
 		rc = iscsi_prep_scsi_cmd_pdu(conn->task);
 		if (rc) {
-			if (rc == -ENOMEM || rc == -EACCES) {
-				spin_lock_bh(&conn->taskqueuelock);
-				list_add_tail(&conn->task->running,
-					      &conn->cmdqueue);
-				conn->task = NULL;
-				spin_unlock_bh(&conn->taskqueuelock);
-				goto done;
-			} else
+			if (rc == -ENOMEM || rc == -EACCES)
+				fail_scsi_task(conn->task, DID_IMM_RETRY);
+			else
 				fail_scsi_task(conn->task, DID_ABORT);
 			spin_lock_bh(&conn->taskqueuelock);
 			continue;
diff --git a/drivers/staging/comedi/drivers/addi_apci_1032.c b/drivers/staging/comedi/drivers/addi_apci_1032.c
index 536a135cd00b3..9058ef473c336 100644
--- a/drivers/staging/comedi/drivers/addi_apci_1032.c
+++ b/drivers/staging/comedi/drivers/addi_apci_1032.c
@@ -269,6 +269,7 @@ static irqreturn_t apci1032_interrupt(int irq, void *d)
 	struct apci1032_private *devpriv = dev->private;
 	struct comedi_subdevice *s = dev->read_subdev;
 	unsigned int ctrl;
+	unsigned short val;
 
 	/* check interrupt is from this device */
 	if ((inl(devpriv->amcc_iobase + AMCC_OP_REG_INTCSR) &
@@ -284,7 +285,8 @@ static irqreturn_t apci1032_interrupt(int irq, void *d)
 	outl(ctrl & ~APCI1032_CTRL_INT_ENA, dev->iobase + APCI1032_CTRL_REG);
 
 	s->state = inl(dev->iobase + APCI1032_STATUS_REG) & 0xffff;
-	comedi_buf_write_samples(s, &s->state, 1);
+	val = s->state;
+	comedi_buf_write_samples(s, &val, 1);
 	comedi_handle_events(dev, s);
 
 	/* enable the interrupt */
diff --git a/drivers/staging/comedi/drivers/addi_apci_1500.c b/drivers/staging/comedi/drivers/addi_apci_1500.c
index c4e36fb6df9d5..1f25f565041cb 100644
--- a/drivers/staging/comedi/drivers/addi_apci_1500.c
+++ b/drivers/staging/comedi/drivers/addi_apci_1500.c
@@ -217,7 +217,7 @@ static irqreturn_t apci1500_interrupt(int irq, void *d)
 	struct comedi_device *dev = d;
 	struct apci1500_private *devpriv = dev->private;
 	struct comedi_subdevice *s = dev->read_subdev;
-	unsigned int status = 0;
+	unsigned short status = 0;
 	unsigned int val;
 
 	val = inl(devpriv->amcc + AMCC_OP_REG_INTCSR);
@@ -247,14 +247,14 @@ static irqreturn_t apci1500_interrupt(int irq, void *d)
 	 *
 	 *    Mask     Meaning
 	 * ----------  ------------------------------------------
-	 * 0x00000001  Event 1 has occurred
-	 * 0x00000010  Event 2 has occurred
-	 * 0x00000100  Counter/timer 1 has run down (not implemented)
-	 * 0x00001000  Counter/timer 2 has run down (not implemented)
-	 * 0x00010000  Counter 3 has run down (not implemented)
-	 * 0x00100000  Watchdog has run down (not implemented)
-	 * 0x01000000  Voltage error
-	 * 0x10000000  Short-circuit error
+	 * 0b00000001  Event 1 has occurred
+	 * 0b00000010  Event 2 has occurred
+	 * 0b00000100  Counter/timer 1 has run down (not implemented)
+	 * 0b00001000  Counter/timer 2 has run down (not implemented)
+	 * 0b00010000  Counter 3 has run down (not implemented)
+	 * 0b00100000  Watchdog has run down (not implemented)
+	 * 0b01000000  Voltage error
+	 * 0b10000000  Short-circuit error
 	 */
 	comedi_buf_write_samples(s, &status, 1);
 	comedi_handle_events(dev, s);
diff --git a/drivers/staging/comedi/drivers/adv_pci1710.c b/drivers/staging/comedi/drivers/adv_pci1710.c
index 399c511cfe0ab..8599258f8c8d2 100644
--- a/drivers/staging/comedi/drivers/adv_pci1710.c
+++ b/drivers/staging/comedi/drivers/adv_pci1710.c
@@ -351,11 +351,11 @@ static int pci171x_ai_eoc(struct comedi_device *dev,
 static int pci171x_ai_read_sample(struct comedi_device *dev,
 				  struct comedi_subdevice *s,
 				  unsigned int cur_chan,
-				  unsigned int *val)
+				  unsigned short *val)
 {
 	const struct boardtype *board = dev->board_ptr;
 	struct pci1710_private *devpriv = dev->private;
-	unsigned int sample;
+	unsigned short sample;
 	unsigned int chan;
 
 	sample = inw(dev->iobase + PCI171X_AD_DATA_REG);
@@ -395,7 +395,7 @@ static int pci171x_ai_insn_read(struct comedi_device *dev,
 	pci171x_ai_setup_chanlist(dev, s, &insn->chanspec, 1, 1);
 
 	for (i = 0; i < insn->n; i++) {
-		unsigned int val;
+		unsigned short val;
 
 		/* start conversion */
 		outw(0, dev->iobase + PCI171X_SOFTTRG_REG);
@@ -516,7 +516,7 @@ static void pci1710_handle_every_sample(struct comedi_device *dev,
 {
 	struct comedi_cmd *cmd = &s->async->cmd;
 	unsigned int status;
-	unsigned int val;
+	unsigned short val;
 	int ret;
 
 	status = inw(dev->iobase + PCI171X_STATUS_REG);
@@ -576,7 +576,7 @@ static void pci1710_handle_fifo(struct comedi_device *dev,
 	}
 
 	for (i = 0; i < devpriv->max_samples; i++) {
-		unsigned int val;
+		unsigned short val;
 		int ret;
 
 		ret = pci171x_ai_read_sample(dev, s, s->async->cur_chan, &val);
diff --git a/drivers/staging/comedi/drivers/das6402.c b/drivers/staging/comedi/drivers/das6402.c
index 1701294b79cdd..666d199983ba9 100644
--- a/drivers/staging/comedi/drivers/das6402.c
+++ b/drivers/staging/comedi/drivers/das6402.c
@@ -193,7 +193,7 @@ static irqreturn_t das6402_interrupt(int irq, void *d)
 	if (status & DAS6402_STATUS_FFULL) {
 		async->events |= COMEDI_CB_OVERFLOW;
 	} else if (status & DAS6402_STATUS_FFNE) {
-		unsigned int val;
+		unsigned short val;
 
 		val = das6402_ai_read_sample(dev, s);
 		comedi_buf_write_samples(s, &val, 1);
diff --git a/drivers/staging/comedi/drivers/das800.c b/drivers/staging/comedi/drivers/das800.c
index b02f12201cf78..91a0c4ec7fdb5 100644
--- a/drivers/staging/comedi/drivers/das800.c
+++ b/drivers/staging/comedi/drivers/das800.c
@@ -436,7 +436,7 @@ static irqreturn_t das800_interrupt(int irq, void *d)
 	struct comedi_cmd *cmd;
 	unsigned long irq_flags;
 	unsigned int status;
-	unsigned int val;
+	unsigned short val;
 	bool fifo_empty;
 	bool fifo_overflow;
 	int i;
diff --git a/drivers/staging/comedi/drivers/dmm32at.c b/drivers/staging/comedi/drivers/dmm32at.c
index 958c0d4aae5c0..48645ecde8109 100644
--- a/drivers/staging/comedi/drivers/dmm32at.c
+++ b/drivers/staging/comedi/drivers/dmm32at.c
@@ -411,7 +411,7 @@ static irqreturn_t dmm32at_isr(int irq, void *d)
 {
 	struct comedi_device *dev = d;
 	unsigned char intstat;
-	unsigned int val;
+	unsigned short val;
 	int i;
 
 	if (!dev->attached) {
diff --git a/drivers/staging/comedi/drivers/me4000.c b/drivers/staging/comedi/drivers/me4000.c
index 15a53204a36a5..4fe856128870b 100644
--- a/drivers/staging/comedi/drivers/me4000.c
+++ b/drivers/staging/comedi/drivers/me4000.c
@@ -933,7 +933,7 @@ static irqreturn_t me4000_ai_isr(int irq, void *dev_id)
 	struct comedi_subdevice *s = dev->read_subdev;
 	int i;
 	int c = 0;
-	unsigned int lval;
+	unsigned short lval;
 
 	if (!dev->attached)
 		return IRQ_NONE;
diff --git a/drivers/staging/comedi/drivers/pcl711.c b/drivers/staging/comedi/drivers/pcl711.c
index 3774daa9d6615..e1334733abe77 100644
--- a/drivers/staging/comedi/drivers/pcl711.c
+++ b/drivers/staging/comedi/drivers/pcl711.c
@@ -193,7 +193,7 @@ static irqreturn_t pcl711_interrupt(int irq, void *d)
 	struct comedi_device *dev = d;
 	struct comedi_subdevice *s = dev->read_subdev;
 	struct comedi_cmd *cmd = &s->async->cmd;
-	unsigned int data;
+	unsigned short data;
 
 	if (!dev->attached) {
 		dev_err(dev->class_dev, "spurious interrupt\n");
diff --git a/drivers/staging/comedi/drivers/pcl818.c b/drivers/staging/comedi/drivers/pcl818.c
index 5aeed44dff706..f062417123087 100644
--- a/drivers/staging/comedi/drivers/pcl818.c
+++ b/drivers/staging/comedi/drivers/pcl818.c
@@ -422,7 +422,7 @@ static int pcl818_ai_eoc(struct comedi_device *dev,
 
 static bool pcl818_ai_write_sample(struct comedi_device *dev,
 				   struct comedi_subdevice *s,
-				   unsigned int chan, unsigned int val)
+				   unsigned int chan, unsigned short val)
 {
 	struct pcl818_private *devpriv = dev->private;
 	struct comedi_cmd *cmd = &s->async->cmd;
diff --git a/drivers/staging/rtl8188eu/core/rtw_ap.c b/drivers/staging/rtl8188eu/core/rtw_ap.c
index f5cedbbc552af..d14a2313fccea 100644
--- a/drivers/staging/rtl8188eu/core/rtw_ap.c
+++ b/drivers/staging/rtl8188eu/core/rtw_ap.c
@@ -921,6 +921,7 @@ int rtw_check_beacon_data(struct adapter *padapter, u8 *pbuf,  int len)
 	/* SSID */
 	p = rtw_get_ie(ie + _BEACON_IE_OFFSET_, _SSID_IE_, &ie_len, (pbss_network->IELength - _BEACON_IE_OFFSET_));
 	if (p && ie_len > 0) {
+		ie_len = min_t(int, ie_len, sizeof(pbss_network->Ssid.Ssid));
 		memset(&pbss_network->Ssid, 0, sizeof(struct ndis_802_11_ssid));
 		memcpy(pbss_network->Ssid.Ssid, (p + 2), ie_len);
 		pbss_network->Ssid.SsidLength = ie_len;
@@ -939,6 +940,7 @@ int rtw_check_beacon_data(struct adapter *padapter, u8 *pbuf,  int len)
 	/*  get supported rates */
 	p = rtw_get_ie(ie + _BEACON_IE_OFFSET_, _SUPPORTEDRATES_IE_, &ie_len, (pbss_network->IELength - _BEACON_IE_OFFSET_));
 	if (p !=  NULL) {
+		ie_len = min_t(int, ie_len, NDIS_802_11_LENGTH_RATES_EX);
 		memcpy(supportRate, p+2, ie_len);
 		supportRateNum = ie_len;
 	}
@@ -946,6 +948,8 @@ int rtw_check_beacon_data(struct adapter *padapter, u8 *pbuf,  int len)
 	/* get ext_supported rates */
 	p = rtw_get_ie(ie + _BEACON_IE_OFFSET_, _EXT_SUPPORTEDRATES_IE_, &ie_len, pbss_network->IELength - _BEACON_IE_OFFSET_);
 	if (p !=  NULL) {
+		ie_len = min_t(int, ie_len,
+			       NDIS_802_11_LENGTH_RATES_EX - supportRateNum);
 		memcpy(supportRate+supportRateNum, p+2, ie_len);
 		supportRateNum += ie_len;
 	}
@@ -1061,6 +1065,7 @@ int rtw_check_beacon_data(struct adapter *padapter, u8 *pbuf,  int len)
 			pht_cap->supp_mcs_set[0] = 0xff;
 			pht_cap->supp_mcs_set[1] = 0x0;
 		}
+		ie_len = min_t(int, ie_len, sizeof(pmlmepriv->htpriv.ht_cap));
 		memcpy(&pmlmepriv->htpriv.ht_cap, p+2, ie_len);
 	}
 
diff --git a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c
index 2a6192e08b750..c29dc91824703 100644
--- a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c
+++ b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c
@@ -1174,9 +1174,11 @@ static int rtw_wx_set_scan(struct net_device *dev, struct iw_request_info *a,
 						break;
 					}
 					sec_len = *(pos++); len -= 1;
-					if (sec_len > 0 && sec_len <= len) {
+					if (sec_len > 0 &&
+					    sec_len <= len &&
+					    sec_len <= 32) {
 						ssid[ssid_index].SsidLength = sec_len;
-						memcpy(ssid[ssid_index].Ssid, pos, ssid[ssid_index].SsidLength);
+						memcpy(ssid[ssid_index].Ssid, pos, sec_len);
 						ssid_index++;
 					}
 					pos += sec_len;
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c b/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c
index 70df6a1485d6f..6f0be1db6fb18 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c
@@ -419,9 +419,10 @@ static int _rtl92e_wx_set_scan(struct net_device *dev,
 		struct iw_scan_req *req = (struct iw_scan_req *)b;
 
 		if (req->essid_len) {
-			ieee->current_network.ssid_len = req->essid_len;
-			memcpy(ieee->current_network.ssid, req->essid,
-			       req->essid_len);
+			int len = min_t(int, req->essid_len, IW_ESSID_MAX_SIZE);
+
+			ieee->current_network.ssid_len = len;
+			memcpy(ieee->current_network.ssid, req->essid, len);
 		}
 	}
 
diff --git a/drivers/staging/rtl8192u/r8192U_wx.c b/drivers/staging/rtl8192u/r8192U_wx.c
index 4911fef2e2e5f..8fb1940751498 100644
--- a/drivers/staging/rtl8192u/r8192U_wx.c
+++ b/drivers/staging/rtl8192u/r8192U_wx.c
@@ -341,8 +341,10 @@ static int r8192_wx_set_scan(struct net_device *dev, struct iw_request_info *a,
 		struct iw_scan_req *req = (struct iw_scan_req *)b;
 
 		if (req->essid_len) {
-			ieee->current_network.ssid_len = req->essid_len;
-			memcpy(ieee->current_network.ssid, req->essid, req->essid_len);
+			int len = min_t(int, req->essid_len, IW_ESSID_MAX_SIZE);
+
+			ieee->current_network.ssid_len = len;
+			memcpy(ieee->current_network.ssid, req->essid, len);
 		}
 	}
 
diff --git a/drivers/staging/rtl8712/rtl871x_cmd.c b/drivers/staging/rtl8712/rtl871x_cmd.c
index 562a102031277..b4eb6af4e5656 100644
--- a/drivers/staging/rtl8712/rtl871x_cmd.c
+++ b/drivers/staging/rtl8712/rtl871x_cmd.c
@@ -242,8 +242,10 @@ u8 r8712_sitesurvey_cmd(struct _adapter *padapter,
 	psurveyPara->ss_ssidlen = 0;
 	memset(psurveyPara->ss_ssid, 0, IW_ESSID_MAX_SIZE + 1);
 	if ((pssid != NULL) && (pssid->SsidLength)) {
-		memcpy(psurveyPara->ss_ssid, pssid->Ssid, pssid->SsidLength);
-		psurveyPara->ss_ssidlen = cpu_to_le32(pssid->SsidLength);
+		int len = min_t(int, pssid->SsidLength, IW_ESSID_MAX_SIZE);
+
+		memcpy(psurveyPara->ss_ssid, pssid->Ssid, len);
+		psurveyPara->ss_ssidlen = cpu_to_le32(len);
 	}
 	set_fwstate(pmlmepriv, _FW_UNDER_SURVEY);
 	r8712_enqueue_cmd(pcmdpriv, ph2c);
diff --git a/drivers/staging/rtl8712/rtl871x_ioctl_linux.c b/drivers/staging/rtl8712/rtl871x_ioctl_linux.c
index 2b348439242f1..20052fa2eedf1 100644
--- a/drivers/staging/rtl8712/rtl871x_ioctl_linux.c
+++ b/drivers/staging/rtl8712/rtl871x_ioctl_linux.c
@@ -935,7 +935,7 @@ static int r871x_wx_set_priv(struct net_device *dev,
 	struct iw_point *dwrq = (struct iw_point *)awrq;
 
 	len = dwrq->length;
-	ext = memdup_user(dwrq->pointer, len);
+	ext = strndup_user(dwrq->pointer, len);
 	if (IS_ERR(ext))
 		return PTR_ERR(ext);
 
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index e5ee349a5382b..53d2f02e18a32 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1928,6 +1928,11 @@ static const struct usb_device_id acm_ids[] = {
 	.driver_info = SEND_ZERO_PACKET,
 	},
 
+	/* Exclude Goodix Fingerprint Reader */
+	{ USB_DEVICE(0x27c6, 0x5395),
+	.driver_info = IGNORE_DEVICE,
+	},
+
 	/* control interfaces without any protocol set */
 	{ USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM,
 		USB_CDC_PROTO_NONE) },
diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c
index 81af315774c62..6903d02a933f5 100644
--- a/drivers/usb/gadget/function/f_uac2.c
+++ b/drivers/usb/gadget/function/f_uac2.c
@@ -997,7 +997,7 @@ static int set_ep_max_packet_size(const struct f_uac2_opts *uac2_opts,
 	}
 
 	max_size_bw = num_channels(chmask) * ssize *
-		DIV_ROUND_UP(srate, factor / (1 << (ep_desc->bInterval - 1)));
+		((srate / (factor / (1 << (ep_desc->bInterval - 1)))) + 1);
 	ep_desc->wMaxPacketSize = cpu_to_le16(min_t(u16, max_size_bw,
 						    max_size_ep));
 
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index e7dee8e3ca8b1..bd6e3555c0479 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -1018,6 +1018,7 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 	struct usb_hcd		*secondary_hcd;
 	int			retval = 0;
 	bool			comp_timer_running = false;
+	bool			pending_portevent = false;
 
 	if (!hcd->state)
 		return 0;
@@ -1151,13 +1152,22 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 
  done:
 	if (retval == 0) {
-		/* Resume root hubs only when have pending events. */
-		if (xhci_pending_portevent(xhci)) {
+		/*
+		 * Resume roothubs only if there are pending events.
+		 * USB 3 devices resend U3 LFPS wake after a 100ms delay if
+		 * the first wake signalling failed, give it that chance.
+		 */
+		pending_portevent = xhci_pending_portevent(xhci);
+		if (!pending_portevent) {
+			msleep(120);
+			pending_portevent = xhci_pending_portevent(xhci);
+		}
+
+		if (pending_portevent) {
 			usb_hcd_resume_root_hub(xhci->shared_hcd);
 			usb_hcd_resume_root_hub(hcd);
 		}
 	}
-
 	/*
 	 * If system is subject to the Quirk, Compliance Mode Timer needs to
 	 * be re-initialized Always after a system resume. Ports are subject
diff --git a/drivers/usb/renesas_usbhs/pipe.c b/drivers/usb/renesas_usbhs/pipe.c
index 75fb41d4e9fc0..22249e389c3d0 100644
--- a/drivers/usb/renesas_usbhs/pipe.c
+++ b/drivers/usb/renesas_usbhs/pipe.c
@@ -805,6 +805,8 @@ struct usbhs_pipe *usbhs_pipe_malloc(struct usbhs_priv *priv,
 
 void usbhs_pipe_free(struct usbhs_pipe *pipe)
 {
+	usbhsp_pipe_select(pipe);
+	usbhsp_pipe_cfg_set(pipe, 0xFFFF, 0);
 	usbhsp_put_pipe(pipe);
 }
 
diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c
index c3d82cabbe65c..2cff9c40f28aa 100644
--- a/drivers/usb/serial/ch341.c
+++ b/drivers/usb/serial/ch341.c
@@ -75,6 +75,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x1a86, 0x7522) },
 	{ USB_DEVICE(0x1a86, 0x7523) },
 	{ USB_DEVICE(0x4348, 0x5523) },
+	{ USB_DEVICE(0x9986, 0x7523) },
 	{ },
 };
 MODULE_DEVICE_TABLE(usb, id_table);
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index ded4c8f2bba4e..91462ff9a99d0 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -142,6 +142,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x8857) },	/* CEL EM357 ZigBee USB Stick */
 	{ USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */
 	{ USB_DEVICE(0x10C4, 0x88A5) }, /* Planet Innovation Ingeni ZigBee USB Device */
+	{ USB_DEVICE(0x10C4, 0x88D8) }, /* Acuity Brands nLight Air Adapter */
 	{ USB_DEVICE(0x10C4, 0x88FB) }, /* CESINEL MEDCAL STII Network Analyzer */
 	{ USB_DEVICE(0x10C4, 0x8938) }, /* CESINEL MEDCAL S II Network Analyzer */
 	{ USB_DEVICE(0x10C4, 0x8946) }, /* Ketra N1 Wireless Interface */
@@ -198,6 +199,8 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x1901, 0x0194) },	/* GE Healthcare Remote Alarm Box */
 	{ USB_DEVICE(0x1901, 0x0195) },	/* GE B850/B650/B450 CP2104 DP UART interface */
 	{ USB_DEVICE(0x1901, 0x0196) },	/* GE B850 CP2105 DP UART interface */
+	{ USB_DEVICE(0x1901, 0x0197) }, /* GE CS1000 Display serial interface */
+	{ USB_DEVICE(0x1901, 0x0198) }, /* GE CS1000 M.2 Key E serial interface */
 	{ USB_DEVICE(0x199B, 0xBA30) }, /* LORD WSDA-200-USB */
 	{ USB_DEVICE(0x19CF, 0x3000) }, /* Parrot NMEA GPS Flight Recorder */
 	{ USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */
diff --git a/drivers/usb/serial/io_edgeport.c b/drivers/usb/serial/io_edgeport.c
index b639d064e5da2..14ab47f88251b 100644
--- a/drivers/usb/serial/io_edgeport.c
+++ b/drivers/usb/serial/io_edgeport.c
@@ -2966,26 +2966,32 @@ static int edge_startup(struct usb_serial *serial)
 				response = -ENODEV;
 			}
 
-			usb_free_urb(edge_serial->interrupt_read_urb);
-			kfree(edge_serial->interrupt_in_buffer);
-
-			usb_free_urb(edge_serial->read_urb);
-			kfree(edge_serial->bulk_in_buffer);
-
-			kfree(edge_serial);
-
-			return response;
+			goto error;
 		}
 
 		/* start interrupt read for this edgeport this interrupt will
 		 * continue as long as the edgeport is connected */
 		response = usb_submit_urb(edge_serial->interrupt_read_urb,
 								GFP_KERNEL);
-		if (response)
+		if (response) {
 			dev_err(ddev, "%s - Error %d submitting control urb\n",
 				__func__, response);
+
+			goto error;
+		}
 	}
 	return response;
+
+error:
+	usb_free_urb(edge_serial->interrupt_read_urb);
+	kfree(edge_serial->interrupt_in_buffer);
+
+	usb_free_urb(edge_serial->read_urb);
+	kfree(edge_serial->bulk_in_buffer);
+
+	kfree(edge_serial);
+
+	return response;
 }
 
 
diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c
index 4aad99a59958b..5501eb89f3951 100644
--- a/drivers/usb/usbip/stub_dev.c
+++ b/drivers/usb/usbip/stub_dev.c
@@ -60,6 +60,8 @@ static ssize_t store_sockfd(struct device *dev, struct device_attribute *attr,
 	int sockfd = 0;
 	struct socket *socket;
 	int rv;
+	struct task_struct *tcp_rx = NULL;
+	struct task_struct *tcp_tx = NULL;
 
 	if (!sdev) {
 		dev_err(dev, "sdev is null\n");
@@ -83,23 +85,47 @@ static ssize_t store_sockfd(struct device *dev, struct device_attribute *attr,
 		}
 
 		socket = sockfd_lookup(sockfd, &err);
-		if (!socket)
+		if (!socket) {
+			dev_err(dev, "failed to lookup sock");
 			goto err;
+		}
 
-		sdev->ud.tcp_socket = socket;
-		sdev->ud.sockfd = sockfd;
+		if (socket->type != SOCK_STREAM) {
+			dev_err(dev, "Expecting SOCK_STREAM - found %d",
+				socket->type);
+			goto sock_err;
+		}
 
+		/* unlock and create threads and get tasks */
 		spin_unlock_irq(&sdev->ud.lock);
+		tcp_rx = kthread_create(stub_rx_loop, &sdev->ud, "stub_rx");
+		if (IS_ERR(tcp_rx)) {
+			sockfd_put(socket);
+			return -EINVAL;
+		}
+		tcp_tx = kthread_create(stub_tx_loop, &sdev->ud, "stub_tx");
+		if (IS_ERR(tcp_tx)) {
+			kthread_stop(tcp_rx);
+			sockfd_put(socket);
+			return -EINVAL;
+		}
 
-		sdev->ud.tcp_rx = kthread_get_run(stub_rx_loop, &sdev->ud,
-						  "stub_rx");
-		sdev->ud.tcp_tx = kthread_get_run(stub_tx_loop, &sdev->ud,
-						  "stub_tx");
+		/* get task structs now */
+		get_task_struct(tcp_rx);
+		get_task_struct(tcp_tx);
 
+		/* lock and update sdev->ud state */
 		spin_lock_irq(&sdev->ud.lock);
+		sdev->ud.tcp_socket = socket;
+		sdev->ud.sockfd = sockfd;
+		sdev->ud.tcp_rx = tcp_rx;
+		sdev->ud.tcp_tx = tcp_tx;
 		sdev->ud.status = SDEV_ST_USED;
 		spin_unlock_irq(&sdev->ud.lock);
 
+		wake_up_process(sdev->ud.tcp_rx);
+		wake_up_process(sdev->ud.tcp_tx);
+
 	} else {
 		dev_info(dev, "stub down\n");
 
@@ -114,6 +140,8 @@ static ssize_t store_sockfd(struct device *dev, struct device_attribute *attr,
 
 	return count;
 
+sock_err:
+	sockfd_put(socket);
 err:
 	spin_unlock_irq(&sdev->ud.lock);
 	return -EINVAL;
diff --git a/drivers/usb/usbip/vhci_sysfs.c b/drivers/usb/usbip/vhci_sysfs.c
index b9432fdec7750..1d681990b398f 100644
--- a/drivers/usb/usbip/vhci_sysfs.c
+++ b/drivers/usb/usbip/vhci_sysfs.c
@@ -202,8 +202,16 @@ static ssize_t store_attach(struct device *dev, struct device_attribute *attr,
 
 	/* Extract socket from fd. */
 	socket = sockfd_lookup(sockfd, &err);
-	if (!socket)
+	if (!socket) {
+		dev_err(dev, "failed to lookup sock");
 		return -EINVAL;
+	}
+	if (socket->type != SOCK_STREAM) {
+		dev_err(dev, "Expecting SOCK_STREAM - found %d",
+			socket->type);
+		sockfd_put(socket);
+		return -EINVAL;
+	}
 
 	/* now need lock until setting vdev status as used */
 
diff --git a/drivers/xen/events/events_2l.c b/drivers/xen/events/events_2l.c
index e902512fcfb50..ca729f19061d3 100644
--- a/drivers/xen/events/events_2l.c
+++ b/drivers/xen/events/events_2l.c
@@ -46,6 +46,11 @@ static unsigned evtchn_2l_max_channels(void)
 	return EVTCHN_2L_NR_CHANNELS;
 }
 
+static void evtchn_2l_remove(evtchn_port_t evtchn, unsigned int cpu)
+{
+	clear_bit(evtchn, BM(per_cpu(cpu_evtchn_mask, cpu)));
+}
+
 static void evtchn_2l_bind_to_cpu(struct irq_info *info, unsigned cpu)
 {
 	clear_bit(info->evtchn, BM(per_cpu(cpu_evtchn_mask, info->cpu)));
@@ -70,12 +75,6 @@ static bool evtchn_2l_is_pending(unsigned port)
 	return sync_test_bit(port, BM(&s->evtchn_pending[0]));
 }
 
-static bool evtchn_2l_test_and_set_mask(unsigned port)
-{
-	struct shared_info *s = HYPERVISOR_shared_info;
-	return sync_test_and_set_bit(port, BM(&s->evtchn_mask[0]));
-}
-
 static void evtchn_2l_mask(unsigned port)
 {
 	struct shared_info *s = HYPERVISOR_shared_info;
@@ -353,18 +352,27 @@ static void evtchn_2l_resume(void)
 				EVTCHN_2L_NR_CHANNELS/BITS_PER_EVTCHN_WORD);
 }
 
+static int evtchn_2l_percpu_deinit(unsigned int cpu)
+{
+	memset(per_cpu(cpu_evtchn_mask, cpu), 0, sizeof(xen_ulong_t) *
+			EVTCHN_2L_NR_CHANNELS/BITS_PER_EVTCHN_WORD);
+
+	return 0;
+}
+
 static const struct evtchn_ops evtchn_ops_2l = {
 	.max_channels      = evtchn_2l_max_channels,
 	.nr_channels       = evtchn_2l_max_channels,
+	.remove            = evtchn_2l_remove,
 	.bind_to_cpu       = evtchn_2l_bind_to_cpu,
 	.clear_pending     = evtchn_2l_clear_pending,
 	.set_pending       = evtchn_2l_set_pending,
 	.is_pending        = evtchn_2l_is_pending,
-	.test_and_set_mask = evtchn_2l_test_and_set_mask,
 	.mask              = evtchn_2l_mask,
 	.unmask            = evtchn_2l_unmask,
 	.handle_events     = evtchn_2l_handle_events,
 	.resume	           = evtchn_2l_resume,
+	.percpu_deinit     = evtchn_2l_percpu_deinit,
 };
 
 void __init xen_evtchn_2l_init(void)
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index ec4074c66d9db..d1e68b4835953 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -99,6 +99,7 @@ static DEFINE_RWLOCK(evtchn_rwlock);
  *   evtchn_rwlock
  *     IRQ-desc lock
  *       percpu eoi_list_lock
+ *         irq_info->lock
  */
 
 static LIST_HEAD(xen_irq_list_head);
@@ -220,6 +221,8 @@ static int xen_irq_info_common_setup(struct irq_info *info,
 	info->irq = irq;
 	info->evtchn = evtchn;
 	info->cpu = cpu;
+	info->mask_reason = EVT_MASK_REASON_EXPLICIT;
+	spin_lock_init(&info->lock);
 
 	ret = set_evtchn_to_irq(evtchn, irq);
 	if (ret < 0)
@@ -286,6 +289,7 @@ static int xen_irq_info_pirq_setup(unsigned irq,
 static void xen_irq_info_cleanup(struct irq_info *info)
 {
 	set_evtchn_to_irq(info->evtchn, -1);
+	xen_evtchn_port_remove(info->evtchn, info->cpu);
 	info->evtchn = 0;
 }
 
@@ -366,6 +370,34 @@ unsigned int cpu_from_evtchn(unsigned int evtchn)
 	return ret;
 }
 
+static void do_mask(struct irq_info *info, u8 reason)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&info->lock, flags);
+
+	if (!info->mask_reason)
+		mask_evtchn(info->evtchn);
+
+	info->mask_reason |= reason;
+
+	spin_unlock_irqrestore(&info->lock, flags);
+}
+
+static void do_unmask(struct irq_info *info, u8 reason)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&info->lock, flags);
+
+	info->mask_reason &= ~reason;
+
+	if (!info->mask_reason)
+		unmask_evtchn(info->evtchn);
+
+	spin_unlock_irqrestore(&info->lock, flags);
+}
+
 #ifdef CONFIG_X86
 static bool pirq_check_eoi_map(unsigned irq)
 {
@@ -501,7 +533,7 @@ static void xen_irq_lateeoi_locked(struct irq_info *info, bool spurious)
 	}
 
 	info->eoi_time = 0;
-	unmask_evtchn(evtchn);
+	do_unmask(info, EVT_MASK_REASON_EOI_PENDING);
 }
 
 static void xen_irq_lateeoi_worker(struct work_struct *work)
@@ -670,6 +702,12 @@ static void xen_evtchn_close(unsigned int port)
 		BUG();
 }
 
+static void event_handler_exit(struct irq_info *info)
+{
+	smp_store_release(&info->is_active, 0);
+	clear_evtchn(info->evtchn);
+}
+
 static void pirq_query_unmask(int irq)
 {
 	struct physdev_irq_status_query irq_status;
@@ -688,7 +726,8 @@ static void pirq_query_unmask(int irq)
 
 static void eoi_pirq(struct irq_data *data)
 {
-	int evtchn = evtchn_from_irq(data->irq);
+	struct irq_info *info = info_for_irq(data->irq);
+	int evtchn = info ? info->evtchn : 0;
 	struct physdev_eoi eoi = { .irq = pirq_from_irq(data->irq) };
 	int rc = 0;
 
@@ -697,16 +736,15 @@ static void eoi_pirq(struct irq_data *data)
 
 	if (unlikely(irqd_is_setaffinity_pending(data)) &&
 	    likely(!irqd_irq_disabled(data))) {
-		int masked = test_and_set_mask(evtchn);
+		do_mask(info, EVT_MASK_REASON_TEMPORARY);
 
-		clear_evtchn(evtchn);
+		event_handler_exit(info);
 
 		irq_move_masked_irq(data);
 
-		if (!masked)
-			unmask_evtchn(evtchn);
+		do_unmask(info, EVT_MASK_REASON_TEMPORARY);
 	} else
-		clear_evtchn(evtchn);
+		event_handler_exit(info);
 
 	if (pirq_needs_eoi(data->irq)) {
 		rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
@@ -757,7 +795,8 @@ static unsigned int __startup_pirq(unsigned int irq)
 		goto err;
 
 out:
-	unmask_evtchn(evtchn);
+	do_unmask(info, EVT_MASK_REASON_EXPLICIT);
+
 	eoi_pirq(irq_get_irq_data(irq));
 
 	return 0;
@@ -784,7 +823,7 @@ static void shutdown_pirq(struct irq_data *data)
 	if (!VALID_EVTCHN(evtchn))
 		return;
 
-	mask_evtchn(evtchn);
+	do_mask(info, EVT_MASK_REASON_EXPLICIT);
 	xen_evtchn_close(evtchn);
 	xen_irq_info_cleanup(info);
 }
@@ -1540,6 +1579,8 @@ void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl)
 	}
 
 	info = info_for_irq(irq);
+	if (xchg_acquire(&info->is_active, 1))
+		return;
 
 	if (ctrl->defer_eoi) {
 		info->eoi_cpu = smp_processor_id();
@@ -1646,8 +1687,8 @@ void rebind_evtchn_irq(int evtchn, int irq)
 static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
 {
 	struct evtchn_bind_vcpu bind_vcpu;
-	int evtchn = evtchn_from_irq(irq);
-	int masked;
+	struct irq_info *info = info_for_irq(irq);
+	int evtchn = info ? info->evtchn : 0;
 
 	if (!VALID_EVTCHN(evtchn))
 		return -1;
@@ -1663,7 +1704,7 @@ static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
 	 * Mask the event while changing the VCPU binding to prevent
 	 * it being delivered on an unexpected VCPU.
 	 */
-	masked = test_and_set_mask(evtchn);
+	do_mask(info, EVT_MASK_REASON_TEMPORARY);
 
 	/*
 	 * If this fails, it usually just indicates that we're dealing with a
@@ -1673,8 +1714,7 @@ static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
 	if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
 		bind_evtchn_to_cpu(evtchn, tcpu);
 
-	if (!masked)
-		unmask_evtchn(evtchn);
+	do_unmask(info, EVT_MASK_REASON_TEMPORARY);
 
 	return 0;
 }
@@ -1689,39 +1729,41 @@ static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
 
 static void enable_dynirq(struct irq_data *data)
 {
-	int evtchn = evtchn_from_irq(data->irq);
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (VALID_EVTCHN(evtchn))
-		unmask_evtchn(evtchn);
+		do_unmask(info, EVT_MASK_REASON_EXPLICIT);
 }
 
 static void disable_dynirq(struct irq_data *data)
 {
-	int evtchn = evtchn_from_irq(data->irq);
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (VALID_EVTCHN(evtchn))
-		mask_evtchn(evtchn);
+		do_mask(info, EVT_MASK_REASON_EXPLICIT);
 }
 
 static void ack_dynirq(struct irq_data *data)
 {
-	int evtchn = evtchn_from_irq(data->irq);
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (!VALID_EVTCHN(evtchn))
 		return;
 
 	if (unlikely(irqd_is_setaffinity_pending(data)) &&
 	    likely(!irqd_irq_disabled(data))) {
-		int masked = test_and_set_mask(evtchn);
+		do_mask(info, EVT_MASK_REASON_TEMPORARY);
 
-		clear_evtchn(evtchn);
+		event_handler_exit(info);
 
 		irq_move_masked_irq(data);
 
-		if (!masked)
-			unmask_evtchn(evtchn);
+		do_unmask(info, EVT_MASK_REASON_TEMPORARY);
 	} else
-		clear_evtchn(evtchn);
+		event_handler_exit(info);
 }
 
 static void mask_ack_dynirq(struct irq_data *data)
@@ -1730,18 +1772,39 @@ static void mask_ack_dynirq(struct irq_data *data)
 	ack_dynirq(data);
 }
 
+static void lateeoi_ack_dynirq(struct irq_data *data)
+{
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
+
+	if (VALID_EVTCHN(evtchn)) {
+		do_mask(info, EVT_MASK_REASON_EOI_PENDING);
+		event_handler_exit(info);
+	}
+}
+
+static void lateeoi_mask_ack_dynirq(struct irq_data *data)
+{
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
+
+	if (VALID_EVTCHN(evtchn)) {
+		do_mask(info, EVT_MASK_REASON_EXPLICIT);
+		event_handler_exit(info);
+	}
+}
+
 static int retrigger_dynirq(struct irq_data *data)
 {
-	unsigned int evtchn = evtchn_from_irq(data->irq);
-	int masked;
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (!VALID_EVTCHN(evtchn))
 		return 0;
 
-	masked = test_and_set_mask(evtchn);
+	do_mask(info, EVT_MASK_REASON_TEMPORARY);
 	set_evtchn(evtchn);
-	if (!masked)
-		unmask_evtchn(evtchn);
+	do_unmask(info, EVT_MASK_REASON_TEMPORARY);
 
 	return 1;
 }
@@ -1836,10 +1899,11 @@ static void restore_cpu_ipis(unsigned int cpu)
 /* Clear an irq's pending state, in preparation for polling on it */
 void xen_clear_irq_pending(int irq)
 {
-	int evtchn = evtchn_from_irq(irq);
+	struct irq_info *info = info_for_irq(irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (VALID_EVTCHN(evtchn))
-		clear_evtchn(evtchn);
+		event_handler_exit(info);
 }
 EXPORT_SYMBOL(xen_clear_irq_pending);
 void xen_set_irq_pending(int irq)
@@ -1948,8 +2012,8 @@ static struct irq_chip xen_lateeoi_chip __read_mostly = {
 	.irq_mask		= disable_dynirq,
 	.irq_unmask		= enable_dynirq,
 
-	.irq_ack		= mask_ack_dynirq,
-	.irq_mask_ack		= mask_ack_dynirq,
+	.irq_ack		= lateeoi_ack_dynirq,
+	.irq_mask_ack		= lateeoi_mask_ack_dynirq,
 
 	.irq_set_affinity	= set_affinity_irq,
 	.irq_retrigger		= retrigger_dynirq,
diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c
index 7addca0d8d26b..5e6ff21201326 100644
--- a/drivers/xen/events/events_fifo.c
+++ b/drivers/xen/events/events_fifo.c
@@ -209,12 +209,6 @@ static bool evtchn_fifo_is_pending(unsigned port)
 	return sync_test_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word));
 }
 
-static bool evtchn_fifo_test_and_set_mask(unsigned port)
-{
-	event_word_t *word = event_word_from_port(port);
-	return sync_test_and_set_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word));
-}
-
 static void evtchn_fifo_mask(unsigned port)
 {
 	event_word_t *word = event_word_from_port(port);
@@ -421,7 +415,6 @@ static const struct evtchn_ops evtchn_ops_fifo = {
 	.clear_pending     = evtchn_fifo_clear_pending,
 	.set_pending       = evtchn_fifo_set_pending,
 	.is_pending        = evtchn_fifo_is_pending,
-	.test_and_set_mask = evtchn_fifo_test_and_set_mask,
 	.mask              = evtchn_fifo_mask,
 	.unmask            = evtchn_fifo_unmask,
 	.handle_events     = evtchn_fifo_handle_events,
diff --git a/drivers/xen/events/events_internal.h b/drivers/xen/events/events_internal.h
index b9b4f59198930..3df6f28b75e69 100644
--- a/drivers/xen/events/events_internal.h
+++ b/drivers/xen/events/events_internal.h
@@ -35,13 +35,19 @@ struct irq_info {
 	struct list_head eoi_list;
 	short refcnt;
 	short spurious_cnt;
-	enum xen_irq_type type;	/* type */
+	short type;		/* type */
+	u8 mask_reason;		/* Why is event channel masked */
+#define EVT_MASK_REASON_EXPLICIT	0x01
+#define EVT_MASK_REASON_TEMPORARY	0x02
+#define EVT_MASK_REASON_EOI_PENDING	0x04
+	u8 is_active;		/* Is event just being handled? */
 	unsigned irq;
 	unsigned int evtchn;	/* event channel */
 	unsigned short cpu;	/* cpu bound */
 	unsigned short eoi_cpu;	/* EOI must happen on this cpu */
 	unsigned int irq_epoch;	/* If eoi_cpu valid: irq_epoch of event */
 	u64 eoi_time;		/* Time in jiffies when to EOI. */
+	spinlock_t lock;
 
 	union {
 		unsigned short virq;
@@ -67,12 +73,12 @@ struct evtchn_ops {
 	unsigned (*nr_channels)(void);
 
 	int (*setup)(struct irq_info *info);
+	void (*remove)(evtchn_port_t port, unsigned int cpu);
 	void (*bind_to_cpu)(struct irq_info *info, unsigned cpu);
 
 	void (*clear_pending)(unsigned port);
 	void (*set_pending)(unsigned port);
 	bool (*is_pending)(unsigned port);
-	bool (*test_and_set_mask)(unsigned port);
 	void (*mask)(unsigned port);
 	void (*unmask)(unsigned port);
 
@@ -109,6 +115,13 @@ static inline int xen_evtchn_port_setup(struct irq_info *info)
 	return 0;
 }
 
+static inline void xen_evtchn_port_remove(evtchn_port_t evtchn,
+					  unsigned int cpu)
+{
+	if (evtchn_ops->remove)
+		evtchn_ops->remove(evtchn, cpu);
+}
+
 static inline void xen_evtchn_port_bind_to_cpu(struct irq_info *info,
 					       unsigned cpu)
 {
@@ -130,11 +143,6 @@ static inline bool test_evtchn(unsigned port)
 	return evtchn_ops->is_pending(port);
 }
 
-static inline bool test_and_set_mask(unsigned port)
-{
-	return evtchn_ops->test_and_set_mask(port);
-}
-
 static inline void mask_evtchn(unsigned port)
 {
 	return evtchn_ops->mask(port);
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 4f4fc9ff36365..5666eb49bbbdd 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -204,7 +204,7 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf)
 		rc = server->ops->queryfs(xid, tcon, buf);
 
 	free_xid(xid);
-	return 0;
+	return rc;
 }
 
 static long cifs_fallocate(struct file *file, int mode, loff_t off, loff_t len)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 3c15291ba1aaa..0c9386978d9d8 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4922,7 +4922,7 @@ static int _nfs4_get_security_label(struct inode *inode, void *buf,
 		return ret;
 	if (!(fattr.valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL))
 		return -ENOENT;
-	return 0;
+	return label.len;
 }
 
 static int nfs4_get_security_label(struct inode *inode, void *buf,
diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h
index 1a2111c775ae1..0e7350973e0e5 100644
--- a/include/linux/can/skb.h
+++ b/include/linux/can/skb.h
@@ -48,8 +48,12 @@ static inline void can_skb_reserve(struct sk_buff *skb)
 
 static inline void can_skb_set_owner(struct sk_buff *skb, struct sock *sk)
 {
-	if (sk) {
-		sock_hold(sk);
+	/* If the socket has already been closed by user space, the
+	 * refcount may already be 0 (and the socket will be freed
+	 * after the last TX skb has been freed). So only increase
+	 * socket refcount if the refcount is > 0.
+	 */
+	if (sk && atomic_inc_not_zero(&sk->sk_refcnt)) {
 		skb->destructor = sock_efree;
 		skb->sk = sk;
 	}
diff --git a/include/uapi/linux/netfilter/nfnetlink_cthelper.h b/include/uapi/linux/netfilter/nfnetlink_cthelper.h
index 33659f6fad3ee..30557bade9354 100644
--- a/include/uapi/linux/netfilter/nfnetlink_cthelper.h
+++ b/include/uapi/linux/netfilter/nfnetlink_cthelper.h
@@ -4,7 +4,7 @@
 #define NFCT_HELPER_STATUS_DISABLED	0
 #define NFCT_HELPER_STATUS_ENABLED	1
 
-enum nfnl_acct_msg_types {
+enum nfnl_cthelper_msg_types {
 	NFNL_MSG_CTHELPER_NEW,
 	NFNL_MSG_CTHELPER_GET,
 	NFNL_MSG_CTHELPER_DEL,
diff --git a/kernel/futex.c b/kernel/futex.c
index 95cdc11c89f8e..ff5499b0c5b34 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1016,6 +1016,39 @@ static void exit_pi_state_list(struct task_struct *curr)
  * [10] There is no transient state which leaves owner and user space
  *	TID out of sync. Except one error case where the kernel is denied
  *	write access to the user address, see fixup_pi_state_owner().
+ *
+ *
+ * Serialization and lifetime rules:
+ *
+ * hb->lock:
+ *
+ *	hb -> futex_q, relation
+ *	futex_q -> pi_state, relation
+ *
+ *	(cannot be raw because hb can contain arbitrary amount
+ *	 of futex_q's)
+ *
+ * pi_mutex->wait_lock:
+ *
+ *	{uval, pi_state}
+ *
+ *	(and pi_mutex 'obviously')
+ *
+ * p->pi_lock:
+ *
+ *	p->pi_state_list -> pi_state->list, relation
+ *
+ * pi_state->refcount:
+ *
+ *	pi_state lifetime
+ *
+ *
+ * Lock order:
+ *
+ *   hb->lock
+ *     pi_mutex->wait_lock
+ *       p->pi_lock
+ *
  */
 
 /*
@@ -1023,10 +1056,12 @@ static void exit_pi_state_list(struct task_struct *curr)
  * the pi_state against the user space value. If correct, attach to
  * it.
  */
-static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state,
+static int attach_to_pi_state(u32 __user *uaddr, u32 uval,
+			      struct futex_pi_state *pi_state,
 			      struct futex_pi_state **ps)
 {
 	pid_t pid = uval & FUTEX_TID_MASK;
+	int ret, uval2;
 
 	/*
 	 * Userspace might have messed up non-PI and PI futexes [3]
@@ -1034,8 +1069,33 @@ static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state,
 	if (unlikely(!pi_state))
 		return -EINVAL;
 
+	/*
+	 * We get here with hb->lock held, and having found a
+	 * futex_top_waiter(). This means that futex_lock_pi() of said futex_q
+	 * has dropped the hb->lock in between queue_me() and unqueue_me_pi(),
+	 * which in turn means that futex_lock_pi() still has a reference on
+	 * our pi_state.
+	 */
 	WARN_ON(!atomic_read(&pi_state->refcount));
 
+	/*
+	 * Now that we have a pi_state, we can acquire wait_lock
+	 * and do the state validation.
+	 */
+	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+
+	/*
+	 * Since {uval, pi_state} is serialized by wait_lock, and our current
+	 * uval was read without holding it, it can have changed. Verify it
+	 * still is what we expect it to be, otherwise retry the entire
+	 * operation.
+	 */
+	if (get_futex_value_locked(&uval2, uaddr))
+		goto out_efault;
+
+	if (uval != uval2)
+		goto out_eagain;
+
 	/*
 	 * Handle the owner died case:
 	 */
@@ -1051,11 +1111,11 @@ static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state,
 			 * is not 0. Inconsistent state. [5]
 			 */
 			if (pid)
-				return -EINVAL;
+				goto out_einval;
 			/*
 			 * Take a ref on the state and return success. [4]
 			 */
-			goto out_state;
+			goto out_attach;
 		}
 
 		/*
@@ -1067,14 +1127,14 @@ static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state,
 		 * Take a ref on the state and return success. [6]
 		 */
 		if (!pid)
-			goto out_state;
+			goto out_attach;
 	} else {
 		/*
 		 * If the owner died bit is not set, then the pi_state
 		 * must have an owner. [7]
 		 */
 		if (!pi_state->owner)
-			return -EINVAL;
+			goto out_einval;
 	}
 
 	/*
@@ -1083,11 +1143,29 @@ static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state,
 	 * user space TID. [9/10]
 	 */
 	if (pid != task_pid_vnr(pi_state->owner))
-		return -EINVAL;
-out_state:
+		goto out_einval;
+
+out_attach:
 	atomic_inc(&pi_state->refcount);
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 	*ps = pi_state;
 	return 0;
+
+out_einval:
+	ret = -EINVAL;
+	goto out_error;
+
+out_eagain:
+	ret = -EAGAIN;
+	goto out_error;
+
+out_efault:
+	ret = -EFAULT;
+	goto out_error;
+
+out_error:
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+	return ret;
 }
 
 /**
@@ -1120,11 +1198,67 @@ static void wait_for_owner_exiting(int ret, struct task_struct *exiting)
 	put_task_struct(exiting);
 }
 
+static int handle_exit_race(u32 __user *uaddr, u32 uval,
+			    struct task_struct *tsk)
+{
+	u32 uval2;
+
+	/*
+	 * If the futex exit state is not yet FUTEX_STATE_DEAD, tell the
+	 * caller that the alleged owner is busy.
+	 */
+	if (tsk && tsk->futex_state != FUTEX_STATE_DEAD)
+		return -EBUSY;
+
+	/*
+	 * Reread the user space value to handle the following situation:
+	 *
+	 * CPU0				CPU1
+	 *
+	 * sys_exit()			sys_futex()
+	 *  do_exit()			 futex_lock_pi()
+	 *                                futex_lock_pi_atomic()
+	 *   exit_signals(tsk)		    No waiters:
+	 *    tsk->flags |= PF_EXITING;	    *uaddr == 0x00000PID
+	 *  mm_release(tsk)		    Set waiter bit
+	 *   exit_robust_list(tsk) {	    *uaddr = 0x80000PID;
+	 *      Set owner died		    attach_to_pi_owner() {
+	 *    *uaddr = 0xC0000000;	     tsk = get_task(PID);
+	 *   }				     if (!tsk->flags & PF_EXITING) {
+	 *  ...				       attach();
+	 *  tsk->futex_state =               } else {
+	 *	FUTEX_STATE_DEAD;              if (tsk->futex_state !=
+	 *					  FUTEX_STATE_DEAD)
+	 *				         return -EAGAIN;
+	 *				       return -ESRCH; <--- FAIL
+	 *				     }
+	 *
+	 * Returning ESRCH unconditionally is wrong here because the
+	 * user space value has been changed by the exiting task.
+	 *
+	 * The same logic applies to the case where the exiting task is
+	 * already gone.
+	 */
+	if (get_futex_value_locked(&uval2, uaddr))
+		return -EFAULT;
+
+	/* If the user space value has changed, try again. */
+	if (uval2 != uval)
+		return -EAGAIN;
+
+	/*
+	 * The exiting task did not have a robust list, the robust list was
+	 * corrupted or the user space value in *uaddr is simply bogus.
+	 * Give up and tell user space.
+	 */
+	return -ESRCH;
+}
+
 /*
  * Lookup the task for the TID provided from user space and attach to
  * it after doing proper sanity checks.
  */
-static int attach_to_pi_owner(u32 uval, union futex_key *key,
+static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key,
 			      struct futex_pi_state **ps,
 			      struct task_struct **exiting)
 {
@@ -1135,12 +1269,15 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key,
 	/*
 	 * We are the first waiter - try to look up the real owner and attach
 	 * the new pi_state to it, but bail out when TID = 0 [1]
+	 *
+	 * The !pid check is paranoid. None of the call sites should end up
+	 * with pid == 0, but better safe than sorry. Let the caller retry
 	 */
 	if (!pid)
-		return -ESRCH;
+		return -EAGAIN;
 	p = futex_find_get_task(pid);
 	if (!p)
-		return -ESRCH;
+		return handle_exit_race(uaddr, uval, NULL);
 
 	if (unlikely(p->flags & PF_KTHREAD)) {
 		put_task_struct(p);
@@ -1159,7 +1296,7 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key,
 		 * FUTEX_STATE_DEAD, we know that the task has finished
 		 * the cleanup:
 		 */
-		int ret = (p->futex_state = FUTEX_STATE_DEAD) ? -ESRCH : -EAGAIN;
+		int ret = handle_exit_race(uaddr, uval, p);
 
 		raw_spin_unlock_irq(&p->pi_lock);
 		/*
@@ -1180,6 +1317,9 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key,
 
 	/*
 	 * No existing pi state. First waiter. [2]
+	 *
+	 * This creates pi_state, we have hb->lock held, this means nothing can
+	 * observe this state, wait_lock is irrelevant.
 	 */
 	pi_state = alloc_pi_state();
 
@@ -1204,7 +1344,8 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key,
 	return 0;
 }
 
-static int lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
+static int lookup_pi_state(u32 __user *uaddr, u32 uval,
+			   struct futex_hash_bucket *hb,
 			   union futex_key *key, struct futex_pi_state **ps,
 			   struct task_struct **exiting)
 {
@@ -1215,13 +1356,13 @@ static int lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 	 * attach to the pi_state when the validation succeeds.
 	 */
 	if (match)
-		return attach_to_pi_state(uval, match->pi_state, ps);
+		return attach_to_pi_state(uaddr, uval, match->pi_state, ps);
 
 	/*
 	 * We are the first waiter - try to look up the owner based on
 	 * @uval and attach to it.
 	 */
-	return attach_to_pi_owner(uval, key, ps, exiting);
+	return attach_to_pi_owner(uaddr, uval, key, ps, exiting);
 }
 
 static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
@@ -1234,7 +1375,7 @@ static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
 	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
 		return -EFAULT;
 
-	/*If user space value changed, let the caller retry */
+	/* If user space value changed, let the caller retry */
 	return curval != uval ? -EAGAIN : 0;
 }
 
@@ -1298,7 +1439,7 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
 	 */
 	match = futex_top_waiter(hb, key);
 	if (match)
-		return attach_to_pi_state(uval, match->pi_state, ps);
+		return attach_to_pi_state(uaddr, uval, match->pi_state, ps);
 
 	/*
 	 * No waiter and user TID is 0. We are here because the
@@ -1337,7 +1478,7 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
 	 * attach to the owner. If that fails, no harm done, we only
 	 * set the FUTEX_WAITERS bit in the user space variable.
 	 */
-	return attach_to_pi_owner(uval, key, ps, exiting);
+	return attach_to_pi_owner(uaddr, newval, key, ps, exiting);
 }
 
 /**
@@ -1438,6 +1579,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
 
 	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) {
 		ret = -EFAULT;
+
 	} else if (curval != uval) {
 		/*
 		 * If a unconditional UNLOCK_PI operation (user space did not
@@ -1971,7 +2113,7 @@ retry_private:
 			 * rereading and handing potential crap to
 			 * lookup_pi_state.
 			 */
-			ret = lookup_pi_state(ret, hb2, &key2,
+			ret = lookup_pi_state(uaddr2, ret, hb2, &key2,
 					      &pi_state, &exiting);
 		}
 
@@ -2249,7 +2391,6 @@ static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	int err = 0;
 
 	oldowner = pi_state->owner;
-
 	/*
 	 * We are here because either:
 	 *
@@ -2268,11 +2409,10 @@ static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	 * because we can fault here. Imagine swapped out pages or a fork
 	 * that marked all the anonymous memory readonly for cow.
 	 *
-	 * Modifying pi_state _before_ the user space value would
-	 * leave the pi_state in an inconsistent state when we fault
-	 * here, because we need to drop the hash bucket lock to
-	 * handle the fault. This might be observed in the PID check
-	 * in lookup_pi_state.
+	 * Modifying pi_state _before_ the user space value would leave the
+	 * pi_state in an inconsistent state when we fault here, because we
+	 * need to drop the locks to handle the fault. This might be observed
+	 * in the PID check in lookup_pi_state.
 	 */
 retry:
 	if (!argowner) {
@@ -2333,21 +2473,26 @@ retry:
 	return argowner == current;
 
 	/*
-	 * To handle the page fault we need to drop the hash bucket
-	 * lock here. That gives the other task (either the highest priority
-	 * waiter itself or the task which stole the rtmutex) the
-	 * chance to try the fixup of the pi_state. So once we are
-	 * back from handling the fault we need to check the pi_state
-	 * after reacquiring the hash bucket lock and before trying to
-	 * do another fixup. When the fixup has been done already we
-	 * simply return.
+	 * To handle the page fault we need to drop the locks here. That gives
+	 * the other task (either the highest priority waiter itself or the
+	 * task which stole the rtmutex) the chance to try the fixup of the
+	 * pi_state. So once we are back from handling the fault we need to
+	 * check the pi_state after reacquiring the locks and before trying to
+	 * do another fixup. When the fixup has been done already we simply
+	 * return.
+	 *
+	 * Note: we hold both hb->lock and pi_mutex->wait_lock. We can safely
+	 * drop hb->lock since the caller owns the hb -> futex_q relation.
+	 * Dropping the pi_mutex->wait_lock requires the state revalidate.
 	 */
 handle_fault:
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 	spin_unlock(q->lock_ptr);
 
 	err = fault_in_user_writeable(uaddr);
 
 	spin_lock(q->lock_ptr);
+	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 
 	/*
 	 * Check if someone else fixed it for us:
diff --git a/mm/slub.c b/mm/slub.c
index 18d1622144afe..40c7a3fbd031e 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1682,7 +1682,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
 
 		t = acquire_slab(s, n, page, object == NULL, &objects);
 		if (!t)
-			continue; /* cmpxchg raced */
+			break;
 
 		available += objects;
 		if (!object) {
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 6dfc3daf7c21e..2a37f367dc047 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -300,7 +300,7 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
 	int flush = 1;
 
 	if (NAPI_GRO_CB(skb)->encap_mark ||
-	    (skb->ip_summed != CHECKSUM_PARTIAL &&
+	    (uh->check && skb->ip_summed != CHECKSUM_PARTIAL &&
 	     NAPI_GRO_CB(skb)->csum_cnt == 0 &&
 	     !NAPI_GRO_CB(skb)->csum_valid))
 		goto out;
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index cdafbd38a456b..8caae1c5d93df 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -271,6 +271,7 @@ static int match_revfn(u8 af, const char *name, u8 revision, int *bestp)
 	const struct xt_match *m;
 	int have_rev = 0;
 
+	mutex_lock(&xt[af].mutex);
 	list_for_each_entry(m, &xt[af].match, list) {
 		if (strcmp(m->name, name) == 0) {
 			if (m->revision > *bestp)
@@ -279,6 +280,7 @@ static int match_revfn(u8 af, const char *name, u8 revision, int *bestp)
 				have_rev = 1;
 		}
 	}
+	mutex_unlock(&xt[af].mutex);
 
 	if (af != NFPROTO_UNSPEC && !have_rev)
 		return match_revfn(NFPROTO_UNSPEC, name, revision, bestp);
@@ -291,6 +293,7 @@ static int target_revfn(u8 af, const char *name, u8 revision, int *bestp)
 	const struct xt_target *t;
 	int have_rev = 0;
 
+	mutex_lock(&xt[af].mutex);
 	list_for_each_entry(t, &xt[af].target, list) {
 		if (strcmp(t->name, name) == 0) {
 			if (t->revision > *bestp)
@@ -299,6 +302,7 @@ static int target_revfn(u8 af, const char *name, u8 revision, int *bestp)
 				have_rev = 1;
 		}
 	}
+	mutex_unlock(&xt[af].mutex);
 
 	if (af != NFPROTO_UNSPEC && !have_rev)
 		return target_revfn(NFPROTO_UNSPEC, name, revision, bestp);
@@ -312,12 +316,10 @@ int xt_find_revision(u8 af, const char *name, u8 revision, int target,
 {
 	int have_rev, best = -1;
 
-	mutex_lock(&xt[af].mutex);
 	if (target == 1)
 		have_rev = target_revfn(af, name, revision, &best);
 	else
 		have_rev = match_revfn(af, name, revision, &best);
-	mutex_unlock(&xt[af].mutex);
 
 	/* Nothing at all?  Return 0 to try loading module. */
 	if (best == -1) {
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index 7250fb38350ce..8cba4c44da4c2 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -362,7 +362,7 @@ static uint32_t (*w2)(uint16_t);
 static int
 is_mcounted_section_name(char const *const txtname)
 {
-	return strcmp(".text",           txtname) == 0 ||
+	return strncmp(".text",          txtname, 5) == 0 ||
 		strcmp(".ref.text",      txtname) == 0 ||
 		strcmp(".sched.text",    txtname) == 0 ||
 		strcmp(".spinlock.text", txtname) == 0 ||
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index ccd6614ea2182..5ca4ec2970197 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -138,6 +138,11 @@ my %text_sections = (
      ".text.unlikely" => 1,
 );
 
+# Acceptable section-prefixes to record.
+my %text_section_prefixes = (
+     ".text." => 1,
+);
+
 # Note: we are nice to C-programmers here, thus we skip the '||='-idiom.
 $objdump = 'objdump' if (!$objdump);
 $objcopy = 'objcopy' if (!$objcopy);
@@ -503,6 +508,14 @@ while (<IN>) {
 
 	# Only record text sections that we know are safe
 	$read_function = defined($text_sections{$1});
+	if (!$read_function) {
+	    foreach my $prefix (keys %text_section_prefixes) {
+	        if (substr($1, 0, length $prefix) eq $prefix) {
+	            $read_function = 1;
+	            last;
+	        }
+	    }
+	}
 	# print out any recorded offsets
 	update_funcs();
 
diff --git a/sound/pci/hda/hda_bind.c b/sound/pci/hda/hda_bind.c
index d0d6dfbfcfdf8..f25c2c43c5626 100644
--- a/sound/pci/hda/hda_bind.c
+++ b/sound/pci/hda/hda_bind.c
@@ -46,6 +46,10 @@ static void hda_codec_unsol_event(struct hdac_device *dev, unsigned int ev)
 	if (codec->bus->shutdown)
 		return;
 
+	/* ignore unsol events during system suspend/resume */
+	if (codec->core.dev.power.power_state.event != PM_EVENT_ON)
+		return;
+
 	if (codec->patch_ops.unsol_event)
 		codec->patch_ops.unsol_event(codec, ev);
 }
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index b249b1b857464..785c64b854ec6 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -2239,6 +2239,18 @@ static void generic_hdmi_free(struct hda_codec *codec)
 }
 
 #ifdef CONFIG_PM
+static int generic_hdmi_suspend(struct hda_codec *codec)
+{
+	struct hdmi_spec *spec = codec->spec;
+	int pin_idx;
+
+	for (pin_idx = 0; pin_idx < spec->num_pins; pin_idx++) {
+		struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx);
+		cancel_delayed_work_sync(&per_pin->work);
+	}
+	return 0;
+}
+
 static int generic_hdmi_resume(struct hda_codec *codec)
 {
 	struct hdmi_spec *spec = codec->spec;
@@ -2262,6 +2274,7 @@ static const struct hda_codec_ops generic_hdmi_patch_ops = {
 	.build_controls		= generic_hdmi_build_controls,
 	.unsol_event		= hdmi_unsol_event,
 #ifdef CONFIG_PM
+	.suspend		= generic_hdmi_suspend,
 	.resume			= generic_hdmi_resume,
 #endif
 };
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 59529a9cab614..79cffe44388f9 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1154,6 +1154,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip)
 	case USB_ID(0x1de7, 0x0114): /* Phoenix Audio MT202pcs */
 	case USB_ID(0x21B4, 0x0081): /* AudioQuest DragonFly */
 	case USB_ID(0x2912, 0x30c8): /* Audioengine D1 */
+	case USB_ID(0x413c, 0xa506): /* Dell AE515 sound bar */
 		return true;
 	}
 	return false;