kernel-alx-legacy/patches-4.9/0151-4.9.52-all-fixes.patch

diff --git a/Makefile b/Makefile
index b48aebbe187f..c53de1e38c6a 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 9
-SUBLEVEL = 51
+SUBLEVEL = 52
 EXTRAVERSION =
 NAME = Roaring Lionus
 
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 1eea99beecc3..85d9ea4a0acc 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -92,6 +92,12 @@ ENTRY(EV_MachineCheck)
 	lr  r0, [efa]
 	mov r1, sp
 
+	; hardware auto-disables MMU, re-enable it to allow kernel vaddr
+	; access for say stack unwinding of modules for crash dumps
+	lr	r3, [ARC_REG_PID]
+	or	r3, r3, MMU_ENABLE
+	sr	r3, [ARC_REG_PID]
+
 	lsr  	r3, r2, 8
 	bmsk 	r3, r3, 7
 	brne    r3, ECR_C_MCHK_DUP_TLB, 1f
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
index bdb295e09160..a4dc881da277 100644
--- a/arch/arc/mm/tlb.c
+++ b/arch/arc/mm/tlb.c
@@ -896,9 +896,6 @@ void do_tlb_overlap_fault(unsigned long cause, unsigned long address,
 
 	local_irq_save(flags);
 
-	/* re-enable the MMU */
-	write_aux_reg(ARC_REG_PID, MMU_ENABLE | read_aux_reg(ARC_REG_PID));
-
 	/* loop thru all sets of TLB */
 	for (set = 0; set < mmu->sets; set++) {
 
diff --git a/arch/mips/math-emu/dp_fmax.c b/arch/mips/math-emu/dp_fmax.c
index fd71b8daaaf2..5bec64f2884e 100644
--- a/arch/mips/math-emu/dp_fmax.c
+++ b/arch/mips/math-emu/dp_fmax.c
@@ -47,14 +47,26 @@ union ieee754dp ieee754dp_fmax(union ieee754dp x, union ieee754dp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
 		return ieee754dp_nanxcpt(x);
 
-	/* numbers are preferred to NaNs */
+	/*
+	 * Quiet NaN handling
+	 */
+
+	/*
+	 *    The case of both inputs quiet NaNs
+	 */
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+		return x;
+
+	/*
+	 *    The cases of exactly one input quiet NaN (numbers
+	 *    are here preferred as returned values to NaNs)
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -80,9 +92,7 @@ union ieee754dp ieee754dp_fmax(union ieee754dp x, union ieee754dp y)
 		return ys ? x : y;
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-		if (xs == ys)
-			return x;
-		return ieee754dp_zero(1);
+		return ieee754dp_zero(xs & ys);
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
 		DPDNORMX;
@@ -106,16 +116,32 @@ union ieee754dp ieee754dp_fmax(union ieee754dp x, union ieee754dp y)
 	else if (xs < ys)
 		return x;
 
-	/* Compare exponent */
-	if (xe > ye)
-		return x;
-	else if (xe < ye)
-		return y;
+	/* Signs of inputs are equal, let's compare exponents */
+	if (xs == 0) {
+		/* Inputs are both positive */
+		if (xe > ye)
+			return x;
+		else if (xe < ye)
+			return y;
+	} else {
+		/* Inputs are both negative */
+		if (xe > ye)
+			return y;
+		else if (xe < ye)
+			return x;
+	}
 
-	/* Compare mantissa */
+	/* Signs and exponents of inputs are equal, let's compare mantissas */
+	if (xs == 0) {
+		/* Inputs are both positive, with equal signs and exponents */
+		if (xm <= ym)
+			return y;
+		return x;
+	}
+	/* Inputs are both negative, with equal signs and exponents */
 	if (xm <= ym)
-		return y;
-	return x;
+		return x;
+	return y;
 }
 
 union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y)
@@ -147,14 +173,26 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
 		return ieee754dp_nanxcpt(x);
 
-	/* numbers are preferred to NaNs */
+	/*
+	 * Quiet NaN handling
+	 */
+
+	/*
+	 *    The case of both inputs quiet NaNs
+	 */
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+		return x;
+
+	/*
+	 *    The cases of exactly one input quiet NaN (numbers
+	 *    are here preferred as returned values to NaNs)
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -164,6 +202,9 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y)
 	/*
 	 * Infinity and zero handling
 	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+		return ieee754dp_inf(xs & ys);
+
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
@@ -171,7 +212,6 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y)
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
@@ -180,9 +220,7 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y)
 		return y;
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-		if (xs == ys)
-			return x;
-		return ieee754dp_zero(1);
+		return ieee754dp_zero(xs & ys);
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
 		DPDNORMX;
@@ -207,7 +245,11 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y)
 		return y;
 
 	/* Compare mantissa */
-	if (xm <= ym)
+	if (xm < ym)
 		return y;
-	return x;
+	else if (xm > ym)
+		return x;
+	else if (xs == 0)
+		return x;
+	return y;
 }
diff --git a/arch/mips/math-emu/dp_fmin.c b/arch/mips/math-emu/dp_fmin.c
index c1072b0dfb95..a287b23818d8 100644
--- a/arch/mips/math-emu/dp_fmin.c
+++ b/arch/mips/math-emu/dp_fmin.c
@@ -47,14 +47,26 @@ union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
 		return ieee754dp_nanxcpt(x);
 
-	/* numbers are preferred to NaNs */
+	/*
+	 * Quiet NaN handling
+	 */
+
+	/*
+	 *    The case of both inputs quiet NaNs
+	 */
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+		return x;
+
+	/*
+	 *    The cases of exactly one input quiet NaN (numbers
+	 *    are here preferred as returned values to NaNs)
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -80,9 +92,7 @@ union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y)
 		return ys ? y : x;
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-		if (xs == ys)
-			return x;
-		return ieee754dp_zero(1);
+		return ieee754dp_zero(xs | ys);
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
 		DPDNORMX;
@@ -106,16 +116,32 @@ union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y)
 	else if (xs < ys)
 		return y;
 
-	/* Compare exponent */
-	if (xe > ye)
-		return y;
-	else if (xe < ye)
-		return x;
+	/* Signs of inputs are the same, let's compare exponents */
+	if (xs == 0) {
+		/* Inputs are both positive */
+		if (xe > ye)
+			return y;
+		else if (xe < ye)
+			return x;
+	} else {
+		/* Inputs are both negative */
+		if (xe > ye)
+			return x;
+		else if (xe < ye)
+			return y;
+	}
 
-	/* Compare mantissa */
+	/* Signs and exponents of inputs are equal, let's compare mantissas */
+	if (xs == 0) {
+		/* Inputs are both positive, with equal signs and exponents */
+		if (xm <= ym)
+			return x;
+		return y;
+	}
+	/* Inputs are both negative, with equal signs and exponents */
 	if (xm <= ym)
-		return x;
-	return y;
+		return y;
+	return x;
 }
 
 union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y)
@@ -147,14 +173,26 @@ union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
 		return ieee754dp_nanxcpt(x);
 
-	/* numbers are preferred to NaNs */
+	/*
+	 * Quiet NaN handling
+	 */
+
+	/*
+	 *    The case of both inputs quiet NaNs
+	 */
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+		return x;
+
+	/*
+	 *    The cases of exactly one input quiet NaN (numbers
+	 *    are here preferred as returned values to NaNs)
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -164,25 +202,25 @@ union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y)
 	/*
 	 * Infinity and zero handling
 	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+		return ieee754dp_inf(xs | ys);
+
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
-		return x;
+		return y;
 
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
-		return y;
+		return x;
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-		if (xs == ys)
-			return x;
-		return ieee754dp_zero(1);
+		return ieee754dp_zero(xs | ys);
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
 		DPDNORMX;
@@ -207,7 +245,11 @@ union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y)
 		return x;
 
 	/* Compare mantissa */
-	if (xm <= ym)
+	if (xm < ym)
+		return x;
+	else if (xm > ym)
+		return y;
+	else if (xs == 1)
 		return x;
 	return y;
 }
diff --git a/arch/mips/math-emu/dp_maddf.c b/arch/mips/math-emu/dp_maddf.c
index 4a2d03c72959..e0d9be5fbf4c 100644
--- a/arch/mips/math-emu/dp_maddf.c
+++ b/arch/mips/math-emu/dp_maddf.c
@@ -14,22 +14,45 @@
 
 #include "ieee754dp.h"
 
-enum maddf_flags {
-	maddf_negate_product	= 1 << 0,
-};
+
+/* 128 bits shift right logical with rounding. */
+void srl128(u64 *hptr, u64 *lptr, int count)
+{
+	u64 low;
+
+	if (count >= 128) {
+		*lptr = *hptr != 0 || *lptr != 0;
+		*hptr = 0;
+	} else if (count >= 64) {
+		if (count == 64) {
+			*lptr = *hptr | (*lptr != 0);
+		} else {
+			low = *lptr;
+			*lptr = *hptr >> (count - 64);
+			*lptr |= (*hptr << (128 - count)) != 0 || low != 0;
+		}
+		*hptr = 0;
+	} else {
+		low = *lptr;
+		*lptr = low >> count | *hptr << (64 - count);
+		*lptr |= (low << (64 - count)) != 0;
+		*hptr = *hptr >> count;
+	}
+}
 
 static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
 				 union ieee754dp y, enum maddf_flags flags)
 {
 	int re;
 	int rs;
-	u64 rm;
 	unsigned lxm;
 	unsigned hxm;
 	unsigned lym;
 	unsigned hym;
 	u64 lrm;
 	u64 hrm;
+	u64 lzm;
+	u64 hzm;
 	u64 t;
 	u64 at;
 	int s;
@@ -48,52 +71,34 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
 
 	ieee754_clearcx();
 
-	switch (zc) {
-	case IEEE754_CLASS_SNAN:
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
+	/*
+	 * Handle the cases when at least one of x, y or z is a NaN.
+	 * Order of precedence is sNaN, qNaN and z, x, y.
+	 */
+	if (zc == IEEE754_CLASS_SNAN)
 		return ieee754dp_nanxcpt(z);
-	case IEEE754_CLASS_DNORM:
-		DPDNORMZ;
-	/* QNAN is handled separately below */
-	}
-
-	switch (CLPAIR(xc, yc)) {
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
-	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
-	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
-	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
-		return ieee754dp_nanxcpt(y);
-
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
+	if (xc == IEEE754_CLASS_SNAN)
 		return ieee754dp_nanxcpt(x);
-
-	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
-	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
-	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
+	if (yc == IEEE754_CLASS_SNAN)
+		return ieee754dp_nanxcpt(y);
+	if (zc == IEEE754_CLASS_QNAN)
+		return z;
+	if (xc == IEEE754_CLASS_QNAN)
+		return x;
+	if (yc == IEEE754_CLASS_QNAN)
 		return y;
 
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
-		return x;
+	if (zc == IEEE754_CLASS_DNORM)
+		DPDNORMZ;
+	/* ZERO z cases are handled separately below */
 
+	switch (CLPAIR(xc, yc)) {
 
 	/*
 	 * Infinity handling
 	 */
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
 		ieee754_setcx(IEEE754_INVALID_OPERATION);
 		return ieee754dp_indef();
 
@@ -102,9 +107,27 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
-		return ieee754dp_inf(xs ^ ys);
+		if ((zc == IEEE754_CLASS_INF) &&
+		    ((!(flags & MADDF_NEGATE_PRODUCT) && (zs != (xs ^ ys))) ||
+		     ((flags & MADDF_NEGATE_PRODUCT) && (zs == (xs ^ ys))))) {
+			/*
+			 * Cases of addition of infinities with opposite signs
+			 * or subtraction of infinities with same signs.
+			 */
+			ieee754_setcx(IEEE754_INVALID_OPERATION);
+			return ieee754dp_indef();
+		}
+		/*
+		 * z is here either not an infinity, or an infinity having the
+		 * same sign as product (x*y) (in case of MADDF.D instruction)
+		 * or product -(x*y) (in MSUBF.D case). The result must be an
+		 * infinity, and its sign is determined only by the value of
+		 * (flags & MADDF_NEGATE_PRODUCT) and the signs of x and y.
+		 */
+		if (flags & MADDF_NEGATE_PRODUCT)
+			return ieee754dp_inf(1 ^ (xs ^ ys));
+		else
+			return ieee754dp_inf(xs ^ ys);
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
@@ -113,32 +136,42 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
 		if (zc == IEEE754_CLASS_INF)
 			return ieee754dp_inf(zs);
-		/* Multiplication is 0 so just return z */
+		if (zc == IEEE754_CLASS_ZERO) {
+			/* Handle cases +0 + (-0) and similar ones. */
+			if ((!(flags & MADDF_NEGATE_PRODUCT)
+					&& (zs == (xs ^ ys))) ||
+			    ((flags & MADDF_NEGATE_PRODUCT)
+					&& (zs != (xs ^ ys))))
+				/*
+				 * Cases of addition of zeros of equal signs
+				 * or subtraction of zeroes of opposite signs.
+				 * The sign of the resulting zero is in any
+				 * such case determined only by the sign of z.
+				 */
+				return z;
+
+			return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD);
+		}
+		/* x*y is here 0, and z is not 0, so just return z */
 		return z;
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
 		DPDNORMX;
 
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
-		else if (zc == IEEE754_CLASS_INF)
+		if (zc == IEEE754_CLASS_INF)
 			return ieee754dp_inf(zs);
 		DPDNORMY;
 		break;
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
-		else if (zc == IEEE754_CLASS_INF)
+		if (zc == IEEE754_CLASS_INF)
 			return ieee754dp_inf(zs);
 		DPDNORMX;
 		break;
 
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
-		else if (zc == IEEE754_CLASS_INF)
+		if (zc == IEEE754_CLASS_INF)
 			return ieee754dp_inf(zs);
 		/* fall through to real computations */
 	}
@@ -157,7 +190,7 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
 
 	re = xe + ye;
 	rs = xs ^ ys;
-	if (flags & maddf_negate_product)
+	if (flags & MADDF_NEGATE_PRODUCT)
 		rs ^= 1;
 
 	/* shunt to top of word */
@@ -165,7 +198,7 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
 	ym <<= 64 - (DP_FBITS + 1);
 
 	/*
-	 * Multiply 64 bits xm, ym to give high 64 bits rm with stickness.
+	 * Multiply 64 bits xm and ym to give 128 bits result in hrm:lrm.
 	 */
 
 	/* 32 * 32 => 64 */
@@ -195,78 +228,110 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
 
 	hrm = hrm + (t >> 32);
 
-	rm = hrm | (lrm != 0);
-
-	/*
-	 * Sticky shift down to normal rounding precision.
-	 */
-	if ((s64) rm < 0) {
-		rm = (rm >> (64 - (DP_FBITS + 1 + 3))) |
-		     ((rm << (DP_FBITS + 1 + 3)) != 0);
+	/* Put explicit bit at bit 126 if necessary */
+	if ((int64_t)hrm < 0) {
+		lrm = (hrm << 63) | (lrm >> 1);
+		hrm = hrm >> 1;
 		re++;
-	} else {
-		rm = (rm >> (64 - (DP_FBITS + 1 + 3 + 1))) |
-		     ((rm << (DP_FBITS + 1 + 3 + 1)) != 0);
 	}
-	assert(rm & (DP_HIDDEN_BIT << 3));
 
-	/* And now the addition */
-	assert(zm & DP_HIDDEN_BIT);
+	assert(hrm & (1 << 62));
 
-	/*
-	 * Provide guard,round and stick bit space.
-	 */
-	zm <<= 3;
+	if (zc == IEEE754_CLASS_ZERO) {
+		/*
+		 * Move explicit bit from bit 126 to bit 55 since the
+		 * ieee754dp_format code expects the mantissa to be
+		 * 56 bits wide (53 + 3 rounding bits).
+		 */
+		srl128(&hrm, &lrm, (126 - 55));
+		return ieee754dp_format(rs, re, lrm);
+	}
+
+	/* Move explicit bit from bit 52 to bit 126 */
+	lzm = 0;
+	hzm = zm << 10;
+	assert(hzm & (1 << 62));
 
+	/* Make the exponents the same */
 	if (ze > re) {
 		/*
 		 * Have to shift y fraction right to align.
 		 */
 		s = ze - re;
-		rm = XDPSRS(rm, s);
+		srl128(&hrm, &lrm, s);
 		re += s;
 	} else if (re > ze) {
 		/*
 		 * Have to shift x fraction right to align.
 		 */
 		s = re - ze;
-		zm = XDPSRS(zm, s);
+		srl128(&hzm, &lzm, s);
 		ze += s;
 	}
 	assert(ze == re);
 	assert(ze <= DP_EMAX);
 
+	/* Do the addition */
 	if (zs == rs) {
 		/*
-		 * Generate 28 bit result of adding two 27 bit numbers
-		 * leaving result in xm, xs and xe.
+		 * Generate 128 bit result by adding two 127 bit numbers
+		 * leaving result in hzm:lzm, zs and ze.
 		 */
-		zm = zm + rm;
-
-		if (zm >> (DP_FBITS + 1 + 3)) { /* carry out */
-			zm = XDPSRS1(zm);
+		hzm = hzm + hrm + (lzm > (lzm + lrm));
+		lzm = lzm + lrm;
+		if ((int64_t)hzm < 0) {        /* carry out */
+			srl128(&hzm, &lzm, 1);
 			ze++;
 		}
 	} else {
-		if (zm >= rm) {
-			zm = zm - rm;
+		if (hzm > hrm || (hzm == hrm && lzm >= lrm)) {
+			hzm = hzm - hrm - (lzm < lrm);
+			lzm = lzm - lrm;
 		} else {
-			zm = rm - zm;
+			hzm = hrm - hzm - (lrm < lzm);
+			lzm = lrm - lzm;
 			zs = rs;
 		}
-		if (zm == 0)
+		if (lzm == 0 && hzm == 0)
 			return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD);
 
 		/*
-		 * Normalize to rounding precision.
+		 * Put explicit bit at bit 126 if necessary.
 		 */
-		while ((zm >> (DP_FBITS + 3)) == 0) {
-			zm <<= 1;
-			ze--;
+		if (hzm == 0) {
+			/* left shift by 63 or 64 bits */
+			if ((int64_t)lzm < 0) {
+				/* MSB of lzm is the explicit bit */
+				hzm = lzm >> 1;
+				lzm = lzm << 63;
+				ze -= 63;
+			} else {
+				hzm = lzm;
+				lzm = 0;
+				ze -= 64;
+			}
+		}
+
+		t = 0;
+		while ((hzm >> (62 - t)) == 0)
+			t++;
+
+		assert(t <= 62);
+		if (t) {
+			hzm = hzm << t | lzm >> (64 - t);
+			lzm = lzm << t;
+			ze -= t;
 		}
 	}
 
-	return ieee754dp_format(zs, ze, zm);
+	/*
+	 * Move explicit bit from bit 126 to bit 55 since the
+	 * ieee754dp_format code expects the mantissa to be
+	 * 56 bits wide (53 + 3 rounding bits).
+	 */
+	srl128(&hzm, &lzm, (126 - 55));
+
+	return ieee754dp_format(zs, ze, lzm);
 }
 
 union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x,
@@ -278,5 +343,5 @@ union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x,
 union ieee754dp ieee754dp_msubf(union ieee754dp z, union ieee754dp x,
 				union ieee754dp y)
 {
-	return _dp_maddf(z, x, y, maddf_negate_product);
+	return _dp_maddf(z, x, y, MADDF_NEGATE_PRODUCT);
 }
diff --git a/arch/mips/math-emu/ieee754int.h b/arch/mips/math-emu/ieee754int.h
index 8bc2f6963324..dd2071f430e0 100644
--- a/arch/mips/math-emu/ieee754int.h
+++ b/arch/mips/math-emu/ieee754int.h
@@ -26,6 +26,10 @@
 
 #define CLPAIR(x, y)	((x)*6+(y))
 
+enum maddf_flags {
+	MADDF_NEGATE_PRODUCT	= 1 << 0,
+};
+
 static inline void ieee754_clearcx(void)
 {
 	ieee754_csr.cx = 0;
diff --git a/arch/mips/math-emu/ieee754sp.h b/arch/mips/math-emu/ieee754sp.h
index 8476067075fe..0f63e4202cff 100644
--- a/arch/mips/math-emu/ieee754sp.h
+++ b/arch/mips/math-emu/ieee754sp.h
@@ -45,6 +45,10 @@ static inline int ieee754sp_finite(union ieee754sp x)
 	return SPBEXP(x) != SP_EMAX + 1 + SP_EBIAS;
 }
 
+/* 64 bit right shift with rounding */
+#define XSPSRS64(v, rs)						\
+	(((rs) >= 64) ? ((v) != 0) : ((v) >> (rs)) | ((v) << (64-(rs)) != 0))
+
 /* 3bit extended single precision sticky right shift */
 #define XSPSRS(v, rs)						\
 	((rs > (SP_FBITS+3))?1:((v) >> (rs)) | ((v) << (32-(rs)) != 0))
diff --git a/arch/mips/math-emu/sp_fmax.c b/arch/mips/math-emu/sp_fmax.c
index 4d000844e48e..74a5a00d2f22 100644
--- a/arch/mips/math-emu/sp_fmax.c
+++ b/arch/mips/math-emu/sp_fmax.c
@@ -47,14 +47,26 @@ union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
 		return ieee754sp_nanxcpt(x);
 
-	/* numbers are preferred to NaNs */
+	/*
+	 * Quiet NaN handling
+	 */
+
+	/*
+	 *    The case of both inputs quiet NaNs
+	 */
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+		return x;
+
+	/*
+	 *    The cases of exactly one input quiet NaN (numbers
+	 *    are here preferred as returned values to NaNs)
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -80,9 +92,7 @@ union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y)
 		return ys ? x : y;
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-		if (xs == ys)
-			return x;
-		return ieee754sp_zero(1);
+		return ieee754sp_zero(xs & ys);
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
 		SPDNORMX;
@@ -106,16 +116,32 @@ union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y)
 	else if (xs < ys)
 		return x;
 
-	/* Compare exponent */
-	if (xe > ye)
-		return x;
-	else if (xe < ye)
-		return y;
+	/* Signs of inputs are equal, let's compare exponents */
+	if (xs == 0) {
+		/* Inputs are both positive */
+		if (xe > ye)
+			return x;
+		else if (xe < ye)
+			return y;
+	} else {
+		/* Inputs are both negative */
+		if (xe > ye)
+			return y;
+		else if (xe < ye)
+			return x;
+	}
 
-	/* Compare mantissa */
+	/* Signs and exponents of inputs are equal, let's compare mantissas */
+	if (xs == 0) {
+		/* Inputs are both positive, with equal signs and exponents */
+		if (xm <= ym)
+			return y;
+		return x;
+	}
+	/* Inputs are both negative, with equal signs and exponents */
 	if (xm <= ym)
-		return y;
-	return x;
+		return x;
+	return y;
 }
 
 union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
@@ -147,14 +173,26 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
 		return ieee754sp_nanxcpt(x);
 
-	/* numbers are preferred to NaNs */
+	/*
+	 * Quiet NaN handling
+	 */
+
+	/*
+	 *    The case of both inputs quiet NaNs
+	 */
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+		return x;
+
+	/*
+	 *    The cases of exactly one input quiet NaN (numbers
+	 *    are here preferred as returned values to NaNs)
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -164,6 +202,9 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
 	/*
 	 * Infinity and zero handling
 	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+		return ieee754sp_inf(xs & ys);
+
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
@@ -171,7 +212,6 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
@@ -180,9 +220,7 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
 		return y;
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-		if (xs == ys)
-			return x;
-		return ieee754sp_zero(1);
+		return ieee754sp_zero(xs & ys);
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
 		SPDNORMX;
@@ -207,7 +245,11 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
 		return y;
 
 	/* Compare mantissa */
-	if (xm <= ym)
+	if (xm < ym)
 		return y;
-	return x;
+	else if (xm > ym)
+		return x;
+	else if (xs == 0)
+		return x;
+	return y;
 }
diff --git a/arch/mips/math-emu/sp_fmin.c b/arch/mips/math-emu/sp_fmin.c
index 4eb1bb9e9dec..c51385f46b09 100644
--- a/arch/mips/math-emu/sp_fmin.c
+++ b/arch/mips/math-emu/sp_fmin.c
@@ -47,14 +47,26 @@ union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
 		return ieee754sp_nanxcpt(x);
 
-	/* numbers are preferred to NaNs */
+	/*
+	 * Quiet NaN handling
+	 */
+
+	/*
+	 *    The case of both inputs quiet NaNs
+	 */
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+		return x;
+
+	/*
+	 *    The cases of exactly one input quiet NaN (numbers
+	 *    are here preferred as returned values to NaNs)
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -80,9 +92,7 @@ union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y)
 		return ys ? y : x;
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-		if (xs == ys)
-			return x;
-		return ieee754sp_zero(1);
+		return ieee754sp_zero(xs | ys);
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
 		SPDNORMX;
@@ -106,16 +116,32 @@ union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y)
 	else if (xs < ys)
 		return y;
 
-	/* Compare exponent */
-	if (xe > ye)
-		return y;
-	else if (xe < ye)
-		return x;
+	/* Signs of inputs are the same, let's compare exponents */
+	if (xs == 0) {
+		/* Inputs are both positive */
+		if (xe > ye)
+			return y;
+		else if (xe < ye)
+			return x;
+	} else {
+		/* Inputs are both negative */
+		if (xe > ye)
+			return x;
+		else if (xe < ye)
+			return y;
+	}
 
-	/* Compare mantissa */
+	/* Signs and exponents of inputs are equal, let's compare mantissas */
+	if (xs == 0) {
+		/* Inputs are both positive, with equal signs and exponents */
+		if (xm <= ym)
+			return x;
+		return y;
+	}
+	/* Inputs are both negative, with equal signs and exponents */
 	if (xm <= ym)
-		return x;
-	return y;
+		return y;
+	return x;
 }
 
 union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y)
@@ -147,14 +173,26 @@ union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
 		return ieee754sp_nanxcpt(x);
 
-	/* numbers are preferred to NaNs */
+	/*
+	 * Quiet NaN handling
+	 */
+
+	/*
+	 *    The case of both inputs quiet NaNs
+	 */
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+		return x;
+
+	/*
+	 *    The cases of exactly one input quiet NaN (numbers
+	 *    are here preferred as returned values to NaNs)
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -164,25 +202,25 @@ union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y)
 	/*
 	 * Infinity and zero handling
 	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+		return ieee754sp_inf(xs | ys);
+
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
-		return x;
+		return y;
 
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
-		return y;
+		return x;
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-		if (xs == ys)
-			return x;
-		return ieee754sp_zero(1);
+		return ieee754sp_zero(xs | ys);
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
 		SPDNORMX;
@@ -207,7 +245,11 @@ union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y)
 		return x;
 
 	/* Compare mantissa */
-	if (xm <= ym)
+	if (xm < ym)
+		return x;
+	else if (xm > ym)
+		return y;
+	else if (xs == 1)
 		return x;
 	return y;
 }
diff --git a/arch/mips/math-emu/sp_maddf.c b/arch/mips/math-emu/sp_maddf.c
index a8cd8b4f235e..7195fe785d81 100644
--- a/arch/mips/math-emu/sp_maddf.c
+++ b/arch/mips/math-emu/sp_maddf.c
@@ -14,9 +14,6 @@
 
 #include "ieee754sp.h"
 
-enum maddf_flags {
-	maddf_negate_product	= 1 << 0,
-};
 
 static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
 				 union ieee754sp y, enum maddf_flags flags)
@@ -24,14 +21,8 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
 	int re;
 	int rs;
 	unsigned rm;
-	unsigned short lxm;
-	unsigned short hxm;
-	unsigned short lym;
-	unsigned short hym;
-	unsigned lrm;
-	unsigned hrm;
-	unsigned t;
-	unsigned at;
+	uint64_t rm64;
+	uint64_t zm64;
 	int s;
 
 	COMPXSP;
@@ -48,51 +39,35 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
 
 	ieee754_clearcx();
 
-	switch (zc) {
-	case IEEE754_CLASS_SNAN:
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
+	/*
+	 * Handle the cases when at least one of x, y or z is a NaN.
+	 * Order of precedence is sNaN, qNaN and z, x, y.
+	 */
+	if (zc == IEEE754_CLASS_SNAN)
 		return ieee754sp_nanxcpt(z);
-	case IEEE754_CLASS_DNORM:
-		SPDNORMZ;
-	/* QNAN is handled separately below */
-	}
-
-	switch (CLPAIR(xc, yc)) {
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
-	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
-	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
-	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+	if (xc == IEEE754_CLASS_SNAN)
+		return ieee754sp_nanxcpt(x);
+	if (yc == IEEE754_CLASS_SNAN)
 		return ieee754sp_nanxcpt(y);
+	if (zc == IEEE754_CLASS_QNAN)
+		return z;
+	if (xc == IEEE754_CLASS_QNAN)
+		return x;
+	if (yc == IEEE754_CLASS_QNAN)
+		return y;
 
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
-		return ieee754sp_nanxcpt(x);
+	if (zc == IEEE754_CLASS_DNORM)
+		SPDNORMZ;
+	/* ZERO z cases are handled separately below */
 
-	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
-	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
-	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
-		return y;
+	switch (CLPAIR(xc, yc)) {
 
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
-		return x;
 
 	/*
 	 * Infinity handling
 	 */
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
 		ieee754_setcx(IEEE754_INVALID_OPERATION);
 		return ieee754sp_indef();
 
@@ -101,9 +76,27 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
-		return ieee754sp_inf(xs ^ ys);
+		if ((zc == IEEE754_CLASS_INF) &&
+		    ((!(flags & MADDF_NEGATE_PRODUCT) && (zs != (xs ^ ys))) ||
+		     ((flags & MADDF_NEGATE_PRODUCT) && (zs == (xs ^ ys))))) {
+			/*
+			 * Cases of addition of infinities with opposite signs
+			 * or subtraction of infinities with same signs.
+			 */
+			ieee754_setcx(IEEE754_INVALID_OPERATION);
+			return ieee754sp_indef();
+		}
+		/*
+		 * z is here either not an infinity, or an infinity having the
+		 * same sign as product (x*y) (in case of MADDF.D instruction)
+		 * or product -(x*y) (in MSUBF.D case). The result must be an
+		 * infinity, and its sign is determined only by the value of
+		 * (flags & MADDF_NEGATE_PRODUCT) and the signs of x and y.
+		 */
+		if (flags & MADDF_NEGATE_PRODUCT)
+			return ieee754sp_inf(1 ^ (xs ^ ys));
+		else
+			return ieee754sp_inf(xs ^ ys);
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
@@ -112,32 +105,42 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
 		if (zc == IEEE754_CLASS_INF)
 			return ieee754sp_inf(zs);
-		/* Multiplication is 0 so just return z */
+		if (zc == IEEE754_CLASS_ZERO) {
+			/* Handle cases +0 + (-0) and similar ones. */
+			if ((!(flags & MADDF_NEGATE_PRODUCT)
+					&& (zs == (xs ^ ys))) ||
+			    ((flags & MADDF_NEGATE_PRODUCT)
+					&& (zs != (xs ^ ys))))
+				/*
+				 * Cases of addition of zeros of equal signs
+				 * or subtraction of zeroes of opposite signs.
+				 * The sign of the resulting zero is in any
+				 * such case determined only by the sign of z.
+				 */
+				return z;
+
+			return ieee754sp_zero(ieee754_csr.rm == FPU_CSR_RD);
+		}
+		/* x*y is here 0, and z is not 0, so just return z */
 		return z;
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
 		SPDNORMX;
 
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
-		else if (zc == IEEE754_CLASS_INF)
+		if (zc == IEEE754_CLASS_INF)
 			return ieee754sp_inf(zs);
 		SPDNORMY;
 		break;
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
-		else if (zc == IEEE754_CLASS_INF)
+		if (zc == IEEE754_CLASS_INF)
 			return ieee754sp_inf(zs);
 		SPDNORMX;
 		break;
 
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
-		else if (zc == IEEE754_CLASS_INF)
+		if (zc == IEEE754_CLASS_INF)
 			return ieee754sp_inf(zs);
 		/* fall through to real computations */
 	}
@@ -158,108 +161,93 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
 
 	re = xe + ye;
 	rs = xs ^ ys;
-	if (flags & maddf_negate_product)
+	if (flags & MADDF_NEGATE_PRODUCT)
 		rs ^= 1;
 
-	/* shunt to top of word */
-	xm <<= 32 - (SP_FBITS + 1);
-	ym <<= 32 - (SP_FBITS + 1);
-
-	/*
-	 * Multiply 32 bits xm, ym to give high 32 bits rm with stickness.
-	 */
-	lxm = xm & 0xffff;
-	hxm = xm >> 16;
-	lym = ym & 0xffff;
-	hym = ym >> 16;
-
-	lrm = lxm * lym;	/* 16 * 16 => 32 */
-	hrm = hxm * hym;	/* 16 * 16 => 32 */
+	/* Multiple 24 bit xm and ym to give 48 bit results */
+	rm64 = (uint64_t)xm * ym;
 
-	t = lxm * hym; /* 16 * 16 => 32 */
-	at = lrm + (t << 16);
-	hrm += at < lrm;
-	lrm = at;
-	hrm = hrm + (t >> 16);
+	/* Shunt to top of word */
+	rm64 = rm64 << 16;
 
-	t = hxm * lym; /* 16 * 16 => 32 */
-	at = lrm + (t << 16);
-	hrm += at < lrm;
-	lrm = at;
-	hrm = hrm + (t >> 16);
-
-	rm = hrm | (lrm != 0);
-
-	/*
-	 * Sticky shift down to normal rounding precision.
-	 */
-	if ((int) rm < 0) {
-		rm = (rm >> (32 - (SP_FBITS + 1 + 3))) |
-		    ((rm << (SP_FBITS + 1 + 3)) != 0);
+	/* Put explicit bit at bit 62 if necessary */
+	if ((int64_t) rm64 < 0) {
+		rm64 = rm64 >> 1;
 		re++;
-	} else {
-		rm = (rm >> (32 - (SP_FBITS + 1 + 3 + 1))) |
-		     ((rm << (SP_FBITS + 1 + 3 + 1)) != 0);
 	}
-	assert(rm & (SP_HIDDEN_BIT << 3));
 
-	/* And now the addition */
+	assert(rm64 & (1 << 62));
 
-	assert(zm & SP_HIDDEN_BIT);
+	if (zc == IEEE754_CLASS_ZERO) {
+		/*
+		 * Move explicit bit from bit 62 to bit 26 since the
+		 * ieee754sp_format code expects the mantissa to be
+		 * 27 bits wide (24 + 3 rounding bits).
+		 */
+		rm = XSPSRS64(rm64, (62 - 26));
+		return ieee754sp_format(rs, re, rm);
+	}
 
-	/*
-	 * Provide guard,round and stick bit space.
-	 */
-	zm <<= 3;
+	/* Move explicit bit from bit 23 to bit 62 */
+	zm64 = (uint64_t)zm << (62 - 23);
+	assert(zm64 & (1 << 62));
 
+	/* Make the exponents the same */
 	if (ze > re) {
 		/*
 		 * Have to shift r fraction right to align.
 		 */
 		s = ze - re;
-		rm = XSPSRS(rm, s);
+		rm64 = XSPSRS64(rm64, s);
 		re += s;
 	} else if (re > ze) {
 		/*
 		 * Have to shift z fraction right to align.
 		 */
 		s = re - ze;
-		zm = XSPSRS(zm, s);
+		zm64 = XSPSRS64(zm64, s);
 		ze += s;
 	}
 	assert(ze == re);
 	assert(ze <= SP_EMAX);
 
+	/* Do the addition */
 	if (zs == rs) {
 		/*
-		 * Generate 28 bit result of adding two 27 bit numbers
-		 * leaving result in zm, zs and ze.
+		 * Generate 64 bit result by adding two 63 bit numbers
+		 * leaving result in zm64, zs and ze.
 		 */
-		zm = zm + rm;
-
-		if (zm >> (SP_FBITS + 1 + 3)) { /* carry out */
-			zm = XSPSRS1(zm);
+		zm64 = zm64 + rm64;
+		if ((int64_t)zm64 < 0) {	/* carry out */
+			zm64 = XSPSRS1(zm64);
 			ze++;
 		}
 	} else {
-		if (zm >= rm) {
-			zm = zm - rm;
+		if (zm64 >= rm64) {
+			zm64 = zm64 - rm64;
 		} else {
-			zm = rm - zm;
+			zm64 = rm64 - zm64;
 			zs = rs;
 		}
-		if (zm == 0)
+		if (zm64 == 0)
 			return ieee754sp_zero(ieee754_csr.rm == FPU_CSR_RD);
 
 		/*
-		 * Normalize in extended single precision
+		 * Put explicit bit at bit 62 if necessary.
 		 */
-		while ((zm >> (SP_MBITS + 3)) == 0) {
-			zm <<= 1;
+		while ((zm64 >> 62) == 0) {
+			zm64 <<= 1;
 			ze--;
 		}
-
 	}
+
+	/*
+	 * Move explicit bit from bit 62 to bit 26 since the
+	 * ieee754sp_format code expects the mantissa to be
+	 * 27 bits wide (24 + 3 rounding bits).
+	 */
+	zm = XSPSRS64(zm64, (62 - 26));
+
 	return ieee754sp_format(zs, ze, zm);
 }
 
@@ -272,5 +260,5 @@ union ieee754sp ieee754sp_maddf(union ieee754sp z, union ieee754sp x,
 union ieee754sp ieee754sp_msubf(union ieee754sp z, union ieee754sp x,
 				union ieee754sp y)
 {
-	return _sp_maddf(z, x, y, maddf_negate_product);
+	return _sp_maddf(z, x, y, MADDF_NEGATE_PRODUCT);
 }
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index b2da7c8baed7..292458b694fb 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -235,6 +235,28 @@ static int emulate_dcbz(struct pt_regs *regs, unsigned char __user *addr)
 
 #define SWIZ_PTR(p)		((unsigned char __user *)((p) ^ swiz))
 
+#define __get_user_or_set_dar(_regs, _dest, _addr)		\
+	({							\
+		int rc = 0;					\
+		typeof(_addr) __addr = (_addr);			\
+		if (__get_user_inatomic(_dest, __addr)) {	\
+			_regs->dar = (unsigned long)__addr;	\
+			rc = -EFAULT;				\
+		}						\
+		rc;						\
+	})
+
+#define __put_user_or_set_dar(_regs, _src, _addr)		\
+	({							\
+		int rc = 0;					\
+		typeof(_addr) __addr = (_addr);			\
+		if (__put_user_inatomic(_src, __addr)) {	\
+			_regs->dar = (unsigned long)__addr;	\
+			rc = -EFAULT;				\
+		}						\
+		rc;						\
+	})
+
 static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr,
 			    unsigned int reg, unsigned int nb,
 			    unsigned int flags, unsigned int instr,
@@ -263,9 +285,10 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr,
 		} else {
 			unsigned long pc = regs->nip ^ (swiz & 4);
 
-			if (__get_user_inatomic(instr,
-						(unsigned int __user *)pc))
+			if (__get_user_or_set_dar(regs, instr,
+						  (unsigned int __user *)pc))
 				return -EFAULT;
+
 			if (swiz == 0 && (flags & SW))
 				instr = cpu_to_le32(instr);
 			nb = (instr >> 11) & 0x1f;
@@ -309,31 +332,31 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr,
 			       ((nb0 + 3) / 4) * sizeof(unsigned long));
 
 		for (i = 0; i < nb; ++i, ++p)
-			if (__get_user_inatomic(REG_BYTE(rptr, i ^ bswiz),
-						SWIZ_PTR(p)))
+			if (__get_user_or_set_dar(regs, REG_BYTE(rptr, i ^ bswiz),
+						  SWIZ_PTR(p)))
 				return -EFAULT;
 		if (nb0 > 0) {
 			rptr = &regs->gpr[0];
 			addr += nb;
 			for (i = 0; i < nb0; ++i, ++p)
-				if (__get_user_inatomic(REG_BYTE(rptr,
-								 i ^ bswiz),
-							SWIZ_PTR(p)))
+				if (__get_user_or_set_dar(regs,
+							  REG_BYTE(rptr, i ^ bswiz),
+							  SWIZ_PTR(p)))
 					return -EFAULT;
 		}
 
 	} else {
 		for (i = 0; i < nb; ++i, ++p)
-			if (__put_user_inatomic(REG_BYTE(rptr, i ^ bswiz),
-						SWIZ_PTR(p)))
+			if (__put_user_or_set_dar(regs, REG_BYTE(rptr, i ^ bswiz),
+						  SWIZ_PTR(p)))
 				return -EFAULT;
 		if (nb0 > 0) {
 			rptr = &regs->gpr[0];
 			addr += nb;
 			for (i = 0; i < nb0; ++i, ++p)
-				if (__put_user_inatomic(REG_BYTE(rptr,
-								 i ^ bswiz),
-							SWIZ_PTR(p)))
+				if (__put_user_or_set_dar(regs,
+							  REG_BYTE(rptr, i ^ bswiz),
+							  SWIZ_PTR(p)))
 					return -EFAULT;
 		}
 	}
@@ -345,29 +368,32 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr,
  * Only POWER6 has these instructions, and it does true little-endian,
  * so we don't need the address swizzling.
  */
-static int emulate_fp_pair(unsigned char __user *addr, unsigned int reg,
-			   unsigned int flags)
+static int emulate_fp_pair(struct pt_regs *regs, unsigned char __user *addr,
+			   unsigned int reg, unsigned int flags)
 {
 	char *ptr0 = (char *) &current->thread.TS_FPR(reg);
 	char *ptr1 = (char *) &current->thread.TS_FPR(reg+1);
-	int i, ret, sw = 0;
+	int i, sw = 0;
 
 	if (reg & 1)
 		return 0;	/* invalid form: FRS/FRT must be even */
 	if (flags & SW)
 		sw = 7;
-	ret = 0;
+
 	for (i = 0; i < 8; ++i) {
 		if (!(flags & ST)) {
-			ret |= __get_user(ptr0[i^sw], addr + i);
-			ret |= __get_user(ptr1[i^sw], addr + i + 8);
+			if (__get_user_or_set_dar(regs, ptr0[i^sw], addr + i))
+				return -EFAULT;
+			if (__get_user_or_set_dar(regs, ptr1[i^sw], addr + i + 8))
+				return -EFAULT;
 		} else {
-			ret |= __put_user(ptr0[i^sw], addr + i);
-			ret |= __put_user(ptr1[i^sw], addr + i + 8);
+			if (__put_user_or_set_dar(regs, ptr0[i^sw], addr + i))
+				return -EFAULT;
+			if (__put_user_or_set_dar(regs, ptr1[i^sw], addr + i + 8))
+				return -EFAULT;
 		}
 	}
-	if (ret)
-		return -EFAULT;
+
 	return 1;	/* exception handled and fixed up */
 }
 
@@ -377,24 +403,27 @@ static int emulate_lq_stq(struct pt_regs *regs, unsigned char __user *addr,
 {
 	char *ptr0 = (char *)&regs->gpr[reg];
 	char *ptr1 = (char *)&regs->gpr[reg+1];
-	int i, ret, sw = 0;
+	int i, sw = 0;
 
 	if (reg & 1)
 		return 0;	/* invalid form: GPR must be even */
 	if (flags & SW)
 		sw = 7;
-	ret = 0;
+
 	for (i = 0; i < 8; ++i) {
 		if (!(flags & ST)) {
-			ret |= __get_user(ptr0[i^sw], addr + i);
-			ret |= __get_user(ptr1[i^sw], addr + i + 8);
+			if (__get_user_or_set_dar(regs, ptr0[i^sw], addr + i))
+				return -EFAULT;
+			if (__get_user_or_set_dar(regs, ptr1[i^sw], addr + i + 8))
+				return -EFAULT;
 		} else {
-			ret |= __put_user(ptr0[i^sw], addr + i);
-			ret |= __put_user(ptr1[i^sw], addr + i + 8);
+			if (__put_user_or_set_dar(regs, ptr0[i^sw], addr + i))
+				return -EFAULT;
+			if (__put_user_or_set_dar(regs, ptr1[i^sw], addr + i + 8))
+				return -EFAULT;
 		}
 	}
-	if (ret)
-		return -EFAULT;
+
 	return 1;	/* exception handled and fixed up */
 }
 #endif /* CONFIG_PPC64 */
@@ -687,9 +716,14 @@ static int emulate_vsx(unsigned char __user *addr, unsigned int reg,
 	for (j = 0; j < length; j += elsize) {
 		for (i = 0; i < elsize; ++i) {
 			if (flags & ST)
-				ret |= __put_user(ptr[i^sw], addr + i);
+				ret = __put_user_or_set_dar(regs, ptr[i^sw],
+							    addr + i);
 			else
-				ret |= __get_user(ptr[i^sw], addr + i);
+				ret = __get_user_or_set_dar(regs, ptr[i^sw],
+							    addr + i);
+
+			if (ret)
+				return ret;
 		}
 		ptr  += elsize;
 #ifdef __LITTLE_ENDIAN__
@@ -739,7 +773,7 @@ int fix_alignment(struct pt_regs *regs)
 	unsigned int dsisr;
 	unsigned char __user *addr;
 	unsigned long p, swiz;
-	int ret, i;
+	int i;
 	union data {
 		u64 ll;
 		double dd;
@@ -936,7 +970,7 @@ int fix_alignment(struct pt_regs *regs)
 		if (flags & F) {
 			/* Special case for 16-byte FP loads and stores */
 			PPC_WARN_ALIGNMENT(fp_pair, regs);
-			return emulate_fp_pair(addr, reg, flags);
+			return emulate_fp_pair(regs, addr, reg, flags);
 		} else {
 #ifdef CONFIG_PPC64
 			/* Special case for 16-byte loads and stores */
@@ -966,15 +1000,12 @@ int fix_alignment(struct pt_regs *regs)
 		}
 
 		data.ll = 0;
-		ret = 0;
 		p = (unsigned long)addr;
 
 		for (i = 0; i < nb; i++)
-			ret |= __get_user_inatomic(data.v[start + i],
-						   SWIZ_PTR(p++));
-
-		if (unlikely(ret))
-			return -EFAULT;
+			if (__get_user_or_set_dar(regs, data.v[start + i],
+						  SWIZ_PTR(p++)))
+				return -EFAULT;
 
 	} else if (flags & F) {
 		data.ll = current->thread.TS_FPR(reg);
@@ -1046,15 +1077,13 @@ int fix_alignment(struct pt_regs *regs)
 			break;
 		}
 
-		ret = 0;
 		p = (unsigned long)addr;
 
 		for (i = 0; i < nb; i++)
-			ret |= __put_user_inatomic(data.v[start + i],
-						   SWIZ_PTR(p++));
+			if (__put_user_or_set_dar(regs, data.v[start + i],
+						  SWIZ_PTR(p++)))
+				return -EFAULT;
 
-		if (unlikely(ret))
-			return -EFAULT;
 	} else if (flags & F)
 		current->thread.TS_FPR(reg) = data.ll;
 	else
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index bea785d7f853..af85d6b12028 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -5,6 +5,7 @@
 #include <linux/errno.h>
 
 typedef struct {
+	spinlock_t lock;
 	cpumask_t cpu_attach_mask;
 	atomic_t flush_count;
 	unsigned int flush_mm;
@@ -25,6 +26,7 @@ typedef struct {
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(name)						   \
+	.context.lock =	__SPIN_LOCK_UNLOCKED(name.context.lock),	   \
 	.context.pgtable_lock =						   \
 			__SPIN_LOCK_UNLOCKED(name.context.pgtable_lock),   \
 	.context.pgtable_list = LIST_HEAD_INIT(name.context.pgtable_list), \
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 515fea5a3fc4..f65a708ac395 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -15,6 +15,7 @@
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
+	spin_lock_init(&mm->context.lock);
 	spin_lock_init(&mm->context.pgtable_lock);
 	INIT_LIST_HEAD(&mm->context.pgtable_list);
 	spin_lock_init(&mm->context.gmap_lock);
@@ -93,7 +94,6 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	if (prev == next)
 		return;
 	cpumask_set_cpu(cpu, &next->context.cpu_attach_mask);
-	cpumask_set_cpu(cpu, mm_cpumask(next));
 	/* Clear old ASCE by loading the kernel ASCE. */
 	__ctl_load(S390_lowcore.kernel_asce, 1, 1);
 	__ctl_load(S390_lowcore.kernel_asce, 7, 7);
@@ -111,9 +111,8 @@ static inline void finish_arch_post_lock_switch(void)
 		preempt_disable();
 		while (atomic_read(&mm->context.flush_count))
 			cpu_relax();
-
-		if (mm->context.flush_mm)
-			__tlb_flush_mm(mm);
+		cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
+		__tlb_flush_mm_lazy(mm);
 		preempt_enable();
 	}
 	set_fs(current->thread.mm_segment);
@@ -126,6 +125,7 @@ static inline void activate_mm(struct mm_struct *prev,
                                struct mm_struct *next)
 {
 	switch_mm(prev, next, current);
+	cpumask_set_cpu(smp_processor_id(), mm_cpumask(next));
 	set_user_asce(next);
 }
 
diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h
index 39846100682a..eed927aeb08f 100644
--- a/arch/s390/include/asm/tlbflush.h
+++ b/arch/s390/include/asm/tlbflush.h
@@ -43,23 +43,6 @@ static inline void __tlb_flush_global(void)
  * Flush TLB entries for a specific mm on all CPUs (in case gmap is used
  * this implicates multiple ASCEs!).
  */
-static inline void __tlb_flush_full(struct mm_struct *mm)
-{
-	preempt_disable();
-	atomic_inc(&mm->context.flush_count);
-	if (cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) {
-		/* Local TLB flush */
-		__tlb_flush_local();
-	} else {
-		/* Global TLB flush */
-		__tlb_flush_global();
-		/* Reset TLB flush mask */
-		cpumask_copy(mm_cpumask(mm), &mm->context.cpu_attach_mask);
-	}
-	atomic_dec(&mm->context.flush_count);
-	preempt_enable();
-}
-
 static inline void __tlb_flush_mm(struct mm_struct *mm)
 {
 	unsigned long gmap_asce;
@@ -71,16 +54,18 @@ static inline void __tlb_flush_mm(struct mm_struct *mm)
 	 */
 	preempt_disable();
 	atomic_inc(&mm->context.flush_count);
+	/* Reset TLB flush mask */
+	cpumask_copy(mm_cpumask(mm), &mm->context.cpu_attach_mask);
+	barrier();
 	gmap_asce = READ_ONCE(mm->context.gmap_asce);
 	if (MACHINE_HAS_IDTE && gmap_asce != -1UL) {
 		if (gmap_asce)
 			__tlb_flush_idte(gmap_asce);
 		__tlb_flush_idte(mm->context.asce);
 	} else {
-		__tlb_flush_full(mm);
+		/* Global TLB flush */
+		__tlb_flush_global();
 	}
-	/* Reset TLB flush mask */
-	cpumask_copy(mm_cpumask(mm), &mm->context.cpu_attach_mask);
 	atomic_dec(&mm->context.flush_count);
 	preempt_enable();
 }
@@ -94,7 +79,6 @@ static inline void __tlb_flush_kernel(void)
 }
 #else
 #define __tlb_flush_global()	__tlb_flush_local()
-#define __tlb_flush_full(mm)	__tlb_flush_local()
 
 /*
  * Flush TLB entries for a specific ASCE on all CPUs.
@@ -112,10 +96,12 @@ static inline void __tlb_flush_kernel(void)
 
 static inline void __tlb_flush_mm_lazy(struct mm_struct * mm)
 {
+	spin_lock(&mm->context.lock);
 	if (mm->context.flush_mm) {
-		__tlb_flush_mm(mm);
 		mm->context.flush_mm = 0;
+		__tlb_flush_mm(mm);
 	}
+	spin_unlock(&mm->context.lock);
 }
 
 /*
diff --git a/block/blk-core.c b/block/blk-core.c
index d1f2801ce836..95379fc83805 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -233,7 +233,7 @@ EXPORT_SYMBOL(blk_start_queue_async);
  **/
 void blk_start_queue(struct request_queue *q)
 {
-	WARN_ON(!irqs_disabled());
+	WARN_ON(!in_interrupt() && !irqs_disabled());
 
 	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
 	__blk_run_queue(q);
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 45af0fe00f33..aaf2f810d170 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -143,8 +143,10 @@ static int skcipher_alloc_sgl(struct sock *sk)
 		sg_init_table(sgl->sg, MAX_SGL_ENTS + 1);
 		sgl->cur = 0;
 
-		if (sg)
+		if (sg) {
 			sg_chain(sg, MAX_SGL_ENTS + 1, sgl->sg);
+			sg_unmark_end(sg + (MAX_SGL_ENTS - 1));
+		}
 
 		list_add_tail(&sgl->list, &ctx->tsgl);
 	}
diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c
index 3822eae102db..6f78cea75103 100644
--- a/drivers/block/skd_main.c
+++ b/drivers/block/skd_main.c
@@ -2163,6 +2163,9 @@ static void skd_send_fitmsg(struct skd_device *skdev,
 		 */
 		qcmd |= FIT_QCMD_MSGSIZE_64;
 
+	/* Make sure skd_msg_buf is written before the doorbell is triggered. */
+	smp_wmb();
+
 	SKD_WRITEQ(skdev, qcmd, FIT_Q_COMMAND);
 
 }
@@ -2209,6 +2212,9 @@ static void skd_send_special_fitmsg(struct skd_device *skdev,
 	qcmd = skspcl->mb_dma_address;
 	qcmd |= FIT_QCMD_QID_NORMAL + FIT_QCMD_MSGSIZE_128;
 
+	/* Make sure skd_msg_buf is written before the doorbell is triggered. */
+	smp_wmb();
+
 	SKD_WRITEQ(skdev, qcmd, FIT_Q_COMMAND);
 }
 
@@ -4622,15 +4628,16 @@ static void skd_free_disk(struct skd_device *skdev)
 {
 	struct gendisk *disk = skdev->disk;
 
-	if (disk != NULL) {
-		struct request_queue *q = disk->queue;
+	if (disk && (disk->flags & GENHD_FL_UP))
+		del_gendisk(disk);
 
-		if (disk->flags & GENHD_FL_UP)
-			del_gendisk(disk);
-		if (q)
-			blk_cleanup_queue(q);
-		put_disk(disk);
+	if (skdev->queue) {
+		blk_cleanup_queue(skdev->queue);
+		skdev->queue = NULL;
+		disk->queue = NULL;
 	}
+
+	put_disk(disk);
 	skdev->disk = NULL;
 }
 
diff --git a/drivers/crypto/ccp/ccp-crypto-aes-xts.c b/drivers/crypto/ccp/ccp-crypto-aes-xts.c
index 58a4244b4752..3f26a415ef44 100644
--- a/drivers/crypto/ccp/ccp-crypto-aes-xts.c
+++ b/drivers/crypto/ccp/ccp-crypto-aes-xts.c
@@ -1,8 +1,9 @@
 /*
  * AMD Cryptographic Coprocessor (CCP) AES XTS crypto API support
  *
- * Copyright (C) 2013 Advanced Micro Devices, Inc.
+ * Copyright (C) 2013,2017 Advanced Micro Devices, Inc.
  *
+ * Author: Gary R Hook <gary.hook@amd.com>
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  *
  * This program is free software; you can redistribute it and/or modify
@@ -164,6 +165,7 @@ static int ccp_aes_xts_crypt(struct ablkcipher_request *req,
 	memset(&rctx->cmd, 0, sizeof(rctx->cmd));
 	INIT_LIST_HEAD(&rctx->cmd.entry);
 	rctx->cmd.engine = CCP_ENGINE_XTS_AES_128;
+	rctx->cmd.u.xts.type = CCP_AES_TYPE_128;
 	rctx->cmd.u.xts.action = (encrypt) ? CCP_AES_ACTION_ENCRYPT
 					   : CCP_AES_ACTION_DECRYPT;
 	rctx->cmd.u.xts.unit_size = unit_size;
diff --git a/drivers/crypto/ccp/ccp-dev-v5.c b/drivers/crypto/ccp/ccp-dev-v5.c
index 2c0ce5f605b3..17b19a68e269 100644
--- a/drivers/crypto/ccp/ccp-dev-v5.c
+++ b/drivers/crypto/ccp/ccp-dev-v5.c
@@ -131,6 +131,7 @@ union ccp_function {
 #define	CCP_AES_MODE(p)		((p)->aes.mode)
 #define	CCP_AES_TYPE(p)		((p)->aes.type)
 #define	CCP_XTS_SIZE(p)		((p)->aes_xts.size)
+#define	CCP_XTS_TYPE(p)		((p)->aes_xts.type)
 #define	CCP_XTS_ENCRYPT(p)	((p)->aes_xts.encrypt)
 #define	CCP_SHA_TYPE(p)		((p)->sha.type)
 #define	CCP_RSA_SIZE(p)		((p)->rsa.size)
@@ -318,6 +319,7 @@ static int ccp5_perform_xts_aes(struct ccp_op *op)
 	CCP5_CMD_PROT(&desc) = 0;
 
 	function.raw = 0;
+	CCP_XTS_TYPE(&function) = op->u.xts.type;
 	CCP_XTS_ENCRYPT(&function) = op->u.xts.action;
 	CCP_XTS_SIZE(&function) = op->u.xts.unit_size;
 	CCP5_CMD_FUNCTION(&desc) = function.raw;
diff --git a/drivers/crypto/ccp/ccp-dev.h b/drivers/crypto/ccp/ccp-dev.h
index 8ac7ae17e1f4..e23c36c7691c 100644
--- a/drivers/crypto/ccp/ccp-dev.h
+++ b/drivers/crypto/ccp/ccp-dev.h
@@ -187,6 +187,7 @@
 #define CCP_AES_CTX_SB_COUNT		1
 
 #define CCP_XTS_AES_KEY_SB_COUNT	1
+#define CCP5_XTS_AES_KEY_SB_COUNT	2
 #define CCP_XTS_AES_CTX_SB_COUNT	1
 
 #define CCP_SHA_SB_COUNT		1
@@ -472,6 +473,7 @@ struct ccp_aes_op {
 };
 
 struct ccp_xts_aes_op {
+	enum ccp_aes_type type;
 	enum ccp_aes_action action;
 	enum ccp_xts_aes_unit_size unit_size;
 };
diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c
index 50fae4442801..64deb006c3be 100644
--- a/drivers/crypto/ccp/ccp-ops.c
+++ b/drivers/crypto/ccp/ccp-ops.c
@@ -779,6 +779,8 @@ static int ccp_run_xts_aes_cmd(struct ccp_cmd_queue *cmd_q,
 	struct ccp_op op;
 	unsigned int unit_size, dm_offset;
 	bool in_place = false;
+	unsigned int sb_count;
+	enum ccp_aes_type aestype;
 	int ret;
 
 	switch (xts->unit_size) {
@@ -802,7 +804,9 @@ static int ccp_run_xts_aes_cmd(struct ccp_cmd_queue *cmd_q,
 		return -EINVAL;
 	}
 
-	if (xts->key_len != AES_KEYSIZE_128)
+	if (xts->key_len == AES_KEYSIZE_128)
+		aestype = CCP_AES_TYPE_128;
+	else
 		return -EINVAL;
 
 	if (!xts->final && (xts->src_len & (AES_BLOCK_SIZE - 1)))
@@ -824,23 +828,44 @@ static int ccp_run_xts_aes_cmd(struct ccp_cmd_queue *cmd_q,
 	op.sb_key = cmd_q->sb_key;
 	op.sb_ctx = cmd_q->sb_ctx;
 	op.init = 1;
+	op.u.xts.type = aestype;
 	op.u.xts.action = xts->action;
 	op.u.xts.unit_size = xts->unit_size;
 
-	/* All supported key sizes fit in a single (32-byte) SB entry
-	 * and must be in little endian format. Use the 256-bit byte
-	 * swap passthru option to convert from big endian to little
-	 * endian.
+	/* A version 3 device only supports 128-bit keys, which fits into a
+	 * single SB entry. A version 5 device uses a 512-bit vector, so two
+	 * SB entries.
 	 */
+	if (cmd_q->ccp->vdata->version == CCP_VERSION(3, 0))
+		sb_count = CCP_XTS_AES_KEY_SB_COUNT;
+	else
+		sb_count = CCP5_XTS_AES_KEY_SB_COUNT;
 	ret = ccp_init_dm_workarea(&key, cmd_q,
-				   CCP_XTS_AES_KEY_SB_COUNT * CCP_SB_BYTES,
+				   sb_count * CCP_SB_BYTES,
 				   DMA_TO_DEVICE);
 	if (ret)
 		return ret;
 
-	dm_offset = CCP_SB_BYTES - AES_KEYSIZE_128;
-	ccp_set_dm_area(&key, dm_offset, xts->key, 0, xts->key_len);
-	ccp_set_dm_area(&key, 0, xts->key, dm_offset, xts->key_len);
+	if (cmd_q->ccp->vdata->version == CCP_VERSION(3, 0)) {
+		/* All supported key sizes must be in little endian format.
+		 * Use the 256-bit byte swap passthru option to convert from
+		 * big endian to little endian.
+		 */
+		dm_offset = CCP_SB_BYTES - AES_KEYSIZE_128;
+		ccp_set_dm_area(&key, dm_offset, xts->key, 0, xts->key_len);
+		ccp_set_dm_area(&key, 0, xts->key, xts->key_len, xts->key_len);
+	} else {
+		/* Version 5 CCPs use a 512-bit space for the key: each portion
+		 * occupies 256 bits, or one entire slot, and is zero-padded.
+		 */
+		unsigned int pad;
+
+		dm_offset = CCP_SB_BYTES;
+		pad = dm_offset - xts->key_len;
+		ccp_set_dm_area(&key, pad, xts->key, 0, xts->key_len);
+		ccp_set_dm_area(&key, dm_offset + pad, xts->key, xts->key_len,
+				xts->key_len);
+	}
 	ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
 			     CCP_PASSTHRU_BYTESWAP_256BIT);
 	if (ret) {
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 7309c0824887..a2449d77af07 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -574,7 +574,7 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	err = device_register(&devfreq->dev);
 	if (err) {
 		mutex_unlock(&devfreq->lock);
-		goto err_out;
+		goto err_dev;
 	}
 
 	devfreq->trans_table =	devm_kzalloc(&devfreq->dev, sizeof(unsigned int) *
@@ -618,6 +618,9 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	mutex_unlock(&devfreq_list_lock);
 
 	device_unregister(&devfreq->dev);
+err_dev:
+	if (devfreq)
+		kfree(devfreq);
 err_out:
 	return ERR_PTR(err);
 }
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index c3b21865443e..1feec34ca9dd 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -47,6 +47,13 @@ static void sun4i_drv_disable_vblank(struct drm_device *drm, unsigned int pipe)
 	sun4i_tcon_enable_vblank(tcon, false);
 }
 
+static void sun4i_drv_lastclose(struct drm_device *dev)
+{
+	struct sun4i_drv *drv = dev->dev_private;
+
+	drm_fbdev_cma_restore_mode(drv->fbdev);
+}
+
 static const struct file_operations sun4i_drv_fops = {
 	.owner		= THIS_MODULE,
 	.open		= drm_open,
@@ -65,6 +72,7 @@ static struct drm_driver sun4i_drv_driver = {
 	.driver_features	= DRIVER_GEM | DRIVER_MODESET | DRIVER_PRIME | DRIVER_ATOMIC,
 
 	/* Generic Operations */
+	.lastclose		= sun4i_drv_lastclose,
 	.fops			= &sun4i_drv_fops,
 	.name			= "sun4i-drm",
 	.desc			= "Allwinner sun4i Display Engine",
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 63e82f8e8308..fb4ce0394ac7 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -446,15 +446,10 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
 
 	ret = ipv6_stub->ipv6_dst_lookup(addr->net, NULL, &dst, &fl6);
 	if (ret < 0)
-		goto put;
+		return ret;
 
 	rt = (struct rt6_info *)dst;
-	if (ipv6_addr_any(&fl6.saddr)) {
-		ret = ipv6_dev_get_saddr(addr->net, ip6_dst_idev(dst)->dev,
-					 &fl6.daddr, 0, &fl6.saddr);
-		if (ret)
-			goto put;
-
+	if (ipv6_addr_any(&src_in->sin6_addr)) {
 		src_in->sin6_family = AF_INET6;
 		src_in->sin6_addr = fl6.saddr;
 	}
@@ -471,9 +466,6 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
 
 	*pdst = dst;
 	return 0;
-put:
-	dst_release(dst);
-	return ret;
 }
 #else
 static int addr6_resolve(struct sockaddr_in6 *src_in,
diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index 4bd5b5caa243..613074e963bb 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -551,7 +551,7 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 		case IB_WR_RDMA_WRITE:
 			if (newreq && !(qp->s_flags & RVT_S_UNLIMITED_CREDIT))
 				qp->s_lsn++;
-			/* FALLTHROUGH */
+			goto no_flow_control;
 		case IB_WR_RDMA_WRITE_WITH_IMM:
 			/* If no credit, return. */
 			if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT) &&
@@ -559,6 +559,7 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 				qp->s_flags |= RVT_S_WAIT_SSN_CREDIT;
 				goto bail;
 			}
+no_flow_control:
 			put_ib_reth_vaddr(
 				wqe->rdma_wr.remote_addr,
 				&ohdr->u.rc.reth);
diff --git a/drivers/infiniband/hw/qib/qib_rc.c b/drivers/infiniband/hw/qib/qib_rc.c
index f3fe787c9426..c1523f9a3c12 100644
--- a/drivers/infiniband/hw/qib/qib_rc.c
+++ b/drivers/infiniband/hw/qib/qib_rc.c
@@ -357,7 +357,7 @@ int qib_make_rc_req(struct rvt_qp *qp, unsigned long *flags)
 		case IB_WR_RDMA_WRITE:
 			if (newreq && !(qp->s_flags & RVT_S_UNLIMITED_CREDIT))
 				qp->s_lsn++;
-			/* FALLTHROUGH */
+			goto no_flow_control;
 		case IB_WR_RDMA_WRITE_WITH_IMM:
 			/* If no credit, return. */
 			if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT) &&
@@ -365,7 +365,7 @@ int qib_make_rc_req(struct rvt_qp *qp, unsigned long *flags)
 				qp->s_flags |= RVT_S_WAIT_SSN_CREDIT;
 				goto bail;
 			}
-
+no_flow_control:
 			ohdr->u.rc.reth.vaddr =
 				cpu_to_be64(wqe->rdma_wr.remote_addr);
 			ohdr->u.rc.reth.rkey =
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 5be14ad29d46..dbf09836ff30 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -904,6 +904,13 @@ static const struct dmi_system_id __initconst i8042_dmi_kbdreset_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P34"),
 		},
 	},
+	{
+		/* Gigabyte P57 - Elantech touchpad */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P57"),
+		},
+	},
 	{
 		/* Schenker XMG C504 - Elantech touchpad */
 		.matches = {
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index c3ea03c9a1a8..02619cabda8b 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -333,6 +333,7 @@ struct cached_dev {
 	/* Limit number of writeback bios in flight */
 	struct semaphore	in_flight;
 	struct task_struct	*writeback_thread;
+	struct workqueue_struct	*writeback_write_wq;
 
 	struct keybuf		writeback_keys;
 
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index a37c1776f2e3..e0f1c6d534fe 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -196,12 +196,12 @@ static void bch_data_insert_start(struct closure *cl)
 	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
 	struct bio *bio = op->bio, *n;
 
-	if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0)
-		wake_up_gc(op->c);
-
 	if (op->bypass)
 		return bch_data_invalidate(cl);
 
+	if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0)
+		wake_up_gc(op->c);
+
 	/*
 	 * Journal writes are marked REQ_PREFLUSH; if the original write was a
 	 * flush, it'll wait on the journal write.
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 66669c8f4161..f4557f558b24 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1025,7 +1025,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
 	}
 
 	if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) {
-		bch_sectors_dirty_init(dc);
+		bch_sectors_dirty_init(&dc->disk);
 		atomic_set(&dc->has_dirty, 1);
 		atomic_inc(&dc->count);
 		bch_writeback_queue(dc);
@@ -1058,6 +1058,8 @@ static void cached_dev_free(struct closure *cl)
 	cancel_delayed_work_sync(&dc->writeback_rate_update);
 	if (!IS_ERR_OR_NULL(dc->writeback_thread))
 		kthread_stop(dc->writeback_thread);
+	if (dc->writeback_write_wq)
+		destroy_workqueue(dc->writeback_write_wq);
 
 	mutex_lock(&bch_register_lock);
 
@@ -1229,6 +1231,7 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
 		goto err;
 
 	bcache_device_attach(d, c, u - c->uuids);
+	bch_sectors_dirty_init(d);
 	bch_flash_dev_request_init(d);
 	add_disk(d->disk);
 
@@ -1967,6 +1970,8 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 			else
 				err = "device busy";
 			mutex_unlock(&bch_register_lock);
+			if (!IS_ERR(bdev))
+				bdput(bdev);
 			if (attr == &ksysfs_register_quiet)
 				goto out;
 		}
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index b3ff57d61dde..4fbb5532f24c 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -191,7 +191,7 @@ STORE(__cached_dev)
 {
 	struct cached_dev *dc = container_of(kobj, struct cached_dev,
 					     disk.kobj);
-	unsigned v = size;
+	ssize_t v = size;
 	struct cache_set *c;
 	struct kobj_uevent_env *env;
 
@@ -226,7 +226,7 @@ STORE(__cached_dev)
 		bch_cached_dev_run(dc);
 
 	if (attr == &sysfs_cache_mode) {
-		ssize_t v = bch_read_string_list(buf, bch_cache_modes + 1);
+		v = bch_read_string_list(buf, bch_cache_modes + 1);
 
 		if (v < 0)
 			return v;
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index dde6172f3f10..eb70f6894f05 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -73,24 +73,44 @@ STRTO_H(strtouint, unsigned int)
 STRTO_H(strtoll, long long)
 STRTO_H(strtoull, unsigned long long)
 
+/**
+ * bch_hprint() - formats @v to human readable string for sysfs.
+ *
+ * @v - signed 64 bit integer
+ * @buf - the (at least 8 byte) buffer to format the result into.
+ *
+ * Returns the number of bytes used by format.
+ */
 ssize_t bch_hprint(char *buf, int64_t v)
 {
 	static const char units[] = "?kMGTPEZY";
-	char dec[4] = "";
-	int u, t = 0;
-
-	for (u = 0; v >= 1024 || v <= -1024; u++) {
-		t = v & ~(~0 << 10);
-		v >>= 10;
-	}
-
-	if (!u)
-		return sprintf(buf, "%llu", v);
-
-	if (v < 100 && v > -100)
-		snprintf(dec, sizeof(dec), ".%i", t / 100);
-
-	return sprintf(buf, "%lli%s%c", v, dec, units[u]);
+	int u = 0, t;
+
+	uint64_t q;
+
+	if (v < 0)
+		q = -v;
+	else
+		q = v;
+
+	/* For as long as the number is more than 3 digits, but at least
+	 * once, shift right / divide by 1024.  Keep the remainder for
+	 * a digit after the decimal point.
+	 */
+	do {
+		u++;
+
+		t = q & ~(~0 << 10);
+		q >>= 10;
+	} while (q >= 1000);
+
+	if (v < 0)
+		/* '-', up to 3 digits, '.', 1 digit, 1 character, null;
+		 * yields 8 bytes.
+		 */
+		return sprintf(buf, "-%llu.%i%c", q, t * 10 / 1024, units[u]);
+	else
+		return sprintf(buf, "%llu.%i%c", q, t * 10 / 1024, units[u]);
 }
 
 ssize_t bch_snprint_string_list(char *buf, size_t size, const char * const list[],
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index e51644e503a5..4ce2b19fe120 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -20,7 +20,8 @@
 static void __update_writeback_rate(struct cached_dev *dc)
 {
 	struct cache_set *c = dc->disk.c;
-	uint64_t cache_sectors = c->nbuckets * c->sb.bucket_size;
+	uint64_t cache_sectors = c->nbuckets * c->sb.bucket_size -
+				bcache_flash_devs_sectors_dirty(c);
 	uint64_t cache_dirty_target =
 		div_u64(cache_sectors * dc->writeback_percent, 100);
 
@@ -186,7 +187,7 @@ static void write_dirty(struct closure *cl)
 
 	closure_bio_submit(&io->bio, cl);
 
-	continue_at(cl, write_dirty_finish, system_wq);
+	continue_at(cl, write_dirty_finish, io->dc->writeback_write_wq);
 }
 
 static void read_dirty_endio(struct bio *bio)
@@ -206,7 +207,7 @@ static void read_dirty_submit(struct closure *cl)
 
 	closure_bio_submit(&io->bio, cl);
 
-	continue_at(cl, write_dirty, system_wq);
+	continue_at(cl, write_dirty, io->dc->writeback_write_wq);
 }
 
 static void read_dirty(struct cached_dev *dc)
@@ -482,17 +483,17 @@ static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b,
 	return MAP_CONTINUE;
 }
 
-void bch_sectors_dirty_init(struct cached_dev *dc)
+void bch_sectors_dirty_init(struct bcache_device *d)
 {
 	struct sectors_dirty_init op;
 
 	bch_btree_op_init(&op.op, -1);
-	op.inode = dc->disk.id;
+	op.inode = d->id;
 
-	bch_btree_map_keys(&op.op, dc->disk.c, &KEY(op.inode, 0, 0),
+	bch_btree_map_keys(&op.op, d->c, &KEY(op.inode, 0, 0),
 			   sectors_dirty_init_fn, 0);
 
-	dc->disk.sectors_dirty_last = bcache_dev_sectors_dirty(&dc->disk);
+	d->sectors_dirty_last = bcache_dev_sectors_dirty(d);
 }
 
 void bch_cached_dev_writeback_init(struct cached_dev *dc)
@@ -516,6 +517,11 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc)
 
 int bch_cached_dev_writeback_start(struct cached_dev *dc)
 {
+	dc->writeback_write_wq = alloc_workqueue("bcache_writeback_wq",
+						WQ_MEM_RECLAIM, 0);
+	if (!dc->writeback_write_wq)
+		return -ENOMEM;
+
 	dc->writeback_thread = kthread_create(bch_writeback_thread, dc,
 					      "bcache_writeback");
 	if (IS_ERR(dc->writeback_thread))
diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h
index 301eaf565167..cdf8d253209e 100644
--- a/drivers/md/bcache/writeback.h
+++ b/drivers/md/bcache/writeback.h
@@ -14,6 +14,25 @@ static inline uint64_t bcache_dev_sectors_dirty(struct bcache_device *d)
 	return ret;
 }
 
+static inline uint64_t  bcache_flash_devs_sectors_dirty(struct cache_set *c)
+{
+	uint64_t i, ret = 0;
+
+	mutex_lock(&bch_register_lock);
+
+	for (i = 0; i < c->nr_uuids; i++) {
+		struct bcache_device *d = c->devices[i];
+
+		if (!d || !UUID_FLASH_ONLY(&c->uuids[i]))
+			continue;
+	   ret += bcache_dev_sectors_dirty(d);
+	}
+
+	mutex_unlock(&bch_register_lock);
+
+	return ret;
+}
+
 static inline unsigned offset_to_stripe(struct bcache_device *d,
 					uint64_t offset)
 {
@@ -85,7 +104,7 @@ static inline void bch_writeback_add(struct cached_dev *dc)
 
 void bcache_dev_sectors_dirty_add(struct cache_set *, unsigned, uint64_t, int);
 
-void bch_sectors_dirty_init(struct cached_dev *dc);
+void bch_sectors_dirty_init(struct bcache_device *);
 void bch_cached_dev_writeback_init(struct cached_dev *);
 int bch_cached_dev_writeback_start(struct cached_dev *);
 
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 2d826927a3bf..fb02c3979bf4 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1992,6 +1992,11 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 	long pages;
 	struct bitmap_page *new_bp;
 
+	if (bitmap->storage.file && !init) {
+		pr_info("md: cannot resize file-based bitmap\n");
+		return -EINVAL;
+	}
+
 	if (chunksize == 0) {
 		/* If there is enough space, leave the chunk size unchanged,
 		 * else increase by factor of two until there is enough space.
diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c
index c2ee6e39fd0c..20397aba6849 100644
--- a/drivers/media/usb/uvc/uvc_ctrl.c
+++ b/drivers/media/usb/uvc/uvc_ctrl.c
@@ -2002,6 +2002,13 @@ int uvc_ctrl_add_mapping(struct uvc_video_chain *chain,
 		goto done;
 	}
 
+	/* Validate the user-provided bit-size and offset */
+	if (mapping->size > 32 ||
+	    mapping->offset + mapping->size > ctrl->info.size * 8) {
+		ret = -EINVAL;
+		goto done;
+	}
+
 	list_for_each_entry(map, &ctrl->info.mappings, list) {
 		if (mapping->id == map->id) {
 			uvc_trace(UVC_TRACE_CONTROL, "Can't add mapping '%s', "
diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
index bacecbd68a6d..dc51dd86377d 100644
--- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
+++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
@@ -773,7 +773,8 @@ static int put_v4l2_event32(struct v4l2_event *kp, struct v4l2_event32 __user *u
 		copy_to_user(&up->u, &kp->u, sizeof(kp->u)) ||
 		put_user(kp->pending, &up->pending) ||
 		put_user(kp->sequence, &up->sequence) ||
-		compat_put_timespec(&kp->timestamp, &up->timestamp) ||
+		put_user(kp->timestamp.tv_sec, &up->timestamp.tv_sec) ||
+		put_user(kp->timestamp.tv_nsec, &up->timestamp.tv_nsec) ||
 		put_user(kp->id, &up->id) ||
 		copy_to_user(up->reserved, kp->reserved, 8 * sizeof(__u32)))
 			return -EFAULT;
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index b57fc6d6e28a..d08dfc8b9ba9 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -586,6 +586,14 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id)
 	events = status & (PCI_EXP_SLTSTA_ABP | PCI_EXP_SLTSTA_PFD |
 			   PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_CC |
 			   PCI_EXP_SLTSTA_DLLSC);
+
+	/*
+	 * If we've already reported a power fault, don't report it again
+	 * until we've done something to handle it.
+	 */
+	if (ctrl->power_fault_detected)
+		events &= ~PCI_EXP_SLTSTA_PFD;
+
 	if (!events)
 		return IRQ_NONE;
 
diff --git a/drivers/pci/hotplug/shpchp_hpc.c b/drivers/pci/hotplug/shpchp_hpc.c
index de0ea474fb73..e5824c7b7b6b 100644
--- a/drivers/pci/hotplug/shpchp_hpc.c
+++ b/drivers/pci/hotplug/shpchp_hpc.c
@@ -1062,6 +1062,8 @@ int shpc_init(struct controller *ctrl, struct pci_dev *pdev)
 		if (rc) {
 			ctrl_info(ctrl, "Can't get msi for the hotplug controller\n");
 			ctrl_info(ctrl, "Use INTx for the hotplug controller\n");
+		} else {
+			pci_set_master(pdev);
 		}
 
 		rc = request_irq(ctrl->pci_dev->irq, shpc_isr, IRQF_SHARED,
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index c9a146948192..a5b7bd3c9bac 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -32,6 +32,7 @@
 #include <linux/pinctrl/pinconf.h>
 #include <linux/pinctrl/pinconf-generic.h>
 
+#include "core.h"
 #include "pinctrl-utils.h"
 #include "pinctrl-amd.h"
 
@@ -712,6 +713,69 @@ static const struct pinconf_ops amd_pinconf_ops = {
 	.pin_config_group_set = amd_pinconf_group_set,
 };
 
+#ifdef CONFIG_PM_SLEEP
+static bool amd_gpio_should_save(struct amd_gpio *gpio_dev, unsigned int pin)
+{
+	const struct pin_desc *pd = pin_desc_get(gpio_dev->pctrl, pin);
+
+	if (!pd)
+		return false;
+
+	/*
+	 * Only restore the pin if it is actually in use by the kernel (or
+	 * by userspace).
+	 */
+	if (pd->mux_owner || pd->gpio_owner ||
+	    gpiochip_line_is_irq(&gpio_dev->gc, pin))
+		return true;
+
+	return false;
+}
+
+int amd_gpio_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct amd_gpio *gpio_dev = platform_get_drvdata(pdev);
+	struct pinctrl_desc *desc = gpio_dev->pctrl->desc;
+	int i;
+
+	for (i = 0; i < desc->npins; i++) {
+		int pin = desc->pins[i].number;
+
+		if (!amd_gpio_should_save(gpio_dev, pin))
+			continue;
+
+		gpio_dev->saved_regs[i] = readl(gpio_dev->base + pin*4);
+	}
+
+	return 0;
+}
+
+int amd_gpio_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct amd_gpio *gpio_dev = platform_get_drvdata(pdev);
+	struct pinctrl_desc *desc = gpio_dev->pctrl->desc;
+	int i;
+
+	for (i = 0; i < desc->npins; i++) {
+		int pin = desc->pins[i].number;
+
+		if (!amd_gpio_should_save(gpio_dev, pin))
+			continue;
+
+		writel(gpio_dev->saved_regs[i], gpio_dev->base + pin*4);
+	}
+
+	return 0;
+}
+
+static const struct dev_pm_ops amd_gpio_pm_ops = {
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(amd_gpio_suspend,
+				     amd_gpio_resume)
+};
+#endif
+
 static struct pinctrl_desc amd_pinctrl_desc = {
 	.pins	= kerncz_pins,
 	.npins = ARRAY_SIZE(kerncz_pins),
@@ -751,6 +815,14 @@ static int amd_gpio_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+#ifdef CONFIG_PM_SLEEP
+	gpio_dev->saved_regs = devm_kcalloc(&pdev->dev, amd_pinctrl_desc.npins,
+					    sizeof(*gpio_dev->saved_regs),
+					    GFP_KERNEL);
+	if (!gpio_dev->saved_regs)
+		return -ENOMEM;
+#endif
+
 	gpio_dev->pdev = pdev;
 	gpio_dev->gc.direction_input	= amd_gpio_direction_input;
 	gpio_dev->gc.direction_output	= amd_gpio_direction_output;
@@ -839,6 +911,9 @@ static struct platform_driver amd_gpio_driver = {
 	.driver		= {
 		.name	= "amd_gpio",
 		.acpi_match_table = ACPI_PTR(amd_gpio_acpi_match),
+#ifdef CONFIG_PM_SLEEP
+		.pm	= &amd_gpio_pm_ops,
+#endif
 	},
 	.probe		= amd_gpio_probe,
 	.remove		= amd_gpio_remove,
diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h
index 7bfea47dbb47..e8bbb20779d0 100644
--- a/drivers/pinctrl/pinctrl-amd.h
+++ b/drivers/pinctrl/pinctrl-amd.h
@@ -95,6 +95,7 @@ struct amd_gpio {
 	struct gpio_chip        gc;
 	struct resource         *res;
 	struct platform_device  *pdev;
+	u32			*saved_regs;
 };
 
 /*  KERNCZ configuration*/
diff --git a/drivers/s390/scsi/zfcp_dbf.c b/drivers/s390/scsi/zfcp_dbf.c
index d5bf36ec8a75..34367d172961 100644
--- a/drivers/s390/scsi/zfcp_dbf.c
+++ b/drivers/s390/scsi/zfcp_dbf.c
@@ -3,7 +3,7 @@
  *
  * Debug traces for zfcp.
  *
- * Copyright IBM Corp. 2002, 2016
+ * Copyright IBM Corp. 2002, 2017
  */
 
 #define KMSG_COMPONENT "zfcp"
@@ -447,6 +447,7 @@ static u16 zfcp_dbf_san_res_cap_len_if_gpn_ft(char *tag,
 	struct fc_ct_hdr *reqh = sg_virt(ct_els->req);
 	struct fc_ns_gid_ft *reqn = (struct fc_ns_gid_ft *)(reqh + 1);
 	struct scatterlist *resp_entry = ct_els->resp;
+	struct fc_ct_hdr *resph;
 	struct fc_gpn_ft_resp *acc;
 	int max_entries, x, last = 0;
 
@@ -473,6 +474,13 @@ static u16 zfcp_dbf_san_res_cap_len_if_gpn_ft(char *tag,
 		return len; /* not GPN_FT response so do not cap */
 
 	acc = sg_virt(resp_entry);
+
+	/* cap all but accept CT responses to at least the CT header */
+	resph = (struct fc_ct_hdr *)acc;
+	if ((ct_els->status) ||
+	    (resph->ct_cmd != cpu_to_be16(FC_FS_ACC)))
+		return max(FC_CT_HDR_LEN, ZFCP_DBF_SAN_MAX_PAYLOAD);
+
 	max_entries = (reqh->ct_mr_size * 4 / sizeof(struct fc_gpn_ft_resp))
 		+ 1 /* zfcp_fc_scan_ports: bytes correct, entries off-by-one
 		     * to account for header as 1st pseudo "entry" */;
@@ -555,8 +563,8 @@ void zfcp_dbf_scsi(char *tag, int level, struct scsi_cmnd *sc,
 	rec->scsi_retries = sc->retries;
 	rec->scsi_allowed = sc->allowed;
 	rec->scsi_id = sc->device->id;
-	/* struct zfcp_dbf_scsi needs to be updated to handle 64bit LUNs */
 	rec->scsi_lun = (u32)sc->device->lun;
+	rec->scsi_lun_64_hi = (u32)(sc->device->lun >> 32);
 	rec->host_scribble = (unsigned long)sc->host_scribble;
 
 	memcpy(rec->scsi_opcode, sc->cmnd,
@@ -564,19 +572,32 @@ void zfcp_dbf_scsi(char *tag, int level, struct scsi_cmnd *sc,
 
 	if (fsf) {
 		rec->fsf_req_id = fsf->req_id;
+		rec->pl_len = FCP_RESP_WITH_EXT;
 		fcp_rsp = (struct fcp_resp_with_ext *)
 				&(fsf->qtcb->bottom.io.fcp_rsp);
+		/* mandatory parts of FCP_RSP IU in this SCSI record */
 		memcpy(&rec->fcp_rsp, fcp_rsp, FCP_RESP_WITH_EXT);
 		if (fcp_rsp->resp.fr_flags & FCP_RSP_LEN_VAL) {
 			fcp_rsp_info = (struct fcp_resp_rsp_info *) &fcp_rsp[1];
 			rec->fcp_rsp_info = fcp_rsp_info->rsp_code;
+			rec->pl_len += be32_to_cpu(fcp_rsp->ext.fr_rsp_len);
 		}
 		if (fcp_rsp->resp.fr_flags & FCP_SNS_LEN_VAL) {
-			rec->pl_len = min((u16)SCSI_SENSE_BUFFERSIZE,
-					  (u16)ZFCP_DBF_PAY_MAX_REC);
-			zfcp_dbf_pl_write(dbf, sc->sense_buffer, rec->pl_len,
-					  "fcp_sns", fsf->req_id);
+			rec->pl_len += be32_to_cpu(fcp_rsp->ext.fr_sns_len);
 		}
+		/* complete FCP_RSP IU in associated PAYload record
+		 * but only if there are optional parts
+		 */
+		if (fcp_rsp->resp.fr_flags != 0)
+			zfcp_dbf_pl_write(
+				dbf, fcp_rsp,
+				/* at least one full PAY record
+				 * but not beyond hardware response field
+				 */
+				min_t(u16, max_t(u16, rec->pl_len,
+						 ZFCP_DBF_PAY_MAX_REC),
+				      FSF_FCP_RSP_SIZE),
+				"fcp_riu", fsf->req_id);
 	}
 
 	debug_event(dbf->scsi, level, rec, sizeof(*rec));
diff --git a/drivers/s390/scsi/zfcp_dbf.h b/drivers/s390/scsi/zfcp_dbf.h
index db186d44cfaf..b60667c145fd 100644
--- a/drivers/s390/scsi/zfcp_dbf.h
+++ b/drivers/s390/scsi/zfcp_dbf.h
@@ -2,7 +2,7 @@
  * zfcp device driver
  * debug feature declarations
  *
- * Copyright IBM Corp. 2008, 2016
+ * Copyright IBM Corp. 2008, 2017
  */
 
 #ifndef ZFCP_DBF_H
@@ -204,7 +204,7 @@ enum zfcp_dbf_scsi_id {
  * @id: unique number of recovery record type
  * @tag: identifier string specifying the location of initiation
  * @scsi_id: scsi device id
- * @scsi_lun: scsi device logical unit number
+ * @scsi_lun: scsi device logical unit number, low part of 64 bit, old 32 bit
  * @scsi_result: scsi result
  * @scsi_retries: current retry number of scsi request
  * @scsi_allowed: allowed retries
@@ -214,6 +214,7 @@ enum zfcp_dbf_scsi_id {
  * @host_scribble: LLD specific data attached to SCSI request
  * @pl_len: length of paload stored as zfcp_dbf_pay
  * @fsf_rsp: response for fsf request
+ * @scsi_lun_64_hi: scsi device logical unit number, high part of 64 bit
  */
 struct zfcp_dbf_scsi {
 	u8 id;
@@ -230,6 +231,7 @@ struct zfcp_dbf_scsi {
 	u64 host_scribble;
 	u16 pl_len;
 	struct fcp_resp_with_ext fcp_rsp;
+	u32 scsi_lun_64_hi;
 } __packed;
 
 /**
@@ -323,7 +325,11 @@ void zfcp_dbf_hba_fsf_response(struct zfcp_fsf_req *req)
 {
 	struct fsf_qtcb *qtcb = req->qtcb;
 
-	if ((qtcb->prefix.prot_status != FSF_PROT_GOOD) &&
+	if (unlikely(req->status & (ZFCP_STATUS_FSFREQ_DISMISSED |
+				    ZFCP_STATUS_FSFREQ_ERROR))) {
+		zfcp_dbf_hba_fsf_resp("fs_rerr", 3, req);
+
+	} else if ((qtcb->prefix.prot_status != FSF_PROT_GOOD) &&
 	    (qtcb->prefix.prot_status != FSF_PROT_FSF_STATUS_PRESENTED)) {
 		zfcp_dbf_hba_fsf_resp("fs_perr", 1, req);
 
@@ -401,7 +407,8 @@ void zfcp_dbf_scsi_abort(char *tag, struct scsi_cmnd *scmd,
  * @flag: indicates type of reset (Target Reset, Logical Unit Reset)
  */
 static inline
-void zfcp_dbf_scsi_devreset(char *tag, struct scsi_cmnd *scmnd, u8 flag)
+void zfcp_dbf_scsi_devreset(char *tag, struct scsi_cmnd *scmnd, u8 flag,
+			    struct zfcp_fsf_req *fsf_req)
 {
 	char tmp_tag[ZFCP_DBF_TAG_LEN];
 
@@ -411,7 +418,7 @@ void zfcp_dbf_scsi_devreset(char *tag, struct scsi_cmnd *scmnd, u8 flag)
 		memcpy(tmp_tag, "lr_", 3);
 
 	memcpy(&tmp_tag[3], tag, 4);
-	_zfcp_dbf_scsi(tmp_tag, 1, scmnd, NULL);
+	_zfcp_dbf_scsi(tmp_tag, 1, scmnd, fsf_req);
 }
 
 /**
diff --git a/drivers/s390/scsi/zfcp_fc.h b/drivers/s390/scsi/zfcp_fc.h
index df2b541c8287..a2275825186f 100644
--- a/drivers/s390/scsi/zfcp_fc.h
+++ b/drivers/s390/scsi/zfcp_fc.h
@@ -4,7 +4,7 @@
  * Fibre Channel related definitions and inline functions for the zfcp
  * device driver
  *
- * Copyright IBM Corp. 2009
+ * Copyright IBM Corp. 2009, 2017
  */
 
 #ifndef ZFCP_FC_H
@@ -279,6 +279,10 @@ void zfcp_fc_eval_fcp_rsp(struct fcp_resp_with_ext *fcp_rsp,
 		     !(rsp_flags & FCP_SNS_LEN_VAL) &&
 		     fcp_rsp->resp.fr_status == SAM_STAT_GOOD)
 			set_host_byte(scsi, DID_ERROR);
+	} else if (unlikely(rsp_flags & FCP_RESID_OVER)) {
+		/* FCP_DL was not sufficient for SCSI data length */
+		if (fcp_rsp->resp.fr_status == SAM_STAT_GOOD)
+			set_host_byte(scsi, DID_ERROR);
 	}
 }
 
diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c
index 27ff38f839fc..1964391db904 100644
--- a/drivers/s390/scsi/zfcp_fsf.c
+++ b/drivers/s390/scsi/zfcp_fsf.c
@@ -928,8 +928,8 @@ static void zfcp_fsf_send_ct_handler(struct zfcp_fsf_req *req)
 
 	switch (header->fsf_status) {
         case FSF_GOOD:
-		zfcp_dbf_san_res("fsscth2", req);
 		ct->status = 0;
+		zfcp_dbf_san_res("fsscth2", req);
 		break;
         case FSF_SERVICE_CLASS_NOT_SUPPORTED:
 		zfcp_fsf_class_not_supp(req);
@@ -1109,8 +1109,8 @@ static void zfcp_fsf_send_els_handler(struct zfcp_fsf_req *req)
 
 	switch (header->fsf_status) {
 	case FSF_GOOD:
-		zfcp_dbf_san_res("fsselh1", req);
 		send_els->status = 0;
+		zfcp_dbf_san_res("fsselh1", req);
 		break;
 	case FSF_SERVICE_CLASS_NOT_SUPPORTED:
 		zfcp_fsf_class_not_supp(req);
@@ -2258,7 +2258,8 @@ int zfcp_fsf_fcp_cmnd(struct scsi_cmnd *scsi_cmnd)
 	fcp_cmnd = (struct fcp_cmnd *) &req->qtcb->bottom.io.fcp_cmnd;
 	zfcp_fc_scsi_to_fcp(fcp_cmnd, scsi_cmnd, 0);
 
-	if (scsi_prot_sg_count(scsi_cmnd)) {
+	if ((scsi_get_prot_op(scsi_cmnd) != SCSI_PROT_NORMAL) &&
+	    scsi_prot_sg_count(scsi_cmnd)) {
 		zfcp_qdio_set_data_div(qdio, &req->qdio_req,
 				       scsi_prot_sg_count(scsi_cmnd));
 		retval = zfcp_qdio_sbals_from_sg(qdio, &req->qdio_req,
diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c
index 07ffdbb5107f..9bd9b9a29dfc 100644
--- a/drivers/s390/scsi/zfcp_scsi.c
+++ b/drivers/s390/scsi/zfcp_scsi.c
@@ -3,7 +3,7 @@
  *
  * Interface to Linux SCSI midlayer.
  *
- * Copyright IBM Corp. 2002, 2016
+ * Copyright IBM Corp. 2002, 2017
  */
 
 #define KMSG_COMPONENT "zfcp"
@@ -273,25 +273,29 @@ static int zfcp_task_mgmt_function(struct scsi_cmnd *scpnt, u8 tm_flags)
 
 		zfcp_erp_wait(adapter);
 		ret = fc_block_scsi_eh(scpnt);
-		if (ret)
+		if (ret) {
+			zfcp_dbf_scsi_devreset("fiof", scpnt, tm_flags, NULL);
 			return ret;
+		}
 
 		if (!(atomic_read(&adapter->status) &
 		      ZFCP_STATUS_COMMON_RUNNING)) {
-			zfcp_dbf_scsi_devreset("nres", scpnt, tm_flags);
+			zfcp_dbf_scsi_devreset("nres", scpnt, tm_flags, NULL);
 			return SUCCESS;
 		}
 	}
-	if (!fsf_req)
+	if (!fsf_req) {
+		zfcp_dbf_scsi_devreset("reqf", scpnt, tm_flags, NULL);
 		return FAILED;
+	}
 
 	wait_for_completion(&fsf_req->completion);
 
 	if (fsf_req->status & ZFCP_STATUS_FSFREQ_TMFUNCFAILED) {
-		zfcp_dbf_scsi_devreset("fail", scpnt, tm_flags);
+		zfcp_dbf_scsi_devreset("fail", scpnt, tm_flags, fsf_req);
 		retval = FAILED;
 	} else {
-		zfcp_dbf_scsi_devreset("okay", scpnt, tm_flags);
+		zfcp_dbf_scsi_devreset("okay", scpnt, tm_flags, fsf_req);
 		zfcp_scsi_forget_cmnds(zfcp_sdev, tm_flags);
 	}
 
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index d8b1fbd4c8aa..35cbd36f8d3b 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -1901,9 +1901,12 @@ static void megasas_complete_outstanding_ioctls(struct megasas_instance *instanc
 			if (cmd_fusion->sync_cmd_idx != (u32)ULONG_MAX) {
 				cmd_mfi = instance->cmd_list[cmd_fusion->sync_cmd_idx];
 				if (cmd_mfi->sync_cmd &&
-					cmd_mfi->frame->hdr.cmd != MFI_CMD_ABORT)
+				    (cmd_mfi->frame->hdr.cmd != MFI_CMD_ABORT)) {
+					cmd_mfi->frame->hdr.cmd_status =
+							MFI_STAT_WRONG_STATE;
 					megasas_complete_cmd(instance,
 							     cmd_mfi, DID_OK);
+				}
 			}
 		}
 	} else {
@@ -5290,7 +5293,8 @@ static int megasas_init_fw(struct megasas_instance *instance)
 		instance->throttlequeuedepth =
 				MEGASAS_THROTTLE_QUEUE_DEPTH;
 
-	if (resetwaittime > MEGASAS_RESET_WAIT_TIME)
+	if ((resetwaittime < 1) ||
+	    (resetwaittime > MEGASAS_RESET_WAIT_TIME))
 		resetwaittime = MEGASAS_RESET_WAIT_TIME;
 
 	if ((scmd_timeout < 10) || (scmd_timeout > MEGASAS_DEFAULT_CMD_TIMEOUT))
@@ -5459,6 +5463,14 @@ megasas_register_aen(struct megasas_instance *instance, u32 seq_num,
 		prev_aen.word =
 			le32_to_cpu(instance->aen_cmd->frame->dcmd.mbox.w[1]);
 
+		if ((curr_aen.members.class < MFI_EVT_CLASS_DEBUG) ||
+		    (curr_aen.members.class > MFI_EVT_CLASS_DEAD)) {
+			dev_info(&instance->pdev->dev,
+				 "%s %d out of range class %d send by application\n",
+				 __func__, __LINE__, curr_aen.members.class);
+			return 0;
+		}
+
 		/*
 		 * A class whose enum value is smaller is inclusive of all
 		 * higher values. If a PROGRESS (= -1) was previously
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 8c4641b518b5..9a34afcb1c4c 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -318,6 +318,8 @@ qla2x00_sysfs_write_optrom_ctl(struct file *filp, struct kobject *kobj,
 		return -EINVAL;
 	if (start > ha->optrom_size)
 		return -EINVAL;
+	if (size > ha->optrom_size - start)
+		size = ha->optrom_size - start;
 
 	mutex_lock(&ha->optrom_mutex);
 	switch (val) {
@@ -343,8 +345,7 @@ qla2x00_sysfs_write_optrom_ctl(struct file *filp, struct kobject *kobj,
 		}
 
 		ha->optrom_region_start = start;
-		ha->optrom_region_size = start + size > ha->optrom_size ?
-		    ha->optrom_size - start : size;
+		ha->optrom_region_size = start + size;
 
 		ha->optrom_state = QLA_SREADING;
 		ha->optrom_buffer = vmalloc(ha->optrom_region_size);
@@ -417,8 +418,7 @@ qla2x00_sysfs_write_optrom_ctl(struct file *filp, struct kobject *kobj,
 		}
 
 		ha->optrom_region_start = start;
-		ha->optrom_region_size = start + size > ha->optrom_size ?
-		    ha->optrom_size - start : size;
+		ha->optrom_region_size = start + size;
 
 		ha->optrom_state = QLA_SWRITING;
 		ha->optrom_buffer = vmalloc(ha->optrom_region_size);
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index 3dfb54abc874..f8ae70476b3a 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -74,7 +74,7 @@ qla24xx_deallocate_vp_id(scsi_qla_host_t *vha)
 	 * ensures no active vp_list traversal while the vport is removed
 	 * from the queue)
 	 */
-	wait_event_timeout(vha->vref_waitq, atomic_read(&vha->vref_count),
+	wait_event_timeout(vha->vref_waitq, !atomic_read(&vha->vref_count),
 	    10*HZ);
 
 	spin_lock_irqsave(&ha->vport_slock, flags);
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 9236a13d5d2a..02dfbc1373e3 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -122,7 +122,7 @@ struct sg_device;		/* forward declarations */
 struct sg_fd;
 
 typedef struct sg_request {	/* SG_MAX_QUEUE requests outstanding per file */
-	struct sg_request *nextrp;	/* NULL -> tail request (slist) */
+	struct list_head entry;	/* list entry */
 	struct sg_fd *parentfp;	/* NULL -> not in use */
 	Sg_scatter_hold data;	/* hold buffer, perhaps scatter list */
 	sg_io_hdr_t header;	/* scsi command+info, see <scsi/sg.h> */
@@ -146,8 +146,7 @@ typedef struct sg_fd {		/* holds the state of a file descriptor */
 	int timeout;		/* defaults to SG_DEFAULT_TIMEOUT      */
 	int timeout_user;	/* defaults to SG_DEFAULT_TIMEOUT_USER */
 	Sg_scatter_hold reserve;	/* buffer held for this file descriptor */
-	unsigned save_scat_len;	/* original length of trunc. scat. element */
-	Sg_request *headrp;	/* head of request slist, NULL->empty */
+	struct list_head rq_list; /* head of request list */
 	struct fasync_struct *async_qp;	/* used by asynchronous notification */
 	Sg_request req_arr[SG_MAX_QUEUE];	/* used as singly-linked list */
 	char low_dma;		/* as in parent but possibly overridden to 1 */
@@ -829,6 +828,39 @@ static int max_sectors_bytes(struct request_queue *q)
 	return max_sectors << 9;
 }
 
+static void
+sg_fill_request_table(Sg_fd *sfp, sg_req_info_t *rinfo)
+{
+	Sg_request *srp;
+	int val;
+	unsigned int ms;
+
+	val = 0;
+	list_for_each_entry(srp, &sfp->rq_list, entry) {
+		if (val > SG_MAX_QUEUE)
+			break;
+		rinfo[val].req_state = srp->done + 1;
+		rinfo[val].problem =
+			srp->header.masked_status &
+			srp->header.host_status &
+			srp->header.driver_status;
+		if (srp->done)
+			rinfo[val].duration =
+				srp->header.duration;
+		else {
+			ms = jiffies_to_msecs(jiffies);
+			rinfo[val].duration =
+				(ms > srp->header.duration) ?
+				(ms - srp->header.duration) : 0;
+		}
+		rinfo[val].orphan = srp->orphan;
+		rinfo[val].sg_io_owned = srp->sg_io_owned;
+		rinfo[val].pack_id = srp->header.pack_id;
+		rinfo[val].usr_ptr = srp->header.usr_ptr;
+		val++;
+	}
+}
+
 static long
 sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 {
@@ -941,7 +973,7 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 		if (!access_ok(VERIFY_WRITE, ip, sizeof (int)))
 			return -EFAULT;
 		read_lock_irqsave(&sfp->rq_list_lock, iflags);
-		for (srp = sfp->headrp; srp; srp = srp->nextrp) {
+		list_for_each_entry(srp, &sfp->rq_list, entry) {
 			if ((1 == srp->done) && (!srp->sg_io_owned)) {
 				read_unlock_irqrestore(&sfp->rq_list_lock,
 						       iflags);
@@ -954,7 +986,8 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 		return 0;
 	case SG_GET_NUM_WAITING:
 		read_lock_irqsave(&sfp->rq_list_lock, iflags);
-		for (val = 0, srp = sfp->headrp; srp; srp = srp->nextrp) {
+		val = 0;
+		list_for_each_entry(srp, &sfp->rq_list, entry) {
 			if ((1 == srp->done) && (!srp->sg_io_owned))
 				++val;
 		}
@@ -1022,42 +1055,15 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 			return -EFAULT;
 		else {
 			sg_req_info_t *rinfo;
-			unsigned int ms;
 
-			rinfo = kmalloc(SZ_SG_REQ_INFO * SG_MAX_QUEUE,
-								GFP_KERNEL);
+			rinfo = kzalloc(SZ_SG_REQ_INFO * SG_MAX_QUEUE,
+					GFP_KERNEL);
 			if (!rinfo)
 				return -ENOMEM;
 			read_lock_irqsave(&sfp->rq_list_lock, iflags);
-			for (srp = sfp->headrp, val = 0; val < SG_MAX_QUEUE;
-			     ++val, srp = srp ? srp->nextrp : srp) {
-				memset(&rinfo[val], 0, SZ_SG_REQ_INFO);
-				if (srp) {
-					rinfo[val].req_state = srp->done + 1;
-					rinfo[val].problem =
-					    srp->header.masked_status & 
-					    srp->header.host_status & 
-					    srp->header.driver_status;
-					if (srp->done)
-						rinfo[val].duration =
-							srp->header.duration;
-					else {
-						ms = jiffies_to_msecs(jiffies);
-						rinfo[val].duration =
-						    (ms > srp->header.duration) ?
-						    (ms - srp->header.duration) : 0;
-					}
-					rinfo[val].orphan = srp->orphan;
-					rinfo[val].sg_io_owned =
-							srp->sg_io_owned;
-					rinfo[val].pack_id =
-							srp->header.pack_id;
-					rinfo[val].usr_ptr =
-							srp->header.usr_ptr;
-				}
-			}
+			sg_fill_request_table(sfp, rinfo);
 			read_unlock_irqrestore(&sfp->rq_list_lock, iflags);
-			result = __copy_to_user(p, rinfo, 
+			result = __copy_to_user(p, rinfo,
 						SZ_SG_REQ_INFO * SG_MAX_QUEUE);
 			result = result ? -EFAULT : 0;
 			kfree(rinfo);
@@ -1163,7 +1169,7 @@ sg_poll(struct file *filp, poll_table * wait)
 		return POLLERR;
 	poll_wait(filp, &sfp->read_wait, wait);
 	read_lock_irqsave(&sfp->rq_list_lock, iflags);
-	for (srp = sfp->headrp; srp; srp = srp->nextrp) {
+	list_for_each_entry(srp, &sfp->rq_list, entry) {
 		/* if any read waiting, flag it */
 		if ((0 == res) && (1 == srp->done) && (!srp->sg_io_owned))
 			res = POLLIN | POLLRDNORM;
@@ -2049,7 +2055,6 @@ sg_unlink_reserve(Sg_fd * sfp, Sg_request * srp)
 	req_schp->pages = NULL;
 	req_schp->page_order = 0;
 	req_schp->sglist_len = 0;
-	sfp->save_scat_len = 0;
 	srp->res_used = 0;
 	/* Called without mutex lock to avoid deadlock */
 	sfp->res_in_use = 0;
@@ -2062,7 +2067,7 @@ sg_get_rq_mark(Sg_fd * sfp, int pack_id)
 	unsigned long iflags;
 
 	write_lock_irqsave(&sfp->rq_list_lock, iflags);
-	for (resp = sfp->headrp; resp; resp = resp->nextrp) {
+	list_for_each_entry(resp, &sfp->rq_list, entry) {
 		/* look for requests that are ready + not SG_IO owned */
 		if ((1 == resp->done) && (!resp->sg_io_owned) &&
 		    ((-1 == pack_id) || (resp->header.pack_id == pack_id))) {
@@ -2080,70 +2085,45 @@ sg_add_request(Sg_fd * sfp)
 {
 	int k;
 	unsigned long iflags;
-	Sg_request *resp;
 	Sg_request *rp = sfp->req_arr;
 
 	write_lock_irqsave(&sfp->rq_list_lock, iflags);
-	resp = sfp->headrp;
-	if (!resp) {
-		memset(rp, 0, sizeof (Sg_request));
-		rp->parentfp = sfp;
-		resp = rp;
-		sfp->headrp = resp;
-	} else {
-		if (0 == sfp->cmd_q)
-			resp = NULL;	/* command queuing disallowed */
-		else {
-			for (k = 0; k < SG_MAX_QUEUE; ++k, ++rp) {
-				if (!rp->parentfp)
-					break;
-			}
-			if (k < SG_MAX_QUEUE) {
-				memset(rp, 0, sizeof (Sg_request));
-				rp->parentfp = sfp;
-				while (resp->nextrp)
-					resp = resp->nextrp;
-				resp->nextrp = rp;
-				resp = rp;
-			} else
-				resp = NULL;
+	if (!list_empty(&sfp->rq_list)) {
+		if (!sfp->cmd_q)
+			goto out_unlock;
+
+		for (k = 0; k < SG_MAX_QUEUE; ++k, ++rp) {
+			if (!rp->parentfp)
+				break;
 		}
+		if (k >= SG_MAX_QUEUE)
+			goto out_unlock;
 	}
-	if (resp) {
-		resp->nextrp = NULL;
-		resp->header.duration = jiffies_to_msecs(jiffies);
-	}
+	memset(rp, 0, sizeof (Sg_request));
+	rp->parentfp = sfp;
+	rp->header.duration = jiffies_to_msecs(jiffies);
+	list_add_tail(&rp->entry, &sfp->rq_list);
 	write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
-	return resp;
+	return rp;
+out_unlock:
+	write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
+	return NULL;
 }
 
 /* Return of 1 for found; 0 for not found */
 static int
 sg_remove_request(Sg_fd * sfp, Sg_request * srp)
 {
-	Sg_request *prev_rp;
-	Sg_request *rp;
 	unsigned long iflags;
 	int res = 0;
 
-	if ((!sfp) || (!srp) || (!sfp->headrp))
+	if (!sfp || !srp || list_empty(&sfp->rq_list))
 		return res;
 	write_lock_irqsave(&sfp->rq_list_lock, iflags);
-	prev_rp = sfp->headrp;
-	if (srp == prev_rp) {
-		sfp->headrp = prev_rp->nextrp;
-		prev_rp->parentfp = NULL;
+	if (!list_empty(&srp->entry)) {
+		list_del(&srp->entry);
+		srp->parentfp = NULL;
 		res = 1;
-	} else {
-		while ((rp = prev_rp->nextrp)) {
-			if (srp == rp) {
-				prev_rp->nextrp = rp->nextrp;
-				rp->parentfp = NULL;
-				res = 1;
-				break;
-			}
-			prev_rp = rp;
-		}
 	}
 	write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
 	return res;
@@ -2162,7 +2142,7 @@ sg_add_sfp(Sg_device * sdp)
 
 	init_waitqueue_head(&sfp->read_wait);
 	rwlock_init(&sfp->rq_list_lock);
-
+	INIT_LIST_HEAD(&sfp->rq_list);
 	kref_init(&sfp->f_ref);
 	mutex_init(&sfp->f_mutex);
 	sfp->timeout = SG_DEFAULT_TIMEOUT;
@@ -2203,10 +2183,13 @@ sg_remove_sfp_usercontext(struct work_struct *work)
 {
 	struct sg_fd *sfp = container_of(work, struct sg_fd, ew.work);
 	struct sg_device *sdp = sfp->parentdp;
+	Sg_request *srp;
 
 	/* Cleanup any responses which were never read(). */
-	while (sfp->headrp)
-		sg_finish_rem_req(sfp->headrp);
+	while (!list_empty(&sfp->rq_list)) {
+		srp = list_first_entry(&sfp->rq_list, Sg_request, entry);
+		sg_finish_rem_req(srp);
+	}
 
 	if (sfp->reserve.bufflen > 0) {
 		SCSI_LOG_TIMEOUT(6, sg_printk(KERN_INFO, sdp,
@@ -2609,7 +2592,7 @@ static int sg_proc_seq_show_devstrs(struct seq_file *s, void *v)
 /* must be called while holding sg_index_lock */
 static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp)
 {
-	int k, m, new_interface, blen, usg;
+	int k, new_interface, blen, usg;
 	Sg_request *srp;
 	Sg_fd *fp;
 	const sg_io_hdr_t *hp;
@@ -2629,13 +2612,11 @@ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp)
 		seq_printf(s, "   cmd_q=%d f_packid=%d k_orphan=%d closed=0\n",
 			   (int) fp->cmd_q, (int) fp->force_packid,
 			   (int) fp->keep_orphan);
-		for (m = 0, srp = fp->headrp;
-				srp != NULL;
-				++m, srp = srp->nextrp) {
+		list_for_each_entry(srp, &fp->rq_list, entry) {
 			hp = &srp->header;
 			new_interface = (hp->interface_id == '\0') ? 0 : 1;
 			if (srp->res_used) {
-				if (new_interface && 
+				if (new_interface &&
 				    (SG_FLAG_MMAP_IO & hp->flags))
 					cp = "     mmap>> ";
 				else
@@ -2666,7 +2647,7 @@ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp)
 			seq_printf(s, "ms sgat=%d op=0x%02x\n", usg,
 				   (int) srp->data.cmd_opcode);
 		}
-		if (0 == m)
+		if (list_empty(&fp->rq_list))
 			seq_puts(s, "     No requests active\n");
 		read_unlock(&fp->rq_list_lock);
 	}
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index c5ab1b0037fc..2bf96d33428a 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1559,6 +1559,8 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 	ret = storvsc_do_io(dev, cmd_request);
 
 	if (ret == -EAGAIN) {
+		if (payload_sz > sizeof(cmd_request->mpb))
+			kfree(payload);
 		/* no more space */
 		return SCSI_MLQUEUE_DEVICE_BUSY;
 	}
diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c
index aa80dc94ddc2..c220c2c0893f 100644
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -361,6 +361,32 @@ int tty_insert_flip_string_flags(struct tty_port *port,
 }
 EXPORT_SYMBOL(tty_insert_flip_string_flags);
 
+/**
+ *	__tty_insert_flip_char   -	Add one character to the tty buffer
+ *	@port: tty port
+ *	@ch: character
+ *	@flag: flag byte
+ *
+ *	Queue a single byte to the tty buffering, with an optional flag.
+ *	This is the slow path of tty_insert_flip_char.
+ */
+int __tty_insert_flip_char(struct tty_port *port, unsigned char ch, char flag)
+{
+	struct tty_buffer *tb;
+	int flags = (flag == TTY_NORMAL) ? TTYB_NORMAL : 0;
+
+	if (!__tty_buffer_request_room(port, 1, flags))
+		return 0;
+
+	tb = port->buf.tail;
+	if (~tb->flags & TTYB_NORMAL)
+		*flag_buf_ptr(tb, tb->used) = flag;
+	*char_buf_ptr(tb, tb->used++) = ch;
+
+	return 1;
+}
+EXPORT_SYMBOL(__tty_insert_flip_char);
+
 /**
  *	tty_schedule_flip	-	push characters to ldisc
  *	@port: tty port to push from
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 5fa9ba1de429..f72535e1898f 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2334,6 +2334,7 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 	unsigned int s_flags = sb->s_flags;
 	int nr_orphans = 0, nr_truncates = 0;
 #ifdef CONFIG_QUOTA
+	int quota_update = 0;
 	int i;
 #endif
 	if (!es->s_last_orphan) {
@@ -2372,14 +2373,32 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 #ifdef CONFIG_QUOTA
 	/* Needed for iput() to work correctly and not trash data */
 	sb->s_flags |= MS_ACTIVE;
-	/* Turn on quotas so that they are updated correctly */
+
+	/*
+	 * Turn on quotas which were not enabled for read-only mounts if
+	 * filesystem has quota feature, so that they are updated correctly.
+	 */
+	if (ext4_has_feature_quota(sb) && (s_flags & MS_RDONLY)) {
+		int ret = ext4_enable_quotas(sb);
+
+		if (!ret)
+			quota_update = 1;
+		else
+			ext4_msg(sb, KERN_ERR,
+				"Cannot turn on quotas: error %d", ret);
+	}
+
+	/* Turn on journaled quotas used for old sytle */
 	for (i = 0; i < EXT4_MAXQUOTAS; i++) {
 		if (EXT4_SB(sb)->s_qf_names[i]) {
 			int ret = ext4_quota_on_mount(sb, i);
-			if (ret < 0)
+
+			if (!ret)
+				quota_update = 1;
+			else
 				ext4_msg(sb, KERN_ERR,
 					"Cannot turn on journaled "
-					"quota: error %d", ret);
+					"quota: type %d: error %d", i, ret);
 		}
 	}
 #endif
@@ -2438,10 +2457,12 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 		ext4_msg(sb, KERN_INFO, "%d truncate%s cleaned up",
 		       PLURAL(nr_truncates));
 #ifdef CONFIG_QUOTA
-	/* Turn quotas off */
-	for (i = 0; i < EXT4_MAXQUOTAS; i++) {
-		if (sb_dqopt(sb)->files[i])
-			dquot_quota_off(sb, i);
+	/* Turn off quotas if they were enabled for orphan cleanup */
+	if (quota_update) {
+		for (i = 0; i < EXT4_MAXQUOTAS; i++) {
+			if (sb_dqopt(sb)->files[i])
+				dquot_quota_off(sb, i);
+		}
 	}
 #endif
 	sb->s_flags = s_flags; /* Restore MS_RDONLY status */
@@ -5365,6 +5386,9 @@ static int ext4_enable_quotas(struct super_block *sb)
 				DQUOT_USAGE_ENABLED |
 				(quota_mopt[type] ? DQUOT_LIMITS_ENABLED : 0));
 			if (err) {
+				for (type--; type >= 0; type--)
+					dquot_quota_off(sb, type);
+
 				ext4_warning(sb,
 					"Failed to enable quota tracking "
 					"(type=%d, err=%d). Please run "
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 0a2115084c3f..582bfee40345 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -75,7 +75,10 @@ nfs4_callback_svc(void *vrqstp)
 
 	set_freezable();
 
-	while (!kthread_should_stop()) {
+	while (!kthread_freezable_should_stop(NULL)) {
+
+		if (signal_pending(current))
+			flush_signals(current);
 		/*
 		 * Listen for a request on the socket
 		 */
@@ -84,6 +87,8 @@ nfs4_callback_svc(void *vrqstp)
 			continue;
 		svc_process(rqstp);
 	}
+	svc_exit_thread(rqstp);
+	module_put_and_exit(0);
 	return 0;
 }
 
@@ -102,9 +107,10 @@ nfs41_callback_svc(void *vrqstp)
 
 	set_freezable();
 
-	while (!kthread_should_stop()) {
-		if (try_to_freeze())
-			continue;
+	while (!kthread_freezable_should_stop(NULL)) {
+
+		if (signal_pending(current))
+			flush_signals(current);
 
 		prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE);
 		spin_lock_bh(&serv->sv_cb_lock);
@@ -120,11 +126,13 @@ nfs41_callback_svc(void *vrqstp)
 				error);
 		} else {
 			spin_unlock_bh(&serv->sv_cb_lock);
-			schedule();
+			if (!kthread_should_stop())
+				schedule();
 			finish_wait(&serv->sv_cb_waitq, &wq);
 		}
-		flush_signals(current);
 	}
+	svc_exit_thread(rqstp);
+	module_put_and_exit(0);
 	return 0;
 }
 
@@ -220,14 +228,14 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv,
 static struct svc_serv_ops nfs40_cb_sv_ops = {
 	.svo_function		= nfs4_callback_svc,
 	.svo_enqueue_xprt	= svc_xprt_do_enqueue,
-	.svo_setup		= svc_set_num_threads,
+	.svo_setup		= svc_set_num_threads_sync,
 	.svo_module		= THIS_MODULE,
 };
 #if defined(CONFIG_NFS_V4_1)
 static struct svc_serv_ops nfs41_cb_sv_ops = {
 	.svo_function		= nfs41_callback_svc,
 	.svo_enqueue_xprt	= svc_xprt_do_enqueue,
-	.svo_setup		= svc_set_num_threads,
+	.svo_setup		= svc_set_num_threads_sync,
 	.svo_module		= THIS_MODULE,
 };
 
diff --git a/fs/orangefs/acl.c b/fs/orangefs/acl.c
index 7a3754488312..9409aac232f7 100644
--- a/fs/orangefs/acl.c
+++ b/fs/orangefs/acl.c
@@ -61,9 +61,9 @@ struct posix_acl *orangefs_get_acl(struct inode *inode, int type)
 	return acl;
 }
 
-int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+static int __orangefs_set_acl(struct inode *inode, struct posix_acl *acl,
+			      int type)
 {
-	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
 	int error = 0;
 	void *value = NULL;
 	size_t size = 0;
@@ -72,22 +72,6 @@ int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name = XATTR_NAME_POSIX_ACL_ACCESS;
-		if (acl) {
-			umode_t mode;
-
-			error = posix_acl_update_mode(inode, &mode, &acl);
-			if (error) {
-				gossip_err("%s: posix_acl_update_mode err: %d\n",
-					   __func__,
-					   error);
-				return error;
-			}
-
-			if (inode->i_mode != mode)
-				SetModeFlag(orangefs_inode);
-			inode->i_mode = mode;
-			mark_inode_dirty_sync(inode);
-		}
 		break;
 	case ACL_TYPE_DEFAULT:
 		name = XATTR_NAME_POSIX_ACL_DEFAULT;
@@ -132,6 +116,29 @@ int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	return error;
 }
 
+int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+{
+	int error;
+
+	if (type == ACL_TYPE_ACCESS && acl) {
+		umode_t mode;
+
+		error = posix_acl_update_mode(inode, &mode, &acl);
+		if (error) {
+			gossip_err("%s: posix_acl_update_mode err: %d\n",
+				   __func__,
+				   error);
+			return error;
+		}
+
+		if (inode->i_mode != mode)
+			SetModeFlag(ORANGEFS_I(inode));
+		inode->i_mode = mode;
+		mark_inode_dirty_sync(inode);
+	}
+	return __orangefs_set_acl(inode, acl, type);
+}
+
 int orangefs_init_acl(struct inode *inode, struct inode *dir)
 {
 	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
@@ -146,13 +153,14 @@ int orangefs_init_acl(struct inode *inode, struct inode *dir)
 		return error;
 
 	if (default_acl) {
-		error = orangefs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
+		error = __orangefs_set_acl(inode, default_acl,
+					   ACL_TYPE_DEFAULT);
 		posix_acl_release(default_acl);
 	}
 
 	if (acl) {
 		if (!error)
-			error = orangefs_set_acl(inode, acl, ACL_TYPE_ACCESS);
+			error = __orangefs_set_acl(inode, acl, ACL_TYPE_ACCESS);
 		posix_acl_release(acl);
 	}
 
diff --git a/include/linux/ccp.h b/include/linux/ccp.h
index edc5d04b9632..1cfe5ef3060b 100644
--- a/include/linux/ccp.h
+++ b/include/linux/ccp.h
@@ -1,7 +1,7 @@
 /*
  * AMD Cryptographic Coprocessor (CCP) driver
  *
- * Copyright (C) 2013,2016 Advanced Micro Devices, Inc.
+ * Copyright (C) 2013,2017 Advanced Micro Devices, Inc.
  *
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  * Author: Gary R Hook <gary.hook@amd.com>
@@ -222,6 +222,7 @@ enum ccp_xts_aes_unit_size {
  * AES operation the new IV overwrites the old IV.
  */
 struct ccp_xts_aes_engine {
+	enum ccp_aes_type type;
 	enum ccp_aes_action action;
 	enum ccp_xts_aes_unit_size unit_size;
 
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 7321ae933867..102c84dcc11a 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -470,6 +470,7 @@ void		   svc_pool_map_put(void);
 struct svc_serv *  svc_create_pooled(struct svc_program *, unsigned int,
 			struct svc_serv_ops *);
 int		   svc_set_num_threads(struct svc_serv *, struct svc_pool *, int);
+int		   svc_set_num_threads_sync(struct svc_serv *, struct svc_pool *, int);
 int		   svc_pool_stats_open(struct svc_serv *serv, struct file *file);
 void		   svc_destroy(struct svc_serv *);
 void		   svc_shutdown_net(struct svc_serv *, struct net *);
diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h
index c28dd523f96e..d43837f2ce3a 100644
--- a/include/linux/tty_flip.h
+++ b/include/linux/tty_flip.h
@@ -12,6 +12,7 @@ extern int tty_prepare_flip_string(struct tty_port *port,
 		unsigned char **chars, size_t size);
 extern void tty_flip_buffer_push(struct tty_port *port);
 void tty_schedule_flip(struct tty_port *port);
+int __tty_insert_flip_char(struct tty_port *port, unsigned char ch, char flag);
 
 static inline int tty_insert_flip_char(struct tty_port *port,
 					unsigned char ch, char flag)
@@ -26,7 +27,7 @@ static inline int tty_insert_flip_char(struct tty_port *port,
 		*char_buf_ptr(tb, tb->used++) = ch;
 		return 1;
 	}
-	return tty_insert_flip_string_flags(port, &ch, &flag, 1);
+	return __tty_insert_flip_char(port, ch, flag);
 }
 
 static inline int tty_insert_flip_string(struct tty_port *port,
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 6e432ed7d0fe..53ed8ae5de1c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2747,13 +2747,14 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 
 	if (!command || !ftrace_enabled) {
 		/*
-		 * If these are per_cpu ops, they still need their
-		 * per_cpu field freed. Since, function tracing is
+		 * If these are dynamic or per_cpu ops, they still
+		 * need their data freed. Since, function tracing is
 		 * not currently active, we can just free them
 		 * without synchronizing all CPUs.
 		 */
-		if (ops->flags & FTRACE_OPS_FL_PER_CPU)
-			per_cpu_ops_free(ops);
+		if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_PER_CPU))
+			goto free_ops;
+
 		return 0;
 	}
 
@@ -2808,6 +2809,7 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 	if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_PER_CPU)) {
 		schedule_on_each_cpu(ftrace_sync);
 
+ free_ops:
 		arch_ftrace_trampoline_free(ops);
 
 		if (ops->flags & FTRACE_OPS_FL_PER_CPU)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 7379f735a9f4..f95bf81529f5 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2369,11 +2369,17 @@ static char *get_trace_buf(void)
 	if (!buffer || buffer->nesting >= 4)
 		return NULL;
 
-	return &buffer->buffer[buffer->nesting++][0];
+	buffer->nesting++;
+
+	/* Interrupts must see nesting incremented before we use the buffer */
+	barrier();
+	return &buffer->buffer[buffer->nesting][0];
 }
 
 static void put_trace_buf(void)
 {
+	/* Don't let the decrement of nesting leak before this */
+	barrier();
 	this_cpu_dec(trace_percpu_buffer->nesting);
 }
 
@@ -5658,7 +5664,7 @@ static int tracing_set_clock(struct trace_array *tr, const char *clockstr)
 	tracing_reset_online_cpus(&tr->trace_buffer);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-	if (tr->flags & TRACE_ARRAY_FL_GLOBAL && tr->max_buffer.buffer)
+	if (tr->max_buffer.buffer)
 		ring_buffer_set_clock(tr->max_buffer.buffer, trace_clocks[i].func);
 	tracing_reset_online_cpus(&tr->max_buffer);
 #endif
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index b0f86ea77881..ca70d11b8aa7 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -272,7 +272,7 @@ static int trace_selftest_ops(struct trace_array *tr, int cnt)
 		goto out_free;
 	if (cnt > 1) {
 		if (trace_selftest_test_global_cnt == 0)
-			goto out;
+			goto out_free;
 	}
 	if (trace_selftest_test_dyn_cnt == 0)
 		goto out_free;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2abf8d5f0ad4..7064aae8ded7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2100,13 +2100,25 @@ static void unreserve_highatomic_pageblock(const struct alloc_context *ac)
 				continue;
 
 			/*
-			 * It should never happen but changes to locking could
-			 * inadvertently allow a per-cpu drain to add pages
-			 * to MIGRATE_HIGHATOMIC while unreserving so be safe
-			 * and watch for underflows.
+			 * In page freeing path, migratetype change is racy so
+			 * we can counter several free pages in a pageblock
+			 * in this loop althoug we changed the pageblock type
+			 * from highatomic to ac->migratetype. So we should
+			 * adjust the count once.
 			 */
-			zone->nr_reserved_highatomic -= min(pageblock_nr_pages,
-				zone->nr_reserved_highatomic);
+			if (get_pageblock_migratetype(page) ==
+							MIGRATE_HIGHATOMIC) {
+				/*
+				 * It should never happen but changes to
+				 * locking could inadvertently allow a per-cpu
+				 * drain to add pages to MIGRATE_HIGHATOMIC
+				 * while unreserving so be safe and watch for
+				 * underflows.
+				 */
+				zone->nr_reserved_highatomic -= min(
+						pageblock_nr_pages,
+						zone->nr_reserved_highatomic);
+			}
 
 			/*
 			 * Convert to ac->migratetype and avoid the normal
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 6bd150882ba4..ed9ce7c63252 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -95,19 +95,26 @@ static struct conntrack_gc_work conntrack_gc_work;
 
 void nf_conntrack_lock(spinlock_t *lock) __acquires(lock)
 {
+	/* 1) Acquire the lock */
 	spin_lock(lock);
-	while (unlikely(nf_conntrack_locks_all)) {
-		spin_unlock(lock);
 
-		/*
-		 * Order the 'nf_conntrack_locks_all' load vs. the
-		 * spin_unlock_wait() loads below, to ensure
-		 * that 'nf_conntrack_locks_all_lock' is indeed held:
-		 */
-		smp_rmb(); /* spin_lock(&nf_conntrack_locks_all_lock) */
-		spin_unlock_wait(&nf_conntrack_locks_all_lock);
-		spin_lock(lock);
-	}
+	/* 2) read nf_conntrack_locks_all, with ACQUIRE semantics
+	 * It pairs with the smp_store_release() in nf_conntrack_all_unlock()
+	 */
+	if (likely(smp_load_acquire(&nf_conntrack_locks_all) == false))
+		return;
+
+	/* fast path failed, unlock */
+	spin_unlock(lock);
+
+	/* Slow path 1) get global lock */
+	spin_lock(&nf_conntrack_locks_all_lock);
+
+	/* Slow path 2) get the lock we want */
+	spin_lock(lock);
+
+	/* Slow path 3) release the global lock */
+	spin_unlock(&nf_conntrack_locks_all_lock);
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_lock);
 
@@ -148,28 +155,27 @@ static void nf_conntrack_all_lock(void)
 	int i;
 
 	spin_lock(&nf_conntrack_locks_all_lock);
-	nf_conntrack_locks_all = true;
 
-	/*
-	 * Order the above store of 'nf_conntrack_locks_all' against
-	 * the spin_unlock_wait() loads below, such that if
-	 * nf_conntrack_lock() observes 'nf_conntrack_locks_all'
-	 * we must observe nf_conntrack_locks[] held:
-	 */
-	smp_mb(); /* spin_lock(&nf_conntrack_locks_all_lock) */
+	nf_conntrack_locks_all = true;
 
 	for (i = 0; i < CONNTRACK_LOCKS; i++) {
-		spin_unlock_wait(&nf_conntrack_locks[i]);
+		spin_lock(&nf_conntrack_locks[i]);
+
+		/* This spin_unlock provides the "release" to ensure that
+		 * nf_conntrack_locks_all==true is visible to everyone that
+		 * acquired spin_lock(&nf_conntrack_locks[]).
+		 */
+		spin_unlock(&nf_conntrack_locks[i]);
 	}
 }
 
 static void nf_conntrack_all_unlock(void)
 {
-	/*
-	 * All prior stores must be complete before we clear
+	/* All prior stores must be complete before we clear
 	 * 'nf_conntrack_locks_all'. Otherwise nf_conntrack_lock()
 	 * might observe the false value but not the entire
-	 * critical section:
+	 * critical section.
+	 * It pairs with the smp_load_acquire() in nf_conntrack_lock()
 	 */
 	smp_store_release(&nf_conntrack_locks_all, false);
 	spin_unlock(&nf_conntrack_locks_all_lock);
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 75f290bddca1..272c34551979 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -702,59 +702,32 @@ choose_victim(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state)
 	return task;
 }
 
-/*
- * Create or destroy enough new threads to make the number
- * of threads the given number.  If `pool' is non-NULL, applies
- * only to threads in that pool, otherwise round-robins between
- * all pools.  Caller must ensure that mutual exclusion between this and
- * server startup or shutdown.
- *
- * Destroying threads relies on the service threads filling in
- * rqstp->rq_task, which only the nfs ones do.  Assumes the serv
- * has been created using svc_create_pooled().
- *
- * Based on code that used to be in nfsd_svc() but tweaked
- * to be pool-aware.
- */
-int
-svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
+/* create new threads */
+static int
+svc_start_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
 {
 	struct svc_rqst	*rqstp;
 	struct task_struct *task;
 	struct svc_pool *chosen_pool;
-	int error = 0;
 	unsigned int state = serv->sv_nrthreads-1;
 	int node;
 
-	if (pool == NULL) {
-		/* The -1 assumes caller has done a svc_get() */
-		nrservs -= (serv->sv_nrthreads-1);
-	} else {
-		spin_lock_bh(&pool->sp_lock);
-		nrservs -= pool->sp_nrthreads;
-		spin_unlock_bh(&pool->sp_lock);
-	}
-
-	/* create new threads */
-	while (nrservs > 0) {
+	do {
 		nrservs--;
 		chosen_pool = choose_pool(serv, pool, &state);
 
 		node = svc_pool_map_get_node(chosen_pool->sp_id);
 		rqstp = svc_prepare_thread(serv, chosen_pool, node);
-		if (IS_ERR(rqstp)) {
-			error = PTR_ERR(rqstp);
-			break;
-		}
+		if (IS_ERR(rqstp))
+			return PTR_ERR(rqstp);
 
 		__module_get(serv->sv_ops->svo_module);
 		task = kthread_create_on_node(serv->sv_ops->svo_function, rqstp,
 					      node, "%s", serv->sv_name);
 		if (IS_ERR(task)) {
-			error = PTR_ERR(task);
 			module_put(serv->sv_ops->svo_module);
 			svc_exit_thread(rqstp);
-			break;
+			return PTR_ERR(task);
 		}
 
 		rqstp->rq_task = task;
@@ -763,18 +736,103 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
 
 		svc_sock_update_bufs(serv);
 		wake_up_process(task);
-	}
+	} while (nrservs > 0);
+
+	return 0;
+}
+
+
+/* destroy old threads */
+static int
+svc_signal_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
+{
+	struct task_struct *task;
+	unsigned int state = serv->sv_nrthreads-1;
+
 	/* destroy old threads */
-	while (nrservs < 0 &&
-	       (task = choose_victim(serv, pool, &state)) != NULL) {
+	do {
+		task = choose_victim(serv, pool, &state);
+		if (task == NULL)
+			break;
 		send_sig(SIGINT, task, 1);
 		nrservs++;
+	} while (nrservs < 0);
+
+	return 0;
+}
+
+/*
+ * Create or destroy enough new threads to make the number
+ * of threads the given number.  If `pool' is non-NULL, applies
+ * only to threads in that pool, otherwise round-robins between
+ * all pools.  Caller must ensure that mutual exclusion between this and
+ * server startup or shutdown.
+ *
+ * Destroying threads relies on the service threads filling in
+ * rqstp->rq_task, which only the nfs ones do.  Assumes the serv
+ * has been created using svc_create_pooled().
+ *
+ * Based on code that used to be in nfsd_svc() but tweaked
+ * to be pool-aware.
+ */
+int
+svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
+{
+	if (pool == NULL) {
+		/* The -1 assumes caller has done a svc_get() */
+		nrservs -= (serv->sv_nrthreads-1);
+	} else {
+		spin_lock_bh(&pool->sp_lock);
+		nrservs -= pool->sp_nrthreads;
+		spin_unlock_bh(&pool->sp_lock);
 	}
 
-	return error;
+	if (nrservs > 0)
+		return svc_start_kthreads(serv, pool, nrservs);
+	if (nrservs < 0)
+		return svc_signal_kthreads(serv, pool, nrservs);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(svc_set_num_threads);
 
+/* destroy old threads */
+static int
+svc_stop_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
+{
+	struct task_struct *task;
+	unsigned int state = serv->sv_nrthreads-1;
+
+	/* destroy old threads */
+	do {
+		task = choose_victim(serv, pool, &state);
+		if (task == NULL)
+			break;
+		kthread_stop(task);
+		nrservs++;
+	} while (nrservs < 0);
+	return 0;
+}
+
+int
+svc_set_num_threads_sync(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
+{
+	if (pool == NULL) {
+		/* The -1 assumes caller has done a svc_get() */
+		nrservs -= (serv->sv_nrthreads-1);
+	} else {
+		spin_lock_bh(&pool->sp_lock);
+		nrservs -= pool->sp_nrthreads;
+		spin_unlock_bh(&pool->sp_lock);
+	}
+
+	if (nrservs > 0)
+		return svc_start_kthreads(serv, pool, nrservs);
+	if (nrservs < 0)
+		return svc_stop_kthreads(serv, pool, nrservs);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(svc_set_num_threads_sync);
+
 /*
  * Called from a server thread as it's exiting. Caller must hold the "service
  * mutex" for the service.