Linux 4.13.4

commit 01a9c948a0 upstream.

The OTP in some SKUs have erroneously allowed 40MHz and 80MHz channels
in the 5.2GHz band.  The firmware has been modified to not allow this
in those SKUs, so the driver needs to do the same otherwise the
firmware will assert when we try to use it.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Documentation/ABI/testing/sysfs-bus-thunderbolt

@@ -45,6 +45,8 @@ Contact:	thunderbolt-software@lists.01.org
 Description:	When a devices supports Thunderbolt secure connect it will
 		have this attribute. Writing 32 byte hex string changes
 		authorization to use the secure connection method instead.
+		Writing an empty string clears the key and regular connection
+		method can be used again.
 
 What:		/sys/bus/thunderbolt/devices/.../device
 Date:		Sep 2017

Documentation/dev-tools/gdb-kernel-debugging.rst

@@ -31,11 +31,13 @@ Setup
   CONFIG_DEBUG_INFO_REDUCED off. If your architecture supports
   CONFIG_FRAME_POINTER, keep it enabled.
 
-- Install that kernel on the guest.
+- Install that kernel on the guest, turn off KASLR if necessary by adding
+  "nokaslr" to the kernel command line.
   Alternatively, QEMU allows to boot the kernel directly using -kernel,
   -append, -initrd command line switches. This is generally only useful if
   you do not depend on modules. See QEMU documentation for more details on
-  this mode.
+  this mode. In this case, you should build the kernel with
+  CONFIG_RANDOMIZE_BASE disabled if the architecture supports KASLR.
 
 - Enable the gdb stub of QEMU/KVM, either
 

Documentation/driver-api/firmware/request_firmware.rst

@@ -44,17 +44,6 @@ request_firmware_nowait
 .. kernel-doc:: drivers/base/firmware_class.c
    :functions: request_firmware_nowait
 
-Considerations for suspend and resume
-=====================================
-
-During suspend and resume only the built-in firmware and the firmware cache
-elements of the firmware API can be used. This is managed by fw_pm_notify().
-
-fw_pm_notify
-------------
-.. kernel-doc:: drivers/base/firmware_class.c
-   :functions: fw_pm_notify
-
 request firmware API expected driver use
 ========================================
 

Makefile

@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 13
-SUBLEVEL = 0
+SUBLEVEL = 4
 EXTRAVERSION =
 NAME = Fearless Coyote
 

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

arch/arc/mm/tlb.c

@@ -908,9 +908,6 @@ 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++) {
 

arch/arm/mm/fault.c

@@ -315,8 +315,11 @@ retry:
 	 * signal first. We do not need to release the mmap_sem because
 	 * it would already be released in __lock_page_or_retry in
 	 * mm/filemap.c. */
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+		if (!user_mode(regs))
+			goto no_context;
 		return 0;
+	}
 
 	/*
 	 * Major/minor page fault accounting is only done on the

arch/arm64/boot/dts/marvell/armada-37xx.dtsi

@@ -323,6 +323,7 @@
 				interrupt-controller;
 				reg = <0x1d00000 0x10000>, /* GICD */
 				      <0x1d40000 0x40000>; /* GICR */
+				interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>;
 			};
 		};
 

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;
 }

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;
 }

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 and ZERO cases are 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 */
@@ -195,81 +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));
 
-	if (zc == IEEE754_CLASS_ZERO)
-		return ieee754dp_format(rs, re, rm);
+	assert(hrm & (1 << 62));
 
-	/* And now the addition */
-	assert(zm & DP_HIDDEN_BIT);
+	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);
+	}
 
-	/*
-	 * Provide guard,round and stick bit space.
-	 */
-	zm <<= 3;
+	/* 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,
@@ -281,5 +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);
 }

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;

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))

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;
 }

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;
 }

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 and ZERO cases are 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 ieee754sp_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 ieee754sp_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 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_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)
+		SPDNORMZ;
+	/* 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 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 */
 	}
@@ -158,111 +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);
+	/* Multiple 24 bit xm and ym to give 48 bit results */
+	rm64 = (uint64_t)xm * ym;
 
-	/*
-	 * 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;
+	/* Shunt to top of word */
+	rm64 = rm64 << 16;
 
-	lrm = lxm * lym;	/* 16 * 16 => 32 */
-	hrm = hxm * hym;	/* 16 * 16 => 32 */
-
-	t = lxm * hym; /* 16 * 16 => 32 */
-	at = lrm + (t << 16);
-	hrm += at < lrm;
-	lrm = at;
-	hrm = hrm + (t >> 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));
 
-	if (zc == IEEE754_CLASS_ZERO)
+	assert(rm64 & (1 << 62));
+
+	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);
+	}
 
-	/* And now the addition */
-
-	assert(zm & SP_HIDDEN_BIT);
-
-	/*
-	 * 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);
 }
 
@@ -275,5 +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);
 }

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

arch/powerpc/platforms/powernv/npu-dma.c

@@ -545,6 +545,12 @@ static void mmio_invalidate(struct npu_context *npu_context, int va,
 	struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS];
 	unsigned long pid = npu_context->mm->context.id;
 
+	/*
+	 * Unfortunately the nest mmu does not support flushing specific
+	 * addresses so we have to flush the whole mm.
+	 */
+	flush_tlb_mm(npu_context->mm);
+
 	/*
 	 * Loop over all the NPUs this process is active on and launch
 	 * an invalidate.
@@ -576,12 +582,6 @@ static void mmio_invalidate(struct npu_context *npu_context, int va,
 		}
 	}
 
-	/*
-	 * Unfortunately the nest mmu does not support flushing specific
-	 * addresses so we have to flush the whole mm.
-	 */
-	flush_tlb_mm(npu_context->mm);
-
 	mmio_invalidate_wait(mmio_atsd_reg, flush);
 	if (flush)
 		/* Wait for the flush to complete */

arch/powerpc/platforms/pseries/hotplug-memory.c

@@ -817,6 +817,9 @@ static int dlpar_memory_add_by_count(u32 lmbs_to_add, struct property *prop)
 		return -EINVAL;
 
 	for (i = 0; i < num_lmbs && lmbs_to_add != lmbs_added; i++) {
+		if (lmbs[i].flags & DRCONF_MEM_ASSIGNED)
+			continue;
+
 		rc = dlpar_acquire_drc(lmbs[i].drc_index);
 		if (rc)
 			continue;
@@ -859,6 +862,7 @@ static int dlpar_memory_add_by_count(u32 lmbs_to_add, struct property *prop)
 				lmbs[i].base_addr, lmbs[i].drc_index);
 			lmbs[i].reserved = 0;
 		}
+		rc = 0;
 	}
 
 	return rc;

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;
@@ -27,6 +28,7 @@ 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), \

arch/s390/include/asm/mmu_context.h

@@ -16,6 +16,7 @@
 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);
@@ -102,7 +103,6 @@ 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);
@@ -120,9 +120,8 @@ 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);
@@ -135,6 +134,7 @@ 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);
 }
 

arch/s390/include/asm/pgtable.h

@@ -505,7 +505,7 @@ static inline int mm_alloc_pgste(struct mm_struct *mm)
  * In the case that a guest uses storage keys
  * faults should no longer be backed by zero pages
  */
-#define mm_forbids_zeropage mm_use_skey
+#define mm_forbids_zeropage mm_has_pgste
 static inline int mm_use_skey(struct mm_struct *mm)
 {
 #ifdef CONFIG_PGSTE

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);
 }
 
 /*

arch/s390/mm/gmap.c

@@ -2120,6 +2120,37 @@ static inline void thp_split_mm(struct mm_struct *mm)
 #endif
 }
 
+/*
+ * Remove all empty zero pages from the mapping for lazy refaulting
+ * - This must be called after mm->context.has_pgste is set, to avoid
+ *   future creation of zero pages
+ * - This must be called after THP was enabled
+ */
+static int __zap_zero_pages(pmd_t *pmd, unsigned long start,
+			   unsigned long end, struct mm_walk *walk)
+{
+	unsigned long addr;
+
+	for (addr = start; addr != end; addr += PAGE_SIZE) {
+		pte_t *ptep;
+		spinlock_t *ptl;
+
+		ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+		if (is_zero_pfn(pte_pfn(*ptep)))
+			ptep_xchg_direct(walk->mm, addr, ptep, __pte(_PAGE_INVALID));
+		pte_unmap_unlock(ptep, ptl);
+	}
+	return 0;
+}
+
+static inline void zap_zero_pages(struct mm_struct *mm)
+{
+	struct mm_walk walk = { .pmd_entry = __zap_zero_pages };
+
+	walk.mm = mm;
+	walk_page_range(0, TASK_SIZE, &walk);
+}
+
 /*
  * switch on pgstes for its userspace process (for kvm)
  */
@@ -2137,6 +2168,7 @@ int s390_enable_sie(void)
 	mm->context.has_pgste = 1;
 	/* split thp mappings and disable thp for future mappings */
 	thp_split_mm(mm);
+	zap_zero_pages(mm);
 	up_write(&mm->mmap_sem);
 	return 0;
 }
@@ -2149,13 +2181,6 @@ EXPORT_SYMBOL_GPL(s390_enable_sie);
 static int __s390_enable_skey(pte_t *pte, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	/*
-	 * Remove all zero page mappings,
-	 * after establishing a policy to forbid zero page mappings
-	 * following faults for that page will get fresh anonymous pages
-	 */
-	if (is_zero_pfn(pte_pfn(*pte)))
-		ptep_xchg_direct(walk->mm, addr, pte, __pte(_PAGE_INVALID));
 	/* Clear storage key */
 	ptep_zap_key(walk->mm, addr, pte);
 	return 0;

arch/x86/include/asm/elf.h

@@ -204,6 +204,7 @@ void set_personality_ia32(bool);
 
 #define ELF_CORE_COPY_REGS(pr_reg, regs)			\
 do {								\
+	unsigned long base;					\
 	unsigned v;						\
 	(pr_reg)[0] = (regs)->r15;				\
 	(pr_reg)[1] = (regs)->r14;				\
@@ -226,8 +227,8 @@ do {								\
 	(pr_reg)[18] = (regs)->flags;				\
 	(pr_reg)[19] = (regs)->sp;				\
 	(pr_reg)[20] = (regs)->ss;				\
-	(pr_reg)[21] = current->thread.fsbase;			\
-	(pr_reg)[22] = current->thread.gsbase;			\
+	rdmsrl(MSR_FS_BASE, base); (pr_reg)[21] = base;		\
+	rdmsrl(MSR_KERNEL_GS_BASE, base); (pr_reg)[22] = base;	\
 	asm("movl %%ds,%0" : "=r" (v)); (pr_reg)[23] = v;	\
 	asm("movl %%es,%0" : "=r" (v)); (pr_reg)[24] = v;	\
 	asm("movl %%fs,%0" : "=r" (v)); (pr_reg)[25] = v;	\

arch/x86/include/asm/page_64.h

@@ -51,6 +51,10 @@ static inline void clear_page(void *page)
 
 void copy_page(void *to, void *from);
 
+#ifdef CONFIG_X86_MCE
+#define arch_unmap_kpfn arch_unmap_kpfn
+#endif
+
 #endif	/* !__ASSEMBLY__ */
 
 #ifdef CONFIG_X86_VSYSCALL_EMULATION

arch/x86/kernel/cpu/mcheck/mce.c

@@ -51,6 +51,7 @@
 #include <asm/mce.h>
 #include <asm/msr.h>
 #include <asm/reboot.h>
+#include <asm/set_memory.h>
 
 #include "mce-internal.h"
 
@@ -1051,6 +1052,48 @@ static int do_memory_failure(struct mce *m)
 	return ret;
 }
 
+#if defined(arch_unmap_kpfn) && defined(CONFIG_MEMORY_FAILURE)
+
+void arch_unmap_kpfn(unsigned long pfn)
+{
+	unsigned long decoy_addr;
+
+	/*
+	 * Unmap this page from the kernel 1:1 mappings to make sure
+	 * we don't log more errors because of speculative access to
+	 * the page.
+	 * We would like to just call:
+	 *	set_memory_np((unsigned long)pfn_to_kaddr(pfn), 1);
+	 * but doing that would radically increase the odds of a
+	 * speculative access to the posion page because we'd have
+	 * the virtual address of the kernel 1:1 mapping sitting
+	 * around in registers.
+	 * Instead we get tricky.  We create a non-canonical address
+	 * that looks just like the one we want, but has bit 63 flipped.
+	 * This relies on set_memory_np() not checking whether we passed
+	 * a legal address.
+	 */
+
+/*
+ * Build time check to see if we have a spare virtual bit. Don't want
+ * to leave this until run time because most developers don't have a
+ * system that can exercise this code path. This will only become a
+ * problem if/when we move beyond 5-level page tables.
+ *
+ * Hard code "9" here because cpp doesn't grok ilog2(PTRS_PER_PGD)
+ */
+#if PGDIR_SHIFT + 9 < 63
+	decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));
+#else
+#error "no unused virtual bit available"
+#endif
+
+	if (set_memory_np(decoy_addr, 1))
+		pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
+
+}
+#endif
+
 /*
  * The actual machine check handler. This only handles real
  * exceptions when something got corrupted coming in through int 18.

arch/x86/kernel/process_64.c

@@ -149,6 +149,123 @@ void release_thread(struct task_struct *dead_task)
 	}
 }
 
+enum which_selector {
+	FS,
+	GS
+};
+
+/*
+ * Saves the FS or GS base for an outgoing thread if FSGSBASE extensions are
+ * not available.  The goal is to be reasonably fast on non-FSGSBASE systems.
+ * It's forcibly inlined because it'll generate better code and this function
+ * is hot.
+ */
+static __always_inline void save_base_legacy(struct task_struct *prev_p,
+					     unsigned short selector,
+					     enum which_selector which)
+{
+	if (likely(selector == 0)) {
+		/*
+		 * On Intel (without X86_BUG_NULL_SEG), the segment base could
+		 * be the pre-existing saved base or it could be zero.  On AMD
+		 * (with X86_BUG_NULL_SEG), the segment base could be almost
+		 * anything.
+		 *
+		 * This branch is very hot (it's hit twice on almost every
+		 * context switch between 64-bit programs), and avoiding
+		 * the RDMSR helps a lot, so we just assume that whatever
+		 * value is already saved is correct.  This matches historical
+		 * Linux behavior, so it won't break existing applications.
+		 *
+		 * To avoid leaking state, on non-X86_BUG_NULL_SEG CPUs, if we
+		 * report that the base is zero, it needs to actually be zero:
+		 * see the corresponding logic in load_seg_legacy.
+		 */
+	} else {
+		/*
+		 * If the selector is 1, 2, or 3, then the base is zero on
+		 * !X86_BUG_NULL_SEG CPUs and could be anything on
+		 * X86_BUG_NULL_SEG CPUs.  In the latter case, Linux
+		 * has never attempted to preserve the base across context
+		 * switches.
+		 *
+		 * If selector > 3, then it refers to a real segment, and
+		 * saving the base isn't necessary.
+		 */
+		if (which == FS)
+			prev_p->thread.fsbase = 0;
+		else
+			prev_p->thread.gsbase = 0;
+	}
+}
+
+static __always_inline void save_fsgs(struct task_struct *task)
+{
+	savesegment(fs, task->thread.fsindex);
+	savesegment(gs, task->thread.gsindex);
+	save_base_legacy(task, task->thread.fsindex, FS);
+	save_base_legacy(task, task->thread.gsindex, GS);
+}
+
+static __always_inline void loadseg(enum which_selector which,
+				    unsigned short sel)
+{
+	if (which == FS)
+		loadsegment(fs, sel);
+	else
+		load_gs_index(sel);
+}
+
+static __always_inline void load_seg_legacy(unsigned short prev_index,
+					    unsigned long prev_base,
+					    unsigned short next_index,
+					    unsigned long next_base,
+					    enum which_selector which)
+{
+	if (likely(next_index <= 3)) {
+		/*
+		 * The next task is using 64-bit TLS, is not using this
+		 * segment at all, or is having fun with arcane CPU features.
+		 */
+		if (next_base == 0) {
+			/*
+			 * Nasty case: on AMD CPUs, we need to forcibly zero
+			 * the base.
+			 */
+			if (static_cpu_has_bug(X86_BUG_NULL_SEG)) {
+				loadseg(which, __USER_DS);
+				loadseg(which, next_index);
+			} else {
+				/*
+				 * We could try to exhaustively detect cases
+				 * under which we can skip the segment load,
+				 * but there's really only one case that matters
+				 * for performance: if both the previous and
+				 * next states are fully zeroed, we can skip
+				 * the load.
+				 *
+				 * (This assumes that prev_base == 0 has no
+				 * false positives.  This is the case on
+				 * Intel-style CPUs.)
+				 */
+				if (likely(prev_index | next_index | prev_base))
+					loadseg(which, next_index);
+			}
+		} else {
+			if (prev_index != next_index)
+				loadseg(which, next_index);
+			wrmsrl(which == FS ? MSR_FS_BASE : MSR_KERNEL_GS_BASE,
+			       next_base);
+		}
+	} else {
+		/*
+		 * The next task is using a real segment.  Loading the selector
+		 * is sufficient.
+		 */
+		loadseg(which, next_index);
+	}
+}
+
 int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 		unsigned long arg, struct task_struct *p, unsigned long tls)
 {
@@ -229,10 +346,19 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip,
 		    unsigned long new_sp,
 		    unsigned int _cs, unsigned int _ss, unsigned int _ds)
 {
+	WARN_ON_ONCE(regs != current_pt_regs());
+
+	if (static_cpu_has(X86_BUG_NULL_SEG)) {
+		/* Loading zero below won't clear the base. */
+		loadsegment(fs, __USER_DS);
+		load_gs_index(__USER_DS);
+	}
+
 	loadsegment(fs, 0);
 	loadsegment(es, _ds);
 	loadsegment(ds, _ds);
 	load_gs_index(0);
+
 	regs->ip		= new_ip;
 	regs->sp		= new_sp;
 	regs->cs		= _cs;
@@ -277,7 +403,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	struct fpu *next_fpu = &next->fpu;
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
-	unsigned prev_fsindex, prev_gsindex;
 
 	switch_fpu_prepare(prev_fpu, cpu);
 
@@ -286,8 +411,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 *
 	 * (e.g. xen_load_tls())
 	 */
-	savesegment(fs, prev_fsindex);
-	savesegment(gs, prev_gsindex);
+	save_fsgs(prev_p);
 
 	/*
 	 * Load TLS before restoring any segments so that segment loads
@@ -326,108 +450,10 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	if (unlikely(next->ds | prev->ds))
 		loadsegment(ds, next->ds);
 
-	/*
-	 * Switch FS and GS.
-	 *
-	 * These are even more complicated than DS and ES: they have
-	 * 64-bit bases are that controlled by arch_prctl.  The bases
-	 * don't necessarily match the selectors, as user code can do
-	 * any number of things to cause them to be inconsistent.
-	 *
-	 * We don't promise to preserve the bases if the selectors are
-	 * nonzero.  We also don't promise to preserve the base if the
-	 * selector is zero and the base doesn't match whatever was
-	 * most recently passed to ARCH_SET_FS/GS.  (If/when the
-	 * FSGSBASE instructions are enabled, we'll need to offer
-	 * stronger guarantees.)
-	 *
-	 * As an invariant,
-	 * (fsbase != 0 && fsindex != 0) || (gsbase != 0 && gsindex != 0) is
-	 * impossible.
-	 */
-	if (next->fsindex) {
-		/* Loading a nonzero value into FS sets the index and base. */
-		loadsegment(fs, next->fsindex);
-	} else {
-		if (next->fsbase) {
-			/* Next index is zero but next base is nonzero. */
-			if (prev_fsindex)
-				loadsegment(fs, 0);
-			wrmsrl(MSR_FS_BASE, next->fsbase);
-		} else {
-			/* Next base and index are both zero. */
-			if (static_cpu_has_bug(X86_BUG_NULL_SEG)) {
-				/*
-				 * We don't know the previous base and can't
-				 * find out without RDMSR.  Forcibly clear it.
-				 */
-				loadsegment(fs, __USER_DS);
-				loadsegment(fs, 0);
-			} else {
-				/*
-				 * If the previous index is zero and ARCH_SET_FS
-				 * didn't change the base, then the base is
-				 * also zero and we don't need to do anything.
-				 */
-				if (prev->fsbase || prev_fsindex)
-					loadsegment(fs, 0);
-			}
-		}
-	}
-	/*
-	 * Save the old state and preserve the invariant.
-	 * NB: if prev_fsindex == 0, then we can't reliably learn the base
-	 * without RDMSR because Intel user code can zero it without telling
-	 * us and AMD user code can program any 32-bit value without telling
-	 * us.
-	 */
-	if (prev_fsindex)
-		prev->fsbase = 0;
-	prev->fsindex = prev_fsindex;
-
-	if (next->gsindex) {
-		/* Loading a nonzero value into GS sets the index and base. */
-		load_gs_index(next->gsindex);
-	} else {
-		if (next->gsbase) {
-			/* Next index is zero but next base is nonzero. */
-			if (prev_gsindex)
-				load_gs_index(0);
-			wrmsrl(MSR_KERNEL_GS_BASE, next->gsbase);
-		} else {
-			/* Next base and index are both zero. */
-			if (static_cpu_has_bug(X86_BUG_NULL_SEG)) {
-				/*
-				 * We don't know the previous base and can't
-				 * find out without RDMSR.  Forcibly clear it.
-				 *
-				 * This contains a pointless SWAPGS pair.
-				 * Fixing it would involve an explicit check
-				 * for Xen or a new pvop.
-				 */
-				load_gs_index(__USER_DS);
-				load_gs_index(0);
-			} else {
-				/*
-				 * If the previous index is zero and ARCH_SET_GS
-				 * didn't change the base, then the base is
-				 * also zero and we don't need to do anything.
-				 */
-				if (prev->gsbase || prev_gsindex)
-					load_gs_index(0);
-			}
-		}
-	}
-	/*
-	 * Save the old state and preserve the invariant.
-	 * NB: if prev_gsindex == 0, then we can't reliably learn the base
-	 * without RDMSR because Intel user code can zero it without telling
-	 * us and AMD user code can program any 32-bit value without telling
-	 * us.
-	 */
-	if (prev_gsindex)
-		prev->gsbase = 0;
-	prev->gsindex = prev_gsindex;
+	load_seg_legacy(prev->fsindex, prev->fsbase,
+			next->fsindex, next->fsbase, FS);
+	load_seg_legacy(prev->gsindex, prev->gsbase,
+			next->gsindex, next->gsbase, GS);
 
 	switch_fpu_finish(next_fpu, cpu);
 

arch/x86/kvm/mmu.c

@@ -4839,7 +4839,8 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
 	 * Note: AMD only (since it supports the PFERR_GUEST_PAGE_MASK used
 	 *       in PFERR_NEXT_GUEST_PAGE)
 	 */
-	if (error_code == PFERR_NESTED_GUEST_PAGE) {
+	if (vcpu->arch.mmu.direct_map &&
+		error_code == PFERR_NESTED_GUEST_PAGE) {
 		kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2));
 		return 1;
 	}

block/blk-core.c

@@ -280,7 +280,7 @@ EXPORT_SYMBOL(blk_start_queue_async);
 void blk_start_queue(struct request_queue *q)
 {
 	lockdep_assert_held(q->queue_lock);
-	WARN_ON(!irqs_disabled());
+	WARN_ON(!in_interrupt() && !irqs_disabled());
 	WARN_ON_ONCE(q->mq_ops);
 
 	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
@@ -2330,7 +2330,12 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
 	if (q->mq_ops) {
 		if (blk_queue_io_stat(q))
 			blk_account_io_start(rq, true);
-		blk_mq_sched_insert_request(rq, false, true, false, false);
+		/*
+		 * Since we have a scheduler attached on the top device,
+		 * bypass a potential scheduler on the bottom device for
+		 * insert.
+		 */
+		blk_mq_request_bypass_insert(rq);
 		return BLK_STS_OK;
 	}
 

block/blk-mq.c

@@ -1357,6 +1357,22 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	blk_mq_hctx_mark_pending(hctx, ctx);
 }
 
+/*
+ * Should only be used carefully, when the caller knows we want to
+ * bypass a potential IO scheduler on the target device.
+ */
+void blk_mq_request_bypass_insert(struct request *rq)
+{
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(rq->q, ctx->cpu);
+
+	spin_lock(&hctx->lock);
+	list_add_tail(&rq->queuelist, &hctx->dispatch);
+	spin_unlock(&hctx->lock);
+
+	blk_mq_run_hw_queue(hctx, false);
+}
+
 void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 			    struct list_head *list)
 

block/blk-mq.h

@@ -54,6 +54,7 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
  */
 void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 				bool at_head);
+void blk_mq_request_bypass_insert(struct request *rq);
 void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 				struct list_head *list);
 

crypto/algif_skcipher.c

@@ -144,8 +144,10 @@ 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);
 	}

crypto/scompress.c

@@ -211,9 +211,7 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir)
 					      scratch_dst, &req->dlen, *ctx);
 	if (!ret) {
 		if (!req->dst) {
-			req->dst = crypto_scomp_sg_alloc(req->dlen,
-				   req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ?
-				   GFP_KERNEL : GFP_ATOMIC);
+			req->dst = crypto_scomp_sg_alloc(req->dlen, GFP_ATOMIC);
 			if (!req->dst)
 				goto out;
 		}

drivers/android/Kconfig

@@ -22,7 +22,7 @@ config ANDROID_BINDER_IPC
 config ANDROID_BINDER_DEVICES
 	string "Android Binder devices"
 	depends on ANDROID_BINDER_IPC
-	default "binder,hwbinder"
+	default "binder,hwbinder,vndbinder"
 	---help---
 	  Default value for the binder.devices parameter.
 

drivers/android/binder.c

@@ -4215,7 +4215,7 @@ static int __init init_binder_device(const char *name)
 static int __init binder_init(void)
 {
 	int ret;
-	char *device_name, *device_names;
+	char *device_name, *device_names, *device_tmp;
 	struct binder_device *device;
 	struct hlist_node *tmp;
 
@@ -4263,7 +4263,8 @@ static int __init binder_init(void)
 	}
 	strcpy(device_names, binder_devices_param);
 
-	while ((device_name = strsep(&device_names, ","))) {
+	device_tmp = device_names;
+	while ((device_name = strsep(&device_tmp, ","))) {
 		ret = init_binder_device(device_name);
 		if (ret)
 			goto err_init_binder_device_failed;
@@ -4277,6 +4278,9 @@ err_init_binder_device_failed:
 		hlist_del(&device->hlist);
 		kfree(device);
 	}
+
+	kfree(device_names);
+
 err_alloc_device_names_failed:
 	debugfs_remove_recursive(binder_debugfs_dir_entry_root);
 

drivers/ata/ahci.c

@@ -1469,7 +1469,14 @@ static void ahci_remap_check(struct pci_dev *pdev, int bar,
 		return;
 
 	dev_warn(&pdev->dev, "Found %d remapped NVMe devices.\n", count);
-	dev_warn(&pdev->dev, "Switch your BIOS from RAID to AHCI mode to use them.\n");
+	dev_warn(&pdev->dev,
+		 "Switch your BIOS from RAID to AHCI mode to use them.\n");
+
+	/*
+	 * Don't rely on the msi-x capability in the remap case,
+	 * share the legacy interrupt across ahci and remapped devices.
+	 */
+	hpriv->flags |= AHCI_HFLAG_NO_MSI;
 }
 
 static int ahci_get_irq_vector(struct ata_host *host, int port)

drivers/ata/pata_amd.c

@@ -616,6 +616,7 @@ static const struct pci_device_id amd[] = {
 	{ PCI_VDEVICE(NVIDIA,	PCI_DEVICE_ID_NVIDIA_NFORCE_MCP73_IDE),	8 },
 	{ PCI_VDEVICE(NVIDIA,	PCI_DEVICE_ID_NVIDIA_NFORCE_MCP77_IDE),	8 },
 	{ PCI_VDEVICE(AMD,	PCI_DEVICE_ID_AMD_CS5536_IDE),		9 },
+	{ PCI_VDEVICE(AMD,	PCI_DEVICE_ID_AMD_CS5536_DEV_IDE),	9 },
 
 	{ },
 };

drivers/ata/pata_cs5536.c

@@ -289,6 +289,7 @@ static int cs5536_init_one(struct pci_dev *dev, const struct pci_device_id *id)
 
 static const struct pci_device_id cs5536[] = {
 	{ PCI_VDEVICE(AMD,	PCI_DEVICE_ID_AMD_CS5536_IDE), },
+	{ PCI_VDEVICE(AMD,	PCI_DEVICE_ID_AMD_CS5536_DEV_IDE), },
 	{ },
 };
 

drivers/base/bus.c

@@ -698,7 +698,7 @@ int bus_add_driver(struct device_driver *drv)
 
 out_unregister:
 	kobject_put(&priv->kobj);
-	kfree(drv->p);
+	/* drv->p is freed in driver_release()  */
 	drv->p = NULL;
 out_put_bus:
 	bus_put(bus);

drivers/base/firmware_class.c

@@ -256,38 +256,6 @@ static int fw_cache_piggyback_on_request(const char *name);
  * guarding for corner cases a global lock should be OK */
 static DEFINE_MUTEX(fw_lock);
 
-static bool __enable_firmware = false;
-
-static void enable_firmware(void)
-{
-	mutex_lock(&fw_lock);
-	__enable_firmware = true;
-	mutex_unlock(&fw_lock);
-}
-
-static void disable_firmware(void)
-{
-	mutex_lock(&fw_lock);
-	__enable_firmware = false;
-	mutex_unlock(&fw_lock);
-}
-
-/*
- * When disabled only the built-in firmware and the firmware cache will be
- * used to look for firmware.
- */
-static bool firmware_enabled(void)
-{
-	bool enabled = false;
-
-	mutex_lock(&fw_lock);
-	if (__enable_firmware)
-		enabled = true;
-	mutex_unlock(&fw_lock);
-
-	return enabled;
-}
-
 static struct firmware_cache fw_cache;
 
 static struct firmware_buf *__allocate_fw_buf(const char *fw_name,
@@ -1239,12 +1207,6 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
 	if (ret <= 0) /* error or already assigned */
 		goto out;
 
-	if (!firmware_enabled()) {
-		WARN(1, "firmware request while host is not available\n");
-		ret = -EHOSTDOWN;
-		goto out;
-	}
-
 	ret = fw_get_filesystem_firmware(device, fw->priv);
 	if (ret) {
 		if (!(opt_flags & FW_OPT_NO_WARN))
@@ -1755,62 +1717,6 @@ static void device_uncache_fw_images_delay(unsigned long delay)
 			   msecs_to_jiffies(delay));
 }
 
-/**
- * fw_pm_notify - notifier for suspend/resume
- * @notify_block: unused
- * @mode: mode we are switching to
- * @unused: unused
- *
- * Used to modify the firmware_class state as we move in between states.
- * The firmware_class implements a firmware cache to enable device driver
- * to fetch firmware upon resume before the root filesystem is ready. We
- * disable API calls which do not use the built-in firmware or the firmware
- * cache when we know these calls will not work.
- *
- * The inner logic behind all this is a bit complex so it is worth summarizing
- * the kernel's own suspend/resume process with context and focus on how this
- * can impact the firmware API.
- *
- * First a review on how we go to suspend::
- *
- *	pm_suspend() --> enter_state() -->
- *	sys_sync()
- *	suspend_prepare() -->
- *		__pm_notifier_call_chain(PM_SUSPEND_PREPARE, ...);
- *		suspend_freeze_processes() -->
- *			freeze_processes() -->
- *				__usermodehelper_set_disable_depth(UMH_DISABLED);
- *				freeze all tasks ...
- *			freeze_kernel_threads()
- *	suspend_devices_and_enter() -->
- *		dpm_suspend_start() -->
- *				dpm_prepare()
- *				dpm_suspend()
- *		suspend_enter()  -->
- *			platform_suspend_prepare()
- *			dpm_suspend_late()
- *			freeze_enter()
- *			syscore_suspend()
- *
- * When we resume we bail out of a loop from suspend_devices_and_enter() and
- * unwind back out to the caller enter_state() where we were before as follows::
- *
- * 	enter_state() -->
- *	suspend_devices_and_enter() --> (bail from loop)
- *		dpm_resume_end() -->
- *			dpm_resume()
- *			dpm_complete()
- *	suspend_finish() -->
- *		suspend_thaw_processes() -->
- *			thaw_processes() -->
- *				__usermodehelper_set_disable_depth(UMH_FREEZING);
- *				thaw_workqueues();
- *				thaw all processes ...
- *				usermodehelper_enable();
- *		pm_notifier_call_chain(PM_POST_SUSPEND);
- *
- * fw_pm_notify() works through pm_notifier_call_chain().
- */
 static int fw_pm_notify(struct notifier_block *notify_block,
 			unsigned long mode, void *unused)
 {
@@ -1824,7 +1730,6 @@ static int fw_pm_notify(struct notifier_block *notify_block,
 		 */
 		kill_pending_fw_fallback_reqs(true);
 		device_cache_fw_images();
-		disable_firmware();
 		break;
 
 	case PM_POST_SUSPEND:
@@ -1837,7 +1742,6 @@ static int fw_pm_notify(struct notifier_block *notify_block,
 		mutex_lock(&fw_lock);
 		fw_cache.state = FW_LOADER_NO_CACHE;
 		mutex_unlock(&fw_lock);
-		enable_firmware();
 
 		device_uncache_fw_images_delay(10 * MSEC_PER_SEC);
 		break;
@@ -1886,7 +1790,6 @@ static void __init fw_cache_init(void)
 static int fw_shutdown_notify(struct notifier_block *unused1,
 			      unsigned long unused2, void *unused3)
 {
-	disable_firmware();
 	/*
 	 * Kill all pending fallback requests to avoid both stalling shutdown,
 	 * and avoid a deadlock with the usermode_lock.
@@ -1902,7 +1805,6 @@ static struct notifier_block fw_shutdown_nb = {
 
 static int __init firmware_class_init(void)
 {
-	enable_firmware();
 	fw_cache_init();
 	register_reboot_notifier(&fw_shutdown_nb);
 #ifdef CONFIG_FW_LOADER_USER_HELPER
@@ -1914,7 +1816,6 @@ static int __init firmware_class_init(void)
 
 static void __exit firmware_class_exit(void)
 {
-	disable_firmware();
 #ifdef CONFIG_PM_SLEEP
 	unregister_syscore_ops(&fw_syscore_ops);
 	unregister_pm_notifier(&fw_cache.pm_notify);

drivers/block/skd_main.c

@@ -2160,6 +2160,9 @@ 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);
 }
 
@@ -2202,6 +2205,9 @@ 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);
 }
 
@@ -4539,15 +4545,16 @@ 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;
 }
 

drivers/bluetooth/btusb.c

@@ -357,6 +357,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x13d3, 0x3410), .driver_info = BTUSB_REALTEK },
 	{ USB_DEVICE(0x13d3, 0x3416), .driver_info = BTUSB_REALTEK },
 	{ USB_DEVICE(0x13d3, 0x3459), .driver_info = BTUSB_REALTEK },
+	{ USB_DEVICE(0x13d3, 0x3494), .driver_info = BTUSB_REALTEK },
 
 	/* Additional Realtek 8821AE Bluetooth devices */
 	{ USB_DEVICE(0x0b05, 0x17dc), .driver_info = BTUSB_REALTEK },

drivers/crypto/caam/caamalg.c

@@ -81,40 +81,6 @@
 #define debug(format, arg...)
 #endif
 
-#ifdef DEBUG
-#include <linux/highmem.h>
-
-static void dbg_dump_sg(const char *level, const char *prefix_str,
-			int prefix_type, int rowsize, int groupsize,
-			struct scatterlist *sg, size_t tlen, bool ascii)
-{
-	struct scatterlist *it;
-	void *it_page;
-	size_t len;
-	void *buf;
-
-	for (it = sg; it != NULL && tlen > 0 ; it = sg_next(sg)) {
-		/*
-		 * make sure the scatterlist's page
-		 * has a valid virtual memory mapping
-		 */
-		it_page = kmap_atomic(sg_page(it));
-		if (unlikely(!it_page)) {
-			printk(KERN_ERR "dbg_dump_sg: kmap failed\n");
-			return;
-		}
-
-		buf = it_page + it->offset;
-		len = min_t(size_t, tlen, it->length);
-		print_hex_dump(level, prefix_str, prefix_type, rowsize,
-			       groupsize, buf, len, ascii);
-		tlen -= len;
-
-		kunmap_atomic(it_page);
-	}
-}
-#endif
-
 static struct list_head alg_list;
 
 struct caam_alg_entry {
@@ -898,10 +864,10 @@ static void ablkcipher_encrypt_done(struct device *jrdev, u32 *desc, u32 err,
 	print_hex_dump(KERN_ERR, "dstiv  @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, req->info,
 		       edesc->src_nents > 1 ? 100 : ivsize, 1);
-	dbg_dump_sg(KERN_ERR, "dst    @"__stringify(__LINE__)": ",
-		    DUMP_PREFIX_ADDRESS, 16, 4, req->dst,
-		    edesc->dst_nents > 1 ? 100 : req->nbytes, 1);
 #endif
+	caam_dump_sg(KERN_ERR, "dst    @" __stringify(__LINE__)": ",
+		     DUMP_PREFIX_ADDRESS, 16, 4, req->dst,
+		     edesc->dst_nents > 1 ? 100 : req->nbytes, 1);
 
 	ablkcipher_unmap(jrdev, edesc, req);
 
@@ -937,10 +903,10 @@ static void ablkcipher_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
 	print_hex_dump(KERN_ERR, "dstiv  @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, req->info,
 		       ivsize, 1);
-	dbg_dump_sg(KERN_ERR, "dst    @"__stringify(__LINE__)": ",
-		    DUMP_PREFIX_ADDRESS, 16, 4, req->dst,
-		    edesc->dst_nents > 1 ? 100 : req->nbytes, 1);
 #endif
+	caam_dump_sg(KERN_ERR, "dst    @" __stringify(__LINE__)": ",
+		     DUMP_PREFIX_ADDRESS, 16, 4, req->dst,
+		     edesc->dst_nents > 1 ? 100 : req->nbytes, 1);
 
 	ablkcipher_unmap(jrdev, edesc, req);
 
@@ -1107,10 +1073,10 @@ static void init_ablkcipher_job(u32 *sh_desc, dma_addr_t ptr,
 		       ivsize, 1);
 	pr_err("asked=%d, nbytes%d\n",
 	       (int)edesc->src_nents > 1 ? 100 : req->nbytes, req->nbytes);
-	dbg_dump_sg(KERN_ERR, "src    @"__stringify(__LINE__)": ",
-		    DUMP_PREFIX_ADDRESS, 16, 4, req->src,
-		    edesc->src_nents > 1 ? 100 : req->nbytes, 1);
 #endif
+	caam_dump_sg(KERN_ERR, "src    @" __stringify(__LINE__)": ",
+		     DUMP_PREFIX_ADDRESS, 16, 4, req->src,
+		     edesc->src_nents > 1 ? 100 : req->nbytes, 1);
 
 	len = desc_len(sh_desc);
 	init_job_desc_shared(desc, ptr, len, HDR_SHARE_DEFER | HDR_REVERSE);
@@ -1164,10 +1130,10 @@ static void init_ablkcipher_giv_job(u32 *sh_desc, dma_addr_t ptr,
 	print_hex_dump(KERN_ERR, "presciv@" __stringify(__LINE__) ": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, req->info,
 		       ivsize, 1);
-	dbg_dump_sg(KERN_ERR, "src    @" __stringify(__LINE__) ": ",
-		    DUMP_PREFIX_ADDRESS, 16, 4, req->src,
-		    edesc->src_nents > 1 ? 100 : req->nbytes, 1);
 #endif
+	caam_dump_sg(KERN_ERR, "src    @" __stringify(__LINE__) ": ",
+		     DUMP_PREFIX_ADDRESS, 16, 4, req->src,
+		     edesc->src_nents > 1 ? 100 : req->nbytes, 1);
 
 	len = desc_len(sh_desc);
 	init_job_desc_shared(desc, ptr, len, HDR_SHARE_DEFER | HDR_REVERSE);
@@ -1449,11 +1415,9 @@ static int aead_decrypt(struct aead_request *req)
 	u32 *desc;
 	int ret = 0;
 
-#ifdef DEBUG
-	dbg_dump_sg(KERN_ERR, "dec src@"__stringify(__LINE__)": ",
-		    DUMP_PREFIX_ADDRESS, 16, 4, req->src,
-		    req->assoclen + req->cryptlen, 1);
-#endif
+	caam_dump_sg(KERN_ERR, "dec src@" __stringify(__LINE__)": ",
+		     DUMP_PREFIX_ADDRESS, 16, 4, req->src,
+		     req->assoclen + req->cryptlen, 1);
 
 	/* allocate extended descriptor */
 	edesc = aead_edesc_alloc(req, AUTHENC_DESC_JOB_IO_LEN,

drivers/crypto/caam/caamalg_qi.c

@@ -776,9 +776,9 @@ static void ablkcipher_done(struct caam_drv_req *drv_req, u32 status)
 	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
 	struct caam_ctx *caam_ctx = crypto_ablkcipher_ctx(ablkcipher);
 	struct device *qidev = caam_ctx->qidev;
-#ifdef DEBUG
 	int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
 
+#ifdef DEBUG
 	dev_err(qidev, "%s %d: status 0x%x\n", __func__, __LINE__, status);
 #endif
 
@@ -791,14 +791,21 @@ static void ablkcipher_done(struct caam_drv_req *drv_req, u32 status)
 	print_hex_dump(KERN_ERR, "dstiv  @" __stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, req->info,
 		       edesc->src_nents > 1 ? 100 : ivsize, 1);
-	dbg_dump_sg(KERN_ERR, "dst    @" __stringify(__LINE__)": ",
-		    DUMP_PREFIX_ADDRESS, 16, 4, req->dst,
-		    edesc->dst_nents > 1 ? 100 : req->nbytes, 1);
+	caam_dump_sg(KERN_ERR, "dst    @" __stringify(__LINE__)": ",
+		     DUMP_PREFIX_ADDRESS, 16, 4, req->dst,
+		     edesc->dst_nents > 1 ? 100 : req->nbytes, 1);
 #endif
 
 	ablkcipher_unmap(qidev, edesc, req);
 	qi_cache_free(edesc);
 
+	/*
+	 * The crypto API expects us to set the IV (req->info) to the last
+	 * ciphertext block. This is used e.g. by the CTS mode.
+	 */
+	scatterwalk_map_and_copy(req->info, req->dst, req->nbytes - ivsize,
+				 ivsize, 0);
+
 	ablkcipher_request_complete(req, status);
 }
 
@@ -1968,7 +1975,7 @@ static struct caam_aead_alg driver_aeads[] = {
 				.cra_name = "echainiv(authenc(hmac(sha256),"
 					    "cbc(des)))",
 				.cra_driver_name = "echainiv-authenc-"
-						   "hmac-sha256-cbc-desi-"
+						   "hmac-sha256-cbc-des-"
 						   "caam-qi",
 				.cra_blocksize = DES_BLOCK_SIZE,
 			},

drivers/crypto/caam/error.c

@@ -9,6 +9,46 @@
 #include "desc.h"
 #include "error.h"
 
+#ifdef DEBUG
+#include <linux/highmem.h>
+
+void caam_dump_sg(const char *level, const char *prefix_str, int prefix_type,
+		  int rowsize, int groupsize, struct scatterlist *sg,
+		  size_t tlen, bool ascii)
+{
+	struct scatterlist *it;
+	void *it_page;
+	size_t len;
+	void *buf;
+
+	for (it = sg; it && tlen > 0 ; it = sg_next(sg)) {
+		/*
+		 * make sure the scatterlist's page
+		 * has a valid virtual memory mapping
+		 */
+		it_page = kmap_atomic(sg_page(it));
+		if (unlikely(!it_page)) {
+			pr_err("caam_dump_sg: kmap failed\n");
+			return;
+		}
+
+		buf = it_page + it->offset;
+		len = min_t(size_t, tlen, it->length);
+		print_hex_dump(level, prefix_str, prefix_type, rowsize,
+			       groupsize, buf, len, ascii);
+		tlen -= len;
+
+		kunmap_atomic(it_page);
+	}
+}
+#else
+void caam_dump_sg(const char *level, const char *prefix_str, int prefix_type,
+		  int rowsize, int groupsize, struct scatterlist *sg,
+		  size_t tlen, bool ascii)
+{}
+#endif /* DEBUG */
+EXPORT_SYMBOL(caam_dump_sg);
+
 static const struct {
 	u8 value;
 	const char *error_text;

drivers/crypto/caam/error.h

@@ -8,4 +8,8 @@
 #define CAAM_ERROR_H
 #define CAAM_ERROR_STR_MAX 302
 void caam_jr_strstatus(struct device *jrdev, u32 status);
+
+void caam_dump_sg(const char *level, const char *prefix_str, int prefix_type,
+		  int rowsize, int groupsize, struct scatterlist *sg,
+		  size_t tlen, bool ascii);
 #endif /* CAAM_ERROR_H */

drivers/crypto/caam/qi.c

@@ -55,6 +55,7 @@ struct caam_qi_pcpu_priv {
 } ____cacheline_aligned;
 
 static DEFINE_PER_CPU(struct caam_qi_pcpu_priv, pcpu_qipriv);
+static DEFINE_PER_CPU(int, last_cpu);
 
 /*
  * caam_qi_priv - CAAM QI backend private params
@@ -392,7 +393,6 @@ struct caam_drv_ctx *caam_drv_ctx_init(struct device *qidev,
 	dma_addr_t hwdesc;
 	struct caam_drv_ctx *drv_ctx;
 	const cpumask_t *cpus = qman_affine_cpus();
-	static DEFINE_PER_CPU(int, last_cpu);
 
 	num_words = desc_len(sh_desc);
 	if (num_words > MAX_SDLEN) {

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;

drivers/crypto/ccp/ccp-dev-v5.c

@@ -145,6 +145,7 @@ 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_DES3_SIZE(p)	((p)->des3.size)
 #define	CCP_DES3_ENCRYPT(p)	((p)->des3.encrypt)
@@ -344,6 +345,7 @@ 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;

drivers/crypto/ccp/ccp-dev.h

@@ -192,6 +192,7 @@
 #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_DES3_KEY_SB_COUNT		1
@@ -497,6 +498,7 @@ 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;
 };

drivers/crypto/ccp/ccp-ops.c

@@ -1038,6 +1038,8 @@ 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) {
@@ -1061,7 +1063,9 @@ 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)))
@@ -1083,23 +1087,44 @@ 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) {

drivers/devfreq/devfreq.c

@@ -564,7 +564,7 @@ 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,
@@ -610,6 +610,9 @@ err_init:
 	mutex_unlock(&devfreq_list_lock);
 
 	device_unregister(&devfreq->dev);
+err_dev:
+	if (devfreq)
+		kfree(devfreq);
 err_out:
 	return ERR_PTR(err);
 }

drivers/fpga/altera-hps2fpga.c

@@ -66,7 +66,7 @@ static int alt_hps2fpga_enable_show(struct fpga_bridge *bridge)
 
 /* The L3 REMAP register is write only, so keep a cached value. */
 static unsigned int l3_remap_shadow;
-static spinlock_t l3_remap_lock;
+static DEFINE_SPINLOCK(l3_remap_lock);
 
 static int _alt_hps2fpga_enable_set(struct altera_hps2fpga_data *priv,
 				    bool enable)
@@ -171,8 +171,6 @@ static int alt_fpga_bridge_probe(struct platform_device *pdev)
 		return -EBUSY;
 	}
 
-	spin_lock_init(&l3_remap_lock);
-
 	if (!of_property_read_u32(dev->of_node, "bridge-enable", &enable)) {
 		if (enable > 1) {
 			dev_warn(dev, "invalid bridge-enable %u > 1\n", enable);

drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c

@@ -95,9 +95,8 @@ int psp_wait_for(struct psp_context *psp, uint32_t reg_index,
 	int i;
 	struct amdgpu_device *adev = psp->adev;
 
-	val = RREG32(reg_index);
-
 	for (i = 0; i < adev->usec_timeout; i++) {
+		val = RREG32(reg_index);
 		if (check_changed) {
 			if (val != reg_val)
 				return 0;

drivers/gpu/drm/amd/amdgpu/psp_v3_1.c

@@ -237,11 +237,9 @@ int psp_v3_1_bootloader_load_sos(struct psp_context *psp)
 
 	/* there might be handshake issue with hardware which needs delay */
 	mdelay(20);
-#if 0
 	ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_81),
 			   RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81),
 			   0, true);
-#endif
 
 	return ret;
 }

drivers/gpu/drm/drm_dp_mst_topology.c

@@ -2540,8 +2540,8 @@ int drm_dp_atomic_find_vcpi_slots(struct drm_atomic_state *state,
 	int req_slots;
 
 	topology_state = drm_atomic_get_mst_topology_state(state, mgr);
-	if (topology_state == NULL)
-		return -ENOMEM;
+	if (IS_ERR(topology_state))
+		return PTR_ERR(topology_state);
 
 	port = drm_dp_get_validated_port_ref(mgr, port);
 	if (port == NULL)
@@ -2580,8 +2580,8 @@ int drm_dp_atomic_release_vcpi_slots(struct drm_atomic_state *state,
 	struct drm_dp_mst_topology_state *topology_state;
 
 	topology_state = drm_atomic_get_mst_topology_state(state, mgr);
-	if (topology_state == NULL)
-		return -ENOMEM;
+	if (IS_ERR(topology_state))
+		return PTR_ERR(topology_state);
 
 	/* We cannot rely on port->vcpi.num_slots to update
 	 * topology_state->avail_slots as the port may not exist if the parent

drivers/gpu/drm/nouveau/nv50_display.c

@@ -4134,7 +4134,7 @@ nv50_disp_atomic_commit(struct drm_device *dev,
 	if (!nonblock) {
 		ret = drm_atomic_helper_wait_for_fences(dev, state, true);
 		if (ret)
-			goto done;
+			goto err_cleanup;
 	}
 
 	for_each_plane_in_state(state, plane, plane_state, i) {
@@ -4162,7 +4162,7 @@ nv50_disp_atomic_commit(struct drm_device *dev,
 		if (crtc->state->enable) {
 			if (!drm->have_disp_power_ref) {
 				drm->have_disp_power_ref = true;
-				return ret;
+				return 0;
 			}
 			active = true;
 			break;
@@ -4174,6 +4174,9 @@ nv50_disp_atomic_commit(struct drm_device *dev,
 		drm->have_disp_power_ref = false;
 	}
 
+err_cleanup:
+	if (ret)
+		drm_atomic_helper_cleanup_planes(dev, state);
 done:
 	pm_runtime_put_autosuspend(dev->dev);
 	return ret;

drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c

@@ -192,6 +192,10 @@ nvkm_pci_new_(const struct nvkm_pci_func *func, struct nvkm_device *device,
 		}
 	}
 
+#ifdef __BIG_ENDIAN
+	pci->msi = false;
+#endif
+
 	pci->msi = nvkm_boolopt(device->cfgopt, "NvMSI", pci->msi);
 	if (pci->msi && func->msi_rearm) {
 		pci->msi = pci_enable_msi(pci->pdev) == 0;

drivers/gpu/drm/ttm/ttm_page_alloc.c

@@ -615,7 +615,7 @@ static void ttm_page_pool_fill_locked(struct ttm_page_pool *pool,
 		} else {
 			pr_err("Failed to fill pool (%p)\n", pool);
 			/* If we have any pages left put them to the pool. */
-			list_for_each_entry(p, &pool->list, lru) {
+			list_for_each_entry(p, &new_pages, lru) {
 				++cpages;
 			}
 			list_splice(&new_pages, &pool->list);

drivers/gpu/drm/vgem/vgem_drv.c

@@ -52,6 +52,7 @@ static void vgem_gem_free_object(struct drm_gem_object *obj)
 	struct drm_vgem_gem_object *vgem_obj = to_vgem_bo(obj);
 
 	kvfree(vgem_obj->pages);
+	mutex_destroy(&vgem_obj->pages_lock);
 
 	if (obj->import_attach)
 		drm_prime_gem_destroy(obj, vgem_obj->table);
@@ -76,11 +77,15 @@ static int vgem_gem_fault(struct vm_fault *vmf)
 	if (page_offset > num_pages)
 		return VM_FAULT_SIGBUS;
 
+	ret = -ENOENT;
+	mutex_lock(&obj->pages_lock);
 	if (obj->pages) {
 		get_page(obj->pages[page_offset]);
 		vmf->page = obj->pages[page_offset];
 		ret = 0;
-	} else {
+	}
+	mutex_unlock(&obj->pages_lock);
+	if (ret) {
 		struct page *page;
 
 		page = shmem_read_mapping_page(
@@ -161,6 +166,8 @@ static struct drm_vgem_gem_object *__vgem_gem_create(struct drm_device *dev,
 		return ERR_PTR(ret);
 	}
 
+	mutex_init(&obj->pages_lock);
+
 	return obj;
 }
 
@@ -274,37 +281,66 @@ static const struct file_operations vgem_driver_fops = {
 	.release	= drm_release,
 };
 
+static struct page **vgem_pin_pages(struct drm_vgem_gem_object *bo)
+{
+	mutex_lock(&bo->pages_lock);
+	if (bo->pages_pin_count++ == 0) {
+		struct page **pages;
+
+		pages = drm_gem_get_pages(&bo->base);
+		if (IS_ERR(pages)) {
+			bo->pages_pin_count--;
+			mutex_unlock(&bo->pages_lock);
+			return pages;
+		}
+
+		bo->pages = pages;
+	}
+	mutex_unlock(&bo->pages_lock);
+
+	return bo->pages;
+}
+
+static void vgem_unpin_pages(struct drm_vgem_gem_object *bo)
+{
+	mutex_lock(&bo->pages_lock);
+	if (--bo->pages_pin_count == 0) {
+		drm_gem_put_pages(&bo->base, bo->pages, true, true);
+		bo->pages = NULL;
+	}
+	mutex_unlock(&bo->pages_lock);
+}
+
 static int vgem_prime_pin(struct drm_gem_object *obj)
 {
+	struct drm_vgem_gem_object *bo = to_vgem_bo(obj);
 	long n_pages = obj->size >> PAGE_SHIFT;
 	struct page **pages;
 
+	pages = vgem_pin_pages(bo);
+	if (IS_ERR(pages))
+		return PTR_ERR(pages);
+
 	/* Flush the object from the CPU cache so that importers can rely
 	 * on coherent indirect access via the exported dma-address.
 	 */
-	pages = drm_gem_get_pages(obj);
-	if (IS_ERR(pages))
-		return PTR_ERR(pages);
-
 	drm_clflush_pages(pages, n_pages);
-	drm_gem_put_pages(obj, pages, true, false);
 
 	return 0;
 }
 
+static void vgem_prime_unpin(struct drm_gem_object *obj)
+{
+	struct drm_vgem_gem_object *bo = to_vgem_bo(obj);
+
+	vgem_unpin_pages(bo);
+}
+
 static struct sg_table *vgem_prime_get_sg_table(struct drm_gem_object *obj)
 {
-	struct sg_table *st;
-	struct page **pages;
+	struct drm_vgem_gem_object *bo = to_vgem_bo(obj);
 
-	pages = drm_gem_get_pages(obj);
-	if (IS_ERR(pages))
-		return ERR_CAST(pages);
-
-	st = drm_prime_pages_to_sg(pages, obj->size >> PAGE_SHIFT);
-	drm_gem_put_pages(obj, pages, false, false);
-
-	return st;
+	return drm_prime_pages_to_sg(bo->pages, bo->base.size >> PAGE_SHIFT);
 }
 
 static struct drm_gem_object* vgem_prime_import(struct drm_device *dev,
@@ -333,6 +369,8 @@ static struct drm_gem_object *vgem_prime_import_sg_table(struct drm_device *dev,
 		__vgem_gem_destroy(obj);
 		return ERR_PTR(-ENOMEM);
 	}
+
+	obj->pages_pin_count++; /* perma-pinned */
 	drm_prime_sg_to_page_addr_arrays(obj->table, obj->pages, NULL,
 					npages);
 	return &obj->base;
@@ -340,23 +378,23 @@ static struct drm_gem_object *vgem_prime_import_sg_table(struct drm_device *dev,
 
 static void *vgem_prime_vmap(struct drm_gem_object *obj)
 {
+	struct drm_vgem_gem_object *bo = to_vgem_bo(obj);
 	long n_pages = obj->size >> PAGE_SHIFT;
 	struct page **pages;
-	void *addr;
 
-	pages = drm_gem_get_pages(obj);
+	pages = vgem_pin_pages(bo);
 	if (IS_ERR(pages))
 		return NULL;
 
-	addr = vmap(pages, n_pages, 0, pgprot_writecombine(PAGE_KERNEL));
-	drm_gem_put_pages(obj, pages, false, false);
-
-	return addr;
+	return vmap(pages, n_pages, 0, pgprot_writecombine(PAGE_KERNEL));
 }
 
 static void vgem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
 {
+	struct drm_vgem_gem_object *bo = to_vgem_bo(obj);
+
 	vunmap(vaddr);
+	vgem_unpin_pages(bo);
 }
 
 static int vgem_prime_mmap(struct drm_gem_object *obj,
@@ -409,6 +447,7 @@ static struct drm_driver vgem_driver = {
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_pin = vgem_prime_pin,
+	.gem_prime_unpin = vgem_prime_unpin,
 	.gem_prime_import = vgem_prime_import,
 	.gem_prime_export = drm_gem_prime_export,
 	.gem_prime_import_sg_table = vgem_prime_import_sg_table,

drivers/gpu/drm/vgem/vgem_drv.h

@@ -43,7 +43,11 @@ struct vgem_file {
 #define to_vgem_bo(x) container_of(x, struct drm_vgem_gem_object, base)
 struct drm_vgem_gem_object {
 	struct drm_gem_object base;
+
 	struct page **pages;
+	unsigned int pages_pin_count;
+	struct mutex pages_lock;
+
 	struct sg_table *table;
 };
 

drivers/hid/wacom_wac.c

@@ -1846,7 +1846,13 @@ static void wacom_wac_pad_usage_mapping(struct hid_device *hdev,
 		features->device_type |= WACOM_DEVICETYPE_PAD;
 		break;
 	case WACOM_HID_WD_TOUCHRINGSTATUS:
-		wacom_map_usage(input, usage, field, EV_ABS, ABS_WHEEL, 0);
+		/*
+		 * Only set up type/code association. Completely mapping
+		 * this usage may overwrite the axis resolution and range.
+		 */
+		usage->type = EV_ABS;
+		usage->code = ABS_WHEEL;
+		set_bit(EV_ABS, input->evbit);
 		features->device_type |= WACOM_DEVICETYPE_PAD;
 		break;
 	case WACOM_HID_WD_BUTTONCONFIG:

drivers/hwtracing/intel_th/pci.c

@@ -95,6 +95,16 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x318e),
 		.driver_data = (kernel_ulong_t)0,
 	},
+	{
+		/* Cannon Lake H */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa326),
+		.driver_data = (kernel_ulong_t)0,
+	},
+	{
+		/* Cannon Lake LP */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x9da6),
+		.driver_data = (kernel_ulong_t)0,
+	},
 	{ 0 },
 };
 

drivers/iio/adc/ti-ads1015.c

@@ -81,18 +81,12 @@ static const unsigned int ads1115_data_rate[] = {
 	8, 16, 32, 64, 128, 250, 475, 860
 };
 
-static const struct {
-	int scale;
-	int uscale;
-} ads1015_scale[] = {
-	{3, 0},
-	{2, 0},
-	{1, 0},
-	{0, 500000},
-	{0, 250000},
-	{0, 125000},
-	{0, 125000},
-	{0, 125000},
+/*
+ * Translation from PGA bits to full-scale positive and negative input voltage
+ * range in mV
+ */
+static int ads1015_fullscale_range[] = {
+	6144, 4096, 2048, 1024, 512, 256, 256, 256
 };
 
 #define ADS1015_V_CHAN(_chan, _addr) {				\
@@ -183,6 +177,12 @@ struct ads1015_data {
 	struct ads1015_channel_data channel_data[ADS1015_CHANNELS];
 
 	unsigned int *data_rate;
+	/*
+	 * Set to true when the ADC is switched to the continuous-conversion
+	 * mode and exits from a power-down state.  This flag is used to avoid
+	 * getting the stale result from the conversion register.
+	 */
+	bool conv_invalid;
 };
 
 static bool ads1015_is_writeable_reg(struct device *dev, unsigned int reg)
@@ -235,33 +235,43 @@ static int ads1015_set_power_state(struct ads1015_data *data, bool on)
 		ret = pm_runtime_put_autosuspend(dev);
 	}
 
-	return ret;
+	return ret < 0 ? ret : 0;
 }
 
 static
 int ads1015_get_adc_result(struct ads1015_data *data, int chan, int *val)
 {
 	int ret, pga, dr, conv_time;
-	bool change;
+	unsigned int old, mask, cfg;
 
 	if (chan < 0 || chan >= ADS1015_CHANNELS)
 		return -EINVAL;
 
-	pga = data->channel_data[chan].pga;
-	dr = data->channel_data[chan].data_rate;
-
-	ret = regmap_update_bits_check(data->regmap, ADS1015_CFG_REG,
-				       ADS1015_CFG_MUX_MASK |
-				       ADS1015_CFG_PGA_MASK,
-				       chan << ADS1015_CFG_MUX_SHIFT |
-				       pga << ADS1015_CFG_PGA_SHIFT,
-				       &change);
-	if (ret < 0)
+	ret = regmap_read(data->regmap, ADS1015_CFG_REG, &old);
+	if (ret)
 		return ret;
 
-	if (change) {
-		conv_time = DIV_ROUND_UP(USEC_PER_SEC, data->data_rate[dr]);
+	pga = data->channel_data[chan].pga;
+	dr = data->channel_data[chan].data_rate;
+	mask = ADS1015_CFG_MUX_MASK | ADS1015_CFG_PGA_MASK |
+		ADS1015_CFG_DR_MASK;
+	cfg = chan << ADS1015_CFG_MUX_SHIFT | pga << ADS1015_CFG_PGA_SHIFT |
+		dr << ADS1015_CFG_DR_SHIFT;
+
+	cfg = (old & ~mask) | (cfg & mask);
+
+	ret = regmap_write(data->regmap, ADS1015_CFG_REG, cfg);
+	if (ret)
+		return ret;
+
+	if (old != cfg || data->conv_invalid) {
+		int dr_old = (old & ADS1015_CFG_DR_MASK) >>
+				ADS1015_CFG_DR_SHIFT;
+
+		conv_time = DIV_ROUND_UP(USEC_PER_SEC, data->data_rate[dr_old]);
+		conv_time += DIV_ROUND_UP(USEC_PER_SEC, data->data_rate[dr]);
 		usleep_range(conv_time, conv_time + 1);
+		data->conv_invalid = false;
 	}
 
 	return regmap_read(data->regmap, ADS1015_CONV_REG, val);
@@ -298,17 +308,20 @@ err:
 	return IRQ_HANDLED;
 }
 
-static int ads1015_set_scale(struct ads1015_data *data, int chan,
+static int ads1015_set_scale(struct ads1015_data *data,
+			     struct iio_chan_spec const *chan,
 			     int scale, int uscale)
 {
 	int i, ret, rindex = -1;
+	int fullscale = div_s64((scale * 1000000LL + uscale) <<
+				(chan->scan_type.realbits - 1), 1000000);
 
-	for (i = 0; i < ARRAY_SIZE(ads1015_scale); i++)
-		if (ads1015_scale[i].scale == scale &&
-		    ads1015_scale[i].uscale == uscale) {
+	for (i = 0; i < ARRAY_SIZE(ads1015_fullscale_range); i++) {
+		if (ads1015_fullscale_range[i] == fullscale) {
 			rindex = i;
 			break;
 		}
+	}
 	if (rindex < 0)
 		return -EINVAL;
 
@@ -318,32 +331,23 @@ static int ads1015_set_scale(struct ads1015_data *data, int chan,
 	if (ret < 0)
 		return ret;
 
-	data->channel_data[chan].pga = rindex;
+	data->channel_data[chan->address].pga = rindex;
 
 	return 0;
 }
 
 static int ads1015_set_data_rate(struct ads1015_data *data, int chan, int rate)
 {
-	int i, ret, rindex = -1;
+	int i;
 
-	for (i = 0; i < ARRAY_SIZE(ads1015_data_rate); i++)
+	for (i = 0; i < ARRAY_SIZE(ads1015_data_rate); i++) {
 		if (data->data_rate[i] == rate) {
-			rindex = i;
-			break;
+			data->channel_data[chan].data_rate = i;
+			return 0;
 		}
-	if (rindex < 0)
-		return -EINVAL;
+	}
 
-	ret = regmap_update_bits(data->regmap, ADS1015_CFG_REG,
-				 ADS1015_CFG_DR_MASK,
-				 rindex << ADS1015_CFG_DR_SHIFT);
-	if (ret < 0)
-		return ret;
-
-	data->channel_data[chan].data_rate = rindex;
-
-	return 0;
+	return -EINVAL;
 }
 
 static int ads1015_read_raw(struct iio_dev *indio_dev,
@@ -385,9 +389,9 @@ static int ads1015_read_raw(struct iio_dev *indio_dev,
 	}
 	case IIO_CHAN_INFO_SCALE:
 		idx = data->channel_data[chan->address].pga;
-		*val = ads1015_scale[idx].scale;
-		*val2 = ads1015_scale[idx].uscale;
-		ret = IIO_VAL_INT_PLUS_MICRO;
+		*val = ads1015_fullscale_range[idx];
+		*val2 = chan->scan_type.realbits - 1;
+		ret = IIO_VAL_FRACTIONAL_LOG2;
 		break;
 	case IIO_CHAN_INFO_SAMP_FREQ:
 		idx = data->channel_data[chan->address].data_rate;
@@ -414,7 +418,7 @@ static int ads1015_write_raw(struct iio_dev *indio_dev,
 	mutex_lock(&data->lock);
 	switch (mask) {
 	case IIO_CHAN_INFO_SCALE:
-		ret = ads1015_set_scale(data, chan->address, val, val2);
+		ret = ads1015_set_scale(data, chan, val, val2);
 		break;
 	case IIO_CHAN_INFO_SAMP_FREQ:
 		ret = ads1015_set_data_rate(data, chan->address, val);
@@ -446,7 +450,10 @@ static const struct iio_buffer_setup_ops ads1015_buffer_setup_ops = {
 	.validate_scan_mask = &iio_validate_scan_mask_onehot,
 };
 
-static IIO_CONST_ATTR(scale_available, "3 2 1 0.5 0.25 0.125");
+static IIO_CONST_ATTR_NAMED(ads1015_scale_available, scale_available,
+	"3 2 1 0.5 0.25 0.125");
+static IIO_CONST_ATTR_NAMED(ads1115_scale_available, scale_available,
+	"0.1875 0.125 0.0625 0.03125 0.015625 0.007813");
 
 static IIO_CONST_ATTR_NAMED(ads1015_sampling_frequency_available,
 	sampling_frequency_available, "128 250 490 920 1600 2400 3300");
@@ -454,7 +461,7 @@ static IIO_CONST_ATTR_NAMED(ads1115_sampling_frequency_available,
 	sampling_frequency_available, "8 16 32 64 128 250 475 860");
 
 static struct attribute *ads1015_attributes[] = {
-	&iio_const_attr_scale_available.dev_attr.attr,
+	&iio_const_attr_ads1015_scale_available.dev_attr.attr,
 	&iio_const_attr_ads1015_sampling_frequency_available.dev_attr.attr,
 	NULL,
 };
@@ -464,7 +471,7 @@ static const struct attribute_group ads1015_attribute_group = {
 };
 
 static struct attribute *ads1115_attributes[] = {
-	&iio_const_attr_scale_available.dev_attr.attr,
+	&iio_const_attr_ads1115_scale_available.dev_attr.attr,
 	&iio_const_attr_ads1115_sampling_frequency_available.dev_attr.attr,
 	NULL,
 };
@@ -630,6 +637,15 @@ static int ads1015_probe(struct i2c_client *client,
 		dev_err(&client->dev, "iio triggered buffer setup failed\n");
 		return ret;
 	}
+
+	ret = regmap_update_bits(data->regmap, ADS1015_CFG_REG,
+				ADS1015_CFG_MOD_MASK,
+				ADS1015_CONTINUOUS << ADS1015_CFG_MOD_SHIFT);
+	if (ret)
+		return ret;
+
+	data->conv_invalid = true;
+
 	ret = pm_runtime_set_active(&client->dev);
 	if (ret)
 		goto err_buffer_cleanup;
@@ -685,10 +701,15 @@ static int ads1015_runtime_resume(struct device *dev)
 {
 	struct iio_dev *indio_dev = i2c_get_clientdata(to_i2c_client(dev));
 	struct ads1015_data *data = iio_priv(indio_dev);
+	int ret;
 
-	return regmap_update_bits(data->regmap, ADS1015_CFG_REG,
+	ret = regmap_update_bits(data->regmap, ADS1015_CFG_REG,
 				  ADS1015_CFG_MOD_MASK,
 				  ADS1015_CONTINUOUS << ADS1015_CFG_MOD_SHIFT);
+	if (!ret)
+		data->conv_invalid = true;
+
+	return ret;
 }
 #endif
 

drivers/infiniband/hw/hfi1/init.c

@@ -483,7 +483,6 @@ void hfi1_init_pportdata(struct pci_dev *pdev, struct hfi1_pportdata *ppd,
 
 	ppd->pkeys[default_pkey_idx] = DEFAULT_P_KEY;
 	ppd->part_enforce |= HFI1_PART_ENFORCE_IN;
-	ppd->part_enforce |= HFI1_PART_ENFORCE_OUT;
 
 	if (loopback) {
 		hfi1_early_err(&pdev->dev,

drivers/infiniband/hw/hfi1/rc.c

@@ -425,7 +425,7 @@ 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) &&
@@ -433,6 +433,7 @@ 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);

drivers/infiniband/hw/mlx5/mr.c

@@ -48,6 +48,7 @@ enum {
 #define MLX5_UMR_ALIGN 2048
 
 static int clean_mr(struct mlx5_ib_mr *mr);
+static int max_umr_order(struct mlx5_ib_dev *dev);
 static int use_umr(struct mlx5_ib_dev *dev, int order);
 static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr);
 
@@ -491,16 +492,18 @@ static struct mlx5_ib_mr *alloc_cached_mr(struct mlx5_ib_dev *dev, int order)
 	struct mlx5_mr_cache *cache = &dev->cache;
 	struct mlx5_ib_mr *mr = NULL;
 	struct mlx5_cache_ent *ent;
+	int last_umr_cache_entry;
 	int c;
 	int i;
 
 	c = order2idx(dev, order);
-	if (c < 0 || c > MAX_UMR_CACHE_ENTRY) {
+	last_umr_cache_entry = order2idx(dev, max_umr_order(dev));
+	if (c < 0 || c > last_umr_cache_entry) {
 		mlx5_ib_warn(dev, "order %d, cache index %d\n", order, c);
 		return NULL;
 	}
 
-	for (i = c; i < MAX_UMR_CACHE_ENTRY; i++) {
+	for (i = c; i <= last_umr_cache_entry; i++) {
 		ent = &cache->ent[i];
 
 		mlx5_ib_dbg(dev, "order %d, cache index %d\n", ent->order, i);
@@ -816,11 +819,16 @@ static int get_octo_len(u64 addr, u64 len, int page_size)
 	return (npages + 1) / 2;
 }
 
-static int use_umr(struct mlx5_ib_dev *dev, int order)
+static int max_umr_order(struct mlx5_ib_dev *dev)
 {
 	if (MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset))
-		return order <= MAX_UMR_CACHE_ENTRY + 2;
-	return order <= MLX5_MAX_UMR_SHIFT;
+		return MAX_UMR_CACHE_ENTRY + 2;
+	return MLX5_MAX_UMR_SHIFT;
+}
+
+static int use_umr(struct mlx5_ib_dev *dev, int order)
+{
+	return order <= max_umr_order(dev);
 }
 
 static int mr_umem_get(struct ib_pd *pd, u64 start, u64 length,

drivers/infiniband/hw/qib/qib_rc.c

@@ -348,7 +348,7 @@ 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) &&
@@ -356,7 +356,7 @@ 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 =

drivers/input/joystick/xpad.c

@@ -1764,10 +1764,12 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id
 		struct usb_endpoint_descriptor *ep =
 				&intf->cur_altsetting->endpoint[i].desc;
 
-		if (usb_endpoint_dir_in(ep))
-			ep_irq_in = ep;
-		else
-			ep_irq_out = ep;
+		if (usb_endpoint_xfer_int(ep)) {
+			if (usb_endpoint_dir_in(ep))
+				ep_irq_in = ep;
+			else
+				ep_irq_out = ep;
+		}
 	}
 
 	if (!ep_irq_in || !ep_irq_out) {

drivers/input/serio/i8042-x86ia64io.h

@@ -839,6 +839,13 @@ 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 = {

drivers/mailbox/bcm-flexrm-mailbox.c

@@ -95,7 +95,7 @@
 
 /* Register RING_CMPL_START_ADDR fields */
 #define CMPL_START_ADDR_VALUE(pa)			\
-	((u32)((((u64)(pa)) >> RING_CMPL_ALIGN_ORDER) & 0x03ffffff))
+	((u32)((((u64)(pa)) >> RING_CMPL_ALIGN_ORDER) & 0x07ffffff))
 
 /* Register RING_CONTROL fields */
 #define CONTROL_MASK_DISABLE_CONTROL			12

drivers/mcb/mcb-lpc.c

@@ -114,6 +114,12 @@ static struct resource sc24_fpga_resource = {
 	.flags = IORESOURCE_MEM,
 };
 
+static struct resource sc31_fpga_resource = {
+	.start = 0xf000e000,
+	.end = 0xf000e000 + CHAM_HEADER_SIZE,
+	.flags = IORESOURCE_MEM,
+};
+
 static struct platform_driver mcb_lpc_driver = {
 	.driver		= {
 		.name = "mcb-lpc",
@@ -132,6 +138,15 @@ static const struct dmi_system_id mcb_lpc_dmi_table[] = {
 		.driver_data = (void *)&sc24_fpga_resource,
 		.callback = mcb_lpc_create_platform_device,
 	},
+	{
+		.ident = "SC31",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "MEN"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "14SC31"),
+		},
+		.driver_data = (void *)&sc31_fpga_resource,
+		.callback = mcb_lpc_create_platform_device,
+	},
 	{}
 };
 MODULE_DEVICE_TABLE(dmi, mcb_lpc_dmi_table);

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;
 

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.
@@ -400,12 +400,6 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
 	if (!congested && !dc->sequential_cutoff)
 		goto rescale;
 
-	if (!congested &&
-	    mode == CACHE_MODE_WRITEBACK &&
-	    op_is_write(bio->bi_opf) &&
-	    op_is_sync(bio->bi_opf))
-		goto rescale;
-
 	spin_lock(&dc->io_lock);
 
 	hlist_for_each_entry(i, iohash(dc, bio->bi_iter.bi_sector), hash)

drivers/md/bcache/super.c

@@ -1026,7 +1026,7 @@ 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);
@@ -1059,6 +1059,8 @@ 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);
 
@@ -1228,6 +1230,7 @@ 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);
 
@@ -1964,6 +1967,8 @@ 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;
 		}

drivers/md/bcache/sysfs.c

@@ -192,7 +192,7 @@ 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;
 
@@ -227,7 +227,7 @@ 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;

drivers/md/bcache/util.c

@@ -74,24 +74,44 @@ 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;
+	int u = 0, t;
 
-	for (u = 0; v >= 1024 || v <= -1024; u++) {
-		t = v & ~(~0 << 10);
-		v >>= 10;
-	}
+	uint64_t q;
 
-	if (!u)
-		return sprintf(buf, "%llu", v);
+	if (v < 0)
+		q = -v;
+	else
+		q = v;
 
-	if (v < 100 && v > -100)
-		snprintf(dec, sizeof(dec), ".%i", t / 100);
+	/* 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++;
 
-	return sprintf(buf, "%lli%s%c", v, dec, units[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[],

drivers/md/bcache/writeback.c

@@ -21,7 +21,8 @@
 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))

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)
 {
@@ -84,7 +103,7 @@ 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 *);
 

drivers/md/bitmap.c

@@ -625,7 +625,7 @@ re_read:
 		err = read_sb_page(bitmap->mddev,
 				   offset,
 				   sb_page,
-				   0, sizeof(bitmap_super_t));
+				   0, PAGE_SIZE);
 	}
 	if (err)
 		return err;
@@ -2058,6 +2058,11 @@ 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.
@@ -2118,7 +2123,7 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 	if (store.sb_page && bitmap->storage.sb_page)
 		memcpy(page_address(store.sb_page),
 		       page_address(bitmap->storage.sb_page),
-		       sizeof(bitmap_super_t));
+		       PAGE_SIZE);
 	bitmap_file_unmap(&bitmap->storage);
 	bitmap->storage = store;
 

drivers/md/raid1.c

@@ -2564,6 +2564,23 @@ static int init_resync(struct r1conf *conf)
 	return 0;
 }
 
+static struct r1bio *raid1_alloc_init_r1buf(struct r1conf *conf)
+{
+	struct r1bio *r1bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO);
+	struct resync_pages *rps;
+	struct bio *bio;
+	int i;
+
+	for (i = conf->poolinfo->raid_disks; i--; ) {
+		bio = r1bio->bios[i];
+		rps = bio->bi_private;
+		bio_reset(bio);
+		bio->bi_private = rps;
+	}
+	r1bio->master_bio = NULL;
+	return r1bio;
+}
+
 /*
  * perform a "sync" on one "block"
  *
@@ -2649,7 +2666,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 
 	bitmap_cond_end_sync(mddev->bitmap, sector_nr,
 		mddev_is_clustered(mddev) && (sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high));
-	r1_bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO);
+	r1_bio = raid1_alloc_init_r1buf(conf);
 
 	raise_barrier(conf, sector_nr);
 

drivers/md/raid10.c

@@ -2798,6 +2798,35 @@ static int init_resync(struct r10conf *conf)
 	return 0;
 }
 
+static struct r10bio *raid10_alloc_init_r10buf(struct r10conf *conf)
+{
+	struct r10bio *r10bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+	struct rsync_pages *rp;
+	struct bio *bio;
+	int nalloc;
+	int i;
+
+	if (test_bit(MD_RECOVERY_SYNC, &conf->mddev->recovery) ||
+	    test_bit(MD_RECOVERY_RESHAPE, &conf->mddev->recovery))
+		nalloc = conf->copies; /* resync */
+	else
+		nalloc = 2; /* recovery */
+
+	for (i = 0; i < nalloc; i++) {
+		bio = r10bio->devs[i].bio;
+		rp = bio->bi_private;
+		bio_reset(bio);
+		bio->bi_private = rp;
+		bio = r10bio->devs[i].repl_bio;
+		if (bio) {
+			rp = bio->bi_private;
+			bio_reset(bio);
+			bio->bi_private = rp;
+		}
+	}
+	return r10bio;
+}
+
 /*
  * perform a "sync" on one "block"
  *
@@ -3027,7 +3056,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				atomic_inc(&mreplace->nr_pending);
 			rcu_read_unlock();
 
-			r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+			r10_bio = raid10_alloc_init_r10buf(conf);
 			r10_bio->state = 0;
 			raise_barrier(conf, rb2 != NULL);
 			atomic_set(&r10_bio->remaining, 0);
@@ -3236,7 +3265,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		}
 		if (sync_blocks < max_sync)
 			max_sync = sync_blocks;
-		r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+		r10_bio = raid10_alloc_init_r10buf(conf);
 		r10_bio->state = 0;
 
 		r10_bio->mddev = mddev;
@@ -4360,7 +4389,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
 
 read_more:
 	/* Now schedule reads for blocks from sector_nr to last */
-	r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+	r10_bio = raid10_alloc_init_r10buf(conf);
 	r10_bio->state = 0;
 	raise_barrier(conf, sectors_done != 0);
 	atomic_set(&r10_bio->remaining, 0);

drivers/md/raid5.c

@@ -6235,6 +6235,10 @@ static void raid5_do_work(struct work_struct *work)
 
 	spin_unlock_irq(&conf->device_lock);
 
+	flush_deferred_bios(conf);
+
+	r5l_flush_stripe_to_raid(conf->log);
+
 	async_tx_issue_pending_all();
 	blk_finish_plug(&plug);
 

drivers/media/i2c/adv7180.c

@@ -1402,6 +1402,8 @@ static int adv7180_remove(struct i2c_client *client)
 
 static const struct i2c_device_id adv7180_id[] = {
 	{ "adv7180", (kernel_ulong_t)&adv7180_info },
+	{ "adv7180cp", (kernel_ulong_t)&adv7180_info },
+	{ "adv7180st", (kernel_ulong_t)&adv7180_info },
 	{ "adv7182", (kernel_ulong_t)&adv7182_info },
 	{ "adv7280", (kernel_ulong_t)&adv7280_info },
 	{ "adv7280-m", (kernel_ulong_t)&adv7280_m_info },

drivers/media/platform/qcom/venus/helpers.c

@@ -243,7 +243,7 @@ static void return_buf_error(struct venus_inst *inst,
 	if (vbuf->vb2_buf.type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE)
 		v4l2_m2m_src_buf_remove_by_buf(m2m_ctx, vbuf);
 	else
-		v4l2_m2m_src_buf_remove_by_buf(m2m_ctx, vbuf);
+		v4l2_m2m_dst_buf_remove_by_buf(m2m_ctx, vbuf);
 
 	v4l2_m2m_buf_done(vbuf, VB2_BUF_STATE_ERROR);
 }

drivers/media/rc/lirc_dev.c

@@ -59,6 +59,8 @@ static void lirc_release(struct device *ld)
 {
 	struct irctl *ir = container_of(ld, struct irctl, dev);
 
+	put_device(ir->dev.parent);
+
 	if (ir->buf_internal) {
 		lirc_buffer_free(ir->buf);
 		kfree(ir->buf);
@@ -218,6 +220,8 @@ int lirc_register_driver(struct lirc_driver *d)
 
 	mutex_unlock(&lirc_dev_lock);
 
+	get_device(ir->dev.parent);
+
 	dev_info(ir->d.dev, "lirc_dev: driver %s registered at minor = %d\n",
 		 ir->d.name, ir->d.minor);
 

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', "

drivers/media/v4l2-core/v4l2-compat-ioctl32.c

@@ -796,7 +796,8 @@ 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;

drivers/misc/cxl/api.c

@@ -336,6 +336,10 @@ int cxl_start_context(struct cxl_context *ctx, u64 wed,
 			mmput(ctx->mm);
 	}
 
+	/*
+	 * Increment driver use count. Enables global TLBIs for hash
+	 * and callbacks to handle the segment table
+	 */
 	cxl_ctx_get();
 
 	if ((rc = cxl_ops->attach_process(ctx, kernel, wed, 0))) {

drivers/misc/cxl/file.c

@@ -95,7 +95,6 @@ static int __afu_open(struct inode *inode, struct file *file, bool master)
 
 	pr_devel("afu_open pe: %i\n", ctx->pe);
 	file->private_data = ctx;
-	cxl_ctx_get();
 
 	/* indicate success */
 	rc = 0;
@@ -225,6 +224,12 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
 	if (ctx->mm)
 		mmput(ctx->mm);
 
+	/*
+	 * Increment driver use count. Enables global TLBIs for hash
+	 * and callbacks to handle the segment table
+	 */
+	cxl_ctx_get();
+
 	trace_cxl_attach(ctx, work.work_element_descriptor, work.num_interrupts, amr);
 
 	if ((rc = cxl_ops->attach_process(ctx, false, work.work_element_descriptor,
@@ -233,6 +238,7 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
 		cxl_adapter_context_put(ctx->afu->adapter);
 		put_pid(ctx->pid);
 		ctx->pid = NULL;
+		cxl_ctx_put();
 		cxl_context_mm_count_put(ctx);
 		goto out;
 	}

drivers/mtd/nand/mxc_nand.c

@@ -876,6 +876,8 @@ static void mxc_do_addr_cycle(struct mtd_info *mtd, int column, int page_addr)
 	}
 }
 
+#define MXC_V1_ECCBYTES		5
+
 static int mxc_v1_ooblayout_ecc(struct mtd_info *mtd, int section,
 				struct mtd_oob_region *oobregion)
 {
@@ -885,7 +887,7 @@ static int mxc_v1_ooblayout_ecc(struct mtd_info *mtd, int section,
 		return -ERANGE;
 
 	oobregion->offset = (section * 16) + 6;
-	oobregion->length = nand_chip->ecc.bytes;
+	oobregion->length = MXC_V1_ECCBYTES;
 
 	return 0;
 }
@@ -907,8 +909,7 @@ static int mxc_v1_ooblayout_free(struct mtd_info *mtd, int section,
 			oobregion->length = 4;
 		}
 	} else {
-		oobregion->offset = ((section - 1) * 16) +
-				    nand_chip->ecc.bytes + 6;
+		oobregion->offset = ((section - 1) * 16) + MXC_V1_ECCBYTES + 6;
 		if (section < nand_chip->ecc.steps)
 			oobregion->length = (section * 16) + 6 -
 					    oobregion->offset;

drivers/mtd/nand/nand_base.c

@@ -3993,10 +3993,13 @@ static void nand_manufacturer_detect(struct nand_chip *chip)
 	 * nand_decode_ext_id() otherwise.
 	 */
 	if (chip->manufacturer.desc && chip->manufacturer.desc->ops &&
-	    chip->manufacturer.desc->ops->detect)
+	    chip->manufacturer.desc->ops->detect) {
+		/* The 3rd id byte holds MLC / multichip data */
+		chip->bits_per_cell = nand_get_bits_per_cell(chip->id.data[2]);
 		chip->manufacturer.desc->ops->detect(chip);
-	else
+	} else {
 		nand_decode_ext_id(chip);
+	}
 }
 
 /*

drivers/mtd/nand/nand_hynix.c

@@ -477,7 +477,7 @@ static void hynix_nand_extract_ecc_requirements(struct nand_chip *chip,
 		 * The ECC requirements field meaning depends on the
 		 * NAND technology.
 		 */
-		u8 nand_tech = chip->id.data[5] & 0x3;
+		u8 nand_tech = chip->id.data[5] & 0x7;
 
 		if (nand_tech < 3) {
 			/* > 26nm, reference: H27UBG8T2A datasheet */
@@ -533,7 +533,7 @@ static void hynix_nand_extract_scrambling_requirements(struct nand_chip *chip,
 		if (nand_tech > 0)
 			chip->options |= NAND_NEED_SCRAMBLING;
 	} else {
-		nand_tech = chip->id.data[5] & 0x3;
+		nand_tech = chip->id.data[5] & 0x7;
 
 		/* < 32nm */
 		if (nand_tech > 2)

drivers/mtd/nand/qcom_nandc.c

@@ -109,7 +109,11 @@
 #define	READ_ADDR			0
 
 /* NAND_DEV_CMD_VLD bits */
-#define	READ_START_VLD			0
+#define	READ_START_VLD			BIT(0)
+#define	READ_STOP_VLD			BIT(1)
+#define	WRITE_START_VLD			BIT(2)
+#define	ERASE_START_VLD			BIT(3)
+#define	SEQ_READ_START_VLD		BIT(4)
 
 /* NAND_EBI2_ECC_BUF_CFG bits */
 #define	NUM_STEPS			0
@@ -148,6 +152,10 @@
 #define	FETCH_ID			0xb
 #define	RESET_DEVICE			0xd
 
+/* Default Value for NAND_DEV_CMD_VLD */
+#define NAND_DEV_CMD_VLD_VAL		(READ_START_VLD | WRITE_START_VLD | \
+					 ERASE_START_VLD | SEQ_READ_START_VLD)
+
 /*
  * the NAND controller performs reads/writes with ECC in 516 byte chunks.
  * the driver calls the chunks 'step' or 'codeword' interchangeably
@@ -672,8 +680,7 @@ static int nandc_param(struct qcom_nand_host *host)
 
 	/* configure CMD1 and VLD for ONFI param probing */
 	nandc_set_reg(nandc, NAND_DEV_CMD_VLD,
-		      (nandc->vld & ~(1 << READ_START_VLD))
-		      | 0 << READ_START_VLD);
+		      (nandc->vld & ~READ_START_VLD));
 	nandc_set_reg(nandc, NAND_DEV_CMD1,
 		      (nandc->cmd1 & ~(0xFF << READ_ADDR))
 		      | NAND_CMD_PARAM << READ_ADDR);
@@ -1893,7 +1900,7 @@ static int qcom_nand_host_setup(struct qcom_nand_host *host)
 				| wide_bus << WIDE_FLASH
 				| 1 << DEV0_CFG1_ECC_DISABLE;
 
-	host->ecc_bch_cfg = host->bch_enabled << ECC_CFG_ECC_DISABLE
+	host->ecc_bch_cfg = !host->bch_enabled << ECC_CFG_ECC_DISABLE
 				| 0 << ECC_SW_RESET
 				| host->cw_data << ECC_NUM_DATA_BYTES
 				| 1 << ECC_FORCE_CLK_OPEN
@@ -1972,13 +1979,14 @@ static int qcom_nandc_setup(struct qcom_nand_controller *nandc)
 {
 	/* kill onenand */
 	nandc_write(nandc, SFLASHC_BURST_CFG, 0);
+	nandc_write(nandc, NAND_DEV_CMD_VLD, NAND_DEV_CMD_VLD_VAL);
 
 	/* enable ADM DMA */
 	nandc_write(nandc, NAND_FLASH_CHIP_SELECT, DM_EN);
 
 	/* save the original values of these registers */
 	nandc->cmd1 = nandc_read(nandc, NAND_DEV_CMD1);
-	nandc->vld = nandc_read(nandc, NAND_DEV_CMD_VLD);
+	nandc->vld = NAND_DEV_CMD_VLD_VAL;
 
 	return 0;
 }

drivers/net/ethernet/freescale/gianfar.c

@@ -3687,7 +3687,7 @@ static noinline void gfar_update_link_state(struct gfar_private *priv)
 		u32 tempval1 = gfar_read(&regs->maccfg1);
 		u32 tempval = gfar_read(&regs->maccfg2);
 		u32 ecntrl = gfar_read(&regs->ecntrl);
-		u32 tx_flow_oldval = (tempval & MACCFG1_TX_FLOW);
+		u32 tx_flow_oldval = (tempval1 & MACCFG1_TX_FLOW);
 
 		if (phydev->duplex != priv->oldduplex) {
 			if (!(phydev->duplex))

drivers/net/wireless/ath/ath10k/core.c

@@ -2055,6 +2055,12 @@ int ath10k_core_start(struct ath10k *ar, enum ath10k_firmware_mode mode,
 		goto err_wmi_detach;
 	}
 
+	/* If firmware indicates Full Rx Reorder support it must be used in a
+	 * slightly different manner. Let HTT code know.
+	 */
+	ar->htt.rx_ring.in_ord_rx = !!(test_bit(WMI_SERVICE_RX_FULL_REORDER,
+						ar->wmi.svc_map));
+
 	status = ath10k_htt_rx_alloc(&ar->htt);
 	if (status) {
 		ath10k_err(ar, "failed to alloc htt rx: %d\n", status);
@@ -2167,12 +2173,6 @@ int ath10k_core_start(struct ath10k *ar, enum ath10k_firmware_mode mode,
 		}
 	}
 
-	/* If firmware indicates Full Rx Reorder support it must be used in a
-	 * slightly different manner. Let HTT code know.
-	 */
-	ar->htt.rx_ring.in_ord_rx = !!(test_bit(WMI_SERVICE_RX_FULL_REORDER,
-						ar->wmi.svc_map));
-
 	status = ath10k_htt_rx_ring_refill(ar);
 	if (status) {
 		ath10k_err(ar, "failed to refill htt rx ring: %d\n", status);

drivers/net/wireless/ath/wcn36xx/main.c

@@ -372,6 +372,8 @@ static int wcn36xx_config(struct ieee80211_hw *hw, u32 changed)
 
 	wcn36xx_dbg(WCN36XX_DBG_MAC, "mac config changed 0x%08x\n", changed);
 
+	mutex_lock(&wcn->conf_mutex);
+
 	if (changed & IEEE80211_CONF_CHANGE_CHANNEL) {
 		int ch = WCN36XX_HW_CHANNEL(wcn);
 		wcn36xx_dbg(WCN36XX_DBG_MAC, "wcn36xx_config channel switch=%d\n",
@@ -382,6 +384,8 @@ static int wcn36xx_config(struct ieee80211_hw *hw, u32 changed)
 		}
 	}
 
+	mutex_unlock(&wcn->conf_mutex);
+
 	return 0;
 }
 
@@ -396,6 +400,8 @@ static void wcn36xx_configure_filter(struct ieee80211_hw *hw,
 
 	wcn36xx_dbg(WCN36XX_DBG_MAC, "mac configure filter\n");
 
+	mutex_lock(&wcn->conf_mutex);
+
 	*total &= FIF_ALLMULTI;
 
 	fp = (void *)(unsigned long)multicast;
@@ -408,6 +414,8 @@ static void wcn36xx_configure_filter(struct ieee80211_hw *hw,
 		else if (NL80211_IFTYPE_STATION == vif->type && tmp->sta_assoc)
 			wcn36xx_smd_set_mc_list(wcn, vif, fp);
 	}
+
+	mutex_unlock(&wcn->conf_mutex);
 	kfree(fp);
 }
 
@@ -471,6 +479,8 @@ static int wcn36xx_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 			 key_conf->key,
 			 key_conf->keylen);
 
+	mutex_lock(&wcn->conf_mutex);
+
 	switch (key_conf->cipher) {
 	case WLAN_CIPHER_SUITE_WEP40:
 		vif_priv->encrypt_type = WCN36XX_HAL_ED_WEP40;
@@ -565,6 +575,8 @@ static int wcn36xx_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	}
 
 out:
+	mutex_unlock(&wcn->conf_mutex);
+
 	return ret;
 }
 
@@ -725,6 +737,8 @@ static void wcn36xx_bss_info_changed(struct ieee80211_hw *hw,
 	wcn36xx_dbg(WCN36XX_DBG_MAC, "mac bss info changed vif %p changed 0x%08x\n",
 		    vif, changed);
 
+	mutex_lock(&wcn->conf_mutex);
+
 	if (changed & BSS_CHANGED_BEACON_INFO) {
 		wcn36xx_dbg(WCN36XX_DBG_MAC,
 			    "mac bss changed dtim period %d\n",
@@ -787,7 +801,13 @@ static void wcn36xx_bss_info_changed(struct ieee80211_hw *hw,
 				     bss_conf->aid);
 
 			vif_priv->sta_assoc = true;
-			rcu_read_lock();
+
+			/*
+			 * Holding conf_mutex ensures mutal exclusion with
+			 * wcn36xx_sta_remove() and as such ensures that sta
+			 * won't be freed while we're operating on it. As such
+			 * we do not need to hold the rcu_read_lock().
+			 */
 			sta = ieee80211_find_sta(vif, bss_conf->bssid);
 			if (!sta) {
 				wcn36xx_err("sta %pM is not found\n",
@@ -811,7 +831,6 @@ static void wcn36xx_bss_info_changed(struct ieee80211_hw *hw,
 			 * place where AID is available.
 			 */
 			wcn36xx_smd_config_sta(wcn, vif, sta);
-			rcu_read_unlock();
 		} else {
 			wcn36xx_dbg(WCN36XX_DBG_MAC,
 				    "disassociated bss %pM vif %pM AID=%d\n",
@@ -873,6 +892,9 @@ static void wcn36xx_bss_info_changed(struct ieee80211_hw *hw,
 		}
 	}
 out:
+
+	mutex_unlock(&wcn->conf_mutex);
+
 	return;
 }
 
@@ -882,7 +904,10 @@ static int wcn36xx_set_rts_threshold(struct ieee80211_hw *hw, u32 value)
 	struct wcn36xx *wcn = hw->priv;
 	wcn36xx_dbg(WCN36XX_DBG_MAC, "mac set RTS threshold %d\n", value);
 
+	mutex_lock(&wcn->conf_mutex);
 	wcn36xx_smd_update_cfg(wcn, WCN36XX_HAL_CFG_RTS_THRESHOLD, value);
+	mutex_unlock(&wcn->conf_mutex);
+
 	return 0;
 }
 
@@ -893,8 +918,12 @@ static void wcn36xx_remove_interface(struct ieee80211_hw *hw,
 	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
 	wcn36xx_dbg(WCN36XX_DBG_MAC, "mac remove interface vif %p\n", vif);
 
+	mutex_lock(&wcn->conf_mutex);
+
 	list_del(&vif_priv->list);
 	wcn36xx_smd_delete_sta_self(wcn, vif->addr);
+
+	mutex_unlock(&wcn->conf_mutex);
 }
 
 static int wcn36xx_add_interface(struct ieee80211_hw *hw,
@@ -915,9 +944,13 @@ static int wcn36xx_add_interface(struct ieee80211_hw *hw,
 		return -EOPNOTSUPP;
 	}
 
+	mutex_lock(&wcn->conf_mutex);
+
 	list_add(&vif_priv->list, &wcn->vif_list);
 	wcn36xx_smd_add_sta_self(wcn, vif);
 
+	mutex_unlock(&wcn->conf_mutex);
+
 	return 0;
 }
 
@@ -930,6 +963,8 @@ static int wcn36xx_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	wcn36xx_dbg(WCN36XX_DBG_MAC, "mac sta add vif %p sta %pM\n",
 		    vif, sta->addr);
 
+	mutex_lock(&wcn->conf_mutex);
+
 	spin_lock_init(&sta_priv->ampdu_lock);
 	sta_priv->vif = vif_priv;
 	/*
@@ -941,6 +976,9 @@ static int wcn36xx_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		sta_priv->aid = sta->aid;
 		wcn36xx_smd_config_sta(wcn, vif, sta);
 	}
+
+	mutex_unlock(&wcn->conf_mutex);
+
 	return 0;
 }
 
@@ -954,8 +992,13 @@ static int wcn36xx_sta_remove(struct ieee80211_hw *hw,
 	wcn36xx_dbg(WCN36XX_DBG_MAC, "mac sta remove vif %p sta %pM index %d\n",
 		    vif, sta->addr, sta_priv->sta_index);
 
+	mutex_lock(&wcn->conf_mutex);
+
 	wcn36xx_smd_delete_sta(wcn, sta_priv->sta_index);
 	sta_priv->vif = NULL;
+
+	mutex_unlock(&wcn->conf_mutex);
+
 	return 0;
 }
 
@@ -999,6 +1042,8 @@ static int wcn36xx_ampdu_action(struct ieee80211_hw *hw,
 	wcn36xx_dbg(WCN36XX_DBG_MAC, "mac ampdu action action %d tid %d\n",
 		    action, tid);
 
+	mutex_lock(&wcn->conf_mutex);
+
 	switch (action) {
 	case IEEE80211_AMPDU_RX_START:
 		sta_priv->tid = tid;
@@ -1038,6 +1083,8 @@ static int wcn36xx_ampdu_action(struct ieee80211_hw *hw,
 		wcn36xx_err("Unknown AMPDU action\n");
 	}
 
+	mutex_unlock(&wcn->conf_mutex);
+
 	return 0;
 }
 
@@ -1216,6 +1263,7 @@ static int wcn36xx_probe(struct platform_device *pdev)
 	wcn = hw->priv;
 	wcn->hw = hw;
 	wcn->dev = &pdev->dev;
+	mutex_init(&wcn->conf_mutex);
 	mutex_init(&wcn->hal_mutex);
 	mutex_init(&wcn->scan_lock);
 

drivers/net/wireless/ath/wcn36xx/wcn36xx.h

@@ -202,6 +202,9 @@ struct wcn36xx {
 	struct qcom_smem_state	*tx_rings_empty_state;
 	unsigned		tx_rings_empty_state_bit;
 
+	/* prevents concurrent FW reconfiguration */
+	struct mutex		conf_mutex;
+
 	/*
 	 * smd_buf must be protected with smd_mutex to garantee
 	 * that all messages are sent one after another

drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c

@@ -159,7 +159,8 @@ void brcmf_feat_attach(struct brcmf_pub *drvr)
 
 	brcmf_feat_firmware_capabilities(ifp);
 	memset(&gscan_cfg, 0, sizeof(gscan_cfg));
-	if (drvr->bus_if->chip != BRCM_CC_43430_CHIP_ID)
+	if (drvr->bus_if->chip != BRCM_CC_43430_CHIP_ID &&
+	    drvr->bus_if->chip != BRCM_CC_4345_CHIP_ID)
 		brcmf_feat_iovar_data_set(ifp, BRCMF_FEAT_GSCAN,
 					  "pfn_gscan_cfg",
 					  &gscan_cfg, sizeof(gscan_cfg));