Merge remote-tracking branch 'remotes/rth-gitlab/tags/pull-fp-20210516' into staging

Reorg FloatParts to use QEMU_GENERIC.
Begin replacing the Berkeley float128 routines with FloatParts128.
  - includes a new implementation of float128_muladd
  - includes the snan silencing that was missing from
    float{32,64}_to_float128 and float128_to_float{32,64}.
  - does not include float128_min/max* (written but not yet reviewed).

# gpg: Signature made Sun 16 May 2021 13:27:10 BST
# gpg:                using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg:                issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [full]
# Primary key fingerprint: 7A48 1E78 868B 4DB6 A85A  05C0 64DF 38E8 AF7E 215F

* remotes/rth-gitlab/tags/pull-fp-20210516: (46 commits)
  softfloat: Move round_to_int_and_pack to softfloat-parts.c.inc
  softfloat: Move round_to_int to softfloat-parts.c.inc
  softfloat: Convert float-to-float conversions with float128
  softfloat: Split float_to_float
  softfloat: Move div_floats to softfloat-parts.c.inc
  softfloat: Introduce sh[lr]_double primitives
  softfloat: Tidy mul128By64To192
  softfloat: Use add192 in mul128To256
  softfloat: Use mulu64 for mul64To128
  softfloat: Move muladd_floats to softfloat-parts.c.inc
  softfloat: Move mul_floats to softfloat-parts.c.inc
  softfloat: Implement float128_add/sub via parts
  softfloat: Move addsub_floats to softfloat-parts.c.inc
  softfloat: Use uadd64_carry, usub64_borrow in softfloat-macros.h
  softfloat: Move round_canonical to softfloat-parts.c.inc
  softfloat: Move sf_canonicalize to softfloat-parts.c.inc
  softfloat: Move pick_nan_muladd to softfloat-parts.c.inc
  softfloat: Move pick_nan to softfloat-parts.c.inc
  softfloat: Move return_nan to softfloat-parts.c.inc
  softfloat: Convert float128_default_nan to parts
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

3 files changed, 380 insertions, 133 deletions

diff --git a/include/fpu/softfloat-macros.h b/include/fpu/softfloat-macros.h
index a35ec28..ec4e27a 100644
--- a/include/fpu/softfloat-macros.h
+++ b/include/fpu/softfloat-macros.h
@@ -83,6 +83,43 @@ this code that are retained.
 #define FPU_SOFTFLOAT_MACROS_H
 
 #include "fpu/softfloat-types.h"
+#include "qemu/host-utils.h"
+
+/**
+ * shl_double: double-word merging left shift
+ * @l: left or most-significant word
+ * @r: right or least-significant word
+ * @c: shift count
+ *
+ * Shift @l left by @c bits, shifting in bits from @r.
+ */
+static inline uint64_t shl_double(uint64_t l, uint64_t r, int c)
+{
+#if defined(__x86_64__)
+    asm("shld %b2, %1, %0" : "+r"(l) : "r"(r), "ci"(c));
+    return l;
+#else
+    return c ? (l << c) | (r >> (64 - c)) : l;
+#endif
+}
+
+/**
+ * shr_double: double-word merging right shift
+ * @l: left or most-significant word
+ * @r: right or least-significant word
+ * @c: shift count
+ *
+ * Shift @r right by @c bits, shifting in bits from @l.
+ */
+static inline uint64_t shr_double(uint64_t l, uint64_t r, int c)
+{
+#if defined(__x86_64__)
+    asm("shrd %b2, %1, %0" : "+r"(r) : "r"(l), "ci"(c));
+    return r;
+#else
+    return c ? (r >> c) | (l << (64 - c)) : r;
+#endif
+}
 
 /*----------------------------------------------------------------------------
 | Shifts `a' right by the number of bits given in `count'.  If any nonzero
@@ -403,16 +440,12 @@ static inline void
 | are stored at the locations pointed to by `z0Ptr' and `z1Ptr'.
 *----------------------------------------------------------------------------*/
 
-static inline void
- add128(
-     uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1, uint64_t *z0Ptr, uint64_t *z1Ptr )
+static inline void add128(uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1,
+                          uint64_t *z0Ptr, uint64_t *z1Ptr)
 {
-    uint64_t z1;
-
-    z1 = a1 + b1;
-    *z1Ptr = z1;
-    *z0Ptr = a0 + b0 + ( z1 < a1 );
-
+    bool c = 0;
+    *z1Ptr = uadd64_carry(a1, b1, &c);
+    *z0Ptr = uadd64_carry(a0, b0, &c);
 }
 
 /*----------------------------------------------------------------------------
@@ -423,34 +456,14 @@ static inline void
 | `z1Ptr', and `z2Ptr'.
 *----------------------------------------------------------------------------*/
 
-static inline void
- add192(
-     uint64_t a0,
-     uint64_t a1,
-     uint64_t a2,
-     uint64_t b0,
-     uint64_t b1,
-     uint64_t b2,
-     uint64_t *z0Ptr,
-     uint64_t *z1Ptr,
-     uint64_t *z2Ptr
- )
+static inline void add192(uint64_t a0, uint64_t a1, uint64_t a2,
+                          uint64_t b0, uint64_t b1, uint64_t b2,
+                          uint64_t *z0Ptr, uint64_t *z1Ptr, uint64_t *z2Ptr)
 {
-    uint64_t z0, z1, z2;
-    int8_t carry0, carry1;
-
-    z2 = a2 + b2;
-    carry1 = ( z2 < a2 );
-    z1 = a1 + b1;
-    carry0 = ( z1 < a1 );
-    z0 = a0 + b0;
-    z1 += carry1;
-    z0 += ( z1 < carry1 );
-    z0 += carry0;
-    *z2Ptr = z2;
-    *z1Ptr = z1;
-    *z0Ptr = z0;
-
+    bool c = 0;
+    *z2Ptr = uadd64_carry(a2, b2, &c);
+    *z1Ptr = uadd64_carry(a1, b1, &c);
+    *z0Ptr = uadd64_carry(a0, b0, &c);
 }
 
 /*----------------------------------------------------------------------------
@@ -461,14 +474,12 @@ static inline void
 | `z1Ptr'.
 *----------------------------------------------------------------------------*/
 
-static inline void
- sub128(
-     uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1, uint64_t *z0Ptr, uint64_t *z1Ptr )
+static inline void sub128(uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1,
+                          uint64_t *z0Ptr, uint64_t *z1Ptr)
 {
-
-    *z1Ptr = a1 - b1;
-    *z0Ptr = a0 - b0 - ( a1 < b1 );
-
+    bool c = 0;
+    *z1Ptr = usub64_borrow(a1, b1, &c);
+    *z0Ptr = usub64_borrow(a0, b0, &c);
 }
 
 /*----------------------------------------------------------------------------
@@ -479,34 +490,14 @@ static inline void
 | pointed to by `z0Ptr', `z1Ptr', and `z2Ptr'.
 *----------------------------------------------------------------------------*/
 
-static inline void
- sub192(
-     uint64_t a0,
-     uint64_t a1,
-     uint64_t a2,
-     uint64_t b0,
-     uint64_t b1,
-     uint64_t b2,
-     uint64_t *z0Ptr,
-     uint64_t *z1Ptr,
-     uint64_t *z2Ptr
- )
+static inline void sub192(uint64_t a0, uint64_t a1, uint64_t a2,
+                          uint64_t b0, uint64_t b1, uint64_t b2,
+                          uint64_t *z0Ptr, uint64_t *z1Ptr, uint64_t *z2Ptr)
 {
-    uint64_t z0, z1, z2;
-    int8_t borrow0, borrow1;
-
-    z2 = a2 - b2;
-    borrow1 = ( a2 < b2 );
-    z1 = a1 - b1;
-    borrow0 = ( a1 < b1 );
-    z0 = a0 - b0;
-    z0 -= ( z1 < borrow1 );
-    z1 -= borrow1;
-    z0 -= borrow0;
-    *z2Ptr = z2;
-    *z1Ptr = z1;
-    *z0Ptr = z0;
-
+    bool c = 0;
+    *z2Ptr = usub64_borrow(a2, b2, &c);
+    *z1Ptr = usub64_borrow(a1, b1, &c);
+    *z0Ptr = usub64_borrow(a0, b0, &c);
 }
 
 /*----------------------------------------------------------------------------
@@ -515,27 +506,10 @@ static inline void
 | `z0Ptr' and `z1Ptr'.
 *----------------------------------------------------------------------------*/
 
-static inline void mul64To128( uint64_t a, uint64_t b, uint64_t *z0Ptr, uint64_t *z1Ptr )
+static inline void
+mul64To128(uint64_t a, uint64_t b, uint64_t *z0Ptr, uint64_t *z1Ptr)
 {
-    uint32_t aHigh, aLow, bHigh, bLow;
-    uint64_t z0, zMiddleA, zMiddleB, z1;
-
-    aLow = a;
-    aHigh = a>>32;
-    bLow = b;
-    bHigh = b>>32;
-    z1 = ( (uint64_t) aLow ) * bLow;
-    zMiddleA = ( (uint64_t) aLow ) * bHigh;
-    zMiddleB = ( (uint64_t) aHigh ) * bLow;
-    z0 = ( (uint64_t) aHigh ) * bHigh;
-    zMiddleA += zMiddleB;
-    z0 += ( ( (uint64_t) ( zMiddleA < zMiddleB ) )<<32 ) + ( zMiddleA>>32 );
-    zMiddleA <<= 32;
-    z1 += zMiddleA;
-    z0 += ( z1 < zMiddleA );
-    *z1Ptr = z1;
-    *z0Ptr = z0;
-
+    mulu64(z1Ptr, z0Ptr, a, b);
 }
 
 /*----------------------------------------------------------------------------
@@ -546,24 +520,14 @@ static inline void mul64To128( uint64_t a, uint64_t b, uint64_t *z0Ptr, uint64_t
 *----------------------------------------------------------------------------*/
 
 static inline void
- mul128By64To192(
-     uint64_t a0,
-     uint64_t a1,
-     uint64_t b,
-     uint64_t *z0Ptr,
-     uint64_t *z1Ptr,
-     uint64_t *z2Ptr
- )
+mul128By64To192(uint64_t a0, uint64_t a1, uint64_t b,
+                uint64_t *z0Ptr, uint64_t *z1Ptr, uint64_t *z2Ptr)
 {
-    uint64_t z0, z1, z2, more1;
-
-    mul64To128( a1, b, &z1, &z2 );
-    mul64To128( a0, b, &z0, &more1 );
-    add128( z0, more1, 0, z1, &z0, &z1 );
-    *z2Ptr = z2;
-    *z1Ptr = z1;
-    *z0Ptr = z0;
+    uint64_t z0, z1, m1;
 
+    mul64To128(a1, b, &m1, z2Ptr);
+    mul64To128(a0, b, &z0, &z1);
+    add128(z0, z1, 0, m1, z0Ptr, z1Ptr);
 }
 
 /*----------------------------------------------------------------------------
@@ -573,34 +537,21 @@ static inline void
 | the locations pointed to by `z0Ptr', `z1Ptr', `z2Ptr', and `z3Ptr'.
 *----------------------------------------------------------------------------*/
 
-static inline void
- mul128To256(
-     uint64_t a0,
-     uint64_t a1,
-     uint64_t b0,
-     uint64_t b1,
-     uint64_t *z0Ptr,
-     uint64_t *z1Ptr,
-     uint64_t *z2Ptr,
-     uint64_t *z3Ptr
- )
+static inline void mul128To256(uint64_t a0, uint64_t a1,
+                               uint64_t b0, uint64_t b1,
+                               uint64_t *z0Ptr, uint64_t *z1Ptr,
+                               uint64_t *z2Ptr, uint64_t *z3Ptr)
 {
-    uint64_t z0, z1, z2, z3;
-    uint64_t more1, more2;
-
-    mul64To128( a1, b1, &z2, &z3 );
-    mul64To128( a1, b0, &z1, &more2 );
-    add128( z1, more2, 0, z2, &z1, &z2 );
-    mul64To128( a0, b0, &z0, &more1 );
-    add128( z0, more1, 0, z1, &z0, &z1 );
-    mul64To128( a0, b1, &more1, &more2 );
-    add128( more1, more2, 0, z2, &more1, &z2 );
-    add128( z0, z1, 0, more1, &z0, &z1 );
-    *z3Ptr = z3;
-    *z2Ptr = z2;
-    *z1Ptr = z1;
-    *z0Ptr = z0;
+    uint64_t z0, z1, z2;
+    uint64_t m0, m1, m2, n1, n2;
+
+    mul64To128(a1, b0, &m1, &m2);
+    mul64To128(a0, b1, &n1, &n2);
+    mul64To128(a1, b1, &z2, z3Ptr);
+    mul64To128(a0, b0, &z0, &z1);
 
+    add192( 0, m1, m2,  0, n1, n2, &m0, &m1, &m2);
+    add192(m0, m1, m2, z0, z1, z2, z0Ptr, z1Ptr, z2Ptr);
 }
 
 /*----------------------------------------------------------------------------
diff --git a/include/fpu/softfloat.h b/include/fpu/softfloat.h
index 78ad5ca..53f2c2e 100644
--- a/include/fpu/softfloat.h
+++ b/include/fpu/softfloat.h
@@ -100,7 +100,10 @@ typedef enum {
 | Routine to raise any or all of the software IEC/IEEE floating-point
 | exception flags.
 *----------------------------------------------------------------------------*/
-void float_raise(uint8_t flags, float_status *status);
+static inline void float_raise(uint8_t flags, float_status *status)
+{
+    status->float_exception_flags |= flags;
+}
 
 /*----------------------------------------------------------------------------
 | If `a' is denormal and we are in flush-to-zero mode then set the
@@ -1194,6 +1197,8 @@ float128 float128_round_to_int(float128, float_status *status);
 float128 float128_add(float128, float128, float_status *status);
 float128 float128_sub(float128, float128, float_status *status);
 float128 float128_mul(float128, float128, float_status *status);
+float128 float128_muladd(float128, float128, float128, int,
+                         float_status *status);
 float128 float128_div(float128, float128, float_status *status);
 float128 float128_rem(float128, float128, float_status *status);
 float128 float128_sqrt(float128, float_status *status);
diff --git a/include/qemu/host-utils.h b/include/qemu/host-utils.h
index cdca299..711b221 100644
--- a/include/qemu/host-utils.h
+++ b/include/qemu/host-utils.h
@@ -26,6 +26,7 @@
 #ifndef HOST_UTILS_H
 #define HOST_UTILS_H
 
+#include "qemu/compiler.h"
 #include "qemu/bswap.h"
 
 #ifdef CONFIG_INT128
@@ -272,6 +273,9 @@ static inline int ctpop64(uint64_t val)
  */
 static inline uint8_t revbit8(uint8_t x)
 {
+#if __has_builtin(__builtin_bitreverse8)
+    return __builtin_bitreverse8(x);
+#else
     /* Assign the correct nibble position.  */
     x = ((x & 0xf0) >> 4)
       | ((x & 0x0f) << 4);
@@ -281,6 +285,7 @@ static inline uint8_t revbit8(uint8_t x)
       | ((x & 0x22) << 1)
       | ((x & 0x11) << 3);
     return x;
+#endif
 }
 
 /**
@@ -289,6 +294,9 @@ static inline uint8_t revbit8(uint8_t x)
  */
 static inline uint16_t revbit16(uint16_t x)
 {
+#if __has_builtin(__builtin_bitreverse16)
+    return __builtin_bitreverse16(x);
+#else
     /* Assign the correct byte position.  */
     x = bswap16(x);
     /* Assign the correct nibble position.  */
@@ -300,6 +308,7 @@ static inline uint16_t revbit16(uint16_t x)
       | ((x & 0x2222) << 1)
       | ((x & 0x1111) << 3);
     return x;
+#endif
 }
 
 /**
@@ -308,6 +317,9 @@ static inline uint16_t revbit16(uint16_t x)
  */
 static inline uint32_t revbit32(uint32_t x)
 {
+#if __has_builtin(__builtin_bitreverse32)
+    return __builtin_bitreverse32(x);
+#else
     /* Assign the correct byte position.  */
     x = bswap32(x);
     /* Assign the correct nibble position.  */
@@ -319,6 +331,7 @@ static inline uint32_t revbit32(uint32_t x)
       | ((x & 0x22222222u) << 1)
       | ((x & 0x11111111u) << 3);
     return x;
+#endif
 }
 
 /**
@@ -327,6 +340,9 @@ static inline uint32_t revbit32(uint32_t x)
  */
 static inline uint64_t revbit64(uint64_t x)
 {
+#if __has_builtin(__builtin_bitreverse64)
+    return __builtin_bitreverse64(x);
+#else
     /* Assign the correct byte position.  */
     x = bswap64(x);
     /* Assign the correct nibble position.  */
@@ -338,6 +354,281 @@ static inline uint64_t revbit64(uint64_t x)
       | ((x & 0x2222222222222222ull) << 1)
       | ((x & 0x1111111111111111ull) << 3);
     return x;
+#endif
+}
+
+/**
+ * sadd32_overflow - addition with overflow indication
+ * @x, @y: addends
+ * @ret: Output for sum
+ *
+ * Computes *@ret = @x + @y, and returns true if and only if that
+ * value has been truncated.
+ */
+static inline bool sadd32_overflow(int32_t x, int32_t y, int32_t *ret)
+{
+#if __has_builtin(__builtin_add_overflow) || __GNUC__ >= 5
+    return __builtin_add_overflow(x, y, ret);
+#else
+    *ret = x + y;
+    return ((*ret ^ x) & ~(x ^ y)) < 0;
+#endif
+}
+
+/**
+ * sadd64_overflow - addition with overflow indication
+ * @x, @y: addends
+ * @ret: Output for sum
+ *
+ * Computes *@ret = @x + @y, and returns true if and only if that
+ * value has been truncated.
+ */
+static inline bool sadd64_overflow(int64_t x, int64_t y, int64_t *ret)
+{
+#if __has_builtin(__builtin_add_overflow) || __GNUC__ >= 5
+    return __builtin_add_overflow(x, y, ret);
+#else
+    *ret = x + y;
+    return ((*ret ^ x) & ~(x ^ y)) < 0;
+#endif
+}
+
+/**
+ * uadd32_overflow - addition with overflow indication
+ * @x, @y: addends
+ * @ret: Output for sum
+ *
+ * Computes *@ret = @x + @y, and returns true if and only if that
+ * value has been truncated.
+ */
+static inline bool uadd32_overflow(uint32_t x, uint32_t y, uint32_t *ret)
+{
+#if __has_builtin(__builtin_add_overflow) || __GNUC__ >= 5
+    return __builtin_add_overflow(x, y, ret);
+#else
+    *ret = x + y;
+    return *ret < x;
+#endif
+}
+
+/**
+ * uadd64_overflow - addition with overflow indication
+ * @x, @y: addends
+ * @ret: Output for sum
+ *
+ * Computes *@ret = @x + @y, and returns true if and only if that
+ * value has been truncated.
+ */
+static inline bool uadd64_overflow(uint64_t x, uint64_t y, uint64_t *ret)
+{
+#if __has_builtin(__builtin_add_overflow) || __GNUC__ >= 5
+    return __builtin_add_overflow(x, y, ret);
+#else
+    *ret = x + y;
+    return *ret < x;
+#endif
+}
+
+/**
+ * ssub32_overflow - subtraction with overflow indication
+ * @x: Minuend
+ * @y: Subtrahend
+ * @ret: Output for difference
+ *
+ * Computes *@ret = @x - @y, and returns true if and only if that
+ * value has been truncated.
+ */
+static inline bool ssub32_overflow(int32_t x, int32_t y, int32_t *ret)
+{
+#if __has_builtin(__builtin_sub_overflow) || __GNUC__ >= 5
+    return __builtin_sub_overflow(x, y, ret);
+#else
+    *ret = x - y;
+    return ((*ret ^ x) & (x ^ y)) < 0;
+#endif
+}
+
+/**
+ * ssub64_overflow - subtraction with overflow indication
+ * @x: Minuend
+ * @y: Subtrahend
+ * @ret: Output for sum
+ *
+ * Computes *@ret = @x - @y, and returns true if and only if that
+ * value has been truncated.
+ */
+static inline bool ssub64_overflow(int64_t x, int64_t y, int64_t *ret)
+{
+#if __has_builtin(__builtin_sub_overflow) || __GNUC__ >= 5
+    return __builtin_sub_overflow(x, y, ret);
+#else
+    *ret = x - y;
+    return ((*ret ^ x) & (x ^ y)) < 0;
+#endif
+}
+
+/**
+ * usub32_overflow - subtraction with overflow indication
+ * @x: Minuend
+ * @y: Subtrahend
+ * @ret: Output for sum
+ *
+ * Computes *@ret = @x - @y, and returns true if and only if that
+ * value has been truncated.
+ */
+static inline bool usub32_overflow(uint32_t x, uint32_t y, uint32_t *ret)
+{
+#if __has_builtin(__builtin_sub_overflow) || __GNUC__ >= 5
+    return __builtin_sub_overflow(x, y, ret);
+#else
+    *ret = x - y;
+    return x < y;
+#endif
+}
+
+/**
+ * usub64_overflow - subtraction with overflow indication
+ * @x: Minuend
+ * @y: Subtrahend
+ * @ret: Output for sum
+ *
+ * Computes *@ret = @x - @y, and returns true if and only if that
+ * value has been truncated.
+ */
+static inline bool usub64_overflow(uint64_t x, uint64_t y, uint64_t *ret)
+{
+#if __has_builtin(__builtin_sub_overflow) || __GNUC__ >= 5
+    return __builtin_sub_overflow(x, y, ret);
+#else
+    *ret = x - y;
+    return x < y;
+#endif
+}
+
+/**
+ * smul32_overflow - multiplication with overflow indication
+ * @x, @y: Input multipliers
+ * @ret: Output for product
+ *
+ * Computes *@ret = @x * @y, and returns true if and only if that
+ * value has been truncated.
+ */
+static inline bool smul32_overflow(int32_t x, int32_t y, int32_t *ret)
+{
+#if __has_builtin(__builtin_mul_overflow) || __GNUC__ >= 5
+    return __builtin_mul_overflow(x, y, ret);
+#else
+    int64_t z = (int64_t)x * y;
+    *ret = z;
+    return *ret != z;
+#endif
+}
+
+/**
+ * smul64_overflow - multiplication with overflow indication
+ * @x, @y: Input multipliers
+ * @ret: Output for product
+ *
+ * Computes *@ret = @x * @y, and returns true if and only if that
+ * value has been truncated.
+ */
+static inline bool smul64_overflow(int64_t x, int64_t y, int64_t *ret)
+{
+#if __has_builtin(__builtin_mul_overflow) || __GNUC__ >= 5
+    return __builtin_mul_overflow(x, y, ret);
+#else
+    uint64_t hi, lo;
+    muls64(&lo, &hi, x, y);
+    *ret = lo;
+    return hi != ((int64_t)lo >> 63);
+#endif
+}
+
+/**
+ * umul32_overflow - multiplication with overflow indication
+ * @x, @y: Input multipliers
+ * @ret: Output for product
+ *
+ * Computes *@ret = @x * @y, and returns true if and only if that
+ * value has been truncated.
+ */
+static inline bool umul32_overflow(uint32_t x, uint32_t y, uint32_t *ret)
+{
+#if __has_builtin(__builtin_mul_overflow) || __GNUC__ >= 5
+    return __builtin_mul_overflow(x, y, ret);
+#else
+    uint64_t z = (uint64_t)x * y;
+    *ret = z;
+    return z > UINT32_MAX;
+#endif
+}
+
+/**
+ * umul64_overflow - multiplication with overflow indication
+ * @x, @y: Input multipliers
+ * @ret: Output for product
+ *
+ * Computes *@ret = @x * @y, and returns true if and only if that
+ * value has been truncated.
+ */
+static inline bool umul64_overflow(uint64_t x, uint64_t y, uint64_t *ret)
+{
+#if __has_builtin(__builtin_mul_overflow) || __GNUC__ >= 5
+    return __builtin_mul_overflow(x, y, ret);
+#else
+    uint64_t hi;
+    mulu64(ret, &hi, x, y);
+    return hi != 0;
+#endif
+}
+
+/**
+ * uadd64_carry - addition with carry-in and carry-out
+ * @x, @y: addends
+ * @pcarry: in-out carry value
+ *
+ * Computes @x + @y + *@pcarry, placing the carry-out back
+ * into *@pcarry and returning the 64-bit sum.
+ */
+static inline uint64_t uadd64_carry(uint64_t x, uint64_t y, bool *pcarry)
+{
+#if __has_builtin(__builtin_addcll)
+    unsigned long long c = *pcarry;
+    x = __builtin_addcll(x, y, c, &c);
+    *pcarry = c & 1;
+    return x;
+#else
+    bool c = *pcarry;
+    /* This is clang's internal expansion of __builtin_addc. */
+    c = uadd64_overflow(x, c, &x);
+    c |= uadd64_overflow(x, y, &x);
+    *pcarry = c;
+    return x;
+#endif
+}
+
+/**
+ * usub64_borrow - subtraction with borrow-in and borrow-out
+ * @x, @y: addends
+ * @pborrow: in-out borrow value
+ *
+ * Computes @x - @y - *@pborrow, placing the borrow-out back
+ * into *@pborrow and returning the 64-bit sum.
+ */
+static inline uint64_t usub64_borrow(uint64_t x, uint64_t y, bool *pborrow)
+{
+#if __has_builtin(__builtin_subcll)
+    unsigned long long b = *pborrow;
+    x = __builtin_subcll(x, y, b, &b);
+    *pborrow = b & 1;
+    return x;
+#else
+    bool b = *pborrow;
+    b = usub64_overflow(x, b, &x);
+    b |= usub64_overflow(x, y, &x);
+    *pborrow = b;
+    return x;
+#endif
 }
 
 /* Host type specific sizes of these routines.  */