Merge tag 'pull-ppc-20220621' of https://gitlab.com/danielhb/qemu into staging

ppc patch queue for 2022-06-21:

- tcg and target/ppc: vector divide instructions and a vbpermd fix for
  BE hosts
- ppc440_uc.c: fix boot of sam460ex machine
- target/ppc: fix stop state on cpu reset
- xive2: Access direct mapped thread contexts from all chips
- a couple of Coverity fixes

# -----BEGIN PGP SIGNATURE-----
#
# iHUEABYKAB0WIQQX6/+ZI9AYAK8oOBk82cqW3gMxZAUCYrGSLAAKCRA82cqW3gMx
# ZEL/AQDhEUUaztu+AWwnPKFZOP9VBU6vO2UIxZF1GHDRnoNlLQD+O6uADnIuxpxl
# klUMX8h2RFIkC0zv6xGN285SzhzpyAw=
# =/2K2
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 21 Jun 2022 02:41:00 AM PDT
# gpg:                using EDDSA key 17EBFF9923D01800AF2838193CD9CA96DE033164
# gpg: Good signature from "Daniel Henrique Barboza <danielhb413@gmail.com>" [unknown]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 17EB FF99 23D0 1800 AF28  3819 3CD9 CA96 DE03 3164

* tag 'pull-ppc-20220621' of https://gitlab.com/danielhb/qemu:
  target/ppc: cpu_init: Clean up stop state on cpu reset
  target/ppc: fix unreachable code in fpu_helper.c
  target/ppc: avoid int32 multiply overflow in int_helper.c
  ppc/pnv: fix extra indent spaces with DEFINE_PROP*
  pnv/xive2: Access direct mapped thread contexts from all chips
  target/ppc: fix vbpermd in big endian hosts
  ppc: fix boot with sam460ex
  target/ppc: Implemented vector module quadword
  target/ppc: Implemented vector module word/doubleword
  target/ppc: Implemented remaining vector divide extended
  host-utils: Implemented signed 256-by-128 division
  host-utils: Implemented unsigned 256-by-128 division
  target/ppc: Implemented vector divide extended word
  target/ppc: Implemented vector divide quadword
  target/ppc: Implemented vector divide instructions

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

1 files changed, 180 insertions, 0 deletions

diff --git a/util/host-utils.c b/util/host-utils.c
index 96d5dc0..fb91bcb 100644
--- a/util/host-utils.c
+++ b/util/host-utils.c
@@ -266,3 +266,183 @@ void ulshift(uint64_t *plow, uint64_t *phigh, int32_t shift, bool *overflow)
         *plow = *plow << shift;
     }
 }
+
+/*
+ * Unsigned 256-by-128 division.
+ * Returns the remainder via r.
+ * Returns lower 128 bit of quotient.
+ * Needs a normalized divisor (most significant bit set to 1).
+ *
+ * Adapted from include/qemu/host-utils.h udiv_qrnnd,
+ * from the GNU Multi Precision Library - longlong.h __udiv_qrnnd
+ * (https://gmplib.org/repo/gmp/file/tip/longlong.h)
+ *
+ * Licensed under the GPLv2/LGPLv3
+ */
+static Int128 udiv256_qrnnd(Int128 *r, Int128 n1, Int128 n0, Int128 d)
+{
+    Int128 d0, d1, q0, q1, r1, r0, m;
+    uint64_t mp0, mp1;
+
+    d0 = int128_make64(int128_getlo(d));
+    d1 = int128_make64(int128_gethi(d));
+
+    r1 = int128_remu(n1, d1);
+    q1 = int128_divu(n1, d1);
+    mp0 = int128_getlo(q1);
+    mp1 = int128_gethi(q1);
+    mulu128(&mp0, &mp1, int128_getlo(d0));
+    m = int128_make128(mp0, mp1);
+    r1 = int128_make128(int128_gethi(n0), int128_getlo(r1));
+    if (int128_ult(r1, m)) {
+        q1 = int128_sub(q1, int128_one());
+        r1 = int128_add(r1, d);
+        if (int128_uge(r1, d)) {
+            if (int128_ult(r1, m)) {
+                q1 = int128_sub(q1, int128_one());
+                r1 = int128_add(r1, d);
+            }
+        }
+    }
+    r1 = int128_sub(r1, m);
+
+    r0 = int128_remu(r1, d1);
+    q0 = int128_divu(r1, d1);
+    mp0 = int128_getlo(q0);
+    mp1 = int128_gethi(q0);
+    mulu128(&mp0, &mp1, int128_getlo(d0));
+    m = int128_make128(mp0, mp1);
+    r0 = int128_make128(int128_getlo(n0), int128_getlo(r0));
+    if (int128_ult(r0, m)) {
+        q0 = int128_sub(q0, int128_one());
+        r0 = int128_add(r0, d);
+        if (int128_uge(r0, d)) {
+            if (int128_ult(r0, m)) {
+                q0 = int128_sub(q0, int128_one());
+                r0 = int128_add(r0, d);
+            }
+        }
+    }
+    r0 = int128_sub(r0, m);
+
+    *r = r0;
+    return int128_or(int128_lshift(q1, 64), q0);
+}
+
+/*
+ * Unsigned 256-by-128 division.
+ * Returns the remainder.
+ * Returns quotient via plow and phigh.
+ * Also returns the remainder via the function return value.
+ */
+Int128 divu256(Int128 *plow, Int128 *phigh, Int128 divisor)
+{
+    Int128 dhi = *phigh;
+    Int128 dlo = *plow;
+    Int128 rem, dhighest;
+    int sh;
+
+    if (!int128_nz(divisor) || !int128_nz(dhi)) {
+        *plow  = int128_divu(dlo, divisor);
+        *phigh = int128_zero();
+        return int128_remu(dlo, divisor);
+    } else {
+        sh = clz128(divisor);
+
+        if (int128_ult(dhi, divisor)) {
+            if (sh != 0) {
+                /* normalize the divisor, shifting the dividend accordingly */
+                divisor = int128_lshift(divisor, sh);
+                dhi = int128_or(int128_lshift(dhi, sh),
+                                int128_urshift(dlo, (128 - sh)));
+                dlo = int128_lshift(dlo, sh);
+            }
+
+            *phigh = int128_zero();
+            *plow = udiv256_qrnnd(&rem, dhi, dlo, divisor);
+        } else {
+            if (sh != 0) {
+                /* normalize the divisor, shifting the dividend accordingly */
+                divisor = int128_lshift(divisor, sh);
+                dhighest = int128_rshift(dhi, (128 - sh));
+                dhi = int128_or(int128_lshift(dhi, sh),
+                                int128_urshift(dlo, (128 - sh)));
+                dlo = int128_lshift(dlo, sh);
+
+                *phigh = udiv256_qrnnd(&dhi, dhighest, dhi, divisor);
+            } else {
+                /*
+                 * dhi >= divisor
+                 * Since the MSB of divisor is set (sh == 0),
+                 * (dhi - divisor) < divisor
+                 *
+                 * Thus, the high part of the quotient is 1, and we can
+                 * calculate the low part with a single call to udiv_qrnnd
+                 * after subtracting divisor from dhi
+                 */
+                dhi = int128_sub(dhi, divisor);
+                *phigh = int128_one();
+            }
+
+            *plow = udiv256_qrnnd(&rem, dhi, dlo, divisor);
+        }
+
+        /*
+         * since the dividend/divisor might have been normalized,
+         * the remainder might also have to be shifted back
+         */
+        rem = int128_urshift(rem, sh);
+        return rem;
+    }
+}
+
+/*
+ * Signed 256-by-128 division.
+ * Returns quotient via plow and phigh.
+ * Also returns the remainder via the function return value.
+ */
+Int128 divs256(Int128 *plow, Int128 *phigh, Int128 divisor)
+{
+    bool neg_quotient = false, neg_remainder = false;
+    Int128 unsig_hi = *phigh, unsig_lo = *plow;
+    Int128 rem;
+
+    if (!int128_nonneg(*phigh)) {
+        neg_quotient = !neg_quotient;
+        neg_remainder = !neg_remainder;
+
+        if (!int128_nz(unsig_lo)) {
+            unsig_hi = int128_neg(unsig_hi);
+        } else {
+            unsig_hi = int128_not(unsig_hi);
+            unsig_lo = int128_neg(unsig_lo);
+        }
+    }
+
+    if (!int128_nonneg(divisor)) {
+        neg_quotient = !neg_quotient;
+
+        divisor = int128_neg(divisor);
+    }
+
+    rem = divu256(&unsig_lo, &unsig_hi, divisor);
+
+    if (neg_quotient) {
+        if (!int128_nz(unsig_lo)) {
+            *phigh = int128_neg(unsig_hi);
+            *plow = int128_zero();
+        } else {
+            *phigh = int128_not(unsig_hi);
+            *plow = int128_neg(unsig_lo);
+        }
+    } else {
+        *phigh = unsig_hi;
+        *plow = unsig_lo;
+    }
+
+    if (neg_remainder) {
+        return int128_neg(rem);
+    } else {
+        return rem;
+    }
+}