Merge tag 'pull-tcg-20230204' of https://gitlab.com/rth7680/qemu into staging

tcg: Add support for TCGv_i128 in parameters and returns.
tcg: Add support for TCGv_i128 in cmpxchg.
tcg: Test CPUJumpCache in tb_jmp_cache_clear_page
tcg: Split out tcg_gen_nonatomic_cmpxchg_i{32,64}
tcg/aarch64: Fix patching of LDR in tb_target_set_jmp_target
target/arm: Use tcg_gen_atomic_cmpxchg_i128
target/i386: Use tcg_gen_atomic_cmpxchg_i128
target/i386: Use tcg_gen_nonatomic_cmpxchg_i{32,64}
target/s390x: Use tcg_gen_atomic_cmpxchg_i128
target/s390x: Use TCGv_i128 in passing and returning float128
target/s390x: Implement CC_OP_NZ in gen_op_calc_cc

# -----BEGIN PGP SIGNATURE-----
#
# iQFRBAABCgA7FiEEekgeeIaLTbaoWgXAZN846K9+IV8FAmPeiDYdHHJpY2hhcmQu
# aGVuZGVyc29uQGxpbmFyby5vcmcACgkQZN846K9+IV+hFQf+K1MkEK1wtpjnqrYD
# 4l36Uo3B7w8Yi6FxbCx9NP78dJNNTjTn0zqhtISRKSzI7TGUCGnmQs40iqYrRe5S
# 9x6LJgTJplI2dsANvtsTaWB5gNzhowPt5tlit+J6Q0POwvvwcBZAOumY8AYt1YP+
# dMsjBLw6HFaqSCU5IERZrB4kBwl61VTkTAtHL2utSZpdsOYoc3y2hzbJ/w3kLK2u
# YXnMvom+Gc1rvQTaSMgiPYFITyx/VtXDe+JQwNikpu7Na+RFjtu7cHmg/BtZFo6s
# 15AsAS8JlENKAunpJiX41UR7SxB8MdyQL5LyjVNWo5F7+YgQuuO1gqYKt6qUwd+A
# oH2uBA==
# =xjMy
# -----END PGP SIGNATURE-----
# gpg: Signature made Sat 04 Feb 2023 16:30:46 GMT
# 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

* tag 'pull-tcg-20230204' of https://gitlab.com/rth7680/qemu: (40 commits)
  tcg/aarch64: Fix patching of LDR in tb_target_set_jmp_target
  target/i386: Inline cmpxchg16b
  target/i386: Inline cmpxchg8b
  target/i386: Split out gen_cmpxchg8b, gen_cmpxchg16b
  target/s390x: Implement CC_OP_NZ in gen_op_calc_cc
  target/s390x: Use tcg_gen_atomic_cmpxchg_i128 for CDSG
  target/s390x: Use Int128 for passing float128
  target/s390x: Use Int128 for returning float128
  target/s390x: Copy wout_x1 to wout_x1_P
  target/s390x: Use Int128 for return from TRE
  target/s390x: Use Int128 for return from CKSM
  target/s390x: Use Int128 for return from CLST
  target/s390x: Use a single return for helper_divs64/u64
  target/s390x: Use a single return for helper_divs32/u32
  tests/tcg/s390x: Add cdsg.c
  tests/tcg/s390x: Add long-double.c
  tests/tcg/s390x: Add clst.c
  tests/tcg/s390x: Add div.c
  target/ppc: Use tcg_gen_atomic_cmpxchg_i128 for STQCX
  target/arm: Use tcg_gen_atomic_cmpxchg_i128 for CASP
  ...

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

5 files changed, 281 insertions, 0 deletions

diff --git a/tests/tcg/s390x/Makefile.target b/tests/tcg/s390x/Makefile.target
index 07fcc6d..72ad309 100644
--- a/tests/tcg/s390x/Makefile.target
+++ b/tests/tcg/s390x/Makefile.target
@@ -24,6 +24,13 @@ TESTS+=trap
 TESTS+=signals-s390x
 TESTS+=branch-relative-long
 TESTS+=noexec
+TESTS+=div
+TESTS+=clst
+TESTS+=long-double
+TESTS+=cdsg
+
+cdsg: CFLAGS+=-pthread
+cdsg: LDFLAGS+=-pthread
 
 Z13_TESTS=vistr
 $(Z13_TESTS): CFLAGS+=-march=z13 -O2
diff --git a/tests/tcg/s390x/cdsg.c b/tests/tcg/s390x/cdsg.c
new file mode 100644
index 0000000..800618f
--- /dev/null
+++ b/tests/tcg/s390x/cdsg.c
@@ -0,0 +1,93 @@
+/*
+ * Test CDSG instruction.
+ *
+ * Increment the first half of aligned_quadword by 1, and the second half by 2
+ * from 2 threads. Verify that the result is consistent.
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+#include <assert.h>
+#include <pthread.h>
+#include <stdbool.h>
+#include <stdlib.h>
+
+static volatile bool start;
+typedef unsigned long aligned_quadword[2] __attribute__((__aligned__(16)));
+static aligned_quadword val;
+static const int n_iterations = 1000000;
+
+static inline int cdsg(unsigned long *orig0, unsigned long *orig1,
+                       unsigned long new0, unsigned long new1,
+                       aligned_quadword *mem)
+{
+    register unsigned long r0 asm("r0");
+    register unsigned long r1 asm("r1");
+    register unsigned long r2 asm("r2");
+    register unsigned long r3 asm("r3");
+    int cc;
+
+    r0 = *orig0;
+    r1 = *orig1;
+    r2 = new0;
+    r3 = new1;
+    asm("cdsg %[r0],%[r2],%[db2]\n"
+        "ipm %[cc]"
+        : [r0] "+r" (r0)
+        , [r1] "+r" (r1)
+        , [db2] "+m" (*mem)
+        , [cc] "=r" (cc)
+        : [r2] "r" (r2)
+        , [r3] "r" (r3)
+        : "cc");
+    *orig0 = r0;
+    *orig1 = r1;
+
+    return (cc >> 28) & 3;
+}
+
+void *cdsg_loop(void *arg)
+{
+    unsigned long orig0, orig1, new0, new1;
+    int cc;
+    int i;
+
+    while (!start) {
+    }
+
+    orig0 = val[0];
+    orig1 = val[1];
+    for (i = 0; i < n_iterations;) {
+        new0 = orig0 + 1;
+        new1 = orig1 + 2;
+
+        cc = cdsg(&orig0, &orig1, new0, new1, &val);
+
+        if (cc == 0) {
+            orig0 = new0;
+            orig1 = new1;
+            i++;
+        } else {
+            assert(cc == 1);
+        }
+    }
+
+    return NULL;
+}
+
+int main(void)
+{
+    pthread_t thread;
+    int ret;
+
+    ret = pthread_create(&thread, NULL, cdsg_loop, NULL);
+    assert(ret == 0);
+    start = true;
+    cdsg_loop(NULL);
+    ret = pthread_join(thread, NULL);
+    assert(ret == 0);
+
+    assert(val[0] == n_iterations * 2);
+    assert(val[1] == n_iterations * 4);
+
+    return EXIT_SUCCESS;
+}
diff --git a/tests/tcg/s390x/clst.c b/tests/tcg/s390x/clst.c
new file mode 100644
index 0000000..ed2fe73
--- /dev/null
+++ b/tests/tcg/s390x/clst.c
@@ -0,0 +1,82 @@
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+
+static int clst(char sep, const char **s1, const char **s2)
+{
+    const char *r1 = *s1;
+    const char *r2 = *s2;
+    int cc;
+
+    do {
+        register int r0 asm("r0") = sep;
+
+        asm("clst %[r1],%[r2]\n"
+            "ipm %[cc]\n"
+            "srl %[cc],28"
+            : [r1] "+r" (r1), [r2] "+r" (r2), "+r" (r0), [cc] "=r" (cc)
+            :
+            : "cc");
+        *s1 = r1;
+        *s2 = r2;
+    } while (cc == 3);
+
+    return cc;
+}
+
+static const struct test {
+    const char *name;
+    char sep;
+    const char *s1;
+    const char *s2;
+    int exp_cc;
+    int exp_off;
+} tests[] = {
+    {
+        .name = "cc0",
+        .sep = 0,
+        .s1 = "aa",
+        .s2 = "aa",
+        .exp_cc = 0,
+        .exp_off = 0,
+    },
+    {
+        .name = "cc1",
+        .sep = 1,
+        .s1 = "a\x01",
+        .s2 = "aa\x01",
+        .exp_cc = 1,
+        .exp_off = 1,
+    },
+    {
+        .name = "cc2",
+        .sep = 2,
+        .s1 = "abc\x02",
+        .s2 = "abb\x02",
+        .exp_cc = 2,
+        .exp_off = 2,
+    },
+};
+
+int main(void)
+{
+    const struct test *t;
+    const char *s1, *s2;
+    size_t i;
+    int cc;
+
+    for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) {
+        t = &tests[i];
+        s1 = t->s1;
+        s2 = t->s2;
+        cc = clst(t->sep, &s1, &s2);
+        if (cc != t->exp_cc ||
+                s1 != t->s1 + t->exp_off ||
+                s2 != t->s2 + t->exp_off) {
+            fprintf(stderr, "%s\n", t->name);
+            return EXIT_FAILURE;
+        }
+    }
+
+    return EXIT_SUCCESS;
+}
diff --git a/tests/tcg/s390x/div.c b/tests/tcg/s390x/div.c
new file mode 100644
index 0000000..6ad9900
--- /dev/null
+++ b/tests/tcg/s390x/div.c
@@ -0,0 +1,75 @@
+#include <assert.h>
+#include <stdint.h>
+
+static void test_dr(void)
+{
+    register int32_t r0 asm("r0") = -1;
+    register int32_t r1 asm("r1") = -4241;
+    int32_t b = 101, q, r;
+
+    asm("dr %[r0],%[b]"
+        : [r0] "+r" (r0), [r1] "+r" (r1)
+        : [b] "r" (b)
+        : "cc");
+    q = r1;
+    r = r0;
+    assert(q == -41);
+    assert(r == -100);
+}
+
+static void test_dlr(void)
+{
+    register uint32_t r0 asm("r0") = 0;
+    register uint32_t r1 asm("r1") = 4243;
+    uint32_t b = 101, q, r;
+
+    asm("dlr %[r0],%[b]"
+        : [r0] "+r" (r0), [r1] "+r" (r1)
+        : [b] "r" (b)
+        : "cc");
+    q = r1;
+    r = r0;
+    assert(q == 42);
+    assert(r == 1);
+}
+
+static void test_dsgr(void)
+{
+    register int64_t r0 asm("r0") = -1;
+    register int64_t r1 asm("r1") = -4241;
+    int64_t b = 101, q, r;
+
+    asm("dsgr %[r0],%[b]"
+        : [r0] "+r" (r0), [r1] "+r" (r1)
+        : [b] "r" (b)
+        : "cc");
+    q = r1;
+    r = r0;
+    assert(q == -41);
+    assert(r == -100);
+}
+
+static void test_dlgr(void)
+{
+    register uint64_t r0 asm("r0") = 0;
+    register uint64_t r1 asm("r1") = 4243;
+    uint64_t b = 101, q, r;
+
+    asm("dlgr %[r0],%[b]"
+        : [r0] "+r" (r0), [r1] "+r" (r1)
+        : [b] "r" (b)
+        : "cc");
+    q = r1;
+    r = r0;
+    assert(q == 42);
+    assert(r == 1);
+}
+
+int main(void)
+{
+    test_dr();
+    test_dlr();
+    test_dsgr();
+    test_dlgr();
+    return 0;
+}
diff --git a/tests/tcg/s390x/long-double.c b/tests/tcg/s390x/long-double.c
new file mode 100644
index 0000000..757a626
--- /dev/null
+++ b/tests/tcg/s390x/long-double.c
@@ -0,0 +1,24 @@
+/*
+ * Perform some basic arithmetic with long double, as a sanity check.
+ * With small integral numbers, we can cross-check with integers.
+ */
+
+#include <assert.h>
+
+int main()
+{
+    int i, j;
+
+    for (i = 1; i < 5; i++) {
+        for (j = 1; j < 5; j++) {
+            long double la = (long double)i + j;
+            long double lm = (long double)i * j;
+            long double ls = (long double)i - j;
+
+            assert(la == i + j);
+            assert(lm == i * j);
+            assert(ls == i - j);
+        }
+    }
+    return 0;
+}