target/i386: fix ADOX followed by ADCX

When ADCX is followed by ADOX or vice versa, the second instruction's
carry comes from EFLAGS and the condition codes use the CC_OP_ADCOX
operation.  Retrieving the carry from EFLAGS is handled by this bit
of gen_ADCOX:

        tcg_gen_extract_tl(carry_in, cpu_cc_src,
            ctz32(cc_op == CC_OP_ADCX ? CC_C : CC_O), 1);

Unfortunately, in this case cc_op has been overwritten by the previous
"if" statement to CC_OP_ADCOX.  This works by chance when the first
instruction is ADCX; however, if the first instruction is ADOX,
ADCX will incorrectly take its carry from OF instead of CF.

Fix by moving the computation of the new cc_op at the end of the function.
The included exhaustive test case fails without this patch and passes
afterwards.

Because ADCX/ADOX need not be invoked through the VEX prefix, this
regression bisects to commit 16fc5726a6e2 ("target/i386: reimplement
0x0f 0x38, add AVX", 2022-10-18).  However, the mistake happened a
little earlier, when BMI instructions were rewritten using the new
decoder framework.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1471
Reported-by: Paul Jolly <https://gitlab.com/myitcv>
Fixes: 1d0b926150e5 ("target/i386: move scalar 0F 38 and 0F 3A instruction to new decoder", 2022-10-18)
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

2 files changed, 80 insertions, 1 deletions

diff --git a/tests/tcg/i386/Makefile.target b/tests/tcg/i386/Makefile.target
index 81831ca..bafd8c2 100644
--- a/tests/tcg/i386/Makefile.target
+++ b/tests/tcg/i386/Makefile.target
@@ -14,7 +14,7 @@ config-cc.mak: Makefile
 I386_SRCS=$(notdir $(wildcard $(I386_SRC)/*.c))
 ALL_X86_TESTS=$(I386_SRCS:.c=)
 SKIP_I386_TESTS=test-i386-ssse3 test-avx test-3dnow test-mmx
-X86_64_TESTS:=$(filter test-i386-bmi2 $(SKIP_I386_TESTS), $(ALL_X86_TESTS))
+X86_64_TESTS:=$(filter test-i386-adcox test-i386-bmi2 $(SKIP_I386_TESTS), $(ALL_X86_TESTS))
 
 test-i386-sse-exceptions: CFLAGS += -msse4.1 -mfpmath=sse
 run-test-i386-sse-exceptions: QEMU_OPTS += -cpu max
@@ -28,6 +28,10 @@ test-i386-bmi2: CFLAGS=-O2
 run-test-i386-bmi2: QEMU_OPTS += -cpu max
 run-plugin-test-i386-bmi2-%: QEMU_OPTS += -cpu max
 
+test-i386-adcox: CFLAGS=-O2
+run-test-i386-adcox: QEMU_OPTS += -cpu max
+run-plugin-test-i386-adcox-%: QEMU_OPTS += -cpu max
+
 #
 # hello-i386 is a barebones app
 #
diff --git a/tests/tcg/i386/test-i386-adcox.c b/tests/tcg/i386/test-i386-adcox.c
new file mode 100644
index 0000000..16169ef
--- /dev/null
+++ b/tests/tcg/i386/test-i386-adcox.c
@@ -0,0 +1,75 @@
+/* See if various BMI2 instructions give expected results */
+#include <assert.h>
+#include <stdint.h>
+#include <stdio.h>
+
+#define CC_C 1
+#define CC_O (1 << 11)
+
+#ifdef __x86_64__
+#define REG uint64_t
+#else
+#define REG uint32_t
+#endif
+
+void test_adox_adcx(uint32_t in_c, uint32_t in_o, REG adcx_operand, REG adox_operand)
+{
+    REG flags;
+    REG out_adcx, out_adox;
+
+    asm("pushf; pop %0" : "=r"(flags));
+    flags &= ~(CC_C | CC_O);
+    flags |= (in_c ? CC_C : 0);
+    flags |= (in_o ? CC_O : 0);
+
+    out_adcx = adcx_operand;
+    out_adox = adox_operand;
+    asm("push %0; popf;"
+        "adox %3, %2;"
+        "adcx %3, %1;"
+        "pushf; pop %0"
+        : "+r" (flags), "+r" (out_adcx), "+r" (out_adox)
+        : "r" ((REG)-1), "0" (flags), "1" (out_adcx), "2" (out_adox));
+
+    assert(out_adcx == in_c + adcx_operand - 1);
+    assert(out_adox == in_o + adox_operand - 1);
+    assert(!!(flags & CC_C) == (in_c || adcx_operand));
+    assert(!!(flags & CC_O) == (in_o || adox_operand));
+}
+
+void test_adcx_adox(uint32_t in_c, uint32_t in_o, REG adcx_operand, REG adox_operand)
+{
+    REG flags;
+    REG out_adcx, out_adox;
+
+    asm("pushf; pop %0" : "=r"(flags));
+    flags &= ~(CC_C | CC_O);
+    flags |= (in_c ? CC_C : 0);
+    flags |= (in_o ? CC_O : 0);
+
+    out_adcx = adcx_operand;
+    out_adox = adox_operand;
+    asm("push %0; popf;"
+        "adcx %3, %1;"
+        "adox %3, %2;"
+        "pushf; pop %0"
+        : "+r" (flags), "+r" (out_adcx), "+r" (out_adox)
+        : "r" ((REG)-1), "0" (flags), "1" (out_adcx), "2" (out_adox));
+
+    assert(out_adcx == in_c + adcx_operand - 1);
+    assert(out_adox == in_o + adox_operand - 1);
+    assert(!!(flags & CC_C) == (in_c || adcx_operand));
+    assert(!!(flags & CC_O) == (in_o || adox_operand));
+}
+
+int main(int argc, char *argv[]) {
+    /* try all combinations of input CF, input OF, CF from op1+op2,  OF from op2+op1 */
+    int i;
+    for (i = 0; i <= 15; i++) {
+        printf("%d\n", i);
+        test_adcx_adox(!!(i & 1), !!(i & 2), !!(i & 4), !!(i & 8));
+        test_adox_adcx(!!(i & 1), !!(i & 2), !!(i & 4), !!(i & 8));
+    }
+    return 0;
+}
+