[PULL 001/113] target/i386: fix operand order for PDEP and PEXT

[Paolo Bonzini]

For PDEP and PEXT, the mask is provided in the memory (mod+r/m)
operand, and therefore is loaded in s->T0 by gen_ldst_modrm.
The source is provided in the second source operand (VEX.vvvv)
and therefore is loaded in s->T1.  Fix the order in which
they are passed to the helpers.

Reported-by: Lenard Szolnoki <blog@lenardszolnoki.com>
Analyzed-by: Lenard Szolnoki <blog@lenardszolnoki.com>
Fixes: https://bugs.launchpad.net/qemu/+bug/1605123
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 target/i386/translate.c         |  8 +++----
 tests/tcg/i386/Makefile.target  |  3 +++
 tests/tcg/i386/test-i386-bmi2.c | 41 +++++++++++++++++++++++++++++++++
 3 files changed, 48 insertions(+), 4 deletions(-)
 create mode 100644 tests/tcg/i386/test-i386-bmi2.c

diff --git a/target/i386/translate.c b/target/i386/translate.c
index 4c57307e42..e8f5f5803a 100644
--- a/target/i386/translate.c
+++ b/target/i386/translate.c
@@ -3936,14 +3936,14 @@ static void gen_sse(CPUX86State *env, DisasContext *s, 
int b,
                 }
                 ot = mo_64_32(s->dflag);
                 gen_ldst_modrm(env, s, modrm, ot, OR_TMP0, 0);
-                /* Note that by zero-extending the mask operand, we
+                /* Note that by zero-extending the source operand, we
                    automatically handle zero-extending the result.  */
                 if (ot == MO_64) {
                     tcg_gen_mov_tl(s->T1, cpu_regs[s->vex_v]);
                 } else {
                     tcg_gen_ext32u_tl(s->T1, cpu_regs[s->vex_v]);
                 }
-                gen_helper_pdep(cpu_regs[reg], s->T0, s->T1);
+                gen_helper_pdep(cpu_regs[reg], s->T1, s->T0);
                 break;
 
             case 0x2f5: /* pext Gy, By, Ey */
@@ -3954,14 +3954,14 @@ static void gen_sse(CPUX86State *env, DisasContext *s, 
int b,
                 }
                 ot = mo_64_32(s->dflag);
                 gen_ldst_modrm(env, s, modrm, ot, OR_TMP0, 0);
-                /* Note that by zero-extending the mask operand, we
+                /* Note that by zero-extending the source operand, we
                    automatically handle zero-extending the result.  */
                 if (ot == MO_64) {
                     tcg_gen_mov_tl(s->T1, cpu_regs[s->vex_v]);
                 } else {
                     tcg_gen_ext32u_tl(s->T1, cpu_regs[s->vex_v]);
                 }
-                gen_helper_pext(cpu_regs[reg], s->T0, s->T1);
+                gen_helper_pext(cpu_regs[reg], s->T1, s->T0);
                 break;
 
             case 0x1f6: /* adcx Gy, Ey */
diff --git a/tests/tcg/i386/Makefile.target b/tests/tcg/i386/Makefile.target
index a66232a67d..ad187cb2c9 100644
--- a/tests/tcg/i386/Makefile.target
+++ b/tests/tcg/i386/Makefile.target
@@ -18,6 +18,9 @@ test-i386-pcmpistri: CFLAGS += -msse4.2
 run-test-i386-pcmpistri: QEMU_OPTS += -cpu max
 run-plugin-test-i386-pcmpistri-%: QEMU_OPTS += -cpu max
 
+run-test-i386-bmi2: QEMU_OPTS += -cpu max
+run-plugin-test-i386-bmi2-%: QEMU_OPTS += -cpu max
+
 #
 # hello-i386 is a barebones app
 #
diff --git a/tests/tcg/i386/test-i386-bmi2.c b/tests/tcg/i386/test-i386-bmi2.c
new file mode 100644
index 0000000000..b61f05b69e
--- /dev/null
+++ b/tests/tcg/i386/test-i386-bmi2.c
@@ -0,0 +1,41 @@
+/* See if various BMI2 instructions give expected results */
+#include <assert.h>
+#include <stdint.h>
+
+int main(int argc, char *argv[]) {
+    uint64_t ehlo = 0x202020204f4c4845ull;
+    uint64_t mask = 0xa080800302020001ull;
+    uint64_t result64;
+    uint32_t result32;
+
+#ifdef __x86_64
+    /* 64 bits */
+    asm volatile ("pextq   %2, %1, %0" : "=r"(result64) : "r"(ehlo), 
"m"(mask));
+    assert(result64 == 133);
+
+    asm volatile ("pdepq   %2, %1, %0" : "=r"(result64) : "r"(result64), 
"m"(mask));
+    assert(result64 == (ehlo & mask));
+
+    asm volatile ("pextq   %2, %1, %0" : "=r"(result64) : "r"(-1ull), 
"m"(mask));
+    assert(result64 == 511); /* mask has 9 bits set */
+
+    asm volatile ("pdepq   %2, %1, %0" : "=r"(result64) : "r"(-1ull), 
"m"(mask));
+    assert(result64 == mask);
+#endif
+
+    /* 32 bits */
+    asm volatile ("pextl   %2, %k1, %k0" : "=r"(result32) : "r"((uint32_t) 
ehlo), "m"(mask));
+    assert(result32 == 5);
+
+    asm volatile ("pdepl   %2, %k1, %k0" : "=r"(result32) : "r"(result32), 
"m"(mask));
+    assert(result32 == (uint32_t)(ehlo & mask));
+
+    asm volatile ("pextl   %2, %k1, %k0" : "=r"(result32) : "r"(-1ull), 
"m"(mask));
+    assert(result32 == 7); /* mask has 3 bits set */
+
+    asm volatile ("pdepl   %2, %k1, %k0" : "=r"(result32) : "r"(-1ull), 
"m"(mask));
+    assert(result32 == (uint32_t)mask);
+
+    return 0;
+}
+
-- 
2.26.2