x86_emulate: properly do IP updates and other side effects on success

The two MMX/SSE/AVX code blocks failed to update IP properly, and these
as well as get_reg_refix(), which "manually" updated IP so far, failed
to do the TF and RF processing needed at the end of successfully
emulated instructions.

Fix the test utility at once to check IP is properly getting updated,
and while at it macroize the respective code quite a bit, hopefully
making it easier to add further tests when the need arises.

Reported-by: Andrei LUTAS <vlutas@bitdefender.com>
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Tested-by: Razvan Cojocaru <rcojocaru@bitdefender.com>
Reviewed-by: Andrew Cooper <andrew.cooper@citrix.com>
master commit: 3af450fd2d9403f208d3ac6459716f027b8597ad
master date: 2014-08-08 09:34:03 +0200

diff --git a/tools/tests/x86_emulator/test_x86_emulator.c b/tools/tests/x86_emulator/test_x86_emulator.c
index 8af30be7ffc878d2034f3d44bb2777de9df2c128..0773557ddf2d6e7fc131ecf2c8e8360f9a0b3701 100644 (file)
--- a/tools/tests/x86_emulator/test_x86_emulator.c
+++ b/tools/tests/x86_emulator/test_x86_emulator.c
@@ -541,23 +541,32 @@ int main(int argc, char **argv)
     printf("skipped\n");
 #endif
 
+#define decl_insn(which) extern const unsigned char which[], which##_len[]
+#define put_insn(which, insn) ".pushsection .test, \"ax\", @progbits\n" \
+                              #which ": " insn "\n"                     \
+                              ".equ " #which "_len, .-" #which "\n"     \
+                              ".popsection"
+#define set_insn(which) (regs.eip = (unsigned long)memcpy(instr, which, \
+                                             (unsigned long)which##_len))
+#define check_eip(which) (regs.eip == (unsigned long)instr + \
+                                      (unsigned long)which##_len)
+
     printf("%-40s", "Testing movq %mm3,(%ecx)...");
     if ( stack_exec && cpu_has_mmx )
     {
-        extern const unsigned char movq_to_mem[];
+        decl_insn(movq_to_mem);
 
         asm volatile ( "pcmpeqb %%mm3, %%mm3\n"
-                       ".pushsection .test, \"a\", @progbits\n"
-                       "movq_to_mem: movq %%mm3, (%0)\n"
-                       ".popsection" :: "c" (NULL) );
+                       put_insn(movq_to_mem, "movq %%mm3, (%0)")
+                       :: "c" (NULL) );
 
-        memcpy(instr, movq_to_mem, 15);
+        set_insn(movq_to_mem);
         memset(res, 0x33, 64);
         memset(res + 8, 0xff, 8);
-        regs.eip    = (unsigned long)&instr[0];
         regs.ecx    = (unsigned long)res;
         rc = x86_emulate(&ctxt, &emulops);
-        if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 8, 32) )
+        if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 8, 32) ||
+             !check_eip(movq_to_mem) )
             goto fail;
         printf("okay\n");
     }
@@ -567,19 +576,17 @@ int main(int argc, char **argv)
     printf("%-40s", "Testing movq (%edx),%mm5...");
     if ( stack_exec && cpu_has_mmx )
     {
-        extern const unsigned char movq_from_mem[];
+        decl_insn(movq_from_mem);
 
         asm volatile ( "pcmpgtb %%mm5, %%mm5\n"
-                       ".pushsection .test, \"a\", @progbits\n"
-                       "movq_from_mem: movq (%0), %%mm5\n"
-                       ".popsection" :: "d" (NULL) );
+                       put_insn(movq_from_mem, "movq (%0), %%mm5")
+                       :: "d" (NULL) );
 
-        memcpy(instr, movq_from_mem, 15);
-        regs.eip    = (unsigned long)&instr[0];
+        set_insn(movq_from_mem);
         regs.ecx    = 0;
         regs.edx    = (unsigned long)res;
         rc = x86_emulate(&ctxt, &emulops);
-        if ( rc != X86EMUL_OKAY )
+        if ( rc != X86EMUL_OKAY || !check_eip(movq_from_mem) )
             goto fail;
         asm ( "pcmpeqb %%mm3, %%mm3\n\t"
               "pcmpeqb %%mm5, %%mm3\n\t"
@@ -594,20 +601,19 @@ int main(int argc, char **argv)
     printf("%-40s", "Testing movdqu %xmm2,(%ecx)...");
     if ( stack_exec && cpu_has_sse2 )
     {
-        extern const unsigned char movdqu_to_mem[];
+        decl_insn(movdqu_to_mem);
 
         asm volatile ( "pcmpeqb %%xmm2, %%xmm2\n"
-                       ".pushsection .test, \"a\", @progbits\n"
-                       "movdqu_to_mem: movdqu %%xmm2, (%0)\n"
-                       ".popsection" :: "c" (NULL) );
+                       put_insn(movdqu_to_mem, "movdqu %%xmm2, (%0)")
+                       :: "c" (NULL) );
 
-        memcpy(instr, movdqu_to_mem, 15);
+        set_insn(movdqu_to_mem);
         memset(res, 0x55, 64);
         memset(res + 8, 0xff, 16);
-        regs.eip    = (unsigned long)&instr[0];
         regs.ecx    = (unsigned long)res;
         rc = x86_emulate(&ctxt, &emulops);
-        if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 8, 32) )
+        if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 8, 32) ||
+             !check_eip(movdqu_to_mem) )
             goto fail;
         printf("okay\n");
     }
@@ -617,19 +623,17 @@ int main(int argc, char **argv)
     printf("%-40s", "Testing movdqu (%edx),%xmm4...");
     if ( stack_exec && cpu_has_sse2 )
     {
-        extern const unsigned char movdqu_from_mem[];
+        decl_insn(movdqu_from_mem);
 
         asm volatile ( "pcmpgtb %%xmm4, %%xmm4\n"
-                       ".pushsection .test, \"a\", @progbits\n"
-                       "movdqu_from_mem: movdqu (%0), %%xmm4\n"
-                       ".popsection" :: "d" (NULL) );
+                       put_insn(movdqu_from_mem, "movdqu (%0), %%xmm4")
+                       :: "d" (NULL) );
 
-        memcpy(instr, movdqu_from_mem, 15);
-        regs.eip    = (unsigned long)&instr[0];
+        set_insn(movdqu_from_mem);
         regs.ecx    = 0;
         regs.edx    = (unsigned long)res;
         rc = x86_emulate(&ctxt, &emulops);
-        if ( rc != X86EMUL_OKAY )
+        if ( rc != X86EMUL_OKAY || !check_eip(movdqu_from_mem) )
             goto fail;
         asm ( "pcmpeqb %%xmm2, %%xmm2\n\t"
               "pcmpeqb %%xmm4, %%xmm2\n\t"
@@ -644,21 +648,20 @@ int main(int argc, char **argv)
     printf("%-40s", "Testing vmovdqu %ymm2,(%ecx)...");
     if ( stack_exec && cpu_has_avx )
     {
-        extern const unsigned char vmovdqu_to_mem[];
+        decl_insn(vmovdqu_to_mem);
 
         asm volatile ( "vpcmpeqb %%xmm2, %%xmm2, %%xmm2\n"
-                       ".pushsection .test, \"a\", @progbits\n"
-                       "vmovdqu_to_mem: vmovdqu %%ymm2, (%0)\n"
-                       ".popsection" :: "c" (NULL) );
+                       put_insn(vmovdqu_to_mem, "vmovdqu %%ymm2, (%0)")
+                       :: "c" (NULL) );
 
-        memcpy(instr, vmovdqu_to_mem, 15);
+        set_insn(vmovdqu_to_mem);
         memset(res, 0x55, 128);
         memset(res + 16, 0xff, 16);
         memset(res + 20, 0x00, 16);
-        regs.eip    = (unsigned long)&instr[0];
         regs.ecx    = (unsigned long)res;
         rc = x86_emulate(&ctxt, &emulops);
-        if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 16, 64) )
+        if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 16, 64) ||
+             !check_eip(vmovdqu_to_mem) )
             goto fail;
         printf("okay\n");
     }
@@ -668,7 +671,7 @@ int main(int argc, char **argv)
     printf("%-40s", "Testing vmovdqu (%edx),%ymm4...");
     if ( stack_exec && cpu_has_avx )
     {
-        extern const unsigned char vmovdqu_from_mem[];
+        decl_insn(vmovdqu_from_mem);
 
 #if 0 /* Don't use AVX2 instructions for now */
         asm volatile ( "vpcmpgtb %%ymm4, %%ymm4, %%ymm4\n"
@@ -676,17 +679,15 @@ int main(int argc, char **argv)
         asm volatile ( "vpcmpgtb %%xmm4, %%xmm4, %%xmm4\n\t"
                        "vinsertf128 $1, %%xmm4, %%ymm4, %%ymm4\n"
 #endif
-                       ".pushsection .test, \"a\", @progbits\n"
-                       "vmovdqu_from_mem: vmovdqu (%0), %%ymm4\n"
-                       ".popsection" :: "d" (NULL) );
+                       put_insn(vmovdqu_from_mem, "vmovdqu (%0), %%ymm4")
+                       :: "d" (NULL) );
 
-        memcpy(instr, vmovdqu_from_mem, 15);
+        set_insn(vmovdqu_from_mem);
         memset(res + 4, 0xff, 16);
-        regs.eip    = (unsigned long)&instr[0];
         regs.ecx    = 0;
         regs.edx    = (unsigned long)res;
         rc = x86_emulate(&ctxt, &emulops);
-        if ( rc != X86EMUL_OKAY )
+        if ( rc != X86EMUL_OKAY || !check_eip(vmovdqu_from_mem) )
             goto fail;
 #if 0 /* Don't use AVX2 instructions for now */
         asm ( "vpcmpeqb %%ymm2, %%ymm2, %%ymm2\n\t"
@@ -713,20 +714,19 @@ int main(int argc, char **argv)
     memset(res + 10, 0x66, 8);
     if ( stack_exec && cpu_has_sse2 )
     {
-        extern const unsigned char movsd_to_mem[];
+        decl_insn(movsd_to_mem);
 
         asm volatile ( "movlpd %0, %%xmm5\n\t"
                        "movhpd %0, %%xmm5\n"
-                       ".pushsection .test, \"a\", @progbits\n"
-                       "movsd_to_mem: movsd %%xmm5, (%1)\n"
-                       ".popsection" :: "m" (res[10]), "c" (NULL) );
+                       put_insn(movsd_to_mem, "movsd %%xmm5, (%1)")
+                       :: "m" (res[10]), "c" (NULL) );
 
-        memcpy(instr, movsd_to_mem, 15);
-        regs.eip    = (unsigned long)&instr[0];
+        set_insn(movsd_to_mem);
         regs.ecx    = (unsigned long)(res + 2);
         regs.edx    = 0;
         rc = x86_emulate(&ctxt, &emulops);
-        if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 8, 32) )
+        if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 8, 32) ||
+             !check_eip(movsd_to_mem) )
             goto fail;
         printf("okay\n");
     }
@@ -739,19 +739,17 @@ int main(int argc, char **argv)
     printf("%-40s", "Testing movaps (%edx),%xmm7...");
     if ( stack_exec && cpu_has_sse )
     {
-        extern const unsigned char movaps_from_mem[];
+        decl_insn(movaps_from_mem);
 
         asm volatile ( "xorps %%xmm7, %%xmm7\n"
-                       ".pushsection .test, \"a\", @progbits\n"
-                       "movaps_from_mem: movaps (%0), %%xmm7\n"
-                       ".popsection" :: "d" (NULL) );
+                       put_insn(movaps_from_mem, "movaps (%0), %%xmm7")
+                       :: "d" (NULL) );
 
-        memcpy(instr, movaps_from_mem, 15);
-        regs.eip    = (unsigned long)&instr[0];
+        set_insn(movaps_from_mem);
         regs.ecx    = 0;
         regs.edx    = (unsigned long)res;
         rc = x86_emulate(&ctxt, &emulops);
-        if ( rc != X86EMUL_OKAY )
+        if ( rc != X86EMUL_OKAY || !check_eip(movaps_from_mem) )
             goto fail;
         asm ( "cmpeqps %1, %%xmm7\n\t"
               "movmskps %%xmm7, %0" : "=r" (rc) : "m" (res[8]) );
@@ -767,19 +765,18 @@ int main(int argc, char **argv)
     memset(res + 10, 0x77, 8);
     if ( stack_exec && cpu_has_avx )
     {
-        extern const unsigned char vmovsd_to_mem[];
+        decl_insn(vmovsd_to_mem);
 
         asm volatile ( "vbroadcastsd %0, %%ymm5\n"
-                       ".pushsection .test, \"a\", @progbits\n"
-                       "vmovsd_to_mem: vmovsd %%xmm5, (%1)\n"
-                       ".popsection" :: "m" (res[10]), "c" (NULL) );
+                       put_insn(vmovsd_to_mem, "vmovsd %%xmm5, (%1)")
+                       :: "m" (res[10]), "c" (NULL) );
 
-        memcpy(instr, vmovsd_to_mem, 15);
-        regs.eip    = (unsigned long)&instr[0];
+        set_insn(vmovsd_to_mem);
         regs.ecx    = (unsigned long)(res + 2);
         regs.edx    = 0;
         rc = x86_emulate(&ctxt, &emulops);
-        if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 8, 32) )
+        if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 8, 32) ||
+             !check_eip(vmovsd_to_mem) )
             goto fail;
         printf("okay\n");
     }
@@ -792,19 +789,17 @@ int main(int argc, char **argv)
     printf("%-40s", "Testing vmovaps (%edx),%ymm7...");
     if ( stack_exec && cpu_has_avx )
     {
-        extern const unsigned char vmovaps_from_mem[];
+        decl_insn(vmovaps_from_mem);
 
         asm volatile ( "vxorps %%ymm7, %%ymm7, %%ymm7\n"
-                       ".pushsection .test, \"a\", @progbits\n"
-                       "vmovaps_from_mem: vmovaps (%0), %%ymm7\n"
-                       ".popsection" :: "d" (NULL) );
+                       put_insn(vmovaps_from_mem, "vmovaps (%0), %%ymm7")
+                       :: "d" (NULL) );
 
-        memcpy(instr, vmovaps_from_mem, 15);
-        regs.eip    = (unsigned long)&instr[0];
+        set_insn(vmovaps_from_mem);
         regs.ecx    = 0;
         regs.edx    = (unsigned long)res;
         rc = x86_emulate(&ctxt, &emulops);
-        if ( rc != X86EMUL_OKAY )
+        if ( rc != X86EMUL_OKAY || !check_eip(vmovaps_from_mem) )
             goto fail;
         asm ( "vcmpeqps %1, %%ymm7, %%ymm0\n\t"
               "vmovmskps %%ymm0, %0" : "=r" (rc) : "m" (res[8]) );
@@ -815,6 +810,11 @@ int main(int argc, char **argv)
     else
         printf("skipped\n");
 
+#undef decl_insn
+#undef put_insn
+#undef set_insn
+#undef check_eip
+
     for ( j = 1; j <= 2; j++ )
     {
 #if defined(__i386__)

diff --git a/xen/arch/x86/x86_emulate/x86_emulate.c b/xen/arch/x86/x86_emulate/x86_emulate.c
index deefdb9072e69510f6f9db76aa5b86e777c9cc64..b0363de550af668a0434ab4bc19752cdf9a88cfb 100644 (file)
--- a/xen/arch/x86/x86_emulate/x86_emulate.c
+++ b/xen/arch/x86/x86_emulate/x86_emulate.c
@@ -720,29 +720,26 @@ do{ uint8_t stub[] = { _bytes, 0xc3 };                                  \
     put_fpu(&fic);                                                      \
 } while (0)
 
-static unsigned long __get_rep_prefix(
-    struct cpu_user_regs *int_regs,
-    struct cpu_user_regs *ext_regs,
+static unsigned long _get_rep_prefix(
+    const struct cpu_user_regs *int_regs,
     int ad_bytes)
 {
-    unsigned long ecx = ((ad_bytes == 2) ? (uint16_t)int_regs->ecx :
-                         (ad_bytes == 4) ? (uint32_t)int_regs->ecx :
-                         int_regs->ecx);
-
-    /* Skip the instruction if no repetitions are required. */
-    if ( ecx == 0 )
-        ext_regs->eip = int_regs->eip;
-
-    return ecx;
+    return (ad_bytes == 2) ? (uint16_t)int_regs->ecx :
+           (ad_bytes == 4) ? (uint32_t)int_regs->ecx :
+           int_regs->ecx;
 }
 
 #define get_rep_prefix() ({                                             \
     unsigned long max_reps = 1;                                         \
     if ( rep_prefix() )                                                 \
-        max_reps = __get_rep_prefix(&_regs, ctxt->regs, ad_bytes);      \
+        max_reps = _get_rep_prefix(&_regs, ad_bytes);                   \
     if ( max_reps == 0 )                                                \
-        goto done;                                                      \
-   max_reps;                                                            \
+    {                                                                   \
+        /* Skip the instruction if no repetitions are required. */      \
+        dst.type = OP_NONE;                                             \
+        goto writeback;                                                 \
+    }                                                                   \
+    max_reps;                                                           \
 })
 
 static void __put_rep_prefix(
@@ -3932,7 +3929,8 @@ x86_emulate(
         if ( !rc && (b & 1) && (ea.type == OP_MEM) )
             rc = ops->write(ea.mem.seg, ea.mem.off, mmvalp,
                             ea.bytes, ctxt);
-        goto done;
+        dst.type = OP_NONE;
+        break;
     }
 
     case 0x20: /* mov cr,reg */
@@ -4199,7 +4197,8 @@ x86_emulate(
         if ( !rc && (b != 0x6f) && (ea.type == OP_MEM) )
             rc = ops->write(ea.mem.seg, ea.mem.off, mmvalp,
                             ea.bytes, ctxt);
-        goto done;
+        dst.type = OP_NONE;
+        break;
     }
 
     case 0x80 ... 0x8f: /* jcc (near) */ {