target/i386: Raise #GP on unaligned m128 accesses when required.

Many instructions which load/store 128-bit values are supposed to
raise #GP when the memory operand isn't 16-byte aligned. This includes:
 - Instructions explicitly requiring memory alignment (Exceptions Type 1
   in the "AVX and SSE Instruction Exception Specification" section of
   the SDM)
 - Legacy SSE instructions that load/store 128-bit values (Exceptions
   Types 2 and 4).

This change sets MO_ALIGN_16 on 128-bit memory accesses that require
16-byte alignment. It adds cpu_record_sigbus and cpu_do_unaligned_access
hooks that simulate a #GP exception in qemu-user and qemu-system,
respectively.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/217
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Ricky Zhou <ricky@rzhou.org>
Message-Id: <20220830034816.57091-2-ricky@rzhou.org>
[Do not bother checking PREFIX_VEX, since AVX is not supported. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

6 files changed, 72 insertions, 29 deletions

diff --git a/target/i386/tcg/excp_helper.c b/target/i386/tcg/excp_helper.c
index c1ffa1c..7c3c8dc 100644
--- a/target/i386/tcg/excp_helper.c
+++ b/target/i386/tcg/excp_helper.c
@@ -140,3 +140,16 @@ G_NORETURN void raise_exception_ra(CPUX86State *env, int exception_index,
 {
     raise_interrupt2(env, exception_index, 0, 0, 0, retaddr);
 }
+
+G_NORETURN void handle_unaligned_access(CPUX86State *env, vaddr vaddr,
+                                        MMUAccessType access_type,
+                                        uintptr_t retaddr)
+{
+    /*
+     * Unaligned accesses are currently only triggered by SSE/AVX
+     * instructions that impose alignment requirements on memory
+     * operands. These instructions raise #GP(0) upon accessing an
+     * unaligned address.
+     */
+    raise_exception_ra(env, EXCP0D_GPF, retaddr);
+}
diff --git a/target/i386/tcg/helper-tcg.h b/target/i386/tcg/helper-tcg.h
index 34167e2..cd17233 100644
--- a/target/i386/tcg/helper-tcg.h
+++ b/target/i386/tcg/helper-tcg.h
@@ -42,17 +42,6 @@ void x86_cpu_do_interrupt(CPUState *cpu);
 bool x86_cpu_exec_interrupt(CPUState *cpu, int int_req);
 #endif
 
-/* helper.c */
-#ifdef CONFIG_USER_ONLY
-void x86_cpu_record_sigsegv(CPUState *cs, vaddr addr,
-                            MMUAccessType access_type,
-                            bool maperr, uintptr_t ra);
-#else
-bool x86_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
-                      MMUAccessType access_type, int mmu_idx,
-                      bool probe, uintptr_t retaddr);
-#endif
-
 void breakpoint_handler(CPUState *cs);
 
 /* n must be a constant to be efficient */
@@ -78,6 +67,23 @@ G_NORETURN void raise_exception_err_ra(CPUX86State *env, int exception_index,
                                        int error_code, uintptr_t retaddr);
 G_NORETURN void raise_interrupt(CPUX86State *nenv, int intno, int is_int,
                                 int error_code, int next_eip_addend);
+G_NORETURN void handle_unaligned_access(CPUX86State *env, vaddr vaddr,
+                                        MMUAccessType access_type,
+                                        uintptr_t retaddr);
+#ifdef CONFIG_USER_ONLY
+void x86_cpu_record_sigsegv(CPUState *cs, vaddr addr,
+                            MMUAccessType access_type,
+                            bool maperr, uintptr_t ra);
+void x86_cpu_record_sigbus(CPUState *cs, vaddr addr,
+                           MMUAccessType access_type, uintptr_t ra);
+#else
+bool x86_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                      MMUAccessType access_type, int mmu_idx,
+                      bool probe, uintptr_t retaddr);
+G_NORETURN void x86_cpu_do_unaligned_access(CPUState *cs, vaddr vaddr,
+                                            MMUAccessType access_type,
+                                            int mmu_idx, uintptr_t retaddr);
+#endif
 
 /* cc_helper.c */
 extern const uint8_t parity_table[256];
diff --git a/target/i386/tcg/sysemu/excp_helper.c b/target/i386/tcg/sysemu/excp_helper.c
index 48feba7..796dc2a 100644
--- a/target/i386/tcg/sysemu/excp_helper.c
+++ b/target/i386/tcg/sysemu/excp_helper.c
@@ -439,3 +439,11 @@ bool x86_cpu_tlb_fill(CPUState *cs, vaddr addr, int size,
     }
     return true;
 }
+
+G_NORETURN void x86_cpu_do_unaligned_access(CPUState *cs, vaddr vaddr,
+                                            MMUAccessType access_type,
+                                            int mmu_idx, uintptr_t retaddr)
+{
+    X86CPU *cpu = X86_CPU(cs);
+    handle_unaligned_access(&cpu->env, vaddr, access_type, retaddr);
+}
diff --git a/target/i386/tcg/tcg-cpu.c b/target/i386/tcg/tcg-cpu.c
index 6fdfdf9..d3c2b8f 100644
--- a/target/i386/tcg/tcg-cpu.c
+++ b/target/i386/tcg/tcg-cpu.c
@@ -75,10 +75,12 @@ static const struct TCGCPUOps x86_tcg_ops = {
 #ifdef CONFIG_USER_ONLY
     .fake_user_interrupt = x86_cpu_do_interrupt,
     .record_sigsegv = x86_cpu_record_sigsegv,
+    .record_sigbus = x86_cpu_record_sigbus,
 #else
     .tlb_fill = x86_cpu_tlb_fill,
     .do_interrupt = x86_cpu_do_interrupt,
     .cpu_exec_interrupt = x86_cpu_exec_interrupt,
+    .do_unaligned_access = x86_cpu_do_unaligned_access,
     .debug_excp_handler = breakpoint_handler,
     .debug_check_breakpoint = x86_debug_check_breakpoint,
 #endif /* !CONFIG_USER_ONLY */
diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c
index d6420df..8ec91d1 100644
--- a/target/i386/tcg/translate.c
+++ b/target/i386/tcg/translate.c
@@ -2738,21 +2738,23 @@ static inline void gen_stq_env_A0(DisasContext *s, int offset)
     tcg_gen_qemu_st_i64(s->tmp1_i64, s->A0, s->mem_index, MO_LEUQ);
 }
 
-static inline void gen_ldo_env_A0(DisasContext *s, int offset)
+static inline void gen_ldo_env_A0(DisasContext *s, int offset, bool align)
 {
     int mem_index = s->mem_index;
-    tcg_gen_qemu_ld_i64(s->tmp1_i64, s->A0, mem_index, MO_LEUQ);
+    tcg_gen_qemu_ld_i64(s->tmp1_i64, s->A0, mem_index,
+                        MO_LEUQ | (align ? MO_ALIGN_16 : 0));
     tcg_gen_st_i64(s->tmp1_i64, cpu_env, offset + offsetof(ZMMReg, ZMM_Q(0)));
     tcg_gen_addi_tl(s->tmp0, s->A0, 8);
     tcg_gen_qemu_ld_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
     tcg_gen_st_i64(s->tmp1_i64, cpu_env, offset + offsetof(ZMMReg, ZMM_Q(1)));
 }
 
-static inline void gen_sto_env_A0(DisasContext *s, int offset)
+static inline void gen_sto_env_A0(DisasContext *s, int offset, bool align)
 {
     int mem_index = s->mem_index;
     tcg_gen_ld_i64(s->tmp1_i64, cpu_env, offset + offsetof(ZMMReg, ZMM_Q(0)));
-    tcg_gen_qemu_st_i64(s->tmp1_i64, s->A0, mem_index, MO_LEUQ);
+    tcg_gen_qemu_st_i64(s->tmp1_i64, s->A0, mem_index,
+                        MO_LEUQ | (align ? MO_ALIGN_16 : 0));
     tcg_gen_addi_tl(s->tmp0, s->A0, 8);
     tcg_gen_ld_i64(s->tmp1_i64, cpu_env, offset + offsetof(ZMMReg, ZMM_Q(1)));
     tcg_gen_qemu_st_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
@@ -3131,7 +3133,7 @@ static const struct SSEOpHelper_table6 sse_op_table6[256] = {
     [0x25] = UNARY_OP(pmovsxdq, SSE41, SSE_OPF_MMX),
     [0x28] = BINARY_OP(pmuldq, SSE41, SSE_OPF_MMX),
     [0x29] = BINARY_OP(pcmpeqq, SSE41, SSE_OPF_MMX),
-    [0x2a] = SPECIAL_OP(SSE41), /* movntqda */
+    [0x2a] = SPECIAL_OP(SSE41), /* movntdqa */
     [0x2b] = BINARY_OP(packusdw, SSE41, SSE_OPF_MMX),
     [0x30] = UNARY_OP(pmovzxbw, SSE41, SSE_OPF_MMX),
     [0x31] = UNARY_OP(pmovzxbd, SSE41, SSE_OPF_MMX),
@@ -3294,17 +3296,17 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
             break;
         case 0x1e7: /* movntdq */
         case 0x02b: /* movntps */
-        case 0x12b: /* movntps */
+        case 0x12b: /* movntpd */
             if (mod == 3)
                 goto illegal_op;
             gen_lea_modrm(env, s, modrm);
-            gen_sto_env_A0(s, ZMM_OFFSET(reg));
+            gen_sto_env_A0(s, ZMM_OFFSET(reg), true);
             break;
         case 0x3f0: /* lddqu */
             if (mod == 3)
                 goto illegal_op;
             gen_lea_modrm(env, s, modrm);
-            gen_ldo_env_A0(s, ZMM_OFFSET(reg));
+            gen_ldo_env_A0(s, ZMM_OFFSET(reg), false);
             break;
         case 0x22b: /* movntss */
         case 0x32b: /* movntsd */
@@ -3373,7 +3375,9 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
         case 0x26f: /* movdqu xmm, ea */
             if (mod != 3) {
                 gen_lea_modrm(env, s, modrm);
-                gen_ldo_env_A0(s, ZMM_OFFSET(reg));
+                gen_ldo_env_A0(s, ZMM_OFFSET(reg),
+                               /* movaps, movapd, movdqa */
+                               b == 0x028 || b == 0x128 || b == 0x16f);
             } else {
                 rm = (modrm & 7) | REX_B(s);
                 gen_op_movo(s, ZMM_OFFSET(reg), ZMM_OFFSET(rm));
@@ -3432,7 +3436,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
         case 0x212: /* movsldup */
             if (mod != 3) {
                 gen_lea_modrm(env, s, modrm);
-                gen_ldo_env_A0(s, ZMM_OFFSET(reg));
+                gen_ldo_env_A0(s, ZMM_OFFSET(reg), true);
             } else {
                 rm = (modrm & 7) | REX_B(s);
                 gen_op_movl(s, offsetof(CPUX86State, xmm_regs[reg].ZMM_L(0)),
@@ -3474,7 +3478,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
         case 0x216: /* movshdup */
             if (mod != 3) {
                 gen_lea_modrm(env, s, modrm);
-                gen_ldo_env_A0(s, ZMM_OFFSET(reg));
+                gen_ldo_env_A0(s, ZMM_OFFSET(reg), true);
             } else {
                 rm = (modrm & 7) | REX_B(s);
                 gen_op_movl(s, offsetof(CPUX86State, xmm_regs[reg].ZMM_L(1)),
@@ -3568,7 +3572,9 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
         case 0x27f: /* movdqu ea, xmm */
             if (mod != 3) {
                 gen_lea_modrm(env, s, modrm);
-                gen_sto_env_A0(s, ZMM_OFFSET(reg));
+                gen_sto_env_A0(s, ZMM_OFFSET(reg),
+                               /* movaps, movapd, movdqa */
+                               b == 0x029 || b == 0x129 || b == 0x17f);
             } else {
                 rm = (modrm & 7) | REX_B(s);
                 gen_op_movo(s, ZMM_OFFSET(rm), ZMM_OFFSET(reg));
@@ -3724,7 +3730,8 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
             if (mod != 3) {
                 gen_lea_modrm(env, s, modrm);
                 op2_offset = offsetof(CPUX86State,xmm_t0);
-                gen_ldo_env_A0(s, op2_offset);
+                /* FIXME: should be 64-bit access if b1 == 0.  */
+                gen_ldo_env_A0(s, op2_offset, !!b1);
             } else {
                 rm = (modrm & 7) | REX_B(s);
                 op2_offset = ZMM_OFFSET(rm);
@@ -3913,11 +3920,11 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
                         tcg_gen_st16_tl(s->tmp0, cpu_env, op2_offset +
                                         offsetof(ZMMReg, ZMM_W(0)));
                         break;
-                    case 0x2a:            /* movntqda */
-                        gen_ldo_env_A0(s, op1_offset);
+                    case 0x2a:            /* movntdqa */
+                        gen_ldo_env_A0(s, op1_offset, true);
                         return;
                     default:
-                        gen_ldo_env_A0(s, op2_offset);
+                        gen_ldo_env_A0(s, op2_offset, true);
                     }
                 }
                 if (!op6->fn[b1].op1) {
@@ -4499,7 +4506,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
             } else {
                 op2_offset = offsetof(CPUX86State, xmm_t0);
                 gen_lea_modrm(env, s, modrm);
-                gen_ldo_env_A0(s, op2_offset);
+                gen_ldo_env_A0(s, op2_offset, true);
             }
 
             val = x86_ldub_code(env, s);
@@ -4606,7 +4613,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
                     break;
                 default:
                     /* 128 bit access */
-                    gen_ldo_env_A0(s, op2_offset);
+                    gen_ldo_env_A0(s, op2_offset, true);
                     break;
                 }
             } else {
diff --git a/target/i386/tcg/user/excp_helper.c b/target/i386/tcg/user/excp_helper.c
index cd507e2..b3bdb78 100644
--- a/target/i386/tcg/user/excp_helper.c
+++ b/target/i386/tcg/user/excp_helper.c
@@ -48,3 +48,10 @@ void x86_cpu_record_sigsegv(CPUState *cs, vaddr addr,
 
     cpu_loop_exit_restore(cs, ra);
 }
+
+void x86_cpu_record_sigbus(CPUState *cs, vaddr addr,
+                           MMUAccessType access_type, uintptr_t ra)
+{
+    X86CPU *cpu = X86_CPU(cs);
+    handle_unaligned_access(&cpu->env, addr, access_type, ra);
+}