@@ -1001,6 +1001,7 @@ typedef uint64_t FeatureWordArray[FEATURE_WORDS];
#define EXCP_VMEXIT 0x100 /* only for system emulation */
#define EXCP_SYSCALL 0x101 /* only for user emulation */
+#define EXCP_VSYSCALL 0x102 /* only for user emulation */
/* i386-specific interrupt pending bits. */
#define CPU_INTERRUPT_POLL CPU_INTERRUPT_TGT_EXT_1
@@ -2215,4 +2216,10 @@ static inline bool hyperv_feat_enabled(X86CPU *cpu, int feat)
return !!(cpu->hyperv_features & BIT(feat));
}
+#if defined(TARGET_X86_64) && \
+ defined(CONFIG_USER_ONLY) && \
+ defined(CONFIG_LINUX)
+# define TARGET_VSYSCALL_PAGE (UINT64_C(-10) << 20)
+#endif
+
#endif /* I386_CPU_H */
@@ -92,6 +92,109 @@ static void gen_signal(CPUX86State *env, int sig, int code, abi_ptr addr)
queue_signal(env, info.si_signo, QEMU_SI_FAULT, &info);
}
+#ifdef TARGET_X86_64
+static bool write_ok_or_segv(CPUX86State *env, abi_ptr addr, size_t len)
+{
+ /*
+ * For all the vsyscalls, NULL means "don't write anything" not
+ * "write it at address 0".
+ */
+ if (addr == 0 || access_ok(VERIFY_WRITE, addr, len)) {
+ return true;
+ }
+
+ env->error_code = PG_ERROR_W_MASK | PG_ERROR_U_MASK;
+ gen_signal(env, TARGET_SIGSEGV, TARGET_SEGV_MAPERR, addr);
+ return false;
+}
+
+/*
+ * Since v3.1, the kernel traps and emulates the vsyscall page.
+ * Entry points other than the official generate SIGSEGV.
+ */
+static void emulate_vsyscall(CPUX86State *env)
+{
+ int syscall;
+ abi_ulong ret;
+ uint64_t caller;
+
+ /*
+ * Validate the entry point. We have already validated the page
+ * during translation to get here; now verify the offset.
+ */
+ switch (env->eip & ~TARGET_PAGE_MASK) {
+ case 0x000:
+ syscall = TARGET_NR_gettimeofday;
+ break;
+ case 0x400:
+ syscall = TARGET_NR_time;
+ break;
+ case 0x800:
+ syscall = TARGET_NR_getcpu;
+ break;
+ default:
+ goto sigsegv;
+ }
+
+ /*
+ * Validate the return address.
+ * Note that the kernel treats this the same as an invalid entry point.
+ */
+ if (get_user_u64(caller, env->regs[R_ESP])) {
+ goto sigsegv;
+ }
+
+ /*
+ * Validate the the pointer arguments.
+ */
+ switch (syscall) {
+ case TARGET_NR_gettimeofday:
+ if (!write_ok_or_segv(env, env->regs[R_EDI],
+ sizeof(struct target_timeval)) ||
+ !write_ok_or_segv(env, env->regs[R_ESI],
+ sizeof(struct target_timezone))) {
+ return;
+ }
+ break;
+ case TARGET_NR_time:
+ if (!write_ok_or_segv(env, env->regs[R_EDI], sizeof(abi_long))) {
+ return;
+ }
+ break;
+ case TARGET_NR_getcpu:
+ if (!write_ok_or_segv(env, env->regs[R_EDI], sizeof(uint32_t)) ||
+ !write_ok_or_segv(env, env->regs[R_ESI], sizeof(uint32_t))) {
+ return;
+ }
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ /*
+ * Perform the syscall. None of the vsyscalls should need restarting.
+ */
+ ret = do_syscall(env, syscall, env->regs[R_EDI], env->regs[R_ESI],
+ env->regs[R_EDX], env->regs[10], env->regs[8],
+ env->regs[9], 0, 0);
+ g_assert(ret != -TARGET_ERESTARTSYS);
+ g_assert(ret != -TARGET_QEMU_ESIGRETURN);
+ if (ret == -TARGET_EFAULT) {
+ goto sigsegv;
+ }
+ env->regs[R_EAX] = ret;
+
+ /* Emulate a ret instruction to leave the vsyscall page. */
+ env->eip = caller;
+ env->regs[R_ESP] += 8;
+ return;
+
+ sigsegv:
+ /* Like force_sig(SIGSEGV). */
+ gen_signal(env, TARGET_SIGSEGV, TARGET_SI_KERNEL, 0);
+}
+#endif
+
void cpu_loop(CPUX86State *env)
{
CPUState *cs = env_cpu(env);
@@ -141,6 +244,11 @@ void cpu_loop(CPUX86State *env)
env->regs[R_EAX] = ret;
}
break;
+#endif
+#ifdef TARGET_X86_64
+ case EXCP_VSYSCALL:
+ emulate_vsyscall(env);
+ break;
#endif
case EXCP0B_NOSEG:
case EXCP0C_STACK:
@@ -8555,7 +8555,19 @@ static bool i386_tr_breakpoint_check(DisasContextBase *dcbase, CPUState *cpu,
static void i386_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu)
{
DisasContext *dc = container_of(dcbase, DisasContext, base);
- target_ulong pc_next = disas_insn(dc, cpu);
+ target_ulong pc_next;
+
+#ifdef TARGET_VSYSCALL_PAGE
+ /*
+ * Detect entry into the vsyscall page and invoke the syscall.
+ */
+ if ((dc->base.pc_next & TARGET_PAGE_MASK) == TARGET_VSYSCALL_PAGE) {
+ gen_exception(dc, EXCP_VSYSCALL, dc->base.pc_next);
+ return;
+ }
+#endif
+
+ pc_next = disas_insn(dc, cpu);
if (dc->tf || (dc->base.tb->flags & HF_INHIBIT_IRQ_MASK)) {
/* if single step mode, we generate only one instruction and