Merge remote-tracking branch 'remotes/vivier2/tags/linux-user-for-5.0-pull-request' into staging

Emulate x86_64 vsyscalls
Fix syscall_nr.h cleanup

# gpg: Signature made Thu 26 Mar 2020 07:23:16 GMT
# gpg:                using RSA key CD2F75DDC8E3A4DC2E4F5173F30C38BD3F2FBE3C
# gpg:                issuer "laurent@vivier.eu"
# gpg: Good signature from "Laurent Vivier <lvivier@redhat.com>" [full]
# gpg:                 aka "Laurent Vivier <laurent@vivier.eu>" [full]
# gpg:                 aka "Laurent Vivier (Red Hat) <lvivier@redhat.com>" [full]
# Primary key fingerprint: CD2F 75DD C8E3 A4DC 2E4F  5173 F30C 38BD 3F2F BE3C

* remotes/vivier2/tags/linux-user-for-5.0-pull-request:
  linux-user: Flush out implementation of gettimeofday
  linux-user: Add x86_64 vsyscall page to /proc/self/maps
  linux-user/i386: Emulate x86_64 vsyscalls
  linux-user/i386: Split out gen_signal
  target/i386: Renumber EXCP_SYSCALL
  linux-user, configure: fix (again) syscall_nr.h dependencies cleanup

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

5 files changed, 205 insertions, 69 deletions

diff --git a/configure b/configure
index da09c35895..89fe881dd4 100755
--- a/configure
+++ b/configure
@@ -1910,9 +1910,11 @@ for arch in alpha hppa m68k xtensa sh4 microblaze arm ppc s390x sparc sparc64 \
     # remove the file if it has been generated in the source directory
     rm -f "${source_path}/linux-user/${arch}/syscall_nr.h"
     # remove the dependency files
-    test -d ${arch}-linux-user && find ${arch}-linux-user -type f -name "*.d" \
-         -exec grep -q "${source_path}/linux-user/${arch}/syscall_nr.h" {} \; \
-         -exec rm {} \;
+    for target in ${arch}*-linux-user ; do
+        test -d "${target}" && find "${target}" -type f -name "*.d" \
+             -exec grep -q "${source_path}/linux-user/${arch}/syscall_nr.h" {} \; \
+             -print | while read file ; do rm "${file}" "${file%.d}.o" ; done
+    done
 done
 
 if test -z "$python"
diff --git a/linux-user/i386/cpu_loop.c b/linux-user/i386/cpu_loop.c
index 024b6f4d58..70cde417e6 100644
--- a/linux-user/i386/cpu_loop.c
+++ b/linux-user/i386/cpu_loop.c
@@ -81,13 +81,126 @@ static void set_idt(int n, unsigned int dpl)
 }
 #endif
 
+static void gen_signal(CPUX86State *env, int sig, int code, abi_ptr addr)
+{
+    target_siginfo_t info = {
+        .si_signo = sig,
+        .si_code = code,
+        ._sifields._sigfault._addr = 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);
     int trapnr;
     abi_ulong pc;
     abi_ulong ret;
-    target_siginfo_t info;
 
     for(;;) {
         cpu_exec_start(cs);
@@ -132,72 +245,52 @@ void cpu_loop(CPUX86State *env)
             }
             break;
 #endif
+#ifdef TARGET_X86_64
+        case EXCP_VSYSCALL:
+            emulate_vsyscall(env);
+            break;
+#endif
         case EXCP0B_NOSEG:
         case EXCP0C_STACK:
-            info.si_signo = TARGET_SIGBUS;
-            info.si_errno = 0;
-            info.si_code = TARGET_SI_KERNEL;
-            info._sifields._sigfault._addr = 0;
-            queue_signal(env, info.si_signo, QEMU_SI_FAULT, &info);
+            gen_signal(env, TARGET_SIGBUS, TARGET_SI_KERNEL, 0);
             break;
         case EXCP0D_GPF:
             /* XXX: potential problem if ABI32 */
 #ifndef TARGET_X86_64
             if (env->eflags & VM_MASK) {
                 handle_vm86_fault(env);
-            } else
-#endif
-            {
-                info.si_signo = TARGET_SIGSEGV;
-                info.si_errno = 0;
-                info.si_code = TARGET_SI_KERNEL;
-                info._sifields._sigfault._addr = 0;
-                queue_signal(env, info.si_signo, QEMU_SI_FAULT, &info);
+                break;
             }
+#endif
+            gen_signal(env, TARGET_SIGSEGV, TARGET_SI_KERNEL, 0);
             break;
         case EXCP0E_PAGE:
-            info.si_signo = TARGET_SIGSEGV;
-            info.si_errno = 0;
-            if (!(env->error_code & 1))
-                info.si_code = TARGET_SEGV_MAPERR;
-            else
-                info.si_code = TARGET_SEGV_ACCERR;
-            info._sifields._sigfault._addr = env->cr[2];
-            queue_signal(env, info.si_signo, QEMU_SI_FAULT, &info);
+            gen_signal(env, TARGET_SIGSEGV,
+                       (env->error_code & 1 ?
+                        TARGET_SEGV_ACCERR : TARGET_SEGV_MAPERR),
+                       env->cr[2]);
             break;
         case EXCP00_DIVZ:
 #ifndef TARGET_X86_64
             if (env->eflags & VM_MASK) {
                 handle_vm86_trap(env, trapnr);
-            } else
-#endif
-            {
-                /* division by zero */
-                info.si_signo = TARGET_SIGFPE;
-                info.si_errno = 0;
-                info.si_code = TARGET_FPE_INTDIV;
-                info._sifields._sigfault._addr = env->eip;
-                queue_signal(env, info.si_signo, QEMU_SI_FAULT, &info);
+                break;
             }
+#endif
+            gen_signal(env, TARGET_SIGFPE, TARGET_FPE_INTDIV, env->eip);
             break;
         case EXCP01_DB:
         case EXCP03_INT3:
 #ifndef TARGET_X86_64
             if (env->eflags & VM_MASK) {
                 handle_vm86_trap(env, trapnr);
-            } else
+                break;
+            }
 #endif
-            {
-                info.si_signo = TARGET_SIGTRAP;
-                info.si_errno = 0;
-                if (trapnr == EXCP01_DB) {
-                    info.si_code = TARGET_TRAP_BRKPT;
-                    info._sifields._sigfault._addr = env->eip;
-                } else {
-                    info.si_code = TARGET_SI_KERNEL;
-                    info._sifields._sigfault._addr = 0;
-                }
-                queue_signal(env, info.si_signo, QEMU_SI_FAULT, &info);
+            if (trapnr == EXCP01_DB) {
+                gen_signal(env, TARGET_SIGTRAP, TARGET_TRAP_BRKPT, env->eip);
+            } else {
+                gen_signal(env, TARGET_SIGTRAP, TARGET_SI_KERNEL, 0);
             }
             break;
         case EXCP04_INTO:
@@ -205,31 +298,19 @@ void cpu_loop(CPUX86State *env)
 #ifndef TARGET_X86_64
             if (env->eflags & VM_MASK) {
                 handle_vm86_trap(env, trapnr);
-            } else
-#endif
-            {
-                info.si_signo = TARGET_SIGSEGV;
-                info.si_errno = 0;
-                info.si_code = TARGET_SI_KERNEL;
-                info._sifields._sigfault._addr = 0;
-                queue_signal(env, info.si_signo, QEMU_SI_FAULT, &info);
+                break;
             }
+#endif
+            gen_signal(env, TARGET_SIGSEGV, TARGET_SI_KERNEL, 0);
             break;
         case EXCP06_ILLOP:
-            info.si_signo = TARGET_SIGILL;
-            info.si_errno = 0;
-            info.si_code = TARGET_ILL_ILLOPN;
-            info._sifields._sigfault._addr = env->eip;
-            queue_signal(env, info.si_signo, QEMU_SI_FAULT, &info);
+            gen_signal(env, TARGET_SIGILL, TARGET_ILL_ILLOPN, env->eip);
             break;
         case EXCP_INTERRUPT:
             /* just indicate that signals should be handled asap */
             break;
         case EXCP_DEBUG:
-            info.si_signo = TARGET_SIGTRAP;
-            info.si_errno = 0;
-            info.si_code = TARGET_TRAP_BRKPT;
-            queue_signal(env, info.si_signo, QEMU_SI_FAULT, &info);
+            gen_signal(env, TARGET_SIGTRAP, TARGET_TRAP_BRKPT, 0);
             break;
         case EXCP_ATOMIC:
             cpu_exec_step_atomic(cs);
diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index 35f4146662..49395dcea9 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -1273,6 +1273,25 @@ static inline abi_long host_to_target_timespec64(abi_ulong target_addr,
     return 0;
 }
 
+#if defined(TARGET_NR_gettimeofday)
+static inline abi_long copy_to_user_timezone(abi_ulong target_tz_addr,
+                                             struct timezone *tz)
+{
+    struct target_timezone *target_tz;
+
+    if (!lock_user_struct(VERIFY_WRITE, target_tz, target_tz_addr, 1)) {
+        return -TARGET_EFAULT;
+    }
+
+    __put_user(tz->tz_minuteswest, &target_tz->tz_minuteswest);
+    __put_user(tz->tz_dsttime, &target_tz->tz_dsttime);
+
+    unlock_user_struct(target_tz, target_tz_addr, 1);
+
+    return 0;
+}
+#endif
+
 #if defined(TARGET_NR_settimeofday)
 static inline abi_long copy_from_user_timezone(struct timezone *tz,
                                                abi_ulong target_tz_addr)
@@ -7144,6 +7163,16 @@ static int open_self_maps(void *cpu_env, int fd)
         }
     }
 
+#ifdef TARGET_VSYSCALL_PAGE
+    /*
+     * We only support execution from the vsyscall page.
+     * This is as if CONFIG_LEGACY_VSYSCALL_XONLY=y from v5.3.
+     */
+    dprintf(fd, TARGET_FMT_lx "-" TARGET_FMT_lx
+            " --xp 00000000 00:00 0 [vsyscall]\n",
+            TARGET_VSYSCALL_PAGE, TARGET_VSYSCALL_PAGE + TARGET_PAGE_SIZE);
+#endif
+
     free(line);
     fclose(fp);
 
@@ -8700,10 +8729,16 @@ static abi_long do_syscall1(void *cpu_env, int num, abi_long arg1,
     case TARGET_NR_gettimeofday:
         {
             struct timeval tv;
-            ret = get_errno(gettimeofday(&tv, NULL));
+            struct timezone tz;
+
+            ret = get_errno(gettimeofday(&tv, &tz));
             if (!is_error(ret)) {
-                if (copy_to_user_timeval(arg1, &tv))
+                if (arg1 && copy_to_user_timeval(arg1, &tv)) {
                     return -TARGET_EFAULT;
+                }
+                if (arg2 && copy_to_user_timezone(arg2, &tz)) {
+                    return -TARGET_EFAULT;
+                }
             }
         }
         return ret;
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index 60d797d594..9af1b0c12e 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -1001,9 +1001,9 @@ typedef uint64_t FeatureWordArray[FEATURE_WORDS];
 #define EXCP11_ALGN	17
 #define EXCP12_MCHK	18
 
-#define EXCP_SYSCALL    0x100 /* only happens in user only emulation
-                                 for syscall instruction */
-#define EXCP_VMEXIT     0x100
+#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
@@ -2219,4 +2219,10 @@ 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 */
diff --git a/target/i386/translate.c b/target/i386/translate.c
index d9af8f4078..5e5dbb41b0 100644
--- a/target/i386/translate.c
+++ b/target/i386/translate.c
@@ -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