5 files changed, 53 insertions, 22 deletions

diff --git a/arch/i386/kernel/entry.S b/arch/i386/kernel/entry.S
index a991d4e5edd2..b389e5f3bdee 100644
--- a/arch/i386/kernel/entry.S
+++ b/arch/i386/kernel/entry.S
@@ -203,7 +203,7 @@ sysenter_past_esp:
         GET_THREAD_INFO(%ebp)
 
         /* Note, _TIF_SECCOMP is bit number 8, and so it needs testw and not testb */
-        testw $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),TI_flags(%ebp)
+        testw $(_TIF_SYSCALL_EMU|_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT),TI_flags(%ebp)
         jnz syscall_trace_entry
         cmpl $(nr_syscalls), %eax
         jae syscall_badsys
@@ -226,9 +226,9 @@ ENTRY(system_call)
         pushl %eax                      # save orig_eax
         SAVE_ALL
         GET_THREAD_INFO(%ebp)
-                                        # system call tracing in operation
+                                        # system call tracing in operation / emulation
         /* Note, _TIF_SECCOMP is bit number 8, and so it needs testw and not testb */
-        testw $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),TI_flags(%ebp)
+        testw $(_TIF_SYSCALL_EMU|_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT),TI_flags(%ebp)
         jnz syscall_trace_entry
         cmpl $(nr_syscalls), %eax
         jae syscall_badsys
@@ -338,6 +338,9 @@ syscall_trace_entry:
         movl %esp, %eax
         xorl %edx,%edx
         call do_syscall_trace
+        cmpl $0, %eax
+        jne syscall_exit                # ret != 0 -> running under PTRACE_SYSEMU,
+                                        # so must skip actual syscall
         movl ORIG_EAX(%esp), %eax
         cmpl $(nr_syscalls), %eax
         jnae syscall_call
diff --git a/arch/i386/kernel/ptrace.c b/arch/i386/kernel/ptrace.c
index 5ee9e1d60653..5b569dc1c227 100644
--- a/arch/i386/kernel/ptrace.c
+++ b/arch/i386/kernel/ptrace.c
@@ -509,15 +509,27 @@ asmlinkage int sys_ptrace(long request, long pid, long addr, long data)
                   }
                   break;
 
+        case PTRACE_SYSEMU: /* continue and stop at next syscall, which will not be executed */
         case PTRACE_SYSCALL:    /* continue and stop at next (return from) syscall */
         case PTRACE_CONT:       /* restart after signal. */
                 ret = -EIO;
                 if (!valid_signal(data))
                         break;
+                /* If we came here with PTRACE_SYSEMU and now continue with
+                 * PTRACE_SYSCALL, entry.S used to intercept the syscall return.
+                 * But it shouldn't!
+                 * So we don't clear TIF_SYSCALL_EMU, which is always unused in
+                 * this special case, to remember, we came from SYSEMU. That
+                 * flag will be cleared by do_syscall_trace().
+                 */
+                if (request == PTRACE_SYSEMU) {
+                        set_tsk_thread_flag(child, TIF_SYSCALL_EMU);
+                } else if (request == PTRACE_CONT) {
+                        clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
+                }
                 if (request == PTRACE_SYSCALL) {
                         set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
-                }
-                else {
+                } else {
                         clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
                 }
                 child->exit_code = data;
@@ -546,6 +558,8 @@ asmlinkage int sys_ptrace(long request, long pid, long addr, long data)
                 ret = -EIO;
                 if (!valid_signal(data))
                         break;
+                /*See do_syscall_trace to know why we don't clear
+                 * TIF_SYSCALL_EMU.*/
                 clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
                 set_singlestep(child);
                 child->exit_code = data;
@@ -678,37 +692,43 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code)
  * - triggered by current->work.syscall_trace
  */
 __attribute__((regparm(3)))
-void do_syscall_trace(struct pt_regs *regs, int entryexit)
+int do_syscall_trace(struct pt_regs *regs, int entryexit)
 {
+        int is_sysemu, is_systrace, is_singlestep, ret = 0;
         /* do the secure computing check first */
         secure_computing(regs->orig_eax);
 
-        if (unlikely(current->audit_context)) {
-                if (entryexit)
-                        audit_syscall_exit(current, AUDITSC_RESULT(regs->eax), regs->eax);
-
-                /* Debug traps, when using PTRACE_SINGLESTEP, must be sent only
-                 * on the syscall exit path. Normally, when TIF_SYSCALL_AUDIT is
-                 * not used, entry.S will call us only on syscall exit, not
-                 * entry ; so when TIF_SYSCALL_AUDIT is used we must avoid
-                 * calling send_sigtrap() on syscall entry.
-                 */
-                else if (is_singlestep)
-                        goto out;
-        }
+        if (unlikely(current->audit_context) && entryexit)
+                audit_syscall_exit(current, AUDITSC_RESULT(regs->eax), regs->eax);
 
         if (!(current->ptrace & PT_PTRACED))
                 goto out;
 
+        is_sysemu = test_thread_flag(TIF_SYSCALL_EMU);
+        is_systrace = test_thread_flag(TIF_SYSCALL_TRACE);
+        is_singlestep = test_thread_flag(TIF_SINGLESTEP);
+
+        /* We can detect the case of coming from PTRACE_SYSEMU and now running
+         * with PTRACE_SYSCALL or PTRACE_SINGLESTEP, by TIF_SYSCALL_EMU being
+         * set additionally.
+         * If so let's reset the flag and return without action (no singlestep
+         * nor syscall tracing, since no actual step has been executed).
+         */
+        if (is_sysemu && (is_systrace || is_singlestep)) {
+                clear_thread_flag(TIF_SYSCALL_EMU);
+                goto out;
+        }
+
         /* Fake a debug trap */
         if (test_thread_flag(TIF_SINGLESTEP))
                 send_sigtrap(current, regs, 0);
 
-        if (!test_thread_flag(TIF_SYSCALL_TRACE))
+        if (!is_systrace && !is_sysemu)
                 goto out;
 
         /* the 0x80 provides a way for the tracing parent to distinguish
            between a syscall stop and SIGTRAP delivery */
+        /* Note that the debugger could change the result of test_thread_flag!*/
         ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD) ? 0x80 : 0));
 
         /*
@@ -720,9 +740,10 @@ void do_syscall_trace(struct pt_regs *regs, int entryexit)
                 send_sig(current->exit_code, current, 1);
                 current->exit_code = 0;
         }
+        ret = is_sysemu;
  out:
         if (unlikely(current->audit_context) && !entryexit)
                 audit_syscall_entry(current, AUDIT_ARCH_I386, regs->orig_eax,
                                     regs->ebx, regs->ecx, regs->edx, regs->esi);
-
+        return ret;
 }
diff --git a/include/asm-i386/thread_info.h b/include/asm-i386/thread_info.h
index 95add81237ea..e2cb9fa6f563 100644
--- a/include/asm-i386/thread_info.h
+++ b/include/asm-i386/thread_info.h
@@ -139,6 +139,7 @@ register unsigned long current_stack_pointer asm("esp") __attribute_used__;
 #define TIF_NEED_RESCHED        3       /* rescheduling necessary */
 #define TIF_SINGLESTEP          4       /* restore singlestep on return to user mode */
 #define TIF_IRET                5       /* return with iret */
+#define TIF_SYSCALL_EMU         6       /* syscall emulation active */
 #define TIF_SYSCALL_AUDIT       7       /* syscall auditing active */
 #define TIF_SECCOMP             8       /* secure computing */
 #define TIF_POLLING_NRFLAG      16      /* true if poll_idle() is polling TIF_NEED_RESCHED */
@@ -150,13 +151,15 @@ register unsigned long current_stack_pointer asm("esp") __attribute_used__;
 #define _TIF_NEED_RESCHED       (1<<TIF_NEED_RESCHED)
 #define _TIF_SINGLESTEP         (1<<TIF_SINGLESTEP)
 #define _TIF_IRET               (1<<TIF_IRET)
+#define _TIF_SYSCALL_EMU        (1<<TIF_SYSCALL_EMU)
 #define _TIF_SYSCALL_AUDIT      (1<<TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP            (1<<TIF_SECCOMP)
 #define _TIF_POLLING_NRFLAG     (1<<TIF_POLLING_NRFLAG)
 
 /* work to do on interrupt/exception return */
 #define _TIF_WORK_MASK \
-  (0x0000FFFF & ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP|_TIF_SECCOMP))
+  (0x0000FFFF & ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP|\
+                  _TIF_SECCOMP|_TIF_SYSCALL_EMU))
 /* work to do on any return to u-space */
 #define _TIF_ALLWORK_MASK       (0x0000FFFF & ~_TIF_SECCOMP)
 
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index a373fc254df2..7528afb6b2ad 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -20,6 +20,7 @@
 #define PTRACE_DETACH           0x11
 
 #define PTRACE_SYSCALL            24
+#define PTRACE_SYSEMU             31
 
 /* 0x4200-0x4300 are reserved for architecture-independent additions.  */
 #define PTRACE_SETOPTIONS       0x4200
diff --git a/kernel/fork.c b/kernel/fork.c
index b65187f0c74e..7e1ead9a6ba4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -994,6 +994,9 @@ static task_t *copy_process(unsigned long clone_flags,
          * of CLONE_PTRACE.
          */
         clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
+#ifdef TIF_SYSCALL_EMU
+        clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
+#endif
 
         /* Our parent execution domain becomes current domain
            These must match for thread signalling to apply */