x86 single_step: TIF_FORCED_TF

This changes the single-step support to use a new thread_info flag
TIF_FORCED_TF instead of the PT_DTRACE flag in task_struct.ptrace.
This keeps arch implementation uses out of this non-arch field.

This changes the ptrace access to eflags to mask TF and maintain
the TIF_FORCED_TF flag directly if userland sets TF, instead of
relying on ptrace_signal_deliver.  The 64-bit and 32-bit kernels
are harmonized on this same behavior.  The ptrace_signal_deliver
approach works now, but this change makes the low-level register
access code reliable when called from different contexts than a
ptrace stop, which will be possible in the future.

The 64-bit do_debug exception handler is also changed not to clear TF
from user-mode registers.  This matches the 32-bit kernel's behavior.

Signed-off-by: Roland McGrath <roland@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

9 files changed, 73 insertions, 50 deletions

diff --git a/arch/x86/ia32/ptrace32.c b/arch/x86/ia32/ptrace32.c
index 9d754b640205..5dee33417313 100644
--- a/arch/x86/ia32/ptrace32.c
+++ b/arch/x86/ia32/ptrace32.c
@@ -89,6 +89,15 @@ static int putreg32(struct task_struct *child, unsigned regno, u32 val)
 		__u64 *flags = &stack[offsetof(struct pt_regs, eflags)/8];
 
 		val &= FLAG_MASK;
+		/*
+		 * If the user value contains TF, mark that
+		 * it was not "us" (the debugger) that set it.
+		 * If not, make sure it stays set if we had.
+		 */
+		if (val & X86_EFLAGS_TF)
+			clear_tsk_thread_flag(child, TIF_FORCED_TF);
+		else if (test_tsk_thread_flag(child, TIF_FORCED_TF))
+			val |= X86_EFLAGS_TF;
 		*flags = val | (*flags & ~FLAG_MASK);
 		break;
 	}
@@ -179,9 +188,17 @@ static int getreg32(struct task_struct *child, unsigned regno, u32 *val)
 	R32(eax, rax);
 	R32(orig_eax, orig_rax);
 	R32(eip, rip);
-	R32(eflags, eflags);
 	R32(esp, rsp);
 
+	case offsetof(struct user32, regs.eflags):
+		/*
+		 * If the debugger set TF, hide it from the readout.
+		 */
+		*val = stack[offsetof(struct pt_regs, eflags)/8];
+		if (test_tsk_thread_flag(child, TIF_FORCED_TF))
+			*val &= ~X86_EFLAGS_TF;
+		break;
+
 	case offsetof(struct user32, u_debugreg[0]):
 		*val = child->thread.debugreg0;
 		break;
@@ -425,4 +442,3 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
 	put_task_struct(child);
 	return ret;
 }
-
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 4d66a56280d3..d9905c9d0fd5 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -817,9 +817,6 @@ asmlinkage int sys_execve(struct pt_regs regs)
 			(char __user * __user *) regs.edx,
 			&regs);
 	if (error == 0) {
-		task_lock(current);
-		current->ptrace &= ~PT_DTRACE;
-		task_unlock(current);
 		/* Make sure we don't return using sysenter.. */
 		set_thread_flag(TIF_IRET);
 	}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index ccc9d68d5a58..f7356e5517f6 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -709,11 +709,6 @@ long sys_execve(char __user *name, char __user * __user *argv,
 	if (IS_ERR(filename)) 
 		return error;
 	error = do_execve(filename, argv, envp, &regs); 
-	if (error == 0) {
-		task_lock(current);
-		current->ptrace &= ~PT_DTRACE;
-		task_unlock(current);
-	}
 	putname(filename);
 	return error;
 }
diff --git a/arch/x86/kernel/ptrace_32.c b/arch/x86/kernel/ptrace_32.c
index b73960885c3f..bc7fd802dcc7 100644
--- a/arch/x86/kernel/ptrace_32.c
+++ b/arch/x86/kernel/ptrace_32.c
@@ -104,6 +104,15 @@ static int putreg(struct task_struct *child,
 			break;
 		case EFL:
 			value &= FLAG_MASK;
+			/*
+			 * If the user value contains TF, mark that
+			 * it was not "us" (the debugger) that set it.
+			 * If not, make sure it stays set if we had.
+			 */
+			if (value & X86_EFLAGS_TF)
+				clear_tsk_thread_flag(child, TIF_FORCED_TF);
+			else if (test_tsk_thread_flag(child, TIF_FORCED_TF))
+				value |= X86_EFLAGS_TF;
 			value |= get_stack_long(child, EFL_OFFSET) & ~FLAG_MASK;
 			break;
 	}
@@ -119,6 +128,14 @@ static unsigned long getreg(struct task_struct *child,
 	unsigned long retval = ~0UL;
 
 	switch (regno >> 2) {
+		case EFL:
+			/*
+			 * If the debugger set TF, hide it from the readout.
+			 */
+			retval = get_stack_long(child, EFL_OFFSET);
+			if (test_tsk_thread_flag(child, TIF_FORCED_TF))
+				retval &= ~X86_EFLAGS_TF;
+			break;
 		case GS:
 			retval = child->thread.gs;
 			break;
diff --git a/arch/x86/kernel/ptrace_64.c b/arch/x86/kernel/ptrace_64.c
index 4abfbced9b26..035d53e99c57 100644
--- a/arch/x86/kernel/ptrace_64.c
+++ b/arch/x86/kernel/ptrace_64.c
@@ -143,6 +143,15 @@ static int putreg(struct task_struct *child,
 			return 0;
 		case offsetof(struct user_regs_struct, eflags):
 			value &= FLAG_MASK;
+			/*
+			 * If the user value contains TF, mark that
+			 * it was not "us" (the debugger) that set it.
+			 * If not, make sure it stays set if we had.
+			 */
+			if (value & X86_EFLAGS_TF)
+				clear_tsk_thread_flag(child, TIF_FORCED_TF);
+			else if (test_tsk_thread_flag(child, TIF_FORCED_TF))
+				value |= X86_EFLAGS_TF;
 			tmp = get_stack_long(child, EFL_OFFSET); 
 			tmp &= ~FLAG_MASK; 
 			value |= tmp;
@@ -189,6 +198,17 @@ static unsigned long getreg(struct task_struct *child, unsigned long regno)
 			if (child->thread.gsindex != GS_TLS_SEL)
 				return 0;
 			return get_desc_base(&child->thread.tls_array[GS_TLS]);
+		case offsetof(struct user_regs_struct, eflags):
+			/*
+			 * If the debugger set TF, hide it from the readout.
+			 */
+			regno = regno - sizeof(struct pt_regs);
+			val = get_stack_long(child, regno);
+			if (test_tsk_thread_flag(child, TIF_IA32))
+				val &= 0xffffffff;
+			if (test_tsk_thread_flag(child, TIF_FORCED_TF))
+				val &= ~X86_EFLAGS_TF;
+			return val;
 		default:
 			regno = regno - sizeof(struct pt_regs);
 			val = get_stack_long(child, regno);
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index 1ac53e9a0859..0a7c812212c9 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -545,14 +545,12 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
 	}
 
 	/*
-	 * If TF is set due to a debugger (PT_DTRACE), clear the TF flag so
-	 * that register information in the sigcontext is correct.
+	 * If TF is set due to a debugger (TIF_FORCED_TF), clear the TF
+	 * flag so that register information in the sigcontext is correct.
 	 */
-	if (unlikely(regs->eflags & TF_MASK)
-	    && likely(current->ptrace & PT_DTRACE)) {
-		current->ptrace &= ~PT_DTRACE;
-		regs->eflags &= ~TF_MASK;
-	}
+	if (unlikely(regs->eflags & X86_EFLAGS_TF) &&
+	    likely(test_and_clear_thread_flag(TIF_FORCED_TF)))
+		regs->eflags &= ~X86_EFLAGS_TF;
 
 	/* Set up the stack frame */
 	if (ka->sa.sa_flags & SA_SIGINFO)
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index 38d806467c0f..ab0178ebe00a 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -349,16 +349,12 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
 	}
 
 	/*
-	 * If TF is set due to a debugger (PT_DTRACE), clear the TF
-	 * flag so that register information in the sigcontext is
-	 * correct.
+	 * If TF is set due to a debugger (TIF_FORCED_TF), clear the TF
+	 * flag so that register information in the sigcontext is correct.
 	 */
-	if (unlikely(regs->eflags & TF_MASK)) {
-		if (likely(current->ptrace & PT_DTRACE)) {
-			current->ptrace &= ~PT_DTRACE;
-			regs->eflags &= ~TF_MASK;
-		}
-	}
+	if (unlikely(regs->eflags & X86_EFLAGS_TF) &&
+	    likely(test_and_clear_thread_flag(TIF_FORCED_TF)))
+		regs->eflags &= ~X86_EFLAGS_TF;
 
 #ifdef CONFIG_IA32_EMULATION
 	if (test_thread_flag(TIF_IA32)) {
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 6732272e3479..243bff650ca5 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -135,7 +135,7 @@ void user_enable_single_step(struct task_struct *child)
 	if (is_setting_trap_flag(child, regs))
 		return;
 
-	child->ptrace |= PT_DTRACE;
+	set_tsk_thread_flag(child, TIF_FORCED_TF);
 }
 
 void user_disable_single_step(struct task_struct *child)
@@ -144,9 +144,6 @@ void user_disable_single_step(struct task_struct *child)
 	clear_tsk_thread_flag(child, TIF_SINGLESTEP);
 
 	/* But touch TF only if it was set by us.. */
-	if (child->ptrace & PT_DTRACE) {
-		struct pt_regs *regs = task_pt_regs(child);
-		regs->eflags &= ~X86_EFLAGS_TF;
-		child->ptrace &= ~PT_DTRACE;
-	}
+	if (test_and_clear_tsk_thread_flag(child, TIF_FORCED_TF))
+		task_pt_regs(child)->eflags &= ~X86_EFLAGS_TF;
 }
diff --git a/arch/x86/kernel/traps_64.c b/arch/x86/kernel/traps_64.c
index aa248d754533..874aca397b02 100644
--- a/arch/x86/kernel/traps_64.c
+++ b/arch/x86/kernel/traps_64.c
@@ -865,27 +865,14 @@ asmlinkage void __kprobes do_debug(struct pt_regs * regs,
 
 	tsk->thread.debugreg6 = condition;
 
-	/* Mask out spurious TF errors due to lazy TF clearing */
+
+	/*
+	 * Single-stepping through TF: make sure we ignore any events in
+	 * kernel space (but re-enable TF when returning to user mode).
+	 */
 	if (condition & DR_STEP) {
-		/*
-		 * The TF error should be masked out only if the current
-		 * process is not traced and if the TRAP flag has been set
-		 * previously by a tracing process (condition detected by
-		 * the PT_DTRACE flag); remember that the i386 TRAP flag
-		 * can be modified by the process itself in user mode,
-		 * allowing programs to debug themselves without the ptrace()
-		 * interface.
-		 */
                 if (!user_mode(regs))
                        goto clear_TF_reenable;
-		/*
-		 * Was the TF flag set by a debugger? If so, clear it now,
-		 * so that register information is correct.
-		 */
-		if (tsk->ptrace & PT_DTRACE) {
-			regs->eflags &= ~TF_MASK;
-			tsk->ptrace &= ~PT_DTRACE;
-		}
 	}
 
 	/* Ok, finally something we can handle */