From 848e8f5f0ad3169560c516fff6471be65f76e69f Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 3 Aug 2012 17:31:46 +0200 Subject: ptrace/x86: Introduce set_task_blockstep() helper No functional changes, preparation for the next fix and for uprobes single-step fixes. Move the code playing with TIF_BLOCKSTEP/DEBUGCTLMSR_BTF into the new helper, set_task_blockstep(). Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju --- arch/x86/kernel/step.c | 41 +++++++++++++++++++++-------------------- 1 file changed, 21 insertions(+), 20 deletions(-) (limited to 'arch/x86/kernel/step.c') diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index c346d116148..7a514986ca0 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -157,6 +157,21 @@ static int enable_single_step(struct task_struct *child) return 1; } +static void set_task_blockstep(struct task_struct *task, bool on) +{ + unsigned long debugctl; + + debugctl = get_debugctlmsr(); + if (on) { + debugctl |= DEBUGCTLMSR_BTF; + set_tsk_thread_flag(task, TIF_BLOCKSTEP); + } else { + debugctl &= ~DEBUGCTLMSR_BTF; + clear_tsk_thread_flag(task, TIF_BLOCKSTEP); + } + update_debugctlmsr(debugctl); +} + /* * Enable single or block step. */ @@ -169,19 +184,10 @@ static void enable_step(struct task_struct *child, bool block) * So no one should try to use debugger block stepping in a program * that uses user-mode single stepping itself. */ - if (enable_single_step(child) && block) { - unsigned long debugctl = get_debugctlmsr(); - - debugctl |= DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); - set_tsk_thread_flag(child, TIF_BLOCKSTEP); - } else if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) { - unsigned long debugctl = get_debugctlmsr(); - - debugctl &= ~DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); - clear_tsk_thread_flag(child, TIF_BLOCKSTEP); - } + if (enable_single_step(child) && block) + set_task_blockstep(child, true); + else if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) + set_task_blockstep(child, false); } void user_enable_single_step(struct task_struct *child) @@ -199,13 +205,8 @@ void user_disable_single_step(struct task_struct *child) /* * Make sure block stepping (BTF) is disabled. */ - if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) { - unsigned long debugctl = get_debugctlmsr(); - - debugctl &= ~DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); - clear_tsk_thread_flag(child, TIF_BLOCKSTEP); - } + if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) + set_task_blockstep(child, false); /* Always clear TIF_SINGLESTEP... */ clear_tsk_thread_flag(child, TIF_SINGLESTEP); -- cgit v1.2.3-70-g09d2 From 95cf00fa5d5e2a200a2c044c84bde8389a237e02 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sat, 11 Aug 2012 18:06:42 +0200 Subject: ptrace/x86: Partly fix set_task_blockstep()->update_debugctlmsr() logic Afaics the usage of update_debugctlmsr() and TIF_BLOCKSTEP in step.c was always very wrong. 1. update_debugctlmsr() was simply unneeded. The child sleeps TASK_TRACED, __switch_to_xtra(next_p => child) should notice TIF_BLOCKSTEP and set/clear DEBUGCTLMSR_BTF after resume if needed. 2. It is wrong. The state of DEBUGCTLMSR_BTF bit in CPU register should always match the state of current's TIF_BLOCKSTEP bit. 3. Even get_debugctlmsr() + update_debugctlmsr() itself does not look right. Irq can change other bits in MSR_IA32_DEBUGCTLMSR register or the caller can be preempted in between. 4. It is not safe to play with TIF_BLOCKSTEP if task != current. DEBUGCTLMSR_BTF and TIF_BLOCKSTEP should always match each other if the task is running. The tracee is stopped but it can be SIGKILL'ed right before set/clear_tsk_thread_flag(). However, now that uprobes uses user_enable_single_step(current) we can't simply remove update_debugctlmsr(). So this patch adds the additional "task == current" check and disables irqs to avoid the race with interrupts/preemption. Unfortunately this patch doesn't solve the last problem, we need another fix. Probably we should teach ptrace_stop() to set/clear single/block stepping after resume. And afaics there is yet another problem: perf can play with MSR_IA32_DEBUGCTLMSR from nmi, this obviously means that even __switch_to_xtra() has problems. Signed-off-by: Oleg Nesterov --- arch/x86/kernel/step.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel/step.c') diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 7a514986ca0..f89cdc6ccd5 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -161,6 +161,16 @@ static void set_task_blockstep(struct task_struct *task, bool on) { unsigned long debugctl; + /* + * Ensure irq/preemption can't change debugctl in between. + * Note also that both TIF_BLOCKSTEP and debugctl should + * be changed atomically wrt preemption. + * FIXME: this means that set/clear TIF_BLOCKSTEP is simply + * wrong if task != current, SIGKILL can wakeup the stopped + * tracee and set/clear can play with the running task, this + * can confuse the next __switch_to_xtra(). + */ + local_irq_disable(); debugctl = get_debugctlmsr(); if (on) { debugctl |= DEBUGCTLMSR_BTF; @@ -169,7 +179,9 @@ static void set_task_blockstep(struct task_struct *task, bool on) debugctl &= ~DEBUGCTLMSR_BTF; clear_tsk_thread_flag(task, TIF_BLOCKSTEP); } - update_debugctlmsr(debugctl); + if (task == current) + update_debugctlmsr(debugctl); + local_irq_enable(); } /* -- cgit v1.2.3-70-g09d2 From 9bd1190a11c9d2c59d35cb999b8d170ad52aab5f Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 3 Sep 2012 15:24:17 +0200 Subject: uprobes/x86: Do not (ab)use TIF_SINGLESTEP/user_*_single_step() for single-stepping user_enable/disable_single_step() was designed for ptrace, it assumes a single user and does unnecessary and wrong things for uprobes. For example: - arch_uprobe_enable_step() can't trust TIF_SINGLESTEP, an application itself can set X86_EFLAGS_TF which must be preserved after arch_uprobe_disable_step(). - we do not want to set TIF_SINGLESTEP/TIF_FORCED_TF in arch_uprobe_enable_step(), this only makes sense for ptrace. - otoh we leak TIF_SINGLESTEP if arch_uprobe_disable_step() doesn't do user_disable_single_step(), the application will be killed after the next syscall. - arch_uprobe_enable_step() does access_process_vm() we do not need/want. Change arch_uprobe_enable/disable_step() to set/clear X86_EFLAGS_TF directly, this is much simpler and more correct. However, we need to clear TIF_BLOCKSTEP/DEBUGCTLMSR_BTF before executing the probed insn, add set_task_blockstep(false). Note: with or without this patch, there is another (hopefully minor) problem. A probed "pushf" insn can see the wrong X86_EFLAGS_TF set by uprobes. Perhaps we should change _disable to update the stack, or teach arch_uprobe_skip_sstep() to emulate this insn. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju --- arch/x86/include/asm/processor.h | 2 ++ arch/x86/kernel/step.c | 2 +- arch/x86/kernel/uprobes.c | 32 ++++++++++++++++++-------------- 3 files changed, 21 insertions(+), 15 deletions(-) (limited to 'arch/x86/kernel/step.c') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d048cad9bca..433d2e5c98a 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -759,6 +759,8 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr) wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr); } +extern void set_task_blockstep(struct task_struct *task, bool on); + /* * from system description table in BIOS. Mostly for MCA use, but * others may find it useful: diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index f89cdc6ccd5..cd3b2438a98 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -157,7 +157,7 @@ static int enable_single_step(struct task_struct *child) return 1; } -static void set_task_blockstep(struct task_struct *task, bool on) +void set_task_blockstep(struct task_struct *task, bool on) { unsigned long debugctl; diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 309a0e02b12..3b4aae68efe 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -683,26 +683,30 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) void arch_uprobe_enable_step(struct arch_uprobe *auprobe) { - struct uprobe_task *utask = current->utask; - struct arch_uprobe_task *autask = &utask->autask; + struct task_struct *task = current; + struct arch_uprobe_task *autask = &task->utask->autask; + struct pt_regs *regs = task_pt_regs(task); autask->restore_flags = 0; - if (!test_tsk_thread_flag(current, TIF_SINGLESTEP) && - !(auprobe->fixups & UPROBE_FIX_SETF)) + if (!(regs->flags & X86_EFLAGS_TF) && + !(auprobe->fixups & UPROBE_FIX_SETF)) autask->restore_flags |= UPROBE_CLEAR_TF; - /* - * The state of TIF_BLOCKSTEP is not saved. With the TF flag set we - * would to examine the opcode and the flags to make it right. Without - * TF block stepping makes no sense. - */ - user_enable_single_step(current); + + regs->flags |= X86_EFLAGS_TF; + if (test_tsk_thread_flag(task, TIF_BLOCKSTEP)) + set_task_blockstep(task, false); } void arch_uprobe_disable_step(struct arch_uprobe *auprobe) { - struct uprobe_task *utask = current->utask; - struct arch_uprobe_task *autask = &utask->autask; - + struct task_struct *task = current; + struct arch_uprobe_task *autask = &task->utask->autask; + struct pt_regs *regs = task_pt_regs(task); + /* + * The state of TIF_BLOCKSTEP was not saved so we can get an extra + * SIGTRAP if we do not clear TF. We need to examine the opcode to + * make it right. + */ if (autask->restore_flags & UPROBE_CLEAR_TF) - user_disable_single_step(current); + regs->flags &= ~X86_EFLAGS_TF; } -- cgit v1.2.3-70-g09d2