Merge branch 'uprobes/core' of git://git.kernel.org/pub/scm/linux/kernel/git/oleg/misc into perf/core

Pull uprobes fixes + cleanups from Oleg Nesterov.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

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:

arch/x86/include/asm/uprobes.h

@@ -42,10 +42,11 @@ struct arch_uprobe {
 };
 
 struct arch_uprobe_task {
-	unsigned long			saved_trap_nr;
 #ifdef CONFIG_X86_64
 	unsigned long			saved_scratch_register;
 #endif
+	unsigned int			saved_trap_nr;
+	unsigned int			saved_tf;
 };
 
 extern int  arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr);

arch/x86/kernel/step.c

@@ -157,6 +157,33 @@ static int enable_single_step(struct task_struct *child)
 	return 1;
 }
 
+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;
+		set_tsk_thread_flag(task, TIF_BLOCKSTEP);
+	} else {
+		debugctl &= ~DEBUGCTLMSR_BTF;
+		clear_tsk_thread_flag(task, TIF_BLOCKSTEP);
+	}
+	if (task == current)
+		update_debugctlmsr(debugctl);
+	local_irq_enable();
+}
+
 /*
  * Enable single or block step.
  */
@@ -169,19 +196,10 @@ 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) {
+	if (enable_single_step(child) && block)
-		unsigned long debugctl = get_debugctlmsr();
+		set_task_blockstep(child, true);
-
+	else if (test_tsk_thread_flag(child, TIF_BLOCKSTEP))
-		debugctl |= DEBUGCTLMSR_BTF;
+		set_task_blockstep(child, false);
-		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);
-	}
 }
 
 void user_enable_single_step(struct task_struct *child)
@@ -199,13 +217,8 @@ void user_disable_single_step(struct task_struct *child)
 	/*
 	 * Make sure block stepping (BTF) is disabled.
 	 */
-	if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) {
+	if (test_tsk_thread_flag(child, TIF_BLOCKSTEP))
-		unsigned long debugctl = get_debugctlmsr();
+		set_task_blockstep(child, false);
-
-		debugctl &= ~DEBUGCTLMSR_BTF;
-		update_debugctlmsr(debugctl);
-		clear_tsk_thread_flag(child, TIF_BLOCKSTEP);
-	}
 
 	/* Always clear TIF_SINGLESTEP... */
 	clear_tsk_thread_flag(child, TIF_SINGLESTEP);

arch/x86/kernel/uprobes.c

@@ -41,6 +41,9 @@
 /* Adjust the return address of a call insn */
 #define UPROBE_FIX_CALL	0x2
 
+/* Instruction will modify TF, don't change it */
+#define UPROBE_FIX_SETF	0x4
+
 #define UPROBE_FIX_RIP_AX	0x8000
 #define UPROBE_FIX_RIP_CX	0x4000
 
@@ -239,6 +242,10 @@ static void prepare_fixups(struct arch_uprobe *auprobe, struct insn *insn)
 	insn_get_opcode(insn);	/* should be a nop */
 
 	switch (OPCODE1(insn)) {
+	case 0x9d:
+		/* popf */
+		auprobe->fixups |= UPROBE_FIX_SETF;
+		break;
 	case 0xc3:		/* ret/lret */
 	case 0xcb:
 	case 0xc2:
@@ -646,7 +653,7 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
  * Skip these instructions as per the currently known x86 ISA.
  * 0x66* { 0x90 | 0x0f 0x1f | 0x0f 0x19 | 0x87 0xc0 }
  */
-bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
+static bool __skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
 	int i;
 
@@ -673,3 +680,46 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	}
 	return false;
 }
+
+bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	bool ret = __skip_sstep(auprobe, regs);
+	if (ret && (regs->flags & X86_EFLAGS_TF))
+		send_sig(SIGTRAP, current, 0);
+	return ret;
+}
+
+void arch_uprobe_enable_step(struct arch_uprobe *auprobe)
+{
+	struct task_struct *task = current;
+	struct arch_uprobe_task	*autask	= &task->utask->autask;
+	struct pt_regs *regs = task_pt_regs(task);
+
+	autask->saved_tf = !!(regs->flags & X86_EFLAGS_TF);
+
+	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 task_struct *task = current;
+	struct arch_uprobe_task	*autask	= &task->utask->autask;
+	bool trapped = (task->utask->state == UTASK_SSTEP_TRAPPED);
+	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 (unlikely(trapped)) {
+		if (!autask->saved_tf)
+			regs->flags &= ~X86_EFLAGS_TF;
+	} else {
+		if (autask->saved_tf)
+			send_sig(SIGTRAP, task, 0);
+		else if (!(auprobe->fixups & UPROBE_FIX_SETF))
+			regs->flags &= ~X86_EFLAGS_TF;
+	}
+}

include/linux/sched.h

@@ -446,7 +446,8 @@ extern int get_dumpable(struct mm_struct *mm);
 #define MMF_VM_HUGEPAGE		17	/* set when VM_HUGEPAGE is set on vma */
 #define MMF_EXE_FILE_CHANGED	18	/* see prctl_set_mm_exe_file() */
 
-#define MMF_HAS_UPROBES		19	/* might have uprobes */
+#define MMF_HAS_UPROBES		19	/* has uprobes */
+#define MMF_RECALC_UPROBES	20	/* MMF_HAS_UPROBES can be wrong */
 
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)
 

include/linux/uprobes.h

@@ -112,6 +112,8 @@ extern void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm);
 extern void uprobe_free_utask(struct task_struct *t);
 extern void uprobe_copy_process(struct task_struct *t);
 extern unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs);
+extern void __weak arch_uprobe_enable_step(struct arch_uprobe *arch);
+extern void __weak arch_uprobe_disable_step(struct arch_uprobe *arch);
 extern int uprobe_post_sstep_notifier(struct pt_regs *regs);
 extern int uprobe_pre_sstep_notifier(struct pt_regs *regs);
 extern void uprobe_notify_resume(struct pt_regs *regs);

kernel/events/uprobes.c

@@ -411,11 +411,10 @@ static struct uprobe *__find_uprobe(struct inode *inode, loff_t offset)
 static struct uprobe *find_uprobe(struct inode *inode, loff_t offset)
 {
 	struct uprobe *uprobe;
-	unsigned long flags;
 
-	spin_lock_irqsave(&uprobes_treelock, flags);
+	spin_lock(&uprobes_treelock);
 	uprobe = __find_uprobe(inode, offset);
-	spin_unlock_irqrestore(&uprobes_treelock, flags);
+	spin_unlock(&uprobes_treelock);
 
 	return uprobe;
 }
@@ -462,12 +461,11 @@ static struct uprobe *__insert_uprobe(struct uprobe *uprobe)
  */
 static struct uprobe *insert_uprobe(struct uprobe *uprobe)
 {
-	unsigned long flags;
 	struct uprobe *u;
 
-	spin_lock_irqsave(&uprobes_treelock, flags);
+	spin_lock(&uprobes_treelock);
 	u = __insert_uprobe(uprobe);
-	spin_unlock_irqrestore(&uprobes_treelock, flags);
+	spin_unlock(&uprobes_treelock);
 
 	/* For now assume that the instruction need not be single-stepped */
 	uprobe->flags |= UPROBE_SKIP_SSTEP;
@@ -686,7 +684,9 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 		set_bit(MMF_HAS_UPROBES, &mm->flags);
 
 	ret = set_swbp(&uprobe->arch, mm, vaddr);
-	if (ret && first_uprobe)
+	if (!ret)
+		clear_bit(MMF_RECALC_UPROBES, &mm->flags);
+	else if (first_uprobe)
 		clear_bit(MMF_HAS_UPROBES, &mm->flags);
 
 	return ret;
@@ -695,6 +695,11 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 static void
 remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)
 {
+	/* can happen if uprobe_register() fails */
+	if (!test_bit(MMF_HAS_UPROBES, &mm->flags))
+		return;
+
+	set_bit(MMF_RECALC_UPROBES, &mm->flags);
 	set_orig_insn(&uprobe->arch, mm, vaddr);
 }
 
@@ -705,11 +710,9 @@ remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vad
  */
 static void delete_uprobe(struct uprobe *uprobe)
 {
-	unsigned long flags;
+	spin_lock(&uprobes_treelock);
-
-	spin_lock_irqsave(&uprobes_treelock, flags);
 	rb_erase(&uprobe->rb_node, &uprobes_tree);
-	spin_unlock_irqrestore(&uprobes_treelock, flags);
+	spin_unlock(&uprobes_treelock);
 	iput(uprobe->inode);
 	put_uprobe(uprobe);
 	atomic_dec(&uprobe_events);
@@ -897,7 +900,8 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *
 	}
 
 	mutex_unlock(uprobes_hash(inode));
-	put_uprobe(uprobe);
+	if (uprobe)
+		put_uprobe(uprobe);
 
 	return ret;
 }
@@ -967,7 +971,6 @@ static void build_probe_list(struct inode *inode,
 				struct list_head *head)
 {
 	loff_t min, max;
-	unsigned long flags;
 	struct rb_node *n, *t;
 	struct uprobe *u;
 
@@ -975,7 +978,7 @@ static void build_probe_list(struct inode *inode,
 	min = vaddr_to_offset(vma, start);
 	max = min + (end - start) - 1;
 
-	spin_lock_irqsave(&uprobes_treelock, flags);
+	spin_lock(&uprobes_treelock);
 	n = find_node_in_range(inode, min, max);
 	if (n) {
 		for (t = n; t; t = rb_prev(t)) {
@@ -993,7 +996,7 @@ static void build_probe_list(struct inode *inode,
 			atomic_inc(&u->ref);
 		}
 	}
-	spin_unlock_irqrestore(&uprobes_treelock, flags);
+	spin_unlock(&uprobes_treelock);
 }
 
 /*
@@ -1030,6 +1033,25 @@ int uprobe_mmap(struct vm_area_struct *vma)
 	return 0;
 }
 
+static bool
+vma_has_uprobes(struct vm_area_struct *vma, unsigned long start, unsigned long end)
+{
+	loff_t min, max;
+	struct inode *inode;
+	struct rb_node *n;
+
+	inode = vma->vm_file->f_mapping->host;
+
+	min = vaddr_to_offset(vma, start);
+	max = min + (end - start) - 1;
+
+	spin_lock(&uprobes_treelock);
+	n = find_node_in_range(inode, min, max);
+	spin_unlock(&uprobes_treelock);
+
+	return !!n;
+}
+
 /*
  * Called in context of a munmap of a vma.
  */
@@ -1041,10 +1063,12 @@ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned lon
 	if (!atomic_read(&vma->vm_mm->mm_users)) /* called by mmput() ? */
 		return;
 
-	if (!test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags))
+	if (!test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags) ||
+	     test_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags))
 		return;
 
-	/* TODO: unmapping uprobe(s) will need more work */
+	if (vma_has_uprobes(vma, start, end))
+		set_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags);
 }
 
 /* Slot allocation for XOL */
@@ -1150,8 +1174,11 @@ void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm)
 {
 	newmm->uprobes_state.xol_area = NULL;
 
-	if (test_bit(MMF_HAS_UPROBES, &oldmm->flags))
+	if (test_bit(MMF_HAS_UPROBES, &oldmm->flags)) {
 		set_bit(MMF_HAS_UPROBES, &newmm->flags);
+		/* unconditionally, dup_mmap() skips VM_DONTCOPY vmas */
+		set_bit(MMF_RECALC_UPROBES, &newmm->flags);
+	}
 }
 
 /*
@@ -1369,6 +1396,25 @@ static bool can_skip_sstep(struct uprobe *uprobe, struct pt_regs *regs)
 	return false;
 }
 
+static void mmf_recalc_uprobes(struct mm_struct *mm)
+{
+	struct vm_area_struct *vma;
+
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		if (!valid_vma(vma, false))
+			continue;
+		/*
+		 * This is not strictly accurate, we can race with
+		 * uprobe_unregister() and see the already removed
+		 * uprobe if delete_uprobe() was not yet called.
+		 */
+		if (vma_has_uprobes(vma, vma->vm_start, vma->vm_end))
+			return;
+	}
+
+	clear_bit(MMF_HAS_UPROBES, &mm->flags);
+}
+
 static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp)
 {
 	struct mm_struct *mm = current->mm;
@@ -1390,11 +1436,24 @@ static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp)
 	} else {
 		*is_swbp = -EFAULT;
 	}
+
+	if (!uprobe && test_and_clear_bit(MMF_RECALC_UPROBES, &mm->flags))
+		mmf_recalc_uprobes(mm);
 	up_read(&mm->mmap_sem);
 
 	return uprobe;
 }
 
+void __weak arch_uprobe_enable_step(struct arch_uprobe *arch)
+{
+	user_enable_single_step(current);
+}
+
+void __weak arch_uprobe_disable_step(struct arch_uprobe *arch)
+{
+	user_disable_single_step(current);
+}
+
 /*
  * Run handler and ask thread to singlestep.
  * Ensure all non-fatal signals cannot interrupt thread while it singlesteps.
@@ -1441,7 +1500,7 @@ static void handle_swbp(struct pt_regs *regs)
 
 	utask->state = UTASK_SSTEP;
 	if (!pre_ssout(uprobe, regs, bp_vaddr)) {
-		user_enable_single_step(current);
+		arch_uprobe_enable_step(&uprobe->arch);
 		return;
 	}
 
@@ -1477,10 +1536,10 @@ static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs)
 	else
 		WARN_ON_ONCE(1);
 
+	arch_uprobe_disable_step(&uprobe->arch);
 	put_uprobe(uprobe);
 	utask->active_uprobe = NULL;
 	utask->state = UTASK_RUNNING;
-	user_disable_single_step(current);
 	xol_free_insn_slot(current);
 
 	spin_lock_irq(&current->sighand->siglock);