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>

4 files changed, 88 insertions, 22 deletions

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/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h
index f3971bbcd1d..8ff8be7835a 100644
--- a/arch/x86/include/asm/uprobes.h
+++ b/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);
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index c346d116148..cd3b2438a98 100644
--- a/arch/x86/kernel/step.c
+++ b/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) {
-                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 +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)) {
-                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);
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 36fd42091fa..9538f00827a 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/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;
+        }
+}