Merge branch 'uprobes/core' of...

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

Pull uprobes updates from Oleg Nesterov:

 - "uretprobes" - an optimization to uprobes, like kretprobes are an optimization
   to kprobes. "perf probe -x file sym%return" now works like kretprobes.

 - PowerPC fixes plus a couple of cleanups/optimizations in uprobes and trace_uprobes.
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Documentation/trace/uprobetracer.txt

-		Uprobe-tracer: Uprobe-based Event Tracing
-		=========================================
-                 Documentation written by Srikar Dronamraju
+            Uprobe-tracer: Uprobe-based Event Tracing
+            =========================================
+
+           Documentation written by Srikar Dronamraju
+
 
 Overview
 --------
@@ -13,78 +15,94 @@ current_tracer. Instead of that, add probe points via
 /sys/kernel/debug/tracing/events/uprobes/<EVENT>/enabled.
 
 However unlike kprobe-event tracer, the uprobe event interface expects the
-user to calculate the offset of the probepoint in the object
+user to calculate the offset of the probepoint in the object.
 
 Synopsis of uprobe_tracer
 -------------------------
-  p[:[GRP/]EVENT] PATH:SYMBOL[+offs] [FETCHARGS]	: Set a probe
+  p[:[GRP/]EVENT] PATH:SYMBOL[+offs] [FETCHARGS] : Set a uprobe
+  r[:[GRP/]EVENT] PATH:SYMBOL[+offs] [FETCHARGS] : Set a return uprobe (uretprobe)
+  -:[GRP/]EVENT                                  : Clear uprobe or uretprobe event
 
- GRP		: Group name. If omitted, use "uprobes" for it.
- EVENT		: Event name. If omitted, the event name is generated
-		  based on SYMBOL+offs.
- PATH		: path to an executable or a library.
- SYMBOL[+offs]	: Symbol+offset where the probe is inserted.
+  GRP           : Group name. If omitted, "uprobes" is the default value.
+  EVENT         : Event name. If omitted, the event name is generated based
+                  on SYMBOL+offs.
+  PATH          : Path to an executable or a library.
+  SYMBOL[+offs] : Symbol+offset where the probe is inserted.
 
- FETCHARGS	: Arguments. Each probe can have up to 128 args.
-  %REG		: Fetch register REG
+  FETCHARGS     : Arguments. Each probe can have up to 128 args.
+   %REG         : Fetch register REG
 
 Event Profiling
 ---------------
- You can check the total number of probe hits and probe miss-hits via
+You can check the total number of probe hits and probe miss-hits via
 /sys/kernel/debug/tracing/uprobe_profile.
- The first column is event name, the second is the number of probe hits,
+The first column is event name, the second is the number of probe hits,
 the third is the number of probe miss-hits.
 
 Usage examples
 --------------
-To add a probe as a new event, write a new definition to uprobe_events
-as below.
+ * Add a probe as a new uprobe event, write a new definition to uprobe_events
+as below: (sets a uprobe at an offset of 0x4245c0 in the executable /bin/bash)
+
+    echo 'p: /bin/bash:0x4245c0' > /sys/kernel/debug/tracing/uprobe_events
+
+ * Add a probe as a new uretprobe event:
+
+    echo 'r: /bin/bash:0x4245c0' > /sys/kernel/debug/tracing/uprobe_events
+
+ * Unset registered event:
 
-  echo 'p: /bin/bash:0x4245c0' > /sys/kernel/debug/tracing/uprobe_events
+    echo '-:bash_0x4245c0' >> /sys/kernel/debug/tracing/uprobe_events
 
- This sets a uprobe at an offset of 0x4245c0 in the executable /bin/bash
+ * Print out the events that are registered:
 
-  echo > /sys/kernel/debug/tracing/uprobe_events
+    cat /sys/kernel/debug/tracing/uprobe_events
 
- This clears all probe points.
+ * Clear all events:
 
-The following example shows how to dump the instruction pointer and %ax
-a register at the probed text address.  Here we are trying to probe
-function zfree in /bin/zsh
+    echo > /sys/kernel/debug/tracing/uprobe_events
+
+Following example shows how to dump the instruction pointer and %ax register
+at the probed text address. Probe zfree function in /bin/zsh:
 
     # cd /sys/kernel/debug/tracing/
-    # cat /proc/`pgrep  zsh`/maps | grep /bin/zsh | grep r-xp
+    # cat /proc/`pgrep zsh`/maps | grep /bin/zsh | grep r-xp
     00400000-0048a000 r-xp 00000000 08:03 130904 /bin/zsh
     # objdump -T /bin/zsh | grep -w zfree
     0000000000446420 g    DF .text  0000000000000012  Base        zfree
 
-0x46420 is the offset of zfree in object /bin/zsh that is loaded at
-0x00400000. Hence the command to probe would be :
+  0x46420 is the offset of zfree in object /bin/zsh that is loaded at
+  0x00400000. Hence the command to uprobe would be:
+
+    # echo 'p:zfree_entry /bin/zsh:0x46420 %ip %ax' > uprobe_events
+
+  And the same for the uretprobe would be:
 
-    # echo 'p /bin/zsh:0x46420 %ip %ax' > uprobe_events
+    # echo 'r:zfree_exit /bin/zsh:0x46420 %ip %ax' >> uprobe_events
 
-Please note: User has to explicitly calculate the offset of the probepoint
+Please note: User has to explicitly calculate the offset of the probe-point
 in the object. We can see the events that are registered by looking at the
 uprobe_events file.
 
     # cat uprobe_events
-    p:uprobes/p_zsh_0x46420 /bin/zsh:0x00046420 arg1=%ip arg2=%ax
+    p:uprobes/zfree_entry /bin/zsh:0x00046420 arg1=%ip arg2=%ax
+    r:uprobes/zfree_exit /bin/zsh:0x00046420 arg1=%ip arg2=%ax
 
-The format of events can be seen by viewing the file events/uprobes/p_zsh_0x46420/format
+Format of events can be seen by viewing the file events/uprobes/zfree_entry/format
 
-    # cat events/uprobes/p_zsh_0x46420/format
-    name: p_zsh_0x46420
+    # cat events/uprobes/zfree_entry/format
+    name: zfree_entry
     ID: 922
     format:
-	field:unsigned short common_type;	offset:0;	size:2;	signed:0;
-	field:unsigned char common_flags;	offset:2;	size:1;	signed:0;
-	field:unsigned char common_preempt_count;	offset:3;	size:1;	signed:0;
-	field:int common_pid;	offset:4;	size:4;	signed:1;
-	field:int common_padding;	offset:8;	size:4;	signed:1;
+         field:unsigned short common_type;         offset:0;  size:2; signed:0;
+         field:unsigned char common_flags;         offset:2;  size:1; signed:0;
+         field:unsigned char common_preempt_count; offset:3;  size:1; signed:0;
+         field:int common_pid;                     offset:4;  size:4; signed:1;
+         field:int common_padding;                 offset:8;  size:4; signed:1;
 
-	field:unsigned long __probe_ip;	offset:12;	size:4;	signed:0;
-	field:u32 arg1;	offset:16;	size:4;	signed:0;
-	field:u32 arg2;	offset:20;	size:4;	signed:0;
+         field:unsigned long __probe_ip;           offset:12; size:4; signed:0;
+         field:u32 arg1;                           offset:16; size:4; signed:0;
+         field:u32 arg2;                           offset:20; size:4; signed:0;
 
     print fmt: "(%lx) arg1=%lx arg2=%lx", REC->__probe_ip, REC->arg1, REC->arg2
 
@@ -94,6 +112,7 @@ events, you need to enable it by:
     # echo 1 > events/uprobes/enable
 
 Lets disable the event after sleeping for some time.
+
     # sleep 20
     # echo 0 > events/uprobes/enable
 
@@ -104,10 +123,11 @@ And you can see the traced information via /sys/kernel/debug/tracing/trace.
     #
     #           TASK-PID    CPU#    TIMESTAMP  FUNCTION
     #              | |       |          |         |
-                 zsh-24842 [006] 258544.995456: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79
-                 zsh-24842 [007] 258545.000270: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79
-                 zsh-24842 [002] 258545.043929: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79
-                 zsh-24842 [004] 258547.046129: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79
-
-Each line shows us probes were triggered for a pid 24842 with ip being
-0x446421 and contents of ax register being 79.
+                 zsh-24842 [006] 258544.995456: zfree_entry: (0x446420) arg1=446420 arg2=79
+                 zsh-24842 [007] 258545.000270: zfree_exit:  (0x446540 <- 0x446420) arg1=446540 arg2=0
+                 zsh-24842 [002] 258545.043929: zfree_entry: (0x446420) arg1=446420 arg2=79
+                 zsh-24842 [004] 258547.046129: zfree_exit:  (0x446540 <- 0x446420) arg1=446540 arg2=0
+
+Output shows us uprobe was triggered for a pid 24842 with ip being 0x446420
+and contents of ax register being 79. And uretprobe was triggered with ip at
+0x446540 with counterpart function entry at 0x446420.

arch/powerpc/include/asm/uprobes.h

@@ -51,4 +51,5 @@ extern int  arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs);
 extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk);
 extern int  arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data);
 extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs);
+extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs);
 #endif	/* _ASM_UPROBES_H */

arch/powerpc/kernel/uprobes.c

@@ -30,6 +30,16 @@
 
 #define UPROBE_TRAP_NR	UINT_MAX
 
+/**
+ * is_trap_insn - check if the instruction is a trap variant
+ * @insn: instruction to be checked.
+ * Returns true if @insn is a trap variant.
+ */
+bool is_trap_insn(uprobe_opcode_t *insn)
+{
+	return (is_trap(*insn));
+}
+
 /**
  * arch_uprobe_analyze_insn
  * @mm: the probed address space.
@@ -43,12 +53,6 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe,
 	if (addr & 0x03)
 		return -EINVAL;
 
-	/*
-	 * We currently don't support a uprobe on an already
-	 * existing breakpoint instruction underneath
-	 */
-	if (is_trap(auprobe->ainsn))
-		return -ENOTSUPP;
 	return 0;
 }
 
@@ -188,3 +192,16 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
 	return false;
 }
+
+unsigned long
+arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs)
+{
+	unsigned long orig_ret_vaddr;
+
+	orig_ret_vaddr = regs->link;
+
+	/* Replace the return addr with trampoline addr */
+	regs->link = trampoline_vaddr;
+
+	return orig_ret_vaddr;
+}

arch/x86/include/asm/uprobes.h

@@ -55,4 +55,5 @@ extern int  arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs);
 extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk);
 extern int  arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data);
 extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs);
+extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs);
 #endif	/* _ASM_UPROBES_H */

arch/x86/kernel/uprobes.c

@@ -697,3 +697,32 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 		send_sig(SIGTRAP, current, 0);
 	return ret;
 }
+
+unsigned long
+arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs)
+{
+	int rasize, ncopied;
+	unsigned long orig_ret_vaddr = 0; /* clear high bits for 32-bit apps */
+
+	rasize = is_ia32_task() ? 4 : 8;
+	ncopied = copy_from_user(&orig_ret_vaddr, (void __user *)regs->sp, rasize);
+	if (unlikely(ncopied))
+		return -1;
+
+	/* check whether address has been already hijacked */
+	if (orig_ret_vaddr == trampoline_vaddr)
+		return orig_ret_vaddr;
+
+	ncopied = copy_to_user((void __user *)regs->sp, &trampoline_vaddr, rasize);
+	if (likely(!ncopied))
+		return orig_ret_vaddr;
+
+	if (ncopied != rasize) {
+		pr_err("uprobe: return address clobbered: pid=%d, %%sp=%#lx, "
+			"%%ip=%#lx\n", current->pid, regs->sp, regs->ip);
+
+		force_sig_info(SIGSEGV, SEND_SIG_FORCED, current);
+	}
+
+	return -1;
+}

include/linux/uprobes.h

@@ -38,6 +38,8 @@ struct inode;
 #define UPROBE_HANDLER_REMOVE		1
 #define UPROBE_HANDLER_MASK		1
 
+#define MAX_URETPROBE_DEPTH		64
+
 enum uprobe_filter_ctx {
 	UPROBE_FILTER_REGISTER,
 	UPROBE_FILTER_UNREGISTER,
@@ -46,6 +48,9 @@ enum uprobe_filter_ctx {
 
 struct uprobe_consumer {
 	int (*handler)(struct uprobe_consumer *self, struct pt_regs *regs);
+	int (*ret_handler)(struct uprobe_consumer *self,
+				unsigned long func,
+				struct pt_regs *regs);
 	bool (*filter)(struct uprobe_consumer *self,
 				enum uprobe_filter_ctx ctx,
 				struct mm_struct *mm);
@@ -68,6 +73,8 @@ struct uprobe_task {
 	enum uprobe_task_state		state;
 	struct arch_uprobe_task		autask;
 
+	struct return_instance		*return_instances;
+	unsigned int			depth;
 	struct uprobe			*active_uprobe;
 
 	unsigned long			xol_vaddr;
@@ -100,6 +107,7 @@ struct uprobes_state {
 extern int __weak set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
 extern int __weak set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
 extern bool __weak is_swbp_insn(uprobe_opcode_t *insn);
+extern bool __weak is_trap_insn(uprobe_opcode_t *insn);
 extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
 extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool);
 extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);

kernel/trace/trace.h

@@ -103,11 +103,6 @@ struct kretprobe_trace_entry_head {
 	unsigned long		ret_ip;
 };
 
-struct uprobe_trace_entry_head {
-	struct trace_entry	ent;
-	unsigned long		ip;
-};
-
 /*
  * trace_flag_type is an enumeration that holds different
  * states when a trace occurs. These are: