perf/uprobe: split uprobe_unregister()

With uprobe_unregister() having grown a synchronize_srcu(), it becomes
fairly slow to call. Esp. since both users of this API call it in a
loop.

Peel off the sync_srcu() and do it once, after the loop.

We also need to add uprobe_unregister_sync() into uprobe_register()'s
error handling path, as we need to be careful about returning to the
caller before we have a guarantee that partially attached consumer won't
be called anymore. This is an unlikely slow path and this should be
totally fine to be slow in the case of a failed attach.

Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: "Peter Zijlstra (Intel)" <[email protected]>
Co-developed-by: Andrii Nakryiko <[email protected]>
Signed-off-by: Andrii Nakryiko <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Oleg Nesterov <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: Peter Zijlstra

include/linux/uprobes.h

@@ -115,7 +115,8 @@ extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs);
 extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t);
 extern struct uprobe *uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc);
 extern int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool);
-extern void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc);
+extern void uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc);
+extern void uprobe_unregister_sync(void);
 extern int uprobe_mmap(struct vm_area_struct *vma);
 extern void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end);
 extern void uprobe_start_dup_mmap(void);
@@ -164,7 +165,10 @@ uprobe_apply(struct uprobe* uprobe, struct uprobe_consumer *uc, bool add)
 	return -ENOSYS;
 }
 static inline void
-uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc)
+uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc)
+{
+}
+static inline void uprobe_unregister_sync(void)
 {
 }
 static inline int uprobe_mmap(struct vm_area_struct *vma)

kernel/events/uprobes.c

@@ -1105,11 +1105,11 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new)
 }
 
 /**
- * uprobe_unregister - unregister an already registered probe.
+ * uprobe_unregister_nosync - unregister an already registered probe.
  * @uprobe: uprobe to remove
  * @uc: identify which probe if multiple probes are colocated.
  */
-void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc)
+void uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc)
 {
 	int err;
 
@@ -1121,12 +1121,15 @@ void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc)
 	/* TODO : cant unregister? schedule a worker thread */
 	if (unlikely(err)) {
 		uprobe_warn(current, "unregister, leaking uprobe");
-		goto out_sync;
+		return;
 	}
 
 	put_uprobe(uprobe);
+}
+EXPORT_SYMBOL_GPL(uprobe_unregister_nosync);
 
-out_sync:
+void uprobe_unregister_sync(void)
+{
 	/*
 	 * Now that handler_chain() and handle_uretprobe_chain() iterate over
 	 * uprobe->consumers list under RCU protection without holding
@@ -1138,7 +1141,7 @@ void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc)
 	 */
 	synchronize_srcu(&uprobes_srcu);
 }
-EXPORT_SYMBOL_GPL(uprobe_unregister);
+EXPORT_SYMBOL_GPL(uprobe_unregister_sync);
 
 /**
  * uprobe_register - register a probe
@@ -1196,7 +1199,13 @@ struct uprobe *uprobe_register(struct inode *inode,
 	up_write(&uprobe->register_rwsem);
 
 	if (ret) {
-		uprobe_unregister(uprobe, uc);
+		uprobe_unregister_nosync(uprobe, uc);
+		/*
+		 * Registration might have partially succeeded, so we can have
+		 * this consumer being called right at this time. We need to
+		 * sync here. It's ok, it's unlikely slow path.
+		 */
+		uprobe_unregister_sync();
 		return ERR_PTR(ret);
 	}
 

kernel/trace/bpf_trace.c

@@ -3184,7 +3184,10 @@ static void bpf_uprobe_unregister(struct bpf_uprobe *uprobes, u32 cnt)
 	u32 i;
 
 	for (i = 0; i < cnt; i++)
-		uprobe_unregister(uprobes[i].uprobe, &uprobes[i].consumer);
+		uprobe_unregister_nosync(uprobes[i].uprobe, &uprobes[i].consumer);
+
+	if (cnt)
+		uprobe_unregister_sync();
 }
 
 static void bpf_uprobe_multi_link_release(struct bpf_link *link)

kernel/trace/trace_uprobe.c

@@ -1097,6 +1097,7 @@ static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter)
 static void __probe_event_disable(struct trace_probe *tp)
 {
 	struct trace_uprobe *tu;
+	bool sync = false;
 
 	tu = container_of(tp, struct trace_uprobe, tp);
 	WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter));
@@ -1105,9 +1106,12 @@ static void __probe_event_disable(struct trace_probe *tp)
 		if (!tu->uprobe)
 			continue;
 
-		uprobe_unregister(tu->uprobe, &tu->consumer);
+		uprobe_unregister_nosync(tu->uprobe, &tu->consumer);
+		sync = true;
 		tu->uprobe = NULL;
 	}
+	if (sync)
+		uprobe_unregister_sync();
 }
 
 static int probe_event_enable(struct trace_event_call *call,

tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c

@@ -475,7 +475,8 @@ static void testmod_unregister_uprobe(void)
 	mutex_lock(&testmod_uprobe_mutex);
 
 	if (uprobe.uprobe) {
-		uprobe_unregister(uprobe.uprobe, &uprobe.consumer);
+		uprobe_unregister_nosync(uprobe.uprobe, &uprobe.consumer);
+		uprobe_unregister_sync();
 		path_put(&uprobe.path);
 		uprobe.uprobe = NULL;
 	}