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) <peterz@infradead.org>
Signed-off-by: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Co-developed-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/r/20240903174603.3554182-6-andrii@kernel.org

diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index f112b56e947987de8005fcf6d2a685771e0ffe35..2b294bf1881fef3cb1d05b9bf2d8862710cad8d1 100644 (file)
--- a/include/linux/uprobes.h
+++ b/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)

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index e15c0306e5354511f7c307dfbf034b9366a8ec64..694f6790e84849331a07fc454b3591c7189185c0 100644 (file)
--- a/kernel/events/uprobes.c
+++ b/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 @@ out_sync:
         */
        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);
        }
 

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index c99bf06176025f164cba535af2e8682bca952827..ac0a01cc8634a994f2fc2a6d0e8775046c0ec571 100644 (file)
--- a/kernel/trace/bpf_trace.c
+++ b/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)

diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 7eb79e0a535250dc75a7b40f710e9514a5b3894e..f7443e996b1b883d98db9cfce8adad2e70cee1e0 100644 (file)
--- a/kernel/trace/trace_uprobe.c
+++ b/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,

diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index 3c0515a278427a2f28bb96b39e0a952b888aa2dc..1fc16657cf425f44fbd248c0f08d0f4a42126360 100644 (file)
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/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;
        }