uprobes/perf: Teach trace_uprobe/perf code to pre-filter

Finally implement uprobe_perf_filter() which checks ->nr_systemwide or
->perf_events to figure out whether we need to insert the breakpoint.

uprobe_perf_open/close are changed to do uprobe_apply(true/false) when
the new perf event comes or goes away.

Note that currently this is very suboptimal:

	- uprobe_register() called by TRACE_REG_PERF_REGISTER becomes a
	  heavy nop, consumer->filter() always returns F at this stage.

	  As it was already discussed we need uprobe_register_only() to
	  avoid the costly register_for_each_vma() when possible.

	- uprobe_apply() is oftenly overkill. Unless "nr_systemwide != 0"
	  changes we need uprobe_apply_mm(), unapply_uprobe() is almost
	  what we need.

	- uprobe_apply() can be simply avoided sometimes, see the next
	  changes.

Testing:

	# perf probe -x /lib/libc.so.6 syscall

	# perl -e 'syscall -1 while 1' &
	[1] 530

	# perf record -e probe_libc:syscall perl -e 'syscall -1 for 1..10; sleep 1'

	# perf report --show-total-period
		100.00%            10     perl  libc-2.8.so    [.] syscall

Before this patch:

	# cat /sys/kernel/debug/tracing/uprobe_profile
		/lib/libc.so.6 syscall				79291

A huge ->nrhit == 79291 reflects the fact that the background process
530 constantly hits this breakpoint too, even if doesn't contribute to
the output.

After the patch:

	# cat /sys/kernel/debug/tracing/uprobe_profile
		/lib/libc.so.6 syscall				10

This shows that only the target process was punished by int3.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>

diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 2a74a93afdae4172e52951677c2c479f9898ff91..b7850f535acf3bac93965b063e0096f18eaa3326 100644 (file)
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -557,7 +557,12 @@ static inline bool is_trace_uprobe_enabled(struct trace_uprobe *tu)
        return tu->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE);
 }
 
-static int probe_event_enable(struct trace_uprobe *tu, int flag)
+typedef bool (*filter_func_t)(struct uprobe_consumer *self,
+                               enum uprobe_filter_ctx ctx,
+                               struct mm_struct *mm);
+
+static int
+probe_event_enable(struct trace_uprobe *tu, int flag, filter_func_t filter)
 {
        int ret = 0;
 
@@ -567,6 +572,7 @@ static int probe_event_enable(struct trace_uprobe *tu, int flag)
        WARN_ON(!uprobe_filter_is_empty(&tu->filter));
 
        tu->flags |= flag;
+       tu->consumer.filter = filter;
        ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
        if (ret)
                tu->flags &= ~flag;
@@ -656,6 +662,22 @@ static int set_print_fmt(struct trace_uprobe *tu)
 }
 
 #ifdef CONFIG_PERF_EVENTS
+static bool
+__uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm)
+{
+       struct perf_event *event;
+
+       if (filter->nr_systemwide)
+               return true;
+
+       list_for_each_entry(event, &filter->perf_events, hw.tp_list) {
+               if (event->hw.tp_target->mm == mm)
+                       return true;
+       }
+
+       return false;
+}
+
 static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event)
 {
        write_lock(&tu->filter.rwlock);
@@ -665,6 +687,8 @@ static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event)
                tu->filter.nr_systemwide++;
        write_unlock(&tu->filter.rwlock);
 
+       uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
+
        return 0;
 }
 
@@ -677,9 +701,25 @@ static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event)
                tu->filter.nr_systemwide--;
        write_unlock(&tu->filter.rwlock);
 
+       uprobe_apply(tu->inode, tu->offset, &tu->consumer, false);
+
        return 0;
 }
 
+static bool uprobe_perf_filter(struct uprobe_consumer *uc,
+                               enum uprobe_filter_ctx ctx, struct mm_struct *mm)
+{
+       struct trace_uprobe *tu;
+       int ret;
+
+       tu = container_of(uc, struct trace_uprobe, consumer);
+       read_lock(&tu->filter.rwlock);
+       ret = __uprobe_perf_filter(&tu->filter, mm);
+       read_unlock(&tu->filter.rwlock);
+
+       return ret;
+}
+
 /* uprobe profile handler */
 static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs)
 {
@@ -722,7 +762,7 @@ int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type,
 
        switch (type) {
        case TRACE_REG_REGISTER:
-               return probe_event_enable(tu, TP_FLAG_TRACE);
+               return probe_event_enable(tu, TP_FLAG_TRACE, NULL);
 
        case TRACE_REG_UNREGISTER:
                probe_event_disable(tu, TP_FLAG_TRACE);
@@ -730,7 +770,7 @@ int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type,
 
 #ifdef CONFIG_PERF_EVENTS
        case TRACE_REG_PERF_REGISTER:
-               return probe_event_enable(tu, TP_FLAG_PROFILE);
+               return probe_event_enable(tu, TP_FLAG_PROFILE, uprobe_perf_filter);
 
        case TRACE_REG_PERF_UNREGISTER:
                probe_event_disable(tu, TP_FLAG_PROFILE);