Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-15 00:21:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

uprobes: turn trace_uprobe's nhit counter to be per-CPU one

Browse Source 
trace_uprobe->nhit counter is not incremented atomically, so its value
is questionable in when uprobe is hit on multiple CPUs simultaneously.

Also, doing this shared counter increment across many CPUs causes heavy
cache line bouncing, limiting uprobe/uretprobe performance scaling with
number of CPUs.

Solve both problems by making this a per-CPU counter.

Link: https://lore.kernel.org/all/20240813203409.3985398-1-andrii@kernel.org/

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
This commit is contained in:
Andrii Nakryiko 2024-08-13 13:34:09 -07:00 committed by Masami Hiramatsu (Google)
parent da3ea35007
commit 10cdb82aa7
1 changed files with 21 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
kernel/trace/trace_uprobe.c
View File

@ -17,6 +17,7 @@
#include <linux/string.h>
#include <linux/rculist.h>
#include <linux/filter.h>
#include <linux/percpu.h>
#include "trace_dynevent.h"
#include "trace_probe.h"
@ -62,7 +63,7 @@ struct trace_uprobe {
char *filename;
unsigned long offset;
unsigned long ref_ctr_offset;
unsigned long nhit;
unsigned long __percpu *nhits;
struct trace_probe tp;
};
@ -337,6 +338,12 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
if (!tu)
return ERR_PTR(-ENOMEM);
tu->nhits = alloc_percpu(unsigned long);
if (!tu->nhits) {
ret = -ENOMEM;
goto error;
}
ret = trace_probe_init(&tu->tp, event, group, true, nargs);
if (ret < 0)
goto error;
@ -349,6 +356,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
return tu;
error:
free_percpu(tu->nhits);
kfree(tu);
return ERR_PTR(ret);
@ -362,6 +370,7 @@ static void free_trace_uprobe(struct trace_uprobe *tu)
path_put(&tu->path);
trace_probe_cleanup(&tu->tp);
kfree(tu->filename);
free_percpu(tu->nhits);
kfree(tu);
}
@ -815,13 +824,21 @@ static int probes_profile_seq_show(struct seq_file *m, void *v)
{
struct dyn_event *ev = v;
struct trace_uprobe *tu;
unsigned long nhits;
int cpu;
if (!is_trace_uprobe(ev))
return 0;
tu = to_trace_uprobe(ev);
nhits = 0;
for_each_possible_cpu(cpu) {
nhits += per_cpu(*tu->nhits, cpu);
}
seq_printf(m, " %s %-44s %15lu\n", tu->filename,
trace_probe_name(&tu->tp), tu->nhit);
trace_probe_name(&tu->tp), nhits);
return 0;
}
@ -1512,7 +1529,8 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
int ret = 0;
tu = container_of(con, struct trace_uprobe, consumer);
tu->nhit++;
this_cpu_inc(*tu->nhits);
udd.tu = tu;
udd.bp_addr = instruction_pointer(regs);