Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752910Ab3FNQVv (ORCPT ); Fri, 14 Jun 2013 12:21:51 -0400 Received: from e39.co.us.ibm.com ([32.97.110.160]:48310 "EHLO e39.co.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752375Ab3FNQVt (ORCPT ); Fri, 14 Jun 2013 12:21:49 -0400 Date: Fri, 14 Jun 2013 09:21:12 -0700 From: "Paul E. McKenney" To: Steven Rostedt Cc: Masami Hiramatsu , "zhangwei(Jovi)" , Frederic Weisbecker , Ingo Molnar , Oleg Nesterov , Srikar Dronamraju , "linux-kernel@vger.kernel.org" , "yrl.pp-manager.tt@hitachi.com" Subject: Re: [PATCH] tracing/uprobes: Support ftrace_event_file base multibuffer Message-ID: <20130614162112.GO5146@linux.vnet.ibm.com> Reply-To: paulmck@linux.vnet.ibm.com References: <51BA7578.4080108@huawei.com> <51BB18EB.9080307@hitachi.com> <1371223918.9844.324.camel@gandalf.local.home> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1371223918.9844.324.camel@gandalf.local.home> User-Agent: Mutt/1.5.21 (2010-09-15) X-TM-AS-MML: No X-Content-Scanned: Fidelis XPS MAILER x-cbid: 13061416-3620-0000-0000-0000031E14A5 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 10500 Lines: 325 On Fri, Jun 14, 2013 at 11:31:58AM -0400, Steven Rostedt wrote: > On Fri, 2013-06-14 at 22:21 +0900, Masami Hiramatsu wrote: > > (2013/06/14 10:44), zhangwei(Jovi) wrote: > > > Support multi-buffer on uprobe-based dynamic events by > > > using ftrace_event_file. > > > > > > The code change is based on kprobe-based dynamic events > > > multibuffer support work commited by Masami(commit 41a7dd420c) > > > > I'm not so sure that rcu_dereference_raw() can ensure the safety > > of accessing pointer in uprobe handler. ( since kprobes disables > > irq and preempt, it could use rcu.) > > Correct. > > > > > Srikar, Oleg, could you check that? > > > > Thank you, > > > > > > > > Signed-off-by: zhangwei(Jovi) > > > Cc: Masami Hiramatsu > > > Cc: Frederic Weisbecker > > > Cc: Oleg Nesterov > > > Cc: Srikar Dronamraju > > > --- > > > kernel/trace/trace_uprobe.c | 183 +++++++++++++++++++++++++++++++++++++------ > > > 1 file changed, 161 insertions(+), 22 deletions(-) > > > > > > diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c > > > index d5d0cd3..31f08d6 100644 > > > --- a/kernel/trace/trace_uprobe.c > > > +++ b/kernel/trace/trace_uprobe.c > > > @@ -53,6 +53,7 @@ struct trace_uprobe { > > > struct list_head list; > > > struct ftrace_event_class class; > > > struct ftrace_event_call call; > > > + struct ftrace_event_file * __rcu *files; > > > struct trace_uprobe_filter filter; > > > struct uprobe_consumer consumer; > > > struct inode *inode; > > > @@ -513,7 +514,8 @@ static const struct file_operations uprobe_profile_ops = { > > > }; > > > > > > static void uprobe_trace_print(struct trace_uprobe *tu, > > > - unsigned long func, struct pt_regs *regs) > > > + unsigned long func, struct pt_regs *regs, > > > + struct ftrace_event_file *ftrace_file) > > > { > > > struct uprobe_trace_entry_head *entry; > > > struct ring_buffer_event *event; > > > @@ -522,9 +524,15 @@ static void uprobe_trace_print(struct trace_uprobe *tu, > > > int size, i; > > > struct ftrace_event_call *call = &tu->call; > > > > > > + WARN_ON(call != ftrace_file->event_call); > > > + > > > + if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags)) > > > + return; > > > + > > > size = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); > > > - event = trace_current_buffer_lock_reserve(&buffer, call->event.type, > > > - size + tu->size, 0, 0); > > > + event = trace_event_buffer_lock_reserve(&buffer, ftrace_file, > > > + call->event.type, > > > + size + tu->size, 0, 0); > > > if (!event) > > > return; > > > > > > @@ -548,15 +556,35 @@ static void uprobe_trace_print(struct trace_uprobe *tu, > > > /* uprobe handler */ > > > static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs) > > > { > > > - if (!is_ret_probe(tu)) > > > - uprobe_trace_print(tu, 0, regs); > > > + struct ftrace_event_file **file; > > > + > > > + if (is_ret_probe(tu)) > > > + return 0; > > > + > > > + file = rcu_dereference_raw(tu->files); > > Why are you using rcu_dereference_raw() and not rcu_dereference(). The > _raw() is a bit special, and unless you know what you are doing with RCU > here, don't use it. > > As I see you using rcu_dereference_raw() all over this patch, along with > mutexes, I believe that you are not using RCU correctly here. If irqs and preempt are disabled, I suggest using rcu_dereference_sched(). That is what it is there for. ;-) Thanx, Paul > -- Steve > > > > + if (unlikely(!file)) > > > + return 0; > > > + > > > + while (*file) { > > > + uprobe_trace_print(tu, 0, regs, *file); > > > + file++; > > > + } > > > + > > > return 0; > > > } > > > > > > static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func, > > > struct pt_regs *regs) > > > { > > > - uprobe_trace_print(tu, func, regs); > > > + struct ftrace_event_file **file = rcu_dereference_raw(tu->files); > > > + > > > + if (unlikely(!file)) > > > + return; > > > + > > > + while (*file) { > > > + uprobe_trace_print(tu, func, regs, *file); > > > + file++; > > > + } > > > } > > > > > > /* Event entry printers */ > > > @@ -597,6 +625,26 @@ partial: > > > return TRACE_TYPE_PARTIAL_LINE; > > > } > > > > > > + > > > +static int trace_uprobe_nr_files(struct trace_uprobe *tu) > > > +{ > > > + struct ftrace_event_file **file; > > > + int ret = 0; > > > + > > > + /* > > > + * Since all tu->files updater is protected by uprobe_enable_lock, > > > + * we don't need to lock an rcu_read_lock. > > > + */ > > > + file = rcu_dereference_raw(tu->files); > > > + if (file) > > > + while (*(file++)) > > > + ret++; > > > + > > > + return ret; > > > +} > > > + > > > +static DEFINE_MUTEX(uprobe_enable_lock); > > > + > > > static inline bool is_trace_uprobe_enabled(struct trace_uprobe *tu) > > > { > > > return tu->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE); > > > @@ -607,33 +655,123 @@ typedef bool (*filter_func_t)(struct uprobe_consumer *self, > > > struct mm_struct *mm); > > > > > > static int > > > -probe_event_enable(struct trace_uprobe *tu, int flag, filter_func_t filter) > > > +probe_event_enable(struct trace_uprobe *tu, struct ftrace_event_file *file, > > > + filter_func_t filter) > > > { > > > + int enabled = 0; > > > int ret = 0; > > > > > > + mutex_lock(&uprobe_enable_lock); > > > + > > > if (is_trace_uprobe_enabled(tu)) > > > - return -EINTR; > > > + enabled = 1; > > > + > > > + if (file) { > > > + struct ftrace_event_file **new, **old; > > > + int n = trace_uprobe_nr_files(tu); > > > + > > > + old = rcu_dereference_raw(tu->files); > > > + /* 1 is for new one and 1 is for stopper */ > > > + new = kzalloc((n + 2) * sizeof(struct ftrace_event_file *), > > > + GFP_KERNEL); > > > + if (!new) { > > > + ret = -ENOMEM; > > > + goto out_unlock; > > > + } > > > + memcpy(new, old, n * sizeof(struct ftrace_event_file *)); > > > + new[n] = file; > > > + /* The last one keeps a NULL */ > > > + > > > + rcu_assign_pointer(tu->files, new); > > > + tu->flags |= TP_FLAG_TRACE; > > > + > > > + if (old) { > > > + /* Make sure the probe is done with old files */ > > > + synchronize_sched(); > > > + kfree(old); > > > + } > > > + } else > > > + tu->flags |= TP_FLAG_PROFILE; > > > > > > 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; > > > + if (!enabled) { > > > + tu->consumer.filter = filter; > > > + ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); > > > + if (ret) > > > + tu->flags &= file ? ~TP_FLAG_TRACE : ~TP_FLAG_PROFILE; > > > + } > > > > > > + out_unlock: > > > + mutex_unlock(&uprobe_enable_lock); > > > return ret; > > > } > > > > > > -static void probe_event_disable(struct trace_uprobe *tu, int flag) > > > +static int > > > +trace_uprobe_file_index(struct trace_uprobe *tu, struct ftrace_event_file *file) > > > { > > > - if (!is_trace_uprobe_enabled(tu)) > > > - return; > > > + struct ftrace_event_file **files; > > > + int i; > > > + > > > + /* > > > + * Since all tu->files updater is protected by uprobe_enable_lock, > > > + * we don't need to lock an rcu_read_lock. > > > + */ > > > + files = rcu_dereference_raw(tu->files); > > > + if (files) { > > > + for (i = 0; files[i]; i++) > > > + if (files[i] == file) > > > + return i; > > > + } > > > + > > > + return -1; > > > +} > > > + > > > +static void > > > +probe_event_disable(struct trace_uprobe *tu, struct ftrace_event_file *file) > > > +{ > > > + mutex_lock(&uprobe_enable_lock); > > > + > > > + if (file) { > > > + struct ftrace_event_file **new, **old; > > > + int n = trace_uprobe_nr_files(tu); > > > + int i, j; > > > + > > > + old = rcu_dereference_raw(tu->files); > > > + if (n == 0 || trace_uprobe_file_index(tu, file) < 0) > > > + goto out_unlock; > > > + > > > + if (n == 1) { /* Remove the last file */ > > > + tu->flags &= ~TP_FLAG_TRACE; > > > + new = NULL; > > > + } else { > > > + new = kzalloc(n * sizeof(struct ftrace_event_file *), > > > + GFP_KERNEL); > > > + if (!new) > > > + goto out_unlock; > > > + > > > + /* This copy & check loop copies the NULL stopper too */ > > > + for (i = 0, j = 0; j < n && i < n + 1; i++) > > > + if (old[i] != file) > > > + new[j++] = old[i]; > > > + } > > > + > > > + rcu_assign_pointer(tu->files, new); > > > + > > > + /* Make sure the probe is done with old files */ > > > + synchronize_sched(); > > > + kfree(old); > > > + } else > > > + tu->flags &= ~TP_FLAG_PROFILE; > > > + > > > > > > WARN_ON(!uprobe_filter_is_empty(&tu->filter)); > > > > > > - uprobe_unregister(tu->inode, tu->offset, &tu->consumer); > > > - tu->flags &= ~flag; > > > + if (!is_trace_uprobe_enabled(tu)) > > > + uprobe_unregister(tu->inode, tu->offset, &tu->consumer); > > > + > > > + out_unlock: > > > + mutex_unlock(&uprobe_enable_lock); > > > } > > > > > > static int uprobe_event_define_fields(struct ftrace_event_call *event_call) > > > @@ -869,21 +1007,22 @@ static > > > int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, void *data) > > > { > > > struct trace_uprobe *tu = event->data; > > > + struct ftrace_event_file *file = data; > > > > > > switch (type) { > > > case TRACE_REG_REGISTER: > > > - return probe_event_enable(tu, TP_FLAG_TRACE, NULL); > > > + return probe_event_enable(tu, file, NULL); > > > > > > case TRACE_REG_UNREGISTER: > > > - probe_event_disable(tu, TP_FLAG_TRACE); > > > + probe_event_disable(tu, file); > > > return 0; > > > > > > #ifdef CONFIG_PERF_EVENTS > > > case TRACE_REG_PERF_REGISTER: > > > - return probe_event_enable(tu, TP_FLAG_PROFILE, uprobe_perf_filter); > > > + return probe_event_enable(tu, NULL, uprobe_perf_filter); > > > > > > case TRACE_REG_PERF_UNREGISTER: > > > - probe_event_disable(tu, TP_FLAG_PROFILE); > > > + probe_event_disable(tu, NULL); > > > return 0; > > > > > > case TRACE_REG_PERF_OPEN: > > > > > > > > > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/