linux-trace-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
To: Alexei Starovoitov <alexei.starovoitov@gmail.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Florent Revest <revest@chromium.org>
Cc: linux-trace-kernel@vger.kernel.org,
	LKML <linux-kernel@vger.kernel.org>,
	Martin KaFai Lau <martin.lau@linux.dev>,
	bpf <bpf@vger.kernel.org>, Sven Schnelle <svens@linux.ibm.com>,
	Alexei Starovoitov <ast@kernel.org>, Jiri Olsa <jolsa@kernel.org>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Alan Maguire <alan.maguire@oracle.com>,
	Mark Rutland <mark.rutland@arm.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Thomas Gleixner <tglx@linutronix.de>, Guo Ren <guoren@kernel.org>
Subject: [RFC PATCH v2 13/31] function_graph: Add "task variables" per task for fgraph_ops
Date: Wed,  8 Nov 2023 23:26:53 +0900	[thread overview]
Message-ID: <169945361301.55307.14643353930499117634.stgit@devnote2> (raw)
In-Reply-To: <169945345785.55307.5003201137843449313.stgit@devnote2>

From: Steven Rostedt (VMware) <rostedt@goodmis.org>

Add a "task variables" array on the tasks shadow ret_stack that is the
size of longs for each possible registered fgraph_ops. That's a total
of 16, taking up 8 * 16 = 128 bytes (out of a page size 4k).

This will allow for fgraph_ops to do specific features on a per task basis
having a way to maintain state for each task.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 Changes in v2:
  - Make description lines shorter than 76 chars.
---
 include/linux/ftrace.h |    2 +
 kernel/trace/fgraph.c  |   73 +++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 74 insertions(+), 1 deletion(-)

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index d30eb8a97a50..3f9f1f48e8fd 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -1071,6 +1071,7 @@ struct fgraph_ops {
 	trace_func_graph_ret_t		retfunc;
 	struct ftrace_ops		ops; /* for the hash lists */
 	void				*private;
+	int				idx;
 };
 
 /*
@@ -1109,6 +1110,7 @@ ftrace_graph_get_ret_stack(struct task_struct *task, int idx);
 
 unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
 				    unsigned long ret, unsigned long *retp);
+unsigned long *fgraph_get_task_var(struct fgraph_ops *gops);
 
 /*
  * Sometimes we don't want to trace a function with the function
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 97cf320d20a8..79bdd3c775dd 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -92,10 +92,18 @@ enum {
 #define SHADOW_STACK_SIZE (PAGE_SIZE)
 #define SHADOW_STACK_INDEX (SHADOW_STACK_SIZE / sizeof(long))
 /* Leave on a buffer at the end */
-#define SHADOW_STACK_MAX_INDEX (SHADOW_STACK_INDEX - (FGRAPH_RET_INDEX + 1))
+#define SHADOW_STACK_MAX_INDEX				\
+	(SHADOW_STACK_INDEX - (FGRAPH_RET_INDEX + 1 + FGRAPH_ARRAY_SIZE))
 
 #define RET_STACK(t, index) ((struct ftrace_ret_stack *)(&(t)->ret_stack[index]))
 
+/*
+ * Each fgraph_ops has a reservered unsigned long at the end (top) of the
+ * ret_stack to store task specific state.
+ */
+#define SHADOW_STACK_TASK_VARS(ret_stack) \
+	((unsigned long *)(&(ret_stack)[SHADOW_STACK_INDEX - FGRAPH_ARRAY_SIZE]))
+
 DEFINE_STATIC_KEY_FALSE(kill_ftrace_graph);
 int ftrace_graph_active;
 
@@ -131,6 +139,44 @@ static void return_run(struct ftrace_graph_ret *trace, struct fgraph_ops *ops)
 {
 }
 
+static void ret_stack_set_task_var(struct task_struct *t, int idx, long val)
+{
+	unsigned long *gvals = SHADOW_STACK_TASK_VARS(t->ret_stack);
+
+	gvals[idx] = val;
+}
+
+static unsigned long *
+ret_stack_get_task_var(struct task_struct *t, int idx)
+{
+	unsigned long *gvals = SHADOW_STACK_TASK_VARS(t->ret_stack);
+
+	return &gvals[idx];
+}
+
+static void ret_stack_init_task_vars(unsigned long *ret_stack)
+{
+	unsigned long *gvals = SHADOW_STACK_TASK_VARS(ret_stack);
+
+	memset(gvals, 0, sizeof(*gvals) * FGRAPH_ARRAY_SIZE);
+}
+
+/**
+ * fgraph_get_task_var - retrieve a task specific state variable
+ * @gops: The ftrace_ops that owns the task specific variable
+ *
+ * Every registered fgraph_ops has a task state variable
+ * reserved on the task's ret_stack. This function returns the
+ * address to that variable.
+ *
+ * Returns the address to the fgraph_ops @gops tasks specific
+ * unsigned long variable.
+ */
+unsigned long *fgraph_get_task_var(struct fgraph_ops *gops)
+{
+	return ret_stack_get_task_var(current, gops->idx);
+}
+
 /*
  * @offset: The index into @t->ret_stack to find the ret_stack entry
  * @index: Where to place the index into @t->ret_stack of that entry
@@ -708,6 +754,7 @@ static int alloc_retstack_tasklist(unsigned long **ret_stack_list)
 
 		if (t->ret_stack == NULL) {
 			atomic_set(&t->trace_overrun, 0);
+			ret_stack_init_task_vars(ret_stack_list[start]);
 			t->curr_ret_stack = 0;
 			t->curr_ret_depth = -1;
 			/* Make sure the tasks see the 0 first: */
@@ -768,6 +815,7 @@ static void
 graph_init_task(struct task_struct *t, unsigned long *ret_stack)
 {
 	atomic_set(&t->trace_overrun, 0);
+	ret_stack_init_task_vars(ret_stack);
 	t->ftrace_timestamp = 0;
 	t->curr_ret_stack = 0;
 	t->curr_ret_depth = -1;
@@ -866,6 +914,24 @@ static int start_graph_tracing(void)
 	return ret;
 }
 
+static void init_task_vars(int idx)
+{
+	struct task_struct *g, *t;
+	int cpu;
+
+	for_each_online_cpu(cpu) {
+		if (idle_task(cpu)->ret_stack)
+			ret_stack_set_task_var(idle_task(cpu), idx, 0);
+	}
+
+	read_lock(&tasklist_lock);
+	for_each_process_thread(g, t) {
+		if (t->ret_stack)
+			ret_stack_set_task_var(t, idx, 0);
+	}
+	read_unlock(&tasklist_lock);
+}
+
 int register_ftrace_graph(struct fgraph_ops *gops)
 {
 	int command = 0;
@@ -901,6 +967,7 @@ int register_ftrace_graph(struct fgraph_ops *gops)
 	fgraph_array[i] = gops;
 	if (i + 1 > fgraph_array_cnt)
 		fgraph_array_cnt = i + 1;
+	gops->idx = i;
 
 	ftrace_graph_active++;
 
@@ -918,6 +985,8 @@ int register_ftrace_graph(struct fgraph_ops *gops)
 		ftrace_graph_return = return_run;
 		ftrace_graph_entry = entry_run;
 		command = FTRACE_START_FUNC_RET;
+	} else {
+		init_task_vars(gops->idx);
 	}
 
 	ret = ftrace_startup(&gops->ops, command);
@@ -942,6 +1011,8 @@ void unregister_ftrace_graph(struct fgraph_ops *gops)
 	if (i >= fgraph_array_cnt)
 		goto out;
 
+	WARN_ON_ONCE(gops->idx != i);
+
 	fgraph_array[i] = &fgraph_stub;
 	if (i + 1 == fgraph_array_cnt) {
 		for (; i >= 0; i--)


  parent reply	other threads:[~2023-11-08 14:26 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-11-08 14:24 [RFC PATCH v2 00/31] tracing: fprobe: function_graph: Multi-function graph and fprobe on fgraph Masami Hiramatsu (Google)
2023-11-08 14:24 ` [RFC PATCH v2 01/31] tracing: Add a comment about ftrace_regs definition Masami Hiramatsu (Google)
2023-11-08 23:14   ` Masami Hiramatsu
2023-11-10 11:11     ` Mark Rutland
2023-11-11  2:24       ` Masami Hiramatsu
2023-11-08 14:24 ` [RFC PATCH v2 02/31] x86: tracing: Add ftrace_regs definition in the header Masami Hiramatsu (Google)
2023-11-08 14:24 ` [RFC PATCH v2 03/31] seq_buf: Export seq_buf_puts() Masami Hiramatsu (Google)
2023-11-08 14:25 ` [RFC PATCH v2 04/31] function_graph: Convert ret_stack to a series of longs Masami Hiramatsu (Google)
2023-11-08 14:25 ` [RFC PATCH v2 05/31] fgraph: Use BUILD_BUG_ON() to make sure we have structures divisible by long Masami Hiramatsu (Google)
2023-11-08 14:25 ` [RFC PATCH v2 06/31] function_graph: Add an array structure that will allow multiple callbacks Masami Hiramatsu (Google)
2023-11-08 14:25 ` [RFC PATCH v2 07/31] function_graph: Allow multiple users to attach to function graph Masami Hiramatsu (Google)
2023-11-08 14:25 ` [RFC PATCH v2 08/31] function_graph: Remove logic around ftrace_graph_entry and return Masami Hiramatsu (Google)
2023-11-08 14:26 ` [RFC PATCH v2 09/31] ftrace/function_graph: Pass fgraph_ops to function graph callbacks Masami Hiramatsu (Google)
2023-11-08 14:26 ` [RFC PATCH v2 10/31] ftrace: Allow function_graph tracer to be enabled in instances Masami Hiramatsu (Google)
2023-11-08 14:26 ` [RFC PATCH v2 11/31] ftrace: Allow ftrace startup flags exist without dynamic ftrace Masami Hiramatsu (Google)
2023-11-08 14:26 ` [RFC PATCH v2 12/31] function_graph: Have the instances use their own ftrace_ops for filtering Masami Hiramatsu (Google)
2023-11-10  1:51   ` Masami Hiramatsu
2023-11-10  2:18     ` Steven Rostedt
2023-11-10  3:09       ` Masami Hiramatsu
2023-11-08 14:26 ` Masami Hiramatsu (Google) [this message]
2023-11-08 14:27 ` [RFC PATCH v2 14/31] function_graph: Move set_graph_function tests to shadow stack global var Masami Hiramatsu (Google)
2023-11-08 14:27 ` [RFC PATCH v2 15/31] function_graph: Move graph depth stored data " Masami Hiramatsu (Google)
2023-11-08 14:27 ` [RFC PATCH v2 16/31] function_graph: Move graph notrace bit " Masami Hiramatsu (Google)
2023-11-08 14:27 ` [RFC PATCH v2 17/31] function_graph: Implement fgraph_reserve_data() and fgraph_retrieve_data() Masami Hiramatsu (Google)
2023-11-08 14:27 ` [RFC PATCH v2 18/31] function_graph: Add selftest for passing local variables Masami Hiramatsu (Google)
2023-11-08 14:28 ` [RFC PATCH v2 19/31] function_graph: Add a new entry handler with parent_ip and ftrace_regs Masami Hiramatsu (Google)
2023-11-08 14:28 ` [RFC PATCH v2 20/31] function_graph: Add a new exit " Masami Hiramatsu (Google)
2023-11-08 23:17   ` Masami Hiramatsu
2023-11-08 14:28 ` [RFC PATCH v2 21/31] x86/ftrace: Enable HAVE_FUNCTION_GRAPH_FREGS Masami Hiramatsu (Google)
2023-11-08 14:28 ` [RFC PATCH v2 22/31] fprobe: Use ftrace_regs in fprobe entry handler Masami Hiramatsu (Google)
2023-11-08 14:28 ` [RFC PATCH v2 23/31] fprobe: Use ftrace_regs in fprobe exit handler Masami Hiramatsu (Google)
2023-11-08 14:28 ` [RFC PATCH v2 24/31] tracing: Add ftrace_partial_regs() for converting ftrace_regs to pt_regs Masami Hiramatsu (Google)
2023-11-08 14:29 ` [RFC PATCH v2 25/31] tracing: Add ftrace_fill_perf_regs() for perf event Masami Hiramatsu (Google)
2023-11-08 14:29 ` [RFC PATCH v2 26/31] fprobe: Rewrite fprobe on function-graph tracer Masami Hiramatsu (Google)
2023-11-10  7:17   ` Masami Hiramatsu
2023-11-11  1:44     ` Steven Rostedt
2023-11-11  3:01       ` Masami Hiramatsu
2023-11-08 14:29 ` [RFC PATCH v2 27/31] tracing/fprobe: Remove nr_maxactive from fprobe Masami Hiramatsu (Google)
2023-11-08 14:29 ` [RFC PATCH v2 28/31] tracing/fprobe: Enable fprobe events with CONFIG_DYNAMIC_FTRACE_WITH_ARGS Masami Hiramatsu (Google)
2023-11-08 14:29 ` [RFC PATCH v2 29/31] bpf: Enable kprobe_multi feature if CONFIG_FPROBE is enabled Masami Hiramatsu (Google)
2023-11-08 14:30 ` [RFC PATCH v2 30/31] selftests: ftrace: Remove obsolate maxactive syntax check Masami Hiramatsu (Google)
2023-11-08 14:30 ` [RFC PATCH v2 31/31] Documentation: probes: Update fprobe on function-graph tracer Masami Hiramatsu (Google)

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=169945361301.55307.14643353930499117634.stgit@devnote2 \
    --to=mhiramat@kernel.org \
    --cc=acme@kernel.org \
    --cc=alan.maguire@oracle.com \
    --cc=alexei.starovoitov@gmail.com \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=guoren@kernel.org \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-trace-kernel@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=martin.lau@linux.dev \
    --cc=peterz@infradead.org \
    --cc=revest@chromium.org \
    --cc=rostedt@goodmis.org \
    --cc=svens@linux.ibm.com \
    --cc=tglx@linutronix.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).