Merge tag 'probes-v6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull probes updates from Masami Hiramatsu:

 - tracing/probes: Add new pseudo-types %pd and %pD support for dumping
   dentry name from 'struct dentry *' and file name from 'struct file *'

 - uprobes performance optimizations:
    - Speed up the BPF uprobe event by delaying the fetching of the
      uprobe event arguments that are not used in BPF
    - Avoid locking by speculatively checking whether uprobe event is
      valid
    - Reduce lock contention by using read/write_lock instead of
      spinlock for uprobe list operation. This improved BPF uprobe
      benchmark result 43% on average

 - rethook: Remove non-fatal warning messages when tracing stack from
   BPF and skip rcu_is_watching() validation in rethook if possible

 - objpool: Optimize objpool (which is used by kretprobes and fprobe as
   rethook backend storage) by inlining functions and avoid caching
   nr_cpu_ids because it is a const value

 - fprobe: Add entry/exit callbacks types (code cleanup)

 - kprobes: Check ftrace was killed in kprobes if it uses ftrace

* tag 'probes-v6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  kprobe/ftrace: bail out if ftrace was killed
  selftests/ftrace: Fix required features for VFS type test case
  objpool: cache nr_possible_cpus() and avoid caching nr_cpu_ids
  objpool: enable inlining objpool_push() and objpool_pop() operations
  rethook: honor CONFIG_FTRACE_VALIDATE_RCU_IS_WATCHING in rethook_try_get()
  ftrace: make extra rcu_is_watching() validation check optional
  uprobes: reduce contention on uprobes_tree access
  rethook: Remove warning messages printed for finding return address of a frame.
  fprobe: Add entry/exit callbacks types
  selftests/ftrace: add fprobe test cases for VFS type "%pd" and "%pD"
  selftests/ftrace: add kprobe test cases for VFS type "%pd" and "%pD"
  Documentation: tracing: add new type '%pd' and '%pD' for kprobe
  tracing/probes: support '%pD' type for print struct file's name
  tracing/probes: support '%pd' type for print struct dentry's name
  uprobes: add speculative lockless system-wide uprobe filter check
  uprobes: prepare uprobe args buffer lazily
  uprobes: encapsulate preparation of uprobe args buffer

9 files changed, 154 insertions, 46 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index b3d7f62ac581..166ad5444eea 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -974,6 +974,19 @@ config FTRACE_RECORD_RECURSION_SIZE
 	  This file can be reset, but the limit can not change in
 	  size at runtime.
 
+config FTRACE_VALIDATE_RCU_IS_WATCHING
+	bool "Validate RCU is on during ftrace execution"
+	depends on FUNCTION_TRACER
+	depends on ARCH_WANTS_NO_INSTR
+	help
+	  All callbacks that attach to the function tracing have some sort of
+	  protection against recursion. This option is only to verify that
+	  ftrace (and other users of ftrace_test_recursion_trylock()) are not
+	  called outside of RCU, as if they are, it can cause a race. But it
+	  also has a noticeable overhead when enabled.
+
+	  If unsure, say N
+
 config RING_BUFFER_RECORD_RECURSION
 	bool "Record functions that recurse in the ring buffer"
 	depends on FTRACE_RECORD_RECURSION
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 50ca4d4f8840..d4efdab463b8 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -7894,6 +7894,7 @@ void ftrace_kill(void)
 	ftrace_disabled = 1;
 	ftrace_enabled = 0;
 	ftrace_trace_function = ftrace_stub;
+	kprobe_ftrace_kill();
 }
 
 /**
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index fa03094e9e69..30d224946881 100644
--- a/kernel/trace/rethook.c
+++ b/kernel/trace/rethook.c
@@ -166,6 +166,7 @@ struct rethook_node *rethook_try_get(struct rethook *rh)
 	if (unlikely(!handler))
 		return NULL;
 
+#if defined(CONFIG_FTRACE_VALIDATE_RCU_IS_WATCHING) || defined(CONFIG_KPROBE_EVENTS_ON_NOTRACE)
 	/*
 	 * This expects the caller will set up a rethook on a function entry.
 	 * When the function returns, the rethook will eventually be reclaimed
@@ -174,6 +175,7 @@ struct rethook_node *rethook_try_get(struct rethook *rh)
 	 */
 	if (unlikely(!rcu_is_watching()))
 		return NULL;
+#endif
 
 	return (struct rethook_node *)objpool_pop(&rh->pool);
 }
@@ -248,7 +250,7 @@ unsigned long rethook_find_ret_addr(struct task_struct *tsk, unsigned long frame
 	if (WARN_ON_ONCE(!cur))
 		return 0;
 
-	if (WARN_ON_ONCE(tsk != current && task_is_running(tsk)))
+	if (tsk != current && task_is_running(tsk))
 		return 0;
 
 	do {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 233d1af39fff..7fe4b539a423 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5540,7 +5540,7 @@ static const char readme_msg[] =
 	"\t     kernel return probes support: $retval, $arg<N>, $comm\n"
 	"\t     type: s8/16/32/64, u8/16/32/64, x8/16/32/64, char, string, symbol,\n"
 	"\t           b<bit-width>@<bit-offset>/<container-size>, ustring,\n"
-	"\t           symstr, <type>\\[<array-size>\\]\n"
+	"\t           symstr, %pd/%pD, <type>\\[<array-size>\\]\n"
 #ifdef CONFIG_HIST_TRIGGERS
 	"\t    field: <stype> <name>;\n"
 	"\t    stype: u8/u16/u32/u64, s8/s16/s32/s64, pid_t,\n"
diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index 4f4280815522..62e6a8f4aae9 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -994,6 +994,7 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 	char gbuf[MAX_EVENT_NAME_LEN];
 	char sbuf[KSYM_NAME_LEN];
 	char abuf[MAX_BTF_ARGS_LEN];
+	char *dbuf = NULL;
 	bool is_tracepoint = false;
 	struct tracepoint *tpoint = NULL;
 	struct traceprobe_parse_context ctx = {
@@ -1104,6 +1105,10 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 		argv = new_argv;
 	}
 
+	ret = traceprobe_expand_dentry_args(argc, argv, &dbuf);
+	if (ret)
+		goto out;
+
 	/* setup a probe */
 	tf = alloc_trace_fprobe(group, event, symbol, tpoint, maxactive,
 				argc, is_return);
@@ -1154,6 +1159,7 @@ out:
 	trace_probe_log_clear();
 	kfree(new_argv);
 	kfree(symbol);
+	kfree(dbuf);
 	return ret;
 
 parse_error:
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 2cb2a3951b4f..16383247bdbf 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -800,6 +800,7 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 	char buf[MAX_EVENT_NAME_LEN];
 	char gbuf[MAX_EVENT_NAME_LEN];
 	char abuf[MAX_BTF_ARGS_LEN];
+	char *dbuf = NULL;
 	struct traceprobe_parse_context ctx = { .flags = TPARG_FL_KERNEL };
 
 	switch (argv[0][0]) {
@@ -951,6 +952,10 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 		argv = new_argv;
 	}
 
+	ret = traceprobe_expand_dentry_args(argc, argv, &dbuf);
+	if (ret)
+		goto out;
+
 	/* setup a probe */
 	tk = alloc_trace_kprobe(group, event, addr, symbol, offset, maxactive,
 				argc, is_return);
@@ -997,6 +1002,7 @@ out:
 	trace_probe_log_clear();
 	kfree(new_argv);
 	kfree(symbol);
+	kfree(dbuf);
 	return ret;
 
 parse_error:
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index c3f2937b434a..5e263c141574 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -12,6 +12,7 @@
 #define pr_fmt(fmt)	"trace_probe: " fmt
 
 #include <linux/bpf.h>
+#include <linux/fs.h>
 #include "trace_btf.h"
 
 #include "trace_probe.h"
@@ -1737,6 +1738,68 @@ error:
 	return ERR_PTR(ret);
 }
 
+/* @buf: *buf must be equal to NULL. Caller must to free *buf */
+int traceprobe_expand_dentry_args(int argc, const char *argv[], char **buf)
+{
+	int i, used, ret;
+	const int bufsize = MAX_DENTRY_ARGS_LEN;
+	char *tmpbuf = NULL;
+
+	if (*buf)
+		return -EINVAL;
+
+	used = 0;
+	for (i = 0; i < argc; i++) {
+		char *tmp;
+		char *equal;
+		size_t arg_len;
+
+		if (!glob_match("*:%p[dD]", argv[i]))
+			continue;
+
+		if (!tmpbuf) {
+			tmpbuf = kmalloc(bufsize, GFP_KERNEL);
+			if (!tmpbuf)
+				return -ENOMEM;
+		}
+
+		tmp = kstrdup(argv[i], GFP_KERNEL);
+		if (!tmp)
+			goto nomem;
+
+		equal = strchr(tmp, '=');
+		if (equal)
+			*equal = '\0';
+		arg_len = strlen(argv[i]);
+		tmp[arg_len - 4] = '\0';
+		if (argv[i][arg_len - 1] == 'd')
+			ret = snprintf(tmpbuf + used, bufsize - used,
+				       "%s%s+0x0(+0x%zx(%s)):string",
+				       equal ? tmp : "", equal ? "=" : "",
+				       offsetof(struct dentry, d_name.name),
+				       equal ? equal + 1 : tmp);
+		else
+			ret = snprintf(tmpbuf + used, bufsize - used,
+				       "%s%s+0x0(+0x%zx(+0x%zx(%s))):string",
+				       equal ? tmp : "", equal ? "=" : "",
+				       offsetof(struct dentry, d_name.name),
+				       offsetof(struct file, f_path.dentry),
+				       equal ? equal + 1 : tmp);
+
+		kfree(tmp);
+		if (ret >= bufsize - used)
+			goto nomem;
+		argv[i] = tmpbuf + used;
+		used += ret + 1;
+	}
+
+	*buf = tmpbuf;
+	return 0;
+nomem:
+	kfree(tmpbuf);
+	return -ENOMEM;
+}
+
 void traceprobe_finish_parse(struct traceprobe_parse_context *ctx)
 {
 	clear_btf_context(ctx);
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index cef3a50628a3..5803e6a41570 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -34,6 +34,7 @@
 #define MAX_ARRAY_LEN		64
 #define MAX_ARG_NAME_LEN	32
 #define MAX_BTF_ARGS_LEN	128
+#define MAX_DENTRY_ARGS_LEN	256
 #define MAX_STRING_SIZE		PATH_MAX
 #define MAX_ARG_BUF_LEN		(MAX_TRACE_ARGS * MAX_ARG_NAME_LEN)
 
@@ -428,6 +429,7 @@ extern int traceprobe_parse_probe_arg(struct trace_probe *tp, int i,
 const char **traceprobe_expand_meta_args(int argc, const char *argv[],
 					 int *new_argc, char *buf, int bufsize,
 					 struct traceprobe_parse_context *ctx);
+extern int traceprobe_expand_dentry_args(int argc, const char *argv[], char **buf);
 
 extern int traceprobe_update_arg(struct probe_arg *arg);
 extern void traceprobe_free_probe_arg(struct probe_arg *arg);
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 9e461362450a..8541fa1494ae 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -854,6 +854,7 @@ static const struct file_operations uprobe_profile_ops = {
 struct uprobe_cpu_buffer {
 	struct mutex mutex;
 	void *buf;
+	int dsize;
 };
 static struct uprobe_cpu_buffer __percpu *uprobe_cpu_buffer;
 static int uprobe_buffer_refcnt;
@@ -940,30 +941,56 @@ static struct uprobe_cpu_buffer *uprobe_buffer_get(void)
 
 static void uprobe_buffer_put(struct uprobe_cpu_buffer *ucb)
 {
+	if (!ucb)
+		return;
 	mutex_unlock(&ucb->mutex);
 }
 
+static struct uprobe_cpu_buffer *prepare_uprobe_buffer(struct trace_uprobe *tu,
+						       struct pt_regs *regs,
+						       struct uprobe_cpu_buffer **ucbp)
+{
+	struct uprobe_cpu_buffer *ucb;
+	int dsize, esize;
+
+	if (*ucbp)
+		return *ucbp;
+
+	esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
+	dsize = __get_data_size(&tu->tp, regs, NULL);
+
+	ucb = uprobe_buffer_get();
+	ucb->dsize = tu->tp.size + dsize;
+
+	store_trace_args(ucb->buf, &tu->tp, regs, NULL, esize, dsize);
+
+	*ucbp = ucb;
+	return ucb;
+}
+
 static void __uprobe_trace_func(struct trace_uprobe *tu,
 				unsigned long func, struct pt_regs *regs,
-				struct uprobe_cpu_buffer *ucb, int dsize,
+				struct uprobe_cpu_buffer **ucbp,
 				struct trace_event_file *trace_file)
 {
 	struct uprobe_trace_entry_head *entry;
 	struct trace_event_buffer fbuffer;
+	struct uprobe_cpu_buffer *ucb;
 	void *data;
 	int size, esize;
 	struct trace_event_call *call = trace_probe_event_call(&tu->tp);
 
 	WARN_ON(call != trace_file->event_call);
 
-	if (WARN_ON_ONCE(tu->tp.size + dsize > PAGE_SIZE))
+	ucb = prepare_uprobe_buffer(tu, regs, ucbp);
+	if (WARN_ON_ONCE(ucb->dsize > PAGE_SIZE))
 		return;
 
 	if (trace_trigger_soft_disabled(trace_file))
 		return;
 
 	esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
-	size = esize + tu->tp.size + dsize;
+	size = esize + ucb->dsize;
 	entry = trace_event_buffer_reserve(&fbuffer, trace_file, size);
 	if (!entry)
 		return;
@@ -977,14 +1004,14 @@ static void __uprobe_trace_func(struct trace_uprobe *tu,
 		data = DATAOF_TRACE_ENTRY(entry, false);
 	}
 
-	memcpy(data, ucb->buf, tu->tp.size + dsize);
+	memcpy(data, ucb->buf, ucb->dsize);
 
 	trace_event_buffer_commit(&fbuffer);
 }
 
 /* uprobe handler */
 static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs,
-			     struct uprobe_cpu_buffer *ucb, int dsize)
+			     struct uprobe_cpu_buffer **ucbp)
 {
 	struct event_file_link *link;
 
@@ -993,7 +1020,7 @@ static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs,
 
 	rcu_read_lock();
 	trace_probe_for_each_link_rcu(link, &tu->tp)
-		__uprobe_trace_func(tu, 0, regs, ucb, dsize, link->file);
+		__uprobe_trace_func(tu, 0, regs, ucbp, link->file);
 	rcu_read_unlock();
 
 	return 0;
@@ -1001,13 +1028,13 @@ static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs,
 
 static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func,
 				 struct pt_regs *regs,
-				 struct uprobe_cpu_buffer *ucb, int dsize)
+				 struct uprobe_cpu_buffer **ucbp)
 {
 	struct event_file_link *link;
 
 	rcu_read_lock();
 	trace_probe_for_each_link_rcu(link, &tu->tp)
-		__uprobe_trace_func(tu, func, regs, ucb, dsize, link->file);
+		__uprobe_trace_func(tu, func, regs, ucbp, link->file);
 	rcu_read_unlock();
 }
 
@@ -1199,9 +1226,6 @@ __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.target->mm == mm)
 			return true;
@@ -1326,6 +1350,13 @@ static bool uprobe_perf_filter(struct uprobe_consumer *uc,
 	tu = container_of(uc, struct trace_uprobe, consumer);
 	filter = tu->tp.event->filter;
 
+	/*
+	 * speculative short-circuiting check to avoid unnecessarily taking
+	 * filter->rwlock below, if the uprobe has system-wide consumer
+	 */
+	if (READ_ONCE(filter->nr_systemwide))
+		return true;
+
 	read_lock(&filter->rwlock);
 	ret = __uprobe_perf_filter(filter, mm);
 	read_unlock(&filter->rwlock);
@@ -1335,10 +1366,11 @@ static bool uprobe_perf_filter(struct uprobe_consumer *uc,
 
 static void __uprobe_perf_func(struct trace_uprobe *tu,
 			       unsigned long func, struct pt_regs *regs,
-			       struct uprobe_cpu_buffer *ucb, int dsize)
+			       struct uprobe_cpu_buffer **ucbp)
 {
 	struct trace_event_call *call = trace_probe_event_call(&tu->tp);
 	struct uprobe_trace_entry_head *entry;
+	struct uprobe_cpu_buffer *ucb;
 	struct hlist_head *head;
 	void *data;
 	int size, esize;
@@ -1356,7 +1388,8 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 
 	esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
 
-	size = esize + tu->tp.size + dsize;
+	ucb = prepare_uprobe_buffer(tu, regs, ucbp);
+	size = esize + ucb->dsize;
 	size = ALIGN(size + sizeof(u32), sizeof(u64)) - sizeof(u32);
 	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough"))
 		return;
@@ -1379,13 +1412,10 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 		data = DATAOF_TRACE_ENTRY(entry, false);
 	}
 
-	memcpy(data, ucb->buf, tu->tp.size + dsize);
-
-	if (size - esize > tu->tp.size + dsize) {
-		int len = tu->tp.size + dsize;
+	memcpy(data, ucb->buf, ucb->dsize);
 
-		memset(data + len, 0, size - esize - len);
-	}
+	if (size - esize > ucb->dsize)
+		memset(data + ucb->dsize, 0, size - esize - ucb->dsize);
 
 	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
 			      head, NULL);
@@ -1395,21 +1425,21 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 
 /* uprobe profile handler */
 static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs,
-			    struct uprobe_cpu_buffer *ucb, int dsize)
+			    struct uprobe_cpu_buffer **ucbp)
 {
 	if (!uprobe_perf_filter(&tu->consumer, 0, current->mm))
 		return UPROBE_HANDLER_REMOVE;
 
 	if (!is_ret_probe(tu))
-		__uprobe_perf_func(tu, 0, regs, ucb, dsize);
+		__uprobe_perf_func(tu, 0, regs, ucbp);
 	return 0;
 }
 
 static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func,
 				struct pt_regs *regs,
-				struct uprobe_cpu_buffer *ucb, int dsize)
+				struct uprobe_cpu_buffer **ucbp)
 {
-	__uprobe_perf_func(tu, func, regs, ucb, dsize);
+	__uprobe_perf_func(tu, func, regs, ucbp);
 }
 
 int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type,
@@ -1474,11 +1504,9 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
 {
 	struct trace_uprobe *tu;
 	struct uprobe_dispatch_data udd;
-	struct uprobe_cpu_buffer *ucb;
-	int dsize, esize;
+	struct uprobe_cpu_buffer *ucb = NULL;
 	int ret = 0;
 
-
 	tu = container_of(con, struct trace_uprobe, consumer);
 	tu->nhit++;
 
@@ -1490,18 +1518,12 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
 	if (WARN_ON_ONCE(!uprobe_cpu_buffer))
 		return 0;
 
-	dsize = __get_data_size(&tu->tp, regs, NULL);
-	esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
-
-	ucb = uprobe_buffer_get();
-	store_trace_args(ucb->buf, &tu->tp, regs, NULL, esize, dsize);
-
 	if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE))
-		ret |= uprobe_trace_func(tu, regs, ucb, dsize);
+		ret |= uprobe_trace_func(tu, regs, &ucb);
 
 #ifdef CONFIG_PERF_EVENTS
 	if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE))
-		ret |= uprobe_perf_func(tu, regs, ucb, dsize);
+		ret |= uprobe_perf_func(tu, regs, &ucb);
 #endif
 	uprobe_buffer_put(ucb);
 	return ret;
@@ -1512,8 +1534,7 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con,
 {
 	struct trace_uprobe *tu;
 	struct uprobe_dispatch_data udd;
-	struct uprobe_cpu_buffer *ucb;
-	int dsize, esize;
+	struct uprobe_cpu_buffer *ucb = NULL;
 
 	tu = container_of(con, struct trace_uprobe, consumer);
 
@@ -1525,18 +1546,12 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con,
 	if (WARN_ON_ONCE(!uprobe_cpu_buffer))
 		return 0;
 
-	dsize = __get_data_size(&tu->tp, regs, NULL);
-	esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
-
-	ucb = uprobe_buffer_get();
-	store_trace_args(ucb->buf, &tu->tp, regs, NULL, esize, dsize);
-
 	if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE))
-		uretprobe_trace_func(tu, func, regs, ucb, dsize);
+		uretprobe_trace_func(tu, func, regs, &ucb);
 
 #ifdef CONFIG_PERF_EVENTS
 	if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE))
-		uretprobe_perf_func(tu, func, regs, ucb, dsize);
+		uretprobe_perf_func(tu, func, regs, &ucb);
 #endif
 	uprobe_buffer_put(ucb);
 	return 0;