1 files changed, 138 insertions, 92 deletions

diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 9e461362450a..f95a2c3d5b1b 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -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"
@@ -58,11 +59,11 @@ struct trace_uprobe {
 	struct dyn_event		devent;
 	struct uprobe_consumer		consumer;
 	struct path			path;
-	struct inode			*inode;
 	char				*filename;
+	struct uprobe			*uprobe;
 	unsigned long			offset;
 	unsigned long			ref_ctr_offset;
-	unsigned long			nhit;
+	unsigned long __percpu		*nhits;
 	struct trace_probe		tp;
 };
 
@@ -88,9 +89,11 @@ static struct trace_uprobe *to_trace_uprobe(struct dyn_event *ev)
 static int register_uprobe_event(struct trace_uprobe *tu);
 static int unregister_uprobe_event(struct trace_uprobe *tu);
 
-static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs);
+static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs,
+			     __u64 *data);
 static int uretprobe_dispatcher(struct uprobe_consumer *con,
-				unsigned long func, struct pt_regs *regs);
+				unsigned long func, struct pt_regs *regs,
+				__u64 *data);
 
 #ifdef CONFIG_STACK_GROWSUP
 static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n)
@@ -337,6 +340,12 @@ 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 +358,7 @@ 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 +372,7 @@ 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);
 }
 
@@ -487,11 +498,11 @@ static int register_trace_uprobe(struct trace_uprobe *tu)
 	struct trace_uprobe *old_tu;
 	int ret;
 
-	mutex_lock(&event_mutex);
+	guard(mutex)(&event_mutex);
 
 	ret = validate_ref_ctr_offset(tu);
 	if (ret)
-		goto end;
+		return ret;
 
 	/* register as an event */
 	old_tu = find_probe_event(trace_probe_name(&tu->tp),
@@ -500,11 +511,9 @@ static int register_trace_uprobe(struct trace_uprobe *tu)
 		if (is_ret_probe(tu) != is_ret_probe(old_tu)) {
 			trace_probe_log_set_index(0);
 			trace_probe_log_err(0, DIFF_PROBE_TYPE);
-			ret = -EEXIST;
-		} else {
-			ret = append_trace_uprobe(tu, old_tu);
+			return -EEXIST;
 		}
-		goto end;
+		return append_trace_uprobe(tu, old_tu);
 	}
 
 	ret = register_uprobe_event(tu);
@@ -514,14 +523,11 @@ static int register_trace_uprobe(struct trace_uprobe *tu)
 			trace_probe_log_err(0, EVENT_EXIST);
 		} else
 			pr_warn("Failed to register probe event(%d)\n", ret);
-		goto end;
+		return ret;
 	}
 
 	dyn_event_add(&tu->devent, trace_probe_event_call(&tu->tp));
 
-end:
-	mutex_unlock(&event_mutex);
-
 	return ret;
 }
 
@@ -557,6 +563,14 @@ static int __trace_uprobe_create(int argc, const char **argv)
 	if (argc < 2)
 		return -ECANCELED;
 
+	trace_probe_log_init("trace_uprobe", argc, argv);
+
+	if (argc - 2 > MAX_TRACE_ARGS) {
+		trace_probe_log_set_index(2);
+		trace_probe_log_err(0, TOO_MANY_ARGS);
+		return -E2BIG;
+	}
+
 	if (argv[0][1] == ':')
 		event = &argv[0][2];
 
@@ -574,7 +588,6 @@ static int __trace_uprobe_create(int argc, const char **argv)
 		return -ECANCELED;
 	}
 
-	trace_probe_log_init("trace_uprobe", argc, argv);
 	trace_probe_log_set_index(1);	/* filename is the 2nd argument */
 
 	*arg++ = '\0';
@@ -681,7 +694,7 @@ static int __trace_uprobe_create(int argc, const char **argv)
 	tu->filename = filename;
 
 	/* parse arguments */
-	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+	for (i = 0; i < argc; i++) {
 		struct traceprobe_parse_context ctx = {
 			.flags = (is_return ? TPARG_FL_RETURN : 0) | TPARG_FL_USER,
 		};
@@ -728,7 +741,7 @@ static int create_or_delete_trace_uprobe(const char *raw_command)
 	if (raw_command[0] == '-')
 		return dyn_event_release(raw_command, &trace_uprobe_ops);
 
-	ret = trace_uprobe_create(raw_command);
+	ret = dyn_event_create(raw_command, &trace_uprobe_ops);
 	return ret == -ECANCELED ? -EINVAL : ret;
 }
 
@@ -815,13 +828,21 @@ 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;
 }
 
@@ -854,9 +875,11 @@ 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;
+#define MAX_UCB_BUFFER_SIZE PAGE_SIZE
 
 static int uprobe_buffer_init(void)
 {
@@ -940,12 +963,41 @@ 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;
+
+	if (WARN_ON_ONCE(ucb->dsize > MAX_UCB_BUFFER_SIZE)) {
+		ucb->dsize = MAX_UCB_BUFFER_SIZE;
+		dsize = MAX_UCB_BUFFER_SIZE - tu->tp.size;
+	}
+
+	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 *ucb,
 				struct trace_event_file *trace_file)
 {
 	struct uprobe_trace_entry_head *entry;
@@ -956,14 +1008,11 @@ static void __uprobe_trace_func(struct trace_uprobe *tu,
 
 	WARN_ON(call != trace_file->event_call);
 
-	if (WARN_ON_ONCE(tu->tp.size + 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;
@@ -977,23 +1026,26 @@ 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;
+	struct uprobe_cpu_buffer *ucb;
 
 	if (is_ret_probe(tu))
 		return 0;
 
+	ucb = prepare_uprobe_buffer(tu, regs, ucbp);
+
 	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, ucb, link->file);
 	rcu_read_unlock();
 
 	return 0;
@@ -1001,13 +1053,16 @@ 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;
+	struct uprobe_cpu_buffer *ucb;
+
+	ucb = prepare_uprobe_buffer(tu, regs, ucbp);
 
 	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, ucb, link->file);
 	rcu_read_unlock();
 }
 
@@ -1047,43 +1102,40 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e
 	return trace_handle_return(s);
 }
 
-typedef bool (*filter_func_t)(struct uprobe_consumer *self,
-				enum uprobe_filter_ctx ctx,
-				struct mm_struct *mm);
+typedef bool (*filter_func_t)(struct uprobe_consumer *self, struct mm_struct *mm);
 
 static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter)
 {
-	int ret;
+	struct inode *inode = d_real_inode(tu->path.dentry);
+	struct uprobe *uprobe;
 
 	tu->consumer.filter = filter;
-	tu->inode = d_real_inode(tu->path.dentry);
-
-	if (tu->ref_ctr_offset)
-		ret = uprobe_register_refctr(tu->inode, tu->offset,
-				tu->ref_ctr_offset, &tu->consumer);
-	else
-		ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
+	uprobe = uprobe_register(inode, tu->offset, tu->ref_ctr_offset, &tu->consumer);
+	if (IS_ERR(uprobe))
+		return PTR_ERR(uprobe);
 
-	if (ret)
-		tu->inode = NULL;
-
-	return ret;
+	tu->uprobe = uprobe;
+	return 0;
 }
 
 static void __probe_event_disable(struct trace_probe *tp)
 {
 	struct trace_uprobe *tu;
+	bool sync = false;
 
 	tu = container_of(tp, struct trace_uprobe, tp);
 	WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter));
 
 	list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) {
-		if (!tu->inode)
+		if (!tu->uprobe)
 			continue;
 
-		uprobe_unregister(tu->inode, tu->offset, &tu->consumer);
-		tu->inode = NULL;
+		uprobe_unregister_nosync(tu->uprobe, &tu->consumer);
+		sync = true;
+		tu->uprobe = NULL;
 	}
+	if (sync)
+		uprobe_unregister_sync();
 }
 
 static int probe_event_enable(struct trace_event_call *call,
@@ -1199,9 +1251,6 @@ __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;
@@ -1282,7 +1331,7 @@ static int uprobe_perf_close(struct trace_event_call *call,
 		return 0;
 
 	list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) {
-		ret = uprobe_apply(tu->inode, tu->offset, &tu->consumer, false);
+		ret = uprobe_apply(tu->uprobe, &tu->consumer, false);
 		if (ret)
 			break;
 	}
@@ -1306,7 +1355,7 @@ static int uprobe_perf_open(struct trace_event_call *call,
 		return 0;
 
 	list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) {
-		err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
+		err = uprobe_apply(tu->uprobe, &tu->consumer, true);
 		if (err) {
 			uprobe_perf_close(call, event);
 			break;
@@ -1316,8 +1365,7 @@ static int uprobe_perf_open(struct trace_event_call *call,
 	return err;
 }
 
-static bool uprobe_perf_filter(struct uprobe_consumer *uc,
-				enum uprobe_filter_ctx ctx, struct mm_struct *mm)
+static bool uprobe_perf_filter(struct uprobe_consumer *uc, struct mm_struct *mm)
 {
 	struct trace_uprobe_filter *filter;
 	struct trace_uprobe *tu;
@@ -1326,6 +1374,13 @@ 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 +1390,11 @@ 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;
@@ -1346,9 +1402,13 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 
 #ifdef CONFIG_BPF_EVENTS
 	if (bpf_prog_array_valid(call)) {
+		const struct bpf_prog_array *array;
 		u32 ret;
 
-		ret = bpf_prog_run_array_uprobe(call->prog_array, regs, bpf_prog_run);
+		rcu_read_lock_trace();
+		array = rcu_dereference_check(call->prog_array, rcu_read_lock_trace_held());
+		ret = bpf_prog_run_array_uprobe(array, regs, bpf_prog_run);
+		rcu_read_unlock_trace();
 		if (!ret)
 			return;
 	}
@@ -1356,7 +1416,8 @@ 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 +1440,10 @@ static void __uprobe_perf_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);
 
-	if (size - esize > tu->tp.size + dsize) {
-		int len = tu->tp.size + 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 +1453,21 @@ 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))
+	if (!uprobe_perf_filter(&tu->consumer, 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,
@@ -1431,7 +1489,7 @@ int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type,
 				    : BPF_FD_TYPE_UPROBE;
 	*filename = tu->filename;
 	*probe_offset = tu->offset;
-	*probe_addr = 0;
+	*probe_addr = tu->ref_ctr_offset;
 	return 0;
 }
 #endif	/* CONFIG_PERF_EVENTS */
@@ -1470,17 +1528,17 @@ trace_uprobe_register(struct trace_event_call *event, enum trace_reg type,
 	}
 }
 
-static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
+static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs,
+			     __u64 *data)
 {
 	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++;
+
+	this_cpu_inc(*tu->nhits);
 
 	udd.tu = tu;
 	udd.bp_addr = instruction_pointer(regs);
@@ -1490,30 +1548,24 @@ 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;
 }
 
 static int uretprobe_dispatcher(struct uprobe_consumer *con,
-				unsigned long func, struct pt_regs *regs)
+				unsigned long func, struct pt_regs *regs,
+				__u64 *data)
 {
 	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 +1577,12 @@ 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;