Merge tag 'trace-v5.18-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull more tracing updates from Steven Rostedt:

- Rename the staging files to give them some meaning. Just
stage1,stag2,etc, does not show what they are for

- Check for NULL from allocation in bootconfig

- Hold event mutex for dyn_event call in user events

- Mark user events to broken (to work on the API)

- Remove eBPF updates from user events

- Remove user events from uapi header to keep it from being installed.

- Move ftrace_graph_is_dead() into inline as it is called from hot
paths and also convert it into a static branch.

* tag 'trace-v5.18-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
tracing: Move user_events.h temporarily out of include/uapi
ftrace: Make ftrace_graph_is_dead() a static branch
tracing: Set user_events to BROKEN
tracing/user_events: Remove eBPF interfaces
tracing/user_events: Hold event_mutex during dyn_event_add
proc: bootconfig: Add null pointer check
tracing: Rename the staging files for trace_events

Documentation/trace/user_events.rst

···
 Overview
 --------
 User based trace events allow user processes to create events and trace data
-that can be viewed via existing tools, such as ftrace, perf and eBPF.
+that can be viewed via existing tools, such as ftrace and perf.
 To enable this feature, build your kernel with CONFIG_USER_EVENTS=y.
 
 Programs can view status of the events via
···
 
 Supported Flags
 ^^^^^^^^^^^^^^^
-**BPF_ITER** - EBPF programs attached to this event will get the raw iovec
-struct instead of any data copies for max performance.
+None yet
 
 Field Format
 ^^^^^^^^^^^^
···
 
 **EVENT_STATUS_FTRACE** - Bit set if ftrace has been attached (Bit 0).
 
-**EVENT_STATUS_PERF** - Bit set if perf/eBPF has been attached (Bit 1).
+**EVENT_STATUS_PERF** - Bit set if perf has been attached (Bit 1).
 
 Writing Data
 ------------
···
   writev(fd, (const struct iovec*)io, 2);
 
 **NOTE:** *The write_index is not emitted out into the trace being recorded.*
-
-EBPF
-----
-EBPF programs that attach to a user-based event tracepoint are given a pointer
-to a struct user_bpf_context. The bpf context contains the data type (which can
-be a user or kernel buffer, or can be a pointer to the iovec) and the data
-length that was emitted (minus the write_index).
 
 Example Code
 ------------

fs/proc/bootconfig.c

···
 	int ret = 0;
 
 	key = kzalloc(XBC_KEYLEN_MAX, GFP_KERNEL);
+	if (!key)
+		return -ENOMEM;
 
 	xbc_for_each_key_value(leaf, val) {
 		ret = xbc_node_compose_key(leaf, key, XBC_KEYLEN_MAX);

include/linux/ftrace.h

···
 
 #include <linux/trace_recursion.h>
 #include <linux/trace_clock.h>
+#include <linux/jump_label.h>
 #include <linux/kallsyms.h>
 #include <linux/linkage.h>
 #include <linux/bitops.h>
···
 extern int register_ftrace_graph(struct fgraph_ops *ops);
 extern void unregister_ftrace_graph(struct fgraph_ops *ops);
 
-extern bool ftrace_graph_is_dead(void);
+/**
+ * ftrace_graph_is_dead - returns true if ftrace_graph_stop() was called
+ *
+ * ftrace_graph_stop() is called when a severe error is detected in
+ * the function graph tracing. This function is called by the critical
+ * paths of function graph to keep those paths from doing any more harm.
+ */
+DECLARE_STATIC_KEY_FALSE(kill_ftrace_graph);
+
+static inline bool ftrace_graph_is_dead(void)
+{
+	return static_branch_unlikely(&kill_ftrace_graph);
+}
+
 extern void ftrace_graph_stop(void);
 
 /* The current handlers in use */

include/linux/user_events.h

···
 /* Create dynamic location entry within a 32-bit value */
 #define DYN_LOC(offset, size) ((size) << 16 | (offset))
 
-/* Use raw iterator for attached BPF program(s), no affect on ftrace/perf */
-#define FLAG_BPF_ITER (1 << 0)
-
 /*
  * Describes an event registration and stores the results of the registration.
  * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum
···
 
 /* Requests to delete a user_event */
 #define DIAG_IOCSDEL _IOW(DIAG_IOC_MAGIC, 1, char*)
-
-/* Data type that was passed to the BPF program */
-enum {
-	/* Data resides in kernel space */
-	USER_BPF_DATA_KERNEL,
-
-	/* Data resides in user space */
-	USER_BPF_DATA_USER,
-
-	/* Data is a pointer to a user_bpf_iter structure */
-	USER_BPF_DATA_ITER,
-};
-
-/*
- * Describes an iovec iterator that BPF programs can use to access data for
- * a given user_event write() / writev() call.
- */
-struct user_bpf_iter {
-
-	/* Offset of the data within the first iovec */
-	__u32 iov_offset;
-
-	/* Number of iovec structures */
-	__u32 nr_segs;
-
-	/* Pointer to iovec structures */
-	const struct iovec *iov;
-};
-
-/* Context that BPF programs receive when attached to a user_event */
-struct user_bpf_context {
-
-	/* Data type being passed (see union below) */
-	__u32 data_type;
-
-	/* Length of the data */
-	__u32 data_len;
-
-	/* Pointer to data, varies by data type */
-	union {
-		/* Kernel data (data_type == USER_BPF_DATA_KERNEL) */
-		void *kdata;
-
-		/* User data (data_type == USER_BPF_DATA_USER) */
-		void *udata;
-
-		/* Direct iovec (data_type == USER_BPF_DATA_ITER) */
-		struct user_bpf_iter *iter;
-	};
-};
 
 #endif /* _UAPI_LINUX_USER_EVENTS_H */

include/trace/trace_custom_events.h

···
 
 /* Stage 1 creates the structure of the recorded event layout */
 
-#include "stages/stage1_defines.h"
+#include "stages/stage1_struct_define.h"
 
 #undef DECLARE_CUSTOM_EVENT_CLASS
 #define DECLARE_CUSTOM_EVENT_CLASS(name, proto, args, tstruct, assign, print) \
···
 
 /* Stage 2 creates the custom class */
 
-#include "stages/stage2_defines.h"
+#include "stages/stage2_data_offsets.h"
 
 #undef DECLARE_CUSTOM_EVENT_CLASS
 #define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
···
 
 /* Stage 3 create the way to print the custom event */
 
-#include "stages/stage3_defines.h"
+#include "stages/stage3_trace_output.h"
 
 #undef DECLARE_CUSTOM_EVENT_CLASS
 #define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
···
 
 /* Stage 4 creates the offset layout for the fields */
 
-#include "stages/stage4_defines.h"
+#include "stages/stage4_event_fields.h"
 
 #undef DECLARE_CUSTOM_EVENT_CLASS
 #define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, func, print)	\
···
 
 /* Stage 5 creates the helper function for dynamic fields */
 
-#include "stages/stage5_defines.h"
+#include "stages/stage5_get_offsets.h"
 
 #undef DECLARE_CUSTOM_EVENT_CLASS
 #define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
···
 
 /* Stage 6 creates the probe function that records the event */
 
-#include "stages/stage6_defines.h"
+#include "stages/stage6_event_callback.h"
 
 #undef DECLARE_CUSTOM_EVENT_CLASS
 #define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
···
 
 /* Stage 7 creates the actual class and event structure for the custom event */
 
-#include "stages/stage7_defines.h"
+#include "stages/stage7_class_define.h"
 
 #undef DECLARE_CUSTOM_EVENT_CLASS
 #define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \

include/trace/trace_events.h

···
 			     PARAMS(print));		       \
 	DEFINE_EVENT(name, name, PARAMS(proto), PARAMS(args));
 
-#include "stages/stage1_defines.h"
+#include "stages/stage1_struct_define.h"
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, print)	\
···
  * The size of an array is also encoded, in the higher 16 bits of <item>.
  */
 
-#include "stages/stage2_defines.h"
+#include "stages/stage2_data_offsets.h"
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
···
  * in binary.
  */
 
-#include "stages/stage3_defines.h"
+#include "stages/stage3_trace_output.h"
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
···
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-#include "stages/stage4_defines.h"
+#include "stages/stage4_event_fields.h"
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print)	\
···
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-#include "stages/stage5_defines.h"
+#include "stages/stage5_get_offsets.h"
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
···
 #define _TRACE_PERF_INIT(call)
 #endif /* CONFIG_PERF_EVENTS */
 
-#include "stages/stage6_defines.h"
+#include "stages/stage6_event_callback.h"
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
···
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-#include "stages/stage7_defines.h"
+#include "stages/stage7_class_define.h"
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\

kernel/trace/fgraph.c

···
  *
  * Highly modified by Steven Rostedt (VMware).
  */
+#include <linux/jump_label.h>
 #include <linux/suspend.h>
 #include <linux/ftrace.h>
 #include <linux/slab.h>
···
 #define ASSIGN_OPS_HASH(opsname, val)
 #endif
 
-static bool kill_ftrace_graph;
+DEFINE_STATIC_KEY_FALSE(kill_ftrace_graph);
 int ftrace_graph_active;
 
 /* Both enabled by default (can be cleared by function_graph tracer flags */
 static bool fgraph_sleep_time = true;
-
-/**
- * ftrace_graph_is_dead - returns true if ftrace_graph_stop() was called
- *
- * ftrace_graph_stop() is called when a severe error is detected in
- * the function graph tracing. This function is called by the critical
- * paths of function graph to keep those paths from doing any more harm.
- */
-bool ftrace_graph_is_dead(void)
-{
-	return kill_ftrace_graph;
-}
 
 /**
  * ftrace_graph_stop - set to permanently disable function graph tracing
···
  */
 void ftrace_graph_stop(void)
 {
-	kill_ftrace_graph = true;
+	static_branch_enable(&kill_ftrace_graph);
 }
 
 /* Add a function return address to the trace stack on thread info.*/

kernel/trace/trace_events_user.c

···
 #define MAX_FIELD_ARRAY_SIZE 1024
 #define MAX_FIELD_ARG_NAME 256
 
-#define MAX_BPF_COPY_SIZE PAGE_SIZE
-#define MAX_STACK_BPF_DATA 512
-
 static char *register_page_data;
 
 static DEFINE_MUTEX(reg_mutex);
···
 				    type[0] != 'u', FILTER_OTHER);
 }
 
-static void user_event_parse_flags(struct user_event *user, char *flags)
-{
-	char *flag;
-
-	if (flags == NULL)
-		return;
-
-	while ((flag = strsep(&flags, ",")) != NULL) {
-		if (strcmp(flag, "BPF_ITER") == 0)
-			user->flags |= FLAG_BPF_ITER;
-	}
-}
-
 static int user_event_parse_fields(struct user_event *user, char *args)
 {
 	char *field;
···
 }
 
 #ifdef CONFIG_PERF_EVENTS
-static void user_event_bpf(struct user_event *user, struct iov_iter *i)
-{
-	struct user_bpf_context context;
-	struct user_bpf_iter bpf_i;
-	char fast_data[MAX_STACK_BPF_DATA];
-	void *temp = NULL;
-
-	if ((user->flags & FLAG_BPF_ITER) && iter_is_iovec(i)) {
-		/* Raw iterator */
-		context.data_type = USER_BPF_DATA_ITER;
-		context.data_len = i->count;
-		context.iter = &bpf_i;
-
-		bpf_i.iov_offset = i->iov_offset;
-		bpf_i.iov = i->iov;
-		bpf_i.nr_segs = i->nr_segs;
-	} else if (i->nr_segs == 1 && iter_is_iovec(i)) {
-		/* Single buffer from user */
-		context.data_type = USER_BPF_DATA_USER;
-		context.data_len = i->count;
-		context.udata = i->iov->iov_base + i->iov_offset;
-	} else {
-		/* Multi buffer from user */
-		struct iov_iter copy = *i;
-		size_t copy_size = min_t(size_t, i->count, MAX_BPF_COPY_SIZE);
-
-		context.data_type = USER_BPF_DATA_KERNEL;
-		context.kdata = fast_data;
-
-		if (unlikely(copy_size > sizeof(fast_data))) {
-			temp = kmalloc(copy_size, GFP_NOWAIT);
-
-			if (temp)
-				context.kdata = temp;
-			else
-				copy_size = sizeof(fast_data);
-		}
-
-		context.data_len = copy_nofault(context.kdata,
-						copy_size, &copy);
-	}
-
-	trace_call_bpf(&user->call, &context);
-
-	kfree(temp);
-}
-
 /*
- * Writes the user supplied payload out to perf ring buffer or eBPF program.
+ * Writes the user supplied payload out to perf ring buffer.
  */
 static void user_event_perf(struct user_event *user, struct iov_iter *i,
 			    void *tpdata, bool *faulted)
 {
 	struct hlist_head *perf_head;
-
-	if (bpf_prog_array_valid(&user->call))
-		user_event_bpf(user, i);
 
 	perf_head = this_cpu_ptr(user->call.perf_events);
 
···
 
 	user->tracepoint.name = name;
 
-	user_event_parse_flags(user, flags);
-
 	ret = user_event_parse_fields(user, args);
 
 	if (ret)
···
 #endif
 
 	mutex_lock(&event_mutex);
+
 	ret = user_event_trace_register(user);
-	mutex_unlock(&event_mutex);
 
 	if (ret)
-		goto put_user;
+		goto put_user_lock;
 
 	user->index = index;
 
···
 	set_bit(user->index, page_bitmap);
 	hash_add(register_table, &user->node, key);
 
+	mutex_unlock(&event_mutex);
+
 	*newuser = user;
 	return 0;
+put_user_lock:
+	mutex_unlock(&event_mutex);
 put_user:
 	user_event_destroy_fields(user);
 	user_event_destroy_validators(user);
···
 				seq_puts(m, " other");
 			busy++;
 		}
-
-		if (flags & FLAG_BPF_ITER)
-			seq_puts(m, " FLAG:BPF_ITER");
 
 		seq_puts(m, "\n");
 		active++;