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
diff --git a/Documentation/trace/user_events.rst b/Documentation/trace/user_events.rst
index bddedab..c180936 100644
--- a/Documentation/trace/user_events.rst
+++ b/Documentation/trace/user_events.rst
@@ -7,7 +7,7 @@
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
@@ -67,8 +67,7 @@
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
^^^^^^^^^^^^
@@ -160,7 +159,7 @@
**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
------------
@@ -204,13 +203,6 @@
**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
------------
See sample code in samples/user_events.
diff --git a/fs/proc/bootconfig.c b/fs/proc/bootconfig.c
index 6d8d4bf..2e244ad 100644
--- a/fs/proc/bootconfig.c
+++ b/fs/proc/bootconfig.c
@@ -32,6 +32,8 @@
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);
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index ed8cf433..4816b7e 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -9,6 +9,7 @@
#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>
@@ -1018,7 +1019,20 @@
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 */
diff --git a/include/linux/user_events.h b/include/linux/user_events.h
index e570840..736e056 100644
--- a/include/linux/user_events.h
+++ b/include/linux/user_events.h
@@ -32,9 +32,6 @@
/* 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
@@ -63,54 +60,4 @@
/* 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 */
diff --git a/include/trace/stages/stage1_defines.h b/include/trace/stages/stage1_struct_define.h
similarity index 100%
rename from include/trace/stages/stage1_defines.h
rename to include/trace/stages/stage1_struct_define.h
diff --git a/include/trace/stages/stage2_defines.h b/include/trace/stages/stage2_data_offsets.h
similarity index 100%
rename from include/trace/stages/stage2_defines.h
rename to include/trace/stages/stage2_data_offsets.h
diff --git a/include/trace/stages/stage3_defines.h b/include/trace/stages/stage3_trace_output.h
similarity index 100%
rename from include/trace/stages/stage3_defines.h
rename to include/trace/stages/stage3_trace_output.h
diff --git a/include/trace/stages/stage4_defines.h b/include/trace/stages/stage4_event_fields.h
similarity index 100%
rename from include/trace/stages/stage4_defines.h
rename to include/trace/stages/stage4_event_fields.h
diff --git a/include/trace/stages/stage5_defines.h b/include/trace/stages/stage5_get_offsets.h
similarity index 100%
rename from include/trace/stages/stage5_defines.h
rename to include/trace/stages/stage5_get_offsets.h
diff --git a/include/trace/stages/stage6_defines.h b/include/trace/stages/stage6_event_callback.h
similarity index 100%
rename from include/trace/stages/stage6_defines.h
rename to include/trace/stages/stage6_event_callback.h
diff --git a/include/trace/stages/stage7_defines.h b/include/trace/stages/stage7_class_define.h
similarity index 100%
rename from include/trace/stages/stage7_defines.h
rename to include/trace/stages/stage7_class_define.h
diff --git a/include/trace/trace_custom_events.h b/include/trace/trace_custom_events.h
index b567c720..6e492db 100644
--- a/include/trace/trace_custom_events.h
+++ b/include/trace/trace_custom_events.h
@@ -35,7 +35,7 @@
/* 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) \
@@ -56,7 +56,7 @@
/* 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) \
@@ -71,7 +71,7 @@
/* 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) \
@@ -102,7 +102,7 @@
/* 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) \
@@ -114,7 +114,7 @@
/* 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) \
@@ -134,7 +134,7 @@
/* 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) \
@@ -182,7 +182,7 @@
/* 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) \
diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
index 8a8cd66..c2f9cab 100644
--- a/include/trace/trace_events.h
+++ b/include/trace/trace_events.h
@@ -45,7 +45,7 @@
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) \
@@ -109,7 +109,7 @@
* 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) \
@@ -181,7 +181,7 @@
* 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) \
@@ -236,7 +236,7 @@
#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) \
@@ -249,7 +249,7 @@
#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) \
@@ -372,7 +372,7 @@
#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) \
@@ -418,7 +418,7 @@
#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) \
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 19028e0..8f4fb32 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -7,6 +7,7 @@
*
* Highly modified by Steven Rostedt (VMware).
*/
+#include <linux/jump_label.h>
#include <linux/suspend.h>
#include <linux/ftrace.h>
#include <linux/slab.h>
@@ -23,25 +24,13 @@
#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
*
* In case of an error int function graph tracing, this is called
@@ -51,7 +40,7 @@
*/
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.*/
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 68d62bf..706e168 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -47,9 +47,6 @@
#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);
@@ -410,19 +407,6 @@
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;
@@ -718,64 +702,14 @@
}
#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, ©);
- }
-
- 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);
if (perf_head && !hlist_empty(perf_head)) {
@@ -1141,8 +1075,6 @@
user->tracepoint.name = name;
- user_event_parse_flags(user, flags);
-
ret = user_event_parse_fields(user, args);
if (ret)
@@ -1170,11 +1102,11 @@
#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;
@@ -1186,8 +1118,12 @@
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);
@@ -1580,9 +1516,6 @@
busy++;
}
- if (flags & FLAG_BPF_ITER)
- seq_puts(m, " FLAG:BPF_ITER");
-
seq_puts(m, "\n");
active++;
}