hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

tracing/user_events: Remove eBPF interfaces 

Remove eBPF interfaces within user_events to ensure they are fully
reviewed.

Link: https://lore.kernel.org/all/20220329165718.GA10381@kbox/
Link: https://lkml.kernel.org/r/20220329173051.10087-1-beaub@linux.microsoft.com

Suggested-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
This commit is contained in:
Beau Belgrave 2022-03-29 10:30:51 -07:00 committed by Steven Rostedt (Google)
parent efe34e99fc
commit 768c1e7f1d
3 changed files with 4 additions and 136 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
Documentation/trace/user_events.rst
View File

@ -7,7 +7,7 @@ user_events: User-based Event Tracing
Overview Overview
-------- --------
User based trace events allow user processes to create events and trace data 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. To enable this feature, build your kernel with CONFIG_USER_EVENTS=y.
Programs can view status of the events via Programs can view status of the events via
@ -67,8 +67,7 @@ The command string format is as follows::
Supported Flags Supported Flags
^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^
**BPF_ITER** - EBPF programs attached to this event will get the raw iovec None yet
struct instead of any data copies for max performance.
Field Format Field Format
^^^^^^^^^^^^ ^^^^^^^^^^^^
@ -160,7 +159,7 @@ The following values are defined to aid in checking what has been attached:
**EVENT_STATUS_FTRACE** - Bit set if ftrace has been attached (Bit 0). **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 Writing Data
------------ ------------
@ -204,13 +203,6 @@ It's advised for user programs to do the following::
**NOTE:** *The write_index is not emitted out into the trace being recorded.* **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 Example Code
------------ ------------
See sample code in samples/user_events. See sample code in samples/user_events.

53
include/uapi/linux/user_events.h
View File

@ -32,9 +32,6 @@
/* Create dynamic location entry within a 32-bit value */ /* Create dynamic location entry within a 32-bit value */
#define DYN_LOC(offset, size) ((size) << 16 | (offset)) #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. * Describes an event registration and stores the results of the registration.
* This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum
@ -63,54 +60,4 @@ struct user_reg {
/* Requests to delete a user_event */ /* Requests to delete a user_event */
#define DIAG_IOCSDEL _IOW(DIAG_IOC_MAGIC, 1, char*) #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 */ #endif /* _UAPI_LINUX_USER_EVENTS_H */

73
kernel/trace/trace_events_user.c
View File

@ -42,9 +42,6 @@
#define MAX_FIELD_ARRAY_SIZE 1024 #define MAX_FIELD_ARRAY_SIZE 1024
#define MAX_FIELD_ARG_NAME 256 #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 char *register_page_data;
static DEFINE_MUTEX(reg_mutex); static DEFINE_MUTEX(reg_mutex);
@ -405,19 +402,6 @@ parse:
type[0] != 'u', FILTER_OTHER); 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) static int user_event_parse_fields(struct user_event *user, char *args)
{ {
char *field; char *field;
@ -713,64 +697,14 @@ discard:
} }
#ifdef CONFIG_PERF_EVENTS #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, static void user_event_perf(struct user_event *user, struct iov_iter *i,
void *tpdata, bool *faulted) void *tpdata, bool *faulted)
{ {
struct hlist_head *perf_head; 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); perf_head = this_cpu_ptr(user->call.perf_events);
if (perf_head && !hlist_empty(perf_head)) { if (perf_head && !hlist_empty(perf_head)) {
@ -1136,8 +1070,6 @@ static int user_event_parse(char *name, char *args, char *flags,
user->tracepoint.name = name; user->tracepoint.name = name;
user_event_parse_flags(user, flags);
ret = user_event_parse_fields(user, args); ret = user_event_parse_fields(user, args);
if (ret) if (ret)
@ -1579,9 +1511,6 @@ static int user_seq_show(struct seq_file *m, void *p)
busy++; busy++;
} }
if (flags & FLAG_BPF_ITER)
seq_puts(m, " FLAG:BPF_ITER");
seq_puts(m, "\n"); seq_puts(m, "\n");
active++; active++;
} }