summaryrefslogtreecommitdiffstats
path: root/kernel/trace/bpf_trace.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace/bpf_trace.c')
-rw-r--r--kernel/trace/bpf_trace.c100
1 files changed, 65 insertions, 35 deletions
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 460a031c77e5..dc498b605d5d 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -122,8 +122,8 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void)
}
/*
- * limited trace_printk()
- * only %d %u %x %ld %lu %lx %lld %llu %llx %p %s conversion specifiers allowed
+ * Only limited trace_printk() conversion specifiers allowed:
+ * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %s
*/
BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
u64, arg2, u64, arg3)
@@ -198,15 +198,42 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
i++;
}
- if (fmt[i] != 'd' && fmt[i] != 'u' && fmt[i] != 'x')
+ if (fmt[i] != 'i' && fmt[i] != 'd' &&
+ fmt[i] != 'u' && fmt[i] != 'x')
return -EINVAL;
fmt_cnt++;
}
- return __trace_printk(1/* fake ip will not be printed */, fmt,
- mod[0] == 2 ? arg1 : mod[0] == 1 ? (long) arg1 : (u32) arg1,
- mod[1] == 2 ? arg2 : mod[1] == 1 ? (long) arg2 : (u32) arg2,
- mod[2] == 2 ? arg3 : mod[2] == 1 ? (long) arg3 : (u32) arg3);
+/* Horrid workaround for getting va_list handling working with different
+ * argument type combinations generically for 32 and 64 bit archs.
+ */
+#define __BPF_TP_EMIT() __BPF_ARG3_TP()
+#define __BPF_TP(...) \
+ __trace_printk(1 /* Fake ip will not be printed. */, \
+ fmt, ##__VA_ARGS__)
+
+#define __BPF_ARG1_TP(...) \
+ ((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64)) \
+ ? __BPF_TP(arg1, ##__VA_ARGS__) \
+ : ((mod[0] == 1 || (mod[0] == 0 && __BITS_PER_LONG == 32)) \
+ ? __BPF_TP((long)arg1, ##__VA_ARGS__) \
+ : __BPF_TP((u32)arg1, ##__VA_ARGS__)))
+
+#define __BPF_ARG2_TP(...) \
+ ((mod[1] == 2 || (mod[1] == 1 && __BITS_PER_LONG == 64)) \
+ ? __BPF_ARG1_TP(arg2, ##__VA_ARGS__) \
+ : ((mod[1] == 1 || (mod[1] == 0 && __BITS_PER_LONG == 32)) \
+ ? __BPF_ARG1_TP((long)arg2, ##__VA_ARGS__) \
+ : __BPF_ARG1_TP((u32)arg2, ##__VA_ARGS__)))
+
+#define __BPF_ARG3_TP(...) \
+ ((mod[2] == 2 || (mod[2] == 1 && __BITS_PER_LONG == 64)) \
+ ? __BPF_ARG2_TP(arg3, ##__VA_ARGS__) \
+ : ((mod[2] == 1 || (mod[2] == 0 && __BITS_PER_LONG == 32)) \
+ ? __BPF_ARG2_TP((long)arg3, ##__VA_ARGS__) \
+ : __BPF_ARG2_TP((u32)arg3, ##__VA_ARGS__)))
+
+ return __BPF_TP_EMIT();
}
static const struct bpf_func_proto bpf_trace_printk_proto = {
@@ -234,7 +261,8 @@ BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags)
unsigned int cpu = smp_processor_id();
u64 index = flags & BPF_F_INDEX_MASK;
struct bpf_event_entry *ee;
- struct perf_event *event;
+ u64 value = 0;
+ int err;
if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
return -EINVAL;
@@ -247,21 +275,14 @@ BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags)
if (!ee)
return -ENOENT;
- event = ee->event;
- if (unlikely(event->attr.type != PERF_TYPE_HARDWARE &&
- event->attr.type != PERF_TYPE_RAW))
- return -EINVAL;
-
- /* make sure event is local and doesn't have pmu::count */
- if (unlikely(event->oncpu != cpu || event->pmu->count))
- return -EINVAL;
-
+ err = perf_event_read_local(ee->event, &value);
/*
- * we don't know if the function is run successfully by the
- * return value. It can be judged in other places, such as
- * eBPF programs.
+ * this api is ugly since we miss [-22..-2] range of valid
+ * counter values, but that's uapi
*/
- return perf_event_read_local(event);
+ if (err)
+ return err;
+ return value;
}
static const struct bpf_func_proto bpf_perf_event_read_proto = {
@@ -272,14 +293,16 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = {
.arg2_type = ARG_ANYTHING,
};
+static DEFINE_PER_CPU(struct perf_sample_data, bpf_sd);
+
static __always_inline u64
__bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
u64 flags, struct perf_raw_record *raw)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
+ struct perf_sample_data *sd = this_cpu_ptr(&bpf_sd);
unsigned int cpu = smp_processor_id();
u64 index = flags & BPF_F_INDEX_MASK;
- struct perf_sample_data sample_data;
struct bpf_event_entry *ee;
struct perf_event *event;
@@ -300,9 +323,9 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
if (unlikely(event->oncpu != cpu))
return -EOPNOTSUPP;
- perf_sample_data_init(&sample_data, 0, 0);
- sample_data.raw = raw;
- perf_event_output(event, &sample_data, regs);
+ perf_sample_data_init(sd, 0, 0);
+ sd->raw = raw;
+ perf_event_output(event, sd, regs);
return 0;
}
@@ -483,7 +506,7 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
/* bpf+kprobe programs can access fields of 'struct pt_regs' */
static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
- enum bpf_reg_type *reg_type)
+ struct bpf_insn_access_aux *info)
{
if (off < 0 || off >= sizeof(struct pt_regs))
return false;
@@ -566,7 +589,7 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
}
static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type,
- enum bpf_reg_type *reg_type)
+ struct bpf_insn_access_aux *info)
{
if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE)
return false;
@@ -585,40 +608,47 @@ const struct bpf_verifier_ops tracepoint_prog_ops = {
};
static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
- enum bpf_reg_type *reg_type)
+ struct bpf_insn_access_aux *info)
{
+ const int size_sp = FIELD_SIZEOF(struct bpf_perf_event_data,
+ sample_period);
+
if (off < 0 || off >= sizeof(struct bpf_perf_event_data))
return false;
if (type != BPF_READ)
return false;
if (off % size != 0)
return false;
- if (off == offsetof(struct bpf_perf_event_data, sample_period)) {
- if (size != sizeof(u64))
+
+ switch (off) {
+ case bpf_ctx_range(struct bpf_perf_event_data, sample_period):
+ bpf_ctx_record_field_size(info, size_sp);
+ if (!bpf_ctx_narrow_access_ok(off, size, size_sp))
return false;
- } else {
+ break;
+ default:
if (size != sizeof(long))
return false;
}
+
return true;
}
static u32 pe_prog_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
- struct bpf_prog *prog)
+ struct bpf_prog *prog, u32 *target_size)
{
struct bpf_insn *insn = insn_buf;
switch (si->off) {
case offsetof(struct bpf_perf_event_data, sample_period):
- BUILD_BUG_ON(FIELD_SIZEOF(struct perf_sample_data, period) != sizeof(u64));
-
*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern,
data), si->dst_reg, si->src_reg,
offsetof(struct bpf_perf_event_data_kern, data));
*insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg,
- offsetof(struct perf_sample_data, period));
+ bpf_target_off(struct perf_sample_data, period, 8,
+ target_size));
break;
default:
*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern,
generated by cgit v1.2.3-55-g7522 (git 2.39.0) at 2025-05-11 01:49:56 +0200