aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/kernel/trace
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/Kconfig12
-rw-r--r--kernel/trace/blktrace.c4
-rw-r--r--kernel/trace/bpf_trace.c343
-rw-r--r--kernel/trace/ftrace.c18
-rw-r--r--kernel/trace/ftrace_internal.h22
-rw-r--r--kernel/trace/preemptirq_delay_test.c38
-rw-r--r--kernel/trace/ring_buffer.c34
-rw-r--r--kernel/trace/trace.c17
-rw-r--r--kernel/trace/trace_boot.c20
-rw-r--r--kernel/trace/trace_events_hist.c7
-rw-r--r--kernel/trace/trace_events_trigger.c10
-rw-r--r--kernel/trace/trace_kprobe.c8
-rw-r--r--kernel/trace/trace_preemptirq.c39
-rw-r--r--kernel/trace/tracing_map.c6
14 files changed, 426 insertions, 152 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 402eef84c859..24876faac753 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -10,11 +10,6 @@ config USER_STACKTRACE_SUPPORT
config NOP_TRACER
bool
-config HAVE_FTRACE_NMI_ENTER
- bool
- help
- See Documentation/trace/ftrace-design.rst
-
config HAVE_FUNCTION_TRACER
bool
help
@@ -72,11 +67,6 @@ config RING_BUFFER
select TRACE_CLOCK
select IRQ_WORK
-config FTRACE_NMI_ENTER
- bool
- depends on HAVE_FTRACE_NMI_ENTER
- default y
-
config EVENT_TRACING
select CONTEXT_SWITCH_TRACER
select GLOB
@@ -158,6 +148,7 @@ config FUNCTION_TRACER
select CONTEXT_SWITCH_TRACER
select GLOB
select TASKS_RCU if PREEMPTION
+ select TASKS_RUDE_RCU
help
Enable the kernel to trace every kernel function. This is done
by using a compiler feature to insert a small, 5-byte No-Operation
@@ -466,7 +457,6 @@ config PROFILE_ANNOTATED_BRANCHES
config PROFILE_ALL_BRANCHES
bool "Profile all if conditionals" if !FORTIFY_SOURCE
select TRACE_BRANCH_PROFILING
- imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED # avoid false positives
help
This tracer profiles all branch conditions. Every if ()
taken in the kernel is recorded whether it hit or miss.
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index ca39dc3230cb..ea47f2084087 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -170,10 +170,10 @@ void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg,
if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
blkcg = NULL;
#ifdef CONFIG_BLK_CGROUP
- trace_note(bt, 0, BLK_TN_MESSAGE, buf, n,
+ trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n,
blkcg ? cgroup_id(blkcg->css.cgroup) : 1);
#else
- trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, 0);
+ trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n, 0);
#endif
local_irq_restore(flags);
}
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index ca1796747a77..3744372a24e2 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -147,7 +147,7 @@ BPF_CALL_3(bpf_probe_read_user, void *, dst, u32, size,
return ret;
}
-static const struct bpf_func_proto bpf_probe_read_user_proto = {
+const struct bpf_func_proto bpf_probe_read_user_proto = {
.func = bpf_probe_read_user,
.gpl_only = true,
.ret_type = RET_INTEGER,
@@ -167,7 +167,7 @@ BPF_CALL_3(bpf_probe_read_user_str, void *, dst, u32, size,
return ret;
}
-static const struct bpf_func_proto bpf_probe_read_user_str_proto = {
+const struct bpf_func_proto bpf_probe_read_user_str_proto = {
.func = bpf_probe_read_user_str,
.gpl_only = true,
.ret_type = RET_INTEGER,
@@ -198,7 +198,7 @@ BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size,
return bpf_probe_read_kernel_common(dst, size, unsafe_ptr, false);
}
-static const struct bpf_func_proto bpf_probe_read_kernel_proto = {
+const struct bpf_func_proto bpf_probe_read_kernel_proto = {
.func = bpf_probe_read_kernel,
.gpl_only = true,
.ret_type = RET_INTEGER,
@@ -253,7 +253,7 @@ BPF_CALL_3(bpf_probe_read_kernel_str, void *, dst, u32, size,
return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr, false);
}
-static const struct bpf_func_proto bpf_probe_read_kernel_str_proto = {
+const struct bpf_func_proto bpf_probe_read_kernel_str_proto = {
.func = bpf_probe_read_kernel_str,
.gpl_only = true,
.ret_type = RET_INTEGER,
@@ -315,6 +315,9 @@ static const struct bpf_func_proto bpf_probe_write_user_proto = {
static const struct bpf_func_proto *bpf_get_probe_write_proto(void)
{
+ if (!capable(CAP_SYS_ADMIN))
+ return NULL;
+
pr_warn_ratelimited("%s[%d] is installing a program with bpf_probe_write_user helper that may corrupt user memory!",
current->comm, task_pid_nr(current));
@@ -323,17 +326,15 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void)
/*
* Only limited trace_printk() conversion specifiers allowed:
- * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %s
+ * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %pks %pus %s
*/
BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
u64, arg2, u64, arg3)
{
+ int i, mod[3] = {}, fmt_cnt = 0;
+ char buf[64], fmt_ptype;
+ void *unsafe_ptr = NULL;
bool str_seen = false;
- int mod[3] = {};
- int fmt_cnt = 0;
- u64 unsafe_addr;
- char buf[64];
- int i;
/*
* bpf_check()->check_func_arg()->check_stack_boundary()
@@ -359,40 +360,71 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
if (fmt[i] == 'l') {
mod[fmt_cnt]++;
i++;
- } else if (fmt[i] == 'p' || fmt[i] == 's') {
+ } else if (fmt[i] == 'p') {
mod[fmt_cnt]++;
+ if ((fmt[i + 1] == 'k' ||
+ fmt[i + 1] == 'u') &&
+ fmt[i + 2] == 's') {
+ fmt_ptype = fmt[i + 1];
+ i += 2;
+ goto fmt_str;
+ }
+
/* disallow any further format extensions */
if (fmt[i + 1] != 0 &&
!isspace(fmt[i + 1]) &&
!ispunct(fmt[i + 1]))
return -EINVAL;
- fmt_cnt++;
- if (fmt[i] == 's') {
- if (str_seen)
- /* allow only one '%s' per fmt string */
- return -EINVAL;
- str_seen = true;
-
- switch (fmt_cnt) {
- case 1:
- unsafe_addr = arg1;
- arg1 = (long) buf;
- break;
- case 2:
- unsafe_addr = arg2;
- arg2 = (long) buf;
- break;
- case 3:
- unsafe_addr = arg3;
- arg3 = (long) buf;
- break;
- }
- buf[0] = 0;
- strncpy_from_unsafe(buf,
- (void *) (long) unsafe_addr,
+
+ goto fmt_next;
+ } else if (fmt[i] == 's') {
+ mod[fmt_cnt]++;
+ fmt_ptype = fmt[i];
+fmt_str:
+ if (str_seen)
+ /* allow only one '%s' per fmt string */
+ return -EINVAL;
+ str_seen = true;
+
+ if (fmt[i + 1] != 0 &&
+ !isspace(fmt[i + 1]) &&
+ !ispunct(fmt[i + 1]))
+ return -EINVAL;
+
+ switch (fmt_cnt) {
+ case 0:
+ unsafe_ptr = (void *)(long)arg1;
+ arg1 = (long)buf;
+ break;
+ case 1:
+ unsafe_ptr = (void *)(long)arg2;
+ arg2 = (long)buf;
+ break;
+ case 2:
+ unsafe_ptr = (void *)(long)arg3;
+ arg3 = (long)buf;
+ break;
+ }
+
+ buf[0] = 0;
+ switch (fmt_ptype) {
+ case 's':
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+ strncpy_from_unsafe(buf, unsafe_ptr,
sizeof(buf));
+ break;
+#endif
+ case 'k':
+ strncpy_from_unsafe_strict(buf, unsafe_ptr,
+ sizeof(buf));
+ break;
+ case 'u':
+ strncpy_from_unsafe_user(buf,
+ (__force void __user *)unsafe_ptr,
+ sizeof(buf));
+ break;
}
- continue;
+ goto fmt_next;
}
if (fmt[i] == 'l') {
@@ -403,6 +435,7 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
if (fmt[i] != 'i' && fmt[i] != 'd' &&
fmt[i] != 'u' && fmt[i] != 'x')
return -EINVAL;
+fmt_next:
fmt_cnt++;
}
@@ -457,6 +490,212 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
return &bpf_trace_printk_proto;
}
+#define MAX_SEQ_PRINTF_VARARGS 12
+#define MAX_SEQ_PRINTF_MAX_MEMCPY 6
+#define MAX_SEQ_PRINTF_STR_LEN 128
+
+struct bpf_seq_printf_buf {
+ char buf[MAX_SEQ_PRINTF_MAX_MEMCPY][MAX_SEQ_PRINTF_STR_LEN];
+};
+static DEFINE_PER_CPU(struct bpf_seq_printf_buf, bpf_seq_printf_buf);
+static DEFINE_PER_CPU(int, bpf_seq_printf_buf_used);
+
+BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size,
+ const void *, data, u32, data_len)
+{
+ int err = -EINVAL, fmt_cnt = 0, memcpy_cnt = 0;
+ int i, buf_used, copy_size, num_args;
+ u64 params[MAX_SEQ_PRINTF_VARARGS];
+ struct bpf_seq_printf_buf *bufs;
+ const u64 *args = data;
+
+ buf_used = this_cpu_inc_return(bpf_seq_printf_buf_used);
+ if (WARN_ON_ONCE(buf_used > 1)) {
+ err = -EBUSY;
+ goto out;
+ }
+
+ bufs = this_cpu_ptr(&bpf_seq_printf_buf);
+
+ /*
+ * bpf_check()->check_func_arg()->check_stack_boundary()
+ * guarantees that fmt points to bpf program stack,
+ * fmt_size bytes of it were initialized and fmt_size > 0
+ */
+ if (fmt[--fmt_size] != 0)
+ goto out;
+
+ if (data_len & 7)
+ goto out;
+
+ for (i = 0; i < fmt_size; i++) {
+ if (fmt[i] == '%') {
+ if (fmt[i + 1] == '%')
+ i++;
+ else if (!data || !data_len)
+ goto out;
+ }
+ }
+
+ num_args = data_len / 8;
+
+ /* check format string for allowed specifiers */
+ for (i = 0; i < fmt_size; i++) {
+ /* only printable ascii for now. */
+ if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ if (fmt[i] != '%')
+ continue;
+
+ if (fmt[i + 1] == '%') {
+ i++;
+ continue;
+ }
+
+ if (fmt_cnt >= MAX_SEQ_PRINTF_VARARGS) {
+ err = -E2BIG;
+ goto out;
+ }
+
+ if (fmt_cnt >= num_args) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ /* fmt[i] != 0 && fmt[last] == 0, so we can access fmt[i + 1] */
+ i++;
+
+ /* skip optional "[0 +-][num]" width formating field */
+ while (fmt[i] == '0' || fmt[i] == '+' || fmt[i] == '-' ||
+ fmt[i] == ' ')
+ i++;
+ if (fmt[i] >= '1' && fmt[i] <= '9') {
+ i++;
+ while (fmt[i] >= '0' && fmt[i] <= '9')
+ i++;
+ }
+
+ if (fmt[i] == 's') {
+ /* try our best to copy */
+ if (memcpy_cnt >= MAX_SEQ_PRINTF_MAX_MEMCPY) {
+ err = -E2BIG;
+ goto out;
+ }
+
+ err = strncpy_from_unsafe_strict(bufs->buf[memcpy_cnt],
+ (void *) (long) args[fmt_cnt],
+ MAX_SEQ_PRINTF_STR_LEN);
+ if (err < 0)
+ bufs->buf[memcpy_cnt][0] = '\0';
+ params[fmt_cnt] = (u64)(long)bufs->buf[memcpy_cnt];
+
+ fmt_cnt++;
+ memcpy_cnt++;
+ continue;
+ }
+
+ if (fmt[i] == 'p') {
+ if (fmt[i + 1] == 0 ||
+ fmt[i + 1] == 'K' ||
+ fmt[i + 1] == 'x') {
+ /* just kernel pointers */
+ params[fmt_cnt] = args[fmt_cnt];
+ fmt_cnt++;
+ continue;
+ }
+
+ /* only support "%pI4", "%pi4", "%pI6" and "%pi6". */
+ if (fmt[i + 1] != 'i' && fmt[i + 1] != 'I') {
+ err = -EINVAL;
+ goto out;
+ }
+ if (fmt[i + 2] != '4' && fmt[i + 2] != '6') {
+ err = -EINVAL;
+ goto out;
+ }
+
+ if (memcpy_cnt >= MAX_SEQ_PRINTF_MAX_MEMCPY) {
+ err = -E2BIG;
+ goto out;
+ }
+
+
+ copy_size = (fmt[i + 2] == '4') ? 4 : 16;
+
+ err = probe_kernel_read(bufs->buf[memcpy_cnt],
+ (void *) (long) args[fmt_cnt],
+ copy_size);
+ if (err < 0)
+ memset(bufs->buf[memcpy_cnt], 0, copy_size);
+ params[fmt_cnt] = (u64)(long)bufs->buf[memcpy_cnt];
+
+ i += 2;
+ fmt_cnt++;
+ memcpy_cnt++;
+ continue;
+ }
+
+ if (fmt[i] == 'l') {
+ i++;
+ if (fmt[i] == 'l')
+ i++;
+ }
+
+ if (fmt[i] != 'i' && fmt[i] != 'd' &&
+ fmt[i] != 'u' && fmt[i] != 'x') {
+ err = -EINVAL;
+ goto out;
+ }
+
+ params[fmt_cnt] = args[fmt_cnt];
+ fmt_cnt++;
+ }
+
+ /* Maximumly we can have MAX_SEQ_PRINTF_VARARGS parameter, just give
+ * all of them to seq_printf().
+ */
+ seq_printf(m, fmt, params[0], params[1], params[2], params[3],
+ params[4], params[5], params[6], params[7], params[8],
+ params[9], params[10], params[11]);
+
+ err = seq_has_overflowed(m) ? -EOVERFLOW : 0;
+out:
+ this_cpu_dec(bpf_seq_printf_buf_used);
+ return err;
+}
+
+static int bpf_seq_printf_btf_ids[5];
+static const struct bpf_func_proto bpf_seq_printf_proto = {
+ .func = bpf_seq_printf,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_BTF_ID,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_PTR_TO_MEM_OR_NULL,
+ .arg5_type = ARG_CONST_SIZE_OR_ZERO,
+ .btf_id = bpf_seq_printf_btf_ids,
+};
+
+BPF_CALL_3(bpf_seq_write, struct seq_file *, m, const void *, data, u32, len)
+{
+ return seq_write(m, data, len) ? -EOVERFLOW : 0;
+}
+
+static int bpf_seq_write_btf_ids[5];
+static const struct bpf_func_proto bpf_seq_write_proto = {
+ .func = bpf_seq_write,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_BTF_ID,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE_OR_ZERO,
+ .btf_id = bpf_seq_write_btf_ids,
+};
+
static __always_inline int
get_map_perf_counter(struct bpf_map *map, u64 flags,
u64 *value, u64 *enabled, u64 *running)
@@ -668,7 +907,7 @@ BPF_CALL_0(bpf_get_current_task)
return (long) current;
}
-static const struct bpf_func_proto bpf_get_current_task_proto = {
+const struct bpf_func_proto bpf_get_current_task_proto = {
.func = bpf_get_current_task,
.gpl_only = true,
.ret_type = RET_INTEGER,
@@ -797,6 +1036,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_map_peek_elem_proto;
case BPF_FUNC_ktime_get_ns:
return &bpf_ktime_get_ns_proto;
+ case BPF_FUNC_ktime_get_boot_ns:
+ return &bpf_ktime_get_boot_ns_proto;
case BPF_FUNC_tail_call:
return &bpf_tail_call_proto;
case BPF_FUNC_get_current_pid_tgid:
@@ -825,14 +1066,16 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_probe_read_user_proto;
case BPF_FUNC_probe_read_kernel:
return &bpf_probe_read_kernel_proto;
- case BPF_FUNC_probe_read:
- return &bpf_probe_read_compat_proto;
case BPF_FUNC_probe_read_user_str:
return &bpf_probe_read_user_str_proto;
case BPF_FUNC_probe_read_kernel_str:
return &bpf_probe_read_kernel_str_proto;
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+ case BPF_FUNC_probe_read:
+ return &bpf_probe_read_compat_proto;
case BPF_FUNC_probe_read_str:
return &bpf_probe_read_compat_str_proto;
+#endif
#ifdef CONFIG_CGROUPS
case BPF_FUNC_get_current_cgroup_id:
return &bpf_get_current_cgroup_id_proto;
@@ -845,6 +1088,16 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_perf_event_read_value_proto;
case BPF_FUNC_get_ns_current_pid_tgid:
return &bpf_get_ns_current_pid_tgid_proto;
+ case BPF_FUNC_ringbuf_output:
+ return &bpf_ringbuf_output_proto;
+ case BPF_FUNC_ringbuf_reserve:
+ return &bpf_ringbuf_reserve_proto;
+ case BPF_FUNC_ringbuf_submit:
+ return &bpf_ringbuf_submit_proto;
+ case BPF_FUNC_ringbuf_discard:
+ return &bpf_ringbuf_discard_proto;
+ case BPF_FUNC_ringbuf_query:
+ return &bpf_ringbuf_query_proto;
default:
return NULL;
}
@@ -1214,7 +1467,7 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
}
}
-static const struct bpf_func_proto *
+const struct bpf_func_proto *
tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
@@ -1224,6 +1477,14 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_xdp_output:
return &bpf_xdp_output_proto;
#endif
+ case BPF_FUNC_seq_printf:
+ return prog->expected_attach_type == BPF_TRACE_ITER ?
+ &bpf_seq_printf_proto :
+ NULL;
+ case BPF_FUNC_seq_write:
+ return prog->expected_attach_type == BPF_TRACE_ITER ?
+ &bpf_seq_write_proto :
+ NULL;
default:
return raw_tp_prog_func_proto(func_id, prog);
}
@@ -1468,7 +1729,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
u32 *ids, prog_cnt, ids_len;
int ret;
- if (!capable(CAP_SYS_ADMIN))
+ if (!perfmon_capable())
return -EPERM;
if (event->attr.type != PERF_TYPE_TRACEPOINT)
return -EINVAL;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 041694a1eb74..b5765aeea698 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -160,17 +160,6 @@ static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
op->saved_func(ip, parent_ip, op, regs);
}
-static void ftrace_sync(struct work_struct *work)
-{
- /*
- * This function is just a stub to implement a hard force
- * of synchronize_rcu(). This requires synchronizing
- * tasks even in userspace and idle.
- *
- * Yes, function tracing is rude.
- */
-}
-
static void ftrace_sync_ipi(void *data)
{
/* Probably not needed, but do it anyway */
@@ -256,7 +245,7 @@ static void update_ftrace_function(void)
* Make sure all CPUs see this. Yes this is slow, but static
* tracing is slow and nasty to have enabled.
*/
- schedule_on_each_cpu(ftrace_sync);
+ synchronize_rcu_tasks_rude();
/* Now all cpus are using the list ops. */
function_trace_op = set_function_trace_op;
/* Make sure the function_trace_op is visible on all CPUs */
@@ -2932,7 +2921,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
* infrastructure to do the synchronization, thus we must do it
* ourselves.
*/
- schedule_on_each_cpu(ftrace_sync);
+ synchronize_rcu_tasks_rude();
/*
* When the kernel is preeptive, tasks can be preempted
@@ -5165,6 +5154,7 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr)
list_del_rcu(&direct->next);
synchronize_rcu_tasks();
kfree(direct);
+ kfree(entry);
ftrace_direct_func_count--;
}
}
@@ -5887,7 +5877,7 @@ ftrace_graph_release(struct inode *inode, struct file *file)
* infrastructure to do the synchronization, thus we must do it
* ourselves.
*/
- schedule_on_each_cpu(ftrace_sync);
+ synchronize_rcu_tasks_rude();
free_ftrace_hash(old_hash);
}
diff --git a/kernel/trace/ftrace_internal.h b/kernel/trace/ftrace_internal.h
index 0456e0a3dab1..382775edf690 100644
--- a/kernel/trace/ftrace_internal.h
+++ b/kernel/trace/ftrace_internal.h
@@ -4,28 +4,6 @@
#ifdef CONFIG_FUNCTION_TRACER
-/*
- * Traverse the ftrace_global_list, invoking all entries. The reason that we
- * can use rcu_dereference_raw_check() is that elements removed from this list
- * are simply leaked, so there is no need to interact with a grace-period
- * mechanism. The rcu_dereference_raw_check() calls are needed to handle
- * concurrent insertions into the ftrace_global_list.
- *
- * Silly Alpha and silly pointer-speculation compiler optimizations!
- */
-#define do_for_each_ftrace_op(op, list) \
- op = rcu_dereference_raw_check(list); \
- do
-
-/*
- * Optimized for just a single item in the list (as that is the normal case).
- */
-#define while_for_each_ftrace_op(op) \
- while (likely(op = rcu_dereference_raw_check((op)->next)) && \
- unlikely((op) != &ftrace_list_end))
-
-extern struct ftrace_ops __rcu *ftrace_ops_list;
-extern struct ftrace_ops ftrace_list_end;
extern struct mutex ftrace_lock;
extern struct ftrace_ops global_ops;
diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c
index 31c0fad4cb9e..312d1a0ca3b6 100644
--- a/kernel/trace/preemptirq_delay_test.c
+++ b/kernel/trace/preemptirq_delay_test.c
@@ -16,6 +16,7 @@
#include <linux/printk.h>
#include <linux/string.h>
#include <linux/sysfs.h>
+#include <linux/completion.h>
static ulong delay = 100;
static char test_mode[12] = "irq";
@@ -28,6 +29,8 @@ MODULE_PARM_DESC(delay, "Period in microseconds (100 us default)");
MODULE_PARM_DESC(test_mode, "Mode of the test such as preempt, irq, or alternate (default irq)");
MODULE_PARM_DESC(burst_size, "The size of a burst (default 1)");
+static struct completion done;
+
#define MIN(x, y) ((x) < (y) ? (x) : (y))
static void busy_wait(ulong time)
@@ -113,22 +116,47 @@ static int preemptirq_delay_run(void *data)
for (i = 0; i < s; i++)
(testfuncs[i])(i);
+
+ complete(&done);
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ while (!kthread_should_stop()) {
+ schedule();
+ set_current_state(TASK_INTERRUPTIBLE);
+ }
+
+ __set_current_state(TASK_RUNNING);
+
return 0;
}
-static struct task_struct *preemptirq_start_test(void)
+static int preemptirq_run_test(void)
{
+ struct task_struct *task;
char task_name[50];
+ init_completion(&done);
+
snprintf(task_name, sizeof(task_name), "%s_test", test_mode);
- return kthread_run(preemptirq_delay_run, NULL, task_name);
+ task = kthread_run(preemptirq_delay_run, NULL, task_name);
+ if (IS_ERR(task))
+ return PTR_ERR(task);
+ if (task) {
+ wait_for_completion(&done);
+ kthread_stop(task);
+ }
+ return 0;
}
static ssize_t trigger_store(struct kobject *kobj, struct kobj_attribute *attr,
const char *buf, size_t count)
{
- preemptirq_start_test();
+ ssize_t ret;
+
+ ret = preemptirq_run_test();
+ if (ret)
+ return ret;
return count;
}
@@ -148,11 +176,9 @@ static struct kobject *preemptirq_delay_kobj;
static int __init preemptirq_delay_init(void)
{
- struct task_struct *test_task;
int retval;
- test_task = preemptirq_start_test();
- retval = PTR_ERR_OR_ZERO(test_task);
+ retval = preemptirq_run_test();
if (retval != 0)
return retval;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 6f0b42ceeb00..b8e1ca48be50 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -193,7 +193,7 @@ rb_event_length(struct ring_buffer_event *event)
case RINGBUF_TYPE_DATA:
return rb_event_data_length(event);
default:
- BUG();
+ WARN_ON_ONCE(1);
}
/* not hit */
return 0;
@@ -249,7 +249,7 @@ rb_event_data(struct ring_buffer_event *event)
{
if (extended_time(event))
event = skip_time_extend(event);
- BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
+ WARN_ON_ONCE(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
/* If length is in len field, then array[0] has the data */
if (event->type_len)
return (void *)&event->array[0];
@@ -3727,7 +3727,7 @@ rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
return;
default:
- BUG();
+ RB_WARN_ON(cpu_buffer, 1);
}
return;
}
@@ -3757,7 +3757,7 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter,
return;
default:
- BUG();
+ RB_WARN_ON(iter->cpu_buffer, 1);
}
return;
}
@@ -4020,7 +4020,7 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts,
return event;
default:
- BUG();
+ RB_WARN_ON(cpu_buffer, 1);
}
return NULL;
@@ -4034,7 +4034,6 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
struct ring_buffer_per_cpu *cpu_buffer;
struct ring_buffer_event *event;
int nr_loops = 0;
- bool failed = false;
if (ts)
*ts = 0;
@@ -4056,19 +4055,14 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
return NULL;
/*
- * We repeat when a time extend is encountered or we hit
- * the end of the page. Since the time extend is always attached
- * to a data event, we should never loop more than three times.
- * Once for going to next page, once on time extend, and
- * finally once to get the event.
- * We should never hit the following condition more than thrice,
- * unless the buffer is very small, and there's a writer
- * that is causing the reader to fail getting an event.
+ * As the writer can mess with what the iterator is trying
+ * to read, just give up if we fail to get an event after
+ * three tries. The iterator is not as reliable when reading
+ * the ring buffer with an active write as the consumer is.
+ * Do not warn if the three failures is reached.
*/
- if (++nr_loops > 3) {
- RB_WARN_ON(cpu_buffer, !failed);
+ if (++nr_loops > 3)
return NULL;
- }
if (rb_per_cpu_empty(cpu_buffer))
return NULL;
@@ -4079,10 +4073,8 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
}
event = rb_iter_head_event(iter);
- if (!event) {
- failed = true;
+ if (!event)
goto again;
- }
switch (event->type_len) {
case RINGBUF_TYPE_PADDING:
@@ -4117,7 +4109,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
return event;
default:
- BUG();
+ RB_WARN_ON(cpu_buffer, 1);
}
return NULL;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8d2b98812625..3ab27022c20f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -947,7 +947,8 @@ int __trace_bputs(unsigned long ip, const char *str)
EXPORT_SYMBOL_GPL(__trace_bputs);
#ifdef CONFIG_TRACER_SNAPSHOT
-void tracing_snapshot_instance_cond(struct trace_array *tr, void *cond_data)
+static void tracing_snapshot_instance_cond(struct trace_array *tr,
+ void *cond_data)
{
struct tracer *tracer = tr->current_trace;
unsigned long flags;
@@ -2661,7 +2662,7 @@ static void output_printk(struct trace_event_buffer *fbuffer)
}
int tracepoint_printk_sysctl(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp,
+ void *buffer, size_t *lenp,
loff_t *ppos)
{
int save_tracepoint_printk;
@@ -6304,13 +6305,6 @@ static void tracing_spd_release_pipe(struct splice_pipe_desc *spd,
__free_page(spd->pages[idx]);
}
-static const struct pipe_buf_operations tracing_pipe_buf_ops = {
- .confirm = generic_pipe_buf_confirm,
- .release = generic_pipe_buf_release,
- .steal = generic_pipe_buf_steal,
- .get = generic_pipe_buf_get,
-};
-
static size_t
tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter)
{
@@ -6372,7 +6366,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
.partial = partial_def,
.nr_pages = 0, /* This gets updated below. */
.nr_pages_max = PIPE_DEF_BUFFERS,
- .ops = &tracing_pipe_buf_ops,
+ .ops = &default_pipe_buf_ops,
.spd_release = tracing_spd_release_pipe,
};
ssize_t ret;
@@ -7581,9 +7575,7 @@ static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe,
/* Pipe buffer operations for a buffer. */
static const struct pipe_buf_operations buffer_pipe_buf_ops = {
- .confirm = generic_pipe_buf_confirm,
.release = buffer_pipe_buf_release,
- .steal = generic_pipe_buf_nosteal,
.get = buffer_pipe_buf_get,
};
@@ -8525,6 +8517,7 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
*/
allocate_snapshot = false;
#endif
+
return 0;
}
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 06d7feb5255f..9de29bb45a27 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -95,24 +95,20 @@ trace_boot_add_kprobe_event(struct xbc_node *node, const char *event)
struct xbc_node *anode;
char buf[MAX_BUF_LEN];
const char *val;
- int ret;
+ int ret = 0;
- kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN);
+ xbc_node_for_each_array_value(node, "probes", anode, val) {
+ kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN);
- ret = kprobe_event_gen_cmd_start(&cmd, event, NULL);
- if (ret)
- return ret;
+ ret = kprobe_event_gen_cmd_start(&cmd, event, val);
+ if (ret)
+ break;
- xbc_node_for_each_array_value(node, "probes", anode, val) {
- ret = kprobe_event_add_field(&cmd, val);
+ ret = kprobe_event_gen_cmd_end(&cmd);
if (ret)
- return ret;
+ pr_err("Failed to add probe: %s\n", buf);
}
- ret = kprobe_event_gen_cmd_end(&cmd);
- if (ret)
- pr_err("Failed to add probe: %s\n", buf);
-
return ret;
}
#else
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 5f6834a2bf41..fcab11cc6833 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -3320,6 +3320,9 @@ static void __destroy_hist_field(struct hist_field *hist_field)
kfree(hist_field->name);
kfree(hist_field->type);
+ kfree(hist_field->system);
+ kfree(hist_field->event_name);
+
kfree(hist_field);
}
@@ -4382,6 +4385,7 @@ static struct hist_field *create_var(struct hist_trigger_data *hist_data,
goto out;
}
+ var->ref = 1;
var->flags = HIST_FIELD_FL_VAR;
var->var.idx = idx;
var->var.hist_data = var->hist_data = hist_data;
@@ -5011,6 +5015,9 @@ static void destroy_field_vars(struct hist_trigger_data *hist_data)
for (i = 0; i < hist_data->n_field_vars; i++)
destroy_field_var(hist_data->field_vars[i]);
+
+ for (i = 0; i < hist_data->n_save_vars; i++)
+ destroy_field_var(hist_data->save_vars[i]);
}
static void save_field_var(struct hist_trigger_data *hist_data,
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index dd34a1b46a86..3a74736da363 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -1088,14 +1088,10 @@ register_snapshot_trigger(char *glob, struct event_trigger_ops *ops,
struct event_trigger_data *data,
struct trace_event_file *file)
{
- int ret = register_trigger(glob, ops, data, file);
-
- if (ret > 0 && tracing_alloc_snapshot_instance(file->tr) != 0) {
- unregister_trigger(glob, ops, data, file);
- ret = 0;
- }
+ if (tracing_alloc_snapshot_instance(file->tr) != 0)
+ return 0;
- return ret;
+ return register_trigger(glob, ops, data, file);
}
static int
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index d0568af4a0ef..35989383ae11 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -453,7 +453,7 @@ static bool __within_notrace_func(unsigned long addr)
static bool within_notrace_func(struct trace_kprobe *tk)
{
- unsigned long addr = addr = trace_kprobe_address(tk);
+ unsigned long addr = trace_kprobe_address(tk);
char symname[KSYM_NAME_LEN], *p;
if (!__within_notrace_func(addr))
@@ -940,6 +940,9 @@ EXPORT_SYMBOL_GPL(kprobe_event_cmd_init);
* complete command or only the first part of it; in the latter case,
* kprobe_event_add_fields() can be used to add more fields following this.
*
+ * Unlikely the synth_event_gen_cmd_start(), @loc must be specified. This
+ * returns -EINVAL if @loc == NULL.
+ *
* Return: 0 if successful, error otherwise.
*/
int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe,
@@ -953,6 +956,9 @@ int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe,
if (cmd->type != DYNEVENT_TYPE_KPROBE)
return -EINVAL;
+ if (!loc)
+ return -EINVAL;
+
if (kretprobe)
snprintf(buf, MAX_EVENT_NAME_LEN, "r:kprobes/%s", name);
else
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index 4d8e99fdbbbe..fb0691b8a88d 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -19,6 +19,24 @@
/* Per-cpu variable to prevent redundant calls when IRQs already off */
static DEFINE_PER_CPU(int, tracing_irq_cpu);
+/*
+ * Like trace_hardirqs_on() but without the lockdep invocation. This is
+ * used in the low level entry code where the ordering vs. RCU is important
+ * and lockdep uses a staged approach which splits the lockdep hardirq
+ * tracking into a RCU on and a RCU off section.
+ */
+void trace_hardirqs_on_prepare(void)
+{
+ if (this_cpu_read(tracing_irq_cpu)) {
+ if (!in_nmi())
+ trace_irq_enable(CALLER_ADDR0, CALLER_ADDR1);
+ tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1);
+ this_cpu_write(tracing_irq_cpu, 0);
+ }
+}
+EXPORT_SYMBOL(trace_hardirqs_on_prepare);
+NOKPROBE_SYMBOL(trace_hardirqs_on_prepare);
+
void trace_hardirqs_on(void)
{
if (this_cpu_read(tracing_irq_cpu)) {
@@ -28,11 +46,31 @@ void trace_hardirqs_on(void)
this_cpu_write(tracing_irq_cpu, 0);
}
+ lockdep_hardirqs_on_prepare(CALLER_ADDR0);
lockdep_hardirqs_on(CALLER_ADDR0);
}
EXPORT_SYMBOL(trace_hardirqs_on);
NOKPROBE_SYMBOL(trace_hardirqs_on);
+/*
+ * Like trace_hardirqs_off() but without the lockdep invocation. This is
+ * used in the low level entry code where the ordering vs. RCU is important
+ * and lockdep uses a staged approach which splits the lockdep hardirq
+ * tracking into a RCU on and a RCU off section.
+ */
+void trace_hardirqs_off_prepare(void)
+{
+ if (!this_cpu_read(tracing_irq_cpu)) {
+ this_cpu_write(tracing_irq_cpu, 1);
+ tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1);
+ if (!in_nmi())
+ trace_irq_disable(CALLER_ADDR0, CALLER_ADDR1);
+ }
+
+}
+EXPORT_SYMBOL(trace_hardirqs_off_prepare);
+NOKPROBE_SYMBOL(trace_hardirqs_off_prepare);
+
void trace_hardirqs_off(void)
{
if (!this_cpu_read(tracing_irq_cpu)) {
@@ -56,6 +94,7 @@ __visible void trace_hardirqs_on_caller(unsigned long caller_addr)
this_cpu_write(tracing_irq_cpu, 0);
}
+ lockdep_hardirqs_on_prepare(CALLER_ADDR0);
lockdep_hardirqs_on(CALLER_ADDR0);
}
EXPORT_SYMBOL(trace_hardirqs_on_caller);
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 9e31bfc818ff..74738c9856f1 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -283,7 +283,7 @@ int tracing_map_add_key_field(struct tracing_map *map,
return idx;
}
-void tracing_map_array_clear(struct tracing_map_array *a)
+static void tracing_map_array_clear(struct tracing_map_array *a)
{
unsigned int i;
@@ -294,7 +294,7 @@ void tracing_map_array_clear(struct tracing_map_array *a)
memset(a->pages[i], 0, PAGE_SIZE);
}
-void tracing_map_array_free(struct tracing_map_array *a)
+static void tracing_map_array_free(struct tracing_map_array *a)
{
unsigned int i;
@@ -316,7 +316,7 @@ void tracing_map_array_free(struct tracing_map_array *a)
kfree(a);
}
-struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts,
+static struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts,
unsigned int entry_size)
{
struct tracing_map_array *a;
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.