aboutsummaryrefslogtreecommitdiff
path: root/kernel/trace
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/Kconfig41
-rw-r--r--kernel/trace/Makefile2
-rw-r--r--kernel/trace/bpf_trace.c440
-rw-r--r--kernel/trace/fgraph.c27
-rw-r--r--kernel/trace/fprobe.c38
-rw-r--r--kernel/trace/ftrace.c110
-rw-r--r--kernel/trace/ftrace_internal.h5
-rw-r--r--kernel/trace/rethook.c16
-rw-r--r--kernel/trace/ring_buffer.c83
-rw-r--r--kernel/trace/trace.c193
-rw-r--r--kernel/trace/trace.h39
-rw-r--r--kernel/trace/trace_boot.c8
-rw-r--r--kernel/trace/trace_btf.c122
-rw-r--r--kernel/trace/trace_btf.h11
-rw-r--r--kernel/trace/trace_entries.h28
-rw-r--r--kernel/trace/trace_eprobe.c80
-rw-r--r--kernel/trace/trace_events.c94
-rw-r--r--kernel/trace/trace_events_filter.c315
-rw-r--r--kernel/trace/trace_events_hist.c9
-rw-r--r--kernel/trace/trace_events_inject.c4
-rw-r--r--kernel/trace/trace_events_synth.c104
-rw-r--r--kernel/trace/trace_events_trigger.c2
-rw-r--r--kernel/trace/trace_events_user.c23
-rw-r--r--kernel/trace/trace_export.c9
-rw-r--r--kernel/trace/trace_fprobe.c1230
-rw-r--r--kernel/trace/trace_functions_graph.c93
-rw-r--r--kernel/trace/trace_hwlat.c2
-rw-r--r--kernel/trace/trace_irqsoff.c3
-rw-r--r--kernel/trace/trace_kprobe.c51
-rw-r--r--kernel/trace/trace_kprobe_selftest.c3
-rw-r--r--kernel/trace/trace_osnoise.c477
-rw-r--r--kernel/trace/trace_output.c4
-rw-r--r--kernel/trace/trace_probe.c898
-rw-r--r--kernel/trace/trace_probe.h73
-rw-r--r--kernel/trace/trace_probe_kernel.h30
-rw-r--r--kernel/trace/trace_probe_tmpl.h10
-rw-r--r--kernel/trace/trace_sched_wakeup.c2
-rw-r--r--kernel/trace/trace_seq.c1
-rw-r--r--kernel/trace/trace_syscalls.c12
-rw-r--r--kernel/trace/trace_uprobe.c22
-rw-r--r--kernel/trace/tracing_map.h4
41 files changed, 4150 insertions, 568 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 8cf97fa4a4b3..61c541c36596 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -31,6 +31,9 @@ config HAVE_FUNCTION_GRAPH_TRACER
help
See Documentation/trace/ftrace-design.rst
+config HAVE_FUNCTION_GRAPH_RETVAL
+ bool
+
config HAVE_DYNAMIC_FTRACE
bool
help
@@ -227,6 +230,18 @@ config FUNCTION_GRAPH_TRACER
the return value. This is done by setting the current return
address on the current task structure into a stack of calls.
+config FUNCTION_GRAPH_RETVAL
+ bool "Kernel Function Graph Return Value"
+ depends on HAVE_FUNCTION_GRAPH_RETVAL
+ depends on FUNCTION_GRAPH_TRACER
+ default n
+ help
+ Support recording and printing the function return value when
+ using function graph tracer. It can be helpful to locate functions
+ that return errors. This feature is off by default, and you can
+ enable it via the trace option funcgraph-retval.
+ See Documentation/trace/ftrace.rst
+
config DYNAMIC_FTRACE
bool "enable/disable function tracing dynamically"
depends on FUNCTION_TRACER
@@ -650,6 +665,32 @@ config BLK_DEV_IO_TRACE
If unsure, say N.
+config FPROBE_EVENTS
+ depends on FPROBE
+ depends on HAVE_REGS_AND_STACK_ACCESS_API
+ bool "Enable fprobe-based dynamic events"
+ select TRACING
+ select PROBE_EVENTS
+ select DYNAMIC_EVENTS
+ default y
+ help
+ This allows user to add tracing events on the function entry and
+ exit via ftrace interface. The syntax is same as the kprobe events
+ and the kprobe events on function entry and exit will be
+ transparently converted to this fprobe events.
+
+config PROBE_EVENTS_BTF_ARGS
+ depends on HAVE_FUNCTION_ARG_ACCESS_API
+ depends on FPROBE_EVENTS || KPROBE_EVENTS
+ depends on DEBUG_INFO_BTF && BPF_SYSCALL
+ bool "Support BTF function arguments for probe events"
+ default y
+ help
+ The user can specify the arguments of the probe event using the names
+ of the arguments of the probed function, when the probe location is a
+ kernel function entry or a tracepoint.
+ This is available only if BTF (BPF Type Format) support is enabled.
+
config KPROBE_EVENTS
depends on KPROBES
depends on HAVE_REGS_AND_STACK_ACCESS_API
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index c6651e16b557..057cd975d014 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -99,11 +99,13 @@ obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
endif
obj-$(CONFIG_DYNAMIC_EVENTS) += trace_dynevent.o
obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
+obj-$(CONFIG_PROBE_EVENTS_BTF_ARGS) += trace_btf.o
obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o
obj-$(CONFIG_BOOTTIME_TRACING) += trace_boot.o
obj-$(CONFIG_FTRACE_RECORD_RECURSION) += trace_recursion_record.o
obj-$(CONFIG_FPROBE) += fprobe.o
obj-$(CONFIG_RETHOOK) += rethook.o
+obj-$(CONFIG_FPROBE_EVENTS) += trace_fprobe.o
obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o
obj-$(CONFIG_RV) += rv/
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 1f4b07da327a..a7264b2c17ad 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -23,6 +23,7 @@
#include <linux/sort.h>
#include <linux/key.h>
#include <linux/verification.h>
+#include <linux/namei.h>
#include <net/bpf_sk_storage.h>
@@ -86,6 +87,9 @@ static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size,
static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx);
static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx);
+static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx);
+static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx);
+
/**
* trace_call_bpf - invoke BPF program
* @call: tracepoint event
@@ -223,17 +227,6 @@ const struct bpf_func_proto bpf_probe_read_user_str_proto = {
.arg3_type = ARG_ANYTHING,
};
-static __always_inline int
-bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr)
-{
- int ret;
-
- ret = copy_from_kernel_nofault(dst, unsafe_ptr, size);
- if (unlikely(ret < 0))
- memset(dst, 0, size);
- return ret;
-}
-
BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size,
const void *, unsafe_ptr)
{
@@ -661,8 +654,7 @@ static DEFINE_PER_CPU(int, bpf_trace_nest_level);
BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
u64, flags, void *, data, u64, size)
{
- struct bpf_trace_sample_data *sds = this_cpu_ptr(&bpf_trace_sds);
- int nest_level = this_cpu_inc_return(bpf_trace_nest_level);
+ struct bpf_trace_sample_data *sds;
struct perf_raw_record raw = {
.frag = {
.size = size,
@@ -670,7 +662,11 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
},
};
struct perf_sample_data *sd;
- int err;
+ int nest_level, err;
+
+ preempt_disable();
+ sds = this_cpu_ptr(&bpf_trace_sds);
+ nest_level = this_cpu_inc_return(bpf_trace_nest_level);
if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(sds->sds))) {
err = -EBUSY;
@@ -688,9 +684,9 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
perf_sample_save_raw_data(sd, &raw);
err = __bpf_perf_event_output(regs, map, flags, sd);
-
out:
this_cpu_dec(bpf_trace_nest_level);
+ preempt_enable();
return err;
}
@@ -715,7 +711,6 @@ static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_misc_sds);
u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy)
{
- int nest_level = this_cpu_inc_return(bpf_event_output_nest_level);
struct perf_raw_frag frag = {
.copy = ctx_copy,
.size = ctx_size,
@@ -732,8 +727,12 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
};
struct perf_sample_data *sd;
struct pt_regs *regs;
+ int nest_level;
u64 ret;
+ preempt_disable();
+ nest_level = this_cpu_inc_return(bpf_event_output_nest_level);
+
if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bpf_misc_sds.sds))) {
ret = -EBUSY;
goto out;
@@ -748,6 +747,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
ret = __bpf_perf_event_output(regs, map, flags, sd);
out:
this_cpu_dec(bpf_event_output_nest_level);
+ preempt_enable();
return ret;
}
@@ -1059,7 +1059,16 @@ static unsigned long get_entry_ip(unsigned long fentry_ip)
BPF_CALL_1(bpf_get_func_ip_kprobe, struct pt_regs *, regs)
{
- struct kprobe *kp = kprobe_running();
+ struct bpf_trace_run_ctx *run_ctx __maybe_unused;
+ struct kprobe *kp;
+
+#ifdef CONFIG_UPROBES
+ run_ctx = container_of(current->bpf_ctx, struct bpf_trace_run_ctx, run_ctx);
+ if (run_ctx->is_uprobe)
+ return ((struct uprobe_dispatch_data *)current->utask->vaddr)->bp_addr;
+#endif
+
+ kp = kprobe_running();
if (!kp || !(kp->flags & KPROBE_FLAG_ON_FUNC_ENTRY))
return 0;
@@ -1098,6 +1107,30 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto_kmulti = {
.arg1_type = ARG_PTR_TO_CTX,
};
+BPF_CALL_1(bpf_get_func_ip_uprobe_multi, struct pt_regs *, regs)
+{
+ return bpf_uprobe_multi_entry_ip(current->bpf_ctx);
+}
+
+static const struct bpf_func_proto bpf_get_func_ip_proto_uprobe_multi = {
+ .func = bpf_get_func_ip_uprobe_multi,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
+BPF_CALL_1(bpf_get_attach_cookie_uprobe_multi, struct pt_regs *, regs)
+{
+ return bpf_uprobe_multi_cookie(current->bpf_ctx);
+}
+
+static const struct bpf_func_proto bpf_get_attach_cookie_proto_umulti = {
+ .func = bpf_get_attach_cookie_uprobe_multi,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
BPF_CALL_1(bpf_get_attach_cookie_trace, void *, ctx)
{
struct bpf_trace_run_ctx *run_ctx;
@@ -1359,9 +1392,9 @@ __bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr,
}
return verify_pkcs7_signature(data_ptr->data,
- bpf_dynptr_get_size(data_ptr),
+ __bpf_dynptr_size(data_ptr),
sig_ptr->data,
- bpf_dynptr_get_size(sig_ptr),
+ __bpf_dynptr_size(sig_ptr),
trusted_keyring->key,
VERIFYING_UNSPECIFIED_SIGNATURE, NULL,
NULL);
@@ -1540,13 +1573,17 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_override_return_proto;
#endif
case BPF_FUNC_get_func_ip:
- return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI ?
- &bpf_get_func_ip_proto_kprobe_multi :
- &bpf_get_func_ip_proto_kprobe;
+ if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI)
+ return &bpf_get_func_ip_proto_kprobe_multi;
+ if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI)
+ return &bpf_get_func_ip_proto_uprobe_multi;
+ return &bpf_get_func_ip_proto_kprobe;
case BPF_FUNC_get_attach_cookie:
- return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI ?
- &bpf_get_attach_cookie_proto_kmulti :
- &bpf_get_attach_cookie_proto_trace;
+ if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI)
+ return &bpf_get_attach_cookie_proto_kmulti;
+ if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI)
+ return &bpf_get_attach_cookie_proto_umulti;
+ return &bpf_get_attach_cookie_proto_trace;
default:
return bpf_tracing_func_proto(func_id, prog);
}
@@ -2369,9 +2406,13 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
if (is_tracepoint || is_syscall_tp) {
*buf = is_tracepoint ? event->tp_event->tp->name
: event->tp_event->name;
- *fd_type = BPF_FD_TYPE_TRACEPOINT;
- *probe_offset = 0x0;
- *probe_addr = 0x0;
+ /* We allow NULL pointer for tracepoint */
+ if (fd_type)
+ *fd_type = BPF_FD_TYPE_TRACEPOINT;
+ if (probe_offset)
+ *probe_offset = 0x0;
+ if (probe_addr)
+ *probe_addr = 0x0;
} else {
/* kprobe/uprobe */
err = -EOPNOTSUPP;
@@ -2384,7 +2425,7 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
#ifdef CONFIG_UPROBE_EVENTS
if (flags & TRACE_EVENT_FL_UPROBE)
err = bpf_get_uprobe_info(event, fd_type, buf,
- probe_offset,
+ probe_offset, probe_addr,
event->attr.type == PERF_TYPE_TRACEPOINT);
#endif
}
@@ -2469,6 +2510,7 @@ struct bpf_kprobe_multi_link {
u32 cnt;
u32 mods_cnt;
struct module **mods;
+ u32 flags;
};
struct bpf_kprobe_multi_run_ctx {
@@ -2558,9 +2600,44 @@ static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link)
kfree(kmulti_link);
}
+static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link,
+ struct bpf_link_info *info)
+{
+ u64 __user *uaddrs = u64_to_user_ptr(info->kprobe_multi.addrs);
+ struct bpf_kprobe_multi_link *kmulti_link;
+ u32 ucount = info->kprobe_multi.count;
+ int err = 0, i;
+
+ if (!uaddrs ^ !ucount)
+ return -EINVAL;
+
+ kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
+ info->kprobe_multi.count = kmulti_link->cnt;
+ info->kprobe_multi.flags = kmulti_link->flags;
+
+ if (!uaddrs)
+ return 0;
+ if (ucount < kmulti_link->cnt)
+ err = -ENOSPC;
+ else
+ ucount = kmulti_link->cnt;
+
+ if (kallsyms_show_value(current_cred())) {
+ if (copy_to_user(uaddrs, kmulti_link->addrs, ucount * sizeof(u64)))
+ return -EFAULT;
+ } else {
+ for (i = 0; i < ucount; i++) {
+ if (put_user(0, uaddrs + i))
+ return -EFAULT;
+ }
+ }
+ return err;
+}
+
static const struct bpf_link_ops bpf_kprobe_multi_link_lops = {
.release = bpf_kprobe_multi_link_release,
.dealloc = bpf_kprobe_multi_link_dealloc,
+ .fill_link_info = bpf_kprobe_multi_link_fill_link_info,
};
static void bpf_kprobe_multi_cookie_swap(void *a, void *b, int size, const void *priv)
@@ -2652,7 +2729,8 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link,
static int
kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip,
- struct pt_regs *regs, void *data)
+ unsigned long ret_ip, struct pt_regs *regs,
+ void *data)
{
struct bpf_kprobe_multi_link *link;
@@ -2663,7 +2741,8 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip,
static void
kprobe_multi_link_exit_handler(struct fprobe *fp, unsigned long fentry_ip,
- struct pt_regs *regs, void *data)
+ unsigned long ret_ip, struct pt_regs *regs,
+ void *data)
{
struct bpf_kprobe_multi_link *link;
@@ -2872,6 +2951,7 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
link->addrs = addrs;
link->cookies = cookies;
link->cnt = cnt;
+ link->flags = flags;
if (cookies) {
/*
@@ -2922,3 +3002,301 @@ static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx)
return 0;
}
#endif
+
+#ifdef CONFIG_UPROBES
+struct bpf_uprobe_multi_link;
+
+struct bpf_uprobe {
+ struct bpf_uprobe_multi_link *link;
+ loff_t offset;
+ u64 cookie;
+ struct uprobe_consumer consumer;
+};
+
+struct bpf_uprobe_multi_link {
+ struct path path;
+ struct bpf_link link;
+ u32 cnt;
+ struct bpf_uprobe *uprobes;
+ struct task_struct *task;
+};
+
+struct bpf_uprobe_multi_run_ctx {
+ struct bpf_run_ctx run_ctx;
+ unsigned long entry_ip;
+ struct bpf_uprobe *uprobe;
+};
+
+static void bpf_uprobe_unregister(struct path *path, struct bpf_uprobe *uprobes,
+ u32 cnt)
+{
+ u32 i;
+
+ for (i = 0; i < cnt; i++) {
+ uprobe_unregister(d_real_inode(path->dentry), uprobes[i].offset,
+ &uprobes[i].consumer);
+ }
+}
+
+static void bpf_uprobe_multi_link_release(struct bpf_link *link)
+{
+ struct bpf_uprobe_multi_link *umulti_link;
+
+ umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
+ bpf_uprobe_unregister(&umulti_link->path, umulti_link->uprobes, umulti_link->cnt);
+}
+
+static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link)
+{
+ struct bpf_uprobe_multi_link *umulti_link;
+
+ umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
+ if (umulti_link->task)
+ put_task_struct(umulti_link->task);
+ path_put(&umulti_link->path);
+ kvfree(umulti_link->uprobes);
+ kfree(umulti_link);
+}
+
+static const struct bpf_link_ops bpf_uprobe_multi_link_lops = {
+ .release = bpf_uprobe_multi_link_release,
+ .dealloc = bpf_uprobe_multi_link_dealloc,
+};
+
+static int uprobe_prog_run(struct bpf_uprobe *uprobe,
+ unsigned long entry_ip,
+ struct pt_regs *regs)
+{
+ struct bpf_uprobe_multi_link *link = uprobe->link;
+ struct bpf_uprobe_multi_run_ctx run_ctx = {
+ .entry_ip = entry_ip,
+ .uprobe = uprobe,
+ };
+ struct bpf_prog *prog = link->link.prog;
+ bool sleepable = prog->aux->sleepable;
+ struct bpf_run_ctx *old_run_ctx;
+ int err = 0;
+
+ if (link->task && current != link->task)
+ return 0;
+
+ if (sleepable)
+ rcu_read_lock_trace();
+ else
+ rcu_read_lock();
+
+ migrate_disable();
+
+ old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
+ err = bpf_prog_run(link->link.prog, regs);
+ bpf_reset_run_ctx(old_run_ctx);
+
+ migrate_enable();
+
+ if (sleepable)
+ rcu_read_unlock_trace();
+ else
+ rcu_read_unlock();
+ return err;
+}
+
+static bool
+uprobe_multi_link_filter(struct uprobe_consumer *con, enum uprobe_filter_ctx ctx,
+ struct mm_struct *mm)
+{
+ struct bpf_uprobe *uprobe;
+
+ uprobe = container_of(con, struct bpf_uprobe, consumer);
+ return uprobe->link->task->mm == mm;
+}
+
+static int
+uprobe_multi_link_handler(struct uprobe_consumer *con, struct pt_regs *regs)
+{
+ struct bpf_uprobe *uprobe;
+
+ uprobe = container_of(con, struct bpf_uprobe, consumer);
+ return uprobe_prog_run(uprobe, instruction_pointer(regs), regs);
+}
+
+static int
+uprobe_multi_link_ret_handler(struct uprobe_consumer *con, unsigned long func, struct pt_regs *regs)
+{
+ struct bpf_uprobe *uprobe;
+
+ uprobe = container_of(con, struct bpf_uprobe, consumer);
+ return uprobe_prog_run(uprobe, func, regs);
+}
+
+static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx)
+{
+ struct bpf_uprobe_multi_run_ctx *run_ctx;
+
+ run_ctx = container_of(current->bpf_ctx, struct bpf_uprobe_multi_run_ctx, run_ctx);
+ return run_ctx->entry_ip;
+}
+
+static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx)
+{
+ struct bpf_uprobe_multi_run_ctx *run_ctx;
+
+ run_ctx = container_of(current->bpf_ctx, struct bpf_uprobe_multi_run_ctx, run_ctx);
+ return run_ctx->uprobe->cookie;
+}
+
+int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+ struct bpf_uprobe_multi_link *link = NULL;
+ unsigned long __user *uref_ctr_offsets;
+ unsigned long *ref_ctr_offsets = NULL;
+ struct bpf_link_primer link_primer;
+ struct bpf_uprobe *uprobes = NULL;
+ struct task_struct *task = NULL;
+ unsigned long __user *uoffsets;
+ u64 __user *ucookies;
+ void __user *upath;
+ u32 flags, cnt, i;
+ struct path path;
+ char *name;
+ pid_t pid;
+ int err;
+
+ /* no support for 32bit archs yet */
+ if (sizeof(u64) != sizeof(void *))
+ return -EOPNOTSUPP;
+
+ if (prog->expected_attach_type != BPF_TRACE_UPROBE_MULTI)
+ return -EINVAL;
+
+ flags = attr->link_create.uprobe_multi.flags;
+ if (flags & ~BPF_F_UPROBE_MULTI_RETURN)
+ return -EINVAL;
+
+ /*
+ * path, offsets and cnt are mandatory,
+ * ref_ctr_offsets and cookies are optional
+ */
+ upath = u64_to_user_ptr(attr->link_create.uprobe_multi.path);
+ uoffsets = u64_to_user_ptr(attr->link_create.uprobe_multi.offsets);
+ cnt = attr->link_create.uprobe_multi.cnt;
+
+ if (!upath || !uoffsets || !cnt)
+ return -EINVAL;
+
+ uref_ctr_offsets = u64_to_user_ptr(attr->link_create.uprobe_multi.ref_ctr_offsets);
+ ucookies = u64_to_user_ptr(attr->link_create.uprobe_multi.cookies);
+
+ name = strndup_user(upath, PATH_MAX);
+ if (IS_ERR(name)) {
+ err = PTR_ERR(name);
+ return err;
+ }
+
+ err = kern_path(name, LOOKUP_FOLLOW, &path);
+ kfree(name);
+ if (err)
+ return err;
+
+ if (!d_is_reg(path.dentry)) {
+ err = -EBADF;
+ goto error_path_put;
+ }
+
+ pid = attr->link_create.uprobe_multi.pid;
+ if (pid) {
+ rcu_read_lock();
+ task = get_pid_task(find_vpid(pid), PIDTYPE_PID);
+ rcu_read_unlock();
+ if (!task)
+ goto error_path_put;
+ }
+
+ err = -ENOMEM;
+
+ link = kzalloc(sizeof(*link), GFP_KERNEL);
+ uprobes = kvcalloc(cnt, sizeof(*uprobes), GFP_KERNEL);
+
+ if (!uprobes || !link)
+ goto error_free;
+
+ if (uref_ctr_offsets) {
+ ref_ctr_offsets = kvcalloc(cnt, sizeof(*ref_ctr_offsets), GFP_KERNEL);
+ if (!ref_ctr_offsets)
+ goto error_free;
+ }
+
+ for (i = 0; i < cnt; i++) {
+ if (ucookies && __get_user(uprobes[i].cookie, ucookies + i)) {
+ err = -EFAULT;
+ goto error_free;
+ }
+ if (uref_ctr_offsets && __get_user(ref_ctr_offsets[i], uref_ctr_offsets + i)) {
+ err = -EFAULT;
+ goto error_free;
+ }
+ if (__get_user(uprobes[i].offset, uoffsets + i)) {
+ err = -EFAULT;
+ goto error_free;
+ }
+
+ uprobes[i].link = link;
+
+ if (flags & BPF_F_UPROBE_MULTI_RETURN)
+ uprobes[i].consumer.ret_handler = uprobe_multi_link_ret_handler;
+ else
+ uprobes[i].consumer.handler = uprobe_multi_link_handler;
+
+ if (pid)
+ uprobes[i].consumer.filter = uprobe_multi_link_filter;
+ }
+
+ link->cnt = cnt;
+ link->uprobes = uprobes;
+ link->path = path;
+ link->task = task;
+
+ bpf_link_init(&link->link, BPF_LINK_TYPE_UPROBE_MULTI,
+ &bpf_uprobe_multi_link_lops, prog);
+
+ for (i = 0; i < cnt; i++) {
+ err = uprobe_register_refctr(d_real_inode(link->path.dentry),
+ uprobes[i].offset,
+ ref_ctr_offsets ? ref_ctr_offsets[i] : 0,
+ &uprobes[i].consumer);
+ if (err) {
+ bpf_uprobe_unregister(&path, uprobes, i);
+ goto error_free;
+ }
+ }
+
+ err = bpf_link_prime(&link->link, &link_primer);
+ if (err)
+ goto error_free;
+
+ kvfree(ref_ctr_offsets);
+ return bpf_link_settle(&link_primer);
+
+error_free:
+ kvfree(ref_ctr_offsets);
+ kvfree(uprobes);
+ kfree(link);
+ if (task)
+ put_task_struct(task);
+error_path_put:
+ path_put(&path);
+ return err;
+}
+#else /* !CONFIG_UPROBES */
+int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+ return -EOPNOTSUPP;
+}
+static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx)
+{
+ return 0;
+}
+static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx)
+{
+ return 0;
+}
+#endif /* CONFIG_UPROBES */
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 218cd95bf8e4..c83c005e654e 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -15,6 +15,7 @@
#include <trace/events/sched.h>
#include "ftrace_internal.h"
+#include "trace.h"
#ifdef CONFIG_DYNAMIC_FTRACE
#define ASSIGN_OPS_HASH(opsname, val) \
@@ -236,16 +237,23 @@ static struct notifier_block ftrace_suspend_notifier = {
.notifier_call = ftrace_suspend_notifier_call,
};
+/* fgraph_ret_regs is not defined without CONFIG_FUNCTION_GRAPH_RETVAL */
+struct fgraph_ret_regs;
+
/*
* Send the trace to the ring-buffer.
* @return the original return address.
*/
-unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
+static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs,
+ unsigned long frame_pointer)
{
struct ftrace_graph_ret trace;
unsigned long ret;
ftrace_pop_return_trace(&trace, &ret, frame_pointer);
+#ifdef CONFIG_FUNCTION_GRAPH_RETVAL
+ trace.retval = fgraph_ret_regs_return_value(ret_regs);
+#endif
trace.rettime = trace_clock_local();
ftrace_graph_return(&trace);
/*
@@ -266,6 +274,23 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
return ret;
}
+/*
+ * After all architecures have selected HAVE_FUNCTION_GRAPH_RETVAL, we can
+ * leave only ftrace_return_to_handler(ret_regs).
+ */
+#ifdef CONFIG_HAVE_FUNCTION_GRAPH_RETVAL
+unsigned long ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs)
+{
+ return __ftrace_return_to_handler(ret_regs,
+ fgraph_ret_regs_frame_pointer(ret_regs));
+}
+#else
+unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
+{
+ return __ftrace_return_to_handler(NULL, frame_pointer);
+}
+#endif
+
/**
* ftrace_graph_get_ret_stack - return the entry of the shadow stack
* @task: The task to read the shadow stack from
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 18d36842faf5..3b21f4063258 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -46,7 +46,7 @@ static inline void __fprobe_handler(unsigned long ip, unsigned long parent_ip,
}
if (fp->entry_handler)
- ret = fp->entry_handler(fp, ip, ftrace_get_regs(fregs), entry_data);
+ ret = fp->entry_handler(fp, ip, parent_ip, ftrace_get_regs(fregs), entry_data);
/* If entry_handler returns !0, nmissed is not counted. */
if (rh) {
@@ -100,19 +100,27 @@ static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip,
return;
}
+ /*
+ * This user handler is shared with other kprobes and is not expected to be
+ * called recursively. So if any other kprobe handler is running, this will
+ * exit as kprobe does. See the section 'Share the callbacks with kprobes'
+ * in Documentation/trace/fprobe.rst for more information.
+ */
if (unlikely(kprobe_running())) {
fp->nmissed++;
- return;
+ goto recursion_unlock;
}
kprobe_busy_begin();
__fprobe_handler(ip, parent_ip, ops, fregs);
kprobe_busy_end();
+
+recursion_unlock:
ftrace_test_recursion_unlock(bit);
}
static void fprobe_exit_handler(struct rethook_node *rh, void *data,
- struct pt_regs *regs)
+ unsigned long ret_ip, struct pt_regs *regs)
{
struct fprobe *fp = (struct fprobe *)data;
struct fprobe_rethook_node *fpr;
@@ -133,7 +141,7 @@ static void fprobe_exit_handler(struct rethook_node *rh, void *data,
return;
}
- fp->exit_handler(fp, fpr->entry_ip, regs,
+ fp->exit_handler(fp, fpr->entry_ip, ret_ip, regs,
fp->entry_data_size ? (void *)fpr->data : NULL);
ftrace_test_recursion_unlock(bit);
}
@@ -348,6 +356,14 @@ int register_fprobe_syms(struct fprobe *fp, const char **syms, int num)
}
EXPORT_SYMBOL_GPL(register_fprobe_syms);
+bool fprobe_is_registered(struct fprobe *fp)
+{
+ if (!fp || (fp->ops.saved_func != fprobe_handler &&
+ fp->ops.saved_func != fprobe_kprobe_handler))
+ return false;
+ return true;
+}
+
/**
* unregister_fprobe() - Unregister fprobe from ftrace
* @fp: A fprobe data structure to be unregistered.
@@ -360,23 +376,19 @@ int unregister_fprobe(struct fprobe *fp)
{
int ret;
- if (!fp || (fp->ops.saved_func != fprobe_handler &&
- fp->ops.saved_func != fprobe_kprobe_handler))
+ if (!fprobe_is_registered(fp))
return -EINVAL;
- /*
- * rethook_free() starts disabling the rethook, but the rethook handlers
- * may be running on other processors at this point. To make sure that all
- * current running handlers are finished, call unregister_ftrace_function()
- * after this.
- */
if (fp->rethook)
- rethook_free(fp->rethook);
+ rethook_stop(fp->rethook);
ret = unregister_ftrace_function(&fp->ops);
if (ret < 0)
return ret;
+ if (fp->rethook)
+ rethook_free(fp->rethook);
+
ftrace_free_filter(&fp->ops);
return ret;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 764668467155..8de8bec5f366 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3305,6 +3305,22 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count)
return cnt;
}
+static void ftrace_free_pages(struct ftrace_page *pages)
+{
+ struct ftrace_page *pg = pages;
+
+ while (pg) {
+ if (pg->records) {
+ free_pages((unsigned long)pg->records, pg->order);
+ ftrace_number_of_pages -= 1 << pg->order;
+ }
+ pages = pg->next;
+ kfree(pg);
+ pg = pages;
+ ftrace_number_of_groups--;
+ }
+}
+
static struct ftrace_page *
ftrace_allocate_pages(unsigned long num_to_init)
{
@@ -3343,17 +3359,7 @@ ftrace_allocate_pages(unsigned long num_to_init)
return start_pg;
free_pages:
- pg = start_pg;
- while (pg) {
- if (pg->records) {
- free_pages((unsigned long)pg->records, pg->order);
- ftrace_number_of_pages -= 1 << pg->order;
- }
- start_pg = pg->next;
- kfree(pg);
- pg = start_pg;
- ftrace_number_of_groups--;
- }
+ ftrace_free_pages(start_pg);
pr_info("ftrace: FAILED to allocate memory for functions\n");
return NULL;
}
@@ -3861,6 +3867,9 @@ static int t_show(struct seq_file *m, void *v)
if (!rec)
return 0;
+ if (iter->flags & FTRACE_ITER_ADDRS)
+ seq_printf(m, "%lx ", rec->ip);
+
if (print_rec(m, rec->ip)) {
/* This should only happen when a rec is disabled */
WARN_ON_ONCE(!(rec->flags & FTRACE_FL_DISABLED));
@@ -3996,6 +4005,30 @@ ftrace_touched_open(struct inode *inode, struct file *file)
return 0;
}
+static int
+ftrace_avail_addrs_open(struct inode *inode, struct file *file)
+{
+ struct ftrace_iterator *iter;
+ int ret;
+
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
+ if (unlikely(ftrace_disabled))
+ return -ENODEV;
+
+ iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter));
+ if (!iter)
+ return -ENOMEM;
+
+ iter->pg = ftrace_pages_start;
+ iter->flags = FTRACE_ITER_ADDRS;
+ iter->ops = &global_ops;
+
+ return 0;
+}
+
/**
* ftrace_regex_open - initialize function tracer filter files
* @ops: The ftrace_ops that hold the hash filters
@@ -5743,7 +5776,7 @@ bool ftrace_filter_param __initdata;
static int __init set_ftrace_notrace(char *str)
{
ftrace_filter_param = true;
- strlcpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE);
+ strscpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE);
return 1;
}
__setup("ftrace_notrace=", set_ftrace_notrace);
@@ -5751,7 +5784,7 @@ __setup("ftrace_notrace=", set_ftrace_notrace);
static int __init set_ftrace_filter(char *str)
{
ftrace_filter_param = true;
- strlcpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE);
+ strscpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE);
return 1;
}
__setup("ftrace_filter=", set_ftrace_filter);
@@ -5763,14 +5796,14 @@ static int ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer);
static int __init set_graph_function(char *str)
{
- strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE);
+ strscpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE);
return 1;
}
__setup("ftrace_graph_filter=", set_graph_function);
static int __init set_graph_notrace_function(char *str)
{
- strlcpy(ftrace_graph_notrace_buf, str, FTRACE_FILTER_SIZE);
+ strscpy(ftrace_graph_notrace_buf, str, FTRACE_FILTER_SIZE);
return 1;
}
__setup("ftrace_graph_notrace=", set_graph_notrace_function);
@@ -5916,6 +5949,13 @@ static const struct file_operations ftrace_touched_fops = {
.release = seq_release_private,
};
+static const struct file_operations ftrace_avail_addrs_fops = {
+ .open = ftrace_avail_addrs_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
static const struct file_operations ftrace_filter_fops = {
.open = ftrace_filter_open,
.read = seq_read,
@@ -6377,6 +6417,9 @@ static __init int ftrace_init_dyn_tracefs(struct dentry *d_tracer)
trace_create_file("available_filter_functions", TRACE_MODE_READ,
d_tracer, NULL, &ftrace_avail_fops);
+ trace_create_file("available_filter_functions_addrs", TRACE_MODE_READ,
+ d_tracer, NULL, &ftrace_avail_addrs_fops);
+
trace_create_file("enabled_functions", TRACE_MODE_READ,
d_tracer, NULL, &ftrace_enabled_fops);
@@ -6434,9 +6477,11 @@ static int ftrace_process_locs(struct module *mod,
unsigned long *start,
unsigned long *end)
{
+ struct ftrace_page *pg_unuse = NULL;
struct ftrace_page *start_pg;
struct ftrace_page *pg;
struct dyn_ftrace *rec;
+ unsigned long skipped = 0;
unsigned long count;
unsigned long *p;
unsigned long addr;
@@ -6499,8 +6544,10 @@ static int ftrace_process_locs(struct module *mod,
* object files to satisfy alignments.
* Skip any NULL pointers.
*/
- if (!addr)
+ if (!addr) {
+ skipped++;
continue;
+ }
end_offset = (pg->index+1) * sizeof(pg->records[0]);
if (end_offset > PAGE_SIZE << pg->order) {
@@ -6514,8 +6561,10 @@ static int ftrace_process_locs(struct module *mod,
rec->ip = addr;
}
- /* We should have used all pages */
- WARN_ON(pg->next);
+ if (pg->next) {
+ pg_unuse = pg->next;
+ pg->next = NULL;
+ }
/* Assign the last page to ftrace_pages */
ftrace_pages = pg;
@@ -6537,6 +6586,11 @@ static int ftrace_process_locs(struct module *mod,
out:
mutex_unlock(&ftrace_lock);
+ /* We should have used all pages unless we skipped some */
+ if (pg_unuse) {
+ WARN_ON(!skipped);
+ ftrace_free_pages(pg_unuse);
+ }
return ret;
}
@@ -6569,8 +6623,8 @@ static int ftrace_get_trampoline_kallsym(unsigned int symnum,
continue;
*value = op->trampoline;
*type = 't';
- strlcpy(name, FTRACE_TRAMPOLINE_SYM, KSYM_NAME_LEN);
- strlcpy(module_name, FTRACE_TRAMPOLINE_MOD, MODULE_NAME_LEN);
+ strscpy(name, FTRACE_TRAMPOLINE_SYM, KSYM_NAME_LEN);
+ strscpy(module_name, FTRACE_TRAMPOLINE_MOD, MODULE_NAME_LEN);
*exported = 0;
return 0;
}
@@ -6725,8 +6779,7 @@ void ftrace_release_mod(struct module *mod)
last_pg = &ftrace_pages_start;
for (pg = ftrace_pages_start; pg; pg = *last_pg) {
rec = &pg->records[0];
- if (within_module_core(rec->ip, mod) ||
- within_module_init(rec->ip, mod)) {
+ if (within_module(rec->ip, mod)) {
/*
* As core pages are first, the first
* page should never be a module page.
@@ -6798,8 +6851,7 @@ void ftrace_module_enable(struct module *mod)
* not part of this module, then skip this pg,
* which the "break" will do.
*/
- if (!within_module_core(rec->ip, mod) &&
- !within_module_init(rec->ip, mod))
+ if (!within_module(rec->ip, mod))
break;
/* Weak functions should still be ignored */
@@ -6933,7 +6985,7 @@ ftrace_func_address_lookup(struct ftrace_mod_map *mod_map,
if (off)
*off = addr - found_func->ip;
if (sym)
- strlcpy(sym, found_func->name, KSYM_NAME_LEN);
+ strscpy(sym, found_func->name, KSYM_NAME_LEN);
return found_func->name;
}
@@ -6987,8 +7039,8 @@ int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
*value = mod_func->ip;
*type = 'T';
- strlcpy(name, mod_func->name, KSYM_NAME_LEN);
- strlcpy(module_name, mod_map->mod->name, MODULE_NAME_LEN);
+ strscpy(name, mod_func->name, KSYM_NAME_LEN);
+ strscpy(module_name, mod_map->mod->name, MODULE_NAME_LEN);
*exported = 1;
preempt_enable();
return 0;
@@ -7088,9 +7140,7 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr)
struct dyn_ftrace key;
struct ftrace_mod_map *mod_map = NULL;
struct ftrace_init_func *func, *func_next;
- struct list_head clear_hash;
-
- INIT_LIST_HEAD(&clear_hash);
+ LIST_HEAD(clear_hash);
key.ip = start;
key.flags = end; /* overload flags, as it is unsigned long */
diff --git a/kernel/trace/ftrace_internal.h b/kernel/trace/ftrace_internal.h
index 382775edf690..5012c04f92c0 100644
--- a/kernel/trace/ftrace_internal.h
+++ b/kernel/trace/ftrace_internal.h
@@ -2,6 +2,9 @@
#ifndef _LINUX_KERNEL_FTRACE_INTERNAL_H
#define _LINUX_KERNEL_FTRACE_INTERNAL_H
+int __register_ftrace_function(struct ftrace_ops *ops);
+int __unregister_ftrace_function(struct ftrace_ops *ops);
+
#ifdef CONFIG_FUNCTION_TRACER
extern struct mutex ftrace_lock;
@@ -15,8 +18,6 @@ int ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs);
#else /* !CONFIG_DYNAMIC_FTRACE */
-int __register_ftrace_function(struct ftrace_ops *ops);
-int __unregister_ftrace_function(struct ftrace_ops *ops);
/* Keep as macros so we do not need to define the commands */
# define ftrace_startup(ops, command) \
({ \
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index 60f6cb2b486b..5eb9b598f4e9 100644
--- a/kernel/trace/rethook.c
+++ b/kernel/trace/rethook.c
@@ -54,6 +54,19 @@ static void rethook_free_rcu(struct rcu_head *head)
}
/**
+ * rethook_stop() - Stop using a rethook.
+ * @rh: the struct rethook to stop.
+ *
+ * Stop using a rethook to prepare for freeing it. If you want to wait for
+ * all running rethook handler before calling rethook_free(), you need to
+ * call this first and wait RCU, and call rethook_free().
+ */
+void rethook_stop(struct rethook *rh)
+{
+ WRITE_ONCE(rh->handler, NULL);
+}
+
+/**
* rethook_free() - Free struct rethook.
* @rh: the struct rethook to be freed.
*
@@ -301,7 +314,8 @@ unsigned long rethook_trampoline_handler(struct pt_regs *regs,
break;
handler = READ_ONCE(rhn->rethook->handler);
if (handler)
- handler(rhn, rhn->rethook->data, regs);
+ handler(rhn, rhn->rethook->data,
+ correct_ret_addr, regs);
if (first == node)
break;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 834b361a4a66..78502d4c7214 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -523,6 +523,8 @@ struct ring_buffer_per_cpu {
rb_time_t before_stamp;
u64 event_stamp[MAX_NEST];
u64 read_stamp;
+ /* pages removed since last reset */
+ unsigned long pages_removed;
/* ring buffer pages to update, > 0 to add, < 0 to remove */
long nr_pages_to_update;
struct list_head new_pages; /* new pages to add */
@@ -536,6 +538,7 @@ struct trace_buffer {
unsigned flags;
int cpus;
atomic_t record_disabled;
+ atomic_t resizing;
cpumask_var_t cpumask;
struct lock_class_key *reader_lock_key;
@@ -558,6 +561,7 @@ struct ring_buffer_iter {
struct buffer_page *head_page;
struct buffer_page *cache_reader_page;
unsigned long cache_read;
+ unsigned long cache_pages_removed;
u64 read_stamp;
u64 page_stamp;
struct ring_buffer_event *event;
@@ -688,10 +692,7 @@ static void rb_time_set(rb_time_t *t, u64 val)
static inline bool
rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set)
{
- unsigned long ret;
-
- ret = local_cmpxchg(l, expect, set);
- return ret == expect;
+ return local_try_cmpxchg(l, &expect, set);
}
static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
@@ -748,9 +749,7 @@ static void rb_time_set(rb_time_t *t, u64 val)
static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
{
- u64 val;
- val = local64_cmpxchg(&t->time, expect, set);
- return val == expect;
+ return local64_try_cmpxchg(&t->time, &expect, set);
}
#endif
@@ -946,6 +945,7 @@ static void rb_wake_up_waiters(struct irq_work *work)
/**
* ring_buffer_wake_waiters - wake up any waiters on this ring buffer
* @buffer: The ring buffer to wake waiters on
+ * @cpu: The CPU buffer to wake waiters on
*
* In the case of a file that represents a ring buffer is closing,
* it is prudent to wake up any waiters that are on this.
@@ -1489,14 +1489,11 @@ static bool rb_head_page_replace(struct buffer_page *old,
{
unsigned long *ptr = (unsigned long *)&old->list.prev->next;
unsigned long val;
- unsigned long ret;
val = *ptr & ~RB_FLAG_MASK;
val |= RB_PAGE_HEAD;
- ret = cmpxchg(ptr, val, (unsigned long)&new->list);
-
- return ret == val;
+ return try_cmpxchg(ptr, &val, (unsigned long)&new->list);
}
/*
@@ -1956,6 +1953,8 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
to_remove = rb_list_head(to_remove)->next;
head_bit |= (unsigned long)to_remove & RB_PAGE_HEAD;
}
+ /* Read iterators need to reset themselves when some pages removed */
+ cpu_buffer->pages_removed += nr_removed;
next_page = rb_list_head(to_remove)->next;
@@ -1977,12 +1976,6 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
cpu_buffer->head_page = list_entry(next_page,
struct buffer_page, list);
- /*
- * change read pointer to make sure any read iterators reset
- * themselves
- */
- cpu_buffer->read = 0;
-
/* pages are removed, resume tracing and then free the pages */
atomic_dec(&cpu_buffer->record_disabled);
raw_spin_unlock_irq(&cpu_buffer->reader_lock);
@@ -2167,7 +2160,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
/* prevent another thread from changing buffer sizes */
mutex_lock(&buffer->mutex);
-
+ atomic_inc(&buffer->resizing);
if (cpu_id == RING_BUFFER_ALL_CPUS) {
/*
@@ -2322,6 +2315,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
atomic_dec(&buffer->record_disabled);
}
+ atomic_dec(&buffer->resizing);
mutex_unlock(&buffer->mutex);
return 0;
@@ -2342,6 +2336,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
}
}
out_err_unlock:
+ atomic_dec(&buffer->resizing);
mutex_unlock(&buffer->mutex);
return err;
}
@@ -3000,7 +2995,6 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
{
unsigned long new_index, old_index;
struct buffer_page *bpage;
- unsigned long index;
unsigned long addr;
u64 write_stamp;
u64 delta;
@@ -3057,8 +3051,9 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
*/
old_index += write_mask;
new_index += write_mask;
- index = local_cmpxchg(&bpage->write, old_index, new_index);
- if (index == old_index) {
+
+ /* caution: old_index gets updated on cmpxchg failure */
+ if (local_try_cmpxchg(&bpage->write, &old_index, new_index)) {
/* update counters */
local_sub(event_length, &cpu_buffer->entries_bytes);
return true;
@@ -3373,7 +3368,6 @@ void ring_buffer_nest_end(struct trace_buffer *buffer)
/**
* ring_buffer_unlock_commit - commit a reserved
* @buffer: The buffer to commit to
- * @event: The event pointer to commit.
*
* This commits the data to the ring buffer, and releases any locks held.
*
@@ -4392,6 +4386,7 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
iter->cache_reader_page = iter->head_page;
iter->cache_read = cpu_buffer->read;
+ iter->cache_pages_removed = cpu_buffer->pages_removed;
if (iter->head) {
iter->read_stamp = cpu_buffer->read_stamp;
@@ -4846,12 +4841,13 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
buffer = cpu_buffer->buffer;
/*
- * Check if someone performed a consuming read to
- * the buffer. A consuming read invalidates the iterator
- * and we need to reset the iterator in this case.
+ * Check if someone performed a consuming read to the buffer
+ * or removed some pages from the buffer. In these cases,
+ * iterator was invalidated and we need to reset it.
*/
if (unlikely(iter->cache_read != cpu_buffer->read ||
- iter->cache_reader_page != cpu_buffer->reader_page))
+ iter->cache_reader_page != cpu_buffer->reader_page ||
+ iter->cache_pages_removed != cpu_buffer->pages_removed))
rb_iter_reset(iter);
again:
@@ -5242,28 +5238,34 @@ unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu)
}
EXPORT_SYMBOL_GPL(ring_buffer_size);
+static void rb_clear_buffer_page(struct buffer_page *page)
+{
+ local_set(&page->write, 0);
+ local_set(&page->entries, 0);
+ rb_init_page(page->page);
+ page->read = 0;
+}
+
static void
rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
{
+ struct buffer_page *page;
+
rb_head_page_deactivate(cpu_buffer);
cpu_buffer->head_page
= list_entry(cpu_buffer->pages, struct buffer_page, list);
- local_set(&cpu_buffer->head_page->write, 0);
- local_set(&cpu_buffer->head_page->entries, 0);
- local_set(&cpu_buffer->head_page->page->commit, 0);
-
- cpu_buffer->head_page->read = 0;
+ rb_clear_buffer_page(cpu_buffer->head_page);
+ list_for_each_entry(page, cpu_buffer->pages, list) {
+ rb_clear_buffer_page(page);
+ }
cpu_buffer->tail_page = cpu_buffer->head_page;
cpu_buffer->commit_page = cpu_buffer->head_page;
INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
INIT_LIST_HEAD(&cpu_buffer->new_pages);
- local_set(&cpu_buffer->reader_page->write, 0);
- local_set(&cpu_buffer->reader_page->entries, 0);
- local_set(&cpu_buffer->reader_page->page->commit, 0);
- cpu_buffer->reader_page->read = 0;
+ rb_clear_buffer_page(cpu_buffer->reader_page);
local_set(&cpu_buffer->entries_bytes, 0);
local_set(&cpu_buffer->overrun, 0);
@@ -5289,6 +5291,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
cpu_buffer->last_overrun = 0;
rb_head_page_activate(cpu_buffer);
+ cpu_buffer->pages_removed = 0;
}
/* Must have disabled the cpu buffer then done a synchronize_rcu */
@@ -5347,7 +5350,6 @@ EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
/**
* ring_buffer_reset_online_cpus - reset a ring buffer per CPU buffer
* @buffer: The ring buffer to reset a per cpu buffer of
- * @cpu: The CPU buffer to be reset
*/
void ring_buffer_reset_online_cpus(struct trace_buffer *buffer)
{
@@ -5535,6 +5537,15 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a,
if (local_read(&cpu_buffer_b->committing))
goto out_dec;
+ /*
+ * When resize is in progress, we cannot swap it because
+ * it will mess the state of the cpu buffer.
+ */
+ if (atomic_read(&buffer_a->resizing))
+ goto out_dec;
+ if (atomic_read(&buffer_b->resizing))
+ goto out_dec;
+
buffer_a->buffers[cpu] = cpu_buffer_b;
buffer_b->buffers[cpu] = cpu_buffer_a;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 64a4dde073ef..2b4ded753367 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -199,7 +199,7 @@ static int boot_snapshot_index;
static int __init set_cmdline_ftrace(char *str)
{
- strlcpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
+ strscpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
default_bootup_tracer = bootup_tracer_buf;
/* We are using ftrace early, expand it */
ring_buffer_expanded = true;
@@ -284,7 +284,7 @@ static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata;
static int __init set_trace_boot_options(char *str)
{
- strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
+ strscpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
return 1;
}
__setup("trace_options=", set_trace_boot_options);
@@ -294,7 +294,7 @@ static char *trace_boot_clock __initdata;
static int __init set_trace_boot_clock(char *str)
{
- strlcpy(trace_boot_clock_buf, str, MAX_TRACER_SIZE);
+ strscpy(trace_boot_clock_buf, str, MAX_TRACER_SIZE);
trace_boot_clock = trace_boot_clock_buf;
return 1;
}
@@ -1928,9 +1928,10 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
* place on this CPU. We fail to record, but we reset
* the max trace buffer (no one writes directly to it)
* and flag that it failed.
+ * Another reason is resize is in progress.
*/
trace_array_printk_buf(tr->max_buffer.buffer, _THIS_IP_,
- "Failed to swap buffers due to commit in progress\n");
+ "Failed to swap buffers due to commit or resize in progress\n");
}
WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY);
@@ -2546,7 +2547,7 @@ static void __trace_find_cmdline(int pid, char comm[])
if (map != NO_CMDLINE_MAP) {
tpid = savedcmd->map_cmdline_to_pid[map];
if (tpid == pid) {
- strlcpy(comm, get_saved_cmdlines(map), TASK_COMM_LEN);
+ strscpy(comm, get_saved_cmdlines(map), TASK_COMM_LEN);
return;
}
}
@@ -3155,16 +3156,16 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
nr_entries = stack_trace_save(fstack->calls, size, skip);
}
- size = nr_entries * sizeof(unsigned long);
event = __trace_buffer_lock_reserve(buffer, TRACE_STACK,
- (sizeof(*entry) - sizeof(entry->caller)) + size,
+ struct_size(entry, caller, nr_entries),
trace_ctx);
if (!event)
goto out;
entry = ring_buffer_event_data(event);
- memcpy(&entry->caller, fstack->calls, size);
entry->size = nr_entries;
+ memcpy(&entry->caller, fstack->calls,
+ flex_array_size(entry, caller, nr_entries));
if (!call_filter_check_discard(call, entry, buffer, event))
__buffer_unlock_commit(buffer, event);
@@ -4188,15 +4189,16 @@ static void *s_start(struct seq_file *m, loff_t *pos)
loff_t l = 0;
int cpu;
- /*
- * copy the tracer to avoid using a global lock all around.
- * iter->trace is a copy of current_trace, the pointer to the
- * name may be used instead of a strcmp(), as iter->trace->name
- * will point to the same string as current_trace->name.
- */
mutex_lock(&trace_types_lock);
- if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name))
- *iter->trace = *tr->current_trace;
+ if (unlikely(tr->current_trace != iter->trace)) {
+ /* Close iter->trace before switching to the new current tracer */
+ if (iter->trace->close)
+ iter->trace->close(iter);
+ iter->trace = tr->current_trace;
+ /* Reopen the new current tracer */
+ if (iter->trace->open)
+ iter->trace->open(iter);
+ }
mutex_unlock(&trace_types_lock);
#ifdef CONFIG_TRACER_MAX_TRACE
@@ -4804,6 +4806,25 @@ static const struct seq_operations tracer_seq_ops = {
.show = s_show,
};
+/*
+ * Note, as iter itself can be allocated and freed in different
+ * ways, this function is only used to free its content, and not
+ * the iterator itself. The only requirement to all the allocations
+ * is that it must zero all fields (kzalloc), as freeing works with
+ * ethier allocated content or NULL.
+ */
+static void free_trace_iter_content(struct trace_iterator *iter)
+{
+ /* The fmt is either NULL, allocated or points to static_fmt_buf */
+ if (iter->fmt != static_fmt_buf)
+ kfree(iter->fmt);
+
+ kfree(iter->temp);
+ kfree(iter->buffer_iter);
+ mutex_destroy(&iter->mutex);
+ free_cpumask_var(iter->started);
+}
+
static struct trace_iterator *
__tracing_open(struct inode *inode, struct file *file, bool snapshot)
{
@@ -4845,16 +4866,8 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
iter->fmt = NULL;
iter->fmt_size = 0;
- /*
- * We make a copy of the current tracer to avoid concurrent
- * changes on it while we are reading.
- */
mutex_lock(&trace_types_lock);
- iter->trace = kzalloc(sizeof(*iter->trace), GFP_KERNEL);
- if (!iter->trace)
- goto fail;
-
- *iter->trace = *tr->current_trace;
+ iter->trace = tr->current_trace;
if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL))
goto fail;
@@ -4919,9 +4932,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
fail:
mutex_unlock(&trace_types_lock);
- kfree(iter->trace);
- kfree(iter->temp);
- kfree(iter->buffer_iter);
+ free_trace_iter_content(iter);
release:
seq_release_private(inode, file);
return ERR_PTR(-ENOMEM);
@@ -5000,12 +5011,7 @@ static int tracing_release(struct inode *inode, struct file *file)
mutex_unlock(&trace_types_lock);
- mutex_destroy(&iter->mutex);
- free_cpumask_var(iter->started);
- kfree(iter->fmt);
- kfree(iter->temp);
- kfree(iter->trace);
- kfree(iter->buffer_iter);
+ free_trace_iter_content(iter);
seq_release_private(inode, file);
return 0;
@@ -5199,7 +5205,7 @@ static const struct file_operations tracing_fops = {
.open = tracing_open,
.read = seq_read,
.read_iter = seq_read_iter,
- .splice_read = generic_file_splice_read,
+ .splice_read = copy_splice_read,
.write = tracing_write_stub,
.llseek = tracing_lseek,
.release = tracing_release,
@@ -5259,11 +5265,17 @@ int tracing_set_cpumask(struct trace_array *tr,
!cpumask_test_cpu(cpu, tracing_cpumask_new)) {
atomic_inc(&per_cpu_ptr(tr->array_buffer.data, cpu)->disabled);
ring_buffer_record_disable_cpu(tr->array_buffer.buffer, cpu);
+#ifdef CONFIG_TRACER_MAX_TRACE
+ ring_buffer_record_disable_cpu(tr->max_buffer.buffer, cpu);
+#endif
}
if (!cpumask_test_cpu(cpu, tr->tracing_cpumask) &&
cpumask_test_cpu(cpu, tracing_cpumask_new)) {
atomic_dec(&per_cpu_ptr(tr->array_buffer.data, cpu)->disabled);
ring_buffer_record_enable_cpu(tr->array_buffer.buffer, cpu);
+#ifdef CONFIG_TRACER_MAX_TRACE
+ ring_buffer_record_enable_cpu(tr->max_buffer.buffer, cpu);
+#endif
}
}
arch_spin_unlock(&tr->max_lock);
@@ -5672,10 +5684,17 @@ static const char readme_msg[] =
" uprobe_events\t\t- Create/append/remove/show the userspace dynamic events\n"
"\t\t\t Write into this file to define/undefine new trace events.\n"
#endif
-#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS)
+#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS) || \
+ defined(CONFIG_FPROBE_EVENTS)
"\t accepts: event-definitions (one definition per line)\n"
+#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS)
"\t Format: p[:[<group>/][<event>]] <place> [<args>]\n"
"\t r[maxactive][:[<group>/][<event>]] <place> [<args>]\n"
+#endif
+#ifdef CONFIG_FPROBE_EVENTS
+ "\t f[:[<group>/][<event>]] <func-name>[%return] [<args>]\n"
+ "\t t[:[<group>/][<event>]] <tracepoint> [<args>]\n"
+#endif
#ifdef CONFIG_HIST_TRIGGERS
"\t s:[synthetic/]<event> <field> [<field>]\n"
#endif
@@ -5691,7 +5710,12 @@ static const char readme_msg[] =
"\t args: <name>=fetcharg[:type]\n"
"\t fetcharg: (%<register>|$<efield>), @<address>, @<symbol>[+|-<offset>],\n"
#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
+#ifdef CONFIG_PROBE_EVENTS_BTF_ARGS
"\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n"
+ "\t <argname>[->field[->field|.field...]],\n"
+#else
+ "\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n"
+#endif
#else
"\t $stack<index>, $stack, $retval, $comm,\n"
#endif
@@ -6276,6 +6300,15 @@ static void set_buffer_entries(struct array_buffer *buf, unsigned long val)
per_cpu_ptr(buf->data, cpu)->entries = val;
}
+static void update_buffer_entries(struct array_buffer *buf, int cpu)
+{
+ if (cpu == RING_BUFFER_ALL_CPUS) {
+ set_buffer_entries(buf, ring_buffer_size(buf->buffer, 0));
+ } else {
+ per_cpu_ptr(buf->data, cpu)->entries = ring_buffer_size(buf->buffer, cpu);
+ }
+}
+
#ifdef CONFIG_TRACER_MAX_TRACE
/* resize @tr's buffer to the size of @size_tr's entries */
static int resize_buffer_duplicate_size(struct array_buffer *trace_buf,
@@ -6354,18 +6387,12 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
return ret;
}
- if (cpu == RING_BUFFER_ALL_CPUS)
- set_buffer_entries(&tr->max_buffer, size);
- else
- per_cpu_ptr(tr->max_buffer.data, cpu)->entries = size;
+ update_buffer_entries(&tr->max_buffer, cpu);
out:
#endif /* CONFIG_TRACER_MAX_TRACE */
- if (cpu == RING_BUFFER_ALL_CPUS)
- set_buffer_entries(&tr->array_buffer, size);
- else
- per_cpu_ptr(tr->array_buffer.data, cpu)->entries = size;
+ update_buffer_entries(&tr->array_buffer, cpu);
return ret;
}
@@ -6676,10 +6703,36 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf,
#endif
+static int open_pipe_on_cpu(struct trace_array *tr, int cpu)
+{
+ if (cpu == RING_BUFFER_ALL_CPUS) {
+ if (cpumask_empty(tr->pipe_cpumask)) {
+ cpumask_setall(tr->pipe_cpumask);
+ return 0;
+ }
+ } else if (!cpumask_test_cpu(cpu, tr->pipe_cpumask)) {
+ cpumask_set_cpu(cpu, tr->pipe_cpumask);
+ return 0;
+ }
+ return -EBUSY;
+}
+
+static void close_pipe_on_cpu(struct trace_array *tr, int cpu)
+{
+ if (cpu == RING_BUFFER_ALL_CPUS) {
+ WARN_ON(!cpumask_full(tr->pipe_cpumask));
+ cpumask_clear(tr->pipe_cpumask);
+ } else {
+ WARN_ON(!cpumask_test_cpu(cpu, tr->pipe_cpumask));
+ cpumask_clear_cpu(cpu, tr->pipe_cpumask);
+ }
+}
+
static int tracing_open_pipe(struct inode *inode, struct file *filp)
{
struct trace_array *tr = inode->i_private;
struct trace_iterator *iter;
+ int cpu;
int ret;
ret = tracing_check_open_get_tr(tr);
@@ -6687,13 +6740,16 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
return ret;
mutex_lock(&trace_types_lock);
+ cpu = tracing_get_cpu(inode);
+ ret = open_pipe_on_cpu(tr, cpu);
+ if (ret)
+ goto fail_pipe_on_cpu;
/* create a buffer to store the information to pass to userspace */
iter = kzalloc(sizeof(*iter), GFP_KERNEL);
if (!iter) {
ret = -ENOMEM;
- __trace_array_put(tr);
- goto out;
+ goto fail_alloc_iter;
}
trace_seq_init(&iter->seq);
@@ -6716,7 +6772,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
iter->tr = tr;
iter->array_buffer = &tr->array_buffer;
- iter->cpu_file = tracing_get_cpu(inode);
+ iter->cpu_file = cpu;
mutex_init(&iter->mutex);
filp->private_data = iter;
@@ -6726,12 +6782,15 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
nonseekable_open(inode, filp);
tr->trace_ref++;
-out:
+
mutex_unlock(&trace_types_lock);
return ret;
fail:
kfree(iter);
+fail_alloc_iter:
+ close_pipe_on_cpu(tr, cpu);
+fail_pipe_on_cpu:
__trace_array_put(tr);
mutex_unlock(&trace_types_lock);
return ret;
@@ -6748,12 +6807,10 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
if (iter->trace->pipe_close)
iter->trace->pipe_close(iter);
-
+ close_pipe_on_cpu(tr, iter->cpu_file);
mutex_unlock(&trace_types_lock);
- free_cpumask_var(iter->started);
- kfree(iter->fmt);
- mutex_destroy(&iter->mutex);
+ free_trace_iter_content(iter);
kfree(iter);
trace_array_put(tr);
@@ -7543,6 +7600,11 @@ out:
return ret;
}
+static void tracing_swap_cpu_buffer(void *tr)
+{
+ update_max_tr_single((struct trace_array *)tr, current, smp_processor_id());
+}
+
static ssize_t
tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
loff_t *ppos)
@@ -7601,13 +7663,15 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
ret = tracing_alloc_snapshot_instance(tr);
if (ret < 0)
break;
- local_irq_disable();
/* Now, we're going to swap */
- if (iter->cpu_file == RING_BUFFER_ALL_CPUS)
+ if (iter->cpu_file == RING_BUFFER_ALL_CPUS) {
+ local_irq_disable();
update_max_tr(tr, current, smp_processor_id(), NULL);
- else
- update_max_tr_single(tr, current, iter->cpu_file);
- local_irq_enable();
+ local_irq_enable();
+ } else {
+ smp_call_function_single(iter->cpu_file, tracing_swap_cpu_buffer,
+ (void *)tr, 1);
+ }
break;
default:
if (tr->allocated_snapshot) {
@@ -8135,7 +8199,7 @@ static const struct file_operations tracing_err_log_fops = {
.open = tracing_err_log_open,
.write = tracing_err_log_write,
.read = seq_read,
- .llseek = seq_lseek,
+ .llseek = tracing_lseek,
.release = tracing_err_log_release,
};
@@ -9411,6 +9475,9 @@ static struct trace_array *trace_array_create(const char *name)
if (!alloc_cpumask_var(&tr->tracing_cpumask, GFP_KERNEL))
goto out_free_tr;
+ if (!zalloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL))
+ goto out_free_tr;
+
tr->trace_flags = global_trace.trace_flags & ~ZEROED_TRACE_FLAGS;
cpumask_copy(tr->tracing_cpumask, cpu_all_mask);
@@ -9452,6 +9519,7 @@ static struct trace_array *trace_array_create(const char *name)
out_free_tr:
ftrace_free_ftrace_ops(tr);
free_trace_buffers(tr);
+ free_cpumask_var(tr->pipe_cpumask);
free_cpumask_var(tr->tracing_cpumask);
kfree(tr->name);
kfree(tr);
@@ -9554,6 +9622,7 @@ static int __remove_instance(struct trace_array *tr)
}
kfree(tr->topts);
+ free_cpumask_var(tr->pipe_cpumask);
free_cpumask_var(tr->tracing_cpumask);
kfree(tr->name);
kfree(tr);
@@ -10351,12 +10420,14 @@ __init static int tracer_alloc_buffers(void)
if (trace_create_savedcmd() < 0)
goto out_free_temp_buffer;
+ if (!zalloc_cpumask_var(&global_trace.pipe_cpumask, GFP_KERNEL))
+ goto out_free_savedcmd;
+
/* TODO: make the number of buffers hot pluggable with CPUS */
if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) {
MEM_FAIL(1, "tracer: failed to allocate ring buffer!\n");
- goto out_free_savedcmd;
+ goto out_free_pipe_cpumask;
}
-
if (global_trace.buffer_disabled)
tracing_off();
@@ -10409,6 +10480,8 @@ __init static int tracer_alloc_buffers(void)
return 0;
+out_free_pipe_cpumask:
+ free_cpumask_var(global_trace.pipe_cpumask);
out_free_savedcmd:
free_saved_cmdlines_buffer(savedcmd);
out_free_temp_buffer:
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 79bdefe9261b..5669dd1f90d9 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -77,6 +77,16 @@ enum trace_type {
#undef __array
#define __array(type, item, size) type item[size];
+/*
+ * For backward compatibility, older user space expects to see the
+ * kernel_stack event with a fixed size caller field. But today the fix
+ * size is ignored by the kernel, and the real structure is dynamic.
+ * Expose to user space: "unsigned long caller[8];" but the real structure
+ * will be "unsigned long caller[] __counted_by(size)"
+ */
+#undef __stack_array
+#define __stack_array(type, item, size, field) type item[] __counted_by(field);
+
#undef __array_desc
#define __array_desc(type, container, item, size)
@@ -113,6 +123,8 @@ enum trace_type {
#define MEM_FAIL(condition, fmt, ...) \
DO_ONCE_LITE_IF(condition, pr_err, "ERROR: " fmt, ##__VA_ARGS__)
+#define FAULT_STRING "(fault)"
+
#define HIST_STACKTRACE_DEPTH 16
#define HIST_STACKTRACE_SIZE (HIST_STACKTRACE_DEPTH * sizeof(unsigned long))
#define HIST_STACKTRACE_SKIP 5
@@ -148,6 +160,17 @@ struct kretprobe_trace_entry_head {
unsigned long ret_ip;
};
+struct fentry_trace_entry_head {
+ struct trace_entry ent;
+ unsigned long ip;
+};
+
+struct fexit_trace_entry_head {
+ struct trace_entry ent;
+ unsigned long func;
+ unsigned long ret_ip;
+};
+
#define TRACE_BUF_SIZE 1024
struct trace_array;
@@ -364,6 +387,8 @@ struct trace_array {
struct list_head events;
struct trace_event_file *trace_marker_file;
cpumask_var_t tracing_cpumask; /* only trace on set CPUs */
+ /* one per_cpu trace_pipe can be opened by only one user */
+ cpumask_var_t pipe_cpumask;
int ref;
int trace_ref;
#ifdef CONFIG_FUNCTION_TRACER
@@ -581,7 +606,6 @@ trace_buffer_iter(struct trace_iterator *iter, int cpu)
int tracer_init(struct tracer *t, struct trace_array *tr);
int tracing_is_enabled(void);
void tracing_reset_online_cpus(struct array_buffer *buf);
-void tracing_reset_current(int cpu);
void tracing_reset_all_online_cpus(void);
void tracing_reset_all_online_cpus_unlocked(void);
int tracing_open_generic(struct inode *inode, struct file *filp);
@@ -682,7 +706,6 @@ void trace_filter_add_remove_task(struct trace_pid_list *pid_list,
void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos);
void *trace_pid_start(struct trace_pid_list *pid_list, loff_t *pos);
int trace_pid_show(struct seq_file *m, void *v);
-void trace_free_pid_list(struct trace_pid_list *pid_list);
int trace_pid_write(struct trace_pid_list *filtered_pids,
struct trace_pid_list **new_pid_list,
const char __user *ubuf, size_t cnt);
@@ -832,6 +855,8 @@ static __always_inline bool ftrace_hash_empty(struct ftrace_hash *hash)
#define TRACE_GRAPH_PRINT_TAIL 0x100
#define TRACE_GRAPH_SLEEP_TIME 0x200
#define TRACE_GRAPH_GRAPH_TIME 0x400
+#define TRACE_GRAPH_PRINT_RETVAL 0x800
+#define TRACE_GRAPH_PRINT_RETVAL_HEX 0x1000
#define TRACE_GRAPH_PRINT_FILL_SHIFT 28
#define TRACE_GRAPH_PRINT_FILL_MASK (0x3 << TRACE_GRAPH_PRINT_FILL_SHIFT)
@@ -1280,6 +1305,14 @@ static inline void trace_branch_disable(void)
/* set ring buffers to default size if not already done so */
int tracing_update_buffers(void);
+union trace_synth_field {
+ u8 as_u8;
+ u16 as_u16;
+ u32 as_u32;
+ u64 as_u64;
+ struct trace_dynamic_info as_dynamic;
+};
+
struct ftrace_event_field {
struct list_head link;
const char *name;
@@ -1309,7 +1342,7 @@ struct trace_subsystem_dir {
struct list_head list;
struct event_subsystem *subsystem;
struct trace_array *tr;
- struct dentry *entry;
+ struct eventfs_file *ef;
int ref_count;
int nr_events;
};
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 778200dd8ede..7ccc7a8e155b 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -31,7 +31,7 @@ trace_boot_set_instance_options(struct trace_array *tr, struct xbc_node *node)
/* Common ftrace options */
xbc_node_for_each_array_value(node, "options", anode, p) {
- if (strlcpy(buf, p, ARRAY_SIZE(buf)) >= ARRAY_SIZE(buf)) {
+ if (strscpy(buf, p, ARRAY_SIZE(buf)) < 0) {
pr_err("String is too long: %s\n", p);
continue;
}
@@ -87,7 +87,7 @@ trace_boot_enable_events(struct trace_array *tr, struct xbc_node *node)
const char *p;
xbc_node_for_each_array_value(node, "events", anode, p) {
- if (strlcpy(buf, p, ARRAY_SIZE(buf)) >= ARRAY_SIZE(buf)) {
+ if (strscpy(buf, p, ARRAY_SIZE(buf)) < 0) {
pr_err("String is too long: %s\n", p);
continue;
}
@@ -486,7 +486,7 @@ trace_boot_init_one_event(struct trace_array *tr, struct xbc_node *gnode,
p = xbc_node_find_value(enode, "filter", NULL);
if (p && *p != '\0') {
- if (strlcpy(buf, p, ARRAY_SIZE(buf)) >= ARRAY_SIZE(buf))
+ if (strscpy(buf, p, ARRAY_SIZE(buf)) < 0)
pr_err("filter string is too long: %s\n", p);
else if (apply_event_filter(file, buf) < 0)
pr_err("Failed to apply filter: %s\n", buf);
@@ -494,7 +494,7 @@ trace_boot_init_one_event(struct trace_array *tr, struct xbc_node *gnode,
if (IS_ENABLED(CONFIG_HIST_TRIGGERS)) {
xbc_node_for_each_array_value(enode, "actions", anode, p) {
- if (strlcpy(buf, p, ARRAY_SIZE(buf)) >= ARRAY_SIZE(buf))
+ if (strscpy(buf, p, ARRAY_SIZE(buf)) < 0)
pr_err("action string is too long: %s\n", p);
else if (trigger_process_regex(file, buf) < 0)
pr_err("Failed to apply an action: %s\n", p);
diff --git a/kernel/trace/trace_btf.c b/kernel/trace/trace_btf.c
new file mode 100644
index 000000000000..ca224d53bfdc
--- /dev/null
+++ b/kernel/trace/trace_btf.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/btf.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+#include "trace_btf.h"
+
+/*
+ * Find a function proto type by name, and return the btf_type with its btf
+ * in *@btf_p. Return NULL if not found.
+ * Note that caller has to call btf_put(*@btf_p) after using the btf_type.
+ */
+const struct btf_type *btf_find_func_proto(const char *func_name, struct btf **btf_p)
+{
+ const struct btf_type *t;
+ s32 id;
+
+ id = bpf_find_btf_id(func_name, BTF_KIND_FUNC, btf_p);
+ if (id < 0)
+ return NULL;
+
+ /* Get BTF_KIND_FUNC type */
+ t = btf_type_by_id(*btf_p, id);
+ if (!t || !btf_type_is_func(t))
+ goto err;
+
+ /* The type of BTF_KIND_FUNC is BTF_KIND_FUNC_PROTO */
+ t = btf_type_by_id(*btf_p, t->type);
+ if (!t || !btf_type_is_func_proto(t))
+ goto err;
+
+ return t;
+err:
+ btf_put(*btf_p);
+ return NULL;
+}
+
+/*
+ * Get function parameter with the number of parameters.
+ * This can return NULL if the function has no parameters.
+ * It can return -EINVAL if the @func_proto is not a function proto type.
+ */
+const struct btf_param *btf_get_func_param(const struct btf_type *func_proto, s32 *nr)
+{
+ if (!btf_type_is_func_proto(func_proto))
+ return ERR_PTR(-EINVAL);
+
+ *nr = btf_type_vlen(func_proto);
+ if (*nr > 0)
+ return (const struct btf_param *)(func_proto + 1);
+ else
+ return NULL;
+}
+
+#define BTF_ANON_STACK_MAX 16
+
+struct btf_anon_stack {
+ u32 tid;
+ u32 offset;
+};
+
+/*
+ * Find a member of data structure/union by name and return it.
+ * Return NULL if not found, or -EINVAL if parameter is invalid.
+ * If the member is an member of anonymous union/structure, the offset
+ * of that anonymous union/structure is stored into @anon_offset. Caller
+ * can calculate the correct offset from the root data structure by
+ * adding anon_offset to the member's offset.
+ */
+const struct btf_member *btf_find_struct_member(struct btf *btf,
+ const struct btf_type *type,
+ const char *member_name,
+ u32 *anon_offset)
+{
+ struct btf_anon_stack *anon_stack;
+ const struct btf_member *member;
+ u32 tid, cur_offset = 0;
+ const char *name;
+ int i, top = 0;
+
+ anon_stack = kcalloc(BTF_ANON_STACK_MAX, sizeof(*anon_stack), GFP_KERNEL);
+ if (!anon_stack)
+ return ERR_PTR(-ENOMEM);
+
+retry:
+ if (!btf_type_is_struct(type)) {
+ member = ERR_PTR(-EINVAL);
+ goto out;
+ }
+
+ for_each_member(i, type, member) {
+ if (!member->name_off) {
+ /* Anonymous union/struct: push it for later use */
+ type = btf_type_skip_modifiers(btf, member->type, &tid);
+ if (type && top < BTF_ANON_STACK_MAX) {
+ anon_stack[top].tid = tid;
+ anon_stack[top++].offset =
+ cur_offset + member->offset;
+ }
+ } else {
+ name = btf_name_by_offset(btf, member->name_off);
+ if (name && !strcmp(member_name, name)) {
+ if (anon_offset)
+ *anon_offset = cur_offset;
+ goto out;
+ }
+ }
+ }
+ if (top > 0) {
+ /* Pop from the anonymous stack and retry */
+ tid = anon_stack[--top].tid;
+ cur_offset = anon_stack[top].offset;
+ type = btf_type_by_id(btf, tid);
+ goto retry;
+ }
+ member = NULL;
+
+out:
+ kfree(anon_stack);
+ return member;
+}
+
diff --git a/kernel/trace/trace_btf.h b/kernel/trace/trace_btf.h
new file mode 100644
index 000000000000..4bc44bc261e6
--- /dev/null
+++ b/kernel/trace/trace_btf.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/btf.h>
+
+const struct btf_type *btf_find_func_proto(const char *func_name,
+ struct btf **btf_p);
+const struct btf_param *btf_get_func_param(const struct btf_type *func_proto,
+ s32 *nr);
+const struct btf_member *btf_find_struct_member(struct btf *btf,
+ const struct btf_type *type,
+ const char *member_name,
+ u32 *anon_offset);
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index cd41e863b51c..c47422b20908 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -86,6 +86,30 @@ FTRACE_ENTRY_PACKED(funcgraph_entry, ftrace_graph_ent_entry,
);
/* Function return entry */
+#ifdef CONFIG_FUNCTION_GRAPH_RETVAL
+
+FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
+
+ TRACE_GRAPH_RET,
+
+ F_STRUCT(
+ __field_struct( struct ftrace_graph_ret, ret )
+ __field_packed( unsigned long, ret, func )
+ __field_packed( unsigned long, ret, retval )
+ __field_packed( int, ret, depth )
+ __field_packed( unsigned int, ret, overrun )
+ __field_packed( unsigned long long, ret, calltime)
+ __field_packed( unsigned long long, ret, rettime )
+ ),
+
+ F_printk("<-- %ps (%d) (start: %llx end: %llx) over: %d retval: %lx",
+ (void *)__entry->func, __entry->depth,
+ __entry->calltime, __entry->rettime,
+ __entry->depth, __entry->retval)
+);
+
+#else
+
FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
TRACE_GRAPH_RET,
@@ -105,6 +129,8 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
__entry->depth)
);
+#endif
+
/*
* Context switch trace entry - which task (and prio) we switched from/to:
*
@@ -164,7 +190,7 @@ FTRACE_ENTRY(kernel_stack, stack_entry,
F_STRUCT(
__field( int, size )
- __array( unsigned long, caller, FTRACE_STACK_ENTRIES )
+ __stack_array( unsigned long, caller, FTRACE_STACK_ENTRIES, size)
),
F_printk("\t=> %ps\n\t=> %ps\n\t=> %ps\n"
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index 67e854979d53..72714cbf475c 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -41,6 +41,10 @@ struct eprobe_data {
struct trace_eprobe *ep;
};
+
+#define for_each_trace_eprobe_tp(ep, _tp) \
+ list_for_each_entry(ep, trace_probe_probe_list(_tp), tp.list)
+
static int __trace_eprobe_create(int argc, const char *argv[]);
static void trace_event_probe_cleanup(struct trace_eprobe *ep)
@@ -227,37 +231,6 @@ error:
return ERR_PTR(ret);
}
-static int trace_eprobe_tp_arg_update(struct trace_eprobe *ep, int i)
-{
- struct probe_arg *parg = &ep->tp.args[i];
- struct ftrace_event_field *field;
- struct list_head *head;
- int ret = -ENOENT;
-
- head = trace_get_fields(ep->event);
- list_for_each_entry(field, head, link) {
- if (!strcmp(parg->code->data, field->name)) {
- kfree(parg->code->data);
- parg->code->data = field;
- return 0;
- }
- }
-
- /*
- * Argument not found on event. But allow for comm and COMM
- * to be used to get the current->comm.
- */
- if (strcmp(parg->code->data, "COMM") == 0 ||
- strcmp(parg->code->data, "comm") == 0) {
- parg->code->op = FETCH_OP_COMM;
- ret = 0;
- }
-
- kfree(parg->code->data);
- parg->code->data = NULL;
- return ret;
-}
-
static int eprobe_event_define_fields(struct trace_event_call *event_call)
{
struct eprobe_trace_entry_head field;
@@ -671,10 +644,11 @@ static int disable_eprobe(struct trace_eprobe *ep,
static int enable_trace_eprobe(struct trace_event_call *call,
struct trace_event_file *file)
{
- struct trace_probe *pos, *tp;
+ struct trace_probe *tp;
struct trace_eprobe *ep;
bool enabled;
int ret = 0;
+ int cnt = 0;
tp = trace_probe_primary_from_call(call);
if (WARN_ON_ONCE(!tp))
@@ -692,18 +666,29 @@ static int enable_trace_eprobe(struct trace_event_call *call,
if (enabled)
return 0;
- list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
- ep = container_of(pos, struct trace_eprobe, tp);
+ for_each_trace_eprobe_tp(ep, tp) {
ret = enable_eprobe(ep, file);
if (ret)
break;
enabled = true;
+ cnt++;
}
if (ret) {
/* Failed to enable one of them. Roll back all */
- if (enabled)
- disable_eprobe(ep, file->tr);
+ if (enabled) {
+ /*
+ * It's a bug if one failed for something other than memory
+ * not being available but another eprobe succeeded.
+ */
+ WARN_ON_ONCE(ret != -ENOMEM);
+
+ for_each_trace_eprobe_tp(ep, tp) {
+ disable_eprobe(ep, file->tr);
+ if (!--cnt)
+ break;
+ }
+ }
if (file)
trace_probe_remove_file(tp, file);
else
@@ -716,7 +701,7 @@ static int enable_trace_eprobe(struct trace_event_call *call,
static int disable_trace_eprobe(struct trace_event_call *call,
struct trace_event_file *file)
{
- struct trace_probe *pos, *tp;
+ struct trace_probe *tp;
struct trace_eprobe *ep;
tp = trace_probe_primary_from_call(call);
@@ -733,10 +718,8 @@ static int disable_trace_eprobe(struct trace_event_call *call,
trace_probe_clear_flag(tp, TP_FLAG_PROFILE);
if (!trace_probe_is_enabled(tp)) {
- list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
- ep = container_of(pos, struct trace_eprobe, tp);
+ for_each_trace_eprobe_tp(ep, tp)
disable_eprobe(ep, file->tr);
- }
}
out:
@@ -817,23 +800,18 @@ find_and_get_event(const char *system, const char *event_name)
static int trace_eprobe_tp_update_arg(struct trace_eprobe *ep, const char *argv[], int i)
{
- unsigned int flags = TPARG_FL_KERNEL | TPARG_FL_TPOINT;
+ struct traceprobe_parse_context ctx = {
+ .event = ep->event,
+ .flags = TPARG_FL_KERNEL | TPARG_FL_TEVENT,
+ };
int ret;
- ret = traceprobe_parse_probe_arg(&ep->tp, i, argv[i], flags);
- if (ret)
- return ret;
-
- if (ep->tp.args[i].code->op == FETCH_OP_TP_ARG) {
- ret = trace_eprobe_tp_arg_update(ep, i);
- if (ret)
- trace_probe_log_err(0, BAD_ATTACH_ARG);
- }
-
+ ret = traceprobe_parse_probe_arg(&ep->tp, i, argv[i], &ctx);
/* Handle symbols "@" */
if (!ret)
ret = traceprobe_update_arg(&ep->tp.args[i]);
+ traceprobe_finish_parse(&ctx);
return ret;
}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 57e539d47989..ed367d713be0 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -611,7 +611,6 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
{
struct trace_event_call *call = file->event_call;
struct trace_array *tr = file->tr;
- unsigned long file_flags = file->flags;
int ret = 0;
int disable;
@@ -635,6 +634,8 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
break;
disable = file->flags & EVENT_FILE_FL_SOFT_DISABLED;
clear_bit(EVENT_FILE_FL_SOFT_MODE_BIT, &file->flags);
+ /* Disable use of trace_buffered_event */
+ trace_buffered_event_disable();
} else
disable = !(file->flags & EVENT_FILE_FL_SOFT_MODE);
@@ -673,6 +674,8 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
if (atomic_inc_return(&file->sm_ref) > 1)
break;
set_bit(EVENT_FILE_FL_SOFT_MODE_BIT, &file->flags);
+ /* Enable use of trace_buffered_event */
+ trace_buffered_event_enable();
}
if (!(file->flags & EVENT_FILE_FL_ENABLED)) {
@@ -712,15 +715,6 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
break;
}
- /* Enable or disable use of trace_buffered_event */
- if ((file_flags & EVENT_FILE_FL_SOFT_DISABLED) !=
- (file->flags & EVENT_FILE_FL_SOFT_DISABLED)) {
- if (file->flags & EVENT_FILE_FL_SOFT_DISABLED)
- trace_buffered_event_enable();
- else
- trace_buffered_event_disable();
- }
-
return ret;
}
@@ -990,7 +984,7 @@ static void remove_subsystem(struct trace_subsystem_dir *dir)
return;
if (!--dir->nr_events) {
- tracefs_remove(dir->entry);
+ eventfs_remove(dir->ef);
list_del(&dir->list);
__put_system_dir(dir);
}
@@ -1011,7 +1005,7 @@ static void remove_event_file_dir(struct trace_event_file *file)
tracefs_remove(dir);
}
-
+ eventfs_remove(file->ef);
list_del(&file->list);
remove_subsystem(file->system);
free_event_filter(file->filter);
@@ -2297,13 +2291,13 @@ create_new_subsystem(const char *name)
return NULL;
}
-static struct dentry *
+static struct eventfs_file *
event_subsystem_dir(struct trace_array *tr, const char *name,
struct trace_event_file *file, struct dentry *parent)
{
struct event_subsystem *system, *iter;
struct trace_subsystem_dir *dir;
- struct dentry *entry;
+ int res;
/* First see if we did not already create this dir */
list_for_each_entry(dir, &tr->systems, list) {
@@ -2311,7 +2305,7 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
if (strcmp(system->name, name) == 0) {
dir->nr_events++;
file->system = dir;
- return dir->entry;
+ return dir->ef;
}
}
@@ -2335,8 +2329,8 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
} else
__get_system(system);
- dir->entry = tracefs_create_dir(name, parent);
- if (!dir->entry) {
+ dir->ef = eventfs_add_subsystem_dir(name, parent);
+ if (IS_ERR(dir->ef)) {
pr_warn("Failed to create system directory %s\n", name);
__put_system(system);
goto out_free;
@@ -2351,22 +2345,22 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
/* the ftrace system is special, do not create enable or filter files */
if (strcmp(name, "ftrace") != 0) {
- entry = tracefs_create_file("filter", TRACE_MODE_WRITE,
- dir->entry, dir,
+ res = eventfs_add_file("filter", TRACE_MODE_WRITE,
+ dir->ef, dir,
&ftrace_subsystem_filter_fops);
- if (!entry) {
+ if (res) {
kfree(system->filter);
system->filter = NULL;
pr_warn("Could not create tracefs '%s/filter' entry\n", name);
}
- trace_create_file("enable", TRACE_MODE_WRITE, dir->entry, dir,
+ eventfs_add_file("enable", TRACE_MODE_WRITE, dir->ef, dir,
&ftrace_system_enable_fops);
}
list_add(&dir->list, &tr->systems);
- return dir->entry;
+ return dir->ef;
out_free:
kfree(dir);
@@ -2419,36 +2413,37 @@ static int
event_create_dir(struct dentry *parent, struct trace_event_file *file)
{
struct trace_event_call *call = file->event_call;
+ struct eventfs_file *ef_subsystem = NULL;
struct trace_array *tr = file->tr;
- struct dentry *d_events;
const char *name;
int ret;
/*
* If the trace point header did not define TRACE_SYSTEM
- * then the system would be called "TRACE_SYSTEM".
+ * then the system would be called "TRACE_SYSTEM". This should
+ * never happen.
*/
- if (strcmp(call->class->system, TRACE_SYSTEM) != 0) {
- d_events = event_subsystem_dir(tr, call->class->system, file, parent);
- if (!d_events)
- return -ENOMEM;
- } else
- d_events = parent;
+ if (WARN_ON_ONCE(strcmp(call->class->system, TRACE_SYSTEM) == 0))
+ return -ENODEV;
+
+ ef_subsystem = event_subsystem_dir(tr, call->class->system, file, parent);
+ if (!ef_subsystem)
+ return -ENOMEM;
name = trace_event_name(call);
- file->dir = tracefs_create_dir(name, d_events);
- if (!file->dir) {
+ file->ef = eventfs_add_dir(name, ef_subsystem);
+ if (IS_ERR(file->ef)) {
pr_warn("Could not create tracefs '%s' directory\n", name);
return -1;
}
if (call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
- trace_create_file("enable", TRACE_MODE_WRITE, file->dir, file,
+ eventfs_add_file("enable", TRACE_MODE_WRITE, file->ef, file,
&ftrace_enable_fops);
#ifdef CONFIG_PERF_EVENTS
if (call->event.type && call->class->reg)
- trace_create_file("id", TRACE_MODE_READ, file->dir,
+ eventfs_add_file("id", TRACE_MODE_READ, file->ef,
(void *)(long)call->event.type,
&ftrace_event_id_fops);
#endif
@@ -2464,27 +2459,27 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
* triggers or filters.
*/
if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) {
- trace_create_file("filter", TRACE_MODE_WRITE, file->dir,
+ eventfs_add_file("filter", TRACE_MODE_WRITE, file->ef,
file, &ftrace_event_filter_fops);
- trace_create_file("trigger", TRACE_MODE_WRITE, file->dir,
+ eventfs_add_file("trigger", TRACE_MODE_WRITE, file->ef,
file, &event_trigger_fops);
}
#ifdef CONFIG_HIST_TRIGGERS
- trace_create_file("hist", TRACE_MODE_READ, file->dir, file,
+ eventfs_add_file("hist", TRACE_MODE_READ, file->ef, file,
&event_hist_fops);
#endif
#ifdef CONFIG_HIST_TRIGGERS_DEBUG
- trace_create_file("hist_debug", TRACE_MODE_READ, file->dir, file,
+ eventfs_add_file("hist_debug", TRACE_MODE_READ, file->ef, file,
&event_hist_debug_fops);
#endif
- trace_create_file("format", TRACE_MODE_READ, file->dir, call,
+ eventfs_add_file("format", TRACE_MODE_READ, file->ef, call,
&ftrace_event_format_fops);
#ifdef CONFIG_TRACE_EVENT_INJECT
if (call->event.type && call->class->reg)
- trace_create_file("inject", 0200, file->dir, file,
+ eventfs_add_file("inject", 0200, file->ef, file,
&event_inject_fops);
#endif
@@ -2833,7 +2828,7 @@ static __init int setup_trace_triggers(char *str)
char *buf;
int i;
- strlcpy(bootup_trigger_buf, str, COMMAND_LINE_SIZE);
+ strscpy(bootup_trigger_buf, str, COMMAND_LINE_SIZE);
ring_buffer_expanded = true;
disable_tracing_selftest("running event triggers");
@@ -3623,7 +3618,7 @@ static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata;
static __init int setup_trace_event(char *str)
{
- strlcpy(bootup_event_buf, str, COMMAND_LINE_SIZE);
+ strscpy(bootup_event_buf, str, COMMAND_LINE_SIZE);
ring_buffer_expanded = true;
disable_tracing_selftest("running event tracing");
@@ -3637,21 +3632,22 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
{
struct dentry *d_events;
struct dentry *entry;
+ int error = 0;
entry = trace_create_file("set_event", TRACE_MODE_WRITE, parent,
tr, &ftrace_set_event_fops);
if (!entry)
return -ENOMEM;
- d_events = tracefs_create_dir("events", parent);
- if (!d_events) {
+ d_events = eventfs_create_events_dir("events", parent);
+ if (IS_ERR(d_events)) {
pr_warn("Could not create tracefs 'events' directory\n");
return -ENOMEM;
}
- entry = trace_create_file("enable", TRACE_MODE_WRITE, d_events,
+ error = eventfs_add_events_file("enable", TRACE_MODE_WRITE, d_events,
tr, &ftrace_tr_enable_fops);
- if (!entry)
+ if (error)
return -ENOMEM;
/* There are not as crucial, just warn if they are not created */
@@ -3664,11 +3660,11 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
&ftrace_set_event_notrace_pid_fops);
/* ring buffer internal formats */
- trace_create_file("header_page", TRACE_MODE_READ, d_events,
+ eventfs_add_events_file("header_page", TRACE_MODE_READ, d_events,
ring_buffer_print_page_header,
&ftrace_show_header_fops);
- trace_create_file("header_event", TRACE_MODE_READ, d_events,
+ eventfs_add_events_file("header_event", TRACE_MODE_READ, d_events,
ring_buffer_print_entry_header,
&ftrace_show_header_fops);
@@ -3756,7 +3752,7 @@ int event_trace_del_tracer(struct trace_array *tr)
down_write(&trace_event_sem);
__trace_remove_event_dirs(tr);
- tracefs_remove(tr->event_dir);
+ eventfs_remove_events_dir(tr->event_dir);
up_write(&trace_event_sem);
tr->event_dir = NULL;
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 1dad64267878..33264e510d16 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -46,15 +46,19 @@ static const char * ops[] = { OPS };
enum filter_pred_fn {
FILTER_PRED_FN_NOP,
FILTER_PRED_FN_64,
+ FILTER_PRED_FN_64_CPUMASK,
FILTER_PRED_FN_S64,
FILTER_PRED_FN_U64,
FILTER_PRED_FN_32,
+ FILTER_PRED_FN_32_CPUMASK,
FILTER_PRED_FN_S32,
FILTER_PRED_FN_U32,
FILTER_PRED_FN_16,
+ FILTER_PRED_FN_16_CPUMASK,
FILTER_PRED_FN_S16,
FILTER_PRED_FN_U16,
FILTER_PRED_FN_8,
+ FILTER_PRED_FN_8_CPUMASK,
FILTER_PRED_FN_S8,
FILTER_PRED_FN_U8,
FILTER_PRED_FN_COMM,
@@ -64,21 +68,25 @@ enum filter_pred_fn {
FILTER_PRED_FN_PCHAR_USER,
FILTER_PRED_FN_PCHAR,
FILTER_PRED_FN_CPU,
+ FILTER_PRED_FN_CPU_CPUMASK,
+ FILTER_PRED_FN_CPUMASK,
+ FILTER_PRED_FN_CPUMASK_CPU,
FILTER_PRED_FN_FUNCTION,
FILTER_PRED_FN_,
FILTER_PRED_TEST_VISITED,
};
struct filter_pred {
- enum filter_pred_fn fn_num;
- u64 val;
- u64 val2;
- struct regex regex;
+ struct regex *regex;
+ struct cpumask *mask;
unsigned short *ops;
struct ftrace_event_field *field;
- int offset;
+ u64 val;
+ u64 val2;
+ enum filter_pred_fn fn_num;
+ int offset;
int not;
- int op;
+ int op;
};
/*
@@ -94,6 +102,8 @@ struct filter_pred {
C(TOO_MANY_OPEN, "Too many '('"), \
C(TOO_MANY_CLOSE, "Too few '('"), \
C(MISSING_QUOTE, "Missing matching quote"), \
+ C(MISSING_BRACE_OPEN, "Missing '{'"), \
+ C(MISSING_BRACE_CLOSE, "Missing '}'"), \
C(OPERAND_TOO_LONG, "Operand too long"), \
C(EXPECT_STRING, "Expecting string field"), \
C(EXPECT_DIGIT, "Expecting numeric field"), \
@@ -103,6 +113,7 @@ struct filter_pred {
C(BAD_SUBSYS_FILTER, "Couldn't find or set field in one of a subsystem's events"), \
C(TOO_MANY_PREDS, "Too many terms in predicate expression"), \
C(INVALID_FILTER, "Meaningless filter expression"), \
+ C(INVALID_CPULIST, "Invalid cpulist"), \
C(IP_FIELD_ONLY, "Only 'ip' field is supported for function trace"), \
C(INVALID_VALUE, "Invalid value (did you forget quotes)?"), \
C(NO_FUNCTION, "Function not found"), \
@@ -186,6 +197,15 @@ enum {
PROCESS_OR = 4,
};
+static void free_predicate(struct filter_pred *pred)
+{
+ if (pred) {
+ kfree(pred->regex);
+ kfree(pred->mask);
+ kfree(pred);
+ }
+}
+
/*
* Without going into a formal proof, this explains the method that is used in
* parsing the logical expressions.
@@ -623,12 +643,64 @@ out_free:
kfree(inverts);
if (prog_stack) {
for (i = 0; prog_stack[i].pred; i++)
- kfree(prog_stack[i].pred);
+ free_predicate(prog_stack[i].pred);
kfree(prog_stack);
}
return ERR_PTR(ret);
}
+static inline int
+do_filter_cpumask(int op, const struct cpumask *mask, const struct cpumask *cmp)
+{
+ switch (op) {
+ case OP_EQ:
+ return cpumask_equal(mask, cmp);
+ case OP_NE:
+ return !cpumask_equal(mask, cmp);
+ case OP_BAND:
+ return cpumask_intersects(mask, cmp);
+ default:
+ return 0;
+ }
+}
+
+/* Optimisation of do_filter_cpumask() for scalar fields */
+static inline int
+do_filter_scalar_cpumask(int op, unsigned int cpu, const struct cpumask *mask)
+{
+ /*
+ * Per the weight-of-one cpumask optimisations, the mask passed in this
+ * function has a weight >= 2, so it is never equal to a single scalar.
+ */
+ switch (op) {
+ case OP_EQ:
+ return false;
+ case OP_NE:
+ return true;
+ case OP_BAND:
+ return cpumask_test_cpu(cpu, mask);
+ default:
+ return 0;
+ }
+}
+
+static inline int
+do_filter_cpumask_scalar(int op, const struct cpumask *mask, unsigned int cpu)
+{
+ switch (op) {
+ case OP_EQ:
+ return cpumask_test_cpu(cpu, mask) &&
+ cpumask_nth(1, mask) >= nr_cpu_ids;
+ case OP_NE:
+ return !cpumask_test_cpu(cpu, mask) ||
+ cpumask_nth(1, mask) < nr_cpu_ids;
+ case OP_BAND:
+ return cpumask_test_cpu(cpu, mask);
+ default:
+ return 0;
+ }
+}
+
enum pred_cmp_types {
PRED_CMP_TYPE_NOP,
PRED_CMP_TYPE_LT,
@@ -672,6 +744,18 @@ static int filter_pred_##type(struct filter_pred *pred, void *event) \
} \
}
+#define DEFINE_CPUMASK_COMPARISON_PRED(size) \
+static int filter_pred_##size##_cpumask(struct filter_pred *pred, void *event) \
+{ \
+ u##size *addr = (u##size *)(event + pred->offset); \
+ unsigned int cpu = *addr; \
+ \
+ if (cpu >= nr_cpu_ids) \
+ return 0; \
+ \
+ return do_filter_scalar_cpumask(pred->op, cpu, pred->mask); \
+}
+
#define DEFINE_EQUALITY_PRED(size) \
static int filter_pred_##size(struct filter_pred *pred, void *event) \
{ \
@@ -693,6 +777,11 @@ DEFINE_COMPARISON_PRED(u16);
DEFINE_COMPARISON_PRED(s8);
DEFINE_COMPARISON_PRED(u8);
+DEFINE_CPUMASK_COMPARISON_PRED(64);
+DEFINE_CPUMASK_COMPARISON_PRED(32);
+DEFINE_CPUMASK_COMPARISON_PRED(16);
+DEFINE_CPUMASK_COMPARISON_PRED(8);
+
DEFINE_EQUALITY_PRED(64);
DEFINE_EQUALITY_PRED(32);
DEFINE_EQUALITY_PRED(16);
@@ -750,7 +839,7 @@ static int filter_pred_string(struct filter_pred *pred, void *event)
char *addr = (char *)(event + pred->offset);
int cmp, match;
- cmp = pred->regex.match(addr, &pred->regex, pred->regex.field_len);
+ cmp = pred->regex->match(addr, pred->regex, pred->regex->field_len);
match = cmp ^ pred->not;
@@ -763,7 +852,7 @@ static __always_inline int filter_pchar(struct filter_pred *pred, char *str)
int len;
len = strlen(str) + 1; /* including tailing '\0' */
- cmp = pred->regex.match(str, &pred->regex, len);
+ cmp = pred->regex->match(str, pred->regex, len);
match = cmp ^ pred->not;
@@ -813,7 +902,7 @@ static int filter_pred_strloc(struct filter_pred *pred, void *event)
char *addr = (char *)(event + str_loc);
int cmp, match;
- cmp = pred->regex.match(addr, &pred->regex, str_len);
+ cmp = pred->regex->match(addr, pred->regex, str_len);
match = cmp ^ pred->not;
@@ -836,7 +925,7 @@ static int filter_pred_strrelloc(struct filter_pred *pred, void *event)
char *addr = (char *)(&item[1]) + str_loc;
int cmp, match;
- cmp = pred->regex.match(addr, &pred->regex, str_len);
+ cmp = pred->regex->match(addr, pred->regex, str_len);
match = cmp ^ pred->not;
@@ -869,12 +958,42 @@ static int filter_pred_cpu(struct filter_pred *pred, void *event)
}
}
+/* Filter predicate for current CPU vs user-provided cpumask */
+static int filter_pred_cpu_cpumask(struct filter_pred *pred, void *event)
+{
+ int cpu = raw_smp_processor_id();
+
+ return do_filter_scalar_cpumask(pred->op, cpu, pred->mask);
+}
+
+/* Filter predicate for cpumask field vs user-provided cpumask */
+static int filter_pred_cpumask(struct filter_pred *pred, void *event)
+{
+ u32 item = *(u32 *)(event + pred->offset);
+ int loc = item & 0xffff;
+ const struct cpumask *mask = (event + loc);
+ const struct cpumask *cmp = pred->mask;
+
+ return do_filter_cpumask(pred->op, mask, cmp);
+}
+
+/* Filter predicate for cpumask field vs user-provided scalar */
+static int filter_pred_cpumask_cpu(struct filter_pred *pred, void *event)
+{
+ u32 item = *(u32 *)(event + pred->offset);
+ int loc = item & 0xffff;
+ const struct cpumask *mask = (event + loc);
+ unsigned int cpu = pred->val;
+
+ return do_filter_cpumask_scalar(pred->op, mask, cpu);
+}
+
/* Filter predicate for COMM. */
static int filter_pred_comm(struct filter_pred *pred, void *event)
{
int cmp;
- cmp = pred->regex.match(current->comm, &pred->regex,
+ cmp = pred->regex->match(current->comm, pred->regex,
TASK_COMM_LEN);
return cmp ^ pred->not;
}
@@ -1004,7 +1123,7 @@ enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not)
static void filter_build_regex(struct filter_pred *pred)
{
- struct regex *r = &pred->regex;
+ struct regex *r = pred->regex;
char *search;
enum regex_type type = MATCH_FULL;
@@ -1169,7 +1288,7 @@ static void free_prog(struct event_filter *filter)
return;
for (i = 0; prog[i].pred; i++)
- kfree(prog[i].pred);
+ free_predicate(prog[i].pred);
kfree(prog);
}
@@ -1236,8 +1355,12 @@ static void filter_free_subsystem_filters(struct trace_subsystem_dir *dir,
int filter_assign_type(const char *type)
{
- if (strstr(type, "__data_loc") && strstr(type, "char"))
- return FILTER_DYN_STRING;
+ if (strstr(type, "__data_loc")) {
+ if (strstr(type, "char"))
+ return FILTER_DYN_STRING;
+ if (strstr(type, "cpumask_t"))
+ return FILTER_CPUMASK;
+ }
if (strstr(type, "__rel_loc") && strstr(type, "char"))
return FILTER_RDYN_STRING;
@@ -1313,24 +1436,32 @@ static int filter_pred_fn_call(struct filter_pred *pred, void *event)
switch (pred->fn_num) {
case FILTER_PRED_FN_64:
return filter_pred_64(pred, event);
+ case FILTER_PRED_FN_64_CPUMASK:
+ return filter_pred_64_cpumask(pred, event);
case FILTER_PRED_FN_S64:
return filter_pred_s64(pred, event);
case FILTER_PRED_FN_U64:
return filter_pred_u64(pred, event);
case FILTER_PRED_FN_32:
return filter_pred_32(pred, event);
+ case FILTER_PRED_FN_32_CPUMASK:
+ return filter_pred_32_cpumask(pred, event);
case FILTER_PRED_FN_S32:
return filter_pred_s32(pred, event);
case FILTER_PRED_FN_U32:
return filter_pred_u32(pred, event);
case FILTER_PRED_FN_16:
return filter_pred_16(pred, event);
+ case FILTER_PRED_FN_16_CPUMASK:
+ return filter_pred_16_cpumask(pred, event);
case FILTER_PRED_FN_S16:
return filter_pred_s16(pred, event);
case FILTER_PRED_FN_U16:
return filter_pred_u16(pred, event);
case FILTER_PRED_FN_8:
return filter_pred_8(pred, event);
+ case FILTER_PRED_FN_8_CPUMASK:
+ return filter_pred_8_cpumask(pred, event);
case FILTER_PRED_FN_S8:
return filter_pred_s8(pred, event);
case FILTER_PRED_FN_U8:
@@ -1349,6 +1480,12 @@ static int filter_pred_fn_call(struct filter_pred *pred, void *event)
return filter_pred_pchar(pred, event);
case FILTER_PRED_FN_CPU:
return filter_pred_cpu(pred, event);
+ case FILTER_PRED_FN_CPU_CPUMASK:
+ return filter_pred_cpu_cpumask(pred, event);
+ case FILTER_PRED_FN_CPUMASK:
+ return filter_pred_cpumask(pred, event);
+ case FILTER_PRED_FN_CPUMASK_CPU:
+ return filter_pred_cpumask_cpu(pred, event);
case FILTER_PRED_FN_FUNCTION:
return filter_pred_function(pred, event);
case FILTER_PRED_TEST_VISITED:
@@ -1553,9 +1690,130 @@ static int parse_pred(const char *str, void *data,
goto err_free;
}
- pred->regex.len = len;
- strncpy(pred->regex.pattern, str + s, len);
- pred->regex.pattern[len] = 0;
+ pred->regex = kzalloc(sizeof(*pred->regex), GFP_KERNEL);
+ if (!pred->regex)
+ goto err_mem;
+ pred->regex->len = len;
+ strncpy(pred->regex->pattern, str + s, len);
+ pred->regex->pattern[len] = 0;
+
+ } else if (!strncmp(str + i, "CPUS", 4)) {
+ unsigned int maskstart;
+ bool single;
+ char *tmp;
+
+ switch (field->filter_type) {
+ case FILTER_CPUMASK:
+ case FILTER_CPU:
+ case FILTER_OTHER:
+ break;
+ default:
+ parse_error(pe, FILT_ERR_ILLEGAL_FIELD_OP, pos + i);
+ goto err_free;
+ }
+
+ switch (op) {
+ case OP_EQ:
+ case OP_NE:
+ case OP_BAND:
+ break;
+ default:
+ parse_error(pe, FILT_ERR_ILLEGAL_FIELD_OP, pos + i);
+ goto err_free;
+ }
+
+ /* Skip CPUS */
+ i += 4;
+ if (str[i++] != '{') {
+ parse_error(pe, FILT_ERR_MISSING_BRACE_OPEN, pos + i);
+ goto err_free;
+ }
+ maskstart = i;
+
+ /* Walk the cpulist until closing } */
+ for (; str[i] && str[i] != '}'; i++)
+ ;
+
+ if (str[i] != '}') {
+ parse_error(pe, FILT_ERR_MISSING_BRACE_CLOSE, pos + i);
+ goto err_free;
+ }
+
+ if (maskstart == i) {
+ parse_error(pe, FILT_ERR_INVALID_CPULIST, pos + i);
+ goto err_free;
+ }
+
+ /* Copy the cpulist between { and } */
+ tmp = kmalloc((i - maskstart) + 1, GFP_KERNEL);
+ if (!tmp)
+ goto err_mem;
+
+ strscpy(tmp, str + maskstart, (i - maskstart) + 1);
+ pred->mask = kzalloc(cpumask_size(), GFP_KERNEL);
+ if (!pred->mask) {
+ kfree(tmp);
+ goto err_mem;
+ }
+
+ /* Now parse it */
+ if (cpulist_parse(tmp, pred->mask)) {
+ kfree(tmp);
+ parse_error(pe, FILT_ERR_INVALID_CPULIST, pos + i);
+ goto err_free;
+ }
+ kfree(tmp);
+
+ /* Move along */
+ i++;
+
+ /*
+ * Optimisation: if the user-provided mask has a weight of one
+ * then we can treat it as a scalar input.
+ */
+ single = cpumask_weight(pred->mask) == 1;
+ if (single) {
+ pred->val = cpumask_first(pred->mask);
+ kfree(pred->mask);
+ pred->mask = NULL;
+ }
+
+ if (field->filter_type == FILTER_CPUMASK) {
+ pred->fn_num = single ?
+ FILTER_PRED_FN_CPUMASK_CPU :
+ FILTER_PRED_FN_CPUMASK;
+ } else if (field->filter_type == FILTER_CPU) {
+ if (single) {
+ if (pred->op == OP_BAND)
+ pred->op = OP_EQ;
+
+ pred->fn_num = FILTER_PRED_FN_CPU;
+ } else {
+ pred->fn_num = FILTER_PRED_FN_CPU_CPUMASK;
+ }
+ } else if (single) {
+ if (pred->op == OP_BAND)
+ pred->op = OP_EQ;
+
+ pred->fn_num = select_comparison_fn(pred->op, field->size, false);
+ if (pred->op == OP_NE)
+ pred->not = 1;
+ } else {
+ switch (field->size) {
+ case 8:
+ pred->fn_num = FILTER_PRED_FN_64_CPUMASK;
+ break;
+ case 4:
+ pred->fn_num = FILTER_PRED_FN_32_CPUMASK;
+ break;
+ case 2:
+ pred->fn_num = FILTER_PRED_FN_16_CPUMASK;
+ break;
+ case 1:
+ pred->fn_num = FILTER_PRED_FN_8_CPUMASK;
+ break;
+ }
+ }
/* This is either a string, or an integer */
} else if (str[i] == '\'' || str[i] == '"') {
@@ -1597,9 +1855,12 @@ static int parse_pred(const char *str, void *data,
goto err_free;
}
- pred->regex.len = len;
- strncpy(pred->regex.pattern, str + s, len);
- pred->regex.pattern[len] = 0;
+ pred->regex = kzalloc(sizeof(*pred->regex), GFP_KERNEL);
+ if (!pred->regex)
+ goto err_mem;
+ pred->regex->len = len;
+ strncpy(pred->regex->pattern, str + s, len);
+ pred->regex->pattern[len] = 0;
filter_build_regex(pred);
@@ -1608,7 +1869,7 @@ static int parse_pred(const char *str, void *data,
} else if (field->filter_type == FILTER_STATIC_STRING) {
pred->fn_num = FILTER_PRED_FN_STRING;
- pred->regex.field_len = field->size;
+ pred->regex->field_len = field->size;
} else if (field->filter_type == FILTER_DYN_STRING) {
pred->fn_num = FILTER_PRED_FN_STRLOC;
@@ -1691,10 +1952,10 @@ static int parse_pred(const char *str, void *data,
return i;
err_free:
- kfree(pred);
+ free_predicate(pred);
return -EINVAL;
err_mem:
- kfree(pred);
+ free_predicate(pred);
return -ENOMEM;
}
@@ -2287,8 +2548,8 @@ static int ftrace_function_set_filter_pred(struct filter_pred *pred,
return ret;
return __ftrace_function_set_filter(pred->op == OP_EQ,
- pred->regex.pattern,
- pred->regex.len,
+ pred->regex->pattern,
+ pred->regex->len,
data);
}
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index b97d3ad832f1..d06938ae0717 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -6663,13 +6663,16 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
if (get_named_trigger_data(trigger_data))
goto enable;
- if (has_hist_vars(hist_data))
- save_hist_vars(hist_data);
-
ret = create_actions(hist_data);
if (ret)
goto out_unreg;
+ if (has_hist_vars(hist_data) || hist_data->n_var_refs) {
+ ret = save_hist_vars(hist_data);
+ if (ret)
+ goto out_unreg;
+ }
+
ret = tracing_map_init(hist_data->map);
if (ret)
goto out_unreg;
diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c
index d6b4935a78c0..abe805d471eb 100644
--- a/kernel/trace/trace_events_inject.c
+++ b/kernel/trace/trace_events_inject.c
@@ -217,7 +217,7 @@ static int parse_entry(char *str, struct trace_event_call *call, void **pentry)
char *addr = (char *)(unsigned long) val;
if (field->filter_type == FILTER_STATIC_STRING) {
- strlcpy(entry + field->offset, addr, field->size);
+ strscpy(entry + field->offset, addr, field->size);
} else if (field->filter_type == FILTER_DYN_STRING ||
field->filter_type == FILTER_RDYN_STRING) {
int str_len = strlen(addr) + 1;
@@ -232,7 +232,7 @@ static int parse_entry(char *str, struct trace_event_call *call, void **pentry)
}
entry = *pentry;
- strlcpy(entry + (entry_size - str_len), addr, str_len);
+ strscpy(entry + (entry_size - str_len), addr, str_len);
str_item = (u32 *)(entry + field->offset);
if (field->filter_type == FILTER_RDYN_STRING)
str_loc -= field->offset + field->size;
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index d6a70aff2410..9897d0bfcab7 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -127,7 +127,7 @@ static bool synth_event_match(const char *system, const char *event,
struct synth_trace_event {
struct trace_entry ent;
- u64 fields[];
+ union trace_synth_field fields[];
};
static int synth_event_define_fields(struct trace_event_call *call)
@@ -321,19 +321,19 @@ static const char *synth_field_fmt(char *type)
static void print_synth_event_num_val(struct trace_seq *s,
char *print_fmt, char *name,
- int size, u64 val, char *space)
+ int size, union trace_synth_field *val, char *space)
{
switch (size) {
case 1:
- trace_seq_printf(s, print_fmt, name, (u8)val, space);
+ trace_seq_printf(s, print_fmt, name, val->as_u8, space);
break;
case 2:
- trace_seq_printf(s, print_fmt, name, (u16)val, space);
+ trace_seq_printf(s, print_fmt, name, val->as_u16, space);
break;
case 4:
- trace_seq_printf(s, print_fmt, name, (u32)val, space);
+ trace_seq_printf(s, print_fmt, name, val->as_u32, space);
break;
default:
@@ -350,7 +350,7 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter,
struct trace_seq *s = &iter->seq;
struct synth_trace_event *entry;
struct synth_event *se;
- unsigned int i, n_u64;
+ unsigned int i, j, n_u64;
char print_fmt[32];
const char *fmt;
@@ -374,43 +374,28 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter,
/* parameter values */
if (se->fields[i]->is_string) {
if (se->fields[i]->is_dynamic) {
- u32 offset, data_offset;
- char *str_field;
-
- offset = (u32)entry->fields[n_u64];
- data_offset = offset & 0xffff;
-
- str_field = (char *)entry + data_offset;
+ union trace_synth_field *data = &entry->fields[n_u64];
trace_seq_printf(s, print_fmt, se->fields[i]->name,
STR_VAR_LEN_MAX,
- str_field,
+ (char *)entry + data->as_dynamic.offset,
i == se->n_fields - 1 ? "" : " ");
n_u64++;
} else {
trace_seq_printf(s, print_fmt, se->fields[i]->name,
STR_VAR_LEN_MAX,
- (char *)&entry->fields[n_u64],
+ (char *)&entry->fields[n_u64].as_u64,
i == se->n_fields - 1 ? "" : " ");
n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
}
} else if (se->fields[i]->is_stack) {
- u32 offset, data_offset, len;
- unsigned long *p, *end;
-
- offset = (u32)entry->fields[n_u64];
- data_offset = offset & 0xffff;
- len = offset >> 16;
-
- p = (void *)entry + data_offset;
- end = (void *)p + len - (sizeof(long) - 1);
+ union trace_synth_field *data = &entry->fields[n_u64];
+ unsigned long *p = (void *)entry + data->as_dynamic.offset;
trace_seq_printf(s, "%s=STACK:\n", se->fields[i]->name);
-
- for (; *p && p < end; p++)
- trace_seq_printf(s, "=> %pS\n", (void *)*p);
+ for (j = 1; j < data->as_dynamic.len / sizeof(long); j++)
+ trace_seq_printf(s, "=> %pS\n", (void *)p[j]);
n_u64++;
-
} else {
struct trace_print_flags __flags[] = {
__def_gfpflag_names, {-1, NULL} };
@@ -419,13 +404,13 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter,
print_synth_event_num_val(s, print_fmt,
se->fields[i]->name,
se->fields[i]->size,
- entry->fields[n_u64],
+ &entry->fields[n_u64],
space);
if (strcmp(se->fields[i]->type, "gfp_t") == 0) {
trace_seq_puts(s, " (");
trace_print_flags_seq(s, "|",
- entry->fields[n_u64],
+ entry->fields[n_u64].as_u64,
__flags);
trace_seq_putc(s, ')');
}
@@ -454,21 +439,16 @@ static unsigned int trace_string(struct synth_trace_event *entry,
int ret;
if (is_dynamic) {
- u32 data_offset;
+ union trace_synth_field *data = &entry->fields[*n_u64];
- data_offset = struct_size(entry, fields, event->n_u64);
- data_offset += data_size;
-
- len = fetch_store_strlen((unsigned long)str_val);
-
- data_offset |= len << 16;
- *(u32 *)&entry->fields[*n_u64] = data_offset;
+ data->as_dynamic.offset = struct_size(entry, fields, event->n_u64) + data_size;
+ data->as_dynamic.len = fetch_store_strlen((unsigned long)str_val);
ret = fetch_store_string((unsigned long)str_val, &entry->fields[*n_u64], entry);
(*n_u64)++;
} else {
- str_field = (char *)&entry->fields[*n_u64];
+ str_field = (char *)&entry->fields[*n_u64].as_u64;
#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
if ((unsigned long)str_val < TASK_SIZE)
@@ -492,6 +472,7 @@ static unsigned int trace_stack(struct synth_trace_event *entry,
unsigned int data_size,
unsigned int *n_u64)
{
+ union trace_synth_field *data = &entry->fields[*n_u64];
unsigned int len;
u32 data_offset;
void *data_loc;
@@ -504,10 +485,6 @@ static unsigned int trace_stack(struct synth_trace_event *entry,
break;
}
- /* Include the zero'd element if it fits */
- if (len < HIST_STACKTRACE_DEPTH)
- len++;
-
len *= sizeof(long);
/* Find the dynamic section to copy the stack into. */
@@ -515,8 +492,9 @@ static unsigned int trace_stack(struct synth_trace_event *entry,
memcpy(data_loc, stack, len);
/* Fill in the field that holds the offset/len combo */
- data_offset |= len << 16;
- *(u32 *)&entry->fields[*n_u64] = data_offset;
+
+ data->as_dynamic.offset = data_offset;
+ data->as_dynamic.len = len;
(*n_u64)++;
@@ -550,7 +528,8 @@ static notrace void trace_event_raw_event_synth(void *__data,
str_val = (char *)(long)var_ref_vals[val_idx];
if (event->dynamic_fields[i]->is_stack) {
- len = *((unsigned long *)str_val);
+ /* reserve one extra element for size */
+ len = *((unsigned long *)str_val) + 1;
len *= sizeof(unsigned long);
} else {
len = fetch_store_strlen((unsigned long)str_val);
@@ -592,19 +571,19 @@ static notrace void trace_event_raw_event_synth(void *__data,
switch (field->size) {
case 1:
- *(u8 *)&entry->fields[n_u64] = (u8)val;
+ entry->fields[n_u64].as_u8 = (u8)val;
break;
case 2:
- *(u16 *)&entry->fields[n_u64] = (u16)val;
+ entry->fields[n_u64].as_u16 = (u16)val;
break;
case 4:
- *(u32 *)&entry->fields[n_u64] = (u32)val;
+ entry->fields[n_u64].as_u32 = (u32)val;
break;
default:
- entry->fields[n_u64] = val;
+ entry->fields[n_u64].as_u64 = val;
break;
}
n_u64++;
@@ -1230,6 +1209,7 @@ EXPORT_SYMBOL_GPL(__synth_event_gen_cmd_start);
* synth_event_gen_cmd_array_start - Start synthetic event command from an array
* @cmd: A pointer to the dynevent_cmd struct representing the new event
* @name: The name of the synthetic event
+ * @mod: The module creating the event, NULL if not created from a module
* @fields: An array of type/name field descriptions
* @n_fields: The number of field descriptions contained in the fields array
*
@@ -1790,19 +1770,19 @@ int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...)
switch (field->size) {
case 1:
- *(u8 *)&state.entry->fields[n_u64] = (u8)val;
+ state.entry->fields[n_u64].as_u8 = (u8)val;
break;
case 2:
- *(u16 *)&state.entry->fields[n_u64] = (u16)val;
+ state.entry->fields[n_u64].as_u16 = (u16)val;
break;
case 4:
- *(u32 *)&state.entry->fields[n_u64] = (u32)val;
+ state.entry->fields[n_u64].as_u32 = (u32)val;
break;
default:
- state.entry->fields[n_u64] = val;
+ state.entry->fields[n_u64].as_u64 = val;
break;
}
n_u64++;
@@ -1883,19 +1863,19 @@ int synth_event_trace_array(struct trace_event_file *file, u64 *vals,
switch (field->size) {
case 1:
- *(u8 *)&state.entry->fields[n_u64] = (u8)val;
+ state.entry->fields[n_u64].as_u8 = (u8)val;
break;
case 2:
- *(u16 *)&state.entry->fields[n_u64] = (u16)val;
+ state.entry->fields[n_u64].as_u16 = (u16)val;
break;
case 4:
- *(u32 *)&state.entry->fields[n_u64] = (u32)val;
+ state.entry->fields[n_u64].as_u32 = (u32)val;
break;
default:
- state.entry->fields[n_u64] = val;
+ state.entry->fields[n_u64].as_u64 = val;
break;
}
n_u64++;
@@ -2030,19 +2010,19 @@ static int __synth_event_add_val(const char *field_name, u64 val,
} else {
switch (field->size) {
case 1:
- *(u8 *)&trace_state->entry->fields[field->offset] = (u8)val;
+ trace_state->entry->fields[field->offset].as_u8 = (u8)val;
break;
case 2:
- *(u16 *)&trace_state->entry->fields[field->offset] = (u16)val;
+ trace_state->entry->fields[field->offset].as_u16 = (u16)val;
break;
case 4:
- *(u32 *)&trace_state->entry->fields[field->offset] = (u32)val;
+ trace_state->entry->fields[field->offset].as_u32 = (u32)val;
break;
default:
- trace_state->entry->fields[field->offset] = val;
+ trace_state->entry->fields[field->offset].as_u64 = val;
break;
}
}
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index e535959939d3..46439e3bcec4 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -31,7 +31,9 @@ void trigger_data_free(struct event_trigger_data *data)
/**
* event_triggers_call - Call triggers associated with a trace event
* @file: The trace_event_file associated with the event
+ * @buffer: The ring buffer that the event is being written to
* @rec: The trace entry for the event, NULL for unconditional invocation
+ * @event: The event meta data in the ring buffer
*
* For each trigger associated with an event, invoke the trigger
* function registered with the associated trigger command. If rec is
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 8df0550415e7..6f046650e527 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -498,7 +498,7 @@ static int user_event_enabler_write(struct user_event_mm *mm,
return -EBUSY;
ret = pin_user_pages_remote(mm->mm, uaddr, 1, FOLL_WRITE | FOLL_NOFAULT,
- &page, NULL, NULL);
+ &page, NULL);
if (unlikely(ret <= 0)) {
if (!fixup_fault)
@@ -1317,6 +1317,9 @@ static int user_field_set_string(struct ftrace_event_field *field,
pos += snprintf(buf + pos, LEN_OR_ZERO, " ");
pos += snprintf(buf + pos, LEN_OR_ZERO, "%s", field->name);
+ if (str_has_prefix(field->type, "struct "))
+ pos += snprintf(buf + pos, LEN_OR_ZERO, " %d", field->size);
+
if (colon)
pos += snprintf(buf + pos, LEN_OR_ZERO, ";");
@@ -1325,14 +1328,14 @@ static int user_field_set_string(struct ftrace_event_field *field,
static int user_event_set_print_fmt(struct user_event *user, char *buf, int len)
{
- struct ftrace_event_field *field, *next;
+ struct ftrace_event_field *field;
struct list_head *head = &user->fields;
int pos = 0, depth = 0;
const char *str_func;
pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
- list_for_each_entry_safe_reverse(field, next, head, link) {
+ list_for_each_entry_reverse(field, head, link) {
if (depth != 0)
pos += snprintf(buf + pos, LEN_OR_ZERO, " ");
@@ -1344,7 +1347,7 @@ static int user_event_set_print_fmt(struct user_event *user, char *buf, int len)
pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
- list_for_each_entry_safe_reverse(field, next, head, link) {
+ list_for_each_entry_reverse(field, head, link) {
if (user_field_is_dyn_string(field->type, &str_func))
pos += snprintf(buf + pos, LEN_OR_ZERO,
", %s(%s)", str_func, field->name);
@@ -1729,7 +1732,7 @@ static int user_event_create(const char *raw_command)
static int user_event_show(struct seq_file *m, struct dyn_event *ev)
{
struct user_event *user = container_of(ev, struct user_event, devent);
- struct ftrace_event_field *field, *next;
+ struct ftrace_event_field *field;
struct list_head *head;
int depth = 0;
@@ -1737,7 +1740,7 @@ static int user_event_show(struct seq_file *m, struct dyn_event *ev)
head = trace_get_fields(&user->call);
- list_for_each_entry_safe_reverse(field, next, head, link) {
+ list_for_each_entry_reverse(field, head, link) {
if (depth == 0)
seq_puts(m, " ");
else
@@ -1813,13 +1816,14 @@ out:
static bool user_fields_match(struct user_event *user, int argc,
const char **argv)
{
- struct ftrace_event_field *field, *next;
+ struct ftrace_event_field *field;
struct list_head *head = &user->fields;
int i = 0;
- list_for_each_entry_safe_reverse(field, next, head, link)
+ list_for_each_entry_reverse(field, head, link) {
if (!user_field_match(field, argc, argv, &i))
return false;
+ }
if (i != argc)
return false;
@@ -2096,7 +2100,8 @@ static ssize_t user_events_write_core(struct file *file, struct iov_iter *i)
if (unlikely(faulted))
return -EFAULT;
- }
+ } else
+ return -EBADF;
return ret;
}
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 58f3946081e2..1698fc22afa0 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -51,6 +51,9 @@ static int ftrace_event_register(struct trace_event_call *call,
#undef __array
#define __array(type, item, size) type item[size];
+#undef __stack_array
+#define __stack_array(type, item, size, field) __array(type, item, size)
+
#undef __array_desc
#define __array_desc(type, container, item, size) type item[size];
@@ -114,6 +117,9 @@ static void __always_unused ____ftrace_check_##name(void) \
is_signed_type(_type), .filter_type = FILTER_OTHER, \
.len = _len },
+#undef __stack_array
+#define __stack_array(_type, _item, _len, _field) __array(_type, _item, _len)
+
#undef __array_desc
#define __array_desc(_type, _container, _item, _len) __array(_type, _item, _len)
@@ -149,6 +155,9 @@ static struct trace_event_fields ftrace_event_fields_##name[] = { \
#undef __array
#define __array(type, item, len)
+#undef __stack_array
+#define __stack_array(type, item, len, field)
+
#undef __array_desc
#define __array_desc(type, container, item, len)
diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
new file mode 100644
index 000000000000..8bfe23af9c73
--- /dev/null
+++ b/kernel/trace/trace_fprobe.c
@@ -0,0 +1,1230 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Fprobe-based tracing events
+ * Copyright (C) 2022 Google LLC.
+ */
+#define pr_fmt(fmt) "trace_fprobe: " fmt
+
+#include <linux/fprobe.h>
+#include <linux/module.h>
+#include <linux/rculist.h>
+#include <linux/security.h>
+#include <linux/tracepoint.h>
+#include <linux/uaccess.h>
+
+#include "trace_dynevent.h"
+#include "trace_probe.h"
+#include "trace_probe_kernel.h"
+#include "trace_probe_tmpl.h"
+
+#define FPROBE_EVENT_SYSTEM "fprobes"
+#define TRACEPOINT_EVENT_SYSTEM "tracepoints"
+#define RETHOOK_MAXACTIVE_MAX 4096
+
+static int trace_fprobe_create(const char *raw_command);
+static int trace_fprobe_show(struct seq_file *m, struct dyn_event *ev);
+static int trace_fprobe_release(struct dyn_event *ev);
+static bool trace_fprobe_is_busy(struct dyn_event *ev);
+static bool trace_fprobe_match(const char *system, const char *event,
+ int argc, const char **argv, struct dyn_event *ev);
+
+static struct dyn_event_operations trace_fprobe_ops = {
+ .create = trace_fprobe_create,
+ .show = trace_fprobe_show,
+ .is_busy = trace_fprobe_is_busy,
+ .free = trace_fprobe_release,
+ .match = trace_fprobe_match,
+};
+
+/*
+ * Fprobe event core functions
+ */
+struct trace_fprobe {
+ struct dyn_event devent;
+ struct fprobe fp;
+ const char *symbol;
+ struct tracepoint *tpoint;
+ struct module *mod;
+ struct trace_probe tp;
+};
+
+static bool is_trace_fprobe(struct dyn_event *ev)
+{
+ return ev->ops == &trace_fprobe_ops;
+}
+
+static struct trace_fprobe *to_trace_fprobe(struct dyn_event *ev)
+{
+ return container_of(ev, struct trace_fprobe, devent);
+}
+
+/**
+ * for_each_trace_fprobe - iterate over the trace_fprobe list
+ * @pos: the struct trace_fprobe * for each entry
+ * @dpos: the struct dyn_event * to use as a loop cursor
+ */
+#define for_each_trace_fprobe(pos, dpos) \
+ for_each_dyn_event(dpos) \
+ if (is_trace_fprobe(dpos) && (pos = to_trace_fprobe(dpos)))
+
+static bool trace_fprobe_is_return(struct trace_fprobe *tf)
+{
+ return tf->fp.exit_handler != NULL;
+}
+
+static bool trace_fprobe_is_tracepoint(struct trace_fprobe *tf)
+{
+ return tf->tpoint != NULL;
+}
+
+static const char *trace_fprobe_symbol(struct trace_fprobe *tf)
+{
+ return tf->symbol ? tf->symbol : "unknown";
+}
+
+static bool trace_fprobe_is_busy(struct dyn_event *ev)
+{
+ struct trace_fprobe *tf = to_trace_fprobe(ev);
+
+ return trace_probe_is_enabled(&tf->tp);
+}
+
+static bool trace_fprobe_match_command_head(struct trace_fprobe *tf,
+ int argc, const char **argv)
+{
+ char buf[MAX_ARGSTR_LEN + 1];
+
+ if (!argc)
+ return true;
+
+ snprintf(buf, sizeof(buf), "%s", trace_fprobe_symbol(tf));
+ if (strcmp(buf, argv[0]))
+ return false;
+ argc--; argv++;
+
+ return trace_probe_match_command_args(&tf->tp, argc, argv);
+}
+
+static bool trace_fprobe_match(const char *system, const char *event,
+ int argc, const char **argv, struct dyn_event *ev)
+{
+ struct trace_fprobe *tf = to_trace_fprobe(ev);
+
+ if (event[0] != '\0' && strcmp(trace_probe_name(&tf->tp), event))
+ return false;
+
+ if (system && strcmp(trace_probe_group_name(&tf->tp), system))
+ return false;
+
+ return trace_fprobe_match_command_head(tf, argc, argv);
+}
+
+static bool trace_fprobe_is_registered(struct trace_fprobe *tf)
+{
+ return fprobe_is_registered(&tf->fp);
+}
+
+/*
+ * Note that we don't verify the fetch_insn code, since it does not come
+ * from user space.
+ */
+static int
+process_fetch_insn(struct fetch_insn *code, void *rec, void *dest,
+ void *base)
+{
+ struct pt_regs *regs = rec;
+ unsigned long val;
+ int ret;
+
+retry:
+ /* 1st stage: get value from context */
+ switch (code->op) {
+ case FETCH_OP_STACK:
+ val = regs_get_kernel_stack_nth(regs, code->param);
+ break;
+ case FETCH_OP_STACKP:
+ val = kernel_stack_pointer(regs);
+ break;
+ case FETCH_OP_RETVAL:
+ val = regs_return_value(regs);
+ break;
+#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
+ case FETCH_OP_ARG:
+ val = regs_get_kernel_argument(regs, code->param);
+ break;
+#endif
+ case FETCH_NOP_SYMBOL: /* Ignore a place holder */
+ code++;
+ goto retry;
+ default:
+ ret = process_common_fetch_insn(code, &val);
+ if (ret < 0)
+ return ret;
+ }
+ code++;
+
+ return process_fetch_insn_bottom(code, val, dest, base);
+}
+NOKPROBE_SYMBOL(process_fetch_insn)
+
+/* function entry handler */
+static nokprobe_inline void
+__fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip,
+ struct pt_regs *regs,
+ struct trace_event_file *trace_file)
+{
+ struct fentry_trace_entry_head *entry;
+ struct trace_event_call *call = trace_probe_event_call(&tf->tp);
+ struct trace_event_buffer fbuffer;
+ int dsize;
+
+ if (WARN_ON_ONCE(call != trace_file->event_call))
+ return;
+
+ if (trace_trigger_soft_disabled(trace_file))
+ return;
+
+ dsize = __get_data_size(&tf->tp, regs);
+
+ entry = trace_event_buffer_reserve(&fbuffer, trace_file,
+ sizeof(*entry) + tf->tp.size + dsize);
+ if (!entry)
+ return;
+
+ fbuffer.regs = regs;
+ entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event);
+ entry->ip = entry_ip;
+ store_trace_args(&entry[1], &tf->tp, regs, sizeof(*entry), dsize);
+
+ trace_event_buffer_commit(&fbuffer);
+}
+
+static void
+fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip,
+ struct pt_regs *regs)
+{
+ struct event_file_link *link;
+
+ trace_probe_for_each_link_rcu(link, &tf->tp)
+ __fentry_trace_func(tf, entry_ip, regs, link->file);
+}
+NOKPROBE_SYMBOL(fentry_trace_func);
+
+/* Kretprobe handler */
+static nokprobe_inline void
+__fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip,
+ unsigned long ret_ip, struct pt_regs *regs,
+ struct trace_event_file *trace_file)
+{
+ struct fexit_trace_entry_head *entry;
+ struct trace_event_buffer fbuffer;
+ struct trace_event_call *call = trace_probe_event_call(&tf->tp);
+ int dsize;
+
+ if (WARN_ON_ONCE(call != trace_file->event_call))
+ return;
+
+ if (trace_trigger_soft_disabled(trace_file))
+ return;
+
+ dsize = __get_data_size(&tf->tp, regs);
+
+ entry = trace_event_buffer_reserve(&fbuffer, trace_file,
+ sizeof(*entry) + tf->tp.size + dsize);
+ if (!entry)
+ return;
+
+ fbuffer.regs = regs;
+ entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event);
+ entry->func = entry_ip;
+ entry->ret_ip = ret_ip;
+ store_trace_args(&entry[1], &tf->tp, regs, sizeof(*entry), dsize);
+
+ trace_event_buffer_commit(&fbuffer);
+}
+
+static void
+fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip,
+ unsigned long ret_ip, struct pt_regs *regs)
+{
+ struct event_file_link *link;
+
+ trace_probe_for_each_link_rcu(link, &tf->tp)
+ __fexit_trace_func(tf, entry_ip, ret_ip, regs, link->file);
+}
+NOKPROBE_SYMBOL(fexit_trace_func);
+
+#ifdef CONFIG_PERF_EVENTS
+
+static int fentry_perf_func(struct trace_fprobe *tf, unsigned long entry_ip,
+ struct pt_regs *regs)
+{
+ struct trace_event_call *call = trace_probe_event_call(&tf->tp);
+ struct fentry_trace_entry_head *entry;
+ struct hlist_head *head;
+ int size, __size, dsize;
+ int rctx;
+
+ head = this_cpu_ptr(call->perf_events);
+ if (hlist_empty(head))
+ return 0;
+
+ dsize = __get_data_size(&tf->tp, regs);
+ __size = sizeof(*entry) + tf->tp.size + dsize;
+ size = ALIGN(__size + sizeof(u32), sizeof(u64));
+ size -= sizeof(u32);
+
+ entry = perf_trace_buf_alloc(size, NULL, &rctx);
+ if (!entry)
+ return 0;
+
+ entry->ip = entry_ip;
+ memset(&entry[1], 0, dsize);
+ store_trace_args(&entry[1], &tf->tp, regs, sizeof(*entry), dsize);
+ perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
+ head, NULL);
+ return 0;
+}
+NOKPROBE_SYMBOL(fentry_perf_func);
+
+static void
+fexit_perf_func(struct trace_fprobe *tf, unsigned long entry_ip,
+ unsigned long ret_ip, struct pt_regs *regs)
+{
+ struct trace_event_call *call = trace_probe_event_call(&tf->tp);
+ struct fexit_trace_entry_head *entry;
+ struct hlist_head *head;
+ int size, __size, dsize;
+ int rctx;
+
+ head = this_cpu_ptr(call->perf_events);
+ if (hlist_empty(head))
+ return;
+
+ dsize = __get_data_size(&tf->tp, regs);
+ __size = sizeof(*entry) + tf->tp.size + dsize;
+ size = ALIGN(__size + sizeof(u32), sizeof(u64));
+ size -= sizeof(u32);
+
+ entry = perf_trace_buf_alloc(size, NULL, &rctx);
+ if (!entry)
+ return;
+
+ entry->func = entry_ip;
+ entry->ret_ip = ret_ip;
+ store_trace_args(&entry[1], &tf->tp, regs, sizeof(*entry), dsize);
+ perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
+ head, NULL);
+}
+NOKPROBE_SYMBOL(fexit_perf_func);
+#endif /* CONFIG_PERF_EVENTS */
+
+static int fentry_dispatcher(struct fprobe *fp, unsigned long entry_ip,
+ unsigned long ret_ip, struct pt_regs *regs,
+ void *entry_data)
+{
+ struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp);
+ int ret = 0;
+
+ if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE))
+ fentry_trace_func(tf, entry_ip, regs);
+#ifdef CONFIG_PERF_EVENTS
+ if (trace_probe_test_flag(&tf->tp, TP_FLAG_PROFILE))
+ ret = fentry_perf_func(tf, entry_ip, regs);
+#endif
+ return ret;
+}
+NOKPROBE_SYMBOL(fentry_dispatcher);
+
+static void fexit_dispatcher(struct fprobe *fp, unsigned long entry_ip,
+ unsigned long ret_ip, struct pt_regs *regs,
+ void *entry_data)
+{
+ struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp);
+
+ if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE))
+ fexit_trace_func(tf, entry_ip, ret_ip, regs);
+#ifdef CONFIG_PERF_EVENTS
+ if (trace_probe_test_flag(&tf->tp, TP_FLAG_PROFILE))
+ fexit_perf_func(tf, entry_ip, ret_ip, regs);
+#endif
+}
+NOKPROBE_SYMBOL(fexit_dispatcher);
+
+static void free_trace_fprobe(struct trace_fprobe *tf)
+{
+ if (tf) {
+ trace_probe_cleanup(&tf->tp);
+ kfree(tf->symbol);
+ kfree(tf);
+ }
+}
+
+/*
+ * Allocate new trace_probe and initialize it (including fprobe).
+ */
+static struct trace_fprobe *alloc_trace_fprobe(const char *group,
+ const char *event,
+ const char *symbol,
+ struct tracepoint *tpoint,
+ int maxactive,
+ int nargs, bool is_return)
+{
+ struct trace_fprobe *tf;
+ int ret = -ENOMEM;
+
+ tf = kzalloc(struct_size(tf, tp.args, nargs), GFP_KERNEL);
+ if (!tf)
+ return ERR_PTR(ret);
+
+ tf->symbol = kstrdup(symbol, GFP_KERNEL);
+ if (!tf->symbol)
+ goto error;
+
+ if (is_return)
+ tf->fp.exit_handler = fexit_dispatcher;
+ else
+ tf->fp.entry_handler = fentry_dispatcher;
+
+ tf->tpoint = tpoint;
+ tf->fp.nr_maxactive = maxactive;
+
+ ret = trace_probe_init(&tf->tp, event, group, false);
+ if (ret < 0)
+ goto error;
+
+ dyn_event_init(&tf->devent, &trace_fprobe_ops);
+ return tf;
+error:
+ free_trace_fprobe(tf);
+ return ERR_PTR(ret);
+}
+
+static struct trace_fprobe *find_trace_fprobe(const char *event,
+ const char *group)
+{
+ struct dyn_event *pos;
+ struct trace_fprobe *tf;
+
+ for_each_trace_fprobe(tf, pos)
+ if (strcmp(trace_probe_name(&tf->tp), event) == 0 &&
+ strcmp(trace_probe_group_name(&tf->tp), group) == 0)
+ return tf;
+ return NULL;
+}
+
+static inline int __enable_trace_fprobe(struct trace_fprobe *tf)
+{
+ if (trace_fprobe_is_registered(tf))
+ enable_fprobe(&tf->fp);
+
+ return 0;
+}
+
+static void __disable_trace_fprobe(struct trace_probe *tp)
+{
+ struct trace_fprobe *tf;
+
+ list_for_each_entry(tf, trace_probe_probe_list(tp), tp.list) {
+ if (!trace_fprobe_is_registered(tf))
+ continue;
+ disable_fprobe(&tf->fp);
+ }
+}
+
+/*
+ * Enable trace_probe
+ * if the file is NULL, enable "perf" handler, or enable "trace" handler.
+ */
+static int enable_trace_fprobe(struct trace_event_call *call,
+ struct trace_event_file *file)
+{
+ struct trace_probe *tp;
+ struct trace_fprobe *tf;
+ bool enabled;
+ int ret = 0;
+
+ tp = trace_probe_primary_from_call(call);
+ if (WARN_ON_ONCE(!tp))
+ return -ENODEV;
+ enabled = trace_probe_is_enabled(tp);
+
+ /* This also changes "enabled" state */
+ if (file) {
+ ret = trace_probe_add_file(tp, file);
+ if (ret)
+ return ret;
+ } else
+ trace_probe_set_flag(tp, TP_FLAG_PROFILE);
+
+ if (!enabled) {
+ list_for_each_entry(tf, trace_probe_probe_list(tp), tp.list) {
+ /* TODO: check the fprobe is gone */
+ __enable_trace_fprobe(tf);
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * Disable trace_probe
+ * if the file is NULL, disable "perf" handler, or disable "trace" handler.
+ */
+static int disable_trace_fprobe(struct trace_event_call *call,
+ struct trace_event_file *file)
+{
+ struct trace_probe *tp;
+
+ tp = trace_probe_primary_from_call(call);
+ if (WARN_ON_ONCE(!tp))
+ return -ENODEV;
+
+ if (file) {
+ if (!trace_probe_get_file_link(tp, file))
+ return -ENOENT;
+ if (!trace_probe_has_single_file(tp))
+ goto out;
+ trace_probe_clear_flag(tp, TP_FLAG_TRACE);
+ } else
+ trace_probe_clear_flag(tp, TP_FLAG_PROFILE);
+
+ if (!trace_probe_is_enabled(tp))
+ __disable_trace_fprobe(tp);
+
+ out:
+ if (file)
+ /*
+ * Synchronization is done in below function. For perf event,
+ * file == NULL and perf_trace_event_unreg() calls
+ * tracepoint_synchronize_unregister() to ensure synchronize
+ * event. We don't need to care about it.
+ */
+ trace_probe_remove_file(tp, file);
+
+ return 0;
+}
+
+/* Event entry printers */
+static enum print_line_t
+print_fentry_event(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct fentry_trace_entry_head *field;
+ struct trace_seq *s = &iter->seq;
+ struct trace_probe *tp;
+
+ field = (struct fentry_trace_entry_head *)iter->ent;
+ tp = trace_probe_primary_from_call(
+ container_of(event, struct trace_event_call, event));
+ if (WARN_ON_ONCE(!tp))
+ goto out;
+
+ trace_seq_printf(s, "%s: (", trace_probe_name(tp));
+
+ if (!seq_print_ip_sym(s, field->ip, flags | TRACE_ITER_SYM_OFFSET))
+ goto out;
+
+ trace_seq_putc(s, ')');
+
+ if (trace_probe_print_args(s, tp->args, tp->nr_args,
+ (u8 *)&field[1], field) < 0)
+ goto out;
+
+ trace_seq_putc(s, '\n');
+ out:
+ return trace_handle_return(s);
+}
+
+static enum print_line_t
+print_fexit_event(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct fexit_trace_entry_head *field;
+ struct trace_seq *s = &iter->seq;
+ struct trace_probe *tp;
+
+ field = (struct fexit_trace_entry_head *)iter->ent;
+ tp = trace_probe_primary_from_call(
+ container_of(event, struct trace_event_call, event));
+ if (WARN_ON_ONCE(!tp))
+ goto out;
+
+ trace_seq_printf(s, "%s: (", trace_probe_name(tp));
+
+ if (!seq_print_ip_sym(s, field->ret_ip, flags | TRACE_ITER_SYM_OFFSET))
+ goto out;
+
+ trace_seq_puts(s, " <- ");
+
+ if (!seq_print_ip_sym(s, field->func, flags & ~TRACE_ITER_SYM_OFFSET))
+ goto out;
+
+ trace_seq_putc(s, ')');
+
+ if (trace_probe_print_args(s, tp->args, tp->nr_args,
+ (u8 *)&field[1], field) < 0)
+ goto out;
+
+ trace_seq_putc(s, '\n');
+
+ out:
+ return trace_handle_return(s);
+}
+
+static int fentry_event_define_fields(struct trace_event_call *event_call)
+{
+ int ret;
+ struct fentry_trace_entry_head field;
+ struct trace_probe *tp;
+
+ tp = trace_probe_primary_from_call(event_call);
+ if (WARN_ON_ONCE(!tp))
+ return -ENOENT;
+
+ DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
+
+ return traceprobe_define_arg_fields(event_call, sizeof(field), tp);
+}
+
+static int fexit_event_define_fields(struct trace_event_call *event_call)
+{
+ int ret;
+ struct fexit_trace_entry_head field;
+ struct trace_probe *tp;
+
+ tp = trace_probe_primary_from_call(event_call);
+ if (WARN_ON_ONCE(!tp))
+ return -ENOENT;
+
+ DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
+ DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);
+
+ return traceprobe_define_arg_fields(event_call, sizeof(field), tp);
+}
+
+static struct trace_event_functions fentry_funcs = {
+ .trace = print_fentry_event
+};
+
+static struct trace_event_functions fexit_funcs = {
+ .trace = print_fexit_event
+};
+
+static struct trace_event_fields fentry_fields_array[] = {
+ { .type = TRACE_FUNCTION_TYPE,
+ .define_fields = fentry_event_define_fields },
+ {}
+};
+
+static struct trace_event_fields fexit_fields_array[] = {
+ { .type = TRACE_FUNCTION_TYPE,
+ .define_fields = fexit_event_define_fields },
+ {}
+};
+
+static int fprobe_register(struct trace_event_call *event,
+ enum trace_reg type, void *data);
+
+static inline void init_trace_event_call(struct trace_fprobe *tf)
+{
+ struct trace_event_call *call = trace_probe_event_call(&tf->tp);
+
+ if (trace_fprobe_is_return(tf)) {
+ call->event.funcs = &fexit_funcs;
+ call->class->fields_array = fexit_fields_array;
+ } else {
+ call->event.funcs = &fentry_funcs;
+ call->class->fields_array = fentry_fields_array;
+ }
+
+ call->flags = TRACE_EVENT_FL_FPROBE;
+ call->class->reg = fprobe_register;
+}
+
+static int register_fprobe_event(struct trace_fprobe *tf)
+{
+ init_trace_event_call(tf);
+
+ return trace_probe_register_event_call(&tf->tp);
+}
+
+static int unregister_fprobe_event(struct trace_fprobe *tf)
+{
+ return trace_probe_unregister_event_call(&tf->tp);
+}
+
+/* Internal register function - just handle fprobe and flags */
+static int __register_trace_fprobe(struct trace_fprobe *tf)
+{
+ int i, ret;
+
+ /* Should we need new LOCKDOWN flag for fprobe? */
+ ret = security_locked_down(LOCKDOWN_KPROBES);
+ if (ret)
+ return ret;
+
+ if (trace_fprobe_is_registered(tf))
+ return -EINVAL;
+
+ for (i = 0; i < tf->tp.nr_args; i++) {
+ ret = traceprobe_update_arg(&tf->tp.args[i]);
+ if (ret)
+ return ret;
+ }
+
+ /* Set/clear disabled flag according to tp->flag */
+ if (trace_probe_is_enabled(&tf->tp))
+ tf->fp.flags &= ~FPROBE_FL_DISABLED;
+ else
+ tf->fp.flags |= FPROBE_FL_DISABLED;
+
+ if (trace_fprobe_is_tracepoint(tf)) {
+ struct tracepoint *tpoint = tf->tpoint;
+ unsigned long ip = (unsigned long)tpoint->probestub;
+ /*
+ * Here, we do 2 steps to enable fprobe on a tracepoint.
+ * At first, put __probestub_##TP function on the tracepoint
+ * and put a fprobe on the stub function.
+ */
+ ret = tracepoint_probe_register_prio_may_exist(tpoint,
+ tpoint->probestub, NULL, 0);
+ if (ret < 0)
+ return ret;
+ return register_fprobe_ips(&tf->fp, &ip, 1);
+ }
+
+ /* TODO: handle filter, nofilter or symbol list */
+ return register_fprobe(&tf->fp, tf->symbol, NULL);
+}
+
+/* Internal unregister function - just handle fprobe and flags */
+static void __unregister_trace_fprobe(struct trace_fprobe *tf)
+{
+ if (trace_fprobe_is_registered(tf)) {
+ unregister_fprobe(&tf->fp);
+ memset(&tf->fp, 0, sizeof(tf->fp));
+ if (trace_fprobe_is_tracepoint(tf)) {
+ tracepoint_probe_unregister(tf->tpoint,
+ tf->tpoint->probestub, NULL);
+ tf->tpoint = NULL;
+ tf->mod = NULL;
+ }
+ }
+}
+
+/* TODO: make this trace_*probe common function */
+/* Unregister a trace_probe and probe_event */
+static int unregister_trace_fprobe(struct trace_fprobe *tf)
+{
+ /* If other probes are on the event, just unregister fprobe */
+ if (trace_probe_has_sibling(&tf->tp))
+ goto unreg;
+
+ /* Enabled event can not be unregistered */
+ if (trace_probe_is_enabled(&tf->tp))
+ return -EBUSY;
+
+ /* If there's a reference to the dynamic event */
+ if (trace_event_dyn_busy(trace_probe_event_call(&tf->tp)))
+ return -EBUSY;
+
+ /* Will fail if probe is being used by ftrace or perf */
+ if (unregister_fprobe_event(tf))
+ return -EBUSY;
+
+unreg:
+ __unregister_trace_fprobe(tf);
+ dyn_event_remove(&tf->devent);
+ trace_probe_unlink(&tf->tp);
+
+ return 0;
+}
+
+static bool trace_fprobe_has_same_fprobe(struct trace_fprobe *orig,
+ struct trace_fprobe *comp)
+{
+ struct trace_probe_event *tpe = orig->tp.event;
+ int i;
+
+ list_for_each_entry(orig, &tpe->probes, tp.list) {
+ if (strcmp(trace_fprobe_symbol(orig),
+ trace_fprobe_symbol(comp)))
+ continue;
+
+ /*
+ * trace_probe_compare_arg_type() ensured that nr_args and
+ * each argument name and type are same. Let's compare comm.
+ */
+ for (i = 0; i < orig->tp.nr_args; i++) {
+ if (strcmp(orig->tp.args[i].comm,
+ comp->tp.args[i].comm))
+ break;
+ }
+
+ if (i == orig->tp.nr_args)
+ return true;
+ }
+
+ return false;
+}
+
+static int append_trace_fprobe(struct trace_fprobe *tf, struct trace_fprobe *to)
+{
+ int ret;
+
+ if (trace_fprobe_is_return(tf) != trace_fprobe_is_return(to) ||
+ trace_fprobe_is_tracepoint(tf) != trace_fprobe_is_tracepoint(to)) {
+ trace_probe_log_set_index(0);
+ trace_probe_log_err(0, DIFF_PROBE_TYPE);
+ return -EEXIST;
+ }
+ ret = trace_probe_compare_arg_type(&tf->tp, &to->tp);
+ if (ret) {
+ /* Note that argument starts index = 2 */
+ trace_probe_log_set_index(ret + 1);
+ trace_probe_log_err(0, DIFF_ARG_TYPE);
+ return -EEXIST;
+ }
+ if (trace_fprobe_has_same_fprobe(to, tf)) {
+ trace_probe_log_set_index(0);
+ trace_probe_log_err(0, SAME_PROBE);
+ return -EEXIST;
+ }
+
+ /* Append to existing event */
+ ret = trace_probe_append(&tf->tp, &to->tp);
+ if (ret)
+ return ret;
+
+ ret = __register_trace_fprobe(tf);
+ if (ret)
+ trace_probe_unlink(&tf->tp);
+ else
+ dyn_event_add(&tf->devent, trace_probe_event_call(&tf->tp));
+
+ return ret;
+}
+
+/* Register a trace_probe and probe_event */
+static int register_trace_fprobe(struct trace_fprobe *tf)
+{
+ struct trace_fprobe *old_tf;
+ int ret;
+
+ mutex_lock(&event_mutex);
+
+ old_tf = find_trace_fprobe(trace_probe_name(&tf->tp),
+ trace_probe_group_name(&tf->tp));
+ if (old_tf) {
+ ret = append_trace_fprobe(tf, old_tf);
+ goto end;
+ }
+
+ /* Register new event */
+ ret = register_fprobe_event(tf);
+ if (ret) {
+ if (ret == -EEXIST) {
+ trace_probe_log_set_index(0);
+ trace_probe_log_err(0, EVENT_EXIST);
+ } else
+ pr_warn("Failed to register probe event(%d)\n", ret);
+ goto end;
+ }
+
+ /* Register fprobe */
+ ret = __register_trace_fprobe(tf);
+ if (ret < 0)
+ unregister_fprobe_event(tf);
+ else
+ dyn_event_add(&tf->devent, trace_probe_event_call(&tf->tp));
+
+end:
+ mutex_unlock(&event_mutex);
+ return ret;
+}
+
+#ifdef CONFIG_MODULES
+static int __tracepoint_probe_module_cb(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ struct tp_module *tp_mod = data;
+ struct trace_fprobe *tf;
+ struct dyn_event *pos;
+
+ if (val != MODULE_STATE_GOING)
+ return NOTIFY_DONE;
+
+ mutex_lock(&event_mutex);
+ for_each_trace_fprobe(tf, pos) {
+ if (tp_mod->mod == tf->mod) {
+ tracepoint_probe_unregister(tf->tpoint,
+ tf->tpoint->probestub, NULL);
+ tf->tpoint = NULL;
+ tf->mod = NULL;
+ }
+ }
+ mutex_unlock(&event_mutex);
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block tracepoint_module_nb = {
+ .notifier_call = __tracepoint_probe_module_cb,
+};
+#endif /* CONFIG_MODULES */
+
+struct __find_tracepoint_cb_data {
+ const char *tp_name;
+ struct tracepoint *tpoint;
+};
+
+static void __find_tracepoint_cb(struct tracepoint *tp, void *priv)
+{
+ struct __find_tracepoint_cb_data *data = priv;
+
+ if (!data->tpoint && !strcmp(data->tp_name, tp->name))
+ data->tpoint = tp;
+}
+
+static struct tracepoint *find_tracepoint(const char *tp_name)
+{
+ struct __find_tracepoint_cb_data data = {
+ .tp_name = tp_name,
+ };
+
+ for_each_kernel_tracepoint(__find_tracepoint_cb, &data);
+
+ return data.tpoint;
+}
+
+static int parse_symbol_and_return(int argc, const char *argv[],
+ char **symbol, bool *is_return,
+ bool is_tracepoint)
+{
+ char *tmp = strchr(argv[1], '%');
+ int i;
+
+ if (tmp) {
+ int len = tmp - argv[1];
+
+ if (!is_tracepoint && !strcmp(tmp, "%return")) {
+ *is_return = true;
+ } else {
+ trace_probe_log_err(len, BAD_ADDR_SUFFIX);
+ return -EINVAL;
+ }
+ *symbol = kmemdup_nul(argv[1], len, GFP_KERNEL);
+ } else
+ *symbol = kstrdup(argv[1], GFP_KERNEL);
+ if (!*symbol)
+ return -ENOMEM;
+
+ if (*is_return)
+ return 0;
+
+ /* If there is $retval, this should be a return fprobe. */
+ for (i = 2; i < argc; i++) {
+ tmp = strstr(argv[i], "$retval");
+ if (tmp && !isalnum(tmp[7]) && tmp[7] != '_') {
+ *is_return = true;
+ /*
+ * NOTE: Don't check is_tracepoint here, because it will
+ * be checked when the argument is parsed.
+ */
+ break;
+ }
+ }
+ return 0;
+}
+
+static int __trace_fprobe_create(int argc, const char *argv[])
+{
+ /*
+ * Argument syntax:
+ * - Add fentry probe:
+ * f[:[GRP/][EVENT]] [MOD:]KSYM [FETCHARGS]
+ * - Add fexit probe:
+ * f[N][:[GRP/][EVENT]] [MOD:]KSYM%return [FETCHARGS]
+ * - Add tracepoint probe:
+ * t[:[GRP/][EVENT]] TRACEPOINT [FETCHARGS]
+ *
+ * Fetch args:
+ * $retval : fetch return value
+ * $stack : fetch stack address
+ * $stackN : fetch Nth entry of stack (N:0-)
+ * $argN : fetch Nth argument (N:1-)
+ * $comm : fetch current task comm
+ * @ADDR : fetch memory at ADDR (ADDR should be in kernel)
+ * @SYM[+|-offs] : fetch memory at SYM +|- offs (SYM is a data symbol)
+ * Dereferencing memory fetch:
+ * +|-offs(ARG) : fetch memory at ARG +|- offs address.
+ * Alias name of args:
+ * NAME=FETCHARG : set NAME as alias of FETCHARG.
+ * Type of args:
+ * FETCHARG:TYPE : use TYPE instead of unsigned long.
+ */
+ struct trace_fprobe *tf = NULL;
+ int i, len, new_argc = 0, ret = 0;
+ bool is_return = false;
+ char *symbol = NULL;
+ const char *event = NULL, *group = FPROBE_EVENT_SYSTEM;
+ const char **new_argv = NULL;
+ int maxactive = 0;
+ char buf[MAX_EVENT_NAME_LEN];
+ char gbuf[MAX_EVENT_NAME_LEN];
+ char sbuf[KSYM_NAME_LEN];
+ char abuf[MAX_BTF_ARGS_LEN];
+ bool is_tracepoint = false;
+ struct tracepoint *tpoint = NULL;
+ struct traceprobe_parse_context ctx = {
+ .flags = TPARG_FL_KERNEL | TPARG_FL_FPROBE,
+ };
+
+ if ((argv[0][0] != 'f' && argv[0][0] != 't') || argc < 2)
+ return -ECANCELED;
+
+ if (argv[0][0] == 't') {
+ is_tracepoint = true;
+ group = TRACEPOINT_EVENT_SYSTEM;
+ }
+
+ trace_probe_log_init("trace_fprobe", argc, argv);
+
+ event = strchr(&argv[0][1], ':');
+ if (event)
+ event++;
+
+ if (isdigit(argv[0][1])) {
+ if (event)
+ len = event - &argv[0][1] - 1;
+ else
+ len = strlen(&argv[0][1]);
+ if (len > MAX_EVENT_NAME_LEN - 1) {
+ trace_probe_log_err(1, BAD_MAXACT);
+ goto parse_error;
+ }
+ memcpy(buf, &argv[0][1], len);
+ buf[len] = '\0';
+ ret = kstrtouint(buf, 0, &maxactive);
+ if (ret || !maxactive) {
+ trace_probe_log_err(1, BAD_MAXACT);
+ goto parse_error;
+ }
+ /* fprobe rethook instances are iterated over via a list. The
+ * maximum should stay reasonable.
+ */
+ if (maxactive > RETHOOK_MAXACTIVE_MAX) {
+ trace_probe_log_err(1, MAXACT_TOO_BIG);
+ goto parse_error;
+ }
+ }
+
+ trace_probe_log_set_index(1);
+
+ /* a symbol(or tracepoint) must be specified */
+ ret = parse_symbol_and_return(argc, argv, &symbol, &is_return, is_tracepoint);
+ if (ret < 0)
+ goto parse_error;
+
+ if (!is_return && maxactive) {
+ trace_probe_log_set_index(0);
+ trace_probe_log_err(1, BAD_MAXACT_TYPE);
+ goto parse_error;
+ }
+
+ trace_probe_log_set_index(0);
+ if (event) {
+ ret = traceprobe_parse_event_name(&event, &group, gbuf,
+ event - argv[0]);
+ if (ret)
+ goto parse_error;
+ }
+
+ if (!event) {
+ /* Make a new event name */
+ if (is_tracepoint)
+ snprintf(buf, MAX_EVENT_NAME_LEN, "%s%s",
+ isdigit(*symbol) ? "_" : "", symbol);
+ else
+ snprintf(buf, MAX_EVENT_NAME_LEN, "%s__%s", symbol,
+ is_return ? "exit" : "entry");
+ sanitize_event_name(buf);
+ event = buf;
+ }
+
+ if (is_return)
+ ctx.flags |= TPARG_FL_RETURN;
+ else
+ ctx.flags |= TPARG_FL_FENTRY;
+
+ if (is_tracepoint) {
+ ctx.flags |= TPARG_FL_TPOINT;
+ tpoint = find_tracepoint(symbol);
+ if (!tpoint) {
+ trace_probe_log_set_index(1);
+ trace_probe_log_err(0, NO_TRACEPOINT);
+ goto parse_error;
+ }
+ ctx.funcname = kallsyms_lookup(
+ (unsigned long)tpoint->probestub,
+ NULL, NULL, NULL, sbuf);
+ } else
+ ctx.funcname = symbol;
+
+ argc -= 2; argv += 2;
+ new_argv = traceprobe_expand_meta_args(argc, argv, &new_argc,
+ abuf, MAX_BTF_ARGS_LEN, &ctx);
+ if (IS_ERR(new_argv)) {
+ ret = PTR_ERR(new_argv);
+ new_argv = NULL;
+ goto out;
+ }
+ if (new_argv) {
+ argc = new_argc;
+ argv = new_argv;
+ }
+
+ /* setup a probe */
+ tf = alloc_trace_fprobe(group, event, symbol, tpoint, maxactive,
+ argc, is_return);
+ if (IS_ERR(tf)) {
+ ret = PTR_ERR(tf);
+ /* This must return -ENOMEM, else there is a bug */
+ WARN_ON_ONCE(ret != -ENOMEM);
+ goto out; /* We know tf is not allocated */
+ }
+
+ if (is_tracepoint)
+ tf->mod = __module_text_address(
+ (unsigned long)tf->tpoint->probestub);
+
+ /* parse arguments */
+ for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+ trace_probe_log_set_index(i + 2);
+ ctx.offset = 0;
+ ret = traceprobe_parse_probe_arg(&tf->tp, i, argv[i], &ctx);
+ if (ret)
+ goto error; /* This can be -ENOMEM */
+ }
+
+ ret = traceprobe_set_print_fmt(&tf->tp,
+ is_return ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL);
+ if (ret < 0)
+ goto error;
+
+ ret = register_trace_fprobe(tf);
+ if (ret) {
+ trace_probe_log_set_index(1);
+ if (ret == -EILSEQ)
+ trace_probe_log_err(0, BAD_INSN_BNDRY);
+ else if (ret == -ENOENT)
+ trace_probe_log_err(0, BAD_PROBE_ADDR);
+ else if (ret != -ENOMEM && ret != -EEXIST)
+ trace_probe_log_err(0, FAIL_REG_PROBE);
+ goto error;
+ }
+
+out:
+ traceprobe_finish_parse(&ctx);
+ trace_probe_log_clear();
+ kfree(new_argv);
+ kfree(symbol);
+ return ret;
+
+parse_error:
+ ret = -EINVAL;
+error:
+ free_trace_fprobe(tf);
+ goto out;
+}
+
+static int trace_fprobe_create(const char *raw_command)
+{
+ return trace_probe_create(raw_command, __trace_fprobe_create);
+}
+
+static int trace_fprobe_release(struct dyn_event *ev)
+{
+ struct trace_fprobe *tf = to_trace_fprobe(ev);
+ int ret = unregister_trace_fprobe(tf);
+
+ if (!ret)
+ free_trace_fprobe(tf);
+ return ret;
+}
+
+static int trace_fprobe_show(struct seq_file *m, struct dyn_event *ev)
+{
+ struct trace_fprobe *tf = to_trace_fprobe(ev);
+ int i;
+
+ if (trace_fprobe_is_tracepoint(tf))
+ seq_putc(m, 't');
+ else
+ seq_putc(m, 'f');
+ if (trace_fprobe_is_return(tf) && tf->fp.nr_maxactive)
+ seq_printf(m, "%d", tf->fp.nr_maxactive);
+ seq_printf(m, ":%s/%s", trace_probe_group_name(&tf->tp),
+ trace_probe_name(&tf->tp));
+
+ seq_printf(m, " %s%s", trace_fprobe_symbol(tf),
+ trace_fprobe_is_return(tf) ? "%return" : "");
+
+ for (i = 0; i < tf->tp.nr_args; i++)
+ seq_printf(m, " %s=%s", tf->tp.args[i].name, tf->tp.args[i].comm);
+ seq_putc(m, '\n');
+
+ return 0;
+}
+
+/*
+ * called by perf_trace_init() or __ftrace_set_clr_event() under event_mutex.
+ */
+static int fprobe_register(struct trace_event_call *event,
+ enum trace_reg type, void *data)
+{
+ struct trace_event_file *file = data;
+
+ switch (type) {
+ case TRACE_REG_REGISTER:
+ return enable_trace_fprobe(event, file);
+ case TRACE_REG_UNREGISTER:
+ return disable_trace_fprobe(event, file);
+
+#ifdef CONFIG_PERF_EVENTS
+ case TRACE_REG_PERF_REGISTER:
+ return enable_trace_fprobe(event, NULL);
+ case TRACE_REG_PERF_UNREGISTER:
+ return disable_trace_fprobe(event, NULL);
+ case TRACE_REG_PERF_OPEN:
+ case TRACE_REG_PERF_CLOSE:
+ case TRACE_REG_PERF_ADD:
+ case TRACE_REG_PERF_DEL:
+ return 0;
+#endif
+ }
+ return 0;
+}
+
+/*
+ * Register dynevent at core_initcall. This allows kernel to setup fprobe
+ * events in postcore_initcall without tracefs.
+ */
+static __init int init_fprobe_trace_early(void)
+{
+ int ret;
+
+ ret = dyn_event_register(&trace_fprobe_ops);
+ if (ret)
+ return ret;
+
+#ifdef CONFIG_MODULES
+ ret = register_tracepoint_module_notifier(&tracepoint_module_nb);
+ if (ret)
+ return ret;
+#endif
+
+ return 0;
+}
+core_initcall(init_fprobe_trace_early);
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 203204cadf92..c35fbaab2a47 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -58,6 +58,12 @@ static struct tracer_opt trace_opts[] = {
{ TRACER_OPT(funcgraph-irqs, TRACE_GRAPH_PRINT_IRQS) },
/* Display function name after trailing } */
{ TRACER_OPT(funcgraph-tail, TRACE_GRAPH_PRINT_TAIL) },
+#ifdef CONFIG_FUNCTION_GRAPH_RETVAL
+ /* Display function return value ? */
+ { TRACER_OPT(funcgraph-retval, TRACE_GRAPH_PRINT_RETVAL) },
+ /* Display function return value in hexadecimal format ? */
+ { TRACER_OPT(funcgraph-retval-hex, TRACE_GRAPH_PRINT_RETVAL_HEX) },
+#endif
/* Include sleep time (scheduled out) between entry and return */
{ TRACER_OPT(sleep-time, TRACE_GRAPH_SLEEP_TIME) },
@@ -619,6 +625,56 @@ print_graph_duration(struct trace_array *tr, unsigned long long duration,
trace_seq_puts(s, "| ");
}
+#ifdef CONFIG_FUNCTION_GRAPH_RETVAL
+
+#define __TRACE_GRAPH_PRINT_RETVAL TRACE_GRAPH_PRINT_RETVAL
+
+static void print_graph_retval(struct trace_seq *s, unsigned long retval,
+ bool leaf, void *func, bool hex_format)
+{
+ unsigned long err_code = 0;
+
+ if (retval == 0 || hex_format)
+ goto done;
+
+ /* Check if the return value matches the negative format */
+ if (IS_ENABLED(CONFIG_64BIT) && (retval & BIT(31)) &&
+ (((u64)retval) >> 32) == 0) {
+ /* sign extension */
+ err_code = (unsigned long)(s32)retval;
+ } else {
+ err_code = retval;
+ }
+
+ if (!IS_ERR_VALUE(err_code))
+ err_code = 0;
+
+done:
+ if (leaf) {
+ if (hex_format || (err_code == 0))
+ trace_seq_printf(s, "%ps(); /* = 0x%lx */\n",
+ func, retval);
+ else
+ trace_seq_printf(s, "%ps(); /* = %ld */\n",
+ func, err_code);
+ } else {
+ if (hex_format || (err_code == 0))
+ trace_seq_printf(s, "} /* %ps = 0x%lx */\n",
+ func, retval);
+ else
+ trace_seq_printf(s, "} /* %ps = %ld */\n",
+ func, err_code);
+ }
+}
+
+#else
+
+#define __TRACE_GRAPH_PRINT_RETVAL 0
+
+#define print_graph_retval(_seq, _retval, _leaf, _func, _format) do {} while (0)
+
+#endif
+
/* Case of a leaf function on its call entry */
static enum print_line_t
print_graph_entry_leaf(struct trace_iterator *iter,
@@ -663,7 +719,15 @@ print_graph_entry_leaf(struct trace_iterator *iter,
for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++)
trace_seq_putc(s, ' ');
- trace_seq_printf(s, "%ps();\n", (void *)call->func);
+ /*
+ * Write out the function return value if the option function-retval is
+ * enabled.
+ */
+ if (flags & __TRACE_GRAPH_PRINT_RETVAL)
+ print_graph_retval(s, graph_ret->retval, true, (void *)call->func,
+ !!(flags & TRACE_GRAPH_PRINT_RETVAL_HEX));
+ else
+ trace_seq_printf(s, "%ps();\n", (void *)call->func);
print_graph_irq(iter, graph_ret->func, TRACE_GRAPH_RET,
cpu, iter->ent->pid, flags);
@@ -942,16 +1006,25 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
trace_seq_putc(s, ' ');
/*
- * If the return function does not have a matching entry,
- * then the entry was lost. Instead of just printing
- * the '}' and letting the user guess what function this
- * belongs to, write out the function name. Always do
- * that if the funcgraph-tail option is enabled.
+ * Always write out the function name and its return value if the
+ * function-retval option is enabled.
*/
- if (func_match && !(flags & TRACE_GRAPH_PRINT_TAIL))
- trace_seq_puts(s, "}\n");
- else
- trace_seq_printf(s, "} /* %ps */\n", (void *)trace->func);
+ if (flags & __TRACE_GRAPH_PRINT_RETVAL) {
+ print_graph_retval(s, trace->retval, false, (void *)trace->func,
+ !!(flags & TRACE_GRAPH_PRINT_RETVAL_HEX));
+ } else {
+ /*
+ * If the return function does not have a matching entry,
+ * then the entry was lost. Instead of just printing
+ * the '}' and letting the user guess what function this
+ * belongs to, write out the function name. Always do
+ * that if the funcgraph-tail option is enabled.
+ */
+ if (func_match && !(flags & TRACE_GRAPH_PRINT_TAIL))
+ trace_seq_puts(s, "}\n");
+ else
+ trace_seq_printf(s, "} /* %ps */\n", (void *)trace->func);
+ }
/* Overrun */
if (flags & TRACE_GRAPH_PRINT_OVERRUN)
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 2f37a6e68aa9..b791524a6536 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -635,7 +635,7 @@ static int s_mode_show(struct seq_file *s, void *v)
else
seq_printf(s, "%s", thread_mode_str[mode]);
- if (mode != MODE_MAX)
+ if (mode < MODE_MAX - 1) /* if mode is any but last */
seq_puts(s, " ");
return 0;
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 590b3d51afae..ba37f768e2f2 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -231,7 +231,8 @@ static void irqsoff_trace_open(struct trace_iterator *iter)
{
if (is_graph(iter->tr))
graph_trace_open(iter);
-
+ else
+ iter->private = NULL;
}
static void irqsoff_trace_close(struct trace_iterator *iter)
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 59cda19a9033..3d7a180a8427 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -30,7 +30,7 @@ static char kprobe_boot_events_buf[COMMAND_LINE_SIZE] __initdata;
static int __init set_kprobe_boot_events(char *str)
{
- strlcpy(kprobe_boot_events_buf, str, COMMAND_LINE_SIZE);
+ strscpy(kprobe_boot_events_buf, str, COMMAND_LINE_SIZE);
disable_tracing_selftest("running kprobe events");
return 1;
@@ -732,9 +732,10 @@ static int __trace_kprobe_create(int argc, const char *argv[])
* FETCHARG:TYPE : use TYPE instead of unsigned long.
*/
struct trace_kprobe *tk = NULL;
- int i, len, ret = 0;
+ int i, len, new_argc = 0, ret = 0;
bool is_return = false;
char *symbol = NULL, *tmp = NULL;
+ const char **new_argv = NULL;
const char *event = NULL, *group = KPROBE_EVENT_SYSTEM;
enum probe_print_type ptype;
int maxactive = 0;
@@ -742,7 +743,8 @@ static int __trace_kprobe_create(int argc, const char *argv[])
void *addr = NULL;
char buf[MAX_EVENT_NAME_LEN];
char gbuf[MAX_EVENT_NAME_LEN];
- unsigned int flags = TPARG_FL_KERNEL;
+ char abuf[MAX_BTF_ARGS_LEN];
+ struct traceprobe_parse_context ctx = { .flags = TPARG_FL_KERNEL };
switch (argv[0][0]) {
case 'r':
@@ -764,7 +766,7 @@ static int __trace_kprobe_create(int argc, const char *argv[])
if (isdigit(argv[0][1])) {
if (!is_return) {
- trace_probe_log_err(1, MAXACT_NO_KPROBE);
+ trace_probe_log_err(1, BAD_MAXACT_TYPE);
goto parse_error;
}
if (event)
@@ -823,10 +825,10 @@ static int __trace_kprobe_create(int argc, const char *argv[])
goto parse_error;
}
if (is_return)
- flags |= TPARG_FL_RETURN;
+ ctx.flags |= TPARG_FL_RETURN;
ret = kprobe_on_func_entry(NULL, symbol, offset);
- if (ret == 0)
- flags |= TPARG_FL_FENTRY;
+ if (ret == 0 && !is_return)
+ ctx.flags |= TPARG_FL_FENTRY;
/* Defer the ENOENT case until register kprobe */
if (ret == -EINVAL && is_return) {
trace_probe_log_err(0, BAD_RETPROBE);
@@ -854,21 +856,35 @@ static int __trace_kprobe_create(int argc, const char *argv[])
event = buf;
}
+ argc -= 2; argv += 2;
+ ctx.funcname = symbol;
+ new_argv = traceprobe_expand_meta_args(argc, argv, &new_argc,
+ abuf, MAX_BTF_ARGS_LEN, &ctx);
+ if (IS_ERR(new_argv)) {
+ ret = PTR_ERR(new_argv);
+ new_argv = NULL;
+ goto out;
+ }
+ if (new_argv) {
+ argc = new_argc;
+ argv = new_argv;
+ }
+
/* setup a probe */
tk = alloc_trace_kprobe(group, event, addr, symbol, offset, maxactive,
- argc - 2, is_return);
+ argc, is_return);
if (IS_ERR(tk)) {
ret = PTR_ERR(tk);
/* This must return -ENOMEM, else there is a bug */
WARN_ON_ONCE(ret != -ENOMEM);
goto out; /* We know tk is not allocated */
}
- argc -= 2; argv += 2;
/* parse arguments */
for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
trace_probe_log_set_index(i + 2);
- ret = traceprobe_parse_probe_arg(&tk->tp, i, argv[i], flags);
+ ctx.offset = 0;
+ ret = traceprobe_parse_probe_arg(&tk->tp, i, argv[i], &ctx);
if (ret)
goto error; /* This can be -ENOMEM */
}
@@ -891,7 +907,9 @@ static int __trace_kprobe_create(int argc, const char *argv[])
}
out:
+ traceprobe_finish_parse(&ctx);
trace_probe_log_clear();
+ kfree(new_argv);
kfree(symbol);
return ret;
@@ -1544,15 +1562,10 @@ int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type,
*fd_type = trace_kprobe_is_return(tk) ? BPF_FD_TYPE_KRETPROBE
: BPF_FD_TYPE_KPROBE;
- if (tk->symbol) {
- *symbol = tk->symbol;
- *probe_offset = tk->rp.kp.offset;
- *probe_addr = 0;
- } else {
- *symbol = NULL;
- *probe_offset = 0;
- *probe_addr = (unsigned long)tk->rp.kp.addr;
- }
+ *probe_offset = tk->rp.kp.offset;
+ *probe_addr = kallsyms_show_value(current_cred()) ?
+ (unsigned long)tk->rp.kp.addr : 0;
+ *symbol = tk->symbol;
return 0;
}
#endif /* CONFIG_PERF_EVENTS */
diff --git a/kernel/trace/trace_kprobe_selftest.c b/kernel/trace/trace_kprobe_selftest.c
index 16548ee4c8c6..3851cd1e6a62 100644
--- a/kernel/trace/trace_kprobe_selftest.c
+++ b/kernel/trace/trace_kprobe_selftest.c
@@ -1,4 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
+
+#include "trace_kprobe_selftest.h"
+
/*
* Function used during the kprobe self test. This function is in a separate
* compile unit so it can be compile with CC_FLAGS_FTRACE to ensure that it
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index e97e3fa5cbed..bd0d01d00fb9 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -181,6 +181,7 @@ struct osn_irq {
#define IRQ_CONTEXT 0
#define THREAD_CONTEXT 1
+#define THREAD_URET 2
/*
* sofirq runtime info.
*/
@@ -238,6 +239,7 @@ struct timerlat_variables {
u64 abs_period;
bool tracing_thread;
u64 count;
+ bool uthread_migrate;
};
static DEFINE_PER_CPU(struct timerlat_variables, per_cpu_timerlat_var);
@@ -1181,6 +1183,78 @@ thread_exit(struct osnoise_variables *osn_var, struct task_struct *t)
osn_var->thread.arrival_time = 0;
}
+#ifdef CONFIG_TIMERLAT_TRACER
+/*
+ * osnoise_stop_exception - Stop tracing and the tracer.
+ */
+static __always_inline void osnoise_stop_exception(char *msg, int cpu)
+{
+ struct osnoise_instance *inst;
+ struct trace_array *tr;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(inst, &osnoise_instances, list) {
+ tr = inst->tr;
+ trace_array_printk_buf(tr->array_buffer.buffer, _THIS_IP_,
+ "stop tracing hit on cpu %d due to exception: %s\n",
+ smp_processor_id(),
+ msg);
+
+ if (test_bit(OSN_PANIC_ON_STOP, &osnoise_options))
+ panic("tracer hit on cpu %d due to exception: %s\n",
+ smp_processor_id(),
+ msg);
+
+ tracer_tracing_off(tr);
+ }
+ rcu_read_unlock();
+}
+
+/*
+ * trace_sched_migrate_callback - sched:sched_migrate_task trace event handler
+ *
+ * his function is hooked to the sched:sched_migrate_task trace event, and monitors
+ * timerlat user-space thread migration.
+ */
+static void trace_sched_migrate_callback(void *data, struct task_struct *p, int dest_cpu)
+{
+ struct osnoise_variables *osn_var;
+ long cpu = task_cpu(p);
+
+ osn_var = per_cpu_ptr(&per_cpu_osnoise_var, cpu);
+ if (osn_var->pid == p->pid && dest_cpu != cpu) {
+ per_cpu_ptr(&per_cpu_timerlat_var, cpu)->uthread_migrate = 1;
+ osnoise_taint("timerlat user-thread migrated\n");
+ osnoise_stop_exception("timerlat user-thread migrated", cpu);
+ }
+}
+
+static int register_migration_monitor(void)
+{
+ int ret = 0;
+
+ /*
+ * Timerlat thread migration check is only required when running timerlat in user-space.
+ * Thus, enable callback only if timerlat is set with no workload.
+ */
+ if (timerlat_enabled() && !test_bit(OSN_WORKLOAD, &osnoise_options))
+ ret = register_trace_sched_migrate_task(trace_sched_migrate_callback, NULL);
+
+ return ret;
+}
+
+static void unregister_migration_monitor(void)
+{
+ if (timerlat_enabled() && !test_bit(OSN_WORKLOAD, &osnoise_options))
+ unregister_trace_sched_migrate_task(trace_sched_migrate_callback, NULL);
+}
+#else
+static int register_migration_monitor(void)
+{
+ return 0;
+}
+static void unregister_migration_monitor(void) {}
+#endif
/*
* trace_sched_switch - sched:sched_switch trace event handler
*
@@ -1204,7 +1278,7 @@ trace_sched_switch_callback(void *data, bool preempt,
}
/*
- * hook_thread_events - Hook the insturmentation for thread noise
+ * hook_thread_events - Hook the instrumentation for thread noise
*
* Hook the osnoise tracer callbacks to handle the noise from other
* threads on the necessary kernel events.
@@ -1217,11 +1291,19 @@ static int hook_thread_events(void)
if (ret)
return -EINVAL;
+ ret = register_migration_monitor();
+ if (ret)
+ goto out_unreg;
+
return 0;
+
+out_unreg:
+ unregister_trace_sched_switch(trace_sched_switch_callback, NULL);
+ return -EINVAL;
}
/*
- * unhook_thread_events - *nhook the insturmentation for thread noise
+ * unhook_thread_events - unhook the instrumentation for thread noise
*
* Unook the osnoise tracer callbacks to handle the noise from other
* threads on the necessary kernel events.
@@ -1229,6 +1311,7 @@ static int hook_thread_events(void)
static void unhook_thread_events(void)
{
unregister_trace_sched_switch(trace_sched_switch_callback, NULL);
+ unregister_migration_monitor();
}
/*
@@ -1286,6 +1369,22 @@ static __always_inline void osnoise_stop_tracing(void)
}
/*
+ * osnoise_has_tracing_on - Check if there is at least one instance on
+ */
+static __always_inline int osnoise_has_tracing_on(void)
+{
+ struct osnoise_instance *inst;
+ int trace_is_on = 0;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(inst, &osnoise_instances, list)
+ trace_is_on += tracer_tracing_is_on(inst->tr);
+ rcu_read_unlock();
+
+ return trace_is_on;
+}
+
+/*
* notify_new_max_latency - Notify a new max latency via fsnotify interface.
*/
static void notify_new_max_latency(u64 latency)
@@ -1517,13 +1616,16 @@ static struct cpumask save_cpumask;
/*
* osnoise_sleep - sleep until the next period
*/
-static void osnoise_sleep(void)
+static void osnoise_sleep(bool skip_period)
{
u64 interval;
ktime_t wake_time;
mutex_lock(&interface_lock);
- interval = osnoise_data.sample_period - osnoise_data.sample_runtime;
+ if (skip_period)
+ interval = osnoise_data.sample_period;
+ else
+ interval = osnoise_data.sample_period - osnoise_data.sample_runtime;
mutex_unlock(&interface_lock);
/*
@@ -1546,6 +1648,39 @@ static void osnoise_sleep(void)
}
/*
+ * osnoise_migration_pending - checks if the task needs to migrate
+ *
+ * osnoise/timerlat threads are per-cpu. If there is a pending request to
+ * migrate the thread away from the current CPU, something bad has happened.
+ * Play the good citizen and leave.
+ *
+ * Returns 0 if it is safe to continue, 1 otherwise.
+ */
+static inline int osnoise_migration_pending(void)
+{
+ if (!current->migration_pending)
+ return 0;
+
+ /*
+ * If migration is pending, there is a task waiting for the
+ * tracer to enable migration. The tracer does not allow migration,
+ * thus: taint and leave to unblock the blocked thread.
+ */
+ osnoise_taint("migration requested to osnoise threads, leaving.");
+
+ /*
+ * Unset this thread from the threads managed by the interface.
+ * The tracers are responsible for cleaning their env before
+ * exiting.
+ */
+ mutex_lock(&interface_lock);
+ this_cpu_osn_var()->kthread = NULL;
+ mutex_unlock(&interface_lock);
+
+ return 1;
+}
+
+/*
* osnoise_main - The osnoise detection kernel thread
*
* Calls run_osnoise() function to measure the osnoise for the configured runtime,
@@ -1553,12 +1688,35 @@ static void osnoise_sleep(void)
*/
static int osnoise_main(void *data)
{
+ unsigned long flags;
+
+ /*
+ * This thread was created pinned to the CPU using PF_NO_SETAFFINITY.
+ * The problem is that cgroup does not allow PF_NO_SETAFFINITY thread.
+ *
+ * To work around this limitation, disable migration and remove the
+ * flag.
+ */
+ migrate_disable();
+ raw_spin_lock_irqsave(&current->pi_lock, flags);
+ current->flags &= ~(PF_NO_SETAFFINITY);
+ raw_spin_unlock_irqrestore(&current->pi_lock, flags);
while (!kthread_should_stop()) {
+ if (osnoise_migration_pending())
+ break;
+
+ /* skip a period if tracing is off on all instances */
+ if (!osnoise_has_tracing_on()) {
+ osnoise_sleep(true);
+ continue;
+ }
+
run_osnoise();
- osnoise_sleep();
+ osnoise_sleep(false);
}
+ migrate_enable();
return 0;
}
@@ -1706,6 +1864,7 @@ static int timerlat_main(void *data)
struct timerlat_variables *tlat = this_cpu_tmr_var();
struct timerlat_sample s;
struct sched_param sp;
+ unsigned long flags;
u64 now, diff;
/*
@@ -1714,6 +1873,18 @@ static int timerlat_main(void *data)
sp.sched_priority = DEFAULT_TIMERLAT_PRIO;
sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
+ /*
+ * This thread was created pinned to the CPU using PF_NO_SETAFFINITY.
+ * The problem is that cgroup does not allow PF_NO_SETAFFINITY thread.
+ *
+ * To work around this limitation, disable migration and remove the
+ * flag.
+ */
+ migrate_disable();
+ raw_spin_lock_irqsave(&current->pi_lock, flags);
+ current->flags &= ~(PF_NO_SETAFFINITY);
+ raw_spin_unlock_irqrestore(&current->pi_lock, flags);
+
tlat->count = 0;
tlat->tracing_thread = false;
@@ -1731,6 +1902,7 @@ static int timerlat_main(void *data)
osn_var->sampling = 1;
while (!kthread_should_stop()) {
+
now = ktime_to_ns(hrtimer_cb_get_time(&tlat->timer));
diff = now - tlat->abs_period;
@@ -1749,10 +1921,14 @@ static int timerlat_main(void *data)
if (time_to_us(diff) >= osnoise_data.stop_tracing_total)
osnoise_stop_tracing();
+ if (osnoise_migration_pending())
+ break;
+
wait_next_period(tlat);
}
hrtimer_cancel(&tlat->timer);
+ migrate_enable();
return 0;
}
#else /* CONFIG_TIMERLAT_TRACER */
@@ -1771,10 +1947,24 @@ static void stop_kthread(unsigned int cpu)
kthread = per_cpu(per_cpu_osnoise_var, cpu).kthread;
if (kthread) {
- kthread_stop(kthread);
+ if (test_bit(OSN_WORKLOAD, &osnoise_options)) {
+ kthread_stop(kthread);
+ } else {
+ /*
+ * This is a user thread waiting on the timerlat_fd. We need
+ * to close all users, and the best way to guarantee this is
+ * by killing the thread. NOTE: this is a purpose specific file.
+ */
+ kill_pid(kthread->thread_pid, SIGKILL, 1);
+ put_task_struct(kthread);
+ }
per_cpu(per_cpu_osnoise_var, cpu).kthread = NULL;
} else {
+ /* if no workload, just return */
if (!test_bit(OSN_WORKLOAD, &osnoise_options)) {
+ /*
+ * This is set in the osnoise tracer case.
+ */
per_cpu(per_cpu_osnoise_var, cpu).sampling = false;
barrier();
return;
@@ -1819,7 +2009,6 @@ static int start_kthread(unsigned int cpu)
barrier();
return 0;
}
-
snprintf(comm, 24, "osnoise/%d", cpu);
}
@@ -1848,6 +2037,11 @@ static int start_per_cpu_kthreads(void)
int retval = 0;
int cpu;
+ if (!test_bit(OSN_WORKLOAD, &osnoise_options)) {
+ if (timerlat_enabled())
+ return 0;
+ }
+
cpus_read_lock();
/*
* Run only on online CPUs in which osnoise is allowed to run.
@@ -2188,6 +2382,223 @@ err_free:
return err;
}
+#ifdef CONFIG_TIMERLAT_TRACER
+static int timerlat_fd_open(struct inode *inode, struct file *file)
+{
+ struct osnoise_variables *osn_var;
+ struct timerlat_variables *tlat;
+ long cpu = (long) inode->i_cdev;
+
+ mutex_lock(&interface_lock);
+
+ /*
+ * This file is accessible only if timerlat is enabled, and
+ * NO_OSNOISE_WORKLOAD is set.
+ */
+ if (!timerlat_enabled() || test_bit(OSN_WORKLOAD, &osnoise_options)) {
+ mutex_unlock(&interface_lock);
+ return -EINVAL;
+ }
+
+ migrate_disable();
+
+ osn_var = this_cpu_osn_var();
+
+ /*
+ * The osn_var->pid holds the single access to this file.
+ */
+ if (osn_var->pid) {
+ mutex_unlock(&interface_lock);
+ migrate_enable();
+ return -EBUSY;
+ }
+
+ /*
+ * timerlat tracer is a per-cpu tracer. Check if the user-space too
+ * is pinned to a single CPU. The tracer laters monitor if the task
+ * migrates and then disables tracer if it does. However, it is
+ * worth doing this basic acceptance test to avoid obviusly wrong
+ * setup.
+ */
+ if (current->nr_cpus_allowed > 1 || cpu != smp_processor_id()) {
+ mutex_unlock(&interface_lock);
+ migrate_enable();
+ return -EPERM;
+ }
+
+ /*
+ * From now on, it is good to go.
+ */
+ file->private_data = inode->i_cdev;
+
+ get_task_struct(current);
+
+ osn_var->kthread = current;
+ osn_var->pid = current->pid;
+
+ /*
+ * Setup is done.
+ */
+ mutex_unlock(&interface_lock);
+
+ tlat = this_cpu_tmr_var();
+ tlat->count = 0;
+
+ migrate_enable();
+ return 0;
+};
+
+/*
+ * timerlat_fd_read - Read function for "timerlat_fd" file
+ * @file: The active open file structure
+ * @ubuf: The userspace provided buffer to read value into
+ * @cnt: The maximum number of bytes to read
+ * @ppos: The current "file" position
+ *
+ * Prints 1 on timerlat, the number of interferences on osnoise, -1 on error.
+ */
+static ssize_t
+timerlat_fd_read(struct file *file, char __user *ubuf, size_t count,
+ loff_t *ppos)
+{
+ long cpu = (long) file->private_data;
+ struct osnoise_variables *osn_var;
+ struct timerlat_variables *tlat;
+ struct timerlat_sample s;
+ s64 diff;
+ u64 now;
+
+ migrate_disable();
+
+ tlat = this_cpu_tmr_var();
+
+ /*
+ * While in user-space, the thread is migratable. There is nothing
+ * we can do about it.
+ * So, if the thread is running on another CPU, stop the machinery.
+ */
+ if (cpu == smp_processor_id()) {
+ if (tlat->uthread_migrate) {
+ migrate_enable();
+ return -EINVAL;
+ }
+ } else {
+ per_cpu_ptr(&per_cpu_timerlat_var, cpu)->uthread_migrate = 1;
+ osnoise_taint("timerlat user thread migrate\n");
+ osnoise_stop_tracing();
+ migrate_enable();
+ return -EINVAL;
+ }
+
+ osn_var = this_cpu_osn_var();
+
+ /*
+ * The timerlat in user-space runs in a different order:
+ * the read() starts from the execution of the previous occurrence,
+ * sleeping for the next occurrence.
+ *
+ * So, skip if we are entering on read() before the first wakeup
+ * from timerlat IRQ:
+ */
+ if (likely(osn_var->sampling)) {
+ now = ktime_to_ns(hrtimer_cb_get_time(&tlat->timer));
+ diff = now - tlat->abs_period;
+
+ /*
+ * it was not a timer firing, but some other signal?
+ */
+ if (diff < 0)
+ goto out;
+
+ s.seqnum = tlat->count;
+ s.timer_latency = diff;
+ s.context = THREAD_URET;
+
+ trace_timerlat_sample(&s);
+
+ notify_new_max_latency(diff);
+
+ tlat->tracing_thread = false;
+ if (osnoise_data.stop_tracing_total)
+ if (time_to_us(diff) >= osnoise_data.stop_tracing_total)
+ osnoise_stop_tracing();
+ } else {
+ tlat->tracing_thread = false;
+ tlat->kthread = current;
+
+ hrtimer_init(&tlat->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
+ tlat->timer.function = timerlat_irq;
+
+ /* Annotate now to drift new period */
+ tlat->abs_period = hrtimer_cb_get_time(&tlat->timer);
+
+ osn_var->sampling = 1;
+ }
+
+ /* wait for the next period */
+ wait_next_period(tlat);
+
+ /* This is the wakeup from this cycle */
+ now = ktime_to_ns(hrtimer_cb_get_time(&tlat->timer));
+ diff = now - tlat->abs_period;
+
+ /*
+ * it was not a timer firing, but some other signal?
+ */
+ if (diff < 0)
+ goto out;
+
+ s.seqnum = tlat->count;
+ s.timer_latency = diff;
+ s.context = THREAD_CONTEXT;
+
+ trace_timerlat_sample(&s);
+
+ if (osnoise_data.stop_tracing_total) {
+ if (time_to_us(diff) >= osnoise_data.stop_tracing_total) {
+ timerlat_dump_stack(time_to_us(diff));
+ notify_new_max_latency(diff);
+ osnoise_stop_tracing();
+ }
+ }
+
+out:
+ migrate_enable();
+ return 0;
+}
+
+static int timerlat_fd_release(struct inode *inode, struct file *file)
+{
+ struct osnoise_variables *osn_var;
+ struct timerlat_variables *tlat_var;
+ long cpu = (long) file->private_data;
+
+ migrate_disable();
+ mutex_lock(&interface_lock);
+
+ osn_var = per_cpu_ptr(&per_cpu_osnoise_var, cpu);
+ tlat_var = per_cpu_ptr(&per_cpu_timerlat_var, cpu);
+
+ hrtimer_cancel(&tlat_var->timer);
+ memset(tlat_var, 0, sizeof(*tlat_var));
+
+ osn_var->sampling = 0;
+ osn_var->pid = 0;
+
+ /*
+ * We are leaving, not being stopped... see stop_kthread();
+ */
+ if (osn_var->kthread) {
+ put_task_struct(osn_var->kthread);
+ osn_var->kthread = NULL;
+ }
+
+ mutex_unlock(&interface_lock);
+ migrate_enable();
+ return 0;
+}
+#endif
+
/*
* osnoise/runtime_us: cannot be greater than the period.
*/
@@ -2251,6 +2662,13 @@ static struct trace_min_max_param timerlat_period = {
.max = &timerlat_max_period,
.min = &timerlat_min_period,
};
+
+static const struct file_operations timerlat_fd_fops = {
+ .open = timerlat_fd_open,
+ .read = timerlat_fd_read,
+ .release = timerlat_fd_release,
+ .llseek = generic_file_llseek,
+};
#endif
static const struct file_operations cpus_fops = {
@@ -2288,18 +2706,63 @@ static int init_timerlat_stack_tracefs(struct dentry *top_dir)
}
#endif /* CONFIG_STACKTRACE */
+static int osnoise_create_cpu_timerlat_fd(struct dentry *top_dir)
+{
+ struct dentry *timerlat_fd;
+ struct dentry *per_cpu;
+ struct dentry *cpu_dir;
+ char cpu_str[30]; /* see trace.c: tracing_init_tracefs_percpu() */
+ long cpu;
+
+ /*
+ * Why not using tracing instance per_cpu/ dir?
+ *
+ * Because osnoise/timerlat have a single workload, having
+ * multiple files like these are wast of memory.
+ */
+ per_cpu = tracefs_create_dir("per_cpu", top_dir);
+ if (!per_cpu)
+ return -ENOMEM;
+
+ for_each_possible_cpu(cpu) {
+ snprintf(cpu_str, 30, "cpu%ld", cpu);
+ cpu_dir = tracefs_create_dir(cpu_str, per_cpu);
+ if (!cpu_dir)
+ goto out_clean;
+
+ timerlat_fd = trace_create_file("timerlat_fd", TRACE_MODE_READ,
+ cpu_dir, NULL, &timerlat_fd_fops);
+ if (!timerlat_fd)
+ goto out_clean;
+
+ /* Record the CPU */
+ d_inode(timerlat_fd)->i_cdev = (void *)(cpu);
+ }
+
+ return 0;
+
+out_clean:
+ tracefs_remove(per_cpu);
+ return -ENOMEM;
+}
+
/*
* init_timerlat_tracefs - A function to initialize the timerlat interface files
*/
static int init_timerlat_tracefs(struct dentry *top_dir)
{
struct dentry *tmp;
+ int retval;
tmp = tracefs_create_file("timerlat_period_us", TRACE_MODE_WRITE, top_dir,
&timerlat_period, &trace_min_max_fops);
if (!tmp)
return -ENOMEM;
+ retval = osnoise_create_cpu_timerlat_fd(top_dir);
+ if (retval)
+ return retval;
+
return init_timerlat_stack_tracefs(top_dir);
}
#else /* CONFIG_TIMERLAT_TRACER */
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 1e33f367783e..db575094c498 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1446,6 +1446,8 @@ static struct trace_event trace_osnoise_event = {
};
/* TRACE_TIMERLAT */
+
+static char *timerlat_lat_context[] = {"irq", "thread", "user-ret"};
static enum print_line_t
trace_timerlat_print(struct trace_iterator *iter, int flags,
struct trace_event *event)
@@ -1458,7 +1460,7 @@ trace_timerlat_print(struct trace_iterator *iter, int flags,
trace_seq_printf(s, "#%-5u context %6s timer_latency %9llu ns\n",
field->seqnum,
- field->context ? "thread" : "irq",
+ timerlat_lat_context[field->context],
field->timer_latency);
return trace_handle_return(s);
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 2d2616678295..4dc74d73fc1d 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -11,6 +11,9 @@
*/
#define pr_fmt(fmt) "trace_probe: " fmt
+#include <linux/bpf.h>
+#include "trace_btf.h"
+
#include "trace_probe.h"
#undef C
@@ -65,7 +68,7 @@ int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s, void *data, void *ent)
int len = *(u32 *)data >> 16;
if (!len)
- trace_seq_puts(s, "(fault)");
+ trace_seq_puts(s, FAULT_STRING);
else
trace_seq_printf(s, "\"%s\"",
(const char *)get_loc_data(data, ent));
@@ -254,7 +257,7 @@ int traceprobe_parse_event_name(const char **pevent, const char **pgroup,
trace_probe_log_err(offset, GROUP_TOO_LONG);
return -EINVAL;
}
- strlcpy(buf, event, slash - event + 1);
+ strscpy(buf, event, slash - event + 1);
if (!is_good_system_name(buf)) {
trace_probe_log_err(offset, BAD_GROUP_NAME);
return -EINVAL;
@@ -283,69 +286,574 @@ int traceprobe_parse_event_name(const char **pevent, const char **pgroup,
return 0;
}
+static int parse_trace_event_arg(char *arg, struct fetch_insn *code,
+ struct traceprobe_parse_context *ctx)
+{
+ struct ftrace_event_field *field;
+ struct list_head *head;
+
+ head = trace_get_fields(ctx->event);
+ list_for_each_entry(field, head, link) {
+ if (!strcmp(arg, field->name)) {
+ code->op = FETCH_OP_TP_ARG;
+ code->data = field;
+ return 0;
+ }
+ }
+ return -ENOENT;
+}
+
+#ifdef CONFIG_PROBE_EVENTS_BTF_ARGS
+
+static u32 btf_type_int(const struct btf_type *t)
+{
+ return *(u32 *)(t + 1);
+}
+
+static bool btf_type_is_char_ptr(struct btf *btf, const struct btf_type *type)
+{
+ const struct btf_type *real_type;
+ u32 intdata;
+ s32 tid;
+
+ real_type = btf_type_skip_modifiers(btf, type->type, &tid);
+ if (!real_type)
+ return false;
+
+ if (BTF_INFO_KIND(real_type->info) != BTF_KIND_INT)
+ return false;
+
+ intdata = btf_type_int(real_type);
+ return !(BTF_INT_ENCODING(intdata) & BTF_INT_SIGNED)
+ && BTF_INT_BITS(intdata) == 8;
+}
+
+static bool btf_type_is_char_array(struct btf *btf, const struct btf_type *type)
+{
+ const struct btf_type *real_type;
+ const struct btf_array *array;
+ u32 intdata;
+ s32 tid;
+
+ if (BTF_INFO_KIND(type->info) != BTF_KIND_ARRAY)
+ return false;
+
+ array = (const struct btf_array *)(type + 1);
+
+ real_type = btf_type_skip_modifiers(btf, array->type, &tid);
+
+ intdata = btf_type_int(real_type);
+ return !(BTF_INT_ENCODING(intdata) & BTF_INT_SIGNED)
+ && BTF_INT_BITS(intdata) == 8;
+}
+
+static int check_prepare_btf_string_fetch(char *typename,
+ struct fetch_insn **pcode,
+ struct traceprobe_parse_context *ctx)
+{
+ struct btf *btf = ctx->btf;
+
+ if (!btf || !ctx->last_type)
+ return 0;
+
+ /* char [] does not need any change. */
+ if (btf_type_is_char_array(btf, ctx->last_type))
+ return 0;
+
+ /* char * requires dereference the pointer. */
+ if (btf_type_is_char_ptr(btf, ctx->last_type)) {
+ struct fetch_insn *code = *pcode + 1;
+
+ if (code->op == FETCH_OP_END) {
+ trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
+ return -E2BIG;
+ }
+ if (typename[0] == 'u')
+ code->op = FETCH_OP_UDEREF;
+ else
+ code->op = FETCH_OP_DEREF;
+ code->offset = 0;
+ *pcode = code;
+ return 0;
+ }
+ /* Other types are not available for string */
+ trace_probe_log_err(ctx->offset, BAD_TYPE4STR);
+ return -EINVAL;
+}
+
+static const char *fetch_type_from_btf_type(struct btf *btf,
+ const struct btf_type *type,
+ struct traceprobe_parse_context *ctx)
+{
+ u32 intdata;
+
+ /* TODO: const char * could be converted as a string */
+ switch (BTF_INFO_KIND(type->info)) {
+ case BTF_KIND_ENUM:
+ /* enum is "int", so convert to "s32" */
+ return "s32";
+ case BTF_KIND_ENUM64:
+ return "s64";
+ case BTF_KIND_PTR:
+ /* pointer will be converted to "x??" */
+ if (IS_ENABLED(CONFIG_64BIT))
+ return "x64";
+ else
+ return "x32";
+ case BTF_KIND_INT:
+ intdata = btf_type_int(type);
+ if (BTF_INT_ENCODING(intdata) & BTF_INT_SIGNED) {
+ switch (BTF_INT_BITS(intdata)) {
+ case 8:
+ return "s8";
+ case 16:
+ return "s16";
+ case 32:
+ return "s32";
+ case 64:
+ return "s64";
+ }
+ } else { /* unsigned */
+ switch (BTF_INT_BITS(intdata)) {
+ case 8:
+ return "u8";
+ case 16:
+ return "u16";
+ case 32:
+ return "u32";
+ case 64:
+ return "u64";
+ }
+ /* bitfield, size is encoded in the type */
+ ctx->last_bitsize = BTF_INT_BITS(intdata);
+ ctx->last_bitoffs += BTF_INT_OFFSET(intdata);
+ return "u64";
+ }
+ }
+ /* TODO: support other types */
+
+ return NULL;
+}
+
+static int query_btf_context(struct traceprobe_parse_context *ctx)
+{
+ const struct btf_param *param;
+ const struct btf_type *type;
+ struct btf *btf;
+ s32 nr;
+
+ if (ctx->btf)
+ return 0;
+
+ if (!ctx->funcname)
+ return -EINVAL;
+
+ type = btf_find_func_proto(ctx->funcname, &btf);
+ if (!type)
+ return -ENOENT;
+
+ ctx->btf = btf;
+ ctx->proto = type;
+
+ /* ctx->params is optional, since func(void) will not have params. */
+ nr = 0;
+ param = btf_get_func_param(type, &nr);
+ if (!IS_ERR_OR_NULL(param)) {
+ /* Hide the first 'data' argument of tracepoint */
+ if (ctx->flags & TPARG_FL_TPOINT) {
+ nr--;
+ param++;
+ }
+ }
+
+ if (nr > 0) {
+ ctx->nr_params = nr;
+ ctx->params = param;
+ } else {
+ ctx->nr_params = 0;
+ ctx->params = NULL;
+ }
+
+ return 0;
+}
+
+static void clear_btf_context(struct traceprobe_parse_context *ctx)
+{
+ if (ctx->btf) {
+ btf_put(ctx->btf);
+ ctx->btf = NULL;
+ ctx->proto = NULL;
+ ctx->params = NULL;
+ ctx->nr_params = 0;
+ }
+}
+
+/* Return 1 if the field separater is arrow operator ('->') */
+static int split_next_field(char *varname, char **next_field,
+ struct traceprobe_parse_context *ctx)
+{
+ char *field;
+ int ret = 0;
+
+ field = strpbrk(varname, ".-");
+ if (field) {
+ if (field[0] == '-' && field[1] == '>') {
+ field[0] = '\0';
+ field += 2;
+ ret = 1;
+ } else if (field[0] == '.') {
+ field[0] = '\0';
+ field += 1;
+ } else {
+ trace_probe_log_err(ctx->offset + field - varname, BAD_HYPHEN);
+ return -EINVAL;
+ }
+ *next_field = field;
+ }
+
+ return ret;
+}
+
+/*
+ * Parse the field of data structure. The @type must be a pointer type
+ * pointing the target data structure type.
+ */
+static int parse_btf_field(char *fieldname, const struct btf_type *type,
+ struct fetch_insn **pcode, struct fetch_insn *end,
+ struct traceprobe_parse_context *ctx)
+{
+ struct fetch_insn *code = *pcode;
+ const struct btf_member *field;
+ u32 bitoffs, anon_offs;
+ char *next;
+ int is_ptr;
+ s32 tid;
+
+ do {
+ /* Outer loop for solving arrow operator ('->') */
+ if (BTF_INFO_KIND(type->info) != BTF_KIND_PTR) {
+ trace_probe_log_err(ctx->offset, NO_PTR_STRCT);
+ return -EINVAL;
+ }
+ /* Convert a struct pointer type to a struct type */
+ type = btf_type_skip_modifiers(ctx->btf, type->type, &tid);
+ if (!type) {
+ trace_probe_log_err(ctx->offset, BAD_BTF_TID);
+ return -EINVAL;
+ }
+
+ bitoffs = 0;
+ do {
+ /* Inner loop for solving dot operator ('.') */
+ next = NULL;
+ is_ptr = split_next_field(fieldname, &next, ctx);
+ if (is_ptr < 0)
+ return is_ptr;
+
+ anon_offs = 0;
+ field = btf_find_struct_member(ctx->btf, type, fieldname,
+ &anon_offs);
+ if (!field) {
+ trace_probe_log_err(ctx->offset, NO_BTF_FIELD);
+ return -ENOENT;
+ }
+ /* Add anonymous structure/union offset */
+ bitoffs += anon_offs;
+
+ /* Accumulate the bit-offsets of the dot-connected fields */
+ if (btf_type_kflag(type)) {
+ bitoffs += BTF_MEMBER_BIT_OFFSET(field->offset);
+ ctx->last_bitsize = BTF_MEMBER_BITFIELD_SIZE(field->offset);
+ } else {
+ bitoffs += field->offset;
+ ctx->last_bitsize = 0;
+ }
+
+ type = btf_type_skip_modifiers(ctx->btf, field->type, &tid);
+ if (!type) {
+ trace_probe_log_err(ctx->offset, BAD_BTF_TID);
+ return -EINVAL;
+ }
+
+ ctx->offset += next - fieldname;
+ fieldname = next;
+ } while (!is_ptr && fieldname);
+
+ if (++code == end) {
+ trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
+ return -EINVAL;
+ }
+ code->op = FETCH_OP_DEREF; /* TODO: user deref support */
+ code->offset = bitoffs / 8;
+ *pcode = code;
+
+ ctx->last_bitoffs = bitoffs % 8;
+ ctx->last_type = type;
+ } while (fieldname);
+
+ return 0;
+}
+
+static int parse_btf_arg(char *varname,
+ struct fetch_insn **pcode, struct fetch_insn *end,
+ struct traceprobe_parse_context *ctx)
+{
+ struct fetch_insn *code = *pcode;
+ const struct btf_param *params;
+ const struct btf_type *type;
+ char *field = NULL;
+ int i, is_ptr, ret;
+ u32 tid;
+
+ if (WARN_ON_ONCE(!ctx->funcname))
+ return -EINVAL;
+
+ is_ptr = split_next_field(varname, &field, ctx);
+ if (is_ptr < 0)
+ return is_ptr;
+ if (!is_ptr && field) {
+ /* dot-connected field on an argument is not supported. */
+ trace_probe_log_err(ctx->offset + field - varname,
+ NOSUP_DAT_ARG);
+ return -EOPNOTSUPP;
+ }
+
+ if (ctx->flags & TPARG_FL_RETURN) {
+ if (strcmp(varname, "$retval") != 0) {
+ trace_probe_log_err(ctx->offset, NO_BTFARG);
+ return -ENOENT;
+ }
+ code->op = FETCH_OP_RETVAL;
+ /* Check whether the function return type is not void */
+ if (query_btf_context(ctx) == 0) {
+ if (ctx->proto->type == 0) {
+ trace_probe_log_err(ctx->offset, NO_RETVAL);
+ return -ENOENT;
+ }
+ tid = ctx->proto->type;
+ goto found;
+ }
+ if (field) {
+ trace_probe_log_err(ctx->offset + field - varname,
+ NO_BTF_ENTRY);
+ return -ENOENT;
+ }
+ return 0;
+ }
+
+ if (!ctx->btf) {
+ ret = query_btf_context(ctx);
+ if (ret < 0 || ctx->nr_params == 0) {
+ trace_probe_log_err(ctx->offset, NO_BTF_ENTRY);
+ return PTR_ERR(params);
+ }
+ }
+ params = ctx->params;
+
+ for (i = 0; i < ctx->nr_params; i++) {
+ const char *name = btf_name_by_offset(ctx->btf, params[i].name_off);
+
+ if (name && !strcmp(name, varname)) {
+ code->op = FETCH_OP_ARG;
+ if (ctx->flags & TPARG_FL_TPOINT)
+ code->param = i + 1;
+ else
+ code->param = i;
+ tid = params[i].type;
+ goto found;
+ }
+ }
+ trace_probe_log_err(ctx->offset, NO_BTFARG);
+ return -ENOENT;
+
+found:
+ type = btf_type_skip_modifiers(ctx->btf, tid, &tid);
+ if (!type) {
+ trace_probe_log_err(ctx->offset, BAD_BTF_TID);
+ return -EINVAL;
+ }
+ /* Initialize the last type information */
+ ctx->last_type = type;
+ ctx->last_bitoffs = 0;
+ ctx->last_bitsize = 0;
+ if (field) {
+ ctx->offset += field - varname;
+ return parse_btf_field(field, type, pcode, end, ctx);
+ }
+ return 0;
+}
+
+static const struct fetch_type *find_fetch_type_from_btf_type(
+ struct traceprobe_parse_context *ctx)
+{
+ struct btf *btf = ctx->btf;
+ const char *typestr = NULL;
+
+ if (btf && ctx->last_type)
+ typestr = fetch_type_from_btf_type(btf, ctx->last_type, ctx);
+
+ return find_fetch_type(typestr, ctx->flags);
+}
+
+static int parse_btf_bitfield(struct fetch_insn **pcode,
+ struct traceprobe_parse_context *ctx)
+{
+ struct fetch_insn *code = *pcode;
+
+ if ((ctx->last_bitsize % 8 == 0) && ctx->last_bitoffs == 0)
+ return 0;
+
+ code++;
+ if (code->op != FETCH_OP_NOP) {
+ trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
+ return -EINVAL;
+ }
+ *pcode = code;
+
+ code->op = FETCH_OP_MOD_BF;
+ code->lshift = 64 - (ctx->last_bitsize + ctx->last_bitoffs);
+ code->rshift = 64 - ctx->last_bitsize;
+ code->basesize = 64 / 8;
+ return 0;
+}
+
+#else
+static void clear_btf_context(struct traceprobe_parse_context *ctx)
+{
+ ctx->btf = NULL;
+}
+
+static int query_btf_context(struct traceprobe_parse_context *ctx)
+{
+ return -EOPNOTSUPP;
+}
+
+static int parse_btf_arg(char *varname,
+ struct fetch_insn **pcode, struct fetch_insn *end,
+ struct traceprobe_parse_context *ctx)
+{
+ trace_probe_log_err(ctx->offset, NOSUP_BTFARG);
+ return -EOPNOTSUPP;
+}
+
+static int parse_btf_bitfield(struct fetch_insn **pcode,
+ struct traceprobe_parse_context *ctx)
+{
+ trace_probe_log_err(ctx->offset, NOSUP_BTFARG);
+ return -EOPNOTSUPP;
+}
+
+#define find_fetch_type_from_btf_type(ctx) \
+ find_fetch_type(NULL, ctx->flags)
+
+static int check_prepare_btf_string_fetch(char *typename,
+ struct fetch_insn **pcode,
+ struct traceprobe_parse_context *ctx)
+{
+ return 0;
+}
+
+#endif
+
#define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))
-static int parse_probe_vars(char *arg, const struct fetch_type *t,
- struct fetch_insn *code, unsigned int flags, int offs)
+/* Parse $vars. @orig_arg points '$', which syncs to @ctx->offset */
+static int parse_probe_vars(char *orig_arg, const struct fetch_type *t,
+ struct fetch_insn **pcode,
+ struct fetch_insn *end,
+ struct traceprobe_parse_context *ctx)
{
+ struct fetch_insn *code = *pcode;
+ int err = TP_ERR_BAD_VAR;
+ char *arg = orig_arg + 1;
unsigned long param;
int ret = 0;
int len;
- if (flags & TPARG_FL_TPOINT) {
+ if (ctx->flags & TPARG_FL_TEVENT) {
if (code->data)
return -EFAULT;
- code->data = kstrdup(arg, GFP_KERNEL);
- if (!code->data)
- return -ENOMEM;
- code->op = FETCH_OP_TP_ARG;
- } else if (strcmp(arg, "retval") == 0) {
- if (flags & TPARG_FL_RETURN) {
+ ret = parse_trace_event_arg(arg, code, ctx);
+ if (!ret)
+ return 0;
+ if (strcmp(arg, "comm") == 0 || strcmp(arg, "COMM") == 0) {
+ code->op = FETCH_OP_COMM;
+ return 0;
+ }
+ /* backward compatibility */
+ ctx->offset = 0;
+ goto inval;
+ }
+
+ if (str_has_prefix(arg, "retval")) {
+ if (!(ctx->flags & TPARG_FL_RETURN)) {
+ err = TP_ERR_RETVAL_ON_PROBE;
+ goto inval;
+ }
+ if (!(ctx->flags & TPARG_FL_KERNEL) ||
+ !IS_ENABLED(CONFIG_PROBE_EVENTS_BTF_ARGS)) {
code->op = FETCH_OP_RETVAL;
- } else {
- trace_probe_log_err(offs, RETVAL_ON_PROBE);
- ret = -EINVAL;
+ return 0;
}
- } else if ((len = str_has_prefix(arg, "stack"))) {
+ return parse_btf_arg(orig_arg, pcode, end, ctx);
+ }
+
+ len = str_has_prefix(arg, "stack");
+ if (len) {
+
if (arg[len] == '\0') {
code->op = FETCH_OP_STACKP;
- } else if (isdigit(arg[len])) {
+ return 0;
+ }
+
+ if (isdigit(arg[len])) {
ret = kstrtoul(arg + len, 10, &param);
- if (ret) {
- goto inval_var;
- } else if ((flags & TPARG_FL_KERNEL) &&
- param > PARAM_MAX_STACK) {
- trace_probe_log_err(offs, BAD_STACK_NUM);
- ret = -EINVAL;
- } else {
- code->op = FETCH_OP_STACK;
- code->param = (unsigned int)param;
+ if (ret)
+ goto inval;
+
+ if ((ctx->flags & TPARG_FL_KERNEL) &&
+ param > PARAM_MAX_STACK) {
+ err = TP_ERR_BAD_STACK_NUM;
+ goto inval;
}
- } else
- goto inval_var;
- } else if (strcmp(arg, "comm") == 0 || strcmp(arg, "COMM") == 0) {
+ code->op = FETCH_OP_STACK;
+ code->param = (unsigned int)param;
+ return 0;
+ }
+ goto inval;
+ }
+
+ if (strcmp(arg, "comm") == 0 || strcmp(arg, "COMM") == 0) {
code->op = FETCH_OP_COMM;
+ return 0;
+ }
+
#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
- } else if (((flags & TPARG_FL_MASK) ==
- (TPARG_FL_KERNEL | TPARG_FL_FENTRY)) &&
- (len = str_has_prefix(arg, "arg"))) {
+ len = str_has_prefix(arg, "arg");
+ if (len && tparg_is_function_entry(ctx->flags)) {
ret = kstrtoul(arg + len, 10, &param);
- if (ret) {
- goto inval_var;
- } else if (!param || param > PARAM_MAX_STACK) {
- trace_probe_log_err(offs, BAD_ARG_NUM);
- return -EINVAL;
+ if (ret)
+ goto inval;
+
+ if (!param || param > PARAM_MAX_STACK) {
+ err = TP_ERR_BAD_ARG_NUM;
+ goto inval;
}
+
code->op = FETCH_OP_ARG;
code->param = (unsigned int)param - 1;
+ /*
+ * The tracepoint probe will probe a stub function, and the
+ * first parameter of the stub is a dummy and should be ignored.
+ */
+ if (ctx->flags & TPARG_FL_TPOINT)
+ code->param++;
+ return 0;
+ }
#endif
- } else
- goto inval_var;
- return ret;
-
-inval_var:
- trace_probe_log_err(offs, BAD_VAR);
+inval:
+ __trace_probe_log_err(ctx->offset, err);
return -EINVAL;
}
@@ -378,7 +886,7 @@ static int __parse_imm_string(char *str, char **pbuf, int offs)
static int
parse_probe_arg(char *arg, const struct fetch_type *type,
struct fetch_insn **pcode, struct fetch_insn *end,
- unsigned int flags, int offs)
+ struct traceprobe_parse_context *ctx)
{
struct fetch_insn *code = *pcode;
unsigned long param;
@@ -389,13 +897,13 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
switch (arg[0]) {
case '$':
- ret = parse_probe_vars(arg + 1, type, code, flags, offs);
+ ret = parse_probe_vars(arg, type, pcode, end, ctx);
break;
case '%': /* named register */
- if (flags & TPARG_FL_TPOINT) {
- /* eprobes do not handle registers */
- trace_probe_log_err(offs, BAD_VAR);
+ if (ctx->flags & (TPARG_FL_TEVENT | TPARG_FL_FPROBE)) {
+ /* eprobe and fprobe do not handle registers */
+ trace_probe_log_err(ctx->offset, BAD_VAR);
break;
}
ret = regs_query_register_offset(arg + 1);
@@ -404,14 +912,14 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
code->param = (unsigned int)ret;
ret = 0;
} else
- trace_probe_log_err(offs, BAD_REG_NAME);
+ trace_probe_log_err(ctx->offset, BAD_REG_NAME);
break;
case '@': /* memory, file-offset or symbol */
if (isdigit(arg[1])) {
ret = kstrtoul(arg + 1, 0, &param);
if (ret) {
- trace_probe_log_err(offs, BAD_MEM_ADDR);
+ trace_probe_log_err(ctx->offset, BAD_MEM_ADDR);
break;
}
/* load address */
@@ -419,13 +927,13 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
code->immediate = param;
} else if (arg[1] == '+') {
/* kprobes don't support file offsets */
- if (flags & TPARG_FL_KERNEL) {
- trace_probe_log_err(offs, FILE_ON_KPROBE);
+ if (ctx->flags & TPARG_FL_KERNEL) {
+ trace_probe_log_err(ctx->offset, FILE_ON_KPROBE);
return -EINVAL;
}
ret = kstrtol(arg + 2, 0, &offset);
if (ret) {
- trace_probe_log_err(offs, BAD_FILE_OFFS);
+ trace_probe_log_err(ctx->offset, BAD_FILE_OFFS);
break;
}
@@ -433,8 +941,8 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
code->immediate = (unsigned long)offset; // imm64?
} else {
/* uprobes don't support symbols */
- if (!(flags & TPARG_FL_KERNEL)) {
- trace_probe_log_err(offs, SYM_ON_UPROBE);
+ if (!(ctx->flags & TPARG_FL_KERNEL)) {
+ trace_probe_log_err(ctx->offset, SYM_ON_UPROBE);
return -EINVAL;
}
/* Preserve symbol for updating */
@@ -443,7 +951,7 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
if (!code->data)
return -ENOMEM;
if (++code == end) {
- trace_probe_log_err(offs, TOO_MANY_OPS);
+ trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
return -EINVAL;
}
code->op = FETCH_OP_IMM;
@@ -451,7 +959,7 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
}
/* These are fetching from memory */
if (++code == end) {
- trace_probe_log_err(offs, TOO_MANY_OPS);
+ trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
return -EINVAL;
}
*pcode = code;
@@ -470,47 +978,51 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
arg++; /* Skip '+', because kstrtol() rejects it. */
tmp = strchr(arg, '(');
if (!tmp) {
- trace_probe_log_err(offs, DEREF_NEED_BRACE);
+ trace_probe_log_err(ctx->offset, DEREF_NEED_BRACE);
return -EINVAL;
}
*tmp = '\0';
ret = kstrtol(arg, 0, &offset);
if (ret) {
- trace_probe_log_err(offs, BAD_DEREF_OFFS);
+ trace_probe_log_err(ctx->offset, BAD_DEREF_OFFS);
break;
}
- offs += (tmp + 1 - arg) + (arg[0] != '-' ? 1 : 0);
+ ctx->offset += (tmp + 1 - arg) + (arg[0] != '-' ? 1 : 0);
arg = tmp + 1;
tmp = strrchr(arg, ')');
if (!tmp) {
- trace_probe_log_err(offs + strlen(arg),
+ trace_probe_log_err(ctx->offset + strlen(arg),
DEREF_OPEN_BRACE);
return -EINVAL;
} else {
- const struct fetch_type *t2 = find_fetch_type(NULL, flags);
+ const struct fetch_type *t2 = find_fetch_type(NULL, ctx->flags);
+ int cur_offs = ctx->offset;
*tmp = '\0';
- ret = parse_probe_arg(arg, t2, &code, end, flags, offs);
+ ret = parse_probe_arg(arg, t2, &code, end, ctx);
if (ret)
break;
+ ctx->offset = cur_offs;
if (code->op == FETCH_OP_COMM ||
code->op == FETCH_OP_DATA) {
- trace_probe_log_err(offs, COMM_CANT_DEREF);
+ trace_probe_log_err(ctx->offset, COMM_CANT_DEREF);
return -EINVAL;
}
if (++code == end) {
- trace_probe_log_err(offs, TOO_MANY_OPS);
+ trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
return -EINVAL;
}
*pcode = code;
code->op = deref;
code->offset = offset;
+ /* Reset the last type if used */
+ ctx->last_type = NULL;
}
break;
case '\\': /* Immediate value */
if (arg[1] == '"') { /* Immediate string */
- ret = __parse_imm_string(arg + 2, &tmp, offs + 2);
+ ret = __parse_imm_string(arg + 2, &tmp, ctx->offset + 2);
if (ret)
break;
code->op = FETCH_OP_DATA;
@@ -518,15 +1030,24 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
} else {
ret = str_to_immediate(arg + 1, &code->immediate);
if (ret)
- trace_probe_log_err(offs + 1, BAD_IMM);
+ trace_probe_log_err(ctx->offset + 1, BAD_IMM);
else
code->op = FETCH_OP_IMM;
}
break;
+ default:
+ if (isalpha(arg[0]) || arg[0] == '_') { /* BTF variable */
+ if (!tparg_is_function_entry(ctx->flags)) {
+ trace_probe_log_err(ctx->offset, NOSUP_BTFARG);
+ return -EINVAL;
+ }
+ ret = parse_btf_arg(arg, pcode, end, ctx);
+ break;
+ }
}
if (!ret && code->op == FETCH_OP_NOP) {
/* Parsed, but do not find fetch method */
- trace_probe_log_err(offs, BAD_FETCH_ARG);
+ trace_probe_log_err(ctx->offset, BAD_FETCH_ARG);
ret = -EINVAL;
}
return ret;
@@ -571,12 +1092,13 @@ static int __parse_bitfield_probe_arg(const char *bf,
/* String length checking wrapper */
static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
- struct probe_arg *parg, unsigned int flags, int offset)
+ struct probe_arg *parg,
+ struct traceprobe_parse_context *ctx)
{
struct fetch_insn *code, *scode, *tmp = NULL;
char *t, *t2, *t3;
- char *arg;
int ret, len;
+ char *arg;
arg = kstrdup(argv, GFP_KERNEL);
if (!arg)
@@ -585,10 +1107,10 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
ret = -EINVAL;
len = strlen(arg);
if (len > MAX_ARGSTR_LEN) {
- trace_probe_log_err(offset, ARG_TOO_LONG);
+ trace_probe_log_err(ctx->offset, ARG_TOO_LONG);
goto out;
} else if (len == 0) {
- trace_probe_log_err(offset, NO_ARG_BODY);
+ trace_probe_log_err(ctx->offset, NO_ARG_BODY);
goto out;
}
@@ -606,23 +1128,24 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
*t2++ = '\0';
t3 = strchr(t2, ']');
if (!t3) {
- offset += t2 + strlen(t2) - arg;
- trace_probe_log_err(offset,
+ int offs = t2 + strlen(t2) - arg;
+
+ trace_probe_log_err(ctx->offset + offs,
ARRAY_NO_CLOSE);
goto out;
} else if (t3[1] != '\0') {
- trace_probe_log_err(offset + t3 + 1 - arg,
+ trace_probe_log_err(ctx->offset + t3 + 1 - arg,
BAD_ARRAY_SUFFIX);
goto out;
}
*t3 = '\0';
if (kstrtouint(t2, 0, &parg->count) || !parg->count) {
- trace_probe_log_err(offset + t2 - arg,
+ trace_probe_log_err(ctx->offset + t2 - arg,
BAD_ARRAY_NUM);
goto out;
}
if (parg->count > MAX_ARRAY_LEN) {
- trace_probe_log_err(offset + t2 - arg,
+ trace_probe_log_err(ctx->offset + t2 - arg,
ARRAY_TOO_BIG);
goto out;
}
@@ -633,17 +1156,17 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
* Since $comm and immediate string can not be dereferenced,
* we can find those by strcmp. But ignore for eprobes.
*/
- if (!(flags & TPARG_FL_TPOINT) &&
+ if (!(ctx->flags & TPARG_FL_TEVENT) &&
(strcmp(arg, "$comm") == 0 || strcmp(arg, "$COMM") == 0 ||
strncmp(arg, "\\\"", 2) == 0)) {
/* The type of $comm must be "string", and not an array. */
if (parg->count || (t && strcmp(t, "string")))
goto out;
- parg->type = find_fetch_type("string", flags);
+ parg->type = find_fetch_type("string", ctx->flags);
} else
- parg->type = find_fetch_type(t, flags);
+ parg->type = find_fetch_type(t, ctx->flags);
if (!parg->type) {
- trace_probe_log_err(offset + (t ? (t - arg) : 0), BAD_TYPE);
+ trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0), BAD_TYPE);
goto out;
}
parg->offset = *size;
@@ -664,11 +1187,24 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
goto out;
code[FETCH_INSN_MAX - 1].op = FETCH_OP_END;
+ ctx->last_type = NULL;
ret = parse_probe_arg(arg, parg->type, &code, &code[FETCH_INSN_MAX - 1],
- flags, offset);
+ ctx);
if (ret)
goto fail;
+ /* Update storing type if BTF is available */
+ if (IS_ENABLED(CONFIG_PROBE_EVENTS_BTF_ARGS) &&
+ ctx->last_type) {
+ if (!t) {
+ parg->type = find_fetch_type_from_btf_type(ctx);
+ } else if (strstr(t, "string")) {
+ ret = check_prepare_btf_string_fetch(t, &code, ctx);
+ if (ret)
+ goto fail;
+ }
+ }
+
ret = -EINVAL;
/* Store operation */
if (parg->type->is_string) {
@@ -676,7 +1212,7 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
if (code->op != FETCH_OP_REG && code->op != FETCH_OP_STACK &&
code->op != FETCH_OP_RETVAL && code->op != FETCH_OP_ARG &&
code->op != FETCH_OP_DEREF && code->op != FETCH_OP_TP_ARG) {
- trace_probe_log_err(offset + (t ? (t - arg) : 0),
+ trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0),
BAD_SYMSTRING);
goto fail;
}
@@ -684,7 +1220,7 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
if (code->op != FETCH_OP_DEREF && code->op != FETCH_OP_UDEREF &&
code->op != FETCH_OP_IMM && code->op != FETCH_OP_COMM &&
code->op != FETCH_OP_DATA && code->op != FETCH_OP_TP_ARG) {
- trace_probe_log_err(offset + (t ? (t - arg) : 0),
+ trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0),
BAD_STRING);
goto fail;
}
@@ -703,7 +1239,7 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
*/
code++;
if (code->op != FETCH_OP_NOP) {
- trace_probe_log_err(offset, TOO_MANY_OPS);
+ trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
goto fail;
}
}
@@ -726,7 +1262,7 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
} else {
code++;
if (code->op != FETCH_OP_NOP) {
- trace_probe_log_err(offset, TOO_MANY_OPS);
+ trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
goto fail;
}
code->op = FETCH_OP_ST_RAW;
@@ -737,9 +1273,14 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
if (t != NULL) {
ret = __parse_bitfield_probe_arg(t, parg->type, &code);
if (ret) {
- trace_probe_log_err(offset + t - arg, BAD_BITFIELD);
+ trace_probe_log_err(ctx->offset + t - arg, BAD_BITFIELD);
goto fail;
}
+ } else if (IS_ENABLED(CONFIG_PROBE_EVENTS_BTF_ARGS) &&
+ ctx->last_type) {
+ ret = parse_btf_bitfield(&code, ctx);
+ if (ret)
+ goto fail;
}
ret = -EINVAL;
/* Loop(Array) operation */
@@ -747,13 +1288,13 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
if (scode->op != FETCH_OP_ST_MEM &&
scode->op != FETCH_OP_ST_STRING &&
scode->op != FETCH_OP_ST_USTRING) {
- trace_probe_log_err(offset + (t ? (t - arg) : 0),
+ trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0),
BAD_STRING);
goto fail;
}
code++;
if (code->op != FETCH_OP_NOP) {
- trace_probe_log_err(offset, TOO_MANY_OPS);
+ trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
goto fail;
}
code->op = FETCH_OP_LP_ARRAY;
@@ -801,8 +1342,35 @@ static int traceprobe_conflict_field_name(const char *name,
return 0;
}
+static char *generate_probe_arg_name(const char *arg, int idx)
+{
+ char *name = NULL;
+ const char *end;
+
+ /*
+ * If argument name is omitted, try arg as a name (BTF variable)
+ * or "argN".
+ */
+ if (IS_ENABLED(CONFIG_PROBE_EVENTS_BTF_ARGS)) {
+ end = strchr(arg, ':');
+ if (!end)
+ end = arg + strlen(arg);
+
+ name = kmemdup_nul(arg, end - arg, GFP_KERNEL);
+ if (!name || !is_good_name(name)) {
+ kfree(name);
+ name = NULL;
+ }
+ }
+
+ if (!name)
+ name = kasprintf(GFP_KERNEL, "arg%d", idx + 1);
+
+ return name;
+}
+
int traceprobe_parse_probe_arg(struct trace_probe *tp, int i, const char *arg,
- unsigned int flags)
+ struct traceprobe_parse_context *ctx)
{
struct probe_arg *parg = &tp->args[i];
const char *body;
@@ -822,8 +1390,7 @@ int traceprobe_parse_probe_arg(struct trace_probe *tp, int i, const char *arg,
parg->name = kmemdup_nul(arg, body - arg, GFP_KERNEL);
body++;
} else {
- /* If argument name is omitted, set "argN" */
- parg->name = kasprintf(GFP_KERNEL, "arg%d", i + 1);
+ parg->name = generate_probe_arg_name(arg, i);
body = arg;
}
if (!parg->name)
@@ -837,9 +1404,9 @@ int traceprobe_parse_probe_arg(struct trace_probe *tp, int i, const char *arg,
trace_probe_log_err(0, USED_ARG_NAME);
return -EINVAL;
}
+ ctx->offset = body - arg;
/* Parse fetch argument */
- return traceprobe_parse_probe_arg_body(body, &tp->size, parg, flags,
- body - arg);
+ return traceprobe_parse_probe_arg_body(body, &tp->size, parg, ctx);
}
void traceprobe_free_probe_arg(struct probe_arg *arg)
@@ -858,6 +1425,151 @@ void traceprobe_free_probe_arg(struct probe_arg *arg)
kfree(arg->fmt);
}
+static int argv_has_var_arg(int argc, const char *argv[], int *args_idx,
+ struct traceprobe_parse_context *ctx)
+{
+ int i, found = 0;
+
+ for (i = 0; i < argc; i++)
+ if (str_has_prefix(argv[i], "$arg")) {
+ trace_probe_log_set_index(i + 2);
+
+ if (!tparg_is_function_entry(ctx->flags)) {
+ trace_probe_log_err(0, NOFENTRY_ARGS);
+ return -EINVAL;
+ }
+
+ if (isdigit(argv[i][4])) {
+ found = 1;
+ continue;
+ }
+
+ if (argv[i][4] != '*') {
+ trace_probe_log_err(0, BAD_VAR);
+ return -EINVAL;
+ }
+
+ if (*args_idx >= 0 && *args_idx < argc) {
+ trace_probe_log_err(0, DOUBLE_ARGS);
+ return -EINVAL;
+ }
+ found = 1;
+ *args_idx = i;
+ }
+
+ return found;
+}
+
+static int sprint_nth_btf_arg(int idx, const char *type,
+ char *buf, int bufsize,
+ struct traceprobe_parse_context *ctx)
+{
+ const char *name;
+ int ret;
+
+ if (idx >= ctx->nr_params) {
+ trace_probe_log_err(0, NO_BTFARG);
+ return -ENOENT;
+ }
+ name = btf_name_by_offset(ctx->btf, ctx->params[idx].name_off);
+ if (!name) {
+ trace_probe_log_err(0, NO_BTF_ENTRY);
+ return -ENOENT;
+ }
+ ret = snprintf(buf, bufsize, "%s%s", name, type);
+ if (ret >= bufsize) {
+ trace_probe_log_err(0, ARGS_2LONG);
+ return -E2BIG;
+ }
+ return ret;
+}
+
+/* Return new_argv which must be freed after use */
+const char **traceprobe_expand_meta_args(int argc, const char *argv[],
+ int *new_argc, char *buf, int bufsize,
+ struct traceprobe_parse_context *ctx)
+{
+ const struct btf_param *params = NULL;
+ int i, j, n, used, ret, args_idx = -1;
+ const char **new_argv = NULL;
+
+ ret = argv_has_var_arg(argc, argv, &args_idx, ctx);
+ if (ret < 0)
+ return ERR_PTR(ret);
+
+ if (!ret) {
+ *new_argc = argc;
+ return NULL;
+ }
+
+ ret = query_btf_context(ctx);
+ if (ret < 0 || ctx->nr_params == 0) {
+ if (args_idx != -1) {
+ /* $arg* requires BTF info */
+ trace_probe_log_err(0, NOSUP_BTFARG);
+ return (const char **)params;
+ }
+ *new_argc = argc;
+ return NULL;
+ }
+
+ if (args_idx >= 0)
+ *new_argc = argc + ctx->nr_params - 1;
+ else
+ *new_argc = argc;
+
+ new_argv = kcalloc(*new_argc, sizeof(char *), GFP_KERNEL);
+ if (!new_argv)
+ return ERR_PTR(-ENOMEM);
+
+ used = 0;
+ for (i = 0, j = 0; i < argc; i++) {
+ trace_probe_log_set_index(i + 2);
+ if (i == args_idx) {
+ for (n = 0; n < ctx->nr_params; n++) {
+ ret = sprint_nth_btf_arg(n, "", buf + used,
+ bufsize - used, ctx);
+ if (ret < 0)
+ goto error;
+
+ new_argv[j++] = buf + used;
+ used += ret + 1;
+ }
+ continue;
+ }
+
+ if (str_has_prefix(argv[i], "$arg")) {
+ char *type = NULL;
+
+ n = simple_strtoul(argv[i] + 4, &type, 10);
+ if (type && !(*type == ':' || *type == '\0')) {
+ trace_probe_log_err(0, BAD_VAR);
+ ret = -ENOENT;
+ goto error;
+ }
+ /* Note: $argN starts from $arg1 */
+ ret = sprint_nth_btf_arg(n - 1, type, buf + used,
+ bufsize - used, ctx);
+ if (ret < 0)
+ goto error;
+ new_argv[j++] = buf + used;
+ used += ret + 1;
+ } else
+ new_argv[j++] = argv[i];
+ }
+
+ return new_argv;
+
+error:
+ kfree(new_argv);
+ return ERR_PTR(ret);
+}
+
+void traceprobe_finish_parse(struct traceprobe_parse_context *ctx)
+{
+ clear_btf_context(ctx);
+}
+
int traceprobe_update_arg(struct probe_arg *arg)
{
struct fetch_insn *code = arg->code;
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 6a4ecfb1da43..02b432ae7513 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -23,6 +23,7 @@
#include <linux/limits.h>
#include <linux/uaccess.h>
#include <linux/bitops.h>
+#include <linux/btf.h>
#include <asm/bitsperlong.h>
#include "trace.h"
@@ -32,7 +33,9 @@
#define MAX_ARGSTR_LEN 63
#define MAX_ARRAY_LEN 64
#define MAX_ARG_NAME_LEN 32
+#define MAX_BTF_ARGS_LEN 128
#define MAX_STRING_SIZE PATH_MAX
+#define MAX_ARG_BUF_LEN (MAX_TRACE_ARGS * MAX_ARG_NAME_LEN)
/* Reserved field names */
#define FIELD_STRING_IP "__probe_ip"
@@ -357,19 +360,58 @@ int trace_probe_print_args(struct trace_seq *s, struct probe_arg *args, int nr_a
#define trace_probe_for_each_link_rcu(pos, tp) \
list_for_each_entry_rcu(pos, &(tp)->event->files, list)
+/*
+ * The flags used for parsing trace_probe arguments.
+ * TPARG_FL_RETURN, TPARG_FL_FENTRY and TPARG_FL_TEVENT are mutually exclusive.
+ * TPARG_FL_KERNEL and TPARG_FL_USER are also mutually exclusive.
+ * TPARG_FL_FPROBE and TPARG_FL_TPOINT are optional but it should be with
+ * TPARG_FL_KERNEL.
+ */
#define TPARG_FL_RETURN BIT(0)
#define TPARG_FL_KERNEL BIT(1)
#define TPARG_FL_FENTRY BIT(2)
-#define TPARG_FL_TPOINT BIT(3)
+#define TPARG_FL_TEVENT BIT(3)
#define TPARG_FL_USER BIT(4)
-#define TPARG_FL_MASK GENMASK(4, 0)
+#define TPARG_FL_FPROBE BIT(5)
+#define TPARG_FL_TPOINT BIT(6)
+#define TPARG_FL_LOC_MASK GENMASK(4, 0)
+
+static inline bool tparg_is_function_entry(unsigned int flags)
+{
+ return (flags & TPARG_FL_LOC_MASK) == (TPARG_FL_KERNEL | TPARG_FL_FENTRY);
+}
+
+struct traceprobe_parse_context {
+ struct trace_event_call *event;
+ /* BTF related parameters */
+ const char *funcname; /* Function name in BTF */
+ const struct btf_type *proto; /* Prototype of the function */
+ const struct btf_param *params; /* Parameter of the function */
+ s32 nr_params; /* The number of the parameters */
+ struct btf *btf; /* The BTF to be used */
+ const struct btf_type *last_type; /* Saved type */
+ u32 last_bitoffs; /* Saved bitoffs */
+ u32 last_bitsize; /* Saved bitsize */
+ unsigned int flags;
+ int offset;
+};
extern int traceprobe_parse_probe_arg(struct trace_probe *tp, int i,
- const char *argv, unsigned int flags);
+ const char *argv,
+ struct traceprobe_parse_context *ctx);
+const char **traceprobe_expand_meta_args(int argc, const char *argv[],
+ int *new_argc, char *buf, int bufsize,
+ struct traceprobe_parse_context *ctx);
extern int traceprobe_update_arg(struct probe_arg *arg);
extern void traceprobe_free_probe_arg(struct probe_arg *arg);
+/*
+ * If either traceprobe_parse_probe_arg() or traceprobe_expand_meta_args() is called,
+ * this MUST be called for clean up the context and return a resource.
+ */
+void traceprobe_finish_parse(struct traceprobe_parse_context *ctx);
+
extern int traceprobe_split_symbol_offset(char *symbol, long *offset);
int traceprobe_parse_event_name(const char **pevent, const char **pgroup,
char *buf, int offset);
@@ -404,11 +446,12 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(REFCNT_OPEN_BRACE, "Reference counter brace is not closed"), \
C(BAD_REFCNT_SUFFIX, "Reference counter has wrong suffix"), \
C(BAD_UPROBE_OFFS, "Invalid uprobe offset"), \
- C(MAXACT_NO_KPROBE, "Maxactive is not for kprobe"), \
+ C(BAD_MAXACT_TYPE, "Maxactive is only for function exit"), \
C(BAD_MAXACT, "Invalid maxactive number"), \
C(MAXACT_TOO_BIG, "Maxactive is too big"), \
C(BAD_PROBE_ADDR, "Invalid probed address or symbol"), \
C(BAD_RETPROBE, "Retprobe address must be an function entry"), \
+ C(NO_TRACEPOINT, "Tracepoint is not found"), \
C(BAD_ADDR_SUFFIX, "Invalid probed address suffix"), \
C(NO_GROUP_NAME, "Group name is not specified"), \
C(GROUP_TOO_LONG, "Group name is too long"), \
@@ -418,6 +461,7 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(BAD_EVENT_NAME, "Event name must follow the same rules as C identifiers"), \
C(EVENT_EXIST, "Given group/event name is already used by another event"), \
C(RETVAL_ON_PROBE, "$retval is not available on probe"), \
+ C(NO_RETVAL, "This function returns 'void' type"), \
C(BAD_STACK_NUM, "Invalid stack number"), \
C(BAD_ARG_NUM, "Invalid argument number"), \
C(BAD_VAR, "Invalid $-valiable specified"), \
@@ -456,7 +500,21 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(NO_EVENT_INFO, "This requires both group and event name to attach"),\
C(BAD_ATTACH_EVENT, "Attached event does not exist"),\
C(BAD_ATTACH_ARG, "Attached event does not have this field"),\
- C(NO_EP_FILTER, "No filter rule after 'if'"),
+ C(NO_EP_FILTER, "No filter rule after 'if'"), \
+ C(NOSUP_BTFARG, "BTF is not available or not supported"), \
+ C(NO_BTFARG, "This variable is not found at this probe point"),\
+ C(NO_BTF_ENTRY, "No BTF entry for this probe point"), \
+ C(BAD_VAR_ARGS, "$arg* must be an independent parameter without name etc."),\
+ C(NOFENTRY_ARGS, "$arg* can be used only on function entry"), \
+ C(DOUBLE_ARGS, "$arg* can be used only once in the parameters"), \
+ C(ARGS_2LONG, "$arg* failed because the argument list is too long"), \
+ C(ARGIDX_2BIG, "$argN index is too big"), \
+ C(NO_PTR_STRCT, "This is not a pointer to union/structure."), \
+ C(NOSUP_DAT_ARG, "Non pointer structure/union argument is not supported."),\
+ C(BAD_HYPHEN, "Failed to parse single hyphen. Forgot '>'?"), \
+ C(NO_BTF_FIELD, "This field is not found."), \
+ C(BAD_BTF_TID, "Failed to get BTF type info."),\
+ C(BAD_TYPE4STR, "This type does not fit for string."),
#undef C
#define C(a, b) TP_ERR_##a
@@ -480,3 +538,8 @@ void __trace_probe_log_err(int offset, int err);
#define trace_probe_log_err(offs, err) \
__trace_probe_log_err(offs, TP_ERR_##err)
+
+struct uprobe_dispatch_data {
+ struct trace_uprobe *tu;
+ unsigned long bp_addr;
+};
diff --git a/kernel/trace/trace_probe_kernel.h b/kernel/trace/trace_probe_kernel.h
index c4e1d4c03a85..bb723eefd7b7 100644
--- a/kernel/trace/trace_probe_kernel.h
+++ b/kernel/trace/trace_probe_kernel.h
@@ -2,8 +2,6 @@
#ifndef __TRACE_PROBE_KERNEL_H_
#define __TRACE_PROBE_KERNEL_H_
-#define FAULT_STRING "(fault)"
-
/*
* This depends on trace_probe.h, but can not include it due to
* the way trace_probe_tmpl.h is used by trace_kprobe.c and trace_eprobe.c.
@@ -15,16 +13,8 @@ static nokprobe_inline int
fetch_store_strlen_user(unsigned long addr)
{
const void __user *uaddr = (__force const void __user *)addr;
- int ret;
- ret = strnlen_user_nofault(uaddr, MAX_STRING_SIZE);
- /*
- * strnlen_user_nofault returns zero on fault, insert the
- * FAULT_STRING when that occurs.
- */
- if (ret <= 0)
- return strlen(FAULT_STRING) + 1;
- return ret;
+ return strnlen_user_nofault(uaddr, MAX_STRING_SIZE);
}
/* Return the length of string -- including null terminal byte */
@@ -44,18 +34,14 @@ fetch_store_strlen(unsigned long addr)
len++;
} while (c && ret == 0 && len < MAX_STRING_SIZE);
- /* For faults, return enough to hold the FAULT_STRING */
- return (ret < 0) ? strlen(FAULT_STRING) + 1 : len;
+ return (ret < 0) ? ret : len;
}
-static nokprobe_inline void set_data_loc(int ret, void *dest, void *__dest, void *base, int len)
+static nokprobe_inline void set_data_loc(int ret, void *dest, void *__dest, void *base)
{
- if (ret >= 0) {
- *(u32 *)dest = make_data_loc(ret, __dest - base);
- } else {
- strscpy(__dest, FAULT_STRING, len);
- ret = strlen(__dest) + 1;
- }
+ if (ret < 0)
+ ret = 0;
+ *(u32 *)dest = make_data_loc(ret, __dest - base);
}
/*
@@ -76,7 +62,7 @@ fetch_store_string_user(unsigned long addr, void *dest, void *base)
__dest = get_loc_data(dest, base);
ret = strncpy_from_user_nofault(__dest, uaddr, maxlen);
- set_data_loc(ret, dest, __dest, base, maxlen);
+ set_data_loc(ret, dest, __dest, base);
return ret;
}
@@ -107,7 +93,7 @@ fetch_store_string(unsigned long addr, void *dest, void *base)
* probing.
*/
ret = strncpy_from_kernel_nofault(__dest, (void *)addr, maxlen);
- set_data_loc(ret, dest, __dest, base, maxlen);
+ set_data_loc(ret, dest, __dest, base);
return ret;
}
diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h
index 00707630788d..3935b347f874 100644
--- a/kernel/trace/trace_probe_tmpl.h
+++ b/kernel/trace/trace_probe_tmpl.h
@@ -156,11 +156,11 @@ stage3:
code++;
goto array;
case FETCH_OP_ST_USTRING:
- ret += fetch_store_strlen_user(val + code->offset);
+ ret = fetch_store_strlen_user(val + code->offset);
code++;
goto array;
case FETCH_OP_ST_SYMSTR:
- ret += fetch_store_symstrlen(val + code->offset);
+ ret = fetch_store_symstrlen(val + code->offset);
code++;
goto array;
default:
@@ -204,6 +204,8 @@ stage3:
array:
/* the last stage: Loop on array */
if (code->op == FETCH_OP_LP_ARRAY) {
+ if (ret < 0)
+ ret = 0;
total += ret;
if (++i < code->param) {
code = s3;
@@ -265,9 +267,7 @@ store_trace_args(void *data, struct trace_probe *tp, void *rec,
if (unlikely(arg->dynamic))
*dl = make_data_loc(maxlen, dyndata - base);
ret = process_fetch_insn(arg->code, rec, dl, base);
- if (unlikely(ret < 0 && arg->dynamic)) {
- *dl = make_data_loc(0, dyndata - base);
- } else {
+ if (arg->dynamic && likely(ret > 0)) {
dyndata += ret;
maxlen -= ret;
}
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 330aee1c1a49..0469a04a355f 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -168,6 +168,8 @@ static void wakeup_trace_open(struct trace_iterator *iter)
{
if (is_graph(iter->tr))
graph_trace_open(iter);
+ else
+ iter->private = NULL;
}
static void wakeup_trace_close(struct trace_iterator *iter)
diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c
index e5e299260d0c..bac06ee3b98b 100644
--- a/kernel/trace/trace_seq.c
+++ b/kernel/trace/trace_seq.c
@@ -131,6 +131,7 @@ EXPORT_SYMBOL_GPL(trace_seq_bitmask);
* trace_seq_vprintf - sequence printing of trace information
* @s: trace sequence descriptor
* @fmt: printf format string
+ * @args: Arguments for the format string
*
* The tracer may use either sequence operations or its own
* copy to user routines. To simplify formatting of a trace
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 942ddbdace4a..de753403cdaf 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -555,12 +555,15 @@ static int perf_call_bpf_enter(struct trace_event_call *call, struct pt_regs *re
struct syscall_trace_enter *rec)
{
struct syscall_tp_t {
- unsigned long long regs;
+ struct trace_entry ent;
unsigned long syscall_nr;
unsigned long args[SYSCALL_DEFINE_MAXARGS];
- } param;
+ } __aligned(8) param;
int i;
+ BUILD_BUG_ON(sizeof(param.ent) < sizeof(void *));
+
+ /* bpf prog requires 'regs' to be the first member in the ctx (a.k.a. &param) */
*(struct pt_regs **)&param = regs;
param.syscall_nr = rec->nr;
for (i = 0; i < sys_data->nb_args; i++)
@@ -657,11 +660,12 @@ static int perf_call_bpf_exit(struct trace_event_call *call, struct pt_regs *reg
struct syscall_trace_exit *rec)
{
struct syscall_tp_t {
- unsigned long long regs;
+ struct trace_entry ent;
unsigned long syscall_nr;
unsigned long ret;
- } param;
+ } __aligned(8) param;
+ /* bpf prog requires 'regs' to be the first member in the ctx (a.k.a. &param) */
*(struct pt_regs **)&param = regs;
param.syscall_nr = rec->nr;
param.ret = rec->ret;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 8b92e34ff0c8..99c051de412a 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -88,11 +88,6 @@ static struct trace_uprobe *to_trace_uprobe(struct dyn_event *ev)
static int register_uprobe_event(struct trace_uprobe *tu);
static int unregister_uprobe_event(struct trace_uprobe *tu);
-struct uprobe_dispatch_data {
- struct trace_uprobe *tu;
- unsigned long bp_addr;
-};
-
static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs);
static int uretprobe_dispatcher(struct uprobe_consumer *con,
unsigned long func, struct pt_regs *regs);
@@ -170,7 +165,8 @@ fetch_store_string(unsigned long addr, void *dest, void *base)
*/
ret++;
*(u32 *)dest = make_data_loc(ret, (void *)dst - base);
- }
+ } else
+ *(u32 *)dest = make_data_loc(0, (void *)dst - base);
return ret;
}
@@ -686,10 +682,13 @@ static int __trace_uprobe_create(int argc, const char **argv)
/* parse arguments */
for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+ struct traceprobe_parse_context ctx = {
+ .flags = (is_return ? TPARG_FL_RETURN : 0) | TPARG_FL_USER,
+ };
+
trace_probe_log_set_index(i + 2);
- ret = traceprobe_parse_probe_arg(&tu->tp, i, argv[i],
- (is_return ? TPARG_FL_RETURN : 0) |
- TPARG_FL_USER);
+ ret = traceprobe_parse_probe_arg(&tu->tp, i, argv[i], &ctx);
+ traceprobe_finish_parse(&ctx);
if (ret)
goto error;
}
@@ -1349,7 +1348,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
if (bpf_prog_array_valid(call)) {
u32 ret;
- ret = bpf_prog_run_array_sleepable(call->prog_array, regs, bpf_prog_run);
+ ret = bpf_prog_run_array_uprobe(call->prog_array, regs, bpf_prog_run);
if (!ret)
return;
}
@@ -1415,7 +1414,7 @@ static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func,
int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type,
const char **filename, u64 *probe_offset,
- bool perf_type_tracepoint)
+ u64 *probe_addr, bool perf_type_tracepoint)
{
const char *pevent = trace_event_name(event->tp_event);
const char *group = event->tp_event->class->system;
@@ -1432,6 +1431,7 @@ int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type,
: BPF_FD_TYPE_UPROBE;
*filename = tu->filename;
*probe_offset = tu->offset;
+ *probe_addr = 0;
return 0;
}
#endif /* CONFIG_PERF_EVENTS */
diff --git a/kernel/trace/tracing_map.h b/kernel/trace/tracing_map.h
index 2c765ee2a4d4..99c37eeebc16 100644
--- a/kernel/trace/tracing_map.h
+++ b/kernel/trace/tracing_map.h
@@ -272,10 +272,6 @@ extern u64 tracing_map_read_sum(struct tracing_map_elt *elt, unsigned int i);
extern u64 tracing_map_read_var(struct tracing_map_elt *elt, unsigned int i);
extern u64 tracing_map_read_var_once(struct tracing_map_elt *elt, unsigned int i);
-extern void tracing_map_set_field_descr(struct tracing_map *map,
- unsigned int i,
- unsigned int key_offset,
- tracing_map_cmp_fn_t cmp_fn);
extern int
tracing_map_sort_entries(struct tracing_map *map,
struct tracing_map_sort_key *sort_keys,