[RFC PATCH 8/8] tracing: probeevent: Add an array for basic types

From: Masami Hiramatsu
Date: Tue Feb 13 2018 - 10:40:06 EST

Add an array for basic types. This allows user to get arraied
basic types from memory address.
The array type syntax is

TYPE[N]

Where TYPE is one of basic type (u8/16/32/64,s8/16/32/64, and
x8/16/32/64) and N is a fixed value.

Signed-off-by: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
---
Documentation/trace/kprobetrace.txt | 7 ++
kernel/trace/trace_kprobe.c | 17 +++++
kernel/trace/trace_probe.c | 111 ++++++++++++++++++++++++++---------
kernel/trace/trace_probe.h | 29 ++++++++-
kernel/trace/trace_uprobe.c | 17 +++++
5 files changed, 144 insertions(+), 37 deletions(-)

diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt
index ec34640becbd..17d3e1a97d85 100644
--- a/Documentation/trace/kprobetrace.txt
+++ b/Documentation/trace/kprobetrace.txt
@@ -65,6 +65,13 @@ in decimal ('s' and 'u') or hexadecimal ('x'). Without type casting, 'x32'
or 'x64' is used depends on the architecture (e.g. x86-32 uses x32, and
x86-64 uses x64).

+These value types can be an array. To record array data, you can add '[N]'
+(where N is a fixed number, less than 64) to the base type.
+E.g. 'x16[4]' means an array of x16 (2bytes hex) with 4 elements.
+Note that the array can be applied to memory type fetchargs, you can not
+apply it to registers/stack-entries etc. (for example, '$stack1:x8[8]' is
+wrong, but '+8($stack):x8[8]' is OK.)
+
String type is a special type, which fetches a "null-terminated" string from
kernel space. This means it will fail and store NULL if the string container
has been paged out.
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index cab5efe0a66c..45e00de573d3 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -835,8 +835,9 @@ static int
process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest,
bool pre)
{
+ struct fetch_insn *s3 = NULL;
unsigned long val;
- int ret;
+ int ret, i = 0;

/* 1st stage: get value from context */
switch (code->op) {
@@ -877,6 +878,8 @@ process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest,
code++;
}

+stage3:
+ s3 = code;
/* 3rd stage: store value to buffer */
switch (code->op) {
case FETCH_OP_ST_RAW:
@@ -902,6 +905,16 @@ process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest,
code++;
}

+ /* the last stage: Loop on array */
+ if (code->op == FETCH_OP_LP_ARRAY) {
+ if (++i < code->param) {
+ code = s3;
+ val += s3->size;
+ dest += s3->size;
+ goto stage3;
+ }
+ }
+
return code->op == FETCH_OP_END ? 0 : -EILSEQ;
}
NOKPROBE_SYMBOL(process_fetch_insn)
@@ -1248,7 +1261,7 @@ static int register_kprobe_event(struct trace_kprobe *tk)
call->event.funcs = &kprobe_funcs;
call->class->define_fields = kprobe_event_define_fields;
}
- if (set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0)
+ if (traceprobe_set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0)
return -ENOMEM;
ret = register_trace_event(&call->event);
if (!ret) {
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 491a640a1a3e..ae96f98506f0 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -378,8 +378,8 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
struct probe_arg *parg, unsigned int flags)
{
struct fetch_insn *code, *tmp = NULL;
- const char *t;
- int ret;
+ char *t, *t2;
+ int ret, len;

if (strlen(arg) > MAX_ARGSTR_LEN) {
pr_info("Argument is too long.: %s\n", arg);
@@ -390,24 +390,40 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
pr_info("Failed to allocate memory for command '%s'.\n", arg);
return -ENOMEM;
}
- t = strchr(parg->comm, ':');
+ t = strchr(arg, ':');
if (t) {
- arg[t - parg->comm] = '\0';
- t++;
+ *t = '\0';
+ t2 = strchr(++t, '[');
+ if (t2) {
+ *t2 = '\0';
+ parg->count = simple_strtoul(t2 + 1, &t2, 0);
+ if (strcmp(t2, "]") || parg->count == 0)
+ return -EINVAL;
+ }
}
/*
* The default type of $comm should be "string", and it can't be
* dereferenced.
*/
if (!t && strcmp(arg, "$comm") == 0)
- t = "string";
- parg->type = find_fetch_type(t);
+ parg->type = find_fetch_type("string");
+ else
+ parg->type = find_fetch_type(t);
if (!parg->type) {
pr_info("Unsupported type: %s\n", t);
return -EINVAL;
}
parg->offset = *size;
- *size += parg->type->size;
+ *size += parg->type->size * (parg->count ?: 1);
+
+ if (parg->count) {
+ len = strlen(parg->type->fmttype) + 6;
+ parg->fmt = kmalloc(len, GFP_KERNEL);
+ if (!parg->fmt)
+ return -ENOMEM;
+ snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype,
+ parg->count);
+ }

code = tmp = kzalloc(sizeof(*code) * FETCH_INSN_MAX, GFP_KERNEL);
if (!code)
@@ -453,6 +469,21 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
if (ret)
goto fail;
}
+ /* Loop(Array) operation */
+ if (parg->count) {
+ if (code->op != FETCH_OP_ST_MEM) {
+ pr_info("array only accepts memory or address\n");
+ ret = -EINVAL;
+ goto fail;
+ }
+ code++;
+ if (code->op != FETCH_OP_NOP) {
+ ret = -E2BIG;
+ goto fail;
+ }
+ code->op = FETCH_OP_LP_ARRAY;
+ code->param = parg->count;
+ }
code++;
code->op = FETCH_OP_END;

@@ -491,14 +522,17 @@ void traceprobe_free_probe_arg(struct probe_arg *arg)
kfree(arg->code);
kfree(arg->name);
kfree(arg->comm);
+ kfree(arg->fmt);
}

+/* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
static int __set_print_fmt(struct trace_probe *tp, char *buf, int len,
bool is_return)
{
- int i;
+ struct probe_arg *parg;
+ int i, j;
int pos = 0;
-
const char *fmt, *arg;

if (!is_return) {
@@ -509,35 +543,51 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len,
arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
}

- /* When len=0, we just calculate the needed length */
-#define LEN_OR_ZERO (len ? len - pos : 0)
-
pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);

for (i = 0; i < tp->nr_args; i++) {
- pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s",
- tp->args[i].name, tp->args[i].type->fmt);
+ parg = tp->args + i;
+ pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=", parg->name);
+ if (parg->count) {
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "{%s",
+ parg->type->fmt);
+ for (j = 1; j < parg->count; j++)
+ pos += snprintf(buf + pos, LEN_OR_ZERO, ",%s",
+ parg->type->fmt);
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "}");
+ } else
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "%s",
+ parg->type->fmt);
}

pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);

for (i = 0; i < tp->nr_args; i++) {
- if (strcmp(tp->args[i].type->name, "string") == 0)
+ parg = tp->args + i;
+ if (parg->count) {
+ if (strcmp(parg->type->name, "string") == 0)
+ fmt = ", __get_str(%s[%d])";
+ else
+ fmt = ", REC->%s[%d]";
+ for (j = 0; j < parg->count; j++)
+ pos += snprintf(buf + pos, LEN_OR_ZERO,
+ fmt, parg->name, j);
+ } else {
+ if (strcmp(parg->type->name, "string") == 0)
+ fmt = ", __get_str(%s)";
+ else
+ fmt = ", REC->%s";
pos += snprintf(buf + pos, LEN_OR_ZERO,
- ", __get_str(%s)",
- tp->args[i].name);
- else
- pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
- tp->args[i].name);
+ fmt, parg->name);
+ }
}

-#undef LEN_OR_ZERO
-
/* return the length of print_fmt */
return pos;
}
+#undef LEN_OR_ZERO

-int set_print_fmt(struct trace_probe *tp, bool is_return)
+int traceprobe_set_print_fmt(struct trace_probe *tp, bool is_return)
{
int len;
char *print_fmt;
@@ -563,11 +613,16 @@ int traceprobe_define_arg_fields(struct trace_event_call *event_call,
/* Set argument names as fields */
for (i = 0; i < tp->nr_args; i++) {
struct probe_arg *parg = &tp->args[i];
-
- ret = trace_define_field(event_call, parg->type->fmttype,
- parg->name,
+ const char *fmt = parg->type->fmttype;
+ int size = parg->type->size;
+
+ if (parg->fmt)
+ fmt = parg->fmt;
+ if (parg->count)
+ size *= parg->count;
+ ret = trace_define_field(event_call, fmt, parg->name,
offset + parg->offset,
- parg->type->size,
+ parg->type->size * parg->count,
parg->type->is_signed,
FILTER_OTHER);
if (ret)
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index c23aa7e20502..62e68e4ef80b 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -114,6 +114,8 @@ enum fetch_op {
FETCH_OP_ST_STRING, /* String: .offset, .size */
// Stage 4 (modify) op
FETCH_OP_MOD_BF, /* Bitfield: .basesize, .lshift, .rshift */
+ // Stage 5 (loop) op
+ FETCH_OP_LP_ARRAY, /* Array: .param = loop count */
FETCH_OP_END,
};

@@ -203,13 +205,16 @@ DECLARE_BASIC_PRINT_TYPE_FUNC(symbol);
_ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, atype)

#define ASSIGN_FETCH_TYPE_END {}
+#define MAX_ARRAY_LEN 64

struct probe_arg {
struct fetch_insn *code;
bool dynamic;/* Dynamic array (string) is used */
unsigned int offset; /* Offset from argument entry */
+ unsigned int count; /* Array count */
const char *name; /* Name of this argument */
const char *comm; /* Command of this argument */
+ char *fmt; /* Format string if needed */
const struct fetch_type *type; /* Type of this argument */
};

@@ -385,16 +390,30 @@ static inline int
print_probe_args(struct trace_seq *s, struct probe_arg *args, int nr_args,
u8 *data, void *field)
{
- int i;
+ void *p;
+ int i, j;

for (i = 0; i < nr_args; i++) {
- trace_seq_printf(s, " %s=", args[i].name);
- if (!args[i].type->print(s, data + args[i].offset, field))
- return -ENOMEM;
+ struct probe_arg *a = args + i;
+
+ trace_seq_printf(s, " %s=", a->name);
+ if (likely(!a->count)) {
+ if (!a->type->print(s, data + a->offset, field))
+ return -ENOMEM;
+ continue;
+ }
+ trace_seq_putc(s, '{');
+ p = data + a->offset;
+ for (j = 0; j < a->count; j++) {
+ if (!a->type->print(s, p, field))
+ return -ENOMEM;
+ trace_seq_putc(s, j == a->count - 1 ? '}' : ',');
+ p += a->type->size;
+ }
}
return 0;
}

-extern int set_print_fmt(struct trace_probe *tp, bool is_return);
+extern int traceprobe_set_print_fmt(struct trace_probe *tp, bool is_return);
extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
size_t offset, struct trace_probe *tp);
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index d6479af1e6ac..6fc7ea0159d4 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -173,8 +173,9 @@ static int
process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest,
bool pre)
{
+ struct fetch_insn *s3 = NULL;
unsigned long val;
- int ret;
+ int ret, i = 0;

/* 1st stage: get value from context */
switch (code->op) {
@@ -210,6 +211,8 @@ process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest,
code++;
}

+stage3:
+ s3 = code;
/* 3rd stage: store value to buffer */
switch (code->op) {
case FETCH_OP_ST_RAW:
@@ -235,6 +238,16 @@ process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest,
code++;
}

+ /* the last stage: Loop on array */
+ if (code->op == FETCH_OP_LP_ARRAY) {
+ if (++i < code->param) {
+ code = s3;
+ val += s3->size;
+ dest += s3->size;
+ goto stage3;
+ }
+ }
+
return code->op == FETCH_OP_END ? 0 : -EILSEQ;
}
NOKPROBE_SYMBOL(process_fetch_insn)
@@ -1303,7 +1316,7 @@ static int register_uprobe_event(struct trace_uprobe *tu)
call->event.funcs = &uprobe_funcs;
call->class->define_fields = uprobe_event_define_fields;

- if (set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0)
+ if (traceprobe_set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0)
return -ENOMEM;

ret = register_trace_event(&call->event);