tracing/probe: Support user-space dereference

Support user-space dereference syntax for probe event arguments
to dereference the data-structure or array in user-space.

The syntax is just adding 'u' before an offset value.

 +|-u<OFFSET>(<FETCHARG>)

e.g. +u8(%ax), +u0(+0(%si))

For example, if you probe do_sched_setscheduler(pid, policy,
param) and record param->sched_priority, you can add new
probe as below;

 p do_sched_setscheduler priority=+u0($arg3)

Note that kprobe event provides this and it doesn't change the
dereference method automatically because we do not know whether
the given address is in userspace or kernel on some archs.

So as same as "ustring", this is an option for user, who has to
carefully choose the dereference method.

Link: http://lkml.kernel.org/r/155789872187.26965.4468456816590888687.stgit@devnote2

Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>

6 files changed, 53 insertions, 14 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index d3a477a16e70..6b3b5b0495a8 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4842,10 +4842,11 @@ static const char readme_msg[] =
 	"\t     args: <name>=fetcharg[:type]\n"
 	"\t fetcharg: %<register>, @<address>, @<symbol>[+|-<offset>],\n"
 #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
-	"\t           $stack<index>, $stack, $retval, $comm, $arg<N>\n"
+	"\t           $stack<index>, $stack, $retval, $comm, $arg<N>,\n"
 #else
-	"\t           $stack<index>, $stack, $retval, $comm\n"
+	"\t           $stack<index>, $stack, $retval, $comm,\n"
 #endif
+	"\t           +|-[u]<offset>(<fetcharg>)\n"
 	"\t     type: s8/16/32/64, u8/16/32/64, x8/16/32/64, string, symbol,\n"
 	"\t           b<bit-width>@<bit-offset>/<container-size>, ustring,\n"
 	"\t           <type>\\[<array-size>\\]\n"
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 439bf04d14ce..ff14eb011c1c 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -952,6 +952,12 @@ probe_mem_read(void *dest, void *src, size_t size)
 	return probe_kernel_read(dest, src, size);
 }
 
+static nokprobe_inline int
+probe_mem_read_user(void *dest, void *src, size_t size)
+{
+	return probe_user_read(dest, src, size);
+}
+
 /* Note that we don't verify it, since the code does not come from user space */
 static int
 process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest,
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 5a0470f7b9de..b6b0593844cd 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -324,6 +324,7 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
 {
 	struct fetch_insn *code = *pcode;
 	unsigned long param;
+	int deref = FETCH_OP_DEREF;
 	long offset = 0;
 	char *tmp;
 	int ret = 0;
@@ -396,9 +397,14 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
 		break;
 
 	case '+':	/* deref memory */
-		arg++;	/* Skip '+', because kstrtol() rejects it. */
-		/* fall through */
 	case '-':
+		if (arg[1] == 'u') {
+			deref = FETCH_OP_UDEREF;
+			arg[1] = arg[0];
+			arg++;
+		}
+		if (arg[0] == '+')
+			arg++;	/* Skip '+', because kstrtol() rejects it. */
 		tmp = strchr(arg, '(');
 		if (!tmp) {
 			trace_probe_log_err(offs, DEREF_NEED_BRACE);
@@ -434,7 +440,7 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
 			}
 			*pcode = code;
 
-			code->op = FETCH_OP_DEREF;
+			code->op = deref;
 			code->offset = offset;
 		}
 		break;
@@ -573,14 +579,15 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 	/* Store operation */
 	if (!strcmp(parg->type->name, "string") ||
 	    !strcmp(parg->type->name, "ustring")) {
-		if (code->op != FETCH_OP_DEREF && code->op != FETCH_OP_IMM &&
-		    code->op != FETCH_OP_COMM) {
+		if (code->op != FETCH_OP_DEREF && code->op != FETCH_OP_UDEREF &&
+		    code->op != FETCH_OP_IMM && code->op != FETCH_OP_COMM) {
 			trace_probe_log_err(offset + (t ? (t - arg) : 0),
 					    BAD_STRING);
 			ret = -EINVAL;
 			goto fail;
 		}
-		if (code->op != FETCH_OP_DEREF || parg->count) {
+		if ((code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM) ||
+		     parg->count) {
 			/*
 			 * IMM and COMM is pointing actual address, those must
 			 * be kept, and if parg->count != 0, this is an array
@@ -594,7 +601,8 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 			}
 		}
 		/* If op == DEREF, replace it with STRING */
-		if (!strcmp(parg->type->name, "ustring"))
+		if (!strcmp(parg->type->name, "ustring") ||
+		    code->op == FETCH_OP_UDEREF)
 			code->op = FETCH_OP_ST_USTRING;
 		else
 			code->op = FETCH_OP_ST_STRING;
@@ -603,6 +611,9 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 	} else if (code->op == FETCH_OP_DEREF) {
 		code->op = FETCH_OP_ST_MEM;
 		code->size = parg->type->size;
+	} else if (code->op == FETCH_OP_UDEREF) {
+		code->op = FETCH_OP_ST_UMEM;
+		code->size = parg->type->size;
 	} else {
 		code++;
 		if (code->op != FETCH_OP_NOP) {
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index c7546e7ff8e2..42816358dd48 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -92,9 +92,11 @@ enum fetch_op {
 	FETCH_OP_FOFFS,		/* File offset: .immediate */
 	// Stage 2 (dereference) op
 	FETCH_OP_DEREF,		/* Dereference: .offset */
+	FETCH_OP_UDEREF,	/* User-space Dereference: .offset */
 	// Stage 3 (store) ops
 	FETCH_OP_ST_RAW,	/* Raw: .size */
 	FETCH_OP_ST_MEM,	/* Mem: .offset, .size */
+	FETCH_OP_ST_UMEM,	/* Mem: .offset, .size */
 	FETCH_OP_ST_STRING,	/* String: .offset, .size */
 	FETCH_OP_ST_USTRING,	/* User String: .offset, .size */
 	// Stage 4 (modify) op
diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h
index 2e9e4dae8839..e5282828f4a6 100644
--- a/kernel/trace/trace_probe_tmpl.h
+++ b/kernel/trace/trace_probe_tmpl.h
@@ -64,6 +64,8 @@ static nokprobe_inline int
 fetch_store_string_user(unsigned long addr, void *dest, void *base);
 static nokprobe_inline int
 probe_mem_read(void *dest, void *src, size_t size);
+static nokprobe_inline int
+probe_mem_read_user(void *dest, void *src, size_t size);
 
 /* From the 2nd stage, routine is same */
 static nokprobe_inline int
@@ -77,14 +79,21 @@ process_fetch_insn_bottom(struct fetch_insn *code, unsigned long val,
 
 stage2:
 	/* 2nd stage: dereference memory if needed */
-	while (code->op == FETCH_OP_DEREF) {
-		lval = val;
-		ret = probe_mem_read(&val, (void *)val + code->offset,
-					sizeof(val));
+	do {
+		if (code->op == FETCH_OP_DEREF) {
+			lval = val;
+			ret = probe_mem_read(&val, (void *)val + code->offset,
+					     sizeof(val));
+		} else if (code->op == FETCH_OP_UDEREF) {
+			lval = val;
+			ret = probe_mem_read_user(&val,
+				 (void *)val + code->offset, sizeof(val));
+		} else
+			break;
 		if (ret)
 			return ret;
 		code++;
-	}
+	} while (1);
 
 	s3 = code;
 stage3:
@@ -109,6 +118,9 @@ stage3:
 	case FETCH_OP_ST_MEM:
 		probe_mem_read(dest, (void *)val + code->offset, code->size);
 		break;
+	case FETCH_OP_ST_UMEM:
+		probe_mem_read_user(dest, (void *)val + code->offset, code->size);
+		break;
 	case FETCH_OP_ST_STRING:
 		loc = *(u32 *)dest;
 		ret = fetch_store_string(val + code->offset, dest, base);
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 852e998051f6..3d6b868830f3 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -140,6 +140,13 @@ probe_mem_read(void *dest, void *src, size_t size)
 
 	return copy_from_user(dest, vaddr, size) ? -EFAULT : 0;
 }
+
+static nokprobe_inline int
+probe_mem_read_user(void *dest, void *src, size_t size)
+{
+	return probe_mem_read(dest, src, size);
+}
+
 /*
  * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
  * length and relative data location.