Message-Id: <155127868250.32576.2419537726154240743.stgit@devbox>
Date:   Wed, 27 Feb 2019 23:44:42 +0900
From:   Masami Hiramatsu <mhiramat@...nel.org>
To:     Steven Rostedt <rostedt@...dmis.org>,
        Linus Torvalds <torvalds@...ux-foundation.org>
Cc:     mhiramat@...nel.org, linux-kernel@...r.kernel.org,
        Andy Lutomirski <luto@...capital.net>,
        Ingo Molnar <mingo@...nel.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Changbin Du <changbin.du@...il.com>,
        Jann Horn <jannh@...gle.com>,
        Kees Cook <keescook@...omium.org>,
        Andy Lutomirski <luto@...nel.org>,
        Alexei Starovoitov <alexei.starovoitov@...il.com>,
        Nadav Amit <namit@...are.com>,
        Peter Zijlstra <peterz@...radead.org>
Subject: [PATCH v3 5/5] 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 arch.

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

Signed-off-by: Masami Hiramatsu <mhiramat@...nel.org>
---
 Changes in v3:
  - Add a section for user memory access to the document.
---
 Documentation/trace/kprobetrace.rst  |   25 ++++++++++++++++++++-----
 Documentation/trace/uprobetracer.rst |    9 +++++----
 kernel/trace/trace.c                 |    5 +++--
 kernel/trace/trace_kprobe.c          |    6 ++++++
 kernel/trace/trace_probe.c           |   27 +++++++++++++++++++++------
 kernel/trace/trace_probe.h           |    2 ++
 kernel/trace/trace_probe_tmpl.h      |   23 ++++++++++++++++++-----
 kernel/trace/trace_uprobe.c          |    7 +++++++
 8 files changed, 82 insertions(+), 22 deletions(-)

diff --git a/Documentation/trace/kprobetrace.rst b/Documentation/trace/kprobetrace.rst
index a3ac7c9ac242..876e555b6bbc 100644
--- a/Documentation/trace/kprobetrace.rst
+++ b/Documentation/trace/kprobetrace.rst
@@ -51,7 +51,7 @@ Synopsis of kprobe_events
   $argN		: Fetch the Nth function argument. (N >= 1) (\*1)
   $retval	: Fetch return value.(\*2)
   $comm		: Fetch current task comm.
-  +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(\*3)
+  +|-[u]OFFS(FETCHARG) : Fetch memory at FETCHARG +|- OFFS address.(\*3)(\*4)
   NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
   FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
 		  (u8/u16/u32/u64/s8/s16/s32/s64), hexadecimal types
@@ -61,6 +61,7 @@ Synopsis of kprobe_events
   (\*1) only for the probe on function entry (offs == 0).
   (\*2) only for return probe.
   (\*3) this is useful for fetching a field of data structures.
+  (\*4) "u" means user-space dereference. See :ref:`user_mem_access`.
 
 Types
 -----
@@ -79,10 +80,7 @@ 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. "ustring" type is an alternative of string for user-space.
-Note that kprobe-event provides string/ustring types, but doesn't change it
-automatically. So user has to decide if the targe string in kernel or in user
-space carefully. On some arch, if you choose wrong one, it always fails to
-record string data.
+See :ref:`user_mem_access` for more info..
 The string array type is a bit different from other types. For other base
 types, <base-type>[1] is equal to <base-type> (e.g. +0(%di):x32[1] is same
 as +0(%di):x32.) But string[1] is not equal to string. The string type itself
@@ -97,6 +95,23 @@ Symbol type('symbol') is an alias of u32 or u64 type (depends on BITS_PER_LONG)
 which shows given pointer in "symbol+offset" style.
 For $comm, the default type is "string"; any other type is invalid.
 
+.. _user_mem_access:
+User Memory Access
+------------------
+Kprobe events supports user-space memory access. For that purpose, you can use
+either user-space dereference syntax or 'ustring' type.
+
+user-space dereference syntax allows you to access a field of a data structure
+n user-space. This is done by "u" prefix with dereference syntax. For example,
++u4(%si) means read a user memory from the user-space address %si+4. You can
+use this for string too, e.g. +u0(%si):string means that the read a user space
+string from the address where %si register points. 'ustring' is a kind of
+short-cut. You can use +0(%si):ustring instead of that.
+
+Note that kprobe-event provides user-memory access syntax, but it doesn't
+use it transparently. This means if you use normal dereference or string type
+for user memory, it might fail, and always fails on some arch. So user has to
+check if the targe data is in kernel or in user space carefully.
 
 Per-Probe Event Filtering
 -------------------------
diff --git a/Documentation/trace/uprobetracer.rst b/Documentation/trace/uprobetracer.rst
index 4c3bfde2ba47..6144423b2368 100644
--- a/Documentation/trace/uprobetracer.rst
+++ b/Documentation/trace/uprobetracer.rst
@@ -42,16 +42,17 @@ Synopsis of uprobe_tracer
    @+OFFSET	: Fetch memory at OFFSET (OFFSET from same file as PATH)
    $stackN	: Fetch Nth entry of stack (N >= 0)
    $stack	: Fetch stack address.
-   $retval	: Fetch return value.(*)
+   $retval	: Fetch return value.(\*1)
    $comm	: Fetch current task comm.
-   +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**)
+   +|-[u]OFFS(FETCHARG) : Fetch memory at FETCHARG +|- OFFS address.(\*2)(\*3)
    NAME=FETCHARG     : Set NAME as the argument name of FETCHARG.
    FETCHARG:TYPE     : Set TYPE as the type of FETCHARG. Currently, basic types
 		       (u8/u16/u32/u64/s8/s16/s32/s64), hexadecimal types
 		       (x8/x16/x32/x64), "string" and bitfield are supported.
 
-  (*) only for return probe.
-  (**) this is useful for fetching a field of data structures.
+  (\*1) only for return probe.
+  (\*2) this is useful for fetching a field of data structures.
+  (\*3) Unlike kprobe event, "u" prefix will be just ignored.
 
 Types
 -----
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4cacbb0e1538..5408a82a015d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4638,10 +4638,11 @@ 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 8b04cae5fd86..c3b8564c263f 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -939,6 +939,12 @@ 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 a7012de37a00..0efef172db17 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -239,6 +239,7 @@ 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;
@@ -301,8 +302,17 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
 		break;
 
 	case '+':	/* deref memory */
-		arg++;	/* Skip '+', because kstrtol() rejects it. */
 	case '-':
+		if (arg[0] == '+') {
+			arg++;	/* Skip '+', because kstrtol() rejects it. */
+			if (arg[0] == 'u') {
+				deref = FETCH_OP_UDEREF;
+				arg++;
+			}
+		} else if (arg[1] == 'u') {	/* Start with "-u" */
+			deref = FETCH_OP_UDEREF;
+			*(++arg) = '-';
+		}
 		tmp = strchr(arg, '(');
 		if (!tmp)
 			return -EINVAL;
@@ -328,7 +338,7 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
 				return -E2BIG;
 			*pcode = code;
 
-			code->op = FETCH_OP_DEREF;
+			code->op = deref;
 			code->offset = offset;
 		}
 		break;
@@ -444,13 +454,14 @@ 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) {
 			pr_info("string only accepts memory or address.\n");
 			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
@@ -463,7 +474,8 @@ 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;
@@ -472,6 +484,9 @@ 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 cf4ba8bbb841..a5e8b2ac2c97 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -91,9 +91,11 @@ 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 7526f6f8d7b0..06f2d901c4cf 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 +118,10 @@ process_fetch_insn_bottom(struct fetch_insn *code, unsigned long val,
 	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 92facae8c3d8..a86afc9e2a6a 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.

Powered by blists - more mailing lists