Skip to contentSkip to conversation

tracing: probeevent: Fix probe argument parser and handler

PATCH Applied Masami Hiramatsu 2 participants 9 messages May 7, 2019 – May 8, 2019 1 message not in the archive

Subsystems (2)
lore
Share & tools
lore

Masami Hiramatsu

author maintainer
#0 lore raw

v3 cover tracing: probeevent: Fix probe argument parser and handler

Hi,

Here is the 3rd version of series to fix several bugs in probe event argument parser and handler routines.

In this version I updated patch [1/3] according to Steve's comment.

I got 2 issues reported by Andreas, see
https://www.mail-archive.com/[email protected]/msg1899098.html

One issue is already fixed by Andreas (Thanks!) but $comm handling issue still exists on uprobe event. [1/3] fixes it.
And I found other issues around that, [2/3] is just a trivial cleanup, [3/3] fixes $comm type issue which occurs not only uprobe events but also on kprobe events. Anyway, after this series applied, $comm must be "string" type and not be an array.

Thank you,

---

Masami Hiramatsu (3):
tracing: uprobes: Re-enable $comm support for uprobe events
tracing: probeevent: Do not accumulate on ret variable
tracing: probeevent: Fix to make the type of $comm string

 kernel/trace/trace_probe.c      |   13 +++++++------
 kernel/trace/trace_probe.h      |    1 +
 kernel/trace/trace_probe_tmpl.h |    2 +-
 kernel/trace/trace_uprobe.c     |   13 +++++++++++--
 4 files changed, 20 insertions(+), 9 deletions(-)

--
Masami Hiramatsu <[email protected]>

author maintainer
#1 lore raw

PATCH v3 1/3 tracing: uprobes: Re-enable $comm support for uprobe events

Since commit 533059281ee5 ("tracing: probeevent: Introduce new argument fetching code") dropped the $comm support from uprobe events, this re-enables it.

For $comm support, uses strlcpy() instead of strncpy_from_user() to copy current task's comm. Because it is in the kernel space, strncpy_from_user() always fails to copy the comm. This also uses strlen() instead of strnlen_user() to measure the length of the comm.

Note that this uses -ECOMM as a token value to fetch the comm string. If the user-space pointer points -ECOMM, it will be translated to task->comm.

Fixes 533059281ee5 ("tracing: probeevent: Introduce new argument fetching code")

---
Changes in v3
- Always add +1 to strlen() result.
- Use -ECOMM as a token to specify current->comm.

---
 kernel/trace/trace_probe.h  |    1 +
 kernel/trace/trace_uprobe.c |   13 +++++++++++--
 2 files changed, 12 insertions(+), 2 deletions(-)
kernel/trace/trace_probe.h +1 -0
index b7737666c1a8..f9a8c632188b 100644
@@ -124,6 +124,7 @@ struct fetch_insn {
 
 /* fetch + deref*N + store + mod + end <= 16, this allows N=12, enough */
 #define FETCH_INSN_MAX	16
+#define FETCH_TOKEN_COMM	(-ECOMM)
 
 /* Fetch type information table */
 struct fetch_type {
kernel/trace/trace_uprobe.c +11 -2
index cd8750a72768..eb7e06b54741 100644
@@ -156,7 +156,10 @@ fetch_store_string(unsigned long addr, void *dest, void *base)
 	if (unlikely(!maxlen))
 		return -ENOMEM;
 
-	ret = strncpy_from_user(dst, src, maxlen);
+	if (addr == FETCH_TOKEN_COMM)
+		ret = strlcpy(dst, current->comm, maxlen);
+	else
+		ret = strncpy_from_user(dst, src, maxlen);
 	if (ret >= 0) {
 		if (ret == maxlen)
 			dst[ret - 1] = '\0';
@@ -180,7 +183,10 @@ fetch_store_strlen(unsigned long addr)
 	int len;
 	void __user *vaddr = (void __force __user *) addr;
 
-	len = strnlen_user(vaddr, MAX_STRING_SIZE);
+	if (addr == FETCH_TOKEN_COMM)
+		len = strlen(current->comm) + 1;
+	else
+		len = strnlen_user(vaddr, MAX_STRING_SIZE);
 
 	return (len > MAX_STRING_SIZE) ? 0 : len;
 }
@@ -220,6 +226,9 @@ process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest,
 	case FETCH_OP_IMM:
 		val = code->immediate;
 		break;
+	case FETCH_OP_COMM:
+		val = FETCH_TOKEN_COMM;
+		break;
 	case FETCH_OP_FOFFS:
 		val = translate_user_vaddr(code->immediate);
 		break;
author maintainer
#2 lore raw

PATCH v3 2/3 tracing: probeevent: Do not accumulate on ret variable

In reply to Masami Hiramatsu

Do not accumulate strlen result on "ret" local variable, because it is accumulated on "total" local variable for array case.

Fixes 40b53b771806 ("tracing: probeevent: Add array type support")
---
 kernel/trace/trace_probe_tmpl.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/trace/trace_probe_tmpl.h +1 -1
index 4737bb8c07a3..c30c61f12ddd 100644
@@ -88,7 +88,7 @@ process_fetch_insn_bottom(struct fetch_insn *code, unsigned long val,
 	/* 3rd stage: store value to buffer */
 	if (unlikely(!dest)) {
 		if (code->op == FETCH_OP_ST_STRING) {
-			ret += fetch_store_strlen(val + code->offset);
+			ret = fetch_store_strlen(val + code->offset);
 			code++;
 			goto array;
 		} else
author maintainer
#3 lore raw

PATCH v3 3/3 tracing: probeevent: Fix to make the type of $comm string

In reply to Masami Hiramatsu

Fix to make the type of $comm "string".
If we set the other type to $comm argument, it shows meaningless value or wrong data. Currently probe events allow us to set string array type (e.g. ":string[2]"), or other digit types like x8 on $comm. But since clearly $comm is just a string data, it should not be fetched by other types including array.

Fixes 35abb67de744 ("tracing: expose current->comm to [ku]probe events")
---
 kernel/trace/trace_probe.c |   13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)
kernel/trace/trace_probe.c +7 -6
index 4cc2d467d34c..e0d1d5353464 100644
@@ -533,13 +533,14 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 			}
 		}
 	}
-	/*
-	 * The default type of $comm should be "string", and it can't be
-	 * dereferenced.
-	 */
-	if (!t && strcmp(arg, "$comm") == 0)
+
+	/* Since $comm can not be dereferred, we can find $comm by strcmp */
+	if (strcmp(arg, "$comm") == 0) {
+		/* The type of $comm must be "string", and not an array. */
+		if (parg->count || (t && strcmp(t, "string")))
+			return -EINVAL;
 		parg->type = find_fetch_type("string");
-	else
+	} else
 		parg->type = find_fetch_type(t);
 	if (!parg->type) {
 		trace_probe_log_err(offset + (t ? (t - arg) : 0), BAD_TYPE);

A message that is not in the archive (sent off-list or not yet received): [email protected]

author maintainer
#5 lore raw

Re: [PATCH v3 3/3] tracing: probeevent: Fix to make the type of $comm string

Quoted 59 lines · On Tue, 07 May 2019 17:47:57 +0000 Sasha Levin <[email protected]> wrote:

Hi,

[This is an automated email]

This commit has been processed because it contains a "Fixes:" tag, fixing commit: 35abb67de744 tracing: expose current->comm to [ku]probe events.

The bot has tested the following trees: v5.0.13, v4.19.40, v4.14.116, v4.9.173.

v5.0.13: Build OK!
v4.19.40: Failed to apply! Possible dependencies:
40b53b771806 ("tracing: probeevent: Add array type support") 533059281ee5 ("tracing: probeevent: Introduce new argument fetching code") 56de76305279 ("tracing: probeevent: Cleanup print argument functions") 60c2e0cebfd0 ("tracing: probeevent: Add symbol type") eeb07b061500 ("tracing: probeevent: Cleanup argument field definition") f451bc89d835 ("tracing: probeevent: Unify fetch type tables")

v4.14.116: Failed to apply! Possible dependencies:
40b53b771806 ("tracing: probeevent: Add array type support") 45408c4f9250 ("tracing: kprobes: Prohibit probing on notrace function") 4bebdc7a85aa ("bpf: add helper bpf_perf_prog_read_value")
533059281ee5 ("tracing: probeevent: Introduce new argument fetching code") 60c2e0cebfd0 ("tracing: probeevent: Add symbol type")
908432ca84fc ("bpf: add helper bpf_perf_event_read_value for perf event array map") 97562633bcba ("bpf: perf event change needed for subsequent bpf helpers") 9802d86585db ("bpf: add a bpf_override_function helper")
b4da3340eae2 ("tracing/kprobe: bpf: Check error injectable event is on function entry") cd86d1fd2102 ("bpf: Adding helper function bpf_getsockops")
dd0bb688eaa2 ("bpf: add a bpf_override_function helper")
de8f3a83b0a0 ("bpf: add meta pointer for direct access")
f3edacbd697f ("bpf: Revert bpf_overrid_function() helper changes.") f451bc89d835 ("tracing: probeevent: Unify fetch type tables")

v4.9.173: Failed to apply! Possible dependencies:
17bedab27231 ("bpf: xdp: Allow head adjustment in XDP prog") 1d9995771fcb ("s390: update defconfigs")
23a4e389bdc7 ("nfp: create separate define for max number of vectors") 40b53b771806 ("tracing: probeevent: Add array type support") 45408c4f9250 ("tracing: kprobes: Prohibit probing on notrace function") 533059281ee5 ("tracing: probeevent: Introduce new argument fetching code") 60c2e0cebfd0 ("tracing: probeevent: Add symbol type")
67f8b1dcb9ee ("net/mlx4_en: Refactor the XDP forwarding rings scheme") 68453c7a8973 ("nfp: centralize runtime reconfiguration logic") 6b0b7551428e ("perf/core: Rename CONFIG_[UK]PROBE_EVENT to CONFIG_[UK]PROBE_EVENTS") 7ff5c83a1deb ("nfp: simplify nfp_net_poll()")
9802d86585db ("bpf: add a bpf_override_function helper")
a4b562bb8ebd ("nfp: use unsigned int for vector/ring counts") b4da3340eae2 ("tracing/kprobe: bpf: Check error injectable event is on function entry") cbeaf7aa733a ("nfp: bring back support for different ring counts") ccc109b8ed24 ("net/mlx4_en: Add TX_XDP for CQ types")
dd0bb688eaa2 ("bpf: add a bpf_override_function helper")
e390b55d5aef ("bpf: make bpf_xdp_adjust_head support mandatory") ecd63a0217d5 ("nfp: add XDP support in the driver")
f18f97ac43d7 ("tracing/kprobes: Add a helper method to return number of probe hits") f3edacbd697f ("bpf: Revert bpf_overrid_function() helper changes.") f451bc89d835 ("tracing: probeevent: Unify fetch type tables")

Quoted 2 lines

How should we proceed with this patch?

Thanks for the report! I missed the Fixes tag. I realized that the comm type check was done in other place in older kernel. This bug was introduced by commit 533059281ee5 ("tracing: probeevent: Introduce new argument fetching code").

Thank you,

Signature · 1 line
Masami Hiramatsu <[email protected]>
maintainer
#6 lore raw

Re: [PATCH v3 3/3] tracing: probeevent: Fix to make the type of $comm string

Quoted 6 lines · On Wed, 8 May 2019 12:24:03 +0900 Masami Hiramatsu <[email protected]> wrote:
Quoted 2 lines

How should we proceed with this patch?

Thanks for the report! I missed the Fixes tag. I realized that the comm type check was done in other place in older kernel. This bug was introduced by commit 533059281ee5 ("tracing: probeevent: Introduce new argument fetching code").

I've applied this to my queue. Should I change the Fixes to the above commit?

-- Steve

author maintainer
#7 lore raw

Re: [PATCH v3 3/3] tracing: probeevent: Fix to make the type of $comm string

Quoted 11 lines · On Tue, 7 May 2019 23:29:09 -0400 Steven Rostedt <[email protected]> wrote:
Quoted 6 lines · On Wed, 8 May 2019 12:24:03 +0900 Masami Hiramatsu <[email protected]> wrote:
Quoted 2 lines

How should we proceed with this patch?

Thanks for the report! I missed the Fixes tag. I realized that the comm type check was done in other place in older kernel. This bug was introduced by commit 533059281ee5 ("tracing: probeevent: Introduce new argument fetching code").

I've applied this to my queue. Should I change the Fixes to the above commit?

Thanks! Yes, please update the Fixes tag to 533059281ee5, that is the correct commit.

Thank you,

Signature · 1 line
Masami Hiramatsu <[email protected]>
maintainer Applied
#8 lore raw
In reply to Masami Hiramatsu
Quoted 11 lines · On Tue, 7 May 2019 22:55:22 +0900 Masami Hiramatsu <[email protected]> wrote:

Hi,

Here is the 3rd version of series to fix several bugs in probe event argument parser and handler routines.

In this version I updated patch [1/3] according to Steve's comment.

I got 2 issues reported by Andreas, see
https://www.mail-archive.com/[email protected]/msg1899098.html

Quoted 7 lines

One issue is already fixed by Andreas (Thanks!) but $comm handling issue still exists on uprobe event. [1/3] fixes it.
And I found other issues around that, [2/3] is just a trivial cleanup, [3/3] fixes $comm type issue which occurs not only uprobe events but also on kprobe events. Anyway, after this series applied, $comm must be "string" type and not be an array.

Thanks Masami,

I applied these to my queue.

-- Steve

author maintainer
#9 lore raw
Quoted 22 lines · On Tue, 7 May 2019 22:10:06 -0400 Steven Rostedt <[email protected]> wrote:
Quoted 11 lines · On Tue, 7 May 2019 22:55:22 +0900 Masami Hiramatsu <[email protected]> wrote:

Hi,

Here is the 3rd version of series to fix several bugs in probe event argument parser and handler routines.

In this version I updated patch [1/3] according to Steve's comment.

I got 2 issues reported by Andreas, see
https://www.mail-archive.com/[email protected]/msg1899098.html

Quoted 7 lines

One issue is already fixed by Andreas (Thanks!) but $comm handling issue still exists on uprobe event. [1/3] fixes it.
And I found other issues around that, [2/3] is just a trivial cleanup, [3/3] fixes $comm type issue which occurs not only uprobe events but also on kprobe events. Anyway, after this series applied, $comm must be "string" type and not be an array.

Quoted 3 lines

Thanks Masami,

I applied these to my queue.

Thank you, Steve! I'll rebase other series on that.

Signature · 1 line
Masami Hiramatsu <[email protected]>