This is a note to let you know that I've just added the patch titled
bpf: Add crosstask check to __bpf_get_stack
to the 5.10-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
bpf-add-crosstask-check-to-__bpf_get_stack.patch
and it can be found in the queue-5.10 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 5bd104386354ee4678843f41b961b36e3dcc6264
Author: Jordan Rome <jordalgo@xxxxxxxx>
Date: Wed Nov 8 03:23:34 2023 -0800
bpf: Add crosstask check to __bpf_get_stack
[ Upstream commit b8e3a87a627b575896e448021e5c2f8a3bc19931 ]
Currently get_perf_callchain only supports user stack walking for
the current task. Passing the correct *crosstask* param will return
0 frames if the task passed to __bpf_get_stack isn't the current
one instead of a single incorrect frame/address. This change
passes the correct *crosstask* param but also does a preemptive
check in __bpf_get_stack if the task is current and returns
-EOPNOTSUPP if it is not.
This issue was found using bpf_get_task_stack inside a BPF
iterator ("iter/task"), which iterates over all tasks.
bpf_get_task_stack works fine for fetching kernel stacks
but because get_perf_callchain relies on the caller to know
if the requested *task* is the current one (via *crosstask*)
it was failing in a confusing way.
It might be possible to get user stacks for all tasks utilizing
something like access_process_vm but that requires the bpf
program calling bpf_get_task_stack to be sleepable and would
therefore be a breaking change.
Fixes: fa28dcb82a38 ("bpf: Introduce helper bpf_get_task_stack()")
Signed-off-by: Jordan Rome <jordalgo@xxxxxxxx>
Signed-off-by: Andrii Nakryiko <andrii@xxxxxxxxxx>
Link: https://lore.kernel.org/bpf/20231108112334.3433136-1-jordalgo@xxxxxxxx
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 36ddfb98b70e..29cc0eb2e488 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3424,6 +3424,8 @@ union bpf_attr {
* long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags)
* Description
* Return a user or a kernel stack in bpf program provided buffer.
+ * Note: the user stack will only be populated if the *task* is
+ * the current task; all other tasks will return -EOPNOTSUPP.
* To achieve this, the helper needs *task*, which is a valid
* pointer to **struct task_struct**. To store the stacktrace, the
* bpf program provides *buf* with a nonnegative *size*.
@@ -3435,6 +3437,7 @@ union bpf_attr {
*
* **BPF_F_USER_STACK**
* Collect a user space stack instead of a kernel stack.
+ * The *task* must be the current task.
* **BPF_F_USER_BUILD_ID**
* Collect buildid+offset instead of ips for user stack,
* only valid if **BPF_F_USER_STACK** is also specified.
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 0c5bf98d5576..b8afea2ceeeb 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -575,6 +575,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
{
u32 trace_nr, copy_len, elem_size, num_elem, max_depth;
bool user_build_id = flags & BPF_F_USER_BUILD_ID;
+ bool crosstask = task && task != current;
u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
bool user = flags & BPF_F_USER_STACK;
struct perf_callchain_entry *trace;
@@ -597,6 +598,14 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
if (task && user && !user_mode(regs))
goto err_fault;
+ /* get_perf_callchain does not support crosstask user stack walking
+ * but returns an empty stack instead of NULL.
+ */
+ if (crosstask && user) {
+ err = -EOPNOTSUPP;
+ goto clear;
+ }
+
num_elem = size / elem_size;
max_depth = num_elem + skip;
if (sysctl_perf_event_max_stack < max_depth)
@@ -608,7 +617,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
trace = get_callchain_entry_for_task(task, max_depth);
else
trace = get_perf_callchain(regs, 0, kernel, user, max_depth,
- false, false);
+ crosstask, false);
if (unlikely(!trace))
goto err_fault;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index fd1a4d843e6f..63ea5bc6f1c4 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3424,6 +3424,8 @@ union bpf_attr {
* long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags)
* Description
* Return a user or a kernel stack in bpf program provided buffer.
+ * Note: the user stack will only be populated if the *task* is
+ * the current task; all other tasks will return -EOPNOTSUPP.
* To achieve this, the helper needs *task*, which is a valid
* pointer to **struct task_struct**. To store the stacktrace, the
* bpf program provides *buf* with a nonnegative *size*.
@@ -3435,6 +3437,7 @@ union bpf_attr {
*
* **BPF_F_USER_STACK**
* Collect a user space stack instead of a kernel stack.
+ * The *task* must be the current task.
* **BPF_F_USER_BUILD_ID**
* Collect buildid+offset instead of ips for user stack,
* only valid if **BPF_F_USER_STACK** is also specified.
