[PATCH v2 bpf-next] bpf: add crosstask check to __bpf_get_stack

[Jordan Rome <jordalgo@meta.com>]

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@meta.com>
---

Changes in v2:
* Return -EOPNOTSUPP in __bpf_get_stack if crosstask and user stack
* Remove changes to bpf selftests (will make a separate patch)

v1:
https://lore.kernel.org/bpf/20231106221423.564362-1-jordalgo@meta.com/

 include/uapi/linux/bpf.h       |  3 +++
 kernel/bpf/stackmap.c          | 11 ++++++++++-
 tools/include/uapi/linux/bpf.h |  3 +++
 3 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0f6cdf52b1da..bda948a685e5 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4517,6 +4517,8 @@ 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*.
@@ -4528,6 +4530,7 @@ 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 d6b277482085..dff7ba539701 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -388,6 +388,7 @@ 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;
@@ -410,6 +411,14 @@ 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)
@@ -421,7 +430,7 @@ 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 0f6cdf52b1da..bda948a685e5 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4517,6 +4517,8 @@ 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*.
@@ -4528,6 +4530,7 @@ 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.
-- 
2.39.3