bpf: Introduce helper bpf_get_task_stack()

Introduce helper bpf_get_task_stack(), which dumps stack trace of given
task. This is different to bpf_get_stack(), which gets stack track of
current task. One potential use case of bpf_get_task_stack() is to call
it from bpf_iter__task and dump all /proc/<pid>/stack to a seq_file.

bpf_get_task_stack() uses stack_trace_save_tsk() instead of
get_perf_callchain() for kernel stack. The benefit of this choice is that
stack_trace_save_tsk() doesn't require changes in arch/. The downside of
using stack_trace_save_tsk() is that stack_trace_save_tsk() dumps the
stack trace to unsigned long array. For 32-bit systems, we need to
translate it to u64 array.

Signed-off-by: Song Liu <[email protected]>
Signed-off-by: Alexei Starovoitov <[email protected]>
Acked-by: Andrii Nakryiko <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]

Author: liu-song-6

Diff for: include/linux/bpf.h

@@ -1627,6 +1627,7 @@ extern const struct bpf_func_proto bpf_get_current_uid_gid_proto;
 extern const struct bpf_func_proto bpf_get_current_comm_proto;
 extern const struct bpf_func_proto bpf_get_stackid_proto;
 extern const struct bpf_func_proto bpf_get_stack_proto;
+extern const struct bpf_func_proto bpf_get_task_stack_proto;
 extern const struct bpf_func_proto bpf_sock_map_update_proto;
 extern const struct bpf_func_proto bpf_sock_hash_update_proto;
 extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto;

Diff for: include/uapi/linux/bpf.h

@@ -3285,6 +3285,39 @@ union bpf_attr {
  *		Dynamically cast a *sk* pointer to a *udp6_sock* pointer.
  *	Return
  *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * 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.
+ *		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*.
+ *
+ *		The last argument, *flags*, holds the number of stack frames to
+ *		skip (from 0 to 255), masked with
+ *		**BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set
+ *		the following flags:
+ *
+ *		**BPF_F_USER_STACK**
+ *			Collect a user space stack instead of a kernel stack.
+ *		**BPF_F_USER_BUILD_ID**
+ *			Collect buildid+offset instead of ips for user stack,
+ *			only valid if **BPF_F_USER_STACK** is also specified.
+ *
+ *		**bpf_get_task_stack**\ () can collect up to
+ *		**PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
+ *		to sufficient large buffer size. Note that
+ *		this limit can be controlled with the **sysctl** program, and
+ *		that it should be manually increased in order to profile long
+ *		user stacks (such as stacks for Java programs). To do so, use:
+ *
+ *		::
+ *
+ *			# sysctl kernel.perf_event_max_stack=<new value>
+ *	Return
+ *		A non-negative value equal to or less than *size* on success,
+ *		or a negative error in case of failure.
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3427,7 +3460,9 @@ union bpf_attr {
 	FN(skc_to_tcp_sock),		\
 	FN(skc_to_tcp_timewait_sock),	\
 	FN(skc_to_tcp_request_sock),	\
-	FN(skc_to_udp6_sock),
+	FN(skc_to_udp6_sock),		\
+	FN(get_task_stack),		\
+	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

Diff for: kernel/bpf/stackmap.c

@@ -348,6 +348,40 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 	}
 }
 
+static struct perf_callchain_entry *
+get_callchain_entry_for_task(struct task_struct *task, u32 init_nr)
+{
+	struct perf_callchain_entry *entry;
+	int rctx;
+
+	entry = get_callchain_entry(&rctx);
+
+	if (!entry)
+		return NULL;
+
+	entry->nr = init_nr +
+		stack_trace_save_tsk(task, (unsigned long *)(entry->ip + init_nr),
+				     sysctl_perf_event_max_stack - init_nr, 0);
+
+	/* stack_trace_save_tsk() works on unsigned long array, while
+	 * perf_callchain_entry uses u64 array. For 32-bit systems, it is
+	 * necessary to fix this mismatch.
+	 */
+	if (__BITS_PER_LONG != 64) {
+		unsigned long *from = (unsigned long *) entry->ip;
+		u64 *to = entry->ip;
+		int i;
+
+		/* copy data from the end to avoid using extra buffer */
+		for (i = entry->nr - 1; i >= (int)init_nr; i--)
+			to[i] = (u64)(from[i]);
+	}
+
+	put_callchain_entry(rctx);
+
+	return entry;
+}
+
 BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
 	   u64, flags)
 {
@@ -448,8 +482,8 @@ const struct bpf_func_proto bpf_get_stackid_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
-	   u64, flags)
+static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
+			    void *buf, u32 size, u64 flags)
 {
 	u32 init_nr, trace_nr, copy_len, elem_size, num_elem;
 	bool user_build_id = flags & BPF_F_USER_BUILD_ID;
@@ -471,13 +505,22 @@ BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
 	if (unlikely(size % elem_size))
 		goto clear;
 
+	/* cannot get valid user stack for task without user_mode regs */
+	if (task && user && !user_mode(regs))
+		goto err_fault;
+
 	num_elem = size / elem_size;
 	if (sysctl_perf_event_max_stack < num_elem)
 		init_nr = 0;
 	else
 		init_nr = sysctl_perf_event_max_stack - num_elem;
-	trace = get_perf_callchain(regs, init_nr, kernel, user,
-				   sysctl_perf_event_max_stack, false, false);
+
+	if (kernel && task)
+		trace = get_callchain_entry_for_task(task, init_nr);
+	else
+		trace = get_perf_callchain(regs, init_nr, kernel, user,
+					   sysctl_perf_event_max_stack,
+					   false, false);
 	if (unlikely(!trace))
 		goto err_fault;
 
@@ -505,6 +548,12 @@ BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
 	return err;
 }
 
+BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
+	   u64, flags)
+{
+	return __bpf_get_stack(regs, NULL, buf, size, flags);
+}
+
 const struct bpf_func_proto bpf_get_stack_proto = {
 	.func		= bpf_get_stack,
 	.gpl_only	= true,
@@ -515,6 +564,26 @@ const struct bpf_func_proto bpf_get_stack_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
+	   u32, size, u64, flags)
+{
+	struct pt_regs *regs = task_pt_regs(task);
+
+	return __bpf_get_stack(regs, task, buf, size, flags);
+}
+
+static int bpf_get_task_stack_btf_ids[5];
+const struct bpf_func_proto bpf_get_task_stack_proto = {
+	.func		= bpf_get_task_stack,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
+	.btf_id		= bpf_get_task_stack_btf_ids,
+};
+
 /* Called from eBPF program */
 static void *stack_map_lookup_elem(struct bpf_map *map, void *key)
 {

Diff for: kernel/bpf/verifier.c

@@ -4864,7 +4864,9 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	if (err)
 		return err;
 
-	if (func_id == BPF_FUNC_get_stack && !env->prog->has_callchain_buf) {
+	if ((func_id == BPF_FUNC_get_stack ||
+	     func_id == BPF_FUNC_get_task_stack) &&
+	    !env->prog->has_callchain_buf) {
 		const char *err_str;
 
 #ifdef CONFIG_PERF_EVENTS

Diff for: kernel/trace/bpf_trace.c

@@ -1137,6 +1137,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_ringbuf_query_proto;
 	case BPF_FUNC_jiffies64:
 		return &bpf_jiffies64_proto;
+	case BPF_FUNC_get_task_stack:
+		return &bpf_get_task_stack_proto;
 	default:
 		return NULL;
 	}

Diff for: scripts/bpf_helpers_doc.py

@@ -426,6 +426,7 @@ class PrinterHelpers(Printer):
             'struct tcp_timewait_sock',
             'struct tcp_request_sock',
             'struct udp6_sock',
+            'struct task_struct',
 
             'struct __sk_buff',
             'struct sk_msg_md',
@@ -468,6 +469,7 @@ class PrinterHelpers(Printer):
             'struct tcp_timewait_sock',
             'struct tcp_request_sock',
             'struct udp6_sock',
+            'struct task_struct',
     }
     mapped_types = {
             'u8': '__u8',

Diff for: tools/include/uapi/linux/bpf.h

@@ -3285,6 +3285,39 @@ union bpf_attr {
  *		Dynamically cast a *sk* pointer to a *udp6_sock* pointer.
  *	Return
  *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * 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.
+ *		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*.
+ *
+ *		The last argument, *flags*, holds the number of stack frames to
+ *		skip (from 0 to 255), masked with
+ *		**BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set
+ *		the following flags:
+ *
+ *		**BPF_F_USER_STACK**
+ *			Collect a user space stack instead of a kernel stack.
+ *		**BPF_F_USER_BUILD_ID**
+ *			Collect buildid+offset instead of ips for user stack,
+ *			only valid if **BPF_F_USER_STACK** is also specified.
+ *
+ *		**bpf_get_task_stack**\ () can collect up to
+ *		**PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
+ *		to sufficient large buffer size. Note that
+ *		this limit can be controlled with the **sysctl** program, and
+ *		that it should be manually increased in order to profile long
+ *		user stacks (such as stacks for Java programs). To do so, use:
+ *
+ *		::
+ *
+ *			# sysctl kernel.perf_event_max_stack=<new value>
+ *	Return
+ *		A non-negative value equal to or less than *size* on success,
+ *		or a negative error in case of failure.
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3427,7 +3460,9 @@ union bpf_attr {
 	FN(skc_to_tcp_sock),		\
 	FN(skc_to_tcp_timewait_sock),	\
 	FN(skc_to_tcp_request_sock),	\
-	FN(skc_to_udp6_sock),
+	FN(skc_to_udp6_sock),		\
+	FN(get_task_stack),		\
+	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call