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 <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200630062846.664389-3-songliubraving@fb.com

3 files changed, 78 insertions, 5 deletions

diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 071f98d0f7c6..5ad72ab2276b 100644
--- a/kernel/bpf/stackmap.c
+++ b/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 @@ clear:
 	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 --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7de98906ddf4..b608185e1ffd 100644
--- a/kernel/bpf/verifier.c
+++ b/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 --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 5d59dda5f661..977ba3b6f6c6 100644
--- a/kernel/trace/bpf_trace.c
+++ b/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;
 	}