bpf: wire up sleepable bpf_get_stack() and bpf_get_task_stack() helpers

Add sleepable implementations of bpf_get_stack() and
bpf_get_task_stack() helpers and allow them to be used from sleepable
BPF program (e.g., sleepable uprobes).

Note, the stack trace IPs capturing itself is not sleepable (that would
need to be a separate project), only build ID fetching is sleepable and
thus more reliable, as it will wait for data to be paged in, if
necessary. For that we make use of sleepable build_id_parse()
implementation.

Now that build ID related internals in kernel/bpf/stackmap.c can be used
both in sleepable and non-sleepable contexts, we need to add additional
rcu_read_lock()/rcu_read_unlock() protection around fetching
perf_callchain_entry, but with the refactoring in previous commit it's
now pretty straightforward. We make sure to do rcu_read_unlock (in
sleepable mode only) right before stack_map_get_build_id_offset() call
which can sleep. By that time we don't have any more use of
perf_callchain_entry.

Note, bpf_get_task_stack() will fail for user mode if task != current.
And for kernel mode build ID are irrelevant. So in that sense adding
sleepable bpf_get_task_stack() implementation is a no-op. It feel right
to wire this up for symmetry and completeness, but I'm open to just
dropping it until we support `user && crosstask` condition.

Reviewed-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20240829174232.3133883-10-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 72 insertions, 18 deletions

diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 6457222b0b46..3615c06b7dfa 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -124,6 +124,12 @@ free_smap:
 	return ERR_PTR(err);
 }
 
+static int fetch_build_id(struct vm_area_struct *vma, unsigned char *build_id, bool may_fault)
+{
+	return may_fault ? build_id_parse(vma, build_id, NULL)
+			 : build_id_parse_nofault(vma, build_id, NULL);
+}
+
 /*
  * Expects all id_offs[i].ip values to be set to correct initial IPs.
  * They will be subsequently:
@@ -135,7 +141,7 @@ free_smap:
  *     BPF_STACK_BUILD_ID_IP.
  */
 static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
-					  u32 trace_nr, bool user)
+					  u32 trace_nr, bool user, bool may_fault)
 {
 	int i;
 	struct mmap_unlock_irq_work *work = NULL;
@@ -166,7 +172,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 			goto build_id_valid;
 		}
 		vma = find_vma(current->mm, ip);
-		if (!vma || build_id_parse_nofault(vma, id_offs[i].build_id, NULL)) {
+		if (!vma || fetch_build_id(vma, id_offs[i].build_id, may_fault)) {
 			/* per entry fall back to ips */
 			id_offs[i].status = BPF_STACK_BUILD_ID_IP;
 			memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX);
@@ -257,7 +263,7 @@ static long __bpf_get_stackid(struct bpf_map *map,
 		id_offs = (struct bpf_stack_build_id *)new_bucket->data;
 		for (i = 0; i < trace_nr; i++)
 			id_offs[i].ip = ips[i];
-		stack_map_get_build_id_offset(id_offs, trace_nr, user);
+		stack_map_get_build_id_offset(id_offs, trace_nr, user, false /* !may_fault */);
 		trace_len = trace_nr * sizeof(struct bpf_stack_build_id);
 		if (hash_matches && bucket->nr == trace_nr &&
 		    memcmp(bucket->data, new_bucket->data, trace_len) == 0) {
@@ -398,7 +404,7 @@ const struct bpf_func_proto bpf_get_stackid_proto_pe = {
 
 static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 			    struct perf_callchain_entry *trace_in,
-			    void *buf, u32 size, u64 flags)
+			    void *buf, u32 size, u64 flags, bool may_fault)
 {
 	u32 trace_nr, copy_len, elem_size, num_elem, max_depth;
 	bool user_build_id = flags & BPF_F_USER_BUILD_ID;
@@ -416,8 +422,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 	if (kernel && user_build_id)
 		goto clear;
 
-	elem_size = (user && user_build_id) ? sizeof(struct bpf_stack_build_id)
-					    : sizeof(u64);
+	elem_size = user_build_id ? sizeof(struct bpf_stack_build_id) : sizeof(u64);
 	if (unlikely(size % elem_size))
 		goto clear;
 
@@ -438,6 +443,9 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 	if (sysctl_perf_event_max_stack < max_depth)
 		max_depth = sysctl_perf_event_max_stack;
 
+	if (may_fault)
+		rcu_read_lock(); /* need RCU for perf's callchain below */
+
 	if (trace_in)
 		trace = trace_in;
 	else if (kernel && task)
@@ -445,28 +453,35 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 	else
 		trace = get_perf_callchain(regs, 0, kernel, user, max_depth,
 					   crosstask, false);
-	if (unlikely(!trace))
-		goto err_fault;
 
-	if (trace->nr < skip)
+	if (unlikely(!trace) || trace->nr < skip) {
+		if (may_fault)
+			rcu_read_unlock();
 		goto err_fault;
+	}
 
 	trace_nr = trace->nr - skip;
 	trace_nr = (trace_nr <= num_elem) ? trace_nr : num_elem;
 	copy_len = trace_nr * elem_size;
 
 	ips = trace->ip + skip;
-	if (user && user_build_id) {
+	if (user_build_id) {
 		struct bpf_stack_build_id *id_offs = buf;
 		u32 i;
 
 		for (i = 0; i < trace_nr; i++)
 			id_offs[i].ip = ips[i];
-		stack_map_get_build_id_offset(buf, trace_nr, user);
 	} else {
 		memcpy(buf, ips, copy_len);
 	}
 
+	/* trace/ips should not be dereferenced after this point */
+	if (may_fault)
+		rcu_read_unlock();
+
+	if (user_build_id)
+		stack_map_get_build_id_offset(buf, trace_nr, user, may_fault);
+
 	if (size > copy_len)
 		memset(buf + copy_len, 0, size - copy_len);
 	return copy_len;
@@ -481,7 +496,7 @@ clear:
 BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
 	   u64, flags)
 {
-	return __bpf_get_stack(regs, NULL, NULL, buf, size, flags);
+	return __bpf_get_stack(regs, NULL, NULL, buf, size, flags, false /* !may_fault */);
 }
 
 const struct bpf_func_proto bpf_get_stack_proto = {
@@ -494,8 +509,24 @@ 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)
+BPF_CALL_4(bpf_get_stack_sleepable, struct pt_regs *, regs, void *, buf, u32, size,
+	   u64, flags)
+{
+	return __bpf_get_stack(regs, NULL, NULL, buf, size, flags, true /* may_fault */);
+}
+
+const struct bpf_func_proto bpf_get_stack_sleepable_proto = {
+	.func		= bpf_get_stack_sleepable,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
+};
+
+static long __bpf_get_task_stack(struct task_struct *task, void *buf, u32 size,
+				 u64 flags, bool may_fault)
 {
 	struct pt_regs *regs;
 	long res = -EINVAL;
@@ -505,12 +536,18 @@ BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
 
 	regs = task_pt_regs(task);
 	if (regs)
-		res = __bpf_get_stack(regs, task, NULL, buf, size, flags);
+		res = __bpf_get_stack(regs, task, NULL, buf, size, flags, may_fault);
 	put_task_stack(task);
 
 	return res;
 }
 
+BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
+	   u32, size, u64, flags)
+{
+	return __bpf_get_task_stack(task, buf, size, flags, false /* !may_fault */);
+}
+
 const struct bpf_func_proto bpf_get_task_stack_proto = {
 	.func		= bpf_get_task_stack,
 	.gpl_only	= false,
@@ -522,6 +559,23 @@ const struct bpf_func_proto bpf_get_task_stack_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_4(bpf_get_task_stack_sleepable, struct task_struct *, task, void *, buf,
+	   u32, size, u64, flags)
+{
+	return __bpf_get_task_stack(task, buf, size, flags, true /* !may_fault */);
+}
+
+const struct bpf_func_proto bpf_get_task_stack_sleepable_proto = {
+	.func		= bpf_get_task_stack_sleepable,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
+	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx,
 	   void *, buf, u32, size, u64, flags)
 {
@@ -533,7 +587,7 @@ BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx,
 	__u64 nr_kernel;
 
 	if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN))
-		return __bpf_get_stack(regs, NULL, NULL, buf, size, flags);
+		return __bpf_get_stack(regs, NULL, NULL, buf, size, flags, false /* !may_fault */);
 
 	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
 			       BPF_F_USER_BUILD_ID)))
@@ -553,7 +607,7 @@ BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx,
 		__u64 nr = trace->nr;
 
 		trace->nr = nr_kernel;
-		err = __bpf_get_stack(regs, NULL, trace, buf, size, flags);
+		err = __bpf_get_stack(regs, NULL, trace, buf, size, flags, false /* !may_fault */);
 
 		/* restore nr */
 		trace->nr = nr;
@@ -565,7 +619,7 @@ BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx,
 			goto clear;
 
 		flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip;
-		err = __bpf_get_stack(regs, NULL, trace, buf, size, flags);
+		err = __bpf_get_stack(regs, NULL, trace, buf, size, flags, false /* !may_fault */);
 	}
 	return err;