1 files changed, 191 insertions, 67 deletions

diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index aecea7451b61..da3d328f5c15 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -28,7 +28,7 @@ struct bpf_stack_map {
 	void *elems;
 	struct pcpu_freelist freelist;
 	u32 n_buckets;
-	struct stack_map_bucket *buckets[];
+	struct stack_map_bucket *buckets[] __counted_by(n_buckets);
 };
 
 static inline bool stack_map_use_build_id(struct bpf_map *map)
@@ -42,6 +42,28 @@ static inline int stack_map_data_size(struct bpf_map *map)
 		sizeof(struct bpf_stack_build_id) : sizeof(u64);
 }
 
+/**
+ * stack_map_calculate_max_depth - Calculate maximum allowed stack trace depth
+ * @size:  Size of the buffer/map value in bytes
+ * @elem_size:  Size of each stack trace element
+ * @flags:  BPF stack trace flags (BPF_F_USER_STACK, BPF_F_USER_BUILD_ID, ...)
+ *
+ * Return: Maximum number of stack trace entries that can be safely stored
+ */
+static u32 stack_map_calculate_max_depth(u32 size, u32 elem_size, u64 flags)
+{
+	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
+	u32 max_depth;
+	u32 curr_sysctl_max_stack = READ_ONCE(sysctl_perf_event_max_stack);
+
+	max_depth = size / elem_size;
+	max_depth += skip;
+	if (max_depth > curr_sysctl_max_stack)
+		return curr_sysctl_max_stack;
+
+	return max_depth;
+}
+
 static int prealloc_elems_and_freelist(struct bpf_stack_map *smap)
 {
 	u64 elem_size = sizeof(struct stack_map_bucket) +
@@ -74,9 +96,6 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 	u64 cost, n_buckets;
 	int err;
 
-	if (!bpf_capable())
-		return ERR_PTR(-EPERM);
-
 	if (attr->map_flags & ~STACK_CREATE_FLAG_MASK)
 		return ERR_PTR(-EINVAL);
 
@@ -94,11 +113,14 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 	} else if (value_size / 8 > sysctl_perf_event_max_stack)
 		return ERR_PTR(-EINVAL);
 
-	/* hash table size must be power of 2 */
-	n_buckets = roundup_pow_of_two(attr->max_entries);
-	if (!n_buckets)
+	/* hash table size must be power of 2; roundup_pow_of_two() can overflow
+	 * into UB on 32-bit arches, so check that first
+	 */
+	if (attr->max_entries > 1UL << 31)
 		return ERR_PTR(-E2BIG);
 
+	n_buckets = roundup_pow_of_two(attr->max_entries);
+
 	cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap);
 	smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr));
 	if (!smap)
@@ -124,8 +146,24 @@ 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:
+ *   - either adjusted in place to a file offset, if build ID fetching
+ *     succeeds; in this case id_offs[i].build_id is set to correct build ID,
+ *     and id_offs[i].status is set to BPF_STACK_BUILD_ID_VALID;
+ *   - or IP will be kept intact, if build ID fetching failed; in this case
+ *     id_offs[i].build_id is zeroed out and id_offs[i].status is set to
+ *     BPF_STACK_BUILD_ID_IP.
+ */
 static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
-					  u64 *ips, u32 trace_nr, bool user)
+					  u32 trace_nr, bool user, bool may_fault)
 {
 	int i;
 	struct mmap_unlock_irq_work *work = NULL;
@@ -142,30 +180,28 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 		/* cannot access current->mm, fall back to ips */
 		for (i = 0; i < trace_nr; i++) {
 			id_offs[i].status = BPF_STACK_BUILD_ID_IP;
-			id_offs[i].ip = ips[i];
 			memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX);
 		}
 		return;
 	}
 
 	for (i = 0; i < trace_nr; i++) {
-		if (range_in_vma(prev_vma, ips[i], ips[i])) {
+		u64 ip = READ_ONCE(id_offs[i].ip);
+
+		if (range_in_vma(prev_vma, ip, ip)) {
 			vma = prev_vma;
-			memcpy(id_offs[i].build_id, prev_build_id,
-			       BUILD_ID_SIZE_MAX);
+			memcpy(id_offs[i].build_id, prev_build_id, BUILD_ID_SIZE_MAX);
 			goto build_id_valid;
 		}
-		vma = find_vma(current->mm, ips[i]);
-		if (!vma || build_id_parse(vma, id_offs[i].build_id, NULL)) {
+		vma = find_vma(current->mm, ip);
+		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;
-			id_offs[i].ip = ips[i];
 			memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX);
 			continue;
 		}
 build_id_valid:
-		id_offs[i].offset = (vma->vm_pgoff << PAGE_SHIFT) + ips[i]
-			- vma->vm_start;
+		id_offs[i].offset = (vma->vm_pgoff << PAGE_SHIFT) + ip - vma->vm_start;
 		id_offs[i].status = BPF_STACK_BUILD_ID_VALID;
 		prev_vma = vma;
 		prev_build_id = id_offs[i].build_id;
@@ -215,8 +251,8 @@ static long __bpf_get_stackid(struct bpf_map *map,
 {
 	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
 	struct stack_map_bucket *bucket, *new_bucket, *old_bucket;
+	u32 hash, id, trace_nr, trace_len, i, max_depth;
 	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
-	u32 hash, id, trace_nr, trace_len;
 	bool user = flags & BPF_F_USER_STACK;
 	u64 *ips;
 	bool hash_matches;
@@ -225,7 +261,8 @@ static long __bpf_get_stackid(struct bpf_map *map,
 		/* skipping more than usable stack trace */
 		return -EFAULT;
 
-	trace_nr = trace->nr - skip;
+	max_depth = stack_map_calculate_max_depth(map->value_size, stack_map_data_size(map), flags);
+	trace_nr = min_t(u32, trace->nr - skip, max_depth - skip);
 	trace_len = trace_nr * sizeof(u64);
 	ips = trace->ip + skip;
 	hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0);
@@ -238,15 +275,18 @@ static long __bpf_get_stackid(struct bpf_map *map,
 		return id;
 
 	if (stack_map_use_build_id(map)) {
+		struct bpf_stack_build_id *id_offs;
+
 		/* for build_id+offset, pop a bucket before slow cmp */
 		new_bucket = (struct stack_map_bucket *)
 			pcpu_freelist_pop(&smap->freelist);
 		if (unlikely(!new_bucket))
 			return -ENOMEM;
 		new_bucket->nr = trace_nr;
-		stack_map_get_build_id_offset(
-			(struct bpf_stack_build_id *)new_bucket->data,
-			ips, trace_nr, user);
+		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, 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) {
@@ -283,22 +323,19 @@ static long __bpf_get_stackid(struct bpf_map *map,
 BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
 	   u64, flags)
 {
-	u32 max_depth = map->value_size / stack_map_data_size(map);
-	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
+	u32 elem_size = stack_map_data_size(map);
 	bool user = flags & BPF_F_USER_STACK;
 	struct perf_callchain_entry *trace;
 	bool kernel = !user;
+	u32 max_depth;
 
 	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
 			       BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
 		return -EINVAL;
 
-	max_depth += skip;
-	if (max_depth > sysctl_perf_event_max_stack)
-		max_depth = sysctl_perf_event_max_stack;
-
-	trace = get_perf_callchain(regs, 0, kernel, user, max_depth,
-				   false, false);
+	max_depth = stack_map_calculate_max_depth(map->value_size, elem_size, flags);
+	trace = get_perf_callchain(regs, kernel, user, max_depth,
+				   false, false, 0);
 
 	if (unlikely(!trace))
 		/* couldn't fetch the stack trace */
@@ -354,15 +391,11 @@ BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx,
 		return -EFAULT;
 
 	nr_kernel = count_kernel_ip(trace);
+	__u64 nr = trace->nr; /* save original */
 
 	if (kernel) {
-		__u64 nr = trace->nr;
-
 		trace->nr = nr_kernel;
 		ret = __bpf_get_stackid(map, trace, flags);
-
-		/* restore nr */
-		trace->nr = nr;
 	} else { /* user */
 		u64 skip = flags & BPF_F_SKIP_FIELD_MASK;
 
@@ -373,6 +406,10 @@ BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx,
 		flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip;
 		ret = __bpf_get_stackid(map, trace, flags);
 	}
+
+	/* restore nr */
+	trace->nr = nr;
+
 	return ret;
 }
 
@@ -387,10 +424,11 @@ 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;
+	u32 trace_nr, copy_len, elem_size, 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;
@@ -404,8 +442,7 @@ 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;
 
@@ -413,33 +450,55 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 	if (task && user && !user_mode(regs))
 		goto err_fault;
 
-	num_elem = size / elem_size;
-	max_depth = num_elem + skip;
-	if (sysctl_perf_event_max_stack < max_depth)
-		max_depth = sysctl_perf_event_max_stack;
+	/* 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;
+	}
+
+	max_depth = stack_map_calculate_max_depth(size, elem_size, flags);
+
+	if (may_fault)
+		rcu_read_lock(); /* need RCU for perf's callchain below */
 
-	if (trace_in)
+	if (trace_in) {
 		trace = trace_in;
-	else if (kernel && task)
+		trace->nr = min_t(u32, trace->nr, max_depth);
+	} else if (kernel && task) {
 		trace = get_callchain_entry_for_task(task, max_depth);
-	else
-		trace = get_perf_callchain(regs, 0, kernel, user, max_depth,
-					   false, false);
-	if (unlikely(!trace))
-		goto err_fault;
+	} else {
+		trace = get_perf_callchain(regs, kernel, user, max_depth,
+					   crosstask, false, 0);
+	}
 
-	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)
-		stack_map_get_build_id_offset(buf, ips, trace_nr, user);
-	else
+	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];
+	} 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);
@@ -455,7 +514,7 @@ 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 = {
@@ -468,8 +527,24 @@ 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;
@@ -479,12 +554,18 @@ 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,
@@ -496,6 +577,23 @@ 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)
 {
@@ -507,7 +605,7 @@ 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)))
@@ -527,7 +625,7 @@ 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;
@@ -539,7 +637,7 @@ 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;
 
@@ -566,7 +664,15 @@ static void *stack_map_lookup_elem(struct bpf_map *map, void *key)
 }
 
 /* Called from syscall */
-int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
+static int stack_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
+					    void *value, u64 flags)
+{
+	return bpf_stackmap_extract(map, key, value, true);
+}
+
+/* Called from syscall */
+int bpf_stackmap_extract(struct bpf_map *map, void *key, void *value,
+			 bool delete)
 {
 	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
 	struct stack_map_bucket *bucket, *old_bucket;
@@ -583,7 +689,10 @@ int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
 	memcpy(value, bucket->data, trace_len);
 	memset(value + trace_len, 0, map->value_size - trace_len);
 
-	old_bucket = xchg(&smap->buckets[id], bucket);
+	if (delete)
+		old_bucket = bucket;
+	else
+		old_bucket = xchg(&smap->buckets[id], bucket);
 	if (old_bucket)
 		pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
 	return 0;
@@ -618,14 +727,14 @@ static int stack_map_get_next_key(struct bpf_map *map, void *key,
 	return 0;
 }
 
-static int stack_map_update_elem(struct bpf_map *map, void *key, void *value,
-				 u64 map_flags)
+static long stack_map_update_elem(struct bpf_map *map, void *key, void *value,
+				  u64 map_flags)
 {
 	return -EINVAL;
 }
 
 /* Called from syscall or from eBPF program */
-static int stack_map_delete_elem(struct bpf_map *map, void *key)
+static long stack_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
 	struct stack_map_bucket *old_bucket;
@@ -654,6 +763,19 @@ static void stack_map_free(struct bpf_map *map)
 	put_callchain_buffers();
 }
 
+static u64 stack_map_mem_usage(const struct bpf_map *map)
+{
+	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
+	u64 value_size = map->value_size;
+	u64 n_buckets = smap->n_buckets;
+	u64 enties = map->max_entries;
+	u64 usage = sizeof(*smap);
+
+	usage += n_buckets * sizeof(struct stack_map_bucket *);
+	usage += enties * (sizeof(struct stack_map_bucket) + value_size);
+	return usage;
+}
+
 BTF_ID_LIST_SINGLE(stack_trace_map_btf_ids, struct, bpf_stack_map)
 const struct bpf_map_ops stack_trace_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
@@ -661,8 +783,10 @@ const struct bpf_map_ops stack_trace_map_ops = {
 	.map_free = stack_map_free,
 	.map_get_next_key = stack_map_get_next_key,
 	.map_lookup_elem = stack_map_lookup_elem,
+	.map_lookup_and_delete_elem = stack_map_lookup_and_delete_elem,
 	.map_update_elem = stack_map_update_elem,
 	.map_delete_elem = stack_map_delete_elem,
 	.map_check_btf = map_check_no_btf,
+	.map_mem_usage = stack_map_mem_usage,
 	.map_btf_id = &stack_trace_map_btf_ids[0],
 };