1 files changed, 222 insertions, 60 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index d447b5e343bf..b51ecb9644d0 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -23,6 +23,7 @@
 #include <linux/timekeeping.h>
 #include <linux/ctype.h>
 #include <linux/nospec.h>
+#include <linux/audit.h>
 #include <uapi/linux/btf.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \
@@ -43,7 +44,7 @@ static DEFINE_SPINLOCK(map_idr_lock);
 int sysctl_unprivileged_bpf_disabled __read_mostly;
 
 static const struct bpf_map_ops * const bpf_map_types[] = {
-#define BPF_PROG_TYPE(_id, _ops)
+#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type)
 #define BPF_MAP_TYPE(_id, _ops) \
 	[_id] = &_ops,
 #include <linux/bpf_types.h>
@@ -127,7 +128,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 	return map;
 }
 
-void *bpf_map_area_alloc(u64 size, int numa_node)
+static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable)
 {
 	/* We really just want to fail instead of triggering OOM killer
 	 * under memory pressure, therefore we set __GFP_NORETRY to kmalloc,
@@ -145,18 +146,33 @@ void *bpf_map_area_alloc(u64 size, int numa_node)
 	if (size >= SIZE_MAX)
 		return NULL;
 
-	if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
+	/* kmalloc()'ed memory can't be mmap()'ed */
+	if (!mmapable && size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
 		area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags,
 				    numa_node);
 		if (area != NULL)
 			return area;
 	}
-
+	if (mmapable) {
+		BUG_ON(!PAGE_ALIGNED(size));
+		return vmalloc_user_node_flags(size, numa_node, GFP_KERNEL |
+					       __GFP_RETRY_MAYFAIL | flags);
+	}
 	return __vmalloc_node_flags_caller(size, numa_node,
 					   GFP_KERNEL | __GFP_RETRY_MAYFAIL |
 					   flags, __builtin_return_address(0));
 }
 
+void *bpf_map_area_alloc(u64 size, int numa_node)
+{
+	return __bpf_map_area_alloc(size, numa_node, false);
+}
+
+void *bpf_map_area_mmapable_alloc(u64 size, int numa_node)
+{
+	return __bpf_map_area_alloc(size, numa_node, true);
+}
+
 void bpf_map_area_free(void *area)
 {
 	kvfree(area);
@@ -314,7 +330,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
 
 static void bpf_map_put_uref(struct bpf_map *map)
 {
-	if (atomic_dec_and_test(&map->usercnt)) {
+	if (atomic64_dec_and_test(&map->usercnt)) {
 		if (map->ops->map_release_uref)
 			map->ops->map_release_uref(map);
 	}
@@ -325,7 +341,7 @@ static void bpf_map_put_uref(struct bpf_map *map)
  */
 static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock)
 {
-	if (atomic_dec_and_test(&map->refcnt)) {
+	if (atomic64_dec_and_test(&map->refcnt)) {
 		/* bpf_map_free_id() must be called first */
 		bpf_map_free_id(map, do_idr_lock);
 		btf_put(map->btf);
@@ -428,6 +444,74 @@ static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf,
 	return -EINVAL;
 }
 
+/* called for any extra memory-mapped regions (except initial) */
+static void bpf_map_mmap_open(struct vm_area_struct *vma)
+{
+	struct bpf_map *map = vma->vm_file->private_data;
+
+	bpf_map_inc_with_uref(map);
+
+	if (vma->vm_flags & VM_WRITE) {
+		mutex_lock(&map->freeze_mutex);
+		map->writecnt++;
+		mutex_unlock(&map->freeze_mutex);
+	}
+}
+
+/* called for all unmapped memory region (including initial) */
+static void bpf_map_mmap_close(struct vm_area_struct *vma)
+{
+	struct bpf_map *map = vma->vm_file->private_data;
+
+	if (vma->vm_flags & VM_WRITE) {
+		mutex_lock(&map->freeze_mutex);
+		map->writecnt--;
+		mutex_unlock(&map->freeze_mutex);
+	}
+
+	bpf_map_put_with_uref(map);
+}
+
+static const struct vm_operations_struct bpf_map_default_vmops = {
+	.open		= bpf_map_mmap_open,
+	.close		= bpf_map_mmap_close,
+};
+
+static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct bpf_map *map = filp->private_data;
+	int err;
+
+	if (!map->ops->map_mmap || map_value_has_spin_lock(map))
+		return -ENOTSUPP;
+
+	if (!(vma->vm_flags & VM_SHARED))
+		return -EINVAL;
+
+	mutex_lock(&map->freeze_mutex);
+
+	if ((vma->vm_flags & VM_WRITE) && map->frozen) {
+		err = -EPERM;
+		goto out;
+	}
+
+	/* set default open/close callbacks */
+	vma->vm_ops = &bpf_map_default_vmops;
+	vma->vm_private_data = map;
+
+	err = map->ops->map_mmap(map, vma);
+	if (err)
+		goto out;
+
+	bpf_map_inc_with_uref(map);
+
+	if (vma->vm_flags & VM_WRITE)
+		map->writecnt++;
+out:
+	mutex_unlock(&map->freeze_mutex);
+	return err;
+}
+
 const struct file_operations bpf_map_fops = {
 #ifdef CONFIG_PROC_FS
 	.show_fdinfo	= bpf_map_show_fdinfo,
@@ -435,6 +519,7 @@ const struct file_operations bpf_map_fops = {
 	.release	= bpf_map_release,
 	.read		= bpf_dummy_read,
 	.write		= bpf_dummy_write,
+	.mmap		= bpf_map_mmap,
 };
 
 int bpf_map_new_fd(struct bpf_map *map, int flags)
@@ -578,8 +663,9 @@ static int map_create(union bpf_attr *attr)
 	if (err)
 		goto free_map;
 
-	atomic_set(&map->refcnt, 1);
-	atomic_set(&map->usercnt, 1);
+	atomic64_set(&map->refcnt, 1);
+	atomic64_set(&map->usercnt, 1);
+	mutex_init(&map->freeze_mutex);
 
 	if (attr->btf_key_type_id || attr->btf_value_type_id) {
 		struct btf *btf;
@@ -656,21 +742,19 @@ struct bpf_map *__bpf_map_get(struct fd f)
 	return f.file->private_data;
 }
 
-/* prog's and map's refcnt limit */
-#define BPF_MAX_REFCNT 32768
-
-struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref)
+void bpf_map_inc(struct bpf_map *map)
 {
-	if (atomic_inc_return(&map->refcnt) > BPF_MAX_REFCNT) {
-		atomic_dec(&map->refcnt);
-		return ERR_PTR(-EBUSY);
-	}
-	if (uref)
-		atomic_inc(&map->usercnt);
-	return map;
+	atomic64_inc(&map->refcnt);
 }
 EXPORT_SYMBOL_GPL(bpf_map_inc);
 
+void bpf_map_inc_with_uref(struct bpf_map *map)
+{
+	atomic64_inc(&map->refcnt);
+	atomic64_inc(&map->usercnt);
+}
+EXPORT_SYMBOL_GPL(bpf_map_inc_with_uref);
+
 struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 {
 	struct fd f = fdget(ufd);
@@ -680,38 +764,30 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 	if (IS_ERR(map))
 		return map;
 
-	map = bpf_map_inc(map, true);
+	bpf_map_inc_with_uref(map);
 	fdput(f);
 
 	return map;
 }
 
 /* map_idr_lock should have been held */
-static struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map,
-					      bool uref)
+static struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref)
 {
 	int refold;
 
-	refold = atomic_fetch_add_unless(&map->refcnt, 1, 0);
-
-	if (refold >= BPF_MAX_REFCNT) {
-		__bpf_map_put(map, false);
-		return ERR_PTR(-EBUSY);
-	}
-
+	refold = atomic64_fetch_add_unless(&map->refcnt, 1, 0);
 	if (!refold)
 		return ERR_PTR(-ENOENT);
-
 	if (uref)
-		atomic_inc(&map->usercnt);
+		atomic64_inc(&map->usercnt);
 
 	return map;
 }
 
-struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map, bool uref)
+struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map)
 {
 	spin_lock_bh(&map_idr_lock);
-	map = __bpf_map_inc_not_zero(map, uref);
+	map = __bpf_map_inc_not_zero(map, false);
 	spin_unlock_bh(&map_idr_lock);
 
 	return map;
@@ -1176,6 +1252,13 @@ static int map_freeze(const union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
+
+	mutex_lock(&map->freeze_mutex);
+
+	if (map->writecnt) {
+		err = -EBUSY;
+		goto err_put;
+	}
 	if (READ_ONCE(map->frozen)) {
 		err = -EBUSY;
 		goto err_put;
@@ -1187,12 +1270,13 @@ static int map_freeze(const union bpf_attr *attr)
 
 	WRITE_ONCE(map->frozen, true);
 err_put:
+	mutex_unlock(&map->freeze_mutex);
 	fdput(f);
 	return err;
 }
 
 static const struct bpf_prog_ops * const bpf_prog_types[] = {
-#define BPF_PROG_TYPE(_id, _name) \
+#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
 	[_id] = & _name ## _prog_ops,
 #define BPF_MAP_TYPE(_id, _ops)
 #include <linux/bpf_types.h>
@@ -1238,6 +1322,34 @@ static void free_used_maps(struct bpf_prog_aux *aux)
 	kfree(aux->used_maps);
 }
 
+enum bpf_event {
+	BPF_EVENT_LOAD,
+	BPF_EVENT_UNLOAD,
+};
+
+static const char * const bpf_event_audit_str[] = {
+	[BPF_EVENT_LOAD]   = "LOAD",
+	[BPF_EVENT_UNLOAD] = "UNLOAD",
+};
+
+static void bpf_audit_prog(const struct bpf_prog *prog, enum bpf_event event)
+{
+	bool has_task_context = event == BPF_EVENT_LOAD;
+	struct audit_buffer *ab;
+
+	if (audit_enabled == AUDIT_OFF)
+		return;
+	ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_BPF);
+	if (unlikely(!ab))
+		return;
+	if (has_task_context)
+		audit_log_task(ab);
+	audit_log_format(ab, "%sprog-id=%u event=%s",
+			 has_task_context ? " " : "",
+			 prog->aux->id, bpf_event_audit_str[event]);
+	audit_log_end(ab);
+}
+
 int __bpf_prog_charge(struct user_struct *user, u32 pages)
 {
 	unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
@@ -1331,6 +1443,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
 	struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
 
 	kvfree(aux->func_info);
+	kfree(aux->func_info_aux);
 	free_used_maps(aux);
 	bpf_prog_uncharge_memlock(aux->prog);
 	security_bpf_prog_free(aux);
@@ -1351,8 +1464,9 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred)
 
 static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
 {
-	if (atomic_dec_and_test(&prog->aux->refcnt)) {
+	if (atomic64_dec_and_test(&prog->aux->refcnt)) {
 		perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0);
+		bpf_audit_prog(prog, BPF_EVENT_UNLOAD);
 		/* bpf_prog_free_id() must be called first */
 		bpf_prog_free_id(prog, do_idr_lock);
 		__bpf_prog_put_noref(prog, true);
@@ -1457,13 +1571,9 @@ static struct bpf_prog *____bpf_prog_get(struct fd f)
 	return f.file->private_data;
 }
 
-struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i)
+void bpf_prog_add(struct bpf_prog *prog, int i)
 {
-	if (atomic_add_return(i, &prog->aux->refcnt) > BPF_MAX_REFCNT) {
-		atomic_sub(i, &prog->aux->refcnt);
-		return ERR_PTR(-EBUSY);
-	}
-	return prog;
+	atomic64_add(i, &prog->aux->refcnt);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_add);
 
@@ -1474,13 +1584,13 @@ void bpf_prog_sub(struct bpf_prog *prog, int i)
 	 * path holds a reference to the program, thus atomic_sub() can
 	 * be safely used in such cases!
 	 */
-	WARN_ON(atomic_sub_return(i, &prog->aux->refcnt) == 0);
+	WARN_ON(atomic64_sub_return(i, &prog->aux->refcnt) == 0);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_sub);
 
-struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
+void bpf_prog_inc(struct bpf_prog *prog)
 {
-	return bpf_prog_add(prog, 1);
+	atomic64_inc(&prog->aux->refcnt);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_inc);
 
@@ -1489,12 +1599,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
 {
 	int refold;
 
-	refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0);
-
-	if (refold >= BPF_MAX_REFCNT) {
-		__bpf_prog_put(prog, false);
-		return ERR_PTR(-EBUSY);
-	}
+	refold = atomic64_fetch_add_unless(&prog->aux->refcnt, 1, 0);
 
 	if (!refold)
 		return ERR_PTR(-ENOENT);
@@ -1532,7 +1637,7 @@ static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type,
 		goto out;
 	}
 
-	prog = bpf_prog_inc(prog);
+	bpf_prog_inc(prog);
 out:
 	fdput(f);
 	return prog;
@@ -1579,7 +1684,7 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr)
 static int
 bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 			   enum bpf_attach_type expected_attach_type,
-			   u32 btf_id)
+			   u32 btf_id, u32 prog_fd)
 {
 	switch (prog_type) {
 	case BPF_PROG_TYPE_TRACING:
@@ -1587,7 +1692,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 			return -EINVAL;
 		break;
 	default:
-		if (btf_id)
+		if (btf_id || prog_fd)
 			return -EINVAL;
 		break;
 	}
@@ -1638,7 +1743,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 }
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD attach_btf_id
+#define	BPF_PROG_LOAD_LAST_FIELD attach_prog_fd
 
 static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 {
@@ -1681,7 +1786,8 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 
 	bpf_prog_load_fixup_attach_type(attr);
 	if (bpf_prog_load_check_attach(type, attr->expected_attach_type,
-				       attr->attach_btf_id))
+				       attr->attach_btf_id,
+				       attr->attach_prog_fd))
 		return -EINVAL;
 
 	/* plain bpf_prog allocation */
@@ -1691,6 +1797,16 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 
 	prog->expected_attach_type = attr->expected_attach_type;
 	prog->aux->attach_btf_id = attr->attach_btf_id;
+	if (attr->attach_prog_fd) {
+		struct bpf_prog *tgt_prog;
+
+		tgt_prog = bpf_prog_get(attr->attach_prog_fd);
+		if (IS_ERR(tgt_prog)) {
+			err = PTR_ERR(tgt_prog);
+			goto free_prog_nouncharge;
+		}
+		prog->aux->linked_prog = tgt_prog;
+	}
 
 	prog->aux->offload_requested = !!attr->prog_ifindex;
 
@@ -1712,7 +1828,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	prog->orig_prog = NULL;
 	prog->jited = 0;
 
-	atomic_set(&prog->aux->refcnt, 1);
+	atomic64_set(&prog->aux->refcnt, 1);
 	prog->gpl_compatible = is_gpl ? 1 : 0;
 
 	if (bpf_prog_is_dev_bound(prog->aux)) {
@@ -1760,6 +1876,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	 */
 	bpf_prog_kallsyms_add(prog);
 	perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0);
+	bpf_audit_prog(prog, BPF_EVENT_LOAD);
 
 	err = bpf_prog_new_fd(prog);
 	if (err < 0)
@@ -1802,6 +1919,49 @@ static int bpf_obj_get(const union bpf_attr *attr)
 				attr->file_flags);
 }
 
+static int bpf_tracing_prog_release(struct inode *inode, struct file *filp)
+{
+	struct bpf_prog *prog = filp->private_data;
+
+	WARN_ON_ONCE(bpf_trampoline_unlink_prog(prog));
+	bpf_prog_put(prog);
+	return 0;
+}
+
+static const struct file_operations bpf_tracing_prog_fops = {
+	.release	= bpf_tracing_prog_release,
+	.read		= bpf_dummy_read,
+	.write		= bpf_dummy_write,
+};
+
+static int bpf_tracing_prog_attach(struct bpf_prog *prog)
+{
+	int tr_fd, err;
+
+	if (prog->expected_attach_type != BPF_TRACE_FENTRY &&
+	    prog->expected_attach_type != BPF_TRACE_FEXIT) {
+		err = -EINVAL;
+		goto out_put_prog;
+	}
+
+	err = bpf_trampoline_link_prog(prog);
+	if (err)
+		goto out_put_prog;
+
+	tr_fd = anon_inode_getfd("bpf-tracing-prog", &bpf_tracing_prog_fops,
+				 prog, O_CLOEXEC);
+	if (tr_fd < 0) {
+		WARN_ON_ONCE(bpf_trampoline_unlink_prog(prog));
+		err = tr_fd;
+		goto out_put_prog;
+	}
+	return tr_fd;
+
+out_put_prog:
+	bpf_prog_put(prog);
+	return err;
+}
+
 struct bpf_raw_tracepoint {
 	struct bpf_raw_event_map *btp;
 	struct bpf_prog *prog;
@@ -1853,14 +2013,16 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 
 	if (prog->type == BPF_PROG_TYPE_TRACING) {
 		if (attr->raw_tracepoint.name) {
-			/* raw_tp name should not be specified in raw_tp
-			 * programs that were verified via in-kernel BTF info
+			/* The attach point for this category of programs
+			 * should be specified via btf_id during program load.
 			 */
 			err = -EINVAL;
 			goto out_put_prog;
 		}
-		/* raw_tp name is taken from type name instead */
-		tp_name = prog->aux->attach_func_name;
+		if (prog->expected_attach_type == BPF_TRACE_RAW_TP)
+			tp_name = prog->aux->attach_func_name;
+		else
+			return bpf_tracing_prog_attach(prog);
 	} else {
 		if (strncpy_from_user(buf,
 				      u64_to_user_ptr(attr->raw_tracepoint.name),