[PATCH bpf-next 08/16] bpf: Extend syscall to accept arena percpu information

[Xu Kuohai]

From: Xu Kuohai <xukuohai@xxxxxxxxxx>

Extend the bpf syscall to accept the arena percpu chunk offset and
size. Both are checked at arena creation time to make sure they are
page-aligned and the percpu chunks live inside the arena vm_range. If
the checks pass, the values are stored in struct bpf_arena for the
verifier and the JIT.

Signed-off-by: Xu Kuohai <xukuohai@xxxxxxxxxx>
---
 include/uapi/linux/bpf.h |  4 ++++
 kernel/bpf/arena.c       | 18 ++++++++++++++++++
 kernel/bpf/syscall.c     |  2 +-
 3 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 9e5fa52c9bc2..6b17dcfc36b4 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1628,6 +1628,10 @@ union bpf_attr {
 		__aligned_u64 excl_prog_hash;
 		/* Size of the passed excl_prog_hash. */
 		__u32 excl_prog_hash_size;
+
+		/* offset and size of an arena percpu chunk */
+		__u32	arena_percpu_chunk_off;
+		__u32	arena_percpu_chunk_sz;
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM and BPF_MAP_FREEZE commands */
diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c
index 868589f07330..05cd6397adae 100644
--- a/kernel/bpf/arena.c
+++ b/kernel/bpf/arena.c
@@ -67,6 +67,9 @@ struct bpf_arena {
 	struct irq_work     free_irq;
 	struct work_struct  free_work;
 	struct llist_head   free_spans;
+	/* percpu chunk offset and size */
+	u32 percpu_chunk_off;
+	u32 percpu_chunk_sz;
 };
 
 static void arena_free_worker(struct work_struct *work);
@@ -298,6 +301,17 @@ static struct bpf_map *arena_map_alloc(union bpf_attr *attr)
 		/* user vma must not cross 32-bit boundary */
 		return ERR_PTR(-ERANGE);
 
+	if (attr->arena_percpu_chunk_sz) {
+		u64 offset = attr->arena_percpu_chunk_off;
+		u64 size = attr->arena_percpu_chunk_sz;
+
+		if (!IS_ALIGNED(offset, PAGE_SIZE) || !IS_ALIGNED(size, PAGE_SIZE))
+			return ERR_PTR(-EINVAL);
+
+		if (offset > vm_range || size > (vm_range - offset) / nr_cpu_ids)
+			return ERR_PTR(-E2BIG);
+	}
+
 	kern_vm = get_vm_area(KERN_VM_SZ, VM_SPARSE | VM_USERMAP);
 	if (!kern_vm)
 		return ERR_PTR(-ENOMEM);
@@ -311,6 +325,10 @@ static struct bpf_map *arena_map_alloc(union bpf_attr *attr)
 	if (arena->user_vm_start)
 		arena->user_vm_end = arena->user_vm_start + vm_range;
 
+	arena->percpu_chunk_sz = attr->arena_percpu_chunk_sz;
+	if (attr->arena_percpu_chunk_sz)
+		arena->percpu_chunk_off = attr->arena_percpu_chunk_off;
+
 	INIT_LIST_HEAD(&arena->vma_list);
 	init_llist_head(&arena->free_spans);
 	init_irq_work(&arena->free_irq, arena_free_irq);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 849bc9136299..240c7349284d 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1396,7 +1396,7 @@ static int map_check_btf(struct bpf_map *map, struct bpf_token *token,
 	return ret;
 }
 
-#define BPF_MAP_CREATE_LAST_FIELD excl_prog_hash_size
+#define BPF_MAP_CREATE_LAST_FIELD arena_percpu_chunk_sz
 /* called via syscall */
 static int map_create_alloc(union bpf_attr *attr, bpfptr_t uattr, struct bpf_verifier_log *log,
 			    struct bpf_map **mapp, struct bpf_token **tokenp)
-- 
2.47.3