bpf: Remove btf_field_offs, use btf_record's fields instead

The btf_field_offs struct contains (offset, size) for btf_record fields,
sorted by offset. btf_field_offs is always used in conjunction with
btf_record, which has btf_field 'fields' array with (offset, type), the
latter of which btf_field_offs' size is derived from via
btf_field_type_size.

This patch adds a size field to struct btf_field and sorts btf_record's
fields by offset, making it possible to get rid of btf_field_offs. Less
data duplication and less code complexity results.

Since btf_field_offs' lifetime closely followed the btf_record used to
populate it, most complexity wins are from removal of initialization
code like:

  if (btf_record_successfully_initialized) {
    foffs = btf_parse_field_offs(rec);
    if (IS_ERR_OR_NULL(foffs))
      // free the btf_record and return err
  }

Other changes in this patch are pretty mechanical:

  * foffs->field_off[i] -> rec->fields[i].offset
  * foffs->field_sz[i] -> rec->fields[i].size
  * Sort rec->fields in btf_parse_fields before returning
    * It's possible that this is necessary independently of other
      changes in this patch. btf_record_find in syscall.c expects
      btf_record's fields to be sorted by offset, yet there's no
      explicit sorting of them before this patch, record's fields are
      populated in the order they're read from BTF struct definition.
      BTF docs don't say anything about the sortedness of struct fields.
  * All functions taking struct btf_field_offs * input now instead take
    struct btf_record *. All callsites of these functions already have
    access to the correct btf_record.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Link: https://lore.kernel.org/r/20230415201811.343116-2-davemarchevsky@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 19 insertions, 25 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 88845aadc47d..7888ed497432 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -210,6 +210,7 @@ struct btf_field_graph_root {
 
 struct btf_field {
 	u32 offset;
+	u32 size;
 	enum btf_field_type type;
 	union {
 		struct btf_field_kptr kptr;
@@ -225,12 +226,6 @@ struct btf_record {
 	struct btf_field fields[];
 };
 
-struct btf_field_offs {
-	u32 cnt;
-	u32 field_off[BTF_FIELDS_MAX];
-	u8 field_sz[BTF_FIELDS_MAX];
-};
-
 struct bpf_map {
 	/* The first two cachelines with read-mostly members of which some
 	 * are also accessed in fast-path (e.g. ops, max_entries).
@@ -257,7 +252,6 @@ struct bpf_map {
 	struct obj_cgroup *objcg;
 #endif
 	char name[BPF_OBJ_NAME_LEN];
-	struct btf_field_offs *field_offs;
 	/* The 3rd and 4th cacheline with misc members to avoid false sharing
 	 * particularly with refcounting.
 	 */
@@ -360,14 +354,14 @@ static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_f
 	return rec->field_mask & type;
 }
 
-static inline void bpf_obj_init(const struct btf_field_offs *foffs, void *obj)
+static inline void bpf_obj_init(const struct btf_record *rec, void *obj)
 {
 	int i;
 
-	if (!foffs)
+	if (IS_ERR_OR_NULL(rec))
 		return;
-	for (i = 0; i < foffs->cnt; i++)
-		memset(obj + foffs->field_off[i], 0, foffs->field_sz[i]);
+	for (i = 0; i < rec->cnt; i++)
+		memset(obj + rec->fields[i].offset, 0, rec->fields[i].size);
 }
 
 /* 'dst' must be a temporary buffer and should not point to memory that is being
@@ -379,7 +373,7 @@ static inline void bpf_obj_init(const struct btf_field_offs *foffs, void *obj)
  */
 static inline void check_and_init_map_value(struct bpf_map *map, void *dst)
 {
-	bpf_obj_init(map->field_offs, dst);
+	bpf_obj_init(map->record, dst);
 }
 
 /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
@@ -399,14 +393,14 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size)
 }
 
 /* copy everything but bpf_spin_lock, bpf_timer, and kptrs. There could be one of each. */
-static inline void bpf_obj_memcpy(struct btf_field_offs *foffs,
+static inline void bpf_obj_memcpy(struct btf_record *rec,
 				  void *dst, void *src, u32 size,
 				  bool long_memcpy)
 {
 	u32 curr_off = 0;
 	int i;
 
-	if (likely(!foffs)) {
+	if (IS_ERR_OR_NULL(rec)) {
 		if (long_memcpy)
 			bpf_long_memcpy(dst, src, round_up(size, 8));
 		else
@@ -414,49 +408,49 @@ static inline void bpf_obj_memcpy(struct btf_field_offs *foffs,
 		return;
 	}
 
-	for (i = 0; i < foffs->cnt; i++) {
-		u32 next_off = foffs->field_off[i];
+	for (i = 0; i < rec->cnt; i++) {
+		u32 next_off = rec->fields[i].offset;
 		u32 sz = next_off - curr_off;
 
 		memcpy(dst + curr_off, src + curr_off, sz);
-		curr_off += foffs->field_sz[i] + sz;
+		curr_off += rec->fields[i].size + sz;
 	}
 	memcpy(dst + curr_off, src + curr_off, size - curr_off);
 }
 
 static inline void copy_map_value(struct bpf_map *map, void *dst, void *src)
 {
-	bpf_obj_memcpy(map->field_offs, dst, src, map->value_size, false);
+	bpf_obj_memcpy(map->record, dst, src, map->value_size, false);
 }
 
 static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src)
 {
-	bpf_obj_memcpy(map->field_offs, dst, src, map->value_size, true);
+	bpf_obj_memcpy(map->record, dst, src, map->value_size, true);
 }
 
-static inline void bpf_obj_memzero(struct btf_field_offs *foffs, void *dst, u32 size)
+static inline void bpf_obj_memzero(struct btf_record *rec, void *dst, u32 size)
 {
 	u32 curr_off = 0;
 	int i;
 
-	if (likely(!foffs)) {
+	if (IS_ERR_OR_NULL(rec)) {
 		memset(dst, 0, size);
 		return;
 	}
 
-	for (i = 0; i < foffs->cnt; i++) {
-		u32 next_off = foffs->field_off[i];
+	for (i = 0; i < rec->cnt; i++) {
+		u32 next_off = rec->fields[i].offset;
 		u32 sz = next_off - curr_off;
 
 		memset(dst + curr_off, 0, sz);
-		curr_off += foffs->field_sz[i] + sz;
+		curr_off += rec->fields[i].size + sz;
 	}
 	memset(dst + curr_off, 0, size - curr_off);
 }
 
 static inline void zero_map_value(struct bpf_map *map, void *dst)
 {
-	bpf_obj_memzero(map->field_offs, dst, map->value_size);
+	bpf_obj_memzero(map->record, dst, map->value_size);
 }
 
 void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,