Merge branch 'support-global-data'

Daniel Borkmann says:

====================
This series is a major rework of previously submitted libbpf
patches [0] in order to add global data support for BPF. The
kernel has been extended to add proper infrastructure that allows
for full .bss/.data/.rodata sections on BPF loader side based
upon feedback from LPC discussions [1]. Latter support is then
also added into libbpf in this series which allows for more
natural C-like programming of BPF programs. For more information
on loader, please refer to 'bpf, libbpf: support global data/bss/
rodata sections' patch in this series.

Thanks a lot!

  v5 -> v6:
   - Removed synchronize_rcu() from map freeze (Jann)
   - Rest as-is
  v4 -> v5:
   - Removed index selection again for ldimm64 (Alexei)
   - Adapted related test cases and added new ones to test
     rejection of off != 0
  v3 -> v4:
   - Various fixes in BTF verification e.g. to disallow
     Var and DataSec to be an intermediate type during resolve (Martin)
   - More BTF test cases added
   - Few cleanups in key-less BTF commit (Martin)
   - Bump libbpf minor version from 2 to 3
   - Renamed and simplified read-only locking
   - Various minor improvements all over the place
  v2 -> v3:
   - Implement BTF support in kernel, libbpf, bpftool, add tests
   - Fix idx + off conversion (Andrii)
   - Document lower / higher bits for direct value access (Andrii)
   - Add tests with small value size (Andrii)
   - Add index selection into ldimm64 (Andrii)
   - Fix missing fdput() (Jann)
   - Reject invalid flags in BPF_F_*_PROG (Jakub)
   - Complete rework of libbpf support, includes:
    - Add objname to map name (Stanislav)
    - Make .rodata map full read-only after setup (Andrii)
    - Merge relocation handling into single one (Andrii)
    - Store global maps into obj->maps array (Andrii, Alexei)
    - Debug message when skipping section (Andrii)
    - Reject non-static global data till we have
      semantics for sharing them (Yonghong, Andrii, Alexei)
    - More test cases and completely reworked prog test (Alexei)
   - Fixes, cleanups, etc all over the set
   - Not yet addressed:
    - Make BTF mandatory for these maps (Alexei)
    -> Waiting till BTF support for these lands first
  v1 -> v2:
    - Instead of 32-bit static data, implement full global
      data support (Alexei)

  [0] https://patchwork.ozlabs.org/cover/1040290/
  [1] http://vger.kernel.org/lpc-bpf2018.html#session-3
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Documentation/bpf/btf.rst

@@ -82,6 +82,8 @@ sequentially and type id is assigned to each recognized type starting from id
     #define BTF_KIND_RESTRICT       11      /* Restrict     */
     #define BTF_KIND_FUNC           12      /* Function     */
     #define BTF_KIND_FUNC_PROTO     13      /* Function Proto       */
+    #define BTF_KIND_VAR            14      /* Variable     */
+    #define BTF_KIND_DATASEC        15      /* Section      */
 
 Note that the type section encodes debug info, not just pure types.
 ``BTF_KIND_FUNC`` is not a type, and it represents a defined subprogram.
@@ -393,6 +395,61 @@ refers to parameter type.
 If the function has variable arguments, the last parameter is encoded with
 ``name_off = 0`` and ``type = 0``.
 
+2.2.14 BTF_KIND_VAR
+~~~~~~~~~~~~~~~~~~~
+
+``struct btf_type`` encoding requirement:
+  * ``name_off``: offset to a valid C identifier
+  * ``info.kind_flag``: 0
+  * ``info.kind``: BTF_KIND_VAR
+  * ``info.vlen``: 0
+  * ``type``: the type of the variable
+
+``btf_type`` is followed by a single ``struct btf_variable`` with the
+following data::
+
+    struct btf_var {
+        __u32   linkage;
+    };
+
+``struct btf_var`` encoding:
+  * ``linkage``: currently only static variable 0, or globally allocated
+                 variable in ELF sections 1
+
+Not all type of global variables are supported by LLVM at this point.
+The following is currently available:
+
+  * static variables with or without section attributes
+  * global variables with section attributes
+
+The latter is for future extraction of map key/value type id's from a
+map definition.
+
+2.2.15 BTF_KIND_DATASEC
+~~~~~~~~~~~~~~~~~~~~~~~
+
+``struct btf_type`` encoding requirement:
+  * ``name_off``: offset to a valid name associated with a variable or
+                  one of .data/.bss/.rodata
+  * ``info.kind_flag``: 0
+  * ``info.kind``: BTF_KIND_DATASEC
+  * ``info.vlen``: # of variables
+  * ``size``: total section size in bytes (0 at compilation time, patched
+              to actual size by BPF loaders such as libbpf)
+
+``btf_type`` is followed by ``info.vlen`` number of ``struct btf_var_secinfo``.::
+
+    struct btf_var_secinfo {
+        __u32   type;
+        __u32   offset;
+        __u32   size;
+    };
+
+``struct btf_var_secinfo`` encoding:
+  * ``type``: the type of the BTF_KIND_VAR variable
+  * ``offset``: the in-section offset of the variable
+  * ``size``: the size of the variable in bytes
+
 3. BTF Kernel API
 *****************
 

include/linux/bpf.h

@@ -57,6 +57,12 @@ struct bpf_map_ops {
 			     const struct btf *btf,
 			     const struct btf_type *key_type,
 			     const struct btf_type *value_type);
+
+	/* Direct value access helpers. */
+	int (*map_direct_value_addr)(const struct bpf_map *map,
+				     u64 *imm, u32 off);
+	int (*map_direct_value_meta)(const struct bpf_map *map,
+				     u64 imm, u32 *off);
 };
 
 struct bpf_map {
@@ -81,7 +87,8 @@ struct bpf_map {
 	struct btf *btf;
 	u32 pages;
 	bool unpriv_array;
-	/* 51 bytes hole */
+	bool frozen; /* write-once */
+	/* 48 bytes hole */
 
 	/* The 3rd and 4th cacheline with misc members to avoid false sharing
 	 * particularly with refcounting.
@@ -424,6 +431,35 @@ struct bpf_array {
 #define BPF_COMPLEXITY_LIMIT_INSNS      1000000 /* yes. 1M insns */
 #define MAX_TAIL_CALL_CNT 32
 
+#define BPF_F_ACCESS_MASK	(BPF_F_RDONLY |		\
+				 BPF_F_RDONLY_PROG |	\
+				 BPF_F_WRONLY |		\
+				 BPF_F_WRONLY_PROG)
+
+#define BPF_MAP_CAN_READ	BIT(0)
+#define BPF_MAP_CAN_WRITE	BIT(1)
+
+static inline u32 bpf_map_flags_to_cap(struct bpf_map *map)
+{
+	u32 access_flags = map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG);
+
+	/* Combination of BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG is
+	 * not possible.
+	 */
+	if (access_flags & BPF_F_RDONLY_PROG)
+		return BPF_MAP_CAN_READ;
+	else if (access_flags & BPF_F_WRONLY_PROG)
+		return BPF_MAP_CAN_WRITE;
+	else
+		return BPF_MAP_CAN_READ | BPF_MAP_CAN_WRITE;
+}
+
+static inline bool bpf_map_flags_access_ok(u32 access_flags)
+{
+	return (access_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) !=
+	       (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG);
+}
+
 struct bpf_event_entry {
 	struct perf_event *event;
 	struct file *perf_file;

include/linux/bpf_verifier.h

@@ -224,6 +224,10 @@ struct bpf_insn_aux_data {
 		unsigned long map_state;	/* pointer/poison value for maps */
 		s32 call_imm;			/* saved imm field of call insn */
 		u32 alu_limit;			/* limit for add/sub register with pointer */
+		struct {
+			u32 map_index;		/* index into used_maps[] */
+			u32 map_off;		/* offset from value base address */
+		};
 	};
 	int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
 	int sanitize_stack_off; /* stack slot to be cleared */

include/linux/btf.h

@@ -51,6 +51,7 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 			   const struct btf_member *m,
 			   u32 expected_offset, u32 expected_size);
 int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t);
+bool btf_type_is_void(const struct btf_type *t);
 
 #ifdef CONFIG_BPF_SYSCALL
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);

include/uapi/linux/bpf.h

@@ -105,6 +105,7 @@ enum bpf_cmd {
 	BPF_BTF_GET_FD_BY_ID,
 	BPF_TASK_FD_QUERY,
 	BPF_MAP_LOOKUP_AND_DELETE_ELEM,
+	BPF_MAP_FREEZE,
 };
 
 enum bpf_map_type {
@@ -255,8 +256,19 @@ enum bpf_attach_type {
  */
 #define BPF_F_ANY_ALIGNMENT	(1U << 1)
 
-/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */
+/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
+ * two extensions:
+ *
+ * insn[0].src_reg:  BPF_PSEUDO_MAP_FD   BPF_PSEUDO_MAP_VALUE
+ * insn[0].imm:      map fd              map fd
+ * insn[1].imm:      0                   offset into value
+ * insn[0].off:      0                   0
+ * insn[1].off:      0                   0
+ * ldimm64 rewrite:  address of map      address of map[0]+offset
+ * verifier type:    CONST_PTR_TO_MAP    PTR_TO_MAP_VALUE
+ */
 #define BPF_PSEUDO_MAP_FD	1
+#define BPF_PSEUDO_MAP_VALUE	2
 
 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
  * offset to another bpf function
@@ -283,7 +295,7 @@ enum bpf_attach_type {
 
 #define BPF_OBJ_NAME_LEN 16U
 
-/* Flags for accessing BPF object */
+/* Flags for accessing BPF object from syscall side. */
 #define BPF_F_RDONLY		(1U << 3)
 #define BPF_F_WRONLY		(1U << 4)
 
@@ -293,6 +305,10 @@ enum bpf_attach_type {
 /* Zero-initialize hash function seed. This should only be used for testing. */
 #define BPF_F_ZERO_SEED		(1U << 6)
 
+/* Flags for accessing BPF object from program side. */
+#define BPF_F_RDONLY_PROG	(1U << 7)
+#define BPF_F_WRONLY_PROG	(1U << 8)
+
 /* flags for BPF_PROG_QUERY */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 

include/uapi/linux/btf.h

@@ -39,11 +39,11 @@ struct btf_type {
 	 *             struct, union and fwd
 	 */
 	__u32 info;
-	/* "size" is used by INT, ENUM, STRUCT and UNION.
+	/* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC.
 	 * "size" tells the size of the type it is describing.
 	 *
 	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
-	 * FUNC and FUNC_PROTO.
+	 * FUNC, FUNC_PROTO and VAR.
 	 * "type" is a type_id referring to another type.
 	 */
 	union {
@@ -70,8 +70,10 @@ struct btf_type {
 #define BTF_KIND_RESTRICT	11	/* Restrict	*/
 #define BTF_KIND_FUNC		12	/* Function	*/
 #define BTF_KIND_FUNC_PROTO	13	/* Function Proto	*/
-#define BTF_KIND_MAX		13
-#define NR_BTF_KINDS		14
+#define BTF_KIND_VAR		14	/* Variable	*/
+#define BTF_KIND_DATASEC	15	/* Section	*/
+#define BTF_KIND_MAX		BTF_KIND_DATASEC
+#define NR_BTF_KINDS		(BTF_KIND_MAX + 1)
 
 /* For some specific BTF_KIND, "struct btf_type" is immediately
  * followed by extra data.
@@ -138,4 +140,26 @@ struct btf_param {
 	__u32	type;
 };
 
+enum {
+	BTF_VAR_STATIC = 0,
+	BTF_VAR_GLOBAL_ALLOCATED,
+};
+
+/* BTF_KIND_VAR is followed by a single "struct btf_var" to describe
+ * additional information related to the variable such as its linkage.
+ */
+struct btf_var {
+	__u32	linkage;
+};
+
+/* BTF_KIND_DATASEC is followed by multiple "struct btf_var_secinfo"
+ * to describe all BTF_KIND_VAR types it contains along with it's
+ * in-section offset as well as size.
+ */
+struct btf_var_secinfo {
+	__u32	type;
+	__u32	offset;
+	__u32	size;
+};
+
 #endif /* _UAPI__LINUX_BTF_H__ */

kernel/bpf/arraymap.c

@@ -22,7 +22,7 @@
 #include "map_in_map.h"
 
 #define ARRAY_CREATE_FLAG_MASK \
-	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+	(BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
 
 static void bpf_array_free_percpu(struct bpf_array *array)
 {
@@ -63,6 +63,7 @@ int array_map_alloc_check(union bpf_attr *attr)
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
 	    attr->value_size == 0 ||
 	    attr->map_flags & ~ARRAY_CREATE_FLAG_MASK ||
+	    !bpf_map_flags_access_ok(attr->map_flags) ||
 	    (percpu && numa_node != NUMA_NO_NODE))
 		return -EINVAL;
 
@@ -160,6 +161,36 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key)
 	return array->value + array->elem_size * (index & array->index_mask);
 }
 
+static int array_map_direct_value_addr(const struct bpf_map *map, u64 *imm,
+				       u32 off)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+
+	if (map->max_entries != 1)
+		return -ENOTSUPP;
+	if (off >= map->value_size)
+		return -EINVAL;
+
+	*imm = (unsigned long)array->value;
+	return 0;
+}
+
+static int array_map_direct_value_meta(const struct bpf_map *map, u64 imm,
+				       u32 *off)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	u64 base = (unsigned long)array->value;
+	u64 range = array->elem_size;
+
+	if (map->max_entries != 1)
+		return -ENOTSUPP;
+	if (imm < base || imm >= base + range)
+		return -ENOENT;
+
+	*off = imm - base;
+	return 0;
+}
+
 /* emit BPF instructions equivalent to C code of array_map_lookup_elem() */
 static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 {
@@ -360,7 +391,8 @@ static void array_map_seq_show_elem(struct bpf_map *map, void *key,
 		return;
 	}
 
-	seq_printf(m, "%u: ", *(u32 *)key);
+	if (map->btf_key_type_id)
+		seq_printf(m, "%u: ", *(u32 *)key);
 	btf_type_seq_show(map->btf, map->btf_value_type_id, value, m);
 	seq_puts(m, "\n");
 
@@ -397,6 +429,18 @@ static int array_map_check_btf(const struct bpf_map *map,
 {
 	u32 int_data;
 
+	/* One exception for keyless BTF: .bss/.data/.rodata map */
+	if (btf_type_is_void(key_type)) {
+		if (map->map_type != BPF_MAP_TYPE_ARRAY ||
+		    map->max_entries != 1)
+			return -EINVAL;
+
+		if (BTF_INFO_KIND(value_type->info) != BTF_KIND_DATASEC)
+			return -EINVAL;
+
+		return 0;
+	}
+
 	if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
 		return -EINVAL;
 
@@ -419,6 +463,8 @@ const struct bpf_map_ops array_map_ops = {
 	.map_update_elem = array_map_update_elem,
 	.map_delete_elem = array_map_delete_elem,
 	.map_gen_lookup = array_map_gen_lookup,
+	.map_direct_value_addr = array_map_direct_value_addr,
+	.map_direct_value_meta = array_map_direct_value_meta,
 	.map_seq_show_elem = array_map_seq_show_elem,
 	.map_check_btf = array_map_check_btf,
 };
@@ -440,6 +486,9 @@ static int fd_array_map_alloc_check(union bpf_attr *attr)
 	/* only file descriptors can be stored in this type of map */
 	if (attr->value_size != sizeof(u32))
 		return -EINVAL;
+	/* Program read-only/write-only not supported for special maps yet. */
+	if (attr->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG))
+		return -EINVAL;
 	return array_map_alloc_check(attr);
 }