Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2021-11-15

We've added 72 non-merge commits during the last 13 day(s) which contain
a total of 171 files changed, 2728 insertions(+), 1143 deletions(-).

The main changes are:

1) Add btf_type_tag attributes to bring kernel annotations like __user/__rcu to
   BTF such that BPF verifier will be able to detect misuse, from Yonghong Song.

2) Big batch of libbpf improvements including various fixes, future proofing APIs,
   and adding a unified, OPTS-based bpf_prog_load() low-level API, from Andrii Nakryiko.

3) Add ingress_ifindex to BPF_SK_LOOKUP program type for selectively applying the
   programmable socket lookup logic to packets from a given netdev, from Mark Pashmfouroush.

4) Remove the 128M upper JIT limit for BPF programs on arm64 and add selftest to
   ensure exception handling still works, from Russell King and Alan Maguire.

5) Add a new bpf_find_vma() helper for tracing to map an address to the backing
   file such as shared library, from Song Liu.

6) Batch of various misc fixes to bpftool, fixing a memory leak in BPF program dump,
   updating documentation and bash-completion among others, from Quentin Monnet.

7) Deprecate libbpf bpf_program__get_prog_info_linear() API and migrate its users as
   the API is heavily tailored around perf and is non-generic, from Dave Marchevsky.

8) Enable libbpf's strict mode by default in bpftool and add a --legacy option as an
   opt-out for more relaxed BPF program requirements, from Stanislav Fomichev.

9) Fix bpftool to use libbpf_get_error() to check for errors, from Hengqi Chen.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (72 commits)
  bpftool: Use libbpf_get_error() to check error
  bpftool: Fix mixed indentation in documentation
  bpftool: Update the lists of names for maps and prog-attach types
  bpftool: Fix indent in option lists in the documentation
  bpftool: Remove inclusion of utilities.mak from Makefiles
  bpftool: Fix memory leak in prog_dump()
  selftests/bpf: Fix a tautological-constant-out-of-range-compare compiler warning
  selftests/bpf: Fix an unused-but-set-variable compiler warning
  bpf: Introduce btf_tracing_ids
  bpf: Extend BTF_ID_LIST_GLOBAL with parameter for number of IDs
  bpftool: Enable libbpf's strict mode by default
  docs/bpf: Update documentation for BTF_KIND_TYPE_TAG support
  selftests/bpf: Clarify llvm dependency with btf_tag selftest
  selftests/bpf: Add a C test for btf_type_tag
  selftests/bpf: Rename progs/tag.c to progs/btf_decl_tag.c
  selftests/bpf: Test BTF_KIND_DECL_TAG for deduplication
  selftests/bpf: Add BTF_KIND_TYPE_TAG unit tests
  selftests/bpf: Test libbpf API function btf__add_type_tag()
  bpftool: Support BTF_KIND_TYPE_TAG
  libbpf: Support BTF_KIND_TYPE_TAG
  ...
====================

Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Documentation/bpf/btf.rst

@@ -86,6 +86,7 @@ sequentially and type id is assigned to each recognized type starting from id
     #define BTF_KIND_DATASEC        15      /* Section      */
     #define BTF_KIND_FLOAT          16      /* Floating point       */
     #define BTF_KIND_DECL_TAG       17      /* Decl Tag     */
+    #define BTF_KIND_TYPE_TAG       18      /* Type Tag     */
 
 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.
@@ -107,7 +108,7 @@ Each type contains the following common data::
          * "size" tells the size of the type it is describing.
          *
          * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
-         * FUNC, FUNC_PROTO and DECL_TAG.
+         * FUNC, FUNC_PROTO, DECL_TAG and TYPE_TAG.
          * "type" is a type_id referring to another type.
          */
         union {
@@ -492,6 +493,16 @@ the attribute is applied to a ``struct``/``union`` member or
 a ``func`` argument, and ``btf_decl_tag.component_idx`` should be a
 valid index (starting from 0) pointing to a member or an argument.
 
+2.2.17 BTF_KIND_TYPE_TAG
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+``struct btf_type`` encoding requirement:
+ * ``name_off``: offset to a non-empty string
+ * ``info.kind_flag``: 0
+ * ``info.kind``: BTF_KIND_TYPE_TAG
+ * ``info.vlen``: 0
+ * ``type``: the type with ``btf_type_tag`` attribute
+
 3. BTF Kernel API
 *****************
 

arch/arm64/include/asm/extable.h

@@ -33,15 +33,6 @@ do {							\
 	(b)->data = (tmp).data;				\
 } while (0)
 
-static inline bool in_bpf_jit(struct pt_regs *regs)
-{
-	if (!IS_ENABLED(CONFIG_BPF_JIT))
-		return false;
-
-	return regs->pc >= BPF_JIT_REGION_START &&
-	       regs->pc < BPF_JIT_REGION_END;
-}
-
 #ifdef CONFIG_BPF_JIT
 bool ex_handler_bpf(const struct exception_table_entry *ex,
 		    struct pt_regs *regs);

arch/arm64/include/asm/memory.h

@@ -44,11 +44,8 @@
 #define _PAGE_OFFSET(va)	(-(UL(1) << (va)))
 #define PAGE_OFFSET		(_PAGE_OFFSET(VA_BITS))
 #define KIMAGE_VADDR		(MODULES_END)
-#define BPF_JIT_REGION_START	(_PAGE_END(VA_BITS_MIN))
-#define BPF_JIT_REGION_SIZE	(SZ_128M)
-#define BPF_JIT_REGION_END	(BPF_JIT_REGION_START + BPF_JIT_REGION_SIZE)
 #define MODULES_END		(MODULES_VADDR + MODULES_VSIZE)
-#define MODULES_VADDR		(BPF_JIT_REGION_END)
+#define MODULES_VADDR		(_PAGE_END(VA_BITS_MIN))
 #define MODULES_VSIZE		(SZ_128M)
 #define VMEMMAP_START		(-(UL(1) << (VA_BITS - VMEMMAP_SHIFT)))
 #define VMEMMAP_END		(VMEMMAP_START + VMEMMAP_SIZE)

arch/arm64/kernel/traps.c

@@ -994,7 +994,7 @@ static struct break_hook bug_break_hook = {
 static int reserved_fault_handler(struct pt_regs *regs, unsigned int esr)
 {
 	pr_err("%s generated an invalid instruction at %pS!\n",
-		in_bpf_jit(regs) ? "BPF JIT" : "Kernel text patching",
+		"Kernel text patching",
 		(void *)instruction_pointer(regs));
 
 	/* We cannot handle this */

arch/arm64/mm/ptdump.c

@@ -41,8 +41,6 @@ static struct addr_marker address_markers[] = {
 	{ 0 /* KASAN_SHADOW_START */,	"Kasan shadow start" },
 	{ KASAN_SHADOW_END,		"Kasan shadow end" },
 #endif
-	{ BPF_JIT_REGION_START,		"BPF start" },
-	{ BPF_JIT_REGION_END,		"BPF end" },
 	{ MODULES_VADDR,		"Modules start" },
 	{ MODULES_END,			"Modules end" },
 	{ VMALLOC_START,		"vmalloc() area" },

arch/arm64/net/bpf_jit_comp.c

@@ -1141,15 +1141,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 u64 bpf_jit_alloc_exec_limit(void)
 {
-	return BPF_JIT_REGION_SIZE;
+	return VMALLOC_END - VMALLOC_START;
 }
 
 void *bpf_jit_alloc_exec(unsigned long size)
 {
-	return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,
-				    BPF_JIT_REGION_END, GFP_KERNEL,
-				    PAGE_KERNEL, 0, NUMA_NO_NODE,
-				    __builtin_return_address(0));
+	return vmalloc(size);
 }
 
 void bpf_jit_free_exec(void *addr)

include/linux/bpf.h

@@ -2163,6 +2163,7 @@ extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto;
 extern const struct bpf_func_proto bpf_sk_setsockopt_proto;
 extern const struct bpf_func_proto bpf_sk_getsockopt_proto;
 extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto;
+extern const struct bpf_func_proto bpf_find_vma_proto;
 
 const struct bpf_func_proto *tracing_prog_func_proto(
   enum bpf_func_id func_id, const struct bpf_prog *prog);

include/linux/btf_ids.h

@@ -73,7 +73,7 @@ asm(							\
 __BTF_ID_LIST(name, local)				\
 extern u32 name[];
 
-#define BTF_ID_LIST_GLOBAL(name)			\
+#define BTF_ID_LIST_GLOBAL(name, n)			\
 __BTF_ID_LIST(name, globl)
 
 /* The BTF_ID_LIST_SINGLE macro defines a BTF_ID_LIST with
@@ -83,7 +83,7 @@ __BTF_ID_LIST(name, globl)
 	BTF_ID_LIST(name) \
 	BTF_ID(prefix, typename)
 #define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) \
-	BTF_ID_LIST_GLOBAL(name) \
+	BTF_ID_LIST_GLOBAL(name, 1)			  \
 	BTF_ID(prefix, typename)
 
 /*
@@ -149,7 +149,7 @@ extern struct btf_id_set name;
 #define BTF_ID_LIST(name) static u32 name[5];
 #define BTF_ID(prefix, name)
 #define BTF_ID_UNUSED
-#define BTF_ID_LIST_GLOBAL(name) u32 name[1];
+#define BTF_ID_LIST_GLOBAL(name, n) u32 name[n];
 #define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1];
 #define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 name[1];
 #define BTF_SET_START(name) static struct btf_id_set name = { 0 };
@@ -189,6 +189,18 @@ MAX_BTF_SOCK_TYPE,
 extern u32 btf_sock_ids[];
 #endif
 
-extern u32 btf_task_struct_ids[];
+#define BTF_TRACING_TYPE_xxx	\
+	BTF_TRACING_TYPE(BTF_TRACING_TYPE_TASK, task_struct)	\
+	BTF_TRACING_TYPE(BTF_TRACING_TYPE_FILE, file)		\
+	BTF_TRACING_TYPE(BTF_TRACING_TYPE_VMA, vm_area_struct)
+
+enum {
+#define BTF_TRACING_TYPE(name, type) name,
+BTF_TRACING_TYPE_xxx
+#undef BTF_TRACING_TYPE
+MAX_BTF_TRACING_TYPE,
+};
+
+extern u32 btf_tracing_ids[];
 
 #endif

include/linux/filter.h

@@ -1374,6 +1374,7 @@ struct bpf_sk_lookup_kern {
 		const struct in6_addr *daddr;
 	} v6;
 	struct sock	*selected_sk;
+	u32		ingress_ifindex;
 	bool		no_reuseport;
 };
 
@@ -1436,7 +1437,7 @@ extern struct static_key_false bpf_sk_lookup_enabled;
 static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol,
 					const __be32 saddr, const __be16 sport,
 					const __be32 daddr, const u16 dport,
-					struct sock **psk)
+					const int ifindex, struct sock **psk)
 {
 	struct bpf_prog_array *run_array;
 	struct sock *selected_sk = NULL;
@@ -1452,6 +1453,7 @@ static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol,
 			.v4.daddr	= daddr,
 			.sport		= sport,
 			.dport		= dport,
+			.ingress_ifindex	= ifindex,
 		};
 		u32 act;
 
@@ -1474,7 +1476,7 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol,
 					const __be16 sport,
 					const struct in6_addr *daddr,
 					const u16 dport,
-					struct sock **psk)
+					const int ifindex, struct sock **psk)
 {
 	struct bpf_prog_array *run_array;
 	struct sock *selected_sk = NULL;
@@ -1490,6 +1492,7 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol,
 			.v6.daddr	= daddr,
 			.sport		= sport,
 			.dport		= dport,
+			.ingress_ifindex	= ifindex,
 		};
 		u32 act;
 

include/uapi/linux/bpf.h

@@ -4938,6 +4938,25 @@ union bpf_attr {
  *		**-ENOENT** if symbol is not found.
  *
  *		**-EPERM** if caller does not have permission to obtain kernel address.
+ *
+ * long bpf_find_vma(struct task_struct *task, u64 addr, void *callback_fn, void *callback_ctx, u64 flags)
+ *	Description
+ *		Find vma of *task* that contains *addr*, call *callback_fn*
+ *		function with *task*, *vma*, and *callback_ctx*.
+ *		The *callback_fn* should be a static function and
+ *		the *callback_ctx* should be a pointer to the stack.
+ *		The *flags* is used to control certain aspects of the helper.
+ *		Currently, the *flags* must be 0.
+ *
+ *		The expected callback signature is
+ *
+ *		long (\*callback_fn)(struct task_struct \*task, struct vm_area_struct \*vma, void \*callback_ctx);
+ *
+ *	Return
+ *		0 on success.
+ *		**-ENOENT** if *task->mm* is NULL, or no vma contains *addr*.
+ *		**-EBUSY** if failed to try lock mmap_lock.
+ *		**-EINVAL** for invalid **flags**.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5120,6 +5139,7 @@ union bpf_attr {
 	FN(trace_vprintk),		\
 	FN(skc_to_unix_sock),		\
 	FN(kallsyms_lookup_name),	\
+	FN(find_vma),			\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -6296,6 +6316,7 @@ struct bpf_sk_lookup {
 	__u32 local_ip4;	/* Network byte order */
 	__u32 local_ip6[4];	/* Network byte order */
 	__u32 local_port;	/* Host byte order */
+	__u32 ingress_ifindex;		/* The arriving interface. Determined by inet_iif. */
 };
 
 /*

include/uapi/linux/btf.h

@@ -43,7 +43,7 @@ struct btf_type {
 	 * "size" tells the size of the type it is describing.
 	 *
 	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
-	 * FUNC, FUNC_PROTO, VAR and DECL_TAG.
+	 * FUNC, FUNC_PROTO, VAR, DECL_TAG and TYPE_TAG.
 	 * "type" is a type_id referring to another type.
 	 */
 	union {
@@ -75,6 +75,7 @@ enum {
 	BTF_KIND_DATASEC	= 15,	/* Section	*/
 	BTF_KIND_FLOAT		= 16,	/* Floating point	*/
 	BTF_KIND_DECL_TAG	= 17,	/* Decl Tag */
+	BTF_KIND_TYPE_TAG	= 18,	/* Type Tag */
 
 	NR_BTF_KINDS,
 	BTF_KIND_MAX		= NR_BTF_KINDS - 1,

kernel/bpf/bpf_task_storage.c

@@ -323,7 +323,7 @@ const struct bpf_func_proto bpf_task_storage_get_proto = {
 	.ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg1_type = ARG_CONST_MAP_PTR,
 	.arg2_type = ARG_PTR_TO_BTF_ID,
-	.arg2_btf_id = &btf_task_struct_ids[0],
+	.arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
 	.arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg4_type = ARG_ANYTHING,
 };
@@ -334,5 +334,5 @@ const struct bpf_func_proto bpf_task_storage_delete_proto = {
 	.ret_type = RET_INTEGER,
 	.arg1_type = ARG_CONST_MAP_PTR,
 	.arg2_type = ARG_PTR_TO_BTF_ID,
-	.arg2_btf_id = &btf_task_struct_ids[0],
+	.arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
 };

kernel/bpf/btf.c

@@ -282,6 +282,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = {
 	[BTF_KIND_DATASEC]	= "DATASEC",
 	[BTF_KIND_FLOAT]	= "FLOAT",
 	[BTF_KIND_DECL_TAG]	= "DECL_TAG",
+	[BTF_KIND_TYPE_TAG]	= "TYPE_TAG",
 };
 
 const char *btf_type_str(const struct btf_type *t)
@@ -418,6 +419,7 @@ static bool btf_type_is_modifier(const struct btf_type *t)
 	case BTF_KIND_VOLATILE:
 	case BTF_KIND_CONST:
 	case BTF_KIND_RESTRICT:
+	case BTF_KIND_TYPE_TAG:
 		return true;
 	}
 
@@ -1737,6 +1739,7 @@ __btf_resolve_size(const struct btf *btf, const struct btf_type *type,
 		case BTF_KIND_VOLATILE:
 		case BTF_KIND_CONST:
 		case BTF_KIND_RESTRICT:
+		case BTF_KIND_TYPE_TAG:
 			id = type->type;
 			type = btf_type_by_id(btf, type->type);
 			break;
@@ -2345,6 +2348,8 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env,
 				   const struct btf_type *t,
 				   u32 meta_left)
 {
+	const char *value;
+
 	if (btf_type_vlen(t)) {
 		btf_verifier_log_type(env, t, "vlen != 0");
 		return -EINVAL;
@@ -2360,7 +2365,7 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
-	/* typedef type must have a valid name, and other ref types,
+	/* typedef/type_tag type must have a valid name, and other ref types,
 	 * volatile, const, restrict, should have a null name.
 	 */
 	if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF) {
@@ -2369,6 +2374,12 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env,
 			btf_verifier_log_type(env, t, "Invalid name");
 			return -EINVAL;
 		}
+	} else if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPE_TAG) {
+		value = btf_name_by_offset(env->btf, t->name_off);
+		if (!value || !value[0]) {
+			btf_verifier_log_type(env, t, "Invalid name");
+			return -EINVAL;
+		}
 	} else {
 		if (t->name_off) {
 			btf_verifier_log_type(env, t, "Invalid name");
@@ -4059,6 +4070,7 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = {
 	[BTF_KIND_DATASEC] = &datasec_ops,
 	[BTF_KIND_FLOAT] = &float_ops,
 	[BTF_KIND_DECL_TAG] = &decl_tag_ops,
+	[BTF_KIND_TYPE_TAG] = &modifier_ops,
 };
 
 static s32 btf_check_meta(struct btf_verifier_env *env,
@@ -6342,7 +6354,10 @@ const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
-BTF_ID_LIST_GLOBAL_SINGLE(btf_task_struct_ids, struct, task_struct)
+BTF_ID_LIST_GLOBAL(btf_tracing_ids, MAX_BTF_TRACING_TYPE)
+#define BTF_TRACING_TYPE(name, type) BTF_ID(struct, type)
+BTF_TRACING_TYPE_xxx
+#undef BTF_TRACING_TYPE
 
 /* BTF ID set registration API for modules */