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

Daniel Borkmann says:

====================
pull-request: bpf-next 2021-01-16

1) Extend atomic operations to the BPF instruction set along with x86-64 JIT support,
   that is, atomic{,64}_{xchg,cmpxchg,fetch_{add,and,or,xor}}, from Brendan Jackman.

2) Add support for using kernel module global variables (__ksym externs in BPF
   programs) retrieved via module's BTF, from Andrii Nakryiko.

3) Generalize BPF stackmap's buildid retrieval and add support to have buildid
   stored in mmap2 event for perf, from Jiri Olsa.

4) Various fixes for cross-building BPF sefltests out-of-tree which then will
   unblock wider automated testing on ARM hardware, from Jean-Philippe Brucker.

5) Allow to retrieve SOL_SOCKET opts from sock_addr progs, from Daniel Borkmann.

6) Clean up driver's XDP buffer init and split into two helpers to init per-
   descriptor and non-changing fields during processing, from Lorenzo Bianconi.

7) Minor misc improvements to libbpf & bpftool, from Ian Rogers.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (41 commits)
  perf: Add build id data in mmap2 event
  bpf: Add size arg to build_id_parse function
  bpf: Move stack_map_get_build_id into lib
  bpf: Document new atomic instructions
  bpf: Add tests for new BPF atomic operations
  bpf: Add bitwise atomic instructions
  bpf: Pull out a macro for interpreting atomic ALU operations
  bpf: Add instructions for atomic_[cmp]xchg
  bpf: Add BPF_FETCH field / create atomic_fetch_add instruction
  bpf: Move BPF_STX reserved field check into BPF_STX verifier code
  bpf: Rename BPF_XADD and prepare to encode other atomics in .imm
  bpf: x86: Factor out a lookup table for some ALU opcodes
  bpf: x86: Factor out emission of REX byte
  bpf: x86: Factor out emission of ModR/M for *(reg + off)
  tools/bpftool: Add -Wall when building BPF programs
  bpf, libbpf: Avoid unused function warning on bpf_tail_call_static
  selftests/bpf: Install btf_dump test cases
  selftests/bpf: Fix installation of urandom_read
  selftests/bpf: Move generated test files to $(TEST_GEN_FILES)
  selftests/bpf: Fix out-of-tree build
  ...
====================

Link: https://lore.kernel.org/r/20210116012922.17823-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

8 files changed, 125 insertions, 19 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 07cb5d15e743..1aac2af12fed 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -761,9 +761,15 @@ struct bpf_ctx_arg_aux {
 	u32 btf_id;
 };
 
+struct btf_mod_pair {
+	struct btf *btf;
+	struct module *module;
+};
+
 struct bpf_prog_aux {
 	atomic64_t refcnt;
 	u32 used_map_cnt;
+	u32 used_btf_cnt;
 	u32 max_ctx_offset;
 	u32 max_pkt_offset;
 	u32 max_tp_access;
@@ -802,6 +808,7 @@ struct bpf_prog_aux {
 	const struct bpf_prog_ops *ops;
 	struct bpf_map **used_maps;
 	struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */
+	struct btf_mod_pair *used_btfs;
 	struct bpf_prog *prog;
 	struct user_struct *user;
 	u64 load_time; /* ns since boottime */
@@ -1206,8 +1213,6 @@ void bpf_prog_sub(struct bpf_prog *prog, int i);
 void bpf_prog_inc(struct bpf_prog *prog);
 struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog);
 void bpf_prog_put(struct bpf_prog *prog);
-void __bpf_free_used_maps(struct bpf_prog_aux *aux,
-			  struct bpf_map **used_maps, u32 len);
 
 void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock);
 void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock);
@@ -1403,7 +1408,10 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size)
 /* verify correctness of eBPF program */
 int bpf_check(struct bpf_prog **fp, union bpf_attr *attr,
 	      union bpf_attr __user *uattr);
+
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
 void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
+#endif
 
 struct btf *bpf_get_btf_vmlinux(void);
 
@@ -1667,12 +1675,18 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 }
 #endif /* CONFIG_BPF_SYSCALL */
 
+void __bpf_free_used_btfs(struct bpf_prog_aux *aux,
+			  struct btf_mod_pair *used_btfs, u32 len);
+
 static inline struct bpf_prog *bpf_prog_get_type(u32 ufd,
 						 enum bpf_prog_type type)
 {
 	return bpf_prog_get_type_dev(ufd, type, false);
 }
 
+void __bpf_free_used_maps(struct bpf_prog_aux *aux,
+			  struct bpf_map **used_maps, u32 len);
+
 bool bpf_prog_get_ok(struct bpf_prog *, enum bpf_prog_type *, bool);
 
 int bpf_prog_offload_compile(struct bpf_prog *prog);
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index e941fe1484e5..dfe6f85d97dd 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -340,6 +340,7 @@ struct bpf_insn_aux_data {
 };
 
 #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
+#define MAX_USED_BTFS 64 /* max number of BTFs accessed by one BPF program */
 
 #define BPF_VERIFIER_TMP_LOG_SIZE	1024
 
@@ -398,7 +399,9 @@ struct bpf_verifier_env {
 	struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
 	struct bpf_verifier_state_list *free_list;
 	struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */
+	struct btf_mod_pair used_btfs[MAX_USED_BTFS]; /* array of BTF's used by BPF program */
 	u32 used_map_cnt;		/* number of used maps */
+	u32 used_btf_cnt;		/* number of used BTF objects */
 	u32 id_gen;			/* used to generate unique reg IDs */
 	bool allow_ptr_leaks;
 	bool allow_ptr_to_map_access;
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 4c200f5d242b..7fabf1428093 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -91,6 +91,9 @@ int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj,
 int btf_get_fd_by_id(u32 id);
 u32 btf_obj_id(const struct btf *btf);
 bool btf_is_kernel(const struct btf *btf);
+bool btf_is_module(const struct btf *btf);
+struct module *btf_try_get_module(const struct btf *btf);
+u32 btf_nr_types(const struct btf *btf);
 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);
diff --git a/include/linux/buildid.h b/include/linux/buildid.h
new file mode 100644
index 000000000000..40232f90db6e
--- /dev/null
+++ b/include/linux/buildid.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_BUILDID_H
+#define _LINUX_BUILDID_H
+
+#include <linux/mm_types.h>
+
+#define BUILD_ID_SIZE_MAX 20
+
+int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id,
+		   __u32 *size);
+
+#endif
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 29c27656165b..7fdce5407214 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -259,15 +259,32 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
 		.off   = OFF,					\
 		.imm   = 0 })
 
-/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */
 
-#define BPF_STX_XADD(SIZE, DST, SRC, OFF)			\
+/*
+ * Atomic operations:
+ *
+ *   BPF_ADD                  *(uint *) (dst_reg + off16) += src_reg
+ *   BPF_AND                  *(uint *) (dst_reg + off16) &= src_reg
+ *   BPF_OR                   *(uint *) (dst_reg + off16) |= src_reg
+ *   BPF_XOR                  *(uint *) (dst_reg + off16) ^= src_reg
+ *   BPF_ADD | BPF_FETCH      src_reg = atomic_fetch_add(dst_reg + off16, src_reg);
+ *   BPF_AND | BPF_FETCH      src_reg = atomic_fetch_and(dst_reg + off16, src_reg);
+ *   BPF_OR | BPF_FETCH       src_reg = atomic_fetch_or(dst_reg + off16, src_reg);
+ *   BPF_XOR | BPF_FETCH      src_reg = atomic_fetch_xor(dst_reg + off16, src_reg);
+ *   BPF_XCHG                 src_reg = atomic_xchg(dst_reg + off16, src_reg)
+ *   BPF_CMPXCHG              r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg)
+ */
+
+#define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF)			\
 	((struct bpf_insn) {					\
-		.code  = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD,	\
+		.code  = BPF_STX | BPF_SIZE(SIZE) | BPF_ATOMIC,	\
 		.dst_reg = DST,					\
 		.src_reg = SRC,					\
 		.off   = OFF,					\
-		.imm   = 0 })
+		.imm   = OP })
+
+/* Legacy alias */
+#define BPF_STX_XADD(SIZE, DST, SRC, OFF) BPF_ATOMIC_OP(SIZE, BPF_ADD, DST, SRC, OFF)
 
 /* Memory store, *(uint *) (dst_reg + off16) = imm32 */
 
@@ -886,7 +903,7 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp);
 u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 #define __bpf_call_base_args \
 	((u64 (*)(u64, u64, u64, u64, u64, const struct bpf_insn *)) \
-	 __bpf_call_base)
+	 (void *)__bpf_call_base)
 
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog);
 void bpf_jit_compile(struct bpf_prog *prog);
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 600acb307db6..0cf3976ce77c 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -76,6 +76,25 @@ struct xdp_buff {
 	u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/
 };
 
+static __always_inline void
+xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq)
+{
+	xdp->frame_sz = frame_sz;
+	xdp->rxq = rxq;
+}
+
+static __always_inline void
+xdp_prepare_buff(struct xdp_buff *xdp, unsigned char *hard_start,
+		 int headroom, int data_len, const bool meta_valid)
+{
+	unsigned char *data = hard_start + headroom;
+
+	xdp->data_hard_start = hard_start;
+	xdp->data = data;
+	xdp->data_end = data + data_len;
+	xdp->data_meta = meta_valid ? data : data + 1;
+}
+
 /* Reserve memory area at end-of data area.
  *
  * This macro reserves tailroom in the XDP buffer by limiting the
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 77d7c1bb2923..c001766adcbc 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -19,7 +19,8 @@
 
 /* ld/ldx fields */
 #define BPF_DW		0x18	/* double word (64-bit) */
-#define BPF_XADD	0xc0	/* exclusive add */
+#define BPF_ATOMIC	0xc0	/* atomic memory ops - op type in immediate */
+#define BPF_XADD	0xc0	/* exclusive add - legacy name */
 
 /* alu/jmp fields */
 #define BPF_MOV		0xb0	/* mov reg to reg */
@@ -43,6 +44,11 @@
 #define BPF_CALL	0x80	/* function call */
 #define BPF_EXIT	0x90	/* function return */
 
+/* atomic op type fields (stored in immediate) */
+#define BPF_FETCH	0x01	/* not an opcode on its own, used to build others */
+#define BPF_XCHG	(0xe0 | BPF_FETCH)	/* atomic exchange */
+#define BPF_CMPXCHG	(0xf0 | BPF_FETCH)	/* atomic compare-and-write */
+
 /* Register numbers */
 enum {
 	BPF_REG_0 = 0,
@@ -2448,7 +2454,7 @@ union bpf_attr {
  *		running simultaneously.
  *
  *		A user should care about the synchronization by himself.
- *		For example, by using the **BPF_STX_XADD** instruction to alter
+ *		For example, by using the **BPF_ATOMIC** instructions to alter
  *		the shared data.
  *	Return
  *		A pointer to the local storage area.
@@ -2993,10 +2999,10 @@ union bpf_attr {
  * 		string length is larger than *size*, just *size*-1 bytes are
  * 		copied and the last byte is set to NUL.
  *
- * 		On success, the length of the copied string is returned. This
- * 		makes this helper useful in tracing programs for reading
- * 		strings, and more importantly to get its length at runtime. See
- * 		the following snippet:
+ * 		On success, returns the number of bytes that were written,
+ * 		including the terminal NUL. This makes this helper useful in
+ * 		tracing programs for reading strings, and more importantly to
+ * 		get its length at runtime. See the following snippet:
  *
  * 		::
  *
@@ -3024,7 +3030,7 @@ union bpf_attr {
  * 		**->mm->env_start**: using this helper and the return value,
  * 		one can quickly iterate at the right offset of the memory area.
  * 	Return
- * 		On success, the strictly positive length of the string,
+ * 		On success, the strictly positive length of the output string,
  * 		including the trailing NUL character. On error, a negative
  * 		value.
  *
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index b15e3447cd9f..cb6f84103560 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -386,7 +386,8 @@ struct perf_event_attr {
 				aux_output     :  1, /* generate AUX records instead of events */
 				cgroup         :  1, /* include cgroup events */
 				text_poke      :  1, /* include text poke events */
-				__reserved_1   : 30;
+				build_id       :  1, /* use build id in mmap2 events */
+				__reserved_1   : 29;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -659,6 +660,22 @@ struct perf_event_mmap_page {
 	__u64	aux_size;
 };
 
+/*
+ * The current state of perf_event_header::misc bits usage:
+ * ('|' used bit, '-' unused bit)
+ *
+ *  012         CDEF
+ *  |||---------||||
+ *
+ *  Where:
+ *    0-2     CPUMODE_MASK
+ *
+ *    C       PROC_MAP_PARSE_TIMEOUT
+ *    D       MMAP_DATA / COMM_EXEC / FORK_EXEC / SWITCH_OUT
+ *    E       MMAP_BUILD_ID / EXACT_IP / SCHED_OUT_PREEMPT
+ *    F       (reserved)
+ */
+
 #define PERF_RECORD_MISC_CPUMODE_MASK		(7 << 0)
 #define PERF_RECORD_MISC_CPUMODE_UNKNOWN	(0 << 0)
 #define PERF_RECORD_MISC_KERNEL			(1 << 0)
@@ -690,6 +707,7 @@ struct perf_event_mmap_page {
  *
  *   PERF_RECORD_MISC_EXACT_IP           - PERF_RECORD_SAMPLE of precise events
  *   PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events
+ *   PERF_RECORD_MISC_MMAP_BUILD_ID      - PERF_RECORD_MMAP2 event
  *
  *
  * PERF_RECORD_MISC_EXACT_IP:
@@ -699,9 +717,13 @@ struct perf_event_mmap_page {
  *
  * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT:
  *   Indicates that thread was preempted in TASK_RUNNING state.
+ *
+ * PERF_RECORD_MISC_MMAP_BUILD_ID:
+ *   Indicates that mmap2 event carries build id data.
  */
 #define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
 #define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT	(1 << 14)
+#define PERF_RECORD_MISC_MMAP_BUILD_ID		(1 << 14)
 /*
  * Reserve the last bit to indicate some extended misc field
  */
@@ -915,10 +937,20 @@ enum perf_event_type {
 	 *	u64				addr;
 	 *	u64				len;
 	 *	u64				pgoff;
-	 *	u32				maj;
-	 *	u32				min;
-	 *	u64				ino;
-	 *	u64				ino_generation;
+	 *	union {
+	 *		struct {
+	 *			u32		maj;
+	 *			u32		min;
+	 *			u64		ino;
+	 *			u64		ino_generation;
+	 *		};
+	 *		struct {
+	 *			u8		build_id_size;
+	 *			u8		__reserved_1;
+	 *			u16		__reserved_2;
+	 *			u8		build_id[20];
+	 *		};
+	 *	};
 	 *	u32				prot, flags;
 	 *	char				filename[];
 	 * 	struct sample_id		sample_id;