Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Alexei Starovoitov says:

====================
pull-request: bpf 2018-02-22

The following pull-request contains BPF updates for your *net* tree.

The main changes are:

1) two urgent fixes for bpf_tail_call logic for x64 and arm64 JITs, from Daniel.

2) cond_resched points in percpu array alloc/free paths, from Eric.

3) lockdep and other minor fixes, from Yonghong, Arnd, Anders, Li.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

arch/arm64/net/bpf_jit_comp.c

@@ -250,8 +250,9 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	off = offsetof(struct bpf_array, map.max_entries);
 	emit_a64_mov_i64(tmp, off, ctx);
 	emit(A64_LDR32(tmp, r2, tmp), ctx);
+	emit(A64_MOV(0, r3, r3), ctx);
 	emit(A64_CMP(0, r3, tmp), ctx);
-	emit(A64_B_(A64_COND_GE, jmp_offset), ctx);
+	emit(A64_B_(A64_COND_CS, jmp_offset), ctx);
 
 	/* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
 	 *     goto out;
@@ -259,7 +260,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	 */
 	emit_a64_mov_i64(tmp, MAX_TAIL_CALL_CNT, ctx);
 	emit(A64_CMP(1, tcc, tmp), ctx);
-	emit(A64_B_(A64_COND_GT, jmp_offset), ctx);
+	emit(A64_B_(A64_COND_HI, jmp_offset), ctx);
 	emit(A64_ADD_I(1, tcc, tcc, 1), ctx);
 
 	/* prog = array->ptrs[index];

arch/x86/include/asm/nospec-branch.h

@@ -177,4 +177,41 @@ static inline void indirect_branch_prediction_barrier(void)
 }
 
 #endif /* __ASSEMBLY__ */
+
+/*
+ * Below is used in the eBPF JIT compiler and emits the byte sequence
+ * for the following assembly:
+ *
+ * With retpolines configured:
+ *
+ *    callq do_rop
+ *  spec_trap:
+ *    pause
+ *    lfence
+ *    jmp spec_trap
+ *  do_rop:
+ *    mov %rax,(%rsp)
+ *    retq
+ *
+ * Without retpolines configured:
+ *
+ *    jmp *%rax
+ */
+#ifdef CONFIG_RETPOLINE
+# define RETPOLINE_RAX_BPF_JIT_SIZE	17
+# define RETPOLINE_RAX_BPF_JIT()				\
+	EMIT1_off32(0xE8, 7);	 /* callq do_rop */		\
+	/* spec_trap: */					\
+	EMIT2(0xF3, 0x90);       /* pause */			\
+	EMIT3(0x0F, 0xAE, 0xE8); /* lfence */			\
+	EMIT2(0xEB, 0xF9);       /* jmp spec_trap */		\
+	/* do_rop: */						\
+	EMIT4(0x48, 0x89, 0x04, 0x24); /* mov %rax,(%rsp) */	\
+	EMIT1(0xC3);             /* retq */
+#else
+# define RETPOLINE_RAX_BPF_JIT_SIZE	2
+# define RETPOLINE_RAX_BPF_JIT()				\
+	EMIT2(0xFF, 0xE0);	 /* jmp *%rax */
+#endif
+
 #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */

arch/x86/net/bpf_jit_comp.c

@@ -13,6 +13,7 @@
 #include <linux/if_vlan.h>
 #include <asm/cacheflush.h>
 #include <asm/set_memory.h>
+#include <asm/nospec-branch.h>
 #include <linux/bpf.h>
 
 /*
@@ -290,7 +291,7 @@ static void emit_bpf_tail_call(u8 **pprog)
 	EMIT2(0x89, 0xD2);                        /* mov edx, edx */
 	EMIT3(0x39, 0x56,                         /* cmp dword ptr [rsi + 16], edx */
 	      offsetof(struct bpf_array, map.max_entries));
-#define OFFSET1 43 /* number of bytes to jump */
+#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* number of bytes to jump */
 	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
 	label1 = cnt;
 
@@ -299,7 +300,7 @@ static void emit_bpf_tail_call(u8 **pprog)
 	 */
 	EMIT2_off32(0x8B, 0x85, 36);              /* mov eax, dword ptr [rbp + 36] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
-#define OFFSET2 32
+#define OFFSET2 (30 + RETPOLINE_RAX_BPF_JIT_SIZE)
 	EMIT2(X86_JA, OFFSET2);                   /* ja out */
 	label2 = cnt;
 	EMIT3(0x83, 0xC0, 0x01);                  /* add eax, 1 */
@@ -313,7 +314,7 @@ static void emit_bpf_tail_call(u8 **pprog)
 	 *   goto out;
 	 */
 	EMIT3(0x48, 0x85, 0xC0);		  /* test rax,rax */
-#define OFFSET3 10
+#define OFFSET3 (8 + RETPOLINE_RAX_BPF_JIT_SIZE)
 	EMIT2(X86_JE, OFFSET3);                   /* je out */
 	label3 = cnt;
 
@@ -326,7 +327,7 @@ static void emit_bpf_tail_call(u8 **pprog)
 	 * rdi == ctx (1st arg)
 	 * rax == prog->bpf_func + prologue_size
 	 */
-	EMIT2(0xFF, 0xE0);                        /* jmp rax */
+	RETPOLINE_RAX_BPF_JIT();
 
 	/* out: */
 	BUILD_BUG_ON(cnt - label1 != OFFSET1);

kernel/bpf/arraymap.c

@@ -26,8 +26,10 @@ static void bpf_array_free_percpu(struct bpf_array *array)
 {
 	int i;
 
-	for (i = 0; i < array->map.max_entries; i++)
+	for (i = 0; i < array->map.max_entries; i++) {
 		free_percpu(array->pptrs[i]);
+		cond_resched();
+	}
 }
 
 static int bpf_array_alloc_percpu(struct bpf_array *array)
@@ -43,6 +45,7 @@ static int bpf_array_alloc_percpu(struct bpf_array *array)
 			return -ENOMEM;
 		}
 		array->pptrs[i] = ptr;
+		cond_resched();
 	}
 
 	return 0;

kernel/bpf/lpm_trie.c

@@ -569,8 +569,7 @@ static void trie_free(struct bpf_map *map)
 		slot = &trie->root;
 
 		for (;;) {
-			node = rcu_dereference_protected(*slot,
+			node = rcu_dereference_protected(*slot, 1);
-					lockdep_is_held(&trie->lock));
 			if (!node)
 				goto out;
 

net/core/filter.c

@@ -3381,17 +3381,13 @@ BPF_CALL_2(bpf_sock_ops_cb_flags_set, struct bpf_sock_ops_kern *, bpf_sock,
 	struct sock *sk = bpf_sock->sk;
 	int val = argval & BPF_SOCK_OPS_ALL_CB_FLAGS;
 
-	if (!sk_fullsock(sk))
+	if (!IS_ENABLED(CONFIG_INET) || !sk_fullsock(sk))
 		return -EINVAL;
 
-#ifdef CONFIG_INET
 	if (val)
 		tcp_sk(sk)->bpf_sock_ops_cb_flags = val;
 
 	return argval & (~BPF_SOCK_OPS_ALL_CB_FLAGS);
-#else
-	return -EINVAL;
-#endif
 }
 
 static const struct bpf_func_proto bpf_sock_ops_cb_flags_set_proto = {

tools/testing/selftests/bpf/.gitignore

@@ -11,3 +11,4 @@ test_progs
 test_tcpbpf_user
 test_verifier_log
 feature
+test_libbpf_open

tools/testing/selftests/bpf/test_maps.c

@@ -126,6 +126,8 @@ static void test_hashmap_sizes(int task, void *data)
 			fd = bpf_create_map(BPF_MAP_TYPE_HASH, i, j,
 					    2, map_flags);
 			if (fd < 0) {
+				if (errno == ENOMEM)
+					return;
 				printf("Failed to create hashmap key=%d value=%d '%s'\n",
 				       i, j, strerror(errno));
 				exit(1);

tools/testing/selftests/bpf/test_tcpbpf_kern.c

@@ -5,7 +5,6 @@
 #include <linux/if_ether.h>
 #include <linux/if_packet.h>
 #include <linux/ip.h>
-#include <linux/in6.h>
 #include <linux/types.h>
 #include <linux/socket.h>
 #include <linux/tcp.h>

tools/testing/selftests/bpf/test_verifier.c

@@ -2586,6 +2586,32 @@ static struct bpf_test tests[] = {
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
 	},
+	{
+		"runtime/jit: pass negative index to tail_call",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_3, -1),
+			BPF_LD_MAP_FD(BPF_REG_2, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_tail_call),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_prog = { 1 },
+		.result = ACCEPT,
+	},
+	{
+		"runtime/jit: pass > 32bit index to tail_call",
+		.insns = {
+			BPF_LD_IMM64(BPF_REG_3, 0x100000000ULL),
+			BPF_LD_MAP_FD(BPF_REG_2, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_tail_call),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_prog = { 2 },
+		.result = ACCEPT,
+	},
 	{
 		"stack pointer arithmetic",
 		.insns = {