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

Alexei Starovoitov says:

====================
pull-request: bpf 2019-06-15

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

The main changes are:

1) fix stack layout of JITed x64 bpf code, from Alexei.

2) fix out of bounds memory access in bpf_sk_storage, from Arthur.

3) fix lpm trie walk, from Jonathan.

4) fix nested bpf_perf_event_output, from Matt.

5) and several other fixes.
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

arch/powerpc/include/asm/ppc-opcode.h

@@ -338,6 +338,7 @@
 #define PPC_INST_MADDLD			0x10000033
 #define PPC_INST_DIVWU			0x7c000396
 #define PPC_INST_DIVD			0x7c0003d2
+#define PPC_INST_DIVDU			0x7c000392
 #define PPC_INST_RLWINM			0x54000000
 #define PPC_INST_RLWINM_DOT		0x54000001
 #define PPC_INST_RLWIMI			0x50000000

arch/powerpc/net/bpf_jit.h

@@ -116,7 +116,7 @@
 				     ___PPC_RA(a) | IMM_L(i))
 #define PPC_DIVWU(d, a, b)	EMIT(PPC_INST_DIVWU | ___PPC_RT(d) |	      \
 				     ___PPC_RA(a) | ___PPC_RB(b))
-#define PPC_DIVD(d, a, b)	EMIT(PPC_INST_DIVD | ___PPC_RT(d) |	      \
+#define PPC_DIVDU(d, a, b)	EMIT(PPC_INST_DIVDU | ___PPC_RT(d) |	      \
 				     ___PPC_RA(a) | ___PPC_RB(b))
 #define PPC_AND(d, a, b)	EMIT(PPC_INST_AND | ___PPC_RA(d) |	      \
 				     ___PPC_RS(a) | ___PPC_RB(b))

arch/powerpc/net/bpf_jit_comp64.c

@@ -399,12 +399,12 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */
 		case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */
 			if (BPF_OP(code) == BPF_MOD) {
-				PPC_DIVD(b2p[TMP_REG_1], dst_reg, src_reg);
+				PPC_DIVDU(b2p[TMP_REG_1], dst_reg, src_reg);
 				PPC_MULD(b2p[TMP_REG_1], src_reg,
 						b2p[TMP_REG_1]);
 				PPC_SUB(dst_reg, dst_reg, b2p[TMP_REG_1]);
 			} else
-				PPC_DIVD(dst_reg, dst_reg, src_reg);
+				PPC_DIVDU(dst_reg, dst_reg, src_reg);
 			break;
 		case BPF_ALU | BPF_MOD | BPF_K: /* (u32) dst %= (u32) imm */
 		case BPF_ALU | BPF_DIV | BPF_K: /* (u32) dst /= (u32) imm */
@@ -432,15 +432,15 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 				break;
 			case BPF_ALU64:
 				if (BPF_OP(code) == BPF_MOD) {
-					PPC_DIVD(b2p[TMP_REG_2], dst_reg,
+					PPC_DIVDU(b2p[TMP_REG_2], dst_reg,
 							b2p[TMP_REG_1]);
 					PPC_MULD(b2p[TMP_REG_1],
 							b2p[TMP_REG_1],
 							b2p[TMP_REG_2]);
 					PPC_SUB(dst_reg, dst_reg,
 							b2p[TMP_REG_1]);
 				} else
-					PPC_DIVD(dst_reg, dst_reg,
+					PPC_DIVDU(dst_reg, dst_reg,
 							b2p[TMP_REG_1]);
 				break;
 			}

arch/x86/net/bpf_jit_comp.c

@@ -190,9 +190,7 @@ struct jit_context {
 #define BPF_MAX_INSN_SIZE	128
 #define BPF_INSN_SAFETY		64
 
-#define AUX_STACK_SPACE		40 /* Space for RBX, R13, R14, R15, tailcnt */
-
-#define PROLOGUE_SIZE		37
+#define PROLOGUE_SIZE		20
 
 /*
  * Emit x86-64 prologue code for BPF program and check its size.
@@ -203,44 +201,19 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
 	u8 *prog = *pprog;
 	int cnt = 0;
 
-	/* push rbp */
-	EMIT1(0x55);
-
-	/* mov rbp,rsp */
-	EMIT3(0x48, 0x89, 0xE5);
-
-	/* sub rsp, rounded_stack_depth + AUX_STACK_SPACE */
-	EMIT3_off32(0x48, 0x81, 0xEC,
-		    round_up(stack_depth, 8) + AUX_STACK_SPACE);
-
-	/* sub rbp, AUX_STACK_SPACE */
-	EMIT4(0x48, 0x83, 0xED, AUX_STACK_SPACE);
-
-	/* mov qword ptr [rbp+0],rbx */
-	EMIT4(0x48, 0x89, 0x5D, 0);
-	/* mov qword ptr [rbp+8],r13 */
-	EMIT4(0x4C, 0x89, 0x6D, 8);
-	/* mov qword ptr [rbp+16],r14 */
-	EMIT4(0x4C, 0x89, 0x75, 16);
-	/* mov qword ptr [rbp+24],r15 */
-	EMIT4(0x4C, 0x89, 0x7D, 24);
-
+	EMIT1(0x55);             /* push rbp */
+	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
+	/* sub rsp, rounded_stack_depth */
+	EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8));
+	EMIT1(0x53);             /* push rbx */
+	EMIT2(0x41, 0x55);       /* push r13 */
+	EMIT2(0x41, 0x56);       /* push r14 */
+	EMIT2(0x41, 0x57);       /* push r15 */
 	if (!ebpf_from_cbpf) {
-		/*
-		 * Clear the tail call counter (tail_call_cnt): for eBPF tail
-		 * calls we need to reset the counter to 0. It's done in two
-		 * instructions, resetting RAX register to 0, and moving it
-		 * to the counter location.
-		 */
-
-		/* xor eax, eax */
-		EMIT2(0x31, 0xc0);
-		/* mov qword ptr [rbp+32], rax */
-		EMIT4(0x48, 0x89, 0x45, 32);
-
+		/* zero init tail_call_cnt */
+		EMIT2(0x6a, 0x00);
 		BUILD_BUG_ON(cnt != PROLOGUE_SIZE);
 	}
-
 	*pprog = prog;
 }
 
@@ -285,13 +258,13 @@ static void emit_bpf_tail_call(u8 **pprog)
 	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
 	 *	goto out;
 	 */
-	EMIT2_off32(0x8B, 0x85, 36);              /* mov eax, dword ptr [rbp + 36] */
+	EMIT2_off32(0x8B, 0x85, -36 - MAX_BPF_STACK); /* mov eax, dword ptr [rbp - 548] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
 #define OFFSET2 (30 + RETPOLINE_RAX_BPF_JIT_SIZE)
 	EMIT2(X86_JA, OFFSET2);                   /* ja out */
 	label2 = cnt;
 	EMIT3(0x83, 0xC0, 0x01);                  /* add eax, 1 */
-	EMIT2_off32(0x89, 0x85, 36);              /* mov dword ptr [rbp + 36], eax */
+	EMIT2_off32(0x89, 0x85, -36 - MAX_BPF_STACK); /* mov dword ptr [rbp -548], eax */
 
 	/* prog = array->ptrs[index]; */
 	EMIT4_off32(0x48, 0x8B, 0x84, 0xD6,       /* mov rax, [rsi + rdx * 8 + offsetof(...)] */
@@ -1040,19 +1013,14 @@ xadd:			if (is_imm8(insn->off))
 			seen_exit = true;
 			/* Update cleanup_addr */
 			ctx->cleanup_addr = proglen;
-			/* mov rbx, qword ptr [rbp+0] */
-			EMIT4(0x48, 0x8B, 0x5D, 0);
-			/* mov r13, qword ptr [rbp+8] */
-			EMIT4(0x4C, 0x8B, 0x6D, 8);
-			/* mov r14, qword ptr [rbp+16] */
-			EMIT4(0x4C, 0x8B, 0x75, 16);
-			/* mov r15, qword ptr [rbp+24] */
-			EMIT4(0x4C, 0x8B, 0x7D, 24);
-
-			/* add rbp, AUX_STACK_SPACE */
-			EMIT4(0x48, 0x83, 0xC5, AUX_STACK_SPACE);
-			EMIT1(0xC9); /* leave */
-			EMIT1(0xC3); /* ret */
+			if (!bpf_prog_was_classic(bpf_prog))
+				EMIT1(0x5B); /* get rid of tail_call_cnt */
+			EMIT2(0x41, 0x5F);   /* pop r15 */
+			EMIT2(0x41, 0x5E);   /* pop r14 */
+			EMIT2(0x41, 0x5D);   /* pop r13 */
+			EMIT1(0x5B);         /* pop rbx */
+			EMIT1(0xC9);         /* leave */
+			EMIT1(0xC3);         /* ret */
 			break;
 
 		default:

include/uapi/linux/bpf.h

@@ -3378,8 +3378,8 @@ struct bpf_raw_tracepoint_args {
 /* DIRECT:  Skip the FIB rules and go to FIB table associated with device
  * OUTPUT:  Do lookup from egress perspective; default is ingress
  */
-#define BPF_FIB_LOOKUP_DIRECT  BIT(0)
-#define BPF_FIB_LOOKUP_OUTPUT  BIT(1)
+#define BPF_FIB_LOOKUP_DIRECT  (1U << 0)
+#define BPF_FIB_LOOKUP_OUTPUT  (1U << 1)
 
 enum {
 	BPF_FIB_LKUP_RET_SUCCESS,      /* lookup successful */

kernel/bpf/devmap.c

@@ -186,6 +186,7 @@ static void dev_map_free(struct bpf_map *map)
 		if (!dev)
 			continue;
 
+		free_percpu(dev->bulkq);
 		dev_put(dev->dev);
 		kfree(dev);
 	}
@@ -281,6 +282,7 @@ void __dev_map_flush(struct bpf_map *map)
 	unsigned long *bitmap = this_cpu_ptr(dtab->flush_needed);
 	u32 bit;
 
+	rcu_read_lock();
 	for_each_set_bit(bit, bitmap, map->max_entries) {
 		struct bpf_dtab_netdev *dev = READ_ONCE(dtab->netdev_map[bit]);
 		struct xdp_bulk_queue *bq;
@@ -291,11 +293,12 @@ void __dev_map_flush(struct bpf_map *map)
 		if (unlikely(!dev))
 			continue;
 
-		__clear_bit(bit, bitmap);
-
 		bq = this_cpu_ptr(dev->bulkq);
 		bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, true);
+
+		__clear_bit(bit, bitmap);
 	}
+	rcu_read_unlock();
 }
 
 /* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or
@@ -388,13 +391,15 @@ static void dev_map_flush_old(struct bpf_dtab_netdev *dev)
 
 		int cpu;
 
+		rcu_read_lock();
 		for_each_online_cpu(cpu) {
 			bitmap = per_cpu_ptr(dev->dtab->flush_needed, cpu);
 			__clear_bit(dev->bit, bitmap);
 
 			bq = per_cpu_ptr(dev->bulkq, cpu);
 			bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, false);
 		}
+		rcu_read_unlock();
 	}
 }
 

kernel/bpf/lpm_trie.c

@@ -716,9 +716,14 @@ static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key)
 	 * have exact two children, so this function will never return NULL.
 	 */
 	for (node = search_root; node;) {
-		if (!(node->flags & LPM_TREE_NODE_FLAG_IM))
+		if (node->flags & LPM_TREE_NODE_FLAG_IM) {
+			node = rcu_dereference(node->child[0]);
+		} else {
 			next_node = node;
-		node = rcu_dereference(node->child[0]);
+			node = rcu_dereference(node->child[0]);
+			if (!node)
+				node = rcu_dereference(next_node->child[1]);
+		}
 	}
 do_copy:
 	next_key->prefixlen = next_node->prefixlen;

kernel/trace/bpf_trace.c

@@ -410,8 +410,6 @@ static const struct bpf_func_proto bpf_perf_event_read_value_proto = {
 	.arg4_type	= ARG_CONST_SIZE,
 };
 
-static DEFINE_PER_CPU(struct perf_sample_data, bpf_trace_sd);
-
 static __always_inline u64
 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
 			u64 flags, struct perf_sample_data *sd)
@@ -442,24 +440,50 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
 	return perf_event_output(event, sd, regs);
 }
 
+/*
+ * Support executing tracepoints in normal, irq, and nmi context that each call
+ * bpf_perf_event_output
+ */
+struct bpf_trace_sample_data {
+	struct perf_sample_data sds[3];
+};
+
+static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_trace_sds);
+static DEFINE_PER_CPU(int, bpf_trace_nest_level);
 BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
 	   u64, flags, void *, data, u64, size)
 {
-	struct perf_sample_data *sd = this_cpu_ptr(&bpf_trace_sd);
+	struct bpf_trace_sample_data *sds = this_cpu_ptr(&bpf_trace_sds);
+	int nest_level = this_cpu_inc_return(bpf_trace_nest_level);
 	struct perf_raw_record raw = {
 		.frag = {
 			.size = size,
 			.data = data,
 		},
 	};
+	struct perf_sample_data *sd;
+	int err;
 
-	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
-		return -EINVAL;
+	if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(sds->sds))) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	sd = &sds->sds[nest_level - 1];
+
+	if (unlikely(flags & ~(BPF_F_INDEX_MASK))) {
+		err = -EINVAL;
+		goto out;
+	}
 
 	perf_sample_data_init(sd, 0, 0);
 	sd->raw = &raw;
 
-	return __bpf_perf_event_output(regs, map, flags, sd);
+	err = __bpf_perf_event_output(regs, map, flags, sd);
+
+out:
+	this_cpu_dec(bpf_trace_nest_level);
+	return err;
 }
 
 static const struct bpf_func_proto bpf_perf_event_output_proto = {
@@ -822,16 +846,48 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 /*
  * bpf_raw_tp_regs are separate from bpf_pt_regs used from skb/xdp
  * to avoid potential recursive reuse issue when/if tracepoints are added
- * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack
+ * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack.
+ *
+ * Since raw tracepoints run despite bpf_prog_active, support concurrent usage
+ * in normal, irq, and nmi context.
  */
-static DEFINE_PER_CPU(struct pt_regs, bpf_raw_tp_regs);
+struct bpf_raw_tp_regs {
+	struct pt_regs regs[3];
+};
+static DEFINE_PER_CPU(struct bpf_raw_tp_regs, bpf_raw_tp_regs);
+static DEFINE_PER_CPU(int, bpf_raw_tp_nest_level);
+static struct pt_regs *get_bpf_raw_tp_regs(void)
+{
+	struct bpf_raw_tp_regs *tp_regs = this_cpu_ptr(&bpf_raw_tp_regs);
+	int nest_level = this_cpu_inc_return(bpf_raw_tp_nest_level);
+
+	if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(tp_regs->regs))) {
+		this_cpu_dec(bpf_raw_tp_nest_level);
+		return ERR_PTR(-EBUSY);
+	}
+
+	return &tp_regs->regs[nest_level - 1];
+}
+
+static void put_bpf_raw_tp_regs(void)
+{
+	this_cpu_dec(bpf_raw_tp_nest_level);
+}
+
 BPF_CALL_5(bpf_perf_event_output_raw_tp, struct bpf_raw_tracepoint_args *, args,
 	   struct bpf_map *, map, u64, flags, void *, data, u64, size)
 {
-	struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs);
+	struct pt_regs *regs = get_bpf_raw_tp_regs();
+	int ret;
+
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
 
 	perf_fetch_caller_regs(regs);
-	return ____bpf_perf_event_output(regs, map, flags, data, size);
+	ret = ____bpf_perf_event_output(regs, map, flags, data, size);
+
+	put_bpf_raw_tp_regs();
+	return ret;
 }
 
 static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
@@ -848,12 +904,18 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
 BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args,
 	   struct bpf_map *, map, u64, flags)
 {
-	struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs);
+	struct pt_regs *regs = get_bpf_raw_tp_regs();
+	int ret;
+
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
 
 	perf_fetch_caller_regs(regs);
 	/* similar to bpf_perf_event_output_tp, but pt_regs fetched differently */
-	return bpf_get_stackid((unsigned long) regs, (unsigned long) map,
-			       flags, 0, 0);
+	ret = bpf_get_stackid((unsigned long) regs, (unsigned long) map,
+			      flags, 0, 0);
+	put_bpf_raw_tp_regs();
+	return ret;
 }
 
 static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = {
@@ -868,11 +930,17 @@ static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = {
 BPF_CALL_4(bpf_get_stack_raw_tp, struct bpf_raw_tracepoint_args *, args,
 	   void *, buf, u32, size, u64, flags)
 {
-	struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs);
+	struct pt_regs *regs = get_bpf_raw_tp_regs();
+	int ret;
+
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
 
 	perf_fetch_caller_regs(regs);
-	return bpf_get_stack((unsigned long) regs, (unsigned long) buf,
-			     (unsigned long) size, flags, 0);
+	ret = bpf_get_stack((unsigned long) regs, (unsigned long) buf,
+			    (unsigned long) size, flags, 0);
+	put_bpf_raw_tp_regs();
+	return ret;
 }
 
 static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = {