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

Alexei Starovoitov says:

====================
pull-request: bpf 2019-02-16

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

The main changes are:

1) fix lockdep false positive in bpf_get_stackid(), from Alexei.

2) several AF_XDP fixes, from Bjorn, Magnus, Davidlohr.

3) fix narrow load from struct bpf_sock, from Martin.

4) mips JIT fixes, from Paul.

5) gso handling fix in bpf helpers, from Willem.
====================

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

7 files changed, 46 insertions, 30 deletions

diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c
index b16710a8a9e7..76e9bf88d3b9 100644
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@@ -79,8 +79,6 @@ enum reg_val_type {
 	REG_64BIT_32BIT,
 	/* 32-bit compatible, need truncation for 64-bit ops. */
 	REG_32BIT,
-	/* 32-bit zero extended. */
-	REG_32BIT_ZERO_EX,
 	/* 32-bit no sign/zero extension needed. */
 	REG_32BIT_POS
 };
@@ -343,12 +341,15 @@ static int build_int_epilogue(struct jit_ctx *ctx, int dest_reg)
 	const struct bpf_prog *prog = ctx->skf;
 	int stack_adjust = ctx->stack_size;
 	int store_offset = stack_adjust - 8;
+	enum reg_val_type td;
 	int r0 = MIPS_R_V0;
 
-	if (dest_reg == MIPS_R_RA &&
-	    get_reg_val_type(ctx, prog->len, BPF_REG_0) == REG_32BIT_ZERO_EX)
+	if (dest_reg == MIPS_R_RA) {
 		/* Don't let zero extended value escape. */
-		emit_instr(ctx, sll, r0, r0, 0);
+		td = get_reg_val_type(ctx, prog->len, BPF_REG_0);
+		if (td == REG_64BIT)
+			emit_instr(ctx, sll, r0, r0, 0);
+	}
 
 	if (ctx->flags & EBPF_SAVE_RA) {
 		emit_instr(ctx, ld, MIPS_R_RA, store_offset, MIPS_R_SP);
@@ -692,7 +693,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		if (dst < 0)
 			return dst;
 		td = get_reg_val_type(ctx, this_idx, insn->dst_reg);
-		if (td == REG_64BIT || td == REG_32BIT_ZERO_EX) {
+		if (td == REG_64BIT) {
 			/* sign extend */
 			emit_instr(ctx, sll, dst, dst, 0);
 		}
@@ -707,7 +708,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		if (dst < 0)
 			return dst;
 		td = get_reg_val_type(ctx, this_idx, insn->dst_reg);
-		if (td == REG_64BIT || td == REG_32BIT_ZERO_EX) {
+		if (td == REG_64BIT) {
 			/* sign extend */
 			emit_instr(ctx, sll, dst, dst, 0);
 		}
@@ -721,7 +722,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		if (dst < 0)
 			return dst;
 		td = get_reg_val_type(ctx, this_idx, insn->dst_reg);
-		if (td == REG_64BIT || td == REG_32BIT_ZERO_EX)
+		if (td == REG_64BIT)
 			/* sign extend */
 			emit_instr(ctx, sll, dst, dst, 0);
 		if (insn->imm == 1) {
@@ -860,13 +861,13 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		if (src < 0 || dst < 0)
 			return -EINVAL;
 		td = get_reg_val_type(ctx, this_idx, insn->dst_reg);
-		if (td == REG_64BIT || td == REG_32BIT_ZERO_EX) {
+		if (td == REG_64BIT) {
 			/* sign extend */
 			emit_instr(ctx, sll, dst, dst, 0);
 		}
 		did_move = false;
 		ts = get_reg_val_type(ctx, this_idx, insn->src_reg);
-		if (ts == REG_64BIT || ts == REG_32BIT_ZERO_EX) {
+		if (ts == REG_64BIT) {
 			int tmp_reg = MIPS_R_AT;
 
 			if (bpf_op == BPF_MOV) {
@@ -1254,8 +1255,7 @@ jeq_common:
 		if (insn->imm == 64 && td == REG_32BIT)
 			emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32);
 
-		if (insn->imm != 64 &&
-		    (td == REG_64BIT || td == REG_32BIT_ZERO_EX)) {
+		if (insn->imm != 64 && td == REG_64BIT) {
 			/* sign extend */
 			emit_instr(ctx, sll, dst, dst, 0);
 		}
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 4c1c82a5678c..bdb9563c64a0 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4212,6 +4212,12 @@ static inline bool skb_is_gso_sctp(const struct sk_buff *skb)
 	return skb_shinfo(skb)->gso_type & SKB_GSO_SCTP;
 }
 
+static inline bool skb_is_gso_tcp(const struct sk_buff *skb)
+{
+	return skb_is_gso(skb) &&
+	       skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6);
+}
+
 static inline void skb_gso_reset(struct sk_buff *skb)
 {
 	skb_shinfo(skb)->gso_size = 0;
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index d43b14535827..950ab2f28922 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -44,7 +44,7 @@ static void do_up_read(struct irq_work *entry)
 	struct stack_map_irq_work *work;
 
 	work = container_of(entry, struct stack_map_irq_work, irq_work);
-	up_read(work->sem);
+	up_read_non_owner(work->sem);
 	work->sem = NULL;
 }
 
@@ -338,6 +338,12 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 	} else {
 		work->sem = &current->mm->mmap_sem;
 		irq_work_queue(&work->irq_work);
+		/*
+		 * The irq_work will release the mmap_sem with
+		 * up_read_non_owner(). The rwsem_release() is called
+		 * here to release the lock from lockdep's perspective.
+		 */
+		rwsem_release(&current->mm->mmap_sem.dep_map, 1, _RET_IP_);
 	}
 }
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 56674a7c3778..8f295b790297 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1617,12 +1617,13 @@ static int check_flow_keys_access(struct bpf_verifier_env *env, int off,
 	return 0;
 }
 
-static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off,
-			     int size, enum bpf_access_type t)
+static int check_sock_access(struct bpf_verifier_env *env, int insn_idx,
+			     u32 regno, int off, int size,
+			     enum bpf_access_type t)
 {
 	struct bpf_reg_state *regs = cur_regs(env);
 	struct bpf_reg_state *reg = &regs[regno];
-	struct bpf_insn_access_aux info;
+	struct bpf_insn_access_aux info = {};
 
 	if (reg->smin_value < 0) {
 		verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
@@ -1636,6 +1637,8 @@ static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off,
 		return -EACCES;
 	}
 
+	env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
+
 	return 0;
 }
 
@@ -2032,7 +2035,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 			verbose(env, "cannot write into socket\n");
 			return -EACCES;
 		}
-		err = check_sock_access(env, regno, off, size, t);
+		err = check_sock_access(env, insn_idx, regno, off, size, t);
 		if (!err && value_regno >= 0)
 			mark_reg_unknown(env, regs, value_regno);
 	} else {
diff --git a/net/core/filter.c b/net/core/filter.c
index 7a54dc11ac2d..f7d0004fc160 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2789,8 +2789,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb)
 	u32 off = skb_mac_header_len(skb);
 	int ret;
 
-	/* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */
-	if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb)))
+	if (!skb_is_gso_tcp(skb))
 		return -ENOTSUPP;
 
 	ret = skb_cow(skb, len_diff);
@@ -2831,8 +2830,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb)
 	u32 off = skb_mac_header_len(skb);
 	int ret;
 
-	/* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */
-	if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb)))
+	if (!skb_is_gso_tcp(skb))
 		return -ENOTSUPP;
 
 	ret = skb_unclone(skb, GFP_ATOMIC);
@@ -2957,8 +2955,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff)
 	u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb);
 	int ret;
 
-	/* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */
-	if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb)))
+	if (!skb_is_gso_tcp(skb))
 		return -ENOTSUPP;
 
 	ret = skb_cow(skb, len_diff);
@@ -2987,8 +2984,7 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff)
 	u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb);
 	int ret;
 
-	/* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */
-	if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb)))
+	if (!skb_is_gso_tcp(skb))
 		return -ENOTSUPP;
 
 	ret = skb_unclone(skb, GFP_ATOMIC);
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index d4de871e7d4d..37e1fe180769 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -125,9 +125,10 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 	return 0;
 
 err_unreg_umem:
-	xdp_clear_umem_at_qid(dev, queue_id);
 	if (!force_zc)
 		err = 0; /* fallback to copy mode */
+	if (err)
+		xdp_clear_umem_at_qid(dev, queue_id);
 out_rtnl_unlock:
 	rtnl_unlock();
 	return err;
@@ -259,10 +260,10 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem)
 	if (!umem->pgs)
 		return -ENOMEM;
 
-	down_write(&current->mm->mmap_sem);
-	npgs = get_user_pages(umem->address, umem->npgs,
-			      gup_flags, &umem->pgs[0], NULL);
-	up_write(&current->mm->mmap_sem);
+	down_read(&current->mm->mmap_sem);
+	npgs = get_user_pages_longterm(umem->address, umem->npgs,
+				       gup_flags, &umem->pgs[0], NULL);
+	up_read(&current->mm->mmap_sem);
 
 	if (npgs != umem->npgs) {
 		if (npgs >= 0) {
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index a03268454a27..45f3b528dc09 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -669,6 +669,8 @@ static int xsk_mmap(struct file *file, struct socket *sock,
 		if (!umem)
 			return -EINVAL;
 
+		/* Matches the smp_wmb() in XDP_UMEM_REG */
+		smp_rmb();
 		if (offset == XDP_UMEM_PGOFF_FILL_RING)
 			q = READ_ONCE(umem->fq);
 		else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING)
@@ -678,6 +680,8 @@ static int xsk_mmap(struct file *file, struct socket *sock,
 	if (!q)
 		return -EINVAL;
 
+	/* Matches the smp_wmb() in xsk_init_queue */
+	smp_rmb();
 	qpg = virt_to_head_page(q->ring);
 	if (size > (PAGE_SIZE << compound_order(qpg)))
 		return -EINVAL;