Add kfunc bpf_xdp_pull_data

drivers/net/ethernet/mellanox/mlx5/core/en_rx.c

@@ -1729,6 +1729,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 	struct mlx5e_wqe_frag_info *head_wi = wi;
 	u16 rx_headroom = rq->buff.headroom;
 	struct mlx5e_frag_page *frag_page;
+	u8 nr_frags_free, old_nr_frags;
 	struct skb_shared_info *sinfo;
 	u32 frag_consumed_bytes;
 	struct bpf_prog *prog;
@@ -1772,17 +1773,27 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 		wi++;
 	}
 
+	old_nr_frags = sinfo->nr_frags;
+
 	prog = rcu_dereference(rq->xdp_prog);
 	if (prog && mlx5e_xdp_handle(rq, prog, mxbuf)) {
 		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
 			struct mlx5e_wqe_frag_info *pwi;
 
+			wi -= old_nr_frags - sinfo->nr_frags;
+
 			for (pwi = head_wi; pwi < wi; pwi++)
 				pwi->frag_page->frags++;
 		}
 		return NULL; /* page/packet was consumed by XDP */
 	}
 
+	nr_frags_free = old_nr_frags - sinfo->nr_frags;
+	if (unlikely(nr_frags_free)) {
+		wi -= nr_frags_free;
+		truesize -= nr_frags_free * frag_info->frag_stride;
+	}
+
 	skb = mlx5e_build_linear_skb(
 		rq, mxbuf->xdp.data_hard_start, rq->buff.frame0_sz,
 		mxbuf->xdp.data - mxbuf->xdp.data_hard_start,
@@ -2004,6 +2015,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 	u32 byte_cnt       = cqe_bcnt;
 	struct skb_shared_info *sinfo;
 	unsigned int truesize = 0;
+	u32 pg_consumed_bytes;
 	struct bpf_prog *prog;
 	struct sk_buff *skb;
 	u32 linear_frame_sz;
@@ -2057,7 +2069,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 
 	while (byte_cnt) {
 		/* Non-linear mode, hence non-XSK, which always uses PAGE_SIZE. */
-		u32 pg_consumed_bytes = min_t(u32, PAGE_SIZE - frag_offset, byte_cnt);
+		pg_consumed_bytes = min_t(u32, PAGE_SIZE - frag_offset, byte_cnt);
 
 		if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state))
 			truesize += pg_consumed_bytes;
@@ -2073,10 +2085,15 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 	}
 
 	if (prog) {
+		u8 nr_frags_free, old_nr_frags = sinfo->nr_frags;
+		u32 len;
+
 		if (mlx5e_xdp_handle(rq, prog, mxbuf)) {
 			if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
 				struct mlx5e_frag_page *pfp;
 
+				frag_page -= old_nr_frags - sinfo->nr_frags;
+
 				for (pfp = head_page; pfp < frag_page; pfp++)
 					pfp->frags++;
 
@@ -2087,9 +2104,22 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 			return NULL; /* page/packet was consumed by XDP */
 		}
 
+		len = mxbuf->xdp.data_end - mxbuf->xdp.data;
+
+		nr_frags_free = old_nr_frags - sinfo->nr_frags;
+		if (unlikely(nr_frags_free)) {
+			frag_page -= nr_frags_free;
+
+			/* the last frag is always freed first */
+			truesize -= ALIGN(pg_consumed_bytes, BIT(rq->mpwqe.log_stride_sz));
+			while (--nr_frags_free)
+				truesize -= nr_frags_free *
+					    ALIGN(PAGE_SIZE, BIT(rq->mpwqe.log_stride_sz));
+		}
+
 		skb = mlx5e_build_linear_skb(
 			rq, mxbuf->xdp.data_hard_start, linear_frame_sz,
-			mxbuf->xdp.data - mxbuf->xdp.data_hard_start, 0,
+			mxbuf->xdp.data - mxbuf->xdp.data_hard_start, len,
 			mxbuf->xdp.data - mxbuf->xdp.data_meta);
 		if (unlikely(!skb)) {
 			mlx5e_page_release_fragmented(rq->page_pool,
@@ -2114,8 +2144,10 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 			do
 				pagep->frags++;
 			while (++pagep < frag_page);
+
+			headlen = min_t(u16, MLX5E_RX_MAX_HEAD - len, sinfo->xdp_frags_size);
+			__pskb_pull_tail(skb, headlen);
 		}
-		__pskb_pull_tail(skb, headlen);
 	} else {
 		dma_addr_t addr;
 

include/net/xdp_sock_drv.h

@@ -160,13 +160,23 @@ static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first)
 	return ret;
 }
 
-static inline void xsk_buff_del_tail(struct xdp_buff *tail)
+static inline void xsk_buff_del_frag(struct xdp_buff *xdp)
 {
-	struct xdp_buff_xsk *xskb = container_of(tail, struct xdp_buff_xsk, xdp);
+	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
 
 	list_del(&xskb->list_node);
 }
 
+static inline struct xdp_buff *xsk_buff_get_head(struct xdp_buff *first)
+{
+	struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp);
+	struct xdp_buff_xsk *frag;
+
+	frag = list_first_entry(&xskb->pool->xskb_list, struct xdp_buff_xsk,
+				list_node);
+	return &frag->xdp;
+}
+
 static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first)
 {
 	struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp);
@@ -389,8 +399,13 @@ static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first)
 	return NULL;
 }
 
-static inline void xsk_buff_del_tail(struct xdp_buff *tail)
+static inline void xsk_buff_del_frag(struct xdp_buff *xdp)
+{
+}
+
+static inline struct xdp_buff *xsk_buff_get_head(struct xdp_buff *first)
 {
+	return NULL;
 }
 
 static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first)

kernel/bpf/verifier.c

@@ -12235,6 +12235,7 @@ enum special_kfunc_type {
 	KF_bpf_dynptr_from_skb,
 	KF_bpf_dynptr_from_xdp,
 	KF_bpf_dynptr_from_skb_meta,
+	KF_bpf_xdp_pull_data,
 	KF_bpf_dynptr_slice,
 	KF_bpf_dynptr_slice_rdwr,
 	KF_bpf_dynptr_clone,
@@ -12285,10 +12286,12 @@ BTF_ID(func, bpf_rbtree_right)
 BTF_ID(func, bpf_dynptr_from_skb)
 BTF_ID(func, bpf_dynptr_from_xdp)
 BTF_ID(func, bpf_dynptr_from_skb_meta)
+BTF_ID(func, bpf_xdp_pull_data)
 #else
 BTF_ID_UNUSED
 BTF_ID_UNUSED
 BTF_ID_UNUSED
+BTF_ID_UNUSED
 #endif
 BTF_ID(func, bpf_dynptr_slice)
 BTF_ID(func, bpf_dynptr_slice_rdwr)
@@ -12358,6 +12361,11 @@ static bool is_kfunc_bpf_preempt_enable(struct bpf_kfunc_call_arg_meta *meta)
 	return meta->func_id == special_kfunc_list[KF_bpf_preempt_enable];
 }
 
+static bool is_kfunc_pkt_changing(struct bpf_kfunc_call_arg_meta *meta)
+{
+	return meta->func_id == special_kfunc_list[KF_bpf_xdp_pull_data];
+}
+
 static enum kfunc_ptr_arg_type
 get_kfunc_ptr_arg_type(struct bpf_verifier_env *env,
 		       struct bpf_kfunc_call_arg_meta *meta,
@@ -14077,6 +14085,9 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		}
 	}
 
+	if (is_kfunc_pkt_changing(&meta))
+		clear_all_pkt_pointers(env);
+
 	nargs = btf_type_vlen(meta.func_proto);
 	args = (const struct btf_param *)(meta.func_proto + 1);
 	for (i = 0; i < nargs; i++) {
@@ -17798,6 +17809,8 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
 			 */
 			if (ret == 0 && is_kfunc_sleepable(&meta))
 				mark_subprog_might_sleep(env, t);
+			if (ret == 0 && is_kfunc_pkt_changing(&meta))
+				mark_subprog_changes_pkt_data(env, t);
 		}
 		return visit_func_call_insn(t, insns, env, insn->src_reg == BPF_PSEUDO_CALL);
 

net/bpf/test_run.c

@@ -1207,8 +1207,8 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 {
 	bool do_live = (kattr->test.flags & BPF_F_TEST_XDP_LIVE_FRAMES);
 	u32 tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	u32 retval = 0, duration, max_data_sz, data_sz;
 	u32 batch_size = kattr->test.batch_size;
-	u32 retval = 0, duration, max_data_sz;
 	u32 size = kattr->test.data_size_in;
 	u32 headroom = XDP_PACKET_HEADROOM;
 	u32 repeat = kattr->test.repeat;
@@ -1246,7 +1246,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 
 	if (ctx) {
 		/* There can't be user provided data before the meta data */
-		if (ctx->data_meta || ctx->data_end != size ||
+		if (ctx->data_meta || ctx->data_end > size ||
 		    ctx->data > ctx->data_end ||
 		    unlikely(xdp_metalen_invalid(ctx->data)) ||
 		    (do_live && (kattr->test.data_out || kattr->test.ctx_out)))
@@ -1256,11 +1256,12 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	}
 
 	max_data_sz = PAGE_SIZE - headroom - tailroom;
-	if (size > max_data_sz) {
+	data_sz = (ctx && ctx->data_end < max_data_sz) ? ctx->data_end : max_data_sz;
+	if (size > data_sz) {
 		/* disallow live data mode for jumbo frames */
 		if (do_live)
 			goto free_ctx;
-		size = max_data_sz;
+		size = data_sz;
 	}
 
 	data = bpf_test_init(kattr, size, max_data_sz, headroom, tailroom);

net/core/filter.c

@@ -4153,34 +4153,44 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset)
 	return 0;
 }
 
-static void bpf_xdp_shrink_data_zc(struct xdp_buff *xdp, int shrink,
+static void bpf_xdp_shrink_data_zc(struct xdp_buff *xdp, int shrink, bool tail,
 				   enum xdp_mem_type mem_type, bool release)
 {
-	struct xdp_buff *zc_frag = xsk_buff_get_tail(xdp);
+	struct xdp_buff *zc_frag = tail ? xsk_buff_get_tail(xdp) :
+					  xsk_buff_get_head(xdp);
 
 	if (release) {
-		xsk_buff_del_tail(zc_frag);
+		xsk_buff_del_frag(zc_frag);
 		__xdp_return(0, mem_type, false, zc_frag);
 	} else {
-		zc_frag->data_end -= shrink;
+		if (tail)
+			zc_frag->data_end -= shrink;
+		else
+			zc_frag->data += shrink;
 	}
 }
 
 static bool bpf_xdp_shrink_data(struct xdp_buff *xdp, skb_frag_t *frag,
-				int shrink)
+				int shrink, bool tail)
 {
 	enum xdp_mem_type mem_type = xdp->rxq->mem.type;
 	bool release = skb_frag_size(frag) == shrink;
 
 	if (mem_type == MEM_TYPE_XSK_BUFF_POOL) {
-		bpf_xdp_shrink_data_zc(xdp, shrink, mem_type, release);
+		bpf_xdp_shrink_data_zc(xdp, shrink, tail, mem_type, release);
 		goto out;
 	}
 
 	if (release)
 		__xdp_return(skb_frag_netmem(frag), mem_type, false, NULL);
 
 out:
+	if (!release) {
+		if (!tail)
+			skb_frag_off_add(frag, shrink);
+		skb_frag_size_sub(frag, shrink);
+	}
+
 	return release;
 }
 
@@ -4198,12 +4208,8 @@ static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset)
 
 		len_free += shrink;
 		offset -= shrink;
-		if (bpf_xdp_shrink_data(xdp, frag, shrink)) {
+		if (bpf_xdp_shrink_data(xdp, frag, shrink, true))
 			n_frags_free++;
-		} else {
-			skb_frag_size_sub(frag, shrink);
-			break;
-		}
 	}
 	sinfo->nr_frags -= n_frags_free;
 	sinfo->xdp_frags_size -= len_free;
@@ -12206,6 +12212,81 @@ __bpf_kfunc int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops,
 	return 0;
 }
 
+/**
+ * bpf_xdp_pull_data() - Pull in non-linear xdp data.
+ * @x: &xdp_md associated with the XDP buffer
+ * @len: length of data to be made directly accessible in the linear part
+ * @flags: future use, must be zero
+ *
+ * Pull in non-linear data in case the XDP buffer associated with @x is
+ * non-linear and not all @len are in the linear data area.
+ *
+ * Direct packet access allows reading and writing linear XDP data through
+ * packet pointers (i.e., &xdp_md->data + offsets). When an eBPF program wants
+ * to directly access data that may be in the non-linear area, call this kfunc
+ * to make sure the data is available in the linear area.
+ *
+ * This kfunc can also be used with bpf_xdp_adjust_head() to decapsulate
+ * headers in the non-linear data area.
+ *
+ * A call to this kfunc is susceptible to change the underlying packet buffer.
+ * Therefore, at load time, all checks on pointers previously done by the
+ * verifier are invalidated and must be performed again, if the kfunc is used
+ * in combination with direct packet access.
+ *
+ * Return:
+ * * %0         - success
+ * * %-EINVAL   - invalid len or flags
+ */
+__bpf_kfunc int bpf_xdp_pull_data(struct xdp_md *x, u32 len, u64 flags)
+{
+	struct xdp_buff *xdp = (struct xdp_buff *)x;
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+	void *data_hard_end = xdp_data_hard_end(xdp);
+	void *data_end = xdp->data + len;
+	int i, delta, n_frags_free = 0, len_free = 0;
+
+	if (flags)
+		return -EINVAL;
+
+	if (unlikely(len > xdp_get_buff_len(xdp)))
+		return -EINVAL;
+
+	if (unlikely(data_end < xdp->data || data_end > data_hard_end))
+		return -EINVAL;
+
+	delta = data_end - xdp->data_end;
+	if (delta <= 0)
+		return 0;
+
+	for (i = 0; i < sinfo->nr_frags && delta; i++) {
+		skb_frag_t *frag = &sinfo->frags[i];
+		u32 shrink = min_t(u32, delta, skb_frag_size(frag));
+
+		memcpy(xdp->data_end + len_free, skb_frag_address(frag), shrink);
+
+		len_free += shrink;
+		delta -= shrink;
+		if (bpf_xdp_shrink_data(xdp, frag, shrink, false))
+			n_frags_free++;
+	}
+
+	if (unlikely(n_frags_free)) {
+		memmove(sinfo->frags, sinfo->frags + n_frags_free,
+			(sinfo->nr_frags - n_frags_free) * sizeof(skb_frag_t));
+
+		sinfo->nr_frags -= n_frags_free;
+
+		if (!sinfo->nr_frags)
+			xdp_buff_clear_frags_flag(xdp);
+	}
+
+	sinfo->xdp_frags_size -= len_free;
+	xdp->data_end = data_end;
+
+	return 0;
+}
+
 __bpf_kfunc_end_defs();
 
 int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
@@ -12233,6 +12314,7 @@ BTF_KFUNCS_END(bpf_kfunc_check_set_skb_meta)
 
 BTF_KFUNCS_START(bpf_kfunc_check_set_xdp)
 BTF_ID_FLAGS(func, bpf_dynptr_from_xdp)
+BTF_ID_FLAGS(func, bpf_xdp_pull_data)
 BTF_KFUNCS_END(bpf_kfunc_check_set_xdp)
 
 BTF_KFUNCS_START(bpf_kfunc_check_set_sock_addr)

tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c

@@ -97,9 +97,7 @@ void test_xdp_context_test_run(void)
 	/* Meta data must be 255 bytes or smaller */
 	test_xdp_context_error(prog_fd, opts, 0, 256, sizeof(data), 0, 0, 0);
 
-	/* Total size of data must match data_end - data_meta */
-	test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32),
-			       sizeof(data) - 1, 0, 0, 0);
+	/* Total size of data must be data_end - data_meta or larger */
 	test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32),
 			       sizeof(data) + 1, 0, 0, 0);