Clean up and document RCU-based object protection for XDP_REDIRECT

.travis.yml

@@ -0,0 +1,35 @@
+sudo: required
+language: bash
+dist: focal
+services:
+    - docker
+git:
+    depth: 3
+
+env:
+    global:
+        - PROJECT_NAME='libbpf'
+        - AUTHOR_EMAIL="$(git log -1 --pretty=\"%aE\")"
+        - REPO_ROOT="$TRAVIS_BUILD_DIR"
+        - CI_ROOT="$REPO_ROOT/travis-ci"
+        - VMTEST_ROOT="$CI_ROOT/vmtest"
+
+addons:
+    apt:
+        packages:
+            - qemu-kvm
+            - zstd
+            - binutils-dev
+            - elfutils
+            - libcap-dev
+            - libelf-dev
+            - libdw-dev
+            - python3-docutils
+
+jobs:
+    include:
+        - stage: Builds & Tests
+          name: Kernel LATEST + selftests
+          language: bash
+          env: KERNEL=LATEST
+          script:  $CI_ROOT/vmtest/run_vmtest.sh || travis_terminate 1

README

@@ -1,18 +0,0 @@
-Linux kernel
-============
-
-There are several guides for kernel developers and users. These guides can
-be rendered in a number of formats, like HTML and PDF. Please read
-Documentation/admin-guide/README.rst first.
-
-In order to build the documentation, use ``make htmldocs`` or
-``make pdfdocs``.  The formatted documentation can also be read online at:
-
-    https://www.kernel.org/doc/html/latest/
-
-There are various text files in the Documentation/ subdirectory,
-several of them using the Restructured Text markup notation.
-
-Please read the Documentation/process/changes.rst file, as it contains the
-requirements for building and running the kernel, and information about
-the problems which may result by upgrading your kernel.

drivers/net/ethernet/amazon/ena/ena_netdev.c

@@ -385,7 +385,6 @@ static int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp)
 	u64 *xdp_stat;
 	int qid;
 
-	rcu_read_lock();
 	xdp_prog = READ_ONCE(rx_ring->xdp_bpf_prog);
 
 	if (!xdp_prog)
@@ -443,8 +442,6 @@ static int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp)
 
 	ena_increase_stat(xdp_stat, 1, &rx_ring->syncp);
 out:
-	rcu_read_unlock();
-
 	return verdict;
 }
 

drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c

@@ -138,9 +138,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 	xdp_prepare_buff(&xdp, *data_ptr - offset, offset, *len, false);
 	orig_data = xdp.data;
 
-	rcu_read_lock();
 	act = bpf_prog_run_xdp(xdp_prog, &xdp);
-	rcu_read_unlock();
 
 	tx_avail = bnxt_tx_avail(bp, txr);
 	/* If the tx ring is not full, we must not update the rx producer yet

drivers/net/ethernet/cavium/thunder/nicvf_main.c

@@ -555,9 +555,7 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog,
 	xdp_prepare_buff(&xdp, hard_start, data - hard_start, len, false);
 	orig_data = xdp.data;
 
-	rcu_read_lock();
 	action = bpf_prog_run_xdp(prog, &xdp);
-	rcu_read_unlock();
 
 	len = xdp.data_end - xdp.data;
 	/* Check if XDP program has changed headers */

drivers/net/ethernet/freescale/dpaa/dpaa_eth.c

@@ -2558,13 +2558,9 @@ static u32 dpaa_run_xdp(struct dpaa_priv *priv, struct qm_fd *fd, void *vaddr,
 	u32 xdp_act;
 	int err;
 
-	rcu_read_lock();
-
 	xdp_prog = READ_ONCE(priv->xdp_prog);
-	if (!xdp_prog) {
-		rcu_read_unlock();
+	if (!xdp_prog)
 		return XDP_PASS;
-	}
 
 	xdp_init_buff(&xdp, DPAA_BP_RAW_SIZE - DPAA_TX_PRIV_DATA_SIZE,
 		      &dpaa_fq->xdp_rxq);
@@ -2638,8 +2634,6 @@ static u32 dpaa_run_xdp(struct dpaa_priv *priv, struct qm_fd *fd, void *vaddr,
 		break;
 	}
 
-	rcu_read_unlock();
-
 	return xdp_act;
 }
 

drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c

@@ -352,8 +352,6 @@ static u32 dpaa2_eth_run_xdp(struct dpaa2_eth_priv *priv,
 	u32 xdp_act = XDP_PASS;
 	int err, offset;
 
-	rcu_read_lock();
-
 	xdp_prog = READ_ONCE(ch->xdp.prog);
 	if (!xdp_prog)
 		goto out;
@@ -414,7 +412,6 @@ static u32 dpaa2_eth_run_xdp(struct dpaa2_eth_priv *priv,
 
 	ch->xdp.res |= xdp_act;
 out:
-	rcu_read_unlock();
 	return xdp_act;
 }
 

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -2298,7 +2298,6 @@ static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 	struct bpf_prog *xdp_prog;
 	u32 act;
 
-	rcu_read_lock();
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 
 	if (!xdp_prog)
@@ -2329,7 +2328,6 @@ static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 		break;
 	}
 xdp_out:
-	rcu_read_unlock();
 	return result;
 }
 

drivers/net/ethernet/intel/i40e/i40e_xsk.c

@@ -153,7 +153,6 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 	struct bpf_prog *xdp_prog;
 	u32 act;
 
-	rcu_read_lock();
 	/* NB! xdp_prog will always be !NULL, due to the fact that
 	 * this path is enabled by setting an XDP program.
 	 */
@@ -162,9 +161,7 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 
 	if (likely(act == XDP_REDIRECT)) {
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
-		rcu_read_unlock();
-		return result;
+		return !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
 	}
 
 	switch (act) {
@@ -184,7 +181,6 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 		result = I40E_XDP_CONSUMED;
 		break;
 	}
-	rcu_read_unlock();
 	return result;
 }
 

drivers/net/ethernet/intel/ice/ice_txrx.c

@@ -1129,15 +1129,11 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		xdp.frame_sz = ice_rx_frame_truesize(rx_ring, size);
 #endif
 
-		rcu_read_lock();
 		xdp_prog = READ_ONCE(rx_ring->xdp_prog);
-		if (!xdp_prog) {
-			rcu_read_unlock();
+		if (!xdp_prog)
 			goto construct_skb;
-		}
 
 		xdp_res = ice_run_xdp(rx_ring, &xdp, xdp_prog);
-		rcu_read_unlock();
 		if (!xdp_res)
 			goto construct_skb;
 		if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) {

drivers/net/ethernet/intel/ice/ice_xsk.c

@@ -463,7 +463,6 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp)
 	struct ice_ring *xdp_ring;
 	u32 act;
 
-	rcu_read_lock();
 	/* ZC patch is enabled only when XDP program is set,
 	 * so here it can not be NULL
 	 */
@@ -473,9 +472,7 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp)
 
 	if (likely(act == XDP_REDIRECT)) {
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		result = !err ? ICE_XDP_REDIR : ICE_XDP_CONSUMED;
-		rcu_read_unlock();
-		return result;
+		return !err ? ICE_XDP_REDIR : ICE_XDP_CONSUMED;
 	}
 
 	switch (act) {
@@ -496,7 +493,6 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp)
 		break;
 	}
 
-	rcu_read_unlock();
 	return result;
 }
 

drivers/net/ethernet/intel/igb/igb_main.c

@@ -8387,7 +8387,6 @@ static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter,
 	struct bpf_prog *xdp_prog;
 	u32 act;
 
-	rcu_read_lock();
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 
 	if (!xdp_prog)
@@ -8420,7 +8419,6 @@ static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter,
 		break;
 	}
 xdp_out:
-	rcu_read_unlock();
 	return ERR_PTR(-result);
 }
 

drivers/net/ethernet/intel/igc/igc_main.c

@@ -2175,18 +2175,15 @@ static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter,
 	struct bpf_prog *prog;
 	int res;
 
-	rcu_read_lock();
-
 	prog = READ_ONCE(adapter->xdp_prog);
 	if (!prog) {
 		res = IGC_XDP_PASS;
-		goto unlock;
+		goto out;
 	}
 
 	res = __igc_xdp_run_prog(adapter, prog, xdp);
 
-unlock:
-	rcu_read_unlock();
+out:
 	return ERR_PTR(-res);
 }
 

drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -2199,7 +2199,6 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
 	struct xdp_frame *xdpf;
 	u32 act;
 
-	rcu_read_lock();
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 
 	if (!xdp_prog)
@@ -2237,7 +2236,6 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
 		break;
 	}
 xdp_out:
-	rcu_read_unlock();
 	return ERR_PTR(-result);
 }
 

drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c

@@ -100,15 +100,12 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
 	struct xdp_frame *xdpf;
 	u32 act;
 
-	rcu_read_lock();
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
 
 	if (likely(act == XDP_REDIRECT)) {
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		result = !err ? IXGBE_XDP_REDIR : IXGBE_XDP_CONSUMED;
-		rcu_read_unlock();
-		return result;
+		return !err ? IXGBE_XDP_REDIR : IXGBE_XDP_CONSUMED;
 	}
 
 	switch (act) {
@@ -132,7 +129,6 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
 		result = IXGBE_XDP_CONSUMED;
 		break;
 	}
-	rcu_read_unlock();
 	return result;
 }
 

drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c

@@ -1054,7 +1054,6 @@ static struct sk_buff *ixgbevf_run_xdp(struct ixgbevf_adapter *adapter,
 	struct bpf_prog *xdp_prog;
 	u32 act;
 
-	rcu_read_lock();
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 
 	if (!xdp_prog)
@@ -1079,7 +1078,6 @@ static struct sk_buff *ixgbevf_run_xdp(struct ixgbevf_adapter *adapter,
 		break;
 	}
 xdp_out:
-	rcu_read_unlock();
 	return ERR_PTR(-result);
 }
 

drivers/net/ethernet/marvell/mvneta.c

@@ -2370,7 +2370,6 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 	/* Get number of received packets */
 	rx_todo = mvneta_rxq_busy_desc_num_get(pp, rxq);
 
-	rcu_read_lock();
 	xdp_prog = READ_ONCE(pp->xdp_prog);
 
 	/* Fairness NAPI loop */
@@ -2448,7 +2447,6 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 		xdp_buf.data_hard_start = NULL;
 		sinfo.nr_frags = 0;
 	}
-	rcu_read_unlock();
 
 	if (xdp_buf.data_hard_start)
 		mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1);

drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c

@@ -3852,8 +3852,6 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 	int rx_done = 0;
 	u32 xdp_ret = 0;
 
-	rcu_read_lock();
-
 	xdp_prog = READ_ONCE(port->xdp_prog);
 
 	/* Get number of received packets and clamp the to-do */
@@ -3988,8 +3986,6 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 		mvpp2_bm_pool_put(port, pool, dma_addr, phys_addr);
 	}
 
-	rcu_read_unlock();
-
 	if (xdp_ret & MVPP2_XDP_REDIR)
 		xdp_do_flush_map();
 

drivers/net/ethernet/mellanox/mlx4/en_rx.c

@@ -679,9 +679,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 
 	ring = priv->rx_ring[cq_ring];
 
-	/* Protect accesses to: ring->xdp_prog, priv->mac_hash list */
-	rcu_read_lock();
-	xdp_prog = rcu_dereference(ring->xdp_prog);
+	xdp_prog = rcu_dereference_bh(ring->xdp_prog);
 	xdp_init_buff(&xdp, priv->frag_info[0].frag_stride, &ring->xdp_rxq);
 	doorbell_pending = false;
 
@@ -744,7 +742,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 				/* Drop the packet, since HW loopback-ed it */
 				mac_hash = ethh->h_source[MLX4_EN_MAC_HASH_IDX];
 				bucket = &priv->mac_hash[mac_hash];
-				hlist_for_each_entry_rcu(entry, bucket, hlist) {
+				hlist_for_each_entry_rcu_bh(entry, bucket, hlist) {
 					if (ether_addr_equal_64bits(entry->mac,
 								    ethh->h_source))
 						goto next;
@@ -899,8 +897,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			break;
 	}
 
-	rcu_read_unlock();
-
 	if (likely(polled)) {
 		if (doorbell_pending) {
 			priv->tx_cq[TX_XDP][cq_ring]->xdp_busy = true;

drivers/net/ethernet/netronome/nfp/nfp_net_common.c

@@ -1819,7 +1819,6 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 	struct xdp_buff xdp;
 	int idx;
 
-	rcu_read_lock();
 	xdp_prog = READ_ONCE(dp->xdp_prog);
 	true_bufsz = xdp_prog ? PAGE_SIZE : dp->fl_bufsz;
 	xdp_init_buff(&xdp, PAGE_SIZE - NFP_NET_RX_BUF_HEADROOM,
@@ -2036,7 +2035,6 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 			if (!nfp_net_xdp_complete(tx_ring))
 				pkts_polled = budget;
 	}
-	rcu_read_unlock();
 
 	return pkts_polled;
 }