Merge tag 'net-6.17-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from wireless. No known regressions at this point.

  Current release - fix to a fix:

   - eth: Revert "net/mlx5e: Update and set Xon/Xoff upon port speed set"

   - wifi: iwlwifi: pcie: fix byte count table for 7000/8000 devices

   - net: clear sk->sk_ino in sk_set_socket(sk, NULL), fix CRIU

  Previous releases - regressions:

   - bonding: set random address only when slaves already exist

   - rxrpc: fix untrusted unsigned subtract

   - eth:
       - ice: fix Rx page leak on multi-buffer frames
       - mlx5: don't return mlx5_link_info table when speed is unknown

  Previous releases - always broken:

   - tls: make sure to abort the stream if headers are bogus

   - tcp: fix null-deref when using TCP-AO with TCP_REPAIR

   - dpll: fix skipping last entry in clock quality level reporting

   - eth: qed: don't collect too many protection override GRC elements,
     fix memory corruption"

* tag 'net-6.17-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (51 commits)
  octeontx2-pf: Fix use-after-free bugs in otx2_sync_tstamp()
  cnic: Fix use-after-free bugs in cnic_delete_task
  devlink rate: Remove unnecessary 'static' from a couple places
  MAINTAINERS: update sundance entry
  net: liquidio: fix overflow in octeon_init_instr_queue()
  net: clear sk->sk_ino in sk_set_socket(sk, NULL)
  Revert "net/mlx5e: Update and set Xon/Xoff upon port speed set"
  selftests: tls: test skb copy under mem pressure and OOB
  tls: make sure to abort the stream if headers are bogus
  selftest: packetdrill: Add tcp_fastopen_server_reset-after-disconnect.pkt.
  tcp: Clear tcp_sk(sk)->fastopen_rsk in tcp_disconnect().
  octeon_ep: fix VF MAC address lifecycle handling
  selftests: bonding: add vlan over bond testing
  bonding: don't set oif to bond dev when getting NS target destination
  net: rfkill: gpio: Fix crash due to dereferencering uninitialized pointer
  net/mlx5e: Add a miss level for ipsec crypto offload
  net/mlx5e: Harden uplink netdev access against device unbind
  MAINTAINERS: make the DPLL entry cover drivers
  doc/netlink: Fix typos in operation attributes
  igc: don't fail igc_probe() on LED setup error
  ...

Author: torvalds

Documentation/netlink/specs/conntrack.yaml

@@ -575,8 +575,8 @@ operations:
             - nat-dst
             - timeout
             - mark
-            - counter-orig
-            - counter-reply
+            - counters-orig
+            - counters-reply
             - use
             - id
             - nat-dst
@@ -591,7 +591,6 @@ operations:
         request:
           value: 0x101
           attributes:
-            - nfgen-family
             - mark
             - filter
             - status
@@ -608,8 +607,8 @@ operations:
             - nat-dst
             - timeout
             - mark
-            - counter-orig
-            - counter-reply
+            - counters-orig
+            - counters-reply
             - use
             - id
             - nat-dst

Documentation/netlink/specs/mptcp_pm.yaml

@@ -28,13 +28,13 @@ definitions:
           traffic-patterns it can take a long time until the
           MPTCP_EVENT_ESTABLISHED is sent.
           Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, sport,
-          dport, server-side.
+          dport, server-side, [flags].
       -
         name: established
         doc: >-
           A MPTCP connection is established (can start new subflows).
           Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, sport,
-          dport, server-side.
+          dport, server-side, [flags].
       -
         name: closed
         doc: >-

MAINTAINERS

@@ -7430,7 +7430,7 @@ S:	Supported
 F:	Documentation/devicetree/bindings/dpll/dpll-device.yaml
 F:	Documentation/devicetree/bindings/dpll/dpll-pin.yaml
 F:	Documentation/driver-api/dpll.rst
-F:	drivers/dpll/*
+F:	drivers/dpll/
 F:	include/linux/dpll.h
 F:	include/uapi/linux/dpll.h
 
@@ -24259,7 +24259,7 @@ F:	Documentation/devicetree/bindings/input/allwinner,sun4i-a10-lradc-keys.yaml
 F:	drivers/input/keyboard/sun4i-lradc-keys.c
 
 SUNDANCE NETWORK DRIVER
-M:	Denis Kirjanov <[email protected]>
+M:	Denis Kirjanov <[email protected]>
 L:	[email protected]
 S:	Maintained
 F:	drivers/net/ethernet/dlink/sundance.c

drivers/dpll/dpll_netlink.c

@@ -211,8 +211,8 @@ static int
 dpll_msg_add_clock_quality_level(struct sk_buff *msg, struct dpll_device *dpll,
 				 struct netlink_ext_ack *extack)
 {
+	DECLARE_BITMAP(qls, DPLL_CLOCK_QUALITY_LEVEL_MAX + 1) = { 0 };
 	const struct dpll_device_ops *ops = dpll_device_ops(dpll);
-	DECLARE_BITMAP(qls, DPLL_CLOCK_QUALITY_LEVEL_MAX) = { 0 };
 	enum dpll_clock_quality_level ql;
 	int ret;
 
@@ -221,7 +221,7 @@ dpll_msg_add_clock_quality_level(struct sk_buff *msg, struct dpll_device *dpll,
 	ret = ops->clock_quality_level_get(dpll, dpll_priv(dpll), qls, extack);
 	if (ret)
 		return ret;
-	for_each_set_bit(ql, qls, DPLL_CLOCK_QUALITY_LEVEL_MAX)
+	for_each_set_bit(ql, qls, DPLL_CLOCK_QUALITY_LEVEL_MAX + 1)
 		if (nla_put_u32(msg, DPLL_A_CLOCK_QUALITY_LEVEL, ql))
 			return -EMSGSIZE;
 

drivers/net/bonding/bond_main.c

@@ -2132,6 +2132,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 		memcpy(ss.__data, bond_dev->dev_addr, bond_dev->addr_len);
 	} else if (bond->params.fail_over_mac == BOND_FOM_FOLLOW &&
 		   BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP &&
+		   bond_has_slaves(bond) &&
 		   memcmp(slave_dev->dev_addr, bond_dev->dev_addr, bond_dev->addr_len) == 0) {
 		/* Set slave to random address to avoid duplicate mac
 		 * address in later fail over.
@@ -3355,7 +3356,6 @@ static void bond_ns_send_all(struct bonding *bond, struct slave *slave)
 		/* Find out through which dev should the packet go */
 		memset(&fl6, 0, sizeof(struct flowi6));
 		fl6.daddr = targets[i];
-		fl6.flowi6_oif = bond->dev->ifindex;
 
 		dst = ip6_route_output(dev_net(bond->dev), NULL, &fl6);
 		if (dst->error) {

drivers/net/ethernet/broadcom/cnic.c

@@ -4230,8 +4230,7 @@ static void cnic_cm_stop_bnx2x_hw(struct cnic_dev *dev)
 
 	cnic_bnx2x_delete_wait(dev, 0);
 
-	cancel_delayed_work(&cp->delete_task);
-	flush_workqueue(cnic_wq);
+	cancel_delayed_work_sync(&cp->delete_task);
 
 	if (atomic_read(&cp->iscsi_conn) != 0)
 		netdev_warn(dev->netdev, "%d iSCSI connections not destroyed\n",

drivers/net/ethernet/cavium/liquidio/request_manager.c

@@ -126,7 +126,7 @@ int octeon_init_instr_queue(struct octeon_device *oct,
 	oct->io_qmask.iq |= BIT_ULL(iq_no);
 
 	/* Set the 32B/64B mode for each input queue */
-	oct->io_qmask.iq64B |= ((conf->instr_type == 64) << iq_no);
+	oct->io_qmask.iq64B |= ((u64)(conf->instr_type == 64) << iq_no);
 	iq->iqcmd_64B = (conf->instr_type == 64);
 
 	oct->fn_list.setup_iq_regs(oct, iq_no);

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

@@ -2736,7 +2736,7 @@ static int dpaa2_switch_setup_dpbp(struct ethsw_core *ethsw)
 		dev_err(dev, "dpsw_ctrl_if_set_pools() failed\n");
 		goto err_get_attr;
 	}
-	ethsw->bpid = dpbp_attrs.id;
+	ethsw->bpid = dpbp_attrs.bpid;
 
 	return 0;
 

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

@@ -948,9 +948,6 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 		if (!eop_desc)
 			break;
 
-		/* prevent any other reads prior to eop_desc */
-		smp_rmb();
-
 		i40e_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf);
 		/* we have caught up to head, no work left to do */
 		if (tx_head == tx_desc)

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

@@ -894,10 +894,6 @@ ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page,
 				   rx_buf->page_offset, size);
 	sinfo->xdp_frags_size += size;
-	/* remember frag count before XDP prog execution; bpf_xdp_adjust_tail()
-	 * can pop off frags but driver has to handle it on its own
-	 */
-	rx_ring->nr_frags = sinfo->nr_frags;
 
 	if (page_is_pfmemalloc(rx_buf->page))
 		xdp_buff_set_frag_pfmemalloc(xdp);
@@ -968,20 +964,20 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
 /**
  * ice_get_pgcnts - grab page_count() for gathered fragments
  * @rx_ring: Rx descriptor ring to store the page counts on
+ * @ntc: the next to clean element (not included in this frame!)
  *
  * This function is intended to be called right before running XDP
  * program so that the page recycling mechanism will be able to take
  * a correct decision regarding underlying pages; this is done in such
  * way as XDP program can change the refcount of page
  */
-static void ice_get_pgcnts(struct ice_rx_ring *rx_ring)
+static void ice_get_pgcnts(struct ice_rx_ring *rx_ring, unsigned int ntc)
 {
-	u32 nr_frags = rx_ring->nr_frags + 1;
 	u32 idx = rx_ring->first_desc;
 	struct ice_rx_buf *rx_buf;
 	u32 cnt = rx_ring->count;
 
-	for (int i = 0; i < nr_frags; i++) {
+	while (idx != ntc) {
 		rx_buf = &rx_ring->rx_buf[idx];
 		rx_buf->pgcnt = page_count(rx_buf->page);
 
@@ -1154,62 +1150,51 @@ ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf)
 }
 
 /**
- * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all frame frags
+ * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all buffers in frame
  * @rx_ring: Rx ring with all the auxiliary data
  * @xdp: XDP buffer carrying linear + frags part
- * @xdp_xmit: XDP_TX/XDP_REDIRECT verdict storage
- * @ntc: a current next_to_clean value to be stored at rx_ring
+ * @ntc: the next to clean element (not included in this frame!)
  * @verdict: return code from XDP program execution
  *
- * Walk through gathered fragments and satisfy internal page
- * recycle mechanism; we take here an action related to verdict
- * returned by XDP program;
+ * Called after XDP program is completed, or on error with verdict set to
+ * ICE_XDP_CONSUMED.
+ *
+ * Walk through buffers from first_desc to the end of the frame, releasing
+ * buffers and satisfying internal page recycle mechanism. The action depends
+ * on verdict from XDP program.
  */
 static void ice_put_rx_mbuf(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
-			    u32 *xdp_xmit, u32 ntc, u32 verdict)
+			    u32 ntc, u32 verdict)
 {
-	u32 nr_frags = rx_ring->nr_frags + 1;
 	u32 idx = rx_ring->first_desc;
 	u32 cnt = rx_ring->count;
-	u32 post_xdp_frags = 1;
 	struct ice_rx_buf *buf;
-	int i;
+	u32 xdp_frags = 0;
+	int i = 0;
 
 	if (unlikely(xdp_buff_has_frags(xdp)))
-		post_xdp_frags += xdp_get_shared_info_from_buff(xdp)->nr_frags;
+		xdp_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags;
 
-	for (i = 0; i < post_xdp_frags; i++) {
+	while (idx != ntc) {
 		buf = &rx_ring->rx_buf[idx];
+		if (++idx == cnt)
+			idx = 0;
 
-		if (verdict & (ICE_XDP_TX | ICE_XDP_REDIR)) {
+		/* An XDP program could release fragments from the end of the
+		 * buffer. For these, we need to keep the pagecnt_bias as-is.
+		 * To do this, only adjust pagecnt_bias for fragments up to
+		 * the total remaining after the XDP program has run.
+		 */
+		if (verdict != ICE_XDP_CONSUMED)
 			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
-			*xdp_xmit |= verdict;
-		} else if (verdict & ICE_XDP_CONSUMED) {
+		else if (i++ <= xdp_frags)
 			buf->pagecnt_bias++;
-		} else if (verdict == ICE_XDP_PASS) {
-			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
-		}
 
 		ice_put_rx_buf(rx_ring, buf);
-
-		if (++idx == cnt)
-			idx = 0;
-	}
-	/* handle buffers that represented frags released by XDP prog;
-	 * for these we keep pagecnt_bias as-is; refcount from struct page
-	 * has been decremented within XDP prog and we do not have to increase
-	 * the biased refcnt
-	 */
-	for (; i < nr_frags; i++) {
-		buf = &rx_ring->rx_buf[idx];
-		ice_put_rx_buf(rx_ring, buf);
-		if (++idx == cnt)
-			idx = 0;
 	}
 
 	xdp->data = NULL;
 	rx_ring->first_desc = ntc;
-	rx_ring->nr_frags = 0;
 }
 
 /**
@@ -1317,6 +1302,10 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 		/* retrieve a buffer from the ring */
 		rx_buf = ice_get_rx_buf(rx_ring, size, ntc);
 
+		/* Increment ntc before calls to ice_put_rx_mbuf() */
+		if (++ntc == cnt)
+			ntc = 0;
+
 		if (!xdp->data) {
 			void *hard_start;
 
@@ -1325,24 +1314,23 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 			xdp_prepare_buff(xdp, hard_start, offset, size, !!offset);
 			xdp_buff_clear_frags_flag(xdp);
 		} else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) {
-			ice_put_rx_mbuf(rx_ring, xdp, NULL, ntc, ICE_XDP_CONSUMED);
+			ice_put_rx_mbuf(rx_ring, xdp, ntc, ICE_XDP_CONSUMED);
 			break;
 		}
-		if (++ntc == cnt)
-			ntc = 0;
 
 		/* skip if it is NOP desc */
 		if (ice_is_non_eop(rx_ring, rx_desc))
 			continue;
 
-		ice_get_pgcnts(rx_ring);
+		ice_get_pgcnts(rx_ring, ntc);
 		xdp_verdict = ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_desc);
 		if (xdp_verdict == ICE_XDP_PASS)
 			goto construct_skb;
 		total_rx_bytes += xdp_get_buff_len(xdp);
 		total_rx_pkts++;
 
-		ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict);
+		ice_put_rx_mbuf(rx_ring, xdp, ntc, xdp_verdict);
+		xdp_xmit |= xdp_verdict & (ICE_XDP_TX | ICE_XDP_REDIR);
 
 		continue;
 construct_skb:
@@ -1355,7 +1343,7 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 			rx_ring->ring_stats->rx_stats.alloc_buf_failed++;
 			xdp_verdict = ICE_XDP_CONSUMED;
 		}
-		ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict);
+		ice_put_rx_mbuf(rx_ring, xdp, ntc, xdp_verdict);
 
 		if (!skb)
 			break;