Merge branch '10GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue

Jeff Kirsher says:

====================
Intel Wired LAN Driver Updates 2018-06-04

This series contains a smorgasbord of updates to documentation, e1000e,
igb, ixgbe, ixgbevf and i40e.

Benjamin Poirier fixes a potential kernel crash due to NULL pointer
dereference in e1000e.

Jeff updates the kernel documentation for e100 and e1000 to correct
default values and URLs which were incorrect in the documentation.  Also
took the time to update these to the new reStructured text format for
kernel documentation.

Joanna Yurdal fixes a missing PTP transmit timestamp by ensuring that
TSICR gets cleared when ICR is cleared.

Sergey updates igb to reset all the transmit queues at one time so that
we only have to wait once for all the queues to be reset.

Alex fixes ixgbevf so that malicious driver detection (MDD) can co-exist
with XDP.

Emil and Tony extend the RTNL lock to ensure we get the most up-to-date
values for the bits and avoid a possible race condition when going down.

YueHaibing from Huawei introduces a helper function in ixgbe for
operation reads to simplify the code a bit more.

Daniel Borkmann adds support for XDP meta data when using build SKB
for i40e.

Shannon Nelson provides twp fixes for the IPSec code in ixgbe, first is
to make sure we do not try to offload the decryption of any incoming
packet that is destined for the management engine.  The other fix is to
resolve a cast problem introduced by a sparse cleanup patch.
====================

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

8 files changed, 195 insertions, 70 deletions

diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index d3fef7fefea8..acf1e8b52b8e 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -3527,15 +3527,12 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
 		}
 		break;
 	case e1000_pch_spt:
-		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
-			/* Stable 24MHz frequency */
-			incperiod = INCPERIOD_24MHZ;
-			incvalue = INCVALUE_24MHZ;
-			shift = INCVALUE_SHIFT_24MHZ;
-			adapter->cc.shift = shift;
-			break;
-		}
-		return -EINVAL;
+		/* Stable 24MHz frequency */
+		incperiod = INCPERIOD_24MHZ;
+		incvalue = INCVALUE_24MHZ;
+		shift = INCVALUE_SHIFT_24MHZ;
+		adapter->cc.shift = shift;
+		break;
 	case e1000_pch_cnp:
 		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
 			/* Stable 24MHz frequency */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 9b698c5acd05..105a26f447c0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2032,6 +2032,21 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
 #if L1_CACHE_BYTES < 128
 	prefetch(xdp->data + L1_CACHE_BYTES);
 #endif
+	/* Note, we get here by enabling legacy-rx via:
+	 *
+	 *    ethtool --set-priv-flags <dev> legacy-rx on
+	 *
+	 * In this mode, we currently get 0 extra XDP headroom as
+	 * opposed to having legacy-rx off, where we process XDP
+	 * packets going to stack via i40e_build_skb(). The latter
+	 * provides us currently with 192 bytes of headroom.
+	 *
+	 * For i40e_construct_skb() mode it means that the
+	 * xdp->data_meta will always point to xdp->data, since
+	 * the helper cannot expand the head. Should this ever
+	 * change in future for legacy-rx mode on, then lets also
+	 * add xdp->data_meta handling here.
+	 */
 
 	/* allocate a skb to store the frags */
 	skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
@@ -2083,19 +2098,25 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
 				      struct i40e_rx_buffer *rx_buffer,
 				      struct xdp_buff *xdp)
 {
-	unsigned int size = xdp->data_end - xdp->data;
+	unsigned int metasize = xdp->data - xdp->data_meta;
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
 #else
 	unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
-				SKB_DATA_ALIGN(I40E_SKB_PAD + size);
+				SKB_DATA_ALIGN(I40E_SKB_PAD +
+					       (xdp->data_end -
+						xdp->data_hard_start));
 #endif
 	struct sk_buff *skb;
 
-	/* prefetch first cache line of first page */
-	prefetch(xdp->data);
+	/* Prefetch first cache line of first page. If xdp->data_meta
+	 * is unused, this points exactly as xdp->data, otherwise we
+	 * likely have a consumer accessing first few bytes of meta
+	 * data, and then actual data.
+	 */
+	prefetch(xdp->data_meta);
 #if L1_CACHE_BYTES < 128
-	prefetch(xdp->data + L1_CACHE_BYTES);
+	prefetch(xdp->data_meta + L1_CACHE_BYTES);
 #endif
 	/* build an skb around the page buffer */
 	skb = build_skb(xdp->data_hard_start, truesize);
@@ -2103,8 +2124,10 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
 		return NULL;
 
 	/* update pointers within the skb to store the data */
-	skb_reserve(skb, I40E_SKB_PAD);
-	__skb_put(skb, size);
+	skb_reserve(skb, I40E_SKB_PAD + (xdp->data - xdp->data_hard_start));
+	__skb_put(skb, xdp->data_end - xdp->data);
+	if (metasize)
+		skb_metadata_set(skb, metasize);
 
 	/* buffer is used by skb, update page_offset */
 #if (PAGE_SIZE < 8192)
@@ -2341,7 +2364,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		if (!skb) {
 			xdp.data = page_address(rx_buffer->page) +
 				   rx_buffer->page_offset;
-			xdp_set_data_meta_invalid(&xdp);
+			xdp.data_meta = xdp.data;
 			xdp.data_hard_start = xdp.data -
 					      i40e_rx_offset(rx_ring);
 			xdp.data_end = xdp.data + size;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 78574c06635b..c33821d2afb3 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2058,6 +2058,7 @@ int igb_up(struct igb_adapter *adapter)
 		igb_assign_vector(adapter->q_vector[0], 0);
 
 	/* Clear any pending interrupts. */
+	rd32(E1000_TSICR);
 	rd32(E1000_ICR);
 	igb_irq_enable(adapter);
 
@@ -3865,6 +3866,7 @@ static int __igb_open(struct net_device *netdev, bool resuming)
 		napi_enable(&(adapter->q_vector[i]->napi));
 
 	/* Clear any pending interrupts. */
+	rd32(E1000_TSICR);
 	rd32(E1000_ICR);
 
 	igb_irq_enable(adapter);
@@ -4053,11 +4055,6 @@ void igb_configure_tx_ring(struct igb_adapter *adapter,
 	u64 tdba = ring->dma;
 	int reg_idx = ring->reg_idx;
 
-	/* disable the queue */
-	wr32(E1000_TXDCTL(reg_idx), 0);
-	wrfl();
-	mdelay(10);
-
 	wr32(E1000_TDLEN(reg_idx),
 	     ring->count * sizeof(union e1000_adv_tx_desc));
 	wr32(E1000_TDBAL(reg_idx),
@@ -4088,8 +4085,16 @@ void igb_configure_tx_ring(struct igb_adapter *adapter,
  **/
 static void igb_configure_tx(struct igb_adapter *adapter)
 {
+	struct e1000_hw *hw = &adapter->hw;
 	int i;
 
+	/* disable the queues */
+	for (i = 0; i < adapter->num_tx_queues; i++)
+		wr32(E1000_TXDCTL(adapter->tx_ring[i]->reg_idx), 0);
+
+	wrfl();
+	usleep_range(10000, 20000);
+
 	for (i = 0; i < adapter->num_tx_queues; i++)
 		igb_configure_tx_ring(adapter, adapter->tx_ring[i]);
 }
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c
index 55fe8114fe99..50dfb02fa34c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c
@@ -10,15 +10,9 @@ static struct dentry *ixgbe_dbg_root;
 
 static char ixgbe_dbg_reg_ops_buf[256] = "";
 
-/**
- * ixgbe_dbg_reg_ops_read - read for reg_ops datum
- * @filp: the opened file
- * @buffer: where to write the data for the user to read
- * @count: the size of the user's buffer
- * @ppos: file position offset
- **/
-static ssize_t ixgbe_dbg_reg_ops_read(struct file *filp, char __user *buffer,
-				    size_t count, loff_t *ppos)
+static ssize_t ixgbe_dbg_common_ops_read(struct file *filp, char __user *buffer,
+					 size_t count, loff_t *ppos,
+					 char *dbg_buf)
 {
 	struct ixgbe_adapter *adapter = filp->private_data;
 	char *buf;
@@ -29,8 +23,7 @@ static ssize_t ixgbe_dbg_reg_ops_read(struct file *filp, char __user *buffer,
 		return 0;
 
 	buf = kasprintf(GFP_KERNEL, "%s: %s\n",
-			adapter->netdev->name,
-			ixgbe_dbg_reg_ops_buf);
+			adapter->netdev->name, dbg_buf);
 	if (!buf)
 		return -ENOMEM;
 
@@ -46,6 +39,20 @@ static ssize_t ixgbe_dbg_reg_ops_read(struct file *filp, char __user *buffer,
 }
 
 /**
+ * ixgbe_dbg_reg_ops_read - read for reg_ops datum
+ * @filp: the opened file
+ * @buffer: where to write the data for the user to read
+ * @count: the size of the user's buffer
+ * @ppos: file position offset
+ **/
+static ssize_t ixgbe_dbg_reg_ops_read(struct file *filp, char __user *buffer,
+				      size_t count, loff_t *ppos)
+{
+	return ixgbe_dbg_common_ops_read(filp, buffer, count, ppos,
+					 ixgbe_dbg_reg_ops_buf);
+}
+
+/**
  * ixgbe_dbg_reg_ops_write - write into reg_ops datum
  * @filp: the opened file
  * @buffer: where to find the user's data
@@ -121,33 +128,11 @@ static char ixgbe_dbg_netdev_ops_buf[256] = "";
  * @count: the size of the user's buffer
  * @ppos: file position offset
  **/
-static ssize_t ixgbe_dbg_netdev_ops_read(struct file *filp,
-					 char __user *buffer,
+static ssize_t ixgbe_dbg_netdev_ops_read(struct file *filp, char __user *buffer,
 					 size_t count, loff_t *ppos)
 {
-	struct ixgbe_adapter *adapter = filp->private_data;
-	char *buf;
-	int len;
-
-	/* don't allow partial reads */
-	if (*ppos != 0)
-		return 0;
-
-	buf = kasprintf(GFP_KERNEL, "%s: %s\n",
-			adapter->netdev->name,
-			ixgbe_dbg_netdev_ops_buf);
-	if (!buf)
-		return -ENOMEM;
-
-	if (count < strlen(buf)) {
-		kfree(buf);
-		return -ENOSPC;
-	}
-
-	len = simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
-
-	kfree(buf);
-	return len;
+	return ixgbe_dbg_common_ops_read(filp, buffer, count, ppos,
+					 ixgbe_dbg_netdev_ops_buf);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index 99b170f1efd1..344a1f213a5f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -445,6 +445,89 @@ static int ixgbe_ipsec_parse_proto_keys(struct xfrm_state *xs,
 }
 
 /**
+ * ixgbe_ipsec_check_mgmt_ip - make sure there is no clash with mgmt IP filters
+ * @xs: pointer to transformer state struct
+ **/
+static int ixgbe_ipsec_check_mgmt_ip(struct xfrm_state *xs)
+{
+	struct net_device *dev = xs->xso.dev;
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 mfval, manc, reg;
+	int num_filters = 4;
+	bool manc_ipv4;
+	u32 bmcipval;
+	int i, j;
+
+#define MANC_EN_IPV4_FILTER      BIT(24)
+#define MFVAL_IPV4_FILTER_SHIFT  16
+#define MFVAL_IPV6_FILTER_SHIFT  24
+#define MIPAF_ARR(_m, _n)        (IXGBE_MIPAF + ((_m) * 0x10) + ((_n) * 4))
+
+#define IXGBE_BMCIP(_n)          (0x5050 + ((_n) * 4))
+#define IXGBE_BMCIPVAL           0x5060
+#define BMCIP_V4                 0x2
+#define BMCIP_V6                 0x3
+#define BMCIP_MASK               0x3
+
+	manc = IXGBE_READ_REG(hw, IXGBE_MANC);
+	manc_ipv4 = !!(manc & MANC_EN_IPV4_FILTER);
+	mfval = IXGBE_READ_REG(hw, IXGBE_MFVAL);
+	bmcipval = IXGBE_READ_REG(hw, IXGBE_BMCIPVAL);
+
+	if (xs->props.family == AF_INET) {
+		/* are there any IPv4 filters to check? */
+		if (manc_ipv4) {
+			/* the 4 ipv4 filters are all in MIPAF(3, i) */
+			for (i = 0; i < num_filters; i++) {
+				if (!(mfval & BIT(MFVAL_IPV4_FILTER_SHIFT + i)))
+					continue;
+
+				reg = IXGBE_READ_REG(hw, MIPAF_ARR(3, i));
+				if (reg == xs->id.daddr.a4)
+					return 1;
+			}
+		}
+
+		if ((bmcipval & BMCIP_MASK) == BMCIP_V4) {
+			reg = IXGBE_READ_REG(hw, IXGBE_BMCIP(3));
+			if (reg == xs->id.daddr.a4)
+				return 1;
+		}
+
+	} else {
+		/* if there are ipv4 filters, they are in the last ipv6 slot */
+		if (manc_ipv4)
+			num_filters = 3;
+
+		for (i = 0; i < num_filters; i++) {
+			if (!(mfval & BIT(MFVAL_IPV6_FILTER_SHIFT + i)))
+				continue;
+
+			for (j = 0; j < 4; j++) {
+				reg = IXGBE_READ_REG(hw, MIPAF_ARR(i, j));
+				if (reg != xs->id.daddr.a6[j])
+					break;
+			}
+			if (j == 4)   /* did we match all 4 words? */
+				return 1;
+		}
+
+		if ((bmcipval & BMCIP_MASK) == BMCIP_V6) {
+			for (j = 0; j < 4; j++) {
+				reg = IXGBE_READ_REG(hw, IXGBE_BMCIP(j));
+				if (reg != xs->id.daddr.a6[j])
+					break;
+			}
+			if (j == 4)   /* did we match all 4 words? */
+				return 1;
+		}
+	}
+
+	return 0;
+}
+
+/**
  * ixgbe_ipsec_add_sa - program device with a security association
  * @xs: pointer to transformer state struct
  **/
@@ -465,6 +548,11 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs)
 		return -EINVAL;
 	}
 
+	if (ixgbe_ipsec_check_mgmt_ip(xs)) {
+		netdev_err(dev, "IPsec IP addr clash with mgmt filters\n");
+		return -EINVAL;
+	}
+
 	if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) {
 		struct rx_sa rsa;
 
@@ -575,7 +663,7 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs)
 
 		/* hash the new entry for faster search in Rx path */
 		hash_add_rcu(ipsec->rx_sa_list, &ipsec->rx_tbl[sa_idx].hlist,
-			     (__force u64)rsa.xs->id.spi);
+			     (__force u32)rsa.xs->id.spi);
 	} else {
 		struct tx_sa tsa;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index ba3035c08572..dd8a3a037c2f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -7621,17 +7621,19 @@ static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter)
 	if (!test_and_clear_bit(__IXGBE_RESET_REQUESTED, &adapter->state))
 		return;
 
+	rtnl_lock();
 	/* If we're already down, removing or resetting, just bail */
 	if (test_bit(__IXGBE_DOWN, &adapter->state) ||
 	    test_bit(__IXGBE_REMOVING, &adapter->state) ||
-	    test_bit(__IXGBE_RESETTING, &adapter->state))
+	    test_bit(__IXGBE_RESETTING, &adapter->state)) {
+		rtnl_unlock();
 		return;
+	}
 
 	ixgbe_dump(adapter);
 	netdev_err(adapter->netdev, "Reset adapter\n");
 	adapter->tx_timeout_count++;
 
-	rtnl_lock();
 	ixgbe_reinit_locked(adapter);
 	rtnl_unlock();
 }
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
index 70c75681495f..56a1031dcc07 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
@@ -76,6 +76,7 @@ enum ixgbevf_ring_state_t {
 	__IXGBEVF_TX_DETECT_HANG,
 	__IXGBEVF_HANG_CHECK_ARMED,
 	__IXGBEVF_TX_XDP_RING,
+	__IXGBEVF_TX_XDP_RING_PRIMED,
 };
 
 #define ring_is_xdp(ring) \
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 083041129539..59416eddd840 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -991,24 +991,45 @@ static int ixgbevf_xmit_xdp_ring(struct ixgbevf_ring *ring,
 		return IXGBEVF_XDP_CONSUMED;
 
 	/* record the location of the first descriptor for this packet */
-	tx_buffer = &ring->tx_buffer_info[ring->next_to_use];
-	tx_buffer->bytecount = len;
-	tx_buffer->gso_segs = 1;
-	tx_buffer->protocol = 0;
-
 	i = ring->next_to_use;
-	tx_desc = IXGBEVF_TX_DESC(ring, i);
+	tx_buffer = &ring->tx_buffer_info[i];
 
 	dma_unmap_len_set(tx_buffer, len, len);
 	dma_unmap_addr_set(tx_buffer, dma, dma);
 	tx_buffer->data = xdp->data;
-	tx_desc->read.buffer_addr = cpu_to_le64(dma);
+	tx_buffer->bytecount = len;
+	tx_buffer->gso_segs = 1;
+	tx_buffer->protocol = 0;
+
+	/* Populate minimal context descriptor that will provide for the
+	 * fact that we are expected to process Ethernet frames.
+	 */
+	if (!test_bit(__IXGBEVF_TX_XDP_RING_PRIMED, &ring->state)) {
+		struct ixgbe_adv_tx_context_desc *context_desc;
+
+		set_bit(__IXGBEVF_TX_XDP_RING_PRIMED, &ring->state);
+
+		context_desc = IXGBEVF_TX_CTXTDESC(ring, 0);
+		context_desc->vlan_macip_lens	=
+			cpu_to_le32(ETH_HLEN << IXGBE_ADVTXD_MACLEN_SHIFT);
+		context_desc->seqnum_seed	= 0;
+		context_desc->type_tucmd_mlhl	=
+			cpu_to_le32(IXGBE_TXD_CMD_DEXT |
+				    IXGBE_ADVTXD_DTYP_CTXT);
+		context_desc->mss_l4len_idx	= 0;
+
+		i = 1;
+	}
 
 	/* put descriptor type bits */
 	cmd_type = IXGBE_ADVTXD_DTYP_DATA |
 		   IXGBE_ADVTXD_DCMD_DEXT |
 		   IXGBE_ADVTXD_DCMD_IFCS;
 	cmd_type |= len | IXGBE_TXD_CMD;
+
+	tx_desc = IXGBEVF_TX_DESC(ring, i);
+	tx_desc->read.buffer_addr = cpu_to_le64(dma);
+
 	tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);
 	tx_desc->read.olinfo_status =
 			cpu_to_le32((len << IXGBE_ADVTXD_PAYLEN_SHIFT) |
@@ -1688,6 +1709,7 @@ static void ixgbevf_configure_tx_ring(struct ixgbevf_adapter *adapter,
 	       sizeof(struct ixgbevf_tx_buffer) * ring->count);
 
 	clear_bit(__IXGBEVF_HANG_CHECK_ARMED, &ring->state);
+	clear_bit(__IXGBEVF_TX_XDP_RING_PRIMED, &ring->state);
 
 	IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(reg_idx), txdctl);
 
@@ -3119,15 +3141,17 @@ static void ixgbevf_reset_subtask(struct ixgbevf_adapter *adapter)
 	if (!test_and_clear_bit(__IXGBEVF_RESET_REQUESTED, &adapter->state))
 		return;
 
+	rtnl_lock();
 	/* If we're already down or resetting, just bail */
 	if (test_bit(__IXGBEVF_DOWN, &adapter->state) ||
 	    test_bit(__IXGBEVF_REMOVING, &adapter->state) ||
-	    test_bit(__IXGBEVF_RESETTING, &adapter->state))
+	    test_bit(__IXGBEVF_RESETTING, &adapter->state)) {
+		rtnl_unlock();
 		return;
+	}
 
 	adapter->tx_timeout_count++;
 
-	rtnl_lock();
 	ixgbevf_reinit_locked(adapter);
 	rtnl_unlock();
 }