Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:

 1) Revert CHECKSUM_COMPLETE optimization in pskb_trim_rcsum(), I can't
    figure out why it breaks things.

 2) Fix comparison in netfilter ipset's hash_netnet4_data_equal(), it
    was basically doing "x == x", from Dave Jones.

 3) Freescale FEC driver was DMA mapping the wrong number of bytes, from
    Sebastian Siewior.

 4) Blackhole and prohibit routes in ipv6 were not doing the right thing
    because their ->input and ->output methods were not being assigned
    correctly.  Now they behave properly like their ipv4 counterparts.
    From Kamala R.

 5) Several drivers advertise the NETIF_F_FRAGLIST capability, but
    really do not support this feature and will send garbage packets if
    fed fraglist SKBs.  From Eric Dumazet.

 6) Fix long standing user triggerable BUG_ON over loopback in RDS
    protocol stack, from Venkat Venkatsubra.

 7) Several not so common code paths can potentially try to invoke
    packet scheduler actions that might be NULL without checking.  Shore
    things up by either 1) defining a method as mandatory and erroring
    on registration if that method is NULL 2) defininig a method as
    optional and the registration function hooks up a default
    implementation when NULL is seen.  From Jamal Hadi Salim.

 8) Fix fragment detection in xen-natback driver, from Paul Durrant.

 9) Kill dangling enter_memory_pressure method in cg_proto ops, from
    Eric W Biederman.

10) SKBs that traverse namespaces should have their local_df cleared,
    from Hannes Frederic Sowa.

11) IOCB file position is not being updated by macvtap_aio_read() and
    tun_chr_aio_read().  From Zhi Yong Wu.

12) Don't free virtio_net netdev before releasing all of the NAPI
    instances.  From Andrey Vagin.

13) Procfs entry leak in xt_hashlimit, from Sergey Popovich.

14) IPv6 routes that are no cached routes should not count against the
    garbage collection limits.  We had this almost right, but were
    missing handling addrconf generated routes properly.  From Hannes
    Frederic Sowa.

15) fib{4,6}_rule_suppress() have to consider potentially seeing NULL
    route info when they are called, from Stefan Tomanek.

16) TUN and MACVTAP have had truncated packet signalling for some time,
    fix from Jason Wang.

17) Fix use after frrr in __udp4_lib_rcv(), from Eric Dumazet.

18) xen-netback does not interpret the NAPI budget properly for TX work,
    fix from Paul Durrant.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (132 commits)
  igb: Fix for issue where values could be too high for udelay function.
  i40e: fix null dereference
  xen-netback: fix gso_prefix check
  net: make neigh_priv_len in struct net_device 16bit instead of 8bit
  drivers: net: cpsw: fix for cpsw crash when build as modules
  xen-netback: napi: don't prematurely request a tx event
  xen-netback: napi: fix abuse of budget
  sch_tbf: use do_div() for 64-bit divide
  udp: ipv4: must add synchronization in udp_sk_rx_dst_set()
  net:fec: remove duplicate lines in comment about errata ERR006358
  Revert "8390 : Replace ei_debug with msg_enable/NETIF_MSG_* feature"
  8390 : Replace ei_debug with msg_enable/NETIF_MSG_* feature
  xen-netback: make sure skb linear area covers checksum field
  net: smc91x: Fix device tree based configuration so it's usable
  udp: ipv4: fix potential use after free in udp_v4_early_demux()
  macvtap: signal truncated packets
  tun: unbreak truncated packet signalling
  net: sched: htb: fix the calculation of quantum
  net: sched: tbf: fix the calculation of max_size
  micrel: add support for KSZ8041RNLI
  ...

6 files changed, 101 insertions, 23 deletions

diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 2e27837ce6a2..fd844b53e385 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -585,7 +585,7 @@ static void efx_start_datapath(struct efx_nic *efx)
 			   EFX_MAX_FRAME_LEN(efx->net_dev->mtu) +
 			   efx->type->rx_buffer_padding);
 	rx_buf_len = (sizeof(struct efx_rx_page_state) +
-		      NET_IP_ALIGN + efx->rx_dma_len);
+		      efx->rx_ip_align + efx->rx_dma_len);
 	if (rx_buf_len <= PAGE_SIZE) {
 		efx->rx_scatter = efx->type->always_rx_scatter;
 		efx->rx_buffer_order = 0;
@@ -645,6 +645,8 @@ static void efx_start_datapath(struct efx_nic *efx)
 		WARN_ON(channel->rx_pkt_n_frags);
 	}
 
+	efx_ptp_start_datapath(efx);
+
 	if (netif_device_present(efx->net_dev))
 		netif_tx_wake_all_queues(efx->net_dev);
 }
@@ -659,6 +661,8 @@ static void efx_stop_datapath(struct efx_nic *efx)
 	EFX_ASSERT_RESET_SERIALISED(efx);
 	BUG_ON(efx->port_enabled);
 
+	efx_ptp_stop_datapath(efx);
+
 	/* Stop RX refill */
 	efx_for_each_channel(channel, efx) {
 		efx_for_each_channel_rx_queue(rx_queue, channel)
@@ -2540,6 +2544,8 @@ static int efx_init_struct(struct efx_nic *efx,
 
 	efx->net_dev = net_dev;
 	efx->rx_prefix_size = efx->type->rx_prefix_size;
+	efx->rx_ip_align =
+		NET_IP_ALIGN ? (efx->rx_prefix_size + NET_IP_ALIGN) % 4 : 0;
 	efx->rx_packet_hash_offset =
 		efx->type->rx_hash_offset - efx->type->rx_prefix_size;
 	spin_lock_init(&efx->stats_lock);
diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index 366c8e3e3784..4b0bd8a1514d 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -50,6 +50,7 @@ struct efx_mcdi_async_param {
 static void efx_mcdi_timeout_async(unsigned long context);
 static int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating,
 			       bool *was_attached_out);
+static bool efx_mcdi_poll_once(struct efx_nic *efx);
 
 static inline struct efx_mcdi_iface *efx_mcdi(struct efx_nic *efx)
 {
@@ -237,6 +238,21 @@ static void efx_mcdi_read_response_header(struct efx_nic *efx)
 	}
 }
 
+static bool efx_mcdi_poll_once(struct efx_nic *efx)
+{
+	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
+
+	rmb();
+	if (!efx->type->mcdi_poll_response(efx))
+		return false;
+
+	spin_lock_bh(&mcdi->iface_lock);
+	efx_mcdi_read_response_header(efx);
+	spin_unlock_bh(&mcdi->iface_lock);
+
+	return true;
+}
+
 static int efx_mcdi_poll(struct efx_nic *efx)
 {
 	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
@@ -272,18 +288,13 @@ static int efx_mcdi_poll(struct efx_nic *efx)
 
 		time = jiffies;
 
-		rmb();
-		if (efx->type->mcdi_poll_response(efx))
+		if (efx_mcdi_poll_once(efx))
 			break;
 
 		if (time_after(time, finish))
 			return -ETIMEDOUT;
 	}
 
-	spin_lock_bh(&mcdi->iface_lock);
-	efx_mcdi_read_response_header(efx);
-	spin_unlock_bh(&mcdi->iface_lock);
-
 	/* Return rc=0 like wait_event_timeout() */
 	return 0;
 }
@@ -619,6 +630,16 @@ int efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen,
 		rc = efx_mcdi_await_completion(efx);
 
 	if (rc != 0) {
+		netif_err(efx, hw, efx->net_dev,
+			  "MC command 0x%x inlen %d mode %d timed out\n",
+			  cmd, (int)inlen, mcdi->mode);
+
+		if (mcdi->mode == MCDI_MODE_EVENTS && efx_mcdi_poll_once(efx)) {
+			netif_err(efx, hw, efx->net_dev,
+				  "MCDI request was completed without an event\n");
+			rc = 0;
+		}
+
 		/* Close the race with efx_mcdi_ev_cpl() executing just too late
 		 * and completing a request we've just cancelled, by ensuring
 		 * that the seqno check therein fails.
@@ -627,11 +648,9 @@ int efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen,
 		++mcdi->seqno;
 		++mcdi->credits;
 		spin_unlock_bh(&mcdi->iface_lock);
+	}
 
-		netif_err(efx, hw, efx->net_dev,
-			  "MC command 0x%x inlen %d mode %d timed out\n",
-			  cmd, (int)inlen, mcdi->mode);
-	} else {
+	if (rc == 0) {
 		size_t hdr_len, data_len;
 
 		/* At the very least we need a memory barrier here to ensure
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index b14a717ac3e8..542a0d252ae0 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -683,6 +683,8 @@ struct vfdi_status;
  * @n_channels: Number of channels in use
  * @n_rx_channels: Number of channels used for RX (= number of RX queues)
  * @n_tx_channels: Number of channels used for TX
+ * @rx_ip_align: RX DMA address offset to have IP header aligned in
+ *	in accordance with NET_IP_ALIGN
  * @rx_dma_len: Current maximum RX DMA length
  * @rx_buffer_order: Order (log2) of number of pages for each RX buffer
  * @rx_buffer_truesize: Amortised allocation size of an RX buffer,
@@ -816,6 +818,7 @@ struct efx_nic {
 	unsigned rss_spread;
 	unsigned tx_channel_offset;
 	unsigned n_tx_channels;
+	unsigned int rx_ip_align;
 	unsigned int rx_dma_len;
 	unsigned int rx_buffer_order;
 	unsigned int rx_buffer_truesize;
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index 11b6112d9249..91c63ec79c5f 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -560,6 +560,8 @@ void efx_ptp_get_ts_info(struct efx_nic *efx, struct ethtool_ts_info *ts_info);
 bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb);
 int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb);
 void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev);
+void efx_ptp_start_datapath(struct efx_nic *efx);
+void efx_ptp_stop_datapath(struct efx_nic *efx);
 
 extern const struct efx_nic_type falcon_a1_nic_type;
 extern const struct efx_nic_type falcon_b0_nic_type;
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index 03acf57df045..3dd39dcfe36b 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -220,6 +220,7 @@ struct efx_ptp_timeset {
  * @evt_list: List of MC receive events awaiting packets
  * @evt_free_list: List of free events
  * @evt_lock: Lock for manipulating evt_list and evt_free_list
+ * @evt_overflow: Boolean indicating that event list has overflowed
  * @rx_evts: Instantiated events (on evt_list and evt_free_list)
  * @workwq: Work queue for processing pending PTP operations
  * @work: Work task
@@ -270,6 +271,7 @@ struct efx_ptp_data {
 	struct list_head evt_list;
 	struct list_head evt_free_list;
 	spinlock_t evt_lock;
+	bool evt_overflow;
 	struct efx_ptp_event_rx rx_evts[MAX_RECEIVE_EVENTS];
 	struct workqueue_struct *workwq;
 	struct work_struct work;
@@ -635,6 +637,11 @@ static void efx_ptp_drop_time_expired_events(struct efx_nic *efx)
 			}
 		}
 	}
+	/* If the event overflow flag is set and the event list is now empty
+	 * clear the flag to re-enable the overflow warning message.
+	 */
+	if (ptp->evt_overflow && list_empty(&ptp->evt_list))
+		ptp->evt_overflow = false;
 	spin_unlock_bh(&ptp->evt_lock);
 }
 
@@ -676,6 +683,11 @@ static enum ptp_packet_state efx_ptp_match_rx(struct efx_nic *efx,
 			break;
 		}
 	}
+	/* If the event overflow flag is set and the event list is now empty
+	 * clear the flag to re-enable the overflow warning message.
+	 */
+	if (ptp->evt_overflow && list_empty(&ptp->evt_list))
+		ptp->evt_overflow = false;
 	spin_unlock_bh(&ptp->evt_lock);
 
 	return rc;
@@ -705,8 +717,9 @@ static bool efx_ptp_process_events(struct efx_nic *efx, struct sk_buff_head *q)
 			__skb_queue_tail(q, skb);
 		} else if (time_after(jiffies, match->expiry)) {
 			match->state = PTP_PACKET_STATE_TIMED_OUT;
-			netif_warn(efx, rx_err, efx->net_dev,
-				   "PTP packet - no timestamp seen\n");
+			if (net_ratelimit())
+				netif_warn(efx, rx_err, efx->net_dev,
+					   "PTP packet - no timestamp seen\n");
 			__skb_queue_tail(q, skb);
 		} else {
 			/* Replace unprocessed entry and stop */
@@ -788,9 +801,14 @@ fail:
 static int efx_ptp_stop(struct efx_nic *efx)
 {
 	struct efx_ptp_data *ptp = efx->ptp_data;
-	int rc = efx_ptp_disable(efx);
 	struct list_head *cursor;
 	struct list_head *next;
+	int rc;
+
+	if (ptp == NULL)
+		return 0;
+
+	rc = efx_ptp_disable(efx);
 
 	if (ptp->rxfilter_installed) {
 		efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED,
@@ -809,11 +827,19 @@ static int efx_ptp_stop(struct efx_nic *efx)
 	list_for_each_safe(cursor, next, &efx->ptp_data->evt_list) {
 		list_move(cursor, &efx->ptp_data->evt_free_list);
 	}
+	ptp->evt_overflow = false;
 	spin_unlock_bh(&efx->ptp_data->evt_lock);
 
 	return rc;
 }
 
+static int efx_ptp_restart(struct efx_nic *efx)
+{
+	if (efx->ptp_data && efx->ptp_data->enabled)
+		return efx_ptp_start(efx);
+	return 0;
+}
+
 static void efx_ptp_pps_worker(struct work_struct *work)
 {
 	struct efx_ptp_data *ptp =
@@ -901,6 +927,7 @@ static int efx_ptp_probe_channel(struct efx_channel *channel)
 	spin_lock_init(&ptp->evt_lock);
 	for (pos = 0; pos < MAX_RECEIVE_EVENTS; pos++)
 		list_add(&ptp->rx_evts[pos].link, &ptp->evt_free_list);
+	ptp->evt_overflow = false;
 
 	ptp->phc_clock_info.owner = THIS_MODULE;
 	snprintf(ptp->phc_clock_info.name,
@@ -989,7 +1016,11 @@ bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb)
 		skb->len >= PTP_MIN_LENGTH &&
 		skb->len <= MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM &&
 		likely(skb->protocol == htons(ETH_P_IP)) &&
+		skb_transport_header_was_set(skb) &&
+		skb_network_header_len(skb) >= sizeof(struct iphdr) &&
 		ip_hdr(skb)->protocol == IPPROTO_UDP &&
+		skb_headlen(skb) >=
+		skb_transport_offset(skb) + sizeof(struct udphdr) &&
 		udp_hdr(skb)->dest == htons(PTP_EVENT_PORT);
 }
 
@@ -1106,7 +1137,7 @@ static int efx_ptp_change_mode(struct efx_nic *efx, bool enable_wanted,
 {
 	if ((enable_wanted != efx->ptp_data->enabled) ||
 	    (enable_wanted && (efx->ptp_data->mode != new_mode))) {
-		int rc;
+		int rc = 0;
 
 		if (enable_wanted) {
 			/* Change of mode requires disable */
@@ -1123,7 +1154,8 @@ static int efx_ptp_change_mode(struct efx_nic *efx, bool enable_wanted,
 			 * succeed.
 			 */
 			efx->ptp_data->mode = new_mode;
-			rc = efx_ptp_start(efx);
+			if (netif_running(efx->net_dev))
+				rc = efx_ptp_start(efx);
 			if (rc == 0) {
 				rc = efx_ptp_synchronize(efx,
 							 PTP_SYNC_ATTEMPTS * 2);
@@ -1295,8 +1327,13 @@ static void ptp_event_rx(struct efx_nic *efx, struct efx_ptp_data *ptp)
 		list_add_tail(&evt->link, &ptp->evt_list);
 
 		queue_work(ptp->workwq, &ptp->work);
-	} else {
-		netif_err(efx, rx_err, efx->net_dev, "No free PTP event");
+	} else if (!ptp->evt_overflow) {
+		/* Log a warning message and set the event overflow flag.
+		 * The message won't be logged again until the event queue
+		 * becomes empty.
+		 */
+		netif_err(efx, rx_err, efx->net_dev, "PTP event queue overflow\n");
+		ptp->evt_overflow = true;
 	}
 	spin_unlock_bh(&ptp->evt_lock);
 }
@@ -1389,7 +1426,7 @@ static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta)
 	if (rc != 0)
 		return rc;
 
-	ptp_data->current_adjfreq = delta;
+	ptp_data->current_adjfreq = adjustment_ns;
 	return 0;
 }
 
@@ -1404,7 +1441,7 @@ static int efx_phc_adjtime(struct ptp_clock_info *ptp, s64 delta)
 
 	MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_ADJUST);
 	MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
-	MCDI_SET_QWORD(inbuf, PTP_IN_ADJUST_FREQ, 0);
+	MCDI_SET_QWORD(inbuf, PTP_IN_ADJUST_FREQ, ptp_data->current_adjfreq);
 	MCDI_SET_DWORD(inbuf, PTP_IN_ADJUST_SECONDS, (u32)delta_ts.tv_sec);
 	MCDI_SET_DWORD(inbuf, PTP_IN_ADJUST_NANOSECONDS, (u32)delta_ts.tv_nsec);
 	return efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
@@ -1491,3 +1528,14 @@ void efx_ptp_probe(struct efx_nic *efx)
 		efx->extra_channel_type[EFX_EXTRA_CHANNEL_PTP] =
 			&efx_ptp_channel_type;
 }
+
+void efx_ptp_start_datapath(struct efx_nic *efx)
+{
+	if (efx_ptp_restart(efx))
+		netif_err(efx, drv, efx->net_dev, "Failed to restart PTP.\n");
+}
+
+void efx_ptp_stop_datapath(struct efx_nic *efx)
+{
+	efx_ptp_stop(efx);
+}
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 8f09e686fc23..42488df1f4ec 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -94,7 +94,7 @@ static inline void efx_sync_rx_buffer(struct efx_nic *efx,
 
 void efx_rx_config_page_split(struct efx_nic *efx)
 {
-	efx->rx_page_buf_step = ALIGN(efx->rx_dma_len + NET_IP_ALIGN,
+	efx->rx_page_buf_step = ALIGN(efx->rx_dma_len + efx->rx_ip_align,
 				      EFX_RX_BUF_ALIGNMENT);
 	efx->rx_bufs_per_page = efx->rx_buffer_order ? 1 :
 		((PAGE_SIZE - sizeof(struct efx_rx_page_state)) /
@@ -189,9 +189,9 @@ static int efx_init_rx_buffers(struct efx_rx_queue *rx_queue)
 		do {
 			index = rx_queue->added_count & rx_queue->ptr_mask;
 			rx_buf = efx_rx_buffer(rx_queue, index);
-			rx_buf->dma_addr = dma_addr + NET_IP_ALIGN;
+			rx_buf->dma_addr = dma_addr + efx->rx_ip_align;
 			rx_buf->page = page;
-			rx_buf->page_offset = page_offset + NET_IP_ALIGN;
+			rx_buf->page_offset = page_offset + efx->rx_ip_align;
 			rx_buf->len = efx->rx_dma_len;
 			rx_buf->flags = 0;
 			++rx_queue->added_count;