From 59cd827f26019ac790b2f34cbad478037f51c570 Mon Sep 17 00:00:00 2001
From: Matt Chen <matt.chen@intel.com>
Date: Mon, 28 Aug 2017 14:57:54 +0800
Subject: iwlwifi: mvm: fix wowlan resume failed to load INIT ucode

If we set disconnect on wowlan and run suspend/resume, will run
into:
...snipped
iwlwifi 0000:01:00.0: Failed to load firmware chunk!
iwlwifi 0000:01:00.0: Could not load the [0] uCode section
iwlwifi 0000:01:00.0: Failed to start INIT ucode: -110
iwlwifi 0000:01:00.0: Failed to run INIT ucode: -110
iwlwifi 0000:01:00.0: Failed to start RT ucode: -110

It is because we still keep IWL_MVM_STATUS_IN_HW_RESTART in
__iwl_mvm_resume.  When mac80211 starts the device as
__iwl_mvm_mac_start(), we will miss iwl_mvm_restart_cleanup(mvm).

Signed-off-by: Matt Chen <matt.chen@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/d3.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index 5de19ea10575..b205a7bfb828 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -2167,7 +2167,7 @@ out:
 	 * 1. We are not using a unified image
 	 * 2. We are using a unified image but had an error while exiting D3
 	 */
-	set_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status);
+	set_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status);
 	set_bit(IWL_MVM_STATUS_D3_RECONFIG, &mvm->status);
 	/*
 	 * When switching images we return 1, which causes mac80211
-- 
cgit v1.2.3


From 6110d9e5bdd15c4e60fb67f330fbf74681e7daf7 Mon Sep 17 00:00:00 2001
From: David Spinadel <david.spinadel@intel.com>
Date: Tue, 29 Aug 2017 13:56:02 +0300
Subject: iwlwifi: mvm: Flush non STA TX queues

When starting wowlan mac80211 requests flush w/o vif
and we ignore this request. As a result some packets
stay stuck in the queue and it may end up with a queue
hang.

Allow the driver to flush queues even if station isn't
specified.

Signed-off-by: David Spinadel <david.spinadel@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 44 ++++++++++++++++++++++-
 1 file changed, 43 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 15f2d826bb4b..64b0be73ea72 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -3975,6 +3975,43 @@ out_unlock:
 	return ret;
 }
 
+static void iwl_mvm_flush_no_vif(struct iwl_mvm *mvm, u32 queues, bool drop)
+{
+	if (drop) {
+		if (iwl_mvm_has_new_tx_api(mvm))
+			/* TODO new tx api */
+			WARN_ONCE(1,
+				  "Need to implement flush TX queue\n");
+		else
+			iwl_mvm_flush_tx_path(mvm,
+				iwl_mvm_flushable_queues(mvm) & queues,
+				0);
+	} else {
+		if (iwl_mvm_has_new_tx_api(mvm)) {
+			struct ieee80211_sta *sta;
+			int i;
+
+			mutex_lock(&mvm->mutex);
+
+			for (i = 0; i < ARRAY_SIZE(mvm->fw_id_to_mac_id); i++) {
+				sta = rcu_dereference_protected(
+						mvm->fw_id_to_mac_id[i],
+						lockdep_is_held(&mvm->mutex));
+				if (IS_ERR_OR_NULL(sta))
+					continue;
+
+				iwl_mvm_wait_sta_queues_empty(mvm,
+						iwl_mvm_sta_from_mac80211(sta));
+			}
+
+			mutex_unlock(&mvm->mutex);
+		} else {
+			iwl_trans_wait_tx_queues_empty(mvm->trans,
+						       queues);
+		}
+	}
+}
+
 static void iwl_mvm_mac_flush(struct ieee80211_hw *hw,
 			      struct ieee80211_vif *vif, u32 queues, bool drop)
 {
@@ -3985,7 +4022,12 @@ static void iwl_mvm_mac_flush(struct ieee80211_hw *hw,
 	int i;
 	u32 msk = 0;
 
-	if (!vif || vif->type != NL80211_IFTYPE_STATION)
+	if (!vif) {
+		iwl_mvm_flush_no_vif(mvm, queues, drop);
+		return;
+	}
+
+	if (vif->type != NL80211_IFTYPE_STATION)
 		return;
 
 	/* Make sure we're done with the deferred traffic before flushing */
-- 
cgit v1.2.3


From 0fe8bed6e37c259b85d123ef9667f972305c9d6b Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Thu, 31 Aug 2017 16:27:06 +0300
Subject: iwlwifi: mvm: send all non-bufferable frames on the probe queue

AP interfaces now send all non-bufferable frames using the broadcast
station. Thus allow them to use the probe queue and don't warn about
it.

Fixes: eb045e6e0389 ("iwlwifi: mvm: Avoid deferring non bufferable frames")
Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index 172b5e63d3fb..6f2e2af23219 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -564,8 +564,8 @@ static int iwl_mvm_get_ctrl_vif_queue(struct iwl_mvm *mvm,
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_ADHOC:
 		/*
-		 * Handle legacy hostapd as well, where station will be added
-		 * only just before sending the association response.
+		 * Non-bufferable frames use the broadcast station, thus they
+		 * use the probe queue.
 		 * Also take care of the case where we send a deauth to a
 		 * station that we don't have, or similarly an association
 		 * response (with non-success status) for a station we can't
@@ -573,9 +573,9 @@ static int iwl_mvm_get_ctrl_vif_queue(struct iwl_mvm *mvm,
 		 * Also, disassociate frames might happen, particular with
 		 * reason 7 ("Class 3 frame received from nonassociated STA").
 		 */
-		if (ieee80211_is_probe_resp(fc) || ieee80211_is_auth(fc) ||
-		    ieee80211_is_deauth(fc) || ieee80211_is_assoc_resp(fc) ||
-		    ieee80211_is_disassoc(fc))
+		if (ieee80211_is_mgmt(fc) &&
+		    (!ieee80211_is_bufferable_mmpdu(fc) ||
+		     ieee80211_is_deauth(fc) || ieee80211_is_disassoc(fc)))
 			return mvm->probe_queue;
 		if (info->hw_queue == info->control.vif->cab_queue)
 			return mvmvif->cab_queue;
-- 
cgit v1.2.3


From bd800e41a3de5c7e56b2fd27088bdaf5e228d227 Mon Sep 17 00:00:00 2001
From: Naftali Goldstein <naftali.goldstein@intel.com>
Date: Mon, 28 Aug 2017 11:51:05 +0300
Subject: iwlwifi: mvm: change state when queueing agg start work

Add a new state to enum iwl_mvm_agg_state, which is used between
queueing the work that starts tx aggregations and actually starting that
work (changing to state IWL_AGG_STARTING).
This solves a race where ieee80211_start_tx_ba_session is called a
second time, before the work queued by the first run has a chance to
change the agg_state. In this case the second call to
ieee80211_start_tx_ba_session returns an error, and the fallback is to
abort the ba session start.

Fixes: 482e48440a0e ("iwlwifi: mvm: change open and close criteria of a BA session")
Signed-off-by: Naftali Goldstein <naftali.goldstein@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/rs.c  | 3 ++-
 drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 6 ++++--
 drivers/net/wireless/intel/iwlwifi/mvm/sta.h | 2 ++
 3 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
index ba7bd049d3d4..0fe723ca844e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
@@ -661,7 +661,8 @@ static void rs_tl_turn_on_agg(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvmsta,
 	    (lq_sta->tx_agg_tid_en & BIT(tid)) &&
 	    (tid_data->tx_count_last >= IWL_MVM_RS_AGG_START_THRESHOLD)) {
 		IWL_DEBUG_RATE(mvm, "try to aggregate tid %d\n", tid);
-		rs_tl_turn_on_agg_for_tid(mvm, lq_sta, tid, sta);
+		if (rs_tl_turn_on_agg_for_tid(mvm, lq_sta, tid, sta) == 0)
+			tid_data->state = IWL_AGG_QUEUED;
 	}
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 411a2055dc45..2dafe9bb4d8b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -2385,8 +2385,10 @@ int iwl_mvm_sta_tx_agg_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	if (WARN_ON_ONCE(tid >= IWL_MAX_TID_COUNT))
 		return -EINVAL;
 
-	if (mvmsta->tid_data[tid].state != IWL_AGG_OFF) {
-		IWL_ERR(mvm, "Start AGG when state is not IWL_AGG_OFF %d!\n",
+	if (mvmsta->tid_data[tid].state != IWL_AGG_QUEUED &&
+	    mvmsta->tid_data[tid].state != IWL_AGG_OFF) {
+		IWL_ERR(mvm,
+			"Start AGG when state is not IWL_AGG_QUEUED or IWL_AGG_OFF %d!\n",
 			mvmsta->tid_data[tid].state);
 		return -ENXIO;
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
index d13893806513..aedabe101cf0 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
@@ -281,6 +281,7 @@ struct iwl_mvm_vif;
  * These states relate to a specific RA / TID.
  *
  * @IWL_AGG_OFF: aggregation is not used
+ * @IWL_AGG_QUEUED: aggregation start work has been queued
  * @IWL_AGG_STARTING: aggregation are starting (between start and oper)
  * @IWL_AGG_ON: aggregation session is up
  * @IWL_EMPTYING_HW_QUEUE_ADDBA: establishing a BA session - waiting for the
@@ -290,6 +291,7 @@ struct iwl_mvm_vif;
  */
 enum iwl_mvm_agg_state {
 	IWL_AGG_OFF = 0,
+	IWL_AGG_QUEUED,
 	IWL_AGG_STARTING,
 	IWL_AGG_ON,
 	IWL_EMPTYING_HW_QUEUE_ADDBA,
-- 
cgit v1.2.3


From 8458e48ac7ad86a5ab7f3d1a8cacd9205a9a97ce Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Sun, 3 Sep 2017 16:04:38 +0300
Subject: iwlwifi: mvm: wake the correct mac80211 queue

iwl_mvm_start_mac_queues() takes a bitmap of the queues to wake.
When deferred tx is purged, set the bit of the hw_queue so
the correct queue will be waken up.

Fixes: 7e39a00d5931 ("iwlwifi: mvm: start mac queues when deferred tx frames are purged")
Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 64b0be73ea72..3a6ce4222ff5 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -2563,7 +2563,7 @@ static void iwl_mvm_purge_deferred_tx_frames(struct iwl_mvm *mvm,
 			 * queues, so we should never get a second deferred
 			 * frame for the RA/TID.
 			 */
-			iwl_mvm_start_mac_queues(mvm, info->hw_queue);
+			iwl_mvm_start_mac_queues(mvm, BIT(info->hw_queue));
 			ieee80211_free_txskb(mvm->hw, skb);
 		}
 	}
-- 
cgit v1.2.3


From 97bce57bd7f96e1218751996f549a6e61f18cc8c Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Fri, 1 Sep 2017 17:59:15 +0300
Subject: iwlwifi: mvm: use IWL_HCMD_NOCOPY for MCAST_FILTER_CMD

The MCAST_FILTER_CMD can get quite large when we have many mcast
addresses to set (we support up to 255).  So the command should be
send as NOCOPY to prevent a warning caused by too-long commands:

WARNING: CPU: 0 PID: 9700 at /root/iwlwifi/stack-dev/drivers/net/wireless/intel/iwlwifi/pcie/tx.c:1550 iwl_pcie_enqueue_hcmd+0x8c7/0xb40 [iwlwifi]
Command MCAST_FILTER_CMD (0x1d0) is too large (328 bytes)

This fixes: https://bugzilla.kernel.org/show_bug.cgi?id=196743

Cc: stable@vger.kernel.org
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 3a6ce4222ff5..635db63f972e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -1546,6 +1546,11 @@ static void iwl_mvm_mc_iface_iterator(void *_data, u8 *mac,
 	struct iwl_mvm_mc_iter_data *data = _data;
 	struct iwl_mvm *mvm = data->mvm;
 	struct iwl_mcast_filter_cmd *cmd = mvm->mcast_filter_cmd;
+	struct iwl_host_cmd hcmd = {
+		.id = MCAST_FILTER_CMD,
+		.flags = CMD_ASYNC,
+		.dataflags[0] = IWL_HCMD_DFL_NOCOPY,
+	};
 	int ret, len;
 
 	/* if we don't have free ports, mcast frames will be dropped */
@@ -1560,7 +1565,10 @@ static void iwl_mvm_mc_iface_iterator(void *_data, u8 *mac,
 	memcpy(cmd->bssid, vif->bss_conf.bssid, ETH_ALEN);
 	len = roundup(sizeof(*cmd) + cmd->count * ETH_ALEN, 4);
 
-	ret = iwl_mvm_send_cmd_pdu(mvm, MCAST_FILTER_CMD, CMD_ASYNC, len, cmd);
+	hcmd.len[0] = len;
+	hcmd.data[0] = cmd;
+
+	ret = iwl_mvm_send_cmd(mvm, &hcmd);
 	if (ret)
 		IWL_ERR(mvm, "mcast filter cmd error. ret=%d\n", ret);
 }
-- 
cgit v1.2.3


From 61e7d91bcf7725b9fcd9cbfc5fa0e0f84f19e6de Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Fri, 1 Sep 2017 18:57:35 +0300
Subject: iwlwifi: mvm: handle FIF_ALLMULTI when setting multicast addresses

We were ignoring the FIF_ALLMULTI flag when setting the multicast
addresses with MCAST_FILTER_CMD.  Check if this flag is set and enable
pass_all accordingly.  We also need to set the count to 0 if pass_all
is enable so we don't pass addresses to the firmware when not needed
(as doing so causes an assert).

This fixes https://bugzilla.kernel.org/show_bug.cgi?id=196741

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 635db63f972e..3bcaa82f59b2 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -1643,6 +1643,12 @@ static void iwl_mvm_configure_filter(struct ieee80211_hw *hw,
 	if (!cmd)
 		goto out;
 
+	if (changed_flags & FIF_ALLMULTI)
+		cmd->pass_all = !!(*total_flags & FIF_ALLMULTI);
+
+	if (cmd->pass_all)
+		cmd->count = 0;
+
 	iwl_mvm_recalc_multicast(mvm);
 out:
 	mutex_unlock(&mvm->mutex);
-- 
cgit v1.2.3


From 3f497de997c7ed34ad8a90b64f1ca53a41d428b4 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Sat, 2 Sep 2017 11:05:22 +0300
Subject: iwlwifi: mvm: initialize status in iwl_mvm_add_int_sta_common()

We always need to initialize the status argument to the success case
before calling iwl_mvm_send_cmd_status() or
iwl_mvm_send_cmd_pdu_status() (which calls the former) otherwise we
may get an uninitialized value back.  In this case, we use
ADD_STA_SUCCESS as success.

Fixes: 732d06e9d9cf ("iwlwifi: mvm: add station before allocating a queue")
Reported by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 2dafe9bb4d8b..c4a343534c5e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -1285,7 +1285,7 @@ static int iwl_mvm_add_int_sta_common(struct iwl_mvm *mvm,
 {
 	struct iwl_mvm_add_sta_cmd cmd;
 	int ret;
-	u32 status;
+	u32 status = ADD_STA_SUCCESS;
 
 	lockdep_assert_held(&mvm->mutex);
 
-- 
cgit v1.2.3


From d460f1fb83a44833a09c8eaa34b30ce553cab8c5 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Sat, 2 Sep 2017 11:25:40 +0300
Subject: iwlwifi: mvm: set status before calling iwl_mvm_send_cmd_status()

We always must set the status to what we consider success before
calling iwl_mvm_send_cmd_status() (also iwl_mvm_send_cmd_pdu_status()
which calls it).  Fix a few places where initialization is missing.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/scan.c | 2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/tt.c   | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index 50983615dce6..774122fed454 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -555,7 +555,7 @@ static int iwl_mvm_lmac_scan_abort(struct iwl_mvm *mvm)
 	struct iwl_host_cmd cmd = {
 		.id = SCAN_OFFLOAD_ABORT_CMD,
 	};
-	u32 status;
+	u32 status = CAN_ABORT_STATUS;
 
 	ret = iwl_mvm_send_cmd_status(mvm, &cmd, &status);
 	if (ret)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
index 8876c2abc440..4d907f60bce9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
@@ -529,6 +529,7 @@ int iwl_mvm_ctdp_command(struct iwl_mvm *mvm, u32 op, u32 state)
 
 	lockdep_assert_held(&mvm->mutex);
 
+	status = 0;
 	ret = iwl_mvm_send_cmd_pdu_status(mvm, WIDE_ID(PHY_OPS_GROUP,
 						       CTDP_CONFIG_CMD),
 					  sizeof(cmd), &cmd, &status);
-- 
cgit v1.2.3


From 5f90472c00ddf1e64c2865f71cced297bd5f80a2 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Mon, 4 Sep 2017 20:27:04 +0300
Subject: iwlwifi: mvm: fix reorder buffer for 9000 devices

The condition to check if reorder buffer ran out of
space is faulty, as it takes into account only the
NSSN.
In case the head SN was too far behind the reorder
buffer should move forward, regardless of the NSSN
status.
This caused the driver to release packets out of order
in some scenarios.

Fixes: b915c10174fb ("iwlwifi: mvm: add reorder buffer per queue")
Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 67ffd9774712..77f77bc5d083 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -672,11 +672,12 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm,
 	 * If there was a significant jump in the nssn - adjust.
 	 * If the SN is smaller than the NSSN it might need to first go into
 	 * the reorder buffer, in which case we just release up to it and the
-	 * rest of the function will take of storing it and releasing up to the
-	 * nssn
+	 * rest of the function will take care of storing it and releasing up to
+	 * the nssn
 	 */
 	if (!iwl_mvm_is_sn_less(nssn, buffer->head_sn + buffer->buf_size,
-				buffer->buf_size)) {
+				buffer->buf_size) ||
+	    !ieee80211_sn_less(sn, buffer->head_sn + buffer->buf_size)) {
 		u16 min_sn = ieee80211_sn_less(sn, nssn) ? sn : nssn;
 
 		iwl_mvm_release_frames(mvm, sta, napi, buffer, min_sn);
-- 
cgit v1.2.3


From 17df6453d4be17910456e99c5a85025aa1b7a246 Mon Sep 17 00:00:00 2001
From: Arend Van Spriel <arend.vanspriel@broadcom.com>
Date: Tue, 12 Sep 2017 10:47:53 +0200
Subject: brcmfmac: add length check in brcmf_cfg80211_escan_handler()

Upon handling the firmware notification for scans the length was
checked properly and may result in corrupting kernel heap memory
due to buffer overruns. This fix addresses CVE-2017-0786.

Cc: stable@vger.kernel.org # v4.0.x
Cc: Kevin Cernekee <cernekee@chromium.org>
Reviewed-by: Hante Meuleman <hante.meuleman@broadcom.com>
Reviewed-by: Pieter-Paul Giesberts <pieter-paul.giesberts@broadcom.com>
Reviewed-by: Franky Lin <franky.lin@broadcom.com>
Signed-off-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../wireless/broadcom/brcm80211/brcmfmac/cfg80211.c    | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index aaed4ab503ad..26a0de371c26 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -3162,6 +3162,7 @@ brcmf_cfg80211_escan_handler(struct brcmf_if *ifp,
 	struct brcmf_cfg80211_info *cfg = ifp->drvr->config;
 	s32 status;
 	struct brcmf_escan_result_le *escan_result_le;
+	u32 escan_buflen;
 	struct brcmf_bss_info_le *bss_info_le;
 	struct brcmf_bss_info_le *bss = NULL;
 	u32 bi_length;
@@ -3181,11 +3182,23 @@ brcmf_cfg80211_escan_handler(struct brcmf_if *ifp,
 
 	if (status == BRCMF_E_STATUS_PARTIAL) {
 		brcmf_dbg(SCAN, "ESCAN Partial result\n");
+		if (e->datalen < sizeof(*escan_result_le)) {
+			brcmf_err("invalid event data length\n");
+			goto exit;
+		}
 		escan_result_le = (struct brcmf_escan_result_le *) data;
 		if (!escan_result_le) {
 			brcmf_err("Invalid escan result (NULL pointer)\n");
 			goto exit;
 		}
+		escan_buflen = le32_to_cpu(escan_result_le->buflen);
+		if (escan_buflen > BRCMF_ESCAN_BUF_SIZE ||
+		    escan_buflen > e->datalen ||
+		    escan_buflen < sizeof(*escan_result_le)) {
+			brcmf_err("Invalid escan buffer length: %d\n",
+				  escan_buflen);
+			goto exit;
+		}
 		if (le16_to_cpu(escan_result_le->bss_count) != 1) {
 			brcmf_err("Invalid bss_count %d: ignoring\n",
 				  escan_result_le->bss_count);
@@ -3202,9 +3215,8 @@ brcmf_cfg80211_escan_handler(struct brcmf_if *ifp,
 		}
 
 		bi_length = le32_to_cpu(bss_info_le->length);
-		if (bi_length != (le32_to_cpu(escan_result_le->buflen) -
-					WL_ESCAN_RESULTS_FIXED_SIZE)) {
-			brcmf_err("Invalid bss_info length %d: ignoring\n",
+		if (bi_length != escan_buflen -	WL_ESCAN_RESULTS_FIXED_SIZE) {
+			brcmf_err("Ignoring invalid bss_info length: %d\n",
 				  bi_length);
 			goto exit;
 		}
-- 
cgit v1.2.3


From 35f62727df0ed8e5e4857e162d94fd46d861f1cf Mon Sep 17 00:00:00 2001
From: Arend Van Spriel <arend.vanspriel@broadcom.com>
Date: Tue, 12 Sep 2017 10:47:54 +0200
Subject: brcmfmac: setup passive scan if requested by user-space

The driver was not properly configuring firmware with regard to the
type of scan. It always performed an active scan even when user-space
was requesting for passive scan, ie. the scan request was done without
any SSIDs specified.

Cc: stable@vger.kernel.org # v4.0.x
Reported-by: Huang, Jiangyang <Jiangyang.Huang@itron.com>
Reviewed-by: Hante Meuleman <hante.meuleman@broadcom.com>
Reviewed-by: Pieter-Paul Giesberts <pieter-paul.giesberts@broadcom.com>
Reviewed-by: Franky Lin <franky.lin@broadcom.com>
Signed-off-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../wireless/broadcom/brcm80211/brcmfmac/cfg80211.c   | 19 ++++---------------
 .../wireless/broadcom/brcm80211/brcmfmac/fwil_types.h |  5 +++++
 2 files changed, 9 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 26a0de371c26..4157c90ad973 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -980,7 +980,7 @@ static void brcmf_escan_prep(struct brcmf_cfg80211_info *cfg,
 
 	eth_broadcast_addr(params_le->bssid);
 	params_le->bss_type = DOT11_BSSTYPE_ANY;
-	params_le->scan_type = 0;
+	params_le->scan_type = BRCMF_SCANTYPE_ACTIVE;
 	params_le->channel_num = 0;
 	params_le->nprobes = cpu_to_le32(-1);
 	params_le->active_time = cpu_to_le32(-1);
@@ -988,12 +988,9 @@ static void brcmf_escan_prep(struct brcmf_cfg80211_info *cfg,
 	params_le->home_time = cpu_to_le32(-1);
 	memset(&params_le->ssid_le, 0, sizeof(params_le->ssid_le));
 
-	/* if request is null exit so it will be all channel broadcast scan */
-	if (!request)
-		return;
-
 	n_ssids = request->n_ssids;
 	n_channels = request->n_channels;
+
 	/* Copy channel array if applicable */
 	brcmf_dbg(SCAN, "### List of channelspecs to scan ### %d\n",
 		  n_channels);
@@ -1030,16 +1027,8 @@ static void brcmf_escan_prep(struct brcmf_cfg80211_info *cfg,
 			ptr += sizeof(ssid_le);
 		}
 	} else {
-		brcmf_dbg(SCAN, "Broadcast scan %p\n", request->ssids);
-		if ((request->ssids) && request->ssids->ssid_len) {
-			brcmf_dbg(SCAN, "SSID %s len=%d\n",
-				  params_le->ssid_le.SSID,
-				  request->ssids->ssid_len);
-			params_le->ssid_le.SSID_len =
-				cpu_to_le32(request->ssids->ssid_len);
-			memcpy(&params_le->ssid_le.SSID, request->ssids->ssid,
-				request->ssids->ssid_len);
-		}
+		brcmf_dbg(SCAN, "Performing passive scan\n");
+		params_le->scan_type = BRCMF_SCANTYPE_PASSIVE;
 	}
 	/* Adding mask to channel numbers */
 	params_le->channel_num =
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
index 8391989b1882..e0d22fedb2b4 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
@@ -45,6 +45,11 @@
 #define BRCMF_SCAN_PARAMS_COUNT_MASK	0x0000ffff
 #define BRCMF_SCAN_PARAMS_NSSID_SHIFT	16
 
+/* scan type definitions */
+#define BRCMF_SCANTYPE_DEFAULT		0xFF
+#define BRCMF_SCANTYPE_ACTIVE		0
+#define BRCMF_SCANTYPE_PASSIVE		1
+
 #define BRCMF_WSEC_MAX_PSK_LEN		32
 #define	BRCMF_WSEC_PASSPHRASE		BIT(0)
 
-- 
cgit v1.2.3


From 20da2ec06bfad2d4dfd40d77d3831f5e56365d20 Mon Sep 17 00:00:00 2001
From: Sergey Matyukevich <sergey.matyukevich.os@quantenna.com>
Date: Mon, 18 Sep 2017 15:29:49 +0300
Subject: qtnfmac: lock access to h/w in tx path

Fix tx path regression. Lock should be held when queuing packets
to h/w fifos in order to properly handle configurations with
multiple enabled interfaces.

Signed-off-by: Sergey Matyukevich <sergey.matyukevich.os@quantenna.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/quantenna/qtnfmac/pearl/pcie.c          | 9 ++++++++-
 drivers/net/wireless/quantenna/qtnfmac/pearl/pcie_bus_priv.h | 2 ++
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie.c b/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie.c
index 502e72b7cdcc..69131965a298 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie.c
@@ -661,14 +661,18 @@ static int qtnf_pcie_data_tx(struct qtnf_bus *bus, struct sk_buff *skb)
 	struct qtnf_pcie_bus_priv *priv = (void *)get_bus_priv(bus);
 	dma_addr_t txbd_paddr, skb_paddr;
 	struct qtnf_tx_bd *txbd;
+	unsigned long flags;
 	int len, i;
 	u32 info;
 	int ret = 0;
 
+	spin_lock_irqsave(&priv->tx0_lock, flags);
+
 	if (!qtnf_tx_queue_ready(priv)) {
 		if (skb->dev)
 			netif_stop_queue(skb->dev);
 
+		spin_unlock_irqrestore(&priv->tx0_lock, flags);
 		return NETDEV_TX_BUSY;
 	}
 
@@ -717,8 +721,10 @@ tx_done:
 		dev_kfree_skb_any(skb);
 	}
 
-	qtnf_pcie_data_tx_reclaim(priv);
 	priv->tx_done_count++;
+	spin_unlock_irqrestore(&priv->tx0_lock, flags);
+
+	qtnf_pcie_data_tx_reclaim(priv);
 
 	return NETDEV_TX_OK;
 }
@@ -1247,6 +1253,7 @@ static int qtnf_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	strcpy(bus->fwname, QTN_PCI_PEARL_FW_NAME);
 	init_completion(&bus->request_firmware_complete);
 	mutex_init(&bus->bus_lock);
+	spin_lock_init(&pcie_priv->tx0_lock);
 	spin_lock_init(&pcie_priv->irq_lock);
 	spin_lock_init(&pcie_priv->tx_reclaim_lock);
 
diff --git a/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie_bus_priv.h b/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie_bus_priv.h
index e76a23716ee0..86ac1ccedb52 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie_bus_priv.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie_bus_priv.h
@@ -34,6 +34,8 @@ struct qtnf_pcie_bus_priv {
 
 	/* lock for tx reclaim operations */
 	spinlock_t tx_reclaim_lock;
+	/* lock for tx0 operations */
+	spinlock_t tx0_lock;
 	u8 msi_enabled;
 	int mps;
 
-- 
cgit v1.2.3


From a715b3a0efe76d36c3ef96a93894a13db9d3a72f Mon Sep 17 00:00:00 2001
From: Sergey Matyukevich <sergey.matyukevich.os@quantenna.com>
Date: Mon, 18 Sep 2017 15:29:50 +0300
Subject: qtnfmac: cancel scans on wireless interface changes

Cancel active scans and deactivate firmware scan watchdog timer
when wireless interface configuration is changed. The usecases
include wireless interface mode change, interface down,
AP stop, virtual interface removal.

Signed-off-by: Sergey Matyukevich <sergey.matyukevich.os@quantenna.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/quantenna/qtnfmac/cfg80211.c | 9 ++++++---
 drivers/net/wireless/quantenna/qtnfmac/cfg80211.h | 3 +++
 drivers/net/wireless/quantenna/qtnfmac/event.c    | 2 --
 3 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
index 856fa6e8327e..a450bc6bc774 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
@@ -115,6 +115,8 @@ int qtnf_del_virtual_intf(struct wiphy *wiphy, struct wireless_dev *wdev)
 
 	vif = qtnf_netdev_get_priv(wdev->netdev);
 
+	qtnf_scan_done(vif->mac, true);
+
 	if (qtnf_cmd_send_del_intf(vif))
 		pr_err("VIF%u.%u: failed to delete VIF\n", vif->mac->macid,
 		       vif->vifid);
@@ -335,6 +337,8 @@ static int qtnf_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 	struct qtnf_vif *vif = qtnf_netdev_get_priv(dev);
 	int ret;
 
+	qtnf_scan_done(vif->mac, true);
+
 	ret = qtnf_cmd_send_stop_ap(vif);
 	if (ret) {
 		pr_err("VIF%u.%u: failed to stop AP operation in FW\n",
@@ -570,8 +574,6 @@ qtnf_del_station(struct wiphy *wiphy, struct net_device *dev,
 	    !qtnf_sta_list_lookup(&vif->sta_list, params->mac))
 		return 0;
 
-	qtnf_scan_done(vif->mac, true);
-
 	ret = qtnf_cmd_send_del_sta(vif, params);
 	if (ret)
 		pr_err("VIF%u.%u: failed to delete STA %pM\n",
@@ -1134,8 +1136,9 @@ void qtnf_virtual_intf_cleanup(struct net_device *ndev)
 		}
 
 		vif->sta_state = QTNF_STA_DISCONNECTED;
-		qtnf_scan_done(mac, true);
 	}
+
+	qtnf_scan_done(mac, true);
 }
 
 void qtnf_cfg80211_vif_reset(struct qtnf_vif *vif)
diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.h b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.h
index 6a4af52522b8..66db26613b1f 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.h
@@ -34,6 +34,9 @@ static inline void qtnf_scan_done(struct qtnf_wmac *mac, bool aborted)
 		.aborted = aborted,
 	};
 
+	if (timer_pending(&mac->scan_timeout))
+		del_timer_sync(&mac->scan_timeout);
+
 	mutex_lock(&mac->mac_lock);
 
 	if (mac->scan_req) {
diff --git a/drivers/net/wireless/quantenna/qtnfmac/event.c b/drivers/net/wireless/quantenna/qtnfmac/event.c
index 0fc2814eafad..43d2e7fd6e02 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/event.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/event.c
@@ -345,8 +345,6 @@ qtnf_event_handle_scan_complete(struct qtnf_wmac *mac,
 		return -EINVAL;
 	}
 
-	if (timer_pending(&mac->scan_timeout))
-		del_timer_sync(&mac->scan_timeout);
 	qtnf_scan_done(mac, le32_to_cpu(status->flags) & QLINK_SCAN_ABORTED);
 
 	return 0;
-- 
cgit v1.2.3


From 6af1de2e4ec49635905aaed31d073a0d92c8d3bf Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 6 Sep 2017 14:58:53 +0200
Subject: ath10k: mark PM functions as __maybe_unused

When CONFIG_PM_SLEEP is disabled, we get a compile-time
warning:

drivers/net/wireless/ath/ath10k/pci.c:3417:12: error: 'ath10k_pci_pm_resume' defined but not used [-Werror=unused-function]
 static int ath10k_pci_pm_resume(struct device *dev)
            ^~~~~~~~~~~~~~~~~~~~
drivers/net/wireless/ath/ath10k/pci.c:3401:12: error: 'ath10k_pci_pm_suspend' defined but not used [-Werror=unused-function]
 static int ath10k_pci_pm_suspend(struct device *dev)

Rather than fixing the #ifdef, this just marks both functions
as __maybe_unused, which is a more robust way to do this.

Fixes: 32faa3f0ee50 ("ath10k: add the PCI PM core suspend/resume ops")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Kalle Valo <kvalo@qca.qualcomm.com>
---
 drivers/net/wireless/ath/ath10k/pci.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c
index bc1633945a56..195dafb98131 100644
--- a/drivers/net/wireless/ath/ath10k/pci.c
+++ b/drivers/net/wireless/ath/ath10k/pci.c
@@ -3396,9 +3396,7 @@ static void ath10k_pci_remove(struct pci_dev *pdev)
 
 MODULE_DEVICE_TABLE(pci, ath10k_pci_id_table);
 
-#ifdef CONFIG_PM
-
-static int ath10k_pci_pm_suspend(struct device *dev)
+static __maybe_unused int ath10k_pci_pm_suspend(struct device *dev)
 {
 	struct ath10k *ar = dev_get_drvdata(dev);
 	int ret;
@@ -3414,7 +3412,7 @@ static int ath10k_pci_pm_suspend(struct device *dev)
 	return ret;
 }
 
-static int ath10k_pci_pm_resume(struct device *dev)
+static __maybe_unused int ath10k_pci_pm_resume(struct device *dev)
 {
 	struct ath10k *ar = dev_get_drvdata(dev);
 	int ret;
@@ -3433,7 +3431,6 @@ static int ath10k_pci_pm_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(ath10k_pci_pm_ops,
 			 ath10k_pci_pm_suspend,
 			 ath10k_pci_pm_resume);
-#endif
 
 static struct pci_driver ath10k_pci_driver = {
 	.name = "ath10k_pci",
-- 
cgit v1.2.3


From 05cf97e7a619fc7ede81ee6bb8ebfa7531b633f5 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Fri, 22 Sep 2017 01:01:11 +0200
Subject: cnic: Fix an error handling path in 'cnic_alloc_bnx2x_resc()'

All the error handling paths 'goto error', except this one.
We should also go to error in this case, or some resources will be
leaking.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/cnic.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index cec94bbb2ea5..8bc126a156e8 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -1278,7 +1278,7 @@ static int cnic_alloc_bnx2x_resc(struct cnic_dev *dev)
 
 	ret = cnic_alloc_dma(dev, kwq_16_dma, pages, 0);
 	if (ret)
-		return -ENOMEM;
+		goto error;
 
 	n = CNIC_PAGE_SIZE / CNIC_KWQ16_DATA_SIZE;
 	for (i = 0, j = 0; i < cp->max_cid_space; i++) {
-- 
cgit v1.2.3


From 5c346525d3591cb032eca86d0f904cc01f1069ff Mon Sep 17 00:00:00 2001
From: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Date: Thu, 21 Sep 2017 18:00:36 -0600
Subject: net: qualcomm: rmnet: Fix rcu splat in rmnet_is_real_dev_registered

Xiaolong reported a suspicious rcu_dereference_check in the device
unregister notifier callback. Since we do not dereference the
rx_handler_data, it's ok to just check for the value of the pointer.
Note that this section is already protected by rtnl_lock.

[  101.364846] WARNING: suspicious RCU usage
[  101.365654] 4.13.0-rc6-01701-gceed73a #1 Not tainted
[  101.370873] -----------------------------
[  101.372472] drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c:57 suspicious rcu_dereference_check() usage!
[  101.374427]
[  101.374427] other info that might help us debug this:
[  101.374427]
[  101.387491]
[  101.387491] rcu_scheduler_active = 2, debug_locks = 1
[  101.389368] 1 lock held by trinity-main/2809:
[  101.390736]  #0:  (rtnl_mutex){+.+.+.}, at: [<8146085b>] rtnl_lock+0xf/0x11
[  101.395482]
[  101.395482] stack backtrace:
[  101.396948] CPU: 0 PID: 2809 Comm: trinity-main Not tainted 4.13.0-rc6-01701-gceed73a #1
[  101.398857] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.9.3-20161025_171302-gandalf 04/01/2014
[  101.401079] Call Trace:
[  101.401656]  dump_stack+0xa1/0xeb
[  101.402871]  lockdep_rcu_suspicious+0xc7/0xd0
[  101.403665]  rmnet_is_real_dev_registered+0x40/0x4e
[  101.405199]  rmnet_config_notify_cb+0x2c/0x142
[  101.406344]  ? wireless_nlevent_flush+0x47/0x71
[  101.407385]  notifier_call_chain+0x2d/0x47
[  101.408645]  raw_notifier_call_chain+0xc/0xe
[  101.409882]  call_netdevice_notifiers_info+0x41/0x49
[  101.411402]  call_netdevice_notifiers+0xc/0xe
[  101.412713]  rollback_registered_many+0x268/0x36e
[  101.413702]  rollback_registered+0x39/0x56
[  101.414965]  unregister_netdevice_queue+0x79/0x88
[  101.415908]  unregister_netdev+0x16/0x1d

Fixes: ceed73a2cf4a ("drivers: net: ethernet: qualcomm: rmnet: Initial implementation")
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Reported-by: kernel test robot <xiaolong.ye@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 98f22551eb45..1e33aea59f50 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -51,10 +51,7 @@ struct rmnet_walk_data {
 
 static int rmnet_is_real_dev_registered(const struct net_device *real_dev)
 {
-	rx_handler_func_t *rx_handler;
-
-	rx_handler = rcu_dereference(real_dev->rx_handler);
-	return (rx_handler == rmnet_rx_handler);
+	return rcu_access_pointer(real_dev->rx_handler) == rmnet_rx_handler;
 }
 
 /* Needs rtnl lock */
-- 
cgit v1.2.3


From cdd10c9627496ad25c87ce6394e29752253c69d3 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 22 Sep 2017 15:39:23 +0200
Subject: l2tp: ensure sessions are freed after their PPPOL2TP socket

If l2tp_tunnel_delete() or l2tp_tunnel_closeall() deletes a session
right after pppol2tp_release() orphaned its socket, then the 'sock'
variable of the pppol2tp_session_close() callback is NULL. Yet the
session is still used by pppol2tp_release().

Therefore we need to take an extra reference in any case, to prevent
l2tp_tunnel_delete() or l2tp_tunnel_closeall() from freeing the session.

Since the pppol2tp_session_close() callback is only set if the session
is associated to a PPPOL2TP socket and that both l2tp_tunnel_delete()
and l2tp_tunnel_closeall() hold the PPPOL2TP socket before calling
pppol2tp_session_close(), we're sure that pppol2tp_session_close() and
pppol2tp_session_destruct() are paired and called in the right order.
So the reference taken by the former will be released by the later.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 50e3ee9a9d61..bc6e8bfc5be4 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -437,11 +437,11 @@ static void pppol2tp_session_close(struct l2tp_session *session)
 
 	BUG_ON(session->magic != L2TP_SESSION_MAGIC);
 
-	if (sock) {
+	if (sock)
 		inet_shutdown(sock, SEND_SHUTDOWN);
-		/* Don't let the session go away before our socket does */
-		l2tp_session_inc_refcount(session);
-	}
+
+	/* Don't let the session go away before our socket does */
+	l2tp_session_inc_refcount(session);
 }
 
 /* Really kill the session socket. (Called from sock_put() if
-- 
cgit v1.2.3


From b228a94066406b6c456321d69643b0d7ce11cfa6 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 22 Sep 2017 15:39:24 +0200
Subject: l2tp: fix race between l2tp_session_delete() and
 l2tp_tunnel_closeall()

There are several ways to remove L2TP sessions:

  * deleting a session explicitly using the netlink interface (with
    L2TP_CMD_SESSION_DELETE),
  * deleting the session's parent tunnel (either by closing the
    tunnel's file descriptor or using the netlink interface),
  * closing the PPPOL2TP file descriptor of a PPP pseudo-wire.

In some cases, when these methods are used concurrently on the same
session, the session can be removed twice, leading to use-after-free
bugs.

This patch adds a 'dead' flag, used by l2tp_session_delete() and
l2tp_tunnel_closeall() to prevent them from stepping on each other's
toes.

The session deletion path used when closing a PPPOL2TP file descriptor
doesn't need to be adapted. It already has to ensure that a session
remains valid for the lifetime of its PPPOL2TP file descriptor.
So it takes an extra reference on the session in the ->session_close()
callback (pppol2tp_session_close()), which is eventually dropped
in the ->sk_destruct() callback of the PPPOL2TP socket
(pppol2tp_session_destruct()).
Still, __l2tp_session_unhash() and l2tp_session_queue_purge() can be
called twice and even concurrently for a given session, but thanks to
proper locking and re-initialisation of list fields, this is not an
issue.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 6 ++++++
 net/l2tp/l2tp_core.h | 1 +
 2 files changed, 7 insertions(+)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index ee485df73ccd..d8c2a89a76e1 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1314,6 +1314,9 @@ again:
 
 			hlist_del_init(&session->hlist);
 
+			if (test_and_set_bit(0, &session->dead))
+				goto again;
+
 			if (session->ref != NULL)
 				(*session->ref)(session);
 
@@ -1750,6 +1753,9 @@ EXPORT_SYMBOL_GPL(__l2tp_session_unhash);
  */
 int l2tp_session_delete(struct l2tp_session *session)
 {
+	if (test_and_set_bit(0, &session->dead))
+		return 0;
+
 	if (session->ref)
 		(*session->ref)(session);
 	__l2tp_session_unhash(session);
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index a305e0c5925a..70a12df40a5f 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -76,6 +76,7 @@ struct l2tp_session_cfg {
 struct l2tp_session {
 	int			magic;		/* should be
 						 * L2TP_SESSION_MAGIC */
+	long			dead;
 
 	struct l2tp_tunnel	*tunnel;	/* back pointer to tunnel
 						 * context */
-- 
cgit v1.2.3


From a93ad944f4ff9a797abff17c73fc4b1e4a1d9141 Mon Sep 17 00:00:00 2001
From: Timur Tabi <timur@codeaurora.org>
Date: Fri, 22 Sep 2017 15:32:44 -0500
Subject: net: qcom/emac: specify the correct size when mapping a DMA buffer

When mapping the RX DMA buffers, the driver was accidentally specifying
zero for the buffer length.  Under normal circumstances, SWIOTLB does not
need to allocate a bounce buffer, so the address is just mapped without
checking the size field.  This is why the error was not detected earlier.

Fixes: b9b17debc69d ("net: emac: emac gigabit ethernet controller driver")
Cc: stable@vger.kernel.org
Signed-off-by: Timur Tabi <timur@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/emac/emac-mac.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
index 0ea3ca09c689..3ed9033e56db 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
@@ -898,7 +898,8 @@ static void emac_mac_rx_descs_refill(struct emac_adapter *adpt,
 
 		curr_rxbuf->dma_addr =
 			dma_map_single(adpt->netdev->dev.parent, skb->data,
-				       curr_rxbuf->length, DMA_FROM_DEVICE);
+				       adpt->rxbuf_size, DMA_FROM_DEVICE);
+
 		ret = dma_mapping_error(adpt->netdev->dev.parent,
 					curr_rxbuf->dma_addr);
 		if (ret) {
-- 
cgit v1.2.3


From 6098d7ddd62f532f80ee2a4b01aca500a8e4e9e4 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 22 Sep 2017 23:29:18 +0200
Subject: rocker: fix rocker_tlv_put_* functions for KASAN

Inlining these functions creates lots of stack variables that each take
64 bytes when KASAN is enabled, leading to this warning about potential
stack overflow:

drivers/net/ethernet/rocker/rocker_ofdpa.c: In function 'ofdpa_cmd_flow_tbl_add':
drivers/net/ethernet/rocker/rocker_ofdpa.c:621:1: error: the frame size of 2752 bytes is larger than 1536 bytes [-Werror=frame-larger-than=]

gcc-8 can now consolidate the stack slots itself, but on older versions
we get the same behavior by using a temporary variable that holds a
copy of the inline function argument.

Cc: stable@vger.kernel.org
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81715
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/rocker/rocker_tlv.h | 48 ++++++++++++++++++++------------
 1 file changed, 30 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/rocker/rocker_tlv.h b/drivers/net/ethernet/rocker/rocker_tlv.h
index a63ef82e7c72..dfae3c9d57c6 100644
--- a/drivers/net/ethernet/rocker/rocker_tlv.h
+++ b/drivers/net/ethernet/rocker/rocker_tlv.h
@@ -139,40 +139,52 @@ rocker_tlv_start(struct rocker_desc_info *desc_info)
 int rocker_tlv_put(struct rocker_desc_info *desc_info,
 		   int attrtype, int attrlen, const void *data);
 
-static inline int rocker_tlv_put_u8(struct rocker_desc_info *desc_info,
-				    int attrtype, u8 value)
+static inline int
+rocker_tlv_put_u8(struct rocker_desc_info *desc_info, int attrtype, u8 value)
 {
-	return rocker_tlv_put(desc_info, attrtype, sizeof(u8), &value);
+	u8 tmp = value; /* work around GCC PR81715 */
+
+	return rocker_tlv_put(desc_info, attrtype, sizeof(u8), &tmp);
 }
 
-static inline int rocker_tlv_put_u16(struct rocker_desc_info *desc_info,
-				     int attrtype, u16 value)
+static inline int
+rocker_tlv_put_u16(struct rocker_desc_info *desc_info, int attrtype, u16 value)
 {
-	return rocker_tlv_put(desc_info, attrtype, sizeof(u16), &value);
+	u16 tmp = value;
+
+	return rocker_tlv_put(desc_info, attrtype, sizeof(u16), &tmp);
 }
 
-static inline int rocker_tlv_put_be16(struct rocker_desc_info *desc_info,
-				      int attrtype, __be16 value)
+static inline int
+rocker_tlv_put_be16(struct rocker_desc_info *desc_info, int attrtype, __be16 value)
 {
-	return rocker_tlv_put(desc_info, attrtype, sizeof(__be16), &value);
+	__be16 tmp = value;
+
+	return rocker_tlv_put(desc_info, attrtype, sizeof(__be16), &tmp);
 }
 
-static inline int rocker_tlv_put_u32(struct rocker_desc_info *desc_info,
-				     int attrtype, u32 value)
+static inline int
+rocker_tlv_put_u32(struct rocker_desc_info *desc_info, int attrtype, u32 value)
 {
-	return rocker_tlv_put(desc_info, attrtype, sizeof(u32), &value);
+	u32 tmp = value;
+
+	return rocker_tlv_put(desc_info, attrtype, sizeof(u32), &tmp);
 }
 
-static inline int rocker_tlv_put_be32(struct rocker_desc_info *desc_info,
-				      int attrtype, __be32 value)
+static inline int
+rocker_tlv_put_be32(struct rocker_desc_info *desc_info, int attrtype, __be32 value)
 {
-	return rocker_tlv_put(desc_info, attrtype, sizeof(__be32), &value);
+	__be32 tmp = value;
+
+	return rocker_tlv_put(desc_info, attrtype, sizeof(__be32), &tmp);
 }
 
-static inline int rocker_tlv_put_u64(struct rocker_desc_info *desc_info,
-				     int attrtype, u64 value)
+static inline int
+rocker_tlv_put_u64(struct rocker_desc_info *desc_info, int attrtype, u64 value)
 {
-	return rocker_tlv_put(desc_info, attrtype, sizeof(u64), &value);
+	u64 tmp = value;
+
+	return rocker_tlv_put(desc_info, attrtype, sizeof(u64), &tmp);
 }
 
 static inline struct rocker_tlv *
-- 
cgit v1.2.3


From b4391db42308c9940944b5d7be5ca4b78fb88dd0 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 22 Sep 2017 23:29:19 +0200
Subject: netlink: fix nla_put_{u8,u16,u32} for KASAN

When CONFIG_KASAN is enabled, the "--param asan-stack=1" causes rather large
stack frames in some functions. This goes unnoticed normally because
CONFIG_FRAME_WARN is disabled with CONFIG_KASAN by default as of commit
3f181b4d8652 ("lib/Kconfig.debug: disable -Wframe-larger-than warnings with
KASAN=y").

The kernelci.org build bot however has the warning enabled and that led
me to investigate it a little further, as every build produces these warnings:

net/wireless/nl80211.c:4389:1: warning: the frame size of 2240 bytes is larger than 2048 bytes [-Wframe-larger-than=]
net/wireless/nl80211.c:1895:1: warning: the frame size of 3776 bytes is larger than 2048 bytes [-Wframe-larger-than=]
net/wireless/nl80211.c:1410:1: warning: the frame size of 2208 bytes is larger than 2048 bytes [-Wframe-larger-than=]
net/bridge/br_netlink.c:1282:1: warning: the frame size of 2544 bytes is larger than 2048 bytes [-Wframe-larger-than=]

Most of this problem is now solved in gcc-8, which can consolidate
the stack slots for the inline function arguments. On older compilers
we can add a workaround by declaring a local variable in each function
to pass the inline function argument.

Cc: stable@vger.kernel.org
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81715
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netlink.h | 73 ++++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 55 insertions(+), 18 deletions(-)

diff --git a/include/net/netlink.h b/include/net/netlink.h
index e51cf5f81597..14c289393071 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -773,7 +773,10 @@ static inline int nla_parse_nested(struct nlattr *tb[], int maxtype,
  */
 static inline int nla_put_u8(struct sk_buff *skb, int attrtype, u8 value)
 {
-	return nla_put(skb, attrtype, sizeof(u8), &value);
+	/* temporary variables to work around GCC PR81715 with asan-stack=1 */
+	u8 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(u8), &tmp);
 }
 
 /**
@@ -784,7 +787,9 @@ static inline int nla_put_u8(struct sk_buff *skb, int attrtype, u8 value)
  */
 static inline int nla_put_u16(struct sk_buff *skb, int attrtype, u16 value)
 {
-	return nla_put(skb, attrtype, sizeof(u16), &value);
+	u16 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(u16), &tmp);
 }
 
 /**
@@ -795,7 +800,9 @@ static inline int nla_put_u16(struct sk_buff *skb, int attrtype, u16 value)
  */
 static inline int nla_put_be16(struct sk_buff *skb, int attrtype, __be16 value)
 {
-	return nla_put(skb, attrtype, sizeof(__be16), &value);
+	__be16 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(__be16), &tmp);
 }
 
 /**
@@ -806,7 +813,9 @@ static inline int nla_put_be16(struct sk_buff *skb, int attrtype, __be16 value)
  */
 static inline int nla_put_net16(struct sk_buff *skb, int attrtype, __be16 value)
 {
-	return nla_put_be16(skb, attrtype | NLA_F_NET_BYTEORDER, value);
+	__be16 tmp = value;
+
+	return nla_put_be16(skb, attrtype | NLA_F_NET_BYTEORDER, tmp);
 }
 
 /**
@@ -817,7 +826,9 @@ static inline int nla_put_net16(struct sk_buff *skb, int attrtype, __be16 value)
  */
 static inline int nla_put_le16(struct sk_buff *skb, int attrtype, __le16 value)
 {
-	return nla_put(skb, attrtype, sizeof(__le16), &value);
+	__le16 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(__le16), &tmp);
 }
 
 /**
@@ -828,7 +839,9 @@ static inline int nla_put_le16(struct sk_buff *skb, int attrtype, __le16 value)
  */
 static inline int nla_put_u32(struct sk_buff *skb, int attrtype, u32 value)
 {
-	return nla_put(skb, attrtype, sizeof(u32), &value);
+	u32 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(u32), &tmp);
 }
 
 /**
@@ -839,7 +852,9 @@ static inline int nla_put_u32(struct sk_buff *skb, int attrtype, u32 value)
  */
 static inline int nla_put_be32(struct sk_buff *skb, int attrtype, __be32 value)
 {
-	return nla_put(skb, attrtype, sizeof(__be32), &value);
+	__be32 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(__be32), &tmp);
 }
 
 /**
@@ -850,7 +865,9 @@ static inline int nla_put_be32(struct sk_buff *skb, int attrtype, __be32 value)
  */
 static inline int nla_put_net32(struct sk_buff *skb, int attrtype, __be32 value)
 {
-	return nla_put_be32(skb, attrtype | NLA_F_NET_BYTEORDER, value);
+	__be32 tmp = value;
+
+	return nla_put_be32(skb, attrtype | NLA_F_NET_BYTEORDER, tmp);
 }
 
 /**
@@ -861,7 +878,9 @@ static inline int nla_put_net32(struct sk_buff *skb, int attrtype, __be32 value)
  */
 static inline int nla_put_le32(struct sk_buff *skb, int attrtype, __le32 value)
 {
-	return nla_put(skb, attrtype, sizeof(__le32), &value);
+	__le32 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(__le32), &tmp);
 }
 
 /**
@@ -874,7 +893,9 @@ static inline int nla_put_le32(struct sk_buff *skb, int attrtype, __le32 value)
 static inline int nla_put_u64_64bit(struct sk_buff *skb, int attrtype,
 				    u64 value, int padattr)
 {
-	return nla_put_64bit(skb, attrtype, sizeof(u64), &value, padattr);
+	u64 tmp = value;
+
+	return nla_put_64bit(skb, attrtype, sizeof(u64), &tmp, padattr);
 }
 
 /**
@@ -887,7 +908,9 @@ static inline int nla_put_u64_64bit(struct sk_buff *skb, int attrtype,
 static inline int nla_put_be64(struct sk_buff *skb, int attrtype, __be64 value,
 			       int padattr)
 {
-	return nla_put_64bit(skb, attrtype, sizeof(__be64), &value, padattr);
+	__be64 tmp = value;
+
+	return nla_put_64bit(skb, attrtype, sizeof(__be64), &tmp, padattr);
 }
 
 /**
@@ -900,7 +923,9 @@ static inline int nla_put_be64(struct sk_buff *skb, int attrtype, __be64 value,
 static inline int nla_put_net64(struct sk_buff *skb, int attrtype, __be64 value,
 				int padattr)
 {
-	return nla_put_be64(skb, attrtype | NLA_F_NET_BYTEORDER, value,
+	__be64 tmp = value;
+
+	return nla_put_be64(skb, attrtype | NLA_F_NET_BYTEORDER, tmp,
 			    padattr);
 }
 
@@ -914,7 +939,9 @@ static inline int nla_put_net64(struct sk_buff *skb, int attrtype, __be64 value,
 static inline int nla_put_le64(struct sk_buff *skb, int attrtype, __le64 value,
 			       int padattr)
 {
-	return nla_put_64bit(skb, attrtype, sizeof(__le64), &value, padattr);
+	__le64 tmp = value;
+
+	return nla_put_64bit(skb, attrtype, sizeof(__le64), &tmp, padattr);
 }
 
 /**
@@ -925,7 +952,9 @@ static inline int nla_put_le64(struct sk_buff *skb, int attrtype, __le64 value,
  */
 static inline int nla_put_s8(struct sk_buff *skb, int attrtype, s8 value)
 {
-	return nla_put(skb, attrtype, sizeof(s8), &value);
+	s8 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(s8), &tmp);
 }
 
 /**
@@ -936,7 +965,9 @@ static inline int nla_put_s8(struct sk_buff *skb, int attrtype, s8 value)
  */
 static inline int nla_put_s16(struct sk_buff *skb, int attrtype, s16 value)
 {
-	return nla_put(skb, attrtype, sizeof(s16), &value);
+	s16 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(s16), &tmp);
 }
 
 /**
@@ -947,7 +978,9 @@ static inline int nla_put_s16(struct sk_buff *skb, int attrtype, s16 value)
  */
 static inline int nla_put_s32(struct sk_buff *skb, int attrtype, s32 value)
 {
-	return nla_put(skb, attrtype, sizeof(s32), &value);
+	s32 tmp = value;
+
+	return nla_put(skb, attrtype, sizeof(s32), &tmp);
 }
 
 /**
@@ -960,7 +993,9 @@ static inline int nla_put_s32(struct sk_buff *skb, int attrtype, s32 value)
 static inline int nla_put_s64(struct sk_buff *skb, int attrtype, s64 value,
 			      int padattr)
 {
-	return nla_put_64bit(skb, attrtype, sizeof(s64), &value, padattr);
+	s64 tmp = value;
+
+	return nla_put_64bit(skb, attrtype, sizeof(s64), &tmp, padattr);
 }
 
 /**
@@ -1010,7 +1045,9 @@ static inline int nla_put_msecs(struct sk_buff *skb, int attrtype,
 static inline int nla_put_in_addr(struct sk_buff *skb, int attrtype,
 				  __be32 addr)
 {
-	return nla_put_be32(skb, attrtype, addr);
+	__be32 tmp = addr;
+
+	return nla_put_be32(skb, attrtype, tmp);
 }
 
 /**
-- 
cgit v1.2.3


From 36f6ee22d2d66046e369757ec6bbe1c482957ba6 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Tue, 26 Sep 2017 15:14:29 +0300
Subject: vti: fix use after free in vti_tunnel_xmit/vti6_tnl_xmit

When running LTP IPsec tests, KASan might report:

BUG: KASAN: use-after-free in vti_tunnel_xmit+0xeee/0xff0 [ip_vti]
Read of size 4 at addr ffff880dc6ad1980 by task swapper/0/0
...
Call Trace:
  <IRQ>
  dump_stack+0x63/0x89
  print_address_description+0x7c/0x290
  kasan_report+0x28d/0x370
  ? vti_tunnel_xmit+0xeee/0xff0 [ip_vti]
  __asan_report_load4_noabort+0x19/0x20
  vti_tunnel_xmit+0xeee/0xff0 [ip_vti]
  ? vti_init_net+0x190/0x190 [ip_vti]
  ? save_stack_trace+0x1b/0x20
  ? save_stack+0x46/0xd0
  dev_hard_start_xmit+0x147/0x510
  ? icmp_echo.part.24+0x1f0/0x210
  __dev_queue_xmit+0x1394/0x1c60
...
Freed by task 0:
  save_stack_trace+0x1b/0x20
  save_stack+0x46/0xd0
  kasan_slab_free+0x70/0xc0
  kmem_cache_free+0x81/0x1e0
  kfree_skbmem+0xb1/0xe0
  kfree_skb+0x75/0x170
  kfree_skb_list+0x3e/0x60
  __dev_queue_xmit+0x1298/0x1c60
  dev_queue_xmit+0x10/0x20
  neigh_resolve_output+0x3a8/0x740
  ip_finish_output2+0x5c0/0xe70
  ip_finish_output+0x4ba/0x680
  ip_output+0x1c1/0x3a0
  xfrm_output_resume+0xc65/0x13d0
  xfrm_output+0x1e4/0x380
  xfrm4_output_finish+0x5c/0x70

Can be fixed if we get skb->len before dst_output().

Fixes: b9959fd3b0fa ("vti: switch to new ip tunnel code")
Fixes: 22e1b23dafa8 ("vti6: Support inter address family tunneling.")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_vti.c  | 3 ++-
 net/ipv6/ip6_vti.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 5ed63d250950..89453cf62158 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -168,6 +168,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 	struct ip_tunnel_parm *parms = &tunnel->parms;
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *tdev;	/* Device to other host */
+	int pkt_len = skb->len;
 	int err;
 	int mtu;
 
@@ -229,7 +230,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	err = dst_output(tunnel->net, skb->sk, skb);
 	if (net_xmit_eval(err) == 0)
-		err = skb->len;
+		err = pkt_len;
 	iptunnel_xmit_stats(dev, err);
 	return NETDEV_TX_OK;
 
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 79444a4bfd6d..bcdc2d557de1 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -445,6 +445,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *tdev;
 	struct xfrm_state *x;
+	int pkt_len = skb->len;
 	int err = -1;
 	int mtu;
 
@@ -502,7 +503,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 		struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
 
 		u64_stats_update_begin(&tstats->syncp);
-		tstats->tx_bytes += skb->len;
+		tstats->tx_bytes += pkt_len;
 		tstats->tx_packets++;
 		u64_stats_update_end(&tstats->syncp);
 	} else {
-- 
cgit v1.2.3


From 62b982eeb4589b2e6d7c01a90590e3a4c2b2ca19 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 26 Sep 2017 16:16:43 +0200
Subject: l2tp: fix race condition in l2tp_tunnel_delete

If we try to delete the same tunnel twice, the first delete operation
does a lookup (l2tp_tunnel_get), finds the tunnel, calls
l2tp_tunnel_delete, which queues it for deletion by
l2tp_tunnel_del_work.

The second delete operation also finds the tunnel and calls
l2tp_tunnel_delete. If the workqueue has already fired and started
running l2tp_tunnel_del_work, then l2tp_tunnel_delete will queue the
same tunnel a second time, and try to free the socket again.

Add a dead flag to prevent firing the workqueue twice. Then we can
remove the check of queue_work's result that was meant to prevent that
race but doesn't.

Reproducer:

    ip l2tp add tunnel tunnel_id 3000 peer_tunnel_id 4000 local 192.168.0.2 remote 192.168.0.1 encap udp udp_sport 5000 udp_dport 6000
    ip l2tp add session name l2tp1 tunnel_id 3000 session_id 1000 peer_session_id 2000
    ip link set l2tp1 up
    ip l2tp del tunnel tunnel_id 3000
    ip l2tp del tunnel tunnel_id 3000

Fixes: f8ccac0e4493 ("l2tp: put tunnel socket release on a workqueue")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 10 ++++------
 net/l2tp/l2tp_core.h |  5 ++++-
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index d8c2a89a76e1..02d61101b108 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1688,14 +1688,12 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create);
 
 /* This function is used by the netlink TUNNEL_DELETE command.
  */
-int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
+void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
 {
-	l2tp_tunnel_inc_refcount(tunnel);
-	if (false == queue_work(l2tp_wq, &tunnel->del_work)) {
-		l2tp_tunnel_dec_refcount(tunnel);
-		return 1;
+	if (!test_and_set_bit(0, &tunnel->dead)) {
+		l2tp_tunnel_inc_refcount(tunnel);
+		queue_work(l2tp_wq, &tunnel->del_work);
 	}
-	return 0;
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_delete);
 
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 70a12df40a5f..67c79d9b5c6c 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -161,6 +161,9 @@ struct l2tp_tunnel_cfg {
 
 struct l2tp_tunnel {
 	int			magic;		/* Should be L2TP_TUNNEL_MAGIC */
+
+	unsigned long		dead;
+
 	struct rcu_head rcu;
 	rwlock_t		hlist_lock;	/* protect session_hlist */
 	bool			acpt_newsess;	/* Indicates whether this
@@ -255,7 +258,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id,
 		       u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg,
 		       struct l2tp_tunnel **tunnelp);
 void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel);
-int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel);
+void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel);
 struct l2tp_session *l2tp_session_create(int priv_size,
 					 struct l2tp_tunnel *tunnel,
 					 u32 session_id, u32 peer_session_id,
-- 
cgit v1.2.3


From d85fc17beeb06f9979d63fe4d9fbffbb1a00bba4 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <igor.russkikh@aquantia.com>
Date: Mon, 25 Sep 2017 10:48:47 +0300
Subject: aquantia: Setup max_mtu in ndev to enable jumbo frames

Although hardware is capable for almost 16K MTU, without max_mtu field
correctly set it only allows standard MTU to be used.
This patch enables max MTU, calculating it from hardware maximum frame size
of 16352 octets (including FCS).

Fixes: 5513e16421cb ("net: ethernet: aquantia: Fixes for aq_ndev_change_mtu")

Signed-off-by: Pavel Belous <Pavel.Belous@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c               | 11 ++---------
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h    |  2 +-
 2 files changed, 3 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 6ac9e2602d6d..bf26a59a9d8e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -214,7 +214,6 @@ struct aq_nic_s *aq_nic_alloc_cold(const struct net_device_ops *ndev_ops,
 	SET_NETDEV_DEV(ndev, dev);
 
 	ndev->if_port = port;
-	ndev->min_mtu = ETH_MIN_MTU;
 	self->ndev = ndev;
 
 	self->aq_pci_func = aq_pci_func;
@@ -283,6 +282,7 @@ int aq_nic_ndev_init(struct aq_nic_s *self)
 	self->ndev->features = aq_hw_caps->hw_features;
 	self->ndev->priv_flags = aq_hw_caps->hw_priv_flags;
 	self->ndev->mtu = aq_nic_cfg->mtu - ETH_HLEN;
+	self->ndev->max_mtu = self->aq_hw_caps.mtu - ETH_FCS_LEN - ETH_HLEN;
 
 	return 0;
 }
@@ -693,16 +693,9 @@ int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev)
 
 int aq_nic_set_mtu(struct aq_nic_s *self, int new_mtu)
 {
-	int err = 0;
-
-	if (new_mtu > self->aq_hw_caps.mtu) {
-		err = -EINVAL;
-		goto err_exit;
-	}
 	self->aq_nic_cfg.mtu = new_mtu;
 
-err_exit:
-	return err;
+	return 0;
 }
 
 int aq_nic_set_mac(struct aq_nic_s *self, struct net_device *ndev)
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
index f3957e930340..fcf89e25a773 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
@@ -16,7 +16,7 @@
 
 #include "../aq_common.h"
 
-#define HW_ATL_B0_MTU_JUMBO (16000U)
+#define HW_ATL_B0_MTU_JUMBO  16352U
 #define HW_ATL_B0_MTU        1514U
 
 #define HW_ATL_B0_TX_RINGS 4U
-- 
cgit v1.2.3


From 3aec6412e007b294d4c135f5c7ed5e5ecf37dd2e Mon Sep 17 00:00:00 2001
From: Igor Russkikh <igor.russkikh@aquantia.com>
Date: Mon, 25 Sep 2017 10:48:48 +0300
Subject: aquantia: Fix Tx queue hangups

Driver did a poor job in managing its Tx queues: Sometimes it could stop
tx queues due to link down condition in aq_nic_xmit - but never waked up
them. That led to Tx path total suspend.
This patch fixes this and improves generic queue management:
- introduces queue restart counter
- uses generic netif_ interface to disable and enable tx path
- refactors link up/down condition and introduces dmesg log event when
  link changes.
- introduces new constant for minimum descriptors count required for queue
  wakeup

Signed-off-by: Pavel Belous <Pavel.Belous@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_cfg.h  |  4 ++
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c  | 91 +++++++++++-------------
 drivers/net/ethernet/aquantia/atlantic/aq_nic.h  |  2 -
 drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 26 +++++++
 drivers/net/ethernet/aquantia/atlantic/aq_ring.h |  4 ++
 drivers/net/ethernet/aquantia/atlantic/aq_vec.c  |  8 +--
 6 files changed, 76 insertions(+), 59 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
index 214986436ece..0fdaaa643073 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
@@ -51,6 +51,10 @@
 
 #define AQ_CFG_SKB_FRAGS_MAX   32U
 
+/* Number of descriptors available in one ring to resume this ring queue
+ */
+#define AQ_CFG_RESTART_DESC_THRES   (AQ_CFG_SKB_FRAGS_MAX * 2)
+
 #define AQ_CFG_NAPI_WEIGHT     64U
 
 #define AQ_CFG_MULTICAST_ADDRESS_MAX     32U
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index bf26a59a9d8e..072a55029f04 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -119,6 +119,35 @@ int aq_nic_cfg_start(struct aq_nic_s *self)
 	return 0;
 }
 
+static int aq_nic_update_link_status(struct aq_nic_s *self)
+{
+	int err = self->aq_hw_ops.hw_get_link_status(self->aq_hw);
+
+	if (err)
+		return err;
+
+	if (self->link_status.mbps != self->aq_hw->aq_link_status.mbps)
+		pr_info("%s: link change old %d new %d\n",
+			AQ_CFG_DRV_NAME, self->link_status.mbps,
+			self->aq_hw->aq_link_status.mbps);
+
+	self->link_status = self->aq_hw->aq_link_status;
+	if (!netif_carrier_ok(self->ndev) && self->link_status.mbps) {
+		aq_utils_obj_set(&self->header.flags,
+				 AQ_NIC_FLAG_STARTED);
+		aq_utils_obj_clear(&self->header.flags,
+				   AQ_NIC_LINK_DOWN);
+		netif_carrier_on(self->ndev);
+		netif_tx_wake_all_queues(self->ndev);
+	}
+	if (netif_carrier_ok(self->ndev) && !self->link_status.mbps) {
+		netif_carrier_off(self->ndev);
+		netif_tx_disable(self->ndev);
+		aq_utils_obj_set(&self->header.flags, AQ_NIC_LINK_DOWN);
+	}
+	return 0;
+}
+
 static void aq_nic_service_timer_cb(unsigned long param)
 {
 	struct aq_nic_s *self = (struct aq_nic_s *)param;
@@ -131,26 +160,13 @@ static void aq_nic_service_timer_cb(unsigned long param)
 	if (aq_utils_obj_test(&self->header.flags, AQ_NIC_FLAGS_IS_NOT_READY))
 		goto err_exit;
 
-	err = self->aq_hw_ops.hw_get_link_status(self->aq_hw);
-	if (err < 0)
+	err = aq_nic_update_link_status(self);
+	if (err)
 		goto err_exit;
 
-	self->link_status = self->aq_hw->aq_link_status;
-
 	self->aq_hw_ops.hw_interrupt_moderation_set(self->aq_hw,
 		    self->aq_nic_cfg.is_interrupt_moderation);
 
-	if (self->link_status.mbps) {
-		aq_utils_obj_set(&self->header.flags,
-				 AQ_NIC_FLAG_STARTED);
-		aq_utils_obj_clear(&self->header.flags,
-				   AQ_NIC_LINK_DOWN);
-		netif_carrier_on(self->ndev);
-	} else {
-		netif_carrier_off(self->ndev);
-		aq_utils_obj_set(&self->header.flags, AQ_NIC_LINK_DOWN);
-	}
-
 	memset(&stats_rx, 0U, sizeof(struct aq_ring_stats_rx_s));
 	memset(&stats_tx, 0U, sizeof(struct aq_ring_stats_tx_s));
 	for (i = AQ_DIMOF(self->aq_vec); i--;) {
@@ -240,7 +256,6 @@ err_exit:
 int aq_nic_ndev_register(struct aq_nic_s *self)
 {
 	int err = 0;
-	unsigned int i = 0U;
 
 	if (!self->ndev) {
 		err = -EINVAL;
@@ -262,8 +277,7 @@ int aq_nic_ndev_register(struct aq_nic_s *self)
 
 	netif_carrier_off(self->ndev);
 
-	for (i = AQ_CFG_VECS_MAX; i--;)
-		aq_nic_ndev_queue_stop(self, i);
+	netif_tx_disable(self->ndev);
 
 	err = register_netdev(self->ndev);
 	if (err < 0)
@@ -318,12 +332,8 @@ struct aq_nic_s *aq_nic_alloc_hot(struct net_device *ndev)
 		err = -EINVAL;
 		goto err_exit;
 	}
-	if (netif_running(ndev)) {
-		unsigned int i;
-
-		for (i = AQ_CFG_VECS_MAX; i--;)
-			netif_stop_subqueue(ndev, i);
-	}
+	if (netif_running(ndev))
+		netif_tx_disable(ndev);
 
 	for (self->aq_vecs = 0; self->aq_vecs < self->aq_nic_cfg.vecs;
 		self->aq_vecs++) {
@@ -383,16 +393,6 @@ err_exit:
 	return err;
 }
 
-void aq_nic_ndev_queue_start(struct aq_nic_s *self, unsigned int idx)
-{
-	netif_start_subqueue(self->ndev, idx);
-}
-
-void aq_nic_ndev_queue_stop(struct aq_nic_s *self, unsigned int idx)
-{
-	netif_stop_subqueue(self->ndev, idx);
-}
-
 int aq_nic_start(struct aq_nic_s *self)
 {
 	struct aq_vec_s *aq_vec = NULL;
@@ -451,10 +451,6 @@ int aq_nic_start(struct aq_nic_s *self)
 			goto err_exit;
 	}
 
-	for (i = 0U, aq_vec = self->aq_vec[0];
-		self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i])
-		aq_nic_ndev_queue_start(self, i);
-
 	err = netif_set_real_num_tx_queues(self->ndev, self->aq_vecs);
 	if (err < 0)
 		goto err_exit;
@@ -463,6 +459,8 @@ int aq_nic_start(struct aq_nic_s *self)
 	if (err < 0)
 		goto err_exit;
 
+	netif_tx_start_all_queues(self->ndev);
+
 err_exit:
 	return err;
 }
@@ -602,7 +600,6 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb)
 	unsigned int vec = skb->queue_mapping % self->aq_nic_cfg.vecs;
 	unsigned int tc = 0U;
 	int err = NETDEV_TX_OK;
-	bool is_nic_in_bad_state;
 
 	frags = skb_shinfo(skb)->nr_frags + 1;
 
@@ -613,13 +610,10 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb)
 		goto err_exit;
 	}
 
-	is_nic_in_bad_state = aq_utils_obj_test(&self->header.flags,
-						AQ_NIC_FLAGS_IS_NOT_TX_READY) ||
-						(aq_ring_avail_dx(ring) <
-						AQ_CFG_SKB_FRAGS_MAX);
+	aq_ring_update_queue_state(ring);
 
-	if (is_nic_in_bad_state) {
-		aq_nic_ndev_queue_stop(self, ring->idx);
+	/* Above status update may stop the queue. Check this. */
+	if (__netif_subqueue_stopped(self->ndev, ring->idx)) {
 		err = NETDEV_TX_BUSY;
 		goto err_exit;
 	}
@@ -631,9 +625,6 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb)
 						      ring,
 						      frags);
 		if (err >= 0) {
-			if (aq_ring_avail_dx(ring) < AQ_CFG_SKB_FRAGS_MAX + 1)
-				aq_nic_ndev_queue_stop(self, ring->idx);
-
 			++ring->stats.tx.packets;
 			ring->stats.tx.bytes += skb->len;
 		}
@@ -898,9 +889,7 @@ int aq_nic_stop(struct aq_nic_s *self)
 	struct aq_vec_s *aq_vec = NULL;
 	unsigned int i = 0U;
 
-	for (i = 0U, aq_vec = self->aq_vec[0];
-		self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i])
-		aq_nic_ndev_queue_stop(self, i);
+	netif_tx_disable(self->ndev);
 
 	del_timer_sync(&self->service_timer);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index 7fc2a5ecb2b7..0ddd556ff901 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -83,8 +83,6 @@ struct net_device *aq_nic_get_ndev(struct aq_nic_s *self);
 int aq_nic_init(struct aq_nic_s *self);
 int aq_nic_cfg_start(struct aq_nic_s *self);
 int aq_nic_ndev_register(struct aq_nic_s *self);
-void aq_nic_ndev_queue_start(struct aq_nic_s *self, unsigned int idx);
-void aq_nic_ndev_queue_stop(struct aq_nic_s *self, unsigned int idx);
 void aq_nic_ndev_free(struct aq_nic_s *self);
 int aq_nic_start(struct aq_nic_s *self);
 int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb);
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 4eee1996a825..02f79b0640ba 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -104,6 +104,32 @@ int aq_ring_init(struct aq_ring_s *self)
 	return 0;
 }
 
+void aq_ring_update_queue_state(struct aq_ring_s *ring)
+{
+	if (aq_ring_avail_dx(ring) <= AQ_CFG_SKB_FRAGS_MAX)
+		aq_ring_queue_stop(ring);
+	else if (aq_ring_avail_dx(ring) > AQ_CFG_RESTART_DESC_THRES)
+		aq_ring_queue_wake(ring);
+}
+
+void aq_ring_queue_wake(struct aq_ring_s *ring)
+{
+	struct net_device *ndev = aq_nic_get_ndev(ring->aq_nic);
+
+	if (__netif_subqueue_stopped(ndev, ring->idx)) {
+		netif_wake_subqueue(ndev, ring->idx);
+		ring->stats.tx.queue_restarts++;
+	}
+}
+
+void aq_ring_queue_stop(struct aq_ring_s *ring)
+{
+	struct net_device *ndev = aq_nic_get_ndev(ring->aq_nic);
+
+	if (!__netif_subqueue_stopped(ndev, ring->idx))
+		netif_stop_subqueue(ndev, ring->idx);
+}
+
 void aq_ring_tx_clean(struct aq_ring_s *self)
 {
 	struct device *dev = aq_nic_get_dev(self->aq_nic);
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
index 782176c5f4f8..24523b5ac68c 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
@@ -94,6 +94,7 @@ struct aq_ring_stats_tx_s {
 	u64 errors;
 	u64 packets;
 	u64 bytes;
+	u64 queue_restarts;
 };
 
 union aq_ring_stats_s {
@@ -147,6 +148,9 @@ struct aq_ring_s *aq_ring_rx_alloc(struct aq_ring_s *self,
 int aq_ring_init(struct aq_ring_s *self);
 void aq_ring_rx_deinit(struct aq_ring_s *self);
 void aq_ring_free(struct aq_ring_s *self);
+void aq_ring_update_queue_state(struct aq_ring_s *ring);
+void aq_ring_queue_wake(struct aq_ring_s *ring);
+void aq_ring_queue_stop(struct aq_ring_s *ring);
 void aq_ring_tx_clean(struct aq_ring_s *self);
 int aq_ring_rx_clean(struct aq_ring_s *self,
 		     struct napi_struct *napi,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
index ebf588004c46..305ff8ffac2c 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
@@ -59,12 +59,7 @@ static int aq_vec_poll(struct napi_struct *napi, int budget)
 			if (ring[AQ_VEC_TX_ID].sw_head !=
 			    ring[AQ_VEC_TX_ID].hw_head) {
 				aq_ring_tx_clean(&ring[AQ_VEC_TX_ID]);
-
-				if (aq_ring_avail_dx(&ring[AQ_VEC_TX_ID]) >
-				    AQ_CFG_SKB_FRAGS_MAX) {
-					aq_nic_ndev_queue_start(self->aq_nic,
-						ring[AQ_VEC_TX_ID].idx);
-				}
+				aq_ring_update_queue_state(&ring[AQ_VEC_TX_ID]);
 				was_tx_cleaned = true;
 			}
 
@@ -364,6 +359,7 @@ void aq_vec_add_stats(struct aq_vec_s *self,
 		stats_tx->packets += tx->packets;
 		stats_tx->bytes += tx->bytes;
 		stats_tx->errors += tx->errors;
+		stats_tx->queue_restarts += tx->queue_restarts;
 	}
 }
 
-- 
cgit v1.2.3


From a7bb1bea3a296549ebfc28afa76276ef392f9afa Mon Sep 17 00:00:00 2001
From: Igor Russkikh <igor.russkikh@aquantia.com>
Date: Mon, 25 Sep 2017 10:48:49 +0300
Subject: aquantia: Fix transient invalid link down/up indications

Due to a bug in aquantia atlantic card firmware, it sometimes reports
invalid link speed bits. That caused driver to report link down events,
although link itself is totally fine.

This patch ignores such out of blue readings.

Signed-off-by: Pavel Belous <Pavel.Belous@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index 4f5ec9a0fbfb..bf734b32e44b 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -351,8 +351,7 @@ int hw_atl_utils_mpi_get_link_status(struct aq_hw_s *self)
 			break;
 
 		default:
-			link_status->mbps = 0U;
-			break;
+			return -EBUSY;
 		}
 	}
 
-- 
cgit v1.2.3


From c7545689244b50c562b1fbbc71905fba224c8a05 Mon Sep 17 00:00:00 2001
From: Pavel Belous <pavel.belous@aquantia.com>
Date: Mon, 25 Sep 2017 10:48:50 +0300
Subject: atlantic: fix iommu errors

Call skb_frag_dma_map multiple times if tx length is greater than
device max and avoid processing tx ring until entire packet has been
sent.

Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: Pavel Belous <pavel.belous@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c  | 43 ++++++++++++++----------
 drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 27 ++++++++++-----
 drivers/net/ethernet/aquantia/atlantic/aq_ring.h |  6 ++--
 3 files changed, 49 insertions(+), 27 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 072a55029f04..0a5bb4114eb4 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -473,6 +473,7 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self,
 	unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
 	unsigned int frag_count = 0U;
 	unsigned int dx = ring->sw_tail;
+	struct aq_ring_buff_s *first = NULL;
 	struct aq_ring_buff_s *dx_buff = &ring->buff_ring[dx];
 
 	if (unlikely(skb_is_gso(skb))) {
@@ -483,6 +484,7 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self,
 		dx_buff->len_l4 = tcp_hdrlen(skb);
 		dx_buff->mss = skb_shinfo(skb)->gso_size;
 		dx_buff->is_txc = 1U;
+		dx_buff->eop_index = 0xffffU;
 
 		dx_buff->is_ipv6 =
 			(ip_hdr(skb)->version == 6) ? 1U : 0U;
@@ -502,6 +504,7 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self,
 	if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa)))
 		goto exit;
 
+	first = dx_buff;
 	dx_buff->len_pkt = skb->len;
 	dx_buff->is_sop = 1U;
 	dx_buff->is_mapped = 1U;
@@ -530,40 +533,46 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self,
 
 	for (; nr_frags--; ++frag_count) {
 		unsigned int frag_len = 0U;
+		unsigned int buff_offset = 0U;
+		unsigned int buff_size = 0U;
 		dma_addr_t frag_pa;
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[frag_count];
 
 		frag_len = skb_frag_size(frag);
-		frag_pa = skb_frag_dma_map(aq_nic_get_dev(self), frag, 0,
-					   frag_len, DMA_TO_DEVICE);
 
-		if (unlikely(dma_mapping_error(aq_nic_get_dev(self), frag_pa)))
-			goto mapping_error;
+		while (frag_len) {
+			if (frag_len > AQ_CFG_TX_FRAME_MAX)
+				buff_size = AQ_CFG_TX_FRAME_MAX;
+			else
+				buff_size = frag_len;
+
+			frag_pa = skb_frag_dma_map(aq_nic_get_dev(self),
+						   frag,
+						   buff_offset,
+						   buff_size,
+						   DMA_TO_DEVICE);
+
+			if (unlikely(dma_mapping_error(aq_nic_get_dev(self),
+						       frag_pa)))
+				goto mapping_error;
 
-		while (frag_len > AQ_CFG_TX_FRAME_MAX) {
 			dx = aq_ring_next_dx(ring, dx);
 			dx_buff = &ring->buff_ring[dx];
 
 			dx_buff->flags = 0U;
-			dx_buff->len = AQ_CFG_TX_FRAME_MAX;
+			dx_buff->len = buff_size;
 			dx_buff->pa = frag_pa;
 			dx_buff->is_mapped = 1U;
+			dx_buff->eop_index = 0xffffU;
+
+			frag_len -= buff_size;
+			buff_offset += buff_size;
 
-			frag_len -= AQ_CFG_TX_FRAME_MAX;
-			frag_pa += AQ_CFG_TX_FRAME_MAX;
 			++ret;
 		}
-
-		dx = aq_ring_next_dx(ring, dx);
-		dx_buff = &ring->buff_ring[dx];
-
-		dx_buff->flags = 0U;
-		dx_buff->len = frag_len;
-		dx_buff->pa = frag_pa;
-		dx_buff->is_mapped = 1U;
-		++ret;
 	}
 
+	first->eop_index = dx;
 	dx_buff->is_eop = 1U;
 	dx_buff->skb = skb;
 	goto exit;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 02f79b0640ba..0654e0c76bc2 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -104,6 +104,12 @@ int aq_ring_init(struct aq_ring_s *self)
 	return 0;
 }
 
+static inline bool aq_ring_dx_in_range(unsigned int h, unsigned int i,
+				       unsigned int t)
+{
+	return (h < t) ? ((h < i) && (i < t)) : ((h < i) || (i < t));
+}
+
 void aq_ring_update_queue_state(struct aq_ring_s *ring)
 {
 	if (aq_ring_avail_dx(ring) <= AQ_CFG_SKB_FRAGS_MAX)
@@ -139,23 +145,28 @@ void aq_ring_tx_clean(struct aq_ring_s *self)
 		struct aq_ring_buff_s *buff = &self->buff_ring[self->sw_head];
 
 		if (likely(buff->is_mapped)) {
-			if (unlikely(buff->is_sop))
+			if (unlikely(buff->is_sop)) {
+				if (!buff->is_eop &&
+				    buff->eop_index != 0xffffU &&
+				    (!aq_ring_dx_in_range(self->sw_head,
+						buff->eop_index,
+						self->hw_head)))
+					break;
+
 				dma_unmap_single(dev, buff->pa, buff->len,
 						 DMA_TO_DEVICE);
-			else
+			} else {
 				dma_unmap_page(dev, buff->pa, buff->len,
 					       DMA_TO_DEVICE);
+			}
 		}
 
 		if (unlikely(buff->is_eop))
 			dev_kfree_skb_any(buff->skb);
-	}
-}
 
-static inline unsigned int aq_ring_dx_in_range(unsigned int h, unsigned int i,
-					       unsigned int t)
-{
-	return (h < t) ? ((h < i) && (i < t)) : ((h < i) || (i < t));
+		buff->pa = 0U;
+		buff->eop_index = 0xffffU;
+	}
 }
 
 #define AQ_SKB_ALIGN SKB_DATA_ALIGN(sizeof(struct skb_shared_info))
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
index 24523b5ac68c..5844078764bd 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
@@ -65,7 +65,7 @@ struct __packed aq_ring_buff_s {
 	};
 	union {
 		struct {
-			u32 len:16;
+			u16 len;
 			u32 is_ip_cso:1;
 			u32 is_udp_cso:1;
 			u32 is_tcp_cso:1;
@@ -77,8 +77,10 @@ struct __packed aq_ring_buff_s {
 			u32 is_cleaned:1;
 			u32 is_error:1;
 			u32 rsvd3:6;
+			u16 eop_index;
+			u16 rsvd4;
 		};
-		u32 flags;
+		u64 flags;
 	};
 };
 
-- 
cgit v1.2.3


From c2cc187e53011c1c4931055984657da9085c763b Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Mon, 25 Sep 2017 13:19:26 +0300
Subject: sctp: Fix a big endian bug in sctp_diag_dump()

The sctp_for_each_transport() function takes an pointer to int.  The
cb->args[] array holds longs so it's only using the high 32 bits.  It
works on little endian system but will break on big endian 64 bit
machines.

Fixes: d25adbeb0cdb ("sctp: fix an use-after-free issue in sctp_sock_dump")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sctp_diag.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c
index 22ed01a76b19..a72a7d925d46 100644
--- a/net/sctp/sctp_diag.c
+++ b/net/sctp/sctp_diag.c
@@ -463,6 +463,7 @@ static void sctp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
 		.r = r,
 		.net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN),
 	};
+	int pos = cb->args[2];
 
 	/* eps hashtable dumps
 	 * args:
@@ -493,7 +494,8 @@ skip:
 		goto done;
 
 	sctp_for_each_transport(sctp_sock_filter, sctp_sock_dump,
-				net, (int *)&cb->args[2], &commp);
+				net, &pos, &commp);
+	cb->args[2] = pos;
 
 done:
 	cb->args[1] = cb->args[4];
-- 
cgit v1.2.3


From 38e8a5c040d3ec99a8351c688dcdf0f549611565 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Mon, 21 Aug 2017 12:04:50 +0300
Subject: net/mlx5e: IPoIB, Fix access to invalid memory address

When cleaning rdma netdevice we need to save the mdev pointer
because priv is released when we release netdev.

This bug was found using the kernel address sanitizer (KASAN).
use-after-free in mlx5_rdma_netdev_free+0xe3/0x100 [mlx5_core]

Fixes: 48935bbb7ae8 ("net/mlx5e: IPoIB, Add netdevice profile skeleton")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 85298051a3e4..145e392ab849 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -572,12 +572,13 @@ void mlx5_rdma_netdev_free(struct net_device *netdev)
 {
 	struct mlx5e_priv          *priv    = mlx5i_epriv(netdev);
 	const struct mlx5e_profile *profile = priv->profile;
+	struct mlx5_core_dev       *mdev    = priv->mdev;
 
 	mlx5e_detach_netdev(priv);
 	profile->cleanup(priv);
 	destroy_workqueue(priv->wq);
 	free_netdev(netdev);
 
-	mlx5e_destroy_mdev_resources(priv->mdev);
+	mlx5e_destroy_mdev_resources(mdev);
 }
 EXPORT_SYMBOL(mlx5_rdma_netdev_free);
-- 
cgit v1.2.3


From 99d3cd27f755d63fd6cf85169eaa873d90769aa5 Mon Sep 17 00:00:00 2001
From: Inbar Karmy <inbark@mellanox.com>
Date: Thu, 24 Aug 2017 17:21:44 +0300
Subject: net/mlx5: Fix FPGA capability location

Currently, FPGA capability is located in (mdev)->caps.hca_cur,
change the location to be (mdev)->caps.fpga,
since hca_cur is reserved for HCA device capabilities.

Fixes: e29341fb3a5b ("net/mlx5: FPGA, Add basic support for Innova")
Signed-off-by: Inbar Karmy <inbark@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c  | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h  | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c | 3 +--
 include/linux/mlx5/device.h                         | 5 ++---
 include/linux/mlx5/driver.h                         | 1 +
 5 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c
index e37453d838db..c0fd2212e890 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c
@@ -71,11 +71,11 @@ int mlx5_fpga_access_reg(struct mlx5_core_dev *dev, u8 size, u64 addr,
 	return 0;
 }
 
-int mlx5_fpga_caps(struct mlx5_core_dev *dev, u32 *caps)
+int mlx5_fpga_caps(struct mlx5_core_dev *dev)
 {
 	u32 in[MLX5_ST_SZ_DW(fpga_cap)] = {0};
 
-	return mlx5_core_access_reg(dev, in, sizeof(in), caps,
+	return mlx5_core_access_reg(dev, in, sizeof(in), dev->caps.fpga,
 				    MLX5_ST_SZ_BYTES(fpga_cap),
 				    MLX5_REG_FPGA_CAP, 0, 0);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h
index 94bdfd47c3f0..d05233c9b4f6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h
@@ -65,7 +65,7 @@ struct mlx5_fpga_qp_counters {
 	u64 rx_total_drop;
 };
 
-int mlx5_fpga_caps(struct mlx5_core_dev *dev, u32 *caps);
+int mlx5_fpga_caps(struct mlx5_core_dev *dev);
 int mlx5_fpga_query(struct mlx5_core_dev *dev, struct mlx5_fpga_query *query);
 int mlx5_fpga_ctrl_op(struct mlx5_core_dev *dev, u8 op);
 int mlx5_fpga_access_reg(struct mlx5_core_dev *dev, u8 size, u64 addr,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
index 9034e9960a76..dc8970346521 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
@@ -139,8 +139,7 @@ int mlx5_fpga_device_start(struct mlx5_core_dev *mdev)
 	if (err)
 		goto out;
 
-	err = mlx5_fpga_caps(fdev->mdev,
-			     fdev->mdev->caps.hca_cur[MLX5_CAP_FPGA]);
+	err = mlx5_fpga_caps(fdev->mdev);
 	if (err)
 		goto out;
 
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index eaf4ad209c8f..e32dbc4934db 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -980,7 +980,6 @@ enum mlx5_cap_type {
 	MLX5_CAP_RESERVED,
 	MLX5_CAP_VECTOR_CALC,
 	MLX5_CAP_QOS,
-	MLX5_CAP_FPGA,
 	/* NUM OF CAP Types */
 	MLX5_CAP_NUM
 };
@@ -1110,10 +1109,10 @@ enum mlx5_mcam_feature_groups {
 	MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_feature_cap_mask.enhanced_features.fld)
 
 #define MLX5_CAP_FPGA(mdev, cap) \
-	MLX5_GET(fpga_cap, (mdev)->caps.hca_cur[MLX5_CAP_FPGA], cap)
+	MLX5_GET(fpga_cap, (mdev)->caps.fpga, cap)
 
 #define MLX5_CAP64_FPGA(mdev, cap) \
-	MLX5_GET64(fpga_cap, (mdev)->caps.hca_cur[MLX5_CAP_FPGA], cap)
+	MLX5_GET64(fpga_cap, (mdev)->caps.fpga, cap)
 
 enum {
 	MLX5_CMD_STAT_OK			= 0x0,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 02ff700e4f30..401c8972cc3a 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -774,6 +774,7 @@ struct mlx5_core_dev {
 		u32 hca_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)];
 		u32 pcam[MLX5_ST_SZ_DW(pcam_reg)];
 		u32 mcam[MLX5_ST_SZ_DW(mcam_reg)];
+		u32 fpga[MLX5_ST_SZ_DW(fpga_cap)];
 	} caps;
 	phys_addr_t		iseg_base;
 	struct mlx5_init_seg __iomem *iseg;
-- 
cgit v1.2.3


From 16f1c5bb3ed75b3cf3ced537db40f7e1a244debe Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Sun, 30 Jul 2017 11:02:51 +0300
Subject: net/mlx5: Check device capability for maximum flow counters

Added check for the maximal number of flow counters attached
to rule (FTE).

Fixes: bd5251dbf156b ('net/mlx5_core: Introduce flow steering destination of type counter')
Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c  |  8 ++++++++
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 11 +++++++++++
 include/linux/mlx5/mlx5_ifc.h                     |  3 ++-
 3 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index e0d0efd903bc..36ecc2b2e187 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -293,6 +293,9 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	}
 
 	if (fte->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
+		int max_list_size = BIT(MLX5_CAP_FLOWTABLE_TYPE(dev,
+					log_max_flow_counter,
+					ft->type));
 		int list_size = 0;
 
 		list_for_each_entry(dst, &fte->node.children, node.list) {
@@ -305,12 +308,17 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 			in_dests += MLX5_ST_SZ_BYTES(dest_format_struct);
 			list_size++;
 		}
+		if (list_size > max_list_size) {
+			err = -EINVAL;
+			goto err_out;
+		}
 
 		MLX5_SET(flow_context, in_flow_context, flow_counter_list_size,
 			 list_size);
 	}
 
 	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+err_out:
 	kvfree(in);
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 5509a752f98e..48dd78975062 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -52,6 +52,7 @@ enum fs_flow_table_type {
 	FS_FT_FDB             = 0X4,
 	FS_FT_SNIFFER_RX	= 0X5,
 	FS_FT_SNIFFER_TX	= 0X6,
+	FS_FT_MAX_TYPE = FS_FT_SNIFFER_TX,
 };
 
 enum fs_flow_table_op_mod {
@@ -260,4 +261,14 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev);
 #define fs_for_each_dst(pos, fte)			\
 	fs_list_for_each_entry(pos, &(fte)->node.children)
 
+#define MLX5_CAP_FLOWTABLE_TYPE(mdev, cap, type) (		\
+	(type == FS_FT_NIC_RX) ? MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) :		\
+	(type == FS_FT_ESW_EGRESS_ACL) ? MLX5_CAP_ESW_EGRESS_ACL(mdev, cap) :		\
+	(type == FS_FT_ESW_INGRESS_ACL) ? MLX5_CAP_ESW_INGRESS_ACL(mdev, cap) :		\
+	(type == FS_FT_FDB) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) :		\
+	(type == FS_FT_SNIFFER_RX) ? MLX5_CAP_FLOWTABLE_SNIFFER_RX(mdev, cap) :		\
+	(type == FS_FT_SNIFFER_TX) ? MLX5_CAP_FLOWTABLE_SNIFFER_TX(mdev, cap) :		\
+	(BUILD_BUG_ON_ZERO(FS_FT_SNIFFER_TX != FS_FT_MAX_TYPE))\
+	)
+
 #endif
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index a528b35a022e..69772347f866 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -327,7 +327,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8         reserved_at_80[0x18];
 	u8         log_max_destination[0x8];
 
-	u8         reserved_at_a0[0x18];
+	u8         log_max_flow_counter[0x8];
+	u8         reserved_at_a8[0x10];
 	u8         log_max_flow[0x8];
 
 	u8         reserved_at_c0[0x40];
-- 
cgit v1.2.3


From ace743214ea205c7d433562c5fa24e33bdfda7ab Mon Sep 17 00:00:00 2001
From: Paul Blakey <paulb@mellanox.com>
Date: Tue, 5 Sep 2017 15:05:51 +0300
Subject: net/mlx5e: Fix erroneous freeing of encap header buffer

In case the neighbour for the tunnel destination isn't valid,
we send a neighbour update request but we free the encap
header buffer. This is wrong, because we still need it for
allocating a HW encap entry once the neighbour is available.

Fix that by skipping freeing it if we wait for neighbour.

Fixes: 232c001398ae ('net/mlx5e: Add support to neighbour update flow')
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index da503e6411da..4e2fc016bdd6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1564,7 +1564,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 		break;
 	default:
 		err = -EOPNOTSUPP;
-		goto out;
+		goto free_encap;
 	}
 	fl4.flowi4_tos = tun_key->tos;
 	fl4.daddr = tun_key->u.ipv4.dst;
@@ -1573,7 +1573,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 	err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev,
 				      &fl4, &n, &ttl);
 	if (err)
-		goto out;
+		goto free_encap;
 
 	/* used by mlx5e_detach_encap to lookup a neigh hash table
 	 * entry in the neigh hash table when a user deletes a rule
@@ -1590,7 +1590,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 	 */
 	err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e);
 	if (err)
-		goto out;
+		goto free_encap;
 
 	read_lock_bh(&n->lock);
 	nud_state = n->nud_state;
@@ -1630,8 +1630,9 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 
 destroy_neigh_entry:
 	mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
-out:
+free_encap:
 	kfree(encap_header);
+out:
 	if (n)
 		neigh_release(n);
 	return err;
@@ -1668,7 +1669,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 		break;
 	default:
 		err = -EOPNOTSUPP;
-		goto out;
+		goto free_encap;
 	}
 
 	fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label);
@@ -1678,7 +1679,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 	err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev,
 				      &fl6, &n, &ttl);
 	if (err)
-		goto out;
+		goto free_encap;
 
 	/* used by mlx5e_detach_encap to lookup a neigh hash table
 	 * entry in the neigh hash table when a user deletes a rule
@@ -1695,7 +1696,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 	 */
 	err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e);
 	if (err)
-		goto out;
+		goto free_encap;
 
 	read_lock_bh(&n->lock);
 	nud_state = n->nud_state;
@@ -1736,8 +1737,9 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 
 destroy_neigh_entry:
 	mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
-out:
+free_encap:
 	kfree(encap_header);
+out:
 	if (n)
 		neigh_release(n);
 	return err;
-- 
cgit v1.2.3


From bdd66ac0aeed971d1cb42b3aa0d11b0ea3842e09 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Sun, 11 Jun 2017 21:13:25 +0300
Subject: net/mlx5e: Disallow TC offloading of unsupported match/action
 combinations

When offloading header re-write, the HW may need to adjust checksums along
the packet. For IP traffic, and a case where we are asked to modify fields in
the IP header, current HW supports that only for TCP and UDP. Enforce it, in
this case fail the offloading attempt for non TCP/UDP packets.

Fixes: d7e75a325cb2 ('net/mlx5e: Add offloading of E-Switch TC pedit (header re-write) actions')
Fixes: 2f4fe4cab073 ('net/mlx5e: Add offloading of NIC TC pedit (header re-write) actions')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 70 +++++++++++++++++++++++++
 1 file changed, 70 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 4e2fc016bdd6..d3786005fba7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1317,6 +1317,69 @@ static bool csum_offload_supported(struct mlx5e_priv *priv, u32 action, u32 upda
 	return true;
 }
 
+static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
+					  struct tcf_exts *exts)
+{
+	const struct tc_action *a;
+	bool modify_ip_header;
+	LIST_HEAD(actions);
+	u8 htype, ip_proto;
+	void *headers_v;
+	u16 ethertype;
+	int nkeys, i;
+
+	headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers);
+	ethertype = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ethertype);
+
+	/* for non-IP we only re-write MACs, so we're okay */
+	if (ethertype != ETH_P_IP && ethertype != ETH_P_IPV6)
+		goto out_ok;
+
+	modify_ip_header = false;
+	tcf_exts_to_list(exts, &actions);
+	list_for_each_entry(a, &actions, list) {
+		if (!is_tcf_pedit(a))
+			continue;
+
+		nkeys = tcf_pedit_nkeys(a);
+		for (i = 0; i < nkeys; i++) {
+			htype = tcf_pedit_htype(a, i);
+			if (htype == TCA_PEDIT_KEY_EX_HDR_TYPE_IP4 ||
+			    htype == TCA_PEDIT_KEY_EX_HDR_TYPE_IP6) {
+				modify_ip_header = true;
+				break;
+			}
+		}
+	}
+
+	ip_proto = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol);
+	if (modify_ip_header && ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) {
+		pr_info("can't offload re-write of ip proto %d\n", ip_proto);
+		return false;
+	}
+
+out_ok:
+	return true;
+}
+
+static bool actions_match_supported(struct mlx5e_priv *priv,
+				    struct tcf_exts *exts,
+				    struct mlx5e_tc_flow_parse_attr *parse_attr,
+				    struct mlx5e_tc_flow *flow)
+{
+	u32 actions;
+
+	if (flow->flags & MLX5E_TC_FLOW_ESWITCH)
+		actions = flow->esw_attr->action;
+	else
+		actions = flow->nic_attr->action;
+
+	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+		return modify_header_match_supported(&parse_attr->spec, exts);
+
+	return true;
+}
+
 static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				struct mlx5e_tc_flow_parse_attr *parse_attr,
 				struct mlx5e_tc_flow *flow)
@@ -1378,6 +1441,9 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 		return -EINVAL;
 	}
 
+	if (!actions_match_supported(priv, exts, parse_attr, flow))
+		return -EOPNOTSUPP;
+
 	return 0;
 }
 
@@ -1936,6 +2002,10 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 
 		return -EINVAL;
 	}
+
+	if (!actions_match_supported(priv, exts, parse_attr, flow))
+		return -EOPNOTSUPP;
+
 	return err;
 }
 
-- 
cgit v1.2.3


From b281208911a549e391d92ee6cb680dcd3d71783b Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Tue, 8 Aug 2017 11:45:28 +0300
Subject: net/mlx5e: Check encap entry state when offloading tunneled flows

Encap entries cached by the driver could be invalidated due to
tunnel destination neighbour state changes.
When attempting to offload a flow that uses a cached encap entry,
we must check the entry validity and defer the offloading
if the entry exists but not valid.

When EAGAIN is returned, the flow offloading to hardware takes place
by the neigh update code when the tunnel destination neighbour
becomes connected.

Fixes: 232c001398ae ("net/mlx5e: Add support to neighbour update flow")
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index d3786005fba7..1aa2028ed995 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1859,6 +1859,7 @@ vxlan_encap_offload_err:
 		}
 	}
 
+	/* must verify if encap is valid or not */
 	if (found)
 		goto attach_flow;
 
@@ -1885,6 +1886,8 @@ attach_flow:
 	*encap_dev = e->out_dev;
 	if (e->flags & MLX5_ENCAP_ENTRY_VALID)
 		attr->encap_id = e->encap_id;
+	else
+		err = -EAGAIN;
 
 	return err;
 
-- 
cgit v1.2.3


From b20eab15a1d5091e45022401e75b49948e8be33f Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Tue, 12 Sep 2017 17:51:12 +0300
Subject: net/mlx5e: Print netdev features correctly in error message

Use the correct formatting for netdev features.

Fixes: 0e405443e803 ("net/mlx5e: Improve set features ndo resiliency")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index dfc29720ab77..84b013dc62e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3333,8 +3333,8 @@ static int mlx5e_handle_feature(struct net_device *netdev,
 
 	err = feature_handler(netdev, enable);
 	if (err) {
-		netdev_err(netdev, "%s feature 0x%llx failed err %d\n",
-			   enable ? "Enable" : "Disable", feature, err);
+		netdev_err(netdev, "%s feature %pNF failed, err %d\n",
+			   enable ? "Enable" : "Disable", &feature, err);
 		return err;
 	}
 
-- 
cgit v1.2.3


From 1456f69ff5fbba48ed5bc86e858e945e693ba0b7 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Sun, 10 Sep 2017 10:36:06 +0300
Subject: net/mlx5e: Don't add/remove 802.1ad rules when changing 802.1Q VLAN
 filter

Toggling of C-tag VLAN filter should not affect the "any S-tag" steering rule.

Fixes: 8a271746a264 ("net/mlx5e: Receive s-tagged packets in promiscuous mode")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_fs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index f11fd07ac4dd..850cdc980ab5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -291,7 +291,7 @@ void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv)
 	priv->fs.vlan.filter_disabled = false;
 	if (priv->netdev->flags & IFF_PROMISC)
 		return;
-	mlx5e_del_any_vid_rules(priv);
+	mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_CTAG_VID, 0);
 }
 
 void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv)
@@ -302,7 +302,7 @@ void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv)
 	priv->fs.vlan.filter_disabled = true;
 	if (priv->netdev->flags & IFF_PROMISC)
 		return;
-	mlx5e_add_any_vid_rules(priv);
+	mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_CTAG_VID, 0);
 }
 
 int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto,
-- 
cgit v1.2.3


From 603e1f5bd3ca76f16688e10040545594d2e91ba4 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Wed, 13 Sep 2017 15:37:50 +0300
Subject: net/mlx5e: Fix calculated checksum offloads counters

Instead of calculating the offloads counters, count them explicitly.
The calculations done for these counters would result in bugs in some
cases, for example:
When running TCP traffic over a VXLAN tunnel with TSO enabled the following
counters would increase:
       tx_csum_partial: 1,333,284
       tx_csum_partial_inner: 29,286
       tx4_csum_partial_inner: 384
       tx7_csum_partial_inner: 8
       tx9_csum_partial_inner: 34
       tx10_csum_partial_inner: 26,807
       tx11_csum_partial_inner: 287
       tx12_csum_partial_inner: 27
       tx16_csum_partial_inner: 6
       tx25_csum_partial_inner: 1,733

Seems like tx_csum_partial increased out of nowhere.
The issue is in the following calculation in mlx5e_update_sw_counters:
s->tx_csum_partial = s->tx_packets - tx_offload_none - s->tx_csum_partial_inner;

While tx_packets increases by the number of GSO segments for each SKB,
tx_csum_partial_inner will only increase by one, resulting in wrong
tx_csum_partial counter.

Fixes: bfe6d8d1d433 ("net/mlx5e: Reorganize ethtool statistics")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 9 +++------
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    | 3 +++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 6 ++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c    | 1 +
 4 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 84b013dc62e9..cc11bbbd0309 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -184,7 +184,6 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 	struct mlx5e_sw_stats temp, *s = &temp;
 	struct mlx5e_rq_stats *rq_stats;
 	struct mlx5e_sq_stats *sq_stats;
-	u64 tx_offload_none = 0;
 	int i, j;
 
 	memset(s, 0, sizeof(*s));
@@ -199,6 +198,7 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 		s->rx_lro_bytes	+= rq_stats->lro_bytes;
 		s->rx_csum_none	+= rq_stats->csum_none;
 		s->rx_csum_complete += rq_stats->csum_complete;
+		s->rx_csum_unnecessary += rq_stats->csum_unnecessary;
 		s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
 		s->rx_xdp_drop += rq_stats->xdp_drop;
 		s->rx_xdp_tx += rq_stats->xdp_tx;
@@ -229,14 +229,11 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 			s->tx_queue_dropped	+= sq_stats->dropped;
 			s->tx_xmit_more		+= sq_stats->xmit_more;
 			s->tx_csum_partial_inner += sq_stats->csum_partial_inner;
-			tx_offload_none		+= sq_stats->csum_none;
+			s->tx_csum_none		+= sq_stats->csum_none;
+			s->tx_csum_partial	+= sq_stats->csum_partial;
 		}
 	}
 
-	/* Update calculated offload counters */
-	s->tx_csum_partial = s->tx_packets - tx_offload_none - s->tx_csum_partial_inner;
-	s->rx_csum_unnecessary = s->rx_packets - s->rx_csum_none - s->rx_csum_complete;
-
 	s->link_down_events_phy = MLX5_GET(ppcnt_reg,
 				priv->stats.pport.phy_counters,
 				counter_set.phys_layer_cntrs.link_down_events);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index f1dd638384d3..15a1687483cc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -627,6 +627,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 
 	if (lro) {
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		rq->stats.csum_unnecessary++;
 		return;
 	}
 
@@ -644,7 +645,9 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 			skb->csum_level = 1;
 			skb->encapsulation = 1;
 			rq->stats.csum_unnecessary_inner++;
+			return;
 		}
+		rq->stats.csum_unnecessary++;
 		return;
 	}
 csum_none:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 6d199ffb1c0b..f8637213afc0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -68,6 +68,7 @@ struct mlx5e_sw_stats {
 	u64 rx_xdp_drop;
 	u64 rx_xdp_tx;
 	u64 rx_xdp_tx_full;
+	u64 tx_csum_none;
 	u64 tx_csum_partial;
 	u64 tx_csum_partial_inner;
 	u64 tx_queue_stopped;
@@ -108,6 +109,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_none) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial_inner) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_stopped) },
@@ -339,6 +341,7 @@ struct mlx5e_rq_stats {
 	u64 packets;
 	u64 bytes;
 	u64 csum_complete;
+	u64 csum_unnecessary;
 	u64 csum_unnecessary_inner;
 	u64 csum_none;
 	u64 lro_packets;
@@ -363,6 +366,7 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_drop) },
@@ -392,6 +396,7 @@ struct mlx5e_sq_stats {
 	u64 tso_bytes;
 	u64 tso_inner_packets;
 	u64 tso_inner_bytes;
+	u64 csum_partial;
 	u64 csum_partial_inner;
 	u64 nop;
 	/* less likely accessed in data path */
@@ -408,6 +413,7 @@ static const struct counter_desc sq_stats_desc[] = {
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_bytes) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_packets) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_bytes) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial_inner) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, nop) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_none) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index fee43e40fa16..1d6925d4369a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -193,6 +193,7 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct
 			sq->stats.csum_partial_inner++;
 		} else {
 			eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM;
+			sq->stats.csum_partial++;
 		}
 	} else
 		sq->stats.csum_none++;
-- 
cgit v1.2.3


From 480df991b869eff02a004e8fe7707900437cfcd4 Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Thu, 31 Aug 2017 18:52:14 +0300
Subject: net/mlx5: Fix static checker warning on steering tracepoints code

Fix this sparse complaint:

drivers/net/ethernet/mellanox/mlx5/core/./diag/fs_tracepoint.h:172:1:
	warning: odd constant _Bool cast (ffffffffffffffff becomes 1)

Fixes: d9fea79171ee ('net/mlx5: Add tracepoints')
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
index 1e3a6c3e4132..80eef4163f52 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
@@ -139,7 +139,7 @@ TRACE_EVENT(mlx5_fs_del_fg,
 	{MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO, "NEXT_PRIO"}
 
 TRACE_EVENT(mlx5_fs_set_fte,
-	    TP_PROTO(const struct fs_fte *fte, bool new_fte),
+	    TP_PROTO(const struct fs_fte *fte, int new_fte),
 	    TP_ARGS(fte, new_fte),
 	    TP_STRUCT__entry(
 		__field(const struct fs_fte *, fte)
@@ -149,7 +149,7 @@ TRACE_EVENT(mlx5_fs_set_fte,
 		__field(u32, action)
 		__field(u32, flow_tag)
 		__field(u8,  mask_enable)
-		__field(bool, new_fte)
+		__field(int, new_fte)
 		__array(u32, mask_outer, MLX5_ST_SZ_DW(fte_match_set_lyr_2_4))
 		__array(u32, mask_inner, MLX5_ST_SZ_DW(fte_match_set_lyr_2_4))
 		__array(u32, mask_misc, MLX5_ST_SZ_DW(fte_match_set_misc))
-- 
cgit v1.2.3


From 353f59f4d41e9c5798a15c5c52958f25b579a3d5 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Sun, 24 Sep 2017 09:54:00 +0200
Subject: net/mlx5: Fix wrong indentation in enable SRIOV code

Smatch is screaming:

drivers/net/ethernet/mellanox/mlx5/core/sriov.c:112
	mlx5_device_enable_sriov() warn: inconsistent indenting

fix that.

Fixes: 7ecf6d8ff154 ('IB/mlx5: Restore IB guid/policy for virtual functions')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/sriov.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index 6c48e9959b65..2a8b529ce6dd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -109,7 +109,7 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs)
 				mlx5_core_warn(dev,
 					       "failed to restore VF %d settings, err %d\n",
 					       vf, err);
-			continue;
+				continue;
 			}
 		}
 		mlx5_core_dbg(dev, "successfully enabled VF* %d\n", vf);
-- 
cgit v1.2.3


From 2580c4c17aee3ad58e9751012bad278dd074ccae Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Thu, 28 Sep 2017 11:32:37 +0200
Subject: tun: bail out from tun_get_user() if the skb is empty

KMSAN (https://github.com/google/kmsan) reported accessing uninitialized
skb->data[0] in the case the skb is empty (i.e. skb->len is 0):

================================================
BUG: KMSAN: use of uninitialized memory in tun_get_user+0x19ba/0x3770
CPU: 0 PID: 3051 Comm: probe Not tainted 4.13.0+ #3140
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
...
 __msan_warning_32+0x66/0xb0 mm/kmsan/kmsan_instr.c:477
 tun_get_user+0x19ba/0x3770 drivers/net/tun.c:1301
 tun_chr_write_iter+0x19f/0x300 drivers/net/tun.c:1365
 call_write_iter ./include/linux/fs.h:1743
 new_sync_write fs/read_write.c:457
 __vfs_write+0x6c3/0x7f0 fs/read_write.c:470
 vfs_write+0x3e4/0x770 fs/read_write.c:518
 SYSC_write+0x12f/0x2b0 fs/read_write.c:565
 SyS_write+0x55/0x80 fs/read_write.c:557
 do_syscall_64+0x242/0x330 arch/x86/entry/common.c:284
 entry_SYSCALL64_slow_path+0x25/0x25 arch/x86/entry/entry_64.S:245
...
origin:
...
 kmsan_poison_shadow+0x6e/0xc0 mm/kmsan/kmsan.c:211
 slab_alloc_node mm/slub.c:2732
 __kmalloc_node_track_caller+0x351/0x370 mm/slub.c:4351
 __kmalloc_reserve net/core/skbuff.c:138
 __alloc_skb+0x26a/0x810 net/core/skbuff.c:231
 alloc_skb ./include/linux/skbuff.h:903
 alloc_skb_with_frags+0x1d7/0xc80 net/core/skbuff.c:4756
 sock_alloc_send_pskb+0xabf/0xfe0 net/core/sock.c:2037
 tun_alloc_skb drivers/net/tun.c:1144
 tun_get_user+0x9a8/0x3770 drivers/net/tun.c:1274
 tun_chr_write_iter+0x19f/0x300 drivers/net/tun.c:1365
 call_write_iter ./include/linux/fs.h:1743
 new_sync_write fs/read_write.c:457
 __vfs_write+0x6c3/0x7f0 fs/read_write.c:470
 vfs_write+0x3e4/0x770 fs/read_write.c:518
 SYSC_write+0x12f/0x2b0 fs/read_write.c:565
 SyS_write+0x55/0x80 fs/read_write.c:557
 do_syscall_64+0x242/0x330 arch/x86/entry/common.c:284
 return_from_SYSCALL_64+0x0/0x6a arch/x86/entry/entry_64.S:245
================================================

Make sure tun_get_user() doesn't touch skb->data[0] unless there is
actual data.

C reproducer below:
==========================
    // autogenerated by syzkaller (http://github.com/google/syzkaller)

    #define _GNU_SOURCE

    #include <fcntl.h>
    #include <linux/if_tun.h>
    #include <netinet/ip.h>
    #include <net/if.h>
    #include <string.h>
    #include <sys/ioctl.h>

    int main()
    {
      int sock = socket(PF_INET, SOCK_STREAM, IPPROTO_IP);
      int tun_fd = open("/dev/net/tun", O_RDWR);
      struct ifreq req;
      memset(&req, 0, sizeof(struct ifreq));
      strcpy((char*)&req.ifr_name, "gre0");
      req.ifr_flags = IFF_UP | IFF_MULTICAST;
      ioctl(tun_fd, TUNSETIFF, &req);
      ioctl(sock, SIOCSIFFLAGS, "gre0");
      write(tun_fd, "hi", 0);
      return 0;
    }
==========================

Signed-off-by: Alexander Potapenko <glider@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 3c9985f29950..5ce580f413b9 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1496,11 +1496,13 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	switch (tun->flags & TUN_TYPE_MASK) {
 	case IFF_TUN:
 		if (tun->flags & IFF_NO_PI) {
-			switch (skb->data[0] & 0xf0) {
-			case 0x40:
+			u8 ip_version = skb->len ? (skb->data[0] >> 4) : 0;
+
+			switch (ip_version) {
+			case 4:
 				pi.proto = htons(ETH_P_IP);
 				break;
-			case 0x60:
+			case 6:
 				pi.proto = htons(ETH_P_IPV6);
 				break;
 			default:
-- 
cgit v1.2.3


From aff3da39211105a42b2108b8af79bf8e16f670fd Mon Sep 17 00:00:00 2001
From: Stefan Chulski <stefanc@marvell.com>
Date: Mon, 25 Sep 2017 14:59:46 +0200
Subject: net: mvpp2: fix parsing fragmentation detection

Parsing fragmentation detection failed due to wrong configured
parser TCAM entry's. Some traffic was marked as fragmented in RX
descriptor, even it wasn't IP fragmented. The hardware also failed to
calculate checksums which lead to use software checksum and caused
performance degradation.

Fixes: 3f518509dedc ("ethernet: Add new driver for Marvell Armada 375 network unit")
Signed-off-by: Antoine Tenart <antoine.tenart@free-electrons.com>
Signed-off-by: Stefan Chulski <stefanc@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2.c | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index dd0ee2691c86..da04939a2748 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -676,6 +676,7 @@ enum mvpp2_tag_type {
 #define MVPP2_PRS_RI_L3_MCAST			BIT(15)
 #define MVPP2_PRS_RI_L3_BCAST			(BIT(15) | BIT(16))
 #define MVPP2_PRS_RI_IP_FRAG_MASK		0x20000
+#define MVPP2_PRS_RI_IP_FRAG_TRUE		BIT(17)
 #define MVPP2_PRS_RI_UDF3_MASK			0x300000
 #define MVPP2_PRS_RI_UDF3_RX_SPECIAL		BIT(21)
 #define MVPP2_PRS_RI_L4_PROTO_MASK		0x1c00000
@@ -2315,7 +2316,7 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto,
 	    (proto != IPPROTO_IGMP))
 		return -EINVAL;
 
-	/* Fragmented packet */
+	/* Not fragmented packet */
 	tid = mvpp2_prs_tcam_first_free(priv, MVPP2_PE_FIRST_FREE_TID,
 					MVPP2_PE_LAST_FREE_TID);
 	if (tid < 0)
@@ -2334,8 +2335,12 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto,
 				  MVPP2_PRS_SRAM_OP_SEL_UDF_ADD);
 	mvpp2_prs_sram_ai_update(&pe, MVPP2_PRS_IPV4_DIP_AI_BIT,
 				 MVPP2_PRS_IPV4_DIP_AI_BIT);
-	mvpp2_prs_sram_ri_update(&pe, ri | MVPP2_PRS_RI_IP_FRAG_MASK,
-				 ri_mask | MVPP2_PRS_RI_IP_FRAG_MASK);
+	mvpp2_prs_sram_ri_update(&pe, ri, ri_mask | MVPP2_PRS_RI_IP_FRAG_MASK);
+
+	mvpp2_prs_tcam_data_byte_set(&pe, 2, 0x00,
+				     MVPP2_PRS_TCAM_PROTO_MASK_L);
+	mvpp2_prs_tcam_data_byte_set(&pe, 3, 0x00,
+				     MVPP2_PRS_TCAM_PROTO_MASK);
 
 	mvpp2_prs_tcam_data_byte_set(&pe, 5, proto, MVPP2_PRS_TCAM_PROTO_MASK);
 	mvpp2_prs_tcam_ai_update(&pe, 0, MVPP2_PRS_IPV4_DIP_AI_BIT);
@@ -2346,7 +2351,7 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto,
 	mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_IP4);
 	mvpp2_prs_hw_write(priv, &pe);
 
-	/* Not fragmented packet */
+	/* Fragmented packet */
 	tid = mvpp2_prs_tcam_first_free(priv, MVPP2_PE_FIRST_FREE_TID,
 					MVPP2_PE_LAST_FREE_TID);
 	if (tid < 0)
@@ -2358,8 +2363,11 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto,
 	pe.sram.word[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
 	mvpp2_prs_sram_ri_update(&pe, ri, ri_mask);
 
-	mvpp2_prs_tcam_data_byte_set(&pe, 2, 0x00, MVPP2_PRS_TCAM_PROTO_MASK_L);
-	mvpp2_prs_tcam_data_byte_set(&pe, 3, 0x00, MVPP2_PRS_TCAM_PROTO_MASK);
+	mvpp2_prs_sram_ri_update(&pe, ri | MVPP2_PRS_RI_IP_FRAG_TRUE,
+				 ri_mask | MVPP2_PRS_RI_IP_FRAG_MASK);
+
+	mvpp2_prs_tcam_data_byte_set(&pe, 2, 0x00, 0x0);
+	mvpp2_prs_tcam_data_byte_set(&pe, 3, 0x00, 0x0);
 
 	/* Update shadow table and hw entry */
 	mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_IP4);
-- 
cgit v1.2.3


From 6bf69a1d6334bed776875c5ca852594ab4e5b209 Mon Sep 17 00:00:00 2001
From: Yan Markman <ymarkman@marvell.com>
Date: Mon, 25 Sep 2017 14:59:47 +0200
Subject: net: mvpp2: fix port list indexing

The private port_list array has a list of pointers to mvpp2_port
instances. This list is allocated given the number of ports enabled in
the device tree, but the pointers are set using the port-id property. If
on a single port is enabled, the port_list array will be of size 1, but
when registering the port, if its id is not 0 the driver will crash.
Other crashes were encountered in various situations.

This fixes the issue by using an index not equal to the value of the
port-id property.

Fixes: 3f518509dedc ("ethernet: Add new driver for Marvell Armada 375 network unit")
Signed-off-by: Antoine Tenart <antoine.tenart@free-electrons.com>
Signed-off-by: Yan Markman <ymarkman@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index da04939a2748..b2f99df81e9c 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -7504,7 +7504,7 @@ static void mvpp2_port_copy_mac_addr(struct net_device *dev, struct mvpp2 *priv,
 /* Ports initialization */
 static int mvpp2_port_probe(struct platform_device *pdev,
 			    struct device_node *port_node,
-			    struct mvpp2 *priv)
+			    struct mvpp2 *priv, int index)
 {
 	struct device_node *phy_node;
 	struct phy *comphy;
@@ -7678,7 +7678,7 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	}
 	netdev_info(dev, "Using %s mac address %pM\n", mac_from, dev->dev_addr);
 
-	priv->port_list[id] = port;
+	priv->port_list[index] = port;
 	return 0;
 
 err_free_port_pcpu:
@@ -8013,10 +8013,12 @@ static int mvpp2_probe(struct platform_device *pdev)
 	}
 
 	/* Initialize ports */
+	i = 0;
 	for_each_available_child_of_node(dn, port_node) {
-		err = mvpp2_port_probe(pdev, port_node, priv);
+		err = mvpp2_port_probe(pdev, port_node, priv, i);
 		if (err < 0)
 			goto err_mg_clk;
+		i++;
 	}
 
 	platform_set_drvdata(pdev, priv);
-- 
cgit v1.2.3


From c7dfc8c848a48f176096f66a14879fb3333a460f Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@free-electrons.com>
Date: Mon, 25 Sep 2017 14:59:48 +0200
Subject: net: mvpp2: do not select the internal source clock

This patch stops the internal MAC Tx clock from being enabled as the
internal clock isn't used. The definition used for the bit controlling
this behaviour is renamed as well as it was wrongly named (bit 4 of
GMAC_CTRL_2_REG).

Fixes: 3919357fb0bb ("net: mvpp2: initialize the GMAC when using a port")
Signed-off-by: Antoine Tenart <antoine.tenart@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index b2f99df81e9c..161055564720 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -333,7 +333,7 @@
 #define     MVPP2_GMAC_INBAND_AN_MASK		BIT(0)
 #define     MVPP2_GMAC_FLOW_CTRL_MASK		GENMASK(2, 1)
 #define     MVPP2_GMAC_PCS_ENABLE_MASK		BIT(3)
-#define     MVPP2_GMAC_PORT_RGMII_MASK		BIT(4)
+#define     MVPP2_GMAC_INTERNAL_CLK_MASK	BIT(4)
 #define     MVPP2_GMAC_DISABLE_PADDING		BIT(5)
 #define     MVPP2_GMAC_PORT_RESET_MASK		BIT(6)
 #define MVPP2_GMAC_AUTONEG_CONFIG		0xc
@@ -4599,7 +4599,6 @@ static void mvpp2_port_mii_gmac_configure(struct mvpp2_port *port)
 	        val |= MVPP2_GMAC_INBAND_AN_MASK | MVPP2_GMAC_PCS_ENABLE_MASK;
 	} else if (phy_interface_mode_is_rgmii(port->phy_interface)) {
 		val &= ~MVPP2_GMAC_PCS_ENABLE_MASK;
-		val |= MVPP2_GMAC_PORT_RGMII_MASK;
 	}
 	writel(val, port->base + MVPP2_GMAC_CTRL_2_REG);
 
-- 
cgit v1.2.3


From 35f493b87ec072c5a2497ffbee243095ef725827 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 25 Sep 2017 08:40:02 -0700
Subject: inetpeer: fix RCU lookup() again

My prior fix was not complete, as we were dereferencing a pointer
three times per node, not twice as I initially thought.

Fixes: 4cc5b44b29a9 ("inetpeer: fix RCU lookup()")
Fixes: b145425f269a ("inetpeer: remove AVL implementation in favor of RB tree")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inetpeer.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index e7eb590c86ce..b20c8ac64081 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -128,9 +128,9 @@ static struct inet_peer *lookup(const struct inetpeer_addr *daddr,
 			break;
 		}
 		if (cmp == -1)
-			pp = &(*pp)->rb_left;
+			pp = &next->rb_left;
 		else
-			pp = &(*pp)->rb_right;
+			pp = &next->rb_right;
 	}
 	*parent_p = parent;
 	*pp_p = pp;
-- 
cgit v1.2.3


From db06ae41945b14feb7f696dcafe8048cc37e8a20 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Mon, 25 Sep 2017 23:32:20 +0200
Subject: net: dsa: mv88e6xxx: Allow dsa and cpu ports in multiple vlans

Ports with the same VLAN must all be in the same bridge. However the
CPU and DSA ports need to be in multiple VLANs spread over multiple
bridges. So exclude them when performing this test.

Fixes: b2f81d304cee ("net: dsa: add CPU and DSA ports as VLAN members")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index c6678aa9b4ef..674dab71d71c 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -1100,6 +1100,10 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port,
 	};
 	int i, err;
 
+	/* DSA and CPU ports have to be members of multiple vlans */
+	if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port))
+		return 0;
+
 	if (!vid_begin)
 		return -EOPNOTSUPP;
 
-- 
cgit v1.2.3


From e804441cfe0b60f6c430901946a69c01eac09df1 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 25 Sep 2017 15:55:53 -0700
Subject: net: dsa: Fix network device registration order

We cannot be registering the network device first, then setting its
carrier off and finally connecting it to a PHY, doing that leaves a
window during which the carrier is at best inconsistent, and at worse
the device is not usable without a down/up sequence since the network
device is visible to user space with possibly no PHY device attached.

Re-order steps so that they make logical sense. This fixes some devices
where the port was not usable after e.g: an unbind then bind of the
driver.

Fixes: 0071f56e46da ("dsa: Register netdev before phy")
Fixes: 91da11f870f0 ("net: Distributed Switch Architecture protocol support")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/slave.c | 31 ++++++++++++++++++-------------
 1 file changed, 18 insertions(+), 13 deletions(-)

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 2afa99506f8b..865e29e62bad 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1301,28 +1301,33 @@ int dsa_slave_create(struct dsa_port *port, const char *name)
 	p->old_duplex = -1;
 
 	port->netdev = slave_dev;
-	ret = register_netdev(slave_dev);
-	if (ret) {
-		netdev_err(master, "error %d registering interface %s\n",
-			   ret, slave_dev->name);
-		port->netdev = NULL;
-		free_percpu(p->stats64);
-		free_netdev(slave_dev);
-		return ret;
-	}
 
 	netif_carrier_off(slave_dev);
 
 	ret = dsa_slave_phy_setup(p, slave_dev);
 	if (ret) {
 		netdev_err(master, "error %d setting up slave phy\n", ret);
-		unregister_netdev(slave_dev);
-		free_percpu(p->stats64);
-		free_netdev(slave_dev);
-		return ret;
+		goto out_free;
+	}
+
+	ret = register_netdev(slave_dev);
+	if (ret) {
+		netdev_err(master, "error %d registering interface %s\n",
+			   ret, slave_dev->name);
+		goto out_phy;
 	}
 
 	return 0;
+
+out_phy:
+	phy_disconnect(p->phy);
+	if (of_phy_is_fixed_link(p->dp->dn))
+		of_phy_deregister_fixed_link(p->dp->dn);
+out_free:
+	free_percpu(p->stats64);
+	free_netdev(slave_dev);
+	port->netdev = NULL;
+	return ret;
 }
 
 void dsa_slave_destroy(struct net_device *slave_dev)
-- 
cgit v1.2.3


From 06d7a1b932c26afe2c0a1f4520ddd417d8eeda79 Mon Sep 17 00:00:00 2001
From: Ed Blake <ed.blake@sondrel.com>
Date: Tue, 26 Sep 2017 11:43:46 +0100
Subject: net: stmmac: dwc-qos: Add suspend / resume support

Add hook to stmmac_pltfr_pm_ops for suspend / resume handling.

Signed-off-by: Ed Blake <ed.blake@sondrel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index dd6a2f9791cc..5efef8001edf 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -511,6 +511,7 @@ static struct platform_driver dwc_eth_dwmac_driver = {
 	.remove = dwc_eth_dwmac_remove,
 	.driver = {
 		.name           = "dwc-eth-dwmac",
+		.pm             = &stmmac_pltfr_pm_ops,
 		.of_match_table = dwc_eth_dwmac_match,
 	},
 };
-- 
cgit v1.2.3


From 1579f678fb4397f9e439d2e373d4ade036c673b4 Mon Sep 17 00:00:00 2001
From: Ed Blake <ed.blake@sondrel.com>
Date: Tue, 26 Sep 2017 11:44:53 +0100
Subject: net: stmmac: dwmac4: Re-enable MAC Rx before powering down

Re-enable the MAC receiver by setting CONFIG_RE before powering down,
as instructed in section 6.3.5.1 of [1].  Without this the MAC fails
to receive WoL packets and never wakes up.

[1] DWC Ethernet QoS Databook 4.10a October 2014

Signed-off-by: Ed Blake <ed.blake@sondrel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index c4407e8e39a3..2f7d7ec59962 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -296,6 +296,7 @@ static void dwmac4_pmt(struct mac_device_info *hw, unsigned long mode)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	unsigned int pmt = 0;
+	u32 config;
 
 	if (mode & WAKE_MAGIC) {
 		pr_debug("GMAC: WOL Magic frame\n");
@@ -306,6 +307,12 @@ static void dwmac4_pmt(struct mac_device_info *hw, unsigned long mode)
 		pmt |= power_down | global_unicast | wake_up_frame_en;
 	}
 
+	if (pmt) {
+		/* The receiver must be enabled for WOL before powering down */
+		config = readl(ioaddr + GMAC_CONFIG);
+		config |= GMAC_CONFIG_RE;
+		writel(config, ioaddr + GMAC_CONFIG);
+	}
 	writel(pmt, ioaddr + GMAC_PMT);
 }
 
-- 
cgit v1.2.3


From 4971613c1639d8e5f102c4e797c3bf8f83a5a69e Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 26 Sep 2017 12:19:37 -0400
Subject: packet: in packet_do_bind, test fanout with bind_lock held

Once a socket has po->fanout set, it remains a member of the group
until it is destroyed. The prot_hook must be constant and identical
across sockets in the group.

If fanout_add races with packet_do_bind between the test of po->fanout
and taking the lock, the bind call may make type or dev inconsistent
with that of the fanout group.

Hold po->bind_lock when testing po->fanout to avoid this race.

I had to introduce artificial delay (local_bh_enable) to actually
observe the race.

Fixes: dc99f600698d ("packet: Add fanout support.")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index d288f52c53f7..a10c2836465c 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3069,13 +3069,15 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
 	int ret = 0;
 	bool unlisted = false;
 
-	if (po->fanout)
-		return -EINVAL;
-
 	lock_sock(sk);
 	spin_lock(&po->bind_lock);
 	rcu_read_lock();
 
+	if (po->fanout) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
 	if (name) {
 		dev = dev_get_by_name_rcu(sock_net(sk), name);
 		if (!dev) {
-- 
cgit v1.2.3


From da7c9561015e93d10fe6aab73e9288e0d09d65a6 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 26 Sep 2017 12:20:17 -0400
Subject: packet: only test po->has_vnet_hdr once in packet_snd

Packet socket option po->has_vnet_hdr can be updated concurrently with
other operations if no ring is attached.

Do not test the option twice in packet_snd, as the value may change in
between calls. A race on setsockopt disable may cause a packet > mtu
to be sent without having GSO options set.

Fixes: bfd5f4a3d605 ("packet: Add GSO/csum offload support.")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index a10c2836465c..bec01a3daf5b 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2840,6 +2840,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	struct virtio_net_hdr vnet_hdr = { 0 };
 	int offset = 0;
 	struct packet_sock *po = pkt_sk(sk);
+	bool has_vnet_hdr = false;
 	int hlen, tlen, linear;
 	int extra_len = 0;
 
@@ -2883,6 +2884,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		err = packet_snd_vnet_parse(msg, &len, &vnet_hdr);
 		if (err)
 			goto out_unlock;
+		has_vnet_hdr = true;
 	}
 
 	if (unlikely(sock_flag(sk, SOCK_NOFCS))) {
@@ -2941,7 +2943,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	skb->priority = sk->sk_priority;
 	skb->mark = sockc.mark;
 
-	if (po->has_vnet_hdr) {
+	if (has_vnet_hdr) {
 		err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le());
 		if (err)
 			goto out_free;
-- 
cgit v1.2.3


From b32ca44a88def4bf92626d8777494c6f14638c42 Mon Sep 17 00:00:00 2001
From: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Date: Tue, 26 Sep 2017 14:57:21 -0400
Subject: net: dsa: mv88e6xxx: lock mutex when freeing IRQs

mv88e6xxx_g2_irq_free locks the registers mutex, but not
mv88e6xxx_g1_irq_free, which results in a stack trace from
assert_reg_lock when unloading the mv88e6xxx module. Fix this.

Fixes: 3460a5770ce9 ("net: dsa: mv88e6xxx: Mask g1 interrupts and free interrupt")
Signed-off-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 674dab71d71c..d74c7335c512 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -3951,7 +3951,9 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev)
 	if (chip->irq > 0) {
 		if (chip->info->g2_irqs > 0)
 			mv88e6xxx_g2_irq_free(chip);
+		mutex_lock(&chip->reg_lock);
 		mv88e6xxx_g1_irq_free(chip);
+		mutex_unlock(&chip->reg_lock);
 	}
 }
 
-- 
cgit v1.2.3


From 9d538fa60bad4f7b23193c89e843797a1cf71ef3 Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Tue, 26 Sep 2017 17:38:50 -0700
Subject: net: Set sk_prot_creator when cloning sockets to the right proto

sk->sk_prot and sk->sk_prot_creator can differ when the app uses
IPV6_ADDRFORM (transforming an IPv6-socket to an IPv4-one).
Which is why sk_prot_creator is there to make sure that sk_prot_free()
does the kmem_cache_free() on the right kmem_cache slab.

Now, if such a socket gets transformed back to a listening socket (using
connect() with AF_UNSPEC) we will allocate an IPv4 tcp_sock through
sk_clone_lock() when a new connection comes in. But sk_prot_creator will
still point to the IPv6 kmem_cache (as everything got copied in
sk_clone_lock()). When freeing, we will thus put this
memory back into the IPv6 kmem_cache although it was allocated in the
IPv4 cache. I have seen memory corruption happening because of this.

With slub-debugging and MEMCG_KMEM enabled this gives the warning
	"cache_from_obj: Wrong slab cache. TCPv6 but object is from TCP"

A C-program to trigger this:

void main(void)
{
        int fd = socket(AF_INET6, SOCK_STREAM, IPPROTO_TCP);
        int new_fd, newest_fd, client_fd;
        struct sockaddr_in6 bind_addr;
        struct sockaddr_in bind_addr4, client_addr1, client_addr2;
        struct sockaddr unsp;
        int val;

        memset(&bind_addr, 0, sizeof(bind_addr));
        bind_addr.sin6_family = AF_INET6;
        bind_addr.sin6_port = ntohs(42424);

        memset(&client_addr1, 0, sizeof(client_addr1));
        client_addr1.sin_family = AF_INET;
        client_addr1.sin_port = ntohs(42424);
        client_addr1.sin_addr.s_addr = inet_addr("127.0.0.1");

        memset(&client_addr2, 0, sizeof(client_addr2));
        client_addr2.sin_family = AF_INET;
        client_addr2.sin_port = ntohs(42421);
        client_addr2.sin_addr.s_addr = inet_addr("127.0.0.1");

        memset(&unsp, 0, sizeof(unsp));
        unsp.sa_family = AF_UNSPEC;

        bind(fd, (struct sockaddr *)&bind_addr, sizeof(bind_addr));

        listen(fd, 5);

        client_fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
        connect(client_fd, (struct sockaddr *)&client_addr1, sizeof(client_addr1));
        new_fd = accept(fd, NULL, NULL);
        close(fd);

        val = AF_INET;
        setsockopt(new_fd, SOL_IPV6, IPV6_ADDRFORM, &val, sizeof(val));

        connect(new_fd, &unsp, sizeof(unsp));

        memset(&bind_addr4, 0, sizeof(bind_addr4));
        bind_addr4.sin_family = AF_INET;
        bind_addr4.sin_port = ntohs(42421);
        bind(new_fd, (struct sockaddr *)&bind_addr4, sizeof(bind_addr4));

        listen(new_fd, 5);

        client_fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
        connect(client_fd, (struct sockaddr *)&client_addr2, sizeof(client_addr2));

        newest_fd = accept(new_fd, NULL, NULL);
        close(new_fd);

        close(client_fd);
        close(new_fd);
}

As far as I can see, this bug has been there since the beginning of the
git-days.

Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/sock.c b/net/core/sock.c
index 9b7b6bbb2a23..7d55c05f449d 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1654,6 +1654,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 
 		sock_copy(newsk, sk);
 
+		newsk->sk_prot_creator = sk->sk_prot;
+
 		/* SANITY */
 		if (likely(newsk->sk_net_refcnt))
 			get_net(sock_net(newsk));
-- 
cgit v1.2.3


From fef0035c0f31322d417d1954bba5ab959bf91183 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Thu, 28 Sep 2017 00:41:44 +0200
Subject: netlink: do not proceed if dump's start() errs

Drivers that use the start method for netlink dumping rely on dumpit not
being called if start fails. For example, ila_xlat.c allocates memory
and assigns it to cb->args[0] in its start() function. It might fail to
do that and return -ENOMEM instead. However, even when returning an
error, dumpit will be called, which, in the example above, quickly
dereferences the memory in cb->args[0], which will OOPS the kernel. This
is but one example of how this goes wrong.

Since start() has always been a function with an int return type, it
therefore makes sense to use it properly, rather than ignoring it. This
patch thus returns early and does not call dumpit() when start() fails.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 327807731b44..94c11cf0459d 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2270,10 +2270,13 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 
 	mutex_unlock(nlk->cb_mutex);
 
+	ret = 0;
 	if (cb->start)
-		cb->start(cb);
+		ret = cb->start(cb);
+
+	if (!ret)
+		ret = netlink_dump(sk);
 
-	ret = netlink_dump(sk);
 	sock_put(sk);
 
 	if (ret)
-- 
cgit v1.2.3


From d51711c0557d6dbd26c63144aef32c7b3ec264b9 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 28 Sep 2017 13:23:31 +0800
Subject: ip_gre: ipgre_tap device should keep dst

Without keeping dst, the tunnel will not update any mtu/pmtu info,
since it does not have a dst on the skb.

Reproducer:
  client(ipgre_tap1 - eth1) <-----> (eth1 - ipgre_tap1)server

After reducing eth1's mtu on client, then perforamnce became 0.

This patch is to netif_keep_dst in gre_tap_init, as ipgre does.

Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 0162fb955b33..8b837f6f5532 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1223,6 +1223,7 @@ static int gre_tap_init(struct net_device *dev)
 {
 	__gre_tunnel_init(dev);
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+	netif_keep_dst(dev);
 
 	return ip_tunnel_init(dev);
 }
-- 
cgit v1.2.3


From 2d40557cc702ed8e5edd9bd422233f86652d932e Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 28 Sep 2017 13:23:50 +0800
Subject: ip6_gre: ip6gre_tap device should keep dst

The patch 'ip_gre: ipgre_tap device should keep dst' fixed
a issue that ipgre_tap mtu couldn't be updated in tx path.

The same fix is needed for ip6gre_tap as well.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 20f66f4c9460..1602b491b281 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1311,6 +1311,7 @@ static void ip6gre_tap_setup(struct net_device *dev)
 	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+	netif_keep_dst(dev);
 }
 
 static bool ip6gre_netlink_encap_parms(struct nlattr *data[],
-- 
cgit v1.2.3


From d41bb33ba33b8f8debe54ed36be6925eb496e354 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 28 Sep 2017 13:24:07 +0800
Subject: ip6_tunnel: update mtu properly for ARPHRD_ETHER tunnel device in tx
 path

Now when updating mtu in tx path, it doesn't consider ARPHRD_ETHER tunnel
device, like ip6gre_tap tunnel, for which it should also subtract ether
header to get the correct mtu.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index f2f21c24915f..a1c24443cd9e 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1043,6 +1043,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	struct dst_entry *dst = NULL, *ndst = NULL;
 	struct net_device *tdev;
 	int mtu;
+	unsigned int eth_hlen = t->dev->type == ARPHRD_ETHER ? ETH_HLEN : 0;
 	unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen;
 	unsigned int max_headroom = psh_hlen;
 	bool use_cache = false;
@@ -1124,7 +1125,7 @@ route_lookup:
 				     t->parms.name);
 		goto tx_err_dst_release;
 	}
-	mtu = dst_mtu(dst) - psh_hlen - t->tun_hlen;
+	mtu = dst_mtu(dst) - eth_hlen - psh_hlen - t->tun_hlen;
 	if (encap_limit >= 0) {
 		max_headroom += 8;
 		mtu -= 8;
@@ -1133,7 +1134,7 @@ route_lookup:
 		mtu = IPV6_MIN_MTU;
 	if (skb_dst(skb) && !t->parms.collect_md)
 		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
-	if (skb->len - t->tun_hlen > mtu && !skb_is_gso(skb)) {
+	if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) {
 		*pmtu = mtu;
 		err = -EMSGSIZE;
 		goto tx_err_dst_release;
-- 
cgit v1.2.3


From 7487449c86c65202b3b725c4524cb48dd65e4e6f Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 28 Sep 2017 15:51:36 +0200
Subject: IPv4: early demux can return an error code

Currently no error is emitted, but this infrastructure will
used by the next patch to allow source address validation
for mcast sockets.
Since early demux can do a route lookup and an ipv4 route
lookup can return an error code this is consistent with the
current ipv4 route infrastructure.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/protocol.h |  4 ++--
 include/net/tcp.h      |  2 +-
 include/net/udp.h      |  2 +-
 net/ipv4/ip_input.c    | 25 +++++++++++++++----------
 net/ipv4/tcp_ipv4.c    |  9 +++++----
 net/ipv4/udp.c         | 11 ++++++-----
 6 files changed, 30 insertions(+), 23 deletions(-)

diff --git a/include/net/protocol.h b/include/net/protocol.h
index 65ba335b0e7e..4fc75f7ae23b 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -39,8 +39,8 @@
 
 /* This is used to register protocols. */
 struct net_protocol {
-	void			(*early_demux)(struct sk_buff *skb);
-	void                    (*early_demux_handler)(struct sk_buff *skb);
+	int			(*early_demux)(struct sk_buff *skb);
+	int			(*early_demux_handler)(struct sk_buff *skb);
 	int			(*handler)(struct sk_buff *skb);
 	void			(*err_handler)(struct sk_buff *skb, u32 info);
 	unsigned int		no_policy:1,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3bc910a9bfc6..89974c5286d8 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -345,7 +345,7 @@ void tcp_v4_err(struct sk_buff *skb, u32);
 
 void tcp_shutdown(struct sock *sk, int how);
 
-void tcp_v4_early_demux(struct sk_buff *skb);
+int tcp_v4_early_demux(struct sk_buff *skb);
 int tcp_v4_rcv(struct sk_buff *skb);
 
 int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
diff --git a/include/net/udp.h b/include/net/udp.h
index 12dfbfe2e2d7..6c759c8594e2 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -259,7 +259,7 @@ static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags,
 	return __skb_recv_udp(sk, flags, noblock, &peeked, &off, err);
 }
 
-void udp_v4_early_demux(struct sk_buff *skb);
+int udp_v4_early_demux(struct sk_buff *skb);
 bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst);
 int udp_get_port(struct sock *sk, unsigned short snum,
 		 int (*saddr_cmp)(const struct sock *,
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index fa2dc8f692c6..57fc13c6ab2b 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -311,9 +311,10 @@ drop:
 static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	const struct iphdr *iph = ip_hdr(skb);
-	struct rtable *rt;
+	int (*edemux)(struct sk_buff *skb);
 	struct net_device *dev = skb->dev;
-	void (*edemux)(struct sk_buff *skb);
+	struct rtable *rt;
+	int err;
 
 	/* if ingress device is enslaved to an L3 master device pass the
 	 * skb to its handler for processing
@@ -331,7 +332,9 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 
 		ipprot = rcu_dereference(inet_protos[protocol]);
 		if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) {
-			edemux(skb);
+			err = edemux(skb);
+			if (unlikely(err))
+				goto drop_error;
 			/* must reload iph, skb->head might have changed */
 			iph = ip_hdr(skb);
 		}
@@ -342,13 +345,10 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 	 *	how the packet travels inside Linux networking.
 	 */
 	if (!skb_valid_dst(skb)) {
-		int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
-					       iph->tos, dev);
-		if (unlikely(err)) {
-			if (err == -EXDEV)
-				__NET_INC_STATS(net, LINUX_MIB_IPRPFILTER);
-			goto drop;
-		}
+		err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
+					   iph->tos, dev);
+		if (unlikely(err))
+			goto drop_error;
 	}
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
@@ -399,6 +399,11 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 drop:
 	kfree_skb(skb);
 	return NET_RX_DROP;
+
+drop_error:
+	if (err == -EXDEV)
+		__NET_INC_STATS(net, LINUX_MIB_IPRPFILTER);
+	goto drop;
 }
 
 /*
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d9416b5162bc..85164d4d3e53 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1503,23 +1503,23 @@ csum_err:
 }
 EXPORT_SYMBOL(tcp_v4_do_rcv);
 
-void tcp_v4_early_demux(struct sk_buff *skb)
+int tcp_v4_early_demux(struct sk_buff *skb)
 {
 	const struct iphdr *iph;
 	const struct tcphdr *th;
 	struct sock *sk;
 
 	if (skb->pkt_type != PACKET_HOST)
-		return;
+		return 0;
 
 	if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr)))
-		return;
+		return 0;
 
 	iph = ip_hdr(skb);
 	th = tcp_hdr(skb);
 
 	if (th->doff < sizeof(struct tcphdr) / 4)
-		return;
+		return 0;
 
 	sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo,
 				       iph->saddr, th->source,
@@ -1538,6 +1538,7 @@ void tcp_v4_early_demux(struct sk_buff *skb)
 				skb_dst_set_noref(skb, dst);
 		}
 	}
+	return 0;
 }
 
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ef29df8648e4..9b30f821fe96 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2221,7 +2221,7 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
 	return NULL;
 }
 
-void udp_v4_early_demux(struct sk_buff *skb)
+int udp_v4_early_demux(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
 	const struct iphdr *iph;
@@ -2234,7 +2234,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
 
 	/* validate the packet */
 	if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
-		return;
+		return 0;
 
 	iph = ip_hdr(skb);
 	uh = udp_hdr(skb);
@@ -2244,14 +2244,14 @@ void udp_v4_early_demux(struct sk_buff *skb)
 		struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
 
 		if (!in_dev)
-			return;
+			return 0;
 
 		/* we are supposed to accept bcast packets */
 		if (skb->pkt_type == PACKET_MULTICAST) {
 			ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
 					       iph->protocol);
 			if (!ours)
-				return;
+				return 0;
 		}
 
 		sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
@@ -2263,7 +2263,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
 	}
 
 	if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt))
-		return;
+		return 0;
 
 	skb->sk = sk;
 	skb->destructor = sock_efree;
@@ -2278,6 +2278,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
 		 */
 		skb_dst_set_noref(skb, dst);
 	}
+	return 0;
 }
 
 int udp_rcv(struct sk_buff *skb)
-- 
cgit v1.2.3


From bc044e8db7962e727a75b591b9851ff2ac5cf846 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 28 Sep 2017 15:51:37 +0200
Subject: udp: perform source validation for mcast early demux

The UDP early demux can leverate the rx dst cache even for
multicast unconnected sockets.

In such scenario the ipv4 source address is validated only on
the first packet in the given flow. After that, when we fetch
the dst entry  from the socket rx cache, we stop enforcing
the rp_filter and we even start accepting any kind of martian
addresses.

Disabling the dst cache for unconnected multicast socket will
cause large performace regression, nearly reducing by half the
max ingress tput.

Instead we factor out a route helper to completely validate an
skb source address for multicast packets and we call it from
the UDP early demux for mcast packets landing on unconnected
sockets, after successful fetching the related cached dst entry.

This still gives a measurable, but limited performance
regression:

		rp_filter = 0		rp_filter = 1
edmux disabled:	1182 Kpps		1127 Kpps
edmux before:	2238 Kpps		2238 Kpps
edmux after:	2037 Kpps		2019 Kpps

The above figures are on top of current net tree.
Applying the net-next commit 6e617de84e87 ("net: avoid a full
fib lookup when rp_filter is disabled.") the delta with
rp_filter == 0 will decrease even more.

Fixes: 421b3885bf6d ("udp: ipv4: Add udp early demux")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/route.h |  4 +++-
 net/ipv4/route.c    | 46 ++++++++++++++++++++++++++--------------------
 net/ipv4/udp.c      | 13 ++++++++++++-
 3 files changed, 41 insertions(+), 22 deletions(-)

diff --git a/include/net/route.h b/include/net/route.h
index 57dfc6850d37..d538e6db1afe 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -175,7 +175,9 @@ static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4
 	fl4->fl4_gre_key = gre_key;
 	return ip_route_output_key(net, fl4);
 }
-
+int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+			  u8 tos, struct net_device *dev,
+			  struct in_device *in_dev, u32 *itag);
 int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
 			 u8 tos, struct net_device *devin);
 int ip_route_input_rcu(struct sk_buff *skb, __be32 dst, __be32 src,
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 94d4cd2d5ea4..ac6fde5d45f1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1520,43 +1520,56 @@ struct rtable *rt_dst_alloc(struct net_device *dev,
 EXPORT_SYMBOL(rt_dst_alloc);
 
 /* called in rcu_read_lock() section */
-static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
-				u8 tos, struct net_device *dev, int our)
+int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+			  u8 tos, struct net_device *dev,
+			  struct in_device *in_dev, u32 *itag)
 {
-	struct rtable *rth;
-	struct in_device *in_dev = __in_dev_get_rcu(dev);
-	unsigned int flags = RTCF_MULTICAST;
-	u32 itag = 0;
 	int err;
 
 	/* Primary sanity checks. */
-
 	if (!in_dev)
 		return -EINVAL;
 
 	if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||
 	    skb->protocol != htons(ETH_P_IP))
-		goto e_inval;
+		return -EINVAL;
 
 	if (ipv4_is_loopback(saddr) && !IN_DEV_ROUTE_LOCALNET(in_dev))
-		goto e_inval;
+		return -EINVAL;
 
 	if (ipv4_is_zeronet(saddr)) {
 		if (!ipv4_is_local_multicast(daddr))
-			goto e_inval;
+			return -EINVAL;
 	} else {
 		err = fib_validate_source(skb, saddr, 0, tos, 0, dev,
-					  in_dev, &itag);
+					  in_dev, itag);
 		if (err < 0)
-			goto e_err;
+			return err;
 	}
+	return 0;
+}
+
+/* called in rcu_read_lock() section */
+static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+			     u8 tos, struct net_device *dev, int our)
+{
+	struct in_device *in_dev = __in_dev_get_rcu(dev);
+	unsigned int flags = RTCF_MULTICAST;
+	struct rtable *rth;
+	u32 itag = 0;
+	int err;
+
+	err = ip_mc_validate_source(skb, daddr, saddr, tos, dev, in_dev, &itag);
+	if (err)
+		return err;
+
 	if (our)
 		flags |= RTCF_LOCAL;
 
 	rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST,
 			   IN_DEV_CONF_GET(in_dev, NOPOLICY), false, false);
 	if (!rth)
-		goto e_nobufs;
+		return -ENOBUFS;
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	rth->dst.tclassid = itag;
@@ -1572,13 +1585,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 
 	skb_dst_set(skb, &rth->dst);
 	return 0;
-
-e_nobufs:
-	return -ENOBUFS;
-e_inval:
-	return -EINVAL;
-e_err:
-	return err;
 }
 
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 9b30f821fe96..5676237d2b0f 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2224,6 +2224,7 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
 int udp_v4_early_demux(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
+	struct in_device *in_dev = NULL;
 	const struct iphdr *iph;
 	const struct udphdr *uh;
 	struct sock *sk = NULL;
@@ -2241,7 +2242,7 @@ int udp_v4_early_demux(struct sk_buff *skb)
 
 	if (skb->pkt_type == PACKET_BROADCAST ||
 	    skb->pkt_type == PACKET_MULTICAST) {
-		struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
+		in_dev = __in_dev_get_rcu(skb->dev);
 
 		if (!in_dev)
 			return 0;
@@ -2272,11 +2273,21 @@ int udp_v4_early_demux(struct sk_buff *skb)
 	if (dst)
 		dst = dst_check(dst, 0);
 	if (dst) {
+		u32 itag = 0;
+
 		/* set noref for now.
 		 * any place which wants to hold dst has to call
 		 * dst_hold_safe()
 		 */
 		skb_dst_set_noref(skb, dst);
+
+		/* for unconnected multicast sockets we need to validate
+		 * the source on each packet
+		 */
+		if (!inet_sk(sk)->inet_daddr && in_dev)
+			return ip_mc_validate_source(skb, iph->daddr,
+						     iph->saddr, iph->tos,
+						     skb->dev, in_dev, &itag);
 	}
 	return 0;
 }
-- 
cgit v1.2.3


From 5a59a3a0ef0e546626a762d49dc06feaa204bab3 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Thu, 28 Sep 2017 17:57:58 +0200
Subject: ppp: fix __percpu annotation

Move sparse annotation right after pointer type.

Fixes sparse warning:
    drivers/net/ppp/ppp_generic.c:1422:13: warning: incorrect type in initializer (different address spaces)
    drivers/net/ppp/ppp_generic.c:1422:13:    expected void const [noderef] <asn:3>*__vpp_verify
    drivers/net/ppp/ppp_generic.c:1422:13:    got int *<noident>
    ...

Fixes: e5dadc65f9e0 ("ppp: Fix false xmit recursion detect with two ppp devices")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index a404552555d4..c3f77e3b7819 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -120,7 +120,7 @@ struct ppp {
 	int		n_channels;	/* how many channels are attached 54 */
 	spinlock_t	rlock;		/* lock for receive side 58 */
 	spinlock_t	wlock;		/* lock for transmit side 5c */
-	int		*xmit_recursion __percpu; /* xmit recursion detect */
+	int __percpu	*xmit_recursion; /* xmit recursion detect */
 	int		mru;		/* max receive unit 60 */
 	unsigned int	flags;		/* control bits 64 */
 	unsigned int	xstate;		/* transmit state bits 68 */
-- 
cgit v1.2.3


From aad06212d36cf34859428a0a279e5c14ee5c9e26 Mon Sep 17 00:00:00 2001
From: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Date: Fri, 29 Sep 2017 10:02:54 +0200
Subject: tipc: use only positive error codes in messages

In commit e3a77561e7d32 ("tipc: split up function tipc_msg_eval()"),
we have updated the function tipc_msg_lookup_dest() to set the error
codes to negative values at destination lookup failures. Thus when
the function sets the error code to -TIPC_ERR_NO_NAME, its inserted
into the 4 bit error field of the message header as 0xf instead of
TIPC_ERR_NO_NAME (1). The value 0xf is an unknown error code.

In this commit, we set only positive error code.

Fixes: e3a77561e7d32 ("tipc: split up function tipc_msg_eval()")
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/msg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 6ef379f004ac..121e59a1d0e7 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -551,7 +551,7 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err)
 		return false;
 	if (msg_errcode(msg))
 		return false;
-	*err = -TIPC_ERR_NO_NAME;
+	*err = TIPC_ERR_NO_NAME;
 	if (skb_linearize(skb))
 		return false;
 	msg = buf_msg(skb);
-- 
cgit v1.2.3


From 935a9749a36828af0e8be224a5cd4bc758112c34 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 1 Oct 2017 22:00:53 +0800
Subject: ip_gre: get key from session_id correctly in erspan_rcv

erspan only uses the first 10 bits of session_id as the key to look
up the tunnel. But in erspan_rcv, it missed 'session_id & ID_MASK'
when getting the key from session_id.

If any other flag is also set in session_id in a packet, it would
fail to find the tunnel due to incorrect key in erspan_rcv.

This patch is to add 'session_id & ID_MASK' there and also remove
the unnecessary variable session_id.

Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 8b837f6f5532..b25b1e5112d0 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -259,7 +259,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 	struct ip_tunnel *tunnel;
 	struct erspanhdr *ershdr;
 	const struct iphdr *iph;
-	__be32 session_id;
 	__be32 index;
 	int len;
 
@@ -275,8 +274,7 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 	/* The original GRE header does not have key field,
 	 * Use ERSPAN 10-bit session ID as key.
 	 */
-	session_id = cpu_to_be32(ntohs(ershdr->session_id));
-	tpi->key = session_id;
+	tpi->key = cpu_to_be32(ntohs(ershdr->session_id) & ID_MASK);
 	index = ershdr->md.index;
 	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex,
 				  tpi->flags | TUNNEL_KEY,
-- 
cgit v1.2.3


From 5513d08d29511c263c00933c00dd7a82fffda3c9 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 1 Oct 2017 22:00:54 +0800
Subject: ip_gre: check packet length and mtu correctly in erspan_xmit

As a ARPHRD_ETHER device, skb->len in erspan_xmit is the length
of the whole ether packet. So before checking if a packet size
exceeds the mtu, skb->len should subtract dev->hard_header_len.

Otherwise, all packets with max size according to mtu would be
trimmed to be truncated packet.

Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index b25b1e5112d0..2a4ef9dc48ff 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -731,7 +731,7 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb,
 	if (skb_cow_head(skb, dev->needed_headroom))
 		goto free_skb;
 
-	if (skb->len > dev->mtu) {
+	if (skb->len - dev->hard_header_len > dev->mtu) {
 		pskb_trim(skb, dev->mtu);
 		truncate = true;
 	}
-- 
cgit v1.2.3


From c122fda271717f4fc618e0a31e833941fd5f1efd Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 1 Oct 2017 22:00:55 +0800
Subject: ip_gre: set tunnel hlen properly in erspan_tunnel_init

According to __gre_tunnel_init, tunnel->hlen should be set as the
headers' length between inner packet and outer iphdr.

It would be used especially to calculate a proper mtu when updating
mtu in tnl_update_pmtu. Now without setting it, a bigger mtu value
than expected would be updated, which hurts performance a lot.

This patch is to fix it by setting tunnel->hlen with:
   tunnel->tun_hlen + tunnel->encap_hlen + sizeof(struct erspanhdr)

Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 2a4ef9dc48ff..fad0bb1e3e9a 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1245,7 +1245,9 @@ static int erspan_tunnel_init(struct net_device *dev)
 
 	tunnel->tun_hlen = 8;
 	tunnel->parms.iph.protocol = IPPROTO_GRE;
-	t_hlen = tunnel->hlen + sizeof(struct iphdr) + sizeof(struct erspanhdr);
+	tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen +
+		       sizeof(struct erspanhdr);
+	t_hlen = tunnel->hlen + sizeof(struct iphdr);
 
 	dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4;
 	dev->mtu = ETH_DATA_LEN - t_hlen - 4;
-- 
cgit v1.2.3


From c84bed440e4e11a973e8c0254d0dfaccfca41fb0 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 1 Oct 2017 22:00:56 +0800
Subject: ip_gre: erspan device should keep dst

The patch 'ip_gre: ipgre_tap device should keep dst' fixed
the issue ipgre_tap dev mtu couldn't be updated in tx path.

The same fix is needed for erspan as well.

Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index fad0bb1e3e9a..467e44d7587d 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1254,6 +1254,7 @@ static int erspan_tunnel_init(struct net_device *dev)
 	dev->features		|= GRE_FEATURES;
 	dev->hw_features	|= GRE_FEATURES;
 	dev->priv_flags		|= IFF_LIVE_ADDR_CHANGE;
+	netif_keep_dst(dev);
 
 	return ip_tunnel_init(dev);
 }
-- 
cgit v1.2.3


From 9f775ead5e570e7e19015b9e4e2f3dd6e71a5935 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Thu, 28 Sep 2017 15:44:38 +0200
Subject: l2tp: fix l2tp_eth module loading

The l2tp_eth module crashes if its netlink callbacks are run when the
pernet data aren't initialised.

We should normally register_pernet_device() before the genl callbacks.
However, the pernet data only maintain a list of l2tpeth interfaces,
and this list is never used. So let's just drop pernet handling
instead.

Fixes: d9e31d17ceba ("l2tp: Add L2TP ethernet pseudowire support")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_eth.c | 51 ++-------------------------------------------------
 1 file changed, 2 insertions(+), 49 deletions(-)

diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 87da9ef61860..014a7bc2a872 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -44,7 +44,6 @@ struct l2tp_eth {
 	struct net_device	*dev;
 	struct sock		*tunnel_sock;
 	struct l2tp_session	*session;
-	struct list_head	list;
 	atomic_long_t		tx_bytes;
 	atomic_long_t		tx_packets;
 	atomic_long_t		tx_dropped;
@@ -58,17 +57,6 @@ struct l2tp_eth_sess {
 	struct net_device	*dev;
 };
 
-/* per-net private data for this module */
-static unsigned int l2tp_eth_net_id;
-struct l2tp_eth_net {
-	struct list_head l2tp_eth_dev_list;
-	spinlock_t l2tp_eth_lock;
-};
-
-static inline struct l2tp_eth_net *l2tp_eth_pernet(struct net *net)
-{
-	return net_generic(net, l2tp_eth_net_id);
-}
 
 static int l2tp_eth_dev_init(struct net_device *dev)
 {
@@ -84,12 +72,6 @@ static int l2tp_eth_dev_init(struct net_device *dev)
 
 static void l2tp_eth_dev_uninit(struct net_device *dev)
 {
-	struct l2tp_eth *priv = netdev_priv(dev);
-	struct l2tp_eth_net *pn = l2tp_eth_pernet(dev_net(dev));
-
-	spin_lock(&pn->l2tp_eth_lock);
-	list_del_init(&priv->list);
-	spin_unlock(&pn->l2tp_eth_lock);
 	dev_put(dev);
 }
 
@@ -273,7 +255,6 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel,
 	struct l2tp_eth *priv;
 	struct l2tp_eth_sess *spriv;
 	int rc;
-	struct l2tp_eth_net *pn;
 
 	if (cfg->ifname) {
 		strlcpy(name, cfg->ifname, IFNAMSIZ);
@@ -305,7 +286,6 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel,
 	priv = netdev_priv(dev);
 	priv->dev = dev;
 	priv->session = session;
-	INIT_LIST_HEAD(&priv->list);
 
 	priv->tunnel_sock = tunnel->sock;
 	session->recv_skb = l2tp_eth_dev_recv;
@@ -326,10 +306,6 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel,
 	strlcpy(session->ifname, dev->name, IFNAMSIZ);
 
 	dev_hold(dev);
-	pn = l2tp_eth_pernet(dev_net(dev));
-	spin_lock(&pn->l2tp_eth_lock);
-	list_add(&priv->list, &pn->l2tp_eth_dev_list);
-	spin_unlock(&pn->l2tp_eth_lock);
 
 	return 0;
 
@@ -342,22 +318,6 @@ out:
 	return rc;
 }
 
-static __net_init int l2tp_eth_init_net(struct net *net)
-{
-	struct l2tp_eth_net *pn = net_generic(net, l2tp_eth_net_id);
-
-	INIT_LIST_HEAD(&pn->l2tp_eth_dev_list);
-	spin_lock_init(&pn->l2tp_eth_lock);
-
-	return 0;
-}
-
-static struct pernet_operations l2tp_eth_net_ops = {
-	.init = l2tp_eth_init_net,
-	.id   = &l2tp_eth_net_id,
-	.size = sizeof(struct l2tp_eth_net),
-};
-
 
 static const struct l2tp_nl_cmd_ops l2tp_eth_nl_cmd_ops = {
 	.session_create	= l2tp_eth_create,
@@ -371,25 +331,18 @@ static int __init l2tp_eth_init(void)
 
 	err = l2tp_nl_register_ops(L2TP_PWTYPE_ETH, &l2tp_eth_nl_cmd_ops);
 	if (err)
-		goto out;
-
-	err = register_pernet_device(&l2tp_eth_net_ops);
-	if (err)
-		goto out_unreg;
+		goto err;
 
 	pr_info("L2TP ethernet pseudowire support (L2TPv3)\n");
 
 	return 0;
 
-out_unreg:
-	l2tp_nl_unregister_ops(L2TP_PWTYPE_ETH);
-out:
+err:
 	return err;
 }
 
 static void __exit l2tp_eth_exit(void)
 {
-	unregister_pernet_device(&l2tp_eth_net_ops);
 	l2tp_nl_unregister_ops(L2TP_PWTYPE_ETH);
 }
 
-- 
cgit v1.2.3


From 90841047a01b452cc8c3f9b990698b264143334a Mon Sep 17 00:00:00 2001
From: Grant Grundler <grundler@chromium.org>
Date: Thu, 28 Sep 2017 11:35:00 -0700
Subject: r8152: add Linksys USB3GIGV1 id

This linksys dongle by default comes up in cdc_ether mode.
This patch allows r8152 to claim the device:
   Bus 002 Device 002: ID 13b1:0041 Linksys

Signed-off-by: Grant Grundler <grundler@chromium.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ether.c | 10 ++++++++++
 drivers/net/usb/r8152.c     |  2 ++
 2 files changed, 12 insertions(+)

diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 8ab281b478f2..677a85360db1 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -547,6 +547,7 @@ static const struct driver_info wwan_info = {
 #define REALTEK_VENDOR_ID	0x0bda
 #define SAMSUNG_VENDOR_ID	0x04e8
 #define LENOVO_VENDOR_ID	0x17ef
+#define LINKSYS_VENDOR_ID	0x13b1
 #define NVIDIA_VENDOR_ID	0x0955
 #define HP_VENDOR_ID		0x03f0
 #define MICROSOFT_VENDOR_ID	0x045e
@@ -737,6 +738,15 @@ static const struct usb_device_id	products[] = {
 	.driver_info = 0,
 },
 
+#if IS_ENABLED(CONFIG_USB_RTL8152)
+/* Linksys USB3GIGV1 Ethernet Adapter */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(LINKSYS_VENDOR_ID, 0x0041, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+#endif
+
 /* ThinkPad USB-C Dock (based on Realtek RTL8153) */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x3062, USB_CLASS_COMM,
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index ceb78e2ea4f0..941ece08ba78 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -613,6 +613,7 @@ enum rtl8152_flags {
 #define VENDOR_ID_MICROSOFT		0x045e
 #define VENDOR_ID_SAMSUNG		0x04e8
 #define VENDOR_ID_LENOVO		0x17ef
+#define VENDOR_ID_LINKSYS		0x13b1
 #define VENDOR_ID_NVIDIA		0x0955
 
 #define MCU_TYPE_PLA			0x0100
@@ -5316,6 +5317,7 @@ static const struct usb_device_id rtl8152_table[] = {
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x7205)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x720c)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x7214)},
+	{REALTEK_USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_NVIDIA,  0x09ff)},
 	{}
 };
-- 
cgit v1.2.3


From 4792ea04bcd03b8ccfd1ae336c5deba52dd9edc9 Mon Sep 17 00:00:00 2001
From: Gregory CLEMENT <gregory.clement@free-electrons.com>
Date: Fri, 29 Sep 2017 14:27:39 +0200
Subject: net: mvpp2: Fix clock resource by adding an optional bus clock

On Armada 7K/8K we need to explicitly enable the bus clock. The bus clock
is optional because not all the SoCs need them but at least for Armada
7K/8K it is actually mandatory.

The binding documentation is updating accordingly.

Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/marvell-pp2.txt | 10 ++++++----
 drivers/net/ethernet/marvell/mvpp2.c                  | 15 +++++++++++++++
 2 files changed, 21 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/marvell-pp2.txt b/Documentation/devicetree/bindings/net/marvell-pp2.txt
index 7e2dad08a12e..1814fa13f6ab 100644
--- a/Documentation/devicetree/bindings/net/marvell-pp2.txt
+++ b/Documentation/devicetree/bindings/net/marvell-pp2.txt
@@ -21,8 +21,9 @@ Required properties:
 	- main controller clock (for both armada-375-pp2 and armada-7k-pp2)
 	- GOP clock (for both armada-375-pp2 and armada-7k-pp2)
 	- MG clock (only for armada-7k-pp2)
-- clock-names: names of used clocks, must be "pp_clk", "gop_clk" and
-  "mg_clk" (the latter only for armada-7k-pp2).
+	- AXI clock (only for armada-7k-pp2)
+- clock-names: names of used clocks, must be "pp_clk", "gop_clk", "mg_clk"
+  and "axi_clk" (the 2 latter only for armada-7k-pp2).
 
 The ethernet ports are represented by subnodes. At least one port is
 required.
@@ -78,8 +79,9 @@ Example for marvell,armada-7k-pp2:
 cpm_ethernet: ethernet@0 {
 	compatible = "marvell,armada-7k-pp22";
 	reg = <0x0 0x100000>, <0x129000 0xb000>;
-	clocks = <&cpm_syscon0 1 3>, <&cpm_syscon0 1 9>, <&cpm_syscon0 1 5>;
-	clock-names = "pp_clk", "gop_clk", "gp_clk";
+	clocks = <&cpm_syscon0 1 3>, <&cpm_syscon0 1 9>,
+		 <&cpm_syscon0 1 5>, <&cpm_syscon0 1 18>;
+	clock-names = "pp_clk", "gop_clk", "gp_clk", "axi_clk";
 
 	eth0: eth0 {
 		interrupts = <ICU_GRP_NSR 39 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index 161055564720..9c86cb7cb988 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -793,6 +793,7 @@ struct mvpp2 {
 	struct clk *pp_clk;
 	struct clk *gop_clk;
 	struct clk *mg_clk;
+	struct clk *axi_clk;
 
 	/* List of pointers to port structures */
 	struct mvpp2_port **port_list;
@@ -7970,6 +7971,18 @@ static int mvpp2_probe(struct platform_device *pdev)
 		err = clk_prepare_enable(priv->mg_clk);
 		if (err < 0)
 			goto err_gop_clk;
+
+		priv->axi_clk = devm_clk_get(&pdev->dev, "axi_clk");
+		if (IS_ERR(priv->axi_clk)) {
+			err = PTR_ERR(priv->axi_clk);
+			if (err == -EPROBE_DEFER)
+				goto err_gop_clk;
+			priv->axi_clk = NULL;
+		} else {
+			err = clk_prepare_enable(priv->axi_clk);
+			if (err < 0)
+				goto err_gop_clk;
+		}
 	}
 
 	/* Get system's tclk rate */
@@ -8024,6 +8037,7 @@ static int mvpp2_probe(struct platform_device *pdev)
 	return 0;
 
 err_mg_clk:
+	clk_disable_unprepare(priv->axi_clk);
 	if (priv->hw_version == MVPP22)
 		clk_disable_unprepare(priv->mg_clk);
 err_gop_clk:
@@ -8061,6 +8075,7 @@ static int mvpp2_remove(struct platform_device *pdev)
 				  aggr_txq->descs_dma);
 	}
 
+	clk_disable_unprepare(priv->axi_clk);
 	clk_disable_unprepare(priv->mg_clk);
 	clk_disable_unprepare(priv->pp_clk);
 	clk_disable_unprepare(priv->gop_clk);
-- 
cgit v1.2.3


From 81359617f1b783a01e6e22b46cbb046e9513b9c6 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 30 Sep 2017 07:34:34 +0200
Subject: net: hns3: Fix an error handling path in 'hclge_rss_init_hw()'

If this sanity check fails, we must free 'rss_indir'. Otherwise there is a
memory leak.
'goto err' as done in the other error handling paths to fix it.

Fixes: 46a3df9f9718 ("net: hns3: Fix for setting rss_size incorrectly")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index e0685e630afe..c1cdbfd83bdb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2652,7 +2652,8 @@ static int hclge_rss_init_hw(struct hclge_dev *hdev)
 		dev_err(&hdev->pdev->dev,
 			"Configure rss tc size failed, invalid TC_SIZE = %d\n",
 			rss_size);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err;
 	}
 
 	roundup_size = roundup_pow_of_two(rss_size);
-- 
cgit v1.2.3


From 28a04c7b7bbecaab642fcb6a2d7354eb70ea7fbe Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 2 Oct 2017 12:14:56 +0200
Subject: mlxsw: spectrum_router: Move VRF refcounting

When creating a new RIF, bumping RIF count of the containing VR is the
last thing to be done. Symmetrically, when destroying a RIF, RIF count
is first dropped and only then the rest of the cleanup proceeds.

That's a problem for loopback RIFs. Those hold two VR references: one
for overlay and one for underlay. mlxsw_sp_rif_destroy() releases the
overlay one, and the deconfigure() callback the underlay one. But if
both overlay and underlay are the same, and if there are no other
artifacts holding the VR alive, this put actually destroys the VR. Later
on, when mlxsw_sp_rif_destroy() calls mlxsw_sp_vr_put() for the same VR,
the VR will already have been released and the kernel crashes with NULL
pointer dereference.

The underlying problem is that the RIF under destruction ends up
referencing the overlay VR much longer than it claims: all the way until
the call to mlxsw_sp_vr_put(). So line up the reference counting
properly to reflect this. Make corresponding changes in
mlxsw_sp_rif_create() as well for symmetry.

Fixes: 6ddb7426a7d4 ("mlxsw: spectrum_router: Introduce loopback RIFs")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 2cfb3f5d092d..3917b4dd4202 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -5068,6 +5068,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 	vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN);
 	if (IS_ERR(vr))
 		return ERR_CAST(vr);
+	vr->rif_count++;
 
 	err = mlxsw_sp_rif_index_alloc(mlxsw_sp, &rif_index);
 	if (err)
@@ -5099,7 +5100,6 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 
 	mlxsw_sp_rif_counters_alloc(rif);
 	mlxsw_sp->router->rifs[rif_index] = rif;
-	vr->rif_count++;
 
 	return rif;
 
@@ -5110,6 +5110,7 @@ err_fid_get:
 	kfree(rif);
 err_rif_alloc:
 err_rif_index_alloc:
+	vr->rif_count--;
 	mlxsw_sp_vr_put(vr);
 	return ERR_PTR(err);
 }
@@ -5124,7 +5125,6 @@ void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
 	mlxsw_sp_router_rif_gone_sync(mlxsw_sp, rif);
 	vr = &mlxsw_sp->router->vrs[rif->vr_id];
 
-	vr->rif_count--;
 	mlxsw_sp->router->rifs[rif->rif_index] = NULL;
 	mlxsw_sp_rif_counters_free(rif);
 	ops->deconfigure(rif);
@@ -5132,6 +5132,7 @@ void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
 		/* Loopback RIFs are not associated with a FID. */
 		mlxsw_sp_fid_put(fid);
 	kfree(rif);
+	vr->rif_count--;
 	mlxsw_sp_vr_put(vr);
 }
 
-- 
cgit v1.2.3


From de0f43c01a4b5d408a5c087c8a92ac1739938f8b Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 2 Oct 2017 12:14:57 +0200
Subject: mlxsw: spectrum_router: Track RIF of IPIP next hops

When considering whether to set RTNH_F_OFFLOAD flag on an IPv6 route,
mlxsw_sp_fib6_entry_offload_set() looks up the mlxsw_sp_nexthop
corresponding to a given route, and decides based on whether the next
hop's offloaded flag was set. When looking for the matching next hop, it
also takes into account the device of the route, which must match next
hop's RIF.

IPIP next hops however hitherto didn't set the RIF. As a result, IPv6
routes forwarding traffic to IP-in-IP netdevices are never marked as
offloaded, even when they actually are.

Thus track RIF of IPIP next hops the same way as that of ETHERNET next
hops.

Fixes: 8f28a3097645 ("mlxsw: spectrum_router: Support IPv6 overlay encap")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 3917b4dd4202..032089efc1a0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -2723,6 +2723,7 @@ static void mlxsw_sp_nexthop_type_fini(struct mlxsw_sp *mlxsw_sp,
 		mlxsw_sp_nexthop_rif_fini(nh);
 		break;
 	case MLXSW_SP_NEXTHOP_TYPE_IPIP:
+		mlxsw_sp_nexthop_rif_fini(nh);
 		mlxsw_sp_nexthop_ipip_fini(mlxsw_sp, nh);
 		break;
 	}
@@ -2742,7 +2743,11 @@ static int mlxsw_sp_nexthop4_type_init(struct mlxsw_sp *mlxsw_sp,
 	    router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, dev,
 						     MLXSW_SP_L3_PROTO_IPV4)) {
 		nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP;
-		return mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev);
+		err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev);
+		if (err)
+			return err;
+		mlxsw_sp_nexthop_rif_init(nh, &nh->ipip_entry->ol_lb->common);
+		return 0;
 	}
 
 	nh->type = MLXSW_SP_NEXTHOP_TYPE_ETH;
@@ -4009,7 +4014,11 @@ static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp,
 	    router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, dev,
 						     MLXSW_SP_L3_PROTO_IPV6)) {
 		nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP;
-		return mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev);
+		err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev);
+		if (err)
+			return err;
+		mlxsw_sp_nexthop_rif_init(nh, &nh->ipip_entry->ol_lb->common);
+		return 0;
 	}
 
 	nh->type = MLXSW_SP_NEXTHOP_TYPE_ETH;
-- 
cgit v1.2.3


From eefca20eb20c66b06cf5ed09b49b1a7caaa27b7b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 2 Oct 2017 12:20:51 -0700
Subject: socket, bpf: fix possible use after free

Starting from linux-4.4, 3WHS no longer takes the listener lock.

Since this time, we might hit a use-after-free in sk_filter_charge(),
if the filter we got in the memcpy() of the listener content
just happened to be replaced by a thread changing listener BPF filter.

To fix this, we need to make sure the filter refcount is not already
zero before incrementing it again.

Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/filter.c | 12 ++++++++----
 net/core/sock.c   |  5 ++++-
 2 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index 82edad58d066..74b8c91fb5f4 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -989,10 +989,14 @@ static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
 
 bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
 {
-	bool ret = __sk_filter_charge(sk, fp);
-	if (ret)
-		refcount_inc(&fp->refcnt);
-	return ret;
+	if (!refcount_inc_not_zero(&fp->refcnt))
+		return false;
+
+	if (!__sk_filter_charge(sk, fp)) {
+		sk_filter_release(fp);
+		return false;
+	}
+	return true;
 }
 
 static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
diff --git a/net/core/sock.c b/net/core/sock.c
index 7d55c05f449d..23953b741a41 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1684,13 +1684,16 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 
 		sock_reset_flag(newsk, SOCK_DONE);
 
-		filter = rcu_dereference_protected(newsk->sk_filter, 1);
+		rcu_read_lock();
+		filter = rcu_dereference(sk->sk_filter);
 		if (filter != NULL)
 			/* though it's an empty new sock, the charging may fail
 			 * if sysctl_optmem_max was changed between creation of
 			 * original socket and cloning
 			 */
 			is_charged = sk_filter_charge(newsk, filter);
+		RCU_INIT_POINTER(newsk->sk_filter, filter);
+		rcu_read_unlock();
 
 		if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
 			/* We need to make sure that we don't uncharge the new
-- 
cgit v1.2.3


From ce024f42c2e28b6bce4ecc1e891b42f57f753892 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 3 Oct 2017 13:20:48 +0300
Subject: net: rtnetlink: fix info leak in RTM_GETSTATS call

When RTM_GETSTATS was added the fields of its header struct were not all
initialized when returning the result thus leaking 4 bytes of information
to user-space per rtnl_fill_statsinfo call, so initialize them now. Thanks
to Alexander Potapenko for the detailed report and bisection.

Reported-by: Alexander Potapenko <glider@google.com>
Fixes: 10c9ead9f3c6 ("rtnetlink: add new RTM_GETSTATS message to dump link stats")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a78fd61da0ec..d4bcdcc68e92 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3854,6 +3854,9 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev,
 		return -EMSGSIZE;
 
 	ifsm = nlmsg_data(nlh);
+	ifsm->family = PF_UNSPEC;
+	ifsm->pad1 = 0;
+	ifsm->pad2 = 0;
 	ifsm->ifindex = dev->ifindex;
 	ifsm->filter_mask = filter_mask;
 
-- 
cgit v1.2.3


From 63ba395cd7a52431cbb61658dad3beb5b24e9300 Mon Sep 17 00:00:00 2001
From: Aleksander Morgado <aleksander@aleksander.es>
Date: Wed, 27 Sep 2017 23:31:03 +0200
Subject: rndis_host: support Novatel Verizon USB730L
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Treat the ef/04/01 interface class/subclass/protocol combination used
by the Novatel Verizon USB730L (1410:9030) as a possible RNDIS
interface.

 T:  Bus=01 Lev=02 Prnt=02 Port=01 Cnt=02 Dev#= 17 Spd=480 MxCh= 0
 D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  3
 P:  Vendor=1410 ProdID=9030 Rev=03.10
 S:  Manufacturer=Novatel Wireless
 S:  Product=MiFi USB730L
 S:  SerialNumber=0123456789ABCDEF
 C:  #Ifs= 3 Cfg#= 1 Atr=80 MxPwr=500mA
 I:  If#= 0 Alt= 0 #EPs= 1 Cls=ef(misc ) Sub=04 Prot=01 Driver=rndis_host
 I:  If#= 1 Alt= 0 #EPs= 2 Cls=0a(data ) Sub=00 Prot=00 Driver=rndis_host
 I:  If#= 2 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=00 Prot=00 Driver=usbhid

Once the network interface is brought up, the user just needs to run a
DHCP client to get IP address and routing setup.

As a side note, other Novatel Verizon USB730L models with the same
vid:pid end up exposing a standard ECM interface which doesn't require
any other kernel update to make it work.

Signed-off-by: Aleksander Morgado <aleksander@aleksander.es>
Reviewed-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ether.c  | 11 ++++++++++-
 drivers/net/usb/rndis_host.c |  4 ++++
 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 677a85360db1..29c7e2ec0dcb 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -54,11 +54,19 @@ static int is_wireless_rndis(struct usb_interface_descriptor *desc)
 		desc->bInterfaceProtocol == 3);
 }
 
+static int is_novatel_rndis(struct usb_interface_descriptor *desc)
+{
+	return (desc->bInterfaceClass == USB_CLASS_MISC &&
+		desc->bInterfaceSubClass == 4 &&
+		desc->bInterfaceProtocol == 1);
+}
+
 #else
 
 #define is_rndis(desc)		0
 #define is_activesync(desc)	0
 #define is_wireless_rndis(desc)	0
+#define is_novatel_rndis(desc)	0
 
 #endif
 
@@ -150,7 +158,8 @@ int usbnet_generic_cdc_bind(struct usbnet *dev, struct usb_interface *intf)
 	 */
 	rndis = (is_rndis(&intf->cur_altsetting->desc) ||
 		 is_activesync(&intf->cur_altsetting->desc) ||
-		 is_wireless_rndis(&intf->cur_altsetting->desc));
+		 is_wireless_rndis(&intf->cur_altsetting->desc) ||
+		 is_novatel_rndis(&intf->cur_altsetting->desc));
 
 	memset(info, 0, sizeof(*info));
 	info->control = intf;
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index a151f267aebb..b807c91abe1d 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -632,6 +632,10 @@ static const struct usb_device_id	products [] = {
 	/* RNDIS for tethering */
 	USB_INTERFACE_INFO(USB_CLASS_WIRELESS_CONTROLLER, 1, 3),
 	.driver_info = (unsigned long) &rndis_info,
+}, {
+	/* Novatel Verizon USB730L */
+	USB_INTERFACE_INFO(USB_CLASS_MISC, 4, 1),
+	.driver_info = (unsigned long) &rndis_info,
 },
 	{ },		// END
 };
-- 
cgit v1.2.3


From 05946876f0c16f6fe1db692d575aba42b25f0811 Mon Sep 17 00:00:00 2001
From: David Wu <david.wu@rock-chips.com>
Date: Sat, 30 Sep 2017 17:47:23 +0800
Subject: net: stmmac: dwmac-rk: Add RK3128 GMAC support

Add constants and callback functions for the dwmac on rk3128 soc.
As can be seen, the base structure is the same, only registers
and the bits in them moved slightly.

Signed-off-by: David Wu <david.wu@rock-chips.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../devicetree/bindings/net/rockchip-dwmac.txt     |   1 +
 drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c     | 112 +++++++++++++++++++++
 2 files changed, 113 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.txt b/Documentation/devicetree/bindings/net/rockchip-dwmac.txt
index 6af8eed1adeb..9c16ee2965a2 100644
--- a/Documentation/devicetree/bindings/net/rockchip-dwmac.txt
+++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.txt
@@ -4,6 +4,7 @@ The device node has following properties.
 
 Required properties:
  - compatible: should be "rockchip,<name>-gamc"
+   "rockchip,rk3128-gmac": found on RK312x SoCs
    "rockchip,rk3228-gmac": found on RK322x SoCs
    "rockchip,rk3288-gmac": found on RK3288 SoCs
    "rockchip,rk3328-gmac": found on RK3328 SoCs
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 99823f54696a..13133b30b575 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -83,6 +83,117 @@ struct rk_priv_data {
 	(((tx) ? soc##_GMAC_TXCLK_DLY_ENABLE : soc##_GMAC_TXCLK_DLY_DISABLE) | \
 	 ((rx) ? soc##_GMAC_RXCLK_DLY_ENABLE : soc##_GMAC_RXCLK_DLY_DISABLE))
 
+#define RK3128_GRF_MAC_CON0	0x0168
+#define RK3128_GRF_MAC_CON1	0x016c
+
+/* RK3128_GRF_MAC_CON0 */
+#define RK3128_GMAC_TXCLK_DLY_ENABLE   GRF_BIT(14)
+#define RK3128_GMAC_TXCLK_DLY_DISABLE  GRF_CLR_BIT(14)
+#define RK3128_GMAC_RXCLK_DLY_ENABLE   GRF_BIT(15)
+#define RK3128_GMAC_RXCLK_DLY_DISABLE  GRF_CLR_BIT(15)
+#define RK3128_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 7)
+#define RK3128_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0)
+
+/* RK3128_GRF_MAC_CON1 */
+#define RK3128_GMAC_PHY_INTF_SEL_RGMII	\
+		(GRF_BIT(6) | GRF_CLR_BIT(7) | GRF_CLR_BIT(8))
+#define RK3128_GMAC_PHY_INTF_SEL_RMII	\
+		(GRF_CLR_BIT(6) | GRF_CLR_BIT(7) | GRF_BIT(8))
+#define RK3128_GMAC_FLOW_CTRL          GRF_BIT(9)
+#define RK3128_GMAC_FLOW_CTRL_CLR      GRF_CLR_BIT(9)
+#define RK3128_GMAC_SPEED_10M          GRF_CLR_BIT(10)
+#define RK3128_GMAC_SPEED_100M         GRF_BIT(10)
+#define RK3128_GMAC_RMII_CLK_25M       GRF_BIT(11)
+#define RK3128_GMAC_RMII_CLK_2_5M      GRF_CLR_BIT(11)
+#define RK3128_GMAC_CLK_125M           (GRF_CLR_BIT(12) | GRF_CLR_BIT(13))
+#define RK3128_GMAC_CLK_25M            (GRF_BIT(12) | GRF_BIT(13))
+#define RK3128_GMAC_CLK_2_5M           (GRF_CLR_BIT(12) | GRF_BIT(13))
+#define RK3128_GMAC_RMII_MODE          GRF_BIT(14)
+#define RK3128_GMAC_RMII_MODE_CLR      GRF_CLR_BIT(14)
+
+static void rk3128_set_to_rgmii(struct rk_priv_data *bsp_priv,
+				int tx_delay, int rx_delay)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "Missing rockchip,grf property\n");
+		return;
+	}
+
+	regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
+		     RK3128_GMAC_PHY_INTF_SEL_RGMII |
+		     RK3128_GMAC_RMII_MODE_CLR);
+	regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON0,
+		     DELAY_ENABLE(RK3128, tx_delay, rx_delay) |
+		     RK3128_GMAC_CLK_RX_DL_CFG(rx_delay) |
+		     RK3128_GMAC_CLK_TX_DL_CFG(tx_delay));
+}
+
+static void rk3128_set_to_rmii(struct rk_priv_data *bsp_priv)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "Missing rockchip,grf property\n");
+		return;
+	}
+
+	regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
+		     RK3128_GMAC_PHY_INTF_SEL_RMII | RK3128_GMAC_RMII_MODE);
+}
+
+static void rk3128_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "Missing rockchip,grf property\n");
+		return;
+	}
+
+	if (speed == 10)
+		regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
+			     RK3128_GMAC_CLK_2_5M);
+	else if (speed == 100)
+		regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
+			     RK3128_GMAC_CLK_25M);
+	else if (speed == 1000)
+		regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
+			     RK3128_GMAC_CLK_125M);
+	else
+		dev_err(dev, "unknown speed value for RGMII! speed=%d", speed);
+}
+
+static void rk3128_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "Missing rockchip,grf property\n");
+		return;
+	}
+
+	if (speed == 10) {
+		regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
+			     RK3128_GMAC_RMII_CLK_2_5M |
+			     RK3128_GMAC_SPEED_10M);
+	} else if (speed == 100) {
+		regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
+			     RK3128_GMAC_RMII_CLK_25M |
+			     RK3128_GMAC_SPEED_100M);
+	} else {
+		dev_err(dev, "unknown speed value for RMII! speed=%d", speed);
+	}
+}
+
+static const struct rk_gmac_ops rk3128_ops = {
+	.set_to_rgmii = rk3128_set_to_rgmii,
+	.set_to_rmii = rk3128_set_to_rmii,
+	.set_rgmii_speed = rk3128_set_rgmii_speed,
+	.set_rmii_speed = rk3128_set_rmii_speed,
+};
+
 #define RK3228_GRF_MAC_CON0	0x0900
 #define RK3228_GRF_MAC_CON1	0x0904
 
@@ -1313,6 +1424,7 @@ static int rk_gmac_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(rk_gmac_pm_ops, rk_gmac_suspend, rk_gmac_resume);
 
 static const struct of_device_id rk_gmac_dwmac_match[] = {
+	{ .compatible = "rockchip,rk3128-gmac", .data = &rk3128_ops },
 	{ .compatible = "rockchip,rk3228-gmac", .data = &rk3228_ops },
 	{ .compatible = "rockchip,rk3288-gmac", .data = &rk3288_ops },
 	{ .compatible = "rockchip,rk3328-gmac", .data = &rk3328_ops },
-- 
cgit v1.2.3


From 90caccdd8cc0215705f18b92771b449b01e2474a Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Tue, 3 Oct 2017 15:37:20 -0700
Subject: bpf: fix bpf_tail_call() x64 JIT

- bpf prog_array just like all other types of bpf array accepts 32-bit index.
  Clarify that in the comment.
- fix x64 JIT of bpf_tail_call which was incorrectly loading 8 instead of 4 bytes
- tighten corresponding check in the interpreter to stay consistent

The JIT bug can be triggered after introduction of BPF_F_NUMA_NODE flag
in commit 96eabe7a40aa in 4.14. Before that the map_flags would stay zero and
though JIT code is wrong it will check bounds correctly.
Hence two fixes tags. All other JITs don't have this problem.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Fixes: 96eabe7a40aa ("bpf: Allow selecting numa node during map creation")
Fixes: b52f00e6a715 ("x86: bpf_jit: implement bpf_tail_call() helper")
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/x86/net/bpf_jit_comp.c | 4 ++--
 include/uapi/linux/bpf.h    | 2 +-
 kernel/bpf/core.c           | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 8c9573660d51..0554e8aef4d5 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -284,9 +284,9 @@ static void emit_bpf_tail_call(u8 **pprog)
 	/* if (index >= array->map.max_entries)
 	 *   goto out;
 	 */
-	EMIT4(0x48, 0x8B, 0x46,                   /* mov rax, qword ptr [rsi + 16] */
+	EMIT2(0x89, 0xD2);                        /* mov edx, edx */
+	EMIT3(0x39, 0x56,                         /* cmp dword ptr [rsi + 16], edx */
 	      offsetof(struct bpf_array, map.max_entries));
-	EMIT3(0x48, 0x39, 0xD0);                  /* cmp rax, rdx */
 #define OFFSET1 43 /* number of bytes to jump */
 	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
 	label1 = cnt;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 43ab5c402f98..f90860d1f897 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -312,7 +312,7 @@ union bpf_attr {
  *     jump into another BPF program
  *     @ctx: context pointer passed to next program
  *     @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
- *     @index: index inside array that selects specific program to run
+ *     @index: 32-bit index inside array that selects specific program to run
  *     Return: 0 on success or negative error
  *
  * int bpf_clone_redirect(skb, ifindex, flags)
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 917cc04a0a94..7b62df86be1d 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1022,7 +1022,7 @@ select_insn:
 		struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2;
 		struct bpf_array *array = container_of(map, struct bpf_array, map);
 		struct bpf_prog *prog;
-		u64 index = BPF_R3;
+		u32 index = BPF_R3;
 
 		if (unlikely(index >= array->map.max_entries))
 			goto out;
-- 
cgit v1.2.3


From e769fcec6bc4bdd1b0e2cf817680148f9c40b1c4 Mon Sep 17 00:00:00 2001
From: Vishakha Narvekar <Vishakha.Narvekar@dell.com>
Date: Tue, 3 Oct 2017 16:13:29 -0400
Subject: net: 8021q: skip packets if the vlan is down

If the vlan is down, free the packet instead of proceeding with other
processing, or counting it as received.  If vlan interfaces are used
as slaves for bonding, with arp monitoring for connectivity, if the rx
counter is seen to be incrementing, then the bond device will not
observe that the interface is down.

CC: David S. Miller <davem@davemloft.net>
Signed-off-by: Vishakha Narvekar <Vishakha.Narvekar@dell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/vlan_core.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index e2ed69850489..0bc31de9071a 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -21,6 +21,12 @@ bool vlan_do_receive(struct sk_buff **skbp)
 	if (unlikely(!skb))
 		return false;
 
+	if (unlikely(!(vlan_dev->flags & IFF_UP))) {
+		kfree_skb(skb);
+		*skbp = NULL;
+		return false;
+	}
+
 	skb->dev = vlan_dev;
 	if (unlikely(skb->pkt_type == PACKET_OTHERHOST)) {
 		/* Our lower layer thinks this is not local, let's make sure.
-- 
cgit v1.2.3