From 27cbf64a766e86f068ce6214f04c00ceb4db1af4 Mon Sep 17 00:00:00 2001
From: Jie Wang
Date: Fri, 10 Dec 2021 21:09:33 +0800
Subject: net: hns3: fix use-after-free bug in hclgevf_send_mbx_msg

Currently, the hns3_remove function firstly uninstall client instance,
and then uninstall acceletion engine device. The netdevice is freed in
client instance uninstall process, but acceletion engine device uninstall
process still use it to trace runtime information. This causes a use after
free problem.

So fixes it by check the instance register state to avoid use after free.

Fixes: d8355240cf8f ("net: hns3: add trace event support for PF/VF mailbox")
Signed-off-by: Jie Wang <wangjie125@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
index fdc66fae0960..c5ac6ecf36e1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@@ -114,7 +114,8 @@ int hclgevf_send_mbx_msg(struct hclgevf_dev *hdev,
 
 	memcpy(&req->msg, send_msg, sizeof(struct hclge_vf_to_pf_msg));
 
-	trace_hclge_vf_mbx_send(hdev, req);
+	if (test_bit(HCLGEVF_STATE_NIC_REGISTERED, &hdev->state))
+		trace_hclge_vf_mbx_send(hdev, req);
 
 	/* synchronous send */
 	if (need_resp) {
-- 
cgit v1.2.3


From 6dde452bceca3f2ed2b33bc46a16ff5682a03a2e Mon Sep 17 00:00:00 2001
From: Yufeng Mo
Date: Fri, 10 Dec 2021 21:09:34 +0800
Subject: net: hns3: fix race condition in debugfs

When multiple threads concurrently access the debugfs content, data
and pointer exceptions may occur. Therefore, mutex lock protection is
added for debugfs.

Fixes: 5e69ea7ee2a6 ("net: hns3: refactor the debugfs process")
Signed-off-by: Yufeng Mo <moyufeng@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |  2 ++
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 20 ++++++++++++++------
 2 files changed, 16 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 3f7a9a4c59d5..63f5abcc6bf4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -839,6 +839,8 @@ struct hnae3_handle {
 
 	u8 netdev_flags;
 	struct dentry *hnae3_dbgfs;
+	/* protects concurrent contention between debugfs commands */
+	struct mutex dbgfs_lock;
 
 	/* Network interface message level enabled bits */
 	u32 msg_enable;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 081295bff765..c381f8af67f0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -1226,6 +1226,7 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer,
 	if (ret)
 		return ret;
 
+	mutex_lock(&handle->dbgfs_lock);
 	save_buf = &hns3_dbg_cmd[index].buf;
 
 	if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) ||
@@ -1238,15 +1239,15 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer,
 		read_buf = *save_buf;
 	} else {
 		read_buf = kvzalloc(hns3_dbg_cmd[index].buf_len, GFP_KERNEL);
-		if (!read_buf)
-			return -ENOMEM;
+		if (!read_buf) {
+			ret = -ENOMEM;
+			goto out;
+		}
 
 		/* save the buffer addr until the last read operation */
 		*save_buf = read_buf;
-	}
 
-	/* get data ready for the first time to read */
-	if (!*ppos) {
+		/* get data ready for the first time to read */
 		ret = hns3_dbg_read_cmd(dbg_data, hns3_dbg_cmd[index].cmd,
 					read_buf, hns3_dbg_cmd[index].buf_len);
 		if (ret)
@@ -1255,8 +1256,10 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer,
 
 	size = simple_read_from_buffer(buffer, count, ppos, read_buf,
 				       strlen(read_buf));
-	if (size > 0)
+	if (size > 0) {
+		mutex_unlock(&handle->dbgfs_lock);
 		return size;
+	}
 
 out:
 	/* free the buffer for the last read operation */
@@ -1265,6 +1268,7 @@ out:
 		*save_buf = NULL;
 	}
 
+	mutex_unlock(&handle->dbgfs_lock);
 	return ret;
 }
 
@@ -1337,6 +1341,8 @@ int hns3_dbg_init(struct hnae3_handle *handle)
 			debugfs_create_dir(hns3_dbg_dentry[i].name,
 					   handle->hnae3_dbgfs);
 
+	mutex_init(&handle->dbgfs_lock);
+
 	for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) {
 		if ((hns3_dbg_cmd[i].cmd == HNAE3_DBG_CMD_TM_NODES &&
 		     ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2) ||
@@ -1363,6 +1369,7 @@ int hns3_dbg_init(struct hnae3_handle *handle)
 	return 0;
 
 out:
+	mutex_destroy(&handle->dbgfs_lock);
 	debugfs_remove_recursive(handle->hnae3_dbgfs);
 	handle->hnae3_dbgfs = NULL;
 	return ret;
@@ -1378,6 +1385,7 @@ void hns3_dbg_uninit(struct hnae3_handle *handle)
 			hns3_dbg_cmd[i].buf = NULL;
 		}
 
+	mutex_destroy(&handle->dbgfs_lock);
 	debugfs_remove_recursive(handle->hnae3_dbgfs);
 	handle->hnae3_dbgfs = NULL;
 }
-- 
cgit v1.2.3


From ab8eb798ddabddb2944401bf31ead9671cb97d95 Mon Sep 17 00:00:00 2001
From: Miaoqian Lin
Date: Sat, 11 Dec 2021 14:01:53 +0000
Subject: net: bcmgenet: Fix NULL vs IS_ERR() checking

The phy_attach() function does not return NULL. It returns error pointers.

Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmmii.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 5f259641437a..c888ddee1fc4 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -589,9 +589,9 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv)
 		 * Internal or external PHY with MDIO access
 		 */
 		phydev = phy_attach(priv->dev, phy_name, pd->phy_interface);
-		if (!phydev) {
+		if (IS_ERR(phydev)) {
 			dev_err(kdev, "failed to register PHY device\n");
-			return -ENODEV;
+			return PTR_ERR(phydev);
 		}
 	} else {
 		/*
-- 
cgit v1.2.3


From be565ec71d1d59438bed0c7ed0a252a327e0b0ef Mon Sep 17 00:00:00 2001
From: Wang Qing
Date: Mon, 13 Dec 2021 01:44:36 -0800
Subject: net: ethernet: ti: add missing of_node_put before return

Fix following coccicheck warning:
WARNING: Function "for_each_child_of_node"
should have of_node_put() before return.

Early exits from for_each_child_of_node should decrement the
node reference counter.

Signed-off-by: Wang Qing <wangqing@vivo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 29 ++++++++++++++++++++---------
 1 file changed, 20 insertions(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index c092cb61416a..ffbbda8f4d41 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -1844,13 +1844,14 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 		if (ret < 0) {
 			dev_err(dev, "%pOF error reading port_id %d\n",
 				port_np, ret);
-			return ret;
+			goto of_node_put;
 		}
 
 		if (!port_id || port_id > common->port_num) {
 			dev_err(dev, "%pOF has invalid port_id %u %s\n",
 				port_np, port_id, port_np->name);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto of_node_put;
 		}
 
 		port = am65_common_get_port(common, port_id);
@@ -1866,8 +1867,10 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 				(AM65_CPSW_NU_FRAM_PORT_OFFSET * (port_id - 1));
 
 		port->slave.mac_sl = cpsw_sl_get("am65", dev, port->port_base);
-		if (IS_ERR(port->slave.mac_sl))
-			return PTR_ERR(port->slave.mac_sl);
+		if (IS_ERR(port->slave.mac_sl)) {
+			ret = PTR_ERR(port->slave.mac_sl);
+			goto of_node_put;
+		}
 
 		port->disabled = !of_device_is_available(port_np);
 		if (port->disabled) {
@@ -1880,7 +1883,7 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 			ret = PTR_ERR(port->slave.ifphy);
 			dev_err(dev, "%pOF error retrieving port phy: %d\n",
 				port_np, ret);
-			return ret;
+			goto of_node_put;
 		}
 
 		port->slave.mac_only =
@@ -1889,10 +1892,12 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 		/* get phy/link info */
 		if (of_phy_is_fixed_link(port_np)) {
 			ret = of_phy_register_fixed_link(port_np);
-			if (ret)
-				return dev_err_probe(dev, ret,
+			if (ret) {
+				ret = dev_err_probe(dev, ret,
 						     "failed to register fixed-link phy %pOF\n",
 						     port_np);
+				goto of_node_put;
+			}
 			port->slave.phy_node = of_node_get(port_np);
 		} else {
 			port->slave.phy_node =
@@ -1902,14 +1907,15 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 		if (!port->slave.phy_node) {
 			dev_err(dev,
 				"slave[%d] no phy found\n", port_id);
-			return -ENODEV;
+			ret = -ENODEV;
+			goto of_node_put;
 		}
 
 		ret = of_get_phy_mode(port_np, &port->slave.phy_if);
 		if (ret) {
 			dev_err(dev, "%pOF read phy-mode err %d\n",
 				port_np, ret);
-			return ret;
+			goto of_node_put;
 		}
 
 		ret = of_get_mac_address(port_np, port->slave.mac_addr);
@@ -1932,6 +1938,11 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 	}
 
 	return 0;
+
+of_node_put:
+	of_node_put(port_np);
+	of_node_put(node);
+	return ret;
 }
 
 static void am65_cpsw_pcpu_stats_free(void *data)
-- 
cgit v1.2.3


From 884d2b845477cd0a18302444dc20fe2d9a01743e Mon Sep 17 00:00:00 2001
From: David Wu
Date: Mon, 13 Dec 2021 19:15:15 +0800
Subject: net: stmmac: Add GFP_DMA32 for rx buffers if no 64 capability

Use page_pool_alloc_pages instead of page_pool_dev_alloc_pages, which
can give the gfp parameter, in the case of not supporting 64-bit width,
using 32-bit address memory can reduce a copy from swiotlb.

Signed-off-by: David Wu <david.wu@rock-chips.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index da8306f60730..8ded4be08b00 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1461,16 +1461,20 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
 {
 	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
 	struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i];
+	gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN);
+
+	if (priv->dma_cap.addr64 <= 32)
+		gfp |= GFP_DMA32;
 
 	if (!buf->page) {
-		buf->page = page_pool_dev_alloc_pages(rx_q->page_pool);
+		buf->page = page_pool_alloc_pages(rx_q->page_pool, gfp);
 		if (!buf->page)
 			return -ENOMEM;
 		buf->page_offset = stmmac_rx_offset(priv);
 	}
 
 	if (priv->sph && !buf->sec_page) {
-		buf->sec_page = page_pool_dev_alloc_pages(rx_q->page_pool);
+		buf->sec_page = page_pool_alloc_pages(rx_q->page_pool, gfp);
 		if (!buf->sec_page)
 			return -ENOMEM;
 
@@ -4482,6 +4486,10 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
 	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
 	int dirty = stmmac_rx_dirty(priv, queue);
 	unsigned int entry = rx_q->dirty_rx;
+	gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN);
+
+	if (priv->dma_cap.addr64 <= 32)
+		gfp |= GFP_DMA32;
 
 	while (dirty-- > 0) {
 		struct stmmac_rx_buffer *buf = &rx_q->buf_pool[entry];
@@ -4494,13 +4502,13 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
 			p = rx_q->dma_rx + entry;
 
 		if (!buf->page) {
-			buf->page = page_pool_dev_alloc_pages(rx_q->page_pool);
+			buf->page = page_pool_alloc_pages(rx_q->page_pool, gfp);
 			if (!buf->page)
 				break;
 		}
 
 		if (priv->sph && !buf->sec_page) {
-			buf->sec_page = page_pool_dev_alloc_pages(rx_q->page_pool);
+			buf->sec_page = page_pool_alloc_pages(rx_q->page_pool, gfp);
 			if (!buf->sec_page)
 				break;
 
-- 
cgit v1.2.3


From bc2f39a6252ee40d9bfc2743d4437d420aec5f6e Mon Sep 17 00:00:00 2001
From: Dan Carpenter
Date: Wed, 10 Nov 2021 11:13:50 +0300
Subject: iavf: missing unlocks in iavf_watchdog_task()

This code was re-organized and there some unlocks missing now.

Fixes: 898ef1cb1cb2 ("iavf: Combine init and watchdog state machines")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index cfdbf8c08d18..884a19c51543 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -2046,6 +2046,7 @@ static void iavf_watchdog_task(struct work_struct *work)
 		}
 		adapter->aq_required = 0;
 		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
+		mutex_unlock(&adapter->crit_lock);
 		queue_delayed_work(iavf_wq,
 				   &adapter->watchdog_task,
 				   msecs_to_jiffies(10));
@@ -2076,9 +2077,8 @@ static void iavf_watchdog_task(struct work_struct *work)
 			iavf_detect_recover_hung(&adapter->vsi);
 		break;
 	case __IAVF_REMOVE:
-		mutex_unlock(&adapter->crit_lock);
-		return;
 	default:
+		mutex_unlock(&adapter->crit_lock);
 		return;
 	}
 
-- 
cgit v1.2.3


From fe523d7c9a8332855376ad5eb1aa301091129ba4 Mon Sep 17 00:00:00 2001
From: Stefan Assmann
Date: Wed, 1 Dec 2021 09:14:34 +0100
Subject: iavf: do not override the adapter state in the watchdog task (again)

The watchdog task incorrectly changes the state to __IAVF_RESETTING,
instead of letting the reset task take care of that. This was already
resolved by commit 22c8fd71d3a5 ("iavf: do not override the adapter
state in the watchdog task") but the problem was reintroduced by the
recent code refactoring in commit 45eebd62999d ("iavf: Refactor iavf
state machine tracking").

Fixes: 45eebd62999d ("iavf: Refactor iavf state machine tracking")
Signed-off-by: Stefan Assmann <sassmann@kpanic.de>
Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 884a19c51543..4e7c04047f91 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -2085,7 +2085,6 @@ static void iavf_watchdog_task(struct work_struct *work)
 	/* check for hw reset */
 	reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK;
 	if (!reg_val) {
-		iavf_change_state(adapter, __IAVF_RESETTING);
 		adapter->flags |= IAVF_FLAG_RESET_PENDING;
 		adapter->aq_required = 0;
 		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
-- 
cgit v1.2.3


From aeb7c75cb77478fdbf821628e9c95c4baa9adc63 Mon Sep 17 00:00:00 2001
From: Ong Boon Leong
Date: Sat, 11 Dec 2021 22:51:34 +0800
Subject: net: stmmac: fix tc flower deletion for VLAN priority Rx steering

To replicate the issue:-

1) Add 1 flower filter for VLAN Priority based frame steering:-
$ IFDEVNAME=eth0
$ tc qdisc add dev $IFDEVNAME ingress
$ tc qdisc add dev $IFDEVNAME root mqprio num_tc 8 \
   map 0 1 2 3 4 5 6 7 0 0 0 0 0 0 0 0 \
   queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 hw 0
$ tc filter add dev $IFDEVNAME parent ffff: protocol 802.1Q \
   flower vlan_prio 0 hw_tc 0

2) Get the 'pref' id
$ tc filter show dev $IFDEVNAME ingress

3) Delete a specific tc flower record (say pref 49151)
$ tc filter del dev $IFDEVNAME parent ffff: pref 49151

From dmesg, we will observe kernel NULL pointer ooops

[  197.170464] BUG: kernel NULL pointer dereference, address: 0000000000000000
[  197.171367] #PF: supervisor read access in kernel mode
[  197.171367] #PF: error_code(0x0000) - not-present page
[  197.171367] PGD 0 P4D 0
[  197.171367] Oops: 0000 [#1] PREEMPT SMP NOPTI

<snip>

[  197.171367] RIP: 0010:tc_setup_cls+0x20b/0x4a0 [stmmac]

<snip>

[  197.171367] Call Trace:
[  197.171367]  <TASK>
[  197.171367]  ? __stmmac_disable_all_queues+0xa8/0xe0 [stmmac]
[  197.171367]  stmmac_setup_tc_block_cb+0x70/0x110 [stmmac]
[  197.171367]  tc_setup_cb_destroy+0xb3/0x180
[  197.171367]  fl_hw_destroy_filter+0x94/0xc0 [cls_flower]

The above issue is due to previous incorrect implementation of
tc_del_vlan_flow(), shown below, that uses flow_cls_offload_flow_rule()
to get struct flow_rule *rule which is no longer valid for tc filter
delete operation.

  struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
  struct flow_dissector *dissector = rule->match.dissector;

So, to ensure tc_del_vlan_flow() deletes the right VLAN cls record for
earlier configured RX queue (configured by hw_tc) in tc_add_vlan_flow(),
this patch introduces stmmac_rfs_entry as driver-side flow_cls_offload
record for 'RX frame steering' tc flower, currently used for VLAN
priority. The implementation has taken consideration for future extension
to include other type RX frame steering such as EtherType based.

v2:
 - Clean up overly extensive backtrace and rewrite git message to better
   explain the kernel NULL pointer issue.

Fixes: 0e039f5cf86c ("net: stmmac: add RX frame steering based on VLAN priority in tc flower")
Tested-by: Kurt Kanzenbach <kurt@linutronix.de>
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac.h    | 17 +++++
 drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 86 +++++++++++++++++++++----
 2 files changed, 90 insertions(+), 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 5f129733aabd..873b9e3e5da2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -172,6 +172,19 @@ struct stmmac_flow_entry {
 	int is_l4;
 };
 
+/* Rx Frame Steering */
+enum stmmac_rfs_type {
+	STMMAC_RFS_T_VLAN,
+	STMMAC_RFS_T_MAX,
+};
+
+struct stmmac_rfs_entry {
+	unsigned long cookie;
+	int in_use;
+	int type;
+	int tc;
+};
+
 struct stmmac_priv {
 	/* Frequently used values are kept adjacent for cache effect */
 	u32 tx_coal_frames[MTL_MAX_TX_QUEUES];
@@ -289,6 +302,10 @@ struct stmmac_priv {
 	struct stmmac_tc_entry *tc_entries;
 	unsigned int flow_entries_max;
 	struct stmmac_flow_entry *flow_entries;
+	unsigned int rfs_entries_max[STMMAC_RFS_T_MAX];
+	unsigned int rfs_entries_cnt[STMMAC_RFS_T_MAX];
+	unsigned int rfs_entries_total;
+	struct stmmac_rfs_entry *rfs_entries;
 
 	/* Pulse Per Second output */
 	struct stmmac_pps_cfg pps[STMMAC_PPS_MAX];
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index 1c4ea0b1b845..d0a2b289f460 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -232,11 +232,33 @@ static int tc_setup_cls_u32(struct stmmac_priv *priv,
 	}
 }
 
+static int tc_rfs_init(struct stmmac_priv *priv)
+{
+	int i;
+
+	priv->rfs_entries_max[STMMAC_RFS_T_VLAN] = 8;
+
+	for (i = 0; i < STMMAC_RFS_T_MAX; i++)
+		priv->rfs_entries_total += priv->rfs_entries_max[i];
+
+	priv->rfs_entries = devm_kcalloc(priv->device,
+					 priv->rfs_entries_total,
+					 sizeof(*priv->rfs_entries),
+					 GFP_KERNEL);
+	if (!priv->rfs_entries)
+		return -ENOMEM;
+
+	dev_info(priv->device, "Enabled RFS Flow TC (entries=%d)\n",
+		 priv->rfs_entries_total);
+
+	return 0;
+}
+
 static int tc_init(struct stmmac_priv *priv)
 {
 	struct dma_features *dma_cap = &priv->dma_cap;
 	unsigned int count;
-	int i;
+	int ret, i;
 
 	if (dma_cap->l3l4fnum) {
 		priv->flow_entries_max = dma_cap->l3l4fnum;
@@ -250,10 +272,14 @@ static int tc_init(struct stmmac_priv *priv)
 		for (i = 0; i < priv->flow_entries_max; i++)
 			priv->flow_entries[i].idx = i;
 
-		dev_info(priv->device, "Enabled Flow TC (entries=%d)\n",
+		dev_info(priv->device, "Enabled L3L4 Flow TC (entries=%d)\n",
 			 priv->flow_entries_max);
 	}
 
+	ret = tc_rfs_init(priv);
+	if (ret)
+		return -ENOMEM;
+
 	if (!priv->plat->fpe_cfg) {
 		priv->plat->fpe_cfg = devm_kzalloc(priv->device,
 						   sizeof(*priv->plat->fpe_cfg),
@@ -607,16 +633,45 @@ static int tc_del_flow(struct stmmac_priv *priv,
 	return ret;
 }
 
+static struct stmmac_rfs_entry *tc_find_rfs(struct stmmac_priv *priv,
+					    struct flow_cls_offload *cls,
+					    bool get_free)
+{
+	int i;
+
+	for (i = 0; i < priv->rfs_entries_total; i++) {
+		struct stmmac_rfs_entry *entry = &priv->rfs_entries[i];
+
+		if (entry->cookie == cls->cookie)
+			return entry;
+		if (get_free && entry->in_use == false)
+			return entry;
+	}
+
+	return NULL;
+}
+
 #define VLAN_PRIO_FULL_MASK (0x07)
 
 static int tc_add_vlan_flow(struct stmmac_priv *priv,
 			    struct flow_cls_offload *cls)
 {
+	struct stmmac_rfs_entry *entry = tc_find_rfs(priv, cls, false);
 	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
 	struct flow_dissector *dissector = rule->match.dissector;
 	int tc = tc_classid_to_hwtc(priv->dev, cls->classid);
 	struct flow_match_vlan match;
 
+	if (!entry) {
+		entry = tc_find_rfs(priv, cls, true);
+		if (!entry)
+			return -ENOENT;
+	}
+
+	if (priv->rfs_entries_cnt[STMMAC_RFS_T_VLAN] >=
+	    priv->rfs_entries_max[STMMAC_RFS_T_VLAN])
+		return -ENOENT;
+
 	/* Nothing to do here */
 	if (!dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_VLAN))
 		return -EINVAL;
@@ -638,6 +693,12 @@ static int tc_add_vlan_flow(struct stmmac_priv *priv,
 
 		prio = BIT(match.key->vlan_priority);
 		stmmac_rx_queue_prio(priv, priv->hw, prio, tc);
+
+		entry->in_use = true;
+		entry->cookie = cls->cookie;
+		entry->tc = tc;
+		entry->type = STMMAC_RFS_T_VLAN;
+		priv->rfs_entries_cnt[STMMAC_RFS_T_VLAN]++;
 	}
 
 	return 0;
@@ -646,20 +707,19 @@ static int tc_add_vlan_flow(struct stmmac_priv *priv,
 static int tc_del_vlan_flow(struct stmmac_priv *priv,
 			    struct flow_cls_offload *cls)
 {
-	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
-	struct flow_dissector *dissector = rule->match.dissector;
-	int tc = tc_classid_to_hwtc(priv->dev, cls->classid);
+	struct stmmac_rfs_entry *entry = tc_find_rfs(priv, cls, false);
 
-	/* Nothing to do here */
-	if (!dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_VLAN))
-		return -EINVAL;
+	if (!entry || !entry->in_use || entry->type != STMMAC_RFS_T_VLAN)
+		return -ENOENT;
 
-	if (tc < 0) {
-		netdev_err(priv->dev, "Invalid traffic class\n");
-		return -EINVAL;
-	}
+	stmmac_rx_queue_prio(priv, priv->hw, 0, entry->tc);
+
+	entry->in_use = false;
+	entry->cookie = 0;
+	entry->tc = 0;
+	entry->type = 0;
 
-	stmmac_rx_queue_prio(priv, priv->hw, 0, tc);
+	priv->rfs_entries_cnt[STMMAC_RFS_T_VLAN]--;
 
 	return 0;
 }
-- 
cgit v1.2.3


From b442f2ea84624873d538e4c5986d7c0d40883a47 Mon Sep 17 00:00:00 2001
From: Danielle Ratson
Date: Tue, 14 Dec 2021 12:21:36 +0200
Subject: mlxsw: spectrum_router: Consolidate MAC profiles when possible

Currently, when setting a router interface (RIF) MAC address while the
MAC profile is not shared with other RIFs, the profile is edited so that
the new MAC address is assigned to it.

This does not take into account a situation in which the new MAC address
already matches an existing MAC profile. In that situation, two MAC
profiles will be occupied even though they hold MAC addresses from the
same profile.

In order to prevent that, add a check to ensure that editing a MAC
profile takes place only when the new MAC address does not match an
existing profile.

Fixes: 605d25cd782a6 ("mlxsw: spectrum_router: Add RIF MAC profiles support")
Reported-by: Maksym Yaremchuk <maksymy@nvidia.com>
Tested-by: Maksym Yaremchuk <maksymy@nvidia.com>
Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 217e3b351dfe..c34833ff1dde 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -8494,7 +8494,8 @@ mlxsw_sp_rif_mac_profile_replace(struct mlxsw_sp *mlxsw_sp,
 	u8 mac_profile;
 	int err;
 
-	if (!mlxsw_sp_rif_mac_profile_is_shared(rif))
+	if (!mlxsw_sp_rif_mac_profile_is_shared(rif) &&
+	    !mlxsw_sp_rif_mac_profile_find(mlxsw_sp, new_mac))
 		return mlxsw_sp_rif_mac_profile_edit(rif, new_mac);
 
 	err = mlxsw_sp_rif_mac_profile_get(mlxsw_sp, new_mac,
-- 
cgit v1.2.3


From 0013881c1145d36bf26165bb70fdd7560a5507a3 Mon Sep 17 00:00:00 2001
From: Karol Kolacinski
Date: Thu, 4 Nov 2021 14:52:11 +0100
Subject: ice: Use div64_u64 instead of div_u64 in adjfine

Change the division in ice_ptp_adjfine from div_u64 to div64_u64.
div_u64 is used when the divisor is 32 bit but in this case incval is
64 bit and it caused incorrect calculations and incval adjustments.

Fixes: 06c16d89d2cb ("ice: register 1588 PTP clock device object for E810 devices")
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Gurucharan G <gurucharanx.g@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ptp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index bf7247c6f58e..ad7cabe7932f 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -705,7 +705,7 @@ static int ice_ptp_adjfine(struct ptp_clock_info *info, long scaled_ppm)
 		scaled_ppm = -scaled_ppm;
 	}
 
-	while ((u64)scaled_ppm > div_u64(U64_MAX, incval)) {
+	while ((u64)scaled_ppm > div64_u64(U64_MAX, incval)) {
 		/* handle overflow by scaling down the scaled_ppm and
 		 * the divisor, losing some precision
 		 */
-- 
cgit v1.2.3


From 37e738b6fdb14529534dca441e0222313688fde3 Mon Sep 17 00:00:00 2001
From: Karol Kolacinski
Date: Tue, 16 Nov 2021 13:07:14 +0100
Subject: ice: Don't put stale timestamps in the skb

The driver has to check if it does not accidentally put the timestamp in
the SKB before previous timestamp gets overwritten.
Timestamp values in the PHY are read only and do not get cleared except
at hardware reset or when a new timestamp value is captured.
The cached_tstamp field is used to detect the case where a new timestamp
has not yet been captured, ensuring that we avoid sending stale
timestamp data to the stack.

Fixes: ea9b847cda64 ("ice: enable transmit timestamps for E810 devices")
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Gurucharan G <gurucharanx.g@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ptp.c | 11 ++++-------
 drivers/net/ethernet/intel/ice/ice_ptp.h |  6 ++++++
 2 files changed, 10 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index ad7cabe7932f..442b031b0edc 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -1540,19 +1540,16 @@ static void ice_ptp_tx_tstamp_work(struct kthread_work *work)
 		if (err)
 			continue;
 
-		/* Check if the timestamp is valid */
-		if (!(raw_tstamp & ICE_PTP_TS_VALID))
+		/* Check if the timestamp is invalid or stale */
+		if (!(raw_tstamp & ICE_PTP_TS_VALID) ||
+		    raw_tstamp == tx->tstamps[idx].cached_tstamp)
 			continue;
 
-		/* clear the timestamp register, so that it won't show valid
-		 * again when re-used.
-		 */
-		ice_clear_phy_tstamp(hw, tx->quad, phy_idx);
-
 		/* The timestamp is valid, so we'll go ahead and clear this
 		 * index and then send the timestamp up to the stack.
 		 */
 		spin_lock(&tx->lock);
+		tx->tstamps[idx].cached_tstamp = raw_tstamp;
 		clear_bit(idx, tx->in_use);
 		skb = tx->tstamps[idx].skb;
 		tx->tstamps[idx].skb = NULL;
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h
index f71ad317d6c8..53c15fc9d996 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.h
@@ -55,15 +55,21 @@ struct ice_perout_channel {
  * struct ice_tx_tstamp - Tracking for a single Tx timestamp
  * @skb: pointer to the SKB for this timestamp request
  * @start: jiffies when the timestamp was first requested
+ * @cached_tstamp: last read timestamp
  *
  * This structure tracks a single timestamp request. The SKB pointer is
  * provided when initiating a request. The start time is used to ensure that
  * we discard old requests that were not fulfilled within a 2 second time
  * window.
+ * Timestamp values in the PHY are read only and do not get cleared except at
+ * hardware reset or when a new timestamp value is captured. The cached_tstamp
+ * field is used to detect the case where a new timestamp has not yet been
+ * captured, ensuring that we avoid sending stale timestamp data to the stack.
  */
 struct ice_tx_tstamp {
 	struct sk_buff *skb;
 	unsigned long start;
+	u64 cached_tstamp;
 };
 
 /**
-- 
cgit v1.2.3


From 584af82154f56e6b2740160fcc84a2966d969e15 Mon Sep 17 00:00:00 2001
From: Karen Sornek
Date: Tue, 31 Aug 2021 13:16:35 +0200
Subject: igb: Fix removal of unicast MAC filters of VFs

Move checking condition of VF MAC filter before clearing
or adding MAC filter to VF to prevent potential blackout caused
by removal of necessary and working VF's MAC filter.

Fixes: 1b8b062a99dc ("igb: add VF trust infrastructure")
Signed-off-by: Karen Sornek <karen.sornek@intel.com>
Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index fd54d3ef890b..b597b8bfb910 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -7648,6 +7648,20 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf,
 	struct vf_mac_filter *entry = NULL;
 	int ret = 0;
 
+	if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) &&
+	    !vf_data->trusted) {
+		dev_warn(&pdev->dev,
+			 "VF %d requested MAC filter but is administratively denied\n",
+			  vf);
+		return -EINVAL;
+	}
+	if (!is_valid_ether_addr(addr)) {
+		dev_warn(&pdev->dev,
+			 "VF %d attempted to set invalid MAC filter\n",
+			  vf);
+		return -EINVAL;
+	}
+
 	switch (info) {
 	case E1000_VF_MAC_FILTER_CLR:
 		/* remove all unicast MAC filters related to the current VF */
@@ -7661,20 +7675,6 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf,
 		}
 		break;
 	case E1000_VF_MAC_FILTER_ADD:
-		if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) &&
-		    !vf_data->trusted) {
-			dev_warn(&pdev->dev,
-				 "VF %d requested MAC filter but is administratively denied\n",
-				 vf);
-			return -EINVAL;
-		}
-		if (!is_valid_ether_addr(addr)) {
-			dev_warn(&pdev->dev,
-				 "VF %d attempted to set invalid MAC filter\n",
-				 vf);
-			return -EINVAL;
-		}
-
 		/* try to find empty slot in the list */
 		list_for_each(pos, &adapter->vf_macs.l) {
 			entry = list_entry(pos, struct vf_mac_filter, l);
-- 
cgit v1.2.3


From b6d335a60dc624c0d279333b22c737faa765b028 Mon Sep 17 00:00:00 2001
From: Letu Ren
Date: Sat, 13 Nov 2021 11:42:34 +0800
Subject: igbvf: fix double free in `igbvf_probe`

In `igbvf_probe`, if register_netdev() fails, the program will go to
label err_hw_init, and then to label err_ioremap. In free_netdev() which
is just below label err_ioremap, there is `list_for_each_entry_safe` and
`netif_napi_del` which aims to delete all entries in `dev->napi_list`.
The program has added an entry `adapter->rx_ring->napi` which is added by
`netif_napi_add` in igbvf_alloc_queues(). However, adapter->rx_ring has
been freed below label err_hw_init. So this a UAF.

In terms of how to patch the problem, we can refer to igbvf_remove() and
delete the entry before `adapter->rx_ring`.

The KASAN logs are as follows:

[   35.126075] BUG: KASAN: use-after-free in free_netdev+0x1fd/0x450
[   35.127170] Read of size 8 at addr ffff88810126d990 by task modprobe/366
[   35.128360]
[   35.128643] CPU: 1 PID: 366 Comm: modprobe Not tainted 5.15.0-rc2+ #14
[   35.129789] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014
[   35.131749] Call Trace:
[   35.132199]  dump_stack_lvl+0x59/0x7b
[   35.132865]  print_address_description+0x7c/0x3b0
[   35.133707]  ? free_netdev+0x1fd/0x450
[   35.134378]  __kasan_report+0x160/0x1c0
[   35.135063]  ? free_netdev+0x1fd/0x450
[   35.135738]  kasan_report+0x4b/0x70
[   35.136367]  free_netdev+0x1fd/0x450
[   35.137006]  igbvf_probe+0x121d/0x1a10 [igbvf]
[   35.137808]  ? igbvf_vlan_rx_add_vid+0x100/0x100 [igbvf]
[   35.138751]  local_pci_probe+0x13c/0x1f0
[   35.139461]  pci_device_probe+0x37e/0x6c0
[   35.165526]
[   35.165806] Allocated by task 366:
[   35.166414]  ____kasan_kmalloc+0xc4/0xf0
[   35.167117]  foo_kmem_cache_alloc_trace+0x3c/0x50 [igbvf]
[   35.168078]  igbvf_probe+0x9c5/0x1a10 [igbvf]
[   35.168866]  local_pci_probe+0x13c/0x1f0
[   35.169565]  pci_device_probe+0x37e/0x6c0
[   35.179713]
[   35.179993] Freed by task 366:
[   35.180539]  kasan_set_track+0x4c/0x80
[   35.181211]  kasan_set_free_info+0x1f/0x40
[   35.181942]  ____kasan_slab_free+0x103/0x140
[   35.182703]  kfree+0xe3/0x250
[   35.183239]  igbvf_probe+0x1173/0x1a10 [igbvf]
[   35.184040]  local_pci_probe+0x13c/0x1f0

Fixes: d4e0fe01a38a0 (igbvf: add new driver to support 82576 virtual functions)
Reported-by: Zheyu Ma <zheyuma97@gmail.com>
Signed-off-by: Letu Ren <fantasquex@gmail.com>
Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igbvf/netdev.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index 74ccd622251a..4d988da68394 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -2859,6 +2859,7 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return 0;
 
 err_hw_init:
+	netif_napi_del(&adapter->rx_ring->napi);
 	kfree(adapter->tx_ring);
 	kfree(adapter->rx_ring);
 err_sw_init:
-- 
cgit v1.2.3


From 0182d1f3fa640888a2ed7e3f6df2fdb10adee7c8 Mon Sep 17 00:00:00 2001
From: Sasha Neftin
Date: Tue, 2 Nov 2021 09:20:06 +0200
Subject: igc: Fix typo in i225 LTR functions

The LTR maximum value was incorrectly written using the scale from
the LTR minimum value. This would cause incorrect values to be sent,
in cases where the initial calculation lead to different min/max scales.

Fixes: 707abf069548 ("igc: Add initial LTR support")
Suggested-by: Dima Ruinskiy <dima.ruinskiy@intel.com>
Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Nechama Kraus <nechamax.kraus@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_i225.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_i225.c b/drivers/net/ethernet/intel/igc/igc_i225.c
index b2ef9fde97b3..b6807e16eea9 100644
--- a/drivers/net/ethernet/intel/igc/igc_i225.c
+++ b/drivers/net/ethernet/intel/igc/igc_i225.c
@@ -636,7 +636,7 @@ s32 igc_set_ltr_i225(struct igc_hw *hw, bool link)
 		ltrv = rd32(IGC_LTRMAXV);
 		if (ltr_max != (ltrv & IGC_LTRMAXV_LTRV_MASK)) {
 			ltrv = IGC_LTRMAXV_LSNP_REQ | ltr_max |
-			       (scale_min << IGC_LTRMAXV_SCALE_SHIFT);
+			       (scale_max << IGC_LTRMAXV_SCALE_SHIFT);
 			wr32(IGC_LTRMAXV, ltrv);
 		}
 	}
-- 
cgit v1.2.3


From 271225fd57c2f1e0b3f8826df51be6c634affefe Mon Sep 17 00:00:00 2001
From: Robert Schlabbach
Date: Tue, 26 Oct 2021 02:24:48 +0200
Subject: ixgbe: Document how to enable NBASE-T support

Commit a296d665eae1 ("ixgbe: Add ethtool support to enable 2.5 and 5.0
Gbps support") introduced suppression of the advertisement of NBASE-T
speeds by default, according to Todd Fujinaka to accommodate customers
with network switches which could not cope with advertised NBASE-T
speeds, as posted in the E1000-devel mailing list:

https://sourceforge.net/p/e1000/mailman/message/37106269/

However, the suppression was not documented at all, nor was how to
enable NBASE-T support.

Properly document the NBASE-T suppression and how to enable NBASE-T
support.

Fixes: a296d665eae1 ("ixgbe: Add ethtool support to enable 2.5 and 5.0 Gbps support")
Reported-by: Robert Schlabbach <robert_s@gmx.net>
Signed-off-by: Robert Schlabbach <robert_s@gmx.net>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../networking/device_drivers/ethernet/intel/ixgbe.rst   | 16 ++++++++++++++++
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c            |  4 ++++
 2 files changed, 20 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/Documentation/networking/device_drivers/ethernet/intel/ixgbe.rst b/Documentation/networking/device_drivers/ethernet/intel/ixgbe.rst
index f1d5233e5e51..0a233b17c664 100644
--- a/Documentation/networking/device_drivers/ethernet/intel/ixgbe.rst
+++ b/Documentation/networking/device_drivers/ethernet/intel/ixgbe.rst
@@ -440,6 +440,22 @@ NOTE: For 82599-based network connections, if you are enabling jumbo frames in
 a virtual function (VF), jumbo frames must first be enabled in the physical
 function (PF). The VF MTU setting cannot be larger than the PF MTU.
 
+NBASE-T Support
+---------------
+The ixgbe driver supports NBASE-T on some devices. However, the advertisement
+of NBASE-T speeds is suppressed by default, to accommodate broken network
+switches which cannot cope with advertised NBASE-T speeds. Use the ethtool
+command to enable advertising NBASE-T speeds on devices which support it::
+
+  ethtool -s eth? advertise 0x1800000001028
+
+On Linux systems with INTERFACES(5), this can be specified as a pre-up command
+in /etc/network/interfaces so that the interface is always brought up with
+NBASE-T support, e.g.::
+
+  iface eth? inet dhcp
+       pre-up ethtool -s eth? advertise 0x1800000001028 || true
+
 Generic Receive Offload, aka GRO
 --------------------------------
 The driver supports the in-kernel software implementation of GRO. GRO has
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 0f9f022260d7..45e2ec4d264d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -5531,6 +5531,10 @@ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw)
 	if (!speed && hw->mac.ops.get_link_capabilities) {
 		ret = hw->mac.ops.get_link_capabilities(hw, &speed,
 							&autoneg);
+		/* remove NBASE-T speeds from default autonegotiation
+		 * to accommodate broken network switches in the field
+		 * which cannot cope with advertised NBASE-T speeds
+		 */
 		speed &= ~(IXGBE_LINK_SPEED_5GB_FULL |
 			   IXGBE_LINK_SPEED_2_5GB_FULL);
 	}
-- 
cgit v1.2.3


From bf0a375055bd1afbbf02a0ef45f7655da7b71317 Mon Sep 17 00:00:00 2001
From: Cyril Novikov
Date: Mon, 1 Nov 2021 18:39:36 -0700
Subject: ixgbe: set X550 MDIO speed before talking to PHY

The MDIO bus speed must be initialized before talking to the PHY the first
time in order to avoid talking to it using a speed that the PHY doesn't
support.

This fixes HW initialization error -17 (IXGBE_ERR_PHY_ADDR_INVALID) on
Denverton CPUs (a.k.a. the Atom C3000 family) on ports with a 10Gb network
plugged in. On those devices, HLREG0[MDCSPD] resets to 1, which combined
with the 10Gb network results in a 24MHz MDIO speed, which is apparently
too fast for the connected PHY. PHY register reads over MDIO bus return
garbage, leading to initialization failure.

Reproduced with Linux kernel 4.19 and 5.15-rc7. Can be reproduced using
the following setup:

* Use an Atom C3000 family system with at least one X552 LAN on the SoC
* Disable PXE or other BIOS network initialization if possible
  (the interface must not be initialized before Linux boots)
* Connect a live 10Gb Ethernet cable to an X550 port
* Power cycle (not reset, doesn't always work) the system and boot Linux
* Observe: ixgbe interfaces w/ 10GbE cables plugged in fail with error -17

Fixes: e84db7272798 ("ixgbe: Introduce function to control MDIO speed")
Signed-off-by: Cyril Novikov <cnovikov@lynx.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
index 9724ffb16518..e4b50c7781ff 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
@@ -3405,6 +3405,9 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw)
 	/* flush pending Tx transactions */
 	ixgbe_clear_tx_pending(hw);
 
+	/* set MDIO speed before talking to the PHY in case it's the 1st time */
+	ixgbe_set_mdio_speed(hw);
+
 	/* PHY ops must be identified and initialized prior to reset */
 	status = hw->phy.ops.init(hw);
 	if (status == IXGBE_ERR_SFP_NOT_SUPPORTED ||
-- 
cgit v1.2.3


From 972ce7e3801e790bb348bfe98be1ab65af15bacd Mon Sep 17 00:00:00 2001
From: Ioana Ciornei
Date: Wed, 15 Dec 2021 12:58:31 +0200
Subject: dpaa2-eth: fix ethtool statistics

Unfortunately, with the blamed commit I also added a side effect in the
ethtool stats shown. Because I added two more fields in the per channel
structure without verifying if its size is used in any way, part of the
ethtool statistics were off by 2.
Fix this by not looking up the size of the structure but instead on a
fixed value kept in a macro.

Fixes: fc398bec0387 ("net: dpaa2: add adaptive interrupt coalescing")
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Link: https://lore.kernel.org/r/20211215105831.290070-1-ioana.ciornei@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h     | 2 ++
 drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 2085844227fe..e54e70ebdd05 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -388,6 +388,8 @@ struct dpaa2_eth_ch_stats {
 	__u64 bytes_per_cdan;
 };
 
+#define DPAA2_ETH_CH_STATS	7
+
 /* Maximum number of queues associated with a DPNI */
 #define DPAA2_ETH_MAX_TCS		8
 #define DPAA2_ETH_MAX_RX_QUEUES_PER_TC	16
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index adb8ce5306ee..3fdbf87dccb1 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -278,7 +278,7 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev,
 	/* Per-channel stats */
 	for (k = 0; k < priv->num_channels; k++) {
 		ch_stats = &priv->channel[k]->stats;
-		for (j = 0; j < sizeof(*ch_stats) / sizeof(__u64) - 1; j++)
+		for (j = 0; j < DPAA2_ETH_CH_STATS; j++)
 			*((__u64 *)data + i + j) += *((__u64 *)ch_stats + j);
 	}
 	i += j;
-- 
cgit v1.2.3


From 0546b224cc7717cc8a2db076b0bb069a9c430794 Mon Sep 17 00:00:00 2001
From: John Keeping
Date: Tue, 14 Dec 2021 19:10:09 +0000
Subject: net: stmmac: dwmac-rk: fix oob read in rk_gmac_setup

KASAN reports an out-of-bounds read in rk_gmac_setup on the line:

	while (ops->regs[i]) {

This happens for most platforms since the regs flexible array member is
empty, so the memory after the ops structure is being read here.  It
seems that mostly this happens to contain zero anyway, so we get lucky
and everything still works.

To avoid adding redundant data to nearly all the ops structures, add a
new flag to indicate whether the regs field is valid and avoid this loop
when it is not.

Fixes: 3bb3d6b1c195 ("net: stmmac: Add RK3566/RK3568 SoC support")
Signed-off-by: John Keeping <john@metanate.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 6924a6aacbd5..c469abc91fa1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -33,6 +33,7 @@ struct rk_gmac_ops {
 	void (*set_rgmii_speed)(struct rk_priv_data *bsp_priv, int speed);
 	void (*set_rmii_speed)(struct rk_priv_data *bsp_priv, int speed);
 	void (*integrated_phy_powerup)(struct rk_priv_data *bsp_priv);
+	bool regs_valid;
 	u32 regs[];
 };
 
@@ -1092,6 +1093,7 @@ static const struct rk_gmac_ops rk3568_ops = {
 	.set_to_rmii = rk3568_set_to_rmii,
 	.set_rgmii_speed = rk3568_set_gmac_speed,
 	.set_rmii_speed = rk3568_set_gmac_speed,
+	.regs_valid = true,
 	.regs = {
 		0xfe2a0000, /* gmac0 */
 		0xfe010000, /* gmac1 */
@@ -1383,7 +1385,7 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev,
 	 * to be distinguished.
 	 */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (res) {
+	if (res && ops->regs_valid) {
 		int i = 0;
 
 		while (ops->regs[i]) {
-- 
cgit v1.2.3


From 407ecd1bd726f240123f704620d46e285ff30dd9 Mon Sep 17 00:00:00 2001
From: Jiasheng Jiang
Date: Wed, 15 Dec 2021 22:37:31 +0800
Subject: sfc_ef100: potential dereference of null pointer

The return value of kmalloc() needs to be checked.
To avoid use in efx_nic_update_stats() in case of the failure of alloc.

Fixes: b593b6f1b492 ("sfc_ef100: statistics gathering")
Signed-off-by: Jiasheng Jiang <jiasheng@iscas.ac.cn>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef100_nic.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c
index 6aa81229b68a..e77a5cb4e40d 100644
--- a/drivers/net/ethernet/sfc/ef100_nic.c
+++ b/drivers/net/ethernet/sfc/ef100_nic.c
@@ -609,6 +609,9 @@ static size_t ef100_update_stats(struct efx_nic *efx,
 	ef100_common_stat_mask(mask);
 	ef100_ethtool_stat_mask(mask);
 
+	if (!mc_stats)
+		return 0;
+
 	efx_nic_copy_stats(efx, mc_stats);
 	efx_nic_update_stats(ef100_stat_desc, EF100_STAT_COUNT, mask,
 			     stats, mc_stats, false);
-- 
cgit v1.2.3


From 8b8e6e782456f1ce02a7ae914bbd5b1053f0b034 Mon Sep 17 00:00:00 2001
From: Florian Fainelli
Date: Wed, 15 Dec 2021 12:24:49 -0800
Subject: net: systemport: Add global locking for descriptor lifecycle

The descriptor list is a shared resource across all of the transmit queues, and
the locking mechanism used today only protects concurrency across a given
transmit queue between the transmit and reclaiming. This creates an opportunity
for the SYSTEMPORT hardware to work on corrupted descriptors if we have
multiple producers at once which is the case when using multiple transmit
queues.

This was particularly noticeable when using multiple flows/transmit queues and
it showed up in interesting ways in that UDP packets would get a correct UDP
header checksum being calculated over an incorrect packet length. Similarly TCP
packets would get an equally correct checksum computed by the hardware over an
incorrect packet length.

The SYSTEMPORT hardware maintains an internal descriptor list that it re-arranges
when the driver produces a new descriptor anytime it writes to the
WRITE_PORT_{HI,LO} registers, there is however some delay in the hardware to
re-organize its descriptors and it is possible that concurrent TX queues
eventually break this internal allocation scheme to the point where the
length/status part of the descriptor gets used for an incorrect data buffer.

The fix is to impose a global serialization for all TX queues in the short
section where we are writing to the WRITE_PORT_{HI,LO} registers which solves
the corruption even with multiple concurrent TX queues being used.

Fixes: 80105befdb4b ("net: systemport: add Broadcom SYSTEMPORT Ethernet MAC driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Link: https://lore.kernel.org/r/20211215202450.4086240-1-f.fainelli@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 5 ++++-
 drivers/net/ethernet/broadcom/bcmsysport.h | 1 +
 2 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 40933bf5a710..60dde29974bf 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1309,11 +1309,11 @@ static netdev_tx_t bcm_sysport_xmit(struct sk_buff *skb,
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	struct device *kdev = &priv->pdev->dev;
 	struct bcm_sysport_tx_ring *ring;
+	unsigned long flags, desc_flags;
 	struct bcm_sysport_cb *cb;
 	struct netdev_queue *txq;
 	u32 len_status, addr_lo;
 	unsigned int skb_len;
-	unsigned long flags;
 	dma_addr_t mapping;
 	u16 queue;
 	int ret;
@@ -1373,8 +1373,10 @@ static netdev_tx_t bcm_sysport_xmit(struct sk_buff *skb,
 	ring->desc_count--;
 
 	/* Ports are latched, so write upper address first */
+	spin_lock_irqsave(&priv->desc_lock, desc_flags);
 	tdma_writel(priv, len_status, TDMA_WRITE_PORT_HI(ring->index));
 	tdma_writel(priv, addr_lo, TDMA_WRITE_PORT_LO(ring->index));
+	spin_unlock_irqrestore(&priv->desc_lock, desc_flags);
 
 	/* Check ring space and update SW control flow */
 	if (ring->desc_count == 0)
@@ -2013,6 +2015,7 @@ static int bcm_sysport_open(struct net_device *dev)
 	}
 
 	/* Initialize both hardware and software ring */
+	spin_lock_init(&priv->desc_lock);
 	for (i = 0; i < dev->num_tx_queues; i++) {
 		ret = bcm_sysport_init_tx_ring(priv, i);
 		if (ret) {
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index 984f76e74b43..16b73bb9acc7 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -711,6 +711,7 @@ struct bcm_sysport_priv {
 	int			wol_irq;
 
 	/* Transmit rings */
+	spinlock_t		desc_lock;
 	struct bcm_sysport_tx_ring *tx_rings;
 
 	/* Receive queue */
-- 
cgit v1.2.3


From afe8a3ba85ec2a6b6849367e25c06a2f8e0ddd05 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski
Date: Mon, 13 Dec 2021 16:31:06 +0100
Subject: ice: xsk: return xsk buffers back to pool when cleaning the ring

Currently we only NULL the xdp_buff pointer in the internal SW ring but
we never give it back to the xsk buffer pool. This means that buffers
can be leaked out of the buff pool and never be used again.

Add missing xsk_buff_free() call to the routine that is supposed to
clean the entries that are left in the ring so that these buffers in the
umem can be used by other sockets.

Also, only go through the space that is actually left to be cleaned
instead of a whole ring.

Fixes: 2d4238f55697 ("ice: Add support for AF_XDP")
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_xsk.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index bb9a80847298..8593717a755e 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -811,14 +811,14 @@ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi)
  */
 void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring)
 {
-	u16 i;
-
-	for (i = 0; i < rx_ring->count; i++) {
-		struct xdp_buff **xdp = &rx_ring->xdp_buf[i];
+	u16 count_mask = rx_ring->count - 1;
+	u16 ntc = rx_ring->next_to_clean;
+	u16 ntu = rx_ring->next_to_use;
 
-		if (!xdp)
-			continue;
+	for ( ; ntc != ntu; ntc = (ntc + 1) & count_mask) {
+		struct xdp_buff **xdp = &rx_ring->xdp_buf[ntc];
 
+		xsk_buff_free(*xdp);
 		*xdp = NULL;
 	}
 }
-- 
cgit v1.2.3


From 617f3e1b588c802517c236087561c6bcb0b4afd6 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski
Date: Mon, 13 Dec 2021 16:31:07 +0100
Subject: ice: xsk: allocate separate memory for XDP SW ring

Currently, the zero-copy data path is reusing the memory region that was
initially allocated for an array of struct ice_rx_buf for its own
purposes. This is error prone as it is based on the ice_rx_buf struct
always being the same size or bigger than what the zero-copy path needs.
There can also be old values present in that array giving rise to errors
when the zero-copy path uses it.

Fix this by freeing the ice_rx_buf region and allocating a new array for
the zero-copy path that has the right length and is initialized to zero.

Fixes: 57f7f8b6bc0b ("ice: Use xdp_buf instead of rx_buf for xsk zero-copy")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_base.c | 17 ++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_txrx.c | 19 ++++++++++++------
 drivers/net/ethernet/intel/ice/ice_xsk.c  | 33 ++++++++++++++++---------------
 3 files changed, 47 insertions(+), 22 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 1efc635cc0f5..fafe020e46ee 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -6,6 +6,18 @@
 #include "ice_lib.h"
 #include "ice_dcb_lib.h"
 
+static bool ice_alloc_rx_buf_zc(struct ice_rx_ring *rx_ring)
+{
+	rx_ring->xdp_buf = kcalloc(rx_ring->count, sizeof(*rx_ring->xdp_buf), GFP_KERNEL);
+	return !!rx_ring->xdp_buf;
+}
+
+static bool ice_alloc_rx_buf(struct ice_rx_ring *rx_ring)
+{
+	rx_ring->rx_buf = kcalloc(rx_ring->count, sizeof(*rx_ring->rx_buf), GFP_KERNEL);
+	return !!rx_ring->rx_buf;
+}
+
 /**
  * __ice_vsi_get_qs_contig - Assign a contiguous chunk of queues to VSI
  * @qs_cfg: gathered variables needed for PF->VSI queues assignment
@@ -492,8 +504,11 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 					 ring->q_index, ring->q_vector->napi.napi_id);
 
+		kfree(ring->rx_buf);
 		ring->xsk_pool = ice_xsk_pool(ring);
 		if (ring->xsk_pool) {
+			if (!ice_alloc_rx_buf_zc(ring))
+				return -ENOMEM;
 			xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
 
 			ring->rx_buf_len =
@@ -508,6 +523,8 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
 				 ring->q_index);
 		} else {
+			if (!ice_alloc_rx_buf(ring))
+				return -ENOMEM;
 			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
 				/* coverity[check_return] */
 				xdp_rxq_info_reg(&ring->xdp_rxq,
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index bc3ba19dc88f..dccf09eefc75 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -419,7 +419,10 @@ void ice_clean_rx_ring(struct ice_rx_ring *rx_ring)
 	}
 
 rx_skip_free:
-	memset(rx_ring->rx_buf, 0, sizeof(*rx_ring->rx_buf) * rx_ring->count);
+	if (rx_ring->xsk_pool)
+		memset(rx_ring->xdp_buf, 0, array_size(rx_ring->count, sizeof(*rx_ring->xdp_buf)));
+	else
+		memset(rx_ring->rx_buf, 0, array_size(rx_ring->count, sizeof(*rx_ring->rx_buf)));
 
 	/* Zero out the descriptor ring */
 	size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc),
@@ -446,8 +449,13 @@ void ice_free_rx_ring(struct ice_rx_ring *rx_ring)
 		if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
 			xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
 	rx_ring->xdp_prog = NULL;
-	devm_kfree(rx_ring->dev, rx_ring->rx_buf);
-	rx_ring->rx_buf = NULL;
+	if (rx_ring->xsk_pool) {
+		kfree(rx_ring->xdp_buf);
+		rx_ring->xdp_buf = NULL;
+	} else {
+		kfree(rx_ring->rx_buf);
+		rx_ring->rx_buf = NULL;
+	}
 
 	if (rx_ring->desc) {
 		size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc),
@@ -475,8 +483,7 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring)
 	/* warn if we are about to overwrite the pointer */
 	WARN_ON(rx_ring->rx_buf);
 	rx_ring->rx_buf =
-		devm_kcalloc(dev, sizeof(*rx_ring->rx_buf), rx_ring->count,
-			     GFP_KERNEL);
+		kcalloc(rx_ring->count, sizeof(*rx_ring->rx_buf), GFP_KERNEL);
 	if (!rx_ring->rx_buf)
 		return -ENOMEM;
 
@@ -505,7 +512,7 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring)
 	return 0;
 
 err:
-	devm_kfree(dev, rx_ring->rx_buf);
+	kfree(rx_ring->rx_buf);
 	rx_ring->rx_buf = NULL;
 	return -ENOMEM;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 8593717a755e..c124229d98fe 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -12,6 +12,11 @@
 #include "ice_txrx_lib.h"
 #include "ice_lib.h"
 
+static struct xdp_buff **ice_xdp_buf(struct ice_rx_ring *rx_ring, u32 idx)
+{
+	return &rx_ring->xdp_buf[idx];
+}
+
 /**
  * ice_qp_reset_stats - Resets all stats for rings of given index
  * @vsi: VSI that contains rings of interest
@@ -372,7 +377,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 	dma_addr_t dma;
 
 	rx_desc = ICE_RX_DESC(rx_ring, ntu);
-	xdp = &rx_ring->xdp_buf[ntu];
+	xdp = ice_xdp_buf(rx_ring, ntu);
 
 	nb_buffs = min_t(u16, count, rx_ring->count - ntu);
 	nb_buffs = xsk_buff_alloc_batch(rx_ring->xsk_pool, xdp, nb_buffs);
@@ -419,19 +424,18 @@ static void ice_bump_ntc(struct ice_rx_ring *rx_ring)
 /**
  * ice_construct_skb_zc - Create an sk_buff from zero-copy buffer
  * @rx_ring: Rx ring
- * @xdp_arr: Pointer to the SW ring of xdp_buff pointers
+ * @xdp: Pointer to XDP buffer
  *
  * This function allocates a new skb from a zero-copy Rx buffer.
  *
  * Returns the skb on success, NULL on failure.
  */
 static struct sk_buff *
-ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff **xdp_arr)
+ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 {
-	struct xdp_buff *xdp = *xdp_arr;
+	unsigned int datasize_hard = xdp->data_end - xdp->data_hard_start;
 	unsigned int metasize = xdp->data - xdp->data_meta;
 	unsigned int datasize = xdp->data_end - xdp->data;
-	unsigned int datasize_hard = xdp->data_end - xdp->data_hard_start;
 	struct sk_buff *skb;
 
 	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, datasize_hard,
@@ -445,7 +449,6 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff **xdp_arr)
 		skb_metadata_set(skb, metasize);
 
 	xsk_buff_free(xdp);
-	*xdp_arr = NULL;
 	return skb;
 }
 
@@ -522,7 +525,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 	while (likely(total_rx_packets < (unsigned int)budget)) {
 		union ice_32b_rx_flex_desc *rx_desc;
 		unsigned int size, xdp_res = 0;
-		struct xdp_buff **xdp;
+		struct xdp_buff *xdp;
 		struct sk_buff *skb;
 		u16 stat_err_bits;
 		u16 vlan_tag = 0;
@@ -545,18 +548,17 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		if (!size)
 			break;
 
-		xdp = &rx_ring->xdp_buf[rx_ring->next_to_clean];
-		xsk_buff_set_size(*xdp, size);
-		xsk_buff_dma_sync_for_cpu(*xdp, rx_ring->xsk_pool);
+		xdp = *ice_xdp_buf(rx_ring, rx_ring->next_to_clean);
+		xsk_buff_set_size(xdp, size);
+		xsk_buff_dma_sync_for_cpu(xdp, rx_ring->xsk_pool);
 
-		xdp_res = ice_run_xdp_zc(rx_ring, *xdp, xdp_prog, xdp_ring);
+		xdp_res = ice_run_xdp_zc(rx_ring, xdp, xdp_prog, xdp_ring);
 		if (xdp_res) {
 			if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))
 				xdp_xmit |= xdp_res;
 			else
-				xsk_buff_free(*xdp);
+				xsk_buff_free(xdp);
 
-			*xdp = NULL;
 			total_rx_bytes += size;
 			total_rx_packets++;
 			cleaned_count++;
@@ -816,10 +818,9 @@ void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring)
 	u16 ntu = rx_ring->next_to_use;
 
 	for ( ; ntc != ntu; ntc = (ntc + 1) & count_mask) {
-		struct xdp_buff **xdp = &rx_ring->xdp_buf[ntc];
+		struct xdp_buff *xdp = *ice_xdp_buf(rx_ring, ntc);
 
-		xsk_buff_free(*xdp);
-		*xdp = NULL;
+		xsk_buff_free(xdp);
 	}
 }
 
-- 
cgit v1.2.3


From 0708b6facb4d165ef22bccddf2dc3e1eb9a12d03 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin
Date: Mon, 13 Dec 2021 16:31:08 +0100
Subject: ice: remove dead store on XSK hotpath

The 'if (ntu == rx_ring->count)' block in ice_alloc_rx_buffers_zc()
was previously residing in the loop, but after introducing the
batched interface it is used only to wrap-around the NTU descriptor,
thus no more need to assign 'xdp'.

Fixes: db804cfc21e9 ("ice: Use the xsk batched rx allocation interface")
Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_xsk.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index c124229d98fe..27f5f64dcbd6 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -397,7 +397,6 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 	ntu += nb_buffs;
 	if (ntu == rx_ring->count) {
 		rx_desc = ICE_RX_DESC(rx_ring, 0);
-		xdp = rx_ring->xdp_buf;
 		ntu = 0;
 	}
 
-- 
cgit v1.2.3


From 8b51a13c37c24c08e488bd58303cb437814f4454 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski
Date: Mon, 13 Dec 2021 16:31:09 +0100
Subject: ice: xsk: do not clear status_error0 for ntu + nb_buffs descriptor

The descriptor that ntu is pointing at when we exit
ice_alloc_rx_bufs_zc() should not have its corresponding DD bit cleared
as descriptor is not allocated in there and it is not valid for HW
usage.

The allocation routine at the entry will fill the descriptor that ntu
points to after it was set to ntu + nb_buffs on previous call.

Even the spec says:
"The tail pointer should be set to one descriptor beyond the last empty
descriptor in host descriptor ring."

Therefore, step away from clearing the status_error0 on ntu + nb_buffs
descriptor.

Fixes: db804cfc21e9 ("ice: Use the xsk batched rx allocation interface")
Reported-by: Elza Mathew <elza.mathew@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_xsk.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 27f5f64dcbd6..ffa9a160766a 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -395,13 +395,9 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 	}
 
 	ntu += nb_buffs;
-	if (ntu == rx_ring->count) {
-		rx_desc = ICE_RX_DESC(rx_ring, 0);
+	if (ntu == rx_ring->count)
 		ntu = 0;
-	}
 
-	/* clear the status bits for the next_to_use descriptor */
-	rx_desc->wb.status_error0 = 0;
 	ice_release_rx_desc(rx_ring, ntu);
 
 	return count == nb_buffs;
-- 
cgit v1.2.3


From 8bea15ab7485863d900982ee6a0ff6f78b339c77 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski
Date: Mon, 13 Dec 2021 16:31:10 +0100
Subject: ice: xsk: allow empty Rx descriptors on XSK ZC data path

Commit ac6f733a7bd5 ("ice: allow empty Rx descriptors") stated that ice
HW can produce empty descriptors that are valid and they should be
processed.

Add this support to xsk ZC path to avoid potential processing problems.

Fixes: 2d4238f55697 ("ice: Add support for AF_XDP")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_xsk.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index ffa9a160766a..c1491dc0675d 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -538,12 +538,18 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		 */
 		dma_rmb();
 
+		xdp = *ice_xdp_buf(rx_ring, rx_ring->next_to_clean);
+
 		size = le16_to_cpu(rx_desc->wb.pkt_len) &
 				   ICE_RX_FLX_DESC_PKT_LEN_M;
-		if (!size)
-			break;
+		if (!size) {
+			xdp->data = NULL;
+			xdp->data_end = NULL;
+			xdp->data_hard_start = NULL;
+			xdp->data_meta = NULL;
+			goto construct_skb;
+		}
 
-		xdp = *ice_xdp_buf(rx_ring, rx_ring->next_to_clean);
 		xsk_buff_set_size(xdp, size);
 		xsk_buff_dma_sync_for_cpu(xdp, rx_ring->xsk_pool);
 
@@ -561,7 +567,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 			ice_bump_ntc(rx_ring);
 			continue;
 		}
-
+construct_skb:
 		/* XDP_PASS path */
 		skb = ice_construct_skb_zc(rx_ring, xdp);
 		if (!skb) {
-- 
cgit v1.2.3


From dcbaf72aa4232a7aa5db5e483972a6fe4ba2b41c Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski
Date: Mon, 13 Dec 2021 16:31:11 +0100
Subject: ice: xsk: fix cleaned_count setting

Currently cleaned_count is initialized to ICE_DESC_UNUSED(rx_ring) and
later on during the Rx processing it is incremented per each frame that
driver consumed. This can result in excessive buffers requested from xsk
pool based on that value.

To address this, just drop cleaned_count and pass
ICE_DESC_UNUSED(rx_ring) directly as a function argument to
ice_alloc_rx_bufs_zc(). Idea is to ask for buffers as many as consumed.

Let us also call ice_alloc_rx_bufs_zc unconditionally at the end of
ice_clean_rx_irq_zc. This has been changed in that way for corresponding
ice_clean_rx_irq, but not here.

Fixes: 2d4238f55697 ("ice: Add support for AF_XDP")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx.h | 1 -
 drivers/net/ethernet/intel/ice/ice_xsk.c  | 6 +-----
 2 files changed, 1 insertion(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index c56dd1749903..b7b3bd4816f0 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -24,7 +24,6 @@
 #define ICE_MAX_DATA_PER_TXD_ALIGNED \
 	(~(ICE_MAX_READ_REQ_SIZE - 1) & ICE_MAX_DATA_PER_TXD)
 
-#define ICE_RX_BUF_WRITE	16	/* Must be power of 2 */
 #define ICE_MAX_TXQ_PER_TXQG	128
 
 /* Attempt to maximize the headroom available for incoming frames. We use a 2K
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index c1491dc0675d..c895351b25e0 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -505,7 +505,6 @@ out_failure:
 int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
-	u16 cleaned_count = ICE_DESC_UNUSED(rx_ring);
 	struct ice_tx_ring *xdp_ring;
 	unsigned int xdp_xmit = 0;
 	struct bpf_prog *xdp_prog;
@@ -562,7 +561,6 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 
 			total_rx_bytes += size;
 			total_rx_packets++;
-			cleaned_count++;
 
 			ice_bump_ntc(rx_ring);
 			continue;
@@ -575,7 +573,6 @@ construct_skb:
 			break;
 		}
 
-		cleaned_count++;
 		ice_bump_ntc(rx_ring);
 
 		if (eth_skb_pad(skb)) {
@@ -597,8 +594,7 @@ construct_skb:
 		ice_receive_skb(rx_ring, skb, vlan_tag);
 	}
 
-	if (cleaned_count >= ICE_RX_BUF_WRITE)
-		failure = !ice_alloc_rx_bufs_zc(rx_ring, cleaned_count);
+	failure = !ice_alloc_rx_bufs_zc(rx_ring, ICE_DESC_UNUSED(rx_ring));
 
 	ice_finalize_xdp_rx(xdp_ring, xdp_xmit);
 	ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes);
-- 
cgit v1.2.3


From 1488fc204568f707fe2a42a913788c00a95af30e Mon Sep 17 00:00:00 2001
From: Aleksander Jan Bajkowski
Date: Fri, 17 Dec 2021 01:07:40 +0100
Subject: net: lantiq_xrx200: increase buffer reservation

If the user sets a lower mtu on the CPU port than on the switch,
then DMA inserts a few more bytes into the buffer than expected.
In the worst case, it may exceed the size of the buffer. The
experiments showed that the buffer should be a multiple of the
burst length value. This patch rounds the length of the rx buffer
upwards and fixes this bug. The reservation of FCS space in the
buffer has been removed as PMAC strips the FCS.

Fixes: 998ac358019e ("net: lantiq: add support for jumbo frames")
Reported-by: Thomas Nixon <tom@tomn.co.uk>
Signed-off-by: Aleksander Jan Bajkowski <olek2@wp.pl>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/lantiq_xrx200.c | 34 ++++++++++++++++++++++++----------
 1 file changed, 24 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 0da09ea81980..96bd6f2b21ed 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -71,6 +71,8 @@ struct xrx200_priv {
 	struct xrx200_chan chan_tx;
 	struct xrx200_chan chan_rx;
 
+	u16 rx_buf_size;
+
 	struct net_device *net_dev;
 	struct device *dev;
 
@@ -97,6 +99,16 @@ static void xrx200_pmac_mask(struct xrx200_priv *priv, u32 clear, u32 set,
 	xrx200_pmac_w32(priv, val, offset);
 }
 
+static int xrx200_max_frame_len(int mtu)
+{
+	return VLAN_ETH_HLEN + mtu;
+}
+
+static int xrx200_buffer_size(int mtu)
+{
+	return round_up(xrx200_max_frame_len(mtu), 4 * XRX200_DMA_BURST_LEN);
+}
+
 /* drop all the packets from the DMA ring */
 static void xrx200_flush_dma(struct xrx200_chan *ch)
 {
@@ -109,8 +121,7 @@ static void xrx200_flush_dma(struct xrx200_chan *ch)
 			break;
 
 		desc->ctl = LTQ_DMA_OWN | LTQ_DMA_RX_OFFSET(NET_IP_ALIGN) |
-			    (ch->priv->net_dev->mtu + VLAN_ETH_HLEN +
-			     ETH_FCS_LEN);
+			    ch->priv->rx_buf_size;
 		ch->dma.desc++;
 		ch->dma.desc %= LTQ_DESC_NUM;
 	}
@@ -158,21 +169,21 @@ static int xrx200_close(struct net_device *net_dev)
 
 static int xrx200_alloc_skb(struct xrx200_chan *ch)
 {
-	int len = ch->priv->net_dev->mtu + VLAN_ETH_HLEN + ETH_FCS_LEN;
 	struct sk_buff *skb = ch->skb[ch->dma.desc];
+	struct xrx200_priv *priv = ch->priv;
 	dma_addr_t mapping;
 	int ret = 0;
 
-	ch->skb[ch->dma.desc] = netdev_alloc_skb_ip_align(ch->priv->net_dev,
-							  len);
+	ch->skb[ch->dma.desc] = netdev_alloc_skb_ip_align(priv->net_dev,
+							  priv->rx_buf_size);
 	if (!ch->skb[ch->dma.desc]) {
 		ret = -ENOMEM;
 		goto skip;
 	}
 
-	mapping = dma_map_single(ch->priv->dev, ch->skb[ch->dma.desc]->data,
-				 len, DMA_FROM_DEVICE);
-	if (unlikely(dma_mapping_error(ch->priv->dev, mapping))) {
+	mapping = dma_map_single(priv->dev, ch->skb[ch->dma.desc]->data,
+				 priv->rx_buf_size, DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(priv->dev, mapping))) {
 		dev_kfree_skb_any(ch->skb[ch->dma.desc]);
 		ch->skb[ch->dma.desc] = skb;
 		ret = -ENOMEM;
@@ -184,7 +195,7 @@ static int xrx200_alloc_skb(struct xrx200_chan *ch)
 	wmb();
 skip:
 	ch->dma.desc_base[ch->dma.desc].ctl =
-		LTQ_DMA_OWN | LTQ_DMA_RX_OFFSET(NET_IP_ALIGN) | len;
+		LTQ_DMA_OWN | LTQ_DMA_RX_OFFSET(NET_IP_ALIGN) | priv->rx_buf_size;
 
 	return ret;
 }
@@ -356,6 +367,7 @@ xrx200_change_mtu(struct net_device *net_dev, int new_mtu)
 	int ret = 0;
 
 	net_dev->mtu = new_mtu;
+	priv->rx_buf_size = xrx200_buffer_size(new_mtu);
 
 	if (new_mtu <= old_mtu)
 		return ret;
@@ -375,6 +387,7 @@ xrx200_change_mtu(struct net_device *net_dev, int new_mtu)
 		ret = xrx200_alloc_skb(ch_rx);
 		if (ret) {
 			net_dev->mtu = old_mtu;
+			priv->rx_buf_size = xrx200_buffer_size(old_mtu);
 			break;
 		}
 		dev_kfree_skb_any(skb);
@@ -505,7 +518,8 @@ static int xrx200_probe(struct platform_device *pdev)
 	net_dev->netdev_ops = &xrx200_netdev_ops;
 	SET_NETDEV_DEV(net_dev, dev);
 	net_dev->min_mtu = ETH_ZLEN;
-	net_dev->max_mtu = XRX200_DMA_DATA_LEN - VLAN_ETH_HLEN - ETH_FCS_LEN;
+	net_dev->max_mtu = XRX200_DMA_DATA_LEN - xrx200_max_frame_len(0);
+	priv->rx_buf_size = xrx200_buffer_size(ETH_DATA_LEN);
 
 	/* load the memory ranges */
 	priv->pmac_reg = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
-- 
cgit v1.2.3


From 8b681bd7c301c423fbe97a6b23388a2180ff04ca Mon Sep 17 00:00:00 2001
From: Yevhen Orlov
Date: Thu, 16 Dec 2021 19:07:36 +0200
Subject: net: marvell: prestera: fix incorrect return of port_find

In case, when some ports is in list and we don't find requested - we
return last iterator state and not return NULL as expected.

Fixes: 501ef3066c89 ("net: marvell: prestera: Add driver for Prestera family ASIC devices")
Signed-off-by: Yevhen Orlov <yevhen.orlov@plvision.eu>
Link: https://lore.kernel.org/r/20211216170736.8851-1-yevhen.orlov@plvision.eu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/prestera/prestera_main.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c
index 4369a3ffad45..6c24375ad9cf 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_main.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c
@@ -54,12 +54,14 @@ int prestera_port_pvid_set(struct prestera_port *port, u16 vid)
 struct prestera_port *prestera_port_find_by_hwid(struct prestera_switch *sw,
 						 u32 dev_id, u32 hw_id)
 {
-	struct prestera_port *port = NULL;
+	struct prestera_port *port = NULL, *tmp;
 
 	read_lock(&sw->port_list_lock);
-	list_for_each_entry(port, &sw->port_list, list) {
-		if (port->dev_id == dev_id && port->hw_id == hw_id)
+	list_for_each_entry(tmp, &sw->port_list, list) {
+		if (tmp->dev_id == dev_id && tmp->hw_id == hw_id) {
+			port = tmp;
 			break;
+		}
 	}
 	read_unlock(&sw->port_list_lock);
 
@@ -68,12 +70,14 @@ struct prestera_port *prestera_port_find_by_hwid(struct prestera_switch *sw,
 
 struct prestera_port *prestera_find_port(struct prestera_switch *sw, u32 id)
 {
-	struct prestera_port *port = NULL;
+	struct prestera_port *port = NULL, *tmp;
 
 	read_lock(&sw->port_list_lock);
-	list_for_each_entry(port, &sw->port_list, list) {
-		if (port->id == id)
+	list_for_each_entry(tmp, &sw->port_list, list) {
+		if (tmp->id == id) {
+			port = tmp;
 			break;
+		}
 	}
 	read_unlock(&sw->port_list_lock);
 
-- 
cgit v1.2.3


From 2efc2256febf214e7b2bdaa21fe6c3c3146acdcb Mon Sep 17 00:00:00 2001
From: Yevhen Orlov
Date: Thu, 16 Dec 2021 19:17:14 +0200
Subject: net: marvell: prestera: fix incorrect structure access

In line:
	upper = info->upper_dev;
We access upper_dev field, which is related only for particular events
(e.g. event == NETDEV_CHANGEUPPER). So, this line cause invalid memory
access for another events,
when ptr is not netdev_notifier_changeupper_info.

The KASAN logs are as follows:

[   30.123165] BUG: KASAN: stack-out-of-bounds in prestera_netdev_port_event.constprop.0+0x68/0x538 [prestera]
[   30.133336] Read of size 8 at addr ffff80000cf772b0 by task udevd/778
[   30.139866]
[   30.141398] CPU: 0 PID: 778 Comm: udevd Not tainted 5.16.0-rc3 #6
[   30.147588] Hardware name: DNI AmazonGo1 A7040 board (DT)
[   30.153056] Call trace:
[   30.155547]  dump_backtrace+0x0/0x2c0
[   30.159320]  show_stack+0x18/0x30
[   30.162729]  dump_stack_lvl+0x68/0x84
[   30.166491]  print_address_description.constprop.0+0x74/0x2b8
[   30.172346]  kasan_report+0x1e8/0x250
[   30.176102]  __asan_load8+0x98/0xe0
[   30.179682]  prestera_netdev_port_event.constprop.0+0x68/0x538 [prestera]
[   30.186847]  prestera_netdev_event_handler+0x1b4/0x1c0 [prestera]
[   30.193313]  raw_notifier_call_chain+0x74/0xa0
[   30.197860]  call_netdevice_notifiers_info+0x68/0xc0
[   30.202924]  register_netdevice+0x3cc/0x760
[   30.207190]  register_netdev+0x24/0x50
[   30.211015]  prestera_device_register+0x8a0/0xba0 [prestera]

Fixes: 3d5048cc54bd ("net: marvell: prestera: move netdev topology validation to prestera_main")
Signed-off-by: Yevhen Orlov <yevhen.orlov@plvision.eu>
Link: https://lore.kernel.org/r/20211216171714.11341-1-yevhen.orlov@plvision.eu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/prestera/prestera_main.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c
index 6c24375ad9cf..c687dc9aa973 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_main.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c
@@ -768,23 +768,27 @@ static int prestera_netdev_port_event(struct net_device *lower,
 				      struct net_device *dev,
 				      unsigned long event, void *ptr)
 {
-	struct netdev_notifier_changeupper_info *info = ptr;
+	struct netdev_notifier_info *info = ptr;
+	struct netdev_notifier_changeupper_info *cu_info;
 	struct prestera_port *port = netdev_priv(dev);
 	struct netlink_ext_ack *extack;
 	struct net_device *upper;
 
-	extack = netdev_notifier_info_to_extack(&info->info);
-	upper = info->upper_dev;
+	extack = netdev_notifier_info_to_extack(info);
+	cu_info = container_of(info,
+			       struct netdev_notifier_changeupper_info,
+			       info);
 
 	switch (event) {
 	case NETDEV_PRECHANGEUPPER:
+		upper = cu_info->upper_dev;
 		if (!netif_is_bridge_master(upper) &&
 		    !netif_is_lag_master(upper)) {
 			NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
 			return -EINVAL;
 		}
 
-		if (!info->linking)
+		if (!cu_info->linking)
 			break;
 
 		if (netdev_has_any_upper_dev(upper)) {
@@ -793,7 +797,7 @@ static int prestera_netdev_port_event(struct net_device *lower,
 		}
 
 		if (netif_is_lag_master(upper) &&
-		    !prestera_lag_master_check(upper, info->upper_info, extack))
+		    !prestera_lag_master_check(upper, cu_info->upper_info, extack))
 			return -EOPNOTSUPP;
 		if (netif_is_lag_master(upper) && vlan_uses_dev(dev)) {
 			NL_SET_ERR_MSG_MOD(extack,
@@ -809,14 +813,15 @@ static int prestera_netdev_port_event(struct net_device *lower,
 		break;
 
 	case NETDEV_CHANGEUPPER:
+		upper = cu_info->upper_dev;
 		if (netif_is_bridge_master(upper)) {
-			if (info->linking)
+			if (cu_info->linking)
 				return prestera_bridge_port_join(upper, port,
 								 extack);
 			else
 				prestera_bridge_port_leave(upper, port);
 		} else if (netif_is_lag_master(upper)) {
-			if (info->linking)
+			if (cu_info->linking)
 				return prestera_lag_port_add(port, upper);
 			else
 				prestera_lag_port_del(port);
-- 
cgit v1.2.3


From 60ec7fcfe76892a1479afab51ff17a4281923156 Mon Sep 17 00:00:00 2001
From: Jiasheng Jiang
Date: Fri, 17 Dec 2021 17:39:11 +0800
Subject: qlcnic: potential dereference null pointer of rx_queue->page_ring

The return value of kcalloc() needs to be checked.
To avoid dereference of null pointer in case of the failure of alloc.
Therefore, it might be better to change the return type of
qlcnic_sriov_alloc_vlans() and return -ENOMEM when alloc fails and
return 0 the others.
Also, qlcnic_sriov_set_guest_vlan_mode() and __qlcnic_pci_sriov_enable()
should deal with the return value of qlcnic_sriov_alloc_vlans().

Fixes: 154d0c810c53 ("qlcnic: VLAN enhancement for 84XX adapters")
Signed-off-by: Jiasheng Jiang <jiasheng@iscas.ac.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h        |  2 +-
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c | 12 +++++++++---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c     |  4 +++-
 3 files changed, 13 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h
index 7160b42f51dd..d0111cb3b40e 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h
@@ -201,7 +201,7 @@ int qlcnic_sriov_get_vf_vport_info(struct qlcnic_adapter *,
 				   struct qlcnic_info *, u16);
 int qlcnic_sriov_cfg_vf_guest_vlan(struct qlcnic_adapter *, u16, u8);
 void qlcnic_sriov_free_vlans(struct qlcnic_adapter *);
-void qlcnic_sriov_alloc_vlans(struct qlcnic_adapter *);
+int qlcnic_sriov_alloc_vlans(struct qlcnic_adapter *);
 bool qlcnic_sriov_check_any_vlan(struct qlcnic_vf_info *);
 void qlcnic_sriov_del_vlan_id(struct qlcnic_sriov *,
 			      struct qlcnic_vf_info *, u16);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
index dd03be3fc82a..42a44c97572a 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
@@ -432,7 +432,7 @@ static int qlcnic_sriov_set_guest_vlan_mode(struct qlcnic_adapter *adapter,
 					    struct qlcnic_cmd_args *cmd)
 {
 	struct qlcnic_sriov *sriov = adapter->ahw->sriov;
-	int i, num_vlans;
+	int i, num_vlans, ret;
 	u16 *vlans;
 
 	if (sriov->allowed_vlans)
@@ -443,7 +443,9 @@ static int qlcnic_sriov_set_guest_vlan_mode(struct qlcnic_adapter *adapter,
 	dev_info(&adapter->pdev->dev, "Number of allowed Guest VLANs = %d\n",
 		 sriov->num_allowed_vlans);
 
-	qlcnic_sriov_alloc_vlans(adapter);
+	ret = qlcnic_sriov_alloc_vlans(adapter);
+	if (ret)
+		return ret;
 
 	if (!sriov->any_vlan)
 		return 0;
@@ -2154,7 +2156,7 @@ static int qlcnic_sriov_vf_resume(struct qlcnic_adapter *adapter)
 	return err;
 }
 
-void qlcnic_sriov_alloc_vlans(struct qlcnic_adapter *adapter)
+int qlcnic_sriov_alloc_vlans(struct qlcnic_adapter *adapter)
 {
 	struct qlcnic_sriov *sriov = adapter->ahw->sriov;
 	struct qlcnic_vf_info *vf;
@@ -2164,7 +2166,11 @@ void qlcnic_sriov_alloc_vlans(struct qlcnic_adapter *adapter)
 		vf = &sriov->vf_info[i];
 		vf->sriov_vlans = kcalloc(sriov->num_allowed_vlans,
 					  sizeof(*vf->sriov_vlans), GFP_KERNEL);
+		if (!vf->sriov_vlans)
+			return -ENOMEM;
 	}
+
+	return 0;
 }
 
 void qlcnic_sriov_free_vlans(struct qlcnic_adapter *adapter)
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
index 447720b93e5a..e90fa97c0ae6 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
@@ -597,7 +597,9 @@ static int __qlcnic_pci_sriov_enable(struct qlcnic_adapter *adapter,
 	if (err)
 		goto del_flr_queue;
 
-	qlcnic_sriov_alloc_vlans(adapter);
+	err = qlcnic_sriov_alloc_vlans(adapter);
+	if (err)
+		goto del_flr_queue;
 
 	return err;
 
-- 
cgit v1.2.3


From 1f06f7d97f741667bab0f459a4f940b21cab1549 Mon Sep 17 00:00:00 2001
From: Jeroen de Borst
Date: Mon, 20 Dec 2021 11:27:46 -0800
Subject: gve: Correct order of processing device options

The legacy raw addressing device option was processed before the
new RDA queue format option.  This caused the supported features mask,
which is provided only on the RDA queue format option, not to be set.

This disabled jumbo-frame support when using raw adressing.

Fixes: 255489f5b33c ("gve: Add a jumbo-frame device option")
Signed-off-by: Jeroen de Borst <jeroendb@google.com>
Link: https://lore.kernel.org/r/20211220192746.2900594-1-jeroendb@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/google/gve/gve_adminq.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c
index 83ae56c310d3..326b56b49216 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.c
+++ b/drivers/net/ethernet/google/gve/gve_adminq.c
@@ -738,10 +738,7 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 	 * is not set to GqiRda, choose the queue format in a priority order:
 	 * DqoRda, GqiRda, GqiQpl. Use GqiQpl as default.
 	 */
-	if (priv->queue_format == GVE_GQI_RDA_FORMAT) {
-		dev_info(&priv->pdev->dev,
-			 "Driver is running with GQI RDA queue format.\n");
-	} else if (dev_op_dqo_rda) {
+	if (dev_op_dqo_rda) {
 		priv->queue_format = GVE_DQO_RDA_FORMAT;
 		dev_info(&priv->pdev->dev,
 			 "Driver is running with DQO RDA queue format.\n");
@@ -753,6 +750,9 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 			 "Driver is running with GQI RDA queue format.\n");
 		supported_features_mask =
 			be32_to_cpu(dev_op_gqi_rda->supported_features_mask);
+	} else if (priv->queue_format == GVE_GQI_RDA_FORMAT) {
+		dev_info(&priv->pdev->dev,
+			 "Driver is running with GQI RDA queue format.\n");
 	} else {
 		priv->queue_format = GVE_GQI_QPL_FORMAT;
 		if (dev_op_gqi_qpl)
-- 
cgit v1.2.3


From ac8c58f5b535d6272324e2b8b4a0454781c9147e Mon Sep 17 00:00:00 2001
From: Heiner Kallweit
Date: Mon, 20 Dec 2021 12:18:44 -0800
Subject: igb: fix deadlock caused by taking RTNL in RPM resume path

Recent net core changes caused an issue with few Intel drivers
(reportedly igb), where taking RTNL in RPM resume path results in a
deadlock. See [0] for a bug report. I don't think the core changes
are wrong, but taking RTNL in RPM resume path isn't needed.
The Intel drivers are the only ones doing this. See [1] for a
discussion on the issue. Following patch changes the RPM resume path
to not take RTNL.

[0] https://bugzilla.kernel.org/show_bug.cgi?id=215129
[1] https://lore.kernel.org/netdev/20211125074949.5f897431@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com/t/

Fixes: bd869245a3dc ("net: core: try to runtime-resume detached device in __dev_open")
Fixes: f32a21376573 ("ethtool: runtime-resume netdev parent before ethtool ioctl ops")
Tested-by: Martin Stolpe <martin.stolpe@gmail.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://lore.kernel.org/r/20211220201844.2714498-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index b597b8bfb910..446894dde182 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -9254,7 +9254,7 @@ static int __maybe_unused igb_suspend(struct device *dev)
 	return __igb_shutdown(to_pci_dev(dev), NULL, 0);
 }
 
-static int __maybe_unused igb_resume(struct device *dev)
+static int __maybe_unused __igb_resume(struct device *dev, bool rpm)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -9297,17 +9297,24 @@ static int __maybe_unused igb_resume(struct device *dev)
 
 	wr32(E1000_WUS, ~0);
 
-	rtnl_lock();
+	if (!rpm)
+		rtnl_lock();
 	if (!err && netif_running(netdev))
 		err = __igb_open(netdev, true);
 
 	if (!err)
 		netif_device_attach(netdev);
-	rtnl_unlock();
+	if (!rpm)
+		rtnl_unlock();
 
 	return err;
 }
 
+static int __maybe_unused igb_resume(struct device *dev)
+{
+	return __igb_resume(dev, false);
+}
+
 static int __maybe_unused igb_runtime_idle(struct device *dev)
 {
 	struct net_device *netdev = dev_get_drvdata(dev);
@@ -9326,7 +9333,7 @@ static int __maybe_unused igb_runtime_suspend(struct device *dev)
 
 static int __maybe_unused igb_runtime_resume(struct device *dev)
 {
-	return igb_resume(dev);
+	return __igb_resume(dev, true);
 }
 
 static void igb_shutdown(struct pci_dev *pdev)
@@ -9442,7 +9449,7 @@ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev,
  *  @pdev: Pointer to PCI device
  *
  *  Restart the card from scratch, as if from a cold-boot. Implementation
- *  resembles the first-half of the igb_resume routine.
+ *  resembles the first-half of the __igb_resume routine.
  **/
 static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev)
 {
@@ -9482,7 +9489,7 @@ static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev)
  *
  *  This callback is called when the error recovery driver tells us that
  *  its OK to resume normal operation. Implementation resembles the
- *  second-half of the igb_resume routine.
+ *  second-half of the __igb_resume routine.
  */
 static void igb_io_resume(struct pci_dev *pdev)
 {
-- 
cgit v1.2.3


From cb93b3e11d405f20a405a07482d01147ef4934a3 Mon Sep 17 00:00:00 2001
From: Jiasheng Jiang
Date: Wed, 22 Dec 2021 15:41:12 +0800
Subject: drivers: net: smc911x: Check for error irq

Because platform_get_irq() could fail and return error irq.
Therefore, it might be better to check it if order to avoid the use of
error irq.

Fixes: ae150435b59e ("smsc: Move the SMC (SMSC) drivers")
Signed-off-by: Jiasheng Jiang <jiasheng@iscas.ac.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/smsc/smc911x.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c
index 89381f796985..dd6f69ced4ee 100644
--- a/drivers/net/ethernet/smsc/smc911x.c
+++ b/drivers/net/ethernet/smsc/smc911x.c
@@ -2072,6 +2072,11 @@ static int smc911x_drv_probe(struct platform_device *pdev)
 
 	ndev->dma = (unsigned char)-1;
 	ndev->irq = platform_get_irq(pdev, 0);
+	if (ndev->irq < 0) {
+		ret = ndev->irq;
+		goto release_both;
+	}
+
 	lp = netdev_priv(ndev);
 	lp->netdev = ndev;
 #ifdef SMC_DYNAMIC_BUS_CONFIG
-- 
cgit v1.2.3


From 99d7fbb5cedf598f67e8be106d6c7b8d91366aef Mon Sep 17 00:00:00 2001
From: Jiasheng Jiang
Date: Wed, 22 Dec 2021 15:59:44 +0800
Subject: net: ks8851: Check for error irq

Because platform_get_irq() could fail and return error irq.
Therefore, it might be better to check it if order to avoid the use of
error irq.

Fixes: 797047f875b5 ("net: ks8851: Implement Parallel bus operations")
Signed-off-by: Jiasheng Jiang <jiasheng@iscas.ac.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/ks8851_par.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/ks8851_par.c b/drivers/net/ethernet/micrel/ks8851_par.c
index 2e25798c610e..7f49042484bd 100644
--- a/drivers/net/ethernet/micrel/ks8851_par.c
+++ b/drivers/net/ethernet/micrel/ks8851_par.c
@@ -321,6 +321,8 @@ static int ks8851_probe_par(struct platform_device *pdev)
 		return ret;
 
 	netdev->irq = platform_get_irq(pdev, 0);
+	if (netdev->irq < 0)
+		return netdev->irq;
 
 	return ks8851_probe_common(netdev, dev, msg_enable);
 }
-- 
cgit v1.2.3


From bdf1b5c3884f6a0dc91b0dbdb8c3b7d205f449e0 Mon Sep 17 00:00:00 2001
From: Jiasheng Jiang
Date: Mon, 20 Dec 2021 21:56:03 +0800
Subject: sfc: Check null pointer of rx_queue->page_ring

Because of the possible failure of the kcalloc, it should be better to
set rx_queue->page_ptr_mask to 0 when it happens in order to maintain
the consistency.

Fixes: 5a6681e22c14 ("sfc: separate out SFC4000 ("Falcon") support into new sfc-falcon driver")
Signed-off-by: Jiasheng Jiang <jiasheng@iscas.ac.cn>
Acked-by: Martin Habets <habetsm.xilinx@gmail.com>
Link: https://lore.kernel.org/r/20211220135603.954944-1-jiasheng@iscas.ac.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/sfc/rx_common.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c
index 68fc7d317693..0983abc0cc5f 100644
--- a/drivers/net/ethernet/sfc/rx_common.c
+++ b/drivers/net/ethernet/sfc/rx_common.c
@@ -150,7 +150,10 @@ static void efx_init_rx_recycle_ring(struct efx_rx_queue *rx_queue)
 					    efx->rx_bufs_per_page);
 	rx_queue->page_ring = kcalloc(page_ring_size,
 				      sizeof(*rx_queue->page_ring), GFP_KERNEL);
-	rx_queue->page_ptr_mask = page_ring_size - 1;
+	if (!rx_queue->page_ring)
+		rx_queue->page_ptr_mask = 0;
+	else
+		rx_queue->page_ptr_mask = page_ring_size - 1;
 }
 
 static void efx_fini_rx_recycle_ring(struct efx_rx_queue *rx_queue)
-- 
cgit v1.2.3


From 9b8bdd1eb5890aeeab7391dddcf8bd51f7b07216 Mon Sep 17 00:00:00 2001
From: Jiasheng Jiang
Date: Mon, 20 Dec 2021 22:03:44 +0800
Subject: sfc: falcon: Check null pointer of rx_queue->page_ring

Because of the possible failure of the kcalloc, it should be better to
set rx_queue->page_ptr_mask to 0 when it happens in order to maintain
the consistency.

Fixes: 5a6681e22c14 ("sfc: separate out SFC4000 ("Falcon") support into new sfc-falcon driver")
Signed-off-by: Jiasheng Jiang <jiasheng@iscas.ac.cn>
Acked-by: Martin Habets <habetsm.xilinx@gmail.com>
Link: https://lore.kernel.org/r/20211220140344.978408-1-jiasheng@iscas.ac.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/sfc/falcon/rx.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sfc/falcon/rx.c b/drivers/net/ethernet/sfc/falcon/rx.c
index 966f13e7475d..11a6aee852e9 100644
--- a/drivers/net/ethernet/sfc/falcon/rx.c
+++ b/drivers/net/ethernet/sfc/falcon/rx.c
@@ -728,7 +728,10 @@ static void ef4_init_rx_recycle_ring(struct ef4_nic *efx,
 					    efx->rx_bufs_per_page);
 	rx_queue->page_ring = kcalloc(page_ring_size,
 				      sizeof(*rx_queue->page_ring), GFP_KERNEL);
-	rx_queue->page_ptr_mask = page_ring_size - 1;
+	if (!rx_queue->page_ring)
+		rx_queue->page_ptr_mask = 0;
+	else
+		rx_queue->page_ptr_mask = page_ring_size - 1;
 }
 
 void ef4_init_rx_queue(struct ef4_rx_queue *rx_queue)
-- 
cgit v1.2.3


From 6b8b42585886c59a008015083282aae434349094 Mon Sep 17 00:00:00 2001
From: Miaoqian Lin
Date: Wed, 22 Dec 2021 06:54:53 +0000
Subject: net/mlx5: DR, Fix NULL vs IS_ERR checking in dr_domain_init_resources

The mlx5_get_uars_page() function  returns error pointers.
Using IS_ERR() to check the return value to fix this.

Fixes: 4ec9e7b02697 ("net/mlx5: DR, Expose steering domain functionality")
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
index 8cbd36c82b3b..f6e6d9209766 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2019 Mellanox Technologies. */
 
 #include <linux/mlx5/eswitch.h>
+#include <linux/err.h>
 #include "dr_types.h"
 
 #define DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, dmn_type)	\
@@ -72,9 +73,9 @@ static int dr_domain_init_resources(struct mlx5dr_domain *dmn)
 	}
 
 	dmn->uar = mlx5_get_uars_page(dmn->mdev);
-	if (!dmn->uar) {
+	if (IS_ERR(dmn->uar)) {
 		mlx5dr_err(dmn, "Couldn't allocate UAR\n");
-		ret = -ENOMEM;
+		ret = PTR_ERR(dmn->uar);
 		goto clean_pd;
 	}
 
-- 
cgit v1.2.3


From 624bf42c2e3930acca9fcfc340b2fa38e712da84 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik
Date: Sun, 12 Dec 2021 16:19:58 +0200
Subject: net/mlx5: DR, Fix querying eswitch manager vport for ECPF

On BlueField the E-Switch manager is the ECPF (vport 0xFFFE), but when
querying capabilities of ECPF eswitch manager, need to query vport 0
with other_vport = 0.

Fixes: 9091b821aaa4 ("net/mlx5: DR, Handle eswitch manager and uplink vports separately")
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
index f6e6d9209766..c54cc45f63dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
@@ -164,9 +164,7 @@ static int dr_domain_query_vport(struct mlx5dr_domain *dmn,
 
 static int dr_domain_query_esw_mngr(struct mlx5dr_domain *dmn)
 {
-	return dr_domain_query_vport(dmn,
-				     dmn->info.caps.is_ecpf ? MLX5_VPORT_ECPF : 0,
-				     false,
+	return dr_domain_query_vport(dmn, 0, false,
 				     &dmn->info.caps.vports.esw_manager_caps);
 }
 
-- 
cgit v1.2.3


From 26a7993c93a74a3fee83a37b46e00e69e49e57c2 Mon Sep 17 00:00:00 2001
From: Shay Drory
Date: Tue, 26 Oct 2021 08:25:19 +0300
Subject: net/mlx5: Use first online CPU instead of hard coded CPU

Hard coded CPU (0 in our case) might be offline. Hence, use the first
online CPU instead.

Fixes: f891b7cdbdcd ("net/mlx5: Enable single IRQ for PCI Function")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 830444f927d4..0e84c005d160 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -398,7 +398,7 @@ irq_pool_request_vector(struct mlx5_irq_pool *pool, int vecidx,
 	cpumask_copy(irq->mask, affinity);
 	if (!irq_pool_is_sf_pool(pool) && !pool->xa_num_irqs.max &&
 	    cpumask_empty(irq->mask))
-		cpumask_set_cpu(0, irq->mask);
+		cpumask_set_cpu(cpumask_first(cpu_online_mask), irq->mask);
 	irq_set_affinity_hint(irq->irqn, irq->mask);
 unlock:
 	mutex_unlock(&pool->lock);
-- 
cgit v1.2.3


From aa968f922039706f6d13e8870b49e424d0a8d9ad Mon Sep 17 00:00:00 2001
From: Shay Drory
Date: Wed, 24 Nov 2021 23:10:57 +0200
Subject: net/mlx5: Fix error print in case of IRQ request failed

In case IRQ layer failed to find or to request irq, the driver is
printing the first cpu of the provided affinity as part of the error
print. Empty affinity is a valid input for the IRQ layer, and it is
an error to call cpumask_first() on empty affinity.

Remove the first cpu print from the error message.

Fixes: c36326d38d93 ("net/mlx5: Round-Robin EQs over IRQs")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 0e84c005d160..bcee30f5de0a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -356,8 +356,8 @@ static struct mlx5_irq *irq_pool_request_affinity(struct mlx5_irq_pool *pool,
 	new_irq = irq_pool_create_irq(pool, affinity);
 	if (IS_ERR(new_irq)) {
 		if (!least_loaded_irq) {
-			mlx5_core_err(pool->dev, "Didn't find IRQ for cpu = %u\n",
-				      cpumask_first(affinity));
+			mlx5_core_err(pool->dev, "Didn't find a matching IRQ. err = %ld\n",
+				      PTR_ERR(new_irq));
 			mutex_unlock(&pool->lock);
 			return new_irq;
 		}
-- 
cgit v1.2.3


From 33de865f7bce3968676e43b0182af0a2dd359dae Mon Sep 17 00:00:00 2001
From: Moshe Shemesh
Date: Tue, 23 Nov 2021 20:08:13 +0200
Subject: net/mlx5: Fix SF health recovery flow

SF do not directly control the PCI device. During recovery flow SF
should not be allowed to do pci disable or pci reset, its PF will do it.

It fixes the following kernel trace:
mlx5_core.sf mlx5_core.sf.25: mlx5_health_try_recover:387:(pid 40948): starting health recovery flow
mlx5_core 0000:03:00.0: mlx5_pci_slot_reset was called
mlx5_core 0000:03:00.0: wait vital counter value 0xab175 after 1 iterations
mlx5_core.sf mlx5_core.sf.25: firmware version: 24.32.532
mlx5_core.sf mlx5_core.sf.23: mlx5_health_try_recover:387:(pid 40946): starting health recovery flow
mlx5_core 0000:03:00.0: mlx5_pci_slot_reset was called
mlx5_core 0000:03:00.0: wait vital counter value 0xab193 after 1 iterations
mlx5_core.sf mlx5_core.sf.23: firmware version: 24.32.532
mlx5_core.sf mlx5_core.sf.25: mlx5_cmd_check:813:(pid 40948): ENABLE_HCA(0x104) op_mod(0x0) failed,
status bad resource state(0x9), syndrome (0x658908)
mlx5_core.sf mlx5_core.sf.25: mlx5_function_setup:1292:(pid 40948): enable hca failed
mlx5_core.sf mlx5_core.sf.25: mlx5_health_try_recover:389:(pid 40948): health recovery failed

Fixes: 1958fc2f0712 ("net/mlx5: SF, Add auxiliary device driver")
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 7df9c7f8d9c8..65083496f913 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1809,12 +1809,13 @@ void mlx5_disable_device(struct mlx5_core_dev *dev)
 
 int mlx5_recover_device(struct mlx5_core_dev *dev)
 {
-	int ret = -EIO;
+	if (!mlx5_core_is_sf(dev)) {
+		mlx5_pci_disable_device(dev);
+		if (mlx5_pci_slot_reset(dev->pdev) != PCI_ERS_RESULT_RECOVERED)
+			return -EIO;
+	}
 
-	mlx5_pci_disable_device(dev);
-	if (mlx5_pci_slot_reset(dev->pdev) == PCI_ERS_RESULT_RECOVERED)
-		ret = mlx5_load_one(dev);
-	return ret;
+	return mlx5_load_one(dev);
 }
 
 static struct pci_driver mlx5_core_driver = {
-- 
cgit v1.2.3


From d671e109bd8548d067b27e39e183a484430bf102 Mon Sep 17 00:00:00 2001
From: Chris Mi
Date: Tue, 14 Dec 2021 03:52:53 +0200
Subject: net/mlx5: Fix tc max supported prio for nic mode

Only prio 1 is supported if firmware doesn't support ignore flow
level for nic mode. The offending commit removed the check wrongly.
Add it back.

Fixes: 9a99c8f1253a ("net/mlx5e: E-Switch, Offload all chain 0 priorities when modify header and forward action is not supported")
Signed-off-by: Chris Mi <cmi@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
index 97e5845b4cfd..d5e47630e284 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
@@ -121,6 +121,9 @@ u32 mlx5_chains_get_nf_ft_chain(struct mlx5_fs_chains *chains)
 
 u32 mlx5_chains_get_prio_range(struct mlx5_fs_chains *chains)
 {
+	if (!mlx5_chains_prios_supported(chains))
+		return 1;
+
 	if (mlx5_chains_ignore_flow_level_supported(chains))
 		return UINT_MAX;
 
-- 
cgit v1.2.3


From 918fc3855a6507a200e9cf22c20be852c0982687 Mon Sep 17 00:00:00 2001
From: Amir Tzin
Date: Tue, 30 Nov 2021 16:05:44 +0200
Subject: net/mlx5e: Wrap the tx reporter dump callback to extract the sq

Function mlx5e_tx_reporter_dump_sq() casts its void * argument to struct
mlx5e_txqsq *, but in TX-timeout-recovery flow the argument is actually
of type struct mlx5e_tx_timeout_ctx *.

 mlx5_core 0000:08:00.1 enp8s0f1: TX timeout detected
 mlx5_core 0000:08:00.1 enp8s0f1: TX timeout on queue: 1, SQ: 0x11ec, CQ: 0x146d, SQ Cons: 0x0 SQ Prod: 0x1, usecs since last trans: 21565000
 BUG: stack guard page was hit at 0000000093f1a2de (stack is 00000000b66ea0dc..000000004d932dae)
 kernel stack overflow (page fault): 0000 [#1] SMP NOPTI
 CPU: 5 PID: 95 Comm: kworker/u20:1 Tainted: G W OE 5.13.0_mlnx #1
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
 Workqueue: mlx5e mlx5e_tx_timeout_work [mlx5_core]
 RIP: 0010:mlx5e_tx_reporter_dump_sq+0xd3/0x180
 [mlx5_core]
 Call Trace:
 mlx5e_tx_reporter_dump+0x43/0x1c0 [mlx5_core]
 devlink_health_do_dump.part.91+0x71/0xd0
 devlink_health_report+0x157/0x1b0
 mlx5e_reporter_tx_timeout+0xb9/0xf0 [mlx5_core]
 ? mlx5e_tx_reporter_err_cqe_recover+0x1d0/0x1d0
 [mlx5_core]
 ? mlx5e_health_queue_dump+0xd0/0xd0 [mlx5_core]
 ? update_load_avg+0x19b/0x550
 ? set_next_entity+0x72/0x80
 ? pick_next_task_fair+0x227/0x340
 ? finish_task_switch+0xa2/0x280
   mlx5e_tx_timeout_work+0x83/0xb0 [mlx5_core]
   process_one_work+0x1de/0x3a0
   worker_thread+0x2d/0x3c0
 ? process_one_work+0x3a0/0x3a0
   kthread+0x115/0x130
 ? kthread_park+0x90/0x90
   ret_from_fork+0x1f/0x30
 --[ end trace 51ccabea504edaff ]---
 RIP: 0010:mlx5e_tx_reporter_dump_sq+0xd3/0x180
 PKRU: 55555554
 Kernel panic - not syncing: Fatal exception
 Kernel Offset: disabled
 end Kernel panic - not syncing: Fatal exception

To fix this bug add a wrapper for mlx5e_tx_reporter_dump_sq() which
extracts the sq from struct mlx5e_tx_timeout_ctx and set it as the
TX-timeout-recovery flow dump callback.

Fixes: 5f29458b77d5 ("net/mlx5e: Support dump callback in TX reporter")
Signed-off-by: Aya Levin <ayal@nvidia.com>
Signed-off-by: Amir Tzin <amirtz@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 4f4bc8726ec4..614cd9477600 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -466,6 +466,14 @@ static int mlx5e_tx_reporter_dump_sq(struct mlx5e_priv *priv, struct devlink_fms
 	return mlx5e_health_fmsg_named_obj_nest_end(fmsg);
 }
 
+static int mlx5e_tx_reporter_timeout_dump(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg,
+					  void *ctx)
+{
+	struct mlx5e_tx_timeout_ctx *to_ctx = ctx;
+
+	return mlx5e_tx_reporter_dump_sq(priv, fmsg, to_ctx->sq);
+}
+
 static int mlx5e_tx_reporter_dump_all_sqs(struct mlx5e_priv *priv,
 					  struct devlink_fmsg *fmsg)
 {
@@ -561,7 +569,7 @@ int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq)
 	to_ctx.sq = sq;
 	err_ctx.ctx = &to_ctx;
 	err_ctx.recover = mlx5e_tx_reporter_timeout_recover;
-	err_ctx.dump = mlx5e_tx_reporter_dump_sq;
+	err_ctx.dump = mlx5e_tx_reporter_timeout_dump;
 	snprintf(err_str, sizeof(err_str),
 		 "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u",
 		 sq->ch_ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc,
-- 
cgit v1.2.3


From a0cb909644c36230a3c48904d14b91732de79fc0 Mon Sep 17 00:00:00 2001
From: Gal Pressman
Date: Mon, 13 Dec 2021 11:05:11 +0200
Subject: net/mlx5e: Fix skb memory leak when TC classifier action offloads are
 disabled

When TC classifier action offloads are disabled (CONFIG_MLX5_CLS_ACT in
Kconfig), the mlx5e_rep_tc_receive() function which is responsible for
passing the skb to the stack (or freeing it) is defined as a nop, and
results in leaking the skb memory. Replace the nop with a call to
napi_gro_receive() to resolve the leak.

Fixes: 28e7606fa8f1 ("net/mlx5e: Refactor rx handler of represetor device")
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Ariel Levkovich <lariel@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h
index d6c7c81690eb..7c9dd3a75f8a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h
@@ -66,7 +66,7 @@ mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
 
 static inline void
 mlx5e_rep_tc_receive(struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq,
-		     struct sk_buff *skb) {}
+		     struct sk_buff *skb) { napi_gro_receive(rq->cq.napi, skb); }
 
 #endif /* CONFIG_MLX5_CLS_ACT */
 
-- 
cgit v1.2.3


From 17958d7cd731b977ae7d4af38d891c3a1235b5f1 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy
Date: Tue, 12 Oct 2021 19:40:09 +0300
Subject: net/mlx5e: Fix interoperability between XSK and ICOSQ recovery flow

Both regular RQ and XSKRQ use the same ICOSQ for UMRs. When doing
recovery for the ICOSQ, don't forget to deactivate XSKRQ.

XSK can be opened and closed while channels are active, so a new mutex
prevents the ICOSQ recovery from running at the same time. The ICOSQ
recovery deactivates and reactivates XSKRQ, so any parallel change in
XSK state would break consistency. As the regular RQ is running, it's
not enough to just flush the recovery work, because it can be
rescheduled.

Fixes: be5323c8379f ("net/mlx5e: Report and recover from CQE error on ICOSQ")
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  2 ++
 .../net/ethernet/mellanox/mlx5/core/en/health.h    |  2 ++
 .../ethernet/mellanox/mlx5/core/en/reporter_rx.c   | 35 +++++++++++++++++++++-
 .../net/ethernet/mellanox/mlx5/core/en/xsk/setup.c | 16 +++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  7 +++--
 5 files changed, 58 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index f0ac6b0d9653..f42067adc79d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -783,6 +783,8 @@ struct mlx5e_channel {
 	DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES);
 	int                        ix;
 	int                        cpu;
+	/* Sync between icosq recovery and XSK enable/disable. */
+	struct mutex               icosq_recovery_lock;
 };
 
 struct mlx5e_ptp;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
index d5b7110a4265..0107e4e73bb0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
@@ -30,6 +30,8 @@ void mlx5e_reporter_rx_destroy(struct mlx5e_priv *priv);
 void mlx5e_reporter_icosq_cqe_err(struct mlx5e_icosq *icosq);
 void mlx5e_reporter_rq_cqe_err(struct mlx5e_rq *rq);
 void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq);
+void mlx5e_reporter_icosq_suspend_recovery(struct mlx5e_channel *c);
+void mlx5e_reporter_icosq_resume_recovery(struct mlx5e_channel *c);
 
 #define MLX5E_REPORTER_PER_Q_MAX_LEN 256
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
index 74086eb556ae..2684e9da9f41 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -62,6 +62,7 @@ static void mlx5e_reset_icosq_cc_pc(struct mlx5e_icosq *icosq)
 
 static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx)
 {
+	struct mlx5e_rq *xskrq = NULL;
 	struct mlx5_core_dev *mdev;
 	struct mlx5e_icosq *icosq;
 	struct net_device *dev;
@@ -70,7 +71,13 @@ static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx)
 	int err;
 
 	icosq = ctx;
+
+	mutex_lock(&icosq->channel->icosq_recovery_lock);
+
+	/* mlx5e_close_rq cancels this work before RQ and ICOSQ are killed. */
 	rq = &icosq->channel->rq;
+	if (test_bit(MLX5E_RQ_STATE_ENABLED, &icosq->channel->xskrq.state))
+		xskrq = &icosq->channel->xskrq;
 	mdev = icosq->channel->mdev;
 	dev = icosq->channel->netdev;
 	err = mlx5_core_query_sq_state(mdev, icosq->sqn, &state);
@@ -84,6 +91,9 @@ static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx)
 		goto out;
 
 	mlx5e_deactivate_rq(rq);
+	if (xskrq)
+		mlx5e_deactivate_rq(xskrq);
+
 	err = mlx5e_wait_for_icosq_flush(icosq);
 	if (err)
 		goto out;
@@ -97,15 +107,28 @@ static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx)
 		goto out;
 
 	mlx5e_reset_icosq_cc_pc(icosq);
+
 	mlx5e_free_rx_in_progress_descs(rq);
+	if (xskrq)
+		mlx5e_free_rx_in_progress_descs(xskrq);
+
 	clear_bit(MLX5E_SQ_STATE_RECOVERING, &icosq->state);
 	mlx5e_activate_icosq(icosq);
-	mlx5e_activate_rq(rq);
 
+	mlx5e_activate_rq(rq);
 	rq->stats->recover++;
+
+	if (xskrq) {
+		mlx5e_activate_rq(xskrq);
+		xskrq->stats->recover++;
+	}
+
+	mutex_unlock(&icosq->channel->icosq_recovery_lock);
+
 	return 0;
 out:
 	clear_bit(MLX5E_SQ_STATE_RECOVERING, &icosq->state);
+	mutex_unlock(&icosq->channel->icosq_recovery_lock);
 	return err;
 }
 
@@ -706,6 +729,16 @@ void mlx5e_reporter_icosq_cqe_err(struct mlx5e_icosq *icosq)
 	mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx);
 }
 
+void mlx5e_reporter_icosq_suspend_recovery(struct mlx5e_channel *c)
+{
+	mutex_lock(&c->icosq_recovery_lock);
+}
+
+void mlx5e_reporter_icosq_resume_recovery(struct mlx5e_channel *c)
+{
+	mutex_unlock(&c->icosq_recovery_lock);
+}
+
 static const struct devlink_health_reporter_ops mlx5_rx_reporter_ops = {
 	.name = "rx",
 	.recover = mlx5e_rx_reporter_recover,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index 538bc2419bd8..8526a5fbbf0b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -4,6 +4,7 @@
 #include "setup.h"
 #include "en/params.h"
 #include "en/txrx.h"
+#include "en/health.h"
 
 /* It matches XDP_UMEM_MIN_CHUNK_SIZE, but as this constant is private and may
  * change unexpectedly, and mlx5e has a minimum valid stride size for striding
@@ -170,7 +171,13 @@ void mlx5e_close_xsk(struct mlx5e_channel *c)
 
 void mlx5e_activate_xsk(struct mlx5e_channel *c)
 {
+	/* ICOSQ recovery deactivates RQs. Suspend the recovery to avoid
+	 * activating XSKRQ in the middle of recovery.
+	 */
+	mlx5e_reporter_icosq_suspend_recovery(c);
 	set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
+	mlx5e_reporter_icosq_resume_recovery(c);
+
 	/* TX queue is created active. */
 
 	spin_lock_bh(&c->async_icosq_lock);
@@ -180,6 +187,13 @@ void mlx5e_activate_xsk(struct mlx5e_channel *c)
 
 void mlx5e_deactivate_xsk(struct mlx5e_channel *c)
 {
-	mlx5e_deactivate_rq(&c->xskrq);
+	/* ICOSQ recovery may reactivate XSKRQ if clear_bit is called in the
+	 * middle of recovery. Suspend the recovery to avoid it.
+	 */
+	mlx5e_reporter_icosq_suspend_recovery(c);
+	clear_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
+	mlx5e_reporter_icosq_resume_recovery(c);
+	synchronize_net(); /* Sync with NAPI to prevent mlx5e_post_rx_wqes. */
+
 	/* TX queue is disabled on close. */
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 65571593ec5c..a572fc9690ed 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1087,8 +1087,6 @@ void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
 void mlx5e_close_rq(struct mlx5e_rq *rq)
 {
 	cancel_work_sync(&rq->dim.work);
-	if (rq->icosq)
-		cancel_work_sync(&rq->icosq->recover_work);
 	cancel_work_sync(&rq->recover_work);
 	mlx5e_destroy_rq(rq);
 	mlx5e_free_rx_descs(rq);
@@ -2088,6 +2086,8 @@ static int mlx5e_open_queues(struct mlx5e_channel *c,
 	if (err)
 		goto err_close_xdpsq_cq;
 
+	mutex_init(&c->icosq_recovery_lock);
+
 	err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->icosq);
 	if (err)
 		goto err_close_async_icosq;
@@ -2156,9 +2156,12 @@ static void mlx5e_close_queues(struct mlx5e_channel *c)
 	mlx5e_close_xdpsq(&c->xdpsq);
 	if (c->xdp)
 		mlx5e_close_xdpsq(&c->rq_xdpsq);
+	/* The same ICOSQ is used for UMRs for both RQ and XSKRQ. */
+	cancel_work_sync(&c->icosq.recover_work);
 	mlx5e_close_rq(&c->rq);
 	mlx5e_close_sqs(c);
 	mlx5e_close_icosq(&c->icosq);
+	mutex_destroy(&c->icosq_recovery_lock);
 	mlx5e_close_icosq(&c->async_icosq);
 	if (c->xdp)
 		mlx5e_close_cq(&c->rq_xdpsq.cq);
-- 
cgit v1.2.3


From 19c4aba2d4e23997061fb11aed8a3e41334bfa14 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy
Date: Wed, 22 Jul 2020 16:32:44 +0300
Subject: net/mlx5e: Fix ICOSQ recovery flow for XSK

There are two ICOSQs per channel: one is needed for RX, and the other
for async operations (XSK TX, kTLS offload). Currently, the recovery
flow for both is the same, and async ICOSQ is mistakenly treated like
the regular ICOSQ.

This patch prevents running the regular ICOSQ recovery on async ICOSQ.
The purpose of async ICOSQ is to handle XSK wakeup requests and post
kTLS offload RX parameters, it has nothing to do with RQ and XSKRQ UMRs,
so the regular recovery sequence is not applicable here.

Fixes: be5323c8379f ("net/mlx5e: Report and recover from CQE error on ICOSQ")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Aya Levin <ayal@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  3 ---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 30 +++++++++++++++++------
 2 files changed, 22 insertions(+), 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index f42067adc79d..b47a0d3ef22f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1016,9 +1016,6 @@ int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param);
 void mlx5e_destroy_rq(struct mlx5e_rq *rq);
 
 struct mlx5e_sq_param;
-int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
-		     struct mlx5e_sq_param *param, struct mlx5e_icosq *sq);
-void mlx5e_close_icosq(struct mlx5e_icosq *sq);
 int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
 		     struct mlx5e_sq_param *param, struct xsk_buff_pool *xsk_pool,
 		     struct mlx5e_xdpsq *sq, bool is_redirect);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a572fc9690ed..3b0f3a831216 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1214,9 +1214,20 @@ static void mlx5e_icosq_err_cqe_work(struct work_struct *recover_work)
 	mlx5e_reporter_icosq_cqe_err(sq);
 }
 
+static void mlx5e_async_icosq_err_cqe_work(struct work_struct *recover_work)
+{
+	struct mlx5e_icosq *sq = container_of(recover_work, struct mlx5e_icosq,
+					      recover_work);
+
+	/* Not implemented yet. */
+
+	netdev_warn(sq->channel->netdev, "async_icosq recovery is not implemented\n");
+}
+
 static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
 			     struct mlx5e_sq_param *param,
-			     struct mlx5e_icosq *sq)
+			     struct mlx5e_icosq *sq,
+			     work_func_t recover_work_func)
 {
 	void *sqc_wq               = MLX5_ADDR_OF(sqc, param->sqc, wq);
 	struct mlx5_core_dev *mdev = c->mdev;
@@ -1237,7 +1248,7 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
 	if (err)
 		goto err_sq_wq_destroy;
 
-	INIT_WORK(&sq->recover_work, mlx5e_icosq_err_cqe_work);
+	INIT_WORK(&sq->recover_work, recover_work_func);
 
 	return 0;
 
@@ -1573,13 +1584,14 @@ void mlx5e_tx_err_cqe_work(struct work_struct *recover_work)
 	mlx5e_reporter_tx_err_cqe(sq);
 }
 
-int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
-		     struct mlx5e_sq_param *param, struct mlx5e_icosq *sq)
+static int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
+			    struct mlx5e_sq_param *param, struct mlx5e_icosq *sq,
+			    work_func_t recover_work_func)
 {
 	struct mlx5e_create_sq_param csp = {};
 	int err;
 
-	err = mlx5e_alloc_icosq(c, param, sq);
+	err = mlx5e_alloc_icosq(c, param, sq, recover_work_func);
 	if (err)
 		return err;
 
@@ -1618,7 +1630,7 @@ void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq)
 	synchronize_net(); /* Sync with NAPI. */
 }
 
-void mlx5e_close_icosq(struct mlx5e_icosq *sq)
+static void mlx5e_close_icosq(struct mlx5e_icosq *sq)
 {
 	struct mlx5e_channel *c = sq->channel;
 
@@ -2082,13 +2094,15 @@ static int mlx5e_open_queues(struct mlx5e_channel *c,
 
 	spin_lock_init(&c->async_icosq_lock);
 
-	err = mlx5e_open_icosq(c, params, &cparam->async_icosq, &c->async_icosq);
+	err = mlx5e_open_icosq(c, params, &cparam->async_icosq, &c->async_icosq,
+			       mlx5e_async_icosq_err_cqe_work);
 	if (err)
 		goto err_close_xdpsq_cq;
 
 	mutex_init(&c->icosq_recovery_lock);
 
-	err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->icosq);
+	err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->icosq,
+			       mlx5e_icosq_err_cqe_work);
 	if (err)
 		goto err_close_async_icosq;
 
-- 
cgit v1.2.3


From 2820110d945923ab2f4901753e4ccbb2a506fa8e Mon Sep 17 00:00:00 2001
From: Chris Mi
Date: Thu, 2 Dec 2021 11:18:02 +0800
Subject: net/mlx5e: Delete forward rule for ct or sample action

When there is ct or sample action, the ct or sample rule will be deleted
and return. But if there is an extra mirror action, the forward rule can't
be deleted because of the return.

Fix it by removing the return.

Fixes: 69e2916ebce4 ("net/mlx5: CT: Add support for mirroring")
Fixes: f94d6389f6a8 ("net/mlx5e: TC, Add support to offload sample action")
Signed-off-by: Chris Mi <cmi@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 3d45f4ae80c0..f633448c3cc7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1196,21 +1196,16 @@ void mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw,
 	if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH)
 		goto offload_rule_0;
 
-	if (flow_flag_test(flow, CT)) {
-		mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr);
-		return;
-	}
-
-	if (flow_flag_test(flow, SAMPLE)) {
-		mlx5e_tc_sample_unoffload(get_sample_priv(flow->priv), flow->rule[0], attr);
-		return;
-	}
-
 	if (attr->esw_attr->split_count)
 		mlx5_eswitch_del_fwd_rule(esw, flow->rule[1], attr);
 
+	if (flow_flag_test(flow, CT))
+		mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr);
+	else if (flow_flag_test(flow, SAMPLE))
+		mlx5e_tc_sample_unoffload(get_sample_priv(flow->priv), flow->rule[0], attr);
+	else
 offload_rule_0:
-	mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr);
+		mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr);
 }
 
 struct mlx5_flow_handle *
-- 
cgit v1.2.3


From 4390c6edc0fb390e699d0f886f45575dfeafeb4b Mon Sep 17 00:00:00 2001
From: Christophe JAILLET
Date: Sat, 6 Nov 2021 18:08:11 +0100
Subject: net/mlx5: Fix some error handling paths in 'mlx5e_tc_add_fdb_flow()'

All the error handling paths of 'mlx5e_tc_add_fdb_flow()' end to 'err_out'
where 'flow_flag_set(flow, FAILED);' is called.

All but the new error handling paths added by the commits given in the
Fixes tag below.

Fix these error handling paths and branch to 'err_out'.

Fixes: 166f431ec6be ("net/mlx5e: Add indirect tc offload of ovs internal port")
Fixes: b16eb3c81fe2 ("net/mlx5: Support internal port as decap route device")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
(cherry picked from commit 31108d142f3632970f6f3e0224bd1c6781c9f87d)
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index f633448c3cc7..a60c7680fd2b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1440,7 +1440,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 							MLX5_FLOW_NAMESPACE_FDB, VPORT_TO_REG,
 							metadata);
 			if (err)
-				return err;
+				goto err_out;
 		}
 	}
 
@@ -1456,13 +1456,15 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		if (attr->chain) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Internal port rule is only supported on chain 0");
-			return -EOPNOTSUPP;
+			err = -EOPNOTSUPP;
+			goto err_out;
 		}
 
 		if (attr->dest_chain) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Internal port rule offload doesn't support goto action");
-			return -EOPNOTSUPP;
+			err = -EOPNOTSUPP;
+			goto err_out;
 		}
 
 		int_port = mlx5e_tc_int_port_get(mlx5e_get_int_port_priv(priv),
@@ -1470,8 +1472,10 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 						 flow_flag_test(flow, EGRESS) ?
 						 MLX5E_TC_INT_PORT_EGRESS :
 						 MLX5E_TC_INT_PORT_INGRESS);
-		if (IS_ERR(int_port))
-			return PTR_ERR(int_port);
+		if (IS_ERR(int_port)) {
+			err = PTR_ERR(int_port);
+			goto err_out;
+		}
 
 		esw_attr->int_port = int_port;
 	}
-- 
cgit v1.2.3


From eccffcf4657ab9a148faaa0eb354d2a091caf552 Mon Sep 17 00:00:00 2001
From: Xiaoliang Yang
Date: Thu, 23 Dec 2021 15:39:28 +0800
Subject: net: stmmac: ptp: fix potentially overflowing expression

Convert the u32 variable to type u64 in a context where expression of
type u64 is required to avoid potential overflow.

Fixes: e9e3720002f6 ("net: stmmac: ptp: update tas basetime after ptp adjust")
Signed-off-by: Xiaoliang Yang <xiaoliang.yang_1@nxp.com>
Link: https://lore.kernel.org/r/20211223073928.37371-1-xiaoliang.yang_1@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index 580cc035536b..be9b58b2abf9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -102,7 +102,7 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta)
 		time.tv_nsec = priv->plat->est->btr_reserve[0];
 		time.tv_sec = priv->plat->est->btr_reserve[1];
 		basetime = timespec64_to_ktime(time);
-		cycle_time = priv->plat->est->ctr[1] * NSEC_PER_SEC +
+		cycle_time = (u64)priv->plat->est->ctr[1] * NSEC_PER_SEC +
 			     priv->plat->est->ctr[0];
 		time = stmmac_calc_tas_basetime(basetime,
 						current_time_ns,
-- 
cgit v1.2.3


From 391e5975c0208ce3739587b33eba08be3e473d79 Mon Sep 17 00:00:00 2001
From: Nobuhiro Iwamatsu
Date: Thu, 23 Dec 2021 16:36:33 +0900
Subject: net: stmmac: dwmac-visconti: Fix value of ETHER_CLK_SEL_FREQ_SEL_2P5M

ETHER_CLK_SEL_FREQ_SEL_2P5M is not 0 bit of the register. This is a
value, which is 0. Fix from BIT(0) to 0.

Reported-by: Yuji Ishikawa <yuji2.ishikawa@toshiba.co.jp>
Fixes: b38dd98ff8d0 ("net: stmmac: Add Toshiba Visconti SoCs glue driver")
Signed-off-by: Nobuhiro Iwamatsu <nobuhiro1.iwamatsu@toshiba.co.jp>
Link: https://lore.kernel.org/r/20211223073633.101306-1-nobuhiro1.iwamatsu@toshiba.co.jp
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
index 66fc8be34bb7..e2e0f977875d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
@@ -26,7 +26,7 @@
 #define ETHER_CLK_SEL_FREQ_SEL_125M	(BIT(9) | BIT(8))
 #define ETHER_CLK_SEL_FREQ_SEL_50M	BIT(9)
 #define ETHER_CLK_SEL_FREQ_SEL_25M	BIT(8)
-#define ETHER_CLK_SEL_FREQ_SEL_2P5M	BIT(0)
+#define ETHER_CLK_SEL_FREQ_SEL_2P5M	0
 #define ETHER_CLK_SEL_TX_CLK_EXT_SEL_IN BIT(0)
 #define ETHER_CLK_SEL_TX_CLK_EXT_SEL_TXC BIT(10)
 #define ETHER_CLK_SEL_TX_CLK_EXT_SEL_DIV BIT(11)
-- 
cgit v1.2.3


From 5f50153288452e10b6edd69ec9112c49442b054a Mon Sep 17 00:00:00 2001
From: Zekun Shen
Date: Sun, 26 Dec 2021 21:32:45 -0500
Subject: atlantic: Fix buff_ring OOB in aq_ring_rx_clean

The function obtain the next buffer without boundary check.
We should return with I/O error code.

The bug is found by fuzzing and the crash report is attached.
It is an OOB bug although reported as use-after-free.

[    4.804724] BUG: KASAN: use-after-free in aq_ring_rx_clean+0x1e88/0x2730 [atlantic]
[    4.805661] Read of size 4 at addr ffff888034fe93a8 by task ksoftirqd/0/9
[    4.806505]
[    4.806703] CPU: 0 PID: 9 Comm: ksoftirqd/0 Tainted: G        W         5.6.0 #34
[    4.809030] Call Trace:
[    4.809343]  dump_stack+0x76/0xa0
[    4.809755]  print_address_description.constprop.0+0x16/0x200
[    4.810455]  ? aq_ring_rx_clean+0x1e88/0x2730 [atlantic]
[    4.811234]  ? aq_ring_rx_clean+0x1e88/0x2730 [atlantic]
[    4.813183]  __kasan_report.cold+0x37/0x7c
[    4.813715]  ? aq_ring_rx_clean+0x1e88/0x2730 [atlantic]
[    4.814393]  kasan_report+0xe/0x20
[    4.814837]  aq_ring_rx_clean+0x1e88/0x2730 [atlantic]
[    4.815499]  ? hw_atl_b0_hw_ring_rx_receive+0x9a5/0xb90 [atlantic]
[    4.816290]  aq_vec_poll+0x179/0x5d0 [atlantic]
[    4.816870]  ? _GLOBAL__sub_I_65535_1_aq_pci_func_init+0x20/0x20 [atlantic]
[    4.817746]  ? __next_timer_interrupt+0xba/0xf0
[    4.818322]  net_rx_action+0x363/0xbd0
[    4.818803]  ? call_timer_fn+0x240/0x240
[    4.819302]  ? __switch_to_asm+0x40/0x70
[    4.819809]  ? napi_busy_loop+0x520/0x520
[    4.820324]  __do_softirq+0x18c/0x634
[    4.820797]  ? takeover_tasklets+0x5f0/0x5f0
[    4.821343]  run_ksoftirqd+0x15/0x20
[    4.821804]  smpboot_thread_fn+0x2f1/0x6b0
[    4.822331]  ? smpboot_unregister_percpu_thread+0x160/0x160
[    4.823041]  ? __kthread_parkme+0x80/0x100
[    4.823571]  ? smpboot_unregister_percpu_thread+0x160/0x160
[    4.824301]  kthread+0x2b5/0x3b0
[    4.824723]  ? kthread_create_on_node+0xd0/0xd0
[    4.825304]  ret_from_fork+0x35/0x40

Signed-off-by: Zekun Shen <bruceshenzk@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 81b3756417ec..77e76c9efd32 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -366,6 +366,10 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 		if (!buff->is_eop) {
 			buff_ = buff;
 			do {
+				if (buff_->next >= self->size) {
+					err = -EIO;
+					goto err_exit;
+				}
 				next_ = buff_->next,
 				buff_ = &self->buff_ring[next_];
 				is_rsc_completed =
@@ -389,6 +393,10 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 			    (buff->is_lro && buff->is_cso_err)) {
 				buff_ = buff;
 				do {
+					if (buff_->next >= self->size) {
+						err = -EIO;
+						goto err_exit;
+					}
 					next_ = buff_->next,
 					buff_ = &self->buff_ring[next_];
 
-- 
cgit v1.2.3


From 1cd5384c88af5b59bf9f3b6c1a151bc14b88c2cd Mon Sep 17 00:00:00 2001
From: Christophe JAILLET
Date: Sun, 26 Dec 2021 18:51:44 +0100
Subject: net: ag71xx: Fix a potential double free in error handling paths

'ndev' is a managed resource allocated with devm_alloc_etherdev(), so there
is no need to call free_netdev() explicitly or there will be a double
free().

Simplify all error handling paths accordingly.

Fixes: d51b6ce441d3 ("net: ethernet: add ag71xx driver")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/atheros/ag71xx.c | 23 ++++++++---------------
 1 file changed, 8 insertions(+), 15 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 88d2ab748399..4579ddf9c427 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -1913,15 +1913,12 @@ static int ag71xx_probe(struct platform_device *pdev)
 	ag->mac_reset = devm_reset_control_get(&pdev->dev, "mac");
 	if (IS_ERR(ag->mac_reset)) {
 		netif_err(ag, probe, ndev, "missing mac reset\n");
-		err = PTR_ERR(ag->mac_reset);
-		goto err_free;
+		return PTR_ERR(ag->mac_reset);
 	}
 
 	ag->mac_base = devm_ioremap(&pdev->dev, res->start, resource_size(res));
-	if (!ag->mac_base) {
-		err = -ENOMEM;
-		goto err_free;
-	}
+	if (!ag->mac_base)
+		return -ENOMEM;
 
 	ndev->irq = platform_get_irq(pdev, 0);
 	err = devm_request_irq(&pdev->dev, ndev->irq, ag71xx_interrupt,
@@ -1929,7 +1926,7 @@ static int ag71xx_probe(struct platform_device *pdev)
 	if (err) {
 		netif_err(ag, probe, ndev, "unable to request IRQ %d\n",
 			  ndev->irq);
-		goto err_free;
+		return err;
 	}
 
 	ndev->netdev_ops = &ag71xx_netdev_ops;
@@ -1957,10 +1954,8 @@ static int ag71xx_probe(struct platform_device *pdev)
 	ag->stop_desc = dmam_alloc_coherent(&pdev->dev,
 					    sizeof(struct ag71xx_desc),
 					    &ag->stop_desc_dma, GFP_KERNEL);
-	if (!ag->stop_desc) {
-		err = -ENOMEM;
-		goto err_free;
-	}
+	if (!ag->stop_desc)
+		return -ENOMEM;
 
 	ag->stop_desc->data = 0;
 	ag->stop_desc->ctrl = 0;
@@ -1975,7 +1970,7 @@ static int ag71xx_probe(struct platform_device *pdev)
 	err = of_get_phy_mode(np, &ag->phy_if_mode);
 	if (err) {
 		netif_err(ag, probe, ndev, "missing phy-mode property in DT\n");
-		goto err_free;
+		return err;
 	}
 
 	netif_napi_add(ndev, &ag->napi, ag71xx_poll, AG71XX_NAPI_WEIGHT);
@@ -1983,7 +1978,7 @@ static int ag71xx_probe(struct platform_device *pdev)
 	err = clk_prepare_enable(ag->clk_eth);
 	if (err) {
 		netif_err(ag, probe, ndev, "Failed to enable eth clk.\n");
-		goto err_free;
+		return err;
 	}
 
 	ag71xx_wr(ag, AG71XX_REG_MAC_CFG1, 0);
@@ -2019,8 +2014,6 @@ err_mdio_remove:
 	ag71xx_mdio_remove(ag);
 err_put_clk:
 	clk_disable_unprepare(ag->clk_eth);
-err_free:
-	free_netdev(ndev);
 	return err;
 }
 
-- 
cgit v1.2.3


From 5be60a945329d82f06fc755a43eeefbfc5f77d72 Mon Sep 17 00:00:00 2001
From: Aleksander Jan Bajkowski
Date: Mon, 27 Dec 2021 17:22:03 +0100
Subject: net: lantiq_xrx200: fix statistics of received bytes

Received frames have FCS truncated. There is no need
to subtract FCS length from the statistics.

Fixes: fe1a56420cf2 ("net: lantiq: Add Lantiq / Intel VRX200 Ethernet driver")
Signed-off-by: Aleksander Jan Bajkowski <olek2@wp.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/lantiq_xrx200.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 96bd6f2b21ed..80bfaf2fec92 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -224,7 +224,7 @@ static int xrx200_hw_receive(struct xrx200_chan *ch)
 	skb->protocol = eth_type_trans(skb, net_dev);
 	netif_receive_skb(skb);
 	net_dev->stats.rx_packets++;
-	net_dev->stats.rx_bytes += len - ETH_FCS_LEN;
+	net_dev->stats.rx_bytes += len;
 
 	return 0;
 }
-- 
cgit v1.2.3


From 1e81dcc1ab7de7a789e60042ce82d5a612632599 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes
Date: Mon, 13 Dec 2021 16:39:49 -0800
Subject: igc: Do not enable crosstimestamping for i225-V models

It was reported that when PCIe PTM is enabled, some lockups could
be observed with some integrated i225-V models.

While the issue is investigated, we can disable crosstimestamp for
those models and see no loss of functionality, because those models
don't have any support for time synchronization.

Fixes: a90ec8483732 ("igc: Add support for PTP getcrosststamp()")
Link: https://lore.kernel.org/all/924175a188159f4e03bd69908a91e606b574139b.camel@gmx.de/
Reported-by: Stefan Dietrich <roots@gmx.de>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Tested-by: Nechama Kraus <nechamax.kraus@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_ptp.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 30568e3544cd..4f9245aa79a1 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -768,7 +768,20 @@ int igc_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr)
  */
 static bool igc_is_crosststamp_supported(struct igc_adapter *adapter)
 {
-	return IS_ENABLED(CONFIG_X86_TSC) ? pcie_ptm_enabled(adapter->pdev) : false;
+	if (!IS_ENABLED(CONFIG_X86_TSC))
+		return false;
+
+	/* FIXME: it was noticed that enabling support for PCIe PTM in
+	 * some i225-V models could cause lockups when bringing the
+	 * interface up/down. There should be no downsides to
+	 * disabling crosstimestamping support for i225-V, as it
+	 * doesn't have any PTP support. That way we gain some time
+	 * while root causing the issue.
+	 */
+	if (adapter->pdev->device == IGC_DEV_ID_I225_V)
+		return false;
+
+	return pcie_ptm_enabled(adapter->pdev);
 }
 
 static struct system_counterval_t igc_device_tstamp_to_system(u64 tstamp)
-- 
cgit v1.2.3


From f85846bbf43de38fb2c89fe7d2a085608c4eb25a Mon Sep 17 00:00:00 2001
From: James McLaughlin
Date: Fri, 17 Dec 2021 16:49:33 -0700
Subject: igc: Fix TX timestamp support for non-MSI-X platforms

Time synchronization was not properly enabled on non-MSI-X platforms.

Fixes: 2c344ae24501 ("igc: Add support for TX timestamping")
Signed-off-by: James McLaughlin <james.mclaughlin@qsc.com>
Reviewed-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Tested-by: Nechama Kraus <nechamax.kraus@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 8e448288ee26..d28a80a00953 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -5467,6 +5467,9 @@ static irqreturn_t igc_intr_msi(int irq, void *data)
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
+	if (icr & IGC_ICR_TS)
+		igc_tsync_interrupt(adapter);
+
 	napi_schedule(&q_vector->napi);
 
 	return IRQ_HANDLED;
@@ -5510,6 +5513,9 @@ static irqreturn_t igc_intr(int irq, void *data)
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
+	if (icr & IGC_ICR_TS)
+		igc_tsync_interrupt(adapter);
+
 	napi_schedule(&q_vector->napi);
 
 	return IRQ_HANDLED;
-- 
cgit v1.2.3


From 140c7bc7d1195750342ea0e6ab76179499ae7cd7 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET
Date: Sun, 26 Dec 2021 15:06:17 +0100
Subject: ionic: Initialize the 'lif->dbid_inuse' bitmap

When allocated, this bitmap is not initialized. Only the first bit is set a
few lines below.

Use bitmap_zalloc() to make sure that it is cleared before being used.

Fixes: 6461b446f2a0 ("ionic: Add interrupts and doorbells")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Link: https://lore.kernel.org/r/6a478eae0b5e6c63774e1f0ddb1a3f8c38fa8ade.1640527506.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_lif.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 63f8a8163b5f..2ff7be17e5af 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -3135,7 +3135,7 @@ int ionic_lif_init(struct ionic_lif *lif)
 		return -EINVAL;
 	}
 
-	lif->dbid_inuse = bitmap_alloc(lif->dbid_count, GFP_KERNEL);
+	lif->dbid_inuse = bitmap_zalloc(lif->dbid_count, GFP_KERNEL);
 	if (!lif->dbid_inuse) {
 		dev_err(dev, "Failed alloc doorbell id bitmap, aborting\n");
 		return -ENOMEM;
-- 
cgit v1.2.3


From 077cdda764c7f147e03e6065ba0cd1dbc1bf00d1 Mon Sep 17 00:00:00 2001
From: Roi Dayan
Date: Wed, 22 Dec 2021 09:20:58 +0200
Subject: net/mlx5e: TC, Fix memory leak with rules with internal port

Fix a memory leak with decap rule with internal port as destination
device. The driver allocates a modify hdr action but doesn't set
the flow attr modify hdr action which results in skipping releasing
the modify hdr action when releasing the flow.

backtrace:
    [<000000005f8c651c>] krealloc+0x83/0xd0
    [<000000009f59b143>] alloc_mod_hdr_actions+0x156/0x310 [mlx5_core]
    [<000000002257f342>] mlx5e_tc_match_to_reg_set_and_get_id+0x12a/0x360 [mlx5_core]
    [<00000000b44ea75a>] mlx5e_tc_add_fdb_flow+0x962/0x1470 [mlx5_core]
    [<0000000003e384a0>] __mlx5e_add_fdb_flow+0x54c/0xb90 [mlx5_core]
    [<00000000ed8b22b6>] mlx5e_configure_flower+0xe45/0x4af0 [mlx5_core]
    [<00000000024f4ab5>] mlx5e_rep_indr_offload.isra.0+0xfe/0x1b0 [mlx5_core]
    [<000000006c3bb494>] mlx5e_rep_indr_setup_tc_cb+0x90/0x130 [mlx5_core]
    [<00000000d3dac2ea>] tc_setup_cb_add+0x1d2/0x420

Fixes: b16eb3c81fe2 ("net/mlx5: Support internal port as decap route device")
Signed-off-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index a60c7680fd2b..5e454a14428f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1441,6 +1441,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 							metadata);
 			if (err)
 				goto err_out;
+
+			attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
 		}
 	}
 
-- 
cgit v1.2.3


From 992d8a4e38f0527f24e273ce3a9cd6dea1a6a436 Mon Sep 17 00:00:00 2001
From: Gal Pressman
Date: Mon, 29 Nov 2021 11:08:41 +0200
Subject: net/mlx5e: Fix wrong features assignment in case of error

In case of an error in mlx5e_set_features(), 'netdev->features' must be
updated with the correct state of the device to indicate which features
were updated successfully.
To do that we maintain a copy of 'netdev->features' and update it after
successful feature changes, so we can assign it to back to
'netdev->features' if needed.

However, since not all netdev features are handled by the driver (e.g.
GRO/TSO/etc), some features may not be updated correctly in case of an
error updating another feature.

For example, while requesting to disable TSO (feature which is not
handled by the driver) and enable HW-GRO, if an error occurs during
HW-GRO enable, 'oper_features' will be assigned with 'netdev->features'
and HW-GRO turned off. TSO will remain enabled in such case, which is a
bug.

To solve that, instead of using 'netdev->features' as the baseline of
'oper_features' and changing it on set feature success, use 'features'
instead and update it in case of errors.

Fixes: 75b81ce719b7 ("net/mlx5e: Don't override netdev features field unless in error flow")
Signed-off-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 3b0f3a831216..41379844eee1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3741,12 +3741,11 @@ static int set_feature_arfs(struct net_device *netdev, bool enable)
 
 static int mlx5e_handle_feature(struct net_device *netdev,
 				netdev_features_t *features,
-				netdev_features_t wanted_features,
 				netdev_features_t feature,
 				mlx5e_feature_handler feature_handler)
 {
-	netdev_features_t changes = wanted_features ^ netdev->features;
-	bool enable = !!(wanted_features & feature);
+	netdev_features_t changes = *features ^ netdev->features;
+	bool enable = !!(*features & feature);
 	int err;
 
 	if (!(changes & feature))
@@ -3754,22 +3753,22 @@ static int mlx5e_handle_feature(struct net_device *netdev,
 
 	err = feature_handler(netdev, enable);
 	if (err) {
+		MLX5E_SET_FEATURE(features, feature, !enable);
 		netdev_err(netdev, "%s feature %pNF failed, err %d\n",
 			   enable ? "Enable" : "Disable", &feature, err);
 		return err;
 	}
 
-	MLX5E_SET_FEATURE(features, feature, enable);
 	return 0;
 }
 
 int mlx5e_set_features(struct net_device *netdev, netdev_features_t features)
 {
-	netdev_features_t oper_features = netdev->features;
+	netdev_features_t oper_features = features;
 	int err = 0;
 
 #define MLX5E_HANDLE_FEATURE(feature, handler) \
-	mlx5e_handle_feature(netdev, &oper_features, features, feature, handler)
+	mlx5e_handle_feature(netdev, &oper_features, feature, handler)
 
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_LRO, set_feature_lro);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_GRO_HW, set_feature_hw_gro);
-- 
cgit v1.2.3


From bf2b09fedc17248b315f80fb249087b7d28a69a6 Mon Sep 17 00:00:00 2001
From: Miaoqian Lin
Date: Thu, 30 Dec 2021 12:26:27 +0000
Subject: fsl/fman: Fix missing put_device() call in fman_port_probe

The reference taken by 'of_find_device_by_node()' must be released when
not needed anymore.
Add the corresponding 'put_device()' in the and error handling paths.

Fixes: 18a6c85fcc78 ("fsl/fman: Add FMan Port Support")
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fman/fman_port.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c
index d9baac0dbc7d..4c9d05c45c03 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.c
+++ b/drivers/net/ethernet/freescale/fman/fman_port.c
@@ -1805,7 +1805,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 	fman = dev_get_drvdata(&fm_pdev->dev);
 	if (!fman) {
 		err = -EINVAL;
-		goto return_err;
+		goto put_device;
 	}
 
 	err = of_property_read_u32(port_node, "cell-index", &val);
@@ -1813,7 +1813,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 		dev_err(port->dev, "%s: reading cell-index for %pOF failed\n",
 			__func__, port_node);
 		err = -EINVAL;
-		goto return_err;
+		goto put_device;
 	}
 	port_id = (u8)val;
 	port->dts_params.id = port_id;
@@ -1847,7 +1847,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 	}  else {
 		dev_err(port->dev, "%s: Illegal port type\n", __func__);
 		err = -EINVAL;
-		goto return_err;
+		goto put_device;
 	}
 
 	port->dts_params.type = port_type;
@@ -1861,7 +1861,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 			dev_err(port->dev, "%s: incorrect qman-channel-id\n",
 				__func__);
 			err = -EINVAL;
-			goto return_err;
+			goto put_device;
 		}
 		port->dts_params.qman_channel_id = qman_channel_id;
 	}
@@ -1871,7 +1871,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 		dev_err(port->dev, "%s: of_address_to_resource() failed\n",
 			__func__);
 		err = -ENOMEM;
-		goto return_err;
+		goto put_device;
 	}
 
 	port->dts_params.fman = fman;
@@ -1896,6 +1896,8 @@ static int fman_port_probe(struct platform_device *of_dev)
 
 	return 0;
 
+put_device:
+	put_device(&fm_pdev->dev);
 return_err:
 	of_node_put(port_node);
 free_port:
-- 
cgit v1.2.3


From c255a34e02efb1393d23ffb205ba1a11320aeffb Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski
Date: Sun, 2 Jan 2022 07:37:26 +0000
Subject: net: ena: Fix undefined state when tx request id is out of bounds

ena_com_tx_comp_req_id_get() checks the req_id of a received completion,
and if it is out of bounds returns -EINVAL. This is a sign that
something is wrong with the device and it needs to be reset.

The current code does not reset the device in this case, which leaves
the driver in an undefined state, where this completion is not properly
handled.

This commit adds a call to handle_invalid_req_id() in ena_clean_tx_irq()
and ena_clean_xdp_irq() which resets the device to fix the issue.

This commit also removes unnecessary request id checks from
validate_tx_req_id() and validate_xdp_req_id(). This check is unneeded
because it was already performed in ena_com_tx_comp_req_id_get(), which
is called right before these functions.

Fixes: 548c4940b9f1 ("net: ena: Implement XDP_TX action")
Signed-off-by: Shay Agroskin <shayagr@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 34 ++++++++++++++++------------
 1 file changed, 20 insertions(+), 14 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 7d5d885d85d5..2274063e34cc 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -1288,26 +1288,22 @@ static int handle_invalid_req_id(struct ena_ring *ring, u16 req_id,
 
 static int validate_tx_req_id(struct ena_ring *tx_ring, u16 req_id)
 {
-	struct ena_tx_buffer *tx_info = NULL;
+	struct ena_tx_buffer *tx_info;
 
-	if (likely(req_id < tx_ring->ring_size)) {
-		tx_info = &tx_ring->tx_buffer_info[req_id];
-		if (likely(tx_info->skb))
-			return 0;
-	}
+	tx_info = &tx_ring->tx_buffer_info[req_id];
+	if (likely(tx_info->skb))
+		return 0;
 
 	return handle_invalid_req_id(tx_ring, req_id, tx_info, false);
 }
 
 static int validate_xdp_req_id(struct ena_ring *xdp_ring, u16 req_id)
 {
-	struct ena_tx_buffer *tx_info = NULL;
+	struct ena_tx_buffer *tx_info;
 
-	if (likely(req_id < xdp_ring->ring_size)) {
-		tx_info = &xdp_ring->tx_buffer_info[req_id];
-		if (likely(tx_info->xdpf))
-			return 0;
-	}
+	tx_info = &xdp_ring->tx_buffer_info[req_id];
+	if (likely(tx_info->xdpf))
+		return 0;
 
 	return handle_invalid_req_id(xdp_ring, req_id, tx_info, true);
 }
@@ -1332,9 +1328,14 @@ static int ena_clean_tx_irq(struct ena_ring *tx_ring, u32 budget)
 
 		rc = ena_com_tx_comp_req_id_get(tx_ring->ena_com_io_cq,
 						&req_id);
-		if (rc)
+		if (rc) {
+			if (unlikely(rc == -EINVAL))
+				handle_invalid_req_id(tx_ring, req_id, NULL,
+						      false);
 			break;
+		}
 
+		/* validate that the request id points to a valid skb */
 		rc = validate_tx_req_id(tx_ring, req_id);
 		if (rc)
 			break;
@@ -1896,9 +1897,14 @@ static int ena_clean_xdp_irq(struct ena_ring *xdp_ring, u32 budget)
 
 		rc = ena_com_tx_comp_req_id_get(xdp_ring->ena_com_io_cq,
 						&req_id);
-		if (rc)
+		if (rc) {
+			if (unlikely(rc == -EINVAL))
+				handle_invalid_req_id(xdp_ring, req_id, NULL,
+						      true);
 			break;
+		}
 
+		/* validate that the request id points to a valid xdp_frame */
 		rc = validate_xdp_req_id(xdp_ring, req_id);
 		if (rc)
 			break;
-- 
cgit v1.2.3


From cb3d4f98f0b26eafa0b913ac3716e4714254a747 Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski
Date: Sun, 2 Jan 2022 07:37:27 +0000
Subject: net: ena: Fix wrong rx request id by resetting device

A wrong request id received from the device is a sign that
something is wrong with it, therefore trigger a device reset.

Also add some debug info to the "Page is NULL" print to make
it easier to debug.

Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)")
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 2274063e34cc..52a8c60b7e29 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -1428,6 +1428,7 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 				  u16 *next_to_clean)
 {
 	struct ena_rx_buffer *rx_info;
+	struct ena_adapter *adapter;
 	u16 len, req_id, buf = 0;
 	struct sk_buff *skb;
 	void *page_addr;
@@ -1440,8 +1441,14 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 	rx_info = &rx_ring->rx_buffer_info[req_id];
 
 	if (unlikely(!rx_info->page)) {
-		netif_err(rx_ring->adapter, rx_err, rx_ring->netdev,
-			  "Page is NULL\n");
+		adapter = rx_ring->adapter;
+		netif_err(adapter, rx_err, rx_ring->netdev,
+			  "Page is NULL. qid %u req_id %u\n", rx_ring->qid, req_id);
+		ena_increase_stat(&rx_ring->rx_stats.bad_req_id, 1, &rx_ring->syncp);
+		adapter->reset_reason = ENA_REGS_RESET_INV_RX_REQ_ID;
+		/* Make sure reset reason is set before triggering the reset */
+		smp_mb__before_atomic();
+		set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
 		return NULL;
 	}
 
-- 
cgit v1.2.3


From 5055dc0348b8b7c168e3296044bccd724e1ae6cd Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski
Date: Sun, 2 Jan 2022 07:37:28 +0000
Subject: net: ena: Fix error handling when calculating max IO queues number

The role of ena_calc_max_io_queue_num() is to return the number
of queues supported by the device, which means the return value
should be >=0.

The function that calls ena_calc_max_io_queue_num(), checks
the return value. If it is 0, it means the device reported
it supports 0 IO queues. This case is considered an error
and is handled by the calling function accordingly.

However the current implementation of ena_calc_max_io_queue_num()
is wrong, since when it detects the device supports 0 IO queues,
it returns -EFAULT.

In such a case the calling function doesn't detect the error,
and therefore doesn't handle it.

This commit changes ena_calc_max_io_queue_num() to return 0
in case the device reported it supports 0 queues, allowing the
calling function to properly handle the error case.

Fixes: 736ce3f414cc ("net: ena: make ethtool -l show correct max number of queues")
Signed-off-by: Shay Agroskin <shayagr@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 52a8c60b7e29..c72f0c7ff4aa 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -4026,10 +4026,6 @@ static u32 ena_calc_max_io_queue_num(struct pci_dev *pdev,
 	max_num_io_queues = min_t(u32, max_num_io_queues, io_tx_cq_num);
 	/* 1 IRQ for mgmnt and 1 IRQs for each IO direction */
 	max_num_io_queues = min_t(u32, max_num_io_queues, pci_msix_vec_count(pdev) - 1);
-	if (unlikely(!max_num_io_queues)) {
-		dev_err(&pdev->dev, "The device doesn't have io queues\n");
-		return -EFAULT;
-	}
 
 	return max_num_io_queues;
 }
-- 
cgit v1.2.3


From 1ef5e1d0dca5b4ffd49d7dec4a83660882f1fda4 Mon Sep 17 00:00:00 2001
From: Markus Koch
Date: Sun, 2 Jan 2022 17:54:08 +0100
Subject: net/fsl: Remove leftover definition in xgmac_mdio

commit 26eee0210ad7 ("net/fsl: fix a bug in xgmac_mdio") fixed a bug in
the QorIQ mdio driver but left the (now unused) incorrect bit definition
for MDIO_DATA_BSY in the code. This commit removes it.

Signed-off-by: Markus Koch <markus@notsyncing.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/xgmac_mdio.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c
index 0b68852379da..5b8b9bcf41a2 100644
--- a/drivers/net/ethernet/freescale/xgmac_mdio.c
+++ b/drivers/net/ethernet/freescale/xgmac_mdio.c
@@ -47,7 +47,6 @@ struct tgec_mdio_controller {
 #define MDIO_CTL_READ		BIT(15)
 
 #define MDIO_DATA(x)		(x & 0xffff)
-#define MDIO_DATA_BSY		BIT(31)
 
 struct mdio_fsl_priv {
 	struct	tgec_mdio_controller __iomem *mdio_base;
-- 
cgit v1.2.3


From 01cbf50877e602e2376af89e4a51c30bc574c618 Mon Sep 17 00:00:00 2001
From: Mateusz Palczewski
Date: Wed, 3 Mar 2021 11:45:33 +0000
Subject: i40e: Fix to not show opcode msg on unsuccessful VF MAC change

Hide i40e opcode information sent during response to VF in case when
untrusted VF tried to change MAC on the VF interface.

This is implemented by adding an additional parameter 'hide' to the
response sent to VF function that hides the display of error
information, but forwards the error code to VF.

Previously it was not possible to send response with some error code
to VF without displaying opcode information.

Fixes: 5c3c48ac6bf5 ("i40e: implement virtual device interface")
Signed-off-by: Grzegorz Szczurek <grzegorzx.szczurek@intel.com>
Signed-off-by: Mateusz Palczewski <mateusz.palczewski@intel.com>
Reviewed-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Tony Brelinski <tony.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 40 +++++++++++++++++-----
 1 file changed, 32 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 2ea4deb8fc44..048f1678ab8a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1877,17 +1877,19 @@ sriov_configure_out:
 /***********************virtual channel routines******************/
 
 /**
- * i40e_vc_send_msg_to_vf
+ * i40e_vc_send_msg_to_vf_ex
  * @vf: pointer to the VF info
  * @v_opcode: virtual channel opcode
  * @v_retval: virtual channel return value
  * @msg: pointer to the msg buffer
  * @msglen: msg length
+ * @is_quiet: true for not printing unsuccessful return values, false otherwise
  *
  * send msg to VF
  **/
-static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode,
-				  u32 v_retval, u8 *msg, u16 msglen)
+static int i40e_vc_send_msg_to_vf_ex(struct i40e_vf *vf, u32 v_opcode,
+				     u32 v_retval, u8 *msg, u16 msglen,
+				     bool is_quiet)
 {
 	struct i40e_pf *pf;
 	struct i40e_hw *hw;
@@ -1903,7 +1905,7 @@ static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode,
 	abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id;
 
 	/* single place to detect unsuccessful return values */
-	if (v_retval) {
+	if (v_retval && !is_quiet) {
 		vf->num_invalid_msgs++;
 		dev_info(&pf->pdev->dev, "VF %d failed opcode %d, retval: %d\n",
 			 vf->vf_id, v_opcode, v_retval);
@@ -1933,6 +1935,23 @@ static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode,
 	return 0;
 }
 
+/**
+ * i40e_vc_send_msg_to_vf
+ * @vf: pointer to the VF info
+ * @v_opcode: virtual channel opcode
+ * @v_retval: virtual channel return value
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ *
+ * send msg to VF
+ **/
+static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode,
+				  u32 v_retval, u8 *msg, u16 msglen)
+{
+	return i40e_vc_send_msg_to_vf_ex(vf, v_opcode, v_retval,
+					 msg, msglen, false);
+}
+
 /**
  * i40e_vc_send_resp_to_vf
  * @vf: pointer to the VF info
@@ -2695,6 +2714,7 @@ error_param:
  * i40e_check_vf_permission
  * @vf: pointer to the VF info
  * @al: MAC address list from virtchnl
+ * @is_quiet: set true for printing msg without opcode info, false otherwise
  *
  * Check that the given list of MAC addresses is allowed. Will return -EPERM
  * if any address in the list is not valid. Checks the following conditions:
@@ -2709,13 +2729,15 @@ error_param:
  * addresses might not be accurate.
  **/
 static inline int i40e_check_vf_permission(struct i40e_vf *vf,
-					   struct virtchnl_ether_addr_list *al)
+					   struct virtchnl_ether_addr_list *al,
+					   bool *is_quiet)
 {
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_vsi *vsi = pf->vsi[vf->lan_vsi_idx];
 	int mac2add_cnt = 0;
 	int i;
 
+	*is_quiet = false;
 	for (i = 0; i < al->num_elements; i++) {
 		struct i40e_mac_filter *f;
 		u8 *addr = al->list[i].addr;
@@ -2739,6 +2761,7 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf,
 		    !ether_addr_equal(addr, vf->default_lan_addr.addr)) {
 			dev_err(&pf->pdev->dev,
 				"VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n");
+			*is_quiet = true;
 			return -EPERM;
 		}
 
@@ -2775,6 +2798,7 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
 	    (struct virtchnl_ether_addr_list *)msg;
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_vsi *vsi = NULL;
+	bool is_quiet = false;
 	i40e_status ret = 0;
 	int i;
 
@@ -2791,7 +2815,7 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
 	 */
 	spin_lock_bh(&vsi->mac_filter_hash_lock);
 
-	ret = i40e_check_vf_permission(vf, al);
+	ret = i40e_check_vf_permission(vf, al, &is_quiet);
 	if (ret) {
 		spin_unlock_bh(&vsi->mac_filter_hash_lock);
 		goto error_param;
@@ -2829,8 +2853,8 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
 
 error_param:
 	/* send the response to the VF */
-	return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ADD_ETH_ADDR,
-				       ret);
+	return i40e_vc_send_msg_to_vf_ex(vf, VIRTCHNL_OP_ADD_ETH_ADDR,
+				       ret, NULL, 0, is_quiet);
 }
 
 /**
-- 
cgit v1.2.3


From 3116f59c12bd24c513194cd3acb3ec1f7d468954 Mon Sep 17 00:00:00 2001
From: Di Zhu
Date: Mon, 29 Nov 2021 19:52:01 +0600
Subject: i40e: fix use-after-free in i40e_sync_filters_subtask()

Using ifconfig command to delete the ipv6 address will cause
the i40e network card driver to delete its internal mac_filter and
i40e_service_task kernel thread will concurrently access the mac_filter.
These two processes are not protected by lock
so causing the following use-after-free problems.

 print_address_description+0x70/0x360
 ? vprintk_func+0x5e/0xf0
 kasan_report+0x1b2/0x330
 i40e_sync_vsi_filters+0x4f0/0x1850 [i40e]
 i40e_sync_filters_subtask+0xe3/0x130 [i40e]
 i40e_service_task+0x195/0x24c0 [i40e]
 process_one_work+0x3f5/0x7d0
 worker_thread+0x61/0x6c0
 ? process_one_work+0x7d0/0x7d0
 kthread+0x1c3/0x1f0
 ? kthread_park+0xc0/0xc0
 ret_from_fork+0x35/0x40

Allocated by task 2279810:
 kasan_kmalloc+0xa0/0xd0
 kmem_cache_alloc_trace+0xf3/0x1e0
 i40e_add_filter+0x127/0x2b0 [i40e]
 i40e_add_mac_filter+0x156/0x190 [i40e]
 i40e_addr_sync+0x2d/0x40 [i40e]
 __hw_addr_sync_dev+0x154/0x210
 i40e_set_rx_mode+0x6d/0xf0 [i40e]
 __dev_set_rx_mode+0xfb/0x1f0
 __dev_mc_add+0x6c/0x90
 igmp6_group_added+0x214/0x230
 __ipv6_dev_mc_inc+0x338/0x4f0
 addrconf_join_solict.part.7+0xa2/0xd0
 addrconf_dad_work+0x500/0x980
 process_one_work+0x3f5/0x7d0
 worker_thread+0x61/0x6c0
 kthread+0x1c3/0x1f0
 ret_from_fork+0x35/0x40

Freed by task 2547073:
 __kasan_slab_free+0x130/0x180
 kfree+0x90/0x1b0
 __i40e_del_filter+0xa3/0xf0 [i40e]
 i40e_del_mac_filter+0xf3/0x130 [i40e]
 i40e_addr_unsync+0x85/0xa0 [i40e]
 __hw_addr_sync_dev+0x9d/0x210
 i40e_set_rx_mode+0x6d/0xf0 [i40e]
 __dev_set_rx_mode+0xfb/0x1f0
 __dev_mc_del+0x69/0x80
 igmp6_group_dropped+0x279/0x510
 __ipv6_dev_mc_dec+0x174/0x220
 addrconf_leave_solict.part.8+0xa2/0xd0
 __ipv6_ifa_notify+0x4cd/0x570
 ipv6_ifa_notify+0x58/0x80
 ipv6_del_addr+0x259/0x4a0
 inet6_addr_del+0x188/0x260
 addrconf_del_ifaddr+0xcc/0x130
 inet6_ioctl+0x152/0x190
 sock_do_ioctl+0xd8/0x2b0
 sock_ioctl+0x2e5/0x4c0
 do_vfs_ioctl+0x14e/0xa80
 ksys_ioctl+0x7c/0xa0
 __x64_sys_ioctl+0x42/0x50
 do_syscall_64+0x98/0x2c0
 entry_SYSCALL_64_after_hwframe+0x65/0xca

Fixes: 41c445ff0f48 ("i40e: main driver core")
Signed-off-by: Di Zhu <zhudi2@huawei.com>
Signed-off-by: Rui Zhang <zhangrui182@huawei.com>
Tested-by: Gurucharan G <gurucharanx.g@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index e118cf9265c7..e0c4d6113c02 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -99,6 +99,24 @@ MODULE_LICENSE("GPL v2");
 
 static struct workqueue_struct *i40e_wq;
 
+static void netdev_hw_addr_refcnt(struct i40e_mac_filter *f,
+				  struct net_device *netdev, int delta)
+{
+	struct netdev_hw_addr *ha;
+
+	if (!f || !netdev)
+		return;
+
+	netdev_for_each_mc_addr(ha, netdev) {
+		if (ether_addr_equal(ha->addr, f->macaddr)) {
+			ha->refcount += delta;
+			if (ha->refcount <= 0)
+				ha->refcount = 1;
+			break;
+		}
+	}
+}
+
 /**
  * i40e_allocate_dma_mem_d - OS specific memory alloc for shared code
  * @hw:   pointer to the HW structure
@@ -2036,6 +2054,7 @@ static void i40e_undo_add_filter_entries(struct i40e_vsi *vsi,
 	hlist_for_each_entry_safe(new, h, from, hlist) {
 		/* We can simply free the wrapper structure */
 		hlist_del(&new->hlist);
+		netdev_hw_addr_refcnt(new->f, vsi->netdev, -1);
 		kfree(new);
 	}
 }
@@ -2383,6 +2402,10 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 						       &tmp_add_list,
 						       &tmp_del_list,
 						       vlan_filters);
+
+		hlist_for_each_entry(new, &tmp_add_list, hlist)
+			netdev_hw_addr_refcnt(new->f, vsi->netdev, 1);
+
 		if (retval)
 			goto err_no_memory_locked;
 
@@ -2515,6 +2538,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 			if (new->f->state == I40E_FILTER_NEW)
 				new->f->state = new->state;
 			hlist_del(&new->hlist);
+			netdev_hw_addr_refcnt(new->f, vsi->netdev, -1);
 			kfree(new);
 		}
 		spin_unlock_bh(&vsi->mac_filter_hash_lock);
-- 
cgit v1.2.3


From 40feded8a247f95957a0de9abd100085fb320a2f Mon Sep 17 00:00:00 2001
From: Mateusz Palczewski
Date: Thu, 9 Dec 2021 11:04:35 +0100
Subject: i40e: Fix for displaying message regarding NVM version

When loading the i40e driver, it prints a message like: 'The driver for the
device detected a newer version of the NVM image v1.x than expected v1.y.
Please install the most recent version of the network driver.' This is
misleading as the driver is working as expected.

Fix that by removing the second part of message and changing it from
dev_info to dev_dbg.

Fixes: 4fb29bddb57f ("i40e: The driver now prints the API version in error message")
Signed-off-by: Mateusz Palczewski <mateusz.palczewski@intel.com>
Tested-by: Gurucharan G <gurucharanx.g@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index e0c4d6113c02..17c3f6d69740 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -15475,8 +15475,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
 	    hw->aq.api_min_ver > I40E_FW_MINOR_VERSION(hw))
-		dev_info(&pdev->dev,
-			 "The driver for the device detected a newer version of the NVM image v%u.%u than expected v%u.%u. Please install the most recent version of the network driver.\n",
+		dev_dbg(&pdev->dev,
+			"The driver for the device detected a newer version of the NVM image v%u.%u than v%u.%u.\n",
 			 hw->aq.api_maj_ver,
 			 hw->aq.api_min_ver,
 			 I40E_FW_API_VERSION_MAJOR,
-- 
cgit v1.2.3


From e738451d78b2f8a9635d66c6a87f304b4d965f7a Mon Sep 17 00:00:00 2001
From: Jedrzej Jagielski
Date: Fri, 17 Dec 2021 14:29:05 +0000
Subject: i40e: Fix incorrect netdev's real number of RX/TX queues

There was a wrong queues representation in sysfs during
driver's reinitialization in case of online cpus number is
less than combined queues. It was caused by stopped
NetworkManager, which is responsible for calling vsi_open
function during driver's initialization.
In specific situation (ex. 12 cpus online) there were 16 queues
in /sys/class/net/<iface>/queues. In case of modifying queues with
value higher, than number of online cpus, then it caused write
errors and other errors.
Add updating of sysfs's queues representation during driver
initialization.

Fixes: 41c445ff0f48 ("i40e: main driver core")
Signed-off-by: Lukasz Cieplicki <lukaszx.cieplicki@intel.com>
Signed-off-by: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Tested-by: Gurucharan G <gurucharanx.g@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 32 ++++++++++++++++++++++-------
 1 file changed, 25 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 17c3f6d69740..61afc220fc6c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -8740,6 +8740,27 @@ int i40e_open(struct net_device *netdev)
 	return 0;
 }
 
+/**
+ * i40e_netif_set_realnum_tx_rx_queues - Update number of tx/rx queues
+ * @vsi: vsi structure
+ *
+ * This updates netdev's number of tx/rx queues
+ *
+ * Returns status of setting tx/rx queues
+ **/
+static int i40e_netif_set_realnum_tx_rx_queues(struct i40e_vsi *vsi)
+{
+	int ret;
+
+	ret = netif_set_real_num_rx_queues(vsi->netdev,
+					   vsi->num_queue_pairs);
+	if (ret)
+		return ret;
+
+	return netif_set_real_num_tx_queues(vsi->netdev,
+					    vsi->num_queue_pairs);
+}
+
 /**
  * i40e_vsi_open -
  * @vsi: the VSI to open
@@ -8776,13 +8797,7 @@ int i40e_vsi_open(struct i40e_vsi *vsi)
 			goto err_setup_rx;
 
 		/* Notify the stack of the actual queue counts. */
-		err = netif_set_real_num_tx_queues(vsi->netdev,
-						   vsi->num_queue_pairs);
-		if (err)
-			goto err_set_queues;
-
-		err = netif_set_real_num_rx_queues(vsi->netdev,
-						   vsi->num_queue_pairs);
+		err = i40e_netif_set_realnum_tx_rx_queues(vsi);
 		if (err)
 			goto err_set_queues;
 
@@ -14173,6 +14188,9 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
 	case I40E_VSI_MAIN:
 	case I40E_VSI_VMDQ2:
 		ret = i40e_config_netdev(vsi);
+		if (ret)
+			goto err_netdev;
+		ret = i40e_netif_set_realnum_tx_rx_queues(vsi);
 		if (ret)
 			goto err_netdev;
 		ret = register_netdev(vsi->netdev);
-- 
cgit v1.2.3


From b712941c8085e638bb92456e866ed3de4404e3d5 Mon Sep 17 00:00:00 2001
From: Karen Sornek
Date: Wed, 1 Sep 2021 09:21:46 +0200
Subject: iavf: Fix limit of total number of queues to active queues of VF

In the absence of this validation, if the user requests to
configure queues more than the enabled queues, it results in
sending the requested number of queues to the kernel stack
(due to the asynchronous nature of VF response), in which
case the stack might pick a queue to transmit that is not
enabled and result in Tx hang. Fix this bug by
limiting the total number of queues allocated for VF to
active queues of VF.

Fixes: d5b33d024496 ("i40evf: add ndo_setup_tc callback to i40evf")
Signed-off-by: Ashwin Vijayavel <ashwin.vijayavel@intel.com>
Signed-off-by: Karen Sornek <karen.sornek@intel.com>
Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 4e7c04047f91..e4439b095533 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -2708,8 +2708,11 @@ static int iavf_validate_ch_config(struct iavf_adapter *adapter,
 		total_max_rate += tx_rate;
 		num_qps += mqprio_qopt->qopt.count[i];
 	}
-	if (num_qps > IAVF_MAX_REQ_QUEUES)
+	if (num_qps > adapter->num_active_queues) {
+		dev_err(&adapter->pdev->dev,
+			"Cannot support requested number of queues\n");
 		return -EINVAL;
+	}
 
 	ret = iavf_validate_tx_bandwidth(adapter, total_max_rate);
 	return ret;
-- 
cgit v1.2.3


From 1d5a474240407c38ca8c7484a656ee39f585399c Mon Sep 17 00:00:00 2001
From: Martin Habets
Date: Sun, 2 Jan 2022 08:41:22 +0000
Subject: sfc: The RX page_ring is optional

The RX page_ring is an optional feature that improves
performance. When allocation fails the driver can still
function, but possibly with a lower bandwidth.
Guard against dereferencing a NULL page_ring.

Fixes: 2768935a4660 ("sfc: reuse pages to avoid DMA mapping/unmapping costs")
Signed-off-by: Martin Habets <habetsm.xilinx@gmail.com>
Reported-by: Jiasheng Jiang <jiasheng@iscas.ac.cn>
Link: https://lore.kernel.org/r/164111288276.5798.10330502993729113868.stgit@palantir17.mph.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/sfc/falcon/rx.c | 5 +++++
 drivers/net/ethernet/sfc/rx_common.c | 5 +++++
 2 files changed, 10 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sfc/falcon/rx.c b/drivers/net/ethernet/sfc/falcon/rx.c
index 11a6aee852e9..0c6cc2191369 100644
--- a/drivers/net/ethernet/sfc/falcon/rx.c
+++ b/drivers/net/ethernet/sfc/falcon/rx.c
@@ -110,6 +110,8 @@ static struct page *ef4_reuse_page(struct ef4_rx_queue *rx_queue)
 	struct ef4_rx_page_state *state;
 	unsigned index;
 
+	if (unlikely(!rx_queue->page_ring))
+		return NULL;
 	index = rx_queue->page_remove & rx_queue->page_ptr_mask;
 	page = rx_queue->page_ring[index];
 	if (page == NULL)
@@ -293,6 +295,9 @@ static void ef4_recycle_rx_pages(struct ef4_channel *channel,
 {
 	struct ef4_rx_queue *rx_queue = ef4_channel_get_rx_queue(channel);
 
+	if (unlikely(!rx_queue->page_ring))
+		return;
+
 	do {
 		ef4_recycle_rx_page(channel, rx_buf);
 		rx_buf = ef4_rx_buf_next(rx_queue, rx_buf);
diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c
index 0983abc0cc5f..633ca77a26fd 100644
--- a/drivers/net/ethernet/sfc/rx_common.c
+++ b/drivers/net/ethernet/sfc/rx_common.c
@@ -45,6 +45,8 @@ static struct page *efx_reuse_page(struct efx_rx_queue *rx_queue)
 	unsigned int index;
 	struct page *page;
 
+	if (unlikely(!rx_queue->page_ring))
+		return NULL;
 	index = rx_queue->page_remove & rx_queue->page_ptr_mask;
 	page = rx_queue->page_ring[index];
 	if (page == NULL)
@@ -114,6 +116,9 @@ void efx_recycle_rx_pages(struct efx_channel *channel,
 {
 	struct efx_rx_queue *rx_queue = efx_channel_get_rx_queue(channel);
 
+	if (unlikely(!rx_queue->page_ring))
+		return;
+
 	do {
 		efx_recycle_rx_page(channel, rx_buf);
 		rx_buf = efx_rx_buf_next(rx_queue, rx_buf);
-- 
cgit v1.2.3