[PATCH AUTOSEL 6.3 06/22] bpf: tcp: Avoid taking fast sock lock in iterator

[PATCH AUTOSEL 6.3 06/22] bpf: tcp: Avoid taking fast sock lock in iterator

[Sasha Levin]

From: Aditi Ghag <aditi.ghag@isovalent.com>

[ Upstream commit 9378096e8a656fb5c4099b26b1370c56f056eab9 ]

This is a preparatory commit to replace `lock_sock_fast` with
`lock_sock`,and facilitate BPF programs executed from the TCP sockets
iterator to be able to destroy TCP sockets using the bpf_sock_destroy
kfunc (implemented in follow-up commits).

Previously, BPF TCP iterator was acquiring the sock lock with BH
disabled. This led to scenarios where the sockets hash table bucket lock
can be acquired with BH enabled in some path versus disabled in other.
In such situation, kernel issued a warning since it thinks that in the
BH enabled path the same bucket lock *might* be acquired again in the
softirq context (BH disabled), which will lead to a potential dead lock.
Since bpf_sock_destroy also happens in a process context, the potential
deadlock warning is likely a false alarm.

Here is a snippet of annotated stack trace that motivated this change:

```

Possible interrupt unsafe locking scenario:

      CPU0                    CPU1
      ----                    ----
 lock(&h->lhash2[i].lock);
                              local_bh_disable();
                              lock(&h->lhash2[i].lock);
kernel imagined possible scenario:
  local_bh_disable();  /* Possible softirq */
  lock(&h->lhash2[i].lock);
*** Potential Deadlock ***

process context:

lock_acquire+0xcd/0x330
_raw_spin_lock+0x33/0x40
------> Acquire (bucket) lhash2.lock with BH enabled
__inet_hash+0x4b/0x210
inet_csk_listen_start+0xe6/0x100
inet_listen+0x95/0x1d0
__sys_listen+0x69/0xb0
__x64_sys_listen+0x14/0x20
do_syscall_64+0x3c/0x90
entry_SYSCALL_64_after_hwframe+0x72/0xdc

bpf_sock_destroy run from iterator:

lock_acquire+0xcd/0x330
_raw_spin_lock+0x33/0x40
------> Acquire (bucket) lhash2.lock with BH disabled
inet_unhash+0x9a/0x110
tcp_set_state+0x6a/0x210
tcp_abort+0x10d/0x200
bpf_prog_6793c5ca50c43c0d_iter_tcp6_server+0xa4/0xa9
bpf_iter_run_prog+0x1ff/0x340
------> lock_sock_fast that acquires sock lock with BH disabled
bpf_iter_tcp_seq_show+0xca/0x190
bpf_seq_read+0x177/0x450

```

Also, Yonghong reported a deadlock for non-listening TCP sockets that
this change resolves. Previously, `lock_sock_fast` held the sock spin
lock with BH which was again being acquired in `tcp_abort`:

```
watchdog: BUG: soft lockup - CPU#0 stuck for 86s! [test_progs:2331]
RIP: 0010:queued_spin_lock_slowpath+0xd8/0x500
Call Trace:
 <TASK>
 _raw_spin_lock+0x84/0x90
 tcp_abort+0x13c/0x1f0
 bpf_prog_88539c5453a9dd47_iter_tcp6_client+0x82/0x89
 bpf_iter_run_prog+0x1aa/0x2c0
 ? preempt_count_sub+0x1c/0xd0
 ? from_kuid_munged+0x1c8/0x210
 bpf_iter_tcp_seq_show+0x14e/0x1b0
 bpf_seq_read+0x36c/0x6a0

bpf_iter_tcp_seq_show
   lock_sock_fast
     __lock_sock_fast
       spin_lock_bh(&sk->sk_lock.slock);
	/* * Fast path return with bottom halves disabled and * sock::sk_lock.slock held.* */

 ...
 tcp_abort
   local_bh_disable();
   spin_lock(&((sk)->sk_lock.slock)); // from bh_lock_sock(sk)

```

With the switch to `lock_sock`, it calls `spin_unlock_bh` before returning:

```
lock_sock
    lock_sock_nested
       spin_lock_bh(&sk->sk_lock.slock);
       :
       spin_unlock_bh(&sk->sk_lock.slock);
```

Acked-by: Yonghong Song <yhs@meta.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Aditi Ghag <aditi.ghag@isovalent.com>
Link: https://lore.kernel.org/r/20230519225157.760788-2-aditi.ghag@isovalent.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/ipv4/tcp_ipv4.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index c87958f979f0a..470c8427a48c2 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2963,7 +2963,6 @@ static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v)
 	struct bpf_iter_meta meta;
 	struct bpf_prog *prog;
 	struct sock *sk = v;
-	bool slow;
 	uid_t uid;
 	int ret;
 
@@ -2971,7 +2970,7 @@ static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v)
 		return 0;
 
 	if (sk_fullsock(sk))
-		slow = lock_sock_fast(sk);
+		lock_sock(sk);
 
 	if (unlikely(sk_unhashed(sk))) {
 		ret = SEQ_SKIP;
@@ -2995,7 +2994,7 @@ static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v)
 
 unlock:
 	if (sk_fullsock(sk))
-		unlock_sock_fast(sk, slow);
+		release_sock(sk);
 	return ret;
 
 }
-- 
2.39.2

[PATCH AUTOSEL 6.3 08/22] devlink: make health report on unregistered instance warn just once

[Sasha Levin]

From: Jakub Kicinski <kuba@kernel.org>

[ Upstream commit 6f4b98147b8dfcabacb19b5c6abd087af66d0049 ]

Devlink health is involved in error recovery. Machines in bad
state tend to be fairly unreliable, and occasionally get stuck
in error loops. Even with a reasonable grace period devlink health
may get a thousand reports in an hour.

In case of reporting on an unregistered devlink instance
the subsequent reports don't add much value. Switch to
WARN_ON_ONCE() to avoid flooding dmesg and fleet monitoring
dashboards.

Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230531015523.48961-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/devlink/health.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/devlink/health.c b/net/devlink/health.c
index 0839706d5741a..194340a8bb863 100644
--- a/net/devlink/health.c
+++ b/net/devlink/health.c
@@ -480,7 +480,7 @@ static void devlink_recover_notify(struct devlink_health_reporter *reporter,
 	int err;
 
 	WARN_ON(cmd != DEVLINK_CMD_HEALTH_REPORTER_RECOVER);
-	WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED));
+	ASSERT_DEVLINK_REGISTERED(devlink);
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
-- 
2.39.2

[PATCH AUTOSEL 6.3 15/22] net: ethernet: litex: add support for 64 bit stats

[Sasha Levin]

From: Jisheng Zhang <jszhang@kernel.org>

[ Upstream commit 18da174d865a87d47d2f33f5b0a322efcf067728 ]

Implement 64 bit per cpu stats to fix the overflow of netdev->stats
on 32 bit platforms. To simplify the code, we use net core
pcpu_sw_netstats infrastructure. One small drawback is some memory
overhead because litex uses just one queue, but we allocate the
counters per cpu.

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Acked-by: Gabriel Somlo <gsomlo@gmail.com>
Link: https://lore.kernel.org/r/20230614162035.300-1-jszhang@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/litex/litex_liteeth.c | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/litex/litex_liteeth.c b/drivers/net/ethernet/litex/litex_liteeth.c
index 35f24e0f09349..ffa96059079c6 100644
--- a/drivers/net/ethernet/litex/litex_liteeth.c
+++ b/drivers/net/ethernet/litex/litex_liteeth.c
@@ -78,8 +78,7 @@ static int liteeth_rx(struct net_device *netdev)
 	memcpy_fromio(data, priv->rx_base + rx_slot * priv->slot_size, len);
 	skb->protocol = eth_type_trans(skb, netdev);
 
-	netdev->stats.rx_packets++;
-	netdev->stats.rx_bytes += len;
+	dev_sw_netstats_rx_add(netdev, len);
 
 	return netif_rx(skb);
 
@@ -185,8 +184,7 @@ static netdev_tx_t liteeth_start_xmit(struct sk_buff *skb,
 	litex_write16(priv->base + LITEETH_READER_LENGTH, skb->len);
 	litex_write8(priv->base + LITEETH_READER_START, 1);
 
-	netdev->stats.tx_bytes += skb->len;
-	netdev->stats.tx_packets++;
+	dev_sw_netstats_tx_add(netdev, 1, skb->len);
 
 	priv->tx_slot = (priv->tx_slot + 1) % priv->num_tx_slots;
 	dev_kfree_skb_any(skb);
@@ -194,9 +192,17 @@ static netdev_tx_t liteeth_start_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 }
 
+static void
+liteeth_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats)
+{
+	netdev_stats_to_stats64(stats, &netdev->stats);
+	dev_fetch_sw_netstats(stats, netdev->tstats);
+}
+
 static const struct net_device_ops liteeth_netdev_ops = {
 	.ndo_open		= liteeth_open,
 	.ndo_stop		= liteeth_stop,
+	.ndo_get_stats64	= liteeth_get_stats64,
 	.ndo_start_xmit         = liteeth_start_xmit,
 };
 
@@ -242,6 +248,11 @@ static int liteeth_probe(struct platform_device *pdev)
 	priv->netdev = netdev;
 	priv->dev = &pdev->dev;
 
+	netdev->tstats = devm_netdev_alloc_pcpu_stats(&pdev->dev,
+						      struct pcpu_sw_netstats);
+	if (!netdev->tstats)
+		return -ENOMEM;
+
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
 		return irq;
-- 
2.39.2

[PATCH AUTOSEL 6.3 16/22] devlink: report devlink_port_type_warn source device

[Sasha Levin]

From: Petr Oros <poros@redhat.com>

[ Upstream commit a52305a81d6bb74b90b400dfa56455d37872fe4b ]

devlink_port_type_warn is scheduled for port devlink and warning
when the port type is not set. But from this warning it is not easy
found out which device (driver) has no devlink port set.

[ 3709.975552] Type was not set for devlink port.
[ 3709.975579] WARNING: CPU: 1 PID: 13092 at net/devlink/leftover.c:6775 devlink_port_type_warn+0x11/0x20
[ 3709.993967] Modules linked in: openvswitch nf_conncount nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nfnetlink bluetooth rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs vhost_net vhost vhost_iotlb tap tun bridge stp llc qrtr intel_rapl_msr intel_rapl_common i10nm_edac nfit libnvdimm x86_pkg_temp_thermal mlx5_ib intel_powerclamp coretemp dell_wmi ledtrig_audio sparse_keymap ipmi_ssif kvm_intel ib_uverbs rfkill ib_core video kvm iTCO_wdt acpi_ipmi intel_vsec irqbypass ipmi_si iTCO_vendor_support dcdbas ipmi_devintf mei_me ipmi_msghandler rapl mei intel_cstate isst_if_mmio isst_if_mbox_pci dell_smbios intel_uncore isst_if_common i2c_i801 dell_wmi_descriptor wmi_bmof i2c_smbus intel_pch_thermal pcspkr acpi_power_meter xfs libcrc32c sd_mod sg nvme_tcp mgag200 i2c_algo_bit nvme_fabrics drm_shmem_helper drm_kms_helper nvme syscopyarea ahci sysfillrect sysimgblt nvme_core fb_sys_fops crct10dif_pclmul libahci mlx5_core sfc crc32_pclmul nvme_common drm
[ 3709.994030]  crc32c_intel mtd t10_pi mlxfw libata tg3 mdio megaraid_sas psample ghash_clmulni_intel pci_hyperv_intf wmi dm_multipath sunrpc dm_mirror dm_region_hash dm_log dm_mod be2iscsi bnx2i cnic uio cxgb4i cxgb4 tls libcxgbi libcxgb qla4xxx iscsi_boot_sysfs iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi fuse
[ 3710.108431] CPU: 1 PID: 13092 Comm: kworker/1:1 Kdump: loaded Not tainted 5.14.0-319.el9.x86_64 #1
[ 3710.108435] Hardware name: Dell Inc. PowerEdge R750/0PJ80M, BIOS 1.8.2 09/14/2022
[ 3710.108437] Workqueue: events devlink_port_type_warn
[ 3710.108440] RIP: 0010:devlink_port_type_warn+0x11/0x20
[ 3710.108443] Code: 84 76 fe ff ff 48 c7 03 20 0e 1a ad 31 c0 e9 96 fd ff ff 66 0f 1f 44 00 00 0f 1f 44 00 00 48 c7 c7 18 24 4e ad e8 ef 71 62 ff <0f> 0b c3 cc cc cc cc 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 f6 87
[ 3710.108445] RSP: 0018:ff3b6d2e8b3c7e90 EFLAGS: 00010282
[ 3710.108447] RAX: 0000000000000000 RBX: ff366d6580127080 RCX: 0000000000000027
[ 3710.108448] RDX: 0000000000000027 RSI: 00000000ffff86de RDI: ff366d753f41f8c8
[ 3710.108449] RBP: ff366d658ff5a0c0 R08: ff366d753f41f8c0 R09: ff3b6d2e8b3c7e18
[ 3710.108450] R10: 0000000000000001 R11: 0000000000000023 R12: ff366d753f430600
[ 3710.108451] R13: ff366d753f436900 R14: 0000000000000000 R15: ff366d753f436905
[ 3710.108452] FS:  0000000000000000(0000) GS:ff366d753f400000(0000) knlGS:0000000000000000
[ 3710.108453] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 3710.108454] CR2: 00007f1c57bc74e0 CR3: 000000111d26a001 CR4: 0000000000773ee0
[ 3710.108456] PKRU: 55555554
[ 3710.108457] Call Trace:
[ 3710.108458]  <TASK>
[ 3710.108459]  process_one_work+0x1e2/0x3b0
[ 3710.108466]  ? rescuer_thread+0x390/0x390
[ 3710.108468]  worker_thread+0x50/0x3a0
[ 3710.108471]  ? rescuer_thread+0x390/0x390
[ 3710.108473]  kthread+0xdd/0x100
[ 3710.108477]  ? kthread_complete_and_exit+0x20/0x20
[ 3710.108479]  ret_from_fork+0x1f/0x30
[ 3710.108485]  </TASK>
[ 3710.108486] ---[ end trace 1b4b23cd0c65d6a0 ]---

After patch:
[  402.473064] ice 0000:41:00.0: Type was not set for devlink port.
[  402.473064] ice 0000:41:00.1: Type was not set for devlink port.

Signed-off-by: Petr Oros <poros@redhat.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230615095447.8259-1-poros@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/devlink/leftover.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index cd02549680767..790e61b2a9404 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -6772,7 +6772,10 @@ void devlink_notify_unregister(struct devlink *devlink)
 
 static void devlink_port_type_warn(struct work_struct *work)
 {
-	WARN(true, "Type was not set for devlink port.");
+	struct devlink_port *port = container_of(to_delayed_work(work),
+						 struct devlink_port,
+						 type_warn_dw);
+	dev_warn(port->devlink->dev, "Type was not set for devlink port.");
 }
 
 static bool devlink_port_type_should_warn(struct devlink_port *devlink_port)
-- 
2.39.2

[PATCH AUTOSEL 6.3 17/22] wifi: wext-core: Fix -Wstringop-overflow warning in ioctl_standard_iw_point()

[Sasha Levin]

From: "Gustavo A. R. Silva" <gustavoars@kernel.org>

[ Upstream commit 71e7552c90db2a2767f5c17c7ec72296b0d92061 ]

-Wstringop-overflow is legitimately warning us about extra_size
pontentially being zero at some point, hence potenially ending
up _allocating_ zero bytes of memory for extra pointer and then
trying to access such object in a call to copy_from_user().

Fix this by adding a sanity check to ensure we never end up
trying to allocate zero bytes of data for extra pointer, before
continue executing the rest of the code in the function.

Address the following -Wstringop-overflow warning seen when built
m68k architecture with allyesconfig configuration:
                 from net/wireless/wext-core.c:11:
In function '_copy_from_user',
    inlined from 'copy_from_user' at include/linux/uaccess.h:183:7,
    inlined from 'ioctl_standard_iw_point' at net/wireless/wext-core.c:825:7:
arch/m68k/include/asm/string.h:48:25: warning: '__builtin_memset' writing 1 or more bytes into a region of size 0 overflows the destination [-Wstringop-overflow=]
   48 | #define memset(d, c, n) __builtin_memset(d, c, n)
      |                         ^~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/uaccess.h:153:17: note: in expansion of macro 'memset'
  153 |                 memset(to + (n - res), 0, res);
      |                 ^~~~~~
In function 'kmalloc',
    inlined from 'kzalloc' at include/linux/slab.h:694:9,
    inlined from 'ioctl_standard_iw_point' at net/wireless/wext-core.c:819:10:
include/linux/slab.h:577:16: note: at offset 1 into destination object of size 0 allocated by '__kmalloc'
  577 |         return __kmalloc(size, flags);
      |                ^~~~~~~~~~~~~~~~~~~~~~

This help with the ongoing efforts to globally enable
-Wstringop-overflow.

Link: https://github.com/KSPP/linux/issues/315
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/ZItSlzvIpjdjNfd8@work
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/wireless/wext-core.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c
index a125fd1fa1342..a161c64d1765e 100644
--- a/net/wireless/wext-core.c
+++ b/net/wireless/wext-core.c
@@ -815,6 +815,12 @@ static int ioctl_standard_iw_point(struct iw_point *iwp, unsigned int cmd,
 		}
 	}
 
+	/* Sanity-check to ensure we never end up _allocating_ zero
+	 * bytes of data for extra.
+	 */
+	if (extra_size <= 0)
+		return -EFAULT;
+
 	/* kzalloc() ensures NULL-termination for essid_compat. */
 	extra = kzalloc(extra_size, GFP_KERNEL);
 	if (!extra)
-- 
2.39.2

[PATCH AUTOSEL 6.3 21/22] igb: Fix igb_down hung on surprise removal

[Sasha Levin]

From: Ying Hsu <yinghsu@chromium.org>

[ Upstream commit 004d25060c78fc31f66da0fa439c544dda1ac9d5 ]

In a setup where a Thunderbolt hub connects to Ethernet and a display
through USB Type-C, users may experience a hung task timeout when they
remove the cable between the PC and the Thunderbolt hub.
This is because the igb_down function is called multiple times when
the Thunderbolt hub is unplugged. For example, the igb_io_error_detected
triggers the first call, and the igb_remove triggers the second call.
The second call to igb_down will block at napi_synchronize.
Here's the call trace:
    __schedule+0x3b0/0xddb
    ? __mod_timer+0x164/0x5d3
    schedule+0x44/0xa8
    schedule_timeout+0xb2/0x2a4
    ? run_local_timers+0x4e/0x4e
    msleep+0x31/0x38
    igb_down+0x12c/0x22a [igb 6615058754948bfde0bf01429257eb59f13030d4]
    __igb_close+0x6f/0x9c [igb 6615058754948bfde0bf01429257eb59f13030d4]
    igb_close+0x23/0x2b [igb 6615058754948bfde0bf01429257eb59f13030d4]
    __dev_close_many+0x95/0xec
    dev_close_many+0x6e/0x103
    unregister_netdevice_many+0x105/0x5b1
    unregister_netdevice_queue+0xc2/0x10d
    unregister_netdev+0x1c/0x23
    igb_remove+0xa7/0x11c [igb 6615058754948bfde0bf01429257eb59f13030d4]
    pci_device_remove+0x3f/0x9c
    device_release_driver_internal+0xfe/0x1b4
    pci_stop_bus_device+0x5b/0x7f
    pci_stop_bus_device+0x30/0x7f
    pci_stop_bus_device+0x30/0x7f
    pci_stop_and_remove_bus_device+0x12/0x19
    pciehp_unconfigure_device+0x76/0xe9
    pciehp_disable_slot+0x6e/0x131
    pciehp_handle_presence_or_link_change+0x7a/0x3f7
    pciehp_ist+0xbe/0x194
    irq_thread_fn+0x22/0x4d
    ? irq_thread+0x1fd/0x1fd
    irq_thread+0x17b/0x1fd
    ? irq_forced_thread_fn+0x5f/0x5f
    kthread+0x142/0x153
    ? __irq_get_irqchip_state+0x46/0x46
    ? kthread_associate_blkcg+0x71/0x71
    ret_from_fork+0x1f/0x30

In this case, igb_io_error_detected detaches the network interface
and requests a PCIE slot reset, however, the PCIE reset callback is
not being invoked and thus the Ethernet connection breaks down.
As the PCIE error in this case is a non-fatal one, requesting a
slot reset can be avoided.
This patch fixes the task hung issue and preserves Ethernet
connection by ignoring non-fatal PCIE errors.

Signed-off-by: Ying Hsu <yinghsu@chromium.org>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/20230620174732.4145155-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index f2f9f81c123b8..c1891e03b8e91 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -9586,6 +9586,11 @@ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev,
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct igb_adapter *adapter = netdev_priv(netdev);
 
+	if (state == pci_channel_io_normal) {
+		dev_warn(&pdev->dev, "Non-correctable non-fatal error reported.\n");
+		return PCI_ERS_RESULT_CAN_RECOVER;
+	}
+
 	netif_device_detach(netdev);
 
 	if (state == pci_channel_io_perm_failure)
-- 
2.39.2

[PATCH AUTOSEL 6.3 22/22] net: hns3: fix strncpy() not using dest-buf length as length issue

[Sasha Levin]

From: Hao Chen <chenhao418@huawei.com>

[ Upstream commit 1cf3d5567f273a8746d1bade00633a93204f80f0 ]

Now, strncpy() in hns3_dbg_fill_content() use src-length as copy-length,
it may result in dest-buf overflow.

This patch is to fix intel compile warning for csky-linux-gcc (GCC) 12.1.0
compiler.

The warning reports as below:

hclge_debugfs.c:92:25: warning: 'strncpy' specified bound depends on
the length of the source argument [-Wstringop-truncation]

strncpy(pos, items[i].name, strlen(items[i].name));

hclge_debugfs.c:90:25: warning: 'strncpy' output truncated before
terminating nul copying as many bytes from a string as its length
[-Wstringop-truncation]

strncpy(pos, result[i], strlen(result[i]));

strncpy() use src-length as copy-length, it may result in
dest-buf overflow.

So,this patch add some values check to avoid this issue.

Signed-off-by: Hao Chen <chenhao418@huawei.com>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/lkml/202207170606.7WtHs9yS-lkp@intel.com/T/
Signed-off-by: Hao Lan <lanhao@huawei.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../ethernet/hisilicon/hns3/hns3_debugfs.c    | 31 ++++++++++++++-----
 .../hisilicon/hns3/hns3pf/hclge_debugfs.c     | 29 ++++++++++++++---
 2 files changed, 48 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index bcccd82a2620f..f6ededec5a4fa 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -435,19 +435,36 @@ static void hns3_dbg_fill_content(char *content, u16 len,
 				  const struct hns3_dbg_item *items,
 				  const char **result, u16 size)
 {
+#define HNS3_DBG_LINE_END_LEN	2
 	char *pos = content;
+	u16 item_len;
 	u16 i;
 
+	if (!len) {
+		return;
+	} else if (len <= HNS3_DBG_LINE_END_LEN) {
+		*pos++ = '\0';
+		return;
+	}
+
 	memset(content, ' ', len);
-	for (i = 0; i < size; i++) {
-		if (result)
-			strncpy(pos, result[i], strlen(result[i]));
-		else
-			strncpy(pos, items[i].name, strlen(items[i].name));
+	len -= HNS3_DBG_LINE_END_LEN;
 
-		pos += strlen(items[i].name) + items[i].interval;
+	for (i = 0; i < size; i++) {
+		item_len = strlen(items[i].name) + items[i].interval;
+		if (len < item_len)
+			break;
+
+		if (result) {
+			if (item_len < strlen(result[i]))
+				break;
+			strscpy(pos, result[i], strlen(result[i]));
+		} else {
+			strscpy(pos, items[i].name, strlen(items[i].name));
+		}
+		pos += item_len;
+		len -= item_len;
 	}
-
 	*pos++ = '\n';
 	*pos++ = '\0';
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index a0b46e7d863eb..233c132dc513e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -88,16 +88,35 @@ static void hclge_dbg_fill_content(char *content, u16 len,
 				   const struct hclge_dbg_item *items,
 				   const char **result, u16 size)
 {
+#define HCLGE_DBG_LINE_END_LEN	2
 	char *pos = content;
+	u16 item_len;
 	u16 i;
 
+	if (!len) {
+		return;
+	} else if (len <= HCLGE_DBG_LINE_END_LEN) {
+		*pos++ = '\0';
+		return;
+	}
+
 	memset(content, ' ', len);
+	len -= HCLGE_DBG_LINE_END_LEN;
+
 	for (i = 0; i < size; i++) {
-		if (result)
-			strncpy(pos, result[i], strlen(result[i]));
-		else
-			strncpy(pos, items[i].name, strlen(items[i].name));
-		pos += strlen(items[i].name) + items[i].interval;
+		item_len = strlen(items[i].name) + items[i].interval;
+		if (len < item_len)
+			break;
+
+		if (result) {
+			if (item_len < strlen(result[i]))
+				break;
+			strscpy(pos, result[i], strlen(result[i]));
+		} else {
+			strscpy(pos, items[i].name, strlen(items[i].name));
+		}
+		pos += item_len;
+		len -= item_len;
 	}
 	*pos++ = '\n';
 	*pos++ = '\0';
-- 
2.39.2