[PATCH AUTOSEL 6.9 05/35] devlink: use kvzalloc() to allocate devlink instance resources

[PATCH AUTOSEL 6.9 05/35] devlink: use kvzalloc() to allocate devlink instance resources

[Sasha Levin]

From: Jian Wen <wenjianhn@gmail.com>

[ Upstream commit 730fffce4fd2eb7a0be2d0b6cd7e55e9194d76d5 ]

During live migration of a virtual machine, the SR-IOV VF need to be
re-registered. It may fail when the memory is badly fragmented.

The related log is as follows.

    kernel: hv_netvsc 6045bdaa-c0d1-6045-bdaa-c0d16045bdaa eth0: VF slot 1 added
...
    kernel: kworker/0:0: page allocation failure: order:7, mode:0x40dc0(GFP_KERNEL|__GFP_COMP|__GFP_ZERO), nodemask=(null),cpuset=/,mems_allowed=0
    kernel: CPU: 0 PID: 24006 Comm: kworker/0:0 Tainted: G            E     5.4...x86_64 #1
    kernel: Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090008  12/07/2018
    kernel: Workqueue: events work_for_cpu_fn
    kernel: Call Trace:
    kernel: dump_stack+0x8b/0xc8
    kernel: warn_alloc+0xff/0x170
    kernel: __alloc_pages_slowpath+0x92c/0xb2b
    kernel: ? get_page_from_freelist+0x1d4/0x1140
    kernel: __alloc_pages_nodemask+0x2f9/0x320
    kernel: alloc_pages_current+0x6a/0xb0
    kernel: kmalloc_order+0x1e/0x70
    kernel: kmalloc_order_trace+0x26/0xb0
    kernel: ? __switch_to_asm+0x34/0x70
    kernel: __kmalloc+0x276/0x280
    kernel: ? _raw_spin_unlock_irqrestore+0x1e/0x40
    kernel: devlink_alloc+0x29/0x110
    kernel: mlx5_devlink_alloc+0x1a/0x20 [mlx5_core]
    kernel: init_one+0x1d/0x650 [mlx5_core]
    kernel: local_pci_probe+0x46/0x90
    kernel: work_for_cpu_fn+0x1a/0x30
    kernel: process_one_work+0x16d/0x390
    kernel: worker_thread+0x1d3/0x3f0
    kernel: kthread+0x105/0x140
    kernel: ? max_active_store+0x80/0x80
    kernel: ? kthread_bind+0x20/0x20
    kernel: ret_from_fork+0x3a/0x50

Signed-off-by: Jian Wen <wenjian1@xiaomi.com>
Link: https://lore.kernel.org/r/20240327082128.942818-1-wenjian1@xiaomi.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/devlink/core.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/devlink/core.c b/net/devlink/core.c
index 7f0b093208d75..f49cd83f1955f 100644
--- a/net/devlink/core.c
+++ b/net/devlink/core.c
@@ -314,7 +314,7 @@ static void devlink_release(struct work_struct *work)
 	mutex_destroy(&devlink->lock);
 	lockdep_unregister_key(&devlink->lock_key);
 	put_device(devlink->dev);
-	kfree(devlink);
+	kvfree(devlink);
 }
 
 void devlink_put(struct devlink *devlink)
@@ -420,7 +420,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops,
 	if (!devlink_reload_actions_valid(ops))
 		return NULL;
 
-	devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL);
+	devlink = kvzalloc(struct_size(devlink, priv, priv_size), GFP_KERNEL);
 	if (!devlink)
 		return NULL;
 
@@ -455,7 +455,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops,
 	return devlink;
 
 err_xa_alloc:
-	kfree(devlink);
+	kvfree(devlink);
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(devlink_alloc_ns);
-- 
2.43.0

[PATCH AUTOSEL 6.9 06/35] batman-adv: bypass empty buckets in batadv_purge_orig_ref()

[Sasha Levin]

From: Eric Dumazet <edumazet@google.com>

[ Upstream commit 40dc8ab605894acae1473e434944924a22cfaaa0 ]

Many syzbot reports are pointing to soft lockups in
batadv_purge_orig_ref() [1]

Root cause is unknown, but we can avoid spending too much
time there and perhaps get more interesting reports.

[1]

watchdog: BUG: soft lockup - CPU#0 stuck for 27s! [kworker/u4:6:621]
Modules linked in:
irq event stamp: 6182794
 hardirqs last  enabled at (6182793): [<ffff8000801dae10>] __local_bh_enable_ip+0x224/0x44c kernel/softirq.c:386
 hardirqs last disabled at (6182794): [<ffff80008ad66a78>] __el1_irq arch/arm64/kernel/entry-common.c:533 [inline]
 hardirqs last disabled at (6182794): [<ffff80008ad66a78>] el1_interrupt+0x24/0x68 arch/arm64/kernel/entry-common.c:551
 softirqs last  enabled at (6182792): [<ffff80008aab71c4>] spin_unlock_bh include/linux/spinlock.h:396 [inline]
 softirqs last  enabled at (6182792): [<ffff80008aab71c4>] batadv_purge_orig_ref+0x114c/0x1228 net/batman-adv/originator.c:1287
 softirqs last disabled at (6182790): [<ffff80008aab61dc>] spin_lock_bh include/linux/spinlock.h:356 [inline]
 softirqs last disabled at (6182790): [<ffff80008aab61dc>] batadv_purge_orig_ref+0x164/0x1228 net/batman-adv/originator.c:1271
CPU: 0 PID: 621 Comm: kworker/u4:6 Not tainted 6.8.0-rc7-syzkaller-g707081b61156 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/29/2024
Workqueue: bat_events batadv_purge_orig
pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : should_resched arch/arm64/include/asm/preempt.h:79 [inline]
 pc : __local_bh_enable_ip+0x228/0x44c kernel/softirq.c:388
 lr : __local_bh_enable_ip+0x224/0x44c kernel/softirq.c:386
sp : ffff800099007970
x29: ffff800099007980 x28: 1fffe00018fce1bd x27: dfff800000000000
x26: ffff0000d2620008 x25: ffff0000c7e70de8 x24: 0000000000000001
x23: 1fffe00018e57781 x22: dfff800000000000 x21: ffff80008aab71c4
x20: ffff0001b40136c0 x19: ffff0000c72bbc08 x18: 1fffe0001a817bb0
x17: ffff800125414000 x16: ffff80008032116c x15: 0000000000000001
x14: 1fffe0001ee9d610 x13: 0000000000000000 x12: 0000000000000003
x11: 0000000000000000 x10: 0000000000ff0100 x9 : 0000000000000000
x8 : 00000000005e5789 x7 : ffff80008aab61dc x6 : 0000000000000000
x5 : 0000000000000000 x4 : 0000000000000001 x3 : 0000000000000000
x2 : 0000000000000006 x1 : 0000000000000080 x0 : ffff800125414000
Call trace:
  __daif_local_irq_enable arch/arm64/include/asm/irqflags.h:27 [inline]
  arch_local_irq_enable arch/arm64/include/asm/irqflags.h:49 [inline]
  __local_bh_enable_ip+0x228/0x44c kernel/softirq.c:386
  __raw_spin_unlock_bh include/linux/spinlock_api_smp.h:167 [inline]
  _raw_spin_unlock_bh+0x3c/0x4c kernel/locking/spinlock.c:210
  spin_unlock_bh include/linux/spinlock.h:396 [inline]
  batadv_purge_orig_ref+0x114c/0x1228 net/batman-adv/originator.c:1287
  batadv_purge_orig+0x20/0x70 net/batman-adv/originator.c:1300
  process_one_work+0x694/0x1204 kernel/workqueue.c:2633
  process_scheduled_works kernel/workqueue.c:2706 [inline]
  worker_thread+0x938/0xef4 kernel/workqueue.c:2787
  kthread+0x288/0x310 kernel/kthread.c:388
  ret_from_fork+0x10/0x20 arch/arm64/kernel/entry.S:860
Sending NMI from CPU 0 to CPUs 1:
NMI backtrace for cpu 1
CPU: 1 PID: 0 Comm: swapper/1 Not tainted 6.8.0-rc7-syzkaller-g707081b61156 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/29/2024
pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : arch_local_irq_enable+0x8/0xc arch/arm64/include/asm/irqflags.h:51
 lr : default_idle_call+0xf8/0x128 kernel/sched/idle.c:103
sp : ffff800093a17d30
x29: ffff800093a17d30 x28: dfff800000000000 x27: 1ffff00012742fb4
x26: ffff80008ec9d000 x25: 0000000000000000 x24: 0000000000000002
x23: 1ffff00011d93a74 x22: ffff80008ec9d3a0 x21: 0000000000000000
x20: ffff0000c19dbc00 x19: ffff8000802d0fd8 x18: 1fffe00036804396
x17: ffff80008ec9d000 x16: ffff8000802d089c x15: 0000000000000001
x14: 1fffe00036805f10 x13: 0000000000000000 x12: 0000000000000003
x11: 0000000000000001 x10: 0000000000000003 x9 : 0000000000000000
x8 : 00000000000ce8d1 x7 : ffff8000804609e4 x6 : 0000000000000000
x5 : 0000000000000001 x4 : 0000000000000001 x3 : ffff80008ad6aac0
x2 : 0000000000000000 x1 : ffff80008aedea60 x0 : ffff800125436000
Call trace:
  __daif_local_irq_enable arch/arm64/include/asm/irqflags.h:27 [inline]
  arch_local_irq_enable+0x8/0xc arch/arm64/include/asm/irqflags.h:49
  cpuidle_idle_call kernel/sched/idle.c:170 [inline]
  do_idle+0x1f0/0x4e8 kernel/sched/idle.c:312
  cpu_startup_entry+0x5c/0x74 kernel/sched/idle.c:410
  secondary_start_kernel+0x198/0x1c0 arch/arm64/kernel/smp.c:272
  __secondary_switched+0xb8/0xbc arch/arm64/kernel/head.S:404

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/batman-adv/originator.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 71c143d4b6d05..ac74f6ead62d5 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -1266,6 +1266,8 @@ void batadv_purge_orig_ref(struct batadv_priv *bat_priv)
 	/* for all origins... */
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
+		if (hlist_empty(head))
+			continue;
 		list_lock = &hash->list_locks[i];
 
 		spin_lock_bh(list_lock);
-- 
2.43.0

[PATCH AUTOSEL 6.9 09/35] af_packet: avoid a false positive warning in packet_setsockopt()

[Sasha Levin]

From: Eric Dumazet <edumazet@google.com>

[ Upstream commit 86d43e2bf93ccac88ef71cee36a23282ebd9e427 ]

Although the code is correct, the following line

	copy_from_sockptr(&req_u.req, optval, len));

triggers this warning :

memcpy: detected field-spanning write (size 28) of single field "dst" at include/linux/sockptr.h:49 (size 16)

Refactor the code to be more explicit.

Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/packet/af_packet.c | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 18f616f487eaa..8c6d3fbb4ed87 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3800,28 +3800,30 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval,
 	case PACKET_TX_RING:
 	{
 		union tpacket_req_u req_u;
-		int len;
 
+		ret = -EINVAL;
 		lock_sock(sk);
 		switch (po->tp_version) {
 		case TPACKET_V1:
 		case TPACKET_V2:
-			len = sizeof(req_u.req);
+			if (optlen < sizeof(req_u.req))
+				break;
+			ret = copy_from_sockptr(&req_u.req, optval,
+						sizeof(req_u.req)) ?
+						-EINVAL : 0;
 			break;
 		case TPACKET_V3:
 		default:
-			len = sizeof(req_u.req3);
+			if (optlen < sizeof(req_u.req3))
+				break;
+			ret = copy_from_sockptr(&req_u.req3, optval,
+						sizeof(req_u.req3)) ?
+						-EINVAL : 0;
 			break;
 		}
-		if (optlen < len) {
-			ret = -EINVAL;
-		} else {
-			if (copy_from_sockptr(&req_u.req, optval, len))
-				ret = -EFAULT;
-			else
-				ret = packet_set_ring(sk, &req_u, 0,
-						    optname == PACKET_TX_RING);
-		}
+		if (!ret)
+			ret = packet_set_ring(sk, &req_u, 0,
+					      optname == PACKET_TX_RING);
 		release_sock(sk);
 		return ret;
 	}
-- 
2.43.0

[PATCH AUTOSEL 6.9 12/35] net: sfp: add quirk for another multigig RollBall transceiver

[Sasha Levin]

From: Marek Behún <kabel@kernel.org>

[ Upstream commit 1c77c721916ae108c2c5865986735bfe92000908 ]

Add quirk for another RollBall copper transceiver: Turris RTSFP-2.5G,
containing 2.5g capable RTL8221B PHY.

Signed-off-by: Marek Behún <kabel@kernel.org>
Signed-off-by: Eric Woudstra <ericwouds@gmail.com>

Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/phy/sfp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index f75c9eb3958ef..6e7639fc64ddc 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -506,6 +506,7 @@ static const struct sfp_quirk sfp_quirks[] = {
 	SFP_QUIRK_M("OEM", "SFP-2.5G-T", sfp_quirk_oem_2_5g),
 	SFP_QUIRK_F("OEM", "RTSFP-10", sfp_fixup_rollball_cc),
 	SFP_QUIRK_F("OEM", "RTSFP-10G", sfp_fixup_rollball_cc),
+	SFP_QUIRK_F("Turris", "RTSFP-2.5G", sfp_fixup_rollball),
 	SFP_QUIRK_F("Turris", "RTSFP-10", sfp_fixup_rollball),
 	SFP_QUIRK_F("Turris", "RTSFP-10G", sfp_fixup_rollball),
 };
-- 
2.43.0

Re: [PATCH AUTOSEL 6.9 12/35] net: sfp: add quirk for another multigig RollBall transceiver

[Marek Behún]

Sasha,

This requires the whole series from which it came:

  https://lore.kernel.org/netdev/20240409073016.367771-1-ericwouds@gmail.com/

It was merged in
  https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=c31bd5b6ff6f70f016e66c0617e0b91fd7aafca4

I don't think this can be easily applied to older kernels, the series
has some dependencies.

Marek

On Mon, 27 May 2024 10:11:17 -0400
Sasha Levin <sashal@kernel.org> wrote:

> From: Marek Behún <kabel@kernel.org>
> 
> [ Upstream commit 1c77c721916ae108c2c5865986735bfe92000908 ]
> 
> Add quirk for another RollBall copper transceiver: Turris RTSFP-2.5G,
> containing 2.5g capable RTL8221B PHY.
> 
> Signed-off-by: Marek Behún <kabel@kernel.org>
> Signed-off-by: Eric Woudstra <ericwouds@gmail.com>
> 
> Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
> Signed-off-by: David S. Miller <davem@davemloft.net>
> Signed-off-by: Sasha Levin <sashal@kernel.org>
> ---
>  drivers/net/phy/sfp.c | 1 +
>  1 file changed, 1 insertion(+)
> 
> diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
> index f75c9eb3958ef..6e7639fc64ddc 100644
> --- a/drivers/net/phy/sfp.c
> +++ b/drivers/net/phy/sfp.c
> @@ -506,6 +506,7 @@ static const struct sfp_quirk sfp_quirks[] = {
>  	SFP_QUIRK_M("OEM", "SFP-2.5G-T", sfp_quirk_oem_2_5g),
>  	SFP_QUIRK_F("OEM", "RTSFP-10", sfp_fixup_rollball_cc),
>  	SFP_QUIRK_F("OEM", "RTSFP-10G", sfp_fixup_rollball_cc),
> +	SFP_QUIRK_F("Turris", "RTSFP-2.5G", sfp_fixup_rollball),
>  	SFP_QUIRK_F("Turris", "RTSFP-10", sfp_fixup_rollball),
>  	SFP_QUIRK_F("Turris", "RTSFP-10G", sfp_fixup_rollball),
>  };

Re: [PATCH AUTOSEL 6.9 12/35] net: sfp: add quirk for another multigig RollBall transceiver

[Sasha Levin]

On Mon, May 27, 2024 at 04:54:41PM +0200, Marek Behún wrote:
>Sasha,
>
>This requires the whole series from which it came:
>
>  https://lore.kernel.org/netdev/20240409073016.367771-1-ericwouds@gmail.com/
>
>It was merged in
>  https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=c31bd5b6ff6f70f016e66c0617e0b91fd7aafca4
>
>I don't think this can be easily applied to older kernels, the series
>has some dependencies.

I'll drop it, thanks!

-- 
Thanks,
Sasha

[PATCH AUTOSEL 6.9 13/35] drop_monitor: replace spin_lock by raw_spin_lock

[Sasha Levin]

From: Wander Lairson Costa <wander@redhat.com>

[ Upstream commit f1e197a665c2148ebc25fe09c53689e60afea195 ]

trace_drop_common() is called with preemption disabled, and it acquires
a spin_lock. This is problematic for RT kernels because spin_locks are
sleeping locks in this configuration, which causes the following splat:

BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:48
in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 449, name: rcuc/47
preempt_count: 1, expected: 0
RCU nest depth: 2, expected: 2
5 locks held by rcuc/47/449:
 #0: ff1100086ec30a60 ((softirq_ctrl.lock)){+.+.}-{2:2}, at: __local_bh_disable_ip+0x105/0x210
 #1: ffffffffb394a280 (rcu_read_lock){....}-{1:2}, at: rt_spin_lock+0xbf/0x130
 #2: ffffffffb394a280 (rcu_read_lock){....}-{1:2}, at: __local_bh_disable_ip+0x11c/0x210
 #3: ffffffffb394a160 (rcu_callback){....}-{0:0}, at: rcu_do_batch+0x360/0xc70
 #4: ff1100086ee07520 (&data->lock){+.+.}-{2:2}, at: trace_drop_common.constprop.0+0xb5/0x290
irq event stamp: 139909
hardirqs last  enabled at (139908): [<ffffffffb1df2b33>] _raw_spin_unlock_irqrestore+0x63/0x80
hardirqs last disabled at (139909): [<ffffffffb19bd03d>] trace_drop_common.constprop.0+0x26d/0x290
softirqs last  enabled at (139892): [<ffffffffb07a1083>] __local_bh_enable_ip+0x103/0x170
softirqs last disabled at (139898): [<ffffffffb0909b33>] rcu_cpu_kthread+0x93/0x1f0
Preemption disabled at:
[<ffffffffb1de786b>] rt_mutex_slowunlock+0xab/0x2e0
CPU: 47 PID: 449 Comm: rcuc/47 Not tainted 6.9.0-rc2-rt1+ #7
Hardware name: Dell Inc. PowerEdge R650/0Y2G81, BIOS 1.6.5 04/15/2022
Call Trace:
 <TASK>
 dump_stack_lvl+0x8c/0xd0
 dump_stack+0x14/0x20
 __might_resched+0x21e/0x2f0
 rt_spin_lock+0x5e/0x130
 ? trace_drop_common.constprop.0+0xb5/0x290
 ? skb_queue_purge_reason.part.0+0x1bf/0x230
 trace_drop_common.constprop.0+0xb5/0x290
 ? preempt_count_sub+0x1c/0xd0
 ? _raw_spin_unlock_irqrestore+0x4a/0x80
 ? __pfx_trace_drop_common.constprop.0+0x10/0x10
 ? rt_mutex_slowunlock+0x26a/0x2e0
 ? skb_queue_purge_reason.part.0+0x1bf/0x230
 ? __pfx_rt_mutex_slowunlock+0x10/0x10
 ? skb_queue_purge_reason.part.0+0x1bf/0x230
 trace_kfree_skb_hit+0x15/0x20
 trace_kfree_skb+0xe9/0x150
 kfree_skb_reason+0x7b/0x110
 skb_queue_purge_reason.part.0+0x1bf/0x230
 ? __pfx_skb_queue_purge_reason.part.0+0x10/0x10
 ? mark_lock.part.0+0x8a/0x520
...

trace_drop_common() also disables interrupts, but this is a minor issue
because we could easily replace it with a local_lock.

Replace the spin_lock with raw_spin_lock to avoid sleeping in atomic
context.

Signed-off-by: Wander Lairson Costa <wander@redhat.com>
Reported-by: Hu Chunyu <chuhu@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/core/drop_monitor.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index b0f221d658be8..430ed18f8584c 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -74,7 +74,7 @@ struct net_dm_hw_entries {
 };
 
 struct per_cpu_dm_data {
-	spinlock_t		lock;	/* Protects 'skb', 'hw_entries' and
+	raw_spinlock_t		lock;	/* Protects 'skb', 'hw_entries' and
 					 * 'send_timer'
 					 */
 	union {
@@ -168,9 +168,9 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data)
 err:
 	mod_timer(&data->send_timer, jiffies + HZ / 10);
 out:
-	spin_lock_irqsave(&data->lock, flags);
+	raw_spin_lock_irqsave(&data->lock, flags);
 	swap(data->skb, skb);
-	spin_unlock_irqrestore(&data->lock, flags);
+	raw_spin_unlock_irqrestore(&data->lock, flags);
 
 	if (skb) {
 		struct nlmsghdr *nlh = (struct nlmsghdr *)skb->data;
@@ -225,7 +225,7 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
 
 	local_irq_save(flags);
 	data = this_cpu_ptr(&dm_cpu_data);
-	spin_lock(&data->lock);
+	raw_spin_lock(&data->lock);
 	dskb = data->skb;
 
 	if (!dskb)
@@ -259,7 +259,7 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
 	}
 
 out:
-	spin_unlock_irqrestore(&data->lock, flags);
+	raw_spin_unlock_irqrestore(&data->lock, flags);
 }
 
 static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb,
@@ -314,9 +314,9 @@ net_dm_hw_reset_per_cpu_data(struct per_cpu_dm_data *hw_data)
 		mod_timer(&hw_data->send_timer, jiffies + HZ / 10);
 	}
 
-	spin_lock_irqsave(&hw_data->lock, flags);
+	raw_spin_lock_irqsave(&hw_data->lock, flags);
 	swap(hw_data->hw_entries, hw_entries);
-	spin_unlock_irqrestore(&hw_data->lock, flags);
+	raw_spin_unlock_irqrestore(&hw_data->lock, flags);
 
 	return hw_entries;
 }
@@ -448,7 +448,7 @@ net_dm_hw_trap_summary_probe(void *ignore, const struct devlink *devlink,
 		return;
 
 	hw_data = this_cpu_ptr(&dm_hw_cpu_data);
-	spin_lock_irqsave(&hw_data->lock, flags);
+	raw_spin_lock_irqsave(&hw_data->lock, flags);
 	hw_entries = hw_data->hw_entries;
 
 	if (!hw_entries)
@@ -477,7 +477,7 @@ net_dm_hw_trap_summary_probe(void *ignore, const struct devlink *devlink,
 	}
 
 out:
-	spin_unlock_irqrestore(&hw_data->lock, flags);
+	raw_spin_unlock_irqrestore(&hw_data->lock, flags);
 }
 
 static const struct net_dm_alert_ops net_dm_alert_summary_ops = {
@@ -1673,7 +1673,7 @@ static struct notifier_block dropmon_net_notifier = {
 
 static void __net_dm_cpu_data_init(struct per_cpu_dm_data *data)
 {
-	spin_lock_init(&data->lock);
+	raw_spin_lock_init(&data->lock);
 	skb_queue_head_init(&data->drop_queue);
 	u64_stats_init(&data->stats.syncp);
 }
-- 
2.43.0

[PATCH AUTOSEL 6.9 17/35] net: sfp: enhance quirk for Fibrestore 2.5G copper SFP module

[Sasha Levin]

From: Marek Behún <kabel@kernel.org>

[ Upstream commit cd4a32e60061789676f7f018a94fcc9ec56732a0 ]

Enhance the quirk for Fibrestore 2.5G copper SFP module. The original
commit e27aca3760c0 ("net: sfp: add quirk for FS's 2.5G copper SFP")
introducing the quirk says that the PHY is inaccessible, but that is
not true.

The module uses Rollball protocol to talk to the PHY, and needs a 4
second wait before probing it, same as FS 10G module.

The PHY inside the module is Realtek RTL8221B-VB-CG PHY. The realtek
driver recently gained support to set it up via clause 45 accesses.

Signed-off-by: Marek Behún <kabel@kernel.org>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20240423085039.26957-2-kabel@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/phy/sfp.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 6e7639fc64ddc..44c47d34a5c68 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -385,18 +385,23 @@ static void sfp_fixup_rollball(struct sfp *sfp)
 	sfp->phy_t_retry = msecs_to_jiffies(1000);
 }
 
-static void sfp_fixup_fs_10gt(struct sfp *sfp)
+static void sfp_fixup_fs_2_5gt(struct sfp *sfp)
 {
-	sfp_fixup_10gbaset_30m(sfp);
 	sfp_fixup_rollball(sfp);
 
-	/* The RollBall fixup is not enough for FS modules, the AQR chip inside
+	/* The RollBall fixup is not enough for FS modules, the PHY chip inside
 	 * them does not return 0xffff for PHY ID registers in all MMDs for the
 	 * while initializing. They need a 4 second wait before accessing PHY.
 	 */
 	sfp->module_t_wait = msecs_to_jiffies(4000);
 }
 
+static void sfp_fixup_fs_10gt(struct sfp *sfp)
+{
+	sfp_fixup_10gbaset_30m(sfp);
+	sfp_fixup_fs_2_5gt(sfp);
+}
+
 static void sfp_fixup_halny_gsfp(struct sfp *sfp)
 {
 	/* Ignore the TX_FAULT and LOS signals on this module.
@@ -472,6 +477,10 @@ static const struct sfp_quirk sfp_quirks[] = {
 	// Rollball protocol to talk to the PHY.
 	SFP_QUIRK_F("FS", "SFP-10G-T", sfp_fixup_fs_10gt),
 
+	// Fiberstore SFP-2.5G-T uses Rollball protocol to talk to the PHY and
+	// needs 4 sec wait before probing the PHY.
+	SFP_QUIRK_F("FS", "SFP-2.5G-T", sfp_fixup_fs_2_5gt),
+
 	// Fiberstore GPON-ONU-34-20BI can operate at 2500base-X, but report 1.2GBd
 	// NRZ in their EEPROM
 	SFP_QUIRK("FS", "GPON-ONU-34-20BI", sfp_quirk_2500basex,
@@ -488,9 +497,6 @@ static const struct sfp_quirk sfp_quirks[] = {
 	SFP_QUIRK("HUAWEI", "MA5671A", sfp_quirk_2500basex,
 		  sfp_fixup_ignore_tx_fault),
 
-	// FS 2.5G Base-T
-	SFP_QUIRK_M("FS", "SFP-2.5G-T", sfp_quirk_oem_2_5g),
-
 	// Lantech 8330-262D-E can operate at 2500base-X, but incorrectly report
 	// 2500MBd NRZ in their EEPROM
 	SFP_QUIRK_M("Lantech", "8330-262D-E", sfp_quirk_2500basex),
-- 
2.43.0

[PATCH AUTOSEL 6.9 18/35] net: sfp: add quirk for ATS SFP-GE-T 1000Base-TX module

[Sasha Levin]

From: Daniel Golle <daniel@makrotopia.org>

[ Upstream commit 0805d67bc0ef95411228e802f31975cfb7555056 ]

Add quirk for ATS SFP-GE-T 1000Base-TX module.

This copper module comes with broken TX_FAULT indicator which must be
ignored for it to work.

Co-authored-by: Josef Schlehofer <pepe.schlehofer@gmail.com>
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
[ rebased on top of net-next ]
Signed-off-by: Marek Behún <kabel@kernel.org>
Link: https://lore.kernel.org/r/20240423090025.29231-1-kabel@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/phy/sfp.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 44c47d34a5c68..8b316baf6305e 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -508,6 +508,9 @@ static const struct sfp_quirk sfp_quirks[] = {
 	SFP_QUIRK_F("Walsun", "HXSX-ATRC-1", sfp_fixup_fs_10gt),
 	SFP_QUIRK_F("Walsun", "HXSX-ATRI-1", sfp_fixup_fs_10gt),
 
+	// OEM SFP-GE-T is a 1000Base-T module with broken TX_FAULT indicator
+	SFP_QUIRK_F("OEM", "SFP-GE-T", sfp_fixup_ignore_tx_fault),
+
 	SFP_QUIRK_F("OEM", "SFP-10G-T", sfp_fixup_rollball_cc),
 	SFP_QUIRK_M("OEM", "SFP-2.5G-T", sfp_quirk_oem_2_5g),
 	SFP_QUIRK_F("OEM", "RTSFP-10", sfp_fixup_rollball_cc),
-- 
2.43.0

[PATCH AUTOSEL 6.9 19/35] net/sched: fix false lockdep warning on qdisc root lock

[Sasha Levin]

From: Davide Caratti <dcaratti@redhat.com>

[ Upstream commit af0cb3fa3f9ed258d14abab0152e28a0f9593084 ]

Xiumei and Christoph reported the following lockdep splat, complaining of
the qdisc root lock being taken twice:

 ============================================
 WARNING: possible recursive locking detected
 6.7.0-rc3+ #598 Not tainted
 --------------------------------------------
 swapper/2/0 is trying to acquire lock:
 ffff888177190110 (&sch->q.lock){+.-.}-{2:2}, at: __dev_queue_xmit+0x1560/0x2e70

 but task is already holding lock:
 ffff88811995a110 (&sch->q.lock){+.-.}-{2:2}, at: __dev_queue_xmit+0x1560/0x2e70

 other info that might help us debug this:
  Possible unsafe locking scenario:

        CPU0
        ----
   lock(&sch->q.lock);
   lock(&sch->q.lock);

  *** DEADLOCK ***

  May be due to missing lock nesting notation

 5 locks held by swapper/2/0:
  #0: ffff888135a09d98 ((&in_dev->mr_ifc_timer)){+.-.}-{0:0}, at: call_timer_fn+0x11a/0x510
  #1: ffffffffaaee5260 (rcu_read_lock){....}-{1:2}, at: ip_finish_output2+0x2c0/0x1ed0
  #2: ffffffffaaee5200 (rcu_read_lock_bh){....}-{1:2}, at: __dev_queue_xmit+0x209/0x2e70
  #3: ffff88811995a110 (&sch->q.lock){+.-.}-{2:2}, at: __dev_queue_xmit+0x1560/0x2e70
  #4: ffffffffaaee5200 (rcu_read_lock_bh){....}-{1:2}, at: __dev_queue_xmit+0x209/0x2e70

 stack backtrace:
 CPU: 2 PID: 0 Comm: swapper/2 Not tainted 6.7.0-rc3+ #598
 Hardware name: Red Hat KVM, BIOS 1.13.0-2.module+el8.3.0+7353+9de0a3cc 04/01/2014
 Call Trace:
  <IRQ>
  dump_stack_lvl+0x4a/0x80
  __lock_acquire+0xfdd/0x3150
  lock_acquire+0x1ca/0x540
  _raw_spin_lock+0x34/0x80
  __dev_queue_xmit+0x1560/0x2e70
  tcf_mirred_act+0x82e/0x1260 [act_mirred]
  tcf_action_exec+0x161/0x480
  tcf_classify+0x689/0x1170
  prio_enqueue+0x316/0x660 [sch_prio]
  dev_qdisc_enqueue+0x46/0x220
  __dev_queue_xmit+0x1615/0x2e70
  ip_finish_output2+0x1218/0x1ed0
  __ip_finish_output+0x8b3/0x1350
  ip_output+0x163/0x4e0
  igmp_ifc_timer_expire+0x44b/0x930
  call_timer_fn+0x1a2/0x510
  run_timer_softirq+0x54d/0x11a0
  __do_softirq+0x1b3/0x88f
  irq_exit_rcu+0x18f/0x1e0
  sysvec_apic_timer_interrupt+0x6f/0x90
  </IRQ>

This happens when TC does a mirred egress redirect from the root qdisc of
device A to the root qdisc of device B. As long as these two locks aren't
protecting the same qdisc, they can be acquired in chain: add a per-qdisc
lockdep key to silence false warnings.
This dynamic key should safely replace the static key we have in sch_htb:
it was added to allow enqueueing to the device "direct qdisc" while still
holding the qdisc root lock.

v2: don't use static keys anymore in HTB direct qdiscs (thanks Eric Dumazet)

CC: Maxim Mikityanskiy <maxim@isovalent.com>
CC: Xiumei Mu <xmu@redhat.com>
Reported-by: Christoph Paasch <cpaasch@apple.com>
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/451
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Link: https://lore.kernel.org/r/7dc06d6158f72053cf877a82e2a7a5bd23692faa.1713448007.git.dcaratti@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/net/sch_generic.h |  1 +
 net/sched/sch_generic.c   |  3 +++
 net/sched/sch_htb.c       | 22 +++-------------------
 3 files changed, 7 insertions(+), 19 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 41ca14e81d55f..0014b9ee5e381 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -128,6 +128,7 @@ struct Qdisc {
 
 	struct rcu_head		rcu;
 	netdevice_tracker	dev_tracker;
+	struct lock_class_key	root_lock_key;
 	/* private data */
 	long privdata[] ____cacheline_aligned;
 };
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 4a2c763e2d116..31dfd6c7405b0 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -945,7 +945,9 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	__skb_queue_head_init(&sch->gso_skb);
 	__skb_queue_head_init(&sch->skb_bad_txq);
 	gnet_stats_basic_sync_init(&sch->bstats);
+	lockdep_register_key(&sch->root_lock_key);
 	spin_lock_init(&sch->q.lock);
+	lockdep_set_class(&sch->q.lock, &sch->root_lock_key);
 
 	if (ops->static_flags & TCQ_F_CPUSTATS) {
 		sch->cpu_bstats =
@@ -1068,6 +1070,7 @@ static void __qdisc_destroy(struct Qdisc *qdisc)
 	if (ops->destroy)
 		ops->destroy(qdisc);
 
+	lockdep_unregister_key(&qdisc->root_lock_key);
 	module_put(ops->owner);
 	netdev_put(dev, &qdisc->dev_tracker);
 
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 93e6fb56f3b58..ff3de37874e4b 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1039,13 +1039,6 @@ static void htb_work_func(struct work_struct *work)
 	rcu_read_unlock();
 }
 
-static void htb_set_lockdep_class_child(struct Qdisc *q)
-{
-	static struct lock_class_key child_key;
-
-	lockdep_set_class(qdisc_lock(q), &child_key);
-}
-
 static int htb_offload(struct net_device *dev, struct tc_htb_qopt_offload *opt)
 {
 	return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_HTB, opt);
@@ -1132,7 +1125,6 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt,
 			return -ENOMEM;
 		}
 
-		htb_set_lockdep_class_child(qdisc);
 		q->direct_qdiscs[ntx] = qdisc;
 		qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	}
@@ -1468,7 +1460,6 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	}
 
 	if (q->offload) {
-		htb_set_lockdep_class_child(new);
 		/* One ref for cl->leaf.q, the other for dev_queue->qdisc. */
 		qdisc_refcount_inc(new);
 		old_q = htb_graft_helper(dev_queue, new);
@@ -1733,11 +1724,8 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg,
 		new_q = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops,
 					  cl->parent->common.classid,
 					  NULL);
-		if (q->offload) {
-			if (new_q)
-				htb_set_lockdep_class_child(new_q);
+		if (q->offload)
 			htb_parent_to_leaf_offload(sch, dev_queue, new_q);
-		}
 	}
 
 	sch_tree_lock(sch);
@@ -1947,13 +1935,9 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 		new_q = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops,
 					  classid, NULL);
 		if (q->offload) {
-			if (new_q) {
-				htb_set_lockdep_class_child(new_q);
-				/* One ref for cl->leaf.q, the other for
-				 * dev_queue->qdisc.
-				 */
+			/* One ref for cl->leaf.q, the other for dev_queue->qdisc. */
+			if (new_q)
 				qdisc_refcount_inc(new_q);
-			}
 			old_q = htb_graft_helper(dev_queue, new_q);
 			/* No qdisc_put needed. */
 			WARN_ON(!(old_q->flags & TCQ_F_BUILTIN));
-- 
2.43.0

[PATCH AUTOSEL 6.9 22/35] net: dsa: realtek: keep default LED state in rtl8366rb

[Sasha Levin]

From: Luiz Angelo Daros de Luca <luizluca@gmail.com>

[ Upstream commit 5edc6585aafefa3d44fb8a84adf241d90227f7a3 ]

This switch family supports four LEDs for each of its six ports. Each
LED group is composed of one of these four LEDs from all six ports. LED
groups can be configured to display hardware information, such as link
activity, or manually controlled through a bitmap in registers
RTL8366RB_LED_0_1_CTRL_REG and RTL8366RB_LED_2_3_CTRL_REG.

After a reset, the default LED group configuration for groups 0 to 3
indicates, respectively, link activity, link at 1000M, 100M, and 10M, or
RTL8366RB_LED_CTRL_REG as 0x5432. These configurations are commonly used
for LED indications. However, the driver was replacing that
configuration to use manually controlled LEDs (RTL8366RB_LED_FORCE)
without providing a way for the OS to control them. The default
configuration is deemed more useful than fixed, uncontrollable turned-on
LEDs.

The driver was enabling/disabling LEDs during port_enable/disable.
However, these events occur when the port is administratively controlled
(up or down) and are not related to link presence. Additionally, when a
port N was disabled, the driver was turning off all LEDs for group N,
not only the corresponding LED for port N in any of those 4 groups. In
such cases, if port 0 was brought down, the LEDs for all ports in LED
group 0 would be turned off. As another side effect, the driver was
wrongly warning that port 5 didn't have an LED ("no LED for port 5").
Since showing the administrative state of ports is not an orthodox way
to use LEDs, it was not worth it to fix it and all this code was
dropped.

The code to disable LEDs was simplified only changing each LED group to
the RTL8366RB_LED_OFF state. Registers RTL8366RB_LED_0_1_CTRL_REG and
RTL8366RB_LED_2_3_CTRL_REG are only used when the corresponding LED
group is configured with RTL8366RB_LED_FORCE and they don't need to be
cleaned. The code still references an LED controlled by
RTL8366RB_INTERRUPT_CONTROL_REG, but as of now, no test device has
actually used it. Also, some magic numbers were replaced by macros.

Signed-off-by: Luiz Angelo Daros de Luca <luizluca@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/dsa/realtek/rtl8366rb.c | 87 +++++++----------------------
 1 file changed, 20 insertions(+), 67 deletions(-)

diff --git a/drivers/net/dsa/realtek/rtl8366rb.c b/drivers/net/dsa/realtek/rtl8366rb.c
index e10ae94cf7711..5ccb1a3a149d8 100644
--- a/drivers/net/dsa/realtek/rtl8366rb.c
+++ b/drivers/net/dsa/realtek/rtl8366rb.c
@@ -185,7 +185,12 @@
 #define RTL8366RB_LED_BLINKRATE_222MS		0x0004
 #define RTL8366RB_LED_BLINKRATE_446MS		0x0005
 
+/* LED trigger event for each group */
 #define RTL8366RB_LED_CTRL_REG			0x0431
+#define RTL8366RB_LED_CTRL_OFFSET(led_group)	\
+	(4 * (led_group))
+#define RTL8366RB_LED_CTRL_MASK(led_group)	\
+	(0xf << RTL8366RB_LED_CTRL_OFFSET(led_group))
 #define RTL8366RB_LED_OFF			0x0
 #define RTL8366RB_LED_DUP_COL			0x1
 #define RTL8366RB_LED_LINK_ACT			0x2
@@ -202,6 +207,11 @@
 #define RTL8366RB_LED_LINK_TX			0xd
 #define RTL8366RB_LED_MASTER			0xe
 #define RTL8366RB_LED_FORCE			0xf
+
+/* The RTL8366RB_LED_X_X registers are used to manually set the LED state only
+ * when the corresponding LED group in RTL8366RB_LED_CTRL_REG is
+ * RTL8366RB_LED_FORCE. Otherwise, it is ignored.
+ */
 #define RTL8366RB_LED_0_1_CTRL_REG		0x0432
 #define RTL8366RB_LED_1_OFFSET			6
 #define RTL8366RB_LED_2_3_CTRL_REG		0x0433
@@ -1001,28 +1011,20 @@ static int rtl8366rb_setup(struct dsa_switch *ds)
 	 */
 	if (priv->leds_disabled) {
 		/* Turn everything off */
-		regmap_update_bits(priv->map,
-				   RTL8366RB_LED_0_1_CTRL_REG,
-				   0x0FFF, 0);
-		regmap_update_bits(priv->map,
-				   RTL8366RB_LED_2_3_CTRL_REG,
-				   0x0FFF, 0);
 		regmap_update_bits(priv->map,
 				   RTL8366RB_INTERRUPT_CONTROL_REG,
 				   RTL8366RB_P4_RGMII_LED,
 				   0);
-		val = RTL8366RB_LED_OFF;
-	} else {
-		/* TODO: make this configurable per LED */
-		val = RTL8366RB_LED_FORCE;
-	}
-	for (i = 0; i < 4; i++) {
-		ret = regmap_update_bits(priv->map,
-					 RTL8366RB_LED_CTRL_REG,
-					 0xf << (i * 4),
-					 val << (i * 4));
-		if (ret)
-			return ret;
+
+		for (i = 0; i < RTL8366RB_NUM_LEDGROUPS; i++) {
+			val = RTL8366RB_LED_OFF << RTL8366RB_LED_CTRL_OFFSET(i);
+			ret = regmap_update_bits(priv->map,
+						 RTL8366RB_LED_CTRL_REG,
+						 RTL8366RB_LED_CTRL_MASK(i),
+						 val);
+			if (ret)
+				return ret;
+		}
 	}
 
 	ret = rtl8366_reset_vlan(priv);
@@ -1167,52 +1169,6 @@ rtl8366rb_mac_link_down(struct dsa_switch *ds, int port, unsigned int mode,
 	}
 }
 
-static void rb8366rb_set_port_led(struct realtek_priv *priv,
-				  int port, bool enable)
-{
-	u16 val = enable ? 0x3f : 0;
-	int ret;
-
-	if (priv->leds_disabled)
-		return;
-
-	switch (port) {
-	case 0:
-		ret = regmap_update_bits(priv->map,
-					 RTL8366RB_LED_0_1_CTRL_REG,
-					 0x3F, val);
-		break;
-	case 1:
-		ret = regmap_update_bits(priv->map,
-					 RTL8366RB_LED_0_1_CTRL_REG,
-					 0x3F << RTL8366RB_LED_1_OFFSET,
-					 val << RTL8366RB_LED_1_OFFSET);
-		break;
-	case 2:
-		ret = regmap_update_bits(priv->map,
-					 RTL8366RB_LED_2_3_CTRL_REG,
-					 0x3F, val);
-		break;
-	case 3:
-		ret = regmap_update_bits(priv->map,
-					 RTL8366RB_LED_2_3_CTRL_REG,
-					 0x3F << RTL8366RB_LED_3_OFFSET,
-					 val << RTL8366RB_LED_3_OFFSET);
-		break;
-	case 4:
-		ret = regmap_update_bits(priv->map,
-					 RTL8366RB_INTERRUPT_CONTROL_REG,
-					 RTL8366RB_P4_RGMII_LED,
-					 enable ? RTL8366RB_P4_RGMII_LED : 0);
-		break;
-	default:
-		dev_err(priv->dev, "no LED for port %d\n", port);
-		return;
-	}
-	if (ret)
-		dev_err(priv->dev, "error updating LED on port %d\n", port);
-}
-
 static int
 rtl8366rb_port_enable(struct dsa_switch *ds, int port,
 		      struct phy_device *phy)
@@ -1226,7 +1182,6 @@ rtl8366rb_port_enable(struct dsa_switch *ds, int port,
 	if (ret)
 		return ret;
 
-	rb8366rb_set_port_led(priv, port, true);
 	return 0;
 }
 
@@ -1241,8 +1196,6 @@ rtl8366rb_port_disable(struct dsa_switch *ds, int port)
 				 BIT(port));
 	if (ret)
 		return;
-
-	rb8366rb_set_port_led(priv, port, false);
 }
 
 static int
-- 
2.43.0

[PATCH AUTOSEL 6.9 23/35] net: dsa: realtek: do not assert reset on remove

[Sasha Levin]

From: Luiz Angelo Daros de Luca <luizluca@gmail.com>

[ Upstream commit 4f580e9aced1816398c1c64f178302a22b8ea6e2 ]

The necessity of asserting the reset on removal was previously
questioned, as DSA's own cleanup methods should suffice to prevent
traffic leakage[1].

When a driver has subdrivers controlled by devres, they will be
unregistered after the main driver's .remove is executed. If it asserts
a reset, the subdrivers will be unable to communicate with the hardware
during their cleanup. For LEDs, this means that they will fail to turn
off, resulting in a timeout error.

[1] https://lore.kernel.org/r/20240123215606.26716-9-luizluca@gmail.com/

Signed-off-by: Luiz Angelo Daros de Luca <luizluca@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/dsa/realtek/rtl83xx.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/dsa/realtek/rtl83xx.c b/drivers/net/dsa/realtek/rtl83xx.c
index d2e876805393b..a9c1702431efb 100644
--- a/drivers/net/dsa/realtek/rtl83xx.c
+++ b/drivers/net/dsa/realtek/rtl83xx.c
@@ -290,16 +290,13 @@ EXPORT_SYMBOL_NS_GPL(rtl83xx_shutdown, REALTEK_DSA);
  * rtl83xx_remove() - Cleanup a realtek switch driver
  * @priv: realtek_priv pointer
  *
- * If a method is provided, this function asserts the hard reset of the switch
- * in order to avoid leaking traffic when the driver is gone.
+ * Placehold for common cleanup procedures.
  *
- * Context: Might sleep if priv->gdev->chip->can_sleep.
+ * Context: Any
  * Return: nothing
  */
 void rtl83xx_remove(struct realtek_priv *priv)
 {
-	/* leave the device reset asserted */
-	rtl83xx_reset_assert(priv);
 }
 EXPORT_SYMBOL_NS_GPL(rtl83xx_remove, REALTEK_DSA);
 
-- 
2.43.0

[PATCH AUTOSEL 6.9 25/35] netpoll: Fix race condition in netpoll_owner_active

[Sasha Levin]

From: Breno Leitao <leitao@debian.org>

[ Upstream commit c2e6a872bde9912f1a7579639c5ca3adf1003916 ]

KCSAN detected a race condition in netpoll:

	BUG: KCSAN: data-race in net_rx_action / netpoll_send_skb
	write (marked) to 0xffff8881164168b0 of 4 bytes by interrupt on cpu 10:
	net_rx_action (./include/linux/netpoll.h:90 net/core/dev.c:6712 net/core/dev.c:6822)
<snip>
	read to 0xffff8881164168b0 of 4 bytes by task 1 on cpu 2:
	netpoll_send_skb (net/core/netpoll.c:319 net/core/netpoll.c:345 net/core/netpoll.c:393)
	netpoll_send_udp (net/core/netpoll.c:?)
<snip>
	value changed: 0x0000000a -> 0xffffffff

This happens because netpoll_owner_active() needs to check if the
current CPU is the owner of the lock, touching napi->poll_owner
non atomically. The ->poll_owner field contains the current CPU holding
the lock.

Use an atomic read to check if the poll owner is the current CPU.

Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240429100437.3487432-1-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/core/netpoll.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 543007f159f99..55bcacf67df3b 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -316,7 +316,7 @@ static int netpoll_owner_active(struct net_device *dev)
 	struct napi_struct *napi;
 
 	list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) {
-		if (napi->poll_owner == smp_processor_id())
+		if (READ_ONCE(napi->poll_owner) == smp_processor_id())
 			return 1;
 	}
 	return 0;
-- 
2.43.0

[PATCH AUTOSEL 6.9 33/35] selftests: net: fix timestamp not arriving in cmsg_time.sh

[Sasha Levin]

From: Jakub Kicinski <kuba@kernel.org>

[ Upstream commit 2d3b8dfd82d76b1295167c6453d683ab99e50794 ]

On slow machines the SND timestamp sometimes doesn't arrive before
we quit. The test only waits as long as the packet delay, so it's
easy for a race condition to happen.

Double the wait but do a bit of polling, once the SND timestamp
arrives there's no point to wait any longer.

This fixes the "TXTIME abs" failures on debug kernels, like:

   Case ICMPv4  - TXTIME abs returned '', expected 'OK'

Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20240510005705.43069-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/net/cmsg_sender.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c
index c79e65581dc37..161db24e3c409 100644
--- a/tools/testing/selftests/net/cmsg_sender.c
+++ b/tools/testing/selftests/net/cmsg_sender.c
@@ -333,16 +333,17 @@ static const char *cs_ts_info2str(unsigned int info)
 	return "unknown";
 }
 
-static void
+static unsigned long
 cs_read_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz)
 {
 	struct sock_extended_err *see;
 	struct scm_timestamping *ts;
+	unsigned long ts_seen = 0;
 	struct cmsghdr *cmsg;
 	int i, err;
 
 	if (!opt.ts.ena)
-		return;
+		return 0;
 	msg->msg_control = cbuf;
 	msg->msg_controllen = cbuf_sz;
 
@@ -396,8 +397,11 @@ cs_read_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz)
 			printf(" %5s ts%d %lluus\n",
 			       cs_ts_info2str(see->ee_info),
 			       i, rel_time);
+			ts_seen |= 1 << see->ee_info;
 		}
 	}
+
+	return ts_seen;
 }
 
 static void ca_set_sockopts(int fd)
@@ -509,10 +513,16 @@ int main(int argc, char *argv[])
 	err = ERN_SUCCESS;
 
 	if (opt.ts.ena) {
-		/* Make sure all timestamps have time to loop back */
-		usleep(opt.txtime.delay);
+		unsigned long seen;
+		int i;
 
-		cs_read_cmsg(fd, &msg, cbuf, sizeof(cbuf));
+		/* Make sure all timestamps have time to loop back */
+		for (i = 0; i < 40; i++) {
+			seen = cs_read_cmsg(fd, &msg, cbuf, sizeof(cbuf));
+			if (seen & (1 << SCM_TSTAMP_SND))
+				break;
+			usleep(opt.txtime.delay / 20);
+		}
 	}
 
 err_out:
-- 
2.43.0

[PATCH AUTOSEL 6.9 34/35] net: ena: Add validation for completion descriptors consistency

[Sasha Levin]

From: David Arinzon <darinzon@amazon.com>

[ Upstream commit b37b98a3a0c1198bafe8c2d9ce0bc845b4e7a9a7 ]

Validate that `first` flag is set only for the first
descriptor in multi-buffer packets.
In case of an invalid descriptor, a reset will occur.
A new reset reason for RX data corruption has been added.

Signed-off-by: Shahar Itzko <itzko@amazon.com>
Signed-off-by: David Arinzon <darinzon@amazon.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240512134637.25299-4-darinzon@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/amazon/ena/ena_eth_com.c | 37 ++++++++++++++-----
 drivers/net/ethernet/amazon/ena/ena_netdev.c  |  2 +
 .../net/ethernet/amazon/ena/ena_regs_defs.h   |  1 +
 3 files changed, 30 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
index 933e619b3a313..4c6e07aa4bbb5 100644
--- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
@@ -229,30 +229,43 @@ static struct ena_eth_io_rx_cdesc_base *
 		idx * io_cq->cdesc_entry_size_in_bytes);
 }
 
-static u16 ena_com_cdesc_rx_pkt_get(struct ena_com_io_cq *io_cq,
-					   u16 *first_cdesc_idx)
+static int ena_com_cdesc_rx_pkt_get(struct ena_com_io_cq *io_cq,
+				    u16 *first_cdesc_idx,
+				    u16 *num_descs)
 {
+	u16 count = io_cq->cur_rx_pkt_cdesc_count, head_masked;
 	struct ena_eth_io_rx_cdesc_base *cdesc;
-	u16 count = 0, head_masked;
 	u32 last = 0;
 
 	do {
+		u32 status;
+
 		cdesc = ena_com_get_next_rx_cdesc(io_cq);
 		if (!cdesc)
 			break;
+		status = READ_ONCE(cdesc->status);
 
 		ena_com_cq_inc_head(io_cq);
+		if (unlikely((status & ENA_ETH_IO_RX_CDESC_BASE_FIRST_MASK) >>
+		    ENA_ETH_IO_RX_CDESC_BASE_FIRST_SHIFT && count != 0)) {
+			struct ena_com_dev *dev = ena_com_io_cq_to_ena_dev(io_cq);
+
+			netdev_err(dev->net_device,
+				   "First bit is on in descriptor #%d on q_id: %d, req_id: %u\n",
+				   count, io_cq->qid, cdesc->req_id);
+			return -EFAULT;
+		}
 		count++;
-		last = (READ_ONCE(cdesc->status) & ENA_ETH_IO_RX_CDESC_BASE_LAST_MASK) >>
-		       ENA_ETH_IO_RX_CDESC_BASE_LAST_SHIFT;
+		last = (status & ENA_ETH_IO_RX_CDESC_BASE_LAST_MASK) >>
+			ENA_ETH_IO_RX_CDESC_BASE_LAST_SHIFT;
 	} while (!last);
 
 	if (last) {
 		*first_cdesc_idx = io_cq->cur_rx_pkt_cdesc_start_idx;
-		count += io_cq->cur_rx_pkt_cdesc_count;
 
 		head_masked = io_cq->head & (io_cq->q_depth - 1);
 
+		*num_descs = count;
 		io_cq->cur_rx_pkt_cdesc_count = 0;
 		io_cq->cur_rx_pkt_cdesc_start_idx = head_masked;
 
@@ -260,11 +273,11 @@ static u16 ena_com_cdesc_rx_pkt_get(struct ena_com_io_cq *io_cq,
 			   "ENA q_id: %d packets were completed. first desc idx %u descs# %d\n",
 			   io_cq->qid, *first_cdesc_idx, count);
 	} else {
-		io_cq->cur_rx_pkt_cdesc_count += count;
-		count = 0;
+		io_cq->cur_rx_pkt_cdesc_count = count;
+		*num_descs = 0;
 	}
 
-	return count;
+	return 0;
 }
 
 static int ena_com_create_meta(struct ena_com_io_sq *io_sq,
@@ -539,10 +552,14 @@ int ena_com_rx_pkt(struct ena_com_io_cq *io_cq,
 	u16 cdesc_idx = 0;
 	u16 nb_hw_desc;
 	u16 i = 0;
+	int rc;
 
 	WARN(io_cq->direction != ENA_COM_IO_QUEUE_DIRECTION_RX, "wrong Q type");
 
-	nb_hw_desc = ena_com_cdesc_rx_pkt_get(io_cq, &cdesc_idx);
+	rc = ena_com_cdesc_rx_pkt_get(io_cq, &cdesc_idx, &nb_hw_desc);
+	if (unlikely(rc != 0))
+		return -EFAULT;
+
 	if (nb_hw_desc == 0) {
 		ena_rx_ctx->descs = nb_hw_desc;
 		return 0;
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index be5acfa41ee0c..8db05f7544f90 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -1347,6 +1347,8 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 	if (rc == -ENOSPC) {
 		ena_increase_stat(&rx_ring->rx_stats.bad_desc_num, 1, &rx_ring->syncp);
 		ena_reset_device(adapter, ENA_REGS_RESET_TOO_MANY_RX_DESCS);
+	} else if (rc == -EFAULT) {
+		ena_reset_device(adapter, ENA_REGS_RESET_RX_DESCRIPTOR_MALFORMED);
 	} else {
 		ena_increase_stat(&rx_ring->rx_stats.bad_req_id, 1,
 				  &rx_ring->syncp);
diff --git a/drivers/net/ethernet/amazon/ena/ena_regs_defs.h b/drivers/net/ethernet/amazon/ena/ena_regs_defs.h
index 2c3d6a77ea79f..a2efebafd686a 100644
--- a/drivers/net/ethernet/amazon/ena/ena_regs_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_regs_defs.h
@@ -22,6 +22,7 @@ enum ena_regs_reset_reason_types {
 	ENA_REGS_RESET_GENERIC                      = 13,
 	ENA_REGS_RESET_MISS_INTERRUPT               = 14,
 	ENA_REGS_RESET_SUSPECTED_POLL_STARVATION    = 15,
+	ENA_REGS_RESET_RX_DESCRIPTOR_MALFORMED	    = 16,
 };
 
 /* ena_registers offsets */
-- 
2.43.0