[PATCH AUTOSEL 5.18 03/93] ath10k: htt_tx: do not interpret Eth frames as WiFi

[PATCH AUTOSEL 5.18 03/93] ath10k: htt_tx: do not interpret Eth frames as WiFi

[Sasha Levin]

From: Sergey Ryazanov <ryazanov.s.a@gmail.com>

[ Upstream commit 70f119fb82af7f7417dc659faf02c91e1f853739 ]

The xmit path for the Ethernet encapsulated frames become more or less
usable since d740d8fd2439 ("ath10k: unify tx mode and dispatch"). This
change reorganize the xmit path in a manageable way to properly support
various tx modes, but misses that the Ethernet encapsulated frame is a
special case. We do not have an IEEE 802.11 header at the begining of
them. But the HTT Tx handler still interprets first bytes of each frame
as an IEEE 802.11 Frame Control field.

Than this code was copied by e62ee5c381c5 ("ath10k: Add support for
htt_data_tx_desc_64 descriptor") and a2097d6444c3 ("ath10k: htt: High
latency TX support") to another handlers. In fact the issue in the high
latency (HL) handler was introduced by 83ac260151e7 ("ath10k: add mic
bytes for pmf management packet").

Ethernet encapsulated frame tx mode stay unused until 75d85fd9993c
("ath10k: introduce basic tdls functionality") started using it for TDLS
frames to avoid key selection issue in some firmwares.

Trying to interpret the begining of an Ethernet encapsulated frame as an
IEEE 802.11 header was not hurt us noticeably since we need to meet two
conditions: (1) xmit should be performed towards a TDLS peer, and (2)
the TDLS peer should have a specific OUI part of its MAC address. Looks
like that the rareness in TDLS communications of OUIs that can be
interpreted as an 802.11 management frame saves users from facing this
issue earlier.

Improve Ethernet tx mode support in the HTT Tx handler by avoiding
interpreting its first bytes as an IEEE 802.11 header. While at it, make
the ieee80211_hdr variable local to the code block that is guarded by
!is_eth check. In this way, we clarify in which cases a frame can be
interpreted as IEEE 802.11, and saves us from similar issues in the
future.

Credits: this change as part of xmit encapsulation offloading support
was originally made by QCA and then submitted for inclusion by John
Crispin [1]. But the whole work was not accepted due to the lack of a
part for 64-bits descriptors [2]. Zhijun You then pointed this out to me
in a reply to my initial RFC patch series. And I made this slightly
reworked version that covered all the HTT Tx handler variants.

1. https://lore.kernel.org/all/20191216092207.31032-1-john@phrozen.org/
2. https://patchwork.kernel.org/project/linux-wireless/patch/20191216092207.31032-1-john@phrozen.org/

Reported-by: Zhijun You <hujy652@gmail.com>
Signed-off-by: Vasanthakumar Thiagarajan <vthiagar@qti.qualcomm.com>
Signed-off-by: John Crispin <john@phrozen.org>
Signed-off-by: Sergey Ryazanov <ryazanov.s.a@gmail.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20220516032519.29831-3-ryazanov.s.a@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/ath/ath10k/htt_tx.c | 61 ++++++++++++++----------
 1 file changed, 35 insertions(+), 26 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/htt_tx.c b/drivers/net/wireless/ath/ath10k/htt_tx.c
index 9842a4b2f78f..a19b0795c86d 100644
--- a/drivers/net/wireless/ath/ath10k/htt_tx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_tx.c
@@ -1275,7 +1275,6 @@ static int ath10k_htt_tx_hl(struct ath10k_htt *htt, enum ath10k_hw_txrx_mode txm
 	struct ath10k *ar = htt->ar;
 	int res, data_len;
 	struct htt_cmd_hdr *cmd_hdr;
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)msdu->data;
 	struct htt_data_tx_desc *tx_desc;
 	struct ath10k_skb_cb *skb_cb = ATH10K_SKB_CB(msdu);
 	struct sk_buff *tmp_skb;
@@ -1286,11 +1285,15 @@ static int ath10k_htt_tx_hl(struct ath10k_htt *htt, enum ath10k_hw_txrx_mode txm
 	u16 flags1 = 0;
 	u16 msdu_id = 0;
 
-	if ((ieee80211_is_action(hdr->frame_control) ||
-	     ieee80211_is_deauth(hdr->frame_control) ||
-	     ieee80211_is_disassoc(hdr->frame_control)) &&
-	     ieee80211_has_protected(hdr->frame_control)) {
-		skb_put(msdu, IEEE80211_CCMP_MIC_LEN);
+	if (!is_eth) {
+		struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)msdu->data;
+
+		if ((ieee80211_is_action(hdr->frame_control) ||
+		     ieee80211_is_deauth(hdr->frame_control) ||
+		     ieee80211_is_disassoc(hdr->frame_control)) &&
+		     ieee80211_has_protected(hdr->frame_control)) {
+			skb_put(msdu, IEEE80211_CCMP_MIC_LEN);
+		}
 	}
 
 	data_len = msdu->len;
@@ -1387,7 +1390,6 @@ static int ath10k_htt_tx_32(struct ath10k_htt *htt,
 {
 	struct ath10k *ar = htt->ar;
 	struct device *dev = ar->dev;
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)msdu->data;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(msdu);
 	struct ath10k_skb_cb *skb_cb = ATH10K_SKB_CB(msdu);
 	struct ath10k_hif_sg_item sg_items[2];
@@ -1419,15 +1421,19 @@ static int ath10k_htt_tx_32(struct ath10k_htt *htt,
 	txbuf_paddr = htt->txbuf.paddr +
 		      (sizeof(struct ath10k_htt_txbuf_32) * msdu_id);
 
-	if ((ieee80211_is_action(hdr->frame_control) ||
-	     ieee80211_is_deauth(hdr->frame_control) ||
-	     ieee80211_is_disassoc(hdr->frame_control)) &&
-	     ieee80211_has_protected(hdr->frame_control)) {
-		skb_put(msdu, IEEE80211_CCMP_MIC_LEN);
-	} else if (!(skb_cb->flags & ATH10K_SKB_F_NO_HWCRYPT) &&
-		   txmode == ATH10K_HW_TXRX_RAW &&
-		   ieee80211_has_protected(hdr->frame_control)) {
-		skb_put(msdu, IEEE80211_CCMP_MIC_LEN);
+	if (!is_eth) {
+		struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)msdu->data;
+
+		if ((ieee80211_is_action(hdr->frame_control) ||
+		     ieee80211_is_deauth(hdr->frame_control) ||
+		     ieee80211_is_disassoc(hdr->frame_control)) &&
+		     ieee80211_has_protected(hdr->frame_control)) {
+			skb_put(msdu, IEEE80211_CCMP_MIC_LEN);
+		} else if (!(skb_cb->flags & ATH10K_SKB_F_NO_HWCRYPT) &&
+			   txmode == ATH10K_HW_TXRX_RAW &&
+			   ieee80211_has_protected(hdr->frame_control)) {
+			skb_put(msdu, IEEE80211_CCMP_MIC_LEN);
+		}
 	}
 
 	skb_cb->paddr = dma_map_single(dev, msdu->data, msdu->len,
@@ -1589,7 +1595,6 @@ static int ath10k_htt_tx_64(struct ath10k_htt *htt,
 {
 	struct ath10k *ar = htt->ar;
 	struct device *dev = ar->dev;
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)msdu->data;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(msdu);
 	struct ath10k_skb_cb *skb_cb = ATH10K_SKB_CB(msdu);
 	struct ath10k_hif_sg_item sg_items[2];
@@ -1621,15 +1626,19 @@ static int ath10k_htt_tx_64(struct ath10k_htt *htt,
 	txbuf_paddr = htt->txbuf.paddr +
 		      (sizeof(struct ath10k_htt_txbuf_64) * msdu_id);
 
-	if ((ieee80211_is_action(hdr->frame_control) ||
-	     ieee80211_is_deauth(hdr->frame_control) ||
-	     ieee80211_is_disassoc(hdr->frame_control)) &&
-	     ieee80211_has_protected(hdr->frame_control)) {
-		skb_put(msdu, IEEE80211_CCMP_MIC_LEN);
-	} else if (!(skb_cb->flags & ATH10K_SKB_F_NO_HWCRYPT) &&
-		   txmode == ATH10K_HW_TXRX_RAW &&
-		   ieee80211_has_protected(hdr->frame_control)) {
-		skb_put(msdu, IEEE80211_CCMP_MIC_LEN);
+	if (!is_eth) {
+		struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)msdu->data;
+
+		if ((ieee80211_is_action(hdr->frame_control) ||
+		     ieee80211_is_deauth(hdr->frame_control) ||
+		     ieee80211_is_disassoc(hdr->frame_control)) &&
+		     ieee80211_has_protected(hdr->frame_control)) {
+			skb_put(msdu, IEEE80211_CCMP_MIC_LEN);
+		} else if (!(skb_cb->flags & ATH10K_SKB_F_NO_HWCRYPT) &&
+			   txmode == ATH10K_HW_TXRX_RAW &&
+			   ieee80211_has_protected(hdr->frame_control)) {
+			skb_put(msdu, IEEE80211_CCMP_MIC_LEN);
+		}
 	}
 
 	skb_cb->paddr = dma_map_single(dev, msdu->data, msdu->len,
-- 
2.35.1

[PATCH AUTOSEL 5.18 04/93] ath10k: fix misreported tx bandwidth for 160Mhz

[Sasha Levin]

From: Maxime Bizon <mbizon@freebox.fr>

[ Upstream commit 75a7062e533e309a9ca0812c69f3ac3cefadb8b1 ]

Because of this missing switch case, 160Mhz transmit was reported as
20Mhz, leading to wrong airtime calculation and AQL limiting max
throughput.

Tested-on: QCA9984 hw2.0 PCI 10.4-3.10-00047

Signed-off-by: Maxime Bizon <mbizon@freebox.fr>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/cd2735a40da7f4fcc5323e3fca3775e7b5402ece.camel@freebox.fr
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/ath/ath10k/htt_rx.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index 771252dd6d4e..e8727c0b0171 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -3884,6 +3884,10 @@ ath10k_update_per_peer_tx_stats(struct ath10k *ar,
 		arsta->tx_info.status.rates[0].flags |=
 				IEEE80211_TX_RC_80_MHZ_WIDTH;
 		break;
+	case RATE_INFO_BW_160:
+		arsta->tx_info.status.rates[0].flags |=
+				IEEE80211_TX_RC_160_MHZ_WIDTH;
+		break;
 	}
 
 	if (peer_stats->succ_pkts) {
-- 
2.35.1

[PATCH AUTOSEL 5.18 09/93] ath10k: fix regdomain info of iw reg set/get

[Sasha Levin]

From: Wen Gong <quic_wgong@quicinc.com>

[ Upstream commit 8723750e2753868591ba86a57b0041c5e38047ad ]

When wlan load, firmware report the reg code with 0x6C for QCA6174,
it is world reg which checked by ath_is_world_regd(), then the reg
will be save into reg_world_copy of ath_common in ath_regd_init().
Later the regulatory of ath_common is updated to another country
code such as "US" in ath_reg_notifier_apply() by below call stack.
After that, regulatory_hint() is called in ath10k_mac_register()
and it lead "iw reg get" show two regdomain info as below.

global
country US: DFS-FCC
	(2400 - 2472 @ 40), (N/A, 30), (N/A)
	(5150 - 5250 @ 80), (N/A, 23), (N/A), AUTO-BW
	(5250 - 5350 @ 80), (N/A, 23), (0 ms), DFS, AUTO-BW
	(5470 - 5730 @ 160), (N/A, 23), (0 ms), DFS
	(5730 - 5850 @ 80), (N/A, 30), (N/A)
	(57240 - 71000 @ 2160), (N/A, 40), (N/A)

phy#0
country US: DFS-FCC
	(2400 - 2472 @ 40), (N/A, 30), (N/A)
	(5150 - 5250 @ 80), (N/A, 23), (N/A), AUTO-BW
	(5250 - 5350 @ 80), (N/A, 23), (0 ms), DFS, AUTO-BW
	(5470 - 5730 @ 160), (N/A, 23), (0 ms), DFS
	(5730 - 5850 @ 80), (N/A, 30), (N/A)
	(57240 - 71000 @ 2160), (N/A, 40), (N/A)

[ 4255.704975] Call Trace:
[ 4255.704983]  ath_reg_notifier_apply+0xa6/0xc5 [ath]
[ 4255.704991]  ath10k_reg_notifier+0x2f/0xd2 [ath10k_core]
[ 4255.705010]  wiphy_regulatory_register+0x5f/0x69 [cfg80211]
[ 4255.705020]  wiphy_register+0x459/0x8f0 [cfg80211]
[ 4255.705042]  ? ieee80211_register_hw+0x3a6/0x7d1 [mac80211]
[ 4255.705049]  ? __kmalloc+0xf4/0x218
[ 4255.705058]  ? ieee80211_register_hw+0x3a6/0x7d1 [mac80211]
[ 4255.705066]  ? ath10k_mac_register+0x70/0xaab [ath10k_core]
[ 4255.705075]  ieee80211_register_hw+0x51a/0x7d1 [mac80211]
[ 4255.705084]  ath10k_mac_register+0x8b4/0xaab [ath10k_core]
[ 4255.705094]  ath10k_core_register_work+0xa5e/0xb45 [ath10k_core]
[ 4255.705100]  ? __schedule+0x61f/0x7d3
[ 4255.705105]  process_one_work+0x1b7/0x392
[ 4255.705109]  worker_thread+0x271/0x35d
[ 4255.705112]  ? pr_cont_work+0x58/0x58
[ 4255.705116]  kthread+0x13f/0x147
[ 4255.705119]  ? pr_cont_work+0x58/0x58
[ 4255.705123]  ? kthread_destroy_worker+0x62/0x62
[ 4255.705126]  ret_from_fork+0x22/0x40

At this moment, the two regdomain info is same, when run "iw reg set KR",
the global regdomain info changed to KR, but the regdomain of phy#0
does not change again. It leads inconsistent values between global and
phy#0 as below.

global
country KR: DFS-JP
        (2402 - 2482 @ 40), (N/A, 13), (N/A)
        (5170 - 5250 @ 80), (N/A, 20), (N/A), AUTO-BW
        (5250 - 5330 @ 80), (N/A, 20), (0 ms), DFS, AUTO-BW
        (5490 - 5710 @ 160), (N/A, 30), (0 ms), DFS
        (5735 - 5835 @ 80), (N/A, 30), (N/A)
        (57000 - 66000 @ 2160), (N/A, 43), (N/A)

phy#0
country US: DFS-FCC
	(2400 - 2472 @ 40), (N/A, 30), (N/A)
	(5150 - 5250 @ 80), (N/A, 23), (N/A), AUTO-BW
	(5250 - 5350 @ 80), (N/A, 23), (0 ms), DFS, AUTO-BW
	(5470 - 5730 @ 160), (N/A, 23), (0 ms), DFS
	(5730 - 5850 @ 80), (N/A, 30), (N/A)
	(57240 - 71000 @ 2160), (N/A, 40), (N/A)

The initial reg code is 0x6C which saved in reg_world_copy of ath_common,
and the code US is updated from cfg80211 later, so ath10k should also
check the initial reg code before regulatory_hint().

After this fix, regdomain info is same between "iw reg get" and "iw reg
set xx", it does not have the regdomain info of phy#0 again.

global
country KR: DFS-JP
        (2402 - 2482 @ 40), (N/A, 13), (N/A)
        (5170 - 5250 @ 80), (N/A, 20), (N/A), AUTO-BW
        (5250 - 5330 @ 80), (N/A, 20), (0 ms), DFS, AUTO-BW
        (5490 - 5710 @ 160), (N/A, 30), (0 ms), DFS
        (5735 - 5835 @ 80), (N/A, 30), (N/A)
        (57000 - 66000 @ 2160), (N/A, 43), (N/A)

This does not effect the channel list and power which ath10k used.
When the country code for regulatory_hint() in ath10k_mac_register()
is same with the global country code, then reg_set_rd_driver() of
cfg80211 called from crda which return -EALREADY to set_regdom() and
then update_all_wiphy_regulatory() will not be called while wlan load.
When run "iw reg set xx", reg_get_regdomain() which used by function
handle_channel() in net/wirelss/reg.c always use the regdomain
returned by get_cfg80211_regdom() because the initiator of last
regulatory_request is NL80211_REGDOM_SET_BY_USER, get_cfg80211_regdom()
is the global regdomain, then all the ieee80211_channel info is updated
in handle_channel() with the global regdomain.

Tested-on: QCA6174 hw3.2 SDIO WLAN.RMH.4.4.1-00049
Tested-on: QCA9984 hw1.0 PCI 10.4-3.6-00104

Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20220525132247.23459-1-quic_wgong@quicinc.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/ath/ath10k/mac.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index a11b31191d5a..66ccc5a2d658 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -10223,7 +10223,8 @@ int ath10k_mac_register(struct ath10k *ar)
 		ar->hw->wiphy->software_iftypes |= BIT(NL80211_IFTYPE_AP_VLAN);
 	}
 
-	if (!ath_is_world_regd(&ar->ath_common.regulatory)) {
+	if (!ath_is_world_regd(&ar->ath_common.reg_world_copy) &&
+	    !ath_is_world_regd(&ar->ath_common.regulatory)) {
 		ret = regulatory_hint(ar->hw->wiphy,
 				      ar->ath_common.regulatory.alpha2);
 		if (ret)
-- 
2.35.1

[PATCH AUTOSEL 5.18 10/93] bpf, sockmap: Fix sk->sk_forward_alloc warn_on in sk_stream_kill_queues

[Sasha Levin]

From: Wang Yufen <wangyufen@huawei.com>

[ Upstream commit d8616ee2affcff37c5d315310da557a694a3303d ]

During TCP sockmap redirect pressure test, the following warning is triggered:

WARNING: CPU: 3 PID: 2145 at net/core/stream.c:205 sk_stream_kill_queues+0xbc/0xd0
CPU: 3 PID: 2145 Comm: iperf Kdump: loaded Tainted: G        W         5.10.0+ #9
Call Trace:
 inet_csk_destroy_sock+0x55/0x110
 inet_csk_listen_stop+0xbb/0x380
 tcp_close+0x41b/0x480
 inet_release+0x42/0x80
 __sock_release+0x3d/0xa0
 sock_close+0x11/0x20
 __fput+0x9d/0x240
 task_work_run+0x62/0x90
 exit_to_user_mode_prepare+0x110/0x120
 syscall_exit_to_user_mode+0x27/0x190
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

The reason we observed is that:

When the listener is closing, a connection may have completed the three-way
handshake but not accepted, and the client has sent some packets. The child
sks in accept queue release by inet_child_forget()->inet_csk_destroy_sock(),
but psocks of child sks have not released.

To fix, add sock_map_destroy to release psocks.

Signed-off-by: Wang Yufen <wangyufen@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20220524075311.649153-1-wangyufen@huawei.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/linux/bpf.h   |  1 +
 include/linux/skmsg.h |  1 +
 net/core/skmsg.c      |  1 +
 net/core/sock_map.c   | 23 +++++++++++++++++++++++
 net/ipv4/tcp_bpf.c    |  1 +
 5 files changed, 27 insertions(+)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 83bd5598ec4d..5db26f20aa70 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2012,6 +2012,7 @@ int sock_map_bpf_prog_query(const union bpf_attr *attr,
 			    union bpf_attr __user *uattr);
 
 void sock_map_unhash(struct sock *sk);
+void sock_map_destroy(struct sock *sk);
 void sock_map_close(struct sock *sk, long timeout);
 #else
 static inline int bpf_prog_offload_init(struct bpf_prog *prog,
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index c5a2d6f50f25..153b6dec9b6a 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -95,6 +95,7 @@ struct sk_psock {
 	spinlock_t			link_lock;
 	refcount_t			refcnt;
 	void (*saved_unhash)(struct sock *sk);
+	void (*saved_destroy)(struct sock *sk);
 	void (*saved_close)(struct sock *sk, long timeout);
 	void (*saved_write_space)(struct sock *sk);
 	void (*saved_data_ready)(struct sock *sk);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index ede0af308f40..2742d8e4dd82 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -716,6 +716,7 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node)
 	psock->eval = __SK_NONE;
 	psock->sk_proto = prot;
 	psock->saved_unhash = prot->unhash;
+	psock->saved_destroy = prot->destroy;
 	psock->saved_close = prot->close;
 	psock->saved_write_space = sk->sk_write_space;
 
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 2d213c4011db..9947c1f94dc3 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -1563,6 +1563,29 @@ void sock_map_unhash(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(sock_map_unhash);
 
+void sock_map_destroy(struct sock *sk)
+{
+	void (*saved_destroy)(struct sock *sk);
+	struct sk_psock *psock;
+
+	rcu_read_lock();
+	psock = sk_psock_get(sk);
+	if (unlikely(!psock)) {
+		rcu_read_unlock();
+		if (sk->sk_prot->destroy)
+			sk->sk_prot->destroy(sk);
+		return;
+	}
+
+	saved_destroy = psock->saved_destroy;
+	sock_map_remove_links(sk, psock);
+	rcu_read_unlock();
+	sk_psock_stop(psock, true);
+	sk_psock_put(sk, psock);
+	saved_destroy(sk);
+}
+EXPORT_SYMBOL_GPL(sock_map_destroy);
+
 void sock_map_close(struct sock *sk, long timeout)
 {
 	void (*saved_close)(struct sock *sk, long timeout);
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 2c597a4e429a..25e83d35138b 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -541,6 +541,7 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS],
 				   struct proto *base)
 {
 	prot[TCP_BPF_BASE]			= *base;
+	prot[TCP_BPF_BASE].destroy		= sock_map_destroy;
 	prot[TCP_BPF_BASE].close		= sock_map_close;
 	prot[TCP_BPF_BASE].recvmsg		= tcp_bpf_recvmsg;
 	prot[TCP_BPF_BASE].sock_is_readable	= sk_msg_is_readable;
-- 
2.35.1

[PATCH AUTOSEL 5.18 15/93] iavf: Add waiting for response from PF in set mac

[Sasha Levin]

From: Mateusz Palczewski <mateusz.palczewski@intel.com>

[ Upstream commit 35a2443d0910fdd6ce29d4f724447ad7029e8f23 ]

Make iavf_set_mac synchronous by waiting for a response
from a PF. Without this iavf_set_mac is always returning
success even though set_mac can be rejected by a PF.
This ensures that when set_mac exits netdev MAC is updated.
This is needed for sending ARPs with correct MAC after
changing VF's MAC. This is also needed by bonding module.

Signed-off-by: Sylwester Dziedziuch <sylwesterx.dziedziuch@intel.com>
Signed-off-by: Mateusz Palczewski <mateusz.palczewski@intel.com>
Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/intel/iavf/iavf.h        |   7 +-
 drivers/net/ethernet/intel/iavf/iavf_main.c   | 127 +++++++++++++++---
 .../net/ethernet/intel/iavf/iavf_virtchnl.c   |  61 ++++++++-
 3 files changed, 174 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index 0ea0361cd86b..69703801d1b0 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -145,7 +145,8 @@ struct iavf_mac_filter {
 		u8 remove:1;        /* filter needs to be removed */
 		u8 add:1;           /* filter needs to be added */
 		u8 is_primary:1;    /* filter is a default VF MAC */
-		u8 padding:4;
+		u8 add_handled:1;   /* received response for filter add */
+		u8 padding:3;
 	};
 };
 
@@ -251,6 +252,7 @@ struct iavf_adapter {
 	struct work_struct adminq_task;
 	struct delayed_work client_task;
 	wait_queue_head_t down_waitqueue;
+	wait_queue_head_t vc_waitqueue;
 	struct iavf_q_vector *q_vectors;
 	struct list_head vlan_filter_list;
 	struct list_head mac_filter_list;
@@ -295,6 +297,7 @@ struct iavf_adapter {
 #define IAVF_FLAG_QUEUES_DISABLED		BIT(17)
 #define IAVF_FLAG_SETUP_NETDEV_FEATURES		BIT(18)
 #define IAVF_FLAG_REINIT_MSIX_NEEDED		BIT(20)
+#define IAVF_FLAG_INITIAL_MAC_SET		BIT(23)
 /* duplicates for common code */
 #define IAVF_FLAG_DCB_ENABLED			0
 	/* flags for admin queue service task */
@@ -567,6 +570,8 @@ void iavf_enable_vlan_stripping_v2(struct iavf_adapter *adapter, u16 tpid);
 void iavf_disable_vlan_stripping_v2(struct iavf_adapter *adapter, u16 tpid);
 void iavf_enable_vlan_insertion_v2(struct iavf_adapter *adapter, u16 tpid);
 void iavf_disable_vlan_insertion_v2(struct iavf_adapter *adapter, u16 tpid);
+int iavf_replace_primary_mac(struct iavf_adapter *adapter,
+			     const u8 *new_mac);
 void
 iavf_set_vlan_offload_features(struct iavf_adapter *adapter,
 			       netdev_features_t prev_features,
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 2e2c153ce46a..2ec3ebb397f3 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -978,6 +978,7 @@ struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter,
 
 		list_add_tail(&f->list, &adapter->mac_filter_list);
 		f->add = true;
+		f->add_handled = false;
 		f->is_new_mac = true;
 		f->is_primary = ether_addr_equal(macaddr, adapter->hw.mac.addr);
 		adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER;
@@ -989,47 +990,132 @@ struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter,
 }
 
 /**
- * iavf_set_mac - NDO callback to set port mac address
- * @netdev: network interface device structure
- * @p: pointer to an address structure
+ * iavf_replace_primary_mac - Replace current primary address
+ * @adapter: board private structure
+ * @new_mac: new MAC address to be applied
  *
- * Returns 0 on success, negative on failure
+ * Replace current dev_addr and send request to PF for removal of previous
+ * primary MAC address filter and addition of new primary MAC filter.
+ * Return 0 for success, -ENOMEM for failure.
+ *
+ * Do not call this with mac_vlan_list_lock!
  **/
-static int iavf_set_mac(struct net_device *netdev, void *p)
+int iavf_replace_primary_mac(struct iavf_adapter *adapter,
+			     const u8 *new_mac)
 {
-	struct iavf_adapter *adapter = netdev_priv(netdev);
 	struct iavf_hw *hw = &adapter->hw;
 	struct iavf_mac_filter *f;
-	struct sockaddr *addr = p;
-
-	if (!is_valid_ether_addr(addr->sa_data))
-		return -EADDRNOTAVAIL;
-
-	if (ether_addr_equal(netdev->dev_addr, addr->sa_data))
-		return 0;
 
 	spin_lock_bh(&adapter->mac_vlan_list_lock);
 
+	list_for_each_entry(f, &adapter->mac_filter_list, list) {
+		f->is_primary = false;
+	}
+
 	f = iavf_find_filter(adapter, hw->mac.addr);
 	if (f) {
 		f->remove = true;
-		f->is_primary = true;
 		adapter->aq_required |= IAVF_FLAG_AQ_DEL_MAC_FILTER;
 	}
 
-	f = iavf_add_filter(adapter, addr->sa_data);
+	f = iavf_add_filter(adapter, new_mac);
+
 	if (f) {
+		/* Always send the request to add if changing primary MAC
+		 * even if filter is already present on the list
+		 */
 		f->is_primary = true;
-		ether_addr_copy(hw->mac.addr, addr->sa_data);
+		f->add = true;
+		adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER;
+		ether_addr_copy(hw->mac.addr, new_mac);
 	}
 
 	spin_unlock_bh(&adapter->mac_vlan_list_lock);
 
 	/* schedule the watchdog task to immediately process the request */
-	if (f)
+	if (f) {
 		queue_work(iavf_wq, &adapter->watchdog_task.work);
+		return 0;
+	}
+	return -ENOMEM;
+}
+
+/**
+ * iavf_is_mac_set_handled - wait for a response to set MAC from PF
+ * @netdev: network interface device structure
+ * @macaddr: MAC address to set
+ *
+ * Returns true on success, false on failure
+ */
+static bool iavf_is_mac_set_handled(struct net_device *netdev,
+				    const u8 *macaddr)
+{
+	struct iavf_adapter *adapter = netdev_priv(netdev);
+	struct iavf_mac_filter *f;
+	bool ret = false;
+
+	spin_lock_bh(&adapter->mac_vlan_list_lock);
+
+	f = iavf_find_filter(adapter, macaddr);
 
-	return (f == NULL) ? -ENOMEM : 0;
+	if (!f || (!f->add && f->add_handled))
+		ret = true;
+
+	spin_unlock_bh(&adapter->mac_vlan_list_lock);
+
+	return ret;
+}
+
+/**
+ * iavf_set_mac - NDO callback to set port MAC address
+ * @netdev: network interface device structure
+ * @p: pointer to an address structure
+ *
+ * Returns 0 on success, negative on failure
+ */
+static int iavf_set_mac(struct net_device *netdev, void *p)
+{
+	struct iavf_adapter *adapter = netdev_priv(netdev);
+	struct sockaddr *addr = p;
+	bool handle_mac = iavf_is_mac_set_handled(netdev, addr->sa_data);
+	int ret;
+
+	if (!is_valid_ether_addr(addr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	ret = iavf_replace_primary_mac(adapter, addr->sa_data);
+
+	if (ret)
+		return ret;
+
+	/* If this is an initial set MAC during VF spawn do not wait */
+	if (adapter->flags & IAVF_FLAG_INITIAL_MAC_SET) {
+		adapter->flags &= ~IAVF_FLAG_INITIAL_MAC_SET;
+		return 0;
+	}
+
+	if (handle_mac)
+		goto done;
+
+	ret = wait_event_interruptible_timeout(adapter->vc_waitqueue, false, msecs_to_jiffies(2500));
+
+	/* If ret < 0 then it means wait was interrupted.
+	 * If ret == 0 then it means we got a timeout.
+	 * else it means we got response for set MAC from PF,
+	 * check if netdev MAC was updated to requested MAC,
+	 * if yes then set MAC succeeded otherwise it failed return -EACCES
+	 */
+	if (ret < 0)
+		return ret;
+
+	if (!ret)
+		return -EAGAIN;
+
+done:
+	if (!ether_addr_equal(netdev->dev_addr, addr->sa_data))
+		return -EACCES;
+
+	return 0;
 }
 
 /**
@@ -2445,6 +2531,8 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter)
 		ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr);
 	}
 
+	adapter->flags |= IAVF_FLAG_INITIAL_MAC_SET;
+
 	adapter->tx_desc_count = IAVF_DEFAULT_TXD;
 	adapter->rx_desc_count = IAVF_DEFAULT_RXD;
 	err = iavf_init_interrupt_scheme(adapter);
@@ -4678,6 +4766,9 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Setup the wait queue for indicating transition to down status */
 	init_waitqueue_head(&adapter->down_waitqueue);
 
+	/* Setup the wait queue for indicating virtchannel events */
+	init_waitqueue_head(&adapter->vc_waitqueue);
+
 	return 0;
 
 err_ioremap:
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 1603e99bae4a..7c98ac1fe458 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -598,6 +598,8 @@ static void iavf_mac_add_ok(struct iavf_adapter *adapter)
 	spin_lock_bh(&adapter->mac_vlan_list_lock);
 	list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) {
 		f->is_new_mac = false;
+		if (!f->add && !f->add_handled)
+			f->add_handled = true;
 	}
 	spin_unlock_bh(&adapter->mac_vlan_list_lock);
 }
@@ -618,6 +620,9 @@ static void iavf_mac_add_reject(struct iavf_adapter *adapter)
 		if (f->remove && ether_addr_equal(f->macaddr, netdev->dev_addr))
 			f->remove = false;
 
+		if (!f->add && !f->add_handled)
+			f->add_handled = true;
+
 		if (f->is_new_mac) {
 			list_del(&f->list);
 			kfree(f);
@@ -1970,6 +1975,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 			iavf_mac_add_reject(adapter);
 			/* restore administratively set MAC address */
 			ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr);
+			wake_up(&adapter->vc_waitqueue);
 			break;
 		case VIRTCHNL_OP_DEL_VLAN:
 			dev_err(&adapter->pdev->dev, "Failed to delete VLAN filter, error %s\n",
@@ -2134,7 +2140,13 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 		if (!v_retval)
 			iavf_mac_add_ok(adapter);
 		if (!ether_addr_equal(netdev->dev_addr, adapter->hw.mac.addr))
-			eth_hw_addr_set(netdev, adapter->hw.mac.addr);
+			if (!ether_addr_equal(netdev->dev_addr,
+					      adapter->hw.mac.addr)) {
+				netif_addr_lock_bh(netdev);
+				eth_hw_addr_set(netdev, adapter->hw.mac.addr);
+				netif_addr_unlock_bh(netdev);
+			}
+		wake_up(&adapter->vc_waitqueue);
 		break;
 	case VIRTCHNL_OP_GET_STATS: {
 		struct iavf_eth_stats *stats =
@@ -2164,10 +2176,11 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 			/* restore current mac address */
 			ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr);
 		} else {
+			netif_addr_lock_bh(netdev);
 			/* refresh current mac address if changed */
-			eth_hw_addr_set(netdev, adapter->hw.mac.addr);
 			ether_addr_copy(netdev->perm_addr,
 					adapter->hw.mac.addr);
+			netif_addr_unlock_bh(netdev);
 		}
 		spin_lock_bh(&adapter->mac_vlan_list_lock);
 		iavf_add_filter(adapter, adapter->hw.mac.addr);
@@ -2203,6 +2216,10 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 		}
 		fallthrough;
 	case VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS: {
+		struct iavf_mac_filter *f;
+		bool was_mac_changed;
+		u64 aq_required = 0;
+
 		if (v_opcode == VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS)
 			memcpy(&adapter->vlan_v2_caps, msg,
 			       min_t(u16, msglen,
@@ -2210,6 +2227,46 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 
 		iavf_process_config(adapter);
 		adapter->flags |= IAVF_FLAG_SETUP_NETDEV_FEATURES;
+		was_mac_changed = !ether_addr_equal(netdev->dev_addr,
+						    adapter->hw.mac.addr);
+
+		spin_lock_bh(&adapter->mac_vlan_list_lock);
+
+		/* re-add all MAC filters */
+		list_for_each_entry(f, &adapter->mac_filter_list, list) {
+			if (was_mac_changed &&
+			    ether_addr_equal(netdev->dev_addr, f->macaddr))
+				ether_addr_copy(f->macaddr,
+						adapter->hw.mac.addr);
+
+			f->is_new_mac = true;
+			f->add = true;
+			f->add_handled = false;
+			f->remove = false;
+		}
+
+		/* re-add all VLAN filters */
+		if (VLAN_FILTERING_ALLOWED(adapter)) {
+			struct iavf_vlan_filter *vlf;
+
+			if (!list_empty(&adapter->vlan_filter_list)) {
+				list_for_each_entry(vlf,
+						    &adapter->vlan_filter_list,
+						    list)
+					vlf->add = true;
+
+				aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER;
+			}
+		}
+
+		spin_unlock_bh(&adapter->mac_vlan_list_lock);
+
+		netif_addr_lock_bh(netdev);
+		eth_hw_addr_set(netdev, adapter->hw.mac.addr);
+		netif_addr_unlock_bh(netdev);
+
+		adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER |
+			aq_required;
 		}
 		break;
 	case VIRTCHNL_OP_ENABLE_QUEUES:
-- 
2.35.1

[PATCH AUTOSEL 5.18 22/93] net/mlx5: Add HW definitions of vport debug counters

[Sasha Levin]

From: Saeed Mahameed <saeedm@nvidia.com>

[ Upstream commit 3e94e61bd44d90070dcda53b647fdc826097ef26 ]

total_q_under_processor_handle - number of queues in error state due to an
async error or errored command.

send_queue_priority_update_flow - number of QP/SQ priority/SL update
events.

cq_overrun - number of times CQ entered an error state due to an
overflow.

async_eq_overrun -number of time an EQ mapped to async events was
overrun.

comp_eq_overrun - number of time an EQ mapped to completion events was
overrun.

quota_exceeded_command - number of commands issued and failed due to quota
exceeded.

invalid_command - number of commands issued and failed dues to any reason
other than quota exceeded.

Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Michael Guralnik <michaelgur@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/linux/mlx5/mlx5_ifc.h | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 2e162ec2a3d3..0df3cf33f48f 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1425,7 +1425,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         reserved_at_120[0xa];
 	u8         log_max_ra_req_dc[0x6];
-	u8         reserved_at_130[0xa];
+	u8         reserved_at_130[0x9];
+	u8         vnic_env_cq_overrun[0x1];
 	u8         log_max_ra_res_dc[0x6];
 
 	u8         reserved_at_140[0x5];
@@ -1620,7 +1621,11 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         nic_receive_steering_discard[0x1];
 	u8         receive_discard_vport_down[0x1];
 	u8         transmit_discard_vport_down[0x1];
-	u8         reserved_at_343[0x5];
+	u8         eq_overrun_count[0x1];
+	u8         reserved_at_344[0x1];
+	u8         invalid_command_count[0x1];
+	u8         quota_exceeded_count[0x1];
+	u8         reserved_at_347[0x1];
 	u8         log_max_flow_counter_bulk[0x8];
 	u8         max_flow_counter_15_0[0x10];
 
@@ -3394,11 +3399,21 @@ struct mlx5_ifc_vnic_diagnostic_statistics_bits {
 
 	u8         transmit_discard_vport_down[0x40];
 
-	u8         reserved_at_140[0xa0];
+	u8         async_eq_overrun[0x20];
+
+	u8         comp_eq_overrun[0x20];
+
+	u8         reserved_at_180[0x20];
+
+	u8         invalid_command[0x20];
+
+	u8         quota_exceeded_command[0x20];
 
 	u8         internal_rq_out_of_buffer[0x20];
 
-	u8         reserved_at_200[0xe00];
+	u8         cq_overrun[0x20];
+
+	u8         reserved_at_220[0xde0];
 };
 
 struct mlx5_ifc_traffic_counter_bits {
-- 
2.35.1

[PATCH AUTOSEL 5.18 25/93] net: phy: marvell-88x2222: set proper phydev->port

[Sasha Levin]

From: Ivan Bornyakov <i.bornyakov@metrotek.ru>

[ Upstream commit 9794ef5a68430946da2dfe7342be53b50bce9a41 ]

phydev->port was not set and always reported as PORT_TP.
Set phydev->port according to inserted SFP module.

Signed-off-by: Ivan Bornyakov <i.bornyakov@metrotek.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/phy/marvell-88x2222.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/phy/marvell-88x2222.c b/drivers/net/phy/marvell-88x2222.c
index d8b31d4d2a73..f070776ca904 100644
--- a/drivers/net/phy/marvell-88x2222.c
+++ b/drivers/net/phy/marvell-88x2222.c
@@ -490,6 +490,7 @@ static int mv2222_sfp_insert(void *upstream, const struct sfp_eeprom_id *id)
 	dev = &phydev->mdio.dev;
 
 	sfp_parse_support(phydev->sfp_bus, id, sfp_supported);
+	phydev->port = sfp_parse_port(phydev->sfp_bus, id, sfp_supported);
 	sfp_interface = sfp_select_interface(phydev->sfp_bus, sfp_supported);
 
 	dev_info(dev, "%s SFP module inserted\n", phy_modes(sfp_interface));
@@ -526,6 +527,7 @@ static void mv2222_sfp_remove(void *upstream)
 
 	priv->line_interface = PHY_INTERFACE_MODE_NA;
 	linkmode_zero(priv->supported);
+	phydev->port = PORT_NONE;
 }
 
 static void mv2222_sfp_link_up(void *upstream)
-- 
2.35.1

[PATCH AUTOSEL 5.18 26/93] selftests: mlxsw: resource_scale: Allow skipping a test

[Sasha Levin]

From: Petr Machata <petrm@nvidia.com>

[ Upstream commit 8cad339db339a39cb82b1188e4be4070a433abac ]

The scale tests are currently testing two things: that some number of
instances of a given resource can actually be created; and that when an
attempt is made to create more than the supported amount, the failures are
noted and handled gracefully.

Sometimes the scale test depends on more than one resource. In particular,
a following patch will add a RIF counter scale test, which depends on the
number of RIF counters that can be bound, and also on the number of RIFs
that can be created.

When the test is limited by the auxiliary resource and not by the primary
one, there's no point trying to run the overflow test, because it would be
testing exhaustion of the wrong resource.

To support this use case, when the $test_get_target yields 0, skip the test
instead.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Amit Cohen <amcohen@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh | 5 +++++
 .../selftests/drivers/net/mlxsw/spectrum/resource_scale.sh   | 4 ++++
 2 files changed, 9 insertions(+)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
index e9f65bd2e299..df920b6ed7c4 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
@@ -36,6 +36,11 @@ for current_test in ${TESTS:-$ALL_TESTS}; do
 	for should_fail in 0 1; do
 		RET=0
 		target=$(${current_test}_get_target "$should_fail")
+		if ((target == 0)); then
+			log_test_skip "'$current_test' should_fail=$should_fail test"
+			continue
+		fi
+
 		${current_test}_setup_prepare
 		setup_wait $num_netifs
 		${current_test}_test "$target" "$should_fail"
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
index dea33dc93790..b75d1fcd2db2 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
@@ -41,6 +41,10 @@ for current_test in ${TESTS:-$ALL_TESTS}; do
 		for should_fail in 0 1; do
 			RET=0
 			target=$(${current_test}_get_target "$should_fail")
+			if ((target == 0)); then
+				log_test_skip "'$current_test' [$profile] should_fail=$should_fail test"
+				continue
+			fi
 			${current_test}_setup_prepare
 			setup_wait $num_netifs
 			${current_test}_test "$target" "$should_fail"
-- 
2.35.1

[PATCH AUTOSEL 5.18 27/93] net: make xpcs_do_config to accept advertising for pcs-xpcs and sja1105

[Sasha Levin]

From: Ong Boon Leong <boon.leong.ong@intel.com>

[ Upstream commit fa9c562f9735d24c3253747eb21f3f0c0f6de48e ]

xpcs_config() has 'advertising' input that is required for C37 1000BASE-X
AN in later patch series. So, we prepare xpcs_do_config() for it.

For sja1105, xpcs_do_config() is used for xpcs configuration without
depending on advertising input, so set to NULL.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 2 +-
 drivers/net/pcs/pcs-xpcs.c             | 6 +++---
 include/linux/pcs/pcs-xpcs.h           | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 7734c6b1baca..48a9b61744bc 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -2331,7 +2331,7 @@ int sja1105_static_config_reload(struct sja1105_private *priv,
 		else
 			mode = MLO_AN_PHY;
 
-		rc = xpcs_do_config(xpcs, priv->phy_mode[i], mode);
+		rc = xpcs_do_config(xpcs, priv->phy_mode[i], mode, NULL);
 		if (rc < 0)
 			goto out;
 
diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index 61418d4dc0cd..b80e680220f5 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -797,7 +797,7 @@ static int xpcs_config_2500basex(struct dw_xpcs *xpcs)
 }
 
 int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface,
-		   unsigned int mode)
+		   unsigned int mode, const unsigned long *advertising)
 {
 	const struct xpcs_compat *compat;
 	int ret;
@@ -845,7 +845,7 @@ static int xpcs_config(struct phylink_pcs *pcs, unsigned int mode,
 {
 	struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs);
 
-	return xpcs_do_config(xpcs, interface, mode);
+	return xpcs_do_config(xpcs, interface, mode, advertising);
 }
 
 static int xpcs_get_state_c73(struct dw_xpcs *xpcs,
@@ -866,7 +866,7 @@ static int xpcs_get_state_c73(struct dw_xpcs *xpcs,
 
 		state->link = 0;
 
-		return xpcs_do_config(xpcs, state->interface, MLO_AN_INBAND);
+		return xpcs_do_config(xpcs, state->interface, MLO_AN_INBAND, NULL);
 	}
 
 	if (state->an_enabled && xpcs_aneg_done_c73(xpcs, state, compat)) {
diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h
index 266eb26fb029..37eb97cc2283 100644
--- a/include/linux/pcs/pcs-xpcs.h
+++ b/include/linux/pcs/pcs-xpcs.h
@@ -30,7 +30,7 @@ int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface);
 void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode,
 		  phy_interface_t interface, int speed, int duplex);
 int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface,
-		   unsigned int mode);
+		   unsigned int mode, const unsigned long *advertising);
 void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces);
 int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns,
 		    int enable);
-- 
2.35.1

[PATCH AUTOSEL 5.18 28/93] net: stmmac: make mdio register skips PHY scanning for fixed-link

[Sasha Levin]

From: Ong Boon Leong <boon.leong.ong@intel.com>

[ Upstream commit ab21cf920928a791aa70b8665b395294da17667c ]

stmmac_mdio_register() lacks fixed-link consideration and only skip PHY
scanning if it has done DT style PHY discovery. So, for DT or ACPI _DSD
setting of fixed-link, the PHY scanning should not happen.

v2: fix incorrect order related to fwnode that is not caught in non-DT
    platform.

Tested-by: Emilio Riva <emilio.riva@ericsson.com>
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 12 +++++++-----
 drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 14 ++++++++++++++
 2 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 6a7f63a58aef..98c4abbcd469 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1119,18 +1119,20 @@ static void stmmac_check_pcs_mode(struct stmmac_priv *priv)
 static int stmmac_init_phy(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
-	struct device_node *node;
+	struct fwnode_handle *fwnode;
 	int ret;
 
-	node = priv->plat->phylink_node;
+	fwnode = of_fwnode_handle(priv->plat->phylink_node);
+	if (!fwnode)
+		fwnode = dev_fwnode(priv->device);
 
-	if (node)
-		ret = phylink_of_phy_connect(priv->phylink, node, 0);
+	if (fwnode)
+		ret = phylink_fwnode_phy_connect(priv->phylink, fwnode, 0);
 
 	/* Some DT bindings do not set-up the PHY handle. Let's try to
 	 * manually parse it
 	 */
-	if (!node || ret) {
+	if (!fwnode || ret) {
 		int addr = priv->plat->phy_addr;
 		struct phy_device *phydev;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index a5d150c5f3d8..971e287aeb05 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -442,9 +442,11 @@ int stmmac_mdio_register(struct net_device *ndev)
 	int err = 0;
 	struct mii_bus *new_bus;
 	struct stmmac_priv *priv = netdev_priv(ndev);
+	struct fwnode_handle *fwnode = of_fwnode_handle(priv->plat->phylink_node);
 	struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data;
 	struct device_node *mdio_node = priv->plat->mdio_node;
 	struct device *dev = ndev->dev.parent;
+	struct fwnode_handle *fixed_node;
 	int addr, found, max_addr;
 
 	if (!mdio_bus_data)
@@ -498,6 +500,18 @@ int stmmac_mdio_register(struct net_device *ndev)
 	if (priv->plat->has_xgmac)
 		stmmac_xgmac2_mdio_read(new_bus, 0, MII_ADDR_C45);
 
+	/* If fixed-link is set, skip PHY scanning */
+	if (!fwnode)
+		fwnode = dev_fwnode(priv->device);
+
+	if (fwnode) {
+		fixed_node = fwnode_get_named_child_node(fwnode, "fixed-link");
+		if (fixed_node) {
+			fwnode_handle_put(fixed_node);
+			goto bus_register_done;
+		}
+	}
+
 	if (priv->plat->phy_node || mdio_node)
 		goto bus_register_done;
 
-- 
2.35.1

[PATCH AUTOSEL 5.18 29/93] net: dsa: ar9331: fix potential dead lock on mdio access

[Sasha Levin]

From: Oleksij Rempel <o.rempel@pengutronix.de>

[ Upstream commit 7a49f2193063b7db60a964fc26774275a4c964cd ]

Rework MDIO locking to avoid potential  circular locking:

 WARNING: possible circular locking dependency detected
 5.19.0-rc1-ar9331-00017-g3ab364c7c48c #5 Not tainted
 ------------------------------------------------------
 kworker/u2:4/68 is trying to acquire lock:
 81f3c83c (ar9331:1005:(&ar9331_mdio_regmap_config)->lock){+.+.}-{4:4}, at: regmap_write+0x50/0x8c

 but task is already holding lock:
 81f60494 (&bus->mdio_lock){+.+.}-{4:4}, at: mdiobus_read+0x40/0x78

 which lock already depends on the new lock.

 the existing dependency chain (in reverse order) is:

 -> #1 (&bus->mdio_lock){+.+.}-{4:4}:
        lock_acquire+0x2d4/0x360
        __mutex_lock+0xf8/0x384
        mutex_lock_nested+0x2c/0x38
        mdiobus_write+0x44/0x80
        ar9331_sw_bus_write+0x50/0xe4
        _regmap_raw_write_impl+0x604/0x724
        _regmap_bus_raw_write+0x9c/0xb4
        _regmap_write+0xdc/0x1a0
        _regmap_update_bits+0xf4/0x118
        _regmap_select_page+0x108/0x138
        _regmap_raw_read+0x25c/0x288
        _regmap_bus_read+0x60/0x98
        _regmap_read+0xd4/0x1b0
        _regmap_update_bits+0xc4/0x118
        regmap_update_bits_base+0x64/0x8c
        ar9331_sw_irq_bus_sync_unlock+0x40/0x6c
        __irq_set_handler+0x7c/0xac
        ar9331_sw_irq_map+0x48/0x7c
        irq_domain_associate+0x174/0x208
        irq_create_mapping_affinity+0x1a8/0x230
        ar9331_sw_probe+0x22c/0x388
        mdio_probe+0x44/0x70
        really_probe+0x200/0x424
        __driver_probe_device+0x290/0x298
        driver_probe_device+0x54/0xe4
        __device_attach_driver+0xe4/0x130
        bus_for_each_drv+0xb4/0xd8
        __device_attach+0x104/0x1a4
        bus_probe_device+0x48/0xc4
        device_add+0x600/0x800
        mdio_device_register+0x68/0xa0
        of_mdiobus_register+0x2bc/0x3c4
        ag71xx_probe+0x6e4/0x984
        platform_probe+0x78/0xd0
        really_probe+0x200/0x424
        __driver_probe_device+0x290/0x298
        driver_probe_device+0x54/0xe4
        __driver_attach+0x17c/0x190
        bus_for_each_dev+0x8c/0xd0
        bus_add_driver+0x110/0x228
        driver_register+0xe4/0x12c
        do_one_initcall+0x104/0x2a0
        kernel_init_freeable+0x250/0x288
        kernel_init+0x34/0x130
        ret_from_kernel_thread+0x14/0x1c

 -> #0 (ar9331:1005:(&ar9331_mdio_regmap_config)->lock){+.+.}-{4:4}:
        check_noncircular+0x88/0xc0
        __lock_acquire+0x10bc/0x18bc
        lock_acquire+0x2d4/0x360
        __mutex_lock+0xf8/0x384
        mutex_lock_nested+0x2c/0x38
        regmap_write+0x50/0x8c
        ar9331_sw_mbus_read+0x74/0x1b8
        __mdiobus_read+0x90/0xec
        mdiobus_read+0x50/0x78
        get_phy_device+0xa0/0x18c
        fwnode_mdiobus_register_phy+0x120/0x1d4
        of_mdiobus_register+0x244/0x3c4
        devm_of_mdiobus_register+0xe8/0x100
        ar9331_sw_setup+0x16c/0x3a0
        dsa_register_switch+0x7dc/0xcc0
        ar9331_sw_probe+0x370/0x388
        mdio_probe+0x44/0x70
        really_probe+0x200/0x424
        __driver_probe_device+0x290/0x298
        driver_probe_device+0x54/0xe4
        __device_attach_driver+0xe4/0x130
        bus_for_each_drv+0xb4/0xd8
        __device_attach+0x104/0x1a4
        bus_probe_device+0x48/0xc4
        deferred_probe_work_func+0xf0/0x10c
        process_one_work+0x314/0x4d4
        worker_thread+0x2a4/0x354
        kthread+0x134/0x13c
        ret_from_kernel_thread+0x14/0x1c

 other info that might help us debug this:

  Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   lock(&bus->mdio_lock);
                                lock(ar9331:1005:(&ar9331_mdio_regmap_config)->lock);
                                lock(&bus->mdio_lock);
   lock(ar9331:1005:(&ar9331_mdio_regmap_config)->lock);

  *** DEADLOCK ***

 5 locks held by kworker/u2:4/68:
  #0: 81c04eb4 ((wq_completion)events_unbound){+.+.}-{0:0}, at: process_one_work+0x1e4/0x4d4
  #1: 81f0de78 (deferred_probe_work){+.+.}-{0:0}, at: process_one_work+0x1e4/0x4d4
  #2: 81f0a880 (&dev->mutex){....}-{4:4}, at: __device_attach+0x40/0x1a4
  #3: 80c8aee0 (dsa2_mutex){+.+.}-{4:4}, at: dsa_register_switch+0x5c/0xcc0
  #4: 81f60494 (&bus->mdio_lock){+.+.}-{4:4}, at: mdiobus_read+0x40/0x78

 stack backtrace:
 CPU: 0 PID: 68 Comm: kworker/u2:4 Not tainted 5.19.0-rc1-ar9331-00017-g3ab364c7c48c #5
 Workqueue: events_unbound deferred_probe_work_func
 Stack : 00000056 800d4638 81f0d64c 00000004 00000018 00000000 80a20000 80a20000
         80937590 81ef3858 81f0d760 3913578a 00000005 8045e824 81f0d600 a8db84cc
         00000000 00000000 80937590 00000a44 00000000 00000002 00000001 ffffffff
         81f0d6a4 80982d7c 0000000f 20202020 80a20000 00000001 80937590 81ef3858
         81f0d760 3913578a 00000005 00000005 00000000 03bd0000 00000000 80e00000
         ...
 Call Trace:
 [<80069db0>] show_stack+0x94/0x130
 [<8045e824>] dump_stack_lvl+0x54/0x8c
 [<800c7fac>] check_noncircular+0x88/0xc0
 [<800ca068>] __lock_acquire+0x10bc/0x18bc
 [<800cb478>] lock_acquire+0x2d4/0x360
 [<807b84c4>] __mutex_lock+0xf8/0x384
 [<807b877c>] mutex_lock_nested+0x2c/0x38
 [<804ea640>] regmap_write+0x50/0x8c
 [<80501e38>] ar9331_sw_mbus_read+0x74/0x1b8
 [<804fe9a0>] __mdiobus_read+0x90/0xec
 [<804feac4>] mdiobus_read+0x50/0x78
 [<804fcf74>] get_phy_device+0xa0/0x18c
 [<804ffeb4>] fwnode_mdiobus_register_phy+0x120/0x1d4
 [<805004f0>] of_mdiobus_register+0x244/0x3c4
 [<804f0c50>] devm_of_mdiobus_register+0xe8/0x100
 [<805017a0>] ar9331_sw_setup+0x16c/0x3a0
 [<807355c8>] dsa_register_switch+0x7dc/0xcc0
 [<80501468>] ar9331_sw_probe+0x370/0x388
 [<804ff0c0>] mdio_probe+0x44/0x70
 [<804d1848>] really_probe+0x200/0x424
 [<804d1cfc>] __driver_probe_device+0x290/0x298
 [<804d1d58>] driver_probe_device+0x54/0xe4
 [<804d2298>] __device_attach_driver+0xe4/0x130
 [<804cf048>] bus_for_each_drv+0xb4/0xd8
 [<804d200c>] __device_attach+0x104/0x1a4
 [<804d026c>] bus_probe_device+0x48/0xc4
 [<804d108c>] deferred_probe_work_func+0xf0/0x10c
 [<800a0ffc>] process_one_work+0x314/0x4d4
 [<800a17fc>] worker_thread+0x2a4/0x354
 [<800a9a54>] kthread+0x134/0x13c
 [<8006306c>] ret_from_kernel_thread+0x14/0x1c
[

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://lore.kernel.org/r/20220616112550.877118-1-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/dsa/qca/ar9331.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/qca/ar9331.c b/drivers/net/dsa/qca/ar9331.c
index e5098cfe44bc..f23ce56fa591 100644
--- a/drivers/net/dsa/qca/ar9331.c
+++ b/drivers/net/dsa/qca/ar9331.c
@@ -818,7 +818,7 @@ static int __ar9331_mdio_write(struct mii_bus *sbus, u8 mode, u16 reg, u16 val)
 		FIELD_GET(AR9331_SW_LOW_ADDR_PHY, reg);
 	r = FIELD_GET(AR9331_SW_LOW_ADDR_REG, reg);
 
-	return mdiobus_write(sbus, p, r, val);
+	return __mdiobus_write(sbus, p, r, val);
 }
 
 static int __ar9331_mdio_read(struct mii_bus *sbus, u16 reg)
@@ -829,7 +829,7 @@ static int __ar9331_mdio_read(struct mii_bus *sbus, u16 reg)
 		FIELD_GET(AR9331_SW_LOW_ADDR_PHY, reg);
 	r = FIELD_GET(AR9331_SW_LOW_ADDR_REG, reg);
 
-	return mdiobus_read(sbus, p, r);
+	return __mdiobus_read(sbus, p, r);
 }
 
 static int ar9331_mdio_read(void *ctx, const void *reg_buf, size_t reg_len,
@@ -849,6 +849,8 @@ static int ar9331_mdio_read(void *ctx, const void *reg_buf, size_t reg_len,
 		return 0;
 	}
 
+	mutex_lock_nested(&sbus->mdio_lock, MDIO_MUTEX_NESTED);
+
 	ret = __ar9331_mdio_read(sbus, reg);
 	if (ret < 0)
 		goto error;
@@ -860,9 +862,13 @@ static int ar9331_mdio_read(void *ctx, const void *reg_buf, size_t reg_len,
 
 	*(u32 *)val_buf |= ret << 16;
 
+	mutex_unlock(&sbus->mdio_lock);
+
 	return 0;
 error:
+	mutex_unlock(&sbus->mdio_lock);
 	dev_err_ratelimited(&sbus->dev, "Bus error. Failed to read register.\n");
+
 	return ret;
 }
 
@@ -872,12 +878,15 @@ static int ar9331_mdio_write(void *ctx, u32 reg, u32 val)
 	struct mii_bus *sbus = priv->sbus;
 	int ret;
 
+	mutex_lock_nested(&sbus->mdio_lock, MDIO_MUTEX_NESTED);
 	if (reg == AR9331_SW_REG_PAGE) {
 		ret = __ar9331_mdio_write(sbus, AR9331_SW_MDIO_PHY_MODE_PAGE,
 					  0, val);
 		if (ret < 0)
 			goto error;
 
+		mutex_unlock(&sbus->mdio_lock);
+
 		return 0;
 	}
 
@@ -897,10 +906,14 @@ static int ar9331_mdio_write(void *ctx, u32 reg, u32 val)
 	if (ret < 0)
 		goto error;
 
+	mutex_unlock(&sbus->mdio_lock);
+
 	return 0;
 
 error:
+	mutex_unlock(&sbus->mdio_lock);
 	dev_err_ratelimited(&sbus->dev, "Bus error. Failed to write register.\n");
+
 	return ret;
 }
 
-- 
2.35.1

[PATCH AUTOSEL 5.18 40/93] mlxsw: cmd: Increase 'config_profile.flood_mode' length

[Sasha Levin]

From: Amit Cohen <amcohen@nvidia.com>

[ Upstream commit 89df3c6261f271c550f120b5ccf4d9c5132e870c ]

Currently, the length of 'config_profile.flood_mode' is defined as 2
bits, while the correct length is 3 bits.

As preparation for unified bridge model, which will use the whole field
length, fix it and increase the field to the correct size.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/cmd.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
index 51b260d54237..0abd69040ba0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
@@ -745,7 +745,7 @@ MLXSW_ITEM32(cmd_mbox, config_profile, max_vid_flood_tables, 0x30, 8, 4);
  * max_fid_offset_flood_tables indicates the number of FID-offset tables.
  * max_fid_flood_tables indicates the number of per-FID tables.
  */
-MLXSW_ITEM32(cmd_mbox, config_profile, flood_mode, 0x30, 0, 2);
+MLXSW_ITEM32(cmd_mbox, config_profile, flood_mode, 0x30, 0, 3);
 
 /* cmd_mbox_config_profile_max_fid_offset_flood_tables
  * Maximum number of FID-offset flooding tables.
-- 
2.35.1

[PATCH AUTOSEL 5.18 46/93] ipv6/addrconf: fix timing bug in tempaddr regen

[Sasha Levin]

From: Sam Edwards <cfsworks@gmail.com>

[ Upstream commit 778964f2fdf05e5d2e6ca9bc3f450b3db454ba9c ]

The addrconf_verify_rtnl() function uses a big if/elseif/elseif/... block
to categorize each address by what type of attention it needs.  An
about-to-expire (RFC 4941) temporary address is one such category, but the
previous elseif branch catches addresses that have already run out their
prefered_lft.  This means that if addrconf_verify_rtnl() fails to run in
the necessary time window (i.e. REGEN_ADVANCE time units before the end of
the prefered_lft), the temporary address will never be regenerated, and no
temporary addresses will be available until each one's valid_lft runs out
and manage_tempaddrs() begins anew.

Fix this by moving the entire temporary address regeneration case out of
that block.  That block is supposed to implement the "destructive" part of
an address's lifecycle, and regenerating a fresh temporary address is not,
semantically speaking, actually tied to any particular lifecycle stage.
The age test is also changed from `age >= prefered_lft - regen_advance`
to `age + regen_advance >= prefered_lft` instead, to ensure no underflow
occurs if the system administrator increases the regen_advance to a value
greater than the already-set prefered_lft.

Note that this does not fix the problem of addrconf_verify_rtnl() sometimes
not running in time, resulting in the race condition described in RFC 4941
section 3.4 - it only ensures that the address is regenerated.  Fixing THAT
problem may require either using jiffies instead of seconds for all time
arithmetic here, or always rounding up when regen_advance is converted to
seconds.

Signed-off-by: Sam Edwards <CFSworks@gmail.com>
Link: https://lore.kernel.org/r/20220623181103.7033-1-CFSworks@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/ipv6/addrconf.c | 62 ++++++++++++++++++++++++---------------------
 1 file changed, 33 insertions(+), 29 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 3b47c901c832..01e3900dd2f8 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4522,6 +4522,39 @@ static void addrconf_verify_rtnl(struct net *net)
 			/* We try to batch several events at once. */
 			age = (now - ifp->tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
 
+			if ((ifp->flags&IFA_F_TEMPORARY) &&
+			    !(ifp->flags&IFA_F_TENTATIVE) &&
+			    ifp->prefered_lft != INFINITY_LIFE_TIME &&
+			    !ifp->regen_count && ifp->ifpub) {
+				/* This is a non-regenerated temporary addr. */
+
+				unsigned long regen_advance = ifp->idev->cnf.regen_max_retry *
+					ifp->idev->cnf.dad_transmits *
+					max(NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME), HZ/100) / HZ;
+
+				if (age + regen_advance >= ifp->prefered_lft) {
+					struct inet6_ifaddr *ifpub = ifp->ifpub;
+					if (time_before(ifp->tstamp + ifp->prefered_lft * HZ, next))
+						next = ifp->tstamp + ifp->prefered_lft * HZ;
+
+					ifp->regen_count++;
+					in6_ifa_hold(ifp);
+					in6_ifa_hold(ifpub);
+					spin_unlock(&ifp->lock);
+
+					spin_lock(&ifpub->lock);
+					ifpub->regen_count = 0;
+					spin_unlock(&ifpub->lock);
+					rcu_read_unlock_bh();
+					ipv6_create_tempaddr(ifpub, true);
+					in6_ifa_put(ifpub);
+					in6_ifa_put(ifp);
+					rcu_read_lock_bh();
+					goto restart;
+				} else if (time_before(ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ, next))
+					next = ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ;
+			}
+
 			if (ifp->valid_lft != INFINITY_LIFE_TIME &&
 			    age >= ifp->valid_lft) {
 				spin_unlock(&ifp->lock);
@@ -4555,35 +4588,6 @@ static void addrconf_verify_rtnl(struct net *net)
 					in6_ifa_put(ifp);
 					goto restart;
 				}
-			} else if ((ifp->flags&IFA_F_TEMPORARY) &&
-				   !(ifp->flags&IFA_F_TENTATIVE)) {
-				unsigned long regen_advance = ifp->idev->cnf.regen_max_retry *
-					ifp->idev->cnf.dad_transmits *
-					max(NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME), HZ/100) / HZ;
-
-				if (age >= ifp->prefered_lft - regen_advance) {
-					struct inet6_ifaddr *ifpub = ifp->ifpub;
-					if (time_before(ifp->tstamp + ifp->prefered_lft * HZ, next))
-						next = ifp->tstamp + ifp->prefered_lft * HZ;
-					if (!ifp->regen_count && ifpub) {
-						ifp->regen_count++;
-						in6_ifa_hold(ifp);
-						in6_ifa_hold(ifpub);
-						spin_unlock(&ifp->lock);
-
-						spin_lock(&ifpub->lock);
-						ifpub->regen_count = 0;
-						spin_unlock(&ifpub->lock);
-						rcu_read_unlock_bh();
-						ipv6_create_tempaddr(ifpub, true);
-						in6_ifa_put(ifpub);
-						in6_ifa_put(ifp);
-						rcu_read_lock_bh();
-						goto restart;
-					}
-				} else if (time_before(ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ, next))
-					next = ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ;
-				spin_unlock(&ifp->lock);
 			} else {
 				/* ifp->prefered_lft <= ifp->valid_lft */
 				if (time_before(ifp->tstamp + ifp->prefered_lft * HZ, next))
-- 
2.35.1

[PATCH AUTOSEL 5.18 50/93] octeontx2-af: fix operand size in bitwise operation

[Sasha Levin]

From: Shijith Thotton <sthotton@marvell.com>

[ Upstream commit b14056914357beee6a84f6ff1b9195f4659fab9d ]

Made size of operands same in bitwise operations.

The patch fixes the klocwork issue, operands in a bitwise operation have
different size at line 375 and 483.

Signed-off-by: Shijith Thotton <sthotton@marvell.com>
Link: https://lore.kernel.org/r/f4fba33fe4f89b420b4da11d51255e7cc6ea1dbf.1656586269.git.sthotton@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
index a9da85e418a4..38bbae5d9ae0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
@@ -17,7 +17,7 @@
 #define	PCI_DEVID_OTX2_CPT10K_PF 0xA0F2
 
 /* Length of initial context fetch in 128 byte words */
-#define CPT_CTX_ILEN    2
+#define CPT_CTX_ILEN    2ULL
 
 #define cpt_get_eng_sts(e_min, e_max, rsp, etype)                   \
 ({                                                                  \
@@ -480,7 +480,7 @@ static int cpt_inline_ipsec_cfg_inbound(struct rvu *rvu, int blkaddr, u8 cptlf,
 	 */
 	if (!is_rvu_otx2(rvu)) {
 		val = (ilog2(NIX_CHAN_CPT_X2P_MASK + 1) << 16);
-		val |= rvu->hw->cpt_chan_base;
+		val |= (u64)rvu->hw->cpt_chan_base;
 
 		rvu_write64(rvu, blkaddr, CPT_AF_X2PX_LINK_CFG(0), val);
 		rvu_write64(rvu, blkaddr, CPT_AF_X2PX_LINK_CFG(1), val);
-- 
2.35.1

[PATCH AUTOSEL 5.18 59/93] octeontx2-af: Don't reset previous pfc config

[Sasha Levin]

From: Hariprasad Kelam <hkelam@marvell.com>

[ Upstream commit 8e1514579246ddc36ba0b860fc8bdd03be085aee ]

Current implementation is such that driver first resets the
existing PFC config before applying new pfc configuration.
This creates a problem like once PF or VFs requests PFC config
previous pfc config by other PFVfs is getting reset.

This patch fixes the problem by removing unnecessary resetting
of PFC config. Also configure Pause quanta value to smaller as
current value is too high.

Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../net/ethernet/marvell/octeontx2/af/cgx.c    | 15 +++++++++++----
 .../net/ethernet/marvell/octeontx2/af/rpm.c    | 18 +++++++++++-------
 .../net/ethernet/marvell/octeontx2/af/rpm.h    |  3 +--
 3 files changed, 23 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 25491edc35ce..931a1a7ebf76 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -847,6 +847,11 @@ static void cgx_lmac_pause_frm_config(void *cgxd, int lmac_id, bool enable)
 	cfg |= CGX_CMR_RX_OVR_BP_EN(lmac_id);
 	cfg &= ~CGX_CMR_RX_OVR_BP_BP(lmac_id);
 	cgx_write(cgx, 0, CGXX_CMR_RX_OVR_BP, cfg);
+
+	/* Disable all PFC classes by default */
+	cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_CBFC_CTL);
+	cfg = FIELD_SET(CGX_PFC_CLASS_MASK, 0, cfg);
+	cgx_write(cgx, lmac_id, CGXX_SMUX_CBFC_CTL, cfg);
 }
 
 int verify_lmac_fc_cfg(void *cgxd, int lmac_id, u8 tx_pause, u8 rx_pause,
@@ -899,6 +904,7 @@ int cgx_lmac_pfc_config(void *cgxd, int lmac_id, u8 tx_pause,
 		return 0;
 
 	cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_CBFC_CTL);
+	pfc_en |= FIELD_GET(CGX_PFC_CLASS_MASK, cfg);
 
 	if (rx_pause) {
 		cfg |= (CGXX_SMUX_CBFC_CTL_RX_EN |
@@ -910,12 +916,13 @@ int cgx_lmac_pfc_config(void *cgxd, int lmac_id, u8 tx_pause,
 			CGXX_SMUX_CBFC_CTL_DRP_EN);
 	}
 
-	if (tx_pause)
+	if (tx_pause) {
 		cfg |= CGXX_SMUX_CBFC_CTL_TX_EN;
-	else
+		cfg = FIELD_SET(CGX_PFC_CLASS_MASK, pfc_en, cfg);
+	} else {
 		cfg &= ~CGXX_SMUX_CBFC_CTL_TX_EN;
-
-	cfg = FIELD_SET(CGX_PFC_CLASS_MASK, pfc_en, cfg);
+		cfg = FIELD_SET(CGX_PFC_CLASS_MASK, 0, cfg);
+	}
 
 	cgx_write(cgx, lmac_id, CGXX_SMUX_CBFC_CTL, cfg);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
index 47e83d7a5804..05666922a45b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
@@ -276,6 +276,11 @@ void rpm_lmac_pause_frm_config(void *rpmd, int lmac_id, bool enable)
 	cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG);
 	cfg |= RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE;
 	rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg);
+
+	/* Disable all PFC classes */
+	cfg = rpm_read(rpm, lmac_id, RPMX_CMRX_PRT_CBFC_CTL);
+	cfg = FIELD_SET(RPM_PFC_CLASS_MASK, 0, cfg);
+	rpm_write(rpm, lmac_id, RPMX_CMRX_PRT_CBFC_CTL, cfg);
 }
 
 int rpm_get_rx_stats(void *rpmd, int lmac_id, int idx, u64 *rx_stat)
@@ -387,15 +392,14 @@ void rpm_lmac_ptp_config(void *rpmd, int lmac_id, bool enable)
 int rpm_lmac_pfc_config(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause, u16 pfc_en)
 {
 	rpm_t *rpm = rpmd;
-	u64 cfg;
+	u64 cfg, class_en;
 
 	if (!is_lmac_valid(rpm, lmac_id))
 		return -ENODEV;
 
-	/* reset PFC class quanta and threshold */
-	rpm_cfg_pfc_quanta_thresh(rpm, lmac_id, 0xffff, false);
-
 	cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG);
+	class_en = rpm_read(rpm, lmac_id, RPMX_CMRX_PRT_CBFC_CTL);
+	pfc_en |= FIELD_GET(RPM_PFC_CLASS_MASK, class_en);
 
 	if (rx_pause) {
 		cfg &= ~(RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE |
@@ -410,9 +414,11 @@ int rpm_lmac_pfc_config(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause, u16 p
 	if (tx_pause) {
 		rpm_cfg_pfc_quanta_thresh(rpm, lmac_id, pfc_en, true);
 		cfg &= ~RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE;
+		class_en = FIELD_SET(RPM_PFC_CLASS_MASK, pfc_en, class_en);
 	} else {
 		rpm_cfg_pfc_quanta_thresh(rpm, lmac_id, 0xfff, false);
 		cfg |= RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE;
+		class_en = FIELD_SET(RPM_PFC_CLASS_MASK, 0, class_en);
 	}
 
 	if (!rx_pause && !tx_pause)
@@ -422,9 +428,7 @@ int rpm_lmac_pfc_config(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause, u16 p
 
 	rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg);
 
-	cfg = rpm_read(rpm, lmac_id, RPMX_CMRX_PRT_CBFC_CTL);
-	cfg = FIELD_SET(RPM_PFC_CLASS_MASK, pfc_en, cfg);
-	rpm_write(rpm, lmac_id, RPMX_CMRX_PRT_CBFC_CTL, cfg);
+	rpm_write(rpm, lmac_id, RPMX_CMRX_PRT_CBFC_CTL, class_en);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h
index 9ab8d49dd180..8205f2626f61 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h
@@ -48,7 +48,6 @@
 #define RPMX_MTI_MAC100X_CL1011_QUANTA_THRESH		0x8130
 #define RPMX_MTI_MAC100X_CL1213_QUANTA_THRESH		0x8138
 #define RPMX_MTI_MAC100X_CL1415_QUANTA_THRESH		0x8140
-#define RPM_DEFAULT_PAUSE_TIME			0xFFFF
 #define RPMX_CMR_RX_OVR_BP		0x4120
 #define RPMX_CMR_RX_OVR_BP_EN(x)	BIT_ULL((x) + 8)
 #define RPMX_CMR_RX_OVR_BP_BP(x)	BIT_ULL((x) + 4)
@@ -70,7 +69,7 @@
 #define RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD              BIT_ULL(7)
 #define RPMX_MTI_MAC100X_CL01_PAUSE_QUANTA              0x80A8
 #define RPMX_MTI_MAC100X_CL89_PAUSE_QUANTA		0x8108
-#define RPM_DEFAULT_PAUSE_TIME                          0xFFFF
+#define RPM_DEFAULT_PAUSE_TIME                          0x7FF
 
 /* Function Declarations */
 int rpm_get_nr_lmacs(void *rpmd);
-- 
2.35.1

[PATCH AUTOSEL 5.18 61/93] bpf: Make non-preallocated allocation low priority

[Sasha Levin]

From: Yafang Shao <laoar.shao@gmail.com>

[ Upstream commit ace2bee839e08df324cb320763258dfd72e6120e ]

GFP_ATOMIC doesn't cooperate well with memcg pressure so far, especially
if we allocate too much GFP_ATOMIC memory. For example, when we set the
memcg limit to limit a non-preallocated bpf memory, the GFP_ATOMIC can
easily break the memcg limit by force charge. So it is very dangerous to
use GFP_ATOMIC in non-preallocated case. One way to make it safe is to
remove __GFP_HIGH from GFP_ATOMIC, IOW, use (__GFP_ATOMIC |
__GFP_KSWAPD_RECLAIM) instead, then it will be limited if we allocate
too much memory. There's a plan to completely remove __GFP_ATOMIC in the
mm side[1], so let's use GFP_NOWAIT instead.

We introduced BPF_F_NO_PREALLOC is because full map pre-allocation is
too memory expensive for some cases. That means removing __GFP_HIGH
doesn't break the rule of BPF_F_NO_PREALLOC, but has the same goal with
it-avoiding issues caused by too much memory. So let's remove it.

This fix can also apply to other run-time allocations, for example, the
allocation in lpm trie, local storage and devmap. So let fix it
consistently over the bpf code

It also fixes a typo in the comment.

[1]. https://lore.kernel.org/linux-mm/163712397076.13692.4727608274002939094@noble.neil.brown.name/

Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: NeilBrown <neilb@suse.de>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Link: https://lore.kernel.org/r/20220709154457.57379-2-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/bpf/devmap.c        | 2 +-
 kernel/bpf/hashtab.c       | 6 +++---
 kernel/bpf/local_storage.c | 2 +-
 kernel/bpf/lpm_trie.c      | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 038f6d7a83e4..bdb8ccab4be2 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -844,7 +844,7 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
 	struct bpf_dtab_netdev *dev;
 
 	dev = bpf_map_kmalloc_node(&dtab->map, sizeof(*dev),
-				   GFP_ATOMIC | __GFP_NOWARN,
+				   GFP_NOWAIT | __GFP_NOWARN,
 				   dtab->map.numa_node);
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 65877967f414..f8b5a4a86827 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -60,7 +60,7 @@
  *
  * As regular device interrupt handlers and soft interrupts are forced into
  * thread context, the existing code which does
- *   spin_lock*(); alloc(GPF_ATOMIC); spin_unlock*();
+ *   spin_lock*(); alloc(GFP_ATOMIC); spin_unlock*();
  * just works.
  *
  * In theory the BPF locks could be converted to regular spinlocks as well,
@@ -955,7 +955,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 				goto dec_count;
 			}
 		l_new = bpf_map_kmalloc_node(&htab->map, htab->elem_size,
-					     GFP_ATOMIC | __GFP_NOWARN,
+					     GFP_NOWAIT | __GFP_NOWARN,
 					     htab->map.numa_node);
 		if (!l_new) {
 			l_new = ERR_PTR(-ENOMEM);
@@ -973,7 +973,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 		} else {
 			/* alloc_percpu zero-fills */
 			pptr = bpf_map_alloc_percpu(&htab->map, size, 8,
-						    GFP_ATOMIC | __GFP_NOWARN);
+						    GFP_NOWAIT | __GFP_NOWARN);
 			if (!pptr) {
 				kfree(l_new);
 				l_new = ERR_PTR(-ENOMEM);
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 497916060ac7..ba6716903816 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -164,7 +164,7 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *key,
 	}
 
 	new = bpf_map_kmalloc_node(map, struct_size(new, data, map->value_size),
-				   __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN,
+				   __GFP_ZERO | GFP_NOWAIT | __GFP_NOWARN,
 				   map->numa_node);
 	if (!new)
 		return -ENOMEM;
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 5763cc7ac4f1..f0b3e1552923 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -284,7 +284,7 @@ static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie,
 	if (value)
 		size += trie->map.value_size;
 
-	node = bpf_map_kmalloc_node(&trie->map, size, GFP_ATOMIC | __GFP_NOWARN,
+	node = bpf_map_kmalloc_node(&trie->map, size, GFP_NOWAIT | __GFP_NOWARN,
 				    trie->map.numa_node);
 	if (!node)
 		return NULL;
-- 
2.35.1

[PATCH AUTOSEL 5.18 68/93] net: devlink: avoid false DEADLOCK warning reported by lockdep

[Sasha Levin]

From: Moshe Shemesh <moshe@nvidia.com>

[ Upstream commit e26fde2f5befad0951fe6345403616bf51e901be ]

Add a lock_class_key per devlink instance to avoid DEADLOCK warning by
lockdep, while locking more than one devlink instance in driver code,
for example in opening VFs flow.

Kernel log:
[  101.433802] ============================================
[  101.433803] WARNING: possible recursive locking detected
[  101.433810] 5.19.0-rc1+ #35 Not tainted
[  101.433812] --------------------------------------------
[  101.433813] bash/892 is trying to acquire lock:
[  101.433815] ffff888127bfc2f8 (&devlink->lock){+.+.}-{3:3}, at: probe_one+0x3c/0x690 [mlx5_core]
[  101.433909]
               but task is already holding lock:
[  101.433910] ffff888118f4c2f8 (&devlink->lock){+.+.}-{3:3}, at: mlx5_core_sriov_configure+0x62/0x280 [mlx5_core]
[  101.433989]
               other info that might help us debug this:
[  101.433990]  Possible unsafe locking scenario:

[  101.433991]        CPU0
[  101.433991]        ----
[  101.433992]   lock(&devlink->lock);
[  101.433993]   lock(&devlink->lock);
[  101.433995]
                *** DEADLOCK ***

[  101.433996]  May be due to missing lock nesting notation

[  101.433996] 6 locks held by bash/892:
[  101.433998]  #0: ffff88810eb50448 (sb_writers#3){.+.+}-{0:0}, at: ksys_write+0xf3/0x1d0
[  101.434009]  #1: ffff888114777c88 (&of->mutex){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x20d/0x520
[  101.434017]  #2: ffff888102b58660 (kn->active#231){.+.+}-{0:0}, at: kernfs_fop_write_iter+0x230/0x520
[  101.434023]  #3: ffff888102d70198 (&dev->mutex){....}-{3:3}, at: sriov_numvfs_store+0x132/0x310
[  101.434031]  #4: ffff888118f4c2f8 (&devlink->lock){+.+.}-{3:3}, at: mlx5_core_sriov_configure+0x62/0x280 [mlx5_core]
[  101.434108]  #5: ffff88812adce198 (&dev->mutex){....}-{3:3}, at: __device_attach+0x76/0x430
[  101.434116]
               stack backtrace:
[  101.434118] CPU: 5 PID: 892 Comm: bash Not tainted 5.19.0-rc1+ #35
[  101.434120] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
[  101.434130] Call Trace:
[  101.434133]  <TASK>
[  101.434135]  dump_stack_lvl+0x57/0x7d
[  101.434145]  __lock_acquire.cold+0x1df/0x3e7
[  101.434151]  ? register_lock_class+0x1880/0x1880
[  101.434157]  lock_acquire+0x1c1/0x550
[  101.434160]  ? probe_one+0x3c/0x690 [mlx5_core]
[  101.434229]  ? lockdep_hardirqs_on_prepare+0x400/0x400
[  101.434232]  ? __xa_alloc+0x1ed/0x2d0
[  101.434236]  ? ksys_write+0xf3/0x1d0
[  101.434239]  __mutex_lock+0x12c/0x14b0
[  101.434243]  ? probe_one+0x3c/0x690 [mlx5_core]
[  101.434312]  ? probe_one+0x3c/0x690 [mlx5_core]
[  101.434380]  ? devlink_alloc_ns+0x11b/0x910
[  101.434385]  ? mutex_lock_io_nested+0x1320/0x1320
[  101.434388]  ? lockdep_init_map_type+0x21a/0x7d0
[  101.434391]  ? lockdep_init_map_type+0x21a/0x7d0
[  101.434393]  ? __init_swait_queue_head+0x70/0xd0
[  101.434397]  probe_one+0x3c/0x690 [mlx5_core]
[  101.434467]  pci_device_probe+0x1b4/0x480
[  101.434471]  really_probe+0x1e0/0xaa0
[  101.434474]  __driver_probe_device+0x219/0x480
[  101.434478]  driver_probe_device+0x49/0x130
[  101.434481]  __device_attach_driver+0x1b8/0x280
[  101.434484]  ? driver_allows_async_probing+0x140/0x140
[  101.434487]  bus_for_each_drv+0x123/0x1a0
[  101.434489]  ? bus_for_each_dev+0x1a0/0x1a0
[  101.434491]  ? lockdep_hardirqs_on_prepare+0x286/0x400
[  101.434494]  ? trace_hardirqs_on+0x2d/0x100
[  101.434498]  __device_attach+0x1a3/0x430
[  101.434501]  ? device_driver_attach+0x1e0/0x1e0
[  101.434503]  ? pci_bridge_d3_possible+0x1e0/0x1e0
[  101.434506]  ? pci_create_resource_files+0xeb/0x190
[  101.434511]  pci_bus_add_device+0x6c/0xa0
[  101.434514]  pci_iov_add_virtfn+0x9e4/0xe00
[  101.434517]  ? trace_hardirqs_on+0x2d/0x100
[  101.434521]  sriov_enable+0x64a/0xca0
[  101.434524]  ? pcibios_sriov_disable+0x10/0x10
[  101.434528]  mlx5_core_sriov_configure+0xab/0x280 [mlx5_core]
[  101.434602]  sriov_numvfs_store+0x20a/0x310
[  101.434605]  ? sriov_totalvfs_show+0xc0/0xc0
[  101.434608]  ? sysfs_file_ops+0x170/0x170
[  101.434611]  ? sysfs_file_ops+0x117/0x170
[  101.434614]  ? sysfs_file_ops+0x170/0x170
[  101.434616]  kernfs_fop_write_iter+0x348/0x520
[  101.434619]  new_sync_write+0x2e5/0x520
[  101.434621]  ? new_sync_read+0x520/0x520
[  101.434624]  ? lock_acquire+0x1c1/0x550
[  101.434626]  ? lockdep_hardirqs_on_prepare+0x400/0x400
[  101.434630]  vfs_write+0x5cb/0x8d0
[  101.434633]  ksys_write+0xf3/0x1d0
[  101.434635]  ? __x64_sys_read+0xb0/0xb0
[  101.434638]  ? lockdep_hardirqs_on_prepare+0x286/0x400
[  101.434640]  ? syscall_enter_from_user_mode+0x1d/0x50
[  101.434643]  do_syscall_64+0x3d/0x90
[  101.434647]  entry_SYSCALL_64_after_hwframe+0x46/0xb0
[  101.434650] RIP: 0033:0x7f5ff536b2f7
[  101.434658] Code: 0d 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f
1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f
05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24
[  101.434661] RSP: 002b:00007ffd9ea85d58 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
[  101.434664] RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007f5ff536b2f7
[  101.434666] RDX: 0000000000000002 RSI: 000055c4c279e230 RDI: 0000000000000001
[  101.434668] RBP: 000055c4c279e230 R08: 000000000000000a R09: 0000000000000001
[  101.434669] R10: 000055c4c283cbf0 R11: 0000000000000246 R12: 0000000000000002
[  101.434670] R13: 00007f5ff543d500 R14: 0000000000000002 R15: 00007f5ff543d700
[  101.434673]  </TASK>

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/core/devlink.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/core/devlink.c b/net/core/devlink.c
index aeca13b6e57b..2c665396a707 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -64,6 +64,7 @@ struct devlink {
 	 * port, sb, dpipe, resource, params, region, traps and more.
 	 */
 	struct mutex lock;
+	struct lock_class_key lock_key;
 	u8 reload_failed:1;
 	refcount_t refcount;
 	struct completion comp;
@@ -9052,7 +9053,9 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops,
 	INIT_LIST_HEAD(&devlink->trap_list);
 	INIT_LIST_HEAD(&devlink->trap_group_list);
 	INIT_LIST_HEAD(&devlink->trap_policer_list);
+	lockdep_register_key(&devlink->lock_key);
 	mutex_init(&devlink->lock);
+	lockdep_set_class(&devlink->lock, &devlink->lock_key);
 	mutex_init(&devlink->reporters_lock);
 	refcount_set(&devlink->refcount, 1);
 	init_completion(&devlink->comp);
@@ -9193,6 +9196,7 @@ void devlink_free(struct devlink *devlink)
 
 	mutex_destroy(&devlink->reporters_lock);
 	mutex_destroy(&devlink->lock);
+	lockdep_unregister_key(&devlink->lock_key);
 	WARN_ON(!list_empty(&devlink->trap_policer_list));
 	WARN_ON(!list_empty(&devlink->trap_group_list));
 	WARN_ON(!list_empty(&devlink->trap_list));
-- 
2.35.1

[PATCH AUTOSEL 5.18 69/93] bpf: Don't redirect packets with invalid pkt_len

[Sasha Levin]

From: Zhengchao Shao <shaozhengchao@huawei.com>

[ Upstream commit fd1894224407c484f652ad456e1ce423e89bb3eb ]

Syzbot found an issue [1]: fq_codel_drop() try to drop a flow whitout any
skbs, that is, the flow->head is null.
The root cause, as the [2] says, is because that bpf_prog_test_run_skb()
run a bpf prog which redirects empty skbs.
So we should determine whether the length of the packet modified by bpf
prog or others like bpf_prog_test is valid before forwarding it directly.

LINK: [1] https://syzkaller.appspot.com/bug?id=0b84da80c2917757915afa89f7738a9d16ec96c5
LINK: [2] https://www.spinics.net/lists/netdev/msg777503.html

Reported-by: syzbot+7a12909485b94426aceb@syzkaller.appspotmail.com
Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20220715115559.139691-1-shaozhengchao@huawei.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/linux/skbuff.h | 8 ++++++++
 net/bpf/test_run.c     | 3 +++
 net/core/dev.c         | 1 +
 3 files changed, 12 insertions(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2394441fa3dd..4fac0091fb65 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2475,6 +2475,14 @@ static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset)
 
 #endif /* NET_SKBUFF_DATA_USES_OFFSET */
 
+static inline void skb_assert_len(struct sk_buff *skb)
+{
+#ifdef CONFIG_DEBUG_NET
+	if (WARN_ONCE(!skb->len, "%s\n", __func__))
+		DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false);
+#endif /* CONFIG_DEBUG_NET */
+}
+
 /*
  *	Add data to an sk_buff
  */
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index af709c182674..f2a9c47c26fc 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -911,6 +911,9 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb)
 {
 	struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb;
 
+	if (!skb->len)
+		return -EINVAL;
+
 	if (!__skb)
 		return 0;
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 842917883adb..301fa691b265 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4102,6 +4102,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 	bool again = false;
 
 	skb_reset_mac_header(skb);
+	skb_assert_len(skb);
 
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP))
 		__skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED);
-- 
2.35.1

[PATCH AUTOSEL 5.18 71/93] can: sja1000: Add Quirk for RZ/N1 SJA1000 CAN controller

[Sasha Levin]

From: Biju Das <biju.das.jz@bp.renesas.com>

[ Upstream commit 2d99bfbf3386962692dcccd73931cb0db07a1a43 ]

As per Chapter 6.5.16 of the RZ/N1 Peripheral Manual, The SJA1000
CAN controller does not support Clock Divider Register compared to
the reference Philips SJA1000 device.

This patch adds a device quirk to handle this difference.

Link: https://lore.kernel.org/all/20220710115248.190280-4-biju.das.jz@bp.renesas.com
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/can/sja1000/sja1000.c | 8 +++++---
 drivers/net/can/sja1000/sja1000.h | 3 ++-
 2 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c
index 966316479485..12c4cd8dc05d 100644
--- a/drivers/net/can/sja1000/sja1000.c
+++ b/drivers/net/can/sja1000/sja1000.c
@@ -184,8 +184,9 @@ static void chipset_init(struct net_device *dev)
 {
 	struct sja1000_priv *priv = netdev_priv(dev);
 
-	/* set clock divider and output control register */
-	priv->write_reg(priv, SJA1000_CDR, priv->cdr | CDR_PELICAN);
+	if (!(priv->flags & SJA1000_QUIRK_NO_CDR_REG))
+		/* set clock divider and output control register */
+		priv->write_reg(priv, SJA1000_CDR, priv->cdr | CDR_PELICAN);
 
 	/* set acceptance filter (accept all) */
 	priv->write_reg(priv, SJA1000_ACCC0, 0x00);
@@ -210,7 +211,8 @@ static void sja1000_start(struct net_device *dev)
 		set_reset_mode(dev);
 
 	/* Initialize chip if uninitialized at this stage */
-	if (!(priv->read_reg(priv, SJA1000_CDR) & CDR_PELICAN))
+	if (!(priv->flags & SJA1000_QUIRK_NO_CDR_REG ||
+	      priv->read_reg(priv, SJA1000_CDR) & CDR_PELICAN))
 		chipset_init(dev);
 
 	/* Clear error counters and error code capture */
diff --git a/drivers/net/can/sja1000/sja1000.h b/drivers/net/can/sja1000/sja1000.h
index 9d46398f8154..7f736f1df547 100644
--- a/drivers/net/can/sja1000/sja1000.h
+++ b/drivers/net/can/sja1000/sja1000.h
@@ -145,7 +145,8 @@
 /*
  * Flags for sja1000priv.flags
  */
-#define SJA1000_CUSTOM_IRQ_HANDLER 0x1
+#define SJA1000_CUSTOM_IRQ_HANDLER	BIT(0)
+#define SJA1000_QUIRK_NO_CDR_REG	BIT(1)
 
 /*
  * SJA1000 private data structure
-- 
2.35.1

[PATCH AUTOSEL 5.18 74/93] Bluetooth: use memset avoid memory leaks

[Sasha Levin]

From: Xiaohui Zhang <xiaohuizhang@ruc.edu.cn>

[ Upstream commit a5133fe87ed827ce94084eecb7830a6d451ef55c ]

Similar to the handling of l2cap_ecred_connect in commit d3715b2333e9
("Bluetooth: use memset avoid memory leaks"), we thought a patch
might be needed here as well.

Use memset to initialize structs to prevent memory leaks
in l2cap_le_connect

Signed-off-by: Xiaohui Zhang <xiaohuizhang@ruc.edu.cn>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/bluetooth/l2cap_core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index ae78490ecd3d..09ecaf556de5 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1369,6 +1369,7 @@ static void l2cap_le_connect(struct l2cap_chan *chan)
 
 	l2cap_le_flowctl_init(chan, 0);
 
+	memset(&req, 0, sizeof(req));
 	req.psm     = chan->psm;
 	req.scid    = cpu_to_le16(chan->scid);
 	req.mtu     = cpu_to_le16(chan->imtu);
-- 
2.35.1

[PATCH AUTOSEL 5.18 75/93] Bluetooth: Collect kcov coverage from hci_rx_work

[Sasha Levin]

From: Tamas Koczka <poprdi@google.com>

[ Upstream commit 9f30de9e0343da05ac621b5817e9b1ce303c6310 ]

Annotate hci_rx_work() with kcov_remote_start() and kcov_remote_stop()
calls, so remote KCOV coverage is collected while processing the rx_q
queue which is the main incoming Bluetooth packet queue.

Coverage is associated with the thread which created the packet skb.

The collected extra coverage helps kernel fuzzing efforts in finding
vulnerabilities.

This change only has effect if the kernel is compiled with CONFIG_KCOV,
otherwise kcov_ functions don't do anything.

Signed-off-by: Tamas Koczka <poprdi@google.com>
Tested-by: Aleksandr Nogikh <nogikh@google.com>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/bluetooth/hci_core.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 19df3905c5f8..a78f0ef7bbdc 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -29,6 +29,7 @@
 #include <linux/rfkill.h>
 #include <linux/debugfs.h>
 #include <linux/crypto.h>
+#include <linux/kcov.h>
 #include <linux/property.h>
 #include <linux/suspend.h>
 #include <linux/wait.h>
@@ -3780,7 +3781,14 @@ static void hci_rx_work(struct work_struct *work)
 
 	BT_DBG("%s", hdev->name);
 
-	while ((skb = skb_dequeue(&hdev->rx_q))) {
+	/* The kcov_remote functions used for collecting packet parsing
+	 * coverage information from this background thread and associate
+	 * the coverage with the syscall's thread which originally injected
+	 * the packet. This helps fuzzing the kernel.
+	 */
+	for (; (skb = skb_dequeue(&hdev->rx_q)); kcov_remote_stop()) {
+		kcov_remote_start_common(skb_get_kcov_handle(skb));
+
 		/* Send copy to monitor */
 		hci_send_to_monitor(hdev, skb);
 
-- 
2.35.1

[PATCH AUTOSEL 5.18 77/93] Bluetooth: hci_sync: Check LMP feature bit instead of quirk

[Sasha Levin]

From: Zijun Hu <quic_zijuhu@quicinc.com>

[ Upstream commit 766ae2422b4312a73510ebee9266bc23b466fbbb ]

BT core driver should addtionally check LMP feature bit
"Erroneous Data Reporting" instead of quirk
HCI_QUIRK_BROKEN_ERR_DATA_REPORTING set by BT device driver to decide if
HCI commands HCI_Read|Write_Default_Erroneous_Data_Reporting are broken.

BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 2, Part C | page 587
This feature indicates whether the device is able to support the
Packet_Status_Flag and the HCI commands HCI_Write_Default_-
Erroneous_Data_Reporting and HCI_Read_Default_Erroneous_-
Data_Reporting.

the quirk was introduced by 'commit cde1a8a99287 ("Bluetooth: btusb: Fix
and detect most of the Chinese Bluetooth controllers")' to mark HCI
commands HCI_Read|Write_Default_Erroneous_Data_Reporting broken by BT
device driver, but the reason why these two HCI commands are broken is
that feature "Erroneous Data Reporting" is not enabled by firmware, this
scenario is illustrated by below log of QCA controllers with USB I/F:

@ RAW Open: hcitool (privileged) version 2.22
< HCI Command: Read Local Supported Commands (0x04|0x0002) plen 0
> HCI Event: Command Complete (0x0e) plen 68
      Read Local Supported Commands (0x04|0x0002) ncmd 1
        Status: Success (0x00)
        Commands: 288 entries
......
          Read Default Erroneous Data Reporting (Octet 18 - Bit 2)
          Write Default Erroneous Data Reporting (Octet 18 - Bit 3)
......

< HCI Command: Read Default Erroneous Data Reporting (0x03|0x005a) plen 0
> HCI Event: Command Complete (0x0e) plen 4
      Read Default Erroneous Data Reporting (0x03|0x005a) ncmd 1
        Status: Unknown HCI Command (0x01)

< HCI Command: Read Local Supported Features (0x04|0x0003) plen 0
> HCI Event: Command Complete (0x0e) plen 12
      Read Local Supported Features (0x04|0x0003) ncmd 1
        Status: Success (0x00)
        Features: 0xff 0xfe 0x0f 0xfe 0xd8 0x3f 0x5b 0x87
          3 slot packets
......

Signed-off-by: Zijun Hu <quic_zijuhu@quicinc.com>
Tested-by: Zijun Hu <quic_zijuhu@quicinc.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/net/bluetooth/hci.h | 1 +
 net/bluetooth/hci_sync.c    | 4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 62a9bb022aed..61051d9d53a2 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -496,6 +496,7 @@ enum {
 #define LMP_EXT_INQ	0x01
 #define LMP_SIMUL_LE_BR	0x02
 #define LMP_SIMPLE_PAIR	0x08
+#define LMP_ERR_DATA_REPORTING 0x20
 #define LMP_NO_FLUSH	0x40
 
 #define LMP_LSTO	0x01
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 351c2390164d..5c352db71819 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -3191,7 +3191,7 @@ static int hci_read_page_scan_activity_sync(struct hci_dev *hdev)
 static int hci_read_def_err_data_reporting_sync(struct hci_dev *hdev)
 {
 	if (!(hdev->commands[18] & 0x04) ||
-	    test_bit(HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, &hdev->quirks))
+	    !(hdev->features[0][6] & LMP_ERR_DATA_REPORTING))
 		return 0;
 
 	return __hci_cmd_sync_status(hdev, HCI_OP_READ_DEF_ERR_DATA_REPORTING,
@@ -3676,7 +3676,7 @@ static int hci_set_err_data_report_sync(struct hci_dev *hdev)
 	bool enabled = hci_dev_test_flag(hdev, HCI_WIDEBAND_SPEECH_ENABLED);
 
 	if (!(hdev->commands[18] & 0x08) ||
-	    test_bit(HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, &hdev->quirks))
+	    !(hdev->features[0][6] & LMP_ERR_DATA_REPORTING))
 		return 0;
 
 	if (enabled == hdev->err_data_reporting)
-- 
2.35.1

[PATCH AUTOSEL 5.18 80/93] Bluetooth: mgmt: Fix using hci_conn_abort

[Sasha Levin]

From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>

[ Upstream commit 1f7435c8f6558a94f75b408a74140bdcbd0f6dd1 ]

This fixes using hci_conn_abort instead of using hci_conn_abort_sync.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/net/bluetooth/hci_sync.h |  2 ++
 net/bluetooth/hci_sync.c         |  3 +--
 net/bluetooth/mgmt.c             | 38 +++++++++++++++++++++++++++++---
 3 files changed, 38 insertions(+), 5 deletions(-)

diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h
index 2492e3b46a8f..544e949b5dbf 100644
--- a/include/net/bluetooth/hci_sync.h
+++ b/include/net/bluetooth/hci_sync.h
@@ -105,4 +105,6 @@ int hci_resume_sync(struct hci_dev *hdev);
 
 struct hci_conn;
 
+int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason);
+
 int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn);
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 5c352db71819..fc6b91669327 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -4404,8 +4404,7 @@ static int hci_reject_conn_sync(struct hci_dev *hdev, struct hci_conn *conn,
 				     sizeof(cp), &cp, HCI_CMD_TIMEOUT);
 }
 
-static int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn,
-			       u8 reason)
+int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason)
 {
 	int err;
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index ae758ab1b558..5b5bee52e835 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2528,6 +2528,37 @@ static int device_unpaired(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			  skip_sk);
 }
 
+static void unpair_device_complete(struct hci_dev *hdev, void *data, int err)
+{
+	struct mgmt_pending_cmd *cmd = data;
+	struct mgmt_cp_unpair_device *cp = cmd->param;
+
+	if (!err)
+		device_unpaired(hdev, &cp->addr.bdaddr, cp->addr.type, cmd->sk);
+
+	cmd->cmd_complete(cmd, err);
+	mgmt_pending_free(cmd);
+}
+
+static int unpair_device_sync(struct hci_dev *hdev, void *data)
+{
+	struct mgmt_pending_cmd *cmd = data;
+	struct mgmt_cp_unpair_device *cp = cmd->param;
+	struct hci_conn *conn;
+
+	if (cp->addr.type == BDADDR_BREDR)
+		conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK,
+					       &cp->addr.bdaddr);
+	else
+		conn = hci_conn_hash_lookup_le(hdev, &cp->addr.bdaddr,
+					       le_addr_type(cp->addr.type));
+
+	if (!conn)
+		return 0;
+
+	return hci_abort_conn_sync(hdev, conn, HCI_ERROR_REMOTE_USER_TERM);
+}
+
 static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 			 u16 len)
 {
@@ -2638,7 +2669,7 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 		goto unlock;
 	}
 
-	cmd = mgmt_pending_add(sk, MGMT_OP_UNPAIR_DEVICE, hdev, cp,
+	cmd = mgmt_pending_new(sk, MGMT_OP_UNPAIR_DEVICE, hdev, cp,
 			       sizeof(*cp));
 	if (!cmd) {
 		err = -ENOMEM;
@@ -2647,9 +2678,10 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	cmd->cmd_complete = addr_cmd_complete;
 
-	err = hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM);
+	err = hci_cmd_sync_queue(hdev, unpair_device_sync, cmd,
+				 unpair_device_complete);
 	if (err < 0)
-		mgmt_pending_remove(cmd);
+		mgmt_pending_free(cmd);
 
 unlock:
 	hci_dev_unlock(hdev);
-- 
2.35.1

[PATCH AUTOSEL 5.18 81/93] bpf/selftests: Fix couldn't retrieve pinned program in xdp veth test

[Sasha Levin]

From: Jie2x Zhou <jie2x.zhou@intel.com>

[ Upstream commit f664f9c6b4a1bb9a10af812df0fbbf6aac28fcc6 ]

Before change:

  selftests: bpf: test_xdp_veth.sh
  Couldn't retrieve pinned program '/sys/fs/bpf/test_xdp_veth/progs/redirect_map_0': No such file or directory
  selftests: xdp_veth [SKIP]
  ok 20 selftests: bpf: test_xdp_veth.sh # SKIP

After change:

  PING 10.1.1.33 (10.1.1.33) 56(84) bytes of data.
  64 bytes from 10.1.1.33: icmp_seq=1 ttl=64 time=0.320 ms
  --- 10.1.1.33 ping statistics ---
  1 packets transmitted, 1 received, 0% packet loss, time 0ms
  rtt min/avg/max/mdev = 0.320/0.320/0.320/0.000 ms
  selftests: xdp_veth [PASS]

For the test case, the following can be found:

  ls /sys/fs/bpf/test_xdp_veth/progs/redirect_map_0
  ls: cannot access '/sys/fs/bpf/test_xdp_veth/progs/redirect_map_0': No such file or directory
  ls /sys/fs/bpf/test_xdp_veth/progs/
  xdp_redirect_map_0  xdp_redirect_map_1  xdp_redirect_map_2

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Jie2x Zhou <jie2x.zhou@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220719082430.9916-1-jie2x.zhou@intel.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/bpf/test_xdp_veth.sh | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_xdp_veth.sh b/tools/testing/selftests/bpf/test_xdp_veth.sh
index 392d28cc4e58..49936c4c8567 100755
--- a/tools/testing/selftests/bpf/test_xdp_veth.sh
+++ b/tools/testing/selftests/bpf/test_xdp_veth.sh
@@ -106,9 +106,9 @@ bpftool prog loadall \
 bpftool map update pinned $BPF_DIR/maps/tx_port key 0 0 0 0 value 122 0 0 0
 bpftool map update pinned $BPF_DIR/maps/tx_port key 1 0 0 0 value 133 0 0 0
 bpftool map update pinned $BPF_DIR/maps/tx_port key 2 0 0 0 value 111 0 0 0
-ip link set dev veth1 xdp pinned $BPF_DIR/progs/redirect_map_0
-ip link set dev veth2 xdp pinned $BPF_DIR/progs/redirect_map_1
-ip link set dev veth3 xdp pinned $BPF_DIR/progs/redirect_map_2
+ip link set dev veth1 xdp pinned $BPF_DIR/progs/xdp_redirect_map_0
+ip link set dev veth2 xdp pinned $BPF_DIR/progs/xdp_redirect_map_1
+ip link set dev veth3 xdp pinned $BPF_DIR/progs/xdp_redirect_map_2
 
 ip -n ${NS1} link set dev veth11 xdp obj xdp_dummy.o sec xdp
 ip -n ${NS2} link set dev veth22 xdp obj xdp_tx.o sec xdp
-- 
2.35.1

[PATCH AUTOSEL 5.18 85/93] net: ethernet: stmicro: stmmac: first disable all queues and disconnect in release

[Sasha Levin]

From: Christian Marangi <ansuelsmth@gmail.com>

[ Upstream commit 7028471edb646bfc532fec0973e50e784cdcb7c6 ]

Disable all queues and disconnect before tx_disable in stmmac_release to
prevent a corner case where packet may be still queued at the same time
tx_disable is called resulting in kernel panic if some packet still has
to be processed.

Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 98c4abbcd469..fd3671f1bad0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3766,8 +3766,6 @@ static int stmmac_release(struct net_device *dev)
 	struct stmmac_priv *priv = netdev_priv(dev);
 	u32 chan;
 
-	netif_tx_disable(dev);
-
 	if (device_may_wakeup(priv->device))
 		phylink_speed_down(priv->phylink, false);
 	/* Stop and disconnect the PHY */
@@ -3779,6 +3777,8 @@ static int stmmac_release(struct net_device *dev)
 	for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++)
 		hrtimer_cancel(&priv->tx_queue[chan].txtimer);
 
+	netif_tx_disable(dev);
+
 	/* Free the IRQ lines */
 	stmmac_free_irq(dev, REQ_IRQ_ERR_ALL, 0);
 
-- 
2.35.1

[PATCH AUTOSEL 5.18 86/93] wifi: rtl8xxxu: Fix the error handling of the probe function

[Sasha Levin]

From: Zheyu Ma <zheyuma97@gmail.com>

[ Upstream commit 13876f2a087ad352bf640a7a0a4a4229ea6e9e4f ]

When the driver fails at ieee80211_alloc_hw() at the probe time, the
driver will free the 'hw' which is not allocated, causing a bug.

The following log can reveal it:

[   15.981294] BUG: KASAN: user-memory-access in mutex_is_locked+0xe/0x40
[   15.981558] Read of size 8 at addr 0000000000001ab0 by task modprobe/373
[   15.982583] Call Trace:
[   15.984282]  ieee80211_free_hw+0x22/0x390
[   15.984446]  rtl8xxxu_probe+0x3a1/0xab30 [rtl8xxxu]

Fix the bug by changing the order of the error handling.

Signed-off-by: Zheyu Ma <zheyuma97@gmail.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220716130444.2950690-1-zheyuma97@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../wireless/realtek/rtl8xxxu/rtl8xxxu_core.c | 21 ++++++++++---------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
index 06d59ffb7444..7ff30de10a7c 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
@@ -6611,7 +6611,7 @@ static int rtl8xxxu_probe(struct usb_interface *interface,
 	if (!hw) {
 		ret = -ENOMEM;
 		priv = NULL;
-		goto exit;
+		goto err_put_dev;
 	}
 
 	priv = hw->priv;
@@ -6633,24 +6633,24 @@ static int rtl8xxxu_probe(struct usb_interface *interface,
 
 	ret = rtl8xxxu_parse_usb(priv, interface);
 	if (ret)
-		goto exit;
+		goto err_set_intfdata;
 
 	ret = rtl8xxxu_identify_chip(priv);
 	if (ret) {
 		dev_err(&udev->dev, "Fatal - failed to identify chip\n");
-		goto exit;
+		goto err_set_intfdata;
 	}
 
 	ret = rtl8xxxu_read_efuse(priv);
 	if (ret) {
 		dev_err(&udev->dev, "Fatal - failed to read EFuse\n");
-		goto exit;
+		goto err_set_intfdata;
 	}
 
 	ret = priv->fops->parse_efuse(priv);
 	if (ret) {
 		dev_err(&udev->dev, "Fatal - failed to parse EFuse\n");
-		goto exit;
+		goto err_set_intfdata;
 	}
 
 	rtl8xxxu_print_chipinfo(priv);
@@ -6658,12 +6658,12 @@ static int rtl8xxxu_probe(struct usb_interface *interface,
 	ret = priv->fops->load_firmware(priv);
 	if (ret) {
 		dev_err(&udev->dev, "Fatal - failed to load firmware\n");
-		goto exit;
+		goto err_set_intfdata;
 	}
 
 	ret = rtl8xxxu_init_device(hw);
 	if (ret)
-		goto exit;
+		goto err_set_intfdata;
 
 	hw->wiphy->max_scan_ssids = 1;
 	hw->wiphy->max_scan_ie_len = IEEE80211_MAX_DATA_LEN;
@@ -6713,12 +6713,12 @@ static int rtl8xxxu_probe(struct usb_interface *interface,
 	if (ret) {
 		dev_err(&udev->dev, "%s: Failed to register: %i\n",
 			__func__, ret);
-		goto exit;
+		goto err_set_intfdata;
 	}
 
 	return 0;
 
-exit:
+err_set_intfdata:
 	usb_set_intfdata(interface, NULL);
 
 	if (priv) {
@@ -6726,9 +6726,10 @@ static int rtl8xxxu_probe(struct usb_interface *interface,
 		mutex_destroy(&priv->usb_buf_mutex);
 		mutex_destroy(&priv->h2c_mutex);
 	}
-	usb_put_dev(udev);
 
 	ieee80211_free_hw(hw);
+err_put_dev:
+	usb_put_dev(udev);
 
 	return ret;
 }
-- 
2.35.1