[PATCH AUTOSEL 5.17 003/135] ath11k: fix the warning of dev_wake in mhi_pm_disable_transition()

[PATCH AUTOSEL 5.17 003/135] ath11k: fix the warning of dev_wake in mhi_pm_disable_transition()

[Sasha Levin]

From: Wen Gong <quic_wgong@quicinc.com>

[ Upstream commit 0d7a8a6204ea9271f1d0a8c66a9fd2f54d2e3cbc ]

When test device recovery with below command, it has warning in message
as below.
echo assert > /sys/kernel/debug/ath11k/wcn6855\ hw2.0/simulate_fw_crash
echo assert > /sys/kernel/debug/ath11k/qca6390\ hw2.0/simulate_fw_crash

warning message:
[ 1965.642121] ath11k_pci 0000:06:00.0: simulating firmware assert crash
[ 1968.471364] ieee80211 phy0: Hardware restart was requested
[ 1968.511305] ------------[ cut here ]------------
[ 1968.511368] WARNING: CPU: 3 PID: 1546 at drivers/bus/mhi/core/pm.c:505 mhi_pm_disable_transition+0xb37/0xda0 [mhi]
[ 1968.511443] Modules linked in: ath11k_pci ath11k mac80211 libarc4 cfg80211 qmi_helpers qrtr_mhi mhi qrtr nvme nvme_core
[ 1968.511563] CPU: 3 PID: 1546 Comm: kworker/u17:0 Kdump: loaded Tainted: G        W         5.17.0-rc3-wt-ath+ #579
[ 1968.511629] Hardware name: Intel(R) Client Systems NUC8i7HVK/NUC8i7HVB, BIOS HNKBLi70.86A.0067.2021.0528.1339 05/28/2021
[ 1968.511704] Workqueue: mhi_hiprio_wq mhi_pm_st_worker [mhi]
[ 1968.511787] RIP: 0010:mhi_pm_disable_transition+0xb37/0xda0 [mhi]
[ 1968.511870] Code: a9 fe ff ff 4c 89 ff 44 89 04 24 e8 03 46 f6 e5 44 8b 04 24 41 83 f8 01 0f 84 21 fe ff ff e9 4c fd ff ff 0f 0b e9 af f8 ff ff <0f> 0b e9 5c f8 ff ff 48 89 df e8 da 9e ee e3 e9 12 fd ff ff 4c 89
[ 1968.511923] RSP: 0018:ffffc900024efbf0 EFLAGS: 00010286
[ 1968.511969] RAX: 00000000ffffffff RBX: ffff88811d241250 RCX: ffffffffc0176922
[ 1968.512014] RDX: 0000000000000000 RSI: 0000000000000004 RDI: ffff888118a90a24
[ 1968.512059] RBP: ffff888118a90800 R08: 0000000000000000 R09: ffff888118a90a27
[ 1968.512102] R10: ffffed1023152144 R11: 0000000000000001 R12: ffff888118a908ac
[ 1968.512229] R13: ffff888118a90928 R14: dffffc0000000000 R15: ffff888118a90a24
[ 1968.512310] FS:  0000000000000000(0000) GS:ffff888234200000(0000) knlGS:0000000000000000
[ 1968.512405] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1968.512493] CR2: 00007f5538f443a8 CR3: 000000016dc28001 CR4: 00000000003706e0
[ 1968.512587] Call Trace:
[ 1968.512672]  <TASK>
[ 1968.512751]  ? _raw_spin_unlock_irq+0x1f/0x40
[ 1968.512859]  mhi_pm_st_worker+0x3ac/0x790 [mhi]
[ 1968.512959]  ? mhi_pm_mission_mode_transition.isra.0+0x7d0/0x7d0 [mhi]
[ 1968.513063]  process_one_work+0x86a/0x1400
[ 1968.513184]  ? pwq_dec_nr_in_flight+0x230/0x230
[ 1968.513312]  ? move_linked_works+0x125/0x290
[ 1968.513416]  worker_thread+0x6db/0xf60
[ 1968.513536]  ? process_one_work+0x1400/0x1400
[ 1968.513627]  kthread+0x241/0x2d0
[ 1968.513733]  ? kthread_complete_and_exit+0x20/0x20
[ 1968.513821]  ret_from_fork+0x22/0x30
[ 1968.513924]  </TASK>

Reason is mhi_deassert_dev_wake() from mhi_device_put() is called
but mhi_assert_dev_wake() from __mhi_device_get_sync() is not called
in progress of recovery. Commit 8e0559921f9a ("bus: mhi: core:
Skip device wake in error or shutdown state") add check for the
pm_state of mhi in __mhi_device_get_sync(), and the pm_state is not
the normal state untill recovery is completed, so it leads the
dev_wake is not 0 and above warning print in mhi_pm_disable_transition()
while checking mhi_cntrl->dev_wake.

Add check in ath11k_pci_write32()/ath11k_pci_read32() to skip call
mhi_device_put() if mhi_device_get_sync() does not really do wake,
then the warning gone.

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03003-QCAHSPSWPL_V1_V2_SILICONZ_LITE-2

Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20220228064606.8981-5-quic_wgong@quicinc.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/ath/ath11k/pci.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c
index 903758751c99..8a3ff12057e8 100644
--- a/drivers/net/wireless/ath/ath11k/pci.c
+++ b/drivers/net/wireless/ath/ath11k/pci.c
@@ -191,6 +191,7 @@ void ath11k_pci_write32(struct ath11k_base *ab, u32 offset, u32 value)
 {
 	struct ath11k_pci *ab_pci = ath11k_pci_priv(ab);
 	u32 window_start;
+	int ret = 0;
 
 	/* for offset beyond BAR + 4K - 32, may
 	 * need to wakeup MHI to access.
@@ -198,7 +199,7 @@ void ath11k_pci_write32(struct ath11k_base *ab, u32 offset, u32 value)
 	if (ab->hw_params.wakeup_mhi &&
 	    test_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags) &&
 	    offset >= ACCESS_ALWAYS_OFF)
-		mhi_device_get_sync(ab_pci->mhi_ctrl->mhi_dev);
+		ret = mhi_device_get_sync(ab_pci->mhi_ctrl->mhi_dev);
 
 	if (offset < WINDOW_START) {
 		iowrite32(value, ab->mem  + offset);
@@ -222,7 +223,8 @@ void ath11k_pci_write32(struct ath11k_base *ab, u32 offset, u32 value)
 
 	if (ab->hw_params.wakeup_mhi &&
 	    test_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags) &&
-	    offset >= ACCESS_ALWAYS_OFF)
+	    offset >= ACCESS_ALWAYS_OFF &&
+	    !ret)
 		mhi_device_put(ab_pci->mhi_ctrl->mhi_dev);
 }
 
@@ -230,6 +232,7 @@ u32 ath11k_pci_read32(struct ath11k_base *ab, u32 offset)
 {
 	struct ath11k_pci *ab_pci = ath11k_pci_priv(ab);
 	u32 val, window_start;
+	int ret = 0;
 
 	/* for offset beyond BAR + 4K - 32, may
 	 * need to wakeup MHI to access.
@@ -237,7 +240,7 @@ u32 ath11k_pci_read32(struct ath11k_base *ab, u32 offset)
 	if (ab->hw_params.wakeup_mhi &&
 	    test_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags) &&
 	    offset >= ACCESS_ALWAYS_OFF)
-		mhi_device_get_sync(ab_pci->mhi_ctrl->mhi_dev);
+		ret = mhi_device_get_sync(ab_pci->mhi_ctrl->mhi_dev);
 
 	if (offset < WINDOW_START) {
 		val = ioread32(ab->mem + offset);
@@ -261,7 +264,8 @@ u32 ath11k_pci_read32(struct ath11k_base *ab, u32 offset)
 
 	if (ab->hw_params.wakeup_mhi &&
 	    test_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags) &&
-	    offset >= ACCESS_ALWAYS_OFF)
+	    offset >= ACCESS_ALWAYS_OFF &&
+	    !ret)
 		mhi_device_put(ab_pci->mhi_ctrl->mhi_dev);
 
 	return val;
-- 
2.35.1

[PATCH AUTOSEL 5.17 005/135] selftests/bpf: Fix vfs_link kprobe definition

[Sasha Levin]

From: Nikolay Borisov <nborisov@suse.com>

[ Upstream commit e299bcd4d16ff86f46c48df1062c8aae0eca1ed8 ]

Since commit 6521f8917082 ("namei: prepare for idmapped mounts")
vfs_link's prototype was changed, the kprobe definition in
profiler selftest in turn wasn't updated. The result is that all
argument after the first are now stored in different registers. This
means that self-test has been broken ever since. Fix it by updating the
kprobe definition accordingly.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220331140949.1410056-1-nborisov@suse.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/bpf/progs/profiler.inc.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h
index 4896fdf816f7..92331053dba3 100644
--- a/tools/testing/selftests/bpf/progs/profiler.inc.h
+++ b/tools/testing/selftests/bpf/progs/profiler.inc.h
@@ -826,8 +826,9 @@ int kprobe_ret__do_filp_open(struct pt_regs* ctx)
 
 SEC("kprobe/vfs_link")
 int BPF_KPROBE(kprobe__vfs_link,
-	       struct dentry* old_dentry, struct inode* dir,
-	       struct dentry* new_dentry, struct inode** delegated_inode)
+	       struct dentry* old_dentry, struct user_namespace *mnt_userns,
+	       struct inode* dir, struct dentry* new_dentry,
+	       struct inode** delegated_inode)
 {
 	struct bpf_func_stats_ctx stats_ctx;
 	bpf_stats_enter(&stats_ctx, profiler_bpf_vfs_link);
-- 
2.35.1

[PATCH AUTOSEL 5.17 006/135] selftests/bpf: Fix parsing of prog types in UAPI hdr for bpftool sync

[Sasha Levin]

From: Quentin Monnet <quentin@isovalent.com>

[ Upstream commit 4eeebce6ac4ad80ee8243bb847c98e0e55848d47 ]

The script for checking that various lists of types in bpftool remain in
sync with the UAPI BPF header uses a regex to parse enum bpf_prog_type.
If this enum contains a set of values different from the list of program
types in bpftool, it complains.

This script should have reported the addition, some time ago, of the new
BPF_PROG_TYPE_SYSCALL, which was not reported to bpftool's program types
list. It failed to do so, because it failed to parse that new type from
the enum. This is because the new value, in the BPF header, has an
explicative comment on the same line, and the regex does not support
that.

Let's update the script to support parsing enum values when they have
comments on the same line.

Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220404140944.64744-1-quentin@isovalent.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/bpf/test_bpftool_synctypes.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/test_bpftool_synctypes.py b/tools/testing/selftests/bpf/test_bpftool_synctypes.py
index 6bf21e47882a..c0e7acd698ed 100755
--- a/tools/testing/selftests/bpf/test_bpftool_synctypes.py
+++ b/tools/testing/selftests/bpf/test_bpftool_synctypes.py
@@ -180,7 +180,7 @@ class FileExtractor(object):
         @enum_name: name of the enum to parse
         """
         start_marker = re.compile(f'enum {enum_name} {{\n')
-        pattern = re.compile('^\s*(BPF_\w+),?$')
+        pattern = re.compile('^\s*(BPF_\w+),?(\s+/\*.*\*/)?$')
         end_marker = re.compile('^};')
         parser = BlockParser(self.reader)
         parser.search_block(start_marker)
-- 
2.35.1

[PATCH AUTOSEL 5.17 007/135] ath11k: Change max no of active probe SSID and BSSID to fw capability

[Sasha Levin]

From: Karthikeyan Kathirvel <quic_kathirve@quicinc.com>

[ Upstream commit 50dc9ce9f80554a88e33b73c30851acf2be36ed3 ]

The maximum number of SSIDs in a for active probe requests is currently
reported as 16 (WLAN_SCAN_PARAMS_MAX_SSID) when registering the driver.
The scan_req_params structure only has the capacity to hold 10 SSIDs.
This leads to a buffer overflow which can be triggered from
wpa_supplicant in userspace. When copying the SSIDs into the
scan_req_params structure in the ath11k_mac_op_hw_scan route, it can
overwrite the extraie pointer.

Firmware supports 16 ssid * 4 bssid, for each ssid 4 bssid combo probe
request will be sent, so totally 64 probe requests supported. So
set both max ssid and bssid to 16 and 4 respectively. Remove the
redundant macros of ssid and bssid.

Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.7.0.1-01300-QCAHKSWPL_SILICONZ-1

Signed-off-by: Karthikeyan Kathirvel <quic_kathirve@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20220329150221.21907-1-quic_kathirve@quicinc.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/ath/ath11k/wmi.h | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/wmi.h b/drivers/net/wireless/ath/ath11k/wmi.h
index 2f26ec1a8aa3..8173570975e4 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.h
+++ b/drivers/net/wireless/ath/ath11k/wmi.h
@@ -3087,9 +3087,6 @@ enum scan_dwelltime_adaptive_mode {
 	SCAN_DWELL_MODE_STATIC = 4
 };
 
-#define WLAN_SCAN_MAX_NUM_SSID          10
-#define WLAN_SCAN_MAX_NUM_BSSID         10
-
 #define WLAN_SSID_MAX_LEN 32
 
 struct element_info {
@@ -3104,7 +3101,6 @@ struct wlan_ssid {
 
 #define WMI_IE_BITMAP_SIZE             8
 
-#define WMI_SCAN_MAX_NUM_SSID                0x0A
 /* prefix used by scan requestor ids on the host */
 #define WMI_HOST_SCAN_REQUESTOR_ID_PREFIX 0xA000
 
@@ -3112,10 +3108,6 @@ struct wlan_ssid {
 /* host cycles through the lower 12 bits to generate ids */
 #define WMI_HOST_SCAN_REQ_ID_PREFIX 0xA000
 
-#define WLAN_SCAN_PARAMS_MAX_SSID    16
-#define WLAN_SCAN_PARAMS_MAX_BSSID   4
-#define WLAN_SCAN_PARAMS_MAX_IE_LEN  256
-
 /* Values lower than this may be refused by some firmware revisions with a scan
  * completion with a timedout reason.
  */
@@ -3311,8 +3303,8 @@ struct scan_req_params {
 	u32 n_probes;
 	u32 *chan_list;
 	u32 notify_scan_events;
-	struct wlan_ssid ssid[WLAN_SCAN_MAX_NUM_SSID];
-	struct wmi_mac_addr bssid_list[WLAN_SCAN_MAX_NUM_BSSID];
+	struct wlan_ssid ssid[WLAN_SCAN_PARAMS_MAX_SSID];
+	struct wmi_mac_addr bssid_list[WLAN_SCAN_PARAMS_MAX_BSSID];
 	struct element_info extraie;
 	struct element_info htcap;
 	struct element_info vhtcap;
-- 
2.35.1

[PATCH AUTOSEL 5.17 008/135] mwifiex: add mutex lock for call in mwifiex_dfs_chan_sw_work_queue

[Sasha Levin]

From: Niels Dossche <dossche.niels@gmail.com>

[ Upstream commit 3e12968f6d12a34b540c39cbd696a760cc4616f0 ]

cfg80211_ch_switch_notify uses ASSERT_WDEV_LOCK to assert that
net_device->ieee80211_ptr->mtx (which is the same as priv->wdev.mtx)
is held during the function's execution.
mwifiex_dfs_chan_sw_work_queue is one of its callers, which does not
hold that lock, therefore violating the assertion.
Add a lock around the call.

Disclaimer:
I am currently working on a static analyser to detect missing locks.
This was a reported case. I manually verified the report by looking
at the code, so that I do not send wrong information or patches.
After concluding that this seems to be a true positive, I created
this patch.
However, as I do not in fact have this particular hardware,
I was unable to test it.

Reviewed-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Niels Dossche <dossche.niels@gmail.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220321225515.32113-1-dossche.niels@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/marvell/mwifiex/11h.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/marvell/mwifiex/11h.c b/drivers/net/wireless/marvell/mwifiex/11h.c
index d2ee6469e67b..3fa25cd64cda 100644
--- a/drivers/net/wireless/marvell/mwifiex/11h.c
+++ b/drivers/net/wireless/marvell/mwifiex/11h.c
@@ -303,5 +303,7 @@ void mwifiex_dfs_chan_sw_work_queue(struct work_struct *work)
 
 	mwifiex_dbg(priv->adapter, MSG,
 		    "indicating channel switch completion to kernel\n");
+	mutex_lock(&priv->wdev.mtx);
 	cfg80211_ch_switch_notify(priv->netdev, &priv->dfs_chandef);
+	mutex_unlock(&priv->wdev.mtx);
 }
-- 
2.35.1

[PATCH AUTOSEL 5.17 009/135] b43legacy: Fix assigning negative value to unsigned variable

[Sasha Levin]

From: Haowen Bai <baihaowen@meizu.com>

[ Upstream commit 3f6b867559b3d43a7ce1b4799b755e812fc0d503 ]

fix warning reported by smatch:
drivers/net/wireless/broadcom/b43legacy/phy.c:1181 b43legacy_phy_lo_b_measure()
warn: assigning (-772) to unsigned variable 'fval'

Signed-off-by: Haowen Bai <baihaowen@meizu.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/1648203433-8736-1-git-send-email-baihaowen@meizu.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/broadcom/b43legacy/phy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/b43legacy/phy.c b/drivers/net/wireless/broadcom/b43legacy/phy.c
index 05404fbd1e70..c1395e622759 100644
--- a/drivers/net/wireless/broadcom/b43legacy/phy.c
+++ b/drivers/net/wireless/broadcom/b43legacy/phy.c
@@ -1123,7 +1123,7 @@ void b43legacy_phy_lo_b_measure(struct b43legacy_wldev *dev)
 	struct b43legacy_phy *phy = &dev->phy;
 	u16 regstack[12] = { 0 };
 	u16 mls;
-	u16 fval;
+	s16 fval;
 	int i;
 	int j;
 
-- 
2.35.1

[PATCH AUTOSEL 5.17 010/135] b43: Fix assigning negative value to unsigned variable

[Sasha Levin]

From: Haowen Bai <baihaowen@meizu.com>

[ Upstream commit 11800d893b38e0e12d636c170c1abc19c43c730c ]

fix warning reported by smatch:
drivers/net/wireless/broadcom/b43/phy_n.c:585 b43_nphy_adjust_lna_gain_table()
warn: assigning (-2) to unsigned variable '*(lna_gain[0])'

Signed-off-by: Haowen Bai <baihaowen@meizu.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/1648203315-28093-1-git-send-email-baihaowen@meizu.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/broadcom/b43/phy_n.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/b43/phy_n.c b/drivers/net/wireless/broadcom/b43/phy_n.c
index cf3ccf4ddfe7..aa5c99465674 100644
--- a/drivers/net/wireless/broadcom/b43/phy_n.c
+++ b/drivers/net/wireless/broadcom/b43/phy_n.c
@@ -582,7 +582,7 @@ static void b43_nphy_adjust_lna_gain_table(struct b43_wldev *dev)
 	u16 data[4];
 	s16 gain[2];
 	u16 minmax[2];
-	static const u16 lna_gain[4] = { -2, 10, 19, 25 };
+	static const s16 lna_gain[4] = { -2, 10, 19, 25 };
 
 	if (nphy->hang_avoid)
 		b43_nphy_stay_in_carrier_search(dev, 1);
-- 
2.35.1

[PATCH AUTOSEL 5.17 011/135] ipw2x00: Fix potential NULL dereference in libipw_xmit()

[Sasha Levin]

From: Haowen Bai <baihaowen@meizu.com>

[ Upstream commit e8366bbabe1d207cf7c5b11ae50e223ae6fc278b ]

crypt and crypt->ops could be null, so we need to checking null
before dereference

Signed-off-by: Haowen Bai <baihaowen@meizu.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/1648797055-25730-1-git-send-email-baihaowen@meizu.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/intel/ipw2x00/libipw_tx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/ipw2x00/libipw_tx.c b/drivers/net/wireless/intel/ipw2x00/libipw_tx.c
index 36d1e6b2568d..4aec1fce1ae2 100644
--- a/drivers/net/wireless/intel/ipw2x00/libipw_tx.c
+++ b/drivers/net/wireless/intel/ipw2x00/libipw_tx.c
@@ -383,7 +383,7 @@ netdev_tx_t libipw_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		/* Each fragment may need to have room for encryption
 		 * pre/postfix */
-		if (host_encrypt)
+		if (host_encrypt && crypt && crypt->ops)
 			bytes_per_frag -= crypt->ops->extra_mpdu_prefix_len +
 			    crypt->ops->extra_mpdu_postfix_len;
 
-- 
2.35.1

[PATCH AUTOSEL 5.17 012/135] ipv6: fix locking issues with loops over idev->addr_list

[Sasha Levin]

From: Niels Dossche <dossche.niels@gmail.com>

[ Upstream commit 51454ea42c1ab4e0c2828bb0d4d53957976980de ]

idev->addr_list needs to be protected by idev->lock. However, it is not
always possible to do so while iterating and performing actions on
inet6_ifaddr instances. For example, multiple functions (like
addrconf_{join,leave}_anycast) eventually call down to other functions
that acquire the idev->lock. The current code temporarily unlocked the
idev->lock during the loops, which can cause race conditions. Moving the
locks up is also not an appropriate solution as the ordering of lock
acquisition will be inconsistent with for example mc_lock.

This solution adds an additional field to inet6_ifaddr that is used
to temporarily add the instances to a temporary list while holding
idev->lock. The temporary list can then be traversed without holding
idev->lock. This change was done in two places. In addrconf_ifdown, the
list_for_each_entry_safe variant of the list loop is also no longer
necessary as there is no deletion within that specific loop.

Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Niels Dossche <dossche.niels@gmail.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20220403231523.45843-1-dossche.niels@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/net/if_inet6.h |  8 ++++++++
 net/ipv6/addrconf.c    | 30 ++++++++++++++++++++++++------
 2 files changed, 32 insertions(+), 6 deletions(-)

diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index f026cf08a8e8..471461023443 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -64,6 +64,14 @@ struct inet6_ifaddr {
 
 	struct hlist_node	addr_lst;
 	struct list_head	if_list;
+	/*
+	 * Used to safely traverse idev->addr_list in process context
+	 * if the idev->lock needed to protect idev->addr_list cannot be held.
+	 * In that case, add the items to this list temporarily and iterate
+	 * without holding idev->lock.
+	 * See addrconf_ifdown and dev_forward_change.
+	 */
+	struct list_head	if_list_aux;
 
 	struct list_head	tmp_list;
 	struct inet6_ifaddr	*ifpub;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 4df84013c4e6..0a9e03465001 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -800,6 +800,7 @@ static void dev_forward_change(struct inet6_dev *idev)
 {
 	struct net_device *dev;
 	struct inet6_ifaddr *ifa;
+	LIST_HEAD(tmp_addr_list);
 
 	if (!idev)
 		return;
@@ -818,14 +819,24 @@ static void dev_forward_change(struct inet6_dev *idev)
 		}
 	}
 
+	read_lock_bh(&idev->lock);
 	list_for_each_entry(ifa, &idev->addr_list, if_list) {
 		if (ifa->flags&IFA_F_TENTATIVE)
 			continue;
+		list_add_tail(&ifa->if_list_aux, &tmp_addr_list);
+	}
+	read_unlock_bh(&idev->lock);
+
+	while (!list_empty(&tmp_addr_list)) {
+		ifa = list_first_entry(&tmp_addr_list,
+				       struct inet6_ifaddr, if_list_aux);
+		list_del(&ifa->if_list_aux);
 		if (idev->cnf.forwarding)
 			addrconf_join_anycast(ifa);
 		else
 			addrconf_leave_anycast(ifa);
 	}
+
 	inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
 				     NETCONFA_FORWARDING,
 				     dev->ifindex, &idev->cnf);
@@ -3730,7 +3741,8 @@ static int addrconf_ifdown(struct net_device *dev, bool unregister)
 	unsigned long event = unregister ? NETDEV_UNREGISTER : NETDEV_DOWN;
 	struct net *net = dev_net(dev);
 	struct inet6_dev *idev;
-	struct inet6_ifaddr *ifa, *tmp;
+	struct inet6_ifaddr *ifa;
+	LIST_HEAD(tmp_addr_list);
 	bool keep_addr = false;
 	bool was_ready;
 	int state, i;
@@ -3822,16 +3834,23 @@ static int addrconf_ifdown(struct net_device *dev, bool unregister)
 		write_lock_bh(&idev->lock);
 	}
 
-	list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) {
+	list_for_each_entry(ifa, &idev->addr_list, if_list)
+		list_add_tail(&ifa->if_list_aux, &tmp_addr_list);
+	write_unlock_bh(&idev->lock);
+
+	while (!list_empty(&tmp_addr_list)) {
 		struct fib6_info *rt = NULL;
 		bool keep;
 
+		ifa = list_first_entry(&tmp_addr_list,
+				       struct inet6_ifaddr, if_list_aux);
+		list_del(&ifa->if_list_aux);
+
 		addrconf_del_dad_work(ifa);
 
 		keep = keep_addr && (ifa->flags & IFA_F_PERMANENT) &&
 			!addr_is_local(&ifa->addr);
 
-		write_unlock_bh(&idev->lock);
 		spin_lock_bh(&ifa->lock);
 
 		if (keep) {
@@ -3862,15 +3881,14 @@ static int addrconf_ifdown(struct net_device *dev, bool unregister)
 			addrconf_leave_solict(ifa->idev, &ifa->addr);
 		}
 
-		write_lock_bh(&idev->lock);
 		if (!keep) {
+			write_lock_bh(&idev->lock);
 			list_del_rcu(&ifa->if_list);
+			write_unlock_bh(&idev->lock);
 			in6_ifa_put(ifa);
 		}
 	}
 
-	write_unlock_bh(&idev->lock);
-
 	/* Step 5: Discard anycast and multicast list */
 	if (unregister) {
 		ipv6_ac_destroy_dev(idev);
-- 
2.35.1

[PATCH AUTOSEL 5.17 016/135] libbpf: Fix a bug with checking bpf_probe_read_kernel() support in old kernels

[Sasha Levin]

From: Runqing Yang <rainkin1993@gmail.com>

[ Upstream commit d252a4a499a07bec21c65873f605c3a1ef52ffed ]

Background:
Libbpf automatically replaces calls to BPF bpf_probe_read_{kernel,user}
[_str]() helpers with bpf_probe_read[_str](), if libbpf detects that
kernel doesn't support new APIs. Specifically, libbpf invokes the
probe_kern_probe_read_kernel function to load a small eBPF program into
the kernel in which bpf_probe_read_kernel API is invoked and lets the
kernel checks whether the new API is valid. If the loading fails, libbpf
considers the new API invalid and replaces it with the old API.

static int probe_kern_probe_read_kernel(void)
{
	struct bpf_insn insns[] = {
		BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),	/* r1 = r10 (fp) */
		BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),	/* r1 += -8 */
		BPF_MOV64_IMM(BPF_REG_2, 8),		/* r2 = 8 */
		BPF_MOV64_IMM(BPF_REG_3, 0),		/* r3 = 0 */
		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel),
		BPF_EXIT_INSN(),
	};
	int fd, insn_cnt = ARRAY_SIZE(insns);

	fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL,
                           "GPL", insns, insn_cnt, NULL);
	return probe_fd(fd);
}

Bug:
On older kernel versions [0], the kernel checks whether the version
number provided in the bpf syscall, matches the LINUX_VERSION_CODE.
If not matched, the bpf syscall fails. eBPF However, the
probe_kern_probe_read_kernel code does not set the kernel version
number provided to the bpf syscall, which causes the loading process
alwasys fails for old versions. It means that libbpf will replace the
new API with the old one even the kernel supports the new one.

Solution:
After a discussion in [1], the solution is using BPF_PROG_TYPE_TRACEPOINT
program type instead of BPF_PROG_TYPE_KPROBE because kernel does not
enfoce version check for tracepoint programs. I test the patch in old
kernels (4.18 and 4.19) and it works well.

  [0] https://elixir.bootlin.com/linux/v4.19/source/kernel/bpf/syscall.c#L1360
  [1] Closes: https://github.com/libbpf/libbpf/issues/473

Signed-off-by: Runqing Yang <rainkin1993@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220409144928.27499-1-rainkin1993@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/lib/bpf/libbpf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 94a6a8543cbc..41515a770e3a 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -4564,7 +4564,7 @@ static int probe_kern_probe_read_kernel(void)
 	};
 	int fd, insn_cnt = ARRAY_SIZE(insns);
 
-	fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", insns, insn_cnt, NULL);
+	fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL);
 	return probe_fd(fd);
 }
 
-- 
2.35.1

[PATCH AUTOSEL 5.17 017/135] mac80211: minstrel_ht: fix where rate stats are stored (fixes debugfs output)

[Sasha Levin]

From: Peter Seiderer <ps.report@gmx.net>

[ Upstream commit 5c6dd7bd569b54c0d2904125d7366aa93f077f67 ]

Using an ath9k card the debugfs output of minstrel_ht looks like the following
(note the zero values for the first four rates sum-of success/attempts):

             best    ____________rate__________    ____statistics___    _____last____    ______sum-of________
mode guard #  rate   [name   idx airtime  max_tp]  [avg(tp) avg(prob)]  [retry|suc|att]  [#success | #attempts]
OFDM       1    DP     6.0M  272    1640     5.2       3.1      53.8       3     0 0             0   0
OFDM       1   C       9.0M  273    1104     7.7       4.6      53.8       4     0 0             0   0
OFDM       1  B       12.0M  274     836    10.0       6.0      53.8       4     0 0             0   0
OFDM       1 A    S   18.0M  275     568    14.3       8.5      53.8       5     0 0             0   0
OFDM       1      S   24.0M  276     436    18.1       0.0       0.0       5     0 1            80   1778
OFDM       1          36.0M  277     300    24.9       0.0       0.0       0     0 1             0   107
OFDM       1      S   48.0M  278     236    30.4       0.0       0.0       0     0 0             0   75
OFDM       1          54.0M  279     212    33.0       0.0       0.0       0     0 0             0   72

Total packet count::    ideal 16582      lookaround 885
Average # of aggregated frames per A-MPDU: 1.0

Debugging showed that the rate statistics for the first four rates where
stored in the MINSTREL_CCK_GROUP instead of the MINSTREL_OFDM_GROUP because
in minstrel_ht_get_stats() the supported check was not honoured as done in
various other places, e.g net/mac80211/rc80211_minstrel_ht_debugfs.c:

 74                 if (!(mi->supported[i] & BIT(j)))
 75                         continue;

With the patch applied the output looks good:

              best    ____________rate__________    ____statistics___    _____last____    ______sum-of________
mode guard #  rate   [name   idx airtime  max_tp]  [avg(tp) avg(prob)]  [retry|suc|att]  [#success | #attempts]
OFDM       1    D      6.0M  272    1640     5.2       5.2     100.0       3     0 0             1   1
OFDM       1   C       9.0M  273    1104     7.7       7.7     100.0       4     0 0            38   38
OFDM       1  B       12.0M  274     836    10.0       9.9      89.5       4     2 2           372   395
OFDM       1 A   P    18.0M  275     568    14.3      14.3      97.2       5    52 53         6956   7181
OFDM       1      S   24.0M  276     436    18.1       0.0       0.0       0     0 1             6   163
OFDM       1          36.0M  277     300    24.9       0.0       0.0       0     0 1             0   35
OFDM       1      S   48.0M  278     236    30.4       0.0       0.0       0     0 0             0   38
OFDM       1      S   54.0M  279     212    33.0       0.0       0.0       0     0 0             0   38

Total packet count::    ideal 7097      lookaround 287
Average # of aggregated frames per A-MPDU: 1.0

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Link: https://lore.kernel.org/r/20220404165414.1036-1-ps.report@gmx.net
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/mac80211/rc80211_minstrel_ht.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c
index 9c3b7fc377c1..50cce990784f 100644
--- a/net/mac80211/rc80211_minstrel_ht.c
+++ b/net/mac80211/rc80211_minstrel_ht.c
@@ -362,6 +362,9 @@ minstrel_ht_get_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi,
 
 	group = MINSTREL_CCK_GROUP;
 	for (idx = 0; idx < ARRAY_SIZE(mp->cck_rates); idx++) {
+		if (!(mi->supported[group] & BIT(idx)))
+			continue;
+
 		if (rate->idx != mp->cck_rates[idx])
 			continue;
 
-- 
2.35.1

[PATCH AUTOSEL 5.17 023/135] sfc: ef10: Fix assigning negative value to unsigned variable

[Sasha Levin]

From: Haowen Bai <baihaowen@meizu.com>

[ Upstream commit b8ff3395fbdf3b79a99d0ef410fc34c51044121e ]

fix warning reported by smatch:
251 drivers/net/ethernet/sfc/ef10.c:2259 efx_ef10_tx_tso_desc()
warn: assigning (-208) to unsigned variable 'ip_tot_len'

Signed-off-by: Haowen Bai <baihaowen@meizu.com>
Acked-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://lore.kernel.org/r/1649640757-30041-1-git-send-email-baihaowen@meizu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/sfc/ef10.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 1ab725d554a5..e50dea0e3859 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -2256,7 +2256,7 @@ int efx_ef10_tx_tso_desc(struct efx_tx_queue *tx_queue, struct sk_buff *skb,
 	 * guaranteed to satisfy the second as we only attempt TSO if
 	 * inner_network_header <= 208.
 	 */
-	ip_tot_len = -EFX_TSO2_MAX_HDRLEN;
+	ip_tot_len = 0x10000 - EFX_TSO2_MAX_HDRLEN;
 	EFX_WARN_ON_ONCE_PARANOID(mss + EFX_TSO2_MAX_HDRLEN +
 				  (tcp->doff << 2u) > ip_tot_len);
 
-- 
2.35.1

[PATCH AUTOSEL 5.17 025/135] rtw88: fix incorrect frequency reported

[Sasha Levin]

From: Po-Hao Huang <phhuang@realtek.com>

[ Upstream commit 6723c0cde84fde582a261c186ce84100dcfa0019 ]

We should only fill in frequency reported by firmware during scan.
Add this so frames won't be dropped by mac80211 due to frequency
mismatch.

Signed-off-by: Po-Hao Huang <phhuang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220407095858.46807-3-pkshih@realtek.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/realtek/rtw88/rx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw88/rx.c b/drivers/net/wireless/realtek/rtw88/rx.c
index d2d607e22198..84aedabdf285 100644
--- a/drivers/net/wireless/realtek/rtw88/rx.c
+++ b/drivers/net/wireless/realtek/rtw88/rx.c
@@ -158,7 +158,8 @@ void rtw_rx_fill_rx_status(struct rtw_dev *rtwdev,
 	memset(rx_status, 0, sizeof(*rx_status));
 	rx_status->freq = hw->conf.chandef.chan->center_freq;
 	rx_status->band = hw->conf.chandef.chan->band;
-	if (rtw_fw_feature_check(&rtwdev->fw, FW_FEATURE_SCAN_OFFLOAD))
+	if (rtw_fw_feature_check(&rtwdev->fw, FW_FEATURE_SCAN_OFFLOAD) &&
+	    test_bit(RTW_FLAG_SCANNING, rtwdev->flags))
 		rtw_set_rx_freq_by_pktstat(pkt_stat, rx_status);
 	if (pkt_stat->crc_err)
 		rx_status->flag |= RX_FLAG_FAILED_FCS_CRC;
-- 
2.35.1

[PATCH AUTOSEL 5.17 026/135] rtw88: 8821c: fix debugfs rssi value

[Sasha Levin]

From: Po-Hao Huang <phhuang@realtek.com>

[ Upstream commit ece31c93d4d68f7eb8eea4431b052aacdb678de2 ]

RSSI value per frame is reported to mac80211 but not maintained in
our own statistics, add it back to help us debug.

Signed-off-by: Po-Hao Huang <phhuang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220407095858.46807-7-pkshih@realtek.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/realtek/rtw88/rtw8821c.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821c.c b/drivers/net/wireless/realtek/rtw88/rtw8821c.c
index 80d4761796b1..0f16f649e03f 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8821c.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8821c.c
@@ -512,6 +512,7 @@ static s8 get_cck_rx_pwr(struct rtw_dev *rtwdev, u8 lna_idx, u8 vga_idx)
 static void query_phy_status_page0(struct rtw_dev *rtwdev, u8 *phy_status,
 				   struct rtw_rx_pkt_stat *pkt_stat)
 {
+	struct rtw_dm_info *dm_info = &rtwdev->dm_info;
 	s8 rx_power;
 	u8 lna_idx = 0;
 	u8 vga_idx = 0;
@@ -523,6 +524,7 @@ static void query_phy_status_page0(struct rtw_dev *rtwdev, u8 *phy_status,
 
 	pkt_stat->rx_power[RF_PATH_A] = rx_power;
 	pkt_stat->rssi = rtw_phy_rf_power_2_rssi(pkt_stat->rx_power, 1);
+	dm_info->rssi[RF_PATH_A] = pkt_stat->rssi;
 	pkt_stat->bw = RTW_CHANNEL_WIDTH_20;
 	pkt_stat->signal_power = rx_power;
 }
@@ -530,6 +532,7 @@ static void query_phy_status_page0(struct rtw_dev *rtwdev, u8 *phy_status,
 static void query_phy_status_page1(struct rtw_dev *rtwdev, u8 *phy_status,
 				   struct rtw_rx_pkt_stat *pkt_stat)
 {
+	struct rtw_dm_info *dm_info = &rtwdev->dm_info;
 	u8 rxsc, bw;
 	s8 min_rx_power = -120;
 
@@ -549,6 +552,7 @@ static void query_phy_status_page1(struct rtw_dev *rtwdev, u8 *phy_status,
 
 	pkt_stat->rx_power[RF_PATH_A] = GET_PHY_STAT_P1_PWDB_A(phy_status) - 110;
 	pkt_stat->rssi = rtw_phy_rf_power_2_rssi(pkt_stat->rx_power, 1);
+	dm_info->rssi[RF_PATH_A] = pkt_stat->rssi;
 	pkt_stat->bw = bw;
 	pkt_stat->signal_power = max(pkt_stat->rx_power[RF_PATH_A],
 				     min_rx_power);
-- 
2.35.1

[PATCH AUTOSEL 5.17 029/135] tcp: consume incoming skb leading to a reset

[Sasha Levin]

From: Eric Dumazet <edumazet@google.com>

[ Upstream commit d9d024f96609016628d750ebc8ee4a6f0d80e6e1 ]

Whenever tcp_validate_incoming() handles a valid RST packet,
we should not pretend the packet was dropped.

Create a special section at the end of tcp_validate_incoming()
to handle this case.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/ipv4/tcp_input.c | 28 ++++++++++++++++------------
 1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 7bf84ce34d9e..96c25c97ee56 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5694,7 +5694,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 						  &tp->last_oow_ack_time))
 				tcp_send_dupack(sk, skb);
 		} else if (tcp_reset_check(sk, skb)) {
-			tcp_reset(sk, skb);
+			goto reset;
 		}
 		goto discard;
 	}
@@ -5730,17 +5730,16 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 		}
 
 		if (rst_seq_match)
-			tcp_reset(sk, skb);
-		else {
-			/* Disable TFO if RST is out-of-order
-			 * and no data has been received
-			 * for current active TFO socket
-			 */
-			if (tp->syn_fastopen && !tp->data_segs_in &&
-			    sk->sk_state == TCP_ESTABLISHED)
-				tcp_fastopen_active_disable(sk);
-			tcp_send_challenge_ack(sk);
-		}
+			goto reset;
+
+		/* Disable TFO if RST is out-of-order
+		 * and no data has been received
+		 * for current active TFO socket
+		 */
+		if (tp->syn_fastopen && !tp->data_segs_in &&
+		    sk->sk_state == TCP_ESTABLISHED)
+			tcp_fastopen_active_disable(sk);
+		tcp_send_challenge_ack(sk);
 		goto discard;
 	}
 
@@ -5765,6 +5764,11 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 discard:
 	tcp_drop(sk, skb);
 	return false;
+
+reset:
+	tcp_reset(sk, skb);
+	__kfree_skb(skb);
+	return false;
 }
 
 /*
-- 
2.35.1

[PATCH AUTOSEL 5.17 033/135] net: sched: use queue_mapping to pick tx queue

[Sasha Levin]

From: Tonghao Zhang <xiangxia.m.yue@gmail.com>

[ Upstream commit 2f1e85b1aee459b7d0fd981839042c6a38ffaf0c ]

This patch fixes issue:
* If we install tc filters with act_skbedit in clsact hook.
  It doesn't work, because netdev_core_pick_tx() overwrites
  queue_mapping.

  $ tc filter ... action skbedit queue_mapping 1

And this patch is useful:
* We can use FQ + EDT to implement efficient policies. Tx queues
  are picked by xps, ndo_select_queue of netdev driver, or skb hash
  in netdev_core_pick_tx(). In fact, the netdev driver, and skb
  hash are _not_ under control. xps uses the CPUs map to select Tx
  queues, but we can't figure out which task_struct of pod/containter
  running on this cpu in most case. We can use clsact filters to classify
  one pod/container traffic to one Tx queue. Why ?

  In containter networking environment, there are two kinds of pod/
  containter/net-namespace. One kind (e.g. P1, P2), the high throughput
  is key in these applications. But avoid running out of network resource,
  the outbound traffic of these pods is limited, using or sharing one
  dedicated Tx queues assigned HTB/TBF/FQ Qdisc. Other kind of pods
  (e.g. Pn), the low latency of data access is key. And the traffic is not
  limited. Pods use or share other dedicated Tx queues assigned FIFO Qdisc.
  This choice provides two benefits. First, contention on the HTB/FQ Qdisc
  lock is significantly reduced since fewer CPUs contend for the same queue.
  More importantly, Qdisc contention can be eliminated completely if each
  CPU has its own FIFO Qdisc for the second kind of pods.

  There must be a mechanism in place to support classifying traffic based on
  pods/container to different Tx queues. Note that clsact is outside of Qdisc
  while Qdisc can run a classifier to select a sub-queue under the lock.

  In general recording the decision in the skb seems a little heavy handed.
  This patch introduces a per-CPU variable, suggested by Eric.

  The xmit.skip_txqueue flag is firstly cleared in __dev_queue_xmit().
  - Tx Qdisc may install that skbedit actions, then xmit.skip_txqueue flag
    is set in qdisc->enqueue() though tx queue has been selected in
    netdev_tx_queue_mapping() or netdev_core_pick_tx(). That flag is cleared
    firstly in __dev_queue_xmit(), is useful:
  - Avoid picking Tx queue with netdev_tx_queue_mapping() in next netdev
    in such case: eth0 macvlan - eth0.3 vlan - eth0 ixgbe-phy:
    For example, eth0, macvlan in pod, which root Qdisc install skbedit
    queue_mapping, send packets to eth0.3, vlan in host. In __dev_queue_xmit() of
    eth0.3, clear the flag, does not select tx queue according to skb->queue_mapping
    because there is no filters in clsact or tx Qdisc of this netdev.
    Same action taked in eth0, ixgbe in Host.
  - Avoid picking Tx queue for next packet. If we set xmit.skip_txqueue
    in tx Qdisc (qdisc->enqueue()), the proper way to clear it is clearing it
    in __dev_queue_xmit when processing next packets.

  For performance reasons, use the static key. If user does not config the NET_EGRESS,
  the patch will not be compiled.

  +----+      +----+      +----+
  | P1 |      | P2 |      | Pn |
  +----+      +----+      +----+
    |           |           |
    +-----------+-----------+
                |
                | clsact/skbedit
                |      MQ
                v
    +-----------+-----------+
    | q0        | q1        | qn
    v           v           v
  HTB/FQ      HTB/FQ  ...  FIFO

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Jonathan Lemon <jonathan.lemon@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Alexander Lobakin <alobakin@pm.me>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Talal Ahmad <talalahmad@google.com>
Cc: Kevin Hao <haokexin@gmail.com>
Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Cc: Antoine Tenart <atenart@kernel.org>
Cc: Wei Wang <weiwan@google.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/linux/netdevice.h |  3 +++
 include/linux/rtnetlink.h |  1 +
 net/core/dev.c            | 31 +++++++++++++++++++++++++++++--
 net/sched/act_skbedit.c   |  6 +++++-
 4 files changed, 38 insertions(+), 3 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index dadd4d2f6d8a..ac4094cf824a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3015,6 +3015,9 @@ struct softnet_data {
 	struct {
 		u16 recursion;
 		u8  more;
+#ifdef CONFIG_NET_EGRESS
+		u8  skip_txqueue;
+#endif
 	} xmit;
 #ifdef CONFIG_RPS
 	/* input_queue_head should be written by cpu owning this struct,
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index bb9cb84114c1..e87c2dccc4d5 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -100,6 +100,7 @@ void net_dec_ingress_queue(void);
 #ifdef CONFIG_NET_EGRESS
 void net_inc_egress_queue(void);
 void net_dec_egress_queue(void);
+void netdev_xmit_skip_txqueue(bool skip);
 #endif
 
 void rtnetlink_init(void);
diff --git a/net/core/dev.c b/net/core/dev.c
index 5f1ac4812277..80dbbd5f6a73 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3860,6 +3860,25 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 
 	return skb;
 }
+
+static struct netdev_queue *
+netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb)
+{
+	int qm = skb_get_queue_mapping(skb);
+
+	return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm));
+}
+
+static bool netdev_xmit_txqueue_skipped(void)
+{
+	return __this_cpu_read(softnet_data.xmit.skip_txqueue);
+}
+
+void netdev_xmit_skip_txqueue(bool skip)
+{
+	__this_cpu_write(softnet_data.xmit.skip_txqueue, skip);
+}
+EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue);
 #endif /* CONFIG_NET_EGRESS */
 
 #ifdef CONFIG_XPS
@@ -4030,7 +4049,7 @@ struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
 static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 {
 	struct net_device *dev = skb->dev;
-	struct netdev_queue *txq;
+	struct netdev_queue *txq = NULL;
 	struct Qdisc *q;
 	int rc = -ENOMEM;
 	bool again = false;
@@ -4058,11 +4077,17 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 			if (!skb)
 				goto out;
 		}
+
+		netdev_xmit_skip_txqueue(false);
+
 		nf_skip_egress(skb, true);
 		skb = sch_handle_egress(skb, &rc, dev);
 		if (!skb)
 			goto out;
 		nf_skip_egress(skb, false);
+
+		if (netdev_xmit_txqueue_skipped())
+			txq = netdev_tx_queue_mapping(dev, skb);
 	}
 #endif
 	/* If device/qdisc don't need skb->dst, release it right now while
@@ -4073,7 +4098,9 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 	else
 		skb_dst_force(skb);
 
-	txq = netdev_core_pick_tx(dev, skb, sb_dev);
+	if (!txq)
+		txq = netdev_core_pick_tx(dev, skb, sb_dev);
+
 	q = rcu_dereference_bh(txq->qdisc);
 
 	trace_net_dev_queue(skb);
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index ceba11b198bb..d5799b4fc499 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -58,8 +58,12 @@ static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a,
 		}
 	}
 	if (params->flags & SKBEDIT_F_QUEUE_MAPPING &&
-	    skb->dev->real_num_tx_queues > params->queue_mapping)
+	    skb->dev->real_num_tx_queues > params->queue_mapping) {
+#ifdef CONFIG_NET_EGRESS
+		netdev_xmit_skip_txqueue(true);
+#endif
 		skb_set_queue_mapping(skb, params->queue_mapping);
+	}
 	if (params->flags & SKBEDIT_F_MARK) {
 		skb->mark &= ~params->mask;
 		skb->mark |= params->mark & params->mask;
-- 
2.35.1

[PATCH AUTOSEL 5.17 038/135] ath9k: fix QCA9561 PA bias level

[Sasha Levin]

From: Thibaut VARÈNE <hacks+kernel@slashdirt.org>

[ Upstream commit e999a5da28a0e0f7de242d841ef7d5e48f4646ae ]

This patch fixes an invalid TX PA DC bias level on QCA9561, which
results in a very low output power and very low throughput as devices
are further away from the AP (compared to other 2.4GHz APs).

This patch was suggested by Felix Fietkau, who noted[1]:
"The value written to that register is wrong, because while the mask
definition AR_CH0_TOP2_XPABIASLVL uses a different value for 9561, the
shift definition AR_CH0_TOP2_XPABIASLVL_S is hardcoded to 12, which is
wrong for 9561."

In real life testing, without this patch the 2.4GHz throughput on
Yuncore XD3200 is around 10Mbps sitting next to the AP, and closer to
practical maximum with the patch applied.

[1] https://lore.kernel.org/all/91c58969-c60e-2f41-00ac-737786d435ae@nbd.name

Signed-off-by: Thibaut VARÈNE <hacks+kernel@slashdirt.org>
Acked-by: Felix Fietkau <nbd@nbd.name>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20220417145145.1847-1-hacks+kernel@slashdirt.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/ath/ath9k/ar9003_phy.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.h b/drivers/net/wireless/ath/ath9k/ar9003_phy.h
index a171dbb29fbb..ad949eb02f3d 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_phy.h
+++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.h
@@ -720,7 +720,7 @@
 #define AR_CH0_TOP2		(AR_SREV_9300(ah) ? 0x1628c : \
 					(AR_SREV_9462(ah) ? 0x16290 : 0x16284))
 #define AR_CH0_TOP2_XPABIASLVL		(AR_SREV_9561(ah) ? 0x1e00 : 0xf000)
-#define AR_CH0_TOP2_XPABIASLVL_S	12
+#define AR_CH0_TOP2_XPABIASLVL_S	(AR_SREV_9561(ah) ? 9 : 12)
 
 #define AR_CH0_XTAL		(AR_SREV_9300(ah) ? 0x16294 : \
 				 ((AR_SREV_9462(ah) || AR_SREV_9565(ah)) ? 0x16298 : \
-- 
2.35.1

[PATCH AUTOSEL 5.17 052/135] ath11k: disable spectral scan during spectral deinit

[Sasha Levin]

From: Hari Chandrakanthan <quic_haric@quicinc.com>

[ Upstream commit 161c64de239c7018e0295e7e0520a19f00aa32dc ]

When ath11k modules are removed using rmmod with spectral scan enabled,
crash is observed. Different crash trace is observed for each crash.

Send spectral scan disable WMI command to firmware before cleaning
the spectral dbring in the spectral_deinit API to avoid this crash.

call trace from one of the crash observed:
[ 1252.880802] Unable to handle kernel NULL pointer dereference at virtual address 00000008
[ 1252.882722] pgd = 0f42e886
[ 1252.890955] [00000008] *pgd=00000000
[ 1252.893478] Internal error: Oops: 5 [#1] PREEMPT SMP ARM
[ 1253.093035] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.89 #0
[ 1253.115261] Hardware name: Generic DT based system
[ 1253.121149] PC is at ath11k_spectral_process_data+0x434/0x574 [ath11k]
[ 1253.125940] LR is at 0x88e31017
[ 1253.132448] pc : [<7f9387b8>]    lr : [<88e31017>]    psr: a0000193
[ 1253.135488] sp : 80d01bc8  ip : 00000001  fp : 970e0000
[ 1253.141737] r10: 88e31000  r9 : 970ec000  r8 : 00000080
[ 1253.146946] r7 : 94734040  r6 : a0000113  r5 : 00000057  r4 : 00000000
[ 1253.152159] r3 : e18cb694  r2 : 00000217  r1 : 1df1f000  r0 : 00000001
[ 1253.158755] Flags: NzCv  IRQs off  FIQs on  Mode SVC_32  ISA ARM  Segment user
[ 1253.165266] Control: 10c0383d  Table: 5e71006a  DAC: 00000055
[ 1253.172472] Process swapper/0 (pid: 0, stack limit = 0x60870141)
[ 1253.458055] [<7f9387b8>] (ath11k_spectral_process_data [ath11k]) from [<7f917fdc>] (ath11k_dbring_buffer_release_event+0x214/0x2e4 [ath11k])
[ 1253.466139] [<7f917fdc>] (ath11k_dbring_buffer_release_event [ath11k]) from [<7f8ea3c4>] (ath11k_wmi_tlv_op_rx+0x1840/0x29cc [ath11k])
[ 1253.478807] [<7f8ea3c4>] (ath11k_wmi_tlv_op_rx [ath11k]) from [<7f8fe868>] (ath11k_htc_rx_completion_handler+0x180/0x4e0 [ath11k])
[ 1253.490699] [<7f8fe868>] (ath11k_htc_rx_completion_handler [ath11k]) from [<7f91308c>] (ath11k_ce_per_engine_service+0x2c4/0x3b4 [ath11k])
[ 1253.502386] [<7f91308c>] (ath11k_ce_per_engine_service [ath11k]) from [<7f9a4198>] (ath11k_pci_ce_tasklet+0x28/0x80 [ath11k_pci])
[ 1253.514811] [<7f9a4198>] (ath11k_pci_ce_tasklet [ath11k_pci]) from [<8032227c>] (tasklet_action_common.constprop.2+0x64/0xe8)
[ 1253.526476] [<8032227c>] (tasklet_action_common.constprop.2) from [<803021e8>] (__do_softirq+0x130/0x2d0)
[ 1253.537756] [<803021e8>] (__do_softirq) from [<80322610>] (irq_exit+0xcc/0xe8)
[ 1253.547304] [<80322610>] (irq_exit) from [<8036a4a4>] (__handle_domain_irq+0x60/0xb4)
[ 1253.554428] [<8036a4a4>] (__handle_domain_irq) from [<805eb348>] (gic_handle_irq+0x4c/0x90)
[ 1253.562321] [<805eb348>] (gic_handle_irq) from [<80301a78>] (__irq_svc+0x58/0x8c)

Tested-on: QCN6122 hw1.0 AHB WLAN.HK.2.6.0.1-00851-QCAHKSWPL_SILICONZ-1

Signed-off-by: Hari Chandrakanthan <quic_haric@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/1649396345-349-1-git-send-email-quic_haric@quicinc.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/ath/ath11k/spectral.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/spectral.c b/drivers/net/wireless/ath/ath11k/spectral.c
index 4100cc1449a2..e997426a1b4b 100644
--- a/drivers/net/wireless/ath/ath11k/spectral.c
+++ b/drivers/net/wireless/ath/ath11k/spectral.c
@@ -212,7 +212,10 @@ static int ath11k_spectral_scan_config(struct ath11k *ar,
 		return -ENODEV;
 
 	arvif->spectral_enabled = (mode != ATH11K_SPECTRAL_DISABLED);
+
+	spin_lock_bh(&ar->spectral.lock);
 	ar->spectral.mode = mode;
+	spin_unlock_bh(&ar->spectral.lock);
 
 	ret = ath11k_wmi_vdev_spectral_enable(ar, arvif->vdev_id,
 					      ATH11K_WMI_SPECTRAL_TRIGGER_CMD_CLEAR,
@@ -843,9 +846,6 @@ static inline void ath11k_spectral_ring_free(struct ath11k *ar)
 {
 	struct ath11k_spectral *sp = &ar->spectral;
 
-	if (!sp->enabled)
-		return;
-
 	ath11k_dbring_srng_cleanup(ar, &sp->rx_ring);
 	ath11k_dbring_buf_cleanup(ar, &sp->rx_ring);
 }
@@ -897,15 +897,16 @@ void ath11k_spectral_deinit(struct ath11k_base *ab)
 		if (!sp->enabled)
 			continue;
 
-		ath11k_spectral_debug_unregister(ar);
-		ath11k_spectral_ring_free(ar);
+		mutex_lock(&ar->conf_mutex);
+		ath11k_spectral_scan_config(ar, ATH11K_SPECTRAL_DISABLED);
+		mutex_unlock(&ar->conf_mutex);
 
 		spin_lock_bh(&sp->lock);
-
-		sp->mode = ATH11K_SPECTRAL_DISABLED;
 		sp->enabled = false;
-
 		spin_unlock_bh(&sp->lock);
+
+		ath11k_spectral_debug_unregister(ar);
+		ath11k_spectral_ring_free(ar);
 	}
 }
 
-- 
2.35.1

[PATCH AUTOSEL 5.17 056/135] ath10k: skip ath10k_halt during suspend for driver state RESTARTING

[Sasha Levin]

From: Abhishek Kumar <kuabhs@chromium.org>

[ Upstream commit b72a4aff947ba807177bdabb43debaf2c66bee05 ]

Double free crash is observed when FW recovery(caused by wmi
timeout/crash) is followed by immediate suspend event. The FW recovery
is triggered by ath10k_core_restart() which calls driver clean up via
ath10k_halt(). When the suspend event occurs between the FW recovery,
the restart worker thread is put into frozen state until suspend completes.
The suspend event triggers ath10k_stop() which again triggers ath10k_halt()
The double invocation of ath10k_halt() causes ath10k_htt_rx_free() to be
called twice(Note: ath10k_htt_rx_alloc was not called by restart worker
thread because of its frozen state), causing the crash.

To fix this, during the suspend flow, skip call to ath10k_halt() in
ath10k_stop() when the current driver state is ATH10K_STATE_RESTARTING.
Also, for driver state ATH10K_STATE_RESTARTING, call
ath10k_wait_for_suspend() in ath10k_stop(). This is because call to
ath10k_wait_for_suspend() is skipped later in
[ath10k_halt() > ath10k_core_stop()] for the driver state
ATH10K_STATE_RESTARTING.

The frozen restart worker thread will be cancelled during resume when the
device comes out of suspend.

Below is the crash stack for reference:

[  428.469167] ------------[ cut here ]------------
[  428.469180] kernel BUG at mm/slub.c:4150!
[  428.469193] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
[  428.469219] Workqueue: events_unbound async_run_entry_fn
[  428.469230] RIP: 0010:kfree+0x319/0x31b
[  428.469241] RSP: 0018:ffffa1fac015fc30 EFLAGS: 00010246
[  428.469247] RAX: ffffedb10419d108 RBX: ffff8c05262b0000
[  428.469252] RDX: ffff8c04a8c07000 RSI: 0000000000000000
[  428.469256] RBP: ffffa1fac015fc78 R08: 0000000000000000
[  428.469276] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  428.469285] Call Trace:
[  428.469295]  ? dma_free_attrs+0x5f/0x7d
[  428.469320]  ath10k_core_stop+0x5b/0x6f
[  428.469336]  ath10k_halt+0x126/0x177
[  428.469352]  ath10k_stop+0x41/0x7e
[  428.469387]  drv_stop+0x88/0x10e
[  428.469410]  __ieee80211_suspend+0x297/0x411
[  428.469441]  rdev_suspend+0x6e/0xd0
[  428.469462]  wiphy_suspend+0xb1/0x105
[  428.469483]  ? name_show+0x2d/0x2d
[  428.469490]  dpm_run_callback+0x8c/0x126
[  428.469511]  ? name_show+0x2d/0x2d
[  428.469517]  __device_suspend+0x2e7/0x41b
[  428.469523]  async_suspend+0x1f/0x93
[  428.469529]  async_run_entry_fn+0x3d/0xd1
[  428.469535]  process_one_work+0x1b1/0x329
[  428.469541]  worker_thread+0x213/0x372
[  428.469547]  kthread+0x150/0x15f
[  428.469552]  ? pr_cont_work+0x58/0x58
[  428.469558]  ? kthread_blkcg+0x31/0x31

Tested-on: QCA6174 hw3.2 PCI WLAN.RM.4.4.1-00288-QCARMSWPZ-1
Co-developed-by: Wen Gong <quic_wgong@quicinc.com>
Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
Signed-off-by: Abhishek Kumar <kuabhs@chromium.org>
Reviewed-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20220426221859.v2.1.I650b809482e1af8d0156ed88b5dc2677a0711d46@changeid
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/ath/ath10k/mac.c | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index b11aaee8b8c0..a11b31191d5a 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -5339,13 +5339,29 @@ static int ath10k_start(struct ieee80211_hw *hw)
 static void ath10k_stop(struct ieee80211_hw *hw)
 {
 	struct ath10k *ar = hw->priv;
+	u32 opt;
 
 	ath10k_drain_tx(ar);
 
 	mutex_lock(&ar->conf_mutex);
 	if (ar->state != ATH10K_STATE_OFF) {
-		if (!ar->hw_rfkill_on)
-			ath10k_halt(ar);
+		if (!ar->hw_rfkill_on) {
+			/* If the current driver state is RESTARTING but not yet
+			 * fully RESTARTED because of incoming suspend event,
+			 * then ath10k_halt() is already called via
+			 * ath10k_core_restart() and should not be called here.
+			 */
+			if (ar->state != ATH10K_STATE_RESTARTING) {
+				ath10k_halt(ar);
+			} else {
+				/* Suspending here, because when in RESTARTING
+				 * state, ath10k_core_stop() skips
+				 * ath10k_wait_for_suspend().
+				 */
+				opt = WMI_PDEV_SUSPEND_AND_DISABLE_INTR;
+				ath10k_wait_for_suspend(ar, opt);
+			}
+		}
 		ar->state = ATH10K_STATE_OFF;
 	}
 	mutex_unlock(&ar->conf_mutex);
-- 
2.35.1

[PATCH AUTOSEL 5.17 061/135] ath11k: fix warning of not found station for bssid in message

[Sasha Levin]

From: Wen Gong <quic_wgong@quicinc.com>

[ Upstream commit 7330e1ec9748948177830c6e1a13379835d577f9 ]

When test connect/disconnect to an AP frequently with WCN6855, sometimes
it show below log.

[  277.040121] wls1: deauthenticating from 8c:21:0a:b3:5a:64 by local choice (Reason: 3=DEAUTH_LEAVING)
[  277.050906] ath11k_pci 0000:05:00.0: wmi stats vdev id 0 mac 00:03:7f:29:61:11
[  277.050944] ath11k_pci 0000:05:00.0: wmi stats bssid 8c:21:0a:b3:5a:64 vif         pK-error
[  277.050954] ath11k_pci 0000:05:00.0: not found station for bssid 8c:21:0a:b3:5a:64
[  277.050961] ath11k_pci 0000:05:00.0: failed to parse rssi chain -71
[  277.050967] ath11k_pci 0000:05:00.0: failed to pull fw stats: -71
[  277.050976] ath11k_pci 0000:05:00.0: wmi stats vdev id 0 mac 00:03:7f:29:61:11
[  277.050983] ath11k_pci 0000:05:00.0: wmi stats bssid 8c:21:0a:b3:5a:64 vif         pK-error
[  277.050989] ath11k_pci 0000:05:00.0: not found station for bssid 8c:21:0a:b3:5a:64
[  277.050995] ath11k_pci 0000:05:00.0: failed to parse rssi chain -71
[  277.051000] ath11k_pci 0000:05:00.0: failed to pull fw stats: -71
[  278.064050] ath11k_pci 0000:05:00.0: failed to request fw stats: -110

Reason is:
When running disconnect operation, sta_info removed from local->sta_hash
by __sta_info_destroy_part1() from __sta_info_flush(), after this,
ieee80211_find_sta_by_ifaddr() which called by
ath11k_wmi_tlv_fw_stats_data_parse() and ath11k_wmi_tlv_rssi_chain_parse()
cannot find this station, then failed log printed.

steps are like this:
1. when disconnect from AP, __sta_info_destroy() called __sta_info_destroy_part1()
and __sta_info_destroy_part2().

2. in __sta_info_destroy_part1(),  it has "sta_info_hash_del(local, sta)"
and "list_del_rcu(&sta->list)", it will remove the ieee80211_sta from the
list of ieee80211_hw.

3. in __sta_info_destroy_part2(), it called drv_sta_state()->ath11k_mac_op_sta_state(),
then peer->sta is clear at this moment.

4. in __sta_info_destroy_part2(), it then called sta_set_sinfo()->drv_sta_statistics()
->ath11k_mac_op_sta_statistics(), then WMI_REQUEST_STATS_CMDID sent to firmware.

5. WMI_UPDATE_STATS_EVENTID reported from firmware, at this moment, the
ieee80211_sta can not be found again because it has remove from list in
step2 and also peer->sta is clear in step3.

6. in __sta_info_destroy_part2(), it then called cleanup_single_sta()->
sta_info_free()->kfree(sta), at this moment, the ieee80211_sta is freed
in memory, then the failed log will not happen because function
ath11k_mac_op_sta_state() will not be called.

Actually this print log is not a real error, it is only to skip parse the
info, so change to skip print by default debug setting.

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3

Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20220428022426.2927-1-quic_wgong@quicinc.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/ath/ath11k/wmi.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c
index 22921673e956..4ad3fe7d7d1f 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.c
+++ b/drivers/net/wireless/ath/ath11k/wmi.c
@@ -5616,9 +5616,9 @@ static int ath11k_wmi_tlv_rssi_chain_parse(struct ath11k_base *ab,
 					   arvif->bssid,
 					   NULL);
 	if (!sta) {
-		ath11k_warn(ab, "not found station for bssid %pM\n",
-			    arvif->bssid);
-		ret = -EPROTO;
+		ath11k_dbg(ab, ATH11K_DBG_WMI,
+			   "not found station of bssid %pM for rssi chain\n",
+			   arvif->bssid);
 		goto exit;
 	}
 
@@ -5716,8 +5716,9 @@ static int ath11k_wmi_tlv_fw_stats_data_parse(struct ath11k_base *ab,
 					   "wmi stats vdev id %d snr %d\n",
 					   src->vdev_id, src->beacon_snr);
 			} else {
-				ath11k_warn(ab, "not found station for bssid %pM\n",
-					    arvif->bssid);
+				ath11k_dbg(ab, ATH11K_DBG_WMI,
+					   "not found station of bssid %pM for vdev stat\n",
+					   arvif->bssid);
 			}
 		}
 
-- 
2.35.1

[PATCH AUTOSEL 5.17 063/135] ipv6: Don't send rs packets to the interface of ARPHRD_TUNNEL

[Sasha Levin]

From: jianghaoran <jianghaoran@kylinos.cn>

[ Upstream commit b52e1cce31ca721e937d517411179f9196ee6135 ]

ARPHRD_TUNNEL interface can't process rs packets
and will generate TX errors

ex:
ip tunnel add ethn mode ipip local 192.168.1.1 remote 192.168.1.2
ifconfig ethn x.x.x.x

ethn: flags=209<UP,POINTOPOINT,RUNNING,NOARP>  mtu 1480
	inet x.x.x.x  netmask 255.255.255.255  destination x.x.x.x
	inet6 fe80::5efe:ac1e:3cdb  prefixlen 64  scopeid 0x20<link>
	tunnel   txqueuelen 1000  (IPIP Tunnel)
	RX packets 0  bytes 0 (0.0 B)
	RX errors 0  dropped 0  overruns 0  frame 0
	TX packets 0  bytes 0 (0.0 B)
	TX errors 3  dropped 0 overruns 0  carrier 0  collisions 0

Signed-off-by: jianghaoran <jianghaoran@kylinos.cn>
Link: https://lore.kernel.org/r/20220429053802.246681-1-jianghaoran@kylinos.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/ipv6/addrconf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 0a9e03465001..5ec289e0f2ac 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4221,7 +4221,8 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id,
 	send_rs = send_mld &&
 		  ipv6_accept_ra(ifp->idev) &&
 		  ifp->idev->cnf.rtr_solicits != 0 &&
-		  (dev->flags&IFF_LOOPBACK) == 0;
+		  (dev->flags & IFF_LOOPBACK) == 0 &&
+		  (dev->type != ARPHRD_TUNNEL);
 	read_unlock_bh(&ifp->idev->lock);
 
 	/* While dad is in progress mld report's source address is in6_addrany.
-- 
2.35.1

[PATCH AUTOSEL 5.17 064/135] net/mlx5: fs, delete the FTE when there are no rules attached to it

[Sasha Levin]

From: Mark Bloch <mbloch@nvidia.com>

[ Upstream commit 7b0c6338597613f465d131bd939a51844a00455a ]

When an FTE has no children is means all the rules where removed
and the FTE can be deleted regardless of the dests_size value.
While dests_size should be 0 when there are no children
be extra careful not to leak memory or get firmware syndrome
if the proper bookkeeping of dests_size wasn't done.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index b6f58d16d145..298c614c631b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -2064,16 +2064,16 @@ void mlx5_del_flow_rules(struct mlx5_flow_handle *handle)
 	down_write_ref_node(&fte->node, false);
 	for (i = handle->num_rules - 1; i >= 0; i--)
 		tree_remove_node(&handle->rule[i]->node, true);
-	if (fte->dests_size) {
-		if (fte->modify_mask)
-			modify_fte(fte);
-		up_write_ref_node(&fte->node, false);
-	} else if (list_empty(&fte->node.children)) {
+	if (list_empty(&fte->node.children)) {
 		del_hw_fte(&fte->node);
 		/* Avoid double call to del_hw_fte */
 		fte->node.del_hw_func = NULL;
 		up_write_ref_node(&fte->node, false);
 		tree_put_node(&fte->node, false);
+	} else if (fte->dests_size) {
+		if (fte->modify_mask)
+			modify_fte(fte);
+		up_write_ref_node(&fte->node, false);
 	} else {
 		up_write_ref_node(&fte->node, false);
 	}
-- 
2.35.1

[PATCH AUTOSEL 5.17 066/135] mlxsw: spectrum_dcb: Do not warn about priority changes

[Sasha Levin]

From: Petr Machata <petrm@nvidia.com>

[ Upstream commit b6b584562cbe7dc357083459d6dd5b171e12cadb ]

The idea behind the warnings is that the user would get warned in case when
more than one priority is configured for a given DSCP value on a netdevice.

The warning is currently wrong, because dcb_ieee_getapp_mask() returns
the first matching entry, not all of them, and the warning will then claim
that some priority is "current", when in fact it is not.

But more importantly, the warning is misleading in general. Consider the
following commands:

 # dcb app flush dev swp19 dscp-prio
 # dcb app add dev swp19 dscp-prio 24:3
 # dcb app replace dev swp19 dscp-prio 24:2

The last command will issue the following warning:

 mlxsw_spectrum3 0000:07:00.0 swp19: Ignoring new priority 2 for DSCP 24 in favor of current value of 3

The reason is that the "replace" command works by first adding the new
value, and then removing all old values. This is the only way to make the
replacement without causing the traffic to be prioritized to whatever the
chip defaults to. The warning is issued in response to adding the new
priority, and then no warning is shown when the old priority is removed.
The upshot is that the canonical way to change traffic prioritization
always produces a warning about ignoring the new priority, but what gets
configured is in fact what the user intended.

An option to just emit warning every time that the prioritization changes
just to make it clear that it happened is obviously unsatisfactory.

Therefore, in this patch, remove the warnings.

Reported-by: Maksym Yaremchuk <maksymy@nvidia.com>
Signed-off-by: Petr Machata <petrm@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/spectrum_dcb.c | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
index 5f92b1691360..aff6d4f35cd2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
@@ -168,8 +168,6 @@ static int mlxsw_sp_dcbnl_ieee_setets(struct net_device *dev,
 static int mlxsw_sp_dcbnl_app_validate(struct net_device *dev,
 				       struct dcb_app *app)
 {
-	int prio;
-
 	if (app->priority >= IEEE_8021QAZ_MAX_TCS) {
 		netdev_err(dev, "APP entry with priority value %u is invalid\n",
 			   app->priority);
@@ -183,17 +181,6 @@ static int mlxsw_sp_dcbnl_app_validate(struct net_device *dev,
 				   app->protocol);
 			return -EINVAL;
 		}
-
-		/* Warn about any DSCP APP entries with the same PID. */
-		prio = fls(dcb_ieee_getapp_mask(dev, app));
-		if (prio--) {
-			if (prio < app->priority)
-				netdev_warn(dev, "Choosing priority %d for DSCP %d in favor of previously-active value of %d\n",
-					    app->priority, app->protocol, prio);
-			else if (prio > app->priority)
-				netdev_warn(dev, "Ignoring new priority %d for DSCP %d in favor of current value of %d\n",
-					    app->priority, app->protocol, prio);
-		}
 		break;
 
 	case IEEE_8021QAZ_APP_SEL_ETHERTYPE:
-- 
2.35.1

[PATCH AUTOSEL 5.17 067/135] mlxsw: Treat LLDP packets as control

[Sasha Levin]

From: Petr Machata <petrm@nvidia.com>

[ Upstream commit 0106668cd2f91bf913fb78972840dedfba80a3c3 ]

When trapping packets for on-CPU processing, Spectrum machines
differentiate between control and non-control traps. Traffic trapped
through non-control traps is treated as data and kept in shared buffer in
pools 0-4. Traffic trapped through control traps is kept in the dedicated
control buffer 9. The advantage of marking traps as control is that
pressure in the data plane does not prevent the control traffic to be
processed.

When the LLDP trap was introduced, it was marked as a control trap. But
then in commit aed4b5721143 ("mlxsw: spectrum: PTP: Hook into packet
receive path"), PTP traps were introduced. Because Ethernet-encapsulated
PTP packets look to the Spectrum-1 ASIC as LLDP traffic and are trapped
under the LLDP trap, this trap was reconfigured as non-control, in sync
with the PTP traps.

There is however no requirement that PTP traffic be handled as data.
Besides, the usual encapsulation for PTP traffic is UDP, not bare Ethernet,
and that is in deployments that even need PTP, which is far less common
than LLDP. This is reflected by the default policer, which was not bumped
up to the 19Kpps / 24Kpps that is the expected load of a PTP-enabled
Spectrum-1 switch.

Marking of LLDP trap as non-control was therefore probably misguided. In
this patch, change it back to control.

Reported-by: Maksym Yaremchuk <maksymy@nvidia.com>
Signed-off-by: Petr Machata <petrm@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/spectrum_trap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
index 47b061b99160..ed4d0d3448f3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -864,7 +864,7 @@ static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = {
 		.trap = MLXSW_SP_TRAP_CONTROL(LLDP, LLDP, TRAP),
 		.listeners_arr = {
 			MLXSW_RXL(mlxsw_sp_rx_ptp_listener, LLDP, TRAP_TO_CPU,
-				  false, SP_LLDP, DISCARD),
+				  true, SP_LLDP, DISCARD),
 		},
 	},
 	{
-- 
2.35.1

[PATCH AUTOSEL 5.17 075/135] net/mlx5: Increase FW pre-init timeout for health recovery

[Sasha Levin]

From: Gavin Li <gavinl@nvidia.com>

[ Upstream commit 37ca95e62ee23fa6d2c2c64e3dc40b4a0c0146dc ]

Currently, health recovery will reload driver to recover it from fatal
errors. During the driver's load process, it would wait for FW to set the
pre-init bit for up to 120 seconds, beyond this threshold it would abort
the load process. In some cases, such as a FW upgrade on the DPU, this
timeout period is insufficient, and the user has no way to recover the
host device.

To solve this issue, introduce a new FW pre-init timeout for health
recovery, which is set to 2 hours.

The timeout for devlink reload and probe will use the original one because
they are user triggered flows, and therefore should not have a
significantly long timeout, during which the user command would hang.

Signed-off-by: Gavin Li <gavinl@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/devlink.c |  4 ++--
 .../ethernet/mellanox/mlx5/core/fw_reset.c    |  2 +-
 .../ethernet/mellanox/mlx5/core/lib/tout.c    |  1 +
 .../ethernet/mellanox/mlx5/core/lib/tout.h    |  1 +
 .../net/ethernet/mellanox/mlx5/core/main.c    | 23 +++++++++++--------
 .../ethernet/mellanox/mlx5/core/mlx5_core.h   |  2 +-
 6 files changed, 20 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index d1093bb2d436..5e432e4fc381 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -182,13 +182,13 @@ static int mlx5_devlink_reload_up(struct devlink *devlink, enum devlink_reload_a
 	*actions_performed = BIT(action);
 	switch (action) {
 	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT:
-		return mlx5_load_one(dev);
+		return mlx5_load_one(dev, false);
 	case DEVLINK_RELOAD_ACTION_FW_ACTIVATE:
 		if (limit == DEVLINK_RELOAD_LIMIT_NO_RESET)
 			break;
 		/* On fw_activate action, also driver is reloaded and reinit performed */
 		*actions_performed |= BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT);
-		return mlx5_load_one(dev);
+		return mlx5_load_one(dev, false);
 	default:
 		/* Unsupported action should not get to this function */
 		WARN_ON(1);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index 1c771287bee5..d5f540132a0e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -106,7 +106,7 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev)
 	if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) {
 		complete(&fw_reset->done);
 	} else {
-		mlx5_load_one(dev);
+		mlx5_load_one(dev, false);
 		devlink_remote_reload_actions_performed(priv_to_devlink(dev), 0,
 							BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) |
 							BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c
index c1df0d3595d8..d758848d34d0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c
@@ -10,6 +10,7 @@ struct mlx5_timeouts {
 
 static const u32 tout_def_sw_val[MAX_TIMEOUT_TYPES] = {
 	[MLX5_TO_FW_PRE_INIT_TIMEOUT_MS] = 120000,
+	[MLX5_TO_FW_PRE_INIT_ON_RECOVERY_TIMEOUT_MS] = 7200000,
 	[MLX5_TO_FW_PRE_INIT_WARN_MESSAGE_INTERVAL_MS] = 20000,
 	[MLX5_TO_FW_PRE_INIT_WAIT_MS] = 2,
 	[MLX5_TO_FW_INIT_MS] = 2000,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h
index 1c42ead782fa..257c03eeab36 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h
@@ -7,6 +7,7 @@
 enum mlx5_timeouts_types {
 	/* pre init timeouts (not read from FW) */
 	MLX5_TO_FW_PRE_INIT_TIMEOUT_MS,
+	MLX5_TO_FW_PRE_INIT_ON_RECOVERY_TIMEOUT_MS,
 	MLX5_TO_FW_PRE_INIT_WARN_MESSAGE_INTERVAL_MS,
 	MLX5_TO_FW_PRE_INIT_WAIT_MS,
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 4e49dca94bc3..56a8079dc16a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1015,7 +1015,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_devcom_unregister_device(dev->priv.devcom);
 }
 
-static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot)
+static int mlx5_function_setup(struct mlx5_core_dev *dev, u64 timeout)
 {
 	int err;
 
@@ -1030,11 +1030,11 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot)
 
 	/* wait for firmware to accept initialization segments configurations
 	 */
-	err = wait_fw_init(dev, mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT),
+	err = wait_fw_init(dev, timeout,
 			   mlx5_tout_ms(dev, FW_PRE_INIT_WARN_MESSAGE_INTERVAL));
 	if (err) {
 		mlx5_core_err(dev, "Firmware over %llu MS in pre-initializing state, aborting\n",
-			      mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT));
+			      timeout);
 		return err;
 	}
 
@@ -1297,7 +1297,7 @@ int mlx5_init_one(struct mlx5_core_dev *dev)
 	mutex_lock(&dev->intf_state_mutex);
 	dev->state = MLX5_DEVICE_STATE_UP;
 
-	err = mlx5_function_setup(dev, true);
+	err = mlx5_function_setup(dev, mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT));
 	if (err)
 		goto err_function;
 
@@ -1361,9 +1361,10 @@ void mlx5_uninit_one(struct mlx5_core_dev *dev)
 	mutex_unlock(&dev->intf_state_mutex);
 }
 
-int mlx5_load_one(struct mlx5_core_dev *dev)
+int mlx5_load_one(struct mlx5_core_dev *dev, bool recovery)
 {
 	int err = 0;
+	u64 timeout;
 
 	mutex_lock(&dev->intf_state_mutex);
 	if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
@@ -1373,7 +1374,11 @@ int mlx5_load_one(struct mlx5_core_dev *dev)
 	/* remove any previous indication of internal error */
 	dev->state = MLX5_DEVICE_STATE_UP;
 
-	err = mlx5_function_setup(dev, false);
+	if (recovery)
+		timeout = mlx5_tout_ms(dev, FW_PRE_INIT_ON_RECOVERY_TIMEOUT);
+	else
+		timeout = mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT);
+	err = mlx5_function_setup(dev, timeout);
 	if (err)
 		goto err_function;
 
@@ -1746,7 +1751,7 @@ static void mlx5_pci_resume(struct pci_dev *pdev)
 
 	mlx5_pci_trace(dev, "Enter, loading driver..\n");
 
-	err = mlx5_load_one(dev);
+	err = mlx5_load_one(dev, false);
 
 	mlx5_pci_trace(dev, "Done, err = %d, device %s\n", err,
 		       !err ? "recovered" : "Failed");
@@ -1833,7 +1838,7 @@ static int mlx5_resume(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
 
-	return mlx5_load_one(dev);
+	return mlx5_load_one(dev, false);
 }
 
 static const struct pci_device_id mlx5_core_pci_table[] = {
@@ -1878,7 +1883,7 @@ int mlx5_recover_device(struct mlx5_core_dev *dev)
 			return -EIO;
 	}
 
-	return mlx5_load_one(dev);
+	return mlx5_load_one(dev, true);
 }
 
 static struct pci_driver mlx5_core_driver = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 6f8baa0f2a73..2d2150fc7a0f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -290,7 +290,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev);
 int mlx5_init_one(struct mlx5_core_dev *dev);
 void mlx5_uninit_one(struct mlx5_core_dev *dev);
 void mlx5_unload_one(struct mlx5_core_dev *dev);
-int mlx5_load_one(struct mlx5_core_dev *dev);
+int mlx5_load_one(struct mlx5_core_dev *dev, bool recovery);
 
 int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 function_id, void *out);
 
-- 
2.35.1

[PATCH AUTOSEL 5.17 078/135] net: remove two BUG() from skb_checksum_help()

[Sasha Levin]

From: Eric Dumazet <edumazet@google.com>

[ Upstream commit d7ea0d9df2a6265b2b180d17ebc64b38105968fc ]

I have a syzbot report that managed to get a crash in skb_checksum_help()

If syzbot can trigger these BUG(), it makes sense to replace
them with more friendly WARN_ON_ONCE() since skb_checksum_help()
can instead return an error code.

Note that syzbot will still crash there, until real bug is fixed.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/core/dev.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 80dbbd5f6a73..178400e4d13e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3156,11 +3156,15 @@ int skb_checksum_help(struct sk_buff *skb)
 	}
 
 	offset = skb_checksum_start_offset(skb);
-	BUG_ON(offset >= skb_headlen(skb));
+	ret = -EINVAL;
+	if (WARN_ON_ONCE(offset >= skb_headlen(skb)))
+		goto out;
+
 	csum = skb_checksum(skb, offset, skb->len - offset, 0);
 
 	offset += skb->csum_offset;
-	BUG_ON(offset + sizeof(__sum16) > skb_headlen(skb));
+	if (WARN_ON_ONCE(offset + sizeof(__sum16) > skb_headlen(skb)))
+		goto out;
 
 	ret = skb_ensure_writable(skb, offset + sizeof(__sum16));
 	if (ret)
-- 
2.35.1

[PATCH AUTOSEL 5.17 090/135] rtlwifi: Use pr_warn instead of WARN_ONCE

[Sasha Levin]

From: Dongliang Mu <mudongliangabcd@gmail.com>

[ Upstream commit ad732da434a2936128769216eddaece3b1af4588 ]

This memory allocation failure can be triggered by fault injection or
high pressure testing, resulting a WARN.

Fix this by replacing WARN with pr_warn.

Reported-by: syzkaller <syzkaller@googlegroups.com>
Signed-off-by: Dongliang Mu <mudongliangabcd@gmail.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220511014453.1621366-1-dzm91@hust.edu.cn
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/realtek/rtlwifi/usb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c
index 86a236873254..a8eebafb9a7e 100644
--- a/drivers/net/wireless/realtek/rtlwifi/usb.c
+++ b/drivers/net/wireless/realtek/rtlwifi/usb.c
@@ -1014,7 +1014,7 @@ int rtl_usb_probe(struct usb_interface *intf,
 	hw = ieee80211_alloc_hw(sizeof(struct rtl_priv) +
 				sizeof(struct rtl_usb_priv), &rtl_ops);
 	if (!hw) {
-		WARN_ONCE(true, "rtl_usb: ieee80211 alloc failed\n");
+		pr_warn("rtl_usb: ieee80211 alloc failed\n");
 		return -ENOMEM;
 	}
 	rtlpriv = hw->priv;
-- 
2.35.1

[PATCH AUTOSEL 5.17 091/135] mt76: mt7921: accept rx frames with non-standard VHT MCS10-11

[Sasha Levin]

From: Felix Fietkau <nbd@nbd.name>

[ Upstream commit 3128ea016965ce9f91ddf4e1dd944724462d1698 ]

The hardware receives them properly, they should not be dropped

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/mediatek/mt76/mt7921/mac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index 84f72dd1bf93..e07707f518a2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -698,7 +698,7 @@ mt7921_mac_fill_rx(struct mt7921_dev *dev, struct sk_buff *skb)
 			status->nss =
 				FIELD_GET(MT_PRXV_NSTS, v0) + 1;
 			status->encoding = RX_ENC_VHT;
-			if (i > 9)
+			if (i > 11)
 				return -EINVAL;
 			break;
 		case MT_PHY_TYPE_HE_MU:
-- 
2.35.1

[PATCH AUTOSEL 5.17 092/135] mt76: fix encap offload ethernet type check

[Sasha Levin]

From: Felix Fietkau <nbd@nbd.name>

[ Upstream commit bc98e7fdd80d215b4b55eea001023231eb8ce12e ]

The driver needs to check if the format is 802.2 vs 802.3 in order to set
a tx descriptor flag. skb->protocol can't be used, since it may not be properly
initialized for packets coming in from a packet socket.
Fix misdetection by checking the ethertype from the skb data instead

Reported-by: Thibaut VARÈNE <hacks+kernel@slashdirt.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/mediatek/mt76/mt7915/mac.c | 4 +++-
 drivers/net/wireless/mediatek/mt76/mt7921/mac.c | 4 +++-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index e4c300aa1526..efc04f7a3c71 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -982,6 +982,7 @@ mt7915_mac_write_txwi_8023(struct mt7915_dev *dev, __le32 *txwi,
 
 	u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
 	u8 fc_type, fc_stype;
+	u16 ethertype;
 	bool wmm = false;
 	u32 val;
 
@@ -995,7 +996,8 @@ mt7915_mac_write_txwi_8023(struct mt7915_dev *dev, __le32 *txwi,
 	val = FIELD_PREP(MT_TXD1_HDR_FORMAT, MT_HDR_FORMAT_802_3) |
 	      FIELD_PREP(MT_TXD1_TID, tid);
 
-	if (be16_to_cpu(skb->protocol) >= ETH_P_802_3_MIN)
+	ethertype = get_unaligned_be16(&skb->data[12]);
+	if (ethertype >= ETH_P_802_3_MIN)
 		val |= MT_TXD1_ETH_802_3;
 
 	txwi[1] |= cpu_to_le32(val);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index e07707f518a2..eac2d85b5864 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -816,6 +816,7 @@ mt7921_mac_write_txwi_8023(struct mt7921_dev *dev, __le32 *txwi,
 {
 	u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
 	u8 fc_type, fc_stype;
+	u16 ethertype;
 	bool wmm = false;
 	u32 val;
 
@@ -829,7 +830,8 @@ mt7921_mac_write_txwi_8023(struct mt7921_dev *dev, __le32 *txwi,
 	val = FIELD_PREP(MT_TXD1_HDR_FORMAT, MT_HDR_FORMAT_802_3) |
 	      FIELD_PREP(MT_TXD1_TID, tid);
 
-	if (be16_to_cpu(skb->protocol) >= ETH_P_802_3_MIN)
+	ethertype = get_unaligned_be16(&skb->data[12]);
+	if (ethertype >= ETH_P_802_3_MIN)
 		val |= MT_TXD1_ETH_802_3;
 
 	txwi[1] |= cpu_to_le32(val);
-- 
2.35.1

[PATCH AUTOSEL 5.17 099/135] usbnet: Run unregister_netdev() before unbind() again

[Sasha Levin]

From: Lukas Wunner <lukas@wunner.de>

[ Upstream commit d1408f6b4dd78fb1b9e26bcf64477984e5f85409 ]

Commit 2c9d6c2b871d ("usbnet: run unbind() before unregister_netdev()")
sought to fix a use-after-free on disconnect of USB Ethernet adapters.

It turns out that a different fix is necessary to address the issue:
https://lore.kernel.org/netdev/18b3541e5372bc9b9fc733d422f4e698c089077c.1650177997.git.lukas@wunner.de/

So the commit was not necessary.

The commit made binding and unbinding of USB Ethernet asymmetrical:
Before, usbnet_probe() first invoked the ->bind() callback and then
register_netdev().  usbnet_disconnect() mirrored that by first invoking
unregister_netdev() and then ->unbind().

Since the commit, the order in usbnet_disconnect() is reversed and no
longer mirrors usbnet_probe().

One consequence is that a PHY disconnected (and stopped) in ->unbind()
is afterwards stopped once more by unregister_netdev() as it closes the
netdev before unregistering.  That necessitates a contortion in ->stop()
because the PHY may only be stopped if it hasn't already been
disconnected.

Reverting the commit allows making the call to phy_stop() unconditional
in ->stop().

Tested-by: Oleksij Rempel <o.rempel@pengutronix.de> # LAN9514/9512/9500
Tested-by: Ferry Toth <fntoth@gmail.com> # LAN9514
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Acked-by: Oliver Neukum <oneukum@suse.com>
Cc: Martyn Welch <martyn.welch@collabora.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/usb/asix_devices.c | 6 +-----
 drivers/net/usb/smsc95xx.c     | 3 +--
 drivers/net/usb/usbnet.c       | 6 +++---
 3 files changed, 5 insertions(+), 10 deletions(-)

diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 6b2fbdf4e0fd..34854ee537dc 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -799,11 +799,7 @@ static int ax88772_stop(struct usbnet *dev)
 {
 	struct asix_common_private *priv = dev->driver_priv;
 
-	/* On unplugged USB, we will get MDIO communication errors and the
-	 * PHY will be set in to PHY_HALTED state.
-	 */
-	if (priv->phydev->state != PHY_HALTED)
-		phy_stop(priv->phydev);
+	phy_stop(priv->phydev);
 
 	return 0;
 }
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index a0f29482294d..d81485cd7e90 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1218,8 +1218,7 @@ static int smsc95xx_start_phy(struct usbnet *dev)
 
 static int smsc95xx_stop(struct usbnet *dev)
 {
-	if (dev->net->phydev)
-		phy_stop(dev->net->phydev);
+	phy_stop(dev->net->phydev);
 
 	return 0;
 }
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 9a6450f796dc..36b24ec11650 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1616,9 +1616,6 @@ void usbnet_disconnect (struct usb_interface *intf)
 		   xdev->bus->bus_name, xdev->devpath,
 		   dev->driver_info->description);
 
-	if (dev->driver_info->unbind)
-		dev->driver_info->unbind(dev, intf);
-
 	net = dev->net;
 	unregister_netdev (net);
 
@@ -1626,6 +1623,9 @@ void usbnet_disconnect (struct usb_interface *intf)
 
 	usb_scuttle_anchored_urbs(&dev->deferred);
 
+	if (dev->driver_info->unbind)
+		dev->driver_info->unbind(dev, intf);
+
 	usb_kill_urb(dev->interrupt);
 	usb_free_urb(dev->interrupt);
 	kfree(dev->padding_pkt);
-- 
2.35.1

[PATCH AUTOSEL 5.17 100/135] Bluetooth: HCI: Add HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN quirk

[Sasha Levin]

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

[ Upstream commit 05abad857277dda198063017b00ba5b9fed2c0cb ]

This adds HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN quirk which can be
used to mark HCI_Enhanced_Setup_Synchronous_Connection as broken even
if its support command bit are set since some controller report it as
supported but the command don't work properly with some configurations
(e.g. BT_VOICE_TRANSPARENT/mSBC).

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/net/bluetooth/hci.h      | 9 +++++++++
 include/net/bluetooth/hci_core.h | 8 ++++++--
 net/bluetooth/hci_conn.c         | 2 +-
 net/bluetooth/sco.c              | 2 +-
 4 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 69ef31cea582..62a9bb022aed 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -265,6 +265,15 @@ enum {
 	 * runtime suspend, because event filtering takes place there.
 	 */
 	HCI_QUIRK_BROKEN_FILTER_CLEAR_ALL,
+
+	/*
+	 * When this quirk is set, disables the use of
+	 * HCI_OP_ENHANCED_SETUP_SYNC_CONN command to setup SCO connections.
+	 *
+	 * This quirk can be set before hci_register_dev is called or
+	 * during the hdev->setup vendor callback.
+	 */
+	HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN,
 };
 
 /* HCI device flags */
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 131514913430..49a88b2f4678 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1483,8 +1483,12 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 #define privacy_mode_capable(dev) (use_ll_privacy(dev) && \
 				   (hdev->commands[39] & 0x04))
 
-/* Use enhanced synchronous connection if command is supported */
-#define enhanced_sco_capable(dev) ((dev)->commands[29] & 0x08)
+/* Use enhanced synchronous connection if command is supported and its quirk
+ * has not been set.
+ */
+#define enhanced_sync_conn_capable(dev) \
+	(((dev)->commands[29] & 0x08) && \
+	 !test_bit(HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN, &(dev)->quirks))
 
 /* Use ext scanning if set ext scan param and ext scan enable is supported */
 #define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 84312c836549..cd51bf2a709b 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -481,7 +481,7 @@ static bool hci_setup_sync_conn(struct hci_conn *conn, __u16 handle)
 
 bool hci_setup_sync(struct hci_conn *conn, __u16 handle)
 {
-	if (enhanced_sco_capable(conn->hdev))
+	if (enhanced_sync_conn_capable(conn->hdev))
 		return hci_enhanced_setup_sync_conn(conn, handle);
 
 	return hci_setup_sync_conn(conn, handle);
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 8eabf41b2993..2a58c7d88433 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -885,7 +885,7 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname,
 			err = -EBADFD;
 			break;
 		}
-		if (enhanced_sco_capable(hdev) &&
+		if (enhanced_sync_conn_capable(hdev) &&
 		    voice.setting == BT_VOICE_TRANSPARENT)
 			sco_pi(sk)->codec.id = BT_CODEC_TRANSPARENT;
 		hci_dev_put(hdev);
-- 
2.35.1

[PATCH AUTOSEL 5.17 112/135] net: phy: micrel: Allow probing without .driver_data

[Sasha Levin]

From: Fabio Estevam <festevam@denx.de>

[ Upstream commit f2ef6f7539c68c6bd6c32323d8845ee102b7c450 ]

Currently, if the .probe element is present in the phy_driver structure
and the .driver_data is not, a NULL pointer dereference happens.

Allow passing .probe without .driver_data by inserting NULL checks
for priv->type.

Signed-off-by: Fabio Estevam <festevam@denx.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20220513114613.762810-1-festevam@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/phy/micrel.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index cfb5378bbb39..f20d8c3e91bf 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -348,7 +348,7 @@ static int kszphy_config_reset(struct phy_device *phydev)
 		}
 	}
 
-	if (priv->led_mode >= 0)
+	if (priv->type && priv->led_mode >= 0)
 		kszphy_setup_led(phydev, priv->type->led_mode_reg, priv->led_mode);
 
 	return 0;
@@ -364,10 +364,10 @@ static int kszphy_config_init(struct phy_device *phydev)
 
 	type = priv->type;
 
-	if (type->has_broadcast_disable)
+	if (type && type->has_broadcast_disable)
 		kszphy_broadcast_disable(phydev);
 
-	if (type->has_nand_tree_disable)
+	if (type && type->has_nand_tree_disable)
 		kszphy_nand_tree_disable(phydev);
 
 	return kszphy_config_reset(phydev);
@@ -1365,7 +1365,7 @@ static int kszphy_probe(struct phy_device *phydev)
 
 	priv->type = type;
 
-	if (type->led_mode_reg) {
+	if (type && type->led_mode_reg) {
 		ret = of_property_read_u32(np, "micrel,led-mode",
 				&priv->led_mode);
 		if (ret)
@@ -1386,7 +1386,8 @@ static int kszphy_probe(struct phy_device *phydev)
 		unsigned long rate = clk_get_rate(clk);
 		bool rmii_ref_clk_sel_25_mhz;
 
-		priv->rmii_ref_clk_sel = type->has_rmii_ref_clk_sel;
+		if (type)
+			priv->rmii_ref_clk_sel = type->has_rmii_ref_clk_sel;
 		rmii_ref_clk_sel_25_mhz = of_property_read_bool(np,
 				"micrel,rmii-reference-clock-select-25-mhz");
 
-- 
2.35.1

[PATCH AUTOSEL 5.17 115/135] rtw89: cfo: check mac_id to avoid out-of-bounds

[Sasha Levin]

From: Ping-Ke Shih <pkshih@realtek.com>

[ Upstream commit 97df85871a5b187609d30fca6d85b912d9e02f29 ]

Somehow, hardware reports incorrect mac_id and pollute memory. Check index
before we access the array.

  UBSAN: array-index-out-of-bounds in rtw89/phy.c:2517:23
  index 188 is out of range for type 's32 [64]'
  CPU: 1 PID: 51550 Comm: irq/35-rtw89_pc Tainted: G           OE
  Call Trace:
   <IRQ>
   show_stack+0x52/0x58
   dump_stack_lvl+0x4c/0x63
   dump_stack+0x10/0x12
   ubsan_epilogue+0x9/0x45
   __ubsan_handle_out_of_bounds.cold+0x44/0x49
   ? __alloc_skb+0x92/0x1d0
   rtw89_phy_cfo_parse+0x44/0x7f [rtw89_core]
   rtw89_core_rx+0x261/0x871 [rtw89_core]
   ? __alloc_skb+0xee/0x1d0
   rtw89_pci_napi_poll+0x3fa/0x4ea [rtw89_pci]
   __napi_poll+0x33/0x1a0
   net_rx_action+0x126/0x260
   ? __queue_work+0x217/0x4c0
   __do_softirq+0xd9/0x315
   ? disable_irq_nosync+0x10/0x10
   do_softirq.part.0+0x6d/0x90
   </IRQ>
   <TASK>
   __local_bh_enable_ip+0x62/0x70
   rtw89_pci_interrupt_threadfn+0x182/0x1a6 [rtw89_pci]
   irq_thread_fn+0x28/0x60
   irq_thread+0xc8/0x190
   ? irq_thread_fn+0x60/0x60
   kthread+0x16b/0x190
   ? irq_thread_check_affinity+0xe0/0xe0
   ? set_kthread_struct+0x50/0x50
   ret_from_fork+0x22/0x30
   </TASK>

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220516005215.5878-4-pkshih@realtek.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/realtek/rtw89/phy.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index 147009888de0..777ad4e8f45f 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -1872,6 +1872,11 @@ void rtw89_phy_cfo_parse(struct rtw89_dev *rtwdev, s16 cfo_val,
 	struct rtw89_cfo_tracking_info *cfo = &rtwdev->cfo_tracking;
 	u8 macid = phy_ppdu->mac_id;
 
+	if (macid >= CFO_TRACK_MAX_USER) {
+		rtw89_warn(rtwdev, "mac_id %d is out of range\n", macid);
+		return;
+	}
+
 	cfo->cfo_tail[macid] += cfo_val;
 	cfo->cfo_cnt[macid]++;
 	cfo->packet_count++;
-- 
2.35.1

[PATCH AUTOSEL 5.17 122/135] can: mcp251xfd: silence clang's -Wunaligned-access warning

[Sasha Levin]

From: Vincent Mailhol <mailhol.vincent@wanadoo.fr>

[ Upstream commit 1a6dd9996699889313327be03981716a8337656b ]

clang emits a -Wunaligned-access warning on union
mcp251xfd_tx_ojb_load_buf.

The reason is that field hw_tx_obj (not declared as packed) is being
packed right after a 16 bits field inside a packed struct:

| union mcp251xfd_tx_obj_load_buf {
| 	struct __packed {
| 		struct mcp251xfd_buf_cmd cmd;
| 		  /* ^ 16 bits fields */
| 		struct mcp251xfd_hw_tx_obj_raw hw_tx_obj;
| 		  /* ^ not declared as packed */
| 	} nocrc;
| 	struct __packed {
| 		struct mcp251xfd_buf_cmd_crc cmd;
| 		struct mcp251xfd_hw_tx_obj_raw hw_tx_obj;
| 		__be16 crc;
| 	} crc;
| } ____cacheline_aligned;

Starting from LLVM 14, having an unpacked struct nested in a packed
struct triggers a warning. c.f. [1].

This is a false positive because the field is always being accessed
with the relevant put_unaligned_*() function. Adding __packed to the
structure declaration silences the warning.

[1] https://github.com/llvm/llvm-project/issues/55520

Link: https://lore.kernel.org/all/20220518114357.55452-1-mailhol.vincent@wanadoo.fr
Signed-off-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Reported-by: kernel test robot <lkp@intel.com>
Tested-by: Nathan Chancellor <nathan@kernel.org> # build
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/can/spi/mcp251xfd/mcp251xfd.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
index f551c900803e..aed6e9d47517 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
@@ -434,7 +434,7 @@ struct mcp251xfd_hw_tef_obj {
 /* The tx_obj_raw version is used in spi async, i.e. without
  * regmap. We have to take care of endianness ourselves.
  */
-struct mcp251xfd_hw_tx_obj_raw {
+struct __packed mcp251xfd_hw_tx_obj_raw {
 	__le32 id;
 	__le32 flags;
 	u8 data[sizeof_field(struct canfd_frame, data)];
-- 
2.35.1

[PATCH AUTOSEL 5.17 124/135] net: ipa: ignore endianness if there is no header

[Sasha Levin]

From: Alex Elder <elder@linaro.org>

[ Upstream commit 332ef7c814bdd60f08d0d9013d0e1104798b2d23 ]

If we program an RX endpoint to have no header (header length is 0),
header-related endpoint configuration values are meaningless and are
ignored.

The only case we support that defines a header is QMAP endpoints.
In ipa_endpoint_init_hdr_ext() we set the endianness mask value
unconditionally, but it should not be done if there is no header
(meaning it is not configured for QMAP).

Set the endianness conditionally, and rearrange the logic in that
function slightly to avoid testing the qmap flag twice.

Delete an incorrect comment in ipa_endpoint_init_aggr().

Signed-off-by: Alex Elder <elder@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ipa/ipa_endpoint.c | 32 +++++++++++++++++---------------
 1 file changed, 17 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c
index 2ecfc17544a6..58b3a2d15d31 100644
--- a/drivers/net/ipa/ipa_endpoint.c
+++ b/drivers/net/ipa/ipa_endpoint.c
@@ -571,19 +571,23 @@ static void ipa_endpoint_init_hdr_ext(struct ipa_endpoint *endpoint)
 	struct ipa *ipa = endpoint->ipa;
 	u32 val = 0;
 
-	val |= HDR_ENDIANNESS_FMASK;		/* big endian */
-
-	/* A QMAP header contains a 6 bit pad field at offset 0.  The RMNet
-	 * driver assumes this field is meaningful in packets it receives,
-	 * and assumes the header's payload length includes that padding.
-	 * The RMNet driver does *not* pad packets it sends, however, so
-	 * the pad field (although 0) should be ignored.
-	 */
-	if (endpoint->data->qmap && !endpoint->toward_ipa) {
-		val |= HDR_TOTAL_LEN_OR_PAD_VALID_FMASK;
-		/* HDR_TOTAL_LEN_OR_PAD is 0 (pad, not total_len) */
-		val |= HDR_PAYLOAD_LEN_INC_PADDING_FMASK;
-		/* HDR_TOTAL_LEN_OR_PAD_OFFSET is 0 */
+	if (endpoint->data->qmap) {
+		/* We have a header, so we must specify its endianness */
+		val |= HDR_ENDIANNESS_FMASK;	/* big endian */
+
+		/* A QMAP header contains a 6 bit pad field at offset 0.
+		 * The RMNet driver assumes this field is meaningful in
+		 * packets it receives, and assumes the header's payload
+		 * length includes that padding.  The RMNet driver does
+		 * *not* pad packets it sends, however, so the pad field
+		 * (although 0) should be ignored.
+		 */
+		if (!endpoint->toward_ipa) {
+			val |= HDR_TOTAL_LEN_OR_PAD_VALID_FMASK;
+			/* HDR_TOTAL_LEN_OR_PAD is 0 (pad, not total_len) */
+			val |= HDR_PAYLOAD_LEN_INC_PADDING_FMASK;
+			/* HDR_TOTAL_LEN_OR_PAD_OFFSET is 0 */
+		}
 	}
 
 	/* HDR_PAYLOAD_LEN_INC_PADDING is 0 */
@@ -739,8 +743,6 @@ static void ipa_endpoint_init_aggr(struct ipa_endpoint *endpoint)
 
 			close_eof = endpoint->data->rx.aggr_close_eof;
 			val |= aggr_sw_eof_active_encoded(version, close_eof);
-
-			/* AGGR_HARD_BYTE_LIMIT_ENABLE is 0 */
 		} else {
 			val |= u32_encode_bits(IPA_ENABLE_DEAGGR,
 					       AGGR_EN_FMASK);
-- 
2.35.1

[PATCH AUTOSEL 5.17 126/135] selftests/bpf: Add missing trampoline program type to trampoline_count test

[Sasha Levin]

From: Yuntao Wang <ytcoode@gmail.com>

[ Upstream commit b23316aabffa835ecc516cb81daeef5b9155e8a5 ]

Currently the trampoline_count test doesn't include any fmod_ret bpf
programs, fix it to make the test cover all possible trampoline program
types.

Since fmod_ret bpf programs can't be attached to __set_task_comm function,
as it's neither whitelisted for error injection nor a security hook, change
it to bpf_modify_return_test.

This patch also does some other cleanups such as removing duplicate code,
dropping inconsistent comments, etc.

Signed-off-by: Yuntao Wang <ytcoode@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20220519150610.601313-1-ytcoode@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/linux/bpf.h                           |   2 +-
 .../bpf/prog_tests/trampoline_count.c         | 134 +++++++-----------
 .../bpf/progs/test_trampoline_count.c         |  16 ++-
 3 files changed, 61 insertions(+), 91 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 3121d1fc8e75..2f7e00e7af37 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -652,7 +652,7 @@ struct btf_func_model {
 #define BPF_TRAMP_F_RET_FENTRY_RET	BIT(4)
 
 /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
- * bytes on x86.  Pick a number to fit into BPF_IMAGE_SIZE / 2
+ * bytes on x86.
  */
 #define BPF_MAX_TRAMP_PROGS 38
 
diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
index 9c795ee52b7b..b0acbda6dbf5 100644
--- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
+++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
@@ -1,126 +1,94 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #define _GNU_SOURCE
-#include <sched.h>
-#include <sys/prctl.h>
 #include <test_progs.h>
 
 #define MAX_TRAMP_PROGS 38
 
 struct inst {
 	struct bpf_object *obj;
-	struct bpf_link   *link_fentry;
-	struct bpf_link   *link_fexit;
+	struct bpf_link   *link;
 };
 
-static int test_task_rename(void)
-{
-	int fd, duration = 0, err;
-	char buf[] = "test_overhead";
-
-	fd = open("/proc/self/comm", O_WRONLY|O_TRUNC);
-	if (CHECK(fd < 0, "open /proc", "err %d", errno))
-		return -1;
-	err = write(fd, buf, sizeof(buf));
-	if (err < 0) {
-		CHECK(err < 0, "task rename", "err %d", errno);
-		close(fd);
-		return -1;
-	}
-	close(fd);
-	return 0;
-}
-
-static struct bpf_link *load(struct bpf_object *obj, const char *name)
+static struct bpf_program *load_prog(char *file, char *name, struct inst *inst)
 {
+	struct bpf_object *obj;
 	struct bpf_program *prog;
-	int duration = 0;
+	int err;
+
+	obj = bpf_object__open_file(file, NULL);
+	if (!ASSERT_OK_PTR(obj, "obj_open_file"))
+		return NULL;
+
+	inst->obj = obj;
+
+	err = bpf_object__load(obj);
+	if (!ASSERT_OK(err, "obj_load"))
+		return NULL;
 
 	prog = bpf_object__find_program_by_name(obj, name);
-	if (CHECK(!prog, "find_probe", "prog '%s' not found\n", name))
-		return ERR_PTR(-EINVAL);
-	return bpf_program__attach_trace(prog);
+	if (!ASSERT_OK_PTR(prog, "obj_find_prog"))
+		return NULL;
+
+	return prog;
 }
 
 /* TODO: use different target function to run in concurrent mode */
 void serial_test_trampoline_count(void)
 {
-	const char *fentry_name = "prog1";
-	const char *fexit_name = "prog2";
-	const char *object = "test_trampoline_count.o";
-	struct inst inst[MAX_TRAMP_PROGS] = {};
-	int err, i = 0, duration = 0;
-	struct bpf_object *obj;
+	char *file = "test_trampoline_count.o";
+	char *const progs[] = { "fentry_test", "fmod_ret_test", "fexit_test" };
+	struct inst inst[MAX_TRAMP_PROGS + 1] = {};
+	struct bpf_program *prog;
 	struct bpf_link *link;
-	char comm[16] = {};
+	int prog_fd, err, i;
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
 
 	/* attach 'allowed' trampoline programs */
 	for (i = 0; i < MAX_TRAMP_PROGS; i++) {
-		obj = bpf_object__open_file(object, NULL);
-		if (!ASSERT_OK_PTR(obj, "obj_open_file")) {
-			obj = NULL;
+		prog = load_prog(file, progs[i % ARRAY_SIZE(progs)], &inst[i]);
+		if (!prog)
 			goto cleanup;
-		}
 
-		err = bpf_object__load(obj);
-		if (CHECK(err, "obj_load", "err %d\n", err))
+		link = bpf_program__attach(prog);
+		if (!ASSERT_OK_PTR(link, "attach_prog"))
 			goto cleanup;
-		inst[i].obj = obj;
-		obj = NULL;
-
-		if (rand() % 2) {
-			link = load(inst[i].obj, fentry_name);
-			if (!ASSERT_OK_PTR(link, "attach_prog")) {
-				link = NULL;
-				goto cleanup;
-			}
-			inst[i].link_fentry = link;
-		} else {
-			link = load(inst[i].obj, fexit_name);
-			if (!ASSERT_OK_PTR(link, "attach_prog")) {
-				link = NULL;
-				goto cleanup;
-			}
-			inst[i].link_fexit = link;
-		}
+
+		inst[i].link = link;
 	}
 
 	/* and try 1 extra.. */
-	obj = bpf_object__open_file(object, NULL);
-	if (!ASSERT_OK_PTR(obj, "obj_open_file")) {
-		obj = NULL;
+	prog = load_prog(file, "fmod_ret_test", &inst[i]);
+	if (!prog)
 		goto cleanup;
-	}
-
-	err = bpf_object__load(obj);
-	if (CHECK(err, "obj_load", "err %d\n", err))
-		goto cleanup_extra;
 
 	/* ..that needs to fail */
-	link = load(obj, fentry_name);
-	err = libbpf_get_error(link);
-	if (!ASSERT_ERR_PTR(link, "cannot attach over the limit")) {
-		bpf_link__destroy(link);
-		goto cleanup_extra;
+	link = bpf_program__attach(prog);
+	if (!ASSERT_ERR_PTR(link, "attach_prog")) {
+		inst[i].link = link;
+		goto cleanup;
 	}
 
 	/* with E2BIG error */
-	ASSERT_EQ(err, -E2BIG, "proper error check");
-	ASSERT_EQ(link, NULL, "ptr_is_null");
+	if (!ASSERT_EQ(libbpf_get_error(link), -E2BIG, "E2BIG"))
+		goto cleanup;
+	if (!ASSERT_EQ(link, NULL, "ptr_is_null"))
+		goto cleanup;
 
 	/* and finaly execute the probe */
-	if (CHECK_FAIL(prctl(PR_GET_NAME, comm, 0L, 0L, 0L)))
-		goto cleanup_extra;
-	CHECK_FAIL(test_task_rename());
-	CHECK_FAIL(prctl(PR_SET_NAME, comm, 0L, 0L, 0L));
+	prog_fd = bpf_program__fd(prog);
+	if (!ASSERT_GE(prog_fd, 0, "bpf_program__fd"))
+		goto cleanup;
+
+	err = bpf_prog_test_run_opts(prog_fd, &opts);
+	if (!ASSERT_OK(err, "bpf_prog_test_run_opts"))
+		goto cleanup;
+
+	ASSERT_EQ(opts.retval & 0xffff, 4, "bpf_modify_return_test.result");
+	ASSERT_EQ(opts.retval >> 16, 1, "bpf_modify_return_test.side_effect");
 
-cleanup_extra:
-	bpf_object__close(obj);
 cleanup:
-	if (i >= MAX_TRAMP_PROGS)
-		i = MAX_TRAMP_PROGS - 1;
 	for (; i >= 0; i--) {
-		bpf_link__destroy(inst[i].link_fentry);
-		bpf_link__destroy(inst[i].link_fexit);
+		bpf_link__destroy(inst[i].link);
 		bpf_object__close(inst[i].obj);
 	}
 }
diff --git a/tools/testing/selftests/bpf/progs/test_trampoline_count.c b/tools/testing/selftests/bpf/progs/test_trampoline_count.c
index f030e469d05b..7765720da7d5 100644
--- a/tools/testing/selftests/bpf/progs/test_trampoline_count.c
+++ b/tools/testing/selftests/bpf/progs/test_trampoline_count.c
@@ -1,20 +1,22 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <stdbool.h>
-#include <stddef.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
-struct task_struct;
+SEC("fentry/bpf_modify_return_test")
+int BPF_PROG(fentry_test, int a, int *b)
+{
+	return 0;
+}
 
-SEC("fentry/__set_task_comm")
-int BPF_PROG(prog1, struct task_struct *tsk, const char *buf, bool exec)
+SEC("fmod_ret/bpf_modify_return_test")
+int BPF_PROG(fmod_ret_test, int a, int *b, int ret)
 {
 	return 0;
 }
 
-SEC("fexit/__set_task_comm")
-int BPF_PROG(prog2, struct task_struct *tsk, const char *buf, bool exec)
+SEC("fexit/bpf_modify_return_test")
+int BPF_PROG(fexit_test, int a, int *b, int ret)
 {
 	return 0;
 }
-- 
2.35.1

[PATCH AUTOSEL 5.17 129/135] rxrpc: Return an error to sendmsg if call failed

[Sasha Levin]

From: David Howells <dhowells@redhat.com>

[ Upstream commit 4ba68c5192554876bd8c3afd904e3064d2915341 ]

If at the end of rxrpc sendmsg() or rxrpc_kernel_send_data() the call that
was being given data was aborted remotely or otherwise failed, return an
error rather than returning the amount of data buffered for transmission.

The call (presumably) did not complete, so there's not much point
continuing with it.  AF_RXRPC considers it "complete" and so will be
unwilling to do anything else with it - and won't send a notification for
it, deeming the return from sendmsg sufficient.

Not returning an error causes afs to incorrectly handle a StoreData
operation that gets interrupted by a change of address due to NAT
reconfiguration.

This doesn't normally affect most operations since their request parameters
tend to fit into a single UDP packet and afs_make_call() returns before the
server responds; StoreData is different as it involves transmission of a
lot of data.

This can be triggered on a client by doing something like:

	dd if=/dev/zero of=/afs/example.com/foo bs=1M count=512

at one prompt, and then changing the network address at another prompt,
e.g.:

	ifconfig enp6s0 inet 192.168.6.2 && route add 192.168.6.1 dev enp6s0

Tracing packets on an Auristor fileserver looks something like:

192.168.6.1 -> 192.168.6.3  RX 107 ACK Idle  Seq: 0  Call: 4  Source Port: 7000  Destination Port: 7001
192.168.6.3 -> 192.168.6.1  AFS (RX) 1482 FS Request: Unknown(64538) (64538)
192.168.6.3 -> 192.168.6.1  AFS (RX) 1482 FS Request: Unknown(64538) (64538)
192.168.6.1 -> 192.168.6.3  RX 107 ACK Idle  Seq: 0  Call: 4  Source Port: 7000  Destination Port: 7001
<ARP exchange for 192.168.6.2>
192.168.6.2 -> 192.168.6.1  AFS (RX) 1482 FS Request: Unknown(0) (0)
192.168.6.2 -> 192.168.6.1  AFS (RX) 1482 FS Request: Unknown(0) (0)
192.168.6.1 -> 192.168.6.2  RX 107 ACK Exceeds Window  Seq: 0  Call: 4  Source Port: 7000  Destination Port: 7001
192.168.6.1 -> 192.168.6.2  RX 74 ABORT  Seq: 0  Call: 4  Source Port: 7000  Destination Port: 7001
192.168.6.1 -> 192.168.6.2  RX 74 ABORT  Seq: 29321  Call: 4  Source Port: 7000  Destination Port: 7001

The Auristor fileserver logs code -453 (RXGEN_SS_UNMARSHAL), but the abort
code received by kafs is -5 (RX_PROTOCOL_ERROR) as the rx layer sees the
condition and generates an abort first and the unmarshal error is a
consequence of that at the application layer.

Reported-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-afs@lists.infradead.org
Link: http://lists.infradead.org/pipermail/linux-afs/2021-December/004810.html # v1
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/rxrpc/sendmsg.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index af8ad6c30b9f..1d38e279e2ef 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -444,6 +444,12 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 
 success:
 	ret = copied;
+	if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE) {
+		read_lock_bh(&call->state_lock);
+		if (call->error < 0)
+			ret = call->error;
+		read_unlock_bh(&call->state_lock);
+	}
 out:
 	call->tx_pending = skb;
 	_leave(" = %d", ret);
-- 
2.35.1

[PATCH AUTOSEL 5.17 130/135] rxrpc, afs: Fix selection of abort codes

[Sasha Levin]

From: David Howells <dhowells@redhat.com>

[ Upstream commit de696c4784f0706884458893c5a6c39b3a3ff65c ]

The RX_USER_ABORT code should really only be used to indicate that the user
of the rxrpc service (ie. userspace) implicitly caused a call to be aborted
- for instance if the AF_RXRPC socket is closed whilst the call was in
progress.  (The user may also explicitly abort a call and specify the abort
code to use).

Change some of the points of generation to use other abort codes instead:

 (1) Abort the call with RXGEN_SS_UNMARSHAL or RXGEN_CC_UNMARSHAL if we see
     ENOMEM and EFAULT during received data delivery and abort with
     RX_CALL_DEAD in the default case.

 (2) Abort with RXGEN_SS_MARSHAL if we get ENOMEM whilst trying to send a
     reply.

 (3) Abort with RX_CALL_DEAD if we stop hearing from the peer if we had
     heard from the peer and abort with RX_CALL_TIMEOUT if we hadn't.

 (4) Abort with RX_CALL_DEAD if we try to disconnect a call that's not
     completed successfully or been aborted.

Reported-by: Jeffrey Altman <jaltman@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/afs/rxrpc.c          | 8 +++++---
 net/rxrpc/call_event.c  | 4 ++--
 net/rxrpc/conn_object.c | 2 +-
 3 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 23a1a92d64bb..a5434f3e57c6 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -537,6 +537,8 @@ static void afs_deliver_to_call(struct afs_call *call)
 		case -ENODATA:
 		case -EBADMSG:
 		case -EMSGSIZE:
+		case -ENOMEM:
+		case -EFAULT:
 			abort_code = RXGEN_CC_UNMARSHAL;
 			if (state != AFS_CALL_CL_AWAIT_REPLY)
 				abort_code = RXGEN_SS_UNMARSHAL;
@@ -544,7 +546,7 @@ static void afs_deliver_to_call(struct afs_call *call)
 						abort_code, ret, "KUM");
 			goto local_abort;
 		default:
-			abort_code = RX_USER_ABORT;
+			abort_code = RX_CALL_DEAD;
 			rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
 						abort_code, ret, "KER");
 			goto local_abort;
@@ -836,7 +838,7 @@ void afs_send_empty_reply(struct afs_call *call)
 	case -ENOMEM:
 		_debug("oom");
 		rxrpc_kernel_abort_call(net->socket, call->rxcall,
-					RX_USER_ABORT, -ENOMEM, "KOO");
+					RXGEN_SS_MARSHAL, -ENOMEM, "KOO");
 		fallthrough;
 	default:
 		_leave(" [error]");
@@ -878,7 +880,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
 	if (n == -ENOMEM) {
 		_debug("oom");
 		rxrpc_kernel_abort_call(net->socket, call->rxcall,
-					RX_USER_ABORT, -ENOMEM, "KOO");
+					RXGEN_SS_MARSHAL, -ENOMEM, "KOO");
 	}
 	_leave(" [error]");
 }
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index 22e05de5d1ca..e426f6831aab 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -377,9 +377,9 @@ void rxrpc_process_call(struct work_struct *work)
 		if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) &&
 		    (int)call->conn->hi_serial - (int)call->rx_serial > 0) {
 			trace_rxrpc_call_reset(call);
-			rxrpc_abort_call("EXP", call, 0, RX_USER_ABORT, -ECONNRESET);
+			rxrpc_abort_call("EXP", call, 0, RX_CALL_DEAD, -ECONNRESET);
 		} else {
-			rxrpc_abort_call("EXP", call, 0, RX_USER_ABORT, -ETIME);
+			rxrpc_abort_call("EXP", call, 0, RX_CALL_TIMEOUT, -ETIME);
 		}
 		set_bit(RXRPC_CALL_EV_ABORT, &call->events);
 		goto recheck_state;
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index b2159dbf5412..660cd9b1a465 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -183,7 +183,7 @@ void __rxrpc_disconnect_call(struct rxrpc_connection *conn,
 			chan->last_type = RXRPC_PACKET_TYPE_ABORT;
 			break;
 		default:
-			chan->last_abort = RX_USER_ABORT;
+			chan->last_abort = RX_CALL_DEAD;
 			chan->last_type = RXRPC_PACKET_TYPE_ABORT;
 			break;
 		}
-- 
2.35.1

[PATCH AUTOSEL 5.17 131/135] afs: Adjust ACK interpretation to try and cope with NAT

[Sasha Levin]

From: David Howells <dhowells@redhat.com>

[ Upstream commit adc9613ff66c26ebaff9814973181ac178beb90b ]

If a client's address changes, say if it is NAT'd, this can disrupt an in
progress operation.  For most operations, this is not much of a problem,
but StoreData can be different as some servers modify the target file as
the data comes in, so if a store request is disrupted, the file can get
corrupted on the server.

The problem is that the server doesn't recognise packets that come after
the change of address as belonging to the original client and will bounce
them, either by sending an OUT_OF_SEQUENCE ACK to the apparent new call if
the packet number falls within the initial sequence number window of a call
or by sending an EXCEEDS_WINDOW ACK if it falls outside and then aborting
it.  In both cases, firstPacket will be 1 and previousPacket will be 0 in
the ACK information.

Fix this by the following means:

 (1) If a client call receives an EXCEEDS_WINDOW ACK with firstPacket as 1
     and previousPacket as 0, assume this indicates that the server saw the
     incoming packets from a different peer and thus as a different call.
     Fail the call with error -ENETRESET.

 (2) Also fail the call if a similar OUT_OF_SEQUENCE ACK occurs if the
     first packet has been hard-ACK'd.  If it hasn't been hard-ACK'd, the
     ACK packet will cause it to get retransmitted, so the call will just
     be repeated.

 (3) Make afs_select_fileserver() treat -ENETRESET as a straight fail of
     the operation.

 (4) Prioritise the error code over things like -ECONNRESET as the server
     did actually respond.

 (5) Make writeback treat -ENETRESET as a retryable error and make it
     redirty all the pages involved in a write so that the VM will retry.

Note that there is still a circumstance that I can't easily deal with: if
the operation is fully received and processed by the server, but the reply
is lost due to address change.  There's no way to know if the op happened.
We can examine the server, but a conflicting change could have been made by
a third party - and we can't tell the difference.  In such a case, a
message like:

    kAFS: vnode modified {100058:146266} b7->b8 YFS.StoreData64 (op=2646a)

will be logged to dmesg on the next op to touch the file and the client
will reset the inode state, including invalidating clean parts of the
pagecache.

Reported-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-afs@lists.infradead.org
Link: http://lists.infradead.org/pipermail/linux-afs/2021-December/004811.html # v1
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/afs/misc.c     |  5 ++++-
 fs/afs/rotate.c   |  4 ++++
 fs/afs/write.c    |  1 +
 net/rxrpc/input.c | 27 +++++++++++++++++++++++++++
 4 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/fs/afs/misc.c b/fs/afs/misc.c
index 1d1a8debe472..933e67fcdab1 100644
--- a/fs/afs/misc.c
+++ b/fs/afs/misc.c
@@ -163,8 +163,11 @@ void afs_prioritise_error(struct afs_error *e, int error, u32 abort_code)
 		return;
 
 	case -ECONNABORTED:
+		error = afs_abort_to_error(abort_code);
+		fallthrough;
+	case -ENETRESET: /* Responded, but we seem to have changed address */
 		e->responded = true;
-		e->error = afs_abort_to_error(abort_code);
+		e->error = error;
 		return;
 	}
 }
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index 79e1a5f6701b..a840c3588ebb 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -292,6 +292,10 @@ bool afs_select_fileserver(struct afs_operation *op)
 		op->error = error;
 		goto iterate_address;
 
+	case -ENETRESET:
+		pr_warn("kAFS: Peer reset %s (op=%x)\n",
+			op->type ? op->type->name : "???", op->debug_id);
+		fallthrough;
 	case -ECONNRESET:
 		_debug("call reset");
 		op->error = error;
diff --git a/fs/afs/write.c b/fs/afs/write.c
index f447c902318d..07454b1ed240 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -638,6 +638,7 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
 	case -EKEYEXPIRED:
 	case -EKEYREJECTED:
 	case -EKEYREVOKED:
+	case -ENETRESET:
 		afs_redirty_pages(wbc, mapping, start, len);
 		mapping_set_error(mapping, ret);
 		break;
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index dc201363f2c4..67d3eba60dc7 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -903,6 +903,33 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 				  rxrpc_propose_ack_respond_to_ack);
 	}
 
+	/* If we get an EXCEEDS_WINDOW ACK from the server, it probably
+	 * indicates that the client address changed due to NAT.  The server
+	 * lost the call because it switched to a different peer.
+	 */
+	if (unlikely(buf.ack.reason == RXRPC_ACK_EXCEEDS_WINDOW) &&
+	    first_soft_ack == 1 &&
+	    prev_pkt == 0 &&
+	    rxrpc_is_client_call(call)) {
+		rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED,
+					  0, -ENETRESET);
+		return;
+	}
+
+	/* If we get an OUT_OF_SEQUENCE ACK from the server, that can also
+	 * indicate a change of address.  However, we can retransmit the call
+	 * if we still have it buffered to the beginning.
+	 */
+	if (unlikely(buf.ack.reason == RXRPC_ACK_OUT_OF_SEQUENCE) &&
+	    first_soft_ack == 1 &&
+	    prev_pkt == 0 &&
+	    call->tx_hard_ack == 0 &&
+	    rxrpc_is_client_call(call)) {
+		rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED,
+					  0, -ENETRESET);
+		return;
+	}
+
 	/* Discard any out-of-order or duplicate ACKs (outside lock). */
 	if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) {
 		trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial,
-- 
2.35.1

[PATCH AUTOSEL 5.17 132/135] eth: tg3: silence the GCC 12 array-bounds warning

[Sasha Levin]

From: Jakub Kicinski <kuba@kernel.org>

[ Upstream commit 9dec850fd7c210a04b4707df8e6c95bfafdd6a4b ]

GCC 12 currently generates a rather inconsistent warning:

drivers/net/ethernet/broadcom/tg3.c:17795:51: warning: array subscript 5 is above array bounds of ‘struct tg3_napi[5]’ [-Warray-bounds]
17795 |                 struct tg3_napi *tnapi = &tp->napi[i];
      |                                           ~~~~~~~~^~~

i is guaranteed < tp->irq_max which in turn is either 1 or 5.
There are more loops like this one in the driver, but strangely
GCC 12 dislikes only this single one.

Silence this silliness for now.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/broadcom/Makefile | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/Makefile b/drivers/net/ethernet/broadcom/Makefile
index 0ddfb5b5d53c..2e6c5f258a1f 100644
--- a/drivers/net/ethernet/broadcom/Makefile
+++ b/drivers/net/ethernet/broadcom/Makefile
@@ -17,3 +17,8 @@ obj-$(CONFIG_BGMAC_BCMA) += bgmac-bcma.o bgmac-bcma-mdio.o
 obj-$(CONFIG_BGMAC_PLATFORM) += bgmac-platform.o
 obj-$(CONFIG_SYSTEMPORT) += bcmsysport.o
 obj-$(CONFIG_BNXT) += bnxt/
+
+# FIXME: temporarily silence -Warray-bounds on non W=1+ builds
+ifndef KBUILD_EXTRA_WARN
+CFLAGS_tg3.o += -Wno-array-bounds
+endif
-- 
2.35.1

[PATCH AUTOSEL 5.17 134/135] selftests/bpf: fix btf_dump/btf_dump due to recent clang change

[Sasha Levin]

From: Yonghong Song <yhs@fb.com>

[ Upstream commit 4050764cbaa25760aab40857f723393c07898474 ]

Latest llvm-project upstream had a change of behavior
related to qualifiers on function return type ([1]).
This caused selftests btf_dump/btf_dump failure.
The following example shows what changed.

  $ cat t.c
  typedef const char * const (* const (* const fn_ptr_arr2_t[5])())(char * (*)(int));
  struct t {
    int a;
    fn_ptr_arr2_t l;
  };
  int foo(struct t *arg) {
    return arg->a;
  }

Compiled with latest upstream llvm15,
  $ clang -O2 -g -target bpf -S -emit-llvm t.c
The related generated debuginfo IR looks like:
  !16 = !DIDerivedType(tag: DW_TAG_typedef, name: "fn_ptr_arr2_t", file: !1, line: 1, baseType: !17)
  !17 = !DICompositeType(tag: DW_TAG_array_type, baseType: !18, size: 320, elements: !32)
  !18 = !DIDerivedType(tag: DW_TAG_const_type, baseType: !19)
  !19 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !20, size: 64)
  !20 = !DISubroutineType(types: !21)
  !21 = !{!22, null}
  !22 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !23, size: 64)
  !23 = !DISubroutineType(types: !24)
  !24 = !{!25, !28}
  !25 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !26, size: 64)
  !26 = !DIDerivedType(tag: DW_TAG_const_type, baseType: !27)
  !27 = !DIBasicType(name: "char", size: 8, encoding: DW_ATE_signed_char)
You can see two intermediate const qualifier to pointer are dropped in debuginfo IR.

With llvm14, we have following debuginfo IR:
  !16 = !DIDerivedType(tag: DW_TAG_typedef, name: "fn_ptr_arr2_t", file: !1, line: 1, baseType: !17)
  !17 = !DICompositeType(tag: DW_TAG_array_type, baseType: !18, size: 320, elements: !34)
  !18 = !DIDerivedType(tag: DW_TAG_const_type, baseType: !19)
  !19 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !20, size: 64)
  !20 = !DISubroutineType(types: !21)
  !21 = !{!22, null}
  !22 = !DIDerivedType(tag: DW_TAG_const_type, baseType: !23)
  !23 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !24, size: 64)
  !24 = !DISubroutineType(types: !25)
  !25 = !{!26, !30}
  !26 = !DIDerivedType(tag: DW_TAG_const_type, baseType: !27)
  !27 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !28, size: 64)
  !28 = !DIDerivedType(tag: DW_TAG_const_type, baseType: !29)
  !29 = !DIBasicType(name: "char", size: 8, encoding: DW_ATE_signed_char)
All const qualifiers are preserved.

To adapt the selftest to both old and new llvm, this patch removed
the intermediate const qualifier in const-to-ptr types, to make the
test succeed again.

  [1] https://reviews.llvm.org/D125919

Reported-by: Mykola Lysenko <mykolal@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/20220523152044.3905809-1-yhs@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
index 1c7105fcae3c..4ee4748133fe 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
@@ -94,7 +94,7 @@ typedef void (* (*signal_t)(int, void (*)(int)))(int);
 
 typedef char * (*fn_ptr_arr1_t[10])(int **);
 
-typedef char * (* const (* const fn_ptr_arr2_t[5])())(char * (*)(int));
+typedef char * (* (* const fn_ptr_arr2_t[5])())(char * (*)(int));
 
 struct struct_w_typedefs {
 	int_t a;
-- 
2.35.1