Skip to content

L
linux
Switch branch/tag
  1. 29 Jul, 2024 10 commits
  3. 27 Jul, 2024 3 commits
  5. 26 Jul, 2024 16 commits
    • Luiz Augusto von Dentz's avatar
      Bluetooth: hci_event: Fix setting DISCOVERY_FINDING for passive scanning · df3d6a3e
      Luiz Augusto von Dentz authored 
      DISCOVERY_FINDING shall only be set for active scanning as passive
scanning is not meant to generate MGMT Device Found events causing
discovering state to go out of sync since userspace would believe it
is discovering when in fact it is just passive scanning.

Cc: stable@vger.kernel.org
Link: https://bugzilla.kernel.org/show_bug.cgi?id=219088
Fixes: 2e2515c1 ("Bluetooth: hci_event: Set DISCOVERY_FINDING on SCAN_ENABLED")
Signed-off-by: default avatarLuiz Augusto von Dentz <luiz.von.dentz@intel.com>
      df3d6a3e
    • Arnd Bergmann's avatar
      Bluetooth: btmtk: remove #ifdef around declarations · 7a8c6fb2
      Arnd Bergmann authored 
      The caller of these functions in btusb.c is guarded with an
if(IS_ENABLED()) style check, so dead code is left out, but the
declarations are still needed at compile time:

drivers/bluetooth/btusb.c: In function 'btusb_mtk_reset':
drivers/bluetooth/btusb.c:2705:15: error: implicit declaration of function 'btmtk_usb_subsys_reset' [-Wimplicit-function-declaration]
 2705 |         err = btmtk_usb_subsys_reset(hdev, btmtk_data->dev_id);
      |               ^~~~~~~~~~~~~~~~~~~~~~
drivers/bluetooth/btusb.c: In function 'btusb_send_frame_mtk':
drivers/bluetooth/btusb.c:2720:23: error: implicit declaration of function 'alloc_mtk_intr_urb' [-Wimplicit-function-declaration]
 2720 |                 urb = alloc_mtk_intr_urb(hdev, skb, btusb_tx_complete);
      |                       ^~~~~~~~~~~~~~~~~~
drivers/bluetooth/btusb.c:2720:21: error: assignment to 'struct urb *' from 'int' makes pointer from integer without a cast [-Wint-conversion]
 2720 |                 urb = alloc_mtk_intr_urb(hdev, skb, btusb_tx_complete);
      |                     ^

Fixes: f0c83a23 ("Bluetooth: btmtk: Fix btmtk.c undefined reference build error")
Signed-off-by: default avatarArnd Bergmann <arnd@arndb.de>
Reviewed-by: default avatarAngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: default avatarLuiz Augusto von Dentz <luiz.von.dentz@intel.com>
      7a8c6fb2
    • Arnd Bergmann's avatar
      Bluetooth: btmtk: Fix btmtk.c undefined reference build error harder · 61f7a8f9
      Arnd Bergmann authored 
      The previous fix was incomplete as the link failure still persists
with CONFIG_USB=m when the sdio or serial wrappers for btmtk.c
are build-in:

btmtk.c:(.text+0x468): undefined reference to `usb_alloc_urb'
btmtk.c:(.text+0x488): undefined reference to `usb_free_urb'
btmtk.c:(.text+0x500): undefined reference to `usb_anchor_urb'
btmtk.c:(.text+0x50a): undefined reference to `usb_submit_urb'
btmtk.c:(.text+0x92c): undefined reference to `usb_control_msg'
btmtk.c:(.text+0xa92): undefined reference to `usb_unanchor_urb'
btmtk.c:(.text+0x11e4): undefined reference to `usb_set_interface'
btmtk.c:(.text+0x120a): undefined reference to `usb_kill_anchored_urbs'

Disallow this configuration.

Fixes: f0c83a23 ("Bluetooth: btmtk: Fix btmtk.c undefined reference build error")
Signed-off-by: default avatarArnd Bergmann <arnd@arndb.de>
Signed-off-by: default avatarLuiz Augusto von Dentz <luiz.von.dentz@intel.com>
      61f7a8f9
    • Chris Lu's avatar
      Bluetooth: btmtk: Fix btmtk.c undefined reference build error · f0c83a23
      Chris Lu authored 
      MediaTek moved some usb interface related function to btmtk.c which
may cause build failed if BT USB Kconfig wasn't enabled.
Fix undefined reference by adding config check.

btmtk.c:(.text+0x89c): undefined reference to `usb_alloc_urb'
btmtk.c:(.text+0x8e3): undefined reference to `usb_free_urb'
btmtk.c:(.text+0x956): undefined reference to `usb_free_urb'
btmtk.c:(.text+0xa0e): undefined reference to `usb_anchor_urb'
btmtk.c:(.text+0xb43): undefined reference to `usb_autopm_get_interface'
btmtk.c:(.text+0xb7e): undefined reference to `usb_autopm_put_interface'
btmtk.c:(.text+0xf70): undefined reference to `usb_disable_autosuspend'
btmtk.c:(.text+0x133a): undefined reference to `usb_control_msg'

Fixes: d019930b ("Bluetooth: btmtk: move btusb_mtk_hci_wmt_sync to btmtk.c")
Reported-by: default avatarkernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202407091928.AH0aGZnx-lkp@intel.com/Signed-off-by: default avatarChris Lu <chris.lu@mediatek.com>
Signed-off-by: default avatarLuiz Augusto von Dentz <luiz.von.dentz@intel.com>
      f0c83a23
    • Luiz Augusto von Dentz's avatar
      Bluetooth: hci_sync: Fix suspending with wrong filter policy · 96b82af3
      Luiz Augusto von Dentz authored 
      When suspending the scan filter policy cannot be 0x00 (no acceptlist)
since that means the host has to process every advertisement report
waking up the system, so this attempts to check if hdev is marked as
suspended and if the resulting filter policy would be 0x00 (no
acceptlist) then skip passive scanning if thre no devices in the
acceptlist otherwise reset the filter policy to 0x01 so the acceptlist
is used since the devices programmed there can still wakeup be system.

Fixes: 182ee45d ("Bluetooth: hci_sync: Rework hci_suspend_notifier")
Signed-off-by: default avatarLuiz Augusto von Dentz <luiz.von.dentz@intel.com>
      96b82af3
    • Chris Lu's avatar
      Bluetooth: btmtk: Fix kernel crash when entering btmtk_usb_suspend · d09009bc
      Chris Lu authored 
      If MediaTek's Bluetooth setup is unsuccessful, a NULL pointer issue
occur when the system is suspended and the anchored kill function
is called. To avoid this, add protection to prevent executing the
anchored kill function if the setup is unsuccessful.

[    6.922106] Hardware name: Acer Tomato (rev2) board (DT)
[    6.922114] Workqueue: pm pm_runtime_work
[    6.922132] pstate: 804000c9
(Nzcv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[    6.922147] pc : usb_kill_anchored_urbs+0x6c/0x1e0
[    6.922164] lr : usb_kill_anchored_urbs+0x48/0x1e0
[    6.922181] sp : ffff800080903b60
[    6.922187] x29: ffff800080903b60
x28: ffff2c7b85c32b80 x27: ffff2c7bbb370930
[    6.922211] x26: 00000000000f4240
x25: 00000000ffffffff x24: ffffd49ece2dcb48
[    6.922255] x20: ffffffffffffffd8
x19: 0000000000000000 x18: 0000000000000006
[    6.922276] x17: 6531656337386238
x16: 3632373862333863 x15: ffff800080903480
[    6.922297] x14: 0000000000000000
x13: 303278302f303178 x12: ffffd49ecf090e30
[    6.922318] x11: 0000000000000001
x10: 0000000000000001 x9 : ffffd49ecd2c5bb4
[    6.922339] x8 : c0000000ffffdfff
x7 : ffffd49ecefe0db8 x6 : 00000000000affa8
[    6.922360] x5 : ffff2c7bbb35dd48
x4 : 0000000000000000 x3 : 0000000000000000
[    6.922379] x2 : 0000000000000000
x1 : 0000000000000003 x0 : ffffffffffffffd8
[    6.922400] Call trace:
[    6.922405]  usb_kill_anchored_urbs+0x6c/0x1e0
[    6.922422]  btmtk_usb_suspend+0x20/0x38
[btmtk 5f200a97badbdfda4266773fee49acfc8e0224d5]
[    6.922444]  btusb_suspend+0xd0/0x210
[btusb 0bfbf19a87ff406c83b87268b87ce1e80e9a829b]
[    6.922469]  usb_suspend_both+0x90/0x288
[    6.922487]  usb_runtime_suspend+0x3c/0xa8
[    6.922507]  __rpm_callback+0x50/0x1f0
[    6.922523]  rpm_callback+0x70/0x88
[    6.922538]  rpm_suspend+0xe4/0x5a0
[    6.922553]  pm_runtime_work+0xd4/0xe0
[    6.922569]  process_one_work+0x18c/0x440
[    6.922588]  worker_thread+0x314/0x428
[    6.922606]  kthread+0x128/0x138
[    6.922621]  ret_from_fork+0x10/0x20
[    6.922644] Code: f100a274 54000520 d503201f d100a260 (b8370000)
[    6.922654] ---[ end trace 0000000000000000 ]---

Fixes: ceac1cb0 ("Bluetooth: btusb: mediatek: add ISO data transmission functions")
Signed-off-by: default avatarChris Lu <chris.lu@mediatek.com>
Reported-by: Nícolas F. R. A. Prado <nfraprado@collabora.com> #KernelCI
Tested-by: default avatarNícolas F. R. A. Prado <nfraprado@collabora.com>
Signed-off-by: default avatarLuiz Augusto von Dentz <luiz.von.dentz@intel.com>
      d09009bc
    • Kiran K's avatar
      Bluetooth: btintel: Fail setup on error · e22a3a9d
      Kiran K authored 
      Do not attempt to send any hci command to controller if *setup* function
fails.

Fixes: af395330 ("Bluetooth: btintel: Add Intel devcoredump support")
Signed-off-by: default avatarKiran K <kiran.k@intel.com>
Signed-off-by: default avatarLuiz Augusto von Dentz <luiz.von.dentz@intel.com>
      e22a3a9d
    • Mark Mentovai's avatar
      net: phy: realtek: add support for RTL8366S Gigabit PHY · 225990c4
      Mark Mentovai authored 
      The PHY built in to the Realtek RTL8366S switch controller was
previously supported by genphy_driver. This PHY does not implement MMD
operations. Since commit 9b01c885 ("net: phy: c22: migrate to
genphy_c45_write_eee_adv()"), MMD register reads have been made during
phy_probe to determine EEE support. For genphy_driver, these reads are
transformed into 802.3 annex 22D clause 45-over-clause 22
mmd_phy_indirect operations that perform MII register writes to
MII_MMD_CTRL and MII_MMD_DATA. This overwrites those two MII registers,
which on this PHY are reserved and have another function, rendering the
PHY unusable while so configured.

Proper support for this PHY is restored by providing a phy_driver that
declares MMD operations as unsupported by using the helper functions
provided for that purpose, while remaining otherwise identical to
genphy_driver.

Fixes: 9b01c885 ("net: phy: c22: migrate to genphy_c45_write_eee_adv()")
Reported-by: default avatarRussell Senior <russell@personaltelco.net>
Closes: https://github.com/openwrt/openwrt/issues/15981
Link: https://github.com/openwrt/openwrt/issues/15739Signed-off-by: default avatarMark Mentovai <mark@mentovai.com>
Reviewed-by: default avatarMaxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      225990c4
    • Johan Hovold's avatar
      wifi: ath12k: fix soft lockup on suspend · a47f3320
      Johan Hovold authored 
      The ext interrupts are enabled when the firmware has been started, but
this may never happen, for example, if the board configuration file is
missing.

When the system is later suspended, the driver unconditionally tries to
disable interrupts, which results in an irq disable imbalance and causes
the driver to spin indefinitely in napi_synchronize().

Make sure that the interrupts have been enabled before attempting to
disable them.

Fixes: d8899132 ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices")
Cc: stable@vger.kernel.org	# 6.3
Signed-off-by: default avatarJohan Hovold <johan+linaro@kernel.org>
Acked-by: default avatarJeff Johnson <quic_jjohnson@quicinc.com>
Link: https://patch.msgid.link/20240709073132.9168-1-johan+linaro@kernel.orgSigned-off-by: default avatarJohannes Berg <johannes.berg@intel.com>
      a47f3320
    • Sean Wang's avatar
      wifi: mt76: mt7921: fix null pointer access in mt792x_mac_link_bss_remove · 6557a28f
      Sean Wang authored 
      Fix null pointer access in mt792x_mac_link_bss_remove.

To prevent null pointer access, we should assign the vif to bss_conf in
mt7921_add_interface. This ensures that subsequent operations on the BSS
can properly reference the correct vif.

[  T843] Call Trace:
[  T843]  <TASK>
[  T843]  ? __die+0x1e/0x60
[  T843]  ? page_fault_oops+0x157/0x450
[  T843]  ? srso_alias_return_thunk+0x5/0xfbef5
[  T843]  ? srso_alias_return_thunk+0x5/0xfbef5
[  T843]  ? search_bpf_extables+0x5a/0x80
[  T843]  ? srso_alias_return_thunk+0x5/0xfbef5
[  T843]  ? exc_page_fault+0x2bb/0x670
[  T843]  ? srso_alias_return_thunk+0x5/0xfbef5
[  T843]  ? lock_timer_base+0x71/0x90
[  T843]  ? asm_exc_page_fault+0x26/0x30
[  T843]  ? mt792x_mac_link_bss_remove+0x24/0x110 [mt792x_lib]
[  T843]  ? mt792x_remove_interface+0x6e/0x90 [mt792x_lib]
[  T843]  ? ieee80211_do_stop+0x507/0x7e0 [mac80211]
[  T843]  ? ieee80211_stop+0x53/0x190 [mac80211]
[  T843]  ? __dev_close_many+0xa5/0x120
[  T843]  ? __dev_change_flags+0x18c/0x220
[  T843]  ? dev_change_flags+0x21/0x60
[  T843]  ? do_setlink+0xdf9/0x11d0
[  T843]  ? srso_alias_return_thunk+0x5/0xfbef5
[  T843]  ? srso_alias_return_thunk+0x5/0xfbef5
[  T843]  ? security_sock_rcv_skb+0x33/0x50
[  T843]  ? srso_alias_return_thunk+0x5/0xfbef5
[  T843]  ? srso_alias_return_thunk+0x5/0xfbef5
[  T843]  ? __nla_validate_parse+0x61/0xd10
[  T843]  ? srso_alias_return_thunk+0x5/0xfbef5
[  T843]  ? genl_done+0x53/0x80
[  T843]  ? srso_alias_return_thunk+0x5/0xfbef5
[  T843]  ? netlink_dump+0x357/0x410
[  T843]  ? __rtnl_newlink+0x5d6/0x980
[  T843]  ? srso_alias_return_thunk+0x5/0xfbef5
[  T843]  ? genl_family_rcv_msg_dumpit+0xdf/0xf0
[  T843]  ? srso_alias_return_thunk+0x5/0xfbef5
[  T843]  ? __kmalloc_cache_noprof+0x44/0x210
[  T843]  ? rtnl_newlink+0x42/0x60
[  T843]  ? rtnetlink_rcv_msg+0x152/0x3f0
[  T843]  ? mptcp_pm_nl_dump_addr+0x180/0x180
[  T843]  ? rtnl_calcit.isra.0+0x130/0x130
[  T843]  ? netlink_rcv_skb+0x56/0x100
[  T843]  ? netlink_unicast+0x199/0x290
[  T843]  ? netlink_sendmsg+0x21d/0x490
[  T843]  ? __sock_sendmsg+0x78/0x80
[  T843]  ? ____sys_sendmsg+0x23f/0x2e0
[  T843]  ? srso_alias_return_thunk+0x5/0xfbef5
[  T843]  ? copy_msghdr_from_user+0x68/0xa0
[  T843]  ? ___sys_sendmsg+0x81/0xd0
[  T843]  ? srso_alias_return_thunk+0x5/0xfbef5
[  T843]  ? crng_fast_key_erasure+0xbc/0xf0
[  T843]  ? srso_alias_return_thunk+0x5/0xfbef5
[  T843]  ? get_random_bytes_user+0x126/0x140
[  T843]  ? srso_alias_return_thunk+0x5/0xfbef5
[  T843]  ? __fdget+0xb1/0xe0
[  T843]  ? __sys_sendmsg+0x56/0xa0
[  T843]  ? srso_alias_return_thunk+0x5/0xfbef5
[  T843]  ? do_syscall_64+0x5f/0x170
[  T843]  ? entry_SYSCALL_64_after_hwframe+0x55/0x5d
[  T843]  </TASK>

Fixes: 1541d63c ("wifi: mt76: mt7925: add mt7925_mac_link_bss_remove to remove per-link BSS")
Reported-by: default avatarBert Karwatzki <spasswolf@web.de>
Closes: https://lore.kernel.org/linux-wireless/2fee61f8c903d02a900ca3188c3742c7effd102e.camel@web.de/#bSigned-off-by: default avatarSean Wang <sean.wang@mediatek.com>
Tested-by: default avatarBert Karwatzki <spasswolf@web.de>
Link: https://patch.msgid.link/20240718234633.12737-1-sean.wang@kernel.orgSigned-off-by: default avatarJohannes Berg <johannes.berg@intel.com>
      6557a28f
    • Baochen Qiang's avatar
      wifi: ath12k: fix reusing outside iterator in ath12k_wow_vif_set_wakeups() · 189d7aae
      Baochen Qiang authored 
      Smatch throws below warning:

	drivers/net/wireless/ath/ath12k/wow.c:434 ath12k_wow_vif_set_wakeups()
	warn: reusing outside iterator: 'i'

	drivers/net/wireless/ath/ath12k/wow.c
	    411         default:
	    412                 break;
	    413         }
	    414
	    415         for (i = 0; i < wowlan->n_patterns; i++) {
	                            ^^^^^^^^^^^^^^^^^^^^^^
	Here we loop until ->n_patterns

	    416                 const struct cfg80211_pkt_pattern *eth_pattern = &patterns[i];
	    417                 struct ath12k_pkt_pattern new_pattern = {};
	    418
	    419                 if (WARN_ON(eth_pattern->pattern_len > WOW_MAX_PATTERN_SIZE))
	    420                         return -EINVAL;
	    421
	    422                 if (ar->ab->wow.wmi_conf_rx_decap_mode ==
	    423                     ATH12K_HW_TXRX_NATIVE_WIFI) {
	    424                         ath12k_wow_convert_8023_to_80211(ar, eth_pattern,
	    425                                                          &new_pattern);
	    426
	    427                         if (WARN_ON(new_pattern.pattern_len > WOW_MAX_PATTERN_SIZE))
	    428                                 return -EINVAL;
	    429                 } else {
	    430                         memcpy(new_pattern.pattern, eth_pattern->pattern,
	    431                                eth_pattern->pattern_len);
	    432
	    433                         /* convert bitmask to bytemask */
	--> 434                         for (i = 0; i < eth_pattern->pattern_len; i++)
	    435                                 if (eth_pattern->mask[i / 8] & BIT(i % 8))
	    436                                         new_pattern.bytemask[i] = 0xff;

	This loop re-uses i and the loop ends with i == eth_pattern->pattern_len.
	This looks like a bug.

Change to use a new iterator 'j' for the inner loop to fix it.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4

Fixes: 4a3c212e ("wifi: ath12k: add basic WoW functionalities")
Reported-by: default avatarDan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/all/d4975b95-9c43-45af-a0ab-80253f18c7f2@stanley.mountain/Signed-off-by: default avatarBaochen Qiang <quic_bqiang@quicinc.com>
Acked-by: default avatarJeff Johnson <quic_jjohnson@quicinc.com>
Link: https://patch.msgid.link/20240722033332.6273-1-quic_bqiang@quicinc.comSigned-off-by: default avatarJohannes Berg <johannes.berg@intel.com>
      189d7aae
    • Johannes Berg's avatar
      wifi: cfg80211: correct S1G beacon length calculation · 6873cc44
      Johannes Berg authored 
      The minimum header length calculation (equivalent to the start
of the elements) for the S1G long beacon erroneously required
only up to the start of u.s1g_beacon rather than the start of
u.s1g_beacon.variable. Fix that, and also shuffle the branches
around a bit to not assign useless values that are overwritten
later.

Reported-by: syzbot+0f3afa93b91202f21939@syzkaller.appspotmail.com
Fixes: 9eaffe50 ("cfg80211: convert S1G beacon to scan results")
Link: https://patch.msgid.link/20240724132912.9662972db7c1.I8779675b5bbda4994cc66f876b6b87a2361c3c0b@changeidSigned-off-by: default avatarJohannes Berg <johannes.berg@intel.com>
      6873cc44
    • Veerendranath Jakkam's avatar
      wifi: cfg80211: fix reporting failed MLO links status with cfg80211_connect_done · baeaabf9
      Veerendranath Jakkam authored 
      Individual MLO links connection status is not copied to
EVENT_CONNECT_RESULT data while processing the connect response
information in cfg80211_connect_done(). Due to this failed links
are wrongly indicated with success status in EVENT_CONNECT_RESULT.

To fix this, copy the individual MLO links status to the
EVENT_CONNECT_RESULT data.

Fixes: 53ad07e9 ("wifi: cfg80211: support reporting failed links")
Signed-off-by: default avatarVeerendranath Jakkam <quic_vjakkam@quicinc.com>
Reviewed-by: default avatarCarlos Llamas <cmllamas@google.com>
Link: https://patch.msgid.link/20240724125327.3495874-1-quic_vjakkam@quicinc.com
[commit message editorial changes]
Signed-off-by: default avatarJohannes Berg <johannes.berg@intel.com>
      baeaabf9
    • Johannes Berg's avatar
      wifi: mac80211: use monitor sdata with driver only if desired · 8f4fa087
      Johannes Berg authored 
      In commit 0d9c2bee ("wifi: mac80211: fix monitor channel
with chanctx emulation") I changed mac80211 to always have an
internal monitor_sdata to have something to have the chanctx
bound to.

However, if the driver didn't also have the WANT_MONITOR flag
this would cause mac80211 to allocate it without telling the
driver (which was intentional) but also use it for later APIs
to the driver without it ever having known about it which was
_not_ intentional.

Check through the code and only use the monitor_sdata in the
relevant places (TX, MU-MIMO follow settings, TX power, and
interface iteration) when the WANT_MONITOR flag is set.

Cc: stable@vger.kernel.org
Fixes: 0d9c2bee ("wifi: mac80211: fix monitor channel with chanctx emulation")
Reported-by: default avatarZeroBeat <ZeroBeat@gmx.de>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219086Tested-by: default avatarLorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20240725184836.25d334157a8e.I02574086da2c5cf0e18264ce5807db6f14ffd9c0@changeidSigned-off-by: default avatarJohannes Berg <johannes.berg@intel.com>
      8f4fa087
    • Eric Dumazet's avatar
      sched: act_ct: take care of padding in struct zones_ht_key · 2191a54f
      Eric Dumazet authored 
      Blamed commit increased lookup key size from 2 bytes to 16 bytes,
because zones_ht_key got a struct net pointer.

Make sure rhashtable_lookup() is not using the padding bytes
which are not initialized.

 BUG: KMSAN: uninit-value in rht_ptr_rcu include/linux/rhashtable.h:376 [inline]
 BUG: KMSAN: uninit-value in __rhashtable_lookup include/linux/rhashtable.h:607 [inline]
 BUG: KMSAN: uninit-value in rhashtable_lookup include/linux/rhashtable.h:646 [inline]
 BUG: KMSAN: uninit-value in rhashtable_lookup_fast include/linux/rhashtable.h:672 [inline]
 BUG: KMSAN: uninit-value in tcf_ct_flow_table_get+0x611/0x2260 net/sched/act_ct.c:329
  rht_ptr_rcu include/linux/rhashtable.h:376 [inline]
  __rhashtable_lookup include/linux/rhashtable.h:607 [inline]
  rhashtable_lookup include/linux/rhashtable.h:646 [inline]
  rhashtable_lookup_fast include/linux/rhashtable.h:672 [inline]
  tcf_ct_flow_table_get+0x611/0x2260 net/sched/act_ct.c:329
  tcf_ct_init+0xa67/0x2890 net/sched/act_ct.c:1408
  tcf_action_init_1+0x6cc/0xb30 net/sched/act_api.c:1425
  tcf_action_init+0x458/0xf00 net/sched/act_api.c:1488
  tcf_action_add net/sched/act_api.c:2061 [inline]
  tc_ctl_action+0x4be/0x19d0 net/sched/act_api.c:2118
  rtnetlink_rcv_msg+0x12fc/0x1410 net/core/rtnetlink.c:6647
  netlink_rcv_skb+0x375/0x650 net/netlink/af_netlink.c:2550
  rtnetlink_rcv+0x34/0x40 net/core/rtnetlink.c:6665
  netlink_unicast_kernel net/netlink/af_netlink.c:1331 [inline]
  netlink_unicast+0xf52/0x1260 net/netlink/af_netlink.c:1357
  netlink_sendmsg+0x10da/0x11e0 net/netlink/af_netlink.c:1901
  sock_sendmsg_nosec net/socket.c:730 [inline]
  __sock_sendmsg+0x30f/0x380 net/socket.c:745
  ____sys_sendmsg+0x877/0xb60 net/socket.c:2597
  ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2651
  __sys_sendmsg net/socket.c:2680 [inline]
  __do_sys_sendmsg net/socket.c:2689 [inline]
  __se_sys_sendmsg net/socket.c:2687 [inline]
  __x64_sys_sendmsg+0x307/0x4a0 net/socket.c:2687
  x64_sys_call+0x2dd6/0x3c10 arch/x86/include/generated/asm/syscalls_64.h:47
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0xcd/0x1e0 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Local variable key created at:
  tcf_ct_flow_table_get+0x4a/0x2260 net/sched/act_ct.c:324
  tcf_ct_init+0xa67/0x2890 net/sched/act_ct.c:1408

Fixes: 88c67aeb ("sched: act_ct: add netns into the key of tcf_ct_flow_table")
Reported-by: syzbot+1b5e4e187cc586d05ea0@syzkaller.appspotmail.com
Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
Cc: Xin Long <lucien.xin@gmail.com>
Reviewed-by: default avatarSimon Horman <horms@kernel.org>
Reviewed-by: default avatarXin Long <lucien.xin@gmail.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      2191a54f
    • Ma Ke's avatar
      net: usb: sr9700: fix uninitialized variable use in sr_mdio_read · 08f3a5c3
      Ma Ke authored 
      It could lead to error happen because the variable res is not updated if
the call to sr_share_read_word returns an error. In this particular case
error code was returned and res stayed uninitialized. Same issue also
applies to sr_read_reg.

This can be avoided by checking the return value of sr_share_read_word
and sr_read_reg, and propagating the error if the read operation failed.

Found by code review.

Cc: stable@vger.kernel.org
Fixes: c9b37458 ("USB2NET : SR9700 : One chip USB 1.1 USB2NET SR9700Device Driver Support")
Signed-off-by: default avatarMa Ke <make24@iscas.ac.cn>
Reviewed-by: default avatarShigeru Yoshida <syoshida@redhat.com>
Reviewed-by: default avatarHariprasad Kelam <hkelam@marvell.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      08f3a5c3
  7. 25 Jul, 2024 11 commits
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7