From e0266319413d5d687ba7b6df7ca99e4b9724a4f2 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Tue, 12 Nov 2024 20:18:33 +0100 Subject: [PATCH 01/16] mptcp: update local address flags when setting it Just like in-kernel pm, when userspace pm does set_flags, it needs to send out MP_PRIO signal, and also modify the flags of the corresponding address entry in the local address list. This patch implements the missing logic. Traverse all address entries on userspace_pm_local_addr_list to find the local address entry, if bkup is true, set the flags of this entry with FLAG_BACKUP, otherwise, clear FLAG_BACKUP. Fixes: 892f396c8e68 ("mptcp: netlink: issue MP_PRIO signals from userspace PMs") Cc: stable@vger.kernel.org Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20241112-net-mptcp-misc-6-12-pm-v1-1-b835580cefa8@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_userspace.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 56dfea9862b7..3f888bfe1462 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -560,6 +560,7 @@ int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info) struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; struct net *net = sock_net(skb->sk); + struct mptcp_pm_addr_entry *entry; struct mptcp_sock *msk; int ret = -EINVAL; struct sock *sk; @@ -601,6 +602,17 @@ int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info) if (loc.flags & MPTCP_PM_ADDR_FLAG_BACKUP) bkup = 1; + spin_lock_bh(&msk->pm.lock); + list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { + if (mptcp_addresses_equal(&entry->addr, &loc.addr, false)) { + if (bkup) + entry->flags |= MPTCP_PM_ADDR_FLAG_BACKUP; + else + entry->flags &= ~MPTCP_PM_ADDR_FLAG_BACKUP; + } + } + spin_unlock_bh(&msk->pm.lock); + lock_sock(sk); ret = mptcp_pm_nl_mp_prio_send_ack(msk, &loc.addr, &rem.addr, bkup); release_sock(sk); -- 2.51.0 From f642c5c4d528d11bd78b6c6f84f541cd3c0bea86 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Tue, 12 Nov 2024 20:18:34 +0100 Subject: [PATCH 02/16] mptcp: hold pm lock when deleting entry When traversing userspace_pm_local_addr_list and deleting an entry from it in mptcp_pm_nl_remove_doit(), msk->pm.lock should be held. This patch holds this lock before mptcp_userspace_pm_lookup_addr_by_id() and releases it after list_move() in mptcp_pm_nl_remove_doit(). Fixes: d9a4594edabf ("mptcp: netlink: Add MPTCP_PM_CMD_REMOVE") Cc: stable@vger.kernel.org Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20241112-net-mptcp-misc-6-12-pm-v1-2-b835580cefa8@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_userspace.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 3f888bfe1462..e35178f5205f 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -308,14 +308,17 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info) lock_sock(sk); + spin_lock_bh(&msk->pm.lock); match = mptcp_userspace_pm_lookup_addr_by_id(msk, id_val); if (!match) { GENL_SET_ERR_MSG(info, "address with specified id not found"); + spin_unlock_bh(&msk->pm.lock); release_sock(sk); goto out; } list_move(&match->list, &free_list); + spin_unlock_bh(&msk->pm.lock); mptcp_pm_remove_addrs(msk, &free_list); -- 2.51.0 From db3eab8110bc0520416101b6a5b52f44a43fb4cf Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Tue, 12 Nov 2024 20:18:35 +0100 Subject: [PATCH 03/16] mptcp: pm: use _rcu variant under rcu_read_lock In mptcp_pm_create_subflow_or_signal_addr(), rcu_read_(un)lock() are used as expected to iterate over the list of local addresses, but list_for_each_entry() was used instead of list_for_each_entry_rcu() in __lookup_addr(). It is important to use this variant which adds the required READ_ONCE() (and diagnostic checks if enabled). Because __lookup_addr() is also used in mptcp_pm_nl_set_flags() where it is called under the pernet->lock and not rcu_read_lock(), an extra condition is then passed to help the diagnostic checks making sure either the associated spin lock or the RCU lock is held. Fixes: 86e39e04482b ("mptcp: keep track of local endpoint still available for each msk") Cc: stable@vger.kernel.org Reviewed-by: Geliang Tang Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20241112-net-mptcp-misc-6-12-pm-v1-3-b835580cefa8@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index db586a5b3866..45a2b5f05d38 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -524,7 +524,8 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info) { struct mptcp_pm_addr_entry *entry; - list_for_each_entry(entry, &pernet->local_addr_list, list) { + list_for_each_entry_rcu(entry, &pernet->local_addr_list, list, + lockdep_is_held(&pernet->lock)) { if (mptcp_addresses_equal(&entry->addr, info, entry->addr.port)) return entry; } -- 2.51.0 From 671154f174e0e7f242507cd074497661deb41bfd Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Tue, 12 Nov 2024 16:20:00 +0000 Subject: [PATCH 04/16] net: phylink: ensure PHY momentary link-fails are handled Normally, phylib won't notify changes in quick succession. However, as a result of commit 3e43b903da04 ("net: phy: Immediately call adjust_link if only tx_lpi_enabled changes") this is no longer true - it is now possible that phy_link_down() and phy_link_up() will both complete before phylink's resolver has run, which means it'll miss that pl->phy_state.link momentarily became false. Rename "mac_link_dropped" to be more generic "link_failed" since it will cover more than the MAC/PCS end of the link failing, and arrange to set this in phylink_phy_change() if we notice that the PHY reports that the link is down. This will ensure that we capture an EEE reconfiguration event. Fixes: 3e43b903da04 ("net: phy: Immediately call adjust_link if only tx_lpi_enabled changes") Signed-off-by: Russell King (Oracle) Reviewed-by: Oleksij Rempel Link: https://patch.msgid.link/E1tAtcW-002RBS-LB@rmk-PC.armlinux.org.uk Signed-off-by: Jakub Kicinski --- drivers/net/phy/phylink.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 4309317de3d1..3e9957b6aa14 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -78,7 +78,7 @@ struct phylink { unsigned int pcs_neg_mode; unsigned int pcs_state; - bool mac_link_dropped; + bool link_failed; bool using_mac_select_pcs; struct sfp_bus *sfp_bus; @@ -1475,9 +1475,9 @@ static void phylink_resolve(struct work_struct *w) cur_link_state = pl->old_link_state; if (pl->phylink_disable_state) { - pl->mac_link_dropped = false; + pl->link_failed = false; link_state.link = false; - } else if (pl->mac_link_dropped) { + } else if (pl->link_failed) { link_state.link = false; retrigger = true; } else { @@ -1572,7 +1572,7 @@ static void phylink_resolve(struct work_struct *w) phylink_link_up(pl, link_state); } if (!link_state.link && retrigger) { - pl->mac_link_dropped = false; + pl->link_failed = false; queue_work(system_power_efficient_wq, &pl->resolve); } mutex_unlock(&pl->state_mutex); @@ -1835,6 +1835,8 @@ static void phylink_phy_change(struct phy_device *phydev, bool up) pl->phy_state.pause |= MLO_PAUSE_RX; pl->phy_state.interface = phydev->interface; pl->phy_state.link = up; + if (!up) + pl->link_failed = true; mutex_unlock(&pl->state_mutex); phylink_run_resolve(pl); @@ -2158,7 +2160,7 @@ EXPORT_SYMBOL_GPL(phylink_disconnect_phy); static void phylink_link_changed(struct phylink *pl, bool up, const char *what) { if (!up) - pl->mac_link_dropped = true; + pl->link_failed = true; phylink_run_resolve(pl); phylink_dbg(pl, "%s link %s\n", what, up ? "up" : "down"); } @@ -2792,7 +2794,7 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl, * link will cycle. */ if (manual_changed) { - pl->mac_link_dropped = true; + pl->link_failed = true; phylink_run_resolve(pl); } -- 2.51.0 From 3342dc8b4623d835e7dd76a15cec2e5a94fe2f93 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Tue, 12 Nov 2024 11:03:47 +0800 Subject: [PATCH 05/16] samples: pktgen: correct dev to DEV In the pktgen_sample01_simple.sh script, the device variable is uppercase 'DEV' instead of lowercase 'dev'. Because of this typo, the script cannot enable UDP tx checksum. Fixes: 460a9aa23de6 ("samples: pktgen: add UDP tx checksum support") Signed-off-by: Wei Fang Reviewed-by: Simon Horman Acked-by: Jesper Dangaard Brouer Link: https://patch.msgid.link/20241112030347.1849335-1-wei.fang@nxp.com Signed-off-by: Jakub Kicinski --- samples/pktgen/pktgen_sample01_simple.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/samples/pktgen/pktgen_sample01_simple.sh b/samples/pktgen/pktgen_sample01_simple.sh index cdb9f497f87d..66cb707479e6 100755 --- a/samples/pktgen/pktgen_sample01_simple.sh +++ b/samples/pktgen/pktgen_sample01_simple.sh @@ -76,7 +76,7 @@ if [ -n "$DST_PORT" ]; then pg_set $DEV "udp_dst_max $UDP_DST_MAX" fi -[ ! -z "$UDP_CSUM" ] && pg_set $dev "flag UDPCSUM" +[ ! -z "$UDP_CSUM" ] && pg_set $DEV "flag UDPCSUM" # Setup random UDP port src range pg_set $DEV "flag UDPSRC_RND" -- 2.51.0 From e28acc9c1ccfcb24c08e020828f69d0a915b06ae Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Fri, 8 Nov 2024 06:08:36 -0800 Subject: [PATCH 06/16] ipmr: Fix access to mfc_cache_list without lock held Accessing `mr_table->mfc_cache_list` is protected by an RCU lock. In the following code flow, the RCU read lock is not held, causing the following error when `RCU_PROVE` is not held. The same problem might show up in the IPv6 code path. 6.12.0-rc5-kbuilder-01145-gbac17284bdcb #33 Tainted: G E N ----------------------------- net/ipv4/ipmr_base.c:313 RCU-list traversed in non-reader section!! rcu_scheduler_active = 2, debug_locks = 1 2 locks held by RetransmitAggre/3519: #0: ffff88816188c6c0 (nlk_cb_mutex-ROUTE){+.+.}-{3:3}, at: __netlink_dump_start+0x8a/0x290 #1: ffffffff83fcf7a8 (rtnl_mutex){+.+.}-{3:3}, at: rtnl_dumpit+0x6b/0x90 stack backtrace: lockdep_rcu_suspicious mr_table_dump ipmr_rtm_dumproute rtnl_dump_all rtnl_dumpit netlink_dump __netlink_dump_start rtnetlink_rcv_msg netlink_rcv_skb netlink_unicast netlink_sendmsg This is not a problem per see, since the RTNL lock is held here, so, it is safe to iterate in the list without the RCU read lock, as suggested by Eric. To alleviate the concern, modify the code to use list_for_each_entry_rcu() with the RTNL-held argument. The annotation will raise an error only if RTNL or RCU read lock are missing during iteration, signaling a legitimate problem, otherwise it will avoid this false positive. This will solve the IPv6 case as well, since ip6mr_rtm_dumproute() calls this function as well. Signed-off-by: Breno Leitao Reviewed-by: David Ahern Link: https://patch.msgid.link/20241108-ipmr_rcu-v2-1-c718998e209b@debian.org Signed-off-by: Jakub Kicinski --- net/ipv4/ipmr_base.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index 271dc03fc6db..f0af12a2f70b 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -310,7 +310,8 @@ int mr_table_dump(struct mr_table *mrt, struct sk_buff *skb, if (filter->filter_set) flags |= NLM_F_DUMP_FILTERED; - list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) { + list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list, + lockdep_rtnl_is_held()) { if (e < s_e) goto next_entry; if (filter->dev && -- 2.51.0 From a03b18a71c128846360cc81ac6fdb0e7d41597b4 Mon Sep 17 00:00:00 2001 From: =?utf8?q?N=C3=ADcolas=20F=2E=20R=2E=20A=2E=20Prado?= Date: Sat, 9 Nov 2024 10:16:32 -0500 Subject: [PATCH 07/16] net: stmmac: dwmac-mediatek: Fix inverted handling of mediatek,mac-wol MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit The mediatek,mac-wol property is being handled backwards to what is described in the binding: it currently enables PHY WOL when the property is present and vice versa. Invert the driver logic so it matches the binding description. Fixes: fd1d62d80ebc ("net: stmmac: replace the use_phy_wol field with a flag") Signed-off-by: Nícolas F. R. A. Prado Link: https://patch.msgid.link/20241109-mediatek-mac-wol-noninverted-v2-1-0e264e213878@collabora.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c index 2a9132d6d743..001857c294fb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c @@ -589,9 +589,9 @@ static int mediatek_dwmac_common_data(struct platform_device *pdev, plat->mac_interface = priv_plat->phy_mode; if (priv_plat->mac_wol) - plat->flags |= STMMAC_FLAG_USE_PHY_WOL; - else plat->flags &= ~STMMAC_FLAG_USE_PHY_WOL; + else + plat->flags |= STMMAC_FLAG_USE_PHY_WOL; plat->riwt_off = 1; plat->maxmtu = ETH_DATA_LEN; plat->host_dma_width = priv_plat->variant->dma_bit_mask; -- 2.51.0 From eb94b7bb10109a14a5431a67e5d8e31cfa06b395 Mon Sep 17 00:00:00 2001 From: Michal Luczaj Date: Mon, 11 Nov 2024 00:17:34 +0100 Subject: [PATCH 08/16] net: Make copy_safe_from_sockptr() match documentation copy_safe_from_sockptr() return copy_from_sockptr() return copy_from_sockptr_offset() return copy_from_user() copy_from_user() does not return an error on fault. Instead, it returns a number of bytes that were not copied. Have it handled. Patch has a side effect: it un-breaks garbage input handling of nfc_llcp_setsockopt() and mISDN's data_sock_setsockopt(). Fixes: 6309863b31dd ("net: add copy_safe_from_sockptr() helper") Signed-off-by: Michal Luczaj Link: https://patch.msgid.link/20241111-sockptr-copy-ret-fix-v1-1-a520083a93fb@rbox.co Signed-off-by: Jakub Kicinski --- include/linux/sockptr.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index fc5a206c4043..195debe2b1db 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -77,7 +77,9 @@ static inline int copy_safe_from_sockptr(void *dst, size_t ksize, { if (optlen < ksize) return -EINVAL; - return copy_from_sockptr(dst, optval, ksize); + if (copy_from_sockptr(dst, optval, ksize)) + return -EFAULT; + return 0; } static inline int copy_struct_from_sockptr(void *dst, size_t ksize, -- 2.51.0 From 5b366eae71937ae7412365340b431064625f9617 Mon Sep 17 00:00:00 2001 From: Vitalii Mordan Date: Fri, 8 Nov 2024 20:33:34 +0300 Subject: [PATCH 09/16] stmmac: dwmac-intel-plat: fix call balance of tx_clk handling routines If the clock dwmac->tx_clk was not enabled in intel_eth_plat_probe, it should not be disabled in any path. Conversely, if it was enabled in intel_eth_plat_probe, it must be disabled in all error paths to ensure proper cleanup. Found by Linux Verification Center (linuxtesting.org) with Klever. Fixes: 9efc9b2b04c7 ("net: stmmac: Add dwmac-intel-plat for GBE driver") Signed-off-by: Vitalii Mordan Link: https://patch.msgid.link/20241108173334.2973603-1-mordan@ispras.ru Signed-off-by: Jakub Kicinski --- .../stmicro/stmmac/dwmac-intel-plat.c | 25 +++++++++++++------ 1 file changed, 17 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c index d68f0c4e7835..9739bc9867c5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c @@ -108,7 +108,12 @@ static int intel_eth_plat_probe(struct platform_device *pdev) if (IS_ERR(dwmac->tx_clk)) return PTR_ERR(dwmac->tx_clk); - clk_prepare_enable(dwmac->tx_clk); + ret = clk_prepare_enable(dwmac->tx_clk); + if (ret) { + dev_err(&pdev->dev, + "Failed to enable tx_clk\n"); + return ret; + } /* Check and configure TX clock rate */ rate = clk_get_rate(dwmac->tx_clk); @@ -119,7 +124,7 @@ static int intel_eth_plat_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "Failed to set tx_clk\n"); - return ret; + goto err_tx_clk_disable; } } } @@ -133,7 +138,7 @@ static int intel_eth_plat_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "Failed to set clk_ptp_ref\n"); - return ret; + goto err_tx_clk_disable; } } } @@ -149,12 +154,15 @@ static int intel_eth_plat_probe(struct platform_device *pdev) } ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); - if (ret) { - clk_disable_unprepare(dwmac->tx_clk); - return ret; - } + if (ret) + goto err_tx_clk_disable; return 0; + +err_tx_clk_disable: + if (dwmac->data->tx_clk_en) + clk_disable_unprepare(dwmac->tx_clk); + return ret; } static void intel_eth_plat_remove(struct platform_device *pdev) @@ -162,7 +170,8 @@ static void intel_eth_plat_remove(struct platform_device *pdev) struct intel_dwmac *dwmac = get_stmmac_bsp_priv(&pdev->dev); stmmac_pltfr_remove(pdev); - clk_disable_unprepare(dwmac->tx_clk); + if (dwmac->data->tx_clk_en) + clk_disable_unprepare(dwmac->tx_clk); } static struct platform_driver intel_eth_plat_driver = { -- 2.51.0 From dc065076ee7768377d7c16af7d1b0767782d8c98 Mon Sep 17 00:00:00 2001 From: Meghana Malladi Date: Mon, 11 Nov 2024 15:28:42 +0530 Subject: [PATCH 10/16] net: ti: icssg-prueth: Fix 1 PPS sync The first PPS latch time needs to be calculated by the driver (in rounded off seconds) and configured as the start time offset for the cycle. After synchronizing two PTP clocks running as master/slave, missing this would cause master and slave to start immediately with some milliseconds drift which causes the PPS signal to never synchronize with the PTP master. Fixes: 186734c15886 ("net: ti: icssg-prueth: add packet timestamping and ptp support") Signed-off-by: Meghana Malladi Reviewed-by: Vadim Fedorenko Reviewed-by: MD Danish Anwar Link: https://patch.msgid.link/20241111095842.478833-1-m-malladi@ti.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/ti/icssg/icssg_prueth.c | 13 +++++++++++-- drivers/net/ethernet/ti/icssg/icssg_prueth.h | 12 ++++++++++++ 2 files changed, 23 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 5c20ceb164df..fe2fd1bfc904 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -411,6 +412,8 @@ static int prueth_perout_enable(void *clockops_data, struct prueth_emac *emac = clockops_data; u32 reduction_factor = 0, offset = 0; struct timespec64 ts; + u64 current_cycle; + u64 start_offset; u64 ns_period; if (!on) @@ -449,8 +452,14 @@ static int prueth_perout_enable(void *clockops_data, writel(reduction_factor, emac->prueth->shram.va + TIMESYNC_FW_WC_SYNCOUT_REDUCTION_FACTOR_OFFSET); - writel(0, emac->prueth->shram.va + - TIMESYNC_FW_WC_SYNCOUT_START_TIME_CYCLECOUNT_OFFSET); + current_cycle = icssg_read_time(emac->prueth->shram.va + + TIMESYNC_FW_WC_CYCLECOUNT_OFFSET); + + /* Rounding of current_cycle count to next second */ + start_offset = roundup(current_cycle, MSEC_PER_SEC); + + hi_lo_writeq(start_offset, emac->prueth->shram.va + + TIMESYNC_FW_WC_SYNCOUT_START_TIME_CYCLECOUNT_OFFSET); return 0; } diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h index 8722bb4a268a..f5c1d473e9f9 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h @@ -330,6 +330,18 @@ static inline int prueth_emac_slice(struct prueth_emac *emac) extern const struct ethtool_ops icssg_ethtool_ops; extern const struct dev_pm_ops prueth_dev_pm_ops; +static inline u64 icssg_read_time(const void __iomem *addr) +{ + u32 low, high; + + do { + high = readl(addr + 4); + low = readl(addr); + } while (high != readl(addr + 4)); + + return low + ((u64)high << 32); +} + /* Classifier helpers */ void icssg_class_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac); void icssg_class_set_host_mac_addr(struct regmap *miig_rt, const u8 *mac); -- 2.51.0 From 8eb36164d1a6769a20ed43033510067ff3dab9ee Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Mon, 11 Nov 2024 10:16:49 +0000 Subject: [PATCH 11/16] bonding: add ns target multicast address to slave device MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Commit 4598380f9c54 ("bonding: fix ns validation on backup slaves") tried to resolve the issue where backup slaves couldn't be brought up when receiving IPv6 Neighbor Solicitation (NS) messages. However, this fix only worked for drivers that receive all multicast messages, such as the veth interface. For standard drivers, the NS multicast message is silently dropped because the slave device is not a member of the NS target multicast group. To address this, we need to make the slave device join the NS target multicast group, ensuring it can receive these IPv6 NS messages to validate the slave’s status properly. There are three policies before joining the multicast group: 1. All settings must be under active-backup mode (alb and tlb do not support arp_validate), with backup slaves and slaves supporting multicast. 2. We can add or remove multicast groups when arp_validate changes. 3. Other operations, such as enslaving, releasing, or setting NS targets, need to be guarded by arp_validate. Fixes: 4e24be018eb9 ("bonding: add new parameter ns_targets") Signed-off-by: Hangbin Liu Reviewed-by: Nikolay Aleksandrov Signed-off-by: Paolo Abeni --- drivers/net/bonding/bond_main.c | 16 +++++- drivers/net/bonding/bond_options.c | 82 +++++++++++++++++++++++++++++- include/net/bond_options.h | 2 + 3 files changed, 98 insertions(+), 2 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index b1bffd8e9a95..15e0f14d0d49 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1008,6 +1008,8 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active, if (bond->dev->flags & IFF_UP) bond_hw_addr_flush(bond->dev, old_active->dev); + + bond_slave_ns_maddrs_add(bond, old_active); } if (new_active) { @@ -1024,6 +1026,8 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active, dev_mc_sync(new_active->dev, bond->dev); netif_addr_unlock_bh(bond->dev); } + + bond_slave_ns_maddrs_del(bond, new_active); } } @@ -2341,6 +2345,11 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, bond_compute_features(bond); bond_set_carrier(bond); + /* Needs to be called before bond_select_active_slave(), which will + * remove the maddrs if the slave is selected as active slave. + */ + bond_slave_ns_maddrs_add(bond, new_slave); + if (bond_uses_primary(bond)) { block_netpoll_tx(); bond_select_active_slave(bond); @@ -2350,7 +2359,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, if (bond_mode_can_use_xmit_hash(bond)) bond_update_slave_arr(bond, NULL); - if (!slave_dev->netdev_ops->ndo_bpf || !slave_dev->netdev_ops->ndo_xdp_xmit) { if (bond->xdp_prog) { @@ -2548,6 +2556,12 @@ static int __bond_release_one(struct net_device *bond_dev, if (oldcurrent == slave) bond_change_active_slave(bond, NULL); + /* Must be called after bond_change_active_slave () as the slave + * might change from an active slave to a backup slave. Then it is + * necessary to clear the maddrs on the backup slave. + */ + bond_slave_ns_maddrs_del(bond, slave); + if (bond_is_lb(bond)) { /* Must be called only after the slave has been * detached from the list and the curr_active_slave diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 95d59a18c022..327b6ecdc77e 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -15,6 +15,7 @@ #include #include +#include static int bond_option_active_slave_set(struct bonding *bond, const struct bond_opt_value *newval); @@ -1234,6 +1235,68 @@ static int bond_option_arp_ip_targets_set(struct bonding *bond, } #if IS_ENABLED(CONFIG_IPV6) +static bool slave_can_set_ns_maddr(const struct bonding *bond, struct slave *slave) +{ + return BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP && + !bond_is_active_slave(slave) && + slave->dev->flags & IFF_MULTICAST; +} + +static void slave_set_ns_maddrs(struct bonding *bond, struct slave *slave, bool add) +{ + struct in6_addr *targets = bond->params.ns_targets; + char slot_maddr[MAX_ADDR_LEN]; + int i; + + if (!slave_can_set_ns_maddr(bond, slave)) + return; + + for (i = 0; i < BOND_MAX_NS_TARGETS; i++) { + if (ipv6_addr_any(&targets[i])) + break; + + if (!ndisc_mc_map(&targets[i], slot_maddr, slave->dev, 0)) { + if (add) + dev_mc_add(slave->dev, slot_maddr); + else + dev_mc_del(slave->dev, slot_maddr); + } + } +} + +void bond_slave_ns_maddrs_add(struct bonding *bond, struct slave *slave) +{ + if (!bond->params.arp_validate) + return; + slave_set_ns_maddrs(bond, slave, true); +} + +void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave) +{ + if (!bond->params.arp_validate) + return; + slave_set_ns_maddrs(bond, slave, false); +} + +static void slave_set_ns_maddr(struct bonding *bond, struct slave *slave, + struct in6_addr *target, struct in6_addr *slot) +{ + char target_maddr[MAX_ADDR_LEN], slot_maddr[MAX_ADDR_LEN]; + + if (!bond->params.arp_validate || !slave_can_set_ns_maddr(bond, slave)) + return; + + /* remove the previous maddr from slave */ + if (!ipv6_addr_any(slot) && + !ndisc_mc_map(slot, slot_maddr, slave->dev, 0)) + dev_mc_del(slave->dev, slot_maddr); + + /* add new maddr on slave if target is set */ + if (!ipv6_addr_any(target) && + !ndisc_mc_map(target, target_maddr, slave->dev, 0)) + dev_mc_add(slave->dev, target_maddr); +} + static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot, struct in6_addr *target, unsigned long last_rx) @@ -1243,8 +1306,10 @@ static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot, struct slave *slave; if (slot >= 0 && slot < BOND_MAX_NS_TARGETS) { - bond_for_each_slave(bond, slave, iter) + bond_for_each_slave(bond, slave, iter) { slave->target_last_arp_rx[slot] = last_rx; + slave_set_ns_maddr(bond, slave, target, &targets[slot]); + } targets[slot] = *target; } } @@ -1296,15 +1361,30 @@ static int bond_option_ns_ip6_targets_set(struct bonding *bond, { return -EPERM; } + +static void slave_set_ns_maddrs(struct bonding *bond, struct slave *slave, bool add) {} + +void bond_slave_ns_maddrs_add(struct bonding *bond, struct slave *slave) {} + +void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave) {} #endif static int bond_option_arp_validate_set(struct bonding *bond, const struct bond_opt_value *newval) { + bool changed = !!bond->params.arp_validate != !!newval->value; + struct list_head *iter; + struct slave *slave; + netdev_dbg(bond->dev, "Setting arp_validate to %s (%llu)\n", newval->string, newval->value); bond->params.arp_validate = newval->value; + if (changed) { + bond_for_each_slave(bond, slave, iter) + slave_set_ns_maddrs(bond, slave, !!bond->params.arp_validate); + } + return 0; } diff --git a/include/net/bond_options.h b/include/net/bond_options.h index 473a0147769e..18687ccf0638 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -161,5 +161,7 @@ void bond_option_arp_ip_targets_clear(struct bonding *bond); #if IS_ENABLED(CONFIG_IPV6) void bond_option_ns_ip6_targets_clear(struct bonding *bond); #endif +void bond_slave_ns_maddrs_add(struct bonding *bond, struct slave *slave); +void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave); #endif /* _NET_BOND_OPTIONS_H */ -- 2.51.0 From 86fb6173d11e773a00a5b6d1b7bd17caff8692b8 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Mon, 11 Nov 2024 10:16:50 +0000 Subject: [PATCH 12/16] selftests: bonding: add ns multicast group testing Add a test to make sure the backup slaves join correct multicast group when arp_validate enabled and ns_ip6_target is set. Here is the result: TEST: arp_validate (active-backup ns_ip6_target arp_validate 0) [ OK ] TEST: arp_validate (join mcast group) [ OK ] TEST: arp_validate (active-backup ns_ip6_target arp_validate 1) [ OK ] TEST: arp_validate (join mcast group) [ OK ] TEST: arp_validate (active-backup ns_ip6_target arp_validate 2) [ OK ] TEST: arp_validate (join mcast group) [ OK ] TEST: arp_validate (active-backup ns_ip6_target arp_validate 3) [ OK ] TEST: arp_validate (join mcast group) [ OK ] TEST: arp_validate (active-backup ns_ip6_target arp_validate 4) [ OK ] TEST: arp_validate (join mcast group) [ OK ] TEST: arp_validate (active-backup ns_ip6_target arp_validate 5) [ OK ] TEST: arp_validate (join mcast group) [ OK ] TEST: arp_validate (active-backup ns_ip6_target arp_validate 6) [ OK ] TEST: arp_validate (join mcast group) [ OK ] Signed-off-by: Hangbin Liu Reviewed-by: Nikolay Aleksandrov Signed-off-by: Paolo Abeni --- .../drivers/net/bonding/bond_options.sh | 54 ++++++++++++++++++- 1 file changed, 53 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh index 41d0859feb7d..edc56e2cc606 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh @@ -11,6 +11,8 @@ ALL_TESTS=" lib_dir=$(dirname "$0") source ${lib_dir}/bond_topo_3d1c.sh +c_maddr="33:33:00:00:00:10" +g_maddr="33:33:00:00:02:54" skip_prio() { @@ -240,6 +242,54 @@ arp_validate_test() done } +# Testing correct multicast groups are added to slaves for ns targets +arp_validate_mcast() +{ + RET=0 + local arp_valid=$(cmd_jq "ip -n ${s_ns} -j -d link show bond0" ".[].linkinfo.info_data.arp_validate") + local active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") + + for i in $(seq 0 2); do + maddr_list=$(ip -n ${s_ns} maddr show dev eth${i}) + + # arp_valid == 0 or active_slave should not join any maddrs + if { [ "$arp_valid" == "null" ] || [ "eth${i}" == ${active_slave} ]; } && \ + echo "$maddr_list" | grep -qE "${c_maddr}|${g_maddr}"; then + RET=1 + check_err 1 "arp_valid $arp_valid active_slave $active_slave, eth$i has mcast group" + # arp_valid != 0 and backup_slave should join both maddrs + elif [ "$arp_valid" != "null" ] && [ "eth${i}" != ${active_slave} ] && \ + ( ! echo "$maddr_list" | grep -q "${c_maddr}" || \ + ! echo "$maddr_list" | grep -q "${m_maddr}"); then + RET=1 + check_err 1 "arp_valid $arp_valid active_slave $active_slave, eth$i has mcast group" + fi + done + + # Do failover + ip -n ${s_ns} link set ${active_slave} down + # wait for active link change + slowwait 2 active_slave_changed $active_slave + active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") + + for i in $(seq 0 2); do + maddr_list=$(ip -n ${s_ns} maddr show dev eth${i}) + + # arp_valid == 0 or active_slave should not join any maddrs + if { [ "$arp_valid" == "null" ] || [ "eth${i}" == ${active_slave} ]; } && \ + echo "$maddr_list" | grep -qE "${c_maddr}|${g_maddr}"; then + RET=1 + check_err 1 "arp_valid $arp_valid active_slave $active_slave, eth$i has mcast group" + # arp_valid != 0 and backup_slave should join both maddrs + elif [ "$arp_valid" != "null" ] && [ "eth${i}" != ${active_slave} ] && \ + ( ! echo "$maddr_list" | grep -q "${c_maddr}" || \ + ! echo "$maddr_list" | grep -q "${m_maddr}"); then + RET=1 + check_err 1 "arp_valid $arp_valid active_slave $active_slave, eth$i has mcast group" + fi + done +} + arp_validate_arp() { local mode=$1 @@ -261,8 +311,10 @@ arp_validate_ns() fi for val in $(seq 0 6); do - arp_validate_test "mode $mode arp_interval 100 ns_ip6_target ${g_ip6} arp_validate $val" + arp_validate_test "mode $mode arp_interval 100 ns_ip6_target ${g_ip6},${c_ip6} arp_validate $val" log_test "arp_validate" "$mode ns_ip6_target arp_validate $val" + arp_validate_mcast + log_test "arp_validate" "join mcast group" done } -- 2.51.0 From ca34aceb322bfcd6ab498884f1805ee12f983259 Mon Sep 17 00:00:00 2001 From: Alexandre Ferrieux Date: Wed, 13 Nov 2024 11:04:28 +0100 Subject: [PATCH 13/16] net: sched: u32: Add test case for systematic hnode IDR leaks Add a tdc test case to exercise the just-fixed systematic leak of IDR entries in u32 hnode disposal. Given the IDR in question is confined to the range [1..0x7FF], it is sufficient to create/delete the same filter 2048 times to fill it up and get a nonzero exit status from "tc filter add". Signed-off-by: Alexandre Ferrieux Acked-by: Jamal Hadi Salim Reviewed-by: Victor Nogueira Link: https://patch.msgid.link/20241113100428.360460-1-alexandre.ferrieux@orange.com Signed-off-by: Paolo Abeni --- .../tc-testing/tc-tests/filters/u32.json | 24 +++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json index 24bd0c2a3014..b2ca9d4e991b 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json @@ -329,5 +329,29 @@ "teardown": [ "$TC qdisc del dev $DEV1 parent root drr" ] + }, + { + "id": "1234", + "name": "Exercise IDR leaks by creating/deleting a filter many (2048) times", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 parent root handle 10: drr", + "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 u32 match ip src 0.0.0.2/32 action drop", + "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 3 u32 match ip src 0.0.0.3/32 action drop" + ], + "cmdUnderTest": "bash -c 'for i in {1..2048} ;do echo filter delete dev $DEV1 pref 3;echo filter add dev $DEV1 parent 10:0 protocol ip prio 3 u32 match ip src 0.0.0.3/32 action drop;done | $TC -b -'", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV1", + "matchPattern": "protocol ip pref 3 u32", + "matchCount": "3", + "teardown": [ + "$TC qdisc del dev $DEV1 parent root drr" + ] } ] -- 2.51.0 From 378e8feea9a70d37a5dc1678b7ec27df21099fa5 Mon Sep 17 00:00:00 2001 From: Romain Gantois Date: Tue, 12 Nov 2024 15:06:08 +0100 Subject: [PATCH 14/16] net: phy: dp83869: fix status reporting for 1000base-x autonegotiation The DP83869 PHY transceiver supports converting from RGMII to 1000base-x. In this operation mode, autonegotiation can be performed, as described in IEEE802.3. The DP83869 has a set of fiber-specific registers located at offset 0xc00. When the transceiver is configured in RGMII-to-1000base-x mode, these registers are mapped onto offset 0, which should make reading the autonegotiation status transparent. However, the fiber registers at offset 0xc04 and 0xc05 follow the bit layout specified in Clause 37, and genphy_read_status() assumes a Clause 22 layout. Thus, genphy_read_status() doesn't properly read the capabilities advertised by the link partner, resulting in incorrect link parameters. Similarly, genphy_config_aneg() doesn't properly write advertised capabilities. Fix the 1000base-x autonegotiation procedure by replacing genphy_read_status() and genphy_config_aneg() with their Clause 37 equivalents. Fixes: a29de52ba2a1 ("net: dp83869: Add ability to advertise Fiber connection") Cc: stable@vger.kernel.org Signed-off-by: Romain Gantois Link: https://patch.msgid.link/20241112-dp83869-1000base-x-v3-1-36005f4ab0d9@bootlin.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/dp83869.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) diff --git a/drivers/net/phy/dp83869.c b/drivers/net/phy/dp83869.c index 5f056d7db83e..b6b38caf9c0e 100644 --- a/drivers/net/phy/dp83869.c +++ b/drivers/net/phy/dp83869.c @@ -153,19 +153,32 @@ struct dp83869_private { int mode; }; +static int dp83869_config_aneg(struct phy_device *phydev) +{ + struct dp83869_private *dp83869 = phydev->priv; + + if (dp83869->mode != DP83869_RGMII_1000_BASE) + return genphy_config_aneg(phydev); + + return genphy_c37_config_aneg(phydev); +} + static int dp83869_read_status(struct phy_device *phydev) { struct dp83869_private *dp83869 = phydev->priv; + bool changed; int ret; + if (dp83869->mode == DP83869_RGMII_1000_BASE) + return genphy_c37_read_status(phydev, &changed); + ret = genphy_read_status(phydev); if (ret) return ret; - if (linkmode_test_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, phydev->supported)) { + if (dp83869->mode == DP83869_RGMII_100_BASE) { if (phydev->link) { - if (dp83869->mode == DP83869_RGMII_100_BASE) - phydev->speed = SPEED_100; + phydev->speed = SPEED_100; } else { phydev->speed = SPEED_UNKNOWN; phydev->duplex = DUPLEX_UNKNOWN; @@ -898,6 +911,7 @@ static int dp83869_phy_reset(struct phy_device *phydev) .soft_reset = dp83869_phy_reset, \ .config_intr = dp83869_config_intr, \ .handle_interrupt = dp83869_handle_interrupt, \ + .config_aneg = dp83869_config_aneg, \ .read_status = dp83869_read_status, \ .get_tunable = dp83869_get_tunable, \ .set_tunable = dp83869_set_tunable, \ -- 2.51.0 From ea301aec8bb718b02b68761d2229fc12c9fefa29 Mon Sep 17 00:00:00 2001 From: =?utf8?q?Peter=20Gro=C3=9Fe?= Date: Wed, 13 Nov 2024 13:07:04 -0800 Subject: [PATCH 15/16] i40e: Fix handling changed priv flags MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit After assembling the new private flags on a PF, the operation to determine the changed flags uses the wrong bitmaps. Instead of xor-ing orig_flags with new_flags, it uses the still unchanged pf->flags, thus changed_flags is always 0. Fix it by using the correct bitmaps. The issue was discovered while debugging why disabling source pruning stopped working with release 6.7. Although the new flags will be copied to pf->flags later on in that function, disabling source pruning requires a reset of the PF, which was skipped due to this bug. Disabling source pruning: $ sudo ethtool --set-priv-flags eno1 disable-source-pruning on $ sudo ethtool --show-priv-flags eno1 Private flags for eno1: MFP : off total-port-shutdown : off LinkPolling : off flow-director-atr : on veb-stats : off hw-atr-eviction : off link-down-on-close : off legacy-rx : off disable-source-pruning: on disable-fw-lldp : off rs-fec : off base-r-fec : off vf-vlan-pruning : off Regarding reproducing: I observed the issue with a rather complicated lab setup, where * two VLAN interfaces are created on eno1 * each with a different MAC address assigned * each moved into a separate namespace * both VLANs are bridged externally, so they form a single layer 2 network The external bridge is done via a channel emulator adding packet loss and delay and the application in the namespaces tries to send/receive traffic and measure the performance. Sender and receiver are separated by namespaces, yet the network card "sees its own traffic" send back to it. To make that work, source pruning has to be disabled. Cc: stable@vger.kernel.org Fixes: 70756d0a4727 ("i40e: Use DECLARE_BITMAP for flags and hw_features fields in i40e_pf") Signed-off-by: Peter Große Reviewed-by: Paul Menzel Reviewed-by: Przemek Kitszel Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20241113210705.1296408-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index f2506511bbff..bce5b76f1e7a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -5299,7 +5299,7 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) } flags_complete: - bitmap_xor(changed_flags, pf->flags, orig_flags, I40E_PF_FLAGS_NBITS); + bitmap_xor(changed_flags, new_flags, orig_flags, I40E_PF_FLAGS_NBITS); if (test_bit(I40E_FLAG_FW_LLDP_DIS, changed_flags)) reset_needed = I40E_PF_RESET_AND_REBUILD_FLAG; -- 2.51.0 From c53bf100f68619acf6cedcf4cf5249a1ca2db0b4 Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Thu, 14 Nov 2024 17:51:56 +0000 Subject: [PATCH 16/16] netdev-genl: Hold rcu_read_lock in napi_get Hold rcu_read_lock in netdev_nl_napi_get_doit, which calls napi_by_id and is required to be called under rcu_read_lock. Cc: stable@vger.kernel.org Fixes: 27f91aaf49b3 ("netdev-genl: Add netlink framework functions for napi") Signed-off-by: Joe Damato Link: https://patch.msgid.link/20241114175157.16604-1-jdamato@fastly.com Signed-off-by: Jakub Kicinski --- net/core/netdev-genl.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 1cb954f2d39e..d2baa1af9df0 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -215,6 +215,7 @@ int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info) return -ENOMEM; rtnl_lock(); + rcu_read_lock(); napi = napi_by_id(napi_id); if (napi) { @@ -224,6 +225,7 @@ int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info) err = -ENOENT; } + rcu_read_unlock(); rtnl_unlock(); if (err) -- 2.51.0