February 2025 - Linux-stable-mirror

[PATCH 3/4] batman-adv: Drop unmanaged ELP metric worker

by Simon Wunderlich

From: Sven Eckelmann <sven(a)narfation.org> The ELP worker needs to calculate new metric values for all neighbors "reachable" over an interface. Some of the used metric sources require locks which might need to sleep. This sleep is incompatible with the RCU list iterator used for the recorded neighbors. The initial approach to work around of this problem was to queue another work item per neighbor and then run this in a new context. Even when this solved the RCU vs might_sleep() conflict, it has a major problems: Nothing was stopping the work item in case it is not needed anymore - for example because one of the related interfaces was removed or the batman-adv module was unloaded - resulting in potential invalid memory accesses. Directly canceling the metric worker also has various problems: * cancel_work_sync for a to-be-deactivated interface is called with rtnl_lock held. But the code in the ELP metric worker also tries to use rtnl_lock() - which will never return in this case. This also means that cancel_work_sync would never return because it is waiting for the worker to finish. * iterating over the neighbor list for the to-be-deactivated interface is currently done using the RCU specific methods. Which means that it is possible to miss items when iterating over it without the associated spinlock - a behaviour which is acceptable for a periodic metric check but not for a cleanup routine (which must "stop" all still running workers) The better approch is to get rid of the per interface neighbor metric worker and handle everything in the interface worker. The original problems are solved by: * creating a list of neighbors which require new metric information inside the RCU protected context, gathering the metric according to the new list outside the RCU protected context * only use rcu_trylock inside metric gathering code to avoid a deadlock when the cancel_delayed_work_sync is called in the interface removal code (which is called with the rtnl_lock held) Cc: stable(a)vger.kernel.org Fixes: c833484e5f38 ("batman-adv: ELP - compute the metric based on the estimated throughput") Signed-off-by: Sven Eckelmann <sven(a)narfation.org> Signed-off-by: Simon Wunderlich <sw(a)simonwunderlich.de> --- net/batman-adv/bat_v.c | 2 -- net/batman-adv/bat_v_elp.c | 71 ++++++++++++++++++++++++++------------ net/batman-adv/bat_v_elp.h | 2 -- net/batman-adv/types.h | 3 -- 4 files changed, 48 insertions(+), 30 deletions(-) diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index ac11f1f08db0..d35479c465e2 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -113,8 +113,6 @@ static void batadv_v_hardif_neigh_init(struct batadv_hardif_neigh_node *hardif_neigh) { ewma_throughput_init(&hardif_neigh->bat_v.throughput); - INIT_WORK(&hardif_neigh->bat_v.metric_work, - batadv_v_elp_throughput_metric_update); } /** diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index 65e52de52bcd..b065578b4436 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -18,6 +18,7 @@ #include <linux/if_ether.h> #include <linux/jiffies.h> #include <linux/kref.h> +#include <linux/list.h> #include <linux/minmax.h> #include <linux/netdevice.h> #include <linux/nl80211.h> @@ -26,6 +27,7 @@ #include <linux/rcupdate.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> +#include <linux/slab.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/types.h> @@ -41,6 +43,18 @@ #include "routing.h" #include "send.h" +/** + * struct batadv_v_metric_queue_entry - list of hardif neighbors which require + * and metric update + */ +struct batadv_v_metric_queue_entry { + /** @hardif_neigh: hardif neighbor scheduled for metric update */ + struct batadv_hardif_neigh_node *hardif_neigh; + + /** @list: list node for metric_queue */ + struct list_head list; +}; + /** * batadv_v_elp_start_timer() - restart timer for ELP periodic work * @hard_iface: the interface for which the timer has to be reset @@ -137,10 +151,17 @@ static bool batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh, goto default_throughput; } + /* only use rtnl_trylock because the elp worker will be cancelled while + * the rntl_lock is held. the cancel_delayed_work_sync() would otherwise + * wait forever when the elp work_item was started and it is then also + * trying to rtnl_lock + */ + if (!rtnl_trylock()) + return false; + /* if not a wifi interface, check if this device provides data via * ethtool (e.g. an Ethernet adapter) */ - rtnl_lock(); ret = __ethtool_get_link_ksettings(hard_iface->net_dev, &link_settings); rtnl_unlock(); if (ret == 0) { @@ -175,31 +196,19 @@ static bool batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh, /** * batadv_v_elp_throughput_metric_update() - worker updating the throughput * metric of a single hop neighbour - * @work: the work queue item + * @neigh: the neighbour to probe */ -void batadv_v_elp_throughput_metric_update(struct work_struct *work) +static void +batadv_v_elp_throughput_metric_update(struct batadv_hardif_neigh_node *neigh) { - struct batadv_hardif_neigh_node_bat_v *neigh_bat_v; - struct batadv_hardif_neigh_node *neigh; u32 throughput; bool valid; - neigh_bat_v = container_of(work, struct batadv_hardif_neigh_node_bat_v, - metric_work); - neigh = container_of(neigh_bat_v, struct batadv_hardif_neigh_node, - bat_v); - valid = batadv_v_elp_get_throughput(neigh, &throughput); if (!valid) - goto put_neigh; + return; ewma_throughput_add(&neigh->bat_v.throughput, throughput); - -put_neigh: - /* decrement refcounter to balance increment performed before scheduling - * this task - */ - batadv_hardif_neigh_put(neigh); } /** @@ -273,14 +282,16 @@ batadv_v_elp_wifi_neigh_probe(struct batadv_hardif_neigh_node *neigh) */ static void batadv_v_elp_periodic_work(struct work_struct *work) { + struct batadv_v_metric_queue_entry *metric_entry; + struct batadv_v_metric_queue_entry *metric_safe; struct batadv_hardif_neigh_node *hardif_neigh; struct batadv_hard_iface *hard_iface; struct batadv_hard_iface_bat_v *bat_v; struct batadv_elp_packet *elp_packet; + struct list_head metric_queue; struct batadv_priv *bat_priv; struct sk_buff *skb; u32 elp_interval; - bool ret; bat_v = container_of(work, struct batadv_hard_iface_bat_v, elp_wq.work); hard_iface = container_of(bat_v, struct batadv_hard_iface, bat_v); @@ -316,6 +327,8 @@ static void batadv_v_elp_periodic_work(struct work_struct *work) atomic_inc(&hard_iface->bat_v.elp_seqno); + INIT_LIST_HEAD(&metric_queue); + /* The throughput metric is updated on each sent packet. This way, if a * node is dead and no longer sends packets, batman-adv is still able to * react timely to its death. @@ -340,16 +353,28 @@ static void batadv_v_elp_periodic_work(struct work_struct *work) /* Reading the estimated throughput from cfg80211 is a task that * may sleep and that is not allowed in an rcu protected - * context. Therefore schedule a task for that. + * context. Therefore add it to metric_queue and process it + * outside rcu protected context. */ - ret = queue_work(batadv_event_workqueue, - &hardif_neigh->bat_v.metric_work); - - if (!ret) + metric_entry = kzalloc(sizeof(*metric_entry), GFP_ATOMIC); + if (!metric_entry) { batadv_hardif_neigh_put(hardif_neigh); + continue; + } + + metric_entry->hardif_neigh = hardif_neigh; + list_add(&metric_entry->list, &metric_queue); } rcu_read_unlock(); + list_for_each_entry_safe(metric_entry, metric_safe, &metric_queue, list) { + batadv_v_elp_throughput_metric_update(metric_entry->hardif_neigh); + + batadv_hardif_neigh_put(metric_entry->hardif_neigh); + list_del(&metric_entry->list); + kfree(metric_entry); + } + restart_timer: batadv_v_elp_start_timer(hard_iface); out: diff --git a/net/batman-adv/bat_v_elp.h b/net/batman-adv/bat_v_elp.h index 9e2740195fa2..c9cb0a307100 100644 --- a/net/batman-adv/bat_v_elp.h +++ b/net/batman-adv/bat_v_elp.h @@ -10,7 +10,6 @@ #include "main.h" #include <linux/skbuff.h> -#include <linux/workqueue.h> int batadv_v_elp_iface_enable(struct batadv_hard_iface *hard_iface); void batadv_v_elp_iface_disable(struct batadv_hard_iface *hard_iface); @@ -19,6 +18,5 @@ void batadv_v_elp_iface_activate(struct batadv_hard_iface *primary_iface, void batadv_v_elp_primary_iface_set(struct batadv_hard_iface *primary_iface); int batadv_v_elp_packet_recv(struct sk_buff *skb, struct batadv_hard_iface *if_incoming); -void batadv_v_elp_throughput_metric_update(struct work_struct *work); #endif /* _NET_BATMAN_ADV_BAT_V_ELP_H_ */ diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 04f6398b3a40..85a50096f5b2 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -596,9 +596,6 @@ struct batadv_hardif_neigh_node_bat_v { * neighbor */ unsigned long last_unicast_tx; - - /** @metric_work: work queue callback item for metric update */ - struct work_struct metric_work; }; /** -- 2.39.5

5 months

1
0
0 0

[PATCH 2/4] batman-adv: Ignore neighbor throughput metrics in error case

by Simon Wunderlich

From: Sven Eckelmann <sven(a)narfation.org> If a temporary error happened in the evaluation of the neighbor throughput information, then the invalid throughput result should not be stored in the throughtput EWMA. Cc: stable(a)vger.kernel.org Signed-off-by: Sven Eckelmann <sven(a)narfation.org> Signed-off-by: Simon Wunderlich <sw(a)simonwunderlich.de> --- net/batman-adv/bat_v_elp.c | 50 ++++++++++++++++++++++++++------------ 1 file changed, 34 insertions(+), 16 deletions(-) diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index fbf499bcc671..65e52de52bcd 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -59,11 +59,13 @@ static void batadv_v_elp_start_timer(struct batadv_hard_iface *hard_iface) /** * batadv_v_elp_get_throughput() - get the throughput towards a neighbour * @neigh: the neighbour for which the throughput has to be obtained + * @pthroughput: calculated throughput towards the given neighbour in multiples + * of 100kpbs (a value of '1' equals 0.1Mbps, '10' equals 1Mbps, etc). * - * Return: The throughput towards the given neighbour in multiples of 100kpbs - * (a value of '1' equals 0.1Mbps, '10' equals 1Mbps, etc). + * Return: true when value behind @pthroughput was set */ -static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) +static bool batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh, + u32 *pthroughput) { struct batadv_hard_iface *hard_iface = neigh->if_incoming; struct net_device *soft_iface = hard_iface->soft_iface; @@ -77,14 +79,16 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) * batman-adv interface */ if (!soft_iface) - return BATADV_THROUGHPUT_DEFAULT_VALUE; + return false; /* if the user specified a customised value for this interface, then * return it directly */ throughput = atomic_read(&hard_iface->bat_v.throughput_override); - if (throughput != 0) - return throughput; + if (throughput != 0) { + *pthroughput = throughput; + return true; + } /* if this is a wireless device, then ask its throughput through * cfg80211 API @@ -111,19 +115,24 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) * possible to delete this neighbor. For now set * the throughput metric to 0. */ - return 0; + *pthroughput = 0; + return true; } if (ret) goto default_throughput; - if (sinfo.filled & BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT)) - return sinfo.expected_throughput / 100; + if (sinfo.filled & BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT)) { + *pthroughput = sinfo.expected_throughput / 100; + return true; + } /* try to estimate the expected throughput based on reported tx * rates */ - if (sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE)) - return cfg80211_calculate_bitrate(&sinfo.txrate) / 3; + if (sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE)) { + *pthroughput = cfg80211_calculate_bitrate(&sinfo.txrate) / 3; + return true; + } goto default_throughput; } @@ -142,8 +151,10 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) hard_iface->bat_v.flags &= ~BATADV_FULL_DUPLEX; throughput = link_settings.base.speed; - if (throughput && throughput != SPEED_UNKNOWN) - return throughput * 10; + if (throughput && throughput != SPEED_UNKNOWN) { + *pthroughput = throughput * 10; + return true; + } } default_throughput: @@ -157,7 +168,8 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) } /* if none of the above cases apply, return the base_throughput */ - return BATADV_THROUGHPUT_DEFAULT_VALUE; + *pthroughput = BATADV_THROUGHPUT_DEFAULT_VALUE; + return true; } /** @@ -169,15 +181,21 @@ void batadv_v_elp_throughput_metric_update(struct work_struct *work) { struct batadv_hardif_neigh_node_bat_v *neigh_bat_v; struct batadv_hardif_neigh_node *neigh; + u32 throughput; + bool valid; neigh_bat_v = container_of(work, struct batadv_hardif_neigh_node_bat_v, metric_work); neigh = container_of(neigh_bat_v, struct batadv_hardif_neigh_node, bat_v); - ewma_throughput_add(&neigh->bat_v.throughput, - batadv_v_elp_get_throughput(neigh)); + valid = batadv_v_elp_get_throughput(neigh, &throughput); + if (!valid) + goto put_neigh; + + ewma_throughput_add(&neigh->bat_v.throughput, throughput); +put_neigh: /* decrement refcounter to balance increment performed before scheduling * this task */ -- 2.39.5

5 months

1
0
0 0

[PATCH net-next 0/4] ptp: vmclock: bugfixes and cleanups for error handling

by Thomas Weißschuh

Some error handling issues I noticed while looking at the code. Only compile-tested. Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> --- Thomas Weißschuh (4): ptp: vmclock: Set driver data before its usage ptp: vmclock: Don't unregister misc device if it was not registered ptp: vmclock: Clean up miscdev and ptp clock through devres ptp: vmclock: Remove goto-based cleanup logic drivers/ptp/ptp_vmclock.c | 46 ++++++++++++++++++++-------------------------- 1 file changed, 20 insertions(+), 26 deletions(-) --- base-commit: 2014c95afecee3e76ca4a56956a936e23283f05b change-id: 20250206-vmclock-probe-57cbcb770925 Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

5 months

4
9
0 0

[PATCH] fs/xattr: actually support O_PATH fds in *xattrat() syscalls

by Mike Yuan

Cited from commit message of original patch [1]: > One use case will be setfiles(8) setting SELinux file contexts > ("security.selinux") without race conditions and without a file > descriptor opened with read access requiring SELinux read permission. Also, generally all *at() syscalls operate on O_PATH fds, unlike f*() ones. Yet the O_PATH fds are rejected by *xattrat() syscalls in the final version merged into tree. Instead, let's switch things to CLASS(fd_raw). Note that there's one side effect: f*xattr() starts to work with O_PATH fds too. It's not clear to me whether this is desirable (e.g. fstat() accepts O_PATH fds as an outlier). [1] https://lore.kernel.org/all/20240426162042.191916-1-cgoettsche@seltendoof.d… Fixes: 6140be90ec70 ("fs/xattr: add *at family syscalls") Signed-off-by: Mike Yuan <me(a)yhndnzj.com> Cc: Al Viro <viro(a)zeniv.linux.org.uk> Cc: Christian Göttsche <cgzones(a)googlemail.com> Cc: Christian Brauner <brauner(a)kernel.org> Cc: <stable(a)vger.kernel.org> --- fs/xattr.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/xattr.c b/fs/xattr.c index 02bee149ad96..15df71e56187 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -704,7 +704,7 @@ static int path_setxattrat(int dfd, const char __user *pathname, filename = getname_maybe_null(pathname, at_flags); if (!filename) { - CLASS(fd, f)(dfd); + CLASS(fd_raw, f)(dfd); if (fd_empty(f)) error = -EBADF; else @@ -848,7 +848,7 @@ static ssize_t path_getxattrat(int dfd, const char __user *pathname, filename = getname_maybe_null(pathname, at_flags); if (!filename) { - CLASS(fd, f)(dfd); + CLASS(fd_raw, f)(dfd); if (fd_empty(f)) return -EBADF; return file_getxattr(fd_file(f), &ctx); @@ -978,7 +978,7 @@ static ssize_t path_listxattrat(int dfd, const char __user *pathname, filename = getname_maybe_null(pathname, at_flags); if (!filename) { - CLASS(fd, f)(dfd); + CLASS(fd_raw, f)(dfd); if (fd_empty(f)) return -EBADF; return file_listxattr(fd_file(f), list, size); @@ -1079,7 +1079,7 @@ static int path_removexattrat(int dfd, const char __user *pathname, filename = getname_maybe_null(pathname, at_flags); if (!filename) { - CLASS(fd, f)(dfd); + CLASS(fd_raw, f)(dfd); if (fd_empty(f)) return -EBADF; return file_removexattr(fd_file(f), &kname); base-commit: a86bf2283d2c9769205407e2b54777c03d012939 -- 2.48.1

5 months

2
9
0 0

[tip: timers/urgent] timers/migration: Fix off-by-one root mis-connection

by tip-bot2 for Frederic Weisbecker

The following commit has been merged into the timers/urgent branch of tip: Commit-ID: 868c9037df626b3c245ee26a290a03ae1f9f58d3 Gitweb: https://git.kernel.org/tip/868c9037df626b3c245ee26a290a03ae1f9f58d3 Author: Frederic Weisbecker <frederic(a)kernel.org> AuthorDate: Wed, 05 Feb 2025 17:02:20 +01:00 Committer: Thomas Gleixner <tglx(a)linutronix.de> CommitterDate: Fri, 07 Feb 2025 09:02:16 +01:00 timers/migration: Fix off-by-one root mis-connection Before attaching a new root to the old root, the children counter of the new root is checked to verify that only the upcoming CPU's top group have been connected to it. However since the recently added commit b729cc1ec21a ("timers/migration: Fix another race between hotplug and idle entry/exit") this check is not valid anymore because the old root is pre-accounted as a child to the new root. Therefore after connecting the upcoming CPU's top group to the new root, the children count to be expected must be 2 and not 1 anymore. This omission results in the old root to not be connected to the new root. Then eventually the system may run with more than one top level, which defeats the purpose of a single idle migrator. Also the old root is pre-accounted but not connected upon the new root creation. But it can be connected to the new root later on. Therefore the old root may be accounted twice to the new root. The propagation of such overcommit can end up creating a double final top-level root with a groupmask incorrectly initialized. Although harmless given that the final top level roots will never have a parent to walk up to, this oddity opportunistically reported the core issue: WARNING: CPU: 8 PID: 0 at kernel/time/timer_migration.c:543 tmigr_requires_handle_remote CPU: 8 UID: 0 PID: 0 Comm: swapper/8 RIP: 0010:tmigr_requires_handle_remote Call Trace: <IRQ> ? tmigr_requires_handle_remote ? hrtimer_run_queues update_process_times tick_periodic tick_handle_periodic __sysvec_apic_timer_interrupt sysvec_apic_timer_interrupt </IRQ> Fix the problem by taking the old root into account in the children count of the new root so the connection is not omitted. Also warn when more than one top level group exists to better detect similar issues in the future. Fixes: b729cc1ec21a ("timers/migration: Fix another race between hotplug and idle entry/exit") Reported-by: Matt Fleming <mfleming(a)cloudflare.com> Signed-off-by: Frederic Weisbecker <frederic(a)kernel.org> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/all/20250205160220.39467-1-frederic@kernel.org --- kernel/time/timer_migration.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index 9cb9b65..2f63308 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -1675,6 +1675,9 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node) } while (i < tmigr_hierarchy_levels); + /* Assert single root */ + WARN_ON_ONCE(!err && !group->parent && !list_is_singular(&tmigr_level_list[top])); + while (i > 0) { group = stack[--i]; @@ -1716,7 +1719,12 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node) WARN_ON_ONCE(top == 0); lvllist = &tmigr_level_list[top]; - if (group->num_children == 1 && list_is_singular(lvllist)) { + + /* + * Newly created root level should have accounted the upcoming + * CPU's child group and pre-accounted the old root. + */ + if (group->num_children == 2 && list_is_singular(lvllist)) { /* * The target CPU must never do the prepare work, except * on early boot when the boot CPU is the target. Otherwise

5 months

1
0
0 0

[PATCH v1 2/2] arm64: dts: qcom: ipq9574: Fix USB vdd info

by Varadarajan Narayanan

USB phys in ipq9574 use the 'L5' regulator. The commit ec4f047679d5 ("arm64: dts: qcom: ipq9574: Enable USB") incorrectly specified it as 'L2'. Because of this when the phy module turns off/on its regulators, 'L2' is turned off/on resulting in 2 issues, namely 'L5' is not turned off/on and the network module powered by the 'L2' is turned off/on. Cc: stable(a)vger.kernel.org Fixes: ec4f047679d5 ("arm64: dts: qcom: ipq9574: Enable USB") Signed-off-by: Varadarajan Narayanan <quic_varada(a)quicinc.com> --- arch/arm64/boot/dts/qcom/ipq9574-rdp-common.dtsi | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/ipq9574-rdp-common.dtsi b/arch/arm64/boot/dts/qcom/ipq9574-rdp-common.dtsi index ae12f069f26f..b24b795873d4 100644 --- a/arch/arm64/boot/dts/qcom/ipq9574-rdp-common.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq9574-rdp-common.dtsi @@ -111,6 +111,13 @@ mp5496_l2: l2 { regulator-always-on; regulator-boot-on; }; + + mp5496_l5: l5 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + regulator-boot-on; + }; }; }; @@ -146,7 +153,7 @@ &usb_0_dwc3 { }; &usb_0_qmpphy { - vdda-pll-supply = <&mp5496_l2>; + vdda-pll-supply = <&mp5496_l5>; vdda-phy-supply = <&regulator_fixed_0p925>; status = "okay"; @@ -154,7 +161,7 @@ &usb_0_qmpphy { &usb_0_qusbphy { vdd-supply = <&regulator_fixed_0p925>; - vdda-pll-supply = <&mp5496_l2>; + vdda-pll-supply = <&mp5496_l5>; vdda-phy-dpdm-supply = <&regulator_fixed_3p3>; status = "okay"; -- 2.34.1

5 months

2
2
0 0

[PATCH net] rtnetlink: fix netns leak with rtnl_setlink()

by Nicolas Dichtel

A call to rtnl_nets_destroy() is needed to release references taken on netns put in rtnl_nets. CC: stable(a)vger.kernel.org Fixes: 636af13f213b ("rtnetlink: Register rtnl_dellink() and rtnl_setlink() with RTNL_FLAG_DOIT_PERNET_WIP.") Signed-off-by: Nicolas Dichtel <nicolas.dichtel(a)6wind.com> --- net/core/rtnetlink.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1f4d4b5570ab..d1e559fce918 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3432,6 +3432,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, err = -ENODEV; rtnl_nets_unlock(&rtnl_nets); + rtnl_nets_destroy(&rtnl_nets); errout: return err; } -- 2.47.1

5 months

3
2
0 0

[PATCH] x86: rust: set rustc-abi=x86-softfloat on rustc>=1.86.0

by Alice Ryhl

When using Rust on the x86 architecture, we are currently using the unstable target.json feature to specify the compilation target. Rustc is going to change how softfloat is specified in the target.json file on x86, thus update generate_rust_target.rs to specify softfloat using the new option. Note that if you enable this parameter with a compiler that does not recognize it, then that triggers a warning but it does not break the build. Cc: stable(a)vger.kernel.org # for 6.12.y Link: https://github.com/rust-lang/rust/pull/136146 Signed-off-by: Alice Ryhl <aliceryhl(a)google.com> --- scripts/generate_rust_target.rs | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs index 0d00ac3723b5..4fd6b6ab3e32 100644 --- a/scripts/generate_rust_target.rs +++ b/scripts/generate_rust_target.rs @@ -165,6 +165,18 @@ fn has(&self, option: &str) -> bool { let option = "CONFIG_".to_owned() + option; self.0.contains_key(&option) } + + /// Is the rustc version at least `major.minor.patch`? + fn rustc_version_atleast(&self, major: u32, minor: u32, patch: u32) -> bool { + let check_version = 100000 * major + 100 * minor + patch; + let actual_version = self + .0 + .get("CONFIG_RUSTC_VERSION") + .unwrap() + .parse::<u32>() + .unwrap(); + check_version <= actual_version + } } fn main() { @@ -182,6 +194,9 @@ fn main() { } } else if cfg.has("X86_64") { ts.push("arch", "x86_64"); + if cfg.rustc_version_atleast(1, 86, 0) { + ts.push("rustc-abi", "x86-softfloat"); + } ts.push( "data-layout", "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128", @@ -215,6 +230,9 @@ fn main() { panic!("32-bit x86 only works under UML"); } ts.push("arch", "x86"); + if cfg.rustc_version_atleast(1, 86, 0) { + ts.push("rustc-abi", "x86-softfloat"); + } ts.push( "data-layout", "e-m:e-p:32:32-p270:32:32-p271:32:32-p272:64:64-i128:128-f64:32:64-f80:32-n8:16:32-S128", --- base-commit: 40384c840ea1944d7c5a392e8975ed088ecf0b37 change-id: 20250203-rustc-1-86-x86-softfloat-0b973054c4bc Best regards, -- Alice Ryhl <aliceryhl(a)google.com>

5 months

3
6
0 0

[PATCH] arm64: tegra: delete the Orin NX/Nano suspend key

by Ivy Huang

From: Ninad Malwade <nmalwade(a)nvidia.com> As per the Orin Nano Dev Kit schematic, GPIO_G.02 is not available on this device family. It should not be used at all on Orin NX/Nano. Having this unused pin mapped as the suspend key can lead to unpredictable behavior for low power modes. Orin NX/Nano uses GPIO_EE.04 as both a "power" button and a "suspend" button. However, we cannot have two gpio-keys mapped to the same GPIO. Therefore delete the "suspend" key. Cc: stable(a)vger.kernel.org Fixes: e63472eda5ea ("arm64: tegra: Support Jetson Orin NX reference platform") Signed-off-by: Ninad Malwade <nmalwade(a)nvidia.com> Signed-off-by: Ivy Huang <yijuh(a)nvidia.com> --- arch/arm64/boot/dts/nvidia/tegra234-p3768-0000+p3767.dtsi | 7 ------- 1 file changed, 7 deletions(-) diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3768-0000+p3767.dtsi b/arch/arm64/boot/dts/nvidia/tegra234-p3768-0000+p3767.dtsi index 19340d13f789..41821354bbda 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234-p3768-0000+p3767.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra234-p3768-0000+p3767.dtsi @@ -227,13 +227,6 @@ wakeup-event-action = <EV_ACT_ASSERTED>; wakeup-source; }; - - key-suspend { - label = "Suspend"; - gpios = <&gpio TEGRA234_MAIN_GPIO(G, 2) GPIO_ACTIVE_LOW>; - linux,input-type = <EV_KEY>; - linux,code = <KEY_SLEEP>; - }; }; fan: pwm-fan { -- 2.17.1

5 months

1
0
0 0

[PATCH v3 1/2] seccomp: passthrough uretprobe systemcall without filtering

by Eyal Birger

When attaching uretprobes to processes running inside docker, the attached process is segfaulted when encountering the retprobe. The reason is that now that uretprobe is a system call the default seccomp filters in docker block it as they only allow a specific set of known syscalls. This is true for other userspace applications which use seccomp to control their syscall surface. Since uretprobe is a "kernel implementation detail" system call which is not used by userspace application code directly, it is impractical and there's very little point in forcing all userspace applications to explicitly allow it in order to avoid crashing tracked processes. Pass this systemcall through seccomp without depending on configuration. Note: uretprobe isn't supported in i386 and __NR_ia32_rt_tgsigqueueinfo uses the same number as __NR_uretprobe so the syscall isn't forced in the compat bitmap. Fixes: ff474a78cef5 ("uprobe: Add uretprobe syscall to speed up return probe") Reported-by: Rafael Buchbinder <rafi(a)rbk.io> Link: https://lore.kernel.org/lkml/CAHsH6Gs3Eh8DFU0wq58c_LF8A4_+o6z456J7BidmcVY2A… Link: https://lore.kernel.org/lkml/20250121182939.33d05470@gandalf.local.home/T/#… Link: https://lore.kernel.org/lkml/20250128145806.1849977-1-eyal.birger@gmail.com/ Cc: stable(a)vger.kernel.org Signed-off-by: Eyal Birger <eyal.birger(a)gmail.com> --- v3: no change - deferring 32bit compat handling as there aren't plans to support this syscall in compat mode. v2: use action_cache bitmap and mode1 array to check the syscall --- kernel/seccomp.c | 24 +++++++++++++++++++++--- 1 file changed, 21 insertions(+), 3 deletions(-) diff --git a/kernel/seccomp.c b/kernel/seccomp.c index f59381c4a2ff..09b6f8e6db51 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -734,13 +734,13 @@ seccomp_prepare_user_filter(const char __user *user_filter) #ifdef SECCOMP_ARCH_NATIVE /** - * seccomp_is_const_allow - check if filter is constant allow with given data + * seccomp_is_filter_const_allow - check if filter is constant allow with given data * @fprog: The BPF programs * @sd: The seccomp data to check against, only syscall number and arch * number are considered constant. */ -static bool seccomp_is_const_allow(struct sock_fprog_kern *fprog, - struct seccomp_data *sd) +static bool seccomp_is_filter_const_allow(struct sock_fprog_kern *fprog, + struct seccomp_data *sd) { unsigned int reg_value = 0; unsigned int pc; @@ -812,6 +812,21 @@ static bool seccomp_is_const_allow(struct sock_fprog_kern *fprog, return false; } +static bool seccomp_is_const_allow(struct sock_fprog_kern *fprog, + struct seccomp_data *sd) +{ +#ifdef __NR_uretprobe + if (sd->nr == __NR_uretprobe +#ifdef SECCOMP_ARCH_COMPAT + && sd->arch != SECCOMP_ARCH_COMPAT +#endif + ) + return true; +#endif + + return seccomp_is_filter_const_allow(fprog, sd); +} + static void seccomp_cache_prepare_bitmap(struct seccomp_filter *sfilter, void *bitmap, const void *bitmap_prev, size_t bitmap_size, int arch) @@ -1023,6 +1038,9 @@ static inline void seccomp_log(unsigned long syscall, long signr, u32 action, */ static const int mode1_syscalls[] = { __NR_seccomp_read, __NR_seccomp_write, __NR_seccomp_exit, __NR_seccomp_sigreturn, +#ifdef __NR_uretprobe + __NR_uretprobe, +#endif -1, /* negative terminated */ }; -- 2.43.0

5 months

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror February 2025