From e2c6d326216642011da318b9edfd5d57ebd5a56f Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Sat, 26 Sep 2026 15:44:26 +0200 Subject: namespace: don't inherit MNT_UMOUNT in clone_mnt() MNT_UMOUNT gets raised on a mount that umount_tree() or umount_one() has taken out of its namespace. It's never cleared. __detach_mounts() unhooks a mount that carries it instead of unmounting it. disconnect_mount() lets an unmounted child stay attached only if its parent carries it. propagate_umount() takes it as the sign that a mount is going to be unmounted when it decides what else can be unmounted, where a chain of locked mounts ends and where a for reparenting an overmount. clone_mnt() copies the flags of the source and only masks MNT_INTERNAL_FLAGS which doesn't include MNT_UMOUNT. A mount that was lazily unmounted but is kept alive by a file descriptor can still be copied when its root is an nsfs or pidfs file because may_copy_tree() accepts those before checking whether the source is mounted at all: mount --bind /proc/self/ns/net /tmp/x exec 3< /tmp/x umount -l /tmp/x mount --bind /proc/self/fd/3 /tmp/y The mount on /tmp/y is attached to the caller's namespace with MNT_UMOUNT already set and every copy of it inherits the flag again. That causes a number of bugs: - Unlink its mountpoint from a mount namespace where it isn't one. __detach_mounts() takes it for a mount that was unmounted earlier, unhooks it from its parent and drops the reference the namespace holds on it. It stays in the namespace with one reference too few and as its own parent, so it can't be unmounted through the file descriptor anymore and the namespace never finds it again. When the namespace goes away it's leaked and points to a freed struct mnt_namespace that may_change_propagation() and anon_ns_root() read on the next propagation change or mount_setattr() through the file descriptor. - Make it shared and unmount a peer. trace_transfers() follows the flag from the peer into it and strips it from its peer group. - Let a propagated umount reach it. gather_candidates() marks it with T_UMOUNT_CANDIDATE but never puts it on the candidate list, so the mark is never cleared and every later propagated umount skips it. If it's the parent of a locked mount handle_locked() takes it as the cutoff and commits the locked child that should have stayed and disconnect_mount() leaves that child attached to it, unmounted under a mounted parent, which is what disconnect_mount() exists to prevent. When the namespace goes away umount_tree() visits the child a second time. And once __detach_mounts() has made it its own parent reparent() never finds the end of the chain of unmounted parents. A clone is a new mount that has never been unmounted. Add MNT_UMOUNT to MNT_INTERNAL_FLAGS so clone_mnt() never copies it. And warn when umount_tree() reaches a mount that already has it set. Fixes: 590ce4bcbfb4 ("mnt: Add MNT_UMOUNT flag") Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260926-work-mount-fixes-2-v1-3-f357abf3d17b@kernel.org Signed-off-by: Christian Brauner (Amutable) --- include/linux/mount.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mount.h b/include/linux/mount.h index acfe7ef86a1b..b16ba5d45605 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -52,7 +52,7 @@ enum mount_flags { MNT_ATIME_MASK = MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME, MNT_INTERNAL_FLAGS = MNT_INTERNAL | MNT_DOOMED | - MNT_SYNC_UMOUNT | MNT_LOCKED + MNT_SYNC_UMOUNT | MNT_LOCKED | MNT_UMOUNT }; struct vfsmount { -- cgit v1.2.3 From 0b6f31a3c0b16066f812e94b52a704174a6f23cd Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 30 Sep 2026 15:32:08 +0200 Subject: unshare: don't drop active namespace references that were never taken Active references on the namespaces of an nsproxy are taken when the nsproxy is installed into a task in switch_task_namespaces() and copy_namespaces() and dropped again by put_nsproxy() through deactivate_nsproxy(). But ksys_unshare() calls put_nsproxy() on an nsproxy that was never installed when set_cred_ucounts() fails. The new namespaces of that nsproxy go from zero to minus one and the namespaces shared with the caller lose a reference that belongs to the nsproxy the caller keeps using: WARNING: kernel/nscommon.c:171 at __ns_ref_active_put+0x1cd/0x230 nsproxy_ns_active_put deactivate_nsproxy ksys_unshare Afterwards the namespaces the caller lives in aren't listed by listns() anymore. set_cred_ucounts() only fails when alloc_ucounts() can't allocate and it only allocates when the real uid of the caller differs from its effective uid. Commit cefd55bd2159 ("nsproxy: fix free_nsproxy() and simplify create_new_namespaces()") separated the two cases on purpose. nsproxy_free() frees an nsproxy that was prepared but never installed and that's what a failed setns() uses in put_nsset(). Export it and use it for a failed unshare() as well. Fixes: a98621a0f187 ("unshare: fix nsproxy leak in ksys_unshare() on set_cred_ucounts() failure") Cc: stable@vger.kernel.org # v7.1+ Link: https://patch.msgid.link/20260930-work-mount-fixes-3-v1-16-be34c83956ae@kernel.org Signed-off-by: Christian Brauner (Amutable) --- include/linux/nsproxy.h | 1 + kernel/fork.c | 3 ++- kernel/nsproxy.c | 2 +- 3 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 5a67648721c7..dc2447f5f092 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -100,6 +100,7 @@ void exit_cred_namespaces(struct task_struct *tsk); void switch_task_namespaces(struct task_struct *tsk, struct nsproxy *new); int exec_task_namespaces(void); void deactivate_nsproxy(struct nsproxy *ns); +void nsproxy_free(struct nsproxy *ns); int unshare_nsproxy_namespaces(unsigned long, struct nsproxy **, struct cred *, struct fs_struct *); int __init nsproxy_cache_init(void); diff --git a/kernel/fork.c b/kernel/fork.c index da48168c504f..d442cd68a37a 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -3338,8 +3338,9 @@ int ksys_unshare(unsigned long unshare_flags) perf_event_namespaces(current); bad_unshare_cleanup_nsproxy: + /* never installed, so no active references to drop */ if (new_nsproxy) - put_nsproxy(new_nsproxy); + nsproxy_free(new_nsproxy); bad_unshare_cleanup_cred: if (new_cred) put_cred(new_cred); diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index d9d3d5973bf5..3fb1595a4a59 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -61,7 +61,7 @@ static inline struct nsproxy *create_nsproxy(void) return nsproxy; } -static inline void nsproxy_free(struct nsproxy *ns) +void nsproxy_free(struct nsproxy *ns) { put_mnt_ns(ns->mnt_ns); put_uts_ns(ns->uts_ns); -- cgit v1.2.3 From 7093c3b8314a4ef7405c4066a2521398c455efe7 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Thu, 1 Oct 2026 13:57:24 +0200 Subject: can: fix unique skb identifier regression under RPS Commit d4fb6514ff8e ("can: use skb hash instead of private variable in headroom") moved the per-skb unique identifier used for raw_rcv() duplicate detection into skb->hash. With RPS enabled, get_rps_cpu() calls skb_get_hash() before the frame reaches the CAN subsystem. Since CAN skbs have no L3/L4 headers, the flow dissector assigns every CAN frame the same non-zero software hash. can_set_skb_uid() only generated a new identifier when skb->hash was 0, so it kept this constant hash. When the SLAB allocator later reused the same skb address, raw_rcv() mistook the next legitimate frame for a duplicate and dropped it. Fix this by storing the CAN UID in the CAN skb extension (struct can_skb_ext::can_skb_uid) instead of skb->hash, decoupling it from any hash the network stack may compute. can_set_skb_uid() keeps its "assign only if unset" behaviour, which preserves UIDs set before transmission (e.g. by isotp to identify echo frames) across the local loopback path. Frames whose extension is shared with another clone (e.g. via tc mirred or netem duplicate) are given a private extension copy before the UID is assigned, so that independently received skb clones from real CAN interfaces (can_skb_uid = 0) don't end up with the same UID. The limitation that tc mirred/netem skb duplicates might be dropped in raw_rcv for looped back isotp echo frame skbs is accepted. There is no valid use-case for tc mirred or netem together with isotp which is not capable to operate on different CAN interfaces simultaneously. For routing and modifying CAN frames together with isotp use can-gw. can-gw and vxcan additionally clear the UID of forwarded/duplicated frames so each newly routed frame gets its own unique identifier. Fixes: d4fb6514ff8e ("can: use skb hash instead of private variable in headroom") Reported-by: Joerg Willmann Closes: https://lore.kernel.org/linux-can/2859AD3D-C805-41A0-9036-C5E8EE152419@clnt.de/ Cc: stable@vger.kernel.org Tested-by: Oliver Hartkopp Tested-by: Joerg Willmann Signed-off-by: Oliver Hartkopp Link: https://patch.msgid.link/20261001115724.27192-1-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde --- drivers/net/can/vxcan.c | 3 +++ include/linux/can/core.h | 3 ++- include/linux/can/skb.h | 4 +++- include/net/can.h | 2 ++ net/can/af_can.c | 47 ++++++++++++++++++++++++++++++++++++----------- net/can/gw.c | 3 +++ net/can/isotp.c | 16 ++++++++++------ net/can/raw.c | 10 +++++++--- 8 files changed, 66 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c index 9e2e25d02471..51148a81d1d9 100644 --- a/drivers/net/can/vxcan.c +++ b/drivers/net/can/vxcan.c @@ -79,6 +79,9 @@ static netdev_tx_t vxcan_xmit(struct sk_buff *oskb, struct net_device *dev) /* reset CAN GW hop counter */ csx->can_gw_hops = 0; + /* start with new CAN skb UID in the other namespace */ + csx->can_skb_uid = 0; + skb->pkt_type = PACKET_BROADCAST; skb->dev = peer; skb->ip_summed = CHECKSUM_UNNECESSARY; diff --git a/include/linux/can/core.h b/include/linux/can/core.h index 3287232e3cad..2de74c2b78b6 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -17,6 +17,7 @@ #include #include #include +#include #define DNAME(dev) ((dev) ? (dev)->name : "any") @@ -58,7 +59,7 @@ extern void can_rx_unregister(struct net *net, struct net_device *dev, void *data); extern int can_send(struct sk_buff *skb, int loop); -void can_set_skb_uid(struct sk_buff *skb); +void can_set_skb_uid(struct can_skb_ext *csx); void can_sock_destruct(struct sock *sk); #endif /* !_CAN_CORE_H */ diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index a70a02967071..5d27843862fc 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -43,8 +43,10 @@ static inline struct can_skb_ext *can_skb_ext_add(struct sk_buff *skb) struct can_skb_ext *csx = skb_ext_add(skb, SKB_EXT_CAN); /* skb_ext_add() returns uninitialized space */ - if (csx) + if (csx) { csx->can_gw_hops = 0; + csx->can_skb_uid = 0; + } return csx; } diff --git a/include/net/can.h b/include/net/can.h index 6db9e826f0e0..2b8af2598732 100644 --- a/include/net/can.h +++ b/include/net/can.h @@ -17,12 +17,14 @@ * @can_framelen: cached echo CAN frame length for bql * @can_gw_hops: can-gw CAN frame time-to-live counter * @can_ext_flags: CAN skb extensions flags + * @can_skb_uid: CAN skb UID for raw_rcv and isotp echo handling */ struct can_skb_ext { int can_iif; u16 can_framelen; u8 can_gw_hops; u8 can_ext_flags; + u32 can_skb_uid; }; #endif /* _NET_CAN_H */ diff --git a/net/can/af_can.c b/net/can/af_can.c index 7bc86b176b4d..34fe3b28d576 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -641,13 +641,10 @@ static int can_rcv_filter(struct can_dev_rcv_lists *dev_rcv_lists, struct sk_buf return matches; } -void can_set_skb_uid(struct sk_buff *skb) +void can_set_skb_uid(struct can_skb_ext *csx) { - /* create non-zero unique skb identifier together with *skb */ - while (!(skb->hash)) - skb->hash = atomic_inc_return(&skbcounter); - - skb->sw_hash = 1; + while (!(csx->can_skb_uid)) + csx->can_skb_uid = atomic_inc_return(&skbcounter); } EXPORT_SYMBOL(can_set_skb_uid); @@ -662,8 +659,6 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev) atomic_long_inc(&pkg_stats->rx_frames); atomic_long_inc(&pkg_stats->rx_frames_delta); - can_set_skb_uid(skb); - rcu_read_lock(); /* deliver the packet to sockets listening on all devices */ @@ -687,8 +682,10 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev) static int can_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { + struct can_skb_ext *csx = can_skb_ext_find(skb); + if (unlikely(dev->type != ARPHRD_CAN || !can_get_ml_priv(dev) || - !can_skb_ext_find(skb) || !can_is_can_skb(skb))) { + !csx || !can_is_can_skb(skb))) { pr_warn_once("PF_CAN: dropped non conform CAN skbuff: dev type %d, len %d\n", dev->type, skb->len); @@ -696,6 +693,14 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, return NET_RX_DROP; } + /* create unshared CAN skb_extension for netem/mirred skb clones */ + csx = skb_ext_add(skb, SKB_EXT_CAN); + if (unlikely(!csx)) { + kfree_skb_reason(skb, SKB_DROP_REASON_NOMEM); + return NET_RX_DROP; + } + + can_set_skb_uid(csx); can_receive(skb, dev); return NET_RX_SUCCESS; } @@ -703,8 +708,10 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { + struct can_skb_ext *csx = can_skb_ext_find(skb); + if (unlikely(dev->type != ARPHRD_CAN || !can_get_ml_priv(dev) || - !can_skb_ext_find(skb) || !can_is_canfd_skb(skb))) { + !csx || !can_is_canfd_skb(skb))) { pr_warn_once("PF_CAN: dropped non conform CAN FD skbuff: dev type %d, len %d\n", dev->type, skb->len); @@ -712,6 +719,14 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, return NET_RX_DROP; } + /* create unshared CAN skb_extension for netem/mirred skb clones */ + csx = skb_ext_add(skb, SKB_EXT_CAN); + if (unlikely(!csx)) { + kfree_skb_reason(skb, SKB_DROP_REASON_NOMEM); + return NET_RX_DROP; + } + + can_set_skb_uid(csx); can_receive(skb, dev); return NET_RX_SUCCESS; } @@ -719,8 +734,10 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, static int canxl_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { + struct can_skb_ext *csx = can_skb_ext_find(skb); + if (unlikely(dev->type != ARPHRD_CAN || !can_get_ml_priv(dev) || - !can_skb_ext_find(skb) || !can_is_canxl_skb(skb))) { + !csx || !can_is_canxl_skb(skb))) { pr_warn_once("PF_CAN: dropped non conform CAN XL skbuff: dev type %d, len %d\n", dev->type, skb->len); @@ -728,6 +745,14 @@ static int canxl_rcv(struct sk_buff *skb, struct net_device *dev, return NET_RX_DROP; } + /* create unshared CAN skb_extension for netem/mirred skb clones */ + csx = skb_ext_add(skb, SKB_EXT_CAN); + if (unlikely(!csx)) { + kfree_skb_reason(skb, SKB_DROP_REASON_NOMEM); + return NET_RX_DROP; + } + + can_set_skb_uid(csx); can_receive(skb, dev); return NET_RX_SUCCESS; } diff --git a/net/can/gw.c b/net/can/gw.c index 0ec99f68aa45..5793cb2420ed 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -527,6 +527,9 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) /* put the incremented hop counter in the cloned skb */ ncsx->can_gw_hops = csx->can_gw_hops + 1; + /* force a new CAN UID generation for the routed frame */ + ncsx->can_skb_uid = 0; + /* first processing of this CAN frame -> adjust to private hop limit */ if (gwj->limit_hops && ncsx->can_gw_hops == 1) ncsx->can_gw_hops = max_hops - gwj->limit_hops + 1; diff --git a/net/can/isotp.c b/net/can/isotp.c index 155530aedce2..f5dc9d04bd68 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -891,7 +891,7 @@ static void isotp_send_cframe(struct isotp_sock *so) csx->can_iif = dev->ifindex; /* set uid in tx skb to identify CF echo frames */ - can_set_skb_uid(skb); + can_set_skb_uid(csx); cf = (struct canfd_frame *)skb->data; skb_put_zero(skb, so->ll.mtu); @@ -917,7 +917,7 @@ static void isotp_send_cframe(struct isotp_sock *so) pr_notice_once("can-isotp: cfecho is %08X != 0\n", old_cfecho); /* set consecutive frame echo tag */ - WRITE_ONCE(so->cfecho, skb->hash); + WRITE_ONCE(so->cfecho, csx->can_skb_uid); /* send frame with local echo enabled */ can_send_ret = can_send(skb, 1); @@ -969,18 +969,22 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data) { struct sock *sk = (struct sock *)data; struct isotp_sock *so = isotp_sk(sk); + struct can_skb_ext *csx = can_skb_ext_find(skb); /* only handle my own local echo CF/SF skb's (no FF!) */ if (skb->sk != sk) return; + if (WARN_ON_ONCE(!csx)) + return; + /* unlike isotp_rcv_fc()/isotp_rcv_cf(), not already under so->rx_lock * (no isotp_rcv() caller here), so take it ourselves */ spin_lock(&so->rx_lock); /* so->cfecho may since belong to a new transfer; recheck under lock */ - if (READ_ONCE(so->cfecho) != skb->hash) + if (READ_ONCE(so->cfecho) != csx->can_skb_uid) goto out_unlock; /* cancel local echo timeout */ @@ -1222,7 +1226,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) csx->can_iif = dev->ifindex; /* set uid in tx skb to identify CF echo frames */ - can_set_skb_uid(skb); + can_set_skb_uid(csx); so->tx.len = size; so->tx.idx = 0; @@ -1261,7 +1265,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) cf->data[ae] |= size; /* set CF echo tag for isotp_rcv_echo() (SF-mode) */ - WRITE_ONCE(so->cfecho, skb->hash); + WRITE_ONCE(so->cfecho, csx->can_skb_uid); } else { /* send first frame */ @@ -1278,7 +1282,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) so->txfc.bs = 0; /* set CF echo tag for isotp_rcv_echo() (CF-mode) */ - WRITE_ONCE(so->cfecho, skb->hash); + WRITE_ONCE(so->cfecho, csx->can_skb_uid); } else { /* standard flow control check */ new_state = ISOTP_WAIT_FIRST_FC; diff --git a/net/can/raw.c b/net/can/raw.c index 82d9c0499c95..0acd4f6c6dd6 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -77,7 +77,7 @@ MODULE_ALIAS("can-proto-1"); struct uniqframe { const struct sk_buff *skb; - u32 hash; + u32 can_skb_uid; unsigned int join_rx_count; }; @@ -133,12 +133,16 @@ static void raw_rcv(struct sk_buff *oskb, void *data) enum skb_drop_reason reason; struct sockaddr_can *addr; struct sk_buff *skb; + struct can_skb_ext *csx = can_skb_ext_find(oskb); unsigned int *pflags; /* check the received tx sock reference */ if (!ro->recv_own_msgs && oskb->sk == sk) return; + if (WARN_ON_ONCE(!csx)) + return; + /* make sure to not pass oversized frames to the socket */ if (!ro->fd_frames && can_is_canfd_skb(oskb)) return; @@ -165,7 +169,7 @@ static void raw_rcv(struct sk_buff *oskb, void *data) /* eliminate multiple filter matches for the same skb */ if (this_cpu_ptr(ro->uniq)->skb == oskb && - this_cpu_ptr(ro->uniq)->hash == oskb->hash) { + this_cpu_ptr(ro->uniq)->can_skb_uid == csx->can_skb_uid) { if (!ro->join_filters) return; @@ -175,7 +179,7 @@ static void raw_rcv(struct sk_buff *oskb, void *data) return; } else { this_cpu_ptr(ro->uniq)->skb = oskb; - this_cpu_ptr(ro->uniq)->hash = oskb->hash; + this_cpu_ptr(ro->uniq)->can_skb_uid = csx->can_skb_uid; this_cpu_ptr(ro->uniq)->join_rx_count = 1; /* drop first frame to check all enabled filters? */ if (ro->join_filters && ro->count > 1) -- cgit v1.2.3 From c83e3d2912432107148cc5e288ddd153a84c0f43 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Thu, 1 Oct 2026 16:07:27 +0200 Subject: braille: nbcon: Allow to use a serial console with NBCON API as Braille console The Braille console is not registered in console_list. Instead, it is integrated with the virtual terminal (VT) and shows what is displayed on the terminal. It writes the data using con->write*() callback of the associated serial console driver. braille_write() is called from the VT code under console_lock(). The associated serial console driver can be converted to the NBCON API though. The situation is similar to flushing nbcon consoles in the legacy loop when some boot consoles are still registered, see nbcon_legacy_emit_next_record(). But there is a big difference though. braille_write() is not directly called from the code paths flushing registered consoles. The VT code expects that braille_write() succeeds. It does not replay the message when it can't acquire the ownership. As a result, braille_write(): + must try harder to get the ownership. + has to be synchronized only against non-printk serial console which depend nbcon_device_try_acquire() using NBCON_PRIO_NORMAL. Let's look at it from another side and try to simulate the original locking using the NBCON API: 1. Take con->device_lock(), aka the port->lock in the legacy serial console driver. 2. Acquire nbcon context to provide some synchronization for a panic() context. Use NBCON_PRIO_NORMAL because it contends only with nbcon_device_try_acquire() users. Do it in a busy loop. It should always succeed when con->device_lock() succeeded because all other users do the same. The only exception is when the context get acquired by a CPU handling panic. 3. In panic, disable interrupts and try to acquire the nbcon context. Use NBCON_PRIO_PANIC. And try even an unsafe takeover because otherwise the Braille console won't see the text shown during panic(). It is similar to the oops_in_progress/trylock handling in the legacy serial console driver. Finally, avoid the newline prepending logic in the existing serial console drivers when they are used as a Braille console. As explained above, the Braille console shows the last modified line on the terminal (VT). braille_write() is called when single characters are added. Most messages are not ended by newline. Anyway, the VT code does not have logic to reply partially printed messages. Fixes: 13189fa73afa ("printk: nbcon: Rely on kthreads for normal operation") Reviewed-by: John Ogness [pmladek@suse.com: Remove white space changes in braille_register_console(). Typo fix.] Link: https://patch.msgid.link/20261001140727.124398-2-pmladek@suse.com Signed-off-by: Petr Mladek --- drivers/accessibility/braille/braille_console.c | 57 +++++++++++++++++- drivers/tty/serial/8250/8250_port.c | 5 +- drivers/tty/serial/amba-pl011.c | 2 +- drivers/tty/serial/imx.c | 2 +- drivers/tty/serial/sifive.c | 2 +- include/linux/console.h | 15 +++++ kernel/printk/nbcon.c | 79 +++++++++++++++++++++++++ 7 files changed, 156 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/accessibility/braille/braille_console.c b/drivers/accessibility/braille/braille_console.c index 06b43b678d6e..5a3e375f4800 100644 --- a/drivers/accessibility/braille/braille_console.c +++ b/drivers/accessibility/braille/braille_console.c @@ -62,14 +62,50 @@ static void braille_write(u16 *buf) { static u16 lastwrite[WIDTH]; unsigned char data[1 + 1 + 2*WIDTH + 2 + 1], csum = 0, *c; + struct nbcon_write_context wctxt = { }; + unsigned long flags; u16 out; int i; if (!braille_co) return; + /* + * Braille console is not registered in console_list. Instead, it + * is integrated with VT and shows what appears on the graphical + * console under console_lock(). From this POV it is a legacy + * console. But it calls serial console driver which might be + * converted to the NBCON API. It is similar to + * nbcon_legacy_emit_next_record() except that we should try + * harder to get the lock. Otherwise, the Braille device won't show + * everything what is displayed on the terminal. + * + * In short, simulate the original locking using NBCON API. + */ + if (braille_co->flags & CON_NBCON) { + if (panic_on_this_cpu()) { + /* + * This should be good enough in practice. Most/all + * serial console drivers have the atomic callback. + */ + if (!braille_co->write_atomic) + return; + + local_irq_save(flags); + /* NBCON API strictly requires the ownership. */ + if (!nbcon_braille_try_acquire(braille_co, &wctxt)) { + local_irq_restore(flags); + return; + } + } else { + braille_co->device_lock(braille_co, &flags); + while (!nbcon_braille_try_acquire(braille_co, &wctxt)) + cpu_relax(); + } + } + if (!memcmp(lastwrite, buf, WIDTH * sizeof(*buf))) - return; + goto unlock_nbcon; memcpy(lastwrite, buf, WIDTH * sizeof(*buf)); #define SOH 1 @@ -102,7 +138,24 @@ static void braille_write(u16 *buf) *c++ = csum; *c++ = ETX; - braille_co->write(braille_co, data, c - data); + if (braille_co->flags & CON_NBCON) { + nbcon_write_context_set_buf(&wctxt, (char *)data, c - data); + if (panic_on_this_cpu()) + braille_co->write_atomic(braille_co, &wctxt); + else + braille_co->write_thread(braille_co, &wctxt); + } else { + braille_co->write(braille_co, data, c - data); + } + +unlock_nbcon: + if (braille_co->flags & CON_NBCON) { + nbcon_braille_release(&wctxt); + if (panic_on_this_cpu()) + local_irq_restore(flags); + else + braille_co->device_unlock(braille_co, flags); + } } /* Follow the VC cursor*/ diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 38fa45e74a37..548fd68ad1fa 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -3417,8 +3417,11 @@ static void __serial8250_console_write(struct uart_8250_port *up, * If the console printer did not fully output the previous line, it * must have been handed or taken over. Insert a newline in order to * maintain clean output. + * + * Braille consoles are an exception. The serial port is not used + * for printk(). The driver is supposed to write exactly what it gets. */ - if (!up->console_line_ended) { + if (unlikely(!up->console_line_ended && !nbcon_write_context_is_braille(wctxt))) { if (use_fifo) __serial8250_console_fifo_write(up, wctxt, "\n", 1); else diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index c4824c201e1c..e67f2ac454b6 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -2656,7 +2656,7 @@ pl011_console_write_atomic(struct console *co, struct nbcon_write_context *wctxt uap, REG_CR); } - if (!uap->console_line_ended) + if (unlikely(!uap->console_line_ended && !nbcon_is_braille(co))) uart_console_write(&uap->port, "\n", 1, pl011_console_putchar); uart_console_write(&uap->port, wctxt->outbuf, wctxt->len, pl011_console_putchar); diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 513dbe95f7e9..986fefb45c63 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -2136,7 +2136,7 @@ static void imx_uart_console_write_atomic(struct console *co, imx_uart_writel(sport, ucr1, UCR1); imx_uart_writel(sport, old_ucr.ucr2 | UCR2_TXEN, UCR2); - if (!sport->last_putchar_was_newline) + if (unlikely(!sport->last_putchar_was_newline && !nbcon_is_braille(co))) uart_console_write(port, "\n", 1, imx_uart_console_putchar); uart_console_write(port, wctxt->outbuf, wctxt->len, imx_uart_console_putchar); diff --git a/drivers/tty/serial/sifive.c b/drivers/tty/serial/sifive.c index 110d67613192..f615701fceb7 100644 --- a/drivers/tty/serial/sifive.c +++ b/drivers/tty/serial/sifive.c @@ -821,7 +821,7 @@ static void sifive_serial_console_write_atomic(struct console *co, ier = __ssp_readl(ssp, SIFIVE_SERIAL_IE_OFFS); __ssp_writel(0, SIFIVE_SERIAL_IE_OFFS, ssp); - if (!ssp->console_line_ended) + if (unlikely(!ssp->console_line_ended && !nbcon_is_braille(co))) uart_console_write(port, "\n", 1, sifive_serial_console_putchar); uart_console_write(port, wctxt->outbuf, wctxt->len, sifive_serial_console_putchar); diff --git a/include/linux/console.h b/include/linux/console.h index 502d1abe3f50..df23148987ee 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -615,6 +615,15 @@ extern bool nbcon_allow_unsafe_takeover(void); extern bool nbcon_kdb_try_acquire(struct console *con, struct nbcon_write_context *wctxt); extern void nbcon_kdb_release(struct nbcon_write_context *wctxt); +extern bool nbcon_write_context_is_braille(struct nbcon_write_context *wctxt); +extern bool nbcon_braille_try_acquire(struct console *con, + struct nbcon_write_context *wctxt); +extern void nbcon_braille_release(struct nbcon_write_context *wctxt); + +static inline bool nbcon_is_braille(struct console *con) +{ + return con && (con->flags & CON_BRL); +} /* * Check if the given console is currently capable and allowed to print @@ -678,8 +687,14 @@ static inline void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt) { } static inline bool nbcon_kdb_try_acquire(struct console *con, struct nbcon_write_context *wctxt) { return false; } static inline void nbcon_kdb_release(struct nbcon_write_context *wctxt) { } +static inline +bool nbcon_write_context_is_braille(struct nbcon_write_context *wctxt) { return false; } static inline bool console_is_usable(struct console *con, short flags, bool use_atomic) { return false; } +static inline bool nbcon_braille_try_acquire(struct console *con, + struct nbcon_write_context *wctxt) { return false; } +static inline void nbcon_braille_release(struct nbcon_write_context *wctxt) { } +static inline bool nbcon_is_braille(struct console *con) { return false; } #endif extern int console_set_on_cmdline; diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c index d17704fe93ae..fb1b37741952 100644 --- a/kernel/printk/nbcon.c +++ b/kernel/printk/nbcon.c @@ -1887,6 +1887,7 @@ bool nbcon_device_try_acquire(struct console *con) memset(ctxt, 0, sizeof(*ctxt)); ctxt->console = con; + /* Keep in sync with nbcon_braille_try_acquire(). */ ctxt->prio = NBCON_PRIO_NORMAL; if (!nbcon_context_try_acquire(ctxt, false)) @@ -2002,3 +2003,81 @@ void nbcon_kdb_release(struct nbcon_write_context *wctxt) */ __nbcon_atomic_flush_pending_con(ctxt->console, prb_next_reserve_seq(prb)); } + +/** + * nbcon_is_braille - Checks whether the nbcon write context is using Braille console + * + * @wctxt: checked nbcon write context + * + * Return: True when the write context is associated with a Braille console. + * Otherwise, return false. + * + * Context: Can be called in any context but only when Braille console is + * registered and the struct console could not disappear. + */ +bool nbcon_write_context_is_braille(struct nbcon_write_context *wctxt) +{ + struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); + struct console *con = ctxt->console; + + return con && con->flags & CON_BRL; +} +EXPORT_SYMBOL_GPL(nbcon_write_context_is_braille); + +/** + * nbcon_braille_try_acquire - Try to acquire nbcon console for braille_write() + * + * @con: The nbcon console to acquire + * @wctxt: The nbcon write context to be used on success + * + * Context: braille_write() for emitting a single buffer on Braille console. + * + * Return: True if the console was acquired. False otherwise. + * + * Braille console is not registered as a proper printk consoles. Instead, + * it is integrated with the graphical virtual terminal. + * + * This function is going to synchronize the Braille write against other + * operations on the used serial port. The port can be used also for a user + * input but printk() won't emit the messages there directly. It means + * the other operations will get synchronized using nbcon_device_try_acquire(). + */ +bool nbcon_braille_try_acquire(struct console *con, + struct nbcon_write_context *wctxt) +{ + struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); + bool success; + + memset(ctxt, 0, sizeof(*ctxt)); + ctxt->console = con; + /* Keep in sync with nbcon_device_try_acquire(). */ + if (panic_on_this_cpu()) + ctxt->prio = NBCON_PRIO_PANIC; + else + ctxt->prio = NBCON_PRIO_NORMAL; + + success = nbcon_context_try_acquire(ctxt, false); + /* + * Try hard in panic, otherwise the Braille console would + * miss a text on the related VT. + */ + if (panic_on_this_cpu() && !success) { + ctxt->allow_unsafe_takeover = true; + success = nbcon_context_try_acquire(ctxt, false); + } + + return success; +} + +/** + * nbcon_braille_release - Release the nbcon console + * + * @wctxt: The nbcon write context initialized by a successful + * nbcon_braille_try_acquire() + */ +void nbcon_braille_release(struct nbcon_write_context *wctxt) +{ + struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); + + nbcon_context_release(ctxt); +} -- cgit v1.2.3 From 564e46d9f6e87912effa03f123d37a511d520f09 Mon Sep 17 00:00:00 2001 From: Karl Bonde Torp Date: Tue, 29 Sep 2026 16:25:00 +0200 Subject: nvme: fix swapped ZRASF zone state values for full and read only The Zone Management Receive command Zone Receive Action Specific (ZRASF) reporting option values for the Full and Read Only zone states are swapped compared to the NVM Express Zoned Namespace Command Set Specification, Revision 1.5, Figure 35: - 5h lists the zones in the ZSF:Full state. - 6h lists the zones in the ZSRO:Read Only state. The nvmet ZNS backend uses these constants to map the ZRASF value received from the host to a block layer zone condition when filtering zones in Report Zones. Because of the swap, a host asking for full zones was given the read only zones, and a host asking for read only zones was given the full zones. Swap the values of NVME_ZRASF_ZONE_STATE_FULL and NVME_ZRASF_ZONE_STATE_READONLY to match the specification. Fixes: aaf2e048af27 ("nvmet: add ZBD over ZNS backend support") Cc: stable@vger.kernel.org Reviewed-by: Damien Le Moal Signed-off-by: Karl Bonde Torp Signed-off-by: Andreas Hindborg Signed-off-by: Keith Busch --- include/linux/nvme.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 91ce434a7e8d..6248711784b3 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1266,8 +1266,8 @@ enum { NVME_ZRASF_ZONE_STATE_IMP_OPEN = 0x02, NVME_ZRASF_ZONE_STATE_EXP_OPEN = 0x03, NVME_ZRASF_ZONE_STATE_CLOSED = 0x04, - NVME_ZRASF_ZONE_STATE_READONLY = 0x05, - NVME_ZRASF_ZONE_STATE_FULL = 0x06, + NVME_ZRASF_ZONE_STATE_FULL = 0x05, + NVME_ZRASF_ZONE_STATE_READONLY = 0x06, NVME_ZRASF_ZONE_STATE_OFFLINE = 0x07, NVME_REPORT_ZONE_PARTIAL = 1, }; -- cgit v1.2.3 From e6ac89b8b1c12e9104df45a14a26e2dfa96ded06 Mon Sep 17 00:00:00 2001 From: Kuba Piecuch Date: Sat, 3 Oct 2026 11:53:17 +0000 Subject: sched_ext: Generate qseq from a per-task counter finish_dispatch() uses the qseq embedded in p->scx.ops_state to tell whether the QUEUED instance of a task it's about to claim is the one scx_bpf_dsq_insert() saw. qseq is generated from rq->scx.ops_qseq, but the counters of different rqs are independent, so if a task is dequeued and re-enqueued on a different rq between scx_bpf_dsq_insert() and finish_dispatch(), the new QUEUED instance can end up with the same qseq as the old one: CPU X CPU Z ----- ----- enqueue p on rq A, qseq = N ops.dispatch() scx_bpf_dsq_insert(p) records qseq N sched_setaffinity(p) dequeue p from rq A enqueue p on rq B, qseq = N finish_dispatch(p, N) qseq matches, p is claimed The claim itself is still atomic so the core stays consistent, but an insert issued for a previous QUEUED instance gets applied to a new one which the BPF scheduler has just received through ops.enqueue(). This breaks the guarantee that dispatches targeting a stale instance are ignored. Generate qseq from a per-task counter, p->scx.ops_qseq, instead so that consecutive QUEUED instances of a task never share a qseq regardless of which rq they're on. The counter is only updated in scx_do_enqueue_task() with the task's rq locked, so no additional synchronization is needed, and it fits in an existing hole in struct sched_ext_entity on 64bit. Remove the now unused rq->scx.ops_qseq. Never generate qseq 0. NONE and DISPATCHING don't carry a qseq, so scx_bpf_dsq_insert() on a task in either state records 0. With a per-task counter, every task's first QUEUED instance would otherwise get qseq 0 and could be claimed by such an insert. Wrap the counter where the QSEQ field wraps so that it can't reach a value that shifts to 0 on 32bit either. Fixes: f0e1a0643a59 ("sched_ext: Implement BPF extensible scheduler class") Cc: stable@vger.kernel.org # v6.12+ Assisted-by: Claude:claude-opus-5.5 Signed-off-by: Kuba Piecuch Signed-off-by: Tejun Heo --- include/linux/sched/ext.h | 1 + kernel/sched/ext/ext.c | 14 ++++++++++---- kernel/sched/ext/internal.h | 5 +++++ kernel/sched/sched.h | 1 - 4 files changed, 16 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 582d7cd4a983..36c04797436c 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -207,6 +207,7 @@ struct sched_ext_entity { s32 holding_cpu; s32 selected_cpu; s32 runnable_cpu; /* cpu @p is runnable on, -1 if not */ + u32 ops_qseq; /* protected by rq lock */ struct task_struct *kf_tasks[2]; /* see SCX_CALL_OP_TASK() */ struct list_head runnable_node; /* rq->scx.runnable_list */ diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index 5209510d6a5e..ac8fe70a9fb6 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -2057,8 +2057,14 @@ void scx_do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags, if (unlikely(!SCX_HAS_OP(sch, enqueue))) goto global; - /* DSQ bypass didn't trigger, enqueue on the BPF scheduler */ - qseq = rq->scx.ops_qseq++ << SCX_OPSS_QSEQ_SHIFT; + /* + * DSQ bypass didn't trigger, enqueue on the BPF scheduler. Wrap the + * per-task qseq counter where the QSEQ field wraps and skip 0, which is + * what scx_bpf_dsq_insert() records for a task in NONE or DISPATCHING. + */ + p->scx.ops_qseq = ((p->scx.ops_qseq + 1) & + (SCX_OPSS_QSEQ_MASK >> SCX_OPSS_QSEQ_SHIFT)) ?: 1; + qseq = (unsigned long)p->scx.ops_qseq << SCX_OPSS_QSEQ_SHIFT; WARN_ON_ONCE(atomic_long_read(&p->scx.ops_state) != SCX_OPSS_NONE); atomic_long_set(&p->scx.ops_state, SCX_OPSS_QUEUEING | qseq); @@ -6969,9 +6975,9 @@ static void scx_dump_cpu(struct scx_sched *sch, struct seq_buf *s, seq_buf_init(&ns, buf, avail); dump_newline(&ns); - scx_dump_line(&ns, "CPU %-4d: nr_run=%u flags=0x%x cpu_rel=%d ops_qseq=%lu ksync=%lu", + scx_dump_line(&ns, "CPU %-4d: nr_run=%u flags=0x%x cpu_rel=%d ksync=%lu", cpu, rq->scx.nr_running, rq->scx.flags, rq->scx.cpu_released, - rq->scx.ops_qseq, rq->scx.kick_sync); + rq->scx.kick_sync); scx_rescue_dump(&ns, rq); scx_dump_line(&ns, " curr=%s[%d] class=%ps", rq->curr->comm, rq->curr->pid, rq->curr->sched_class); diff --git a/kernel/sched/ext/internal.h b/kernel/sched/ext/internal.h index 1df8f583b0ec..5b37faa532d6 100644 --- a/kernel/sched/ext/internal.h +++ b/kernel/sched/ext/internal.h @@ -1998,6 +1998,11 @@ enum scx_ops_state { * dequeue/requeue, the dispatcher can tell whether it still has a claim * on the task being dispatched. * + * QSEQ is generated from the per-task p->scx.ops_qseq counter so that + * it doesn't repeat across QUEUED instances of the same task even if + * the task moves between rqs. 0 is never used as a valid QSEQ since + * NONE and DISPATCHING map to this value. + * * As some 32bit archs can't do 64bit store_release/load_acquire, * p->scx.ops_state is atomic_long_t which leaves 30 bits for QSEQ on * 32bit machines. The dispatch race window QSEQ protects is very narrow diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 742cce9da4e9..9ed0cb605c33 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -813,7 +813,6 @@ struct scx_rq { #endif struct list_head runnable_list; /* runnable tasks on this rq */ struct list_head ddsp_deferred_locals; /* deferred ddsps from enq */ - unsigned long ops_qseq; /* both stashed across the activate_task() in move_remote_task_to_local_dsq() */ u64 remote_activate_enq_flags; struct scx_sched *remote_activate_sch; -- cgit v1.2.3 From c9ec8607b4d1ce4e862f5b6ba2f0eb727387988a Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 2 Oct 2026 15:52:47 +0200 Subject: fsnotify: let a filesystem refuse marks on its objects Don't let nullfs be watched. fanotify refuses mount and filesystem marks on SB_NOUSER superblocks but inode marks of inotify, fanotify and dnotify go through. The one inode of knullfs is the root of every kernel thread and the following patches make it reachable from userspace as the directory that stands in for an unmounted mount. A watch placed through one such directory would report the opens through all the others, across users. Add FS_DISALLOW_NOTIFY next to FS_DISALLOW_NOTIFY_PERM, refuse a mark on any object of such a filesystem in fsnotify_add_mark_list() where every backend ends up and set it for nullfs. There's nothing to watch on a permanently empty and immutable filesystem. Link: https://patch.msgid.link/20261002-work-mount-fixes-4-v1-16-dd44b89d44ce@kernel.org Signed-off-by: Christian Brauner (Amutable) --- fs/notify/mark.c | 4 ++++ fs/nullfs.c | 1 + include/linux/fs.h | 1 + 3 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/fs/notify/mark.c b/fs/notify/mark.c index b2640d836a71..d17628580a57 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -903,6 +903,10 @@ static int fsnotify_add_mark_list(struct fsnotify_mark *mark, void *obj, if (WARN_ON(!fsnotify_valid_obj_type(obj_type))) return -EINVAL; + /* the filesystem doesn't want its objects watched */ + if (sb && (sb->s_type->fs_flags & FS_DISALLOW_NOTIFY)) + return -EINVAL; + /* * Attach the sb info before attaching a connector to any object on sb. * The sb info will remain attached as long as sb lives. diff --git a/fs/nullfs.c b/fs/nullfs.c index 40aa228bd81a..55a04f2d7761 100644 --- a/fs/nullfs.c +++ b/fs/nullfs.c @@ -61,6 +61,7 @@ static int nullfs_init_fs_context(struct fs_context *fc) struct file_system_type nullfs_fs_type = { .name = "nullfs", + .fs_flags = FS_DISALLOW_NOTIFY, .init_fs_context = nullfs_init_fs_context, .kill_sb = kill_anon_super, }; diff --git a/include/linux/fs.h b/include/linux/fs.h index f9d1e05e8ae6..784fa20217c4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2296,6 +2296,7 @@ struct file_system_type { #define FS_POWER_FREEZE 256 /* Always freeze on suspend/hibernate */ #define FS_USERNS_MOUNT_RESTRICTED 512 /* Restrict mount in userns if not already visible */ #define FS_USERNS_DELEGATABLE 1024 /* Can be mounted inside userns from outside */ +#define FS_DISALLOW_NOTIFY 2048 /* No fsnotify marks on its objects */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; -- cgit v1.2.3 From e08f57a7dcb83818c058e415988c23beb6c5a47f Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 2 Oct 2026 15:52:50 +0200 Subject: readdir: take no inode lock on an immutable directory iterate_dir() takes the directory's i_rwsem shared and holds it across ->iterate_shared(). For a directory that never has an entry and is never removed the lock keeps nothing still, it only orders every reader and every writer of that inode behind each other. For the directory of a nullfs instance that matters. The instance of the initial mount namespace is the root of every empty mount namespace and the private instance is the root of every kernel thread, so one inode is shared across users who have nothing else in common. And a reader can hold the lock for as long as it likes: back the getdents() buffer with a mapping of a file on a FUSE mount of your own, let the copy of "." and ".." fault and let the server wait. Queue an exclusive taker behind it, a mkdir() in that directory goes through start_dirop() before the read-only mount is reported, and from then on every lookup that misses the dcache in that directory, every create and every mount on it waits until the server answers. One user of an empty mount namespace stalls all the others. Add FOP_IMMUTABLE for the file operations of a directory that never changes and is never removed and let iterate_dir() skip the lock for it. The flag never changes for a file, ->f_pos is protected by f_pos_lock since directories are FMODE_ATOMIC_POS, IS_DEADDIR can't be set on such a directory and neither touch_atime() nor fsnotify take i_rwsem. Set it on the nullfs directory. The placeholder directories of libfs never have an entry either but their owners remove them, so they keep the lock. Fixes: 9d4e752a24f7 ("namespace: allow creating empty mount namespaces") Cc: stable@vger.kernel.org # v7.1+ Link: https://patch.msgid.link/20261002-work-mount-fixes-4-v1-19-dd44b89d44ce@kernel.org Signed-off-by: Christian Brauner (Amutable) --- fs/nullfs.c | 1 + fs/readdir.c | 13 +++++++++---- include/linux/fs.h | 2 ++ 3 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/nullfs.c b/fs/nullfs.c index d90c71f5eece..ca0dbe3dc259 100644 --- a/fs/nullfs.c +++ b/fs/nullfs.c @@ -36,6 +36,7 @@ static const struct file_operations nullfs_dir_operations = { .fsync = noop_fsync, .lock = nullfs_nolock, .flock = nullfs_nolock, + .fop_flags = FOP_IMMUTABLE, }; static int nullfs_fs_fill_super(struct super_block *s, struct fs_context *fc) diff --git a/fs/readdir.c b/fs/readdir.c index 76bb1ae3a450..f2288841337a 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -87,6 +87,8 @@ EXPORT_SYMBOL(wrap_directory_iterator); int iterate_dir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); + /* never an entry, never removed: nothing for the lock to keep still */ + bool locked = !(file->f_op->fop_flags & FOP_IMMUTABLE); int res = -ENOTDIR; if (!file->f_op->iterate_shared) @@ -100,9 +102,11 @@ int iterate_dir(struct file *file, struct dir_context *ctx) if (res) goto out; - res = down_read_killable(&inode->i_rwsem); - if (res) - goto out; + if (locked) { + res = down_read_killable(&inode->i_rwsem); + if (res) + goto out; + } res = -ENOENT; if (!IS_DEADDIR(inode)) { @@ -112,7 +116,8 @@ int iterate_dir(struct file *file, struct dir_context *ctx) fsnotify_access(file); file_accessed(file); } - inode_unlock_shared(inode); + if (locked) + inode_unlock_shared(inode); out: return res; } diff --git a/include/linux/fs.h b/include/linux/fs.h index 784fa20217c4..deb411e86661 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1978,6 +1978,8 @@ struct file_operations { #define FOP_ASYNC_LOCK ((__force fop_flags_t)(1 << 6)) /* File system supports uncached read/write buffered IO */ #define FOP_DONTCACHE ((__force fop_flags_t)(1 << 7)) +/* Never changes and is never removed, readdir of a directory takes no lock */ +#define FOP_IMMUTABLE ((__force fop_flags_t)(1 << 8)) /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, -- cgit v1.2.3 From 44378d02c5aaae24b60a75fbbb539b4aa4db503d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 1 Oct 2026 19:11:39 +0000 Subject: net: always dissect GSO packets in __virtio_net_hdr_to_skb() Commit 9e8db5913264 ("net: avoid false positives in untrusted gso validation") added a '&& skb->network_header' check before flow-dissecting GSO packets without VIRTIO_NET_HDR_F_NEEDS_CSUM in __virtio_net_hdr_to_skb(), because some callers (such as tun_get_user(), tun_xdp_one(), virtnet_receive_done(), and raw_verify_header()) called virtio_net_hdr_*_to_skb() before initializing skb->network_header and skb->dev. Because __alloc_skb() and __build_skb_around() zero-initialize skb->network_header to 0 (unlike mac_header and transport_header which are initialized to ~0U), those four callers always had skb->network_header == 0 and bypassed flow dissection in __virtio_net_hdr_to_skb(). More generally, skb->network_header is an offset from skb->head (where 0 is also a valid offset whenever skb_headroom(skb) is 0), not a boolean flag. Whenever the 'if (gso_type && skb->network_header)' branch was skipped, the fallback 'else if (gso_type)' only pulled nh_min_len + thlen (40 bytes for TCPv4) without dissecting the packet, without validating ip_proto or n_proto, and without setting skb->transport_header. If the packet has a malformed network header, it is not rejected and a subsequent skb_probe_transport_header() also fails, leaving skb->transport_header at ~0U (0xffff). Similarly, if an IPv4 packet carries IP options (ihl > 5) or an IPv6 packet carries extension headers, pulling only nh_min_len + thlen can leave the TCP header outside skb->head. In both cases, tcp_hdrlen(skb) in skb_gso_transport_seglen() reads out-of-bounds: BUG: KASAN: slab-out-of-bounds in skb_gso_transport_seglen Read of size 2 by task poc/133 skb_gso_transport_seglen (net/core/gso.c:155) skb_gso_validate_mac_len (net/core/gso.c:270) tbf_enqueue (net/sched/sch_tbf.c:260) dev_qdisc_enqueue (net/core/dev.c:4227) __dev_queue_xmit (net/core/dev.c:4884) In addition, checking virtio_net_hdr_match_proto() only inside 'if (!skb->protocol)' before flow dissection both skipped validation when skb->protocol was pre-set by the caller and rejected VLAN-tagged frames whose outer L2 protocol is ETH_P_8021Q or ETH_P_8021AD. Fix this by: 1. Initializing skb->dev and skb->network_header (plus skb->protocol for IFF_TUN) before virtio_net_hdr_*_to_skb() in tun_get_user(), tun_xdp_one(), virtnet_receive_done(), and raw_verify_header(). In tun_get_user(), drop the redundant skb_reset_mac_header(skb) in the IFF_TUN case since __virtio_net_hdr_to_skb() unconditionally resets mac_header. 2. Removing '&& skb->network_header' and the unvalidated 'else if (gso_type)' fallback in __virtio_net_hdr_to_skb() so all GSO packets without VIRTIO_NET_HDR_F_NEEDS_CSUM are flow-dissected, have their transport header pulled into linear data, and have skb->transport_header set. 3. Moving the virtio_net_hdr_match_proto() check to after skb_flow_dissect_flow_keys_basic(), validating keys.basic.n_proto against hdr_gso_type. Fixes: 9e8db5913264 ("net: avoid false positives in untrusted gso validation") Fixes: d5be7f632bad ("net: validate untrusted gso packets without csum offload") Fixes: 924a9bc362a5 ("net: check if protocol extracted by virtio_net_hdr_set_proto is correct") Reported-by: Weiming Shi Closes: https://lore.kernel.org/netdev/20260927163117.746432-2-bestswngs@gmail.com/ Signed-off-by: Eric Dumazet Reviewed-by: Willem de Bruijn Cc: Michael S. Tsirkin Link: https://patch.msgid.link/20261001191140.2818991-3-edumazet@kernel.org Signed-off-by: Jakub Kicinski --- arch/um/drivers/vector_transports.c | 1 + drivers/net/tun.c | 23 ++++++++------ drivers/net/virtio_net.c | 2 ++ include/linux/virtio_net.h | 60 ++++++++++++++++--------------------- 4 files changed, 42 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/arch/um/drivers/vector_transports.c b/arch/um/drivers/vector_transports.c index ddd127ee9678..e1fb2a76fdff 100644 --- a/arch/um/drivers/vector_transports.c +++ b/arch/um/drivers/vector_transports.c @@ -209,6 +209,7 @@ static int raw_verify_header( if ((vheader->flags & VIRTIO_NET_HDR_F_DATA_VALID) > 0) return 1; + skb_set_network_header(skb, ETH_HLEN); virtio_net_hdr_to_skb(skb, vheader, virtio_legacy_is_little_endian()); return 0; } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 5a302709a68a..242899f7fd07 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1897,12 +1897,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, } } - if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, &hdr)) { - atomic_long_inc(&tun->rx_frame_errors); - err = -EINVAL; - goto free_skb; - } - + skb->dev = tun->dev; switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: if (tun->flags & IFF_NO_PI) { @@ -1927,9 +1922,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, } } - skb_reset_mac_header(skb); + skb_reset_network_header(skb); skb->protocol = pi.proto; - skb->dev = tun->dev; break; case IFF_TAP: if (!pskb_may_pull(skb, ETH_HLEN)) { @@ -1937,10 +1931,19 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, drop_reason = SKB_DROP_REASON_HDR_TRUNC; goto drop; } - skb->protocol = eth_type_trans(skb, tun->dev); + skb_set_network_header(skb, ETH_HLEN); break; } + if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, &hdr)) { + atomic_long_inc(&tun->rx_frame_errors); + err = -EINVAL; + goto free_skb; + } + + if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) + skb->protocol = eth_type_trans(skb, tun->dev); + /* copy skb_ubuf_info for callback when skb has no error */ if (zerocopy) { skb_zcopy_init(skb, msg_control); @@ -2600,6 +2603,8 @@ build: features = tun_vnet_hdr_guest_features(READ_ONCE(tun->vnet_hdr_sz)); tnl_hdr = (struct virtio_net_hdr_v1_hash_tunnel *)gso; + skb->dev = tun->dev; + skb_set_network_header(skb, ETH_HLEN); if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, tnl_hdr)) { atomic_long_inc(&tun->rx_frame_errors); kfree_skb(skb); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index bf82ef9874ab..daab43ac92ce 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2515,6 +2515,8 @@ static void virtnet_receive_done(struct virtnet_info *vi, struct receive_queue * goto frame_err; } + skb->dev = dev; + skb_set_network_header(skb, ETH_HLEN); if (virtio_net_hdr_tnl_to_skb(skb, &hdr->tnl_hdr, vi->rx_tnl, vi->rx_tnl_csum, virtio_is_little_endian(vi->vdev))) { diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index c381b916c1b5..d6466f96cdd0 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -111,48 +111,38 @@ static inline int __virtio_net_hdr_to_skb(struct sk_buff *skb, p_off = nh_min_len + thlen; if (!pskb_may_pull(skb, p_off)) return -EINVAL; - } else { + } else if (gso_type) { /* gso packets without NEEDS_CSUM do not set transport_offset. * probe and drop if does not match one of the above types. */ - if (gso_type && skb->network_header) { - struct flow_keys_basic keys; - - if (!skb->protocol) { - __be16 protocol = dev_parse_header_protocol(skb); - - if (!protocol) - virtio_net_hdr_set_proto(skb, hdr); - else if (!virtio_net_hdr_match_proto(protocol, - hdr_gso_type)) - return -EINVAL; - else - skb->protocol = protocol; - } + struct flow_keys_basic keys; + + if (!skb->protocol) { + skb->protocol = dev_parse_header_protocol(skb); + if (!skb->protocol) + virtio_net_hdr_set_proto(skb, hdr); + } retry: - if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, - NULL, 0, 0, 0, - 0)) { - /* UFO does not specify ipv4 or 6: try both */ - if (gso_type & SKB_GSO_UDP && - skb->protocol == htons(ETH_P_IP)) { - skb->protocol = htons(ETH_P_IPV6); - goto retry; - } - return -EINVAL; + if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, + NULL, 0, 0, 0, + 0)) { + /* UFO does not specify ipv4 or 6: try both */ + if (gso_type & SKB_GSO_UDP && + skb->protocol == htons(ETH_P_IP)) { + skb->protocol = htons(ETH_P_IPV6); + goto retry; } + return -EINVAL; + } - p_off = keys.control.thoff + thlen; - if (!pskb_may_pull(skb, p_off) || - keys.basic.ip_proto != ip_proto) - return -EINVAL; + p_off = keys.control.thoff + thlen; + if (!pskb_may_pull(skb, p_off) || + keys.basic.ip_proto != ip_proto || + !virtio_net_hdr_match_proto(keys.basic.n_proto, + hdr_gso_type)) + return -EINVAL; - skb_set_transport_header(skb, keys.control.thoff); - } else if (gso_type) { - p_off = nh_min_len + thlen; - if (!pskb_may_pull(skb, p_off)) - return -EINVAL; - } + skb_set_transport_header(skb, keys.control.thoff); } if (hdr_gso_type != VIRTIO_NET_HDR_GSO_NONE) { -- cgit v1.2.3 From 6da8f402e362b2f546e2efb7167fc9597aef6faf Mon Sep 17 00:00:00 2001 From: Eugene Gvozdetsky Date: Fri, 9 Oct 2026 01:08:49 +0200 Subject: io_uring/register: don't exempt disabled rings from task restrictions A ring created with IORING_SETUP_R_DISABLED is exempt from its register restrictions until it is enabled. This lets the creator register the restrictions and then enable the ring with IORING_REGISTER_ENABLE_RINGS, whether or not that opcode is in the allowed set. Since commit ed82f35b926b ("io_uring: allow registration of per-task restrictions"), a ring also inherits restrictions from the task that creates it, and the same exemption applies to those. A task whose register opcodes are restricted can therefore create a disabled ring, issue any register opcode on it, and then enable it. Mark rings whose restrictions were inherited from the task, and keep checking register opcodes for them while the ring is disabled. Enabling such a ring now requires IORING_REGISTER_ENABLE_RINGS to be in the task's allowed set. Per-ring restrictions registered on a disabled ring work as before. Fixes: ed82f35b926b ("io_uring: allow registration of per-task restrictions") Cc: stable@vger.kernel.org Assisted-by: Claude:claude-opus-5-5 Signed-off-by: Eugene Gvozdetsky Link: https://patch.msgid.link/20261009-iouring-task-restrict-fix-v1-1-a49daf55a12c@gmail.com [axboe: amend with inheritance flag fixup] Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 2 ++ io_uring/io_uring.c | 3 ++- io_uring/register.c | 9 ++++++++- 3 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 6b9e9c669bb3..f9aab8d3f861 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -317,6 +317,8 @@ enum { IO_RING_F_DRAIN_DISABLED = BIT(10), IO_RING_F_COMPAT = BIT(11), IO_RING_F_IOWQ_LIMITS_SET = BIT(12), + /* restrictions were inherited from the task that created the ring */ + IO_RING_F_RESTRICT_INHERITED = BIT(13), }; struct iou_ctx {}; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 79c40e0abf17..c994157173a2 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2962,7 +2962,8 @@ static void io_ctx_restriction_clone(struct io_ring_ctx *ctx, if (dst->op_registered) ctx->int_flags |= IO_RING_F_OP_RESTRICTED; if (dst->reg_registered) - ctx->int_flags |= IO_RING_F_REG_RESTRICTED; + ctx->int_flags |= IO_RING_F_REG_RESTRICTED | + IO_RING_F_RESTRICT_INHERITED; } static __cold int io_uring_create(struct io_ctx_config *config) diff --git a/io_uring/register.c b/io_uring/register.c index d11a53d68431..dab3eb4258df 100644 --- a/io_uring/register.c +++ b/io_uring/register.c @@ -766,7 +766,14 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, if (ctx->submitter_task && ctx->submitter_task != current) return -EEXIST; - if ((ctx->int_flags & IO_RING_F_REG_RESTRICTED) && !(ctx->flags & IORING_SETUP_R_DISABLED)) { + /* + * A disabled ring is exempt from its own register restrictions, so + * that the creator can set them up and then enable the ring. That + * does not apply to restrictions inherited from the task. + */ + if ((ctx->int_flags & IO_RING_F_REG_RESTRICTED) && + (!(ctx->flags & IORING_SETUP_R_DISABLED) || + (ctx->int_flags & IO_RING_F_RESTRICT_INHERITED))) { opcode = array_index_nospec(opcode, IORING_REGISTER_LAST); if (!test_bit(opcode, ctx->restrictions.register_op)) return -EACCES; -- cgit v1.2.3