From: Greg Kroah-Hartman Date: Mon, 19 Feb 2024 19:04:36 +0000 (+0100) Subject: 6.1-stable patches X-Git-Tag: v4.19.307~101 X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=e49a171bfa67c000a36a673510e42b7814e6422e;p=thirdparty%2Fkernel%2Fstable-queue.git 6.1-stable patches added patches: asoc-amd-yc-add-dmi-quirk-for-lenovo-ideapad-pro-5-16arp8.patch can-j1939-fix-uaf-in-j1939_sk_match_filter-during-setsockopt-so_j1939_filter.patch can-j1939-prevent-deadlock-by-changing-j1939_socks_lock-to-rwlock.patch can-netlink-fix-tdco-calculation-using-the-old-data-bittiming.patch ceph-prevent-use-after-free-in-encode_cap_msg.patch crypto-ccp-fix-null-pointer-dereference-in-__sev_platform_shutdown_locked.patch exit-wait_task_zombie-kill-the-no-longer-necessary-spin_lock_irq-siglock.patch fs-hugetlb-fix-null-pointer-dereference-in-hugetlbs_fill_super.patch fs-proc-do_task_stat-move-thread_group_cputime_adjusted-outside-of-lock_task_sighand.patch fs-relax-mount_setattr-permission-checks.patch hv_netvsc-register-vf-in-netvsc_probe-if-net_device_register-missed.patch irqchip-gic-v3-its-fix-gicv4.1-vpe-affinity-update.patch irqchip-irq-brcmstb-l2-add-write-memory-barrier-before-exit.patch mm-hugetlb-pages-should-not-be-reserved-by-shmat-if-shm_noreserve.patch mmc-sdhci-pci-o2micro-fix-a-warm-reboot-issue-that-disk-can-t-be-detected-by-bios.patch net-ethernet-ti-cpsw-enable-mac_managed_pm-to-fix-mdio.patch net-ethernet-ti-cpsw_new-enable-mac_managed_pm-to-fix-mdio.patch nfp-flower-prevent-re-adding-mac-index-for-bonded-port.patch nfp-use-correct-macro-for-lengthselect-in-bar-config.patch of-property-fix-typo-in-io-channels.patch pmdomain-core-move-the-unused-cleanup-to-a-_sync-initcall.patch s390-qeth-fix-potential-loss-of-l3-ip-in-case-of-network-issues.patch tools-rtla-exit-with-exit_success-when-help-is-invoked.patch tools-rtla-fix-makefile-compiler-options-for-clang.patch tools-rtla-fix-uninitialized-bucket-data-bucket_size-warning.patch tools-rtla-remove-unused-sched_getattr-function.patch tools-rtla-replace-setting-prio-with-nice-for-sched_other.patch wifi-cfg80211-fix-wiphy-delayed-work-queueing.patch wifi-mac80211-reload-info-pointer-in-ieee80211_tx_dequeue.patch zonefs-improve-error-handling.patch --- diff --git a/queue-6.1/asoc-amd-yc-add-dmi-quirk-for-lenovo-ideapad-pro-5-16arp8.patch b/queue-6.1/asoc-amd-yc-add-dmi-quirk-for-lenovo-ideapad-pro-5-16arp8.patch new file mode 100644 index 00000000000..f05d7ab4b9f --- /dev/null +++ b/queue-6.1/asoc-amd-yc-add-dmi-quirk-for-lenovo-ideapad-pro-5-16arp8.patch @@ -0,0 +1,39 @@ +From 610010737f74482a61896596a0116876ecf9e65c Mon Sep 17 00:00:00 2001 +From: Mario Limonciello +Date: Mon, 5 Feb 2024 15:48:53 -0600 +Subject: ASoC: amd: yc: Add DMI quirk for Lenovo Ideapad Pro 5 16ARP8 + +From: Mario Limonciello + +commit 610010737f74482a61896596a0116876ecf9e65c upstream. + +The laptop requires a quirk ID to enable its internal microphone. Add +it to the DMI quirk table. + +Reported-by: Stanislav Petrov +Closes: https://bugzilla.kernel.org/show_bug.cgi?id=216925 +Cc: stable@vger.kernel.org +Signed-off-by: Mario Limonciello +Link: https://lore.kernel.org/r/20240205214853.2689-1-mario.limonciello@amd.com +Signed-off-by: Mark Brown +Signed-off-by: Greg Kroah-Hartman +--- + sound/soc/amd/yc/acp6x-mach.c | 7 +++++++ + 1 file changed, 7 insertions(+) + +--- a/sound/soc/amd/yc/acp6x-mach.c ++++ b/sound/soc/amd/yc/acp6x-mach.c +@@ -245,6 +245,13 @@ static const struct dmi_system_id yc_acp + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), ++ DMI_MATCH(DMI_PRODUCT_NAME, "83AS"), ++ } ++ }, ++ { ++ .driver_data = &acp6x_card, ++ .matches = { ++ DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "82UG"), + } + }, diff --git a/queue-6.1/can-j1939-fix-uaf-in-j1939_sk_match_filter-during-setsockopt-so_j1939_filter.patch b/queue-6.1/can-j1939-fix-uaf-in-j1939_sk_match_filter-during-setsockopt-so_j1939_filter.patch new file mode 100644 index 00000000000..f740f983827 --- /dev/null +++ b/queue-6.1/can-j1939-fix-uaf-in-j1939_sk_match_filter-during-setsockopt-so_j1939_filter.patch @@ -0,0 +1,194 @@ +From efe7cf828039aedb297c1f9920b638fffee6aabc Mon Sep 17 00:00:00 2001 +From: Oleksij Rempel +Date: Fri, 20 Oct 2023 15:38:14 +0200 +Subject: can: j1939: Fix UAF in j1939_sk_match_filter during setsockopt(SO_J1939_FILTER) + +From: Oleksij Rempel + +commit efe7cf828039aedb297c1f9920b638fffee6aabc upstream. + +Lock jsk->sk to prevent UAF when setsockopt(..., SO_J1939_FILTER, ...) +modifies jsk->filters while receiving packets. + +Following trace was seen on affected system: + ================================================================== + BUG: KASAN: slab-use-after-free in j1939_sk_recv_match_one+0x1af/0x2d0 [can_j1939] + Read of size 4 at addr ffff888012144014 by task j1939/350 + + CPU: 0 PID: 350 Comm: j1939 Tainted: G W OE 6.5.0-rc5 #1 + Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 + Call Trace: + print_report+0xd3/0x620 + ? kasan_complete_mode_report_info+0x7d/0x200 + ? j1939_sk_recv_match_one+0x1af/0x2d0 [can_j1939] + kasan_report+0xc2/0x100 + ? j1939_sk_recv_match_one+0x1af/0x2d0 [can_j1939] + __asan_load4+0x84/0xb0 + j1939_sk_recv_match_one+0x1af/0x2d0 [can_j1939] + j1939_sk_recv+0x20b/0x320 [can_j1939] + ? __kasan_check_write+0x18/0x20 + ? __pfx_j1939_sk_recv+0x10/0x10 [can_j1939] + ? j1939_simple_recv+0x69/0x280 [can_j1939] + ? j1939_ac_recv+0x5e/0x310 [can_j1939] + j1939_can_recv+0x43f/0x580 [can_j1939] + ? __pfx_j1939_can_recv+0x10/0x10 [can_j1939] + ? raw_rcv+0x42/0x3c0 [can_raw] + ? __pfx_j1939_can_recv+0x10/0x10 [can_j1939] + can_rcv_filter+0x11f/0x350 [can] + can_receive+0x12f/0x190 [can] + ? __pfx_can_rcv+0x10/0x10 [can] + can_rcv+0xdd/0x130 [can] + ? __pfx_can_rcv+0x10/0x10 [can] + __netif_receive_skb_one_core+0x13d/0x150 + ? __pfx___netif_receive_skb_one_core+0x10/0x10 + ? __kasan_check_write+0x18/0x20 + ? _raw_spin_lock_irq+0x8c/0xe0 + __netif_receive_skb+0x23/0xb0 + process_backlog+0x107/0x260 + __napi_poll+0x69/0x310 + net_rx_action+0x2a1/0x580 + ? __pfx_net_rx_action+0x10/0x10 + ? __pfx__raw_spin_lock+0x10/0x10 + ? handle_irq_event+0x7d/0xa0 + __do_softirq+0xf3/0x3f8 + do_softirq+0x53/0x80 + + + __local_bh_enable_ip+0x6e/0x70 + netif_rx+0x16b/0x180 + can_send+0x32b/0x520 [can] + ? __pfx_can_send+0x10/0x10 [can] + ? __check_object_size+0x299/0x410 + raw_sendmsg+0x572/0x6d0 [can_raw] + ? __pfx_raw_sendmsg+0x10/0x10 [can_raw] + ? apparmor_socket_sendmsg+0x2f/0x40 + ? __pfx_raw_sendmsg+0x10/0x10 [can_raw] + sock_sendmsg+0xef/0x100 + sock_write_iter+0x162/0x220 + ? __pfx_sock_write_iter+0x10/0x10 + ? __rtnl_unlock+0x47/0x80 + ? security_file_permission+0x54/0x320 + vfs_write+0x6ba/0x750 + ? __pfx_vfs_write+0x10/0x10 + ? __fget_light+0x1ca/0x1f0 + ? __rcu_read_unlock+0x5b/0x280 + ksys_write+0x143/0x170 + ? __pfx_ksys_write+0x10/0x10 + ? __kasan_check_read+0x15/0x20 + ? fpregs_assert_state_consistent+0x62/0x70 + __x64_sys_write+0x47/0x60 + do_syscall_64+0x60/0x90 + ? do_syscall_64+0x6d/0x90 + ? irqentry_exit+0x3f/0x50 + ? exc_page_fault+0x79/0xf0 + entry_SYSCALL_64_after_hwframe+0x6e/0xd8 + + Allocated by task 348: + kasan_save_stack+0x2a/0x50 + kasan_set_track+0x29/0x40 + kasan_save_alloc_info+0x1f/0x30 + __kasan_kmalloc+0xb5/0xc0 + __kmalloc_node_track_caller+0x67/0x160 + j1939_sk_setsockopt+0x284/0x450 [can_j1939] + __sys_setsockopt+0x15c/0x2f0 + __x64_sys_setsockopt+0x6b/0x80 + do_syscall_64+0x60/0x90 + entry_SYSCALL_64_after_hwframe+0x6e/0xd8 + + Freed by task 349: + kasan_save_stack+0x2a/0x50 + kasan_set_track+0x29/0x40 + kasan_save_free_info+0x2f/0x50 + __kasan_slab_free+0x12e/0x1c0 + __kmem_cache_free+0x1b9/0x380 + kfree+0x7a/0x120 + j1939_sk_setsockopt+0x3b2/0x450 [can_j1939] + __sys_setsockopt+0x15c/0x2f0 + __x64_sys_setsockopt+0x6b/0x80 + do_syscall_64+0x60/0x90 + entry_SYSCALL_64_after_hwframe+0x6e/0xd8 + +Fixes: 9d71dd0c70099 ("can: add support of SAE J1939 protocol") +Reported-by: Sili Luo +Suggested-by: Sili Luo +Acked-by: Oleksij Rempel +Cc: stable@vger.kernel.org +Signed-off-by: Oleksij Rempel +Link: https://lore.kernel.org/all/20231020133814.383996-1-o.rempel@pengutronix.de +Signed-off-by: Marc Kleine-Budde +Signed-off-by: Greg Kroah-Hartman +--- + net/can/j1939/j1939-priv.h | 1 + + net/can/j1939/socket.c | 22 ++++++++++++++++++---- + 2 files changed, 19 insertions(+), 4 deletions(-) + +--- a/net/can/j1939/j1939-priv.h ++++ b/net/can/j1939/j1939-priv.h +@@ -301,6 +301,7 @@ struct j1939_sock { + + int ifindex; + struct j1939_addr addr; ++ spinlock_t filters_lock; + struct j1939_filter *filters; + int nfilters; + pgn_t pgn_rx_filter; +--- a/net/can/j1939/socket.c ++++ b/net/can/j1939/socket.c +@@ -262,12 +262,17 @@ static bool j1939_sk_match_dst(struct j1 + static bool j1939_sk_match_filter(struct j1939_sock *jsk, + const struct j1939_sk_buff_cb *skcb) + { +- const struct j1939_filter *f = jsk->filters; +- int nfilter = jsk->nfilters; ++ const struct j1939_filter *f; ++ int nfilter; ++ ++ spin_lock_bh(&jsk->filters_lock); ++ ++ f = jsk->filters; ++ nfilter = jsk->nfilters; + + if (!nfilter) + /* receive all when no filters are assigned */ +- return true; ++ goto filter_match_found; + + for (; nfilter; ++f, --nfilter) { + if ((skcb->addr.pgn & f->pgn_mask) != f->pgn) +@@ -276,9 +281,15 @@ static bool j1939_sk_match_filter(struct + continue; + if ((skcb->addr.src_name & f->name_mask) != f->name) + continue; +- return true; ++ goto filter_match_found; + } ++ ++ spin_unlock_bh(&jsk->filters_lock); + return false; ++ ++filter_match_found: ++ spin_unlock_bh(&jsk->filters_lock); ++ return true; + } + + static bool j1939_sk_recv_match_one(struct j1939_sock *jsk, +@@ -401,6 +412,7 @@ static int j1939_sk_init(struct sock *sk + atomic_set(&jsk->skb_pending, 0); + spin_lock_init(&jsk->sk_session_queue_lock); + INIT_LIST_HEAD(&jsk->sk_session_queue); ++ spin_lock_init(&jsk->filters_lock); + + /* j1939_sk_sock_destruct() depends on SOCK_RCU_FREE flag */ + sock_set_flag(sk, SOCK_RCU_FREE); +@@ -703,9 +715,11 @@ static int j1939_sk_setsockopt(struct so + } + + lock_sock(&jsk->sk); ++ spin_lock_bh(&jsk->filters_lock); + ofilters = jsk->filters; + jsk->filters = filters; + jsk->nfilters = count; ++ spin_unlock_bh(&jsk->filters_lock); + release_sock(&jsk->sk); + kfree(ofilters); + return 0; diff --git a/queue-6.1/can-j1939-prevent-deadlock-by-changing-j1939_socks_lock-to-rwlock.patch b/queue-6.1/can-j1939-prevent-deadlock-by-changing-j1939_socks_lock-to-rwlock.patch new file mode 100644 index 00000000000..d3cab9af053 --- /dev/null +++ b/queue-6.1/can-j1939-prevent-deadlock-by-changing-j1939_socks_lock-to-rwlock.patch @@ -0,0 +1,153 @@ +From 6cdedc18ba7b9dacc36466e27e3267d201948c8d Mon Sep 17 00:00:00 2001 +From: Ziqi Zhao +Date: Fri, 21 Jul 2023 09:22:26 -0700 +Subject: can: j1939: prevent deadlock by changing j1939_socks_lock to rwlock + +From: Ziqi Zhao + +commit 6cdedc18ba7b9dacc36466e27e3267d201948c8d upstream. + +The following 3 locks would race against each other, causing the +deadlock situation in the Syzbot bug report: + +- j1939_socks_lock +- active_session_list_lock +- sk_session_queue_lock + +A reasonable fix is to change j1939_socks_lock to an rwlock, since in +the rare situations where a write lock is required for the linked list +that j1939_socks_lock is protecting, the code does not attempt to +acquire any more locks. This would break the circular lock dependency, +where, for example, the current thread already locks j1939_socks_lock +and attempts to acquire sk_session_queue_lock, and at the same time, +another thread attempts to acquire j1939_socks_lock while holding +sk_session_queue_lock. + +NOTE: This patch along does not fix the unregister_netdevice bug +reported by Syzbot; instead, it solves a deadlock situation to prepare +for one or more further patches to actually fix the Syzbot bug, which +appears to be a reference counting problem within the j1939 codebase. + +Reported-by: +Signed-off-by: Ziqi Zhao +Reviewed-by: Oleksij Rempel +Acked-by: Oleksij Rempel +Link: https://lore.kernel.org/all/20230721162226.8639-1-astrajoan@yahoo.com +[mkl: remove unrelated newline change] +Cc: stable@vger.kernel.org +Signed-off-by: Marc Kleine-Budde +Signed-off-by: Greg Kroah-Hartman +--- + net/can/j1939/j1939-priv.h | 2 +- + net/can/j1939/main.c | 2 +- + net/can/j1939/socket.c | 24 ++++++++++++------------ + 3 files changed, 14 insertions(+), 14 deletions(-) + +--- a/net/can/j1939/j1939-priv.h ++++ b/net/can/j1939/j1939-priv.h +@@ -86,7 +86,7 @@ struct j1939_priv { + unsigned int tp_max_packet_size; + + /* lock for j1939_socks list */ +- spinlock_t j1939_socks_lock; ++ rwlock_t j1939_socks_lock; + struct list_head j1939_socks; + + struct kref rx_kref; +--- a/net/can/j1939/main.c ++++ b/net/can/j1939/main.c +@@ -274,7 +274,7 @@ struct j1939_priv *j1939_netdev_start(st + return ERR_PTR(-ENOMEM); + + j1939_tp_init(priv); +- spin_lock_init(&priv->j1939_socks_lock); ++ rwlock_init(&priv->j1939_socks_lock); + INIT_LIST_HEAD(&priv->j1939_socks); + + mutex_lock(&j1939_netdev_lock); +--- a/net/can/j1939/socket.c ++++ b/net/can/j1939/socket.c +@@ -80,16 +80,16 @@ static void j1939_jsk_add(struct j1939_p + jsk->state |= J1939_SOCK_BOUND; + j1939_priv_get(priv); + +- spin_lock_bh(&priv->j1939_socks_lock); ++ write_lock_bh(&priv->j1939_socks_lock); + list_add_tail(&jsk->list, &priv->j1939_socks); +- spin_unlock_bh(&priv->j1939_socks_lock); ++ write_unlock_bh(&priv->j1939_socks_lock); + } + + static void j1939_jsk_del(struct j1939_priv *priv, struct j1939_sock *jsk) + { +- spin_lock_bh(&priv->j1939_socks_lock); ++ write_lock_bh(&priv->j1939_socks_lock); + list_del_init(&jsk->list); +- spin_unlock_bh(&priv->j1939_socks_lock); ++ write_unlock_bh(&priv->j1939_socks_lock); + + j1939_priv_put(priv); + jsk->state &= ~J1939_SOCK_BOUND; +@@ -329,13 +329,13 @@ bool j1939_sk_recv_match(struct j1939_pr + struct j1939_sock *jsk; + bool match = false; + +- spin_lock_bh(&priv->j1939_socks_lock); ++ read_lock_bh(&priv->j1939_socks_lock); + list_for_each_entry(jsk, &priv->j1939_socks, list) { + match = j1939_sk_recv_match_one(jsk, skcb); + if (match) + break; + } +- spin_unlock_bh(&priv->j1939_socks_lock); ++ read_unlock_bh(&priv->j1939_socks_lock); + + return match; + } +@@ -344,11 +344,11 @@ void j1939_sk_recv(struct j1939_priv *pr + { + struct j1939_sock *jsk; + +- spin_lock_bh(&priv->j1939_socks_lock); ++ read_lock_bh(&priv->j1939_socks_lock); + list_for_each_entry(jsk, &priv->j1939_socks, list) { + j1939_sk_recv_one(jsk, skb); + } +- spin_unlock_bh(&priv->j1939_socks_lock); ++ read_unlock_bh(&priv->j1939_socks_lock); + } + + static void j1939_sk_sock_destruct(struct sock *sk) +@@ -1080,12 +1080,12 @@ void j1939_sk_errqueue(struct j1939_sess + } + + /* spread RX notifications to all sockets subscribed to this session */ +- spin_lock_bh(&priv->j1939_socks_lock); ++ read_lock_bh(&priv->j1939_socks_lock); + list_for_each_entry(jsk, &priv->j1939_socks, list) { + if (j1939_sk_recv_match_one(jsk, &session->skcb)) + __j1939_sk_errqueue(session, &jsk->sk, type); + } +- spin_unlock_bh(&priv->j1939_socks_lock); ++ read_unlock_bh(&priv->j1939_socks_lock); + }; + + void j1939_sk_send_loop_abort(struct sock *sk, int err) +@@ -1273,7 +1273,7 @@ void j1939_sk_netdev_event_netdown(struc + struct j1939_sock *jsk; + int error_code = ENETDOWN; + +- spin_lock_bh(&priv->j1939_socks_lock); ++ read_lock_bh(&priv->j1939_socks_lock); + list_for_each_entry(jsk, &priv->j1939_socks, list) { + jsk->sk.sk_err = error_code; + if (!sock_flag(&jsk->sk, SOCK_DEAD)) +@@ -1281,7 +1281,7 @@ void j1939_sk_netdev_event_netdown(struc + + j1939_sk_queue_drop_all(priv, jsk, error_code); + } +- spin_unlock_bh(&priv->j1939_socks_lock); ++ read_unlock_bh(&priv->j1939_socks_lock); + } + + static int j1939_sk_no_ioctlcmd(struct socket *sock, unsigned int cmd, diff --git a/queue-6.1/can-netlink-fix-tdco-calculation-using-the-old-data-bittiming.patch b/queue-6.1/can-netlink-fix-tdco-calculation-using-the-old-data-bittiming.patch new file mode 100644 index 00000000000..4c266489632 --- /dev/null +++ b/queue-6.1/can-netlink-fix-tdco-calculation-using-the-old-data-bittiming.patch @@ -0,0 +1,35 @@ +From 2aa0a5e65eae27dbd96faca92c84ecbf6f492d42 Mon Sep 17 00:00:00 2001 +From: Maxime Jayat +Date: Mon, 6 Nov 2023 19:01:58 +0100 +Subject: can: netlink: Fix TDCO calculation using the old data bittiming + +From: Maxime Jayat + +commit 2aa0a5e65eae27dbd96faca92c84ecbf6f492d42 upstream. + +The TDCO calculation was done using the currently applied data bittiming, +instead of the newly computed data bittiming, which means that the TDCO +had an invalid value unless setting the same data bittiming twice. + +Fixes: d99755f71a80 ("can: netlink: add interface for CAN-FD Transmitter Delay Compensation (TDC)") +Signed-off-by: Maxime Jayat +Reviewed-by: Vincent Mailhol +Link: https://lore.kernel.org/all/40579c18-63c0-43a4-8d4c-f3a6c1c0b417@munic.io +Cc: stable@vger.kernel.org +Signed-off-by: Marc Kleine-Budde +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/can/dev/netlink.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/net/can/dev/netlink.c ++++ b/drivers/net/can/dev/netlink.c +@@ -311,7 +311,7 @@ static int can_changelink(struct net_dev + /* Neither of TDC parameters nor TDC flags are + * provided: do calculation + */ +- can_calc_tdco(&priv->tdc, priv->tdc_const, &priv->data_bittiming, ++ can_calc_tdco(&priv->tdc, priv->tdc_const, &dbt, + &priv->ctrlmode, priv->ctrlmode_supported); + } /* else: both CAN_CTRLMODE_TDC_{AUTO,MANUAL} are explicitly + * turned off. TDC is disabled: do nothing diff --git a/queue-6.1/ceph-prevent-use-after-free-in-encode_cap_msg.patch b/queue-6.1/ceph-prevent-use-after-free-in-encode_cap_msg.patch new file mode 100644 index 00000000000..03c72bc19f9 --- /dev/null +++ b/queue-6.1/ceph-prevent-use-after-free-in-encode_cap_msg.patch @@ -0,0 +1,53 @@ +From cda4672da1c26835dcbd7aec2bfed954eda9b5ef Mon Sep 17 00:00:00 2001 +From: Rishabh Dave +Date: Thu, 1 Feb 2024 17:07:16 +0530 +Subject: ceph: prevent use-after-free in encode_cap_msg() + +From: Rishabh Dave + +commit cda4672da1c26835dcbd7aec2bfed954eda9b5ef upstream. + +In fs/ceph/caps.c, in encode_cap_msg(), "use after free" error was +caught by KASAN at this line - 'ceph_buffer_get(arg->xattr_buf);'. This +implies before the refcount could be increment here, it was freed. + +In same file, in "handle_cap_grant()" refcount is decremented by this +line - 'ceph_buffer_put(ci->i_xattrs.blob);'. It appears that a race +occurred and resource was freed by the latter line before the former +line could increment it. + +encode_cap_msg() is called by __send_cap() and __send_cap() is called by +ceph_check_caps() after calling __prep_cap(). __prep_cap() is where +arg->xattr_buf is assigned to ci->i_xattrs.blob. This is the spot where +the refcount must be increased to prevent "use after free" error. + +Cc: stable@vger.kernel.org +Link: https://tracker.ceph.com/issues/59259 +Signed-off-by: Rishabh Dave +Reviewed-by: Jeff Layton +Reviewed-by: Xiubo Li +Signed-off-by: Ilya Dryomov +Signed-off-by: Greg Kroah-Hartman +--- + fs/ceph/caps.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +--- a/fs/ceph/caps.c ++++ b/fs/ceph/caps.c +@@ -1391,7 +1391,7 @@ static void __prep_cap(struct cap_msg_ar + if (flushing & CEPH_CAP_XATTR_EXCL) { + arg->old_xattr_buf = __ceph_build_xattrs_blob(ci); + arg->xattr_version = ci->i_xattrs.version; +- arg->xattr_buf = ci->i_xattrs.blob; ++ arg->xattr_buf = ceph_buffer_get(ci->i_xattrs.blob); + } else { + arg->xattr_buf = NULL; + arg->old_xattr_buf = NULL; +@@ -1457,6 +1457,7 @@ static void __send_cap(struct cap_msg_ar + encode_cap_msg(msg, arg); + ceph_con_send(&arg->session->s_con, msg); + ceph_buffer_put(arg->old_xattr_buf); ++ ceph_buffer_put(arg->xattr_buf); + if (arg->wake) + wake_up_all(&ci->i_cap_wq); + } diff --git a/queue-6.1/crypto-ccp-fix-null-pointer-dereference-in-__sev_platform_shutdown_locked.patch b/queue-6.1/crypto-ccp-fix-null-pointer-dereference-in-__sev_platform_shutdown_locked.patch new file mode 100644 index 00000000000..43363b07a5f --- /dev/null +++ b/queue-6.1/crypto-ccp-fix-null-pointer-dereference-in-__sev_platform_shutdown_locked.patch @@ -0,0 +1,118 @@ +From ccb88e9549e7cfd8bcd511c538f437e20026e983 Mon Sep 17 00:00:00 2001 +From: Kim Phillips +Date: Thu, 25 Jan 2024 17:12:53 -0600 +Subject: crypto: ccp - Fix null pointer dereference in __sev_platform_shutdown_locked + +From: Kim Phillips + +commit ccb88e9549e7cfd8bcd511c538f437e20026e983 upstream. + +The SEV platform device can be shutdown with a null psp_master, +e.g., using DEBUG_TEST_DRIVER_REMOVE. Found using KASAN: + +[ 137.148210] ccp 0000:23:00.1: enabling device (0000 -> 0002) +[ 137.162647] ccp 0000:23:00.1: no command queues available +[ 137.170598] ccp 0000:23:00.1: sev enabled +[ 137.174645] ccp 0000:23:00.1: psp enabled +[ 137.178890] general protection fault, probably for non-canonical address 0xdffffc000000001e: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC KASAN NOPTI +[ 137.182693] KASAN: null-ptr-deref in range [0x00000000000000f0-0x00000000000000f7] +[ 137.182693] CPU: 93 PID: 1 Comm: swapper/0 Not tainted 6.8.0-rc1+ #311 +[ 137.182693] RIP: 0010:__sev_platform_shutdown_locked+0x51/0x180 +[ 137.182693] Code: 08 80 3c 08 00 0f 85 0e 01 00 00 48 8b 1d 67 b6 01 08 48 b8 00 00 00 00 00 fc ff df 48 8d bb f0 00 00 00 48 89 f9 48 c1 e9 03 <80> 3c 01 00 0f 85 fe 00 00 00 48 8b 9b f0 00 00 00 48 85 db 74 2c +[ 137.182693] RSP: 0018:ffffc900000cf9b0 EFLAGS: 00010216 +[ 137.182693] RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 000000000000001e +[ 137.182693] RDX: 0000000000000000 RSI: 0000000000000008 RDI: 00000000000000f0 +[ 137.182693] RBP: ffffc900000cf9c8 R08: 0000000000000000 R09: fffffbfff58f5a66 +[ 137.182693] R10: ffffc900000cf9c8 R11: ffffffffac7ad32f R12: ffff8881e5052c28 +[ 137.182693] R13: ffff8881e5052c28 R14: ffff8881758e43e8 R15: ffffffffac64abf8 +[ 137.182693] FS: 0000000000000000(0000) GS:ffff889de7000000(0000) knlGS:0000000000000000 +[ 137.182693] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +[ 137.182693] CR2: 0000000000000000 CR3: 0000001cf7c7e000 CR4: 0000000000350ef0 +[ 137.182693] Call Trace: +[ 137.182693] +[ 137.182693] ? show_regs+0x6c/0x80 +[ 137.182693] ? __die_body+0x24/0x70 +[ 137.182693] ? die_addr+0x4b/0x80 +[ 137.182693] ? exc_general_protection+0x126/0x230 +[ 137.182693] ? asm_exc_general_protection+0x2b/0x30 +[ 137.182693] ? __sev_platform_shutdown_locked+0x51/0x180 +[ 137.182693] sev_firmware_shutdown.isra.0+0x1e/0x80 +[ 137.182693] sev_dev_destroy+0x49/0x100 +[ 137.182693] psp_dev_destroy+0x47/0xb0 +[ 137.182693] sp_destroy+0xbb/0x240 +[ 137.182693] sp_pci_remove+0x45/0x60 +[ 137.182693] pci_device_remove+0xaa/0x1d0 +[ 137.182693] device_remove+0xc7/0x170 +[ 137.182693] really_probe+0x374/0xbe0 +[ 137.182693] ? srso_return_thunk+0x5/0x5f +[ 137.182693] __driver_probe_device+0x199/0x460 +[ 137.182693] driver_probe_device+0x4e/0xd0 +[ 137.182693] __driver_attach+0x191/0x3d0 +[ 137.182693] ? __pfx___driver_attach+0x10/0x10 +[ 137.182693] bus_for_each_dev+0x100/0x190 +[ 137.182693] ? __pfx_bus_for_each_dev+0x10/0x10 +[ 137.182693] ? __kasan_check_read+0x15/0x20 +[ 137.182693] ? srso_return_thunk+0x5/0x5f +[ 137.182693] ? _raw_spin_unlock+0x27/0x50 +[ 137.182693] driver_attach+0x41/0x60 +[ 137.182693] bus_add_driver+0x2a8/0x580 +[ 137.182693] driver_register+0x141/0x480 +[ 137.182693] __pci_register_driver+0x1d6/0x2a0 +[ 137.182693] ? srso_return_thunk+0x5/0x5f +[ 137.182693] ? esrt_sysfs_init+0x1cd/0x5d0 +[ 137.182693] ? __pfx_sp_mod_init+0x10/0x10 +[ 137.182693] sp_pci_init+0x22/0x30 +[ 137.182693] sp_mod_init+0x14/0x30 +[ 137.182693] ? __pfx_sp_mod_init+0x10/0x10 +[ 137.182693] do_one_initcall+0xd1/0x470 +[ 137.182693] ? __pfx_do_one_initcall+0x10/0x10 +[ 137.182693] ? parameq+0x80/0xf0 +[ 137.182693] ? srso_return_thunk+0x5/0x5f +[ 137.182693] ? __kmalloc+0x3b0/0x4e0 +[ 137.182693] ? kernel_init_freeable+0x92d/0x1050 +[ 137.182693] ? kasan_populate_vmalloc_pte+0x171/0x190 +[ 137.182693] ? srso_return_thunk+0x5/0x5f +[ 137.182693] kernel_init_freeable+0xa64/0x1050 +[ 137.182693] ? __pfx_kernel_init+0x10/0x10 +[ 137.182693] kernel_init+0x24/0x160 +[ 137.182693] ? __switch_to_asm+0x3e/0x70 +[ 137.182693] ret_from_fork+0x40/0x80 +[ 137.182693] ? __pfx_kernel_init+0x10/0x10 +[ 137.182693] ret_from_fork_asm+0x1b/0x30 +[ 137.182693] +[ 137.182693] Modules linked in: +[ 137.538483] ---[ end trace 0000000000000000 ]--- + +Fixes: 1b05ece0c931 ("crypto: ccp - During shutdown, check SEV data pointer before using") +Cc: stable@vger.kernel.org +Reviewed-by: Mario Limonciello +Signed-off-by: Kim Phillips +Reviewed-by: Liam Merwick +Acked-by: John Allen +Signed-off-by: Herbert Xu +Signed-off-by: Greg Kroah-Hartman +--- + drivers/crypto/ccp/sev-dev.c | 10 ++++++++-- + 1 file changed, 8 insertions(+), 2 deletions(-) + +--- a/drivers/crypto/ccp/sev-dev.c ++++ b/drivers/crypto/ccp/sev-dev.c +@@ -515,10 +515,16 @@ EXPORT_SYMBOL_GPL(sev_platform_init); + + static int __sev_platform_shutdown_locked(int *error) + { +- struct sev_device *sev = psp_master->sev_data; ++ struct psp_device *psp = psp_master; ++ struct sev_device *sev; + int ret; + +- if (!sev || sev->state == SEV_STATE_UNINIT) ++ if (!psp || !psp->sev_data) ++ return 0; ++ ++ sev = psp->sev_data; ++ ++ if (sev->state == SEV_STATE_UNINIT) + return 0; + + ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, NULL, error); diff --git a/queue-6.1/exit-wait_task_zombie-kill-the-no-longer-necessary-spin_lock_irq-siglock.patch b/queue-6.1/exit-wait_task_zombie-kill-the-no-longer-necessary-spin_lock_irq-siglock.patch new file mode 100644 index 00000000000..ff9080b0229 --- /dev/null +++ b/queue-6.1/exit-wait_task_zombie-kill-the-no-longer-necessary-spin_lock_irq-siglock.patch @@ -0,0 +1,59 @@ +From c1be35a16b2f1fe21f4f26f9de030ad6eaaf6a25 Mon Sep 17 00:00:00 2001 +From: Oleg Nesterov +Date: Tue, 23 Jan 2024 16:34:00 +0100 +Subject: exit: wait_task_zombie: kill the no longer necessary spin_lock_irq(siglock) + +From: Oleg Nesterov + +commit c1be35a16b2f1fe21f4f26f9de030ad6eaaf6a25 upstream. + +After the recent changes nobody use siglock to read the values protected +by stats_lock, we can kill spin_lock_irq(¤t->sighand->siglock) and +update the comment. + +With this patch only __exit_signal() and thread_group_start_cputime() take +stats_lock under siglock. + +Link: https://lkml.kernel.org/r/20240123153359.GA21866@redhat.com +Signed-off-by: Oleg Nesterov +Signed-off-by: Dylan Hatch +Cc: Eric W. Biederman +Cc: +Signed-off-by: Andrew Morton +Signed-off-by: Greg Kroah-Hartman +--- + kernel/exit.c | 10 +++------- + 1 file changed, 3 insertions(+), 7 deletions(-) + +--- a/kernel/exit.c ++++ b/kernel/exit.c +@@ -1146,17 +1146,14 @@ static int wait_task_zombie(struct wait_ + * and nobody can change them. + * + * psig->stats_lock also protects us from our sub-threads +- * which can reap other children at the same time. Until +- * we change k_getrusage()-like users to rely on this lock +- * we have to take ->siglock as well. ++ * which can reap other children at the same time. + * + * We use thread_group_cputime_adjusted() to get times for + * the thread group, which consolidates times for all threads + * in the group including the group leader. + */ + thread_group_cputime_adjusted(p, &tgutime, &tgstime); +- spin_lock_irq(¤t->sighand->siglock); +- write_seqlock(&psig->stats_lock); ++ write_seqlock_irq(&psig->stats_lock); + psig->cutime += tgutime + sig->cutime; + psig->cstime += tgstime + sig->cstime; + psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime; +@@ -1179,8 +1176,7 @@ static int wait_task_zombie(struct wait_ + psig->cmaxrss = maxrss; + task_io_accounting_add(&psig->ioac, &p->ioac); + task_io_accounting_add(&psig->ioac, &sig->ioac); +- write_sequnlock(&psig->stats_lock); +- spin_unlock_irq(¤t->sighand->siglock); ++ write_sequnlock_irq(&psig->stats_lock); + } + + if (wo->wo_rusage) diff --git a/queue-6.1/fs-hugetlb-fix-null-pointer-dereference-in-hugetlbs_fill_super.patch b/queue-6.1/fs-hugetlb-fix-null-pointer-dereference-in-hugetlbs_fill_super.patch new file mode 100644 index 00000000000..25ad557384f --- /dev/null +++ b/queue-6.1/fs-hugetlb-fix-null-pointer-dereference-in-hugetlbs_fill_super.patch @@ -0,0 +1,156 @@ +From 79d72c68c58784a3e1cd2378669d51bfd0cb7498 Mon Sep 17 00:00:00 2001 +From: Oscar Salvador +Date: Tue, 30 Jan 2024 22:04:18 +0100 +Subject: fs,hugetlb: fix NULL pointer dereference in hugetlbs_fill_super + +From: Oscar Salvador + +commit 79d72c68c58784a3e1cd2378669d51bfd0cb7498 upstream. + +When configuring a hugetlb filesystem via the fsconfig() syscall, there is +a possible NULL dereference in hugetlbfs_fill_super() caused by assigning +NULL to ctx->hstate in hugetlbfs_parse_param() when the requested pagesize +is non valid. + +E.g: Taking the following steps: + + fd = fsopen("hugetlbfs", FSOPEN_CLOEXEC); + fsconfig(fd, FSCONFIG_SET_STRING, "pagesize", "1024", 0); + fsconfig(fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); + +Given that the requested "pagesize" is invalid, ctxt->hstate will be replaced +with NULL, losing its previous value, and we will print an error: + + ... + ... + case Opt_pagesize: + ps = memparse(param->string, &rest); + ctx->hstate = h; + if (!ctx->hstate) { + pr_err("Unsupported page size %lu MB\n", ps / SZ_1M); + return -EINVAL; + } + return 0; + ... + ... + +This is a problem because later on, we will dereference ctxt->hstate in +hugetlbfs_fill_super() + + ... + ... + sb->s_blocksize = huge_page_size(ctx->hstate); + ... + ... + +Causing below Oops. + +Fix this by replacing cxt->hstate value only when then pagesize is known +to be valid. + + kernel: hugetlbfs: Unsupported page size 0 MB + kernel: BUG: kernel NULL pointer dereference, address: 0000000000000028 + kernel: #PF: supervisor read access in kernel mode + kernel: #PF: error_code(0x0000) - not-present page + kernel: PGD 800000010f66c067 P4D 800000010f66c067 PUD 1b22f8067 PMD 0 + kernel: Oops: 0000 [#1] PREEMPT SMP PTI + kernel: CPU: 4 PID: 5659 Comm: syscall Tainted: G E 6.8.0-rc2-default+ #22 5a47c3fef76212addcc6eb71344aabc35190ae8f + kernel: Hardware name: Intel Corp. GROVEPORT/GROVEPORT, BIOS GVPRCRB1.86B.0016.D04.1705030402 05/03/2017 + kernel: RIP: 0010:hugetlbfs_fill_super+0xb4/0x1a0 + kernel: Code: 48 8b 3b e8 3e c6 ed ff 48 85 c0 48 89 45 20 0f 84 d6 00 00 00 48 b8 ff ff ff ff ff ff ff 7f 4c 89 e7 49 89 44 24 20 48 8b 03 <8b> 48 28 b8 00 10 00 00 48 d3 e0 49 89 44 24 18 48 8b 03 8b 40 28 + kernel: RSP: 0018:ffffbe9960fcbd48 EFLAGS: 00010246 + kernel: RAX: 0000000000000000 RBX: ffff9af5272ae780 RCX: 0000000000372004 + kernel: RDX: ffffffffffffffff RSI: ffffffffffffffff RDI: ffff9af555e9b000 + kernel: RBP: ffff9af52ee66b00 R08: 0000000000000040 R09: 0000000000370004 + kernel: R10: ffffbe9960fcbd48 R11: 0000000000000040 R12: ffff9af555e9b000 + kernel: R13: ffffffffa66b86c0 R14: ffff9af507d2f400 R15: ffff9af507d2f400 + kernel: FS: 00007ffbc0ba4740(0000) GS:ffff9b0bd7000000(0000) knlGS:0000000000000000 + kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 + kernel: CR2: 0000000000000028 CR3: 00000001b1ee0000 CR4: 00000000001506f0 + kernel: Call Trace: + kernel: + kernel: ? __die_body+0x1a/0x60 + kernel: ? page_fault_oops+0x16f/0x4a0 + kernel: ? search_bpf_extables+0x65/0x70 + kernel: ? fixup_exception+0x22/0x310 + kernel: ? exc_page_fault+0x69/0x150 + kernel: ? asm_exc_page_fault+0x22/0x30 + kernel: ? __pfx_hugetlbfs_fill_super+0x10/0x10 + kernel: ? hugetlbfs_fill_super+0xb4/0x1a0 + kernel: ? hugetlbfs_fill_super+0x28/0x1a0 + kernel: ? __pfx_hugetlbfs_fill_super+0x10/0x10 + kernel: vfs_get_super+0x40/0xa0 + kernel: ? __pfx_bpf_lsm_capable+0x10/0x10 + kernel: vfs_get_tree+0x25/0xd0 + kernel: vfs_cmd_create+0x64/0xe0 + kernel: __x64_sys_fsconfig+0x395/0x410 + kernel: do_syscall_64+0x80/0x160 + kernel: ? syscall_exit_to_user_mode+0x82/0x240 + kernel: ? do_syscall_64+0x8d/0x160 + kernel: ? syscall_exit_to_user_mode+0x82/0x240 + kernel: ? do_syscall_64+0x8d/0x160 + kernel: ? exc_page_fault+0x69/0x150 + kernel: entry_SYSCALL_64_after_hwframe+0x6e/0x76 + kernel: RIP: 0033:0x7ffbc0cb87c9 + kernel: Code: 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 97 96 0d 00 f7 d8 64 89 01 48 + kernel: RSP: 002b:00007ffc29d2f388 EFLAGS: 00000206 ORIG_RAX: 00000000000001af + kernel: RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007ffbc0cb87c9 + kernel: RDX: 0000000000000000 RSI: 0000000000000006 RDI: 0000000000000003 + kernel: RBP: 00007ffc29d2f3b0 R08: 0000000000000000 R09: 0000000000000000 + kernel: R10: 0000000000000000 R11: 0000000000000206 R12: 0000000000000000 + kernel: R13: 00007ffc29d2f4c0 R14: 0000000000000000 R15: 0000000000000000 + kernel: + kernel: Modules linked in: rpcsec_gss_krb5(E) auth_rpcgss(E) nfsv4(E) dns_resolver(E) nfs(E) lockd(E) grace(E) sunrpc(E) netfs(E) af_packet(E) bridge(E) stp(E) llc(E) iscsi_ibft(E) iscsi_boot_sysfs(E) intel_rapl_msr(E) intel_rapl_common(E) iTCO_wdt(E) intel_pmc_bxt(E) sb_edac(E) iTCO_vendor_support(E) x86_pkg_temp_thermal(E) intel_powerclamp(E) coretemp(E) kvm_intel(E) rfkill(E) ipmi_ssif(E) kvm(E) acpi_ipmi(E) irqbypass(E) pcspkr(E) igb(E) ipmi_si(E) mei_me(E) i2c_i801(E) joydev(E) intel_pch_thermal(E) i2c_smbus(E) dca(E) lpc_ich(E) mei(E) ipmi_devintf(E) ipmi_msghandler(E) acpi_pad(E) tiny_power_button(E) button(E) fuse(E) efi_pstore(E) configfs(E) ip_tables(E) x_tables(E) ext4(E) mbcache(E) jbd2(E) hid_generic(E) usbhid(E) sd_mod(E) t10_pi(E) crct10dif_pclmul(E) crc32_pclmul(E) crc32c_intel(E) polyval_clmulni(E) ahci(E) xhci_pci(E) polyval_generic(E) gf128mul(E) ghash_clmulni_intel(E) sha512_ssse3(E) sha256_ssse3(E) xhci_pci_renesas(E) libahci(E) ehci_pci(E) sha1_ssse3(E) xhci_hcd(E) ehci_hcd(E) libata(E) + kernel: mgag200(E) i2c_algo_bit(E) usbcore(E) wmi(E) sg(E) dm_multipath(E) dm_mod(E) scsi_dh_rdac(E) scsi_dh_emc(E) scsi_dh_alua(E) scsi_mod(E) scsi_common(E) aesni_intel(E) crypto_simd(E) cryptd(E) + kernel: Unloaded tainted modules: acpi_cpufreq(E):1 fjes(E):1 + kernel: CR2: 0000000000000028 + kernel: ---[ end trace 0000000000000000 ]--- + kernel: RIP: 0010:hugetlbfs_fill_super+0xb4/0x1a0 + kernel: Code: 48 8b 3b e8 3e c6 ed ff 48 85 c0 48 89 45 20 0f 84 d6 00 00 00 48 b8 ff ff ff ff ff ff ff 7f 4c 89 e7 49 89 44 24 20 48 8b 03 <8b> 48 28 b8 00 10 00 00 48 d3 e0 49 89 44 24 18 48 8b 03 8b 40 28 + kernel: RSP: 0018:ffffbe9960fcbd48 EFLAGS: 00010246 + kernel: RAX: 0000000000000000 RBX: ffff9af5272ae780 RCX: 0000000000372004 + kernel: RDX: ffffffffffffffff RSI: ffffffffffffffff RDI: ffff9af555e9b000 + kernel: RBP: ffff9af52ee66b00 R08: 0000000000000040 R09: 0000000000370004 + kernel: R10: ffffbe9960fcbd48 R11: 0000000000000040 R12: ffff9af555e9b000 + kernel: R13: ffffffffa66b86c0 R14: ffff9af507d2f400 R15: ffff9af507d2f400 + kernel: FS: 00007ffbc0ba4740(0000) GS:ffff9b0bd7000000(0000) knlGS:0000000000000000 + kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 + kernel: CR2: 0000000000000028 CR3: 00000001b1ee0000 CR4: 00000000001506f0 + +Link: https://lkml.kernel.org/r/20240130210418.3771-1-osalvador@suse.de +Fixes: 32021982a324 ("hugetlbfs: Convert to fs_context") +Signed-off-by: Michal Hocko +Signed-off-by: Oscar Salvador +Acked-by: Muchun Song +Cc: +Signed-off-by: Andrew Morton +Signed-off-by: Greg Kroah-Hartman +--- + fs/hugetlbfs/inode.c | 6 ++++-- + 1 file changed, 4 insertions(+), 2 deletions(-) + +--- a/fs/hugetlbfs/inode.c ++++ b/fs/hugetlbfs/inode.c +@@ -1350,6 +1350,7 @@ static int hugetlbfs_parse_param(struct + { + struct hugetlbfs_fs_context *ctx = fc->fs_private; + struct fs_parse_result result; ++ struct hstate *h; + char *rest; + unsigned long ps; + int opt; +@@ -1394,11 +1395,12 @@ static int hugetlbfs_parse_param(struct + + case Opt_pagesize: + ps = memparse(param->string, &rest); +- ctx->hstate = size_to_hstate(ps); +- if (!ctx->hstate) { ++ h = size_to_hstate(ps); ++ if (!h) { + pr_err("Unsupported page size %lu MB\n", ps / SZ_1M); + return -EINVAL; + } ++ ctx->hstate = h; + return 0; + + case Opt_min_size: diff --git a/queue-6.1/fs-proc-do_task_stat-move-thread_group_cputime_adjusted-outside-of-lock_task_sighand.patch b/queue-6.1/fs-proc-do_task_stat-move-thread_group_cputime_adjusted-outside-of-lock_task_sighand.patch new file mode 100644 index 00000000000..41c88702fff --- /dev/null +++ b/queue-6.1/fs-proc-do_task_stat-move-thread_group_cputime_adjusted-outside-of-lock_task_sighand.patch @@ -0,0 +1,76 @@ +From 60f92acb60a989b14e4b744501a0df0f82ef30a3 Mon Sep 17 00:00:00 2001 +From: Oleg Nesterov +Date: Tue, 23 Jan 2024 16:33:55 +0100 +Subject: fs/proc: do_task_stat: move thread_group_cputime_adjusted() outside of lock_task_sighand() + +From: Oleg Nesterov + +commit 60f92acb60a989b14e4b744501a0df0f82ef30a3 upstream. + +Patch series "fs/proc: do_task_stat: use sig->stats_". + +do_task_stat() has the same problem as getrusage() had before "getrusage: +use sig->stats_lock rather than lock_task_sighand()": a hard lockup. If +NR_CPUS threads call lock_task_sighand() at the same time and the process +has NR_THREADS, spin_lock_irq will spin with irqs disabled O(NR_CPUS * +NR_THREADS) time. + + +This patch (of 3): + +thread_group_cputime() does its own locking, we can safely shift +thread_group_cputime_adjusted() which does another for_each_thread loop +outside of ->siglock protected section. + +Not only this removes for_each_thread() from the critical section with +irqs disabled, this removes another case when stats_lock is taken with +siglock held. We want to remove this dependency, then we can change the +users of stats_lock to not disable irqs. + +Link: https://lkml.kernel.org/r/20240123153313.GA21832@redhat.com +Link: https://lkml.kernel.org/r/20240123153355.GA21854@redhat.com +Signed-off-by: Oleg Nesterov +Signed-off-by: Dylan Hatch +Cc: Eric W. Biederman +Cc: +Signed-off-by: Andrew Morton +Signed-off-by: Greg Kroah-Hartman +--- + fs/proc/array.c | 10 ++++++---- + 1 file changed, 6 insertions(+), 4 deletions(-) + +--- a/fs/proc/array.c ++++ b/fs/proc/array.c +@@ -501,7 +501,7 @@ static int do_task_stat(struct seq_file + + sigemptyset(&sigign); + sigemptyset(&sigcatch); +- cutime = cstime = utime = stime = 0; ++ cutime = cstime = 0; + cgtime = gtime = 0; + + if (lock_task_sighand(task, &flags)) { +@@ -535,7 +535,6 @@ static int do_task_stat(struct seq_file + + min_flt += sig->min_flt; + maj_flt += sig->maj_flt; +- thread_group_cputime_adjusted(task, &utime, &stime); + gtime += sig->gtime; + + if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED)) +@@ -551,10 +550,13 @@ static int do_task_stat(struct seq_file + + if (permitted && (!whole || num_threads < 2)) + wchan = !task_is_running(task); +- if (!whole) { ++ ++ if (whole) { ++ thread_group_cputime_adjusted(task, &utime, &stime); ++ } else { ++ task_cputime_adjusted(task, &utime, &stime); + min_flt = task->min_flt; + maj_flt = task->maj_flt; +- task_cputime_adjusted(task, &utime, &stime); + gtime = task_gtime(task); + } + diff --git a/queue-6.1/fs-relax-mount_setattr-permission-checks.patch b/queue-6.1/fs-relax-mount_setattr-permission-checks.patch new file mode 100644 index 00000000000..82dadfffd1d --- /dev/null +++ b/queue-6.1/fs-relax-mount_setattr-permission-checks.patch @@ -0,0 +1,59 @@ +From 46f5ab762d048dad224436978315cbc2fa79c630 Mon Sep 17 00:00:00 2001 +From: Christian Brauner +Date: Tue, 6 Feb 2024 11:22:09 +0100 +Subject: fs: relax mount_setattr() permission checks + +From: Christian Brauner + +commit 46f5ab762d048dad224436978315cbc2fa79c630 upstream. + +When we added mount_setattr() I added additional checks compared to the +legacy do_reconfigure_mnt() and do_change_type() helpers used by regular +mount(2). If that mount had a parent then verify that the caller and the +mount namespace the mount is attached to match and if not make sure that +it's an anonymous mount. + +The real rootfs falls into neither category. It is neither an anoymous +mount because it is obviously attached to the initial mount namespace +but it also obviously doesn't have a parent mount. So that means legacy +mount(2) allows changing mount properties on the real rootfs but +mount_setattr(2) blocks this. I never thought much about this but of +course someone on this planet of earth changes properties on the real +rootfs as can be seen in [1]. + +Since util-linux finally switched to the new mount api in 2.39 not so +long ago it also relies on mount_setattr() and that surfaced this issue +when Fedora 39 finally switched to it. Fix this. + +Link: https://bugzilla.redhat.com/show_bug.cgi?id=2256843 +Link: https://lore.kernel.org/r/20240206-vfs-mount-rootfs-v1-1-19b335eee133@kernel.org +Reviewed-by: Jan Kara +Reported-by: Karel Zak +Cc: stable@vger.kernel.org # v5.12+ +Signed-off-by: Christian Brauner +Signed-off-by: Greg Kroah-Hartman +--- + fs/namespace.c | 11 ++++++++--- + 1 file changed, 8 insertions(+), 3 deletions(-) + +--- a/fs/namespace.c ++++ b/fs/namespace.c +@@ -4172,10 +4172,15 @@ static int do_mount_setattr(struct path + /* + * If this is an attached mount make sure it's located in the callers + * mount namespace. If it's not don't let the caller interact with it. +- * If this is a detached mount make sure it has an anonymous mount +- * namespace attached to it, i.e. we've created it via OPEN_TREE_CLONE. ++ * ++ * If this mount doesn't have a parent it's most often simply a ++ * detached mount with an anonymous mount namespace. IOW, something ++ * that's simply not attached yet. But there are apparently also users ++ * that do change mount properties on the rootfs itself. That obviously ++ * neither has a parent nor is it a detached mount so we cannot ++ * unconditionally check for detached mounts. + */ +- if (!(mnt_has_parent(mnt) ? check_mnt(mnt) : is_anon_ns(mnt->mnt_ns))) ++ if ((mnt_has_parent(mnt) || !is_anon_ns(mnt->mnt_ns)) && !check_mnt(mnt)) + goto out; + + /* diff --git a/queue-6.1/hv_netvsc-register-vf-in-netvsc_probe-if-net_device_register-missed.patch b/queue-6.1/hv_netvsc-register-vf-in-netvsc_probe-if-net_device_register-missed.patch new file mode 100644 index 00000000000..9a31f7aa2c4 --- /dev/null +++ b/queue-6.1/hv_netvsc-register-vf-in-netvsc_probe-if-net_device_register-missed.patch @@ -0,0 +1,179 @@ +From 9cae43da9867412f8bd09aee5c8a8dc5e8dc3dc2 Mon Sep 17 00:00:00 2001 +From: Shradha Gupta +Date: Thu, 1 Feb 2024 20:40:38 -0800 +Subject: hv_netvsc: Register VF in netvsc_probe if NET_DEVICE_REGISTER missed + +From: Shradha Gupta + +commit 9cae43da9867412f8bd09aee5c8a8dc5e8dc3dc2 upstream. + +If hv_netvsc driver is unloaded and reloaded, the NET_DEVICE_REGISTER +handler cannot perform VF register successfully as the register call +is received before netvsc_probe is finished. This is because we +register register_netdevice_notifier() very early( even before +vmbus_driver_register()). +To fix this, we try to register each such matching VF( if it is visible +as a netdevice) at the end of netvsc_probe. + +Cc: stable@vger.kernel.org +Fixes: 85520856466e ("hv_netvsc: Fix race of register_netdevice_notifier and VF register") +Suggested-by: Dexuan Cui +Signed-off-by: Shradha Gupta +Reviewed-by: Haiyang Zhang +Reviewed-by: Dexuan Cui +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/hyperv/netvsc_drv.c | 82 ++++++++++++++++++++++++++++++---------- + 1 file changed, 62 insertions(+), 20 deletions(-) + +--- a/drivers/net/hyperv/netvsc_drv.c ++++ b/drivers/net/hyperv/netvsc_drv.c +@@ -42,6 +42,10 @@ + #define LINKCHANGE_INT (2 * HZ) + #define VF_TAKEOVER_INT (HZ / 10) + ++/* Macros to define the context of vf registration */ ++#define VF_REG_IN_PROBE 1 ++#define VF_REG_IN_NOTIFIER 2 ++ + static unsigned int ring_size __ro_after_init = 128; + module_param(ring_size, uint, 0444); + MODULE_PARM_DESC(ring_size, "Ring buffer size (# of 4K pages)"); +@@ -2181,7 +2185,7 @@ static rx_handler_result_t netvsc_vf_han + } + + static int netvsc_vf_join(struct net_device *vf_netdev, +- struct net_device *ndev) ++ struct net_device *ndev, int context) + { + struct net_device_context *ndev_ctx = netdev_priv(ndev); + int ret; +@@ -2204,7 +2208,11 @@ static int netvsc_vf_join(struct net_dev + goto upper_link_failed; + } + +- schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT); ++ /* If this registration is called from probe context vf_takeover ++ * is taken care of later in probe itself. ++ */ ++ if (context == VF_REG_IN_NOTIFIER) ++ schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT); + + call_netdevice_notifiers(NETDEV_JOIN, vf_netdev); + +@@ -2342,7 +2350,7 @@ static int netvsc_prepare_bonding(struct + return NOTIFY_DONE; + } + +-static int netvsc_register_vf(struct net_device *vf_netdev) ++static int netvsc_register_vf(struct net_device *vf_netdev, int context) + { + struct net_device_context *net_device_ctx; + struct netvsc_device *netvsc_dev; +@@ -2382,7 +2390,7 @@ static int netvsc_register_vf(struct net + + netdev_info(ndev, "VF registering: %s\n", vf_netdev->name); + +- if (netvsc_vf_join(vf_netdev, ndev) != 0) ++ if (netvsc_vf_join(vf_netdev, ndev, context) != 0) + return NOTIFY_DONE; + + dev_hold(vf_netdev); +@@ -2480,10 +2488,31 @@ static int netvsc_unregister_vf(struct n + return NOTIFY_OK; + } + ++static int check_dev_is_matching_vf(struct net_device *event_ndev) ++{ ++ /* Skip NetVSC interfaces */ ++ if (event_ndev->netdev_ops == &device_ops) ++ return -ENODEV; ++ ++ /* Avoid non-Ethernet type devices */ ++ if (event_ndev->type != ARPHRD_ETHER) ++ return -ENODEV; ++ ++ /* Avoid Vlan dev with same MAC registering as VF */ ++ if (is_vlan_dev(event_ndev)) ++ return -ENODEV; ++ ++ /* Avoid Bonding master dev with same MAC registering as VF */ ++ if (netif_is_bond_master(event_ndev)) ++ return -ENODEV; ++ ++ return 0; ++} ++ + static int netvsc_probe(struct hv_device *dev, + const struct hv_vmbus_device_id *dev_id) + { +- struct net_device *net = NULL; ++ struct net_device *net = NULL, *vf_netdev; + struct net_device_context *net_device_ctx; + struct netvsc_device_info *device_info = NULL; + struct netvsc_device *nvdev; +@@ -2592,6 +2621,30 @@ static int netvsc_probe(struct hv_device + } + + list_add(&net_device_ctx->list, &netvsc_dev_list); ++ ++ /* When the hv_netvsc driver is unloaded and reloaded, the ++ * NET_DEVICE_REGISTER for the vf device is replayed before probe ++ * is complete. This is because register_netdevice_notifier() gets ++ * registered before vmbus_driver_register() so that callback func ++ * is set before probe and we don't miss events like NETDEV_POST_INIT ++ * So, in this section we try to register the matching vf device that ++ * is present as a netdevice, knowing that its register call is not ++ * processed in the netvsc_netdev_notifier(as probing is progress and ++ * get_netvsc_byslot fails). ++ */ ++ for_each_netdev(dev_net(net), vf_netdev) { ++ ret = check_dev_is_matching_vf(vf_netdev); ++ if (ret != 0) ++ continue; ++ ++ if (net != get_netvsc_byslot(vf_netdev)) ++ continue; ++ ++ netvsc_prepare_bonding(vf_netdev); ++ netvsc_register_vf(vf_netdev, VF_REG_IN_PROBE); ++ __netvsc_vf_setup(net, vf_netdev); ++ break; ++ } + rtnl_unlock(); + + netvsc_devinfo_put(device_info); +@@ -2748,28 +2801,17 @@ static int netvsc_netdev_event(struct no + unsigned long event, void *ptr) + { + struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); ++ int ret = 0; + +- /* Skip our own events */ +- if (event_dev->netdev_ops == &device_ops) +- return NOTIFY_DONE; +- +- /* Avoid non-Ethernet type devices */ +- if (event_dev->type != ARPHRD_ETHER) +- return NOTIFY_DONE; +- +- /* Avoid Vlan dev with same MAC registering as VF */ +- if (is_vlan_dev(event_dev)) +- return NOTIFY_DONE; +- +- /* Avoid Bonding master dev with same MAC registering as VF */ +- if (netif_is_bond_master(event_dev)) ++ ret = check_dev_is_matching_vf(event_dev); ++ if (ret != 0) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_POST_INIT: + return netvsc_prepare_bonding(event_dev); + case NETDEV_REGISTER: +- return netvsc_register_vf(event_dev); ++ return netvsc_register_vf(event_dev, VF_REG_IN_NOTIFIER); + case NETDEV_UNREGISTER: + return netvsc_unregister_vf(event_dev); + case NETDEV_UP: diff --git a/queue-6.1/irqchip-gic-v3-its-fix-gicv4.1-vpe-affinity-update.patch b/queue-6.1/irqchip-gic-v3-its-fix-gicv4.1-vpe-affinity-update.patch new file mode 100644 index 00000000000..3fda4048f7d --- /dev/null +++ b/queue-6.1/irqchip-gic-v3-its-fix-gicv4.1-vpe-affinity-update.patch @@ -0,0 +1,80 @@ +From af9acbfc2c4b72c378d0b9a2ee023ed01055d3e2 Mon Sep 17 00:00:00 2001 +From: Marc Zyngier +Date: Tue, 13 Feb 2024 10:12:06 +0000 +Subject: irqchip/gic-v3-its: Fix GICv4.1 VPE affinity update + +From: Marc Zyngier + +commit af9acbfc2c4b72c378d0b9a2ee023ed01055d3e2 upstream. + +When updating the affinity of a VPE, the VMOVP command is currently skipped +if the two CPUs are part of the same VPE affinity. + +But this is wrong, as the doorbell corresponding to this VPE is still +delivered on the 'old' CPU, which screws up the balancing. Furthermore, +offlining that 'old' CPU results in doorbell interrupts generated for this +VPE being discarded. + +The harsh reality is that VMOVP cannot be elided when a set_affinity() +request occurs. It needs to be obeyed, and if an optimisation is to be +made, it is at the point where the affinity change request is made (such as +in KVM). + +Drop the VMOVP elision altogether, and only use the vpe_table_mask +to try and stay within the same ITS affinity group if at all possible. + +Fixes: dd3f050a216e (irqchip/gic-v4.1: Implement the v4.1 flavour of VMOVP) +Reported-by: Kunkun Jiang +Signed-off-by: Marc Zyngier +Signed-off-by: Thomas Gleixner +Cc: stable@vger.kernel.org +Link: https://lore.kernel.org/r/20240213101206.2137483-4-maz@kernel.org +Signed-off-by: Greg Kroah-Hartman +--- + drivers/irqchip/irq-gic-v3-its.c | 22 +++++++++++++--------- + 1 file changed, 13 insertions(+), 9 deletions(-) + +--- a/drivers/irqchip/irq-gic-v3-its.c ++++ b/drivers/irqchip/irq-gic-v3-its.c +@@ -3805,8 +3805,9 @@ static int its_vpe_set_affinity(struct i + bool force) + { + struct its_vpe *vpe = irq_data_get_irq_chip_data(d); +- int from, cpu = cpumask_first(mask_val); ++ struct cpumask common, *table_mask; + unsigned long flags; ++ int from, cpu; + + /* + * Changing affinity is mega expensive, so let's be as lazy as +@@ -3822,19 +3823,22 @@ static int its_vpe_set_affinity(struct i + * taken on any vLPI handling path that evaluates vpe->col_idx. + */ + from = vpe_to_cpuid_lock(vpe, &flags); +- if (from == cpu) +- goto out; +- +- vpe->col_idx = cpu; ++ table_mask = gic_data_rdist_cpu(from)->vpe_table_mask; + + /* +- * GICv4.1 allows us to skip VMOVP if moving to a cpu whose RD +- * is sharing its VPE table with the current one. ++ * If we are offered another CPU in the same GICv4.1 ITS ++ * affinity, pick this one. Otherwise, any CPU will do. + */ +- if (gic_data_rdist_cpu(cpu)->vpe_table_mask && +- cpumask_test_cpu(from, gic_data_rdist_cpu(cpu)->vpe_table_mask)) ++ if (table_mask && cpumask_and(&common, mask_val, table_mask)) ++ cpu = cpumask_test_cpu(from, &common) ? from : cpumask_first(&common); ++ else ++ cpu = cpumask_first(mask_val); ++ ++ if (from == cpu) + goto out; + ++ vpe->col_idx = cpu; ++ + its_send_vmovp(vpe); + its_vpe_db_proxy_move(vpe, from, cpu); + diff --git a/queue-6.1/irqchip-irq-brcmstb-l2-add-write-memory-barrier-before-exit.patch b/queue-6.1/irqchip-irq-brcmstb-l2-add-write-memory-barrier-before-exit.patch new file mode 100644 index 00000000000..2b3360b39c2 --- /dev/null +++ b/queue-6.1/irqchip-irq-brcmstb-l2-add-write-memory-barrier-before-exit.patch @@ -0,0 +1,63 @@ +From b0344d6854d25a8b3b901c778b1728885dd99007 Mon Sep 17 00:00:00 2001 +From: Doug Berger +Date: Fri, 9 Feb 2024 17:24:49 -0800 +Subject: irqchip/irq-brcmstb-l2: Add write memory barrier before exit + +From: Doug Berger + +commit b0344d6854d25a8b3b901c778b1728885dd99007 upstream. + +It was observed on Broadcom devices that use GIC v3 architecture L1 +interrupt controllers as the parent of brcmstb-l2 interrupt controllers +that the deactivation of the parent interrupt could happen before the +brcmstb-l2 deasserted its output. This would lead the GIC to reactivate the +interrupt only to find that no L2 interrupt was pending. The result was a +spurious interrupt invoking handle_bad_irq() with its associated +messaging. While this did not create a functional problem it is a waste of +cycles. + +The hazard exists because the memory mapped bus writes to the brcmstb-l2 +registers are buffered and the GIC v3 architecture uses a very efficient +system register write to deactivate the interrupt. + +Add a write memory barrier prior to invoking chained_irq_exit() to +introduce a dsb(st) on those systems to ensure the system register write +cannot be executed until the memory mapped writes are visible to the +system. + +[ florian: Added Fixes tag ] + +Fixes: 7f646e92766e ("irqchip: brcmstb-l2: Add Broadcom Set Top Box Level-2 interrupt controller") +Signed-off-by: Doug Berger +Signed-off-by: Florian Fainelli +Signed-off-by: Thomas Gleixner +Acked-by: Florian Fainelli +Acked-by: Marc Zyngier +Cc: stable@vger.kernel.org +Link: https://lore.kernel.org/r/20240210012449.3009125-1-florian.fainelli@broadcom.com +Signed-off-by: Greg Kroah-Hartman +--- + drivers/irqchip/irq-brcmstb-l2.c | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +--- a/drivers/irqchip/irq-brcmstb-l2.c ++++ b/drivers/irqchip/irq-brcmstb-l2.c +@@ -2,7 +2,7 @@ + /* + * Generic Broadcom Set Top Box Level 2 Interrupt controller driver + * +- * Copyright (C) 2014-2017 Broadcom ++ * Copyright (C) 2014-2024 Broadcom + */ + + #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +@@ -113,6 +113,9 @@ static void brcmstb_l2_intc_irq_handle(s + generic_handle_domain_irq(b->domain, irq); + } while (status); + out: ++ /* Don't ack parent before all device writes are done */ ++ wmb(); ++ + chained_irq_exit(chip, desc); + } + diff --git a/queue-6.1/mm-hugetlb-pages-should-not-be-reserved-by-shmat-if-shm_noreserve.patch b/queue-6.1/mm-hugetlb-pages-should-not-be-reserved-by-shmat-if-shm_noreserve.patch new file mode 100644 index 00000000000..6647562ef5f --- /dev/null +++ b/queue-6.1/mm-hugetlb-pages-should-not-be-reserved-by-shmat-if-shm_noreserve.patch @@ -0,0 +1,103 @@ +From e656c7a9e59607d1672d85ffa9a89031876ffe67 Mon Sep 17 00:00:00 2001 +From: Prakash Sangappa +Date: Tue, 23 Jan 2024 12:04:42 -0800 +Subject: mm: hugetlb pages should not be reserved by shmat() if SHM_NORESERVE + +From: Prakash Sangappa + +commit e656c7a9e59607d1672d85ffa9a89031876ffe67 upstream. + +For shared memory of type SHM_HUGETLB, hugetlb pages are reserved in +shmget() call. If SHM_NORESERVE flags is specified then the hugetlb pages +are not reserved. However when the shared memory is attached with the +shmat() call the hugetlb pages are getting reserved incorrectly for +SHM_HUGETLB shared memory created with SHM_NORESERVE which is a bug. + +------------------------------- +Following test shows the issue. + +$cat shmhtb.c + +int main() +{ + int shmflags = 0660 | IPC_CREAT | SHM_HUGETLB | SHM_NORESERVE; + int shmid; + + shmid = shmget(SKEY, SHMSZ, shmflags); + if (shmid < 0) + { + printf("shmat: shmget() failed, %d\n", errno); + return 1; + } + printf("After shmget()\n"); + system("cat /proc/meminfo | grep -i hugepages_"); + + shmat(shmid, NULL, 0); + printf("\nAfter shmat()\n"); + system("cat /proc/meminfo | grep -i hugepages_"); + + shmctl(shmid, IPC_RMID, NULL); + return 0; +} + + #sysctl -w vm.nr_hugepages=20 + #./shmhtb + +After shmget() +HugePages_Total: 20 +HugePages_Free: 20 +HugePages_Rsvd: 0 +HugePages_Surp: 0 + +After shmat() +HugePages_Total: 20 +HugePages_Free: 20 +HugePages_Rsvd: 5 <-- +HugePages_Surp: 0 +-------------------------------- + +Fix is to ensure that hugetlb pages are not reserved for SHM_HUGETLB shared +memory in the shmat() call. + +Link: https://lkml.kernel.org/r/1706040282-12388-1-git-send-email-prakash.sangappa@oracle.com +Signed-off-by: Prakash Sangappa +Acked-by: Muchun Song +Cc: +Signed-off-by: Andrew Morton +Signed-off-by: Greg Kroah-Hartman +--- + fs/hugetlbfs/inode.c | 13 ++++++++++++- + 1 file changed, 12 insertions(+), 1 deletion(-) + +--- a/fs/hugetlbfs/inode.c ++++ b/fs/hugetlbfs/inode.c +@@ -123,6 +123,7 @@ static int hugetlbfs_file_mmap(struct fi + loff_t len, vma_len; + int ret; + struct hstate *h = hstate_file(file); ++ vm_flags_t vm_flags; + + /* + * vma address alignment (but not the pgoff alignment) has +@@ -164,10 +165,20 @@ static int hugetlbfs_file_mmap(struct fi + file_accessed(file); + + ret = -ENOMEM; ++ ++ vm_flags = vma->vm_flags; ++ /* ++ * for SHM_HUGETLB, the pages are reserved in the shmget() call so skip ++ * reserving here. Note: only for SHM hugetlbfs file, the inode ++ * flag S_PRIVATE is set. ++ */ ++ if (inode->i_flags & S_PRIVATE) ++ vm_flags |= VM_NORESERVE; ++ + if (!hugetlb_reserve_pages(inode, + vma->vm_pgoff >> huge_page_order(h), + len >> huge_page_shift(h), vma, +- vma->vm_flags)) ++ vm_flags)) + goto out; + + ret = 0; diff --git a/queue-6.1/mmc-sdhci-pci-o2micro-fix-a-warm-reboot-issue-that-disk-can-t-be-detected-by-bios.patch b/queue-6.1/mmc-sdhci-pci-o2micro-fix-a-warm-reboot-issue-that-disk-can-t-be-detected-by-bios.patch new file mode 100644 index 00000000000..ab27030d1b3 --- /dev/null +++ b/queue-6.1/mmc-sdhci-pci-o2micro-fix-a-warm-reboot-issue-that-disk-can-t-be-detected-by-bios.patch @@ -0,0 +1,69 @@ +From 58aeb5623c2ebdadefe6352b14f8076a7073fea0 Mon Sep 17 00:00:00 2001 +From: Fred Ai +Date: Sat, 3 Feb 2024 02:29:08 -0800 +Subject: mmc: sdhci-pci-o2micro: Fix a warm reboot issue that disk can't be detected by BIOS + +From: Fred Ai + +commit 58aeb5623c2ebdadefe6352b14f8076a7073fea0 upstream. + +Driver shall switch clock source from DLL clock to +OPE clock when power off card to ensure that card +can be identified with OPE clock by BIOS. + +Signed-off-by: Fred Ai +Fixes:4be33cf18703 ("mmc: sdhci-pci-o2micro: Improve card input timing at SDR104/HS200 mode") +Cc: stable@vger.kernel.org +Link: https://lore.kernel.org/r/20240203102908.4683-1-fredaibayhubtech@126.com +Signed-off-by: Ulf Hansson +Signed-off-by: Greg Kroah-Hartman +--- + drivers/mmc/host/sdhci-pci-o2micro.c | 30 ++++++++++++++++++++++++++++++ + 1 file changed, 30 insertions(+) + +--- a/drivers/mmc/host/sdhci-pci-o2micro.c ++++ b/drivers/mmc/host/sdhci-pci-o2micro.c +@@ -602,6 +602,35 @@ static void sdhci_pci_o2_set_clock(struc + sdhci_o2_enable_clk(host, clk); + } + ++static void sdhci_pci_o2_set_power(struct sdhci_host *host, unsigned char mode, unsigned short vdd) ++{ ++ struct sdhci_pci_chip *chip; ++ struct sdhci_pci_slot *slot = sdhci_priv(host); ++ u32 scratch_32 = 0; ++ u8 scratch_8 = 0; ++ ++ chip = slot->chip; ++ ++ if (mode == MMC_POWER_OFF) { ++ /* UnLock WP */ ++ pci_read_config_byte(chip->pdev, O2_SD_LOCK_WP, &scratch_8); ++ scratch_8 &= 0x7f; ++ pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch_8); ++ ++ /* Set PCR 0x354[16] to switch Clock Source back to OPE Clock */ ++ pci_read_config_dword(chip->pdev, O2_SD_OUTPUT_CLK_SOURCE_SWITCH, &scratch_32); ++ scratch_32 &= ~(O2_SD_SEL_DLL); ++ pci_write_config_dword(chip->pdev, O2_SD_OUTPUT_CLK_SOURCE_SWITCH, scratch_32); ++ ++ /* Lock WP */ ++ pci_read_config_byte(chip->pdev, O2_SD_LOCK_WP, &scratch_8); ++ scratch_8 |= 0x80; ++ pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch_8); ++ } ++ ++ sdhci_set_power(host, mode, vdd); ++} ++ + static int sdhci_pci_o2_probe_slot(struct sdhci_pci_slot *slot) + { + struct sdhci_pci_chip *chip; +@@ -911,6 +940,7 @@ static const struct sdhci_ops sdhci_pci_ + .set_bus_width = sdhci_set_bus_width, + .reset = sdhci_reset, + .set_uhs_signaling = sdhci_set_uhs_signaling, ++ .set_power = sdhci_pci_o2_set_power, + }; + + const struct sdhci_pci_fixes sdhci_o2 = { diff --git a/queue-6.1/net-ethernet-ti-cpsw-enable-mac_managed_pm-to-fix-mdio.patch b/queue-6.1/net-ethernet-ti-cpsw-enable-mac_managed_pm-to-fix-mdio.patch new file mode 100644 index 00000000000..dd78ae99bbc --- /dev/null +++ b/queue-6.1/net-ethernet-ti-cpsw-enable-mac_managed_pm-to-fix-mdio.patch @@ -0,0 +1,62 @@ +From bc4ce46b1e3d1da4309405cd4afc7c0fcddd0b90 Mon Sep 17 00:00:00 2001 +From: Sinthu Raja +Date: Tue, 6 Feb 2024 06:29:28 +0530 +Subject: net: ethernet: ti: cpsw: enable mac_managed_pm to fix mdio + +From: Sinthu Raja + +commit bc4ce46b1e3d1da4309405cd4afc7c0fcddd0b90 upstream. + +The below commit introduced a WARN when phy state is not in the states: +PHY_HALTED, PHY_READY and PHY_UP. +commit 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state") + +When cpsw resumes, there have port in PHY_NOLINK state, so the below +warning comes out. Set mac_managed_pm be true to tell mdio that the phy +resume/suspend is managed by the mac, to fix the following warning: + +WARNING: CPU: 0 PID: 965 at drivers/net/phy/phy_device.c:326 mdio_bus_phy_resume+0x140/0x144 +CPU: 0 PID: 965 Comm: sh Tainted: G O 6.1.46-g247b2535b2 #1 +Hardware name: Generic AM33XX (Flattened Device Tree) + unwind_backtrace from show_stack+0x18/0x1c + show_stack from dump_stack_lvl+0x24/0x2c + dump_stack_lvl from __warn+0x84/0x15c + __warn from warn_slowpath_fmt+0x1a8/0x1c8 + warn_slowpath_fmt from mdio_bus_phy_resume+0x140/0x144 + mdio_bus_phy_resume from dpm_run_callback+0x3c/0x140 + dpm_run_callback from device_resume+0xb8/0x2b8 + device_resume from dpm_resume+0x144/0x314 + dpm_resume from dpm_resume_end+0x14/0x20 + dpm_resume_end from suspend_devices_and_enter+0xd0/0x924 + suspend_devices_and_enter from pm_suspend+0x2e0/0x33c + pm_suspend from state_store+0x74/0xd0 + state_store from kernfs_fop_write_iter+0x104/0x1ec + kernfs_fop_write_iter from vfs_write+0x1b8/0x358 + vfs_write from ksys_write+0x78/0xf8 + ksys_write from ret_fast_syscall+0x0/0x54 +Exception stack(0xe094dfa8 to 0xe094dff0) +dfa0: 00000004 005c3fb8 00000001 005c3fb8 00000004 00000001 +dfc0: 00000004 005c3fb8 b6f6bba0 00000004 00000004 0059edb8 00000000 00000000 +dfe0: 00000004 bed918f0 b6f09bd3 b6e89a66 + +Cc: # v6.0+ +Fixes: 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state") +Fixes: fba863b81604 ("net: phy: make PHY PM ops a no-op if MAC driver manages PHY PM") +Signed-off-by: Sinthu Raja +Signed-off-by: Paolo Abeni +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/ethernet/ti/cpsw.c | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/drivers/net/ethernet/ti/cpsw.c ++++ b/drivers/net/ethernet/ti/cpsw.c +@@ -631,6 +631,8 @@ static void cpsw_slave_open(struct cpsw_ + } + } + ++ phy->mac_managed_pm = true; ++ + slave->phy = phy; + + phy_attached_info(slave->phy); diff --git a/queue-6.1/net-ethernet-ti-cpsw_new-enable-mac_managed_pm-to-fix-mdio.patch b/queue-6.1/net-ethernet-ti-cpsw_new-enable-mac_managed_pm-to-fix-mdio.patch new file mode 100644 index 00000000000..1153d8b20fe --- /dev/null +++ b/queue-6.1/net-ethernet-ti-cpsw_new-enable-mac_managed_pm-to-fix-mdio.patch @@ -0,0 +1,63 @@ +From 9def04e759caa5a3d741891037ae99f81e2fff01 Mon Sep 17 00:00:00 2001 +From: Sinthu Raja +Date: Tue, 6 Feb 2024 06:29:27 +0530 +Subject: net: ethernet: ti: cpsw_new: enable mac_managed_pm to fix mdio + +From: Sinthu Raja + +commit 9def04e759caa5a3d741891037ae99f81e2fff01 upstream. + +The below commit introduced a WARN when phy state is not in the states: +PHY_HALTED, PHY_READY and PHY_UP. +commit 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state") + +When cpsw_new resumes, there have port in PHY_NOLINK state, so the below +warning comes out. Set mac_managed_pm be true to tell mdio that the phy +resume/suspend is managed by the mac, to fix the following warning: + +WARNING: CPU: 0 PID: 965 at drivers/net/phy/phy_device.c:326 mdio_bus_phy_resume+0x140/0x144 +CPU: 0 PID: 965 Comm: sh Tainted: G O 6.1.46-g247b2535b2 #1 +Hardware name: Generic AM33XX (Flattened Device Tree) + unwind_backtrace from show_stack+0x18/0x1c + show_stack from dump_stack_lvl+0x24/0x2c + dump_stack_lvl from __warn+0x84/0x15c + __warn from warn_slowpath_fmt+0x1a8/0x1c8 + warn_slowpath_fmt from mdio_bus_phy_resume+0x140/0x144 + mdio_bus_phy_resume from dpm_run_callback+0x3c/0x140 + dpm_run_callback from device_resume+0xb8/0x2b8 + device_resume from dpm_resume+0x144/0x314 + dpm_resume from dpm_resume_end+0x14/0x20 + dpm_resume_end from suspend_devices_and_enter+0xd0/0x924 + suspend_devices_and_enter from pm_suspend+0x2e0/0x33c + pm_suspend from state_store+0x74/0xd0 + state_store from kernfs_fop_write_iter+0x104/0x1ec + kernfs_fop_write_iter from vfs_write+0x1b8/0x358 + vfs_write from ksys_write+0x78/0xf8 + ksys_write from ret_fast_syscall+0x0/0x54 +Exception stack(0xe094dfa8 to 0xe094dff0) +dfa0: 00000004 005c3fb8 00000001 005c3fb8 00000004 00000001 +dfc0: 00000004 005c3fb8 b6f6bba0 00000004 00000004 0059edb8 00000000 00000000 +dfe0: 00000004 bed918f0 b6f09bd3 b6e89a66 + +Cc: # v6.0+ +Fixes: 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state") +Fixes: fba863b81604 ("net: phy: make PHY PM ops a no-op if MAC driver manages PHY PM") +Signed-off-by: Sinthu Raja +Signed-off-by: Paolo Abeni +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/ethernet/ti/cpsw_new.c | 3 +++ + 1 file changed, 3 insertions(+) + +--- a/drivers/net/ethernet/ti/cpsw_new.c ++++ b/drivers/net/ethernet/ti/cpsw_new.c +@@ -772,6 +772,9 @@ static void cpsw_slave_open(struct cpsw_ + slave->slave_num); + return; + } ++ ++ phy->mac_managed_pm = true; ++ + slave->phy = phy; + + phy_attached_info(slave->phy); diff --git a/queue-6.1/nfp-flower-prevent-re-adding-mac-index-for-bonded-port.patch b/queue-6.1/nfp-flower-prevent-re-adding-mac-index-for-bonded-port.patch new file mode 100644 index 00000000000..f82fac269c7 --- /dev/null +++ b/queue-6.1/nfp-flower-prevent-re-adding-mac-index-for-bonded-port.patch @@ -0,0 +1,50 @@ +From 1a1c13303ff6d64e6f718dc8aa614e580ca8d9b4 Mon Sep 17 00:00:00 2001 +From: Daniel de Villiers +Date: Fri, 2 Feb 2024 13:37:18 +0200 +Subject: nfp: flower: prevent re-adding mac index for bonded port + +From: Daniel de Villiers + +commit 1a1c13303ff6d64e6f718dc8aa614e580ca8d9b4 upstream. + +When physical ports are reset (either through link failure or manually +toggled down and up again) that are slaved to a Linux bond with a tunnel +endpoint IP address on the bond device, not all tunnel packets arriving +on the bond port are decapped as expected. + +The bond dev assigns the same MAC address to itself and each of its +slaves. When toggling a slave device, the same MAC address is therefore +offloaded to the NFP multiple times with different indexes. + +The issue only occurs when re-adding the shared mac. The +nfp_tunnel_add_shared_mac() function has a conditional check early on +that checks if a mac entry already exists and if that mac entry is +global: (entry && nfp_tunnel_is_mac_idx_global(entry->index)). In the +case of a bonded device (For example br-ex), the mac index is obtained, +and no new index is assigned. + +We therefore modify the conditional in nfp_tunnel_add_shared_mac() to +check if the port belongs to the LAG along with the existing checks to +prevent a new global mac index from being re-assigned to the slave port. + +Fixes: 20cce8865098 ("nfp: flower: enable MAC address sharing for offloadable devs") +CC: stable@vger.kernel.org # 5.1+ +Signed-off-by: Daniel de Villiers +Signed-off-by: Louis Peens +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c ++++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +@@ -980,7 +980,7 @@ nfp_tunnel_add_shared_mac(struct nfp_app + u16 nfp_mac_idx = 0; + + entry = nfp_tunnel_lookup_offloaded_macs(app, netdev->dev_addr); +- if (entry && nfp_tunnel_is_mac_idx_global(entry->index)) { ++ if (entry && (nfp_tunnel_is_mac_idx_global(entry->index) || netif_is_lag_port(netdev))) { + if (entry->bridge_count || + !nfp_flower_is_supported_bridge(netdev)) { + nfp_tunnel_offloaded_macs_inc_ref_and_link(entry, diff --git a/queue-6.1/nfp-use-correct-macro-for-lengthselect-in-bar-config.patch b/queue-6.1/nfp-use-correct-macro-for-lengthselect-in-bar-config.patch new file mode 100644 index 00000000000..aa447157268 --- /dev/null +++ b/queue-6.1/nfp-use-correct-macro-for-lengthselect-in-bar-config.patch @@ -0,0 +1,46 @@ +From b3d4f7f2288901ed2392695919b3c0e24c1b4084 Mon Sep 17 00:00:00 2001 +From: Daniel Basilio +Date: Fri, 2 Feb 2024 13:37:17 +0200 +Subject: nfp: use correct macro for LengthSelect in BAR config + +From: Daniel Basilio + +commit b3d4f7f2288901ed2392695919b3c0e24c1b4084 upstream. + +The 1st and 2nd expansion BAR configuration registers are configured, +when the driver starts up, in variables 'barcfg_msix_general' and +'barcfg_msix_xpb', respectively. The 'LengthSelect' field is ORed in +from bit 0, which is incorrect. The 'LengthSelect' field should +start from bit 27. + +This has largely gone un-noticed because +NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT happens to be 0. + +Fixes: 4cb584e0ee7d ("nfp: add CPP access core") +Cc: stable@vger.kernel.org # 4.11+ +Signed-off-by: Daniel Basilio +Signed-off-by: Louis Peens +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c | 6 ++++-- + 1 file changed, 4 insertions(+), 2 deletions(-) + +--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c ++++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c +@@ -537,11 +537,13 @@ static int enable_bars(struct nfp6000_pc + const u32 barcfg_msix_general = + NFP_PCIE_BAR_PCIE2CPP_MapType( + NFP_PCIE_BAR_PCIE2CPP_MapType_GENERAL) | +- NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT; ++ NFP_PCIE_BAR_PCIE2CPP_LengthSelect( ++ NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT); + const u32 barcfg_msix_xpb = + NFP_PCIE_BAR_PCIE2CPP_MapType( + NFP_PCIE_BAR_PCIE2CPP_MapType_BULK) | +- NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT | ++ NFP_PCIE_BAR_PCIE2CPP_LengthSelect( ++ NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT) | + NFP_PCIE_BAR_PCIE2CPP_Target_BaseAddress( + NFP_CPP_TARGET_ISLAND_XPB); + const u32 barcfg_explicit[4] = { diff --git a/queue-6.1/of-property-fix-typo-in-io-channels.patch b/queue-6.1/of-property-fix-typo-in-io-channels.patch new file mode 100644 index 00000000000..f2993fd7787 --- /dev/null +++ b/queue-6.1/of-property-fix-typo-in-io-channels.patch @@ -0,0 +1,35 @@ +From 8f7e917907385e112a845d668ae2832f41e64bf5 Mon Sep 17 00:00:00 2001 +From: Nuno Sa +Date: Tue, 23 Jan 2024 16:14:22 +0100 +Subject: of: property: fix typo in io-channels + +From: Nuno Sa + +commit 8f7e917907385e112a845d668ae2832f41e64bf5 upstream. + +The property is io-channels and not io-channel. This was effectively +preventing the devlink creation. + +Fixes: 8e12257dead7 ("of: property: Add device link support for iommus, mboxes and io-channels") +Cc: stable@vger.kernel.org +Signed-off-by: Nuno Sa +Reviewed-by: Saravana Kannan +Acked-by: Jonathan Cameron +Link: https://lore.kernel.org/r/20240123-iio-backend-v7-1-1bff236b8693@analog.com +Signed-off-by: Rob Herring +Signed-off-by: Greg Kroah-Hartman +--- + drivers/of/property.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/of/property.c ++++ b/drivers/of/property.c +@@ -1243,7 +1243,7 @@ DEFINE_SIMPLE_PROP(clocks, "clocks", "#c + DEFINE_SIMPLE_PROP(interconnects, "interconnects", "#interconnect-cells") + DEFINE_SIMPLE_PROP(iommus, "iommus", "#iommu-cells") + DEFINE_SIMPLE_PROP(mboxes, "mboxes", "#mbox-cells") +-DEFINE_SIMPLE_PROP(io_channels, "io-channel", "#io-channel-cells") ++DEFINE_SIMPLE_PROP(io_channels, "io-channels", "#io-channel-cells") + DEFINE_SIMPLE_PROP(interrupt_parent, "interrupt-parent", NULL) + DEFINE_SIMPLE_PROP(dmas, "dmas", "#dma-cells") + DEFINE_SIMPLE_PROP(power_domains, "power-domains", "#power-domain-cells") diff --git a/queue-6.1/pmdomain-core-move-the-unused-cleanup-to-a-_sync-initcall.patch b/queue-6.1/pmdomain-core-move-the-unused-cleanup-to-a-_sync-initcall.patch new file mode 100644 index 00000000000..154efe1a335 --- /dev/null +++ b/queue-6.1/pmdomain-core-move-the-unused-cleanup-to-a-_sync-initcall.patch @@ -0,0 +1,34 @@ +From 741ba0134fa7822fcf4e4a0a537a5c4cfd706b20 Mon Sep 17 00:00:00 2001 +From: Konrad Dybcio +Date: Wed, 27 Dec 2023 16:21:24 +0100 +Subject: pmdomain: core: Move the unused cleanup to a _sync initcall + +From: Konrad Dybcio + +commit 741ba0134fa7822fcf4e4a0a537a5c4cfd706b20 upstream. + +The unused clock cleanup uses the _sync initcall to give all users at +earlier initcalls time to probe. Do the same to avoid leaving some PDs +dangling at "on" (which actually happened on qcom!). + +Fixes: 2fe71dcdfd10 ("PM / domains: Add late_initcall to disable unused PM domains") +Signed-off-by: Konrad Dybcio +Cc: stable@vger.kernel.org +Link: https://lore.kernel.org/r/20231227-topic-pmdomain_sync_cleanup-v1-1-5f36769d538b@linaro.org +Signed-off-by: Ulf Hansson +Signed-off-by: Greg Kroah-Hartman +--- + drivers/base/power/domain.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/base/power/domain.c ++++ b/drivers/base/power/domain.c +@@ -1052,7 +1052,7 @@ static int __init genpd_power_off_unused + + return 0; + } +-late_initcall(genpd_power_off_unused); ++late_initcall_sync(genpd_power_off_unused); + + #ifdef CONFIG_PM_SLEEP + diff --git a/queue-6.1/s390-qeth-fix-potential-loss-of-l3-ip-in-case-of-network-issues.patch b/queue-6.1/s390-qeth-fix-potential-loss-of-l3-ip-in-case-of-network-issues.patch new file mode 100644 index 00000000000..568cc2869e6 --- /dev/null +++ b/queue-6.1/s390-qeth-fix-potential-loss-of-l3-ip-in-case-of-network-issues.patch @@ -0,0 +1,70 @@ +From 2fe8a236436fe40d8d26a1af8d150fc80f04ee1a Mon Sep 17 00:00:00 2001 +From: Alexandra Winter +Date: Tue, 6 Feb 2024 09:58:49 +0100 +Subject: s390/qeth: Fix potential loss of L3-IP@ in case of network issues + +From: Alexandra Winter + +commit 2fe8a236436fe40d8d26a1af8d150fc80f04ee1a upstream. + +Symptom: +In case of a bad cable connection (e.g. dirty optics) a fast sequence of +network DOWN-UP-DOWN-UP could happen. UP triggers recovery of the qeth +interface. In case of a second DOWN while recovery is still ongoing, it +can happen that the IP@ of a Layer3 qeth interface is lost and will not +be recovered by the second UP. + +Problem: +When registration of IP addresses with Layer 3 qeth devices fails, (e.g. +because of bad address format) the respective IP address is deleted from +its hash-table in the driver. If registration fails because of a ENETDOWN +condition, the address should stay in the hashtable, so a subsequent +recovery can restore it. + +3caa4af834df ("qeth: keep ip-address after LAN_OFFLINE failure") +fixes this for registration failures during normal operation, but not +during recovery. + +Solution: +Keep L3-IP address in case of ENETDOWN in qeth_l3_recover_ip(). For +consistency with qeth_l3_add_ip() we also keep it in case of EADDRINUSE, +i.e. for some reason the card already/still has this address registered. + +Fixes: 4a71df50047f ("qeth: new qeth device driver") +Cc: stable@vger.kernel.org +Signed-off-by: Alexandra Winter +Link: https://lore.kernel.org/r/20240206085849.2902775-1-wintera@linux.ibm.com +Signed-off-by: Paolo Abeni +Signed-off-by: Greg Kroah-Hartman +--- + drivers/s390/net/qeth_l3_main.c | 9 ++++++--- + 1 file changed, 6 insertions(+), 3 deletions(-) + +--- a/drivers/s390/net/qeth_l3_main.c ++++ b/drivers/s390/net/qeth_l3_main.c +@@ -254,9 +254,10 @@ static void qeth_l3_clear_ip_htable(stru + if (!recover) { + hash_del(&addr->hnode); + kfree(addr); +- continue; ++ } else { ++ /* prepare for recovery */ ++ addr->disp_flag = QETH_DISP_ADDR_ADD; + } +- addr->disp_flag = QETH_DISP_ADDR_ADD; + } + + mutex_unlock(&card->ip_lock); +@@ -277,9 +278,11 @@ static void qeth_l3_recover_ip(struct qe + if (addr->disp_flag == QETH_DISP_ADDR_ADD) { + rc = qeth_l3_register_addr_entry(card, addr); + +- if (!rc) { ++ if (!rc || rc == -EADDRINUSE || rc == -ENETDOWN) { ++ /* keep it in the records */ + addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING; + } else { ++ /* bad address */ + hash_del(&addr->hnode); + kfree(addr); + } diff --git a/queue-6.1/series b/queue-6.1/series index 3743eec488f..68f9ac914e8 100644 --- a/queue-6.1/series +++ b/queue-6.1/series @@ -129,3 +129,33 @@ alsa-hda-realtek-fix-mute-micmute-led-for-hp-mt645.patch alsa-hda-conexant-add-quirk-for-sws-js201d.patch nilfs2-fix-data-corruption-in-dsync-block-recovery-for-small-block-sizes.patch nilfs2-fix-hang-in-nilfs_lookup_dirty_data_buffers.patch +crypto-ccp-fix-null-pointer-dereference-in-__sev_platform_shutdown_locked.patch +nfp-use-correct-macro-for-lengthselect-in-bar-config.patch +nfp-flower-prevent-re-adding-mac-index-for-bonded-port.patch +wifi-cfg80211-fix-wiphy-delayed-work-queueing.patch +wifi-mac80211-reload-info-pointer-in-ieee80211_tx_dequeue.patch +exit-wait_task_zombie-kill-the-no-longer-necessary-spin_lock_irq-siglock.patch +irqchip-irq-brcmstb-l2-add-write-memory-barrier-before-exit.patch +irqchip-gic-v3-its-fix-gicv4.1-vpe-affinity-update.patch +zonefs-improve-error-handling.patch +mmc-sdhci-pci-o2micro-fix-a-warm-reboot-issue-that-disk-can-t-be-detected-by-bios.patch +asoc-amd-yc-add-dmi-quirk-for-lenovo-ideapad-pro-5-16arp8.patch +tools-rtla-remove-unused-sched_getattr-function.patch +tools-rtla-replace-setting-prio-with-nice-for-sched_other.patch +tools-rtla-exit-with-exit_success-when-help-is-invoked.patch +tools-rtla-fix-uninitialized-bucket-data-bucket_size-warning.patch +tools-rtla-fix-makefile-compiler-options-for-clang.patch +fs-relax-mount_setattr-permission-checks.patch +net-ethernet-ti-cpsw-enable-mac_managed_pm-to-fix-mdio.patch +s390-qeth-fix-potential-loss-of-l3-ip-in-case-of-network-issues.patch +net-ethernet-ti-cpsw_new-enable-mac_managed_pm-to-fix-mdio.patch +hv_netvsc-register-vf-in-netvsc_probe-if-net_device_register-missed.patch +ceph-prevent-use-after-free-in-encode_cap_msg.patch +fs-hugetlb-fix-null-pointer-dereference-in-hugetlbs_fill_super.patch +mm-hugetlb-pages-should-not-be-reserved-by-shmat-if-shm_noreserve.patch +of-property-fix-typo-in-io-channels.patch +can-netlink-fix-tdco-calculation-using-the-old-data-bittiming.patch +can-j1939-prevent-deadlock-by-changing-j1939_socks_lock-to-rwlock.patch +can-j1939-fix-uaf-in-j1939_sk_match_filter-during-setsockopt-so_j1939_filter.patch +pmdomain-core-move-the-unused-cleanup-to-a-_sync-initcall.patch +fs-proc-do_task_stat-move-thread_group_cputime_adjusted-outside-of-lock_task_sighand.patch diff --git a/queue-6.1/tools-rtla-exit-with-exit_success-when-help-is-invoked.patch b/queue-6.1/tools-rtla-exit-with-exit_success-when-help-is-invoked.patch new file mode 100644 index 00000000000..d623602f1c4 --- /dev/null +++ b/queue-6.1/tools-rtla-exit-with-exit_success-when-help-is-invoked.patch @@ -0,0 +1,90 @@ +From b5f319360371087d52070d8f3fc7789e80ce69a6 Mon Sep 17 00:00:00 2001 +From: John Kacur +Date: Fri, 2 Feb 2024 19:16:07 -0500 +Subject: tools/rtla: Exit with EXIT_SUCCESS when help is invoked + +From: John Kacur + +commit b5f319360371087d52070d8f3fc7789e80ce69a6 upstream. + +Fix rtla so that the following commands exit with 0 when help is invoked + +rtla osnoise top -h +rtla osnoise hist -h +rtla timerlat top -h +rtla timerlat hist -h + +Link: https://lore.kernel.org/linux-trace-devel/20240203001607.69703-1-jkacur@redhat.com + +Cc: stable@vger.kernel.org +Fixes: 1eeb6328e8b3 ("rtla/timerlat: Add timerlat hist mode") +Signed-off-by: John Kacur +Signed-off-by: Daniel Bristot de Oliveira +Signed-off-by: Greg Kroah-Hartman +--- + tools/tracing/rtla/src/osnoise_hist.c | 6 +++++- + tools/tracing/rtla/src/osnoise_top.c | 6 +++++- + tools/tracing/rtla/src/timerlat_hist.c | 6 +++++- + tools/tracing/rtla/src/timerlat_top.c | 6 +++++- + 4 files changed, 20 insertions(+), 4 deletions(-) + +--- a/tools/tracing/rtla/src/osnoise_hist.c ++++ b/tools/tracing/rtla/src/osnoise_hist.c +@@ -472,7 +472,11 @@ static void osnoise_hist_usage(char *usa + + for (i = 0; msg[i]; i++) + fprintf(stderr, "%s\n", msg[i]); +- exit(1); ++ ++ if (usage) ++ exit(EXIT_FAILURE); ++ ++ exit(EXIT_SUCCESS); + } + + /* +--- a/tools/tracing/rtla/src/osnoise_top.c ++++ b/tools/tracing/rtla/src/osnoise_top.c +@@ -282,7 +282,11 @@ void osnoise_top_usage(char *usage) + + for (i = 0; msg[i]; i++) + fprintf(stderr, "%s\n", msg[i]); +- exit(1); ++ ++ if (usage) ++ exit(EXIT_FAILURE); ++ ++ exit(EXIT_SUCCESS); + } + + /* +--- a/tools/tracing/rtla/src/timerlat_hist.c ++++ b/tools/tracing/rtla/src/timerlat_hist.c +@@ -475,7 +475,11 @@ static void timerlat_hist_usage(char *us + + for (i = 0; msg[i]; i++) + fprintf(stderr, "%s\n", msg[i]); +- exit(1); ++ ++ if (usage) ++ exit(EXIT_FAILURE); ++ ++ exit(EXIT_SUCCESS); + } + + /* +--- a/tools/tracing/rtla/src/timerlat_top.c ++++ b/tools/tracing/rtla/src/timerlat_top.c +@@ -305,7 +305,11 @@ static void timerlat_top_usage(char *usa + + for (i = 0; msg[i]; i++) + fprintf(stderr, "%s\n", msg[i]); +- exit(1); ++ ++ if (usage) ++ exit(EXIT_FAILURE); ++ ++ exit(EXIT_SUCCESS); + } + + /* diff --git a/queue-6.1/tools-rtla-fix-makefile-compiler-options-for-clang.patch b/queue-6.1/tools-rtla-fix-makefile-compiler-options-for-clang.patch new file mode 100644 index 00000000000..18697ec213f --- /dev/null +++ b/queue-6.1/tools-rtla-fix-makefile-compiler-options-for-clang.patch @@ -0,0 +1,72 @@ +From bc4cbc9d260ba8358ca63662919f4bb223cb603b Mon Sep 17 00:00:00 2001 +From: Daniel Bristot de Oliveira +Date: Tue, 6 Feb 2024 12:05:29 +0100 +Subject: tools/rtla: Fix Makefile compiler options for clang + +From: Daniel Bristot de Oliveira + +commit bc4cbc9d260ba8358ca63662919f4bb223cb603b upstream. + +The following errors are showing up when compiling rtla with clang: + + $ make HOSTCC=clang CC=clang LLVM_IAS=1 + [...] + + clang -O -g -DVERSION=\"6.8.0-rc1\" -flto=auto -ffat-lto-objects + -fexceptions -fstack-protector-strong + -fasynchronous-unwind-tables -fstack-clash-protection -Wall + -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 + -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized + $(pkg-config --cflags libtracefs) -c -o src/utils.o src/utils.c + + clang: warning: optimization flag '-ffat-lto-objects' is not supported [-Wignored-optimization-argument] + warning: unknown warning option '-Wno-maybe-uninitialized'; did you mean '-Wno-uninitialized'? [-Wunknown-warning-option] + 1 warning generated. + + clang -o rtla -ggdb src/osnoise.o src/osnoise_hist.o src/osnoise_top.o + src/rtla.o src/timerlat_aa.o src/timerlat.o src/timerlat_hist.o + src/timerlat_top.o src/timerlat_u.o src/trace.o src/utils.o $(pkg-config --libs libtracefs) + + src/osnoise.o: file not recognized: file format not recognized + clang: error: linker command failed with exit code 1 (use -v to see invocation) + make: *** [Makefile:110: rtla] Error 1 + +Solve these issues by: + - removing -ffat-lto-objects and -Wno-maybe-uninitialized if using clang + - informing the linker about -flto=auto + +Link: https://lore.kernel.org/linux-trace-kernel/567ac1b94effc228ce9a0225b9df7232a9b35b55.1707217097.git.bristot@kernel.org + +Cc: stable@vger.kernel.org +Cc: Masami Hiramatsu +Cc: Nathan Chancellor +Cc: Nick Desaulniers +Cc: Bill Wendling +Cc: Justin Stitt +Fixes: 1a7b22ab15eb ("tools/rtla: Build with EXTRA_{C,LD}FLAGS") +Suggested-by: Donald Zickus +Signed-off-by: Daniel Bristot de Oliveira +Signed-off-by: Greg Kroah-Hartman +--- + tools/tracing/rtla/Makefile | 7 ++++++- + 1 file changed, 6 insertions(+), 1 deletion(-) + +--- a/tools/tracing/rtla/Makefile ++++ b/tools/tracing/rtla/Makefile +@@ -28,10 +28,15 @@ FOPTS := -flto=auto -ffat-lto-objects -f + -fasynchronous-unwind-tables -fstack-clash-protection + WOPTS := -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized + ++ifeq ($(CC),clang) ++ FOPTS := $(filter-out -ffat-lto-objects, $(FOPTS)) ++ WOPTS := $(filter-out -Wno-maybe-uninitialized, $(WOPTS)) ++endif ++ + TRACEFS_HEADERS := $$($(PKG_CONFIG) --cflags libtracefs) + + CFLAGS := -O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) $(EXTRA_CFLAGS) +-LDFLAGS := -ggdb $(EXTRA_LDFLAGS) ++LDFLAGS := -flto=auto -ggdb $(EXTRA_LDFLAGS) + LIBS := $$($(PKG_CONFIG) --libs libtracefs) + + SRC := $(wildcard src/*.c) diff --git a/queue-6.1/tools-rtla-fix-uninitialized-bucket-data-bucket_size-warning.patch b/queue-6.1/tools-rtla-fix-uninitialized-bucket-data-bucket_size-warning.patch new file mode 100644 index 00000000000..6c38e1cfaa8 --- /dev/null +++ b/queue-6.1/tools-rtla-fix-uninitialized-bucket-data-bucket_size-warning.patch @@ -0,0 +1,107 @@ +From 64dc40f7523369912d7adb22c8cb655f71610505 Mon Sep 17 00:00:00 2001 +From: Daniel Bristot de Oliveira +Date: Tue, 6 Feb 2024 12:05:30 +0100 +Subject: tools/rtla: Fix uninitialized bucket/data->bucket_size warning + +From: Daniel Bristot de Oliveira + +commit 64dc40f7523369912d7adb22c8cb655f71610505 upstream. + +When compiling rtla with clang, I am getting the following warnings: + +$ make HOSTCC=clang CC=clang LLVM_IAS=1 + +[..] +clang -O -g -DVERSION=\"6.8.0-rc3\" -flto=auto -fexceptions + -fstack-protector-strong -fasynchronous-unwind-tables + -fstack-clash-protection -Wall -Werror=format-security + -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS + $(pkg-config --cflags libtracefs) + -c -o src/osnoise_hist.o src/osnoise_hist.c +src/osnoise_hist.c:138:6: warning: variable 'bucket' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized] + 138 | if (data->bucket_size) + | ^~~~~~~~~~~~~~~~~ +src/osnoise_hist.c:149:6: note: uninitialized use occurs here + 149 | if (bucket < entries) + | ^~~~~~ +src/osnoise_hist.c:138:2: note: remove the 'if' if its condition is always true + 138 | if (data->bucket_size) + | ^~~~~~~~~~~~~~~~~~~~~~ + 139 | bucket = duration / data->bucket_size; +src/osnoise_hist.c:132:12: note: initialize the variable 'bucket' to silence this warning + 132 | int bucket; + | ^ + | = 0 +1 warning generated. + +[...] + +clang -O -g -DVERSION=\"6.8.0-rc3\" -flto=auto -fexceptions + -fstack-protector-strong -fasynchronous-unwind-tables + -fstack-clash-protection -Wall -Werror=format-security + -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS + $(pkg-config --cflags libtracefs) + -c -o src/timerlat_hist.o src/timerlat_hist.c +src/timerlat_hist.c:181:6: warning: variable 'bucket' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized] + 181 | if (data->bucket_size) + | ^~~~~~~~~~~~~~~~~ +src/timerlat_hist.c:204:6: note: uninitialized use occurs here + 204 | if (bucket < entries) + | ^~~~~~ +src/timerlat_hist.c:181:2: note: remove the 'if' if its condition is always true + 181 | if (data->bucket_size) + | ^~~~~~~~~~~~~~~~~~~~~~ + 182 | bucket = latency / data->bucket_size; +src/timerlat_hist.c:175:12: note: initialize the variable 'bucket' to silence this warning + 175 | int bucket; + | ^ + | = 0 +1 warning generated. + +This is a legit warning, but data->bucket_size is always > 0 (see +timerlat_hist_parse_args()), so the if is not necessary. + +Remove the unneeded if (data->bucket_size) to avoid the warning. + +Link: https://lkml.kernel.org/r/6e1b1665cd99042ae705b3e0fc410858c4c42346.1707217097.git.bristot@kernel.org + +Cc: stable@vger.kernel.org +Cc: Masami Hiramatsu +Cc: Nathan Chancellor +Cc: Nick Desaulniers +Cc: Bill Wendling +Cc: Justin Stitt +Cc: Donald Zickus +Fixes: 1eeb6328e8b3 ("rtla/timerlat: Add timerlat hist mode") +Fixes: 829a6c0b5698 ("rtla/osnoise: Add the hist mode") +Signed-off-by: Daniel Bristot de Oliveira +Signed-off-by: Greg Kroah-Hartman +--- + tools/tracing/rtla/src/osnoise_hist.c | 3 +-- + tools/tracing/rtla/src/timerlat_hist.c | 3 +-- + 2 files changed, 2 insertions(+), 4 deletions(-) + +--- a/tools/tracing/rtla/src/osnoise_hist.c ++++ b/tools/tracing/rtla/src/osnoise_hist.c +@@ -129,8 +129,7 @@ static void osnoise_hist_update_multiple + if (params->output_divisor) + duration = duration / params->output_divisor; + +- if (data->bucket_size) +- bucket = duration / data->bucket_size; ++ bucket = duration / data->bucket_size; + + total_duration = duration * count; + +--- a/tools/tracing/rtla/src/timerlat_hist.c ++++ b/tools/tracing/rtla/src/timerlat_hist.c +@@ -151,8 +151,7 @@ timerlat_hist_update(struct osnoise_tool + if (params->output_divisor) + latency = latency / params->output_divisor; + +- if (data->bucket_size) +- bucket = latency / data->bucket_size; ++ bucket = latency / data->bucket_size; + + if (!thread) { + hist = data->hist[cpu].irq; diff --git a/queue-6.1/tools-rtla-remove-unused-sched_getattr-function.patch b/queue-6.1/tools-rtla-remove-unused-sched_getattr-function.patch new file mode 100644 index 00000000000..3934ab5d2f3 --- /dev/null +++ b/queue-6.1/tools-rtla-remove-unused-sched_getattr-function.patch @@ -0,0 +1,52 @@ +From 084ce16df0f060efd371092a09a7ae74a536dc11 Mon Sep 17 00:00:00 2001 +From: Daniel Bristot de Oliveira +Date: Tue, 6 Feb 2024 12:05:32 +0100 +Subject: tools/rtla: Remove unused sched_getattr() function + +From: Daniel Bristot de Oliveira + +commit 084ce16df0f060efd371092a09a7ae74a536dc11 upstream. + +Clang is reporting: + +$ make HOSTCC=clang CC=clang LLVM_IAS=1 +[...] +clang -O -g -DVERSION=\"6.8.0-rc3\" -flto=auto -fexceptions -fstack-protector-strong -fasynchronous-unwind-tables -fstack-clash-protection -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS $(pkg-config --cflags libtracefs) -c -o src/utils.o src/utils.c +src/utils.c:241:19: warning: unused function 'sched_getattr' [-Wunused-function] + 241 | static inline int sched_getattr(pid_t pid, struct sched_attr *attr, + | ^~~~~~~~~~~~~ +1 warning generated. + +Which is correct, so remove the unused function. + +Link: https://lkml.kernel.org/r/eaed7ba122c4ae88ce71277c824ef41cbf789385.1707217097.git.bristot@kernel.org + +Cc: stable@vger.kernel.org +Cc: Masami Hiramatsu +Cc: Nathan Chancellor +Cc: Nick Desaulniers +Cc: Bill Wendling +Cc: Justin Stitt +Cc: Donald Zickus +Fixes: b1696371d865 ("rtla: Helper functions for rtla") +Signed-off-by: Daniel Bristot de Oliveira +Signed-off-by: Greg Kroah-Hartman +--- + tools/tracing/rtla/src/utils.c | 6 ------ + 1 file changed, 6 deletions(-) + +--- a/tools/tracing/rtla/src/utils.c ++++ b/tools/tracing/rtla/src/utils.c +@@ -243,12 +243,6 @@ static inline int sched_setattr(pid_t pi + return syscall(__NR_sched_setattr, pid, attr, flags); + } + +-static inline int sched_getattr(pid_t pid, struct sched_attr *attr, +- unsigned int size, unsigned int flags) +-{ +- return syscall(__NR_sched_getattr, pid, attr, size, flags); +-} +- + int __set_sched_attr(int pid, struct sched_attr *attr) + { + int flags = 0; diff --git a/queue-6.1/tools-rtla-replace-setting-prio-with-nice-for-sched_other.patch b/queue-6.1/tools-rtla-replace-setting-prio-with-nice-for-sched_other.patch new file mode 100644 index 00000000000..48540df0917 --- /dev/null +++ b/queue-6.1/tools-rtla-replace-setting-prio-with-nice-for-sched_other.patch @@ -0,0 +1,55 @@ +From 14f08c976ffe0d2117c6199c32663df1cbc45c65 Mon Sep 17 00:00:00 2001 +From: limingming3 +Date: Wed, 7 Feb 2024 14:51:42 +0800 +Subject: tools/rtla: Replace setting prio with nice for SCHED_OTHER + +From: limingming3 + +commit 14f08c976ffe0d2117c6199c32663df1cbc45c65 upstream. + +Since the sched_priority for SCHED_OTHER is always 0, it makes no +sence to set it. +Setting nice for SCHED_OTHER seems more meaningful. + +Link: https://lkml.kernel.org/r/20240207065142.1753909-1-limingming3@lixiang.com + +Cc: stable@vger.kernel.org +Fixes: b1696371d865 ("rtla: Helper functions for rtla") +Signed-off-by: limingming3 +Signed-off-by: Daniel Bristot de Oliveira +Signed-off-by: Greg Kroah-Hartman +--- + tools/tracing/rtla/src/utils.c | 6 +++--- + tools/tracing/rtla/src/utils.h | 2 ++ + 2 files changed, 5 insertions(+), 3 deletions(-) + +--- a/tools/tracing/rtla/src/utils.c ++++ b/tools/tracing/rtla/src/utils.c +@@ -478,13 +478,13 @@ int parse_prio(char *arg, struct sched_a + if (prio == INVALID_VAL) + return -1; + +- if (prio < sched_get_priority_min(SCHED_OTHER)) ++ if (prio < MIN_NICE) + return -1; +- if (prio > sched_get_priority_max(SCHED_OTHER)) ++ if (prio > MAX_NICE) + return -1; + + sched_param->sched_policy = SCHED_OTHER; +- sched_param->sched_priority = prio; ++ sched_param->sched_nice = prio; + break; + default: + return -1; +--- a/tools/tracing/rtla/src/utils.h ++++ b/tools/tracing/rtla/src/utils.h +@@ -7,6 +7,8 @@ + */ + #define BUFF_U64_STR_SIZE 24 + #define MAX_PATH 1024 ++#define MAX_NICE 20 ++#define MIN_NICE -19 + + #define container_of(ptr, type, member)({ \ + const typeof(((type *)0)->member) *__mptr = (ptr); \ diff --git a/queue-6.1/wifi-cfg80211-fix-wiphy-delayed-work-queueing.patch b/queue-6.1/wifi-cfg80211-fix-wiphy-delayed-work-queueing.patch new file mode 100644 index 00000000000..4d11443a85f --- /dev/null +++ b/queue-6.1/wifi-cfg80211-fix-wiphy-delayed-work-queueing.patch @@ -0,0 +1,37 @@ +From b743287d7a0007493f5cada34ed2085d475050b4 Mon Sep 17 00:00:00 2001 +From: Johannes Berg +Date: Thu, 25 Jan 2024 09:51:09 +0100 +Subject: wifi: cfg80211: fix wiphy delayed work queueing + +From: Johannes Berg + +commit b743287d7a0007493f5cada34ed2085d475050b4 upstream. + +When a wiphy work is queued with timer, and then again +without a delay, it's started immediately but *also* +started again after the timer expires. This can lead, +for example, to warnings in mac80211's offchannel code +as reported by Jouni. Running the same work twice isn't +expected, of course. Fix this by deleting the timer at +this point, when queuing immediately due to delay=0. + +Cc: stable@vger.kernel.org +Reported-by: Jouni Malinen +Fixes: a3ee4dc84c4e ("wifi: cfg80211: add a work abstraction with special semantics") +Link: https://msgid.link/20240125095108.2feb0eaaa446.I4617f3210ed0e7f252290d5970dac6a876aa595b@changeid +Signed-off-by: Johannes Berg +Signed-off-by: Greg Kroah-Hartman +--- + net/wireless/core.c | 1 + + 1 file changed, 1 insertion(+) + +--- a/net/wireless/core.c ++++ b/net/wireless/core.c +@@ -1671,6 +1671,7 @@ void wiphy_delayed_work_queue(struct wip + unsigned long delay) + { + if (!delay) { ++ del_timer(&dwork->timer); + wiphy_work_queue(wiphy, &dwork->work); + return; + } diff --git a/queue-6.1/wifi-mac80211-reload-info-pointer-in-ieee80211_tx_dequeue.patch b/queue-6.1/wifi-mac80211-reload-info-pointer-in-ieee80211_tx_dequeue.patch new file mode 100644 index 00000000000..ed25a29dfa7 --- /dev/null +++ b/queue-6.1/wifi-mac80211-reload-info-pointer-in-ieee80211_tx_dequeue.patch @@ -0,0 +1,51 @@ +From c98d8836b817d11fdff4ca7749cbbe04ff7f0c64 Mon Sep 17 00:00:00 2001 +From: Johannes Berg +Date: Wed, 31 Jan 2024 16:49:10 +0100 +Subject: wifi: mac80211: reload info pointer in ieee80211_tx_dequeue() + +From: Johannes Berg + +commit c98d8836b817d11fdff4ca7749cbbe04ff7f0c64 upstream. + +This pointer can change here since the SKB can change, so we +actually later open-coded IEEE80211_SKB_CB() again. Reload +the pointer where needed, so the monitor-mode case using it +gets fixed, and then use info-> later as well. + +Cc: stable@vger.kernel.org +Fixes: 531682159092 ("mac80211: fix VLAN handling with TXQs") +Link: https://msgid.link/20240131164910.b54c28d583bc.I29450cec84ea6773cff5d9c16ff92b836c331471@changeid +Signed-off-by: Johannes Berg +Signed-off-by: Greg Kroah-Hartman +--- + net/mac80211/tx.c | 5 +++-- + 1 file changed, 3 insertions(+), 2 deletions(-) + +--- a/net/mac80211/tx.c ++++ b/net/mac80211/tx.c +@@ -5,7 +5,7 @@ + * Copyright 2006-2007 Jiri Benc + * Copyright 2007 Johannes Berg + * Copyright 2013-2014 Intel Mobile Communications GmbH +- * Copyright (C) 2018-2022 Intel Corporation ++ * Copyright (C) 2018-2024 Intel Corporation + * + * Transmit and frame generation functions. + */ +@@ -3838,6 +3838,7 @@ begin: + goto begin; + + skb = __skb_dequeue(&tx.skbs); ++ info = IEEE80211_SKB_CB(skb); + + if (!skb_queue_empty(&tx.skbs)) { + spin_lock_bh(&fq->lock); +@@ -3882,7 +3883,7 @@ begin: + } + + encap_out: +- IEEE80211_SKB_CB(skb)->control.vif = vif; ++ info->control.vif = vif; + + if (tx.sta && + wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) { diff --git a/queue-6.1/zonefs-improve-error-handling.patch b/queue-6.1/zonefs-improve-error-handling.patch new file mode 100644 index 00000000000..af93f1facb0 --- /dev/null +++ b/queue-6.1/zonefs-improve-error-handling.patch @@ -0,0 +1,252 @@ +From 14db5f64a971fce3d8ea35de4dfc7f443a3efb92 Mon Sep 17 00:00:00 2001 +From: Damien Le Moal +Date: Thu, 8 Feb 2024 17:26:59 +0900 +Subject: zonefs: Improve error handling + +From: Damien Le Moal + +commit 14db5f64a971fce3d8ea35de4dfc7f443a3efb92 upstream. + +Write error handling is racy and can sometime lead to the error recovery +path wrongly changing the inode size of a sequential zone file to an +incorrect value which results in garbage data being readable at the end +of a file. There are 2 problems: + +1) zonefs_file_dio_write() updates a zone file write pointer offset + after issuing a direct IO with iomap_dio_rw(). This update is done + only if the IO succeed for synchronous direct writes. However, for + asynchronous direct writes, the update is done without waiting for + the IO completion so that the next asynchronous IO can be + immediately issued. However, if an asynchronous IO completes with a + failure right before the i_truncate_mutex lock protecting the update, + the update may change the value of the inode write pointer offset + that was corrected by the error path (zonefs_io_error() function). + +2) zonefs_io_error() is called when a read or write error occurs. This + function executes a report zone operation using the callback function + zonefs_io_error_cb(), which does all the error recovery handling + based on the current zone condition, write pointer position and + according to the mount options being used. However, depending on the + zoned device being used, a report zone callback may be executed in a + context that is different from the context of __zonefs_io_error(). As + a result, zonefs_io_error_cb() may be executed without the inode + truncate mutex lock held, which can lead to invalid error processing. + +Fix both problems as follows: +- Problem 1: Perform the inode write pointer offset update before a + direct write is issued with iomap_dio_rw(). This is safe to do as + partial direct writes are not supported (IOMAP_DIO_PARTIAL is not + set) and any failed IO will trigger the execution of zonefs_io_error() + which will correct the inode write pointer offset to reflect the + current state of the one on the device. +- Problem 2: Change zonefs_io_error_cb() into zonefs_handle_io_error() + and call this function directly from __zonefs_io_error() after + obtaining the zone information using blkdev_report_zones() with a + simple callback function that copies to a local stack variable the + struct blk_zone obtained from the device. This ensures that error + handling is performed holding the inode truncate mutex. + This change also simplifies error handling for conventional zone files + by bypassing the execution of report zones entirely. This is safe to + do because the condition of conventional zones cannot be read-only or + offline and conventional zone files are always fully mapped with a + constant file size. + +Reported-by: Shin'ichiro Kawasaki +Fixes: 8dcc1a9d90c1 ("fs: New zonefs file system") +Cc: stable@vger.kernel.org +Signed-off-by: Damien Le Moal +Tested-by: Shin'ichiro Kawasaki +Reviewed-by: Johannes Thumshirn +Reviewed-by: Himanshu Madhani +Signed-off-by: Greg Kroah-Hartman +--- + fs/zonefs/file.c | 42 +++++++++++++++++++++------------ + fs/zonefs/super.c | 68 ++++++++++++++++++++++++++++++------------------------ + 2 files changed, 66 insertions(+), 44 deletions(-) + +--- a/fs/zonefs/file.c ++++ b/fs/zonefs/file.c +@@ -349,7 +349,12 @@ static int zonefs_file_write_dio_end_io( + struct zonefs_inode_info *zi = ZONEFS_I(inode); + + if (error) { +- zonefs_io_error(inode, true); ++ /* ++ * For Sync IOs, error recovery is called from ++ * zonefs_file_dio_write(). ++ */ ++ if (!is_sync_kiocb(iocb)) ++ zonefs_io_error(inode, true); + return error; + } + +@@ -577,6 +582,14 @@ static ssize_t zonefs_file_dio_write(str + ret = -EINVAL; + goto inode_unlock; + } ++ /* ++ * Advance the zone write pointer offset. This assumes that the ++ * IO will succeed, which is OK to do because we do not allow ++ * partial writes (IOMAP_DIO_PARTIAL is not set) and if the IO ++ * fails, the error path will correct the write pointer offset. ++ */ ++ z->z_wpoffset += count; ++ zonefs_inode_account_active(inode); + mutex_unlock(&zi->i_truncate_mutex); + append = sync; + } +@@ -596,20 +609,19 @@ static ssize_t zonefs_file_dio_write(str + ret = -EBUSY; + } + +- if (zonefs_zone_is_seq(z) && +- (ret > 0 || ret == -EIOCBQUEUED)) { +- if (ret > 0) +- count = ret; +- +- /* +- * Update the zone write pointer offset assuming the write +- * operation succeeded. If it did not, the error recovery path +- * will correct it. Also do active seq file accounting. +- */ +- mutex_lock(&zi->i_truncate_mutex); +- z->z_wpoffset += count; +- zonefs_inode_account_active(inode); +- mutex_unlock(&zi->i_truncate_mutex); ++ /* ++ * For a failed IO or partial completion, trigger error recovery ++ * to update the zone write pointer offset to a correct value. ++ * For asynchronous IOs, zonefs_file_write_dio_end_io() may already ++ * have executed error recovery if the IO already completed when we ++ * reach here. However, we cannot know that and execute error recovery ++ * again (that will not change anything). ++ */ ++ if (zonefs_zone_is_seq(z)) { ++ if (ret > 0 && ret != count) ++ ret = -EIO; ++ if (ret < 0 && ret != -EIOCBQUEUED) ++ zonefs_io_error(inode, true); + } + + inode_unlock: +--- a/fs/zonefs/super.c ++++ b/fs/zonefs/super.c +@@ -245,16 +245,18 @@ static void zonefs_inode_update_mode(str + z->z_flags &= ~ZONEFS_ZONE_INIT_MODE; + } + +-struct zonefs_ioerr_data { +- struct inode *inode; +- bool write; +-}; +- + static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, + void *data) + { +- struct zonefs_ioerr_data *err = data; +- struct inode *inode = err->inode; ++ struct blk_zone *z = data; ++ ++ *z = *zone; ++ return 0; ++} ++ ++static void zonefs_handle_io_error(struct inode *inode, struct blk_zone *zone, ++ bool write) ++{ + struct zonefs_zone *z = zonefs_inode_zone(inode); + struct super_block *sb = inode->i_sb; + struct zonefs_sb_info *sbi = ZONEFS_SB(sb); +@@ -269,8 +271,8 @@ static int zonefs_io_error_cb(struct blk + data_size = zonefs_check_zone_condition(sb, z, zone); + isize = i_size_read(inode); + if (!(z->z_flags & (ZONEFS_ZONE_READONLY | ZONEFS_ZONE_OFFLINE)) && +- !err->write && isize == data_size) +- return 0; ++ !write && isize == data_size) ++ return; + + /* + * At this point, we detected either a bad zone or an inconsistency +@@ -291,7 +293,7 @@ static int zonefs_io_error_cb(struct blk + * In all cases, warn about inode size inconsistency and handle the + * IO error according to the zone condition and to the mount options. + */ +- if (zonefs_zone_is_seq(z) && isize != data_size) ++ if (isize != data_size) + zonefs_warn(sb, + "inode %lu: invalid size %lld (should be %lld)\n", + inode->i_ino, isize, data_size); +@@ -351,8 +353,6 @@ static int zonefs_io_error_cb(struct blk + zonefs_i_size_write(inode, data_size); + z->z_wpoffset = data_size; + zonefs_inode_account_active(inode); +- +- return 0; + } + + /* +@@ -366,23 +366,25 @@ void __zonefs_io_error(struct inode *ino + { + struct zonefs_zone *z = zonefs_inode_zone(inode); + struct super_block *sb = inode->i_sb; +- struct zonefs_sb_info *sbi = ZONEFS_SB(sb); + unsigned int noio_flag; +- unsigned int nr_zones = 1; +- struct zonefs_ioerr_data err = { +- .inode = inode, +- .write = write, +- }; ++ struct blk_zone zone; + int ret; + + /* +- * The only files that have more than one zone are conventional zone +- * files with aggregated conventional zones, for which the inode zone +- * size is always larger than the device zone size. +- */ +- if (z->z_size > bdev_zone_sectors(sb->s_bdev)) +- nr_zones = z->z_size >> +- (sbi->s_zone_sectors_shift + SECTOR_SHIFT); ++ * Conventional zone have no write pointer and cannot become read-only ++ * or offline. So simply fake a report for a single or aggregated zone ++ * and let zonefs_handle_io_error() correct the zone inode information ++ * according to the mount options. ++ */ ++ if (!zonefs_zone_is_seq(z)) { ++ zone.start = z->z_sector; ++ zone.len = z->z_size >> SECTOR_SHIFT; ++ zone.wp = zone.start + zone.len; ++ zone.type = BLK_ZONE_TYPE_CONVENTIONAL; ++ zone.cond = BLK_ZONE_COND_NOT_WP; ++ zone.capacity = zone.len; ++ goto handle_io_error; ++ } + + /* + * Memory allocations in blkdev_report_zones() can trigger a memory +@@ -393,12 +395,20 @@ void __zonefs_io_error(struct inode *ino + * the GFP_NOIO context avoids both problems. + */ + noio_flag = memalloc_noio_save(); +- ret = blkdev_report_zones(sb->s_bdev, z->z_sector, nr_zones, +- zonefs_io_error_cb, &err); +- if (ret != nr_zones) ++ ret = blkdev_report_zones(sb->s_bdev, z->z_sector, 1, ++ zonefs_io_error_cb, &zone); ++ memalloc_noio_restore(noio_flag); ++ ++ if (ret != 1) { + zonefs_err(sb, "Get inode %lu zone information failed %d\n", + inode->i_ino, ret); +- memalloc_noio_restore(noio_flag); ++ zonefs_warn(sb, "remounting filesystem read-only\n"); ++ sb->s_flags |= SB_RDONLY; ++ return; ++ } ++ ++handle_io_error: ++ zonefs_handle_io_error(inode, &zone, write); + } + + static struct kmem_cache *zonefs_inode_cachep;