From 6bba280ae245c394859f2aa7f24208ac5f02cc6c Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Sat, 15 Jun 2024 22:01:15 -0400 Subject: [PATCH] Fixes for 6.6 Signed-off-by: Sasha Levin --- ...-data-races-around-sk-sk_state-for-w.patch | 88 ++++++ ...-data-race-of-net-unx.sysctl_max_dgr.patch | 38 +++ ...-data-race-of-sk-sk_shutdown-in-sk_d.patch | 37 +++ ...-data-race-of-sk-sk_state-in-unix_in.patch | 50 +++ ...-data-race-of-sk-sk_state-in-unix_st.patch | 60 ++++ ...-race-of-sk-sk_state-in-unix_st.patch-2156 | 39 +++ ...otate-data-races-around-sk-sk_sndbuf.patch | 57 ++++ ...-data-races-around-sk-sk_state-in-se.patch | 72 +++++ ...-data-races-around-sk-sk_state-in-un.patch | 128 ++++++++ ...races-around-sk-sk_state-in-un.patch-11288 | 71 +++++ ...k_state-under-unix_state_lock-for-tr.patch | 90 ++++++ ...queue_empty_lockless-in-unix_release.patch | 44 +++ ...queue_len_lockless-in-sk_diag_show_r.patch | 41 +++ ..._recvq_full_lockless-in-unix_stream_.patch | 72 +++++ ...unt-imbalance-on-inbound-connections.patch | 93 ++++++ ...ee-in-ax25_dev_free-with-ax25_dev_pu.patch | 39 +++ ...tial-use-after-free-in-bpf_link_free.patch | 74 +++++ ...fix-multi-uprobe-pid-filtering-logic.patch | 87 ++++++ .../bpf-optimize-the-free-of-inner-map.patch | 146 +++++++++ ...-context-for-rawtp-test_run-callback.patch | 52 ++++ ...r_offsets-values-in-bpf_uprobe-array.patch | 89 ++++++ ...ll-the-eventfs_inodes-from-the-event.patch | 119 ++++++++ ...erflow-when-setting-values-via-sysfs.patch | 80 +++++ ...t-of-bounds-in-ext4_mb_find_good_gro.patch | 148 +++++++++ ...-refactor-out-ext4_generic_attr_show.patch | 132 ++++++++ ...m-disable-clocks-if-qcom_scm_bw_enab.patch | 98 ++++++ ...distinguish-reset-from-.ndo_bpf-in-x.patch | 181 +++++++++++ ...ion-of-tlvs-in-preserved-fields-area.patch | 124 ++++++++ .../ice-remove-af_xdp_zc_qps-bitmap.patch | 170 +++++++++++ ...ssible-race-in-__fib6_drop_pcpu_from.patch | 130 ++++++++ ...ipv6-ioam-block-bh-from-ioam6_output.patch | 65 ++++ ...-in-seg6_output_core-and-seg6_input_.patch | 94 ++++++ ...tc-allow-large-non-standard-interrup.patch | 98 ++++++ ...tc-introduce-andes-hart-level-interr.patch | 196 ++++++++++++ ...tc-prevent-memory-leak-when-riscv_in.patch | 55 ++++ ...em-instead-of-rwlock-for-lease-break.patch | 287 ++++++++++++++++++ ...ntercept-accesses-to-msr_ia32_xss-fo.patch | 111 +++++++ ...ate-lbr-virtualization-to-the-proces.patch | 148 +++++++++ ...low-sev-es-guests-when-x86_feature_l.patch | 100 ++++++ ...-failure-use-a-folio-in-me_huge_page.patch | 63 ++++ ...e-fix-handling-of-dissolved-but-not-.patch | 147 +++++++++ ...e-wait-sockets-for-mptcp_mib_currest.patch | 61 ++++ ...the-error-condition-in-ethtool_get_p.patch | 44 +++ ...stop-health-timer-during-driver-remo.patch | 105 +++++++ ...nted-pointer-delete-is-case-of-flow-.patch | 51 ++++ ...iting-for-pci-if-pci-channel-is-offl.patch | 86 ++++++ ...e-multi-thread-manner-of-ncsi-driver.patch | 220 ++++++++++++++ ...si-simplify-kconfig-dts-control-flow.patch | 152 ++++++++++ ...ix-ksz9477-phy-issues-after-suspend-.patch | 125 ++++++++ ...sz8061-fix-errata-solution-not-takin.patch | 96 ++++++ ...ltiq-fix-possible-oob-write-in-multi.patch | 38 +++ ...-always-validate-tca_taprio_attr_pri.patch | 63 ++++ ...erwriting-when-adjusting-sock-bufsiz.patch | 68 +++++ ...tls-fix-marking-packets-as-decrypted.patch | 46 +++ ...x-tainted-pointer-delete-is-case-of-.patch | 44 +++ ..._empty_dir-misjudgment-and-long-loop.patch | 51 ++++ ...e-mapped-address-from-nilfs_get_page.patch | 146 +++++++++ ...ays-allocate-pf-entries-from-low-pri.patch | 87 ++++++ ...r-message-on-failed-pin-verification.patch | 42 +++ ...ncorrect-reg_subtype-labels-in-kvm_r.patch | 45 +++ ...ed-to-use-mask-when-hart-index-bit-i.patch | 48 +++ ...-error-output-and-clean-up-ufshcd_mc.patch | 86 ++++++ ...paction_test-fix-bogus-test-success-.patch | 109 +++++++ ...mm-conform-test-to-tap-format-output.patch | 229 ++++++++++++++ ...-a-consistent-test-name-for-check_co.patch | 124 ++++++++ queue-6.6/series | 80 +++++ ...e-wait-sockets-for-tcp_mib_currestab.patch | 71 +++++ ...rx-data-ring-on-dma-allocation-failu.patch | 116 +++++++ ...sion-when-dropping-packets-due-to-in.patch | 65 ++++ ...lly-move-wiphy-work-to-unbound-workq.patch | 62 ++++ ...1-lock-wiphy-in-cfg80211_get_station.patch | 103 +++++++ ...msr-use-correct-nla_get_ux-functions.patch | 85 ++++++ ..._ini-move-iwl_dbg_tlv_free-outside-o.patch | 41 +++ ...-check-n_ssids-before-accessing-the-.patch | 49 +++ ...-mvm-don-t-initialize-csa_work-twice.patch | 39 +++ ...-don-t-read-past-the-mfuart-notifcat.patch | 55 ++++ ...mvm-revert-gen2-tx-a-mpdu-size-to-64.patch | 49 +++ ...-iwlwifi-mvm-set-properly-mac-header.patch | 45 +++ ...rrectly-parse-spatial-reuse-paramete.patch | 65 ++++ ...x-deadlock-in-ieee80211_sta_ps_deliv.patch | 109 +++++++ ...sh-fix-leak-of-mesh_preq_queue-objec.patch | 100 ++++++ 81 files changed, 7313 insertions(+) create mode 100644 queue-6.6/af_unix-annodate-data-races-around-sk-sk_state-for-w.patch create mode 100644 queue-6.6/af_unix-annotate-data-race-of-net-unx.sysctl_max_dgr.patch create mode 100644 queue-6.6/af_unix-annotate-data-race-of-sk-sk_shutdown-in-sk_d.patch create mode 100644 queue-6.6/af_unix-annotate-data-race-of-sk-sk_state-in-unix_in.patch create mode 100644 queue-6.6/af_unix-annotate-data-race-of-sk-sk_state-in-unix_st.patch create mode 100644 queue-6.6/af_unix-annotate-data-race-of-sk-sk_state-in-unix_st.patch-2156 create mode 100644 queue-6.6/af_unix-annotate-data-races-around-sk-sk_sndbuf.patch create mode 100644 queue-6.6/af_unix-annotate-data-races-around-sk-sk_state-in-se.patch create mode 100644 queue-6.6/af_unix-annotate-data-races-around-sk-sk_state-in-un.patch create mode 100644 queue-6.6/af_unix-annotate-data-races-around-sk-sk_state-in-un.patch-11288 create mode 100644 queue-6.6/af_unix-set-sk-sk_state-under-unix_state_lock-for-tr.patch create mode 100644 queue-6.6/af_unix-use-skb_queue_empty_lockless-in-unix_release.patch create mode 100644 queue-6.6/af_unix-use-skb_queue_len_lockless-in-sk_diag_show_r.patch create mode 100644 queue-6.6/af_unix-use-unix_recvq_full_lockless-in-unix_stream_.patch create mode 100644 queue-6.6/ax25-fix-refcount-imbalance-on-inbound-connections.patch create mode 100644 queue-6.6/ax25-replace-kfree-in-ax25_dev_free-with-ax25_dev_pu.patch create mode 100644 queue-6.6/bpf-fix-a-potential-use-after-free-in-bpf_link_free.patch create mode 100644 queue-6.6/bpf-fix-multi-uprobe-pid-filtering-logic.patch create mode 100644 queue-6.6/bpf-optimize-the-free-of-inner-map.patch create mode 100644 queue-6.6/bpf-set-run-context-for-rawtp-test_run-callback.patch create mode 100644 queue-6.6/bpf-store-ref_ctr_offsets-values-in-bpf_uprobe-array.patch create mode 100644 queue-6.6/eventfs-update-all-the-eventfs_inodes-from-the-event.patch create mode 100644 queue-6.6/ext4-avoid-overflow-when-setting-values-via-sysfs.patch create mode 100644 queue-6.6/ext4-fix-slab-out-of-bounds-in-ext4_mb_find_good_gro.patch create mode 100644 queue-6.6/ext4-refactor-out-ext4_generic_attr_show.patch create mode 100644 queue-6.6/firmware-qcom_scm-disable-clocks-if-qcom_scm_bw_enab.patch create mode 100644 queue-6.6/ice-add-flag-to-distinguish-reset-from-.ndo_bpf-in-x.patch create mode 100644 queue-6.6/ice-fix-iteration-of-tlvs-in-preserved-fields-area.patch create mode 100644 queue-6.6/ice-remove-af_xdp_zc_qps-bitmap.patch create mode 100644 queue-6.6/ipv6-fix-possible-race-in-__fib6_drop_pcpu_from.patch create mode 100644 queue-6.6/ipv6-ioam-block-bh-from-ioam6_output.patch create mode 100644 queue-6.6/ipv6-sr-block-bh-in-seg6_output_core-and-seg6_input_.patch create mode 100644 queue-6.6/irqchip-riscv-intc-allow-large-non-standard-interrup.patch create mode 100644 queue-6.6/irqchip-riscv-intc-introduce-andes-hart-level-interr.patch create mode 100644 queue-6.6/irqchip-riscv-intc-prevent-memory-leak-when-riscv_in.patch create mode 100644 queue-6.6/ksmbd-use-rwsem-instead-of-rwlock-for-lease-break.patch create mode 100644 queue-6.6/kvm-sev-do-not-intercept-accesses-to-msr_ia32_xss-fo.patch create mode 100644 queue-6.6/kvm-sev-es-delegate-lbr-virtualization-to-the-proces.patch create mode 100644 queue-6.6/kvm-sev-es-disallow-sev-es-guests-when-x86_feature_l.patch create mode 100644 queue-6.6/memory-failure-use-a-folio-in-me_huge_page.patch create mode 100644 queue-6.6/mm-memory-failure-fix-handling-of-dissolved-but-not-.patch create mode 100644 queue-6.6/mptcp-count-close-wait-sockets-for-mptcp_mib_currest.patch create mode 100644 queue-6.6/net-ethtool-fix-the-error-condition-in-ethtool_get_p.patch create mode 100644 queue-6.6/net-mlx5-always-stop-health-timer-during-driver-remo.patch create mode 100644 queue-6.6/net-mlx5-fix-tainted-pointer-delete-is-case-of-flow-.patch create mode 100644 queue-6.6/net-mlx5-stop-waiting-for-pci-if-pci-channel-is-offl.patch create mode 100644 queue-6.6/net-ncsi-fix-the-multi-thread-manner-of-ncsi-driver.patch create mode 100644 queue-6.6/net-ncsi-simplify-kconfig-dts-control-flow.patch create mode 100644 queue-6.6/net-phy-micrel-fix-ksz9477-phy-issues-after-suspend-.patch create mode 100644 queue-6.6/net-phy-micrel-ksz8061-fix-errata-solution-not-takin.patch create mode 100644 queue-6.6/net-sched-sch_multiq-fix-possible-oob-write-in-multi.patch create mode 100644 queue-6.6/net-sched-taprio-always-validate-tca_taprio_attr_pri.patch create mode 100644 queue-6.6/net-smc-avoid-overwriting-when-adjusting-sock-bufsiz.patch create mode 100644 queue-6.6/net-tls-fix-marking-packets-as-decrypted.patch create mode 100644 queue-6.6/net-wwan-iosm-fix-tainted-pointer-delete-is-case-of-.patch create mode 100644 queue-6.6/nilfs2-fix-nilfs_empty_dir-misjudgment-and-long-loop.patch create mode 100644 queue-6.6/nilfs2-return-the-mapped-address-from-nilfs_get_page.patch create mode 100644 queue-6.6/octeontx2-af-always-allocate-pf-entries-from-low-pri.patch create mode 100644 queue-6.6/ptp-fix-error-message-on-failed-pin-verification.patch create mode 100644 queue-6.6/risc-v-kvm-fix-incorrect-reg_subtype-labels-in-kvm_r.patch create mode 100644 queue-6.6/risc-v-kvm-no-need-to-use-mask-when-hart-index-bit-i.patch create mode 100644 queue-6.6/scsi-ufs-mcq-fix-error-output-and-clean-up-ufshcd_mc.patch create mode 100644 queue-6.6/selftests-mm-compaction_test-fix-bogus-test-success-.patch create mode 100644 queue-6.6/selftests-mm-conform-test-to-tap-format-output.patch create mode 100644 queue-6.6/selftests-mm-log-a-consistent-test-name-for-check_co.patch create mode 100644 queue-6.6/tcp-count-close-wait-sockets-for-tcp_mib_currestab.patch create mode 100644 queue-6.6/vmxnet3-disable-rx-data-ring-on-dma-allocation-failu.patch create mode 100644 queue-6.6/vxlan-fix-regression-when-dropping-packets-due-to-in.patch create mode 100644 queue-6.6/wifi-cfg80211-fully-move-wiphy-work-to-unbound-workq.patch create mode 100644 queue-6.6/wifi-cfg80211-lock-wiphy-in-cfg80211_get_station.patch create mode 100644 queue-6.6/wifi-cfg80211-pmsr-use-correct-nla_get_ux-functions.patch create mode 100644 queue-6.6/wifi-iwlwifi-dbg_ini-move-iwl_dbg_tlv_free-outside-o.patch create mode 100644 queue-6.6/wifi-iwlwifi-mvm-check-n_ssids-before-accessing-the-.patch create mode 100644 queue-6.6/wifi-iwlwifi-mvm-don-t-initialize-csa_work-twice.patch create mode 100644 queue-6.6/wifi-iwlwifi-mvm-don-t-read-past-the-mfuart-notifcat.patch create mode 100644 queue-6.6/wifi-iwlwifi-mvm-revert-gen2-tx-a-mpdu-size-to-64.patch create mode 100644 queue-6.6/wifi-iwlwifi-mvm-set-properly-mac-header.patch create mode 100644 queue-6.6/wifi-mac80211-correctly-parse-spatial-reuse-paramete.patch create mode 100644 queue-6.6/wifi-mac80211-fix-deadlock-in-ieee80211_sta_ps_deliv.patch create mode 100644 queue-6.6/wifi-mac80211-mesh-fix-leak-of-mesh_preq_queue-objec.patch diff --git a/queue-6.6/af_unix-annodate-data-races-around-sk-sk_state-for-w.patch b/queue-6.6/af_unix-annodate-data-races-around-sk-sk_state-for-w.patch new file mode 100644 index 00000000000..7c6aac2a03d --- /dev/null +++ b/queue-6.6/af_unix-annodate-data-races-around-sk-sk_state-for-w.patch @@ -0,0 +1,88 @@ +From 7396984c57611b2d5fa829452d2a13999a574330 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 09:52:28 -0700 +Subject: af_unix: Annodate data-races around sk->sk_state for writers. + +From: Kuniyuki Iwashima + +[ Upstream commit 942238f9735a4a4ebf8274b218d9a910158941d1 ] + +sk->sk_state is changed under unix_state_lock(), but it's read locklessly +in many places. + +This patch adds WRITE_ONCE() on the writer side. + +We will add READ_ONCE() to the lockless readers in the following patches. + +Fixes: 83301b5367a9 ("af_unix: Set TCP_ESTABLISHED for datagram sockets too") +Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") +Signed-off-by: Kuniyuki Iwashima +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/unix/af_unix.c | 14 ++++++++------ + 1 file changed, 8 insertions(+), 6 deletions(-) + +diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c +index 348f9e34f6696..bd2af62f58605 100644 +--- a/net/unix/af_unix.c ++++ b/net/unix/af_unix.c +@@ -617,7 +617,7 @@ static void unix_release_sock(struct sock *sk, int embrion) + u->path.dentry = NULL; + u->path.mnt = NULL; + state = sk->sk_state; +- sk->sk_state = TCP_CLOSE; ++ WRITE_ONCE(sk->sk_state, TCP_CLOSE); + + skpair = unix_peer(sk); + unix_peer(sk) = NULL; +@@ -739,7 +739,8 @@ static int unix_listen(struct socket *sock, int backlog) + if (backlog > sk->sk_max_ack_backlog) + wake_up_interruptible_all(&u->peer_wait); + sk->sk_max_ack_backlog = backlog; +- sk->sk_state = TCP_LISTEN; ++ WRITE_ONCE(sk->sk_state, TCP_LISTEN); ++ + /* set credentials so connect can copy them */ + init_peercred(sk); + err = 0; +@@ -1411,7 +1412,8 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, + if (err) + goto out_unlock; + +- sk->sk_state = other->sk_state = TCP_ESTABLISHED; ++ WRITE_ONCE(sk->sk_state, TCP_ESTABLISHED); ++ WRITE_ONCE(other->sk_state, TCP_ESTABLISHED); + } else { + /* + * 1003.1g breaking connected state with AF_UNSPEC +@@ -1428,7 +1430,7 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, + + unix_peer(sk) = other; + if (!other) +- sk->sk_state = TCP_CLOSE; ++ WRITE_ONCE(sk->sk_state, TCP_CLOSE); + unix_dgram_peer_wake_disconnect_wakeup(sk, old_peer); + + unix_state_double_unlock(sk, other); +@@ -1644,7 +1646,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, + copy_peercred(sk, other); + + sock->state = SS_CONNECTED; +- sk->sk_state = TCP_ESTABLISHED; ++ WRITE_ONCE(sk->sk_state, TCP_ESTABLISHED); + sock_hold(newsk); + + smp_mb__after_atomic(); /* sock_hold() does an atomic_inc() */ +@@ -2027,7 +2029,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, + unix_peer(sk) = NULL; + unix_dgram_peer_wake_disconnect_wakeup(sk, other); + +- sk->sk_state = TCP_CLOSE; ++ WRITE_ONCE(sk->sk_state, TCP_CLOSE); + unix_state_unlock(sk); + + unix_dgram_disconnected(sk, other); +-- +2.43.0 + diff --git a/queue-6.6/af_unix-annotate-data-race-of-net-unx.sysctl_max_dgr.patch b/queue-6.6/af_unix-annotate-data-race-of-net-unx.sysctl_max_dgr.patch new file mode 100644 index 00000000000..7eebec27272 --- /dev/null +++ b/queue-6.6/af_unix-annotate-data-race-of-net-unx.sysctl_max_dgr.patch @@ -0,0 +1,38 @@ +From 0c145926e227ed63ed75060455dfe2b5c50ff4f2 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 09:52:37 -0700 +Subject: af_unix: Annotate data-race of net->unx.sysctl_max_dgram_qlen. + +From: Kuniyuki Iwashima + +[ Upstream commit bd9f2d05731f6a112d0c7391a0d537bfc588dbe6 ] + +net->unx.sysctl_max_dgram_qlen is exposed as a sysctl knob and can be +changed concurrently. + +Let's use READ_ONCE() in unix_create1(). + +Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") +Signed-off-by: Kuniyuki Iwashima +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/unix/af_unix.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c +index 4640497c29da4..2b35c517be718 100644 +--- a/net/unix/af_unix.c ++++ b/net/unix/af_unix.c +@@ -990,7 +990,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, + sk->sk_hash = unix_unbound_hash(sk); + sk->sk_allocation = GFP_KERNEL_ACCOUNT; + sk->sk_write_space = unix_write_space; +- sk->sk_max_ack_backlog = net->unx.sysctl_max_dgram_qlen; ++ sk->sk_max_ack_backlog = READ_ONCE(net->unx.sysctl_max_dgram_qlen); + sk->sk_destruct = unix_sock_destructor; + u = unix_sk(sk); + u->inflight = 0; +-- +2.43.0 + diff --git a/queue-6.6/af_unix-annotate-data-race-of-sk-sk_shutdown-in-sk_d.patch b/queue-6.6/af_unix-annotate-data-race-of-sk-sk_shutdown-in-sk_d.patch new file mode 100644 index 00000000000..4acd7eaeb25 --- /dev/null +++ b/queue-6.6/af_unix-annotate-data-race-of-sk-sk_shutdown-in-sk_d.patch @@ -0,0 +1,37 @@ +From 77bbbdb45d0c9fb6b4366fcd23f3e79327a4415e Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 09:52:41 -0700 +Subject: af_unix: Annotate data-race of sk->sk_shutdown in sk_diag_fill(). + +From: Kuniyuki Iwashima + +[ Upstream commit efaf24e30ec39ebbea9112227485805a48b0ceb1 ] + +While dumping sockets via UNIX_DIAG, we do not hold unix_state_lock(). + +Let's use READ_ONCE() to read sk->sk_shutdown. + +Fixes: e4e541a84863 ("sock-diag: Report shutdown for inet and unix sockets (v2)") +Signed-off-by: Kuniyuki Iwashima +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/unix/diag.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/net/unix/diag.c b/net/unix/diag.c +index fc56244214c30..1de7500b41b61 100644 +--- a/net/unix/diag.c ++++ b/net/unix/diag.c +@@ -165,7 +165,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r + sock_diag_put_meminfo(sk, skb, UNIX_DIAG_MEMINFO)) + goto out_nlmsg_trim; + +- if (nla_put_u8(skb, UNIX_DIAG_SHUTDOWN, sk->sk_shutdown)) ++ if (nla_put_u8(skb, UNIX_DIAG_SHUTDOWN, READ_ONCE(sk->sk_shutdown))) + goto out_nlmsg_trim; + + if ((req->udiag_show & UDIAG_SHOW_UID) && +-- +2.43.0 + diff --git a/queue-6.6/af_unix-annotate-data-race-of-sk-sk_state-in-unix_in.patch b/queue-6.6/af_unix-annotate-data-race-of-sk-sk_state-in-unix_in.patch new file mode 100644 index 00000000000..6165b0ae4ea --- /dev/null +++ b/queue-6.6/af_unix-annotate-data-race-of-sk-sk_state-in-unix_in.patch @@ -0,0 +1,50 @@ +From ae32731906e3462330643d827d6fb88c170bf792 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 09:52:29 -0700 +Subject: af_unix: Annotate data-race of sk->sk_state in unix_inq_len(). + +From: Kuniyuki Iwashima + +[ Upstream commit 3a0f38eb285c8c2eead4b3230c7ac2983707599d ] + +ioctl(SIOCINQ) calls unix_inq_len() that checks sk->sk_state first +and returns -EINVAL if it's TCP_LISTEN. + +Then, for SOCK_STREAM sockets, unix_inq_len() returns the number of +bytes in recvq. + +However, unix_inq_len() does not hold unix_state_lock(), and the +concurrent listen() might change the state after checking sk->sk_state. + +If the race occurs, 0 is returned for the listener, instead of -EINVAL, +because the length of skb with embryo is 0. + +We could hold unix_state_lock() in unix_inq_len(), but it's overkill +given the result is true for pre-listen() TCP_CLOSE state. + +So, let's use READ_ONCE() for sk->sk_state in unix_inq_len(). + +Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") +Signed-off-by: Kuniyuki Iwashima +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/unix/af_unix.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c +index bd2af62f58605..8d0918a112a9d 100644 +--- a/net/unix/af_unix.c ++++ b/net/unix/af_unix.c +@@ -2983,7 +2983,7 @@ long unix_inq_len(struct sock *sk) + struct sk_buff *skb; + long amount = 0; + +- if (sk->sk_state == TCP_LISTEN) ++ if (READ_ONCE(sk->sk_state) == TCP_LISTEN) + return -EINVAL; + + spin_lock(&sk->sk_receive_queue.lock); +-- +2.43.0 + diff --git a/queue-6.6/af_unix-annotate-data-race-of-sk-sk_state-in-unix_st.patch b/queue-6.6/af_unix-annotate-data-race-of-sk-sk_state-in-unix_st.patch new file mode 100644 index 00000000000..247bd10dbde --- /dev/null +++ b/queue-6.6/af_unix-annotate-data-race-of-sk-sk_state-in-unix_st.patch @@ -0,0 +1,60 @@ +From 9ca458fd70435e9c3615e46bf42aa05e30144e1f Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 09:52:31 -0700 +Subject: af_unix: Annotate data-race of sk->sk_state in unix_stream_connect(). + +From: Kuniyuki Iwashima + +[ Upstream commit a9bf9c7dc6a5899c01cb8f6e773a66315a5cd4b7 ] + +As small optimisation, unix_stream_connect() prefetches the client's +sk->sk_state without unix_state_lock() and checks if it's TCP_CLOSE. + +Later, sk->sk_state is checked again under unix_state_lock(). + +Let's use READ_ONCE() for the first check and TCP_CLOSE directly for +the second check. + +Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") +Signed-off-by: Kuniyuki Iwashima +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/unix/af_unix.c | 7 ++----- + 1 file changed, 2 insertions(+), 5 deletions(-) + +diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c +index 4a43091c95419..53d67d540a574 100644 +--- a/net/unix/af_unix.c ++++ b/net/unix/af_unix.c +@@ -1491,7 +1491,6 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, + struct sk_buff *skb = NULL; + long timeo; + int err; +- int st; + + err = unix_validate_addr(sunaddr, addr_len); + if (err) +@@ -1577,9 +1576,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, + + Well, and we have to recheck the state after socket locked. + */ +- st = sk->sk_state; +- +- switch (st) { ++ switch (READ_ONCE(sk->sk_state)) { + case TCP_CLOSE: + /* This is ok... continue with connect */ + break; +@@ -1594,7 +1591,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, + + unix_state_lock_nested(sk, U_LOCK_SECOND); + +- if (sk->sk_state != st) { ++ if (sk->sk_state != TCP_CLOSE) { + unix_state_unlock(sk); + unix_state_unlock(other); + sock_put(other); +-- +2.43.0 + diff --git a/queue-6.6/af_unix-annotate-data-race-of-sk-sk_state-in-unix_st.patch-2156 b/queue-6.6/af_unix-annotate-data-race-of-sk-sk_state-in-unix_st.patch-2156 new file mode 100644 index 00000000000..6e6889fb0a3 --- /dev/null +++ b/queue-6.6/af_unix-annotate-data-race-of-sk-sk_state-in-unix_st.patch-2156 @@ -0,0 +1,39 @@ +From bf16a061d15cca7a40cde9ac0dc06f4d9452d3a3 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 09:52:34 -0700 +Subject: af_unix: Annotate data-race of sk->sk_state in + unix_stream_read_skb(). + +From: Kuniyuki Iwashima + +[ Upstream commit af4c733b6b1aded4dc808fafece7dfe6e9d2ebb3 ] + +unix_stream_read_skb() is called from sk->sk_data_ready() context +where unix_state_lock() is not held. + +Let's use READ_ONCE() there. + +Fixes: 77462de14a43 ("af_unix: Add read_sock for stream socket types") +Signed-off-by: Kuniyuki Iwashima +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/unix/af_unix.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c +index dfa013283f478..2299a464c602e 100644 +--- a/net/unix/af_unix.c ++++ b/net/unix/af_unix.c +@@ -2630,7 +2630,7 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, + + static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor) + { +- if (unlikely(sk->sk_state != TCP_ESTABLISHED)) ++ if (unlikely(READ_ONCE(sk->sk_state) != TCP_ESTABLISHED)) + return -ENOTCONN; + + return unix_read_skb(sk, recv_actor); +-- +2.43.0 + diff --git a/queue-6.6/af_unix-annotate-data-races-around-sk-sk_sndbuf.patch b/queue-6.6/af_unix-annotate-data-races-around-sk-sk_sndbuf.patch new file mode 100644 index 00000000000..46ce515f0ec --- /dev/null +++ b/queue-6.6/af_unix-annotate-data-races-around-sk-sk_sndbuf.patch @@ -0,0 +1,57 @@ +From 690aaeb9c70d88aa1165eec8297415ca0cf130e4 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 09:52:36 -0700 +Subject: af_unix: Annotate data-races around sk->sk_sndbuf. + +From: Kuniyuki Iwashima + +[ Upstream commit b0632e53e0da8054e36bc973f0eec69d30f1b7c6 ] + +sk_setsockopt() changes sk->sk_sndbuf under lock_sock(), but it's +not used in af_unix.c. + +Let's use READ_ONCE() to read sk->sk_sndbuf in unix_writable(), +unix_dgram_sendmsg(), and unix_stream_sendmsg(). + +Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") +Signed-off-by: Kuniyuki Iwashima +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/unix/af_unix.c | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c +index 2299a464c602e..4640497c29da4 100644 +--- a/net/unix/af_unix.c ++++ b/net/unix/af_unix.c +@@ -534,7 +534,7 @@ static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other) + static int unix_writable(const struct sock *sk, unsigned char state) + { + return state != TCP_LISTEN && +- (refcount_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf; ++ (refcount_read(&sk->sk_wmem_alloc) << 2) <= READ_ONCE(sk->sk_sndbuf); + } + + static void unix_write_space(struct sock *sk) +@@ -1944,7 +1944,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, + } + + err = -EMSGSIZE; +- if (len > sk->sk_sndbuf - 32) ++ if (len > READ_ONCE(sk->sk_sndbuf) - 32) + goto out; + + if (len > SKB_MAX_ALLOC) { +@@ -2223,7 +2223,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, + &err, 0); + } else { + /* Keep two messages in the pipe so it schedules better */ +- size = min_t(int, size, (sk->sk_sndbuf >> 1) - 64); ++ size = min_t(int, size, (READ_ONCE(sk->sk_sndbuf) >> 1) - 64); + + /* allow fallback to order-0 allocations */ + size = min_t(int, size, SKB_MAX_HEAD(0) + UNIX_SKB_FRAGS_SZ); +-- +2.43.0 + diff --git a/queue-6.6/af_unix-annotate-data-races-around-sk-sk_state-in-se.patch b/queue-6.6/af_unix-annotate-data-races-around-sk-sk_state-in-se.patch new file mode 100644 index 00000000000..e781ee6c379 --- /dev/null +++ b/queue-6.6/af_unix-annotate-data-races-around-sk-sk_state-in-se.patch @@ -0,0 +1,72 @@ +From ba60cfb238d5a856abaf9d6ebde0b0b5be1bfd03 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 09:52:33 -0700 +Subject: af_unix: Annotate data-races around sk->sk_state in sendmsg() and + recvmsg(). + +From: Kuniyuki Iwashima + +[ Upstream commit 8a34d4e8d9742a24f74998f45a6a98edd923319b ] + +The following functions read sk->sk_state locklessly and proceed only if +the state is TCP_ESTABLISHED. + + * unix_stream_sendmsg + * unix_stream_read_generic + * unix_seqpacket_sendmsg + * unix_seqpacket_recvmsg + +Let's use READ_ONCE() there. + +Fixes: a05d2ad1c1f3 ("af_unix: Only allow recv on connected seqpacket sockets.") +Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") +Signed-off-by: Kuniyuki Iwashima +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/unix/af_unix.c | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c +index 53d67d540a574..dfa013283f478 100644 +--- a/net/unix/af_unix.c ++++ b/net/unix/af_unix.c +@@ -2202,7 +2202,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, + } + + if (msg->msg_namelen) { +- err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP; ++ err = READ_ONCE(sk->sk_state) == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP; + goto out_err; + } else { + err = -ENOTCONN; +@@ -2316,7 +2316,7 @@ static int unix_seqpacket_sendmsg(struct socket *sock, struct msghdr *msg, + if (err) + return err; + +- if (sk->sk_state != TCP_ESTABLISHED) ++ if (READ_ONCE(sk->sk_state) != TCP_ESTABLISHED) + return -ENOTCONN; + + if (msg->msg_namelen) +@@ -2330,7 +2330,7 @@ static int unix_seqpacket_recvmsg(struct socket *sock, struct msghdr *msg, + { + struct sock *sk = sock->sk; + +- if (sk->sk_state != TCP_ESTABLISHED) ++ if (READ_ONCE(sk->sk_state) != TCP_ESTABLISHED) + return -ENOTCONN; + + return unix_dgram_recvmsg(sock, msg, size, flags); +@@ -2654,7 +2654,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, + size_t size = state->size; + unsigned int last_len; + +- if (unlikely(sk->sk_state != TCP_ESTABLISHED)) { ++ if (unlikely(READ_ONCE(sk->sk_state) != TCP_ESTABLISHED)) { + err = -EINVAL; + goto out; + } +-- +2.43.0 + diff --git a/queue-6.6/af_unix-annotate-data-races-around-sk-sk_state-in-un.patch b/queue-6.6/af_unix-annotate-data-races-around-sk-sk_state-in-un.patch new file mode 100644 index 00000000000..6628a3b27a1 --- /dev/null +++ b/queue-6.6/af_unix-annotate-data-races-around-sk-sk_state-in-un.patch @@ -0,0 +1,128 @@ +From 96f29f372dfc8cc6f4de99a692013e957b8089e5 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 09:52:30 -0700 +Subject: af_unix: Annotate data-races around sk->sk_state in + unix_write_space() and poll(). + +From: Kuniyuki Iwashima + +[ Upstream commit eb0718fb3e97ad0d6f4529b810103451c90adf94 ] + +unix_poll() and unix_dgram_poll() read sk->sk_state locklessly and +calls unix_writable() which also reads sk->sk_state without holding +unix_state_lock(). + +Let's use READ_ONCE() in unix_poll() and unix_dgram_poll() and pass +it to unix_writable(). + +While at it, we remove TCP_SYN_SENT check in unix_dgram_poll() as +that state does not exist for AF_UNIX socket since the code was added. + +Fixes: 1586a5877db9 ("af_unix: do not report POLLOUT on listeners") +Fixes: 3c73419c09a5 ("af_unix: fix 'poll for write'/ connected DGRAM sockets") +Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") +Signed-off-by: Kuniyuki Iwashima +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/unix/af_unix.c | 25 ++++++++++++------------- + 1 file changed, 12 insertions(+), 13 deletions(-) + +diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c +index 8d0918a112a9d..4a43091c95419 100644 +--- a/net/unix/af_unix.c ++++ b/net/unix/af_unix.c +@@ -531,9 +531,9 @@ static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other) + return 0; + } + +-static int unix_writable(const struct sock *sk) ++static int unix_writable(const struct sock *sk, unsigned char state) + { +- return sk->sk_state != TCP_LISTEN && ++ return state != TCP_LISTEN && + (refcount_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf; + } + +@@ -542,7 +542,7 @@ static void unix_write_space(struct sock *sk) + struct socket_wq *wq; + + rcu_read_lock(); +- if (unix_writable(sk)) { ++ if (unix_writable(sk, READ_ONCE(sk->sk_state))) { + wq = rcu_dereference(sk->sk_wq); + if (skwq_has_sleeper(wq)) + wake_up_interruptible_sync_poll(&wq->wait, +@@ -3095,12 +3095,14 @@ static int unix_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon + static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wait) + { + struct sock *sk = sock->sk; ++ unsigned char state; + __poll_t mask; + u8 shutdown; + + sock_poll_wait(file, sock, wait); + mask = 0; + shutdown = READ_ONCE(sk->sk_shutdown); ++ state = READ_ONCE(sk->sk_state); + + /* exceptional events? */ + if (READ_ONCE(sk->sk_err)) +@@ -3122,14 +3124,14 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa + + /* Connection-based need to check for termination and startup */ + if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) && +- sk->sk_state == TCP_CLOSE) ++ state == TCP_CLOSE) + mask |= EPOLLHUP; + + /* + * we set writable also when the other side has shut down the + * connection. This prevents stuck sockets. + */ +- if (unix_writable(sk)) ++ if (unix_writable(sk, state)) + mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; + + return mask; +@@ -3140,12 +3142,14 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, + { + struct sock *sk = sock->sk, *other; + unsigned int writable; ++ unsigned char state; + __poll_t mask; + u8 shutdown; + + sock_poll_wait(file, sock, wait); + mask = 0; + shutdown = READ_ONCE(sk->sk_shutdown); ++ state = READ_ONCE(sk->sk_state); + + /* exceptional events? */ + if (READ_ONCE(sk->sk_err) || +@@ -3165,19 +3169,14 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, + mask |= EPOLLIN | EPOLLRDNORM; + + /* Connection-based need to check for termination and startup */ +- if (sk->sk_type == SOCK_SEQPACKET) { +- if (sk->sk_state == TCP_CLOSE) +- mask |= EPOLLHUP; +- /* connection hasn't started yet? */ +- if (sk->sk_state == TCP_SYN_SENT) +- return mask; +- } ++ if (sk->sk_type == SOCK_SEQPACKET && state == TCP_CLOSE) ++ mask |= EPOLLHUP; + + /* No write status requested, avoid expensive OUT tests. */ + if (!(poll_requested_events(wait) & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT))) + return mask; + +- writable = unix_writable(sk); ++ writable = unix_writable(sk, state); + if (writable) { + unix_state_lock(sk); + +-- +2.43.0 + diff --git a/queue-6.6/af_unix-annotate-data-races-around-sk-sk_state-in-un.patch-11288 b/queue-6.6/af_unix-annotate-data-races-around-sk-sk_state-in-un.patch-11288 new file mode 100644 index 00000000000..ef275509633 --- /dev/null +++ b/queue-6.6/af_unix-annotate-data-races-around-sk-sk_state-in-un.patch-11288 @@ -0,0 +1,71 @@ +From 87d9c159f3e859a47af2df9f05481b8d4086b95e Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 09:52:35 -0700 +Subject: af_unix: Annotate data-races around sk->sk_state in UNIX_DIAG. + +From: Kuniyuki Iwashima + +[ Upstream commit 0aa3be7b3e1f8f997312cc4705f8165e02806f8f ] + +While dumping AF_UNIX sockets via UNIX_DIAG, sk->sk_state is read +locklessly. + +Let's use READ_ONCE() there. + +Note that the result could be inconsistent if the socket is dumped +during the state change. This is common for other SOCK_DIAG and +similar interfaces. + +Fixes: c9da99e6475f ("unix_diag: Fixup RQLEN extension report") +Fixes: 2aac7a2cb0d9 ("unix_diag: Pending connections IDs NLA") +Fixes: 45a96b9be6ec ("unix_diag: Dumping all sockets core") +Signed-off-by: Kuniyuki Iwashima +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/unix/diag.c | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +diff --git a/net/unix/diag.c b/net/unix/diag.c +index 3438b7af09af5..9151c72e742fc 100644 +--- a/net/unix/diag.c ++++ b/net/unix/diag.c +@@ -65,7 +65,7 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb) + u32 *buf; + int i; + +- if (sk->sk_state == TCP_LISTEN) { ++ if (READ_ONCE(sk->sk_state) == TCP_LISTEN) { + spin_lock(&sk->sk_receive_queue.lock); + + attr = nla_reserve(nlskb, UNIX_DIAG_ICONS, +@@ -103,7 +103,7 @@ static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb) + { + struct unix_diag_rqlen rql; + +- if (sk->sk_state == TCP_LISTEN) { ++ if (READ_ONCE(sk->sk_state) == TCP_LISTEN) { + rql.udiag_rqueue = sk->sk_receive_queue.qlen; + rql.udiag_wqueue = sk->sk_max_ack_backlog; + } else { +@@ -136,7 +136,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r + rep = nlmsg_data(nlh); + rep->udiag_family = AF_UNIX; + rep->udiag_type = sk->sk_type; +- rep->udiag_state = sk->sk_state; ++ rep->udiag_state = READ_ONCE(sk->sk_state); + rep->pad = 0; + rep->udiag_ino = sk_ino; + sock_diag_save_cookie(sk, rep->udiag_cookie); +@@ -215,7 +215,7 @@ static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) + sk_for_each(sk, &net->unx.table.buckets[slot]) { + if (num < s_num) + goto next; +- if (!(req->udiag_states & (1 << sk->sk_state))) ++ if (!(req->udiag_states & (1 << READ_ONCE(sk->sk_state)))) + goto next; + if (sk_diag_dump(sk, skb, req, sk_user_ns(skb->sk), + NETLINK_CB(cb->skb).portid, +-- +2.43.0 + diff --git a/queue-6.6/af_unix-set-sk-sk_state-under-unix_state_lock-for-tr.patch b/queue-6.6/af_unix-set-sk-sk_state-under-unix_state_lock-for-tr.patch new file mode 100644 index 00000000000..d572c25223c --- /dev/null +++ b/queue-6.6/af_unix-set-sk-sk_state-under-unix_state_lock-for-tr.patch @@ -0,0 +1,90 @@ +From e4131c30c30e955025d38f3eddc42b96a9b59f23 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 09:52:27 -0700 +Subject: af_unix: Set sk->sk_state under unix_state_lock() for truly + disconencted peer. + +From: Kuniyuki Iwashima + +[ Upstream commit 26bfb8b57063f52b867f9b6c8d1742fcb5bd656c ] + +When a SOCK_DGRAM socket connect()s to another socket, the both sockets' +sk->sk_state are changed to TCP_ESTABLISHED so that we can register them +to BPF SOCKMAP. + +When the socket disconnects from the peer by connect(AF_UNSPEC), the state +is set back to TCP_CLOSE. + +Then, the peer's state is also set to TCP_CLOSE, but the update is done +locklessly and unconditionally. + +Let's say socket A connect()ed to B, B connect()ed to C, and A disconnects +from B. + +After the first two connect()s, all three sockets' sk->sk_state are +TCP_ESTABLISHED: + + $ ss -xa + Netid State Recv-Q Send-Q Local Address:Port Peer Address:PortProcess + u_dgr ESTAB 0 0 @A 641 * 642 + u_dgr ESTAB 0 0 @B 642 * 643 + u_dgr ESTAB 0 0 @C 643 * 0 + +And after the disconnect, B's state is TCP_CLOSE even though it's still +connected to C and C's state is TCP_ESTABLISHED. + + $ ss -xa + Netid State Recv-Q Send-Q Local Address:Port Peer Address:PortProcess + u_dgr UNCONN 0 0 @A 641 * 0 + u_dgr UNCONN 0 0 @B 642 * 643 + u_dgr ESTAB 0 0 @C 643 * 0 + +In this case, we cannot register B to SOCKMAP. + +So, when a socket disconnects from the peer, we should not set TCP_CLOSE to +the peer if the peer is connected to yet another socket, and this must be +done under unix_state_lock(). + +Note that we use WRITE_ONCE() for sk->sk_state as there are many lockless +readers. These data-races will be fixed in the following patches. + +Fixes: 83301b5367a9 ("af_unix: Set TCP_ESTABLISHED for datagram sockets too") +Signed-off-by: Kuniyuki Iwashima +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/unix/af_unix.c | 10 ++++++++-- + 1 file changed, 8 insertions(+), 2 deletions(-) + +diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c +index d01314dc86ecb..348f9e34f6696 100644 +--- a/net/unix/af_unix.c ++++ b/net/unix/af_unix.c +@@ -571,7 +571,6 @@ static void unix_dgram_disconnected(struct sock *sk, struct sock *other) + sk_error_report(other); + } + } +- other->sk_state = TCP_CLOSE; + } + + static void unix_sock_destructor(struct sock *sk) +@@ -1434,8 +1433,15 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, + + unix_state_double_unlock(sk, other); + +- if (other != old_peer) ++ if (other != old_peer) { + unix_dgram_disconnected(sk, old_peer); ++ ++ unix_state_lock(old_peer); ++ if (!unix_peer(old_peer)) ++ WRITE_ONCE(old_peer->sk_state, TCP_CLOSE); ++ unix_state_unlock(old_peer); ++ } ++ + sock_put(old_peer); + } else { + unix_peer(sk) = other; +-- +2.43.0 + diff --git a/queue-6.6/af_unix-use-skb_queue_empty_lockless-in-unix_release.patch b/queue-6.6/af_unix-use-skb_queue_empty_lockless-in-unix_release.patch new file mode 100644 index 00000000000..e337c2da299 --- /dev/null +++ b/queue-6.6/af_unix-use-skb_queue_empty_lockless-in-unix_release.patch @@ -0,0 +1,44 @@ +From 8b8be27125e368ab6283a839d16c5082142886e5 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 09:52:39 -0700 +Subject: af_unix: Use skb_queue_empty_lockless() in unix_release_sock(). + +From: Kuniyuki Iwashima + +[ Upstream commit 83690b82d228b3570565ebd0b41873933238b97f ] + +If the socket type is SOCK_STREAM or SOCK_SEQPACKET, unix_release_sock() +checks the length of the peer socket's recvq under unix_state_lock(). + +However, unix_stream_read_generic() calls skb_unlink() after releasing +the lock. Also, for SOCK_SEQPACKET, __skb_try_recv_datagram() unlinks +skb without unix_state_lock(). + +Thues, unix_state_lock() does not protect qlen. + +Let's use skb_queue_empty_lockless() in unix_release_sock(). + +Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") +Signed-off-by: Kuniyuki Iwashima +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/unix/af_unix.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c +index ea68472847cae..e6395647558af 100644 +--- a/net/unix/af_unix.c ++++ b/net/unix/af_unix.c +@@ -632,7 +632,7 @@ static void unix_release_sock(struct sock *sk, int embrion) + unix_state_lock(skpair); + /* No more writes */ + WRITE_ONCE(skpair->sk_shutdown, SHUTDOWN_MASK); +- if (!skb_queue_empty(&sk->sk_receive_queue) || embrion) ++ if (!skb_queue_empty_lockless(&sk->sk_receive_queue) || embrion) + WRITE_ONCE(skpair->sk_err, ECONNRESET); + unix_state_unlock(skpair); + skpair->sk_state_change(skpair); +-- +2.43.0 + diff --git a/queue-6.6/af_unix-use-skb_queue_len_lockless-in-sk_diag_show_r.patch b/queue-6.6/af_unix-use-skb_queue_len_lockless-in-sk_diag_show_r.patch new file mode 100644 index 00000000000..a6b07e9e388 --- /dev/null +++ b/queue-6.6/af_unix-use-skb_queue_len_lockless-in-sk_diag_show_r.patch @@ -0,0 +1,41 @@ +From 37088efe544f1bc7ccb2891d6235a1127d7cccb3 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 09:52:40 -0700 +Subject: af_unix: Use skb_queue_len_lockless() in sk_diag_show_rqlen(). + +From: Kuniyuki Iwashima + +[ Upstream commit 5d915e584d8408211d4567c22685aae8820bfc55 ] + +We can dump the socket queue length via UNIX_DIAG by specifying +UDIAG_SHOW_RQLEN. + +If sk->sk_state is TCP_LISTEN, we return the recv queue length, +but here we do not hold recvq lock. + +Let's use skb_queue_len_lockless() in sk_diag_show_rqlen(). + +Fixes: c9da99e6475f ("unix_diag: Fixup RQLEN extension report") +Signed-off-by: Kuniyuki Iwashima +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/unix/diag.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/net/unix/diag.c b/net/unix/diag.c +index 9151c72e742fc..fc56244214c30 100644 +--- a/net/unix/diag.c ++++ b/net/unix/diag.c +@@ -104,7 +104,7 @@ static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb) + struct unix_diag_rqlen rql; + + if (READ_ONCE(sk->sk_state) == TCP_LISTEN) { +- rql.udiag_rqueue = sk->sk_receive_queue.qlen; ++ rql.udiag_rqueue = skb_queue_len_lockless(&sk->sk_receive_queue); + rql.udiag_wqueue = sk->sk_max_ack_backlog; + } else { + rql.udiag_rqueue = (u32) unix_inq_len(sk); +-- +2.43.0 + diff --git a/queue-6.6/af_unix-use-unix_recvq_full_lockless-in-unix_stream_.patch b/queue-6.6/af_unix-use-unix_recvq_full_lockless-in-unix_stream_.patch new file mode 100644 index 00000000000..888c7f86bdb --- /dev/null +++ b/queue-6.6/af_unix-use-unix_recvq_full_lockless-in-unix_stream_.patch @@ -0,0 +1,72 @@ +From 245b65fb304bb39a7fc47d9c337a404606ae6779 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 09:52:38 -0700 +Subject: af_unix: Use unix_recvq_full_lockless() in unix_stream_connect(). + +From: Kuniyuki Iwashima + +[ Upstream commit 45d872f0e65593176d880ec148f41ad7c02e40a7 ] + +Once sk->sk_state is changed to TCP_LISTEN, it never changes. + +unix_accept() takes advantage of this characteristics; it does not +hold the listener's unix_state_lock() and only acquires recvq lock +to pop one skb. + +It means unix_state_lock() does not prevent the queue length from +changing in unix_stream_connect(). + +Thus, we need to use unix_recvq_full_lockless() to avoid data-race. + +Now we remove unix_recvq_full() as no one uses it. + +Note that we can remove READ_ONCE() for sk->sk_max_ack_backlog in +unix_recvq_full_lockless() because of the following reasons: + + (1) For SOCK_DGRAM, it is a written-once field in unix_create1() + + (2) For SOCK_STREAM and SOCK_SEQPACKET, it is changed under the + listener's unix_state_lock() in unix_listen(), and we hold + the lock in unix_stream_connect() + +Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") +Signed-off-by: Kuniyuki Iwashima +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/unix/af_unix.c | 10 ++-------- + 1 file changed, 2 insertions(+), 8 deletions(-) + +diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c +index 2b35c517be718..ea68472847cae 100644 +--- a/net/unix/af_unix.c ++++ b/net/unix/af_unix.c +@@ -222,15 +222,9 @@ static inline int unix_may_send(struct sock *sk, struct sock *osk) + return unix_peer(osk) == NULL || unix_our_peer(sk, osk); + } + +-static inline int unix_recvq_full(const struct sock *sk) +-{ +- return skb_queue_len(&sk->sk_receive_queue) > sk->sk_max_ack_backlog; +-} +- + static inline int unix_recvq_full_lockless(const struct sock *sk) + { +- return skb_queue_len_lockless(&sk->sk_receive_queue) > +- READ_ONCE(sk->sk_max_ack_backlog); ++ return skb_queue_len_lockless(&sk->sk_receive_queue) > sk->sk_max_ack_backlog; + } + + struct sock *unix_peer_get(struct sock *s) +@@ -1551,7 +1545,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, + if (other->sk_shutdown & RCV_SHUTDOWN) + goto out_unlock; + +- if (unix_recvq_full(other)) { ++ if (unix_recvq_full_lockless(other)) { + err = -EAGAIN; + if (!timeo) + goto out_unlock; +-- +2.43.0 + diff --git a/queue-6.6/ax25-fix-refcount-imbalance-on-inbound-connections.patch b/queue-6.6/ax25-fix-refcount-imbalance-on-inbound-connections.patch new file mode 100644 index 00000000000..b71ea7d552c --- /dev/null +++ b/queue-6.6/ax25-fix-refcount-imbalance-on-inbound-connections.patch @@ -0,0 +1,93 @@ +From 26b7c87d3ee390beec9e9518b48acb19a4ab195b Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 29 May 2024 17:02:43 -0400 +Subject: ax25: Fix refcount imbalance on inbound connections + +From: Lars Kellogg-Stedman + +[ Upstream commit 3c34fb0bd4a4237592c5ecb5b2e2531900c55774 ] + +When releasing a socket in ax25_release(), we call netdev_put() to +decrease the refcount on the associated ax.25 device. However, the +execution path for accepting an incoming connection never calls +netdev_hold(). This imbalance leads to refcount errors, and ultimately +to kernel crashes. + +A typical call trace for the above situation will start with one of the +following errors: + + refcount_t: decrement hit 0; leaking memory. + refcount_t: underflow; use-after-free. + +And will then have a trace like: + + Call Trace: + + ? show_regs+0x64/0x70 + ? __warn+0x83/0x120 + ? refcount_warn_saturate+0xb2/0x100 + ? report_bug+0x158/0x190 + ? prb_read_valid+0x20/0x30 + ? handle_bug+0x3e/0x70 + ? exc_invalid_op+0x1c/0x70 + ? asm_exc_invalid_op+0x1f/0x30 + ? refcount_warn_saturate+0xb2/0x100 + ? refcount_warn_saturate+0xb2/0x100 + ax25_release+0x2ad/0x360 + __sock_release+0x35/0xa0 + sock_close+0x19/0x20 + [...] + +On reboot (or any attempt to remove the interface), the kernel gets +stuck in an infinite loop: + + unregister_netdevice: waiting for ax0 to become free. Usage count = 0 + +This patch corrects these issues by ensuring that we call netdev_hold() +and ax25_dev_hold() for new connections in ax25_accept(). This makes the +logic leading to ax25_accept() match the logic for ax25_bind(): in both +cases we increment the refcount, which is ultimately decremented in +ax25_release(). + +Fixes: 9fd75b66b8f6 ("ax25: Fix refcount leaks caused by ax25_cb_del()") +Signed-off-by: Lars Kellogg-Stedman +Tested-by: Duoming Zhou +Tested-by: Dan Cross +Tested-by: Chris Maness +Reviewed-by: Dan Carpenter +Link: https://lore.kernel.org/r/20240529210242.3346844-2-lars@oddbit.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/ax25/af_ax25.c | 6 ++++++ + 1 file changed, 6 insertions(+) + +diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c +index 9d11d26e46c0e..26a3095bec462 100644 +--- a/net/ax25/af_ax25.c ++++ b/net/ax25/af_ax25.c +@@ -1378,8 +1378,10 @@ static int ax25_accept(struct socket *sock, struct socket *newsock, int flags, + { + struct sk_buff *skb; + struct sock *newsk; ++ ax25_dev *ax25_dev; + DEFINE_WAIT(wait); + struct sock *sk; ++ ax25_cb *ax25; + int err = 0; + + if (sock->state != SS_UNCONNECTED) +@@ -1434,6 +1436,10 @@ static int ax25_accept(struct socket *sock, struct socket *newsock, int flags, + kfree_skb(skb); + sk_acceptq_removed(sk); + newsock->state = SS_CONNECTED; ++ ax25 = sk_to_ax25(newsk); ++ ax25_dev = ax25->ax25_dev; ++ netdev_hold(ax25_dev->dev, &ax25->dev_tracker, GFP_ATOMIC); ++ ax25_dev_hold(ax25_dev); + + out: + release_sock(sk); +-- +2.43.0 + diff --git a/queue-6.6/ax25-replace-kfree-in-ax25_dev_free-with-ax25_dev_pu.patch b/queue-6.6/ax25-replace-kfree-in-ax25_dev_free-with-ax25_dev_pu.patch new file mode 100644 index 00000000000..8f7e6b69b4a --- /dev/null +++ b/queue-6.6/ax25-replace-kfree-in-ax25_dev_free-with-ax25_dev_pu.patch @@ -0,0 +1,39 @@ +From 76d3a341a96f5901a339ca0575679b60541ab59b Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 30 May 2024 13:17:33 +0800 +Subject: ax25: Replace kfree() in ax25_dev_free() with ax25_dev_put() + +From: Duoming Zhou + +[ Upstream commit 166fcf86cd34e15c7f383eda4642d7a212393008 ] + +The object "ax25_dev" is managed by reference counting. Thus it should +not be directly released by kfree(), replace with ax25_dev_put(). + +Fixes: d01ffb9eee4a ("ax25: add refcount in ax25_dev to avoid UAF bugs") +Suggested-by: Dan Carpenter +Signed-off-by: Duoming Zhou +Reviewed-by: Dan Carpenter +Link: https://lore.kernel.org/r/20240530051733.11416-1-duoming@zju.edu.cn +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/ax25/ax25_dev.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c +index c9d55b99a7a57..67ae6b8c52989 100644 +--- a/net/ax25/ax25_dev.c ++++ b/net/ax25/ax25_dev.c +@@ -193,7 +193,7 @@ void __exit ax25_dev_free(void) + list_for_each_entry_safe(s, n, &ax25_dev_list, list) { + netdev_put(s->dev, &s->dev_tracker); + list_del(&s->list); +- kfree(s); ++ ax25_dev_put(s); + } + spin_unlock_bh(&ax25_dev_lock); + } +-- +2.43.0 + diff --git a/queue-6.6/bpf-fix-a-potential-use-after-free-in-bpf_link_free.patch b/queue-6.6/bpf-fix-a-potential-use-after-free-in-bpf_link_free.patch new file mode 100644 index 00000000000..a7108f8427a --- /dev/null +++ b/queue-6.6/bpf-fix-a-potential-use-after-free-in-bpf_link_free.patch @@ -0,0 +1,74 @@ +From 52314dfb675481eed7aa68602187d9ed773a904f Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sun, 2 Jun 2024 11:27:03 -0700 +Subject: bpf: Fix a potential use-after-free in bpf_link_free() + +From: Cong Wang + +[ Upstream commit 2884dc7d08d98a89d8d65121524bb7533183a63a ] + +After commit 1a80dbcb2dba, bpf_link can be freed by +link->ops->dealloc_deferred, but the code still tests and uses +link->ops->dealloc afterward, which leads to a use-after-free as +reported by syzbot. Actually, one of them should be sufficient, so +just call one of them instead of both. Also add a WARN_ON() in case +of any problematic implementation. + +Fixes: 1a80dbcb2dba ("bpf: support deferring bpf_link dealloc to after RCU grace period") +Reported-by: syzbot+1989ee16d94720836244@syzkaller.appspotmail.com +Signed-off-by: Cong Wang +Signed-off-by: Daniel Borkmann +Acked-by: Jiri Olsa +Link: https://lore.kernel.org/bpf/20240602182703.207276-1-xiyou.wangcong@gmail.com +Signed-off-by: Sasha Levin +--- + kernel/bpf/syscall.c | 11 ++++++----- + 1 file changed, 6 insertions(+), 5 deletions(-) + +diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c +index e9a68c6043ce5..65df92f5b1922 100644 +--- a/kernel/bpf/syscall.c ++++ b/kernel/bpf/syscall.c +@@ -2830,6 +2830,7 @@ static int bpf_obj_get(const union bpf_attr *attr) + void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, + const struct bpf_link_ops *ops, struct bpf_prog *prog) + { ++ WARN_ON(ops->dealloc && ops->dealloc_deferred); + atomic64_set(&link->refcnt, 1); + link->type = type; + link->id = 0; +@@ -2888,16 +2889,17 @@ static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu) + /* bpf_link_free is guaranteed to be called from process context */ + static void bpf_link_free(struct bpf_link *link) + { ++ const struct bpf_link_ops *ops = link->ops; + bool sleepable = false; + + bpf_link_free_id(link->id); + if (link->prog) { + sleepable = link->prog->aux->sleepable; + /* detach BPF program, clean up used resources */ +- link->ops->release(link); ++ ops->release(link); + bpf_prog_put(link->prog); + } +- if (link->ops->dealloc_deferred) { ++ if (ops->dealloc_deferred) { + /* schedule BPF link deallocation; if underlying BPF program + * is sleepable, we need to first wait for RCU tasks trace + * sync, then go through "classic" RCU grace period +@@ -2906,9 +2908,8 @@ static void bpf_link_free(struct bpf_link *link) + call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp); + else + call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp); +- } +- if (link->ops->dealloc) +- link->ops->dealloc(link); ++ } else if (ops->dealloc) ++ ops->dealloc(link); + } + + static void bpf_link_put_deferred(struct work_struct *work) +-- +2.43.0 + diff --git a/queue-6.6/bpf-fix-multi-uprobe-pid-filtering-logic.patch b/queue-6.6/bpf-fix-multi-uprobe-pid-filtering-logic.patch new file mode 100644 index 00000000000..5de9ffbc28d --- /dev/null +++ b/queue-6.6/bpf-fix-multi-uprobe-pid-filtering-logic.patch @@ -0,0 +1,87 @@ +From e64fb4a765c5dfb1cd0b26f2df392c89a00ff04d Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 21 May 2024 09:33:57 -0700 +Subject: bpf: fix multi-uprobe PID filtering logic + +From: Andrii Nakryiko + +[ Upstream commit 46ba0e49b64232adac35a2bc892f1710c5b0fb7f ] + +Current implementation of PID filtering logic for multi-uprobes in +uprobe_prog_run() is filtering down to exact *thread*, while the intent +for PID filtering it to filter by *process* instead. The check in +uprobe_prog_run() also differs from the analogous one in +uprobe_multi_link_filter() for some reason. The latter is correct, +checking task->mm, not the task itself. + +Fix the check in uprobe_prog_run() to perform the same task->mm check. + +While doing this, we also update get_pid_task() use to use PIDTYPE_TGID +type of lookup, given the intent is to get a representative task of an +entire process. This doesn't change behavior, but seems more logical. It +would hold task group leader task now, not any random thread task. + +Last but not least, given multi-uprobe support is half-broken due to +this PID filtering logic (depending on whether PID filtering is +important or not), we need to make it easy for user space consumers +(including libbpf) to easily detect whether PID filtering logic was +already fixed. + +We do it here by adding an early check on passed pid parameter. If it's +negative (and so has no chance of being a valid PID), we return -EINVAL. +Previous behavior would eventually return -ESRCH ("No process found"), +given there can't be any process with negative PID. This subtle change +won't make any practical change in behavior, but will allow applications +to detect PID filtering fixes easily. Libbpf fixes take advantage of +this in the next patch. + +Cc: stable@vger.kernel.org +Acked-by: Jiri Olsa +Fixes: b733eeade420 ("bpf: Add pid filter support for uprobe_multi link") +Signed-off-by: Andrii Nakryiko +Link: https://lore.kernel.org/r/20240521163401.3005045-2-andrii@kernel.org +Signed-off-by: Alexei Starovoitov +Signed-off-by: Sasha Levin +--- + kernel/trace/bpf_trace.c | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c +index 8edbafe0d4cdf..cc29bf49f7159 100644 +--- a/kernel/trace/bpf_trace.c ++++ b/kernel/trace/bpf_trace.c +@@ -3099,7 +3099,7 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe, + struct bpf_run_ctx *old_run_ctx; + int err = 0; + +- if (link->task && current != link->task) ++ if (link->task && current->mm != link->task->mm) + return 0; + + if (sleepable) +@@ -3200,8 +3200,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr + upath = u64_to_user_ptr(attr->link_create.uprobe_multi.path); + uoffsets = u64_to_user_ptr(attr->link_create.uprobe_multi.offsets); + cnt = attr->link_create.uprobe_multi.cnt; ++ pid = attr->link_create.uprobe_multi.pid; + +- if (!upath || !uoffsets || !cnt) ++ if (!upath || !uoffsets || !cnt || pid < 0) + return -EINVAL; + if (cnt > MAX_UPROBE_MULTI_CNT) + return -E2BIG; +@@ -3225,10 +3226,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr + goto error_path_put; + } + +- pid = attr->link_create.uprobe_multi.pid; + if (pid) { + rcu_read_lock(); +- task = get_pid_task(find_vpid(pid), PIDTYPE_PID); ++ task = get_pid_task(find_vpid(pid), PIDTYPE_TGID); + rcu_read_unlock(); + if (!task) { + err = -ESRCH; +-- +2.43.0 + diff --git a/queue-6.6/bpf-optimize-the-free-of-inner-map.patch b/queue-6.6/bpf-optimize-the-free-of-inner-map.patch new file mode 100644 index 00000000000..6774ada95d3 --- /dev/null +++ b/queue-6.6/bpf-optimize-the-free-of-inner-map.patch @@ -0,0 +1,146 @@ +From 6b63e0c5b1b4a84478ad049cb4dc08ab2ab9057a Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 4 Dec 2023 22:04:23 +0800 +Subject: bpf: Optimize the free of inner map + +From: Hou Tao + +[ Upstream commit af66bfd3c8538ed21cf72af18426fc4a408665cf ] + +When removing the inner map from the outer map, the inner map will be +freed after one RCU grace period and one RCU tasks trace grace +period, so it is certain that the bpf program, which may access the +inner map, has exited before the inner map is freed. + +However there is no need to wait for one RCU tasks trace grace period if +the outer map is only accessed by non-sleepable program. So adding +sleepable_refcnt in bpf_map and increasing sleepable_refcnt when adding +the outer map into env->used_maps for sleepable program. Although the +max number of bpf program is INT_MAX - 1, the number of bpf programs +which are being loaded may be greater than INT_MAX, so using atomic64_t +instead of atomic_t for sleepable_refcnt. When removing the inner map +from the outer map, using sleepable_refcnt to decide whether or not a +RCU tasks trace grace period is needed before freeing the inner map. + +Signed-off-by: Hou Tao +Link: https://lore.kernel.org/r/20231204140425.1480317-6-houtao@huaweicloud.com +Signed-off-by: Alexei Starovoitov +Stable-dep-of: 2884dc7d08d9 ("bpf: Fix a potential use-after-free in bpf_link_free()") +Signed-off-by: Sasha Levin +--- + include/linux/bpf.h | 2 ++ + kernel/bpf/core.c | 4 ++++ + kernel/bpf/map_in_map.c | 14 +++++++++----- + kernel/bpf/syscall.c | 8 ++++++++ + kernel/bpf/verifier.c | 4 +++- + 5 files changed, 26 insertions(+), 6 deletions(-) + +diff --git a/include/linux/bpf.h b/include/linux/bpf.h +index 2ebb5d4d43dc6..e4cd28c38b825 100644 +--- a/include/linux/bpf.h ++++ b/include/linux/bpf.h +@@ -296,6 +296,8 @@ struct bpf_map { + bool bypass_spec_v1; + bool frozen; /* write-once; write-protected by freeze_mutex */ + bool free_after_mult_rcu_gp; ++ bool free_after_rcu_gp; ++ atomic64_t sleepable_refcnt; + s64 __percpu *elem_count; + }; + +diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c +index 1333273a71ded..05445a4d55181 100644 +--- a/kernel/bpf/core.c ++++ b/kernel/bpf/core.c +@@ -2673,12 +2673,16 @@ void __bpf_free_used_maps(struct bpf_prog_aux *aux, + struct bpf_map **used_maps, u32 len) + { + struct bpf_map *map; ++ bool sleepable; + u32 i; + ++ sleepable = aux->sleepable; + for (i = 0; i < len; i++) { + map = used_maps[i]; + if (map->ops->map_poke_untrack) + map->ops->map_poke_untrack(map, aux); ++ if (sleepable) ++ atomic64_dec(&map->sleepable_refcnt); + bpf_map_put(map); + } + } +diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c +index 3248ff5d81617..8ef269e66ba50 100644 +--- a/kernel/bpf/map_in_map.c ++++ b/kernel/bpf/map_in_map.c +@@ -131,12 +131,16 @@ void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) + { + struct bpf_map *inner_map = ptr; + +- /* The inner map may still be used by both non-sleepable and sleepable +- * bpf program, so free it after one RCU grace period and one tasks +- * trace RCU grace period. ++ /* Defer the freeing of inner map according to the sleepable attribute ++ * of bpf program which owns the outer map, so unnecessary waiting for ++ * RCU tasks trace grace period can be avoided. + */ +- if (need_defer) +- WRITE_ONCE(inner_map->free_after_mult_rcu_gp, true); ++ if (need_defer) { ++ if (atomic64_read(&map->sleepable_refcnt)) ++ WRITE_ONCE(inner_map->free_after_mult_rcu_gp, true); ++ else ++ WRITE_ONCE(inner_map->free_after_rcu_gp, true); ++ } + bpf_map_put(inner_map); + } + +diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c +index e886157a9efbb..e9a68c6043ce5 100644 +--- a/kernel/bpf/syscall.c ++++ b/kernel/bpf/syscall.c +@@ -753,8 +753,11 @@ void bpf_map_put(struct bpf_map *map) + /* bpf_map_free_id() must be called first */ + bpf_map_free_id(map); + ++ WARN_ON_ONCE(atomic64_read(&map->sleepable_refcnt)); + if (READ_ONCE(map->free_after_mult_rcu_gp)) + call_rcu_tasks_trace(&map->rcu, bpf_map_free_mult_rcu_gp); ++ else if (READ_ONCE(map->free_after_rcu_gp)) ++ call_rcu(&map->rcu, bpf_map_free_rcu_gp); + else + bpf_map_free_in_work(map); + } +@@ -5358,6 +5361,11 @@ static int bpf_prog_bind_map(union bpf_attr *attr) + goto out_unlock; + } + ++ /* The bpf program will not access the bpf map, but for the sake of ++ * simplicity, increase sleepable_refcnt for sleepable program as well. ++ */ ++ if (prog->aux->sleepable) ++ atomic64_inc(&map->sleepable_refcnt); + memcpy(used_maps_new, used_maps_old, + sizeof(used_maps_old[0]) * prog->aux->used_map_cnt); + used_maps_new[prog->aux->used_map_cnt] = map; +diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c +index 24d7a32f1710e..ec0464c075bb4 100644 +--- a/kernel/bpf/verifier.c ++++ b/kernel/bpf/verifier.c +@@ -17732,10 +17732,12 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) + return -E2BIG; + } + ++ if (env->prog->aux->sleepable) ++ atomic64_inc(&map->sleepable_refcnt); + /* hold the map. If the program is rejected by verifier, + * the map will be released by release_maps() or it + * will be used by the valid program until it's unloaded +- * and all maps are released in free_used_maps() ++ * and all maps are released in bpf_free_used_maps() + */ + bpf_map_inc(map); + +-- +2.43.0 + diff --git a/queue-6.6/bpf-set-run-context-for-rawtp-test_run-callback.patch b/queue-6.6/bpf-set-run-context-for-rawtp-test_run-callback.patch new file mode 100644 index 00000000000..5114d12d44d --- /dev/null +++ b/queue-6.6/bpf-set-run-context-for-rawtp-test_run-callback.patch @@ -0,0 +1,52 @@ +From 16792e4767e068eb6bdcbe4aa1378f9c556bf2bc Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 17:00:24 +0200 +Subject: bpf: Set run context for rawtp test_run callback + +From: Jiri Olsa + +[ Upstream commit d0d1df8ba18abc57f28fb3bc053b2bf319367f2c ] + +syzbot reported crash when rawtp program executed through the +test_run interface calls bpf_get_attach_cookie helper or any +other helper that touches task->bpf_ctx pointer. + +Setting the run context (task->bpf_ctx pointer) for test_run +callback. + +Fixes: 7adfc6c9b315 ("bpf: Add bpf_get_attach_cookie() BPF helper to access bpf_cookie value") +Reported-by: syzbot+3ab78ff125b7979e45f9@syzkaller.appspotmail.com +Signed-off-by: Jiri Olsa +Signed-off-by: Andrii Nakryiko +Signed-off-by: Daniel Borkmann +Closes: https://syzkaller.appspot.com/bug?extid=3ab78ff125b7979e45f9 +Link: https://lore.kernel.org/bpf/20240604150024.359247-1-jolsa@kernel.org +Signed-off-by: Sasha Levin +--- + net/bpf/test_run.c | 6 ++++++ + 1 file changed, 6 insertions(+) + +diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c +index 478ee7aba85f3..12a2934b28ffb 100644 +--- a/net/bpf/test_run.c ++++ b/net/bpf/test_run.c +@@ -707,10 +707,16 @@ static void + __bpf_prog_test_run_raw_tp(void *data) + { + struct bpf_raw_tp_test_run_info *info = data; ++ struct bpf_trace_run_ctx run_ctx = {}; ++ struct bpf_run_ctx *old_run_ctx; ++ ++ old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + + rcu_read_lock(); + info->retval = bpf_prog_run(info->prog, info->ctx); + rcu_read_unlock(); ++ ++ bpf_reset_run_ctx(old_run_ctx); + } + + int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, +-- +2.43.0 + diff --git a/queue-6.6/bpf-store-ref_ctr_offsets-values-in-bpf_uprobe-array.patch b/queue-6.6/bpf-store-ref_ctr_offsets-values-in-bpf_uprobe-array.patch new file mode 100644 index 00000000000..17c45a40034 --- /dev/null +++ b/queue-6.6/bpf-store-ref_ctr_offsets-values-in-bpf_uprobe-array.patch @@ -0,0 +1,89 @@ +From efa5a4c1a704aced85d41f838cb02edade141d99 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sat, 25 Nov 2023 20:31:26 +0100 +Subject: bpf: Store ref_ctr_offsets values in bpf_uprobe array + +From: Jiri Olsa + +[ Upstream commit 4930b7f53a298533bc31d7540b6ea8b79a000331 ] + +We will need to return ref_ctr_offsets values through link_info +interface in following change, so we need to keep them around. + +Storing ref_ctr_offsets values directly into bpf_uprobe array. + +Signed-off-by: Jiri Olsa +Signed-off-by: Andrii Nakryiko +Acked-by: Andrii Nakryiko +Acked-by: Song Liu +Link: https://lore.kernel.org/bpf/20231125193130.834322-3-jolsa@kernel.org +Stable-dep-of: 2884dc7d08d9 ("bpf: Fix a potential use-after-free in bpf_link_free()") +Signed-off-by: Sasha Levin +--- + kernel/trace/bpf_trace.c | 14 +++----------- + 1 file changed, 3 insertions(+), 11 deletions(-) + +diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c +index 1e79084a9d9d2..8edbafe0d4cdf 100644 +--- a/kernel/trace/bpf_trace.c ++++ b/kernel/trace/bpf_trace.c +@@ -3030,6 +3030,7 @@ struct bpf_uprobe_multi_link; + struct bpf_uprobe { + struct bpf_uprobe_multi_link *link; + loff_t offset; ++ unsigned long ref_ctr_offset; + u64 cookie; + struct uprobe_consumer consumer; + }; +@@ -3169,7 +3170,6 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr + { + struct bpf_uprobe_multi_link *link = NULL; + unsigned long __user *uref_ctr_offsets; +- unsigned long *ref_ctr_offsets = NULL; + struct bpf_link_primer link_primer; + struct bpf_uprobe *uprobes = NULL; + struct task_struct *task = NULL; +@@ -3244,18 +3244,12 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr + if (!uprobes || !link) + goto error_free; + +- if (uref_ctr_offsets) { +- ref_ctr_offsets = kvcalloc(cnt, sizeof(*ref_ctr_offsets), GFP_KERNEL); +- if (!ref_ctr_offsets) +- goto error_free; +- } +- + for (i = 0; i < cnt; i++) { + if (ucookies && __get_user(uprobes[i].cookie, ucookies + i)) { + err = -EFAULT; + goto error_free; + } +- if (uref_ctr_offsets && __get_user(ref_ctr_offsets[i], uref_ctr_offsets + i)) { ++ if (uref_ctr_offsets && __get_user(uprobes[i].ref_ctr_offset, uref_ctr_offsets + i)) { + err = -EFAULT; + goto error_free; + } +@@ -3286,7 +3280,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr + for (i = 0; i < cnt; i++) { + err = uprobe_register_refctr(d_real_inode(link->path.dentry), + uprobes[i].offset, +- ref_ctr_offsets ? ref_ctr_offsets[i] : 0, ++ uprobes[i].ref_ctr_offset, + &uprobes[i].consumer); + if (err) { + bpf_uprobe_unregister(&path, uprobes, i); +@@ -3298,11 +3292,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr + if (err) + goto error_free; + +- kvfree(ref_ctr_offsets); + return bpf_link_settle(&link_primer); + + error_free: +- kvfree(ref_ctr_offsets); + kvfree(uprobes); + kfree(link); + if (task) +-- +2.43.0 + diff --git a/queue-6.6/eventfs-update-all-the-eventfs_inodes-from-the-event.patch b/queue-6.6/eventfs-update-all-the-eventfs_inodes-from-the-event.patch new file mode 100644 index 00000000000..df18f178270 --- /dev/null +++ b/queue-6.6/eventfs-update-all-the-eventfs_inodes-from-the-event.patch @@ -0,0 +1,119 @@ +From 37f214b9a41fc5430db2183e843cdbbc64a8daf9 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 23 May 2024 01:14:28 -0400 +Subject: eventfs: Update all the eventfs_inodes from the events descriptor + +From: Steven Rostedt (Google) + +[ Upstream commit 340f0c7067a95281ad13734f8225f49c6cf52067 ] + +The change to update the permissions of the eventfs_inode had the +misconception that using the tracefs_inode would find all the +eventfs_inodes that have been updated and reset them on remount. +The problem with this approach is that the eventfs_inodes are freed when +they are no longer used (basically the reason the eventfs system exists). +When they are freed, the updated eventfs_inodes are not reset on a remount +because their tracefs_inodes have been freed. + +Instead, since the events directory eventfs_inode always has a +tracefs_inode pointing to it (it is not freed when finished), and the +events directory has a link to all its children, have the +eventfs_remount() function only operate on the events eventfs_inode and +have it descend into its children updating their uid and gids. + +Link: https://lore.kernel.org/all/CAK7LNARXgaWw3kH9JgrnH4vK6fr8LDkNKf3wq8NhMWJrVwJyVQ@mail.gmail.com/ +Link: https://lore.kernel.org/linux-trace-kernel/20240523051539.754424703@goodmis.org + +Cc: stable@vger.kernel.org +Cc: Masami Hiramatsu +Cc: Mark Rutland +Cc: Mathieu Desnoyers +Cc: Andrew Morton +Fixes: baa23a8d4360d ("tracefs: Reset permissions on remount if permissions are options") +Reported-by: Masahiro Yamada +Signed-off-by: Steven Rostedt (Google) +Signed-off-by: Sasha Levin +--- + fs/tracefs/event_inode.c | 51 ++++++++++++++++++++++++++++++---------- + 1 file changed, 39 insertions(+), 12 deletions(-) + +diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c +index b521e904a7ce9..b406bb3430f3d 100644 +--- a/fs/tracefs/event_inode.c ++++ b/fs/tracefs/event_inode.c +@@ -305,33 +305,60 @@ static const struct file_operations eventfs_file_operations = { + .llseek = generic_file_llseek, + }; + +-/* +- * On a remount of tracefs, if UID or GID options are set, then +- * the mount point inode permissions should be used. +- * Reset the saved permission flags appropriately. +- */ +-void eventfs_remount(struct tracefs_inode *ti, bool update_uid, bool update_gid) ++static void eventfs_set_attrs(struct eventfs_inode *ei, bool update_uid, kuid_t uid, ++ bool update_gid, kgid_t gid, int level) + { +- struct eventfs_inode *ei = ti->private; ++ struct eventfs_inode *ei_child; + +- if (!ei) ++ /* Update events// */ ++ if (WARN_ON_ONCE(level > 3)) + return; + +- if (update_uid) ++ if (update_uid) { + ei->attr.mode &= ~EVENTFS_SAVE_UID; ++ ei->attr.uid = uid; ++ } + +- if (update_gid) ++ if (update_gid) { + ei->attr.mode &= ~EVENTFS_SAVE_GID; ++ ei->attr.gid = gid; ++ } ++ ++ list_for_each_entry(ei_child, &ei->children, list) { ++ eventfs_set_attrs(ei_child, update_uid, uid, update_gid, gid, level + 1); ++ } + + if (!ei->entry_attrs) + return; + + for (int i = 0; i < ei->nr_entries; i++) { +- if (update_uid) ++ if (update_uid) { + ei->entry_attrs[i].mode &= ~EVENTFS_SAVE_UID; +- if (update_gid) ++ ei->entry_attrs[i].uid = uid; ++ } ++ if (update_gid) { + ei->entry_attrs[i].mode &= ~EVENTFS_SAVE_GID; ++ ei->entry_attrs[i].gid = gid; ++ } + } ++ ++} ++ ++/* ++ * On a remount of tracefs, if UID or GID options are set, then ++ * the mount point inode permissions should be used. ++ * Reset the saved permission flags appropriately. ++ */ ++void eventfs_remount(struct tracefs_inode *ti, bool update_uid, bool update_gid) ++{ ++ struct eventfs_inode *ei = ti->private; ++ ++ /* Only the events directory does the updates */ ++ if (!ei || !ei->is_events || ei->is_freed) ++ return; ++ ++ eventfs_set_attrs(ei, update_uid, ti->vfs_inode.i_uid, ++ update_gid, ti->vfs_inode.i_gid, 0); + } + + /* Return the evenfs_inode of the "events" directory */ +-- +2.43.0 + diff --git a/queue-6.6/ext4-avoid-overflow-when-setting-values-via-sysfs.patch b/queue-6.6/ext4-avoid-overflow-when-setting-values-via-sysfs.patch new file mode 100644 index 00000000000..8e8ce7ddf5a --- /dev/null +++ b/queue-6.6/ext4-avoid-overflow-when-setting-values-via-sysfs.patch @@ -0,0 +1,80 @@ +From 9fd5aac986651796cd9c05d89eb56da4b1700499 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 19 Mar 2024 19:33:17 +0800 +Subject: ext4: avoid overflow when setting values via sysfs + +From: Baokun Li + +[ Upstream commit 9e8e819f8f272c4e5dcd0bd6c7450e36481ed139 ] + +When setting values of type unsigned int through sysfs, we use kstrtoul() +to parse it and then truncate part of it as the final set value, when the +set value is greater than UINT_MAX, the set value will not match what we +see because of the truncation. As follows: + + $ echo 4294967296 > /sys/fs/ext4/sda/mb_max_linear_groups + $ cat /sys/fs/ext4/sda/mb_max_linear_groups + 0 + +So we use kstrtouint() to parse the attr_pointer_ui type to avoid the +inconsistency described above. In addition, a judgment is added to avoid +setting s_resv_clusters less than 0. + +Signed-off-by: Baokun Li +Reviewed-by: Jan Kara +Link: https://lore.kernel.org/r/20240319113325.3110393-2-libaokun1@huawei.com +Signed-off-by: Theodore Ts'o +Stable-dep-of: 13df4d44a3aa ("ext4: fix slab-out-of-bounds in ext4_mb_find_good_group_avg_frag_lists()") +Signed-off-by: Sasha Levin +--- + fs/ext4/sysfs.c | 11 ++++++----- + 1 file changed, 6 insertions(+), 5 deletions(-) + +diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c +index 6d332dff79ddc..ca820620b9742 100644 +--- a/fs/ext4/sysfs.c ++++ b/fs/ext4/sysfs.c +@@ -104,7 +104,7 @@ static ssize_t reserved_clusters_store(struct ext4_sb_info *sbi, + int ret; + + ret = kstrtoull(skip_spaces(buf), 0, &val); +- if (ret || val >= clusters) ++ if (ret || val >= clusters || (s64)val < 0) + return -EINVAL; + + atomic64_set(&sbi->s_resv_clusters, val); +@@ -451,7 +451,8 @@ static ssize_t ext4_attr_store(struct kobject *kobj, + s_kobj); + struct ext4_attr *a = container_of(attr, struct ext4_attr, attr); + void *ptr = calc_ptr(a, sbi); +- unsigned long t; ++ unsigned int t; ++ unsigned long lt; + int ret; + + switch (a->attr_id) { +@@ -460,7 +461,7 @@ static ssize_t ext4_attr_store(struct kobject *kobj, + case attr_pointer_ui: + if (!ptr) + return 0; +- ret = kstrtoul(skip_spaces(buf), 0, &t); ++ ret = kstrtouint(skip_spaces(buf), 0, &t); + if (ret) + return ret; + if (a->attr_ptr == ptr_ext4_super_block_offset) +@@ -471,10 +472,10 @@ static ssize_t ext4_attr_store(struct kobject *kobj, + case attr_pointer_ul: + if (!ptr) + return 0; +- ret = kstrtoul(skip_spaces(buf), 0, &t); ++ ret = kstrtoul(skip_spaces(buf), 0, <); + if (ret) + return ret; +- *((unsigned long *) ptr) = t; ++ *((unsigned long *) ptr) = lt; + return len; + case attr_inode_readahead: + return inode_readahead_blks_store(sbi, buf, len); +-- +2.43.0 + diff --git a/queue-6.6/ext4-fix-slab-out-of-bounds-in-ext4_mb_find_good_gro.patch b/queue-6.6/ext4-fix-slab-out-of-bounds-in-ext4_mb_find_good_gro.patch new file mode 100644 index 00000000000..14b20de814f --- /dev/null +++ b/queue-6.6/ext4-fix-slab-out-of-bounds-in-ext4_mb_find_good_gro.patch @@ -0,0 +1,148 @@ +From 5b3aec93e827c7c6217daec225d3881015346967 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 19 Mar 2024 19:33:20 +0800 +Subject: ext4: fix slab-out-of-bounds in + ext4_mb_find_good_group_avg_frag_lists() + +From: Baokun Li + +[ Upstream commit 13df4d44a3aaabe61cd01d277b6ee23ead2a5206 ] + +We can trigger a slab-out-of-bounds with the following commands: + + mkfs.ext4 -F /dev/$disk 10G + mount /dev/$disk /tmp/test + echo 2147483647 > /sys/fs/ext4/$disk/mb_group_prealloc + echo test > /tmp/test/file && sync + +================================================================== +BUG: KASAN: slab-out-of-bounds in ext4_mb_find_good_group_avg_frag_lists+0x8a/0x200 [ext4] +Read of size 8 at addr ffff888121b9d0f0 by task kworker/u2:0/11 +CPU: 0 PID: 11 Comm: kworker/u2:0 Tainted: GL 6.7.0-next-20240118 #521 +Call Trace: + dump_stack_lvl+0x2c/0x50 + kasan_report+0xb6/0xf0 + ext4_mb_find_good_group_avg_frag_lists+0x8a/0x200 [ext4] + ext4_mb_regular_allocator+0x19e9/0x2370 [ext4] + ext4_mb_new_blocks+0x88a/0x1370 [ext4] + ext4_ext_map_blocks+0x14f7/0x2390 [ext4] + ext4_map_blocks+0x569/0xea0 [ext4] + ext4_do_writepages+0x10f6/0x1bc0 [ext4] +[...] +================================================================== + +The flow of issue triggering is as follows: + +// Set s_mb_group_prealloc to 2147483647 via sysfs +ext4_mb_new_blocks + ext4_mb_normalize_request + ext4_mb_normalize_group_request + ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_mb_group_prealloc + ext4_mb_regular_allocator + ext4_mb_choose_next_group + ext4_mb_choose_next_group_best_avail + mb_avg_fragment_size_order + order = fls(len) - 2 = 29 + ext4_mb_find_good_group_avg_frag_lists + frag_list = &sbi->s_mb_avg_fragment_size[order] + if (list_empty(frag_list)) // Trigger SOOB! + +At 4k block size, the length of the s_mb_avg_fragment_size list is 14, +but an oversized s_mb_group_prealloc is set, causing slab-out-of-bounds +to be triggered by an attempt to access an element at index 29. + +Add a new attr_id attr_clusters_in_group with values in the range +[0, sbi->s_clusters_per_group] and declare mb_group_prealloc as +that type to fix the issue. In addition avoid returning an order +from mb_avg_fragment_size_order() greater than MB_NUM_ORDERS(sb) +and reduce some useless loops. + +Fixes: 7e170922f06b ("ext4: Add allocation criteria 1.5 (CR1_5)") +CC: stable@vger.kernel.org +Signed-off-by: Baokun Li +Reviewed-by: Jan Kara +Reviewed-by: Ojaswin Mujoo +Link: https://lore.kernel.org/r/20240319113325.3110393-5-libaokun1@huawei.com +Signed-off-by: Theodore Ts'o +Signed-off-by: Sasha Levin +--- + fs/ext4/mballoc.c | 4 ++++ + fs/ext4/sysfs.c | 13 ++++++++++++- + 2 files changed, 16 insertions(+), 1 deletion(-) + +diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c +index aadfeb0f5b7f3..f55ab800a7539 100644 +--- a/fs/ext4/mballoc.c ++++ b/fs/ext4/mballoc.c +@@ -831,6 +831,8 @@ static int mb_avg_fragment_size_order(struct super_block *sb, ext4_grpblk_t len) + return 0; + if (order == MB_NUM_ORDERS(sb)) + order--; ++ if (WARN_ON_ONCE(order > MB_NUM_ORDERS(sb))) ++ order = MB_NUM_ORDERS(sb) - 1; + return order; + } + +@@ -1008,6 +1010,8 @@ static void ext4_mb_choose_next_group_best_avail(struct ext4_allocation_context + * goal length. + */ + order = fls(ac->ac_g_ex.fe_len) - 1; ++ if (WARN_ON_ONCE(order - 1 > MB_NUM_ORDERS(ac->ac_sb))) ++ order = MB_NUM_ORDERS(ac->ac_sb); + min_order = order - sbi->s_mb_best_avail_max_trim_order; + if (min_order < 0) + min_order = 0; +diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c +index 295ea9a32de91..ca66e33f61815 100644 +--- a/fs/ext4/sysfs.c ++++ b/fs/ext4/sysfs.c +@@ -29,6 +29,7 @@ typedef enum { + attr_trigger_test_error, + attr_first_error_time, + attr_last_error_time, ++ attr_clusters_in_group, + attr_feature, + attr_pointer_ui, + attr_pointer_ul, +@@ -207,13 +208,14 @@ EXT4_ATTR_FUNC(sra_exceeded_retry_limit, 0444); + + EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, inode_readahead, + ext4_sb_info, s_inode_readahead_blks); ++EXT4_ATTR_OFFSET(mb_group_prealloc, 0644, clusters_in_group, ++ ext4_sb_info, s_mb_group_prealloc); + EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal); + EXT4_RW_ATTR_SBI_UI(mb_stats, s_mb_stats); + EXT4_RW_ATTR_SBI_UI(mb_max_to_scan, s_mb_max_to_scan); + EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan); + EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs); + EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request); +-EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc); + EXT4_RW_ATTR_SBI_UI(mb_max_linear_groups, s_mb_max_linear_groups); + EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb); + EXT4_ATTR(trigger_fs_error, 0200, trigger_test_error); +@@ -376,6 +378,7 @@ static ssize_t ext4_generic_attr_show(struct ext4_attr *a, + + switch (a->attr_id) { + case attr_inode_readahead: ++ case attr_clusters_in_group: + case attr_pointer_ui: + if (a->attr_ptr == ptr_ext4_super_block_offset) + return sysfs_emit(buf, "%u\n", le32_to_cpup(ptr)); +@@ -459,6 +462,14 @@ static ssize_t ext4_attr_store(struct kobject *kobj, + else + *((unsigned int *) ptr) = t; + return len; ++ case attr_clusters_in_group: ++ ret = kstrtouint(skip_spaces(buf), 0, &t); ++ if (ret) ++ return ret; ++ if (t > sbi->s_clusters_per_group) ++ return -EINVAL; ++ *((unsigned int *) ptr) = t; ++ return len; + case attr_pointer_ul: + if (!ptr) + return 0; +-- +2.43.0 + diff --git a/queue-6.6/ext4-refactor-out-ext4_generic_attr_show.patch b/queue-6.6/ext4-refactor-out-ext4_generic_attr_show.patch new file mode 100644 index 00000000000..30d2b9883e4 --- /dev/null +++ b/queue-6.6/ext4-refactor-out-ext4_generic_attr_show.patch @@ -0,0 +1,132 @@ +From ab049cbb779321b16f125be5e86889cc6c96892f Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 19 Mar 2024 19:33:19 +0800 +Subject: ext4: refactor out ext4_generic_attr_show() + +From: Baokun Li + +[ Upstream commit 57341fe3179c7694c92dcf99e7f836cee4c800dd ] + +Refactor out the function ext4_generic_attr_show() to handle the reading +of values of various common types, with no functional changes. + +Signed-off-by: Baokun Li +Reviewed-by: Zhang Yi +Reviewed-by: Jan Kara +Link: https://lore.kernel.org/r/20240319113325.3110393-4-libaokun1@huawei.com +Signed-off-by: Theodore Ts'o +Stable-dep-of: 13df4d44a3aa ("ext4: fix slab-out-of-bounds in ext4_mb_find_good_group_avg_frag_lists()") +Signed-off-by: Sasha Levin +--- + fs/ext4/sysfs.c | 74 +++++++++++++++++++++---------------------------- + 1 file changed, 32 insertions(+), 42 deletions(-) + +diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c +index ca820620b9742..295ea9a32de91 100644 +--- a/fs/ext4/sysfs.c ++++ b/fs/ext4/sysfs.c +@@ -366,13 +366,42 @@ static ssize_t __print_tstamp(char *buf, __le32 lo, __u8 hi) + #define print_tstamp(buf, es, tstamp) \ + __print_tstamp(buf, (es)->tstamp, (es)->tstamp ## _hi) + ++static ssize_t ext4_generic_attr_show(struct ext4_attr *a, ++ struct ext4_sb_info *sbi, char *buf) ++{ ++ void *ptr = calc_ptr(a, sbi); ++ ++ if (!ptr) ++ return 0; ++ ++ switch (a->attr_id) { ++ case attr_inode_readahead: ++ case attr_pointer_ui: ++ if (a->attr_ptr == ptr_ext4_super_block_offset) ++ return sysfs_emit(buf, "%u\n", le32_to_cpup(ptr)); ++ return sysfs_emit(buf, "%u\n", *((unsigned int *) ptr)); ++ case attr_pointer_ul: ++ return sysfs_emit(buf, "%lu\n", *((unsigned long *) ptr)); ++ case attr_pointer_u8: ++ return sysfs_emit(buf, "%u\n", *((unsigned char *) ptr)); ++ case attr_pointer_u64: ++ if (a->attr_ptr == ptr_ext4_super_block_offset) ++ return sysfs_emit(buf, "%llu\n", le64_to_cpup(ptr)); ++ return sysfs_emit(buf, "%llu\n", *((unsigned long long *) ptr)); ++ case attr_pointer_string: ++ return sysfs_emit(buf, "%.*s\n", a->attr_size, (char *) ptr); ++ case attr_pointer_atomic: ++ return sysfs_emit(buf, "%d\n", atomic_read((atomic_t *) ptr)); ++ } ++ return 0; ++} ++ + static ssize_t ext4_attr_show(struct kobject *kobj, + struct attribute *attr, char *buf) + { + struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info, + s_kobj); + struct ext4_attr *a = container_of(attr, struct ext4_attr, attr); +- void *ptr = calc_ptr(a, sbi); + + switch (a->attr_id) { + case attr_delayed_allocation_blocks: +@@ -391,45 +420,6 @@ static ssize_t ext4_attr_show(struct kobject *kobj, + return sysfs_emit(buf, "%llu\n", + (unsigned long long) + percpu_counter_sum(&sbi->s_sra_exceeded_retry_limit)); +- case attr_inode_readahead: +- case attr_pointer_ui: +- if (!ptr) +- return 0; +- if (a->attr_ptr == ptr_ext4_super_block_offset) +- return sysfs_emit(buf, "%u\n", +- le32_to_cpup(ptr)); +- else +- return sysfs_emit(buf, "%u\n", +- *((unsigned int *) ptr)); +- case attr_pointer_ul: +- if (!ptr) +- return 0; +- return sysfs_emit(buf, "%lu\n", +- *((unsigned long *) ptr)); +- case attr_pointer_u8: +- if (!ptr) +- return 0; +- return sysfs_emit(buf, "%u\n", +- *((unsigned char *) ptr)); +- case attr_pointer_u64: +- if (!ptr) +- return 0; +- if (a->attr_ptr == ptr_ext4_super_block_offset) +- return sysfs_emit(buf, "%llu\n", +- le64_to_cpup(ptr)); +- else +- return sysfs_emit(buf, "%llu\n", +- *((unsigned long long *) ptr)); +- case attr_pointer_string: +- if (!ptr) +- return 0; +- return sysfs_emit(buf, "%.*s\n", a->attr_size, +- (char *) ptr); +- case attr_pointer_atomic: +- if (!ptr) +- return 0; +- return sysfs_emit(buf, "%d\n", +- atomic_read((atomic_t *) ptr)); + case attr_feature: + return sysfs_emit(buf, "supported\n"); + case attr_first_error_time: +@@ -438,9 +428,9 @@ static ssize_t ext4_attr_show(struct kobject *kobj, + return print_tstamp(buf, sbi->s_es, s_last_error_time); + case attr_journal_task: + return journal_task_show(sbi, buf); ++ default: ++ return ext4_generic_attr_show(a, sbi, buf); + } +- +- return 0; + } + + static ssize_t ext4_attr_store(struct kobject *kobj, +-- +2.43.0 + diff --git a/queue-6.6/firmware-qcom_scm-disable-clocks-if-qcom_scm_bw_enab.patch b/queue-6.6/firmware-qcom_scm-disable-clocks-if-qcom_scm_bw_enab.patch new file mode 100644 index 00000000000..49ab0dded0d --- /dev/null +++ b/queue-6.6/firmware-qcom_scm-disable-clocks-if-qcom_scm_bw_enab.patch @@ -0,0 +1,98 @@ +From 3b0bc94bf5ada503debb1d6a2e20004f57177d8c Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 4 Mar 2024 14:14:53 +0100 +Subject: firmware: qcom_scm: disable clocks if qcom_scm_bw_enable() fails + +From: Gabor Juhos + +[ Upstream commit 0c50b7fcf2773b4853e83fc15aba1a196ba95966 ] + +There are several functions which are calling qcom_scm_bw_enable() +then returns immediately if the call fails and leaves the clocks +enabled. + +Change the code of these functions to disable clocks when the +qcom_scm_bw_enable() call fails. This also fixes a possible dma +buffer leak in the qcom_scm_pas_init_image() function. + +Compile tested only due to lack of hardware with interconnect +support. + +Cc: stable@vger.kernel.org +Fixes: 65b7ebda5028 ("firmware: qcom_scm: Add bw voting support to the SCM interface") +Signed-off-by: Gabor Juhos +Reviewed-by: Mukesh Ojha +Link: https://lore.kernel.org/r/20240304-qcom-scm-disable-clk-v1-1-b36e51577ca1@gmail.com +Signed-off-by: Bjorn Andersson +Signed-off-by: Sasha Levin +--- + drivers/firmware/qcom_scm.c | 18 ++++++++++++------ + 1 file changed, 12 insertions(+), 6 deletions(-) + +diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c +index ff7c155239e31..7af59985f1c1f 100644 +--- a/drivers/firmware/qcom_scm.c ++++ b/drivers/firmware/qcom_scm.c +@@ -498,13 +498,14 @@ int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, size_t size, + + ret = qcom_scm_bw_enable(); + if (ret) +- return ret; ++ goto disable_clk; + + desc.args[1] = mdata_phys; + + ret = qcom_scm_call(__scm->dev, &desc, &res); +- + qcom_scm_bw_disable(); ++ ++disable_clk: + qcom_scm_clk_disable(); + + out: +@@ -566,10 +567,12 @@ int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, phys_addr_t size) + + ret = qcom_scm_bw_enable(); + if (ret) +- return ret; ++ goto disable_clk; + + ret = qcom_scm_call(__scm->dev, &desc, &res); + qcom_scm_bw_disable(); ++ ++disable_clk: + qcom_scm_clk_disable(); + + return ret ? : res.result[0]; +@@ -601,10 +604,12 @@ int qcom_scm_pas_auth_and_reset(u32 peripheral) + + ret = qcom_scm_bw_enable(); + if (ret) +- return ret; ++ goto disable_clk; + + ret = qcom_scm_call(__scm->dev, &desc, &res); + qcom_scm_bw_disable(); ++ ++disable_clk: + qcom_scm_clk_disable(); + + return ret ? : res.result[0]; +@@ -635,11 +640,12 @@ int qcom_scm_pas_shutdown(u32 peripheral) + + ret = qcom_scm_bw_enable(); + if (ret) +- return ret; ++ goto disable_clk; + + ret = qcom_scm_call(__scm->dev, &desc, &res); +- + qcom_scm_bw_disable(); ++ ++disable_clk: + qcom_scm_clk_disable(); + + return ret ? : res.result[0]; +-- +2.43.0 + diff --git a/queue-6.6/ice-add-flag-to-distinguish-reset-from-.ndo_bpf-in-x.patch b/queue-6.6/ice-add-flag-to-distinguish-reset-from-.ndo_bpf-in-x.patch new file mode 100644 index 00000000000..3ede4388e6c --- /dev/null +++ b/queue-6.6/ice-add-flag-to-distinguish-reset-from-.ndo_bpf-in-x.patch @@ -0,0 +1,181 @@ +From bb63f5d12a4d58d790b4227255eaff353a6b217e Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 3 Jun 2024 14:42:33 -0700 +Subject: ice: add flag to distinguish reset from .ndo_bpf in XDP rings config + +From: Larysa Zaremba + +[ Upstream commit 744d197162c2070a6045a71e2666ed93a57cc65d ] + +Commit 6624e780a577 ("ice: split ice_vsi_setup into smaller functions") +has placed ice_vsi_free_q_vectors() after ice_destroy_xdp_rings() in +the rebuild process. The behaviour of the XDP rings config functions is +context-dependent, so the change of order has led to +ice_destroy_xdp_rings() doing additional work and removing XDP prog, when +it was supposed to be preserved. + +Also, dependency on the PF state reset flags creates an additional, +fortunately less common problem: + +* PFR is requested e.g. by tx_timeout handler +* .ndo_bpf() is asked to delete the program, calls ice_destroy_xdp_rings(), + but reset flag is set, so rings are destroyed without deleting the + program +* ice_vsi_rebuild tries to delete non-existent XDP rings, because the + program is still on the VSI +* system crashes + +With a similar race, when requested to attach a program, +ice_prepare_xdp_rings() can actually skip setting the program in the VSI +and nevertheless report success. + +Instead of reverting to the old order of function calls, add an enum +argument to both ice_prepare_xdp_rings() and ice_destroy_xdp_rings() in +order to distinguish between calls from rebuild and .ndo_bpf(). + +Fixes: efc2214b6047 ("ice: Add support for XDP") +Reviewed-by: Igor Bagnucki +Signed-off-by: Larysa Zaremba +Reviewed-by: Simon Horman +Tested-by: Chandan Kumar Rout +Signed-off-by: Jacob Keller +Link: https://lore.kernel.org/r/20240603-net-2024-05-30-intel-net-fixes-v2-4-e3563aa89b0c@intel.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/ice/ice.h | 11 +++++++++-- + drivers/net/ethernet/intel/ice/ice_lib.c | 5 +++-- + drivers/net/ethernet/intel/ice/ice_main.c | 22 ++++++++++++---------- + 3 files changed, 24 insertions(+), 14 deletions(-) + +diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h +index cf00eaa3e9955..c7962f322db2d 100644 +--- a/drivers/net/ethernet/intel/ice/ice.h ++++ b/drivers/net/ethernet/intel/ice/ice.h +@@ -892,9 +892,16 @@ int ice_down(struct ice_vsi *vsi); + int ice_down_up(struct ice_vsi *vsi); + int ice_vsi_cfg_lan(struct ice_vsi *vsi); + struct ice_vsi *ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi); ++ ++enum ice_xdp_cfg { ++ ICE_XDP_CFG_FULL, /* Fully apply new config in .ndo_bpf() */ ++ ICE_XDP_CFG_PART, /* Save/use part of config in VSI rebuild */ ++}; ++ + int ice_vsi_determine_xdp_res(struct ice_vsi *vsi); +-int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog); +-int ice_destroy_xdp_rings(struct ice_vsi *vsi); ++int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog, ++ enum ice_xdp_cfg cfg_type); ++int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type); + int + ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, + u32 flags); +diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c +index 5a7ba0355d338..13ca3342a0cea 100644 +--- a/drivers/net/ethernet/intel/ice/ice_lib.c ++++ b/drivers/net/ethernet/intel/ice/ice_lib.c +@@ -2462,7 +2462,8 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) + ret = ice_vsi_determine_xdp_res(vsi); + if (ret) + goto unroll_vector_base; +- ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog); ++ ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog, ++ ICE_XDP_CFG_PART); + if (ret) + goto unroll_vector_base; + } +@@ -2613,7 +2614,7 @@ void ice_vsi_decfg(struct ice_vsi *vsi) + /* return value check can be skipped here, it always returns + * 0 if reset is in progress + */ +- ice_destroy_xdp_rings(vsi); ++ ice_destroy_xdp_rings(vsi, ICE_XDP_CFG_PART); + + ice_vsi_clear_rings(vsi); + ice_vsi_free_q_vectors(vsi); +diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c +index 8ebb6517f6b96..5d71febdcd4dd 100644 +--- a/drivers/net/ethernet/intel/ice/ice_main.c ++++ b/drivers/net/ethernet/intel/ice/ice_main.c +@@ -2657,10 +2657,12 @@ static void ice_vsi_assign_bpf_prog(struct ice_vsi *vsi, struct bpf_prog *prog) + * ice_prepare_xdp_rings - Allocate, configure and setup Tx rings for XDP + * @vsi: VSI to bring up Tx rings used by XDP + * @prog: bpf program that will be assigned to VSI ++ * @cfg_type: create from scratch or restore the existing configuration + * + * Return 0 on success and negative value on error + */ +-int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) ++int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog, ++ enum ice_xdp_cfg cfg_type) + { + u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; + int xdp_rings_rem = vsi->num_xdp_txq; +@@ -2736,7 +2738,7 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) + * taken into account at the end of ice_vsi_rebuild, where + * ice_cfg_vsi_lan is being called + */ +- if (ice_is_reset_in_progress(pf->state)) ++ if (cfg_type == ICE_XDP_CFG_PART) + return 0; + + /* tell the Tx scheduler that right now we have +@@ -2788,22 +2790,21 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) + /** + * ice_destroy_xdp_rings - undo the configuration made by ice_prepare_xdp_rings + * @vsi: VSI to remove XDP rings ++ * @cfg_type: disable XDP permanently or allow it to be restored later + * + * Detach XDP rings from irq vectors, clean up the PF bitmap and free + * resources + */ +-int ice_destroy_xdp_rings(struct ice_vsi *vsi) ++int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type) + { + u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; + struct ice_pf *pf = vsi->back; + int i, v_idx; + + /* q_vectors are freed in reset path so there's no point in detaching +- * rings; in case of rebuild being triggered not from reset bits +- * in pf->state won't be set, so additionally check first q_vector +- * against NULL ++ * rings + */ +- if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0]) ++ if (cfg_type == ICE_XDP_CFG_PART) + goto free_qmap; + + ice_for_each_q_vector(vsi, v_idx) { +@@ -2844,7 +2845,7 @@ int ice_destroy_xdp_rings(struct ice_vsi *vsi) + if (static_key_enabled(&ice_xdp_locking_key)) + static_branch_dec(&ice_xdp_locking_key); + +- if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0]) ++ if (cfg_type == ICE_XDP_CFG_PART) + return 0; + + ice_vsi_assign_bpf_prog(vsi, NULL); +@@ -2955,7 +2956,8 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, + if (xdp_ring_err) { + NL_SET_ERR_MSG_MOD(extack, "Not enough Tx resources for XDP"); + } else { +- xdp_ring_err = ice_prepare_xdp_rings(vsi, prog); ++ xdp_ring_err = ice_prepare_xdp_rings(vsi, prog, ++ ICE_XDP_CFG_FULL); + if (xdp_ring_err) + NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed"); + } +@@ -2966,7 +2968,7 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, + NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Rx resources failed"); + } else if (ice_is_xdp_ena_vsi(vsi) && !prog) { + xdp_features_clear_redirect_target(vsi->netdev); +- xdp_ring_err = ice_destroy_xdp_rings(vsi); ++ xdp_ring_err = ice_destroy_xdp_rings(vsi, ICE_XDP_CFG_FULL); + if (xdp_ring_err) + NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed"); + /* reallocate Rx queues that were used for zero-copy */ +-- +2.43.0 + diff --git a/queue-6.6/ice-fix-iteration-of-tlvs-in-preserved-fields-area.patch b/queue-6.6/ice-fix-iteration-of-tlvs-in-preserved-fields-area.patch new file mode 100644 index 00000000000..6fcc76b7d2f --- /dev/null +++ b/queue-6.6/ice-fix-iteration-of-tlvs-in-preserved-fields-area.patch @@ -0,0 +1,124 @@ +From ffd967a3e5e55bed80c4577e4afdb9c868aaf7e4 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 3 Jun 2024 14:42:30 -0700 +Subject: ice: fix iteration of TLVs in Preserved Fields Area + +From: Jacob Keller + +[ Upstream commit 03e4a092be8ce3de7c1baa7ae14e68b64e3ea644 ] + +The ice_get_pfa_module_tlv() function iterates over the Type-Length-Value +structures in the Preserved Fields Area (PFA) of the NVM. This is used by +the driver to access data such as the Part Board Assembly identifier. + +The function uses simple logic to iterate over the PFA. First, the pointer +to the PFA in the NVM is read. Then the total length of the PFA is read +from the first word. + +A pointer to the first TLV is initialized, and a simple loop iterates over +each TLV. The pointer is moved forward through the NVM until it exceeds the +PFA area. + +The logic seems sound, but it is missing a key detail. The Preserved +Fields Area length includes one additional final word. This is documented +in the device data sheet as a dummy word which contains 0xFFFF. All NVMs +have this extra word. + +If the driver tries to scan for a TLV that is not in the PFA, it will read +past the size of the PFA. It reads and interprets the last dummy word of +the PFA as a TLV with type 0xFFFF. It then reads the word following the PFA +as a length. + +The PFA resides within the Shadow RAM portion of the NVM, which is +relatively small. All of its offsets are within a 16-bit size. The PFA +pointer and TLV pointer are stored by the driver as 16-bit values. + +In almost all cases, the word following the PFA will be such that +interpreting it as a length will result in 16-bit arithmetic overflow. Once +overflowed, the new next_tlv value is now below the maximum offset of the +PFA. Thus, the driver will continue to iterate the data as TLVs. In the +worst case, the driver hits on a sequence of reads which loop back to +reading the same offsets in an endless loop. + +To fix this, we need to correct the loop iteration check to account for +this extra word at the end of the PFA. This alone is sufficient to resolve +the known cases of this issue in the field. However, it is plausible that +an NVM could be misconfigured or have corrupt data which results in the +same kind of overflow. Protect against this by using check_add_overflow +when calculating both the maximum offset of the TLVs, and when calculating +the next_tlv offset at the end of each loop iteration. This ensures that +the driver will not get stuck in an infinite loop when scanning the PFA. + +Fixes: e961b679fb0b ("ice: add board identifier info to devlink .info_get") +Co-developed-by: Paul Greenwalt +Signed-off-by: Paul Greenwalt +Reviewed-by: Przemek Kitszel +Tested-by: Pucha Himasekhar Reddy +Signed-off-by: Jacob Keller +Link: https://lore.kernel.org/r/20240603-net-2024-05-30-intel-net-fixes-v2-1-e3563aa89b0c@intel.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/ice/ice_nvm.c | 28 ++++++++++++++++++------ + 1 file changed, 21 insertions(+), 7 deletions(-) + +diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c +index f6f52a2480662..2fb43cded572c 100644 +--- a/drivers/net/ethernet/intel/ice/ice_nvm.c ++++ b/drivers/net/ethernet/intel/ice/ice_nvm.c +@@ -441,8 +441,7 @@ int + ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len, + u16 module_type) + { +- u16 pfa_len, pfa_ptr; +- u16 next_tlv; ++ u16 pfa_len, pfa_ptr, next_tlv, max_tlv; + int status; + + status = ice_read_sr_word(hw, ICE_SR_PFA_PTR, &pfa_ptr); +@@ -455,11 +454,23 @@ ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len, + ice_debug(hw, ICE_DBG_INIT, "Failed to read PFA length.\n"); + return status; + } ++ ++ /* The Preserved Fields Area contains a sequence of Type-Length-Value ++ * structures which define its contents. The PFA length includes all ++ * of the TLVs, plus the initial length word itself, *and* one final ++ * word at the end after all of the TLVs. ++ */ ++ if (check_add_overflow(pfa_ptr, pfa_len - 1, &max_tlv)) { ++ dev_warn(ice_hw_to_dev(hw), "PFA starts at offset %u. PFA length of %u caused 16-bit arithmetic overflow.\n", ++ pfa_ptr, pfa_len); ++ return -EINVAL; ++ } ++ + /* Starting with first TLV after PFA length, iterate through the list + * of TLVs to find the requested one. + */ + next_tlv = pfa_ptr + 1; +- while (next_tlv < pfa_ptr + pfa_len) { ++ while (next_tlv < max_tlv) { + u16 tlv_sub_module_type; + u16 tlv_len; + +@@ -483,10 +494,13 @@ ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len, + } + return -EINVAL; + } +- /* Check next TLV, i.e. current TLV pointer + length + 2 words +- * (for current TLV's type and length) +- */ +- next_tlv = next_tlv + tlv_len + 2; ++ ++ if (check_add_overflow(next_tlv, 2, &next_tlv) || ++ check_add_overflow(next_tlv, tlv_len, &next_tlv)) { ++ dev_warn(ice_hw_to_dev(hw), "TLV of type %u and length 0x%04x caused 16-bit arithmetic overflow. The PFA starts at 0x%04x and has length of 0x%04x\n", ++ tlv_sub_module_type, tlv_len, pfa_ptr, pfa_len); ++ return -EINVAL; ++ } + } + /* Module does not exist */ + return -ENOENT; +-- +2.43.0 + diff --git a/queue-6.6/ice-remove-af_xdp_zc_qps-bitmap.patch b/queue-6.6/ice-remove-af_xdp_zc_qps-bitmap.patch new file mode 100644 index 00000000000..e04823f016b --- /dev/null +++ b/queue-6.6/ice-remove-af_xdp_zc_qps-bitmap.patch @@ -0,0 +1,170 @@ +From 6c9a25771b74ed890a3f3f7b3510360e4067c49d Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 3 Jun 2024 14:42:32 -0700 +Subject: ice: remove af_xdp_zc_qps bitmap + +From: Larysa Zaremba + +[ Upstream commit adbf5a42341f6ea038d3626cd4437d9f0ad0b2dd ] + +Referenced commit has introduced a bitmap to distinguish between ZC and +copy-mode AF_XDP queues, because xsk_get_pool_from_qid() does not do this +for us. + +The bitmap would be especially useful when restoring previous state after +rebuild, if only it was not reallocated in the process. This leads to e.g. +xdpsock dying after changing number of queues. + +Instead of preserving the bitmap during the rebuild, remove it completely +and distinguish between ZC and copy-mode queues based on the presence of +a device associated with the pool. + +Fixes: e102db780e1c ("ice: track AF_XDP ZC enabled queues in bitmap") +Reviewed-by: Przemek Kitszel +Signed-off-by: Larysa Zaremba +Reviewed-by: Simon Horman +Tested-by: Chandan Kumar Rout +Signed-off-by: Jacob Keller +Link: https://lore.kernel.org/r/20240603-net-2024-05-30-intel-net-fixes-v2-3-e3563aa89b0c@intel.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/ice/ice.h | 32 ++++++++++++++++-------- + drivers/net/ethernet/intel/ice/ice_lib.c | 8 ------ + drivers/net/ethernet/intel/ice/ice_xsk.c | 13 +++++----- + 3 files changed, 27 insertions(+), 26 deletions(-) + +diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h +index 5022b036ca4f9..cf00eaa3e9955 100644 +--- a/drivers/net/ethernet/intel/ice/ice.h ++++ b/drivers/net/ethernet/intel/ice/ice.h +@@ -407,7 +407,6 @@ struct ice_vsi { + struct ice_tc_cfg tc_cfg; + struct bpf_prog *xdp_prog; + struct ice_tx_ring **xdp_rings; /* XDP ring array */ +- unsigned long *af_xdp_zc_qps; /* tracks AF_XDP ZC enabled qps */ + u16 num_xdp_txq; /* Used XDP queues */ + u8 xdp_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */ + +@@ -714,6 +713,25 @@ static inline void ice_set_ring_xdp(struct ice_tx_ring *ring) + ring->flags |= ICE_TX_FLAGS_RING_XDP; + } + ++/** ++ * ice_get_xp_from_qid - get ZC XSK buffer pool bound to a queue ID ++ * @vsi: pointer to VSI ++ * @qid: index of a queue to look at XSK buff pool presence ++ * ++ * Return: A pointer to xsk_buff_pool structure if there is a buffer pool ++ * attached and configured as zero-copy, NULL otherwise. ++ */ ++static inline struct xsk_buff_pool *ice_get_xp_from_qid(struct ice_vsi *vsi, ++ u16 qid) ++{ ++ struct xsk_buff_pool *pool = xsk_get_pool_from_qid(vsi->netdev, qid); ++ ++ if (!ice_is_xdp_ena_vsi(vsi)) ++ return NULL; ++ ++ return (pool && pool->dev) ? pool : NULL; ++} ++ + /** + * ice_xsk_pool - get XSK buffer pool bound to a ring + * @ring: Rx ring to use +@@ -726,10 +744,7 @@ static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring) + struct ice_vsi *vsi = ring->vsi; + u16 qid = ring->q_index; + +- if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) +- return NULL; +- +- return xsk_get_pool_from_qid(vsi->netdev, qid); ++ return ice_get_xp_from_qid(vsi, qid); + } + + /** +@@ -754,12 +769,7 @@ static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid) + if (!ring) + return; + +- if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) { +- ring->xsk_pool = NULL; +- return; +- } +- +- ring->xsk_pool = xsk_get_pool_from_qid(vsi->netdev, qid); ++ ring->xsk_pool = ice_get_xp_from_qid(vsi, qid); + } + + /** +diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c +index 2004120a58acd..5a7ba0355d338 100644 +--- a/drivers/net/ethernet/intel/ice/ice_lib.c ++++ b/drivers/net/ethernet/intel/ice/ice_lib.c +@@ -117,14 +117,8 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi) + if (!vsi->q_vectors) + goto err_vectors; + +- vsi->af_xdp_zc_qps = bitmap_zalloc(max_t(int, vsi->alloc_txq, vsi->alloc_rxq), GFP_KERNEL); +- if (!vsi->af_xdp_zc_qps) +- goto err_zc_qps; +- + return 0; + +-err_zc_qps: +- devm_kfree(dev, vsi->q_vectors); + err_vectors: + devm_kfree(dev, vsi->rxq_map); + err_rxq_map: +@@ -321,8 +315,6 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi) + + dev = ice_pf_to_dev(pf); + +- bitmap_free(vsi->af_xdp_zc_qps); +- vsi->af_xdp_zc_qps = NULL; + /* free the ring and vector containers */ + devm_kfree(dev, vsi->q_vectors); + vsi->q_vectors = NULL; +diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c +index 7bd71660011e4..f53566cb6bfbd 100644 +--- a/drivers/net/ethernet/intel/ice/ice_xsk.c ++++ b/drivers/net/ethernet/intel/ice/ice_xsk.c +@@ -289,7 +289,6 @@ static int ice_xsk_pool_disable(struct ice_vsi *vsi, u16 qid) + if (!pool) + return -EINVAL; + +- clear_bit(qid, vsi->af_xdp_zc_qps); + xsk_pool_dma_unmap(pool, ICE_RX_DMA_ATTR); + + return 0; +@@ -320,8 +319,6 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) + if (err) + return err; + +- set_bit(qid, vsi->af_xdp_zc_qps); +- + return 0; + } + +@@ -369,11 +366,13 @@ ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring, bool pool_present) + int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc) + { + struct ice_rx_ring *rx_ring; +- unsigned long q; ++ uint i; ++ ++ ice_for_each_rxq(vsi, i) { ++ rx_ring = vsi->rx_rings[i]; ++ if (!rx_ring->xsk_pool) ++ continue; + +- for_each_set_bit(q, vsi->af_xdp_zc_qps, +- max_t(int, vsi->alloc_txq, vsi->alloc_rxq)) { +- rx_ring = vsi->rx_rings[q]; + if (ice_realloc_rx_xdp_bufs(rx_ring, zc)) + return -ENOMEM; + } +-- +2.43.0 + diff --git a/queue-6.6/ipv6-fix-possible-race-in-__fib6_drop_pcpu_from.patch b/queue-6.6/ipv6-fix-possible-race-in-__fib6_drop_pcpu_from.patch new file mode 100644 index 00000000000..dbbae732ae5 --- /dev/null +++ b/queue-6.6/ipv6-fix-possible-race-in-__fib6_drop_pcpu_from.patch @@ -0,0 +1,130 @@ +From 80172505be30e9eb896e3331991e19c0f692dc2b Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 19:35:49 +0000 +Subject: ipv6: fix possible race in __fib6_drop_pcpu_from() + +From: Eric Dumazet + +[ Upstream commit b01e1c030770ff3b4fe37fc7cc6bca03f594133f ] + +syzbot found a race in __fib6_drop_pcpu_from() [1] + +If compiler reads more than once (*ppcpu_rt), +second read could read NULL, if another cpu clears +the value in rt6_get_pcpu_route(). + +Add a READ_ONCE() to prevent this race. + +Also add rcu_read_lock()/rcu_read_unlock() because +we rely on RCU protection while dereferencing pcpu_rt. + +[1] + +Oops: general protection fault, probably for non-canonical address 0xdffffc0000000012: 0000 [#1] PREEMPT SMP KASAN PTI +KASAN: null-ptr-deref in range [0x0000000000000090-0x0000000000000097] +CPU: 0 PID: 7543 Comm: kworker/u8:17 Not tainted 6.10.0-rc1-syzkaller-00013-g2bfcfd584ff5 #0 +Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/02/2024 +Workqueue: netns cleanup_net + RIP: 0010:__fib6_drop_pcpu_from.part.0+0x10a/0x370 net/ipv6/ip6_fib.c:984 +Code: f8 48 c1 e8 03 80 3c 28 00 0f 85 16 02 00 00 4d 8b 3f 4d 85 ff 74 31 e8 74 a7 fa f7 49 8d bf 90 00 00 00 48 89 f8 48 c1 e8 03 <80> 3c 28 00 0f 85 1e 02 00 00 49 8b 87 90 00 00 00 48 8b 0c 24 48 +RSP: 0018:ffffc900040df070 EFLAGS: 00010206 +RAX: 0000000000000012 RBX: 0000000000000001 RCX: ffffffff89932e16 +RDX: ffff888049dd1e00 RSI: ffffffff89932d7c RDI: 0000000000000091 +RBP: dffffc0000000000 R08: 0000000000000005 R09: 0000000000000007 +R10: 0000000000000001 R11: 0000000000000006 R12: ffff88807fa080b8 +R13: fffffbfff1a9a07d R14: ffffed100ff41022 R15: 0000000000000001 +FS: 0000000000000000(0000) GS:ffff8880b9200000(0000) knlGS:0000000000000000 +CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +CR2: 0000001b32c26000 CR3: 000000005d56e000 CR4: 00000000003526f0 +DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 +DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 +Call Trace: + + __fib6_drop_pcpu_from net/ipv6/ip6_fib.c:966 [inline] + fib6_drop_pcpu_from net/ipv6/ip6_fib.c:1027 [inline] + fib6_purge_rt+0x7f2/0x9f0 net/ipv6/ip6_fib.c:1038 + fib6_del_route net/ipv6/ip6_fib.c:1998 [inline] + fib6_del+0xa70/0x17b0 net/ipv6/ip6_fib.c:2043 + fib6_clean_node+0x426/0x5b0 net/ipv6/ip6_fib.c:2205 + fib6_walk_continue+0x44f/0x8d0 net/ipv6/ip6_fib.c:2127 + fib6_walk+0x182/0x370 net/ipv6/ip6_fib.c:2175 + fib6_clean_tree+0xd7/0x120 net/ipv6/ip6_fib.c:2255 + __fib6_clean_all+0x100/0x2d0 net/ipv6/ip6_fib.c:2271 + rt6_sync_down_dev net/ipv6/route.c:4906 [inline] + rt6_disable_ip+0x7ed/0xa00 net/ipv6/route.c:4911 + addrconf_ifdown.isra.0+0x117/0x1b40 net/ipv6/addrconf.c:3855 + addrconf_notify+0x223/0x19e0 net/ipv6/addrconf.c:3778 + notifier_call_chain+0xb9/0x410 kernel/notifier.c:93 + call_netdevice_notifiers_info+0xbe/0x140 net/core/dev.c:1992 + call_netdevice_notifiers_extack net/core/dev.c:2030 [inline] + call_netdevice_notifiers net/core/dev.c:2044 [inline] + dev_close_many+0x333/0x6a0 net/core/dev.c:1585 + unregister_netdevice_many_notify+0x46d/0x19f0 net/core/dev.c:11193 + unregister_netdevice_many net/core/dev.c:11276 [inline] + default_device_exit_batch+0x85b/0xae0 net/core/dev.c:11759 + ops_exit_list+0x128/0x180 net/core/net_namespace.c:178 + cleanup_net+0x5b7/0xbf0 net/core/net_namespace.c:640 + process_one_work+0x9fb/0x1b60 kernel/workqueue.c:3231 + process_scheduled_works kernel/workqueue.c:3312 [inline] + worker_thread+0x6c8/0xf70 kernel/workqueue.c:3393 + kthread+0x2c1/0x3a0 kernel/kthread.c:389 + ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:147 + ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 + +Fixes: d52d3997f843 ("ipv6: Create percpu rt6_info") +Signed-off-by: Eric Dumazet +Cc: Martin KaFai Lau +Link: https://lore.kernel.org/r/20240604193549.981839-1-edumazet@google.com +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/ipv6/ip6_fib.c | 6 +++++- + net/ipv6/route.c | 1 + + 2 files changed, 6 insertions(+), 1 deletion(-) + +diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c +index 8184076a3924e..4356806b52bd5 100644 +--- a/net/ipv6/ip6_fib.c ++++ b/net/ipv6/ip6_fib.c +@@ -961,6 +961,7 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, + if (!fib6_nh->rt6i_pcpu) + return; + ++ rcu_read_lock(); + /* release the reference to this fib entry from + * all of its cached pcpu routes + */ +@@ -969,7 +970,9 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, + struct rt6_info *pcpu_rt; + + ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); +- pcpu_rt = *ppcpu_rt; ++ ++ /* Paired with xchg() in rt6_get_pcpu_route() */ ++ pcpu_rt = READ_ONCE(*ppcpu_rt); + + /* only dropping the 'from' reference if the cached route + * is using 'match'. The cached pcpu_rt->from only changes +@@ -983,6 +986,7 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, + fib6_info_release(from); + } + } ++ rcu_read_unlock(); + } + + struct fib6_nh_pcpu_arg { +diff --git a/net/ipv6/route.c b/net/ipv6/route.c +index c48eaa7c23401..0a37f04177337 100644 +--- a/net/ipv6/route.c ++++ b/net/ipv6/route.c +@@ -1399,6 +1399,7 @@ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res) + struct rt6_info *prev, **p; + + p = this_cpu_ptr(res->nh->rt6i_pcpu); ++ /* Paired with READ_ONCE() in __fib6_drop_pcpu_from() */ + prev = xchg(p, NULL); + if (prev) { + dst_dev_put(&prev->dst); +-- +2.43.0 + diff --git a/queue-6.6/ipv6-ioam-block-bh-from-ioam6_output.patch b/queue-6.6/ipv6-ioam-block-bh-from-ioam6_output.patch new file mode 100644 index 00000000000..44e806e715a --- /dev/null +++ b/queue-6.6/ipv6-ioam-block-bh-from-ioam6_output.patch @@ -0,0 +1,65 @@ +From 1628e1a1ec5d0f3d344f1c5d26c4241ef6d2f1d1 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 31 May 2024 13:26:32 +0000 +Subject: ipv6: ioam: block BH from ioam6_output() + +From: Eric Dumazet + +[ Upstream commit 2fe40483ec257de2a0d819ef88e3e76c7e261319 ] + +As explained in commit 1378817486d6 ("tipc: block BH +before using dst_cache"), net/core/dst_cache.c +helpers need to be called with BH disabled. + +Disabling preemption in ioam6_output() is not good enough, +because ioam6_output() is called from process context, +lwtunnel_output() only uses rcu_read_lock(). + +We might be interrupted by a softirq, re-enter ioam6_output() +and corrupt dst_cache data structures. + +Fix the race by using local_bh_disable() instead of +preempt_disable(). + +Fixes: 8cb3bf8bff3c ("ipv6: ioam: Add support for the ip6ip6 encapsulation") +Signed-off-by: Eric Dumazet +Cc: Justin Iurman +Acked-by: Paolo Abeni +Link: https://lore.kernel.org/r/20240531132636.2637995-2-edumazet@google.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/ipv6/ioam6_iptunnel.c | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c +index f6f5b83dd954d..a5cfc5b0b206b 100644 +--- a/net/ipv6/ioam6_iptunnel.c ++++ b/net/ipv6/ioam6_iptunnel.c +@@ -351,9 +351,9 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb) + goto drop; + + if (!ipv6_addr_equal(&orig_daddr, &ipv6_hdr(skb)->daddr)) { +- preempt_disable(); ++ local_bh_disable(); + dst = dst_cache_get(&ilwt->cache); +- preempt_enable(); ++ local_bh_enable(); + + if (unlikely(!dst)) { + struct ipv6hdr *hdr = ipv6_hdr(skb); +@@ -373,9 +373,9 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb) + goto drop; + } + +- preempt_disable(); ++ local_bh_disable(); + dst_cache_set_ip6(&ilwt->cache, dst, &fl6.saddr); +- preempt_enable(); ++ local_bh_enable(); + } + + skb_dst_drop(skb); +-- +2.43.0 + diff --git a/queue-6.6/ipv6-sr-block-bh-in-seg6_output_core-and-seg6_input_.patch b/queue-6.6/ipv6-sr-block-bh-in-seg6_output_core-and-seg6_input_.patch new file mode 100644 index 00000000000..537e6555654 --- /dev/null +++ b/queue-6.6/ipv6-sr-block-bh-in-seg6_output_core-and-seg6_input_.patch @@ -0,0 +1,94 @@ +From ae57cd72b4e762c57a13f83b368164b9cdfad1e7 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 31 May 2024 13:26:34 +0000 +Subject: ipv6: sr: block BH in seg6_output_core() and seg6_input_core() + +From: Eric Dumazet + +[ Upstream commit c0b98ac1cc104f48763cdb27b1e9ac25fd81fc90 ] + +As explained in commit 1378817486d6 ("tipc: block BH +before using dst_cache"), net/core/dst_cache.c +helpers need to be called with BH disabled. + +Disabling preemption in seg6_output_core() is not good enough, +because seg6_output_core() is called from process context, +lwtunnel_output() only uses rcu_read_lock(). + +We might be interrupted by a softirq, re-enter seg6_output_core() +and corrupt dst_cache data structures. + +Fix the race by using local_bh_disable() instead of +preempt_disable(). + +Apply a similar change in seg6_input_core(). + +Fixes: fa79581ea66c ("ipv6: sr: fix several BUGs when preemption is enabled") +Fixes: 6c8702c60b88 ("ipv6: sr: add support for SRH encapsulation and injection with lwtunnels") +Signed-off-by: Eric Dumazet +Cc: David Lebrun +Acked-by: Paolo Abeni +Link: https://lore.kernel.org/r/20240531132636.2637995-4-edumazet@google.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/ipv6/seg6_iptunnel.c | 14 ++++++-------- + 1 file changed, 6 insertions(+), 8 deletions(-) + +diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c +index a75df2ec8db0d..098632adc9b5a 100644 +--- a/net/ipv6/seg6_iptunnel.c ++++ b/net/ipv6/seg6_iptunnel.c +@@ -464,23 +464,21 @@ static int seg6_input_core(struct net *net, struct sock *sk, + + slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate); + +- preempt_disable(); ++ local_bh_disable(); + dst = dst_cache_get(&slwt->cache); +- preempt_enable(); + + if (!dst) { + ip6_route_input(skb); + dst = skb_dst(skb); + if (!dst->error) { +- preempt_disable(); + dst_cache_set_ip6(&slwt->cache, dst, + &ipv6_hdr(skb)->saddr); +- preempt_enable(); + } + } else { + skb_dst_drop(skb); + skb_dst_set(skb, dst); + } ++ local_bh_enable(); + + err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); + if (unlikely(err)) +@@ -536,9 +534,9 @@ static int seg6_output_core(struct net *net, struct sock *sk, + + slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate); + +- preempt_disable(); ++ local_bh_disable(); + dst = dst_cache_get(&slwt->cache); +- preempt_enable(); ++ local_bh_enable(); + + if (unlikely(!dst)) { + struct ipv6hdr *hdr = ipv6_hdr(skb); +@@ -558,9 +556,9 @@ static int seg6_output_core(struct net *net, struct sock *sk, + goto drop; + } + +- preempt_disable(); ++ local_bh_disable(); + dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr); +- preempt_enable(); ++ local_bh_enable(); + } + + skb_dst_drop(skb); +-- +2.43.0 + diff --git a/queue-6.6/irqchip-riscv-intc-allow-large-non-standard-interrup.patch b/queue-6.6/irqchip-riscv-intc-allow-large-non-standard-interrup.patch new file mode 100644 index 00000000000..a1e124f8029 --- /dev/null +++ b/queue-6.6/irqchip-riscv-intc-allow-large-non-standard-interrup.patch @@ -0,0 +1,98 @@ +From eed7836bce48533294afc37ef0c2453a6e9384b1 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 22 Feb 2024 16:39:38 +0800 +Subject: irqchip/riscv-intc: Allow large non-standard interrupt number + +From: Yu Chien Peter Lin + +[ Upstream commit 96303bcb401c21dc1426d8d9bb1fc74aae5c02a9 ] + +Currently, the implementation of the RISC-V INTC driver uses the +interrupt cause as the hardware interrupt number, with a maximum of +64 interrupts. However, the platform can expand the interrupt number +further for custom local interrupts. + +To fully utilize the available local interrupt sources, switch +to using irq_domain_create_tree() that creates the radix tree +map, add global variables (riscv_intc_nr_irqs, riscv_intc_custom_base +and riscv_intc_custom_nr_irqs) to determine the valid range of local +interrupt number (hwirq). + +Signed-off-by: Yu Chien Peter Lin +Signed-off-by: Thomas Gleixner +Reviewed-by: Randolph +Reviewed-by: Anup Patel +Reviewed-by: Atish Patra +Link: https://lore.kernel.org/r/20240222083946.3977135-3-peterlin@andestech.com +Stable-dep-of: 0110c4b11047 ("irqchip/riscv-intc: Prevent memory leak when riscv_intc_init_common() fails") +Signed-off-by: Sasha Levin +--- + drivers/irqchip/irq-riscv-intc.c | 26 +++++++++++++++++++------- + 1 file changed, 19 insertions(+), 7 deletions(-) + +diff --git a/drivers/irqchip/irq-riscv-intc.c b/drivers/irqchip/irq-riscv-intc.c +index e8d01b14ccdde..684875c397280 100644 +--- a/drivers/irqchip/irq-riscv-intc.c ++++ b/drivers/irqchip/irq-riscv-intc.c +@@ -19,15 +19,16 @@ + #include + + static struct irq_domain *intc_domain; ++static unsigned int riscv_intc_nr_irqs __ro_after_init = BITS_PER_LONG; ++static unsigned int riscv_intc_custom_base __ro_after_init = BITS_PER_LONG; ++static unsigned int riscv_intc_custom_nr_irqs __ro_after_init; + + static asmlinkage void riscv_intc_irq(struct pt_regs *regs) + { + unsigned long cause = regs->cause & ~CAUSE_IRQ_FLAG; + +- if (unlikely(cause >= BITS_PER_LONG)) +- panic("unexpected interrupt cause"); +- +- generic_handle_domain_irq(intc_domain, cause); ++ if (generic_handle_domain_irq(intc_domain, cause)) ++ pr_warn_ratelimited("Failed to handle interrupt (cause: %ld)\n", cause); + } + + /* +@@ -93,6 +94,14 @@ static int riscv_intc_domain_alloc(struct irq_domain *domain, + if (ret) + return ret; + ++ /* ++ * Only allow hwirq for which we have corresponding standard or ++ * custom interrupt enable register. ++ */ ++ if ((hwirq >= riscv_intc_nr_irqs && hwirq < riscv_intc_custom_base) || ++ (hwirq >= riscv_intc_custom_base + riscv_intc_custom_nr_irqs)) ++ return -EINVAL; ++ + for (i = 0; i < nr_irqs; i++) { + ret = riscv_intc_domain_map(domain, virq + i, hwirq + i); + if (ret) +@@ -117,8 +126,7 @@ static int __init riscv_intc_init_common(struct fwnode_handle *fn) + { + int rc; + +- intc_domain = irq_domain_create_linear(fn, BITS_PER_LONG, +- &riscv_intc_domain_ops, NULL); ++ intc_domain = irq_domain_create_tree(fn, &riscv_intc_domain_ops, NULL); + if (!intc_domain) { + pr_err("unable to add IRQ domain\n"); + return -ENXIO; +@@ -132,7 +140,11 @@ static int __init riscv_intc_init_common(struct fwnode_handle *fn) + + riscv_set_intc_hwnode_fn(riscv_intc_hwnode); + +- pr_info("%d local interrupts mapped\n", BITS_PER_LONG); ++ pr_info("%d local interrupts mapped\n", riscv_intc_nr_irqs); ++ if (riscv_intc_custom_nr_irqs) { ++ pr_info("%d custom local interrupts mapped\n", ++ riscv_intc_custom_nr_irqs); ++ } + + return 0; + } +-- +2.43.0 + diff --git a/queue-6.6/irqchip-riscv-intc-introduce-andes-hart-level-interr.patch b/queue-6.6/irqchip-riscv-intc-introduce-andes-hart-level-interr.patch new file mode 100644 index 00000000000..03cc1d23e27 --- /dev/null +++ b/queue-6.6/irqchip-riscv-intc-introduce-andes-hart-level-interr.patch @@ -0,0 +1,196 @@ +From e10b5b43681415f4ca17eb091644e3918191621c Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 22 Feb 2024 16:39:39 +0800 +Subject: irqchip/riscv-intc: Introduce Andes hart-level interrupt controller + +From: Yu Chien Peter Lin + +[ Upstream commit f4cc33e78ba8624a79ba8dea98ce5c85aa9ca33c ] + +Add support for the Andes hart-level interrupt controller. This +controller provides interrupt mask/unmask functions to access the +custom register (SLIE) where the non-standard S-mode local interrupt +enable bits are located. The base of custom interrupt number is set +to 256. + +To share the riscv_intc_domain_map() with the generic RISC-V INTC and +ACPI, add a chip parameter to riscv_intc_init_common(), so it can be +passed to the irq_domain_set_info() as a private data. + +Andes hart-level interrupt controller requires the "andestech,cpu-intc" +compatible string to be present in interrupt-controller of cpu node to +enable the use of custom local interrupt source. +e.g., + + cpu0: cpu@0 { + compatible = "andestech,ax45mp", "riscv"; + ... + cpu0-intc: interrupt-controller { + #interrupt-cells = <0x01>; + compatible = "andestech,cpu-intc", "riscv,cpu-intc"; + interrupt-controller; + }; + }; + +Signed-off-by: Yu Chien Peter Lin +Signed-off-by: Thomas Gleixner +Reviewed-by: Randolph +Reviewed-by: Anup Patel +Link: https://lore.kernel.org/r/20240222083946.3977135-4-peterlin@andestech.com +Stable-dep-of: 0110c4b11047 ("irqchip/riscv-intc: Prevent memory leak when riscv_intc_init_common() fails") +Signed-off-by: Sasha Levin +--- + drivers/irqchip/irq-riscv-intc.c | 58 ++++++++++++++++++++++++++++---- + include/linux/soc/andes/irq.h | 18 ++++++++++ + 2 files changed, 69 insertions(+), 7 deletions(-) + create mode 100644 include/linux/soc/andes/irq.h + +diff --git a/drivers/irqchip/irq-riscv-intc.c b/drivers/irqchip/irq-riscv-intc.c +index 684875c397280..0cd6b48a5dbf9 100644 +--- a/drivers/irqchip/irq-riscv-intc.c ++++ b/drivers/irqchip/irq-riscv-intc.c +@@ -17,6 +17,7 @@ + #include + #include + #include ++#include + + static struct irq_domain *intc_domain; + static unsigned int riscv_intc_nr_irqs __ro_after_init = BITS_PER_LONG; +@@ -48,6 +49,31 @@ static void riscv_intc_irq_unmask(struct irq_data *d) + csr_set(CSR_IE, BIT(d->hwirq)); + } + ++static void andes_intc_irq_mask(struct irq_data *d) ++{ ++ /* ++ * Andes specific S-mode local interrupt causes (hwirq) ++ * are defined as (256 + n) and controlled by n-th bit ++ * of SLIE. ++ */ ++ unsigned int mask = BIT(d->hwirq % BITS_PER_LONG); ++ ++ if (d->hwirq < ANDES_SLI_CAUSE_BASE) ++ csr_clear(CSR_IE, mask); ++ else ++ csr_clear(ANDES_CSR_SLIE, mask); ++} ++ ++static void andes_intc_irq_unmask(struct irq_data *d) ++{ ++ unsigned int mask = BIT(d->hwirq % BITS_PER_LONG); ++ ++ if (d->hwirq < ANDES_SLI_CAUSE_BASE) ++ csr_set(CSR_IE, mask); ++ else ++ csr_set(ANDES_CSR_SLIE, mask); ++} ++ + static void riscv_intc_irq_eoi(struct irq_data *d) + { + /* +@@ -71,12 +97,21 @@ static struct irq_chip riscv_intc_chip = { + .irq_eoi = riscv_intc_irq_eoi, + }; + ++static struct irq_chip andes_intc_chip = { ++ .name = "RISC-V INTC", ++ .irq_mask = andes_intc_irq_mask, ++ .irq_unmask = andes_intc_irq_unmask, ++ .irq_eoi = riscv_intc_irq_eoi, ++}; ++ + static int riscv_intc_domain_map(struct irq_domain *d, unsigned int irq, + irq_hw_number_t hwirq) + { ++ struct irq_chip *chip = d->host_data; ++ + irq_set_percpu_devid(irq); +- irq_domain_set_info(d, irq, hwirq, &riscv_intc_chip, d->host_data, +- handle_percpu_devid_irq, NULL, NULL); ++ irq_domain_set_info(d, irq, hwirq, chip, NULL, handle_percpu_devid_irq, ++ NULL, NULL); + + return 0; + } +@@ -122,11 +157,12 @@ static struct fwnode_handle *riscv_intc_hwnode(void) + return intc_domain->fwnode; + } + +-static int __init riscv_intc_init_common(struct fwnode_handle *fn) ++static int __init riscv_intc_init_common(struct fwnode_handle *fn, ++ struct irq_chip *chip) + { + int rc; + +- intc_domain = irq_domain_create_tree(fn, &riscv_intc_domain_ops, NULL); ++ intc_domain = irq_domain_create_tree(fn, &riscv_intc_domain_ops, chip); + if (!intc_domain) { + pr_err("unable to add IRQ domain\n"); + return -ENXIO; +@@ -152,8 +188,9 @@ static int __init riscv_intc_init_common(struct fwnode_handle *fn) + static int __init riscv_intc_init(struct device_node *node, + struct device_node *parent) + { +- int rc; ++ struct irq_chip *chip = &riscv_intc_chip; + unsigned long hartid; ++ int rc; + + rc = riscv_of_parent_hartid(node, &hartid); + if (rc < 0) { +@@ -178,10 +215,17 @@ static int __init riscv_intc_init(struct device_node *node, + return 0; + } + +- return riscv_intc_init_common(of_node_to_fwnode(node)); ++ if (of_device_is_compatible(node, "andestech,cpu-intc")) { ++ riscv_intc_custom_base = ANDES_SLI_CAUSE_BASE; ++ riscv_intc_custom_nr_irqs = ANDES_RV_IRQ_LAST; ++ chip = &andes_intc_chip; ++ } ++ ++ return riscv_intc_init_common(of_node_to_fwnode(node), chip); + } + + IRQCHIP_DECLARE(riscv, "riscv,cpu-intc", riscv_intc_init); ++IRQCHIP_DECLARE(andes, "andestech,cpu-intc", riscv_intc_init); + + #ifdef CONFIG_ACPI + +@@ -208,7 +252,7 @@ static int __init riscv_intc_acpi_init(union acpi_subtable_headers *header, + return -ENOMEM; + } + +- return riscv_intc_init_common(fn); ++ return riscv_intc_init_common(fn, &riscv_intc_chip); + } + + IRQCHIP_ACPI_DECLARE(riscv_intc, ACPI_MADT_TYPE_RINTC, NULL, +diff --git a/include/linux/soc/andes/irq.h b/include/linux/soc/andes/irq.h +new file mode 100644 +index 0000000000000..edc3182d6e661 +--- /dev/null ++++ b/include/linux/soc/andes/irq.h +@@ -0,0 +1,18 @@ ++/* SPDX-License-Identifier: GPL-2.0-only */ ++/* ++ * Copyright (C) 2023 Andes Technology Corporation ++ */ ++#ifndef __ANDES_IRQ_H ++#define __ANDES_IRQ_H ++ ++/* Andes PMU irq number */ ++#define ANDES_RV_IRQ_PMOVI 18 ++#define ANDES_RV_IRQ_LAST ANDES_RV_IRQ_PMOVI ++#define ANDES_SLI_CAUSE_BASE 256 ++ ++/* Andes PMU related registers */ ++#define ANDES_CSR_SLIE 0x9c4 ++#define ANDES_CSR_SLIP 0x9c5 ++#define ANDES_CSR_SCOUNTEROF 0x9d4 ++ ++#endif /* __ANDES_IRQ_H */ +-- +2.43.0 + diff --git a/queue-6.6/irqchip-riscv-intc-prevent-memory-leak-when-riscv_in.patch b/queue-6.6/irqchip-riscv-intc-prevent-memory-leak-when-riscv_in.patch new file mode 100644 index 00000000000..a81997536a8 --- /dev/null +++ b/queue-6.6/irqchip-riscv-intc-prevent-memory-leak-when-riscv_in.patch @@ -0,0 +1,55 @@ +From 3e094b6741d6f81ca0d381015936e068e4e65f8e Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 27 May 2024 13:41:13 +0530 +Subject: irqchip/riscv-intc: Prevent memory leak when riscv_intc_init_common() + fails + +From: Sunil V L + +[ Upstream commit 0110c4b110477bb1f19b0d02361846be7ab08300 ] + +When riscv_intc_init_common() fails, the firmware node allocated is not +freed. Add the missing free(). + +Fixes: 7023b9d83f03 ("irqchip/riscv-intc: Add ACPI support") +Signed-off-by: Sunil V L +Signed-off-by: Thomas Gleixner +Reviewed-by: Anup Patel +Cc: stable@vger.kernel.org +Link: https://lore.kernel.org/r/20240527081113.616189-1-sunilvl@ventanamicro.com +Signed-off-by: Sasha Levin +--- + drivers/irqchip/irq-riscv-intc.c | 9 +++++++-- + 1 file changed, 7 insertions(+), 2 deletions(-) + +diff --git a/drivers/irqchip/irq-riscv-intc.c b/drivers/irqchip/irq-riscv-intc.c +index 0cd6b48a5dbf9..627beae9649a2 100644 +--- a/drivers/irqchip/irq-riscv-intc.c ++++ b/drivers/irqchip/irq-riscv-intc.c +@@ -232,8 +232,9 @@ IRQCHIP_DECLARE(andes, "andestech,cpu-intc", riscv_intc_init); + static int __init riscv_intc_acpi_init(union acpi_subtable_headers *header, + const unsigned long end) + { +- struct fwnode_handle *fn; + struct acpi_madt_rintc *rintc; ++ struct fwnode_handle *fn; ++ int rc; + + rintc = (struct acpi_madt_rintc *)header; + +@@ -252,7 +253,11 @@ static int __init riscv_intc_acpi_init(union acpi_subtable_headers *header, + return -ENOMEM; + } + +- return riscv_intc_init_common(fn, &riscv_intc_chip); ++ rc = riscv_intc_init_common(fn, &riscv_intc_chip); ++ if (rc) ++ irq_domain_free_fwnode(fn); ++ ++ return rc; + } + + IRQCHIP_ACPI_DECLARE(riscv_intc, ACPI_MADT_TYPE_RINTC, NULL, +-- +2.43.0 + diff --git a/queue-6.6/ksmbd-use-rwsem-instead-of-rwlock-for-lease-break.patch b/queue-6.6/ksmbd-use-rwsem-instead-of-rwlock-for-lease-break.patch new file mode 100644 index 00000000000..74bc46b3012 --- /dev/null +++ b/queue-6.6/ksmbd-use-rwsem-instead-of-rwlock-for-lease-break.patch @@ -0,0 +1,287 @@ +From 8ba343ad504a3ba51867b1bf66266434373f93ce Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 2 May 2024 10:07:50 +0900 +Subject: ksmbd: use rwsem instead of rwlock for lease break + +From: Namjae Jeon + +[ Upstream commit d1c189c6cb8b0fb7b5ee549237d27889c40c2f8b ] + +lease break wait for lease break acknowledgment. +rwsem is more suitable than unlock while traversing the list for parent +lease break in ->m_op_list. + +Cc: stable@vger.kernel.org +Signed-off-by: Namjae Jeon +Signed-off-by: Steve French +Signed-off-by: Sasha Levin +--- + fs/smb/server/oplock.c | 30 +++++++++++------------------- + fs/smb/server/smb2pdu.c | 4 ++-- + fs/smb/server/smb_common.c | 4 ++-- + fs/smb/server/vfs_cache.c | 28 ++++++++++++++-------------- + fs/smb/server/vfs_cache.h | 2 +- + 5 files changed, 30 insertions(+), 38 deletions(-) + +diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c +index 7d17a14378e33..a8f52c4ebbdad 100644 +--- a/fs/smb/server/oplock.c ++++ b/fs/smb/server/oplock.c +@@ -207,9 +207,9 @@ static void opinfo_add(struct oplock_info *opinfo) + { + struct ksmbd_inode *ci = opinfo->o_fp->f_ci; + +- write_lock(&ci->m_lock); ++ down_write(&ci->m_lock); + list_add_rcu(&opinfo->op_entry, &ci->m_op_list); +- write_unlock(&ci->m_lock); ++ up_write(&ci->m_lock); + } + + static void opinfo_del(struct oplock_info *opinfo) +@@ -221,9 +221,9 @@ static void opinfo_del(struct oplock_info *opinfo) + lease_del_list(opinfo); + write_unlock(&lease_list_lock); + } +- write_lock(&ci->m_lock); ++ down_write(&ci->m_lock); + list_del_rcu(&opinfo->op_entry); +- write_unlock(&ci->m_lock); ++ up_write(&ci->m_lock); + } + + static unsigned long opinfo_count(struct ksmbd_file *fp) +@@ -526,21 +526,18 @@ static struct oplock_info *same_client_has_lease(struct ksmbd_inode *ci, + * Compare lease key and client_guid to know request from same owner + * of same client + */ +- read_lock(&ci->m_lock); ++ down_read(&ci->m_lock); + list_for_each_entry(opinfo, &ci->m_op_list, op_entry) { + if (!opinfo->is_lease || !opinfo->conn) + continue; +- read_unlock(&ci->m_lock); + lease = opinfo->o_lease; + + ret = compare_guid_key(opinfo, client_guid, lctx->lease_key); + if (ret) { + m_opinfo = opinfo; + /* skip upgrading lease about breaking lease */ +- if (atomic_read(&opinfo->breaking_cnt)) { +- read_lock(&ci->m_lock); ++ if (atomic_read(&opinfo->breaking_cnt)) + continue; +- } + + /* upgrading lease */ + if ((atomic_read(&ci->op_count) + +@@ -570,9 +567,8 @@ static struct oplock_info *same_client_has_lease(struct ksmbd_inode *ci, + lease_none_upgrade(opinfo, lctx->req_state); + } + } +- read_lock(&ci->m_lock); + } +- read_unlock(&ci->m_lock); ++ up_read(&ci->m_lock); + + return m_opinfo; + } +@@ -1119,7 +1115,7 @@ void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, + if (!p_ci) + return; + +- read_lock(&p_ci->m_lock); ++ down_read(&p_ci->m_lock); + list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) { + if (opinfo->conn == NULL || !opinfo->is_lease) + continue; +@@ -1137,13 +1133,11 @@ void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, + continue; + } + +- read_unlock(&p_ci->m_lock); + oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE); + opinfo_conn_put(opinfo); +- read_lock(&p_ci->m_lock); + } + } +- read_unlock(&p_ci->m_lock); ++ up_read(&p_ci->m_lock); + + ksmbd_inode_put(p_ci); + } +@@ -1164,7 +1158,7 @@ void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp) + if (!p_ci) + return; + +- read_lock(&p_ci->m_lock); ++ down_read(&p_ci->m_lock); + list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) { + if (opinfo->conn == NULL || !opinfo->is_lease) + continue; +@@ -1178,13 +1172,11 @@ void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp) + atomic_dec(&opinfo->conn->r_count); + continue; + } +- read_unlock(&p_ci->m_lock); + oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE); + opinfo_conn_put(opinfo); +- read_lock(&p_ci->m_lock); + } + } +- read_unlock(&p_ci->m_lock); ++ up_read(&p_ci->m_lock); + + ksmbd_inode_put(p_ci); + } +diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c +index 6a15c5d64f415..8df93c9d4ee41 100644 +--- a/fs/smb/server/smb2pdu.c ++++ b/fs/smb/server/smb2pdu.c +@@ -3376,9 +3376,9 @@ int smb2_open(struct ksmbd_work *work) + * after daccess, saccess, attrib_only, and stream are + * initialized. + */ +- write_lock(&fp->f_ci->m_lock); ++ down_write(&fp->f_ci->m_lock); + list_add(&fp->node, &fp->f_ci->m_fp_list); +- write_unlock(&fp->f_ci->m_lock); ++ up_write(&fp->f_ci->m_lock); + + /* Check delete pending among previous fp before oplock break */ + if (ksmbd_inode_pending_delete(fp)) { +diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c +index fcaf373cc0080..474dadf6b7b8b 100644 +--- a/fs/smb/server/smb_common.c ++++ b/fs/smb/server/smb_common.c +@@ -646,7 +646,7 @@ int ksmbd_smb_check_shared_mode(struct file *filp, struct ksmbd_file *curr_fp) + * Lookup fp in master fp list, and check desired access and + * shared mode between previous open and current open. + */ +- read_lock(&curr_fp->f_ci->m_lock); ++ down_read(&curr_fp->f_ci->m_lock); + list_for_each_entry(prev_fp, &curr_fp->f_ci->m_fp_list, node) { + if (file_inode(filp) != file_inode(prev_fp->filp)) + continue; +@@ -722,7 +722,7 @@ int ksmbd_smb_check_shared_mode(struct file *filp, struct ksmbd_file *curr_fp) + break; + } + } +- read_unlock(&curr_fp->f_ci->m_lock); ++ up_read(&curr_fp->f_ci->m_lock); + + return rc; + } +diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c +index 030f70700036c..6cb599cd287ee 100644 +--- a/fs/smb/server/vfs_cache.c ++++ b/fs/smb/server/vfs_cache.c +@@ -165,7 +165,7 @@ static int ksmbd_inode_init(struct ksmbd_inode *ci, struct ksmbd_file *fp) + ci->m_fattr = 0; + INIT_LIST_HEAD(&ci->m_fp_list); + INIT_LIST_HEAD(&ci->m_op_list); +- rwlock_init(&ci->m_lock); ++ init_rwsem(&ci->m_lock); + ci->m_de = fp->filp->f_path.dentry; + return 0; + } +@@ -261,14 +261,14 @@ static void __ksmbd_inode_close(struct ksmbd_file *fp) + } + + if (atomic_dec_and_test(&ci->m_count)) { +- write_lock(&ci->m_lock); ++ down_write(&ci->m_lock); + if (ci->m_flags & (S_DEL_ON_CLS | S_DEL_PENDING)) { + ci->m_flags &= ~(S_DEL_ON_CLS | S_DEL_PENDING); +- write_unlock(&ci->m_lock); ++ up_write(&ci->m_lock); + ksmbd_vfs_unlink(filp); +- write_lock(&ci->m_lock); ++ down_write(&ci->m_lock); + } +- write_unlock(&ci->m_lock); ++ up_write(&ci->m_lock); + + ksmbd_inode_free(ci); + } +@@ -289,9 +289,9 @@ static void __ksmbd_remove_fd(struct ksmbd_file_table *ft, struct ksmbd_file *fp + if (!has_file_id(fp->volatile_id)) + return; + +- write_lock(&fp->f_ci->m_lock); ++ down_write(&fp->f_ci->m_lock); + list_del_init(&fp->node); +- write_unlock(&fp->f_ci->m_lock); ++ up_write(&fp->f_ci->m_lock); + + write_lock(&ft->lock); + idr_remove(ft->idr, fp->volatile_id); +@@ -523,17 +523,17 @@ struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry) + if (!ci) + return NULL; + +- read_lock(&ci->m_lock); ++ down_read(&ci->m_lock); + list_for_each_entry(lfp, &ci->m_fp_list, node) { + if (inode == file_inode(lfp->filp)) { + atomic_dec(&ci->m_count); + lfp = ksmbd_fp_get(lfp); +- read_unlock(&ci->m_lock); ++ up_read(&ci->m_lock); + return lfp; + } + } + atomic_dec(&ci->m_count); +- read_unlock(&ci->m_lock); ++ up_read(&ci->m_lock); + return NULL; + } + +@@ -705,13 +705,13 @@ static bool session_fd_check(struct ksmbd_tree_connect *tcon, + + conn = fp->conn; + ci = fp->f_ci; +- write_lock(&ci->m_lock); ++ down_write(&ci->m_lock); + list_for_each_entry_rcu(op, &ci->m_op_list, op_entry) { + if (op->conn != conn) + continue; + op->conn = NULL; + } +- write_unlock(&ci->m_lock); ++ up_write(&ci->m_lock); + + fp->conn = NULL; + fp->tcon = NULL; +@@ -801,13 +801,13 @@ int ksmbd_reopen_durable_fd(struct ksmbd_work *work, struct ksmbd_file *fp) + fp->tcon = work->tcon; + + ci = fp->f_ci; +- write_lock(&ci->m_lock); ++ down_write(&ci->m_lock); + list_for_each_entry_rcu(op, &ci->m_op_list, op_entry) { + if (op->conn) + continue; + op->conn = fp->conn; + } +- write_unlock(&ci->m_lock); ++ up_write(&ci->m_lock); + + __open_id(&work->sess->file_table, fp, OPEN_ID_TYPE_VOLATILE_ID); + if (!has_file_id(fp->volatile_id)) { +diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h +index ed44fb4e18e79..5a225e7055f19 100644 +--- a/fs/smb/server/vfs_cache.h ++++ b/fs/smb/server/vfs_cache.h +@@ -47,7 +47,7 @@ struct stream { + }; + + struct ksmbd_inode { +- rwlock_t m_lock; ++ struct rw_semaphore m_lock; + atomic_t m_count; + atomic_t op_count; + /* opinfo count for streams */ +-- +2.43.0 + diff --git a/queue-6.6/kvm-sev-do-not-intercept-accesses-to-msr_ia32_xss-fo.patch b/queue-6.6/kvm-sev-do-not-intercept-accesses-to-msr_ia32_xss-fo.patch new file mode 100644 index 00000000000..5d7933f2f36 --- /dev/null +++ b/queue-6.6/kvm-sev-do-not-intercept-accesses-to-msr_ia32_xss-fo.patch @@ -0,0 +1,111 @@ +From 0d2adef0d6b8775bfaad1d626dd690bfc39fa8c4 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 16 Oct 2023 08:27:32 -0500 +Subject: KVM: SEV: Do not intercept accesses to MSR_IA32_XSS for SEV-ES guests + +From: Michael Roth + +[ Upstream commit a26b7cd2254695f8258cc370f33280db0a9a3813 ] + +When intercepts are enabled for MSR_IA32_XSS, the host will swap in/out +the guest-defined values while context-switching to/from guest mode. +However, in the case of SEV-ES, vcpu->arch.guest_state_protected is set, +so the guest-defined value is effectively ignored when switching to +guest mode with the understanding that the VMSA will handle swapping +in/out this register state. + +However, SVM is still configured to intercept these accesses for SEV-ES +guests, so the values in the initial MSR_IA32_XSS are effectively +read-only, and a guest will experience undefined behavior if it actually +tries to write to this MSR. Fortunately, only CET/shadowstack makes use +of this register on SEV-ES-capable systems currently, which isn't yet +widely used, but this may become more of an issue in the future. + +Additionally, enabling intercepts of MSR_IA32_XSS results in #VC +exceptions in the guest in certain paths that can lead to unexpected #VC +nesting levels. One example is SEV-SNP guests when handling #VC +exceptions for CPUID instructions involving leaf 0xD, subleaf 0x1, since +they will access MSR_IA32_XSS as part of servicing the CPUID #VC, then +generate another #VC when accessing MSR_IA32_XSS, which can lead to +guest crashes if an NMI occurs at that point in time. Running perf on a +guest while it is issuing such a sequence is one example where these can +be problematic. + +Address this by disabling intercepts of MSR_IA32_XSS for SEV-ES guests +if the host/guest configuration allows it. If the host/guest +configuration doesn't allow for MSR_IA32_XSS, leave it intercepted so +that it can be caught by the existing checks in +kvm_{set,get}_msr_common() if the guest still attempts to access it. + +Fixes: 376c6d285017 ("KVM: SVM: Provide support for SEV-ES vCPU creation/loading") +Cc: Alexey Kardashevskiy +Suggested-by: Tom Lendacky +Signed-off-by: Michael Roth +Message-Id: <20231016132819.1002933-4-michael.roth@amd.com> +Signed-off-by: Paolo Bonzini +Stable-dep-of: b7e4be0a224f ("KVM: SEV-ES: Delegate LBR virtualization to the processor") +Signed-off-by: Sasha Levin +--- + arch/x86/kvm/svm/sev.c | 19 +++++++++++++++++++ + arch/x86/kvm/svm/svm.c | 1 + + arch/x86/kvm/svm/svm.h | 2 +- + 3 files changed, 21 insertions(+), 1 deletion(-) + +diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c +index 0e643d7a06d9e..f809dcfacc8a3 100644 +--- a/arch/x86/kvm/svm/sev.c ++++ b/arch/x86/kvm/svm/sev.c +@@ -2994,6 +2994,25 @@ static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm) + + set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux); + } ++ ++ /* ++ * For SEV-ES, accesses to MSR_IA32_XSS should not be intercepted if ++ * the host/guest supports its use. ++ * ++ * guest_can_use() checks a number of requirements on the host/guest to ++ * ensure that MSR_IA32_XSS is available, but it might report true even ++ * if X86_FEATURE_XSAVES isn't configured in the guest to ensure host ++ * MSR_IA32_XSS is always properly restored. For SEV-ES, it is better ++ * to further check that the guest CPUID actually supports ++ * X86_FEATURE_XSAVES so that accesses to MSR_IA32_XSS by misbehaved ++ * guests will still get intercepted and caught in the normal ++ * kvm_emulate_rdmsr()/kvm_emulated_wrmsr() paths. ++ */ ++ if (guest_can_use(vcpu, X86_FEATURE_XSAVES) && ++ guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) ++ set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 1, 1); ++ else ++ set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 0, 0); + } + + void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm) +diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c +index 9e084e22a12f7..08f1397138c80 100644 +--- a/arch/x86/kvm/svm/svm.c ++++ b/arch/x86/kvm/svm/svm.c +@@ -103,6 +103,7 @@ static const struct svm_direct_access_msrs { + { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, + { .index = MSR_IA32_LASTINTFROMIP, .always = false }, + { .index = MSR_IA32_LASTINTTOIP, .always = false }, ++ { .index = MSR_IA32_XSS, .always = false }, + { .index = MSR_EFER, .always = false }, + { .index = MSR_IA32_CR_PAT, .always = false }, + { .index = MSR_AMD64_SEV_ES_GHCB, .always = true }, +diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h +index 53bc4b0e388be..fb0ac8497fb20 100644 +--- a/arch/x86/kvm/svm/svm.h ++++ b/arch/x86/kvm/svm/svm.h +@@ -30,7 +30,7 @@ + #define IOPM_SIZE PAGE_SIZE * 3 + #define MSRPM_SIZE PAGE_SIZE * 2 + +-#define MAX_DIRECT_ACCESS_MSRS 46 ++#define MAX_DIRECT_ACCESS_MSRS 47 + #define MSRPM_OFFSETS 32 + extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; + extern bool npt_enabled; +-- +2.43.0 + diff --git a/queue-6.6/kvm-sev-es-delegate-lbr-virtualization-to-the-proces.patch b/queue-6.6/kvm-sev-es-delegate-lbr-virtualization-to-the-proces.patch new file mode 100644 index 00000000000..43fad7d4104 --- /dev/null +++ b/queue-6.6/kvm-sev-es-delegate-lbr-virtualization-to-the-proces.patch @@ -0,0 +1,148 @@ +From a2c2128bf706bb2619e38ef0d65a87e26533be0c Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 31 May 2024 04:46:44 +0000 +Subject: KVM: SEV-ES: Delegate LBR virtualization to the processor + +From: Ravi Bangoria + +[ Upstream commit b7e4be0a224fe5c6be30c1c8bdda8d2317ad6ba4 ] + +As documented in APM[1], LBR Virtualization must be enabled for SEV-ES +guests. Although KVM currently enforces LBRV for SEV-ES guests, there +are multiple issues with it: + +o MSR_IA32_DEBUGCTLMSR is still intercepted. Since MSR_IA32_DEBUGCTLMSR + interception is used to dynamically toggle LBRV for performance reasons, + this can be fatal for SEV-ES guests. For ex SEV-ES guest on Zen3: + + [guest ~]# wrmsr 0x1d9 0x4 + KVM: entry failed, hardware error 0xffffffff + EAX=00000004 EBX=00000000 ECX=000001d9 EDX=00000000 + + Fix this by never intercepting MSR_IA32_DEBUGCTLMSR for SEV-ES guests. + No additional save/restore logic is required since MSR_IA32_DEBUGCTLMSR + is of swap type A. + +o KVM will disable LBRV if userspace sets MSR_IA32_DEBUGCTLMSR before the + VMSA is encrypted. Fix this by moving LBRV enablement code post VMSA + encryption. + +[1]: AMD64 Architecture Programmer's Manual Pub. 40332, Rev. 4.07 - June + 2023, Vol 2, 15.35.2 Enabling SEV-ES. + https://bugzilla.kernel.org/attachment.cgi?id=304653 + +Fixes: 376c6d285017 ("KVM: SVM: Provide support for SEV-ES vCPU creation/loading") +Co-developed-by: Nikunj A Dadhania +Signed-off-by: Nikunj A Dadhania +Signed-off-by: Ravi Bangoria +Message-ID: <20240531044644.768-4-ravi.bangoria@amd.com> +Signed-off-by: Paolo Bonzini +Signed-off-by: Sasha Levin +--- + arch/x86/kvm/svm/sev.c | 13 ++++++++----- + arch/x86/kvm/svm/svm.c | 8 +++++++- + arch/x86/kvm/svm/svm.h | 3 ++- + 3 files changed, 17 insertions(+), 7 deletions(-) + +diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c +index f809dcfacc8a3..99e72b8a96ac0 100644 +--- a/arch/x86/kvm/svm/sev.c ++++ b/arch/x86/kvm/svm/sev.c +@@ -664,6 +664,14 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, + return ret; + + vcpu->arch.guest_state_protected = true; ++ ++ /* ++ * SEV-ES guest mandates LBR Virtualization to be _always_ ON. Enable it ++ * only after setting guest_state_protected because KVM_SET_MSRS allows ++ * dynamic toggling of LBRV (for performance reason) on write access to ++ * MSR_IA32_DEBUGCTLMSR when guest_state_protected is not set. ++ */ ++ svm_enable_lbrv(vcpu); + return 0; + } + +@@ -3035,7 +3043,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) + struct kvm_vcpu *vcpu = &svm->vcpu; + + svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE; +- svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK; + + /* + * An SEV-ES guest requires a VMSA area that is a separate from the +@@ -3087,10 +3094,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) + /* Clear intercepts on selected MSRs */ + set_msr_interception(vcpu, svm->msrpm, MSR_EFER, 1, 1); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_CR_PAT, 1, 1); +- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1); +- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); +- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); +- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); + } + + void sev_init_vmcb(struct vcpu_svm *svm) +diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c +index 08f1397138c80..e3c2acc1adc73 100644 +--- a/arch/x86/kvm/svm/svm.c ++++ b/arch/x86/kvm/svm/svm.c +@@ -99,6 +99,7 @@ static const struct svm_direct_access_msrs { + { .index = MSR_IA32_SPEC_CTRL, .always = false }, + { .index = MSR_IA32_PRED_CMD, .always = false }, + { .index = MSR_IA32_FLUSH_CMD, .always = false }, ++ { .index = MSR_IA32_DEBUGCTLMSR, .always = false }, + { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, + { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, + { .index = MSR_IA32_LASTINTFROMIP, .always = false }, +@@ -1008,7 +1009,7 @@ void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb) + vmcb_mark_dirty(to_vmcb, VMCB_LBR); + } + +-static void svm_enable_lbrv(struct kvm_vcpu *vcpu) ++void svm_enable_lbrv(struct kvm_vcpu *vcpu) + { + struct vcpu_svm *svm = to_svm(vcpu); + +@@ -1018,6 +1019,9 @@ static void svm_enable_lbrv(struct kvm_vcpu *vcpu) + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); + ++ if (sev_es_guest(vcpu->kvm)) ++ set_msr_interception(vcpu, svm->msrpm, MSR_IA32_DEBUGCTLMSR, 1, 1); ++ + /* Move the LBR msrs to the vmcb02 so that the guest can see them. */ + if (is_guest_mode(vcpu)) + svm_copy_lbrs(svm->vmcb, svm->vmcb01.ptr); +@@ -1027,6 +1031,8 @@ static void svm_disable_lbrv(struct kvm_vcpu *vcpu) + { + struct vcpu_svm *svm = to_svm(vcpu); + ++ KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm); ++ + svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK; + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0); +diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h +index fb0ac8497fb20..37ada9808d9b5 100644 +--- a/arch/x86/kvm/svm/svm.h ++++ b/arch/x86/kvm/svm/svm.h +@@ -30,7 +30,7 @@ + #define IOPM_SIZE PAGE_SIZE * 3 + #define MSRPM_SIZE PAGE_SIZE * 2 + +-#define MAX_DIRECT_ACCESS_MSRS 47 ++#define MAX_DIRECT_ACCESS_MSRS 48 + #define MSRPM_OFFSETS 32 + extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; + extern bool npt_enabled; +@@ -542,6 +542,7 @@ u32 *svm_vcpu_alloc_msrpm(void); + void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm); + void svm_vcpu_free_msrpm(u32 *msrpm); + void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb); ++void svm_enable_lbrv(struct kvm_vcpu *vcpu); + void svm_update_lbrv(struct kvm_vcpu *vcpu); + + int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer); +-- +2.43.0 + diff --git a/queue-6.6/kvm-sev-es-disallow-sev-es-guests-when-x86_feature_l.patch b/queue-6.6/kvm-sev-es-disallow-sev-es-guests-when-x86_feature_l.patch new file mode 100644 index 00000000000..d5d1767d7d7 --- /dev/null +++ b/queue-6.6/kvm-sev-es-disallow-sev-es-guests-when-x86_feature_l.patch @@ -0,0 +1,100 @@ +From ff0ac631a134392bed4fad24c0fcc162204be63a Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 31 May 2024 04:46:43 +0000 +Subject: KVM: SEV-ES: Disallow SEV-ES guests when X86_FEATURE_LBRV is absent + +From: Ravi Bangoria + +[ Upstream commit d922056215617eedfbdbc29fe49953423686fe5e ] + +As documented in APM[1], LBR Virtualization must be enabled for SEV-ES +guests. So, prevent SEV-ES guests when LBRV support is missing. + +[1]: AMD64 Architecture Programmer's Manual Pub. 40332, Rev. 4.07 - June + 2023, Vol 2, 15.35.2 Enabling SEV-ES. + https://bugzilla.kernel.org/attachment.cgi?id=304653 + +Fixes: 376c6d285017 ("KVM: SVM: Provide support for SEV-ES vCPU creation/loading") +Signed-off-by: Ravi Bangoria +Message-ID: <20240531044644.768-3-ravi.bangoria@amd.com> +Signed-off-by: Paolo Bonzini +Signed-off-by: Sasha Levin +--- + arch/x86/kvm/svm/sev.c | 6 ++++++ + arch/x86/kvm/svm/svm.c | 16 +++++++--------- + arch/x86/kvm/svm/svm.h | 1 + + 3 files changed, 14 insertions(+), 9 deletions(-) + +diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c +index c5845f31c34dc..0e643d7a06d9e 100644 +--- a/arch/x86/kvm/svm/sev.c ++++ b/arch/x86/kvm/svm/sev.c +@@ -2264,6 +2264,12 @@ void __init sev_hardware_setup(void) + if (!boot_cpu_has(X86_FEATURE_SEV_ES)) + goto out; + ++ if (!lbrv) { ++ WARN_ONCE(!boot_cpu_has(X86_FEATURE_LBRV), ++ "LBRV must be present for SEV-ES support"); ++ goto out; ++ } ++ + /* Has the system been allocated ASIDs for SEV-ES? */ + if (min_sev_asid == 1) + goto out; +diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c +index 1efbe8b33f6a1..9e084e22a12f7 100644 +--- a/arch/x86/kvm/svm/svm.c ++++ b/arch/x86/kvm/svm/svm.c +@@ -214,7 +214,7 @@ int vgif = true; + module_param(vgif, int, 0444); + + /* enable/disable LBR virtualization */ +-static int lbrv = true; ++int lbrv = true; + module_param(lbrv, int, 0444); + + static int tsc_scaling = true; +@@ -5248,6 +5248,12 @@ static __init int svm_hardware_setup(void) + + nrips = nrips && boot_cpu_has(X86_FEATURE_NRIPS); + ++ if (lbrv) { ++ if (!boot_cpu_has(X86_FEATURE_LBRV)) ++ lbrv = false; ++ else ++ pr_info("LBR virtualization supported\n"); ++ } + /* + * Note, SEV setup consumes npt_enabled and enable_mmio_caching (which + * may be modified by svm_adjust_mmio_mask()), as well as nrips. +@@ -5301,14 +5307,6 @@ static __init int svm_hardware_setup(void) + svm_x86_ops.set_vnmi_pending = NULL; + } + +- +- if (lbrv) { +- if (!boot_cpu_has(X86_FEATURE_LBRV)) +- lbrv = false; +- else +- pr_info("LBR virtualization supported\n"); +- } +- + if (!enable_pmu) + pr_info("PMU virtualization is disabled\n"); + +diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h +index be67ab7fdd104..53bc4b0e388be 100644 +--- a/arch/x86/kvm/svm/svm.h ++++ b/arch/x86/kvm/svm/svm.h +@@ -39,6 +39,7 @@ extern int vgif; + extern bool intercept_smi; + extern bool x2avic_enabled; + extern bool vnmi; ++extern int lbrv; + + /* + * Clean bits in VMCB. +-- +2.43.0 + diff --git a/queue-6.6/memory-failure-use-a-folio-in-me_huge_page.patch b/queue-6.6/memory-failure-use-a-folio-in-me_huge_page.patch new file mode 100644 index 00000000000..5ce3fec6f4e --- /dev/null +++ b/queue-6.6/memory-failure-use-a-folio-in-me_huge_page.patch @@ -0,0 +1,63 @@ +From ca963e2fedd01fd9b6180487a9c2b85fd5db4160 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 17 Nov 2023 16:14:45 +0000 +Subject: memory-failure: use a folio in me_huge_page() + +From: Matthew Wilcox (Oracle) + +[ Upstream commit b6fd410c32f1a66a52a42d6aae1ab7b011b74547 ] + +This function was already explicitly calling compound_head(); +unfortunately the compiler can't know that and elide the redundant calls +to compound_head() buried in page_mapping(), unlock_page(), etc. Switch +to using a folio, which does let us elide these calls. + +Link: https://lkml.kernel.org/r/20231117161447.2461643-5-willy@infradead.org +Signed-off-by: Matthew Wilcox (Oracle) +Cc: Naoya Horiguchi +Signed-off-by: Andrew Morton +Stable-dep-of: 8cf360b9d6a8 ("mm/memory-failure: fix handling of dissolved but not taken off from buddy pages") +Signed-off-by: Sasha Levin +--- + mm/memory-failure.c | 12 ++++++------ + 1 file changed, 6 insertions(+), 6 deletions(-) + +diff --git a/mm/memory-failure.c b/mm/memory-failure.c +index 5378edad9df8f..9c27ec0a27a30 100644 +--- a/mm/memory-failure.c ++++ b/mm/memory-failure.c +@@ -1193,25 +1193,25 @@ static int me_swapcache_clean(struct page_state *ps, struct page *p) + */ + static int me_huge_page(struct page_state *ps, struct page *p) + { ++ struct folio *folio = page_folio(p); + int res; +- struct page *hpage = compound_head(p); + struct address_space *mapping; + bool extra_pins = false; + +- mapping = page_mapping(hpage); ++ mapping = folio_mapping(folio); + if (mapping) { +- res = truncate_error_page(hpage, page_to_pfn(p), mapping); ++ res = truncate_error_page(&folio->page, page_to_pfn(p), mapping); + /* The page is kept in page cache. */ + extra_pins = true; +- unlock_page(hpage); ++ folio_unlock(folio); + } else { +- unlock_page(hpage); ++ folio_unlock(folio); + /* + * migration entry prevents later access on error hugepage, + * so we can free and dissolve it into buddy to save healthy + * subpages. + */ +- put_page(hpage); ++ folio_put(folio); + if (__page_handle_poison(p) >= 0) { + page_ref_inc(p); + res = MF_RECOVERED; +-- +2.43.0 + diff --git a/queue-6.6/mm-memory-failure-fix-handling-of-dissolved-but-not-.patch b/queue-6.6/mm-memory-failure-fix-handling-of-dissolved-but-not-.patch new file mode 100644 index 00000000000..e921c9cfc2e --- /dev/null +++ b/queue-6.6/mm-memory-failure-fix-handling-of-dissolved-but-not-.patch @@ -0,0 +1,147 @@ +From bf13c3d590f238b92e3275732323c81088339738 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 23 May 2024 15:12:17 +0800 +Subject: mm/memory-failure: fix handling of dissolved but not taken off from + buddy pages + +From: Miaohe Lin + +[ Upstream commit 8cf360b9d6a840700e06864236a01a883b34bbad ] + +When I did memory failure tests recently, below panic occurs: + +page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x8cee00 +flags: 0x6fffe0000000000(node=1|zone=2|lastcpupid=0x7fff) +raw: 06fffe0000000000 dead000000000100 dead000000000122 0000000000000000 +raw: 0000000000000000 0000000000000009 00000000ffffffff 0000000000000000 +page dumped because: VM_BUG_ON_PAGE(!PageBuddy(page)) +------------[ cut here ]------------ +kernel BUG at include/linux/page-flags.h:1009! +invalid opcode: 0000 [#1] PREEMPT SMP NOPTI +RIP: 0010:__del_page_from_free_list+0x151/0x180 +RSP: 0018:ffffa49c90437998 EFLAGS: 00000046 +RAX: 0000000000000035 RBX: 0000000000000009 RCX: ffff8dd8dfd1c9c8 +RDX: 0000000000000000 RSI: 0000000000000027 RDI: ffff8dd8dfd1c9c0 +RBP: ffffd901233b8000 R08: ffffffffab5511f8 R09: 0000000000008c69 +R10: 0000000000003c15 R11: ffffffffab5511f8 R12: ffff8dd8fffc0c80 +R13: 0000000000000001 R14: ffff8dd8fffc0c80 R15: 0000000000000009 +FS: 00007ff916304740(0000) GS:ffff8dd8dfd00000(0000) knlGS:0000000000000000 +CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +CR2: 000055eae50124c8 CR3: 00000008479e0000 CR4: 00000000000006f0 +Call Trace: + + __rmqueue_pcplist+0x23b/0x520 + get_page_from_freelist+0x26b/0xe40 + __alloc_pages_noprof+0x113/0x1120 + __folio_alloc_noprof+0x11/0xb0 + alloc_buddy_hugetlb_folio.isra.0+0x5a/0x130 + __alloc_fresh_hugetlb_folio+0xe7/0x140 + alloc_pool_huge_folio+0x68/0x100 + set_max_huge_pages+0x13d/0x340 + hugetlb_sysctl_handler_common+0xe8/0x110 + proc_sys_call_handler+0x194/0x280 + vfs_write+0x387/0x550 + ksys_write+0x64/0xe0 + do_syscall_64+0xc2/0x1d0 + entry_SYSCALL_64_after_hwframe+0x77/0x7f +RIP: 0033:0x7ff916114887 +RSP: 002b:00007ffec8a2fd78 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 +RAX: ffffffffffffffda RBX: 000055eae500e350 RCX: 00007ff916114887 +RDX: 0000000000000004 RSI: 000055eae500e390 RDI: 0000000000000003 +RBP: 000055eae50104c0 R08: 0000000000000000 R09: 000055eae50104c0 +R10: 0000000000000077 R11: 0000000000000246 R12: 0000000000000004 +R13: 0000000000000004 R14: 00007ff916216b80 R15: 00007ff916216a00 + +Modules linked in: mce_inject hwpoison_inject +---[ end trace 0000000000000000 ]--- + +And before the panic, there had an warning about bad page state: + +BUG: Bad page state in process page-types pfn:8cee00 +page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x8cee00 +flags: 0x6fffe0000000000(node=1|zone=2|lastcpupid=0x7fff) +page_type: 0xffffff7f(buddy) +raw: 06fffe0000000000 ffffd901241c0008 ffffd901240f8008 0000000000000000 +raw: 0000000000000000 0000000000000009 00000000ffffff7f 0000000000000000 +page dumped because: nonzero mapcount +Modules linked in: mce_inject hwpoison_inject +CPU: 8 PID: 154211 Comm: page-types Not tainted 6.9.0-rc4-00499-g5544ec3178e2-dirty #22 +Call Trace: + + dump_stack_lvl+0x83/0xa0 + bad_page+0x63/0xf0 + free_unref_page+0x36e/0x5c0 + unpoison_memory+0x50b/0x630 + simple_attr_write_xsigned.constprop.0.isra.0+0xb3/0x110 + debugfs_attr_write+0x42/0x60 + full_proxy_write+0x5b/0x80 + vfs_write+0xcd/0x550 + ksys_write+0x64/0xe0 + do_syscall_64+0xc2/0x1d0 + entry_SYSCALL_64_after_hwframe+0x77/0x7f +RIP: 0033:0x7f189a514887 +RSP: 002b:00007ffdcd899718 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 +RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f189a514887 +RDX: 0000000000000009 RSI: 00007ffdcd899730 RDI: 0000000000000003 +RBP: 00007ffdcd8997a0 R08: 0000000000000000 R09: 00007ffdcd8994b2 +R10: 0000000000000000 R11: 0000000000000246 R12: 00007ffdcda199a8 +R13: 0000000000404af1 R14: 000000000040ad78 R15: 00007f189a7a5040 + + +The root cause should be the below race: + + memory_failure + try_memory_failure_hugetlb + me_huge_page + __page_handle_poison + dissolve_free_hugetlb_folio + drain_all_pages -- Buddy page can be isolated e.g. for compaction. + take_page_off_buddy -- Failed as page is not in the buddy list. + -- Page can be putback into buddy after compaction. + page_ref_inc -- Leads to buddy page with refcnt = 1. + +Then unpoison_memory() can unpoison the page and send the buddy page back +into buddy list again leading to the above bad page state warning. And +bad_page() will call page_mapcount_reset() to remove PageBuddy from buddy +page leading to later VM_BUG_ON_PAGE(!PageBuddy(page)) when trying to +allocate this page. + +Fix this issue by only treating __page_handle_poison() as successful when +it returns 1. + +Link: https://lkml.kernel.org/r/20240523071217.1696196-1-linmiaohe@huawei.com +Fixes: ceaf8fbea79a ("mm, hwpoison: skip raw hwpoison page in freeing 1GB hugepage") +Signed-off-by: Miaohe Lin +Cc: Naoya Horiguchi +Cc: +Signed-off-by: Andrew Morton +Signed-off-by: Sasha Levin +--- + mm/memory-failure.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/mm/memory-failure.c b/mm/memory-failure.c +index 9c27ec0a27a30..c7e2b609184b6 100644 +--- a/mm/memory-failure.c ++++ b/mm/memory-failure.c +@@ -1212,7 +1212,7 @@ static int me_huge_page(struct page_state *ps, struct page *p) + * subpages. + */ + folio_put(folio); +- if (__page_handle_poison(p) >= 0) { ++ if (__page_handle_poison(p) > 0) { + page_ref_inc(p); + res = MF_RECOVERED; + } else { +@@ -2082,7 +2082,7 @@ static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb + */ + if (res == 0) { + folio_unlock(folio); +- if (__page_handle_poison(p) >= 0) { ++ if (__page_handle_poison(p) > 0) { + page_ref_inc(p); + res = MF_RECOVERED; + } else { +-- +2.43.0 + diff --git a/queue-6.6/mptcp-count-close-wait-sockets-for-mptcp_mib_currest.patch b/queue-6.6/mptcp-count-close-wait-sockets-for-mptcp_mib_currest.patch new file mode 100644 index 00000000000..9cb6bec9dd1 --- /dev/null +++ b/queue-6.6/mptcp-count-close-wait-sockets-for-mptcp_mib_currest.patch @@ -0,0 +1,61 @@ +From d24c56ac9d2f8400d8ea97477f8a506c309e7def Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 01:02:17 +0800 +Subject: mptcp: count CLOSE-WAIT sockets for MPTCP_MIB_CURRESTAB + +From: Jason Xing + +[ Upstream commit 9633e9377e6af0244f7381e86b9aac5276f5be97 ] + +Like previous patch does in TCP, we need to adhere to RFC 1213: + + "tcpCurrEstab OBJECT-TYPE + ... + The number of TCP connections for which the current state + is either ESTABLISHED or CLOSE- WAIT." + +So let's consider CLOSE-WAIT sockets. + +The logic of counting +When we increment the counter? +a) Only if we change the state to ESTABLISHED. + +When we decrement the counter? +a) if the socket leaves ESTABLISHED and will never go into CLOSE-WAIT, +say, on the client side, changing from ESTABLISHED to FIN-WAIT-1. +b) if the socket leaves CLOSE-WAIT, say, on the server side, changing +from CLOSE-WAIT to LAST-ACK. + +Fixes: d9cd27b8cd19 ("mptcp: add CurrEstab MIB counter support") +Signed-off-by: Jason Xing +Reviewed-by: Matthieu Baerts (NGI0) +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/mptcp/protocol.c | 9 +++++++-- + 1 file changed, 7 insertions(+), 2 deletions(-) + +diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c +index 618d80112d1e2..4ace52e4211ad 100644 +--- a/net/mptcp/protocol.c ++++ b/net/mptcp/protocol.c +@@ -2873,9 +2873,14 @@ void mptcp_set_state(struct sock *sk, int state) + if (oldstate != TCP_ESTABLISHED) + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB); + break; +- ++ case TCP_CLOSE_WAIT: ++ /* Unlike TCP, MPTCP sk would not have the TCP_SYN_RECV state: ++ * MPTCP "accepted" sockets will be created later on. So no ++ * transition from TCP_SYN_RECV to TCP_CLOSE_WAIT. ++ */ ++ break; + default: +- if (oldstate == TCP_ESTABLISHED) ++ if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT) + MPTCP_DEC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB); + } + +-- +2.43.0 + diff --git a/queue-6.6/net-ethtool-fix-the-error-condition-in-ethtool_get_p.patch b/queue-6.6/net-ethtool-fix-the-error-condition-in-ethtool_get_p.patch new file mode 100644 index 00000000000..d90dad8f032 --- /dev/null +++ b/queue-6.6/net-ethtool-fix-the-error-condition-in-ethtool_get_p.patch @@ -0,0 +1,44 @@ +From 7597eef1bf5f3cbcf838db6f39e7099437437502 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 5 Jun 2024 11:47:43 +0800 +Subject: net: ethtool: fix the error condition in + ethtool_get_phy_stats_ethtool() + +From: Su Hui + +[ Upstream commit 0dcc53abf58d572d34c5313de85f607cd33fc691 ] + +Clang static checker (scan-build) warning: +net/ethtool/ioctl.c:line 2233, column 2 +Called function pointer is null (null dereference). + +Return '-EOPNOTSUPP' when 'ops->get_ethtool_phy_stats' is NULL to fix +this typo error. + +Fixes: 201ed315f967 ("net/ethtool/ioctl: split ethtool_get_phy_stats into multiple helpers") +Signed-off-by: Su Hui +Reviewed-by: Przemek Kitszel +Reviewed-by: Hariprasad Kelam +Link: https://lore.kernel.org/r/20240605034742.921751-1-suhui@nfschina.com +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/ethtool/ioctl.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c +index 0b0ce4f81c017..7cb23bcf8ef7a 100644 +--- a/net/ethtool/ioctl.c ++++ b/net/ethtool/ioctl.c +@@ -2134,7 +2134,7 @@ static int ethtool_get_phy_stats_ethtool(struct net_device *dev, + const struct ethtool_ops *ops = dev->ethtool_ops; + int n_stats, ret; + +- if (!ops || !ops->get_sset_count || ops->get_ethtool_phy_stats) ++ if (!ops || !ops->get_sset_count || !ops->get_ethtool_phy_stats) + return -EOPNOTSUPP; + + n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS); +-- +2.43.0 + diff --git a/queue-6.6/net-mlx5-always-stop-health-timer-during-driver-remo.patch b/queue-6.6/net-mlx5-always-stop-health-timer-during-driver-remo.patch new file mode 100644 index 00000000000..744b7886c63 --- /dev/null +++ b/queue-6.6/net-mlx5-always-stop-health-timer-during-driver-remo.patch @@ -0,0 +1,105 @@ +From 19a8d0c667bfb8613b3ba9953f573b5329ef8832 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 00:04:43 +0300 +Subject: net/mlx5: Always stop health timer during driver removal + +From: Shay Drory + +[ Upstream commit c8b3f38d2dae0397944814d691a419c451f9906f ] + +Currently, if teardown_hca fails to execute during driver removal, mlx5 +does not stop the health timer. Afterwards, mlx5 continue with driver +teardown. This may lead to a UAF bug, which results in page fault +Oops[1], since the health timer invokes after resources were freed. + +Hence, stop the health monitor even if teardown_hca fails. + +[1] +mlx5_core 0000:18:00.0: E-Switch: Unload vfs: mode(LEGACY), nvfs(0), necvfs(0), active vports(0) +mlx5_core 0000:18:00.0: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0) +mlx5_core 0000:18:00.0: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0) +mlx5_core 0000:18:00.0: E-Switch: cleanup +mlx5_core 0000:18:00.0: wait_func:1155:(pid 1967079): TEARDOWN_HCA(0x103) timeout. Will cause a leak of a command resource +mlx5_core 0000:18:00.0: mlx5_function_close:1288:(pid 1967079): tear_down_hca failed, skip cleanup +BUG: unable to handle page fault for address: ffffa26487064230 +PGD 100c00067 P4D 100c00067 PUD 100e5a067 PMD 105ed7067 PTE 0 +Oops: 0000 [#1] PREEMPT SMP PTI +CPU: 0 PID: 0 Comm: swapper/0 Tainted: G OE ------- --- 6.7.0-68.fc38.x86_64 #1 +Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0013.121520200651 12/15/2020 +RIP: 0010:ioread32be+0x34/0x60 +RSP: 0018:ffffa26480003e58 EFLAGS: 00010292 +RAX: ffffa26487064200 RBX: ffff9042d08161a0 RCX: ffff904c108222c0 +RDX: 000000010bbf1b80 RSI: ffffffffc055ddb0 RDI: ffffa26487064230 +RBP: ffff9042d08161a0 R08: 0000000000000022 R09: ffff904c108222e8 +R10: 0000000000000004 R11: 0000000000000441 R12: ffffffffc055ddb0 +R13: ffffa26487064200 R14: ffffa26480003f00 R15: ffff904c108222c0 +FS: 0000000000000000(0000) GS:ffff904c10800000(0000) knlGS:0000000000000000 +CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +CR2: ffffa26487064230 CR3: 00000002c4420006 CR4: 00000000007706f0 +DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 +DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 +PKRU: 55555554 +Call Trace: + + ? __die+0x23/0x70 + ? page_fault_oops+0x171/0x4e0 + ? exc_page_fault+0x175/0x180 + ? asm_exc_page_fault+0x26/0x30 + ? __pfx_poll_health+0x10/0x10 [mlx5_core] + ? __pfx_poll_health+0x10/0x10 [mlx5_core] + ? ioread32be+0x34/0x60 + mlx5_health_check_fatal_sensors+0x20/0x100 [mlx5_core] + ? __pfx_poll_health+0x10/0x10 [mlx5_core] + poll_health+0x42/0x230 [mlx5_core] + ? __next_timer_interrupt+0xbc/0x110 + ? __pfx_poll_health+0x10/0x10 [mlx5_core] + call_timer_fn+0x21/0x130 + ? __pfx_poll_health+0x10/0x10 [mlx5_core] + __run_timers+0x222/0x2c0 + run_timer_softirq+0x1d/0x40 + __do_softirq+0xc9/0x2c8 + __irq_exit_rcu+0xa6/0xc0 + sysvec_apic_timer_interrupt+0x72/0x90 + + + asm_sysvec_apic_timer_interrupt+0x1a/0x20 +RIP: 0010:cpuidle_enter_state+0xcc/0x440 + ? cpuidle_enter_state+0xbd/0x440 + cpuidle_enter+0x2d/0x40 + do_idle+0x20d/0x270 + cpu_startup_entry+0x2a/0x30 + rest_init+0xd0/0xd0 + arch_call_rest_init+0xe/0x30 + start_kernel+0x709/0xa90 + x86_64_start_reservations+0x18/0x30 + x86_64_start_kernel+0x96/0xa0 + secondary_startup_64_no_verify+0x18f/0x19b +---[ end trace 0000000000000000 ]--- + +Fixes: 9b98d395b85d ("net/mlx5: Start health poll at earlier stage of driver load") +Signed-off-by: Shay Drory +Reviewed-by: Moshe Shemesh +Signed-off-by: Tariq Toukan +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/mellanox/mlx5/core/main.c | 3 +++ + 1 file changed, 3 insertions(+) + +diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c +index 9710ddac1f1a8..2237b3d01e0e5 100644 +--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c ++++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c +@@ -1287,6 +1287,9 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot) + + if (!err) + mlx5_function_disable(dev, boot); ++ else ++ mlx5_stop_health_poll(dev, boot); ++ + return err; + } + +-- +2.43.0 + diff --git a/queue-6.6/net-mlx5-fix-tainted-pointer-delete-is-case-of-flow-.patch b/queue-6.6/net-mlx5-fix-tainted-pointer-delete-is-case-of-flow-.patch new file mode 100644 index 00000000000..c6ec2b3ebb6 --- /dev/null +++ b/queue-6.6/net-mlx5-fix-tainted-pointer-delete-is-case-of-flow-.patch @@ -0,0 +1,51 @@ +From efc6b345f3586c85d0f061b43bc4710c5d95bdab Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 13:05:52 +0300 +Subject: net/mlx5: Fix tainted pointer delete is case of flow rules creation + fail + +From: Aleksandr Mishin + +[ Upstream commit 229bedbf62b13af5aba6525ad10b62ad38d9ccb5 ] + +In case of flow rule creation fail in mlx5_lag_create_port_sel_table(), +instead of previously created rules, the tainted pointer is deleted +deveral times. +Fix this bug by using correct flow rules pointers. + +Found by Linux Verification Center (linuxtesting.org) with SVACE. + +Fixes: 352899f384d4 ("net/mlx5: Lag, use buckets in hash mode") +Signed-off-by: Aleksandr Mishin +Reviewed-by: Jacob Keller +Reviewed-by: Tariq Toukan +Link: https://lore.kernel.org/r/20240604100552.25201-1-amishin@t-argos.ru +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c | 8 ++++++-- + 1 file changed, 6 insertions(+), 2 deletions(-) + +diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c +index 7d9bbb494d95b..005661248c7e9 100644 +--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c ++++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c +@@ -88,9 +88,13 @@ static int mlx5_lag_create_port_sel_table(struct mlx5_lag *ldev, + &dest, 1); + if (IS_ERR(lag_definer->rules[idx])) { + err = PTR_ERR(lag_definer->rules[idx]); +- while (i--) +- while (j--) ++ do { ++ while (j--) { ++ idx = i * ldev->buckets + j; + mlx5_del_flow_rules(lag_definer->rules[idx]); ++ } ++ j = ldev->buckets; ++ } while (i--); + goto destroy_fg; + } + } +-- +2.43.0 + diff --git a/queue-6.6/net-mlx5-stop-waiting-for-pci-if-pci-channel-is-offl.patch b/queue-6.6/net-mlx5-stop-waiting-for-pci-if-pci-channel-is-offl.patch new file mode 100644 index 00000000000..99e718ca03e --- /dev/null +++ b/queue-6.6/net-mlx5-stop-waiting-for-pci-if-pci-channel-is-offl.patch @@ -0,0 +1,86 @@ +From e88b9027c87901fe100c47670d360c31adda2fd5 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 00:04:42 +0300 +Subject: net/mlx5: Stop waiting for PCI if pci channel is offline + +From: Moshe Shemesh + +[ Upstream commit 33afbfcc105a572159750f2ebee834a8a70fdd96 ] + +In case pci channel becomes offline the driver should not wait for PCI +reads during health dump and recovery flow. The driver has timeout for +each of these loops trying to read PCI, so it would fail anyway. +However, in case of recovery waiting till timeout may cause the pci +error_detected() callback fail to meet pci_dpc_recovered() wait timeout. + +Fixes: b3bd076f7501 ("net/mlx5: Report devlink health on FW fatal issues") +Signed-off-by: Moshe Shemesh +Reviewed-by: Shay Drori +Signed-off-by: Tariq Toukan +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/mellanox/mlx5/core/fw.c | 4 ++++ + drivers/net/ethernet/mellanox/mlx5/core/health.c | 8 ++++++++ + drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c | 4 ++++ + 3 files changed, 16 insertions(+) + +diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c +index 58f4c0d0fafa2..70898f0a9866c 100644 +--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c ++++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c +@@ -373,6 +373,10 @@ int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev) + do { + if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) + break; ++ if (pci_channel_offline(dev->pdev)) { ++ mlx5_core_err(dev, "PCI channel offline, stop waiting for NIC IFC\n"); ++ return -EACCES; ++ } + + cond_resched(); + } while (!time_after(jiffies, end)); +diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c +index 2fb2598b775ef..d798834c4e755 100644 +--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c ++++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c +@@ -248,6 +248,10 @@ void mlx5_error_sw_reset(struct mlx5_core_dev *dev) + do { + if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) + break; ++ if (pci_channel_offline(dev->pdev)) { ++ mlx5_core_err(dev, "PCI channel offline, stop waiting for NIC IFC\n"); ++ goto unlock; ++ } + + msleep(20); + } while (!time_after(jiffies, end)); +@@ -317,6 +321,10 @@ int mlx5_health_wait_pci_up(struct mlx5_core_dev *dev) + mlx5_core_warn(dev, "device is being removed, stop waiting for PCI\n"); + return -ENODEV; + } ++ if (pci_channel_offline(dev->pdev)) { ++ mlx5_core_err(dev, "PCI channel offline, stop waiting for PCI\n"); ++ return -EACCES; ++ } + msleep(100); + } + return 0; +diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c +index 6b774e0c27665..d0b595ba61101 100644 +--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c ++++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c +@@ -74,6 +74,10 @@ int mlx5_vsc_gw_lock(struct mlx5_core_dev *dev) + ret = -EBUSY; + goto pci_unlock; + } ++ if (pci_channel_offline(dev->pdev)) { ++ ret = -EACCES; ++ goto pci_unlock; ++ } + + /* Check if semaphore is already locked */ + ret = vsc_read(dev, VSC_SEMAPHORE_OFFSET, &lock_val); +-- +2.43.0 + diff --git a/queue-6.6/net-ncsi-fix-the-multi-thread-manner-of-ncsi-driver.patch b/queue-6.6/net-ncsi-fix-the-multi-thread-manner-of-ncsi-driver.patch new file mode 100644 index 00000000000..9328ddd621c --- /dev/null +++ b/queue-6.6/net-ncsi-fix-the-multi-thread-manner-of-ncsi-driver.patch @@ -0,0 +1,220 @@ +From 4f2d6470d0422c2965ac6f511c08b8a976441ce5 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 29 May 2024 14:58:55 +0800 +Subject: net/ncsi: Fix the multi thread manner of NCSI driver + +From: DelphineCCChiu + +[ Upstream commit e85e271dec0270982afed84f70dc37703fcc1d52 ] + +Currently NCSI driver will send several NCSI commands back to back without +waiting the response of previous NCSI command or timeout in some state +when NIC have multi channel. This operation against the single thread +manner defined by NCSI SPEC(section 6.3.2.3 in DSP0222_1.1.1) + +According to NCSI SPEC(section 6.2.13.1 in DSP0222_1.1.1), we should probe +one channel at a time by sending NCSI commands (Clear initial state, Get +version ID, Get capabilities...), than repeat this steps until the max +number of channels which we got from NCSI command (Get capabilities) has +been probed. + +Fixes: e6f44ed6d04d ("net/ncsi: Package and channel management") +Signed-off-by: DelphineCCChiu +Link: https://lore.kernel.org/r/20240529065856.825241-1-delphine_cc_chiu@wiwynn.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/ncsi/internal.h | 2 ++ + net/ncsi/ncsi-manage.c | 73 +++++++++++++++++++++--------------------- + net/ncsi/ncsi-rsp.c | 4 ++- + 3 files changed, 41 insertions(+), 38 deletions(-) + +diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h +index 374412ed780b6..ef0f8f73826f5 100644 +--- a/net/ncsi/internal.h ++++ b/net/ncsi/internal.h +@@ -325,6 +325,7 @@ struct ncsi_dev_priv { + spinlock_t lock; /* Protect the NCSI device */ + unsigned int package_probe_id;/* Current ID during probe */ + unsigned int package_num; /* Number of packages */ ++ unsigned int channel_probe_id;/* Current cahnnel ID during probe */ + struct list_head packages; /* List of packages */ + struct ncsi_channel *hot_channel; /* Channel was ever active */ + struct ncsi_request requests[256]; /* Request table */ +@@ -343,6 +344,7 @@ struct ncsi_dev_priv { + bool multi_package; /* Enable multiple packages */ + bool mlx_multi_host; /* Enable multi host Mellanox */ + u32 package_whitelist; /* Packages to configure */ ++ unsigned char channel_count; /* Num of channels to probe */ + }; + + struct ncsi_cmd_arg { +diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c +index f3d7fe86fea13..90c6cf676221a 100644 +--- a/net/ncsi/ncsi-manage.c ++++ b/net/ncsi/ncsi-manage.c +@@ -510,17 +510,19 @@ static void ncsi_suspend_channel(struct ncsi_dev_priv *ndp) + + break; + case ncsi_dev_state_suspend_gls: +- ndp->pending_req_num = np->channel_num; ++ ndp->pending_req_num = 1; + + nca.type = NCSI_PKT_CMD_GLS; + nca.package = np->id; ++ nca.channel = ndp->channel_probe_id; ++ ret = ncsi_xmit_cmd(&nca); ++ if (ret) ++ goto error; ++ ndp->channel_probe_id++; + +- nd->state = ncsi_dev_state_suspend_dcnt; +- NCSI_FOR_EACH_CHANNEL(np, nc) { +- nca.channel = nc->id; +- ret = ncsi_xmit_cmd(&nca); +- if (ret) +- goto error; ++ if (ndp->channel_probe_id == ndp->channel_count) { ++ ndp->channel_probe_id = 0; ++ nd->state = ncsi_dev_state_suspend_dcnt; + } + + break; +@@ -1340,7 +1342,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) + { + struct ncsi_dev *nd = &ndp->ndev; + struct ncsi_package *np; +- struct ncsi_channel *nc; + struct ncsi_cmd_arg nca; + unsigned char index; + int ret; +@@ -1418,23 +1419,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) + + nd->state = ncsi_dev_state_probe_cis; + break; +- case ncsi_dev_state_probe_cis: +- ndp->pending_req_num = NCSI_RESERVED_CHANNEL; +- +- /* Clear initial state */ +- nca.type = NCSI_PKT_CMD_CIS; +- nca.package = ndp->active_package->id; +- for (index = 0; index < NCSI_RESERVED_CHANNEL; index++) { +- nca.channel = index; +- ret = ncsi_xmit_cmd(&nca); +- if (ret) +- goto error; +- } +- +- nd->state = ncsi_dev_state_probe_gvi; +- if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY)) +- nd->state = ncsi_dev_state_probe_keep_phy; +- break; + case ncsi_dev_state_probe_keep_phy: + ndp->pending_req_num = 1; + +@@ -1447,14 +1431,17 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) + + nd->state = ncsi_dev_state_probe_gvi; + break; ++ case ncsi_dev_state_probe_cis: + case ncsi_dev_state_probe_gvi: + case ncsi_dev_state_probe_gc: + case ncsi_dev_state_probe_gls: + np = ndp->active_package; +- ndp->pending_req_num = np->channel_num; ++ ndp->pending_req_num = 1; + +- /* Retrieve version, capability or link status */ +- if (nd->state == ncsi_dev_state_probe_gvi) ++ /* Clear initial state Retrieve version, capability or link status */ ++ if (nd->state == ncsi_dev_state_probe_cis) ++ nca.type = NCSI_PKT_CMD_CIS; ++ else if (nd->state == ncsi_dev_state_probe_gvi) + nca.type = NCSI_PKT_CMD_GVI; + else if (nd->state == ncsi_dev_state_probe_gc) + nca.type = NCSI_PKT_CMD_GC; +@@ -1462,19 +1449,29 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) + nca.type = NCSI_PKT_CMD_GLS; + + nca.package = np->id; +- NCSI_FOR_EACH_CHANNEL(np, nc) { +- nca.channel = nc->id; +- ret = ncsi_xmit_cmd(&nca); +- if (ret) +- goto error; +- } ++ nca.channel = ndp->channel_probe_id; + +- if (nd->state == ncsi_dev_state_probe_gvi) ++ ret = ncsi_xmit_cmd(&nca); ++ if (ret) ++ goto error; ++ ++ if (nd->state == ncsi_dev_state_probe_cis) { ++ nd->state = ncsi_dev_state_probe_gvi; ++ if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY) && ndp->channel_probe_id == 0) ++ nd->state = ncsi_dev_state_probe_keep_phy; ++ } else if (nd->state == ncsi_dev_state_probe_gvi) { + nd->state = ncsi_dev_state_probe_gc; +- else if (nd->state == ncsi_dev_state_probe_gc) ++ } else if (nd->state == ncsi_dev_state_probe_gc) { + nd->state = ncsi_dev_state_probe_gls; +- else ++ } else { ++ nd->state = ncsi_dev_state_probe_cis; ++ ndp->channel_probe_id++; ++ } ++ ++ if (ndp->channel_probe_id == ndp->channel_count) { ++ ndp->channel_probe_id = 0; + nd->state = ncsi_dev_state_probe_dp; ++ } + break; + case ncsi_dev_state_probe_dp: + ndp->pending_req_num = 1; +@@ -1775,6 +1772,7 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev, + ndp->requests[i].ndp = ndp; + timer_setup(&ndp->requests[i].timer, ncsi_request_timeout, 0); + } ++ ndp->channel_count = NCSI_RESERVED_CHANNEL; + + spin_lock_irqsave(&ncsi_dev_lock, flags); + list_add_tail_rcu(&ndp->node, &ncsi_dev_list); +@@ -1808,6 +1806,7 @@ int ncsi_start_dev(struct ncsi_dev *nd) + + if (!(ndp->flags & NCSI_DEV_PROBED)) { + ndp->package_probe_id = 0; ++ ndp->channel_probe_id = 0; + nd->state = ncsi_dev_state_probe; + schedule_work(&ndp->work); + return 0; +diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c +index 480e80e3c2836..f22d67cb04d37 100644 +--- a/net/ncsi/ncsi-rsp.c ++++ b/net/ncsi/ncsi-rsp.c +@@ -795,12 +795,13 @@ static int ncsi_rsp_handler_gc(struct ncsi_request *nr) + struct ncsi_rsp_gc_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; ++ struct ncsi_package *np; + size_t size; + + /* Find the channel */ + rsp = (struct ncsi_rsp_gc_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, +- NULL, &nc); ++ &np, &nc); + if (!nc) + return -ENODEV; + +@@ -835,6 +836,7 @@ static int ncsi_rsp_handler_gc(struct ncsi_request *nr) + */ + nc->vlan_filter.bitmap = U64_MAX; + nc->vlan_filter.n_vids = rsp->vlan_cnt; ++ np->ndp->channel_count = rsp->channel_cnt; + + return 0; + } +-- +2.43.0 + diff --git a/queue-6.6/net-ncsi-simplify-kconfig-dts-control-flow.patch b/queue-6.6/net-ncsi-simplify-kconfig-dts-control-flow.patch new file mode 100644 index 00000000000..7f7ea277315 --- /dev/null +++ b/queue-6.6/net-ncsi-simplify-kconfig-dts-control-flow.patch @@ -0,0 +1,152 @@ +From 9b5a2e9563620e69eb8d011babb5a8afc944bd12 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 14 Nov 2023 10:07:33 -0600 +Subject: net/ncsi: Simplify Kconfig/dts control flow + +From: Peter Delevoryas + +[ Upstream commit c797ce168930ce3d62a9b7fc4d7040963ee6a01e ] + +Background: + +1. CONFIG_NCSI_OEM_CMD_KEEP_PHY + +If this is enabled, we send an extra OEM Intel command in the probe +sequence immediately after discovering a channel (e.g. after "Clear +Initial State"). + +2. CONFIG_NCSI_OEM_CMD_GET_MAC + +If this is enabled, we send one of 3 OEM "Get MAC Address" commands from +Broadcom, Mellanox (Nvidida), and Intel in the *configuration* sequence +for a channel. + +3. mellanox,multi-host (or mlx,multi-host) + +Introduced by this patch: + +https://lore.kernel.org/all/20200108234341.2590674-1-vijaykhemka@fb.com/ + +Which was actually originally from cosmo.chou@quantatw.com: + +https://github.com/facebook/openbmc-linux/commit/9f132a10ec48db84613519258cd8a317fb9c8f1b + +Cosmo claimed that the Nvidia ConnectX-4 and ConnectX-6 NIC's don't +respond to Get Version ID, et. al in the probe sequence unless you send +the Set MC Affinity command first. + +Problem Statement: + +We've been using a combination of #ifdef code blocks and IS_ENABLED() +conditions to conditionally send these OEM commands. + +It makes adding any new code around these commands hard to understand. + +Solution: + +In this patch, I just want to remove the conditionally compiled blocks +of code, and always use IS_ENABLED(...) to do dynamic control flow. + +I don't think the small amount of code this adds to non-users of the OEM +Kconfigs is a big deal. + +Signed-off-by: Peter Delevoryas +Signed-off-by: David S. Miller +Stable-dep-of: e85e271dec02 ("net/ncsi: Fix the multi thread manner of NCSI driver") +Signed-off-by: Sasha Levin +--- + net/ncsi/ncsi-manage.c | 20 +++----------------- + 1 file changed, 3 insertions(+), 17 deletions(-) + +diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c +index d9da942ad53dd..f3d7fe86fea13 100644 +--- a/net/ncsi/ncsi-manage.c ++++ b/net/ncsi/ncsi-manage.c +@@ -689,8 +689,6 @@ static int set_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, + return 0; + } + +-#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY) +- + static int ncsi_oem_keep_phy_intel(struct ncsi_cmd_arg *nca) + { + unsigned char data[NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN]; +@@ -716,10 +714,6 @@ static int ncsi_oem_keep_phy_intel(struct ncsi_cmd_arg *nca) + return ret; + } + +-#endif +- +-#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC) +- + /* NCSI OEM Command APIs */ + static int ncsi_oem_gma_handler_bcm(struct ncsi_cmd_arg *nca) + { +@@ -856,8 +850,6 @@ static int ncsi_gma_handler(struct ncsi_cmd_arg *nca, unsigned int mf_id) + return nch->handler(nca); + } + +-#endif /* CONFIG_NCSI_OEM_CMD_GET_MAC */ +- + /* Determine if a given channel from the channel_queue should be used for Tx */ + static bool ncsi_channel_is_tx(struct ncsi_dev_priv *ndp, + struct ncsi_channel *nc) +@@ -1039,20 +1031,18 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) + goto error; + } + +- nd->state = ncsi_dev_state_config_oem_gma; ++ nd->state = IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC) ++ ? ncsi_dev_state_config_oem_gma ++ : ncsi_dev_state_config_clear_vids; + break; + case ncsi_dev_state_config_oem_gma: + nd->state = ncsi_dev_state_config_clear_vids; +- ret = -1; + +-#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC) + nca.type = NCSI_PKT_CMD_OEM; + nca.package = np->id; + nca.channel = nc->id; + ndp->pending_req_num = 1; + ret = ncsi_gma_handler(&nca, nc->version.mf_id); +-#endif /* CONFIG_NCSI_OEM_CMD_GET_MAC */ +- + if (ret < 0) + schedule_work(&ndp->work); + +@@ -1404,7 +1394,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) + + schedule_work(&ndp->work); + break; +-#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC) + case ncsi_dev_state_probe_mlx_gma: + ndp->pending_req_num = 1; + +@@ -1429,7 +1418,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) + + nd->state = ncsi_dev_state_probe_cis; + break; +-#endif /* CONFIG_NCSI_OEM_CMD_GET_MAC */ + case ncsi_dev_state_probe_cis: + ndp->pending_req_num = NCSI_RESERVED_CHANNEL; + +@@ -1447,7 +1435,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) + if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY)) + nd->state = ncsi_dev_state_probe_keep_phy; + break; +-#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY) + case ncsi_dev_state_probe_keep_phy: + ndp->pending_req_num = 1; + +@@ -1460,7 +1447,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) + + nd->state = ncsi_dev_state_probe_gvi; + break; +-#endif /* CONFIG_NCSI_OEM_CMD_KEEP_PHY */ + case ncsi_dev_state_probe_gvi: + case ncsi_dev_state_probe_gc: + case ncsi_dev_state_probe_gls: +-- +2.43.0 + diff --git a/queue-6.6/net-phy-micrel-fix-ksz9477-phy-issues-after-suspend-.patch b/queue-6.6/net-phy-micrel-fix-ksz9477-phy-issues-after-suspend-.patch new file mode 100644 index 00000000000..ad2c131ddb5 --- /dev/null +++ b/queue-6.6/net-phy-micrel-fix-ksz9477-phy-issues-after-suspend-.patch @@ -0,0 +1,125 @@ +From 8ce307f811a481f5666f6d71770b6f2fde167bd0 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 28 May 2024 19:20:23 -0700 +Subject: net: phy: micrel: fix KSZ9477 PHY issues after suspend/resume + +From: Tristram Ha + +[ Upstream commit 6149db4997f582e958da675092f21c666e3b67b7 ] + +When the PHY is powered up after powered down most of the registers are +reset, so the PHY setup code needs to be done again. In addition the +interrupt register will need to be setup again so that link status +indication works again. + +Fixes: 26dd2974c5b5 ("net: phy: micrel: Move KSZ9477 errata fixes to PHY driver") +Signed-off-by: Tristram Ha +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/phy/micrel.c | 62 ++++++++++++++++++++++++++++++++++++---- + 1 file changed, 56 insertions(+), 6 deletions(-) + +diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c +index fc31fcfb0cdb4..048704758b150 100644 +--- a/drivers/net/phy/micrel.c ++++ b/drivers/net/phy/micrel.c +@@ -1821,7 +1821,7 @@ static const struct ksz9477_errata_write ksz9477_errata_writes[] = { + {0x1c, 0x20, 0xeeee}, + }; + +-static int ksz9477_config_init(struct phy_device *phydev) ++static int ksz9477_phy_errata(struct phy_device *phydev) + { + int err; + int i; +@@ -1849,16 +1849,30 @@ static int ksz9477_config_init(struct phy_device *phydev) + return err; + } + ++ err = genphy_restart_aneg(phydev); ++ if (err) ++ return err; ++ ++ return err; ++} ++ ++static int ksz9477_config_init(struct phy_device *phydev) ++{ ++ int err; ++ ++ /* Only KSZ9897 family of switches needs this fix. */ ++ if ((phydev->phy_id & 0xf) == 1) { ++ err = ksz9477_phy_errata(phydev); ++ if (err) ++ return err; ++ } ++ + /* According to KSZ9477 Errata DS80000754C (Module 4) all EEE modes + * in this switch shall be regarded as broken. + */ + if (phydev->dev_flags & MICREL_NO_EEE) + phydev->eee_broken_modes = -1; + +- err = genphy_restart_aneg(phydev); +- if (err) +- return err; +- + return kszphy_config_init(phydev); + } + +@@ -1967,6 +1981,42 @@ static int kszphy_resume(struct phy_device *phydev) + return 0; + } + ++static int ksz9477_resume(struct phy_device *phydev) ++{ ++ int ret; ++ ++ /* No need to initialize registers if not powered down. */ ++ ret = phy_read(phydev, MII_BMCR); ++ if (ret < 0) ++ return ret; ++ if (!(ret & BMCR_PDOWN)) ++ return 0; ++ ++ genphy_resume(phydev); ++ ++ /* After switching from power-down to normal mode, an internal global ++ * reset is automatically generated. Wait a minimum of 1 ms before ++ * read/write access to the PHY registers. ++ */ ++ usleep_range(1000, 2000); ++ ++ /* Only KSZ9897 family of switches needs this fix. */ ++ if ((phydev->phy_id & 0xf) == 1) { ++ ret = ksz9477_phy_errata(phydev); ++ if (ret) ++ return ret; ++ } ++ ++ /* Enable PHY Interrupts */ ++ if (phy_interrupt_is_valid(phydev)) { ++ phydev->interrupts = PHY_INTERRUPT_ENABLED; ++ if (phydev->drv->config_intr) ++ phydev->drv->config_intr(phydev); ++ } ++ ++ return 0; ++} ++ + static int kszphy_probe(struct phy_device *phydev) + { + const struct kszphy_type *type = phydev->drv->driver_data; +@@ -4916,7 +4966,7 @@ static struct phy_driver ksphy_driver[] = { + .config_intr = kszphy_config_intr, + .handle_interrupt = kszphy_handle_interrupt, + .suspend = genphy_suspend, +- .resume = genphy_resume, ++ .resume = ksz9477_resume, + .get_features = ksz9477_get_features, + } }; + +-- +2.43.0 + diff --git a/queue-6.6/net-phy-micrel-ksz8061-fix-errata-solution-not-takin.patch b/queue-6.6/net-phy-micrel-ksz8061-fix-errata-solution-not-takin.patch new file mode 100644 index 00000000000..44050c65124 --- /dev/null +++ b/queue-6.6/net-phy-micrel-ksz8061-fix-errata-solution-not-takin.patch @@ -0,0 +1,96 @@ +From cf3cc2c40c65e6e4ad3d3c74f3ed03125d227166 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 30 May 2024 18:38:01 -0700 +Subject: net: phy: Micrel KSZ8061: fix errata solution not taking effect + problem + +From: Tristram Ha + +[ Upstream commit 0a8d3f2e3e8d8aea8af017e14227b91d5989b696 ] + +KSZ8061 needs to write to a MMD register at driver initialization to fix +an errata. This worked in 5.0 kernel but not in newer kernels. The +issue is the main phylib code no longer resets PHY at the very beginning. +Calling phy resuming code later will reset the chip if it is already +powered down at the beginning. This wipes out the MMD register write. +Solution is to implement a phy resume function for KSZ8061 to take care +of this problem. + +Fixes: 232ba3a51cc2 ("net: phy: Micrel KSZ8061: link failure after cable connect") +Signed-off-by: Tristram Ha +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/phy/micrel.c | 42 +++++++++++++++++++++++++++++++++++++++- + 1 file changed, 41 insertions(+), 1 deletion(-) + +diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c +index 048704758b150..366ae22534373 100644 +--- a/drivers/net/phy/micrel.c ++++ b/drivers/net/phy/micrel.c +@@ -770,6 +770,17 @@ static int ksz8061_config_init(struct phy_device *phydev) + { + int ret; + ++ /* Chip can be powered down by the bootstrap code. */ ++ ret = phy_read(phydev, MII_BMCR); ++ if (ret < 0) ++ return ret; ++ if (ret & BMCR_PDOWN) { ++ ret = phy_write(phydev, MII_BMCR, ret & ~BMCR_PDOWN); ++ if (ret < 0) ++ return ret; ++ usleep_range(1000, 2000); ++ } ++ + ret = phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_DEVID1, 0xB61A); + if (ret) + return ret; +@@ -2017,6 +2028,35 @@ static int ksz9477_resume(struct phy_device *phydev) + return 0; + } + ++static int ksz8061_resume(struct phy_device *phydev) ++{ ++ int ret; ++ ++ /* This function can be called twice when the Ethernet device is on. */ ++ ret = phy_read(phydev, MII_BMCR); ++ if (ret < 0) ++ return ret; ++ if (!(ret & BMCR_PDOWN)) ++ return 0; ++ ++ genphy_resume(phydev); ++ usleep_range(1000, 2000); ++ ++ /* Re-program the value after chip is reset. */ ++ ret = phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_DEVID1, 0xB61A); ++ if (ret) ++ return ret; ++ ++ /* Enable PHY Interrupts */ ++ if (phy_interrupt_is_valid(phydev)) { ++ phydev->interrupts = PHY_INTERRUPT_ENABLED; ++ if (phydev->drv->config_intr) ++ phydev->drv->config_intr(phydev); ++ } ++ ++ return 0; ++} ++ + static int kszphy_probe(struct phy_device *phydev) + { + const struct kszphy_type *type = phydev->drv->driver_data; +@@ -4812,7 +4852,7 @@ static struct phy_driver ksphy_driver[] = { + .config_intr = kszphy_config_intr, + .handle_interrupt = kszphy_handle_interrupt, + .suspend = kszphy_suspend, +- .resume = kszphy_resume, ++ .resume = ksz8061_resume, + }, { + .phy_id = PHY_ID_KSZ9021, + .phy_id_mask = 0x000ffffe, +-- +2.43.0 + diff --git a/queue-6.6/net-sched-sch_multiq-fix-possible-oob-write-in-multi.patch b/queue-6.6/net-sched-sch_multiq-fix-possible-oob-write-in-multi.patch new file mode 100644 index 00000000000..43f7de4af2a --- /dev/null +++ b/queue-6.6/net-sched-sch_multiq-fix-possible-oob-write-in-multi.patch @@ -0,0 +1,38 @@ +From 857559f24ab8ddbbc256c4a6945cbf4ca8ad379f Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 3 Jun 2024 15:13:03 +0800 +Subject: net: sched: sch_multiq: fix possible OOB write in multiq_tune() + +From: Hangyu Hua + +[ Upstream commit affc18fdc694190ca7575b9a86632a73b9fe043d ] + +q->bands will be assigned to qopt->bands to execute subsequent code logic +after kmalloc. So the old q->bands should not be used in kmalloc. +Otherwise, an out-of-bounds write will occur. + +Fixes: c2999f7fb05b ("net: sched: multiq: don't call qdisc_put() while holding tree lock") +Signed-off-by: Hangyu Hua +Acked-by: Cong Wang +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/sched/sch_multiq.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c +index 75c9c860182b4..0d6649d937c9f 100644 +--- a/net/sched/sch_multiq.c ++++ b/net/sched/sch_multiq.c +@@ -185,7 +185,7 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, + + qopt->bands = qdisc_dev(sch)->real_num_tx_queues; + +- removed = kmalloc(sizeof(*removed) * (q->max_bands - q->bands), ++ removed = kmalloc(sizeof(*removed) * (q->max_bands - qopt->bands), + GFP_KERNEL); + if (!removed) + return -ENOMEM; +-- +2.43.0 + diff --git a/queue-6.6/net-sched-taprio-always-validate-tca_taprio_attr_pri.patch b/queue-6.6/net-sched-taprio-always-validate-tca_taprio_attr_pri.patch new file mode 100644 index 00000000000..abd91bb6b21 --- /dev/null +++ b/queue-6.6/net-sched-taprio-always-validate-tca_taprio_attr_pri.patch @@ -0,0 +1,63 @@ +From 09a751f74b6baf7df1493612b34f6cabf7870ee0 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 18:15:11 +0000 +Subject: net/sched: taprio: always validate TCA_TAPRIO_ATTR_PRIOMAP + +From: Eric Dumazet + +[ Upstream commit f921a58ae20852d188f70842431ce6519c4fdc36 ] + +If one TCA_TAPRIO_ATTR_PRIOMAP attribute has been provided, +taprio_parse_mqprio_opt() must validate it, or userspace +can inject arbitrary data to the kernel, the second time +taprio_change() is called. + +First call (with valid attributes) sets dev->num_tc +to a non zero value. + +Second call (with arbitrary mqprio attributes) +returns early from taprio_parse_mqprio_opt() +and bad things can happen. + +Fixes: a3d43c0d56f1 ("taprio: Add support adding an admin schedule") +Reported-by: Noam Rathaus +Signed-off-by: Eric Dumazet +Acked-by: Vinicius Costa Gomes +Reviewed-by: Vladimir Oltean +Link: https://lore.kernel.org/r/20240604181511.769870-1-edumazet@google.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/sched/sch_taprio.c | 15 ++++++--------- + 1 file changed, 6 insertions(+), 9 deletions(-) + +diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c +index a315748a5e531..418d4a846d04a 100644 +--- a/net/sched/sch_taprio.c ++++ b/net/sched/sch_taprio.c +@@ -1186,16 +1186,13 @@ static int taprio_parse_mqprio_opt(struct net_device *dev, + { + bool allow_overlapping_txqs = TXTIME_ASSIST_IS_ENABLED(taprio_flags); + +- if (!qopt && !dev->num_tc) { +- NL_SET_ERR_MSG(extack, "'mqprio' configuration is necessary"); +- return -EINVAL; +- } +- +- /* If num_tc is already set, it means that the user already +- * configured the mqprio part +- */ +- if (dev->num_tc) ++ if (!qopt) { ++ if (!dev->num_tc) { ++ NL_SET_ERR_MSG(extack, "'mqprio' configuration is necessary"); ++ return -EINVAL; ++ } + return 0; ++ } + + /* taprio imposes that traffic classes map 1:n to tx queues */ + if (qopt->num_tc > dev->num_tx_queues) { +-- +2.43.0 + diff --git a/queue-6.6/net-smc-avoid-overwriting-when-adjusting-sock-bufsiz.patch b/queue-6.6/net-smc-avoid-overwriting-when-adjusting-sock-bufsiz.patch new file mode 100644 index 00000000000..2109eaf93c2 --- /dev/null +++ b/queue-6.6/net-smc-avoid-overwriting-when-adjusting-sock-bufsiz.patch @@ -0,0 +1,68 @@ +From 0f974c14b66ae11bfb9233c96d99c2d3d455c37a Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 31 May 2024 16:54:17 +0800 +Subject: net/smc: avoid overwriting when adjusting sock bufsizes + +From: Wen Gu + +[ Upstream commit fb0aa0781a5f457e3864da68af52c3b1f4f7fd8f ] + +When copying smc settings to clcsock, avoid setting clcsock's sk_sndbuf +to sysctl_tcp_wmem[1], since this may overwrite the value set by +tcp_sndbuf_expand() in TCP connection establishment. + +And the other setting sk_{snd|rcv}buf to sysctl value in +smc_adjust_sock_bufsizes() can also be omitted since the initialization +of smc sock and clcsock has set sk_{snd|rcv}buf to smc.sysctl_{w|r}mem +or ipv4_sysctl_tcp_{w|r}mem[1]. + +Fixes: 30c3c4a4497c ("net/smc: Use correct buffer sizes when switching between TCP and SMC") +Link: https://lore.kernel.org/r/5eaf3858-e7fd-4db8-83e8-3d7a3e0e9ae2@linux.alibaba.com +Signed-off-by: Wen Gu +Reviewed-by: Wenjia Zhang +Reviewed-by: Gerd Bayer , too. +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/smc/af_smc.c | 22 ++-------------------- + 1 file changed, 2 insertions(+), 20 deletions(-) + +diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c +index ef5b5d498ef3e..3158b94fd347a 100644 +--- a/net/smc/af_smc.c ++++ b/net/smc/af_smc.c +@@ -460,29 +460,11 @@ static int smc_bind(struct socket *sock, struct sockaddr *uaddr, + static void smc_adjust_sock_bufsizes(struct sock *nsk, struct sock *osk, + unsigned long mask) + { +- struct net *nnet = sock_net(nsk); +- + nsk->sk_userlocks = osk->sk_userlocks; +- if (osk->sk_userlocks & SOCK_SNDBUF_LOCK) { ++ if (osk->sk_userlocks & SOCK_SNDBUF_LOCK) + nsk->sk_sndbuf = osk->sk_sndbuf; +- } else { +- if (mask == SK_FLAGS_SMC_TO_CLC) +- WRITE_ONCE(nsk->sk_sndbuf, +- READ_ONCE(nnet->ipv4.sysctl_tcp_wmem[1])); +- else +- WRITE_ONCE(nsk->sk_sndbuf, +- 2 * READ_ONCE(nnet->smc.sysctl_wmem)); +- } +- if (osk->sk_userlocks & SOCK_RCVBUF_LOCK) { ++ if (osk->sk_userlocks & SOCK_RCVBUF_LOCK) + nsk->sk_rcvbuf = osk->sk_rcvbuf; +- } else { +- if (mask == SK_FLAGS_SMC_TO_CLC) +- WRITE_ONCE(nsk->sk_rcvbuf, +- READ_ONCE(nnet->ipv4.sysctl_tcp_rmem[1])); +- else +- WRITE_ONCE(nsk->sk_rcvbuf, +- 2 * READ_ONCE(nnet->smc.sysctl_rmem)); +- } + } + + static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, +-- +2.43.0 + diff --git a/queue-6.6/net-tls-fix-marking-packets-as-decrypted.patch b/queue-6.6/net-tls-fix-marking-packets-as-decrypted.patch new file mode 100644 index 00000000000..b4724a7bf14 --- /dev/null +++ b/queue-6.6/net-tls-fix-marking-packets-as-decrypted.patch @@ -0,0 +1,46 @@ +From f8966de14c774dfea90e71e43c9e747256197ea1 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 30 May 2024 16:26:07 -0700 +Subject: net: tls: fix marking packets as decrypted + +From: Jakub Kicinski + +[ Upstream commit a535d59432370343058755100ee75ab03c0e3f91 ] + +For TLS offload we mark packets with skb->decrypted to make sure +they don't escape the host without getting encrypted first. +The crypto state lives in the socket, so it may get detached +by a call to skb_orphan(). As a safety check - the egress path +drops all packets with skb->decrypted and no "crypto-safe" socket. + +The skb marking was added to sendpage only (and not sendmsg), +because tls_device injected data into the TCP stack using sendpage. +This special case was missed when sendpage got folded into sendmsg. + +Fixes: c5c37af6ecad ("tcp: Convert do_tcp_sendpages() to use MSG_SPLICE_PAGES") +Signed-off-by: Jakub Kicinski +Reviewed-by: Eric Dumazet +Link: https://lore.kernel.org/r/20240530232607.82686-1-kuba@kernel.org +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/ipv4/tcp.c | 3 +++ + 1 file changed, 3 insertions(+) + +diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c +index 7bf774bdb9386..a9b33135513d8 100644 +--- a/net/ipv4/tcp.c ++++ b/net/ipv4/tcp.c +@@ -1158,6 +1158,9 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) + + process_backlog++; + ++#ifdef CONFIG_SKB_DECRYPTED ++ skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED); ++#endif + tcp_skb_entail(sk, skb); + copy = size_goal; + +-- +2.43.0 + diff --git a/queue-6.6/net-wwan-iosm-fix-tainted-pointer-delete-is-case-of-.patch b/queue-6.6/net-wwan-iosm-fix-tainted-pointer-delete-is-case-of-.patch new file mode 100644 index 00000000000..ac07e5cec34 --- /dev/null +++ b/queue-6.6/net-wwan-iosm-fix-tainted-pointer-delete-is-case-of-.patch @@ -0,0 +1,44 @@ +From a39d7419af3dff19bcdb42ccff2241ac593023eb Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 11:25:00 +0300 +Subject: net: wwan: iosm: Fix tainted pointer delete is case of region + creation fail + +From: Aleksandr Mishin + +[ Upstream commit b0c9a26435413b81799047a7be53255640432547 ] + +In case of region creation fail in ipc_devlink_create_region(), previously +created regions delete process starts from tainted pointer which actually +holds error code value. +Fix this bug by decreasing region index before delete. + +Found by Linux Verification Center (linuxtesting.org) with SVACE. + +Fixes: 4dcd183fbd67 ("net: wwan: iosm: devlink registration") +Signed-off-by: Aleksandr Mishin +Acked-by: Sergey Ryazanov +Reviewed-by: Simon Horman +Link: https://lore.kernel.org/r/20240604082500.20769-1-amishin@t-argos.ru +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + drivers/net/wwan/iosm/iosm_ipc_devlink.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/net/wwan/iosm/iosm_ipc_devlink.c b/drivers/net/wwan/iosm/iosm_ipc_devlink.c +index 2fe724d623c06..33c5a46f1b922 100644 +--- a/drivers/net/wwan/iosm/iosm_ipc_devlink.c ++++ b/drivers/net/wwan/iosm/iosm_ipc_devlink.c +@@ -210,7 +210,7 @@ static int ipc_devlink_create_region(struct iosm_devlink *devlink) + rc = PTR_ERR(devlink->cd_regions[i]); + dev_err(devlink->dev, "Devlink region fail,err %d", rc); + /* Delete previously created regions */ +- for ( ; i >= 0; i--) ++ for (i--; i >= 0; i--) + devlink_region_destroy(devlink->cd_regions[i]); + goto region_create_fail; + } +-- +2.43.0 + diff --git a/queue-6.6/nilfs2-fix-nilfs_empty_dir-misjudgment-and-long-loop.patch b/queue-6.6/nilfs2-fix-nilfs_empty_dir-misjudgment-and-long-loop.patch new file mode 100644 index 00000000000..279bc102236 --- /dev/null +++ b/queue-6.6/nilfs2-fix-nilfs_empty_dir-misjudgment-and-long-loop.patch @@ -0,0 +1,51 @@ +From ee51c6a7d475f7b66f41988c7f6915352a03a264 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 22:42:55 +0900 +Subject: nilfs2: fix nilfs_empty_dir() misjudgment and long loop on I/O errors + +From: Ryusuke Konishi + +[ Upstream commit 7373a51e7998b508af7136530f3a997b286ce81c ] + +The error handling in nilfs_empty_dir() when a directory folio/page read +fails is incorrect, as in the old ext2 implementation, and if the +folio/page cannot be read or nilfs_check_folio() fails, it will falsely +determine the directory as empty and corrupt the file system. + +In addition, since nilfs_empty_dir() does not immediately return on a +failed folio/page read, but continues to loop, this can cause a long loop +with I/O if i_size of the directory's inode is also corrupted, causing the +log writer thread to wait and hang, as reported by syzbot. + +Fix these issues by making nilfs_empty_dir() immediately return a false +value (0) if it fails to get a directory folio/page. + +Link: https://lkml.kernel.org/r/20240604134255.7165-1-konishi.ryusuke@gmail.com +Signed-off-by: Ryusuke Konishi +Reported-by: syzbot+c8166c541d3971bf6c87@syzkaller.appspotmail.com +Closes: https://syzkaller.appspot.com/bug?extid=c8166c541d3971bf6c87 +Fixes: 2ba466d74ed7 ("nilfs2: directory entry operations") +Tested-by: Ryusuke Konishi +Cc: +Signed-off-by: Andrew Morton +Signed-off-by: Sasha Levin +--- + fs/nilfs2/dir.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c +index c6b88be8a9d73..23a8357f127bc 100644 +--- a/fs/nilfs2/dir.c ++++ b/fs/nilfs2/dir.c +@@ -627,7 +627,7 @@ int nilfs_empty_dir(struct inode *inode) + + kaddr = nilfs_get_page(inode, i, &page); + if (IS_ERR(kaddr)) +- continue; ++ return 0; + + de = (struct nilfs_dir_entry *)kaddr; + kaddr += nilfs_last_byte(inode, i) - NILFS_DIR_REC_LEN(1); +-- +2.43.0 + diff --git a/queue-6.6/nilfs2-return-the-mapped-address-from-nilfs_get_page.patch b/queue-6.6/nilfs2-return-the-mapped-address-from-nilfs_get_page.patch new file mode 100644 index 00000000000..6cf483c9fcd --- /dev/null +++ b/queue-6.6/nilfs2-return-the-mapped-address-from-nilfs_get_page.patch @@ -0,0 +1,146 @@ +From 3f1b1789ee70ff1a5669ae71b69cd4a4509467a9 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 27 Nov 2023 23:30:25 +0900 +Subject: nilfs2: return the mapped address from nilfs_get_page() + +From: Matthew Wilcox (Oracle) + +[ Upstream commit 09a46acb3697e50548bb265afa1d79163659dd85 ] + +In prepartion for switching from kmap() to kmap_local(), return the kmap +address from nilfs_get_page() instead of having the caller look up +page_address(). + +[konishi.ryusuke: fixed a missing blank line after declaration] +Link: https://lkml.kernel.org/r/20231127143036.2425-7-konishi.ryusuke@gmail.com +Signed-off-by: Matthew Wilcox (Oracle) +Signed-off-by: Ryusuke Konishi +Signed-off-by: Andrew Morton +Stable-dep-of: 7373a51e7998 ("nilfs2: fix nilfs_empty_dir() misjudgment and long loop on I/O errors") +Signed-off-by: Sasha Levin +--- + fs/nilfs2/dir.c | 57 +++++++++++++++++++++++-------------------------- + 1 file changed, 27 insertions(+), 30 deletions(-) + +diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c +index 929edc0b101a0..c6b88be8a9d73 100644 +--- a/fs/nilfs2/dir.c ++++ b/fs/nilfs2/dir.c +@@ -186,19 +186,24 @@ static bool nilfs_check_page(struct page *page) + return false; + } + +-static struct page *nilfs_get_page(struct inode *dir, unsigned long n) ++static void *nilfs_get_page(struct inode *dir, unsigned long n, ++ struct page **pagep) + { + struct address_space *mapping = dir->i_mapping; + struct page *page = read_mapping_page(mapping, n, NULL); ++ void *kaddr; + +- if (!IS_ERR(page)) { +- kmap(page); +- if (unlikely(!PageChecked(page))) { +- if (!nilfs_check_page(page)) +- goto fail; +- } ++ if (IS_ERR(page)) ++ return page; ++ ++ kaddr = kmap(page); ++ if (unlikely(!PageChecked(page))) { ++ if (!nilfs_check_page(page)) ++ goto fail; + } +- return page; ++ ++ *pagep = page; ++ return kaddr; + + fail: + nilfs_put_page(page); +@@ -275,14 +280,14 @@ static int nilfs_readdir(struct file *file, struct dir_context *ctx) + for ( ; n < npages; n++, offset = 0) { + char *kaddr, *limit; + struct nilfs_dir_entry *de; +- struct page *page = nilfs_get_page(inode, n); ++ struct page *page; + +- if (IS_ERR(page)) { ++ kaddr = nilfs_get_page(inode, n, &page); ++ if (IS_ERR(kaddr)) { + nilfs_error(sb, "bad page in #%lu", inode->i_ino); + ctx->pos += PAGE_SIZE - offset; + return -EIO; + } +- kaddr = page_address(page); + de = (struct nilfs_dir_entry *)(kaddr + offset); + limit = kaddr + nilfs_last_byte(inode, n) - + NILFS_DIR_REC_LEN(1); +@@ -345,11 +350,9 @@ nilfs_find_entry(struct inode *dir, const struct qstr *qstr, + start = 0; + n = start; + do { +- char *kaddr; ++ char *kaddr = nilfs_get_page(dir, n, &page); + +- page = nilfs_get_page(dir, n); +- if (!IS_ERR(page)) { +- kaddr = page_address(page); ++ if (!IS_ERR(kaddr)) { + de = (struct nilfs_dir_entry *)kaddr; + kaddr += nilfs_last_byte(dir, n) - reclen; + while ((char *) de <= kaddr) { +@@ -387,15 +390,11 @@ nilfs_find_entry(struct inode *dir, const struct qstr *qstr, + + struct nilfs_dir_entry *nilfs_dotdot(struct inode *dir, struct page **p) + { +- struct page *page = nilfs_get_page(dir, 0); +- struct nilfs_dir_entry *de = NULL; ++ struct nilfs_dir_entry *de = nilfs_get_page(dir, 0, p); + +- if (!IS_ERR(page)) { +- de = nilfs_next_entry( +- (struct nilfs_dir_entry *)page_address(page)); +- *p = page; +- } +- return de; ++ if (IS_ERR(de)) ++ return NULL; ++ return nilfs_next_entry(de); + } + + ino_t nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr) +@@ -459,12 +458,11 @@ int nilfs_add_link(struct dentry *dentry, struct inode *inode) + for (n = 0; n <= npages; n++) { + char *dir_end; + +- page = nilfs_get_page(dir, n); +- err = PTR_ERR(page); +- if (IS_ERR(page)) ++ kaddr = nilfs_get_page(dir, n, &page); ++ err = PTR_ERR(kaddr); ++ if (IS_ERR(kaddr)) + goto out; + lock_page(page); +- kaddr = page_address(page); + dir_end = kaddr + nilfs_last_byte(dir, n); + de = (struct nilfs_dir_entry *)kaddr; + kaddr += PAGE_SIZE - reclen; +@@ -627,11 +625,10 @@ int nilfs_empty_dir(struct inode *inode) + char *kaddr; + struct nilfs_dir_entry *de; + +- page = nilfs_get_page(inode, i); +- if (IS_ERR(page)) ++ kaddr = nilfs_get_page(inode, i, &page); ++ if (IS_ERR(kaddr)) + continue; + +- kaddr = page_address(page); + de = (struct nilfs_dir_entry *)kaddr; + kaddr += nilfs_last_byte(inode, i) - NILFS_DIR_REC_LEN(1); + +-- +2.43.0 + diff --git a/queue-6.6/octeontx2-af-always-allocate-pf-entries-from-low-pri.patch b/queue-6.6/octeontx2-af-always-allocate-pf-entries-from-low-pri.patch new file mode 100644 index 00000000000..ee132e5dccf --- /dev/null +++ b/queue-6.6/octeontx2-af-always-allocate-pf-entries-from-low-pri.patch @@ -0,0 +1,87 @@ +From 9b45cd4ceb9e6be0fa8640dd6920ff62e4a8076c Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 29 May 2024 20:59:44 +0530 +Subject: octeontx2-af: Always allocate PF entries from low prioriy zone + +From: Subbaraya Sundeep + +[ Upstream commit 8b0f7410942cdc420c4557eda02bfcdf60ccec17 ] + +PF mcam entries has to be at low priority always so that VF +can install longest prefix match rules at higher priority. +This was taken care currently but when priority allocation +wrt reference entry is requested then entries are allocated +from mid-zone instead of low priority zone. Fix this and +always allocate entries from low priority zone for PFs. + +Fixes: 7df5b4b260dd ("octeontx2-af: Allocate low priority entries for PF") +Signed-off-by: Subbaraya Sundeep +Reviewed-by: Jacob Keller +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + .../ethernet/marvell/octeontx2/af/rvu_npc.c | 33 ++++++++++++------- + 1 file changed, 22 insertions(+), 11 deletions(-) + +diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +index 91a4ea529d077..00ef6d201b973 100644 +--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c ++++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +@@ -2506,7 +2506,17 @@ static int npc_mcam_alloc_entries(struct npc_mcam *mcam, u16 pcifunc, + * - when available free entries are less. + * Lower priority ones out of avaialble free entries are always + * chosen when 'high vs low' question arises. ++ * ++ * For a VF base MCAM match rule is set by its PF. And all the ++ * further MCAM rules installed by VF on its own are ++ * concatenated with the base rule set by its PF. Hence PF entries ++ * should be at lower priority compared to VF entries. Otherwise ++ * base rule is hit always and rules installed by VF will be of ++ * no use. Hence if the request is from PF then allocate low ++ * priority entries. + */ ++ if (!(pcifunc & RVU_PFVF_FUNC_MASK)) ++ goto lprio_alloc; + + /* Get the search range for priority allocation request */ + if (req->priority) { +@@ -2515,17 +2525,6 @@ static int npc_mcam_alloc_entries(struct npc_mcam *mcam, u16 pcifunc, + goto alloc; + } + +- /* For a VF base MCAM match rule is set by its PF. And all the +- * further MCAM rules installed by VF on its own are +- * concatenated with the base rule set by its PF. Hence PF entries +- * should be at lower priority compared to VF entries. Otherwise +- * base rule is hit always and rules installed by VF will be of +- * no use. Hence if the request is from PF and NOT a priority +- * allocation request then allocate low priority entries. +- */ +- if (!(pcifunc & RVU_PFVF_FUNC_MASK)) +- goto lprio_alloc; +- + /* Find out the search range for non-priority allocation request + * + * Get MCAM free entry count in middle zone. +@@ -2555,6 +2554,18 @@ static int npc_mcam_alloc_entries(struct npc_mcam *mcam, u16 pcifunc, + reverse = true; + start = 0; + end = mcam->bmap_entries; ++ /* Ensure PF requests are always at bottom and if PF requests ++ * for higher/lower priority entry wrt reference entry then ++ * honour that criteria and start search for entries from bottom ++ * and not in mid zone. ++ */ ++ if (!(pcifunc & RVU_PFVF_FUNC_MASK) && ++ req->priority == NPC_MCAM_HIGHER_PRIO) ++ end = req->ref_entry; ++ ++ if (!(pcifunc & RVU_PFVF_FUNC_MASK) && ++ req->priority == NPC_MCAM_LOWER_PRIO) ++ start = req->ref_entry; + } + + alloc: +-- +2.43.0 + diff --git a/queue-6.6/ptp-fix-error-message-on-failed-pin-verification.patch b/queue-6.6/ptp-fix-error-message-on-failed-pin-verification.patch new file mode 100644 index 00000000000..643ef1b569a --- /dev/null +++ b/queue-6.6/ptp-fix-error-message-on-failed-pin-verification.patch @@ -0,0 +1,42 @@ +From 096e6d27b84ca0bf3c15bb7df6965d5e9dd9db57 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 14:05:27 +0200 +Subject: ptp: Fix error message on failed pin verification + +From: Karol Kolacinski + +[ Upstream commit 323a359f9b077f382f4483023d096a4d316fd135 ] + +On failed verification of PTP clock pin, error message prints channel +number instead of pin index after "pin", which is incorrect. + +Fix error message by adding channel number to the message and printing +pin number instead of channel number. + +Fixes: 6092315dfdec ("ptp: introduce programmable pins.") +Signed-off-by: Karol Kolacinski +Acked-by: Richard Cochran +Link: https://lore.kernel.org/r/20240604120555.16643-1-karol.kolacinski@intel.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/ptp/ptp_chardev.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c +index 5a3a4cc0bec82..91cc6ffa0095e 100644 +--- a/drivers/ptp/ptp_chardev.c ++++ b/drivers/ptp/ptp_chardev.c +@@ -84,7 +84,8 @@ int ptp_set_pinfunc(struct ptp_clock *ptp, unsigned int pin, + } + + if (info->verify(info, pin, func, chan)) { +- pr_err("driver cannot use function %u on pin %u\n", func, chan); ++ pr_err("driver cannot use function %u and channel %u on pin %u\n", ++ func, chan, pin); + return -EOPNOTSUPP; + } + +-- +2.43.0 + diff --git a/queue-6.6/risc-v-kvm-fix-incorrect-reg_subtype-labels-in-kvm_r.patch b/queue-6.6/risc-v-kvm-fix-incorrect-reg_subtype-labels-in-kvm_r.patch new file mode 100644 index 00000000000..d8169332277 --- /dev/null +++ b/queue-6.6/risc-v-kvm-fix-incorrect-reg_subtype-labels-in-kvm_r.patch @@ -0,0 +1,45 @@ +From c4e141d240577937df973647ba65469a5a13f73a Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 23 May 2024 10:13:34 +0800 +Subject: RISC-V: KVM: Fix incorrect reg_subtype labels in + kvm_riscv_vcpu_set_reg_isa_ext function + +From: Quan Zhou + +[ Upstream commit c66f3b40b17d3dfc4b6abb5efde8e71c46971821 ] + +In the function kvm_riscv_vcpu_set_reg_isa_ext, the original code +used incorrect reg_subtype labels KVM_REG_RISCV_SBI_MULTI_EN/DIS. +These have been corrected to KVM_REG_RISCV_ISA_MULTI_EN/DIS respectively. +Although they are numerically equivalent, the actual processing +will not result in errors, but it may lead to ambiguous code semantics. + +Fixes: 613029442a4b ("RISC-V: KVM: Extend ONE_REG to enable/disable multiple ISA extensions") +Signed-off-by: Quan Zhou +Reviewed-by: Andrew Jones +Link: https://lore.kernel.org/r/ff1c6771a67d660db94372ac9aaa40f51e5e0090.1716429371.git.zhouquan@iscas.ac.cn +Signed-off-by: Anup Patel +Signed-off-by: Sasha Levin +--- + arch/riscv/kvm/vcpu_onereg.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c +index b7e0e03c69b1e..d520b25d85616 100644 +--- a/arch/riscv/kvm/vcpu_onereg.c ++++ b/arch/riscv/kvm/vcpu_onereg.c +@@ -614,9 +614,9 @@ static int kvm_riscv_vcpu_set_reg_isa_ext(struct kvm_vcpu *vcpu, + switch (reg_subtype) { + case KVM_REG_RISCV_ISA_SINGLE: + return riscv_vcpu_set_isa_ext_single(vcpu, reg_num, reg_val); +- case KVM_REG_RISCV_SBI_MULTI_EN: ++ case KVM_REG_RISCV_ISA_MULTI_EN: + return riscv_vcpu_set_isa_ext_multi(vcpu, reg_num, reg_val, true); +- case KVM_REG_RISCV_SBI_MULTI_DIS: ++ case KVM_REG_RISCV_ISA_MULTI_DIS: + return riscv_vcpu_set_isa_ext_multi(vcpu, reg_num, reg_val, false); + default: + return -ENOENT; +-- +2.43.0 + diff --git a/queue-6.6/risc-v-kvm-no-need-to-use-mask-when-hart-index-bit-i.patch b/queue-6.6/risc-v-kvm-no-need-to-use-mask-when-hart-index-bit-i.patch new file mode 100644 index 00000000000..a268b2e3806 --- /dev/null +++ b/queue-6.6/risc-v-kvm-no-need-to-use-mask-when-hart-index-bit-i.patch @@ -0,0 +1,48 @@ +From 6f977ad4508099b59eb9bc41bc9cb56204ed6dad Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 15 Apr 2024 14:49:04 +0800 +Subject: RISC-V: KVM: No need to use mask when hart-index-bit is 0 + +From: Yong-Xuan Wang + +[ Upstream commit 2d707b4e37f9b0c37b8b2392f91b04c5b63ea538 ] + +When the maximum hart number within groups is 1, hart-index-bit is set to +0. Consequently, there is no need to restore the hart ID from IMSIC +addresses and hart-index-bit settings. Currently, QEMU and kvmtool do not +pass correct hart-index-bit values when the maximum hart number is a +power of 2, thereby avoiding this issue. Corresponding patches for QEMU +and kvmtool will also be dispatched. + +Fixes: 89d01306e34d ("RISC-V: KVM: Implement device interface for AIA irqchip") +Signed-off-by: Yong-Xuan Wang +Reviewed-by: Andrew Jones +Link: https://lore.kernel.org/r/20240415064905.25184-1-yongxuan.wang@sifive.com +Signed-off-by: Anup Patel +Signed-off-by: Sasha Levin +--- + arch/riscv/kvm/aia_device.c | 7 ++++--- + 1 file changed, 4 insertions(+), 3 deletions(-) + +diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c +index 0eb689351b7d0..5cd407c6a8e4f 100644 +--- a/arch/riscv/kvm/aia_device.c ++++ b/arch/riscv/kvm/aia_device.c +@@ -237,10 +237,11 @@ static gpa_t aia_imsic_ppn(struct kvm_aia *aia, gpa_t addr) + + static u32 aia_imsic_hart_index(struct kvm_aia *aia, gpa_t addr) + { +- u32 hart, group = 0; ++ u32 hart = 0, group = 0; + +- hart = (addr >> (aia->nr_guest_bits + IMSIC_MMIO_PAGE_SHIFT)) & +- GENMASK_ULL(aia->nr_hart_bits - 1, 0); ++ if (aia->nr_hart_bits) ++ hart = (addr >> (aia->nr_guest_bits + IMSIC_MMIO_PAGE_SHIFT)) & ++ GENMASK_ULL(aia->nr_hart_bits - 1, 0); + if (aia->nr_group_bits) + group = (addr >> aia->nr_group_shift) & + GENMASK_ULL(aia->nr_group_bits - 1, 0); +-- +2.43.0 + diff --git a/queue-6.6/scsi-ufs-mcq-fix-error-output-and-clean-up-ufshcd_mc.patch b/queue-6.6/scsi-ufs-mcq-fix-error-output-and-clean-up-ufshcd_mc.patch new file mode 100644 index 00000000000..da5e28e030e --- /dev/null +++ b/queue-6.6/scsi-ufs-mcq-fix-error-output-and-clean-up-ufshcd_mc.patch @@ -0,0 +1,86 @@ +From 91685991175328a16ee4371b9b914d89a65998fc Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 24 May 2024 10:59:04 +0900 +Subject: scsi: ufs: mcq: Fix error output and clean up ufshcd_mcq_abort() + +From: Chanwoo Lee + +[ Upstream commit d53b681ce9ca7db5ef4ecb8d2cf465ae4a031264 ] + +An error unrelated to ufshcd_try_to_abort_task is being logged and can +cause confusion. Modify ufshcd_mcq_abort() to print the result of the abort +failure. For readability, return immediately instead of 'goto'. + +Fixes: f1304d442077 ("scsi: ufs: mcq: Added ufshcd_mcq_abort()") +Signed-off-by: Chanwoo Lee +Link: https://lore.kernel.org/r/20240524015904.1116005-1-cw9316.lee@samsung.com +Reviewed-by: Bart Van Assche +Signed-off-by: Martin K. Petersen +Signed-off-by: Sasha Levin +--- + drivers/ufs/core/ufs-mcq.c | 17 ++++++++--------- + 1 file changed, 8 insertions(+), 9 deletions(-) + +diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c +index 7ae3096814282..4e84ee6564d4b 100644 +--- a/drivers/ufs/core/ufs-mcq.c ++++ b/drivers/ufs/core/ufs-mcq.c +@@ -630,20 +630,20 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd) + struct ufshcd_lrb *lrbp = &hba->lrb[tag]; + struct ufs_hw_queue *hwq; + unsigned long flags; +- int err = FAILED; ++ int err; + + if (!ufshcd_cmd_inflight(lrbp->cmd)) { + dev_err(hba->dev, + "%s: skip abort. cmd at tag %d already completed.\n", + __func__, tag); +- goto out; ++ return FAILED; + } + + /* Skip task abort in case previous aborts failed and report failure */ + if (lrbp->req_abort_skip) { + dev_err(hba->dev, "%s: skip abort. tag %d failed earlier\n", + __func__, tag); +- goto out; ++ return FAILED; + } + + hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd)); +@@ -655,7 +655,7 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd) + */ + dev_err(hba->dev, "%s: cmd found in sq. hwq=%d, tag=%d\n", + __func__, hwq->id, tag); +- goto out; ++ return FAILED; + } + + /* +@@ -663,18 +663,17 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd) + * in the completion queue either. Query the device to see if + * the command is being processed in the device. + */ +- if (ufshcd_try_to_abort_task(hba, tag)) { ++ err = ufshcd_try_to_abort_task(hba, tag); ++ if (err) { + dev_err(hba->dev, "%s: device abort failed %d\n", __func__, err); + lrbp->req_abort_skip = true; +- goto out; ++ return FAILED; + } + +- err = SUCCESS; + spin_lock_irqsave(&hwq->cq_lock, flags); + if (ufshcd_cmd_inflight(lrbp->cmd)) + ufshcd_release_scsi_cmd(hba, lrbp); + spin_unlock_irqrestore(&hwq->cq_lock, flags); + +-out: +- return err; ++ return SUCCESS; + } +-- +2.43.0 + diff --git a/queue-6.6/selftests-mm-compaction_test-fix-bogus-test-success-.patch b/queue-6.6/selftests-mm-compaction_test-fix-bogus-test-success-.patch new file mode 100644 index 00000000000..e484d8bb089 --- /dev/null +++ b/queue-6.6/selftests-mm-compaction_test-fix-bogus-test-success-.patch @@ -0,0 +1,109 @@ +From 278704bd01c53651dd762299d1ee11d376b15ad8 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 21 May 2024 13:13:56 +0530 +Subject: selftests/mm: compaction_test: fix bogus test success on Aarch64 + +From: Dev Jain + +[ Upstream commit d4202e66a4b1fe6968f17f9f09bbc30d08f028a1 ] + +Patch series "Fixes for compaction_test", v2. + +The compaction_test memory selftest introduces fragmentation in memory +and then tries to allocate as many hugepages as possible. This series +addresses some problems. + +On Aarch64, if nr_hugepages == 0, then the test trivially succeeds since +compaction_index becomes 0, which is less than 3, due to no division by +zero exception being raised. We fix that by checking for division by +zero. + +Secondly, correctly set the number of hugepages to zero before trying +to set a large number of them. + +Now, consider a situation in which, at the start of the test, a non-zero +number of hugepages have been already set (while running the entire +selftests/mm suite, or manually by the admin). The test operates on 80% +of memory to avoid OOM-killer invocation, and because some memory is +already blocked by hugepages, it would increase the chance of OOM-killing. +Also, since mem_free used in check_compaction() is the value before we +set nr_hugepages to zero, the chance that the compaction_index will +be small is very high if the preset nr_hugepages was high, leading to a +bogus test success. + +This patch (of 3): + +Currently, if at runtime we are not able to allocate a huge page, the test +will trivially pass on Aarch64 due to no exception being raised on +division by zero while computing compaction_index. Fix that by checking +for nr_hugepages == 0. Anyways, in general, avoid a division by zero by +exiting the program beforehand. While at it, fix a typo, and handle the +case where the number of hugepages may overflow an integer. + +Link: https://lkml.kernel.org/r/20240521074358.675031-1-dev.jain@arm.com +Link: https://lkml.kernel.org/r/20240521074358.675031-2-dev.jain@arm.com +Fixes: bd67d5c15cc1 ("Test compaction of mlocked memory") +Signed-off-by: Dev Jain +Cc: Anshuman Khandual +Cc: Shuah Khan +Cc: Sri Jayaramappa +Cc: +Signed-off-by: Andrew Morton +Signed-off-by: Sasha Levin +--- + tools/testing/selftests/mm/compaction_test.c | 20 +++++++++++++------- + 1 file changed, 13 insertions(+), 7 deletions(-) + +diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c +index 6aa6460b854ea..309b3750e57e1 100644 +--- a/tools/testing/selftests/mm/compaction_test.c ++++ b/tools/testing/selftests/mm/compaction_test.c +@@ -82,12 +82,13 @@ int prereq(void) + return -1; + } + +-int check_compaction(unsigned long mem_free, unsigned int hugepage_size) ++int check_compaction(unsigned long mem_free, unsigned long hugepage_size) + { ++ unsigned long nr_hugepages_ul; + int fd, ret = -1; + int compaction_index = 0; +- char initial_nr_hugepages[10] = {0}; +- char nr_hugepages[10] = {0}; ++ char initial_nr_hugepages[20] = {0}; ++ char nr_hugepages[20] = {0}; + + /* We want to test with 80% of available memory. Else, OOM killer comes + in to play */ +@@ -136,7 +137,12 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) + + /* We should have been able to request at least 1/3 rd of the memory in + huge pages */ +- compaction_index = mem_free/(atoi(nr_hugepages) * hugepage_size); ++ nr_hugepages_ul = strtoul(nr_hugepages, NULL, 10); ++ if (!nr_hugepages_ul) { ++ ksft_print_msg("ERROR: No memory is available as huge pages\n"); ++ goto close_fd; ++ } ++ compaction_index = mem_free/(nr_hugepages_ul * hugepage_size); + + lseek(fd, 0, SEEK_SET); + +@@ -147,11 +153,11 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) + goto close_fd; + } + +- ksft_print_msg("Number of huge pages allocated = %d\n", +- atoi(nr_hugepages)); ++ ksft_print_msg("Number of huge pages allocated = %lu\n", ++ nr_hugepages_ul); + + if (compaction_index > 3) { +- ksft_print_msg("ERROR: Less that 1/%d of memory is available\n" ++ ksft_print_msg("ERROR: Less than 1/%d of memory is available\n" + "as huge pages\n", compaction_index); + goto close_fd; + } +-- +2.43.0 + diff --git a/queue-6.6/selftests-mm-conform-test-to-tap-format-output.patch b/queue-6.6/selftests-mm-conform-test-to-tap-format-output.patch new file mode 100644 index 00000000000..dfcdf8154dc --- /dev/null +++ b/queue-6.6/selftests-mm-conform-test-to-tap-format-output.patch @@ -0,0 +1,229 @@ +From 42f14c56f2cd1ae93434e99c7a4dd97d83dd6adb Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 1 Jan 2024 13:36:12 +0500 +Subject: selftests/mm: conform test to TAP format output + +From: Muhammad Usama Anjum + +[ Upstream commit 9a21701edc41465de56f97914741bfb7bfc2517d ] + +Conform the layout, informational and status messages to TAP. No +functional change is intended other than the layout of output messages. + +Link: https://lkml.kernel.org/r/20240101083614.1076768-1-usama.anjum@collabora.com +Signed-off-by: Muhammad Usama Anjum +Cc: Shuah Khan +Signed-off-by: Andrew Morton +Stable-dep-of: d4202e66a4b1 ("selftests/mm: compaction_test: fix bogus test success on Aarch64") +Signed-off-by: Sasha Levin +--- + tools/testing/selftests/mm/compaction_test.c | 91 ++++++++++---------- + 1 file changed, 44 insertions(+), 47 deletions(-) + +diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c +index 55dec92e1e58c..f81931c1f8386 100644 +--- a/tools/testing/selftests/mm/compaction_test.c ++++ b/tools/testing/selftests/mm/compaction_test.c +@@ -33,7 +33,7 @@ int read_memory_info(unsigned long *memfree, unsigned long *hugepagesize) + FILE *cmdfile = popen(cmd, "r"); + + if (!(fgets(buffer, sizeof(buffer), cmdfile))) { +- perror("Failed to read meminfo\n"); ++ ksft_print_msg("Failed to read meminfo: %s\n", strerror(errno)); + return -1; + } + +@@ -44,7 +44,7 @@ int read_memory_info(unsigned long *memfree, unsigned long *hugepagesize) + cmdfile = popen(cmd, "r"); + + if (!(fgets(buffer, sizeof(buffer), cmdfile))) { +- perror("Failed to read meminfo\n"); ++ ksft_print_msg("Failed to read meminfo: %s\n", strerror(errno)); + return -1; + } + +@@ -62,14 +62,14 @@ int prereq(void) + fd = open("/proc/sys/vm/compact_unevictable_allowed", + O_RDONLY | O_NONBLOCK); + if (fd < 0) { +- perror("Failed to open\n" +- "/proc/sys/vm/compact_unevictable_allowed\n"); ++ ksft_print_msg("Failed to open /proc/sys/vm/compact_unevictable_allowed: %s\n", ++ strerror(errno)); + return -1; + } + + if (read(fd, &allowed, sizeof(char)) != sizeof(char)) { +- perror("Failed to read from\n" +- "/proc/sys/vm/compact_unevictable_allowed\n"); ++ ksft_print_msg("Failed to read from /proc/sys/vm/compact_unevictable_allowed: %s\n", ++ strerror(errno)); + close(fd); + return -1; + } +@@ -78,12 +78,13 @@ int prereq(void) + if (allowed == '1') + return 0; + ++ ksft_print_msg("Compaction isn't allowed\n"); + return -1; + } + + int check_compaction(unsigned long mem_free, unsigned int hugepage_size) + { +- int fd; ++ int fd, ret = -1; + int compaction_index = 0; + char initial_nr_hugepages[10] = {0}; + char nr_hugepages[10] = {0}; +@@ -94,12 +95,14 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) + + fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); + if (fd < 0) { +- perror("Failed to open /proc/sys/vm/nr_hugepages"); ++ ksft_test_result_fail("Failed to open /proc/sys/vm/nr_hugepages: %s\n", ++ strerror(errno)); + return -1; + } + + if (read(fd, initial_nr_hugepages, sizeof(initial_nr_hugepages)) <= 0) { +- perror("Failed to read from /proc/sys/vm/nr_hugepages"); ++ ksft_test_result_fail("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", ++ strerror(errno)); + goto close_fd; + } + +@@ -107,7 +110,8 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) + + /* Start with the initial condition of 0 huge pages*/ + if (write(fd, "0", sizeof(char)) != sizeof(char)) { +- perror("Failed to write 0 to /proc/sys/vm/nr_hugepages\n"); ++ ksft_test_result_fail("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", ++ strerror(errno)); + goto close_fd; + } + +@@ -116,14 +120,16 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) + /* Request a large number of huge pages. The Kernel will allocate + as much as it can */ + if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) { +- perror("Failed to write 100000 to /proc/sys/vm/nr_hugepages\n"); ++ ksft_test_result_fail("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n", ++ strerror(errno)); + goto close_fd; + } + + lseek(fd, 0, SEEK_SET); + + if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { +- perror("Failed to re-read from /proc/sys/vm/nr_hugepages\n"); ++ ksft_test_result_fail("Failed to re-read from /proc/sys/vm/nr_hugepages: %s\n", ++ strerror(errno)); + goto close_fd; + } + +@@ -131,67 +137,58 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) + huge pages */ + compaction_index = mem_free/(atoi(nr_hugepages) * hugepage_size); + +- if (compaction_index > 3) { +- printf("No of huge pages allocated = %d\n", +- (atoi(nr_hugepages))); +- fprintf(stderr, "ERROR: Less that 1/%d of memory is available\n" +- "as huge pages\n", compaction_index); +- goto close_fd; +- } +- +- printf("No of huge pages allocated = %d\n", +- (atoi(nr_hugepages))); +- + lseek(fd, 0, SEEK_SET); + + if (write(fd, initial_nr_hugepages, strlen(initial_nr_hugepages)) + != strlen(initial_nr_hugepages)) { +- perror("Failed to write value to /proc/sys/vm/nr_hugepages\n"); ++ ksft_test_result_fail("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n", ++ strerror(errno)); + goto close_fd; + } + +- close(fd); +- return 0; ++ if (compaction_index > 3) { ++ ksft_print_msg("ERROR: Less that 1/%d of memory is available\n" ++ "as huge pages\n", compaction_index); ++ ksft_test_result_fail("No of huge pages allocated = %d\n", (atoi(nr_hugepages))); ++ goto close_fd; ++ } ++ ++ ksft_test_result_pass("Memory compaction succeeded. No of huge pages allocated = %d\n", ++ (atoi(nr_hugepages))); ++ ret = 0; + + close_fd: + close(fd); +- printf("Not OK. Compaction test failed."); +- return -1; ++ return ret; + } + + + int main(int argc, char **argv) + { + struct rlimit lim; +- struct map_list *list, *entry; ++ struct map_list *list = NULL, *entry; + size_t page_size, i; + void *map = NULL; + unsigned long mem_free = 0; + unsigned long hugepage_size = 0; + long mem_fragmentable_MB = 0; + +- if (prereq() != 0) { +- printf("Either the sysctl compact_unevictable_allowed is not\n" +- "set to 1 or couldn't read the proc file.\n" +- "Skipping the test\n"); +- return KSFT_SKIP; +- } ++ ksft_print_header(); ++ ++ if (prereq() != 0) ++ return ksft_exit_pass(); ++ ++ ksft_set_plan(1); + + lim.rlim_cur = RLIM_INFINITY; + lim.rlim_max = RLIM_INFINITY; +- if (setrlimit(RLIMIT_MEMLOCK, &lim)) { +- perror("Failed to set rlimit:\n"); +- return -1; +- } ++ if (setrlimit(RLIMIT_MEMLOCK, &lim)) ++ ksft_exit_fail_msg("Failed to set rlimit: %s\n", strerror(errno)); + + page_size = getpagesize(); + +- list = NULL; +- +- if (read_memory_info(&mem_free, &hugepage_size) != 0) { +- printf("ERROR: Cannot read meminfo\n"); +- return -1; +- } ++ if (read_memory_info(&mem_free, &hugepage_size) != 0) ++ ksft_exit_fail_msg("Failed to get meminfo\n"); + + mem_fragmentable_MB = mem_free * 0.8 / 1024; + +@@ -227,7 +224,7 @@ int main(int argc, char **argv) + } + + if (check_compaction(mem_free, hugepage_size) == 0) +- return 0; ++ return ksft_exit_pass(); + +- return -1; ++ return ksft_exit_fail(); + } +-- +2.43.0 + diff --git a/queue-6.6/selftests-mm-log-a-consistent-test-name-for-check_co.patch b/queue-6.6/selftests-mm-log-a-consistent-test-name-for-check_co.patch new file mode 100644 index 00000000000..7b17409d838 --- /dev/null +++ b/queue-6.6/selftests-mm-log-a-consistent-test-name-for-check_co.patch @@ -0,0 +1,124 @@ +From e000985fd213b09a0f3301b78b68a20a51ad08f8 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 9 Feb 2024 14:30:04 +0000 +Subject: selftests/mm: log a consistent test name for check_compaction + +From: Mark Brown + +[ Upstream commit f3b7568c49420d2dcd251032c9ca1e069ec8a6c9 ] + +Every test result report in the compaction test prints a distinct log +messae, and some of the reports print a name that varies at runtime. This +causes problems for automation since a lot of automation software uses the +printed string as the name of the test, if the name varies from run to run +and from pass to fail then the automation software can't identify that a +test changed result or that the same tests are being run. + +Refactor the logging to use a consistent name when printing the result of +the test, printing the existing messages as diagnostic information instead +so they are still available for people trying to interpret the results. + +Link: https://lkml.kernel.org/r/20240209-kselftest-mm-cleanup-v1-2-a3c0386496b5@kernel.org +Signed-off-by: Mark Brown +Cc: Muhammad Usama Anjum +Cc: Ryan Roberts +Cc: Shuah Khan +Signed-off-by: Andrew Morton +Stable-dep-of: d4202e66a4b1 ("selftests/mm: compaction_test: fix bogus test success on Aarch64") +Signed-off-by: Sasha Levin +--- + tools/testing/selftests/mm/compaction_test.c | 35 +++++++++++--------- + 1 file changed, 19 insertions(+), 16 deletions(-) + +diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c +index f81931c1f8386..6aa6460b854ea 100644 +--- a/tools/testing/selftests/mm/compaction_test.c ++++ b/tools/testing/selftests/mm/compaction_test.c +@@ -95,14 +95,15 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) + + fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); + if (fd < 0) { +- ksft_test_result_fail("Failed to open /proc/sys/vm/nr_hugepages: %s\n", +- strerror(errno)); +- return -1; ++ ksft_print_msg("Failed to open /proc/sys/vm/nr_hugepages: %s\n", ++ strerror(errno)); ++ ret = -1; ++ goto out; + } + + if (read(fd, initial_nr_hugepages, sizeof(initial_nr_hugepages)) <= 0) { +- ksft_test_result_fail("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", +- strerror(errno)); ++ ksft_print_msg("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", ++ strerror(errno)); + goto close_fd; + } + +@@ -110,8 +111,8 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) + + /* Start with the initial condition of 0 huge pages*/ + if (write(fd, "0", sizeof(char)) != sizeof(char)) { +- ksft_test_result_fail("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", +- strerror(errno)); ++ ksft_print_msg("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", ++ strerror(errno)); + goto close_fd; + } + +@@ -120,16 +121,16 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) + /* Request a large number of huge pages. The Kernel will allocate + as much as it can */ + if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) { +- ksft_test_result_fail("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n", +- strerror(errno)); ++ ksft_print_msg("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n", ++ strerror(errno)); + goto close_fd; + } + + lseek(fd, 0, SEEK_SET); + + if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { +- ksft_test_result_fail("Failed to re-read from /proc/sys/vm/nr_hugepages: %s\n", +- strerror(errno)); ++ ksft_print_msg("Failed to re-read from /proc/sys/vm/nr_hugepages: %s\n", ++ strerror(errno)); + goto close_fd; + } + +@@ -141,24 +142,26 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) + + if (write(fd, initial_nr_hugepages, strlen(initial_nr_hugepages)) + != strlen(initial_nr_hugepages)) { +- ksft_test_result_fail("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n", +- strerror(errno)); ++ ksft_print_msg("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n", ++ strerror(errno)); + goto close_fd; + } + ++ ksft_print_msg("Number of huge pages allocated = %d\n", ++ atoi(nr_hugepages)); ++ + if (compaction_index > 3) { + ksft_print_msg("ERROR: Less that 1/%d of memory is available\n" + "as huge pages\n", compaction_index); +- ksft_test_result_fail("No of huge pages allocated = %d\n", (atoi(nr_hugepages))); + goto close_fd; + } + +- ksft_test_result_pass("Memory compaction succeeded. No of huge pages allocated = %d\n", +- (atoi(nr_hugepages))); + ret = 0; + + close_fd: + close(fd); ++ out: ++ ksft_test_result(ret == 0, "check_compaction\n"); + return ret; + } + +-- +2.43.0 + diff --git a/queue-6.6/series b/queue-6.6/series index e46106ce743..2c353f57a20 100644 --- a/queue-6.6/series +++ b/queue-6.6/series @@ -134,3 +134,83 @@ powerpc-bpf-enforce-full-ordering-for-atomic-operations-with-bpf_fetch.patch smb-client-fix-deadlock-in-smb2_find_smb_tcon.patch selftests-net-more-strict-check-in-net_helper.patch smp-provide-setup_max_cpus-definition-on-up-too.patch +wifi-mac80211-mesh-fix-leak-of-mesh_preq_queue-objec.patch +wifi-mac80211-fix-deadlock-in-ieee80211_sta_ps_deliv.patch +wifi-cfg80211-fully-move-wiphy-work-to-unbound-workq.patch +wifi-cfg80211-lock-wiphy-in-cfg80211_get_station.patch +wifi-cfg80211-pmsr-use-correct-nla_get_ux-functions.patch +wifi-iwlwifi-mvm-don-t-initialize-csa_work-twice.patch +wifi-iwlwifi-mvm-revert-gen2-tx-a-mpdu-size-to-64.patch +wifi-iwlwifi-mvm-set-properly-mac-header.patch +wifi-iwlwifi-dbg_ini-move-iwl_dbg_tlv_free-outside-o.patch +wifi-iwlwifi-mvm-check-n_ssids-before-accessing-the-.patch +wifi-iwlwifi-mvm-don-t-read-past-the-mfuart-notifcat.patch +wifi-mac80211-correctly-parse-spatial-reuse-paramete.patch +scsi-ufs-mcq-fix-error-output-and-clean-up-ufshcd_mc.patch +risc-v-kvm-no-need-to-use-mask-when-hart-index-bit-i.patch +risc-v-kvm-fix-incorrect-reg_subtype-labels-in-kvm_r.patch +ax25-fix-refcount-imbalance-on-inbound-connections.patch +ax25-replace-kfree-in-ax25_dev_free-with-ax25_dev_pu.patch +net-ncsi-simplify-kconfig-dts-control-flow.patch +net-ncsi-fix-the-multi-thread-manner-of-ncsi-driver.patch +net-phy-micrel-fix-ksz9477-phy-issues-after-suspend-.patch +bpf-store-ref_ctr_offsets-values-in-bpf_uprobe-array.patch +bpf-optimize-the-free-of-inner-map.patch +bpf-fix-a-potential-use-after-free-in-bpf_link_free.patch +kvm-sev-es-disallow-sev-es-guests-when-x86_feature_l.patch +kvm-sev-do-not-intercept-accesses-to-msr_ia32_xss-fo.patch +kvm-sev-es-delegate-lbr-virtualization-to-the-proces.patch +vmxnet3-disable-rx-data-ring-on-dma-allocation-failu.patch +ipv6-ioam-block-bh-from-ioam6_output.patch +ipv6-sr-block-bh-in-seg6_output_core-and-seg6_input_.patch +net-tls-fix-marking-packets-as-decrypted.patch +bpf-set-run-context-for-rawtp-test_run-callback.patch +octeontx2-af-always-allocate-pf-entries-from-low-pri.patch +net-smc-avoid-overwriting-when-adjusting-sock-bufsiz.patch +net-phy-micrel-ksz8061-fix-errata-solution-not-takin.patch +net-sched-sch_multiq-fix-possible-oob-write-in-multi.patch +vxlan-fix-regression-when-dropping-packets-due-to-in.patch +tcp-count-close-wait-sockets-for-tcp_mib_currestab.patch +mptcp-count-close-wait-sockets-for-mptcp_mib_currest.patch +net-mlx5-stop-waiting-for-pci-if-pci-channel-is-offl.patch +net-mlx5-always-stop-health-timer-during-driver-remo.patch +net-mlx5-fix-tainted-pointer-delete-is-case-of-flow-.patch +net-sched-taprio-always-validate-tca_taprio_attr_pri.patch +ptp-fix-error-message-on-failed-pin-verification.patch +ice-fix-iteration-of-tlvs-in-preserved-fields-area.patch +ice-remove-af_xdp_zc_qps-bitmap.patch +ice-add-flag-to-distinguish-reset-from-.ndo_bpf-in-x.patch +net-wwan-iosm-fix-tainted-pointer-delete-is-case-of-.patch +af_unix-set-sk-sk_state-under-unix_state_lock-for-tr.patch +af_unix-annodate-data-races-around-sk-sk_state-for-w.patch +af_unix-annotate-data-race-of-sk-sk_state-in-unix_in.patch +af_unix-annotate-data-races-around-sk-sk_state-in-un.patch +af_unix-annotate-data-race-of-sk-sk_state-in-unix_st.patch +af_unix-annotate-data-races-around-sk-sk_state-in-se.patch +af_unix-annotate-data-race-of-sk-sk_state-in-unix_st.patch-2156 +af_unix-annotate-data-races-around-sk-sk_state-in-un.patch-11288 +af_unix-annotate-data-races-around-sk-sk_sndbuf.patch +af_unix-annotate-data-race-of-net-unx.sysctl_max_dgr.patch +af_unix-use-unix_recvq_full_lockless-in-unix_stream_.patch +af_unix-use-skb_queue_empty_lockless-in-unix_release.patch +af_unix-use-skb_queue_len_lockless-in-sk_diag_show_r.patch +af_unix-annotate-data-race-of-sk-sk_shutdown-in-sk_d.patch +ipv6-fix-possible-race-in-__fib6_drop_pcpu_from.patch +net-ethtool-fix-the-error-condition-in-ethtool_get_p.patch +ksmbd-use-rwsem-instead-of-rwlock-for-lease-break.patch +firmware-qcom_scm-disable-clocks-if-qcom_scm_bw_enab.patch +memory-failure-use-a-folio-in-me_huge_page.patch +mm-memory-failure-fix-handling-of-dissolved-but-not-.patch +selftests-mm-conform-test-to-tap-format-output.patch +selftests-mm-log-a-consistent-test-name-for-check_co.patch +selftests-mm-compaction_test-fix-bogus-test-success-.patch +irqchip-riscv-intc-allow-large-non-standard-interrup.patch +irqchip-riscv-intc-introduce-andes-hart-level-interr.patch +irqchip-riscv-intc-prevent-memory-leak-when-riscv_in.patch +ext4-avoid-overflow-when-setting-values-via-sysfs.patch +ext4-refactor-out-ext4_generic_attr_show.patch +ext4-fix-slab-out-of-bounds-in-ext4_mb_find_good_gro.patch +eventfs-update-all-the-eventfs_inodes-from-the-event.patch +bpf-fix-multi-uprobe-pid-filtering-logic.patch +nilfs2-return-the-mapped-address-from-nilfs_get_page.patch +nilfs2-fix-nilfs_empty_dir-misjudgment-and-long-loop.patch diff --git a/queue-6.6/tcp-count-close-wait-sockets-for-tcp_mib_currestab.patch b/queue-6.6/tcp-count-close-wait-sockets-for-tcp_mib_currestab.patch new file mode 100644 index 00000000000..a2781abe47c --- /dev/null +++ b/queue-6.6/tcp-count-close-wait-sockets-for-tcp_mib_currestab.patch @@ -0,0 +1,71 @@ +From 1f1047cd8d5eca76bb9ef8d80e84ddea3c17dc1a Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 4 Jun 2024 01:02:16 +0800 +Subject: tcp: count CLOSE-WAIT sockets for TCP_MIB_CURRESTAB + +From: Jason Xing + +[ Upstream commit a46d0ea5c94205f40ecf912d1bb7806a8a64704f ] + +According to RFC 1213, we should also take CLOSE-WAIT sockets into +consideration: + + "tcpCurrEstab OBJECT-TYPE + ... + The number of TCP connections for which the current state + is either ESTABLISHED or CLOSE- WAIT." + +After this, CurrEstab counter will display the total number of +ESTABLISHED and CLOSE-WAIT sockets. + +The logic of counting +When we increment the counter? +a) if we change the state to ESTABLISHED. +b) if we change the state from SYN-RECEIVED to CLOSE-WAIT. + +When we decrement the counter? +a) if the socket leaves ESTABLISHED and will never go into CLOSE-WAIT, +say, on the client side, changing from ESTABLISHED to FIN-WAIT-1. +b) if the socket leaves CLOSE-WAIT, say, on the server side, changing +from CLOSE-WAIT to LAST-ACK. + +Please note: there are two chances that old state of socket can be changed +to CLOSE-WAIT in tcp_fin(). One is SYN-RECV, the other is ESTABLISHED. +So we have to take care of the former case. + +Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") +Signed-off-by: Jason Xing +Reviewed-by: Eric Dumazet +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/ipv4/tcp.c | 6 +++++- + 1 file changed, 5 insertions(+), 1 deletion(-) + +diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c +index a9b33135513d8..2df05ea2e00fe 100644 +--- a/net/ipv4/tcp.c ++++ b/net/ipv4/tcp.c +@@ -2640,6 +2640,10 @@ void tcp_set_state(struct sock *sk, int state) + if (oldstate != TCP_ESTABLISHED) + TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); + break; ++ case TCP_CLOSE_WAIT: ++ if (oldstate == TCP_SYN_RECV) ++ TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); ++ break; + + case TCP_CLOSE: + if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED) +@@ -2651,7 +2655,7 @@ void tcp_set_state(struct sock *sk, int state) + inet_put_port(sk); + fallthrough; + default: +- if (oldstate == TCP_ESTABLISHED) ++ if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT) + TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); + } + +-- +2.43.0 + diff --git a/queue-6.6/vmxnet3-disable-rx-data-ring-on-dma-allocation-failu.patch b/queue-6.6/vmxnet3-disable-rx-data-ring-on-dma-allocation-failu.patch new file mode 100644 index 00000000000..6853486904d --- /dev/null +++ b/queue-6.6/vmxnet3-disable-rx-data-ring-on-dma-allocation-failu.patch @@ -0,0 +1,116 @@ +From 723e56905b13966536e7bc6fee19cc844504788d Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 31 May 2024 12:37:11 +0200 +Subject: vmxnet3: disable rx data ring on dma allocation failure + +From: Matthias Stocker + +[ Upstream commit ffbe335b8d471f79b259e950cb20999700670456 ] + +When vmxnet3_rq_create() fails to allocate memory for rq->data_ring.base, +the subsequent call to vmxnet3_rq_destroy_all_rxdataring does not reset +rq->data_ring.desc_size for the data ring that failed, which presumably +causes the hypervisor to reference it on packet reception. + +To fix this bug, rq->data_ring.desc_size needs to be set to 0 to tell +the hypervisor to disable this feature. + +[ 95.436876] kernel BUG at net/core/skbuff.c:207! +[ 95.439074] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI +[ 95.440411] CPU: 7 PID: 0 Comm: swapper/7 Not tainted 6.9.3-dirty #1 +[ 95.441558] Hardware name: VMware, Inc. VMware Virtual +Platform/440BX Desktop Reference Platform, BIOS 6.00 12/12/2018 +[ 95.443481] RIP: 0010:skb_panic+0x4d/0x4f +[ 95.444404] Code: 4f 70 50 8b 87 c0 00 00 00 50 8b 87 bc 00 00 00 50 +ff b7 d0 00 00 00 4c 8b 8f c8 00 00 00 48 c7 c7 68 e8 be 9f e8 63 58 f9 +ff <0f> 0b 48 8b 14 24 48 c7 c1 d0 73 65 9f e8 a1 ff ff ff 48 8b 14 24 +[ 95.447684] RSP: 0018:ffffa13340274dd0 EFLAGS: 00010246 +[ 95.448762] RAX: 0000000000000089 RBX: ffff8fbbc72b02d0 RCX: 000000000000083f +[ 95.450148] RDX: 0000000000000000 RSI: 00000000000000f6 RDI: 000000000000083f +[ 95.451520] RBP: 000000000000002d R08: 0000000000000000 R09: ffffa13340274c60 +[ 95.452886] R10: ffffffffa04ed468 R11: 0000000000000002 R12: 0000000000000000 +[ 95.454293] R13: ffff8fbbdab3c2d0 R14: ffff8fbbdbd829e0 R15: ffff8fbbdbd809e0 +[ 95.455682] FS: 0000000000000000(0000) GS:ffff8fbeefd80000(0000) knlGS:0000000000000000 +[ 95.457178] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +[ 95.458340] CR2: 00007fd0d1f650c8 CR3: 0000000115f28000 CR4: 00000000000406f0 +[ 95.459791] Call Trace: +[ 95.460515] +[ 95.461180] ? __die_body.cold+0x19/0x27 +[ 95.462150] ? die+0x2e/0x50 +[ 95.462976] ? do_trap+0xca/0x110 +[ 95.463973] ? do_error_trap+0x6a/0x90 +[ 95.464966] ? skb_panic+0x4d/0x4f +[ 95.465901] ? exc_invalid_op+0x50/0x70 +[ 95.466849] ? skb_panic+0x4d/0x4f +[ 95.467718] ? asm_exc_invalid_op+0x1a/0x20 +[ 95.468758] ? skb_panic+0x4d/0x4f +[ 95.469655] skb_put.cold+0x10/0x10 +[ 95.470573] vmxnet3_rq_rx_complete+0x862/0x11e0 [vmxnet3] +[ 95.471853] vmxnet3_poll_rx_only+0x36/0xb0 [vmxnet3] +[ 95.473185] __napi_poll+0x2b/0x160 +[ 95.474145] net_rx_action+0x2c6/0x3b0 +[ 95.475115] handle_softirqs+0xe7/0x2a0 +[ 95.476122] __irq_exit_rcu+0x97/0xb0 +[ 95.477109] common_interrupt+0x85/0xa0 +[ 95.478102] +[ 95.478846] +[ 95.479603] asm_common_interrupt+0x26/0x40 +[ 95.480657] RIP: 0010:pv_native_safe_halt+0xf/0x20 +[ 95.481801] Code: 22 d7 e9 54 87 01 00 0f 1f 40 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa eb 07 0f 00 2d 93 ba 3b 00 fb f4 2c 87 01 00 66 66 2e 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90 +[ 95.485563] RSP: 0018:ffffa133400ffe58 EFLAGS: 00000246 +[ 95.486882] RAX: 0000000000004000 RBX: ffff8fbbc1d14064 RCX: 0000000000000000 +[ 95.488477] RDX: ffff8fbeefd80000 RSI: ffff8fbbc1d14000 RDI: 0000000000000001 +[ 95.490067] RBP: ffff8fbbc1d14064 R08: ffffffffa0652260 R09: 00000000000010d3 +[ 95.491683] R10: 0000000000000018 R11: ffff8fbeefdb4764 R12: ffffffffa0652260 +[ 95.493389] R13: ffffffffa06522e0 R14: 0000000000000001 R15: 0000000000000000 +[ 95.495035] acpi_safe_halt+0x14/0x20 +[ 95.496127] acpi_idle_do_entry+0x2f/0x50 +[ 95.497221] acpi_idle_enter+0x7f/0xd0 +[ 95.498272] cpuidle_enter_state+0x81/0x420 +[ 95.499375] cpuidle_enter+0x2d/0x40 +[ 95.500400] do_idle+0x1e5/0x240 +[ 95.501385] cpu_startup_entry+0x29/0x30 +[ 95.502422] start_secondary+0x11c/0x140 +[ 95.503454] common_startup_64+0x13e/0x141 +[ 95.504466] +[ 95.505197] Modules linked in: nft_fib_inet nft_fib_ipv4 +nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 +nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 +nf_defrag_ipv4 rfkill ip_set nf_tables vsock_loopback +vmw_vsock_virtio_transport_common qrtr vmw_vsock_vmci_transport vsock +sunrpc binfmt_misc pktcdvd vmw_balloon pcspkr vmw_vmci i2c_piix4 joydev +loop dm_multipath nfnetlink zram crct10dif_pclmul crc32_pclmul vmwgfx +crc32c_intel polyval_clmulni polyval_generic ghash_clmulni_intel +sha512_ssse3 sha256_ssse3 vmxnet3 sha1_ssse3 drm_ttm_helper vmw_pvscsi +ttm ata_generic pata_acpi serio_raw scsi_dh_rdac scsi_dh_emc +scsi_dh_alua ip6_tables ip_tables fuse +[ 95.516536] ---[ end trace 0000000000000000 ]--- + +Fixes: 6f4833383e85 ("net: vmxnet3: Fix NULL pointer dereference in vmxnet3_rq_rx_complete()") +Signed-off-by: Matthias Stocker +Reviewed-by: Subbaraya Sundeep +Reviewed-by: Ronak Doshi +Link: https://lore.kernel.org/r/20240531103711.101961-1-mstocker@barracuda.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/vmxnet3/vmxnet3_drv.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c +index 0578864792b60..beebe09eb88ff 100644 +--- a/drivers/net/vmxnet3/vmxnet3_drv.c ++++ b/drivers/net/vmxnet3/vmxnet3_drv.c +@@ -2034,8 +2034,8 @@ vmxnet3_rq_destroy_all_rxdataring(struct vmxnet3_adapter *adapter) + rq->data_ring.base, + rq->data_ring.basePA); + rq->data_ring.base = NULL; +- rq->data_ring.desc_size = 0; + } ++ rq->data_ring.desc_size = 0; + } + } + +-- +2.43.0 + diff --git a/queue-6.6/vxlan-fix-regression-when-dropping-packets-due-to-in.patch b/queue-6.6/vxlan-fix-regression-when-dropping-packets-due-to-in.patch new file mode 100644 index 00000000000..f53338ae9e3 --- /dev/null +++ b/queue-6.6/vxlan-fix-regression-when-dropping-packets-due-to-in.patch @@ -0,0 +1,65 @@ +From f679d0d54570b3cd07f02145a1e8e067ea0a9558 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 3 Jun 2024 10:59:26 +0200 +Subject: vxlan: Fix regression when dropping packets due to invalid src + addresses + +From: Daniel Borkmann + +[ Upstream commit 1cd4bc987abb2823836cbb8f887026011ccddc8a ] + +Commit f58f45c1e5b9 ("vxlan: drop packets from invalid src-address") +has recently been added to vxlan mainly in the context of source +address snooping/learning so that when it is enabled, an entry in the +FDB is not being created for an invalid address for the corresponding +tunnel endpoint. + +Before commit f58f45c1e5b9 vxlan was similarly behaving as geneve in +that it passed through whichever macs were set in the L2 header. It +turns out that this change in behavior breaks setups, for example, +Cilium with netkit in L3 mode for Pods as well as tunnel mode has been +passing before the change in f58f45c1e5b9 for both vxlan and geneve. +After mentioned change it is only passing for geneve as in case of +vxlan packets are dropped due to vxlan_set_mac() returning false as +source and destination macs are zero which for E/W traffic via tunnel +is totally fine. + +Fix it by only opting into the is_valid_ether_addr() check in +vxlan_set_mac() when in fact source address snooping/learning is +actually enabled in vxlan. This is done by moving the check into +vxlan_snoop(). With this change, the Cilium connectivity test suite +passes again for both tunnel flavors. + +Fixes: f58f45c1e5b9 ("vxlan: drop packets from invalid src-address") +Signed-off-by: Daniel Borkmann +Cc: David Bauer +Cc: Ido Schimmel +Cc: Nikolay Aleksandrov +Cc: Martin KaFai Lau +Reviewed-by: Ido Schimmel +Reviewed-by: Nikolay Aleksandrov +Reviewed-by: David Bauer +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/vxlan/vxlan_core.c | 4 ++++ + 1 file changed, 4 insertions(+) + +diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c +index c24ff08abe0da..8268fa331826e 100644 +--- a/drivers/net/vxlan/vxlan_core.c ++++ b/drivers/net/vxlan/vxlan_core.c +@@ -1446,6 +1446,10 @@ static bool vxlan_snoop(struct net_device *dev, + struct vxlan_fdb *f; + u32 ifindex = 0; + ++ /* Ignore packets from invalid src-address */ ++ if (!is_valid_ether_addr(src_mac)) ++ return true; ++ + #if IS_ENABLED(CONFIG_IPV6) + if (src_ip->sa.sa_family == AF_INET6 && + (ipv6_addr_type(&src_ip->sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL)) +-- +2.43.0 + diff --git a/queue-6.6/wifi-cfg80211-fully-move-wiphy-work-to-unbound-workq.patch b/queue-6.6/wifi-cfg80211-fully-move-wiphy-work-to-unbound-workq.patch new file mode 100644 index 00000000000..6467804ce5a --- /dev/null +++ b/queue-6.6/wifi-cfg80211-fully-move-wiphy-work-to-unbound-workq.patch @@ -0,0 +1,62 @@ +From 83691708b4e46023aad354aa5c61ffc8a892079a Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 22 May 2024 12:41:25 +0200 +Subject: wifi: cfg80211: fully move wiphy work to unbound workqueue + +From: Johannes Berg + +[ Upstream commit e296c95eac655008d5a709b8cf54d0018da1c916 ] + +Previously I had moved the wiphy work to the unbound +system workqueue, but missed that when it restarts and +during resume it was still using the normal system +workqueue. Fix that. + +Fixes: 91d20ab9d9ca ("wifi: cfg80211: use system_unbound_wq for wiphy work") +Reviewed-by: Miriam Rachel Korenblit +Link: https://msgid.link/20240522124126.7ca959f2cbd3.I3e2a71ef445d167b84000ccf934ea245aef8d395@changeid +Signed-off-by: Johannes Berg +Signed-off-by: Sasha Levin +--- + net/wireless/core.c | 2 +- + net/wireless/sysfs.c | 4 ++-- + 2 files changed, 3 insertions(+), 3 deletions(-) + +diff --git a/net/wireless/core.c b/net/wireless/core.c +index ff743e1f2e2cb..68aa8f0d70140 100644 +--- a/net/wireless/core.c ++++ b/net/wireless/core.c +@@ -431,7 +431,7 @@ static void cfg80211_wiphy_work(struct work_struct *work) + if (wk) { + list_del_init(&wk->entry); + if (!list_empty(&rdev->wiphy_work_list)) +- schedule_work(work); ++ queue_work(system_unbound_wq, work); + spin_unlock_irq(&rdev->wiphy_work_lock); + + wk->func(&rdev->wiphy, wk); +diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c +index 565511a3f461e..62f26618f6747 100644 +--- a/net/wireless/sysfs.c ++++ b/net/wireless/sysfs.c +@@ -5,7 +5,7 @@ + * + * Copyright 2005-2006 Jiri Benc + * Copyright 2006 Johannes Berg +- * Copyright (C) 2020-2021, 2023 Intel Corporation ++ * Copyright (C) 2020-2021, 2023-2024 Intel Corporation + */ + + #include +@@ -137,7 +137,7 @@ static int wiphy_resume(struct device *dev) + if (rdev->wiphy.registered && rdev->ops->resume) + ret = rdev_resume(rdev); + rdev->suspended = false; +- schedule_work(&rdev->wiphy_work); ++ queue_work(system_unbound_wq, &rdev->wiphy_work); + wiphy_unlock(&rdev->wiphy); + + if (ret) +-- +2.43.0 + diff --git a/queue-6.6/wifi-cfg80211-lock-wiphy-in-cfg80211_get_station.patch b/queue-6.6/wifi-cfg80211-lock-wiphy-in-cfg80211_get_station.patch new file mode 100644 index 00000000000..c1236e7a11f --- /dev/null +++ b/queue-6.6/wifi-cfg80211-lock-wiphy-in-cfg80211_get_station.patch @@ -0,0 +1,103 @@ +From 2da9ee7ecd4a649b5a2a8f360b980eb17f9beea7 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 21 May 2024 21:47:26 +0200 +Subject: wifi: cfg80211: Lock wiphy in cfg80211_get_station + +From: Remi Pommarel + +[ Upstream commit 642f89daa34567d02f312d03e41523a894906dae ] + +Wiphy should be locked before calling rdev_get_station() (see lockdep +assert in ieee80211_get_station()). + +This fixes the following kernel NULL dereference: + + Unable to handle kernel NULL pointer dereference at virtual address 0000000000000050 + Mem abort info: + ESR = 0x0000000096000006 + EC = 0x25: DABT (current EL), IL = 32 bits + SET = 0, FnV = 0 + EA = 0, S1PTW = 0 + FSC = 0x06: level 2 translation fault + Data abort info: + ISV = 0, ISS = 0x00000006 + CM = 0, WnR = 0 + user pgtable: 4k pages, 48-bit VAs, pgdp=0000000003001000 + [0000000000000050] pgd=0800000002dca003, p4d=0800000002dca003, pud=08000000028e9003, pmd=0000000000000000 + Internal error: Oops: 0000000096000006 [#1] SMP + Modules linked in: netconsole dwc3_meson_g12a dwc3_of_simple dwc3 ip_gre gre ath10k_pci ath10k_core ath9k ath9k_common ath9k_hw ath + CPU: 0 PID: 1091 Comm: kworker/u8:0 Not tainted 6.4.0-02144-g565f9a3a7911-dirty #705 + Hardware name: RPT (r1) (DT) + Workqueue: bat_events batadv_v_elp_throughput_metric_update + pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) + pc : ath10k_sta_statistics+0x10/0x2dc [ath10k_core] + lr : sta_set_sinfo+0xcc/0xbd4 + sp : ffff000007b43ad0 + x29: ffff000007b43ad0 x28: ffff0000071fa900 x27: ffff00000294ca98 + x26: ffff000006830880 x25: ffff000006830880 x24: ffff00000294c000 + x23: 0000000000000001 x22: ffff000007b43c90 x21: ffff800008898acc + x20: ffff00000294c6e8 x19: ffff000007b43c90 x18: 0000000000000000 + x17: 445946354d552d78 x16: 62661f7200000000 x15: 57464f445946354d + x14: 0000000000000000 x13: 00000000000000e3 x12: d5f0acbcebea978e + x11: 00000000000000e3 x10: 000000010048fe41 x9 : 0000000000000000 + x8 : ffff000007b43d90 x7 : 000000007a1e2125 x6 : 0000000000000000 + x5 : ffff0000024e0900 x4 : ffff800000a0250c x3 : ffff000007b43c90 + x2 : ffff00000294ca98 x1 : ffff000006831920 x0 : 0000000000000000 + Call trace: + ath10k_sta_statistics+0x10/0x2dc [ath10k_core] + sta_set_sinfo+0xcc/0xbd4 + ieee80211_get_station+0x2c/0x44 + cfg80211_get_station+0x80/0x154 + batadv_v_elp_get_throughput+0x138/0x1fc + batadv_v_elp_throughput_metric_update+0x1c/0xa4 + process_one_work+0x1ec/0x414 + worker_thread+0x70/0x46c + kthread+0xdc/0xe0 + ret_from_fork+0x10/0x20 + Code: a9bb7bfd 910003fd a90153f3 f9411c40 (f9402814) + +This happens because STA has time to disconnect and reconnect before +batadv_v_elp_throughput_metric_update() delayed work gets scheduled. In +this situation, ath10k_sta_state() can be in the middle of resetting +arsta data when the work queue get chance to be scheduled and ends up +accessing it. Locking wiphy prevents that. + +Fixes: 7406353d43c8 ("cfg80211: implement cfg80211_get_station cfg80211 API") +Signed-off-by: Remi Pommarel +Reviewed-by: Nicolas Escande +Acked-by: Antonio Quartulli +Link: https://msgid.link/983b24a6a176e0800c01aedcd74480d9b551cb13.1716046653.git.repk@triplefau.lt +Signed-off-by: Johannes Berg +Signed-off-by: Sasha Levin +--- + net/wireless/util.c | 7 ++++++- + 1 file changed, 6 insertions(+), 1 deletion(-) + +diff --git a/net/wireless/util.c b/net/wireless/util.c +index 9aa7bdce20b26..57ea6d5b092d4 100644 +--- a/net/wireless/util.c ++++ b/net/wireless/util.c +@@ -2399,6 +2399,7 @@ int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr, + { + struct cfg80211_registered_device *rdev; + struct wireless_dev *wdev; ++ int ret; + + wdev = dev->ieee80211_ptr; + if (!wdev) +@@ -2410,7 +2411,11 @@ int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr, + + memset(sinfo, 0, sizeof(*sinfo)); + +- return rdev_get_station(rdev, dev, mac_addr, sinfo); ++ wiphy_lock(&rdev->wiphy); ++ ret = rdev_get_station(rdev, dev, mac_addr, sinfo); ++ wiphy_unlock(&rdev->wiphy); ++ ++ return ret; + } + EXPORT_SYMBOL(cfg80211_get_station); + +-- +2.43.0 + diff --git a/queue-6.6/wifi-cfg80211-pmsr-use-correct-nla_get_ux-functions.patch b/queue-6.6/wifi-cfg80211-pmsr-use-correct-nla_get_ux-functions.patch new file mode 100644 index 00000000000..0a1043e0c4f --- /dev/null +++ b/queue-6.6/wifi-cfg80211-pmsr-use-correct-nla_get_ux-functions.patch @@ -0,0 +1,85 @@ +From 31bed732ca3a12a59ab37c5f6d4c4ad54a234f8d Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 21 May 2024 15:50:59 +0800 +Subject: wifi: cfg80211: pmsr: use correct nla_get_uX functions + +From: Lin Ma + +[ Upstream commit ab904521f4de52fef4f179d2dfc1877645ef5f5c ] + +The commit 9bb7e0f24e7e ("cfg80211: add peer measurement with FTM +initiator API") defines four attributes NL80211_PMSR_FTM_REQ_ATTR_ +{NUM_BURSTS_EXP}/{BURST_PERIOD}/{BURST_DURATION}/{FTMS_PER_BURST} in +following ways. + +static const struct nla_policy +nl80211_pmsr_ftm_req_attr_policy[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1] = { + ... + [NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP] = + NLA_POLICY_MAX(NLA_U8, 15), + [NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD] = { .type = NLA_U16 }, + [NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION] = + NLA_POLICY_MAX(NLA_U8, 15), + [NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST] = + NLA_POLICY_MAX(NLA_U8, 31), + ... +}; + +That is, those attributes are expected to be NLA_U8 and NLA_U16 types. +However, the consumers of these attributes in `pmsr_parse_ftm` blindly +all use `nla_get_u32`, which is incorrect and causes functionality issues +on little-endian platforms. Hence, fix them with the correct `nla_get_u8` +and `nla_get_u16` functions. + +Fixes: 9bb7e0f24e7e ("cfg80211: add peer measurement with FTM initiator API") +Signed-off-by: Lin Ma +Link: https://msgid.link/20240521075059.47999-1-linma@zju.edu.cn +Signed-off-by: Johannes Berg +Signed-off-by: Sasha Levin +--- + net/wireless/pmsr.c | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c +index 9611aa0bd0513..841a4516793b1 100644 +--- a/net/wireless/pmsr.c ++++ b/net/wireless/pmsr.c +@@ -56,7 +56,7 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, + out->ftm.burst_period = 0; + if (tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD]) + out->ftm.burst_period = +- nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD]); ++ nla_get_u16(tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD]); + + out->ftm.asap = !!tb[NL80211_PMSR_FTM_REQ_ATTR_ASAP]; + if (out->ftm.asap && !capa->ftm.asap) { +@@ -75,7 +75,7 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, + out->ftm.num_bursts_exp = 0; + if (tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP]) + out->ftm.num_bursts_exp = +- nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP]); ++ nla_get_u8(tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP]); + + if (capa->ftm.max_bursts_exponent >= 0 && + out->ftm.num_bursts_exp > capa->ftm.max_bursts_exponent) { +@@ -88,7 +88,7 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, + out->ftm.burst_duration = 15; + if (tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION]) + out->ftm.burst_duration = +- nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION]); ++ nla_get_u8(tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION]); + + out->ftm.ftms_per_burst = 0; + if (tb[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST]) +@@ -107,7 +107,7 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, + out->ftm.ftmr_retries = 3; + if (tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES]) + out->ftm.ftmr_retries = +- nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES]); ++ nla_get_u8(tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES]); + + out->ftm.request_lci = !!tb[NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI]; + if (out->ftm.request_lci && !capa->ftm.request_lci) { +-- +2.43.0 + diff --git a/queue-6.6/wifi-iwlwifi-dbg_ini-move-iwl_dbg_tlv_free-outside-o.patch b/queue-6.6/wifi-iwlwifi-dbg_ini-move-iwl_dbg_tlv_free-outside-o.patch new file mode 100644 index 00000000000..1933a1b051b --- /dev/null +++ b/queue-6.6/wifi-iwlwifi-dbg_ini-move-iwl_dbg_tlv_free-outside-o.patch @@ -0,0 +1,41 @@ +From 69698e8515f0d90e21494433aa46cd2f5e582ed6 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 10 May 2024 17:06:39 +0300 +Subject: wifi: iwlwifi: dbg_ini: move iwl_dbg_tlv_free outside of debugfs + ifdef + +From: Shahar S Matityahu + +[ Upstream commit 87821b67dea87addbc4ab093ba752753b002176a ] + +The driver should call iwl_dbg_tlv_free even if debugfs is not defined +since ini mode does not depend on debugfs ifdef. + +Fixes: 68f6f492c4fa ("iwlwifi: trans: support loading ini TLVs from external file") +Signed-off-by: Shahar S Matityahu +Reviewed-by: Luciano Coelho +Signed-off-by: Miri Korenblit +Link: https://msgid.link/20240510170500.c8e3723f55b0.I5e805732b0be31ee6b83c642ec652a34e974ff10@changeid +Signed-off-by: Johannes Berg +Signed-off-by: Sasha Levin +--- + drivers/net/wireless/intel/iwlwifi/iwl-drv.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +index 8faf4e7872bb9..a56593b6135f6 100644 +--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c ++++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +@@ -1824,8 +1824,8 @@ struct iwl_drv *iwl_drv_start(struct iwl_trans *trans) + err_fw: + #ifdef CONFIG_IWLWIFI_DEBUGFS + debugfs_remove_recursive(drv->dbgfs_drv); +- iwl_dbg_tlv_free(drv->trans); + #endif ++ iwl_dbg_tlv_free(drv->trans); + kfree(drv); + err: + return ERR_PTR(ret); +-- +2.43.0 + diff --git a/queue-6.6/wifi-iwlwifi-mvm-check-n_ssids-before-accessing-the-.patch b/queue-6.6/wifi-iwlwifi-mvm-check-n_ssids-before-accessing-the-.patch new file mode 100644 index 00000000000..dc6619b79bc --- /dev/null +++ b/queue-6.6/wifi-iwlwifi-mvm-check-n_ssids-before-accessing-the-.patch @@ -0,0 +1,49 @@ +From d0f1dc0266e7dcf3889986408711a0457518cc77 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 13 May 2024 13:27:12 +0300 +Subject: wifi: iwlwifi: mvm: check n_ssids before accessing the ssids + +From: Miri Korenblit + +[ Upstream commit 60d62757df30b74bf397a2847a6db7385c6ee281 ] + +In some versions of cfg80211, the ssids poinet might be a valid one even +though n_ssids is 0. Accessing the pointer in this case will cuase an +out-of-bound access. Fix this by checking n_ssids first. + +Fixes: c1a7515393e4 ("iwlwifi: mvm: add adaptive dwell support") +Signed-off-by: Miri Korenblit +Reviewed-by: Ilan Peer +Reviewed-by: Johannes Berg +Link: https://msgid.link/20240513132416.6e4d1762bf0d.I5a0e6cc8f02050a766db704d15594c61fe583d45@changeid +Signed-off-by: Johannes Berg +Signed-off-by: Sasha Levin +--- + drivers/net/wireless/intel/iwlwifi/mvm/scan.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +index 03ec900a33433..0841f1d6dc475 100644 +--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c ++++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +@@ -1304,7 +1304,7 @@ static void iwl_mvm_scan_umac_dwell(struct iwl_mvm *mvm, + if (IWL_MVM_ADWELL_MAX_BUDGET) + cmd->v7.adwell_max_budget = + cpu_to_le16(IWL_MVM_ADWELL_MAX_BUDGET); +- else if (params->ssids && params->ssids[0].ssid_len) ++ else if (params->n_ssids && params->ssids[0].ssid_len) + cmd->v7.adwell_max_budget = + cpu_to_le16(IWL_SCAN_ADWELL_MAX_BUDGET_DIRECTED_SCAN); + else +@@ -1406,7 +1406,7 @@ iwl_mvm_scan_umac_dwell_v11(struct iwl_mvm *mvm, + if (IWL_MVM_ADWELL_MAX_BUDGET) + general_params->adwell_max_budget = + cpu_to_le16(IWL_MVM_ADWELL_MAX_BUDGET); +- else if (params->ssids && params->ssids[0].ssid_len) ++ else if (params->n_ssids && params->ssids[0].ssid_len) + general_params->adwell_max_budget = + cpu_to_le16(IWL_SCAN_ADWELL_MAX_BUDGET_DIRECTED_SCAN); + else +-- +2.43.0 + diff --git a/queue-6.6/wifi-iwlwifi-mvm-don-t-initialize-csa_work-twice.patch b/queue-6.6/wifi-iwlwifi-mvm-don-t-initialize-csa_work-twice.patch new file mode 100644 index 00000000000..080fa5b7f4b --- /dev/null +++ b/queue-6.6/wifi-iwlwifi-mvm-don-t-initialize-csa_work-twice.patch @@ -0,0 +1,39 @@ +From ea977dd5acec25d66e09d8fcd09ddc6cc86f73b3 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sun, 12 May 2024 15:25:00 +0300 +Subject: wifi: iwlwifi: mvm: don't initialize csa_work twice + +From: Miri Korenblit + +[ Upstream commit 92158790ce4391ce4c35d8dfbce759195e4724cb ] + +The initialization of this worker moved to iwl_mvm_mac_init_mvmvif +but we removed only from the pre-MLD version of the add_interface +callback. Remove it also from the MLD version. + +Fixes: 0bcc2155983e ("wifi: iwlwifi: mvm: init vif works only once") +Signed-off-by: Miri Korenblit +Reviewed-by: Johannes Berg +Link: https://msgid.link/20240512152312.4f15b41604f0.Iec912158e5a706175531d3736d77d25adf02fba4@changeid +Signed-off-by: Johannes Berg +Signed-off-by: Sasha Levin +--- + drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c | 2 -- + 1 file changed, 2 deletions(-) + +diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c +index aef8824469e1e..4d9a872818a52 100644 +--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c ++++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c +@@ -73,8 +73,6 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw, + goto out_free_bf; + + iwl_mvm_tcm_add_vif(mvm, vif); +- INIT_DELAYED_WORK(&mvmvif->csa_work, +- iwl_mvm_channel_switch_disconnect_wk); + + if (vif->type == NL80211_IFTYPE_MONITOR) { + mvm->monitor_on = true; +-- +2.43.0 + diff --git a/queue-6.6/wifi-iwlwifi-mvm-don-t-read-past-the-mfuart-notifcat.patch b/queue-6.6/wifi-iwlwifi-mvm-don-t-read-past-the-mfuart-notifcat.patch new file mode 100644 index 00000000000..cdfa096fcd9 --- /dev/null +++ b/queue-6.6/wifi-iwlwifi-mvm-don-t-read-past-the-mfuart-notifcat.patch @@ -0,0 +1,55 @@ +From 74c9edf84eee9b2e70aa9f0a16feaf790b6e8fa6 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 13 May 2024 13:27:14 +0300 +Subject: wifi: iwlwifi: mvm: don't read past the mfuart notifcation + +From: Emmanuel Grumbach + +[ Upstream commit 4bb95f4535489ed830cf9b34b0a891e384d1aee4 ] + +In case the firmware sends a notification that claims it has more data +than it has, we will read past that was allocated for the notification. +Remove the print of the buffer, we won't see it by default. If needed, +we can see the content with tracing. + +This was reported by KFENCE. + +Fixes: bdccdb854f2f ("iwlwifi: mvm: support MFUART dump in case of MFUART assert") +Signed-off-by: Emmanuel Grumbach +Reviewed-by: Johannes Berg +Signed-off-by: Miri Korenblit +Link: https://msgid.link/20240513132416.ba82a01a559e.Ia91dd20f5e1ca1ad380b95e68aebf2794f553d9b@changeid +Signed-off-by: Johannes Berg +Signed-off-by: Sasha Levin +--- + drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 10 ---------- + 1 file changed, 10 deletions(-) + +diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +index 1d5ee4330f29f..51f396287dc69 100644 +--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c ++++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +@@ -92,20 +92,10 @@ void iwl_mvm_mfu_assert_dump_notif(struct iwl_mvm *mvm, + { + struct iwl_rx_packet *pkt = rxb_addr(rxb); + struct iwl_mfu_assert_dump_notif *mfu_dump_notif = (void *)pkt->data; +- __le32 *dump_data = mfu_dump_notif->data; +- int n_words = le32_to_cpu(mfu_dump_notif->data_size) / sizeof(__le32); +- int i; + + if (mfu_dump_notif->index_num == 0) + IWL_INFO(mvm, "MFUART assert id 0x%x occurred\n", + le32_to_cpu(mfu_dump_notif->assert_id)); +- +- for (i = 0; i < n_words; i++) +- IWL_DEBUG_INFO(mvm, +- "MFUART assert dump, dword %u: 0x%08x\n", +- le16_to_cpu(mfu_dump_notif->index_num) * +- n_words + i, +- le32_to_cpu(dump_data[i])); + } + + static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait, +-- +2.43.0 + diff --git a/queue-6.6/wifi-iwlwifi-mvm-revert-gen2-tx-a-mpdu-size-to-64.patch b/queue-6.6/wifi-iwlwifi-mvm-revert-gen2-tx-a-mpdu-size-to-64.patch new file mode 100644 index 00000000000..63b78be8b97 --- /dev/null +++ b/queue-6.6/wifi-iwlwifi-mvm-revert-gen2-tx-a-mpdu-size-to-64.patch @@ -0,0 +1,49 @@ +From 0a0be8ecd046348419591638ccf9ea9b1c835c3c Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 10 May 2024 17:06:33 +0300 +Subject: wifi: iwlwifi: mvm: revert gen2 TX A-MPDU size to 64 + +From: Johannes Berg + +[ Upstream commit 4a7aace2899711592327463c1a29ffee44fcc66e ] + +We don't actually support >64 even for HE devices, so revert +back to 64. This fixes an issue where the session is refused +because the queue is configured differently from the actual +session later. + +Fixes: 514c30696fbc ("iwlwifi: add support for IEEE802.11ax") +Signed-off-by: Johannes Berg +Reviewed-by: Liad Kaufman +Reviewed-by: Luciano Coelho +Signed-off-by: Miri Korenblit +Link: https://msgid.link/20240510170500.52f7b4cf83aa.If47e43adddf7fe250ed7f5571fbb35d8221c7c47@changeid +Signed-off-by: Johannes Berg +Signed-off-by: Sasha Levin +--- + drivers/net/wireless/intel/iwlwifi/mvm/rs.h | 9 ++------- + 1 file changed, 2 insertions(+), 7 deletions(-) + +diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h +index 1ca375a5cf6b5..639cecc7a6e60 100644 +--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h ++++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h +@@ -122,13 +122,8 @@ enum { + + #define LINK_QUAL_AGG_FRAME_LIMIT_DEF (63) + #define LINK_QUAL_AGG_FRAME_LIMIT_MAX (63) +-/* +- * FIXME - various places in firmware API still use u8, +- * e.g. LQ command and SCD config command. +- * This should be 256 instead. +- */ +-#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_DEF (255) +-#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_MAX (255) ++#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_DEF (64) ++#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_MAX (64) + #define LINK_QUAL_AGG_FRAME_LIMIT_MIN (0) + + #define LQ_SIZE 2 /* 2 mode tables: "Active" and "Search" */ +-- +2.43.0 + diff --git a/queue-6.6/wifi-iwlwifi-mvm-set-properly-mac-header.patch b/queue-6.6/wifi-iwlwifi-mvm-set-properly-mac-header.patch new file mode 100644 index 00000000000..0f90b681369 --- /dev/null +++ b/queue-6.6/wifi-iwlwifi-mvm-set-properly-mac-header.patch @@ -0,0 +1,45 @@ +From 25b87d9a8ede43973b52e7c0c5cfcc1cbab21738 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 10 May 2024 17:06:35 +0300 +Subject: wifi: iwlwifi: mvm: set properly mac header + +From: Mordechay Goodstein + +[ Upstream commit 0f2e9f6f21d1ff292363cdfb5bc4d492eeaff76e ] + +In the driver we only use skb_put* for adding data to the skb, hence data +never moves and skb_reset_mac_haeder would set mac_header to the first +time data was added and not to mac80211 header, fix this my using the +actual len of bytes added for setting the mac header. + +Fixes: 3f7a9d577d47 ("wifi: iwlwifi: mvm: simplify by using SKB MAC header pointer") +Signed-off-by: Mordechay Goodstein +Reviewed-by: Johannes Berg +Signed-off-by: Miri Korenblit +Link: https://msgid.link/20240510170500.12f2de2909c3.I72a819b96f2fe55bde192a8fd31a4b96c301aa73@changeid +Signed-off-by: Johannes Berg +Signed-off-by: Sasha Levin +--- + drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +index e9360b555ac93..8cff24d5f5f40 100644 +--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c ++++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +@@ -2730,8 +2730,11 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi, + * + * We mark it as mac header, for upper layers to know where + * all radio tap header ends. ++ * ++ * Since data doesn't move data while putting data on skb and that is ++ * the only way we use, data + len is the next place that hdr would be put + */ +- skb_reset_mac_header(skb); ++ skb_set_mac_header(skb, skb->len); + + /* + * Override the nss from the rx_vec since the rate_n_flags has +-- +2.43.0 + diff --git a/queue-6.6/wifi-mac80211-correctly-parse-spatial-reuse-paramete.patch b/queue-6.6/wifi-mac80211-correctly-parse-spatial-reuse-paramete.patch new file mode 100644 index 00000000000..d7a7786f215 --- /dev/null +++ b/queue-6.6/wifi-mac80211-correctly-parse-spatial-reuse-paramete.patch @@ -0,0 +1,65 @@ +From c5dfb8503cb89cb63920fe680e039076c166744d Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 16 May 2024 10:18:54 +0800 +Subject: wifi: mac80211: correctly parse Spatial Reuse Parameter Set element + +From: Lingbo Kong + +[ Upstream commit a26d8dc5227f449a54518a8b40733a54c6600a8b ] + +Currently, the way of parsing Spatial Reuse Parameter Set element is +incorrect and some members of struct ieee80211_he_obss_pd are not assigned. + +To address this issue, it must be parsed in the order of the elements of +Spatial Reuse Parameter Set defined in the IEEE Std 802.11ax specification. + +The diagram of the Spatial Reuse Parameter Set element (IEEE Std 802.11ax +-2021-9.4.2.252). + +------------------------------------------------------------------------- +| | | | |Non-SRG| SRG | SRG | SRG | SRG | +|Element|Length| Element | SR |OBSS PD|OBSS PD|OBSS PD| BSS |Partial| +| ID | | ID |Control| Max | Min | Max |Color | BSSID | +| | |Extension| | Offset| Offset|Offset |Bitmap|Bitmap | +------------------------------------------------------------------------- + +Fixes: 1ced169cc1c2 ("mac80211: allow setting spatial reuse parameters from bss_conf") +Signed-off-by: Lingbo Kong +Link: https://msgid.link/20240516021854.5682-3-quic_lingbok@quicinc.com +Signed-off-by: Johannes Berg +Signed-off-by: Sasha Levin +--- + net/mac80211/he.c | 10 ++++++++-- + 1 file changed, 8 insertions(+), 2 deletions(-) + +diff --git a/net/mac80211/he.c b/net/mac80211/he.c +index 9f5ffdc9db284..ecbb042dd0433 100644 +--- a/net/mac80211/he.c ++++ b/net/mac80211/he.c +@@ -230,15 +230,21 @@ ieee80211_he_spr_ie_to_bss_conf(struct ieee80211_vif *vif, + + if (!he_spr_ie_elem) + return; ++ ++ he_obss_pd->sr_ctrl = he_spr_ie_elem->he_sr_control; + data = he_spr_ie_elem->optional; + + if (he_spr_ie_elem->he_sr_control & + IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT) +- data++; ++ he_obss_pd->non_srg_max_offset = *data++; ++ + if (he_spr_ie_elem->he_sr_control & + IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT) { +- he_obss_pd->max_offset = *data++; + he_obss_pd->min_offset = *data++; ++ he_obss_pd->max_offset = *data++; ++ memcpy(he_obss_pd->bss_color_bitmap, data, 8); ++ data += 8; ++ memcpy(he_obss_pd->partial_bssid_bitmap, data, 8); + he_obss_pd->enable = true; + } + } +-- +2.43.0 + diff --git a/queue-6.6/wifi-mac80211-fix-deadlock-in-ieee80211_sta_ps_deliv.patch b/queue-6.6/wifi-mac80211-fix-deadlock-in-ieee80211_sta_ps_deliv.patch new file mode 100644 index 00000000000..1205d4b8cc2 --- /dev/null +++ b/queue-6.6/wifi-mac80211-fix-deadlock-in-ieee80211_sta_ps_deliv.patch @@ -0,0 +1,109 @@ +From 372d642d3493ee4d27306fc6ab5846b68d45b158 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 29 May 2024 08:57:53 +0200 +Subject: wifi: mac80211: Fix deadlock in ieee80211_sta_ps_deliver_wakeup() + +From: Remi Pommarel + +[ Upstream commit 44c06bbde6443de206b30f513100b5670b23fc5e ] + +The ieee80211_sta_ps_deliver_wakeup() function takes sta->ps_lock to +synchronizes with ieee80211_tx_h_unicast_ps_buf() which is called from +softirq context. However using only spin_lock() to get sta->ps_lock in +ieee80211_sta_ps_deliver_wakeup() does not prevent softirq to execute +on this same CPU, to run ieee80211_tx_h_unicast_ps_buf() and try to +take this same lock ending in deadlock. Below is an example of rcu stall +that arises in such situation. + + rcu: INFO: rcu_sched self-detected stall on CPU + rcu: 2-....: (42413413 ticks this GP) idle=b154/1/0x4000000000000000 softirq=1763/1765 fqs=21206996 + rcu: (t=42586894 jiffies g=2057 q=362405 ncpus=4) + CPU: 2 PID: 719 Comm: wpa_supplicant Tainted: G W 6.4.0-02158-g1b062f552873 #742 + Hardware name: RPT (r1) (DT) + pstate: 00000005 (nzcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) + pc : queued_spin_lock_slowpath+0x58/0x2d0 + lr : invoke_tx_handlers_early+0x5b4/0x5c0 + sp : ffff00001ef64660 + x29: ffff00001ef64660 x28: ffff000009bc1070 x27: ffff000009bc0ad8 + x26: ffff000009bc0900 x25: ffff00001ef647a8 x24: 0000000000000000 + x23: ffff000009bc0900 x22: ffff000009bc0900 x21: ffff00000ac0e000 + x20: ffff00000a279e00 x19: ffff00001ef646e8 x18: 0000000000000000 + x17: ffff800016468000 x16: ffff00001ef608c0 x15: 0010533c93f64f80 + x14: 0010395c9faa3946 x13: 0000000000000000 x12: 00000000fa83b2da + x11: 000000012edeceea x10: ffff0000010fbe00 x9 : 0000000000895440 + x8 : 000000000010533c x7 : ffff00000ad8b740 x6 : ffff00000c350880 + x5 : 0000000000000007 x4 : 0000000000000001 x3 : 0000000000000000 + x2 : 0000000000000000 x1 : 0000000000000001 x0 : ffff00000ac0e0e8 + Call trace: + queued_spin_lock_slowpath+0x58/0x2d0 + ieee80211_tx+0x80/0x12c + ieee80211_tx_pending+0x110/0x278 + tasklet_action_common.constprop.0+0x10c/0x144 + tasklet_action+0x20/0x28 + _stext+0x11c/0x284 + ____do_softirq+0xc/0x14 + call_on_irq_stack+0x24/0x34 + do_softirq_own_stack+0x18/0x20 + do_softirq+0x74/0x7c + __local_bh_enable_ip+0xa0/0xa4 + _ieee80211_wake_txqs+0x3b0/0x4b8 + __ieee80211_wake_queue+0x12c/0x168 + ieee80211_add_pending_skbs+0xec/0x138 + ieee80211_sta_ps_deliver_wakeup+0x2a4/0x480 + ieee80211_mps_sta_status_update.part.0+0xd8/0x11c + ieee80211_mps_sta_status_update+0x18/0x24 + sta_apply_parameters+0x3bc/0x4c0 + ieee80211_change_station+0x1b8/0x2dc + nl80211_set_station+0x444/0x49c + genl_family_rcv_msg_doit.isra.0+0xa4/0xfc + genl_rcv_msg+0x1b0/0x244 + netlink_rcv_skb+0x38/0x10c + genl_rcv+0x34/0x48 + netlink_unicast+0x254/0x2bc + netlink_sendmsg+0x190/0x3b4 + ____sys_sendmsg+0x1e8/0x218 + ___sys_sendmsg+0x68/0x8c + __sys_sendmsg+0x44/0x84 + __arm64_sys_sendmsg+0x20/0x28 + do_el0_svc+0x6c/0xe8 + el0_svc+0x14/0x48 + el0t_64_sync_handler+0xb0/0xb4 + el0t_64_sync+0x14c/0x150 + +Using spin_lock_bh()/spin_unlock_bh() instead prevents softirq to raise +on the same CPU that is holding the lock. + +Fixes: 1d147bfa6429 ("mac80211: fix AP powersave TX vs. wakeup race") +Signed-off-by: Remi Pommarel +Link: https://msgid.link/8e36fe07d0fbc146f89196cd47a53c8a0afe84aa.1716910344.git.repk@triplefau.lt +Signed-off-by: Johannes Berg +Signed-off-by: Sasha Levin +--- + net/mac80211/sta_info.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c +index c61eb867bb4a7..984f8f67492fd 100644 +--- a/net/mac80211/sta_info.c ++++ b/net/mac80211/sta_info.c +@@ -1709,7 +1709,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) + skb_queue_head_init(&pending); + + /* sync with ieee80211_tx_h_unicast_ps_buf */ +- spin_lock(&sta->ps_lock); ++ spin_lock_bh(&sta->ps_lock); + /* Send all buffered frames to the station */ + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + int count = skb_queue_len(&pending), tmp; +@@ -1738,7 +1738,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) + */ + clear_sta_flag(sta, WLAN_STA_PSPOLL); + clear_sta_flag(sta, WLAN_STA_UAPSD); +- spin_unlock(&sta->ps_lock); ++ spin_unlock_bh(&sta->ps_lock); + + atomic_dec(&ps->num_sta_ps); + +-- +2.43.0 + diff --git a/queue-6.6/wifi-mac80211-mesh-fix-leak-of-mesh_preq_queue-objec.patch b/queue-6.6/wifi-mac80211-mesh-fix-leak-of-mesh_preq_queue-objec.patch new file mode 100644 index 00000000000..5e1c17cd818 --- /dev/null +++ b/queue-6.6/wifi-mac80211-mesh-fix-leak-of-mesh_preq_queue-objec.patch @@ -0,0 +1,100 @@ +From 7d970bc63270145f7dc07eb9fe6f12c36539799a Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 28 May 2024 16:26:05 +0200 +Subject: wifi: mac80211: mesh: Fix leak of mesh_preq_queue objects + +From: Nicolas Escande + +[ Upstream commit b7d7f11a291830fdf69d3301075dd0fb347ced84 ] + +The hwmp code use objects of type mesh_preq_queue, added to a list in +ieee80211_if_mesh, to keep track of mpath we need to resolve. If the mpath +gets deleted, ex mesh interface is removed, the entries in that list will +never get cleaned. Fix this by flushing all corresponding items of the +preq_queue in mesh_path_flush_pending(). + +This should take care of KASAN reports like this: + +unreferenced object 0xffff00000668d800 (size 128): + comm "kworker/u8:4", pid 67, jiffies 4295419552 (age 1836.444s) + hex dump (first 32 bytes): + 00 1f 05 09 00 00 ff ff 00 d5 68 06 00 00 ff ff ..........h..... + 8e 97 ea eb 3e b8 01 00 00 00 00 00 00 00 00 00 ....>........... + backtrace: + [<000000007302a0b6>] __kmem_cache_alloc_node+0x1e0/0x35c + [<00000000049bd418>] kmalloc_trace+0x34/0x80 + [<0000000000d792bb>] mesh_queue_preq+0x44/0x2a8 + [<00000000c99c3696>] mesh_nexthop_resolve+0x198/0x19c + [<00000000926bf598>] ieee80211_xmit+0x1d0/0x1f4 + [<00000000fc8c2284>] __ieee80211_subif_start_xmit+0x30c/0x764 + [<000000005926ee38>] ieee80211_subif_start_xmit+0x9c/0x7a4 + [<000000004c86e916>] dev_hard_start_xmit+0x174/0x440 + [<0000000023495647>] __dev_queue_xmit+0xe24/0x111c + [<00000000cfe9ca78>] batadv_send_skb_packet+0x180/0x1e4 + [<000000007bacc5d5>] batadv_v_elp_periodic_work+0x2f4/0x508 + [<00000000adc3cd94>] process_one_work+0x4b8/0xa1c + [<00000000b36425d1>] worker_thread+0x9c/0x634 + [<0000000005852dd5>] kthread+0x1bc/0x1c4 + [<000000005fccd770>] ret_from_fork+0x10/0x20 +unreferenced object 0xffff000009051f00 (size 128): + comm "kworker/u8:4", pid 67, jiffies 4295419553 (age 1836.440s) + hex dump (first 32 bytes): + 90 d6 92 0d 00 00 ff ff 00 d8 68 06 00 00 ff ff ..........h..... + 36 27 92 e4 02 e0 01 00 00 58 79 06 00 00 ff ff 6'.......Xy..... + backtrace: + [<000000007302a0b6>] __kmem_cache_alloc_node+0x1e0/0x35c + [<00000000049bd418>] kmalloc_trace+0x34/0x80 + [<0000000000d792bb>] mesh_queue_preq+0x44/0x2a8 + [<00000000c99c3696>] mesh_nexthop_resolve+0x198/0x19c + [<00000000926bf598>] ieee80211_xmit+0x1d0/0x1f4 + [<00000000fc8c2284>] __ieee80211_subif_start_xmit+0x30c/0x764 + [<000000005926ee38>] ieee80211_subif_start_xmit+0x9c/0x7a4 + [<000000004c86e916>] dev_hard_start_xmit+0x174/0x440 + [<0000000023495647>] __dev_queue_xmit+0xe24/0x111c + [<00000000cfe9ca78>] batadv_send_skb_packet+0x180/0x1e4 + [<000000007bacc5d5>] batadv_v_elp_periodic_work+0x2f4/0x508 + [<00000000adc3cd94>] process_one_work+0x4b8/0xa1c + [<00000000b36425d1>] worker_thread+0x9c/0x634 + [<0000000005852dd5>] kthread+0x1bc/0x1c4 + [<000000005fccd770>] ret_from_fork+0x10/0x20 + +Fixes: 050ac52cbe1f ("mac80211: code for on-demand Hybrid Wireless Mesh Protocol") +Signed-off-by: Nicolas Escande +Link: https://msgid.link/20240528142605.1060566-1-nico.escande@gmail.com +Signed-off-by: Johannes Berg +Signed-off-by: Sasha Levin +--- + net/mac80211/mesh_pathtbl.c | 13 +++++++++++++ + 1 file changed, 13 insertions(+) + +diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c +index 59f7264194ce3..530581ba812b4 100644 +--- a/net/mac80211/mesh_pathtbl.c ++++ b/net/mac80211/mesh_pathtbl.c +@@ -1011,10 +1011,23 @@ void mesh_path_discard_frame(struct ieee80211_sub_if_data *sdata, + */ + void mesh_path_flush_pending(struct mesh_path *mpath) + { ++ struct ieee80211_sub_if_data *sdata = mpath->sdata; ++ struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; ++ struct mesh_preq_queue *preq, *tmp; + struct sk_buff *skb; + + while ((skb = skb_dequeue(&mpath->frame_queue)) != NULL) + mesh_path_discard_frame(mpath->sdata, skb); ++ ++ spin_lock_bh(&ifmsh->mesh_preq_queue_lock); ++ list_for_each_entry_safe(preq, tmp, &ifmsh->preq_queue.list, list) { ++ if (ether_addr_equal(mpath->dst, preq->dst)) { ++ list_del(&preq->list); ++ kfree(preq); ++ --ifmsh->preq_queue_len; ++ } ++ } ++ spin_unlock_bh(&ifmsh->mesh_preq_queue_lock); + } + + /** +-- +2.43.0 + -- 2.47.3