From: Sasha Levin Date: Fri, 2 Feb 2024 21:37:31 +0000 (-0500) Subject: Fixes for 6.6 X-Git-Tag: v6.1.77~53 X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=a9e1e64f7405550b0e50f64ea5362ad3f7916993;p=thirdparty%2Fkernel%2Fstable-queue.git Fixes for 6.6 Signed-off-by: Sasha Levin --- diff --git a/queue-6.6/af_unix-fix-lockdep-positive-in-sk_diag_dump_icons.patch b/queue-6.6/af_unix-fix-lockdep-positive-in-sk_diag_dump_icons.patch new file mode 100644 index 00000000000..b58a6525581 --- /dev/null +++ b/queue-6.6/af_unix-fix-lockdep-positive-in-sk_diag_dump_icons.patch @@ -0,0 +1,243 @@ +From 948d478e08f85a584715eb61488c38026c5717eb Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 30 Jan 2024 18:42:35 +0000 +Subject: af_unix: fix lockdep positive in sk_diag_dump_icons() + +From: Eric Dumazet + +[ Upstream commit 4d322dce82a1d44f8c83f0f54f95dd1b8dcf46c9 ] + +syzbot reported a lockdep splat [1]. + +Blamed commit hinted about the possible lockdep +violation, and code used unix_state_lock_nested() +in an attempt to silence lockdep. + +It is not sufficient, because unix_state_lock_nested() +is already used from unix_state_double_lock(). + +We need to use a separate subclass. + +This patch adds a distinct enumeration to make things +more explicit. + +Also use swap() in unix_state_double_lock() as a clean up. + +v2: add a missing inline keyword to unix_state_lock_nested() + +[1] +WARNING: possible circular locking dependency detected +6.8.0-rc1-syzkaller-00356-g8a696a29c690 #0 Not tainted + +syz-executor.1/2542 is trying to acquire lock: + ffff88808b5df9e8 (rlock-AF_UNIX){+.+.}-{2:2}, at: skb_queue_tail+0x36/0x120 net/core/skbuff.c:3863 + +but task is already holding lock: + ffff88808b5dfe70 (&u->lock/1){+.+.}-{2:2}, at: unix_dgram_sendmsg+0xfc7/0x2200 net/unix/af_unix.c:2089 + +which lock already depends on the new lock. + +the existing dependency chain (in reverse order) is: + +-> #1 (&u->lock/1){+.+.}-{2:2}: + lock_acquire+0x1e3/0x530 kernel/locking/lockdep.c:5754 + _raw_spin_lock_nested+0x31/0x40 kernel/locking/spinlock.c:378 + sk_diag_dump_icons net/unix/diag.c:87 [inline] + sk_diag_fill+0x6ea/0xfe0 net/unix/diag.c:157 + sk_diag_dump net/unix/diag.c:196 [inline] + unix_diag_dump+0x3e9/0x630 net/unix/diag.c:220 + netlink_dump+0x5c1/0xcd0 net/netlink/af_netlink.c:2264 + __netlink_dump_start+0x5d7/0x780 net/netlink/af_netlink.c:2370 + netlink_dump_start include/linux/netlink.h:338 [inline] + unix_diag_handler_dump+0x1c3/0x8f0 net/unix/diag.c:319 + sock_diag_rcv_msg+0xe3/0x400 + netlink_rcv_skb+0x1df/0x430 net/netlink/af_netlink.c:2543 + sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:280 + netlink_unicast_kernel net/netlink/af_netlink.c:1341 [inline] + netlink_unicast+0x7e6/0x980 net/netlink/af_netlink.c:1367 + netlink_sendmsg+0xa37/0xd70 net/netlink/af_netlink.c:1908 + sock_sendmsg_nosec net/socket.c:730 [inline] + __sock_sendmsg net/socket.c:745 [inline] + sock_write_iter+0x39a/0x520 net/socket.c:1160 + call_write_iter include/linux/fs.h:2085 [inline] + new_sync_write fs/read_write.c:497 [inline] + vfs_write+0xa74/0xca0 fs/read_write.c:590 + ksys_write+0x1a0/0x2c0 fs/read_write.c:643 + do_syscall_x64 arch/x86/entry/common.c:52 [inline] + do_syscall_64+0xf5/0x230 arch/x86/entry/common.c:83 + entry_SYSCALL_64_after_hwframe+0x63/0x6b + +-> #0 (rlock-AF_UNIX){+.+.}-{2:2}: + check_prev_add kernel/locking/lockdep.c:3134 [inline] + check_prevs_add kernel/locking/lockdep.c:3253 [inline] + validate_chain+0x1909/0x5ab0 kernel/locking/lockdep.c:3869 + __lock_acquire+0x1345/0x1fd0 kernel/locking/lockdep.c:5137 + lock_acquire+0x1e3/0x530 kernel/locking/lockdep.c:5754 + __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline] + _raw_spin_lock_irqsave+0xd5/0x120 kernel/locking/spinlock.c:162 + skb_queue_tail+0x36/0x120 net/core/skbuff.c:3863 + unix_dgram_sendmsg+0x15d9/0x2200 net/unix/af_unix.c:2112 + sock_sendmsg_nosec net/socket.c:730 [inline] + __sock_sendmsg net/socket.c:745 [inline] + ____sys_sendmsg+0x592/0x890 net/socket.c:2584 + ___sys_sendmsg net/socket.c:2638 [inline] + __sys_sendmmsg+0x3b2/0x730 net/socket.c:2724 + __do_sys_sendmmsg net/socket.c:2753 [inline] + __se_sys_sendmmsg net/socket.c:2750 [inline] + __x64_sys_sendmmsg+0xa0/0xb0 net/socket.c:2750 + do_syscall_x64 arch/x86/entry/common.c:52 [inline] + do_syscall_64+0xf5/0x230 arch/x86/entry/common.c:83 + entry_SYSCALL_64_after_hwframe+0x63/0x6b + +other info that might help us debug this: + + Possible unsafe locking scenario: + + CPU0 CPU1 + ---- ---- + lock(&u->lock/1); + lock(rlock-AF_UNIX); + lock(&u->lock/1); + lock(rlock-AF_UNIX); + + *** DEADLOCK *** + +1 lock held by syz-executor.1/2542: + #0: ffff88808b5dfe70 (&u->lock/1){+.+.}-{2:2}, at: unix_dgram_sendmsg+0xfc7/0x2200 net/unix/af_unix.c:2089 + +stack backtrace: +CPU: 1 PID: 2542 Comm: syz-executor.1 Not tainted 6.8.0-rc1-syzkaller-00356-g8a696a29c690 #0 +Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023 +Call Trace: + + __dump_stack lib/dump_stack.c:88 [inline] + dump_stack_lvl+0x1e7/0x2d0 lib/dump_stack.c:106 + check_noncircular+0x366/0x490 kernel/locking/lockdep.c:2187 + check_prev_add kernel/locking/lockdep.c:3134 [inline] + check_prevs_add kernel/locking/lockdep.c:3253 [inline] + validate_chain+0x1909/0x5ab0 kernel/locking/lockdep.c:3869 + __lock_acquire+0x1345/0x1fd0 kernel/locking/lockdep.c:5137 + lock_acquire+0x1e3/0x530 kernel/locking/lockdep.c:5754 + __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline] + _raw_spin_lock_irqsave+0xd5/0x120 kernel/locking/spinlock.c:162 + skb_queue_tail+0x36/0x120 net/core/skbuff.c:3863 + unix_dgram_sendmsg+0x15d9/0x2200 net/unix/af_unix.c:2112 + sock_sendmsg_nosec net/socket.c:730 [inline] + __sock_sendmsg net/socket.c:745 [inline] + ____sys_sendmsg+0x592/0x890 net/socket.c:2584 + ___sys_sendmsg net/socket.c:2638 [inline] + __sys_sendmmsg+0x3b2/0x730 net/socket.c:2724 + __do_sys_sendmmsg net/socket.c:2753 [inline] + __se_sys_sendmmsg net/socket.c:2750 [inline] + __x64_sys_sendmmsg+0xa0/0xb0 net/socket.c:2750 + do_syscall_x64 arch/x86/entry/common.c:52 [inline] + do_syscall_64+0xf5/0x230 arch/x86/entry/common.c:83 + entry_SYSCALL_64_after_hwframe+0x63/0x6b +RIP: 0033:0x7f26d887cda9 +Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 20 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 +RSP: 002b:00007f26d95a60c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000133 +RAX: ffffffffffffffda RBX: 00007f26d89abf80 RCX: 00007f26d887cda9 +RDX: 000000000000003e RSI: 00000000200bd000 RDI: 0000000000000004 +RBP: 00007f26d88c947a R08: 0000000000000000 R09: 0000000000000000 +R10: 00000000000008c0 R11: 0000000000000246 R12: 0000000000000000 +R13: 000000000000000b R14: 00007f26d89abf80 R15: 00007ffcfe081a68 + +Fixes: 2aac7a2cb0d9 ("unix_diag: Pending connections IDs NLA") +Reported-by: syzbot +Signed-off-by: Eric Dumazet +Reviewed-by: Kuniyuki Iwashima +Link: https://lore.kernel.org/r/20240130184235.1620738-1-edumazet@google.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + include/net/af_unix.h | 20 ++++++++++++++------ + net/unix/af_unix.c | 14 ++++++-------- + net/unix/diag.c | 2 +- + 3 files changed, 21 insertions(+), 15 deletions(-) + +diff --git a/include/net/af_unix.h b/include/net/af_unix.h +index 49c4640027d8..afd40dce40f3 100644 +--- a/include/net/af_unix.h ++++ b/include/net/af_unix.h +@@ -46,12 +46,6 @@ struct scm_stat { + + #define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) + +-#define unix_state_lock(s) spin_lock(&unix_sk(s)->lock) +-#define unix_state_unlock(s) spin_unlock(&unix_sk(s)->lock) +-#define unix_state_lock_nested(s) \ +- spin_lock_nested(&unix_sk(s)->lock, \ +- SINGLE_DEPTH_NESTING) +- + /* The AF_UNIX socket */ + struct unix_sock { + /* WARNING: sk has to be the first member */ +@@ -77,6 +71,20 @@ struct unix_sock { + #define unix_sk(ptr) container_of_const(ptr, struct unix_sock, sk) + #define unix_peer(sk) (unix_sk(sk)->peer) + ++#define unix_state_lock(s) spin_lock(&unix_sk(s)->lock) ++#define unix_state_unlock(s) spin_unlock(&unix_sk(s)->lock) ++enum unix_socket_lock_class { ++ U_LOCK_NORMAL, ++ U_LOCK_SECOND, /* for double locking, see unix_state_double_lock(). */ ++ U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */ ++}; ++ ++static inline void unix_state_lock_nested(struct sock *sk, ++ enum unix_socket_lock_class subclass) ++{ ++ spin_lock_nested(&unix_sk(sk)->lock, subclass); ++} ++ + #define peer_wait peer_wq.wait + + long unix_inq_len(struct sock *sk); +diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c +index 1e1a88bd4e68..510b1d6758db 100644 +--- a/net/unix/af_unix.c ++++ b/net/unix/af_unix.c +@@ -1343,13 +1343,11 @@ static void unix_state_double_lock(struct sock *sk1, struct sock *sk2) + unix_state_lock(sk1); + return; + } +- if (sk1 < sk2) { +- unix_state_lock(sk1); +- unix_state_lock_nested(sk2); +- } else { +- unix_state_lock(sk2); +- unix_state_lock_nested(sk1); +- } ++ if (sk1 > sk2) ++ swap(sk1, sk2); ++ ++ unix_state_lock(sk1); ++ unix_state_lock_nested(sk2, U_LOCK_SECOND); + } + + static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2) +@@ -1582,7 +1580,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, + goto out_unlock; + } + +- unix_state_lock_nested(sk); ++ unix_state_lock_nested(sk, U_LOCK_SECOND); + + if (sk->sk_state != st) { + unix_state_unlock(sk); +diff --git a/net/unix/diag.c b/net/unix/diag.c +index 616b55c5b890..3438b7af09af 100644 +--- a/net/unix/diag.c ++++ b/net/unix/diag.c +@@ -84,7 +84,7 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb) + * queue lock. With the other's queue locked it's + * OK to lock the state. + */ +- unix_state_lock_nested(req); ++ unix_state_lock_nested(req, U_LOCK_DIAG); + peer = unix_sk(req)->peer; + buf[i++] = (peer ? sock_i_ino(peer) : 0); + unix_state_unlock(req); +-- +2.43.0 + diff --git a/queue-6.6/bridge-mcast-fix-disabled-snooping-after-long-uptime.patch b/queue-6.6/bridge-mcast-fix-disabled-snooping-after-long-uptime.patch new file mode 100644 index 00000000000..cf8aa3ef9c0 --- /dev/null +++ b/queue-6.6/bridge-mcast-fix-disabled-snooping-after-long-uptime.patch @@ -0,0 +1,158 @@ +From 92018ec1c45973af50f0035bf6ed95e008192b42 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sat, 27 Jan 2024 18:50:32 +0100 +Subject: bridge: mcast: fix disabled snooping after long uptime +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Linus Lüssing + +[ Upstream commit f5c3eb4b7251baba5cd72c9e93920e710ac8194a ] + +The original idea of the delay_time check was to not apply multicast +snooping too early when an MLD querier appears. And to instead wait at +least for MLD reports to arrive before switching from flooding to group +based, MLD snooped forwarding, to avoid temporary packet loss. + +However in a batman-adv mesh network it was noticed that after 248 days of +uptime 32bit MIPS based devices would start to signal that they had +stopped applying multicast snooping due to missing queriers - even though +they were the elected querier and still sending MLD queries themselves. + +While time_is_before_jiffies() generally is safe against jiffies +wrap-arounds, like the code comments in jiffies.h explain, it won't +be able to track a difference larger than ULONG_MAX/2. With a 32bit +large jiffies and one jiffies tick every 10ms (CONFIG_HZ=100) on these MIPS +devices running OpenWrt this would result in a difference larger than +ULONG_MAX/2 after 248 (= 2^32/100/60/60/24/2) days and +time_is_before_jiffies() would then start to return false instead of +true. Leading to multicast snooping not being applied to multicast +packets anymore. + +Fix this issue by using a proper timer_list object which won't have this +ULONG_MAX/2 difference limitation. + +Fixes: b00589af3b04 ("bridge: disable snooping if there is no querier") +Signed-off-by: Linus Lüssing +Acked-by: Nikolay Aleksandrov +Link: https://lore.kernel.org/r/20240127175033.9640-1-linus.luessing@c0d3.blue +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/bridge/br_multicast.c | 20 +++++++++++++++----- + net/bridge/br_private.h | 4 ++-- + 2 files changed, 17 insertions(+), 7 deletions(-) + +diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c +index 96d1fc78dd39..38373b4fb7dd 100644 +--- a/net/bridge/br_multicast.c ++++ b/net/bridge/br_multicast.c +@@ -1761,6 +1761,10 @@ static void br_ip6_multicast_querier_expired(struct timer_list *t) + } + #endif + ++static void br_multicast_query_delay_expired(struct timer_list *t) ++{ ++} ++ + static void br_multicast_select_own_querier(struct net_bridge_mcast *brmctx, + struct br_ip *ip, + struct sk_buff *skb) +@@ -3197,7 +3201,7 @@ br_multicast_update_query_timer(struct net_bridge_mcast *brmctx, + unsigned long max_delay) + { + if (!timer_pending(&query->timer)) +- query->delay_time = jiffies + max_delay; ++ mod_timer(&query->delay_timer, jiffies + max_delay); + + mod_timer(&query->timer, jiffies + brmctx->multicast_querier_interval); + } +@@ -4040,13 +4044,11 @@ void br_multicast_ctx_init(struct net_bridge *br, + brmctx->multicast_querier_interval = 255 * HZ; + brmctx->multicast_membership_interval = 260 * HZ; + +- brmctx->ip4_other_query.delay_time = 0; + brmctx->ip4_querier.port_ifidx = 0; + seqcount_spinlock_init(&brmctx->ip4_querier.seq, &br->multicast_lock); + brmctx->multicast_igmp_version = 2; + #if IS_ENABLED(CONFIG_IPV6) + brmctx->multicast_mld_version = 1; +- brmctx->ip6_other_query.delay_time = 0; + brmctx->ip6_querier.port_ifidx = 0; + seqcount_spinlock_init(&brmctx->ip6_querier.seq, &br->multicast_lock); + #endif +@@ -4055,6 +4057,8 @@ void br_multicast_ctx_init(struct net_bridge *br, + br_ip4_multicast_local_router_expired, 0); + timer_setup(&brmctx->ip4_other_query.timer, + br_ip4_multicast_querier_expired, 0); ++ timer_setup(&brmctx->ip4_other_query.delay_timer, ++ br_multicast_query_delay_expired, 0); + timer_setup(&brmctx->ip4_own_query.timer, + br_ip4_multicast_query_expired, 0); + #if IS_ENABLED(CONFIG_IPV6) +@@ -4062,6 +4066,8 @@ void br_multicast_ctx_init(struct net_bridge *br, + br_ip6_multicast_local_router_expired, 0); + timer_setup(&brmctx->ip6_other_query.timer, + br_ip6_multicast_querier_expired, 0); ++ timer_setup(&brmctx->ip6_other_query.delay_timer, ++ br_multicast_query_delay_expired, 0); + timer_setup(&brmctx->ip6_own_query.timer, + br_ip6_multicast_query_expired, 0); + #endif +@@ -4196,10 +4202,12 @@ static void __br_multicast_stop(struct net_bridge_mcast *brmctx) + { + del_timer_sync(&brmctx->ip4_mc_router_timer); + del_timer_sync(&brmctx->ip4_other_query.timer); ++ del_timer_sync(&brmctx->ip4_other_query.delay_timer); + del_timer_sync(&brmctx->ip4_own_query.timer); + #if IS_ENABLED(CONFIG_IPV6) + del_timer_sync(&brmctx->ip6_mc_router_timer); + del_timer_sync(&brmctx->ip6_other_query.timer); ++ del_timer_sync(&brmctx->ip6_other_query.delay_timer); + del_timer_sync(&brmctx->ip6_own_query.timer); + #endif + } +@@ -4642,13 +4650,15 @@ int br_multicast_set_querier(struct net_bridge_mcast *brmctx, unsigned long val) + max_delay = brmctx->multicast_query_response_interval; + + if (!timer_pending(&brmctx->ip4_other_query.timer)) +- brmctx->ip4_other_query.delay_time = jiffies + max_delay; ++ mod_timer(&brmctx->ip4_other_query.delay_timer, ++ jiffies + max_delay); + + br_multicast_start_querier(brmctx, &brmctx->ip4_own_query); + + #if IS_ENABLED(CONFIG_IPV6) + if (!timer_pending(&brmctx->ip6_other_query.timer)) +- brmctx->ip6_other_query.delay_time = jiffies + max_delay; ++ mod_timer(&brmctx->ip6_other_query.delay_timer, ++ jiffies + max_delay); + + br_multicast_start_querier(brmctx, &brmctx->ip6_own_query); + #endif +diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h +index a1f4acfa6994..82e63908dce8 100644 +--- a/net/bridge/br_private.h ++++ b/net/bridge/br_private.h +@@ -78,7 +78,7 @@ struct bridge_mcast_own_query { + /* other querier */ + struct bridge_mcast_other_query { + struct timer_list timer; +- unsigned long delay_time; ++ struct timer_list delay_timer; + }; + + /* selected querier */ +@@ -1149,7 +1149,7 @@ __br_multicast_querier_exists(struct net_bridge_mcast *brmctx, + own_querier_enabled = false; + } + +- return time_is_before_jiffies(querier->delay_time) && ++ return !timer_pending(&querier->delay_timer) && + (own_querier_enabled || timer_pending(&querier->timer)); + } + +-- +2.43.0 + diff --git a/queue-6.6/devlink-fix-referring-to-hw_addr-attribute-during-st.patch b/queue-6.6/devlink-fix-referring-to-hw_addr-attribute-during-st.patch new file mode 100644 index 00000000000..85e31aa1d15 --- /dev/null +++ b/queue-6.6/devlink-fix-referring-to-hw_addr-attribute-during-st.patch @@ -0,0 +1,41 @@ +From 8c9d370ec83c0cb0da458ac6e3f1c1ad324bff46 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 29 Jan 2024 21:10:59 +0200 +Subject: devlink: Fix referring to hw_addr attribute during state validation + +From: Parav Pandit + +[ Upstream commit 1a89e24f8bfd3e3562d69709c9d9cd185ded869b ] + +When port function state change is requested, and when the driver +does not support it, it refers to the hw address attribute instead +of state attribute. Seems like a copy paste error. + +Fix it by referring to the port function state attribute. + +Fixes: c0bea69d1ca7 ("devlink: Validate port function request") +Signed-off-by: Parav Pandit +Reviewed-by: Jiri Pirko +Link: https://lore.kernel.org/r/20240129191059.129030-1-parav@nvidia.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/devlink/port.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/net/devlink/port.c b/net/devlink/port.c +index 4763b42885fb..91ba1ca0f355 100644 +--- a/net/devlink/port.c ++++ b/net/devlink/port.c +@@ -665,7 +665,7 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port, + return -EOPNOTSUPP; + } + if (tb[DEVLINK_PORT_FN_ATTR_STATE] && !ops->port_fn_state_set) { +- NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR], ++ NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FN_ATTR_STATE], + "Function does not support state setting"); + return -EOPNOTSUPP; + } +-- +2.43.0 + diff --git a/queue-6.6/e1000e-correct-maximum-frequency-adjustment-values.patch b/queue-6.6/e1000e-correct-maximum-frequency-adjustment-values.patch new file mode 100644 index 00000000000..17d6b2d3080 --- /dev/null +++ b/queue-6.6/e1000e-correct-maximum-frequency-adjustment-values.patch @@ -0,0 +1,175 @@ +From b4dc3fec7b327224d67b8016e0d277293ef4ec63 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 11 Dec 2023 18:05:52 -0800 +Subject: e1000e: correct maximum frequency adjustment values + +From: Jacob Keller + +[ Upstream commit f1f6a6b1830a8f1dc92ee26fae76333f446b0663 ] + +The e1000e driver supports hardware with a variety of different clock +speeds, and thus a variety of different increment values used for +programming its PTP hardware clock. + +The values currently programmed in e1000e_ptp_init are incorrect. In +particular, only two maximum adjustments are used: 24000000 - 1, and +600000000 - 1. These were originally intended to be used with the 96 MHz +clock and the 25 MHz clock. + +Both of these values are actually slightly too high. For the 96 MHz clock, +the actual maximum value that can safely be programmed is 23,999,938. For +the 25 MHz clock, the maximum value is 599,999,904. + +Worse, several devices use a 24 MHz clock or a 38.4 MHz clock. These parts +are incorrectly assigned one of either the 24million or 600million values. +For the 24 MHz clock, this is not a significant issue: its current +increment value can support an adjustment up to 7billion in the positive +direction. However, the 38.4 KHz clock uses an increment value which can +only support up to 230,769,157 before it starts overflowing. + +To understand where these values come from, consider that frequency +adjustments have the form of: + +new_incval = base_incval + (base_incval * adjustment) / (unit of adjustment) + +The maximum adjustment is reported in terms of parts per billion: +new_incval = base_incval + (base_incval * adjustment) / 1 billion + +The largest possible adjustment is thus given by the following: +max_incval = base_incval + (base_incval * max_adj) / 1 billion + +Re-arranging to solve for max_adj: +max_adj = (max_incval - base_incval) * 1 billion / base_incval + +We also need to ensure that negative adjustments cannot underflow. This can +be achieved simply by ensuring max_adj is always less than 1 billion. + +Introduce new macros in e1000.h codifying the maximum adjustment in PPB for +each frequency given its associated increment values. Also clarify where +these values come from by commenting about the above equations. + +Replace the switch statement in e1000e_ptp_init with one which mirrors the +increment value switch statement from e1000e_get_base_timinica. For each +device, assign the appropriate maximum adjustment based on its frequency. +Some parts can have one of two frequency modes as determined by +E1000_TSYNCRXCTL_SYSCFI. + +Since the new flow directly matches the assignments in +e1000e_get_base_timinca, and uses well defined macro names, it is much +easier to verify that the resulting maximum adjustments are correct. It +also avoids difficult to parse construction such as the "hw->mac.type < +e1000_phc_lpt", and the use of fallthrough which was especially confusing +when combined with a conditional block. + +Note that I believe the current increment value configuration used for +24MHz clocks is sub-par, as it leaves at least 3 extra bits available in +the INCVALUE register. However, fixing that requires more careful review of +the clock rate and associated values. + +Reported-by: Trey Harrison +Fixes: 68fe1d5da548 ("e1000e: Add Support for 38.4MHZ frequency") +Fixes: d89777bf0e42 ("e1000e: add support for IEEE-1588 PTP") +Signed-off-by: Jacob Keller +Tested-by: Naama Meir +Signed-off-by: Tony Nguyen +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/e1000e/e1000.h | 20 ++++++++++++++++++++ + drivers/net/ethernet/intel/e1000e/ptp.c | 22 +++++++++++++++------- + 2 files changed, 35 insertions(+), 7 deletions(-) + +diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h +index a187582d2299..ba9c19e6994c 100644 +--- a/drivers/net/ethernet/intel/e1000e/e1000.h ++++ b/drivers/net/ethernet/intel/e1000e/e1000.h +@@ -360,23 +360,43 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca); + * As a result, a shift of INCVALUE_SHIFT_n is used to fit a value of + * INCVALUE_n into the TIMINCA register allowing 32+8+(24-INCVALUE_SHIFT_n) + * bits to count nanoseconds leaving the rest for fractional nonseconds. ++ * ++ * Any given INCVALUE also has an associated maximum adjustment value. This ++ * maximum adjustment value is the largest increase (or decrease) which can be ++ * safely applied without overflowing the INCVALUE. Since INCVALUE has ++ * a maximum range of 24 bits, its largest value is 0xFFFFFF. ++ * ++ * To understand where the maximum value comes from, consider the following ++ * equation: ++ * ++ * new_incval = base_incval + (base_incval * adjustment) / 1billion ++ * ++ * To avoid overflow that means: ++ * max_incval = base_incval + (base_incval * max_adj) / billion ++ * ++ * Re-arranging: ++ * max_adj = floor(((max_incval - base_incval) * 1billion) / 1billion) + */ + #define INCVALUE_96MHZ 125 + #define INCVALUE_SHIFT_96MHZ 17 + #define INCPERIOD_SHIFT_96MHZ 2 + #define INCPERIOD_96MHZ (12 >> INCPERIOD_SHIFT_96MHZ) ++#define MAX_PPB_96MHZ 23999900 /* 23,999,900 ppb */ + + #define INCVALUE_25MHZ 40 + #define INCVALUE_SHIFT_25MHZ 18 + #define INCPERIOD_25MHZ 1 ++#define MAX_PPB_25MHZ 599999900 /* 599,999,900 ppb */ + + #define INCVALUE_24MHZ 125 + #define INCVALUE_SHIFT_24MHZ 14 + #define INCPERIOD_24MHZ 3 ++#define MAX_PPB_24MHZ 999999999 /* 999,999,999 ppb */ + + #define INCVALUE_38400KHZ 26 + #define INCVALUE_SHIFT_38400KHZ 19 + #define INCPERIOD_38400KHZ 1 ++#define MAX_PPB_38400KHZ 230769100 /* 230,769,100 ppb */ + + /* Another drawback of scaling the incvalue by a large factor is the + * 64-bit SYSTIM register overflows more quickly. This is dealt with +diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c +index 02d871bc112a..bbcfd529399b 100644 +--- a/drivers/net/ethernet/intel/e1000e/ptp.c ++++ b/drivers/net/ethernet/intel/e1000e/ptp.c +@@ -280,8 +280,17 @@ void e1000e_ptp_init(struct e1000_adapter *adapter) + + switch (hw->mac.type) { + case e1000_pch2lan: ++ adapter->ptp_clock_info.max_adj = MAX_PPB_96MHZ; ++ break; + case e1000_pch_lpt: ++ if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) ++ adapter->ptp_clock_info.max_adj = MAX_PPB_96MHZ; ++ else ++ adapter->ptp_clock_info.max_adj = MAX_PPB_25MHZ; ++ break; + case e1000_pch_spt: ++ adapter->ptp_clock_info.max_adj = MAX_PPB_24MHZ; ++ break; + case e1000_pch_cnp: + case e1000_pch_tgp: + case e1000_pch_adp: +@@ -289,15 +298,14 @@ void e1000e_ptp_init(struct e1000_adapter *adapter) + case e1000_pch_lnp: + case e1000_pch_ptp: + case e1000_pch_nvp: +- if ((hw->mac.type < e1000_pch_lpt) || +- (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)) { +- adapter->ptp_clock_info.max_adj = 24000000 - 1; +- break; +- } +- fallthrough; ++ if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) ++ adapter->ptp_clock_info.max_adj = MAX_PPB_24MHZ; ++ else ++ adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ; ++ break; + case e1000_82574: + case e1000_82583: +- adapter->ptp_clock_info.max_adj = 600000000 - 1; ++ adapter->ptp_clock_info.max_adj = MAX_PPB_25MHZ; + break; + default: + break; +-- +2.43.0 + diff --git a/queue-6.6/gve-fix-skb-truesize-underestimation.patch b/queue-6.6/gve-fix-skb-truesize-underestimation.patch new file mode 100644 index 00000000000..91ebe319bb0 --- /dev/null +++ b/queue-6.6/gve-fix-skb-truesize-underestimation.patch @@ -0,0 +1,60 @@ +From a136392c72e50b3986cc26c5cf834d4d0e1a0720 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 24 Jan 2024 08:10:25 -0800 +Subject: gve: Fix skb truesize underestimation + +From: Praveen Kaligineedi + +[ Upstream commit 534326711000c318fe1523c77308450522baa499 ] + +For a skb frag with a newly allocated copy page, the true size is +incorrectly set to packet buffer size. It should be set to PAGE_SIZE +instead. + +Fixes: 82fd151d38d9 ("gve: Reduce alloc and copy costs in the GQ rx path") +Signed-off-by: Praveen Kaligineedi +Link: https://lore.kernel.org/r/20240124161025.1819836-1-pkaligineedi@google.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/google/gve/gve_rx.c | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c +index 73655347902d..93ff7c8ec905 100644 +--- a/drivers/net/ethernet/google/gve/gve_rx.c ++++ b/drivers/net/ethernet/google/gve/gve_rx.c +@@ -362,7 +362,7 @@ static enum pkt_hash_types gve_rss_type(__be16 pkt_flags) + + static struct sk_buff *gve_rx_add_frags(struct napi_struct *napi, + struct gve_rx_slot_page_info *page_info, +- u16 packet_buffer_size, u16 len, ++ unsigned int truesize, u16 len, + struct gve_rx_ctx *ctx) + { + u32 offset = page_info->page_offset + page_info->pad; +@@ -395,10 +395,10 @@ static struct sk_buff *gve_rx_add_frags(struct napi_struct *napi, + if (skb != ctx->skb_head) { + ctx->skb_head->len += len; + ctx->skb_head->data_len += len; +- ctx->skb_head->truesize += packet_buffer_size; ++ ctx->skb_head->truesize += truesize; + } + skb_add_rx_frag(skb, num_frags, page_info->page, +- offset, len, packet_buffer_size); ++ offset, len, truesize); + + return ctx->skb_head; + } +@@ -492,7 +492,7 @@ static struct sk_buff *gve_rx_copy_to_pool(struct gve_rx_ring *rx, + + memcpy(alloc_page_info.page_address, src, page_info->pad + len); + skb = gve_rx_add_frags(napi, &alloc_page_info, +- rx->packet_buffer_size, ++ PAGE_SIZE, + len, ctx); + + u64_stats_update_begin(&rx->statss); +-- +2.43.0 + diff --git a/queue-6.6/hid-hidraw-fix-a-problem-of-memory-leak-in-hidraw_re.patch b/queue-6.6/hid-hidraw-fix-a-problem-of-memory-leak-in-hidraw_re.patch new file mode 100644 index 00000000000..59d3f691539 --- /dev/null +++ b/queue-6.6/hid-hidraw-fix-a-problem-of-memory-leak-in-hidraw_re.patch @@ -0,0 +1,43 @@ +From fa7fa451927ae3bbf99680655616640ed701b44e Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 25 Jan 2024 14:32:26 +0800 +Subject: HID: hidraw: fix a problem of memory leak in hidraw_release() + +From: Su Hui + +[ Upstream commit a3bdcdd022c68942a774e8e63424cc11c85aab78 ] + +'struct hidraw_list' is a circular queue whose head can be smaller than +tail. Using 'list->tail != list->head' to release all memory that should +be released. + +Fixes: a5623a203cff ("HID: hidraw: fix memory leak in hidraw_release()") +Signed-off-by: Su Hui +Reviewed-by: Dan Carpenter +Signed-off-by: Jiri Kosina +Signed-off-by: Sasha Levin +--- + drivers/hid/hidraw.c | 7 +++++-- + 1 file changed, 5 insertions(+), 2 deletions(-) + +diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c +index 13c8dd8cd350..2bc762d31ac7 100644 +--- a/drivers/hid/hidraw.c ++++ b/drivers/hid/hidraw.c +@@ -357,8 +357,11 @@ static int hidraw_release(struct inode * inode, struct file * file) + down_write(&minors_rwsem); + + spin_lock_irqsave(&hidraw_table[minor]->list_lock, flags); +- for (int i = list->tail; i < list->head; i++) +- kfree(list->buffer[i].value); ++ while (list->tail != list->head) { ++ kfree(list->buffer[list->tail].value); ++ list->buffer[list->tail].value = NULL; ++ list->tail = (list->tail + 1) & (HIDRAW_BUFFER_SIZE - 1); ++ } + list_del(&list->node); + spin_unlock_irqrestore(&hidraw_table[minor]->list_lock, flags); + kfree(list); +-- +2.43.0 + diff --git a/queue-6.6/ip6_tunnel-make-sure-to-pull-inner-header-in-__ip6_t.patch b/queue-6.6/ip6_tunnel-make-sure-to-pull-inner-header-in-__ip6_t.patch new file mode 100644 index 00000000000..d5622f3a350 --- /dev/null +++ b/queue-6.6/ip6_tunnel-make-sure-to-pull-inner-header-in-__ip6_t.patch @@ -0,0 +1,139 @@ +From 23ef75ff153a8563e7d44e06f2016e0a978b91fb Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 25 Jan 2024 17:05:57 +0000 +Subject: ip6_tunnel: make sure to pull inner header in __ip6_tnl_rcv() + +From: Eric Dumazet + +[ Upstream commit 8d975c15c0cd744000ca386247432d57b21f9df0 ] + +syzbot found __ip6_tnl_rcv() could access unitiliazed data [1]. + +Call pskb_inet_may_pull() to fix this, and initialize ipv6h +variable after this call as it can change skb->head. + +[1] + BUG: KMSAN: uninit-value in __INET_ECN_decapsulate include/net/inet_ecn.h:253 [inline] + BUG: KMSAN: uninit-value in INET_ECN_decapsulate include/net/inet_ecn.h:275 [inline] + BUG: KMSAN: uninit-value in IP6_ECN_decapsulate+0x7df/0x1e50 include/net/inet_ecn.h:321 + __INET_ECN_decapsulate include/net/inet_ecn.h:253 [inline] + INET_ECN_decapsulate include/net/inet_ecn.h:275 [inline] + IP6_ECN_decapsulate+0x7df/0x1e50 include/net/inet_ecn.h:321 + ip6ip6_dscp_ecn_decapsulate+0x178/0x1b0 net/ipv6/ip6_tunnel.c:727 + __ip6_tnl_rcv+0xd4e/0x1590 net/ipv6/ip6_tunnel.c:845 + ip6_tnl_rcv+0xce/0x100 net/ipv6/ip6_tunnel.c:888 + gre_rcv+0x143f/0x1870 + ip6_protocol_deliver_rcu+0xda6/0x2a60 net/ipv6/ip6_input.c:438 + ip6_input_finish net/ipv6/ip6_input.c:483 [inline] + NF_HOOK include/linux/netfilter.h:314 [inline] + ip6_input+0x15d/0x430 net/ipv6/ip6_input.c:492 + ip6_mc_input+0xa7e/0xc80 net/ipv6/ip6_input.c:586 + dst_input include/net/dst.h:461 [inline] + ip6_rcv_finish+0x5db/0x870 net/ipv6/ip6_input.c:79 + NF_HOOK include/linux/netfilter.h:314 [inline] + ipv6_rcv+0xda/0x390 net/ipv6/ip6_input.c:310 + __netif_receive_skb_one_core net/core/dev.c:5532 [inline] + __netif_receive_skb+0x1a6/0x5a0 net/core/dev.c:5646 + netif_receive_skb_internal net/core/dev.c:5732 [inline] + netif_receive_skb+0x58/0x660 net/core/dev.c:5791 + tun_rx_batched+0x3ee/0x980 drivers/net/tun.c:1555 + tun_get_user+0x53af/0x66d0 drivers/net/tun.c:2002 + tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2048 + call_write_iter include/linux/fs.h:2084 [inline] + new_sync_write fs/read_write.c:497 [inline] + vfs_write+0x786/0x1200 fs/read_write.c:590 + ksys_write+0x20f/0x4c0 fs/read_write.c:643 + __do_sys_write fs/read_write.c:655 [inline] + __se_sys_write fs/read_write.c:652 [inline] + __x64_sys_write+0x93/0xd0 fs/read_write.c:652 + do_syscall_x64 arch/x86/entry/common.c:52 [inline] + do_syscall_64+0x6d/0x140 arch/x86/entry/common.c:83 + entry_SYSCALL_64_after_hwframe+0x63/0x6b + +Uninit was created at: + slab_post_alloc_hook+0x129/0xa70 mm/slab.h:768 + slab_alloc_node mm/slub.c:3478 [inline] + kmem_cache_alloc_node+0x5e9/0xb10 mm/slub.c:3523 + kmalloc_reserve+0x13d/0x4a0 net/core/skbuff.c:560 + __alloc_skb+0x318/0x740 net/core/skbuff.c:651 + alloc_skb include/linux/skbuff.h:1286 [inline] + alloc_skb_with_frags+0xc8/0xbd0 net/core/skbuff.c:6334 + sock_alloc_send_pskb+0xa80/0xbf0 net/core/sock.c:2787 + tun_alloc_skb drivers/net/tun.c:1531 [inline] + tun_get_user+0x1e8a/0x66d0 drivers/net/tun.c:1846 + tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2048 + call_write_iter include/linux/fs.h:2084 [inline] + new_sync_write fs/read_write.c:497 [inline] + vfs_write+0x786/0x1200 fs/read_write.c:590 + ksys_write+0x20f/0x4c0 fs/read_write.c:643 + __do_sys_write fs/read_write.c:655 [inline] + __se_sys_write fs/read_write.c:652 [inline] + __x64_sys_write+0x93/0xd0 fs/read_write.c:652 + do_syscall_x64 arch/x86/entry/common.c:52 [inline] + do_syscall_64+0x6d/0x140 arch/x86/entry/common.c:83 + entry_SYSCALL_64_after_hwframe+0x63/0x6b + +CPU: 0 PID: 5034 Comm: syz-executor331 Not tainted 6.7.0-syzkaller-00562-g9f8413c4a66f #0 +Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023 + +Fixes: 0d3c703a9d17 ("ipv6: Cleanup IPv6 tunnel receive path") +Reported-by: syzbot +Signed-off-by: Eric Dumazet +Reviewed-by: Simon Horman +Link: https://lore.kernel.org/r/20240125170557.2663942-1-edumazet@google.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/ipv6/ip6_tunnel.c | 21 ++++++++++++++++++--- + 1 file changed, 18 insertions(+), 3 deletions(-) + +diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c +index 46c19bd48990..9bbabf750a21 100644 +--- a/net/ipv6/ip6_tunnel.c ++++ b/net/ipv6/ip6_tunnel.c +@@ -796,8 +796,8 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, + struct sk_buff *skb), + bool log_ecn_err) + { +- const struct ipv6hdr *ipv6h = ipv6_hdr(skb); +- int err; ++ const struct ipv6hdr *ipv6h; ++ int nh, err; + + if ((!(tpi->flags & TUNNEL_CSUM) && + (tunnel->parms.i_flags & TUNNEL_CSUM)) || +@@ -829,7 +829,6 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, + goto drop; + } + +- ipv6h = ipv6_hdr(skb); + skb->protocol = eth_type_trans(skb, tunnel->dev); + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); + } else { +@@ -837,7 +836,23 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, + skb_reset_mac_header(skb); + } + ++ /* Save offset of outer header relative to skb->head, ++ * because we are going to reset the network header to the inner header ++ * and might change skb->head. ++ */ ++ nh = skb_network_header(skb) - skb->head; ++ + skb_reset_network_header(skb); ++ ++ if (!pskb_inet_may_pull(skb)) { ++ DEV_STATS_INC(tunnel->dev, rx_length_errors); ++ DEV_STATS_INC(tunnel->dev, rx_errors); ++ goto drop; ++ } ++ ++ /* Get the outer header. */ ++ ipv6h = (struct ipv6hdr *)(skb->head + nh); ++ + memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); + + __skb_tunnel_rx(skb, tunnel->dev, tunnel->net); +-- +2.43.0 + diff --git a/queue-6.6/ipmr-fix-kernel-panic-when-forwarding-mcast-packets.patch b/queue-6.6/ipmr-fix-kernel-panic-when-forwarding-mcast-packets.patch new file mode 100644 index 00000000000..5a3980b3581 --- /dev/null +++ b/queue-6.6/ipmr-fix-kernel-panic-when-forwarding-mcast-packets.patch @@ -0,0 +1,170 @@ +From 89a198ff69fe47d43bd7f0bf1e3c7227db26a2e8 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 25 Jan 2024 15:18:47 +0100 +Subject: ipmr: fix kernel panic when forwarding mcast packets + +From: Nicolas Dichtel + +[ Upstream commit e622502c310f1069fd9f41cd38210553115f610a ] + +The stacktrace was: +[ 86.305548] BUG: kernel NULL pointer dereference, address: 0000000000000092 +[ 86.306815] #PF: supervisor read access in kernel mode +[ 86.307717] #PF: error_code(0x0000) - not-present page +[ 86.308624] PGD 0 P4D 0 +[ 86.309091] Oops: 0000 [#1] PREEMPT SMP NOPTI +[ 86.309883] CPU: 2 PID: 3139 Comm: pimd Tainted: G U 6.8.0-6wind-knet #1 +[ 86.311027] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.1-0-g0551a4be2c-prebuilt.qemu-project.org 04/01/2014 +[ 86.312728] RIP: 0010:ip_mr_forward (/build/work/knet/net/ipv4/ipmr.c:1985) +[ 86.313399] Code: f9 1f 0f 87 85 03 00 00 48 8d 04 5b 48 8d 04 83 49 8d 44 c5 00 48 8b 40 70 48 39 c2 0f 84 d9 00 00 00 49 8b 46 58 48 83 e0 fe <80> b8 92 00 00 00 00 0f 84 55 ff ff ff 49 83 47 38 01 45 85 e4 0f +[ 86.316565] RSP: 0018:ffffad21c0583ae0 EFLAGS: 00010246 +[ 86.317497] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 +[ 86.318596] RDX: ffff9559cb46c000 RSI: 0000000000000000 RDI: 0000000000000000 +[ 86.319627] RBP: ffffad21c0583b30 R08: 0000000000000000 R09: 0000000000000000 +[ 86.320650] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000001 +[ 86.321672] R13: ffff9559c093a000 R14: ffff9559cc00b800 R15: ffff9559c09c1d80 +[ 86.322873] FS: 00007f85db661980(0000) GS:ffff955a79d00000(0000) knlGS:0000000000000000 +[ 86.324291] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +[ 86.325314] CR2: 0000000000000092 CR3: 000000002f13a000 CR4: 0000000000350ef0 +[ 86.326589] Call Trace: +[ 86.327036] +[ 86.327434] ? show_regs (/build/work/knet/arch/x86/kernel/dumpstack.c:479) +[ 86.328049] ? __die (/build/work/knet/arch/x86/kernel/dumpstack.c:421 /build/work/knet/arch/x86/kernel/dumpstack.c:434) +[ 86.328508] ? page_fault_oops (/build/work/knet/arch/x86/mm/fault.c:707) +[ 86.329107] ? do_user_addr_fault (/build/work/knet/arch/x86/mm/fault.c:1264) +[ 86.329756] ? srso_return_thunk (/build/work/knet/arch/x86/lib/retpoline.S:223) +[ 86.330350] ? __irq_work_queue_local (/build/work/knet/kernel/irq_work.c:111 (discriminator 1)) +[ 86.331013] ? exc_page_fault (/build/work/knet/./arch/x86/include/asm/paravirt.h:693 /build/work/knet/arch/x86/mm/fault.c:1515 /build/work/knet/arch/x86/mm/fault.c:1563) +[ 86.331702] ? asm_exc_page_fault (/build/work/knet/./arch/x86/include/asm/idtentry.h:570) +[ 86.332468] ? ip_mr_forward (/build/work/knet/net/ipv4/ipmr.c:1985) +[ 86.333183] ? srso_return_thunk (/build/work/knet/arch/x86/lib/retpoline.S:223) +[ 86.333920] ipmr_mfc_add (/build/work/knet/./include/linux/rcupdate.h:782 /build/work/knet/net/ipv4/ipmr.c:1009 /build/work/knet/net/ipv4/ipmr.c:1273) +[ 86.334583] ? __pfx_ipmr_hash_cmp (/build/work/knet/net/ipv4/ipmr.c:363) +[ 86.335357] ip_mroute_setsockopt (/build/work/knet/net/ipv4/ipmr.c:1470) +[ 86.336135] ? srso_return_thunk (/build/work/knet/arch/x86/lib/retpoline.S:223) +[ 86.336854] ? ip_mroute_setsockopt (/build/work/knet/net/ipv4/ipmr.c:1470) +[ 86.337679] do_ip_setsockopt (/build/work/knet/net/ipv4/ip_sockglue.c:944) +[ 86.338408] ? __pfx_unix_stream_read_actor (/build/work/knet/net/unix/af_unix.c:2862) +[ 86.339232] ? srso_return_thunk (/build/work/knet/arch/x86/lib/retpoline.S:223) +[ 86.339809] ? aa_sk_perm (/build/work/knet/security/apparmor/include/cred.h:153 /build/work/knet/security/apparmor/net.c:181) +[ 86.340342] ip_setsockopt (/build/work/knet/net/ipv4/ip_sockglue.c:1415) +[ 86.340859] raw_setsockopt (/build/work/knet/net/ipv4/raw.c:836) +[ 86.341408] ? security_socket_setsockopt (/build/work/knet/security/security.c:4561 (discriminator 13)) +[ 86.342116] sock_common_setsockopt (/build/work/knet/net/core/sock.c:3716) +[ 86.342747] do_sock_setsockopt (/build/work/knet/net/socket.c:2313) +[ 86.343363] __sys_setsockopt (/build/work/knet/./include/linux/file.h:32 /build/work/knet/net/socket.c:2336) +[ 86.344020] __x64_sys_setsockopt (/build/work/knet/net/socket.c:2340) +[ 86.344766] do_syscall_64 (/build/work/knet/arch/x86/entry/common.c:52 /build/work/knet/arch/x86/entry/common.c:83) +[ 86.345433] ? srso_return_thunk (/build/work/knet/arch/x86/lib/retpoline.S:223) +[ 86.346161] ? syscall_exit_work (/build/work/knet/./include/linux/audit.h:357 /build/work/knet/kernel/entry/common.c:160) +[ 86.346938] ? srso_return_thunk (/build/work/knet/arch/x86/lib/retpoline.S:223) +[ 86.347657] ? syscall_exit_to_user_mode (/build/work/knet/kernel/entry/common.c:215) +[ 86.348538] ? srso_return_thunk (/build/work/knet/arch/x86/lib/retpoline.S:223) +[ 86.349262] ? do_syscall_64 (/build/work/knet/./arch/x86/include/asm/cpufeature.h:171 /build/work/knet/arch/x86/entry/common.c:98) +[ 86.349971] entry_SYSCALL_64_after_hwframe (/build/work/knet/arch/x86/entry/entry_64.S:129) + +The original packet in ipmr_cache_report() may be queued and then forwarded +with ip_mr_forward(). This last function has the assumption that the skb +dst is set. + +After the below commit, the skb dst is dropped by ipv4_pktinfo_prepare(), +which causes the oops. + +Fixes: bb7403655b3c ("ipmr: support IP_PKTINFO on cache report IGMP msg") +Signed-off-by: Nicolas Dichtel +Reviewed-by: Eric Dumazet +Link: https://lore.kernel.org/r/20240125141847.1931933-1-nicolas.dichtel@6wind.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + include/net/ip.h | 2 +- + net/ipv4/ip_sockglue.c | 6 ++++-- + net/ipv4/ipmr.c | 2 +- + net/ipv4/raw.c | 2 +- + net/ipv4/udp.c | 2 +- + 5 files changed, 8 insertions(+), 6 deletions(-) + +diff --git a/include/net/ip.h b/include/net/ip.h +index 3489a1cca5e7..162cf2d2f841 100644 +--- a/include/net/ip.h ++++ b/include/net/ip.h +@@ -758,7 +758,7 @@ int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev); + * Functions provided by ip_sockglue.c + */ + +-void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb); ++void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst); + void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb, int tlen, int offset); + int ip_cmsg_send(struct sock *sk, struct msghdr *msg, +diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c +index cce9cb25f3b3..1a6952921e07 100644 +--- a/net/ipv4/ip_sockglue.c ++++ b/net/ipv4/ip_sockglue.c +@@ -1369,12 +1369,13 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, + * ipv4_pktinfo_prepare - transfer some info from rtable to skb + * @sk: socket + * @skb: buffer ++ * @drop_dst: if true, drops skb dst + * + * To support IP_CMSG_PKTINFO option, we store rt_iif and specific + * destination in skb->cb[] before dst drop. + * This way, receiver doesn't make cache line misses to read rtable. + */ +-void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb) ++void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst) + { + struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb); + bool prepare = inet_test_bit(PKTINFO, sk) || +@@ -1403,7 +1404,8 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb) + pktinfo->ipi_ifindex = 0; + pktinfo->ipi_spec_dst.s_addr = 0; + } +- skb_dst_drop(skb); ++ if (drop_dst) ++ skb_dst_drop(skb); + } + + int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, +diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c +index 0063a237253b..e49242706b5f 100644 +--- a/net/ipv4/ipmr.c ++++ b/net/ipv4/ipmr.c +@@ -1073,7 +1073,7 @@ static int ipmr_cache_report(const struct mr_table *mrt, + msg = (struct igmpmsg *)skb_network_header(skb); + msg->im_vif = vifi; + msg->im_vif_hi = vifi >> 8; +- ipv4_pktinfo_prepare(mroute_sk, pkt); ++ ipv4_pktinfo_prepare(mroute_sk, pkt, false); + memcpy(skb->cb, pkt->cb, sizeof(skb->cb)); + /* Add our header */ + igmp = skb_put(skb, sizeof(struct igmphdr)); +diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c +index 4b5db5d1edc2..c0ef81f0bcee 100644 +--- a/net/ipv4/raw.c ++++ b/net/ipv4/raw.c +@@ -292,7 +292,7 @@ static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb) + + /* Charge it to the socket. */ + +- ipv4_pktinfo_prepare(sk, skb); ++ ipv4_pktinfo_prepare(sk, skb, true); + if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) { + kfree_skb_reason(skb, reason); + return NET_RX_DROP; +diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c +index 7be4ddc80d95..8e5a8b3b22c6 100644 +--- a/net/ipv4/udp.c ++++ b/net/ipv4/udp.c +@@ -2167,7 +2167,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) + + udp_csum_pull_header(skb); + +- ipv4_pktinfo_prepare(sk, skb); ++ ipv4_pktinfo_prepare(sk, skb, true); + return __udp_queue_rcv_skb(sk, skb); + + csum_error: +-- +2.43.0 + diff --git a/queue-6.6/ipv6-ensure-natural-alignment-of-const-ipv6-loopback.patch b/queue-6.6/ipv6-ensure-natural-alignment-of-const-ipv6-loopback.patch new file mode 100644 index 00000000000..fae61c98a38 --- /dev/null +++ b/queue-6.6/ipv6-ensure-natural-alignment-of-const-ipv6-loopback.patch @@ -0,0 +1,78 @@ +From 81b6d2d11b72f557766c69c160808a381cccc8be Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 26 Jan 2024 09:32:20 +0100 +Subject: ipv6: Ensure natural alignment of const ipv6 loopback and router + addresses + +From: Helge Deller + +[ Upstream commit 60365049ccbacd101654a66ddcb299abfabd4fc5 ] + +On a parisc64 kernel I sometimes notice this kernel warning: +Kernel unaligned access to 0x40ff8814 at ndisc_send_skb+0xc0/0x4d8 + +The address 0x40ff8814 points to the in6addr_linklocal_allrouters +variable and the warning simply means that some ipv6 function tries to +read a 64-bit word directly from the not-64-bit aligned +in6addr_linklocal_allrouters variable. + +Unaligned accesses are non-critical as the architecture or exception +handlers usually will fix it up at runtime. Nevertheless it may trigger +a performance penality for some architectures. For details read the +"unaligned-memory-access" kernel documentation. + +The patch below ensures that the ipv6 loopback and router addresses will +always be naturally aligned. This prevents the unaligned accesses for +all architectures. + +Signed-off-by: Helge Deller +Fixes: 034dfc5df99eb ("ipv6: export in6addr_loopback to modules") +Acked-by: Paolo Abeni +Link: https://lore.kernel.org/r/ZbNuFM1bFqoH-UoY@p100 +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/ipv6/addrconf_core.c | 21 ++++++++++++++------- + 1 file changed, 14 insertions(+), 7 deletions(-) + +diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c +index 507a8353a6bd..c008d21925d7 100644 +--- a/net/ipv6/addrconf_core.c ++++ b/net/ipv6/addrconf_core.c +@@ -220,19 +220,26 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { + EXPORT_SYMBOL_GPL(ipv6_stub); + + /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ +-const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT; ++const struct in6_addr in6addr_loopback __aligned(BITS_PER_LONG/8) ++ = IN6ADDR_LOOPBACK_INIT; + EXPORT_SYMBOL(in6addr_loopback); +-const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT; ++const struct in6_addr in6addr_any __aligned(BITS_PER_LONG/8) ++ = IN6ADDR_ANY_INIT; + EXPORT_SYMBOL(in6addr_any); +-const struct in6_addr in6addr_linklocal_allnodes = IN6ADDR_LINKLOCAL_ALLNODES_INIT; ++const struct in6_addr in6addr_linklocal_allnodes __aligned(BITS_PER_LONG/8) ++ = IN6ADDR_LINKLOCAL_ALLNODES_INIT; + EXPORT_SYMBOL(in6addr_linklocal_allnodes); +-const struct in6_addr in6addr_linklocal_allrouters = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; ++const struct in6_addr in6addr_linklocal_allrouters __aligned(BITS_PER_LONG/8) ++ = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; + EXPORT_SYMBOL(in6addr_linklocal_allrouters); +-const struct in6_addr in6addr_interfacelocal_allnodes = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; ++const struct in6_addr in6addr_interfacelocal_allnodes __aligned(BITS_PER_LONG/8) ++ = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; + EXPORT_SYMBOL(in6addr_interfacelocal_allnodes); +-const struct in6_addr in6addr_interfacelocal_allrouters = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; ++const struct in6_addr in6addr_interfacelocal_allrouters __aligned(BITS_PER_LONG/8) ++ = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; + EXPORT_SYMBOL(in6addr_interfacelocal_allrouters); +-const struct in6_addr in6addr_sitelocal_allrouters = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; ++const struct in6_addr in6addr_sitelocal_allrouters __aligned(BITS_PER_LONG/8) ++ = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; + EXPORT_SYMBOL(in6addr_sitelocal_allrouters); + + static void snmp6_free_dev(struct inet6_dev *idev) +-- +2.43.0 + diff --git a/queue-6.6/ixgbe-fix-an-error-handling-path-in-ixgbe_read_iosf_.patch b/queue-6.6/ixgbe-fix-an-error-handling-path-in-ixgbe_read_iosf_.patch new file mode 100644 index 00000000000..0bb20702e5e --- /dev/null +++ b/queue-6.6/ixgbe-fix-an-error-handling-path-in-ixgbe_read_iosf_.patch @@ -0,0 +1,44 @@ +From e60020b174f1f72f41b95759081b3e5d401bbd68 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sat, 20 Jan 2024 18:25:36 +0100 +Subject: ixgbe: Fix an error handling path in ixgbe_read_iosf_sb_reg_x550() + +From: Christophe JAILLET + +[ Upstream commit bbc404d20d1b46d89b461918bc44587620eda200 ] + +All error handling paths, except this one, go to 'out' where +release_swfw_sync() is called. +This call balances the acquire_swfw_sync() call done at the beginning of +the function. + +Branch to the error handling path in order to correctly release some +resources in case of error. + +Fixes: ae14a1d8e104 ("ixgbe: Fix IOSF SB access issues") +Signed-off-by: Christophe JAILLET +Reviewed-by: Simon Horman +Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) +Signed-off-by: Tony Nguyen +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +index fe2d2d2f0494..cdc912bba808 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +@@ -717,7 +717,8 @@ static s32 ixgbe_read_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr, + error = (command & IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK) >> + IXGBE_SB_IOSF_CTRL_CMPL_ERR_SHIFT; + hw_dbg(hw, "Failed to read, error %x\n", error); +- return -EIO; ++ ret = -EIO; ++ goto out; + } + + if (!ret) +-- +2.43.0 + diff --git a/queue-6.6/ixgbe-refactor-overtemp-event-handling.patch b/queue-6.6/ixgbe-refactor-overtemp-event-handling.patch new file mode 100644 index 00000000000..3df3a084407 --- /dev/null +++ b/queue-6.6/ixgbe-refactor-overtemp-event-handling.patch @@ -0,0 +1,293 @@ +From 4dbe1430932b42809f96ecf5ab329597ae1c64ab Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 18 Dec 2023 11:39:25 +0100 +Subject: ixgbe: Refactor overtemp event handling + +From: Jedrzej Jagielski + +[ Upstream commit 6c1b4af8c1b20c70dde01e58381685d6a4a1d2c8 ] + +Currently ixgbe driver is notified of overheating events +via internal IXGBE_ERR_OVERTEMP error code. + +Change the approach for handle_lasi() to use freshly introduced +is_overtemp function parameter which set when such event occurs. +Change check_overtemp() to bool and return true if overtemp +event occurs. + +Reviewed-by: Przemek Kitszel +Signed-off-by: Jedrzej Jagielski +Reviewed-by: Jacob Keller +Reviewed-by: Simon Horman +Tested-by: Sunitha Mekala (A Contingent worker at Intel) +Signed-off-by: Tony Nguyen +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 16 +++----- + drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c | 21 +++++----- + drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h | 2 +- + drivers/net/ethernet/intel/ixgbe/ixgbe_type.h | 4 +- + drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c | 41 +++++++++++-------- + 5 files changed, 43 insertions(+), 41 deletions(-) + +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +index f7c6482d6b63..9d4f808c4bfa 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +@@ -2756,7 +2756,6 @@ static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter) + { + struct ixgbe_hw *hw = &adapter->hw; + u32 eicr = adapter->interrupt_event; +- s32 rc; + + if (test_bit(__IXGBE_DOWN, &adapter->state)) + return; +@@ -2790,14 +2789,13 @@ static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter) + } + + /* Check if this is not due to overtemp */ +- if (hw->phy.ops.check_overtemp(hw) != IXGBE_ERR_OVERTEMP) ++ if (!hw->phy.ops.check_overtemp(hw)) + return; + + break; + case IXGBE_DEV_ID_X550EM_A_1G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T_L: +- rc = hw->phy.ops.check_overtemp(hw); +- if (rc != IXGBE_ERR_OVERTEMP) ++ if (!hw->phy.ops.check_overtemp(hw)) + return; + break; + default: +@@ -7938,7 +7936,7 @@ static void ixgbe_service_timer(struct timer_list *t) + static void ixgbe_phy_interrupt_subtask(struct ixgbe_adapter *adapter) + { + struct ixgbe_hw *hw = &adapter->hw; +- u32 status; ++ bool overtemp; + + if (!(adapter->flags2 & IXGBE_FLAG2_PHY_INTERRUPT)) + return; +@@ -7948,11 +7946,9 @@ static void ixgbe_phy_interrupt_subtask(struct ixgbe_adapter *adapter) + if (!hw->phy.ops.handle_lasi) + return; + +- status = hw->phy.ops.handle_lasi(&adapter->hw); +- if (status != IXGBE_ERR_OVERTEMP) +- return; +- +- e_crit(drv, "%s\n", ixgbe_overheat_msg); ++ hw->phy.ops.handle_lasi(&adapter->hw, &overtemp); ++ if (overtemp) ++ e_crit(drv, "%s\n", ixgbe_overheat_msg); + } + + static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter) +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +index 7c0a1a0a5eda..930dc5071936 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +@@ -408,8 +408,7 @@ s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw) + return status; + + /* Don't reset PHY if it's shut down due to overtemp. */ +- if (!hw->phy.reset_if_overtemp && +- (IXGBE_ERR_OVERTEMP == hw->phy.ops.check_overtemp(hw))) ++ if (!hw->phy.reset_if_overtemp && hw->phy.ops.check_overtemp(hw)) + return 0; + + /* Blocked by MNG FW so bail */ +@@ -2748,22 +2747,24 @@ static void ixgbe_i2c_bus_clear(struct ixgbe_hw *hw) + * @hw: pointer to hardware structure + * + * Checks if the LASI temp alarm status was triggered due to overtemp ++ * ++ * Return true when an overtemp event detected, otherwise false. + **/ +-s32 ixgbe_tn_check_overtemp(struct ixgbe_hw *hw) ++bool ixgbe_tn_check_overtemp(struct ixgbe_hw *hw) + { + u16 phy_data = 0; ++ u32 status; + + if (hw->device_id != IXGBE_DEV_ID_82599_T3_LOM) +- return 0; ++ return false; + + /* Check that the LASI temp alarm status was triggered */ +- hw->phy.ops.read_reg(hw, IXGBE_TN_LASI_STATUS_REG, +- MDIO_MMD_PMAPMD, &phy_data); +- +- if (!(phy_data & IXGBE_TN_LASI_STATUS_TEMP_ALARM)) +- return 0; ++ status = hw->phy.ops.read_reg(hw, IXGBE_TN_LASI_STATUS_REG, ++ MDIO_MMD_PMAPMD, &phy_data); ++ if (status) ++ return false; + +- return IXGBE_ERR_OVERTEMP; ++ return !!(phy_data & IXGBE_TN_LASI_STATUS_TEMP_ALARM); + } + + /** ixgbe_set_copper_phy_power - Control power for copper phy +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h +index 6544c4539c0d..ef72729d7c93 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h +@@ -155,7 +155,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw); + s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, + u16 *list_offset, + u16 *data_offset); +-s32 ixgbe_tn_check_overtemp(struct ixgbe_hw *hw); ++bool ixgbe_tn_check_overtemp(struct ixgbe_hw *hw); + s32 ixgbe_read_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 *data); + s32 ixgbe_read_i2c_byte_generic_unlocked(struct ixgbe_hw *hw, u8 byte_offset, +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +index 4b19b1282f28..61b9774b3d31 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +@@ -3509,10 +3509,10 @@ struct ixgbe_phy_operations { + s32 (*read_i2c_sff8472)(struct ixgbe_hw *, u8 , u8 *); + s32 (*read_i2c_eeprom)(struct ixgbe_hw *, u8 , u8 *); + s32 (*write_i2c_eeprom)(struct ixgbe_hw *, u8, u8); +- s32 (*check_overtemp)(struct ixgbe_hw *); ++ bool (*check_overtemp)(struct ixgbe_hw *); + s32 (*set_phy_power)(struct ixgbe_hw *, bool on); + s32 (*enter_lplu)(struct ixgbe_hw *); +- s32 (*handle_lasi)(struct ixgbe_hw *hw); ++ s32 (*handle_lasi)(struct ixgbe_hw *hw, bool *); + s32 (*read_i2c_byte_unlocked)(struct ixgbe_hw *, u8 offset, u8 addr, + u8 *value); + s32 (*write_i2c_byte_unlocked)(struct ixgbe_hw *, u8 offset, u8 addr, +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +index 19de26520a88..fe2d2d2f0494 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +@@ -600,8 +600,10 @@ static s32 ixgbe_setup_fw_link(struct ixgbe_hw *hw) + rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_SETUP_LINK, &setup); + if (rc) + return rc; ++ + if (setup[0] == FW_PHY_ACT_SETUP_LINK_RSP_DOWN) +- return IXGBE_ERR_OVERTEMP; ++ return -EIO; ++ + return 0; + } + +@@ -2369,18 +2371,18 @@ static s32 ixgbe_get_link_capabilities_X550em(struct ixgbe_hw *hw, + * @hw: pointer to hardware structure + * @lsc: pointer to boolean flag which indicates whether external Base T + * PHY interrupt is lsc ++ * @is_overtemp: indicate whether an overtemp event encountered + * + * Determime if external Base T PHY interrupt cause is high temperature + * failure alarm or link status change. +- * +- * Return IXGBE_ERR_OVERTEMP if interrupt is high temperature +- * failure alarm, else return PHY access status. + **/ +-static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc) ++static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc, ++ bool *is_overtemp) + { + u32 status; + u16 reg; + ++ *is_overtemp = false; + *lsc = false; + + /* Vendor alarm triggered */ +@@ -2412,7 +2414,8 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc) + if (reg & IXGBE_MDIO_GLOBAL_ALM_1_HI_TMP_FAIL) { + /* power down the PHY in case the PHY FW didn't already */ + ixgbe_set_copper_phy_power(hw, false); +- return IXGBE_ERR_OVERTEMP; ++ *is_overtemp = true; ++ return -EIO; + } + if (reg & IXGBE_MDIO_GLOBAL_ALM_1_DEV_FAULT) { + /* device fault alarm triggered */ +@@ -2426,7 +2429,8 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc) + if (reg == IXGBE_MDIO_GLOBAL_FAULT_MSG_HI_TMP) { + /* power down the PHY in case the PHY FW didn't */ + ixgbe_set_copper_phy_power(hw, false); +- return IXGBE_ERR_OVERTEMP; ++ *is_overtemp = true; ++ return -EIO; + } + } + +@@ -2462,12 +2466,12 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc) + **/ + static s32 ixgbe_enable_lasi_ext_t_x550em(struct ixgbe_hw *hw) + { ++ bool lsc, overtemp; + u32 status; + u16 reg; +- bool lsc; + + /* Clear interrupt flags */ +- status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc); ++ status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc, &overtemp); + + /* Enable link status change alarm */ + +@@ -2546,21 +2550,20 @@ static s32 ixgbe_enable_lasi_ext_t_x550em(struct ixgbe_hw *hw) + /** + * ixgbe_handle_lasi_ext_t_x550em - Handle external Base T PHY interrupt + * @hw: pointer to hardware structure ++ * @is_overtemp: indicate whether an overtemp event encountered + * + * Handle external Base T PHY interrupt. If high temperature + * failure alarm then return error, else if link status change + * then setup internal/external PHY link +- * +- * Return IXGBE_ERR_OVERTEMP if interrupt is high temperature +- * failure alarm, else return PHY access status. + **/ +-static s32 ixgbe_handle_lasi_ext_t_x550em(struct ixgbe_hw *hw) ++static s32 ixgbe_handle_lasi_ext_t_x550em(struct ixgbe_hw *hw, ++ bool *is_overtemp) + { + struct ixgbe_phy_info *phy = &hw->phy; + bool lsc; + u32 status; + +- status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc); ++ status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc, is_overtemp); + if (status) + return status; + +@@ -3188,21 +3191,23 @@ static s32 ixgbe_reset_phy_fw(struct ixgbe_hw *hw) + /** + * ixgbe_check_overtemp_fw - Check firmware-controlled PHYs for overtemp + * @hw: pointer to hardware structure ++ * ++ * Return true when an overtemp event detected, otherwise false. + */ +-static s32 ixgbe_check_overtemp_fw(struct ixgbe_hw *hw) ++static bool ixgbe_check_overtemp_fw(struct ixgbe_hw *hw) + { + u32 store[FW_PHY_ACT_DATA_COUNT] = { 0 }; + s32 rc; + + rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_GET_LINK_INFO, &store); + if (rc) +- return rc; ++ return false; + + if (store[0] & FW_PHY_ACT_GET_LINK_INFO_TEMP) { + ixgbe_shutdown_fw_phy(hw); +- return IXGBE_ERR_OVERTEMP; ++ return true; + } +- return 0; ++ return false; + } + + /** +-- +2.43.0 + diff --git a/queue-6.6/ixgbe-refactor-returning-internal-error-codes.patch b/queue-6.6/ixgbe-refactor-returning-internal-error-codes.patch new file mode 100644 index 00000000000..fff6dd0dbc9 --- /dev/null +++ b/queue-6.6/ixgbe-refactor-returning-internal-error-codes.patch @@ -0,0 +1,2369 @@ +From 6215781929fe2dbe7d1c6ab1349d4c2c5c5fe548 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 18 Dec 2023 11:39:26 +0100 +Subject: ixgbe: Refactor returning internal error codes + +From: Jedrzej Jagielski + +[ Upstream commit 5795f533f30a80aa0473652876296ebc9129e33a ] + +Change returning codes to the kernel ones instead of +the internal ones for the entire ixgbe driver. + +Reviewed-by: Jacob Keller +Reviewed-by: Przemek Kitszel +Reviewed-by: Simon Horman +Signed-off-by: Jedrzej Jagielski +Tested-by: Sunitha Mekala (A Contingent worker at Intel) +Signed-off-by: Tony Nguyen +Stable-dep-of: bbc404d20d1b ("ixgbe: Fix an error handling path in ixgbe_read_iosf_sb_reg_x550()") +Signed-off-by: Sasha Levin +--- + .../net/ethernet/intel/ixgbe/ixgbe_82598.c | 36 ++--- + .../net/ethernet/intel/ixgbe/ixgbe_82599.c | 61 ++++---- + .../net/ethernet/intel/ixgbe/ixgbe_common.c | 145 ++++++++---------- + .../net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 2 +- + drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 26 ++-- + drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c | 34 ++-- + drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h | 1 - + drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c | 84 +++++----- + .../net/ethernet/intel/ixgbe/ixgbe_sriov.c | 2 +- + drivers/net/ethernet/intel/ixgbe/ixgbe_type.h | 39 ----- + drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c | 44 +++--- + drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c | 107 +++++++------ + 12 files changed, 264 insertions(+), 317 deletions(-) + +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c +index 100388968e4d..3d56481e16bc 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c +@@ -123,14 +123,14 @@ static s32 ixgbe_init_phy_ops_82598(struct ixgbe_hw *hw) + if (ret_val) + return ret_val; + if (hw->phy.sfp_type == ixgbe_sfp_type_unknown) +- return IXGBE_ERR_SFP_NOT_SUPPORTED; ++ return -EOPNOTSUPP; + + /* Check to see if SFP+ module is supported */ + ret_val = ixgbe_get_sfp_init_sequence_offsets(hw, + &list_offset, + &data_offset); + if (ret_val) +- return IXGBE_ERR_SFP_NOT_SUPPORTED; ++ return -EOPNOTSUPP; + break; + default: + break; +@@ -213,7 +213,7 @@ static s32 ixgbe_get_link_capabilities_82598(struct ixgbe_hw *hw, + break; + + default: +- return IXGBE_ERR_LINK_SETUP; ++ return -EIO; + } + + return 0; +@@ -283,7 +283,7 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw) + + /* Validate the water mark configuration */ + if (!hw->fc.pause_time) +- return IXGBE_ERR_INVALID_LINK_SETTINGS; ++ return -EINVAL; + + /* Low water mark of zero causes XOFF floods */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { +@@ -292,7 +292,7 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw) + if (!hw->fc.low_water[i] || + hw->fc.low_water[i] >= hw->fc.high_water[i]) { + hw_dbg(hw, "Invalid water mark configuration\n"); +- return IXGBE_ERR_INVALID_LINK_SETTINGS; ++ return -EINVAL; + } + } + } +@@ -369,7 +369,7 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw) + break; + default: + hw_dbg(hw, "Flow control param set incorrectly\n"); +- return IXGBE_ERR_CONFIG; ++ return -EIO; + } + + /* Set 802.3x based flow control settings. */ +@@ -438,7 +438,7 @@ static s32 ixgbe_start_mac_link_82598(struct ixgbe_hw *hw, + msleep(100); + } + if (!(links_reg & IXGBE_LINKS_KX_AN_COMP)) { +- status = IXGBE_ERR_AUTONEG_NOT_COMPLETE; ++ status = -EIO; + hw_dbg(hw, "Autonegotiation did not complete.\n"); + } + } +@@ -478,7 +478,7 @@ static s32 ixgbe_validate_link_ready(struct ixgbe_hw *hw) + + if (timeout == IXGBE_VALIDATE_LINK_READY_TIMEOUT) { + hw_dbg(hw, "Link was indicated but link is down\n"); +- return IXGBE_ERR_LINK_SETUP; ++ return -EIO; + } + + return 0; +@@ -594,7 +594,7 @@ static s32 ixgbe_setup_mac_link_82598(struct ixgbe_hw *hw, + speed &= link_capabilities; + + if (speed == IXGBE_LINK_SPEED_UNKNOWN) +- return IXGBE_ERR_LINK_SETUP; ++ return -EINVAL; + + /* Set KX4/KX support according to speed requested */ + else if (link_mode == IXGBE_AUTOC_LMS_KX4_AN || +@@ -701,9 +701,9 @@ static s32 ixgbe_reset_hw_82598(struct ixgbe_hw *hw) + + /* Init PHY and function pointers, perform SFP setup */ + phy_status = hw->phy.ops.init(hw); +- if (phy_status == IXGBE_ERR_SFP_NOT_SUPPORTED) ++ if (phy_status == -EOPNOTSUPP) + return phy_status; +- if (phy_status == IXGBE_ERR_SFP_NOT_PRESENT) ++ if (phy_status == -ENOENT) + goto mac_reset_top; + + hw->phy.ops.reset(hw); +@@ -727,7 +727,7 @@ static s32 ixgbe_reset_hw_82598(struct ixgbe_hw *hw) + udelay(1); + } + if (ctrl & IXGBE_CTRL_RST) { +- status = IXGBE_ERR_RESET_FAILED; ++ status = -EIO; + hw_dbg(hw, "Reset polling failed to complete.\n"); + } + +@@ -789,7 +789,7 @@ static s32 ixgbe_set_vmdq_82598(struct ixgbe_hw *hw, u32 rar, u32 vmdq) + /* Make sure we are using a valid rar index range */ + if (rar >= rar_entries) { + hw_dbg(hw, "RAR index %d is out of range.\n", rar); +- return IXGBE_ERR_INVALID_ARGUMENT; ++ return -EINVAL; + } + + rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(rar)); +@@ -814,7 +814,7 @@ static s32 ixgbe_clear_vmdq_82598(struct ixgbe_hw *hw, u32 rar, u32 vmdq) + /* Make sure we are using a valid rar index range */ + if (rar >= rar_entries) { + hw_dbg(hw, "RAR index %d is out of range.\n", rar); +- return IXGBE_ERR_INVALID_ARGUMENT; ++ return -EINVAL; + } + + rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(rar)); +@@ -845,7 +845,7 @@ static s32 ixgbe_set_vfta_82598(struct ixgbe_hw *hw, u32 vlan, u32 vind, + u32 vftabyte; + + if (vlan > 4095) +- return IXGBE_ERR_PARAM; ++ return -EINVAL; + + /* Determine 32-bit word position in array */ + regindex = (vlan >> 5) & 0x7F; /* upper seven bits */ +@@ -964,7 +964,7 @@ static s32 ixgbe_read_i2c_phy_82598(struct ixgbe_hw *hw, u8 dev_addr, + gssr = IXGBE_GSSR_PHY0_SM; + + if (hw->mac.ops.acquire_swfw_sync(hw, gssr) != 0) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + + if (hw->phy.type == ixgbe_phy_nl) { + /* +@@ -993,7 +993,7 @@ static s32 ixgbe_read_i2c_phy_82598(struct ixgbe_hw *hw, u8 dev_addr, + + if (sfp_stat != IXGBE_I2C_EEPROM_STATUS_PASS) { + hw_dbg(hw, "EEPROM read did not pass.\n"); +- status = IXGBE_ERR_SFP_NOT_PRESENT; ++ status = -ENOENT; + goto out; + } + +@@ -1003,7 +1003,7 @@ static s32 ixgbe_read_i2c_phy_82598(struct ixgbe_hw *hw, u8 dev_addr, + + *eeprom_data = (u8)(sfp_data >> 8); + } else { +- status = IXGBE_ERR_PHY; ++ status = -EIO; + } + + out: +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +index 58ea959a4482..339e106a5732 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +@@ -117,7 +117,7 @@ static s32 ixgbe_setup_sfp_modules_82599(struct ixgbe_hw *hw) + ret_val = hw->mac.ops.acquire_swfw_sync(hw, + IXGBE_GSSR_MAC_CSR_SM); + if (ret_val) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + + if (hw->eeprom.ops.read(hw, ++data_offset, &data_value)) + goto setup_sfp_err; +@@ -144,7 +144,7 @@ static s32 ixgbe_setup_sfp_modules_82599(struct ixgbe_hw *hw) + + if (ret_val) { + hw_dbg(hw, " sfp module setup not complete\n"); +- return IXGBE_ERR_SFP_SETUP_NOT_COMPLETE; ++ return -EIO; + } + } + +@@ -159,7 +159,7 @@ static s32 ixgbe_setup_sfp_modules_82599(struct ixgbe_hw *hw) + usleep_range(hw->eeprom.semaphore_delay * 1000, + hw->eeprom.semaphore_delay * 2000); + hw_err(hw, "eeprom read at offset %d failed\n", data_offset); +- return IXGBE_ERR_SFP_SETUP_NOT_COMPLETE; ++ return -EIO; + } + + /** +@@ -184,7 +184,7 @@ static s32 prot_autoc_read_82599(struct ixgbe_hw *hw, bool *locked, + ret_val = hw->mac.ops.acquire_swfw_sync(hw, + IXGBE_GSSR_MAC_CSR_SM); + if (ret_val) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + + *locked = true; + } +@@ -219,7 +219,7 @@ static s32 prot_autoc_write_82599(struct ixgbe_hw *hw, u32 autoc, bool locked) + ret_val = hw->mac.ops.acquire_swfw_sync(hw, + IXGBE_GSSR_MAC_CSR_SM); + if (ret_val) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + + locked = true; + } +@@ -400,7 +400,7 @@ static s32 ixgbe_get_link_capabilities_82599(struct ixgbe_hw *hw, + break; + + default: +- return IXGBE_ERR_LINK_SETUP; ++ return -EIO; + } + + if (hw->phy.multispeed_fiber) { +@@ -541,7 +541,7 @@ static s32 ixgbe_start_mac_link_82599(struct ixgbe_hw *hw, + msleep(100); + } + if (!(links_reg & IXGBE_LINKS_KX_AN_COMP)) { +- status = IXGBE_ERR_AUTONEG_NOT_COMPLETE; ++ status = -EIO; + hw_dbg(hw, "Autoneg did not complete.\n"); + } + } +@@ -794,7 +794,7 @@ static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw, + speed &= link_capabilities; + + if (speed == IXGBE_LINK_SPEED_UNKNOWN) +- return IXGBE_ERR_LINK_SETUP; ++ return -EINVAL; + + /* Use stored value (EEPROM defaults) of AUTOC to find KR/KX4 support*/ + if (hw->mac.orig_link_settings_stored) +@@ -861,8 +861,7 @@ static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw, + msleep(100); + } + if (!(links_reg & IXGBE_LINKS_KX_AN_COMP)) { +- status = +- IXGBE_ERR_AUTONEG_NOT_COMPLETE; ++ status = -EIO; + hw_dbg(hw, "Autoneg did not complete.\n"); + } + } +@@ -927,7 +926,7 @@ static s32 ixgbe_reset_hw_82599(struct ixgbe_hw *hw) + /* Identify PHY and related function pointers */ + status = hw->phy.ops.init(hw); + +- if (status == IXGBE_ERR_SFP_NOT_SUPPORTED) ++ if (status == -EOPNOTSUPP) + return status; + + /* Setup SFP module if there is one present. */ +@@ -936,7 +935,7 @@ static s32 ixgbe_reset_hw_82599(struct ixgbe_hw *hw) + hw->phy.sfp_setup_needed = false; + } + +- if (status == IXGBE_ERR_SFP_NOT_SUPPORTED) ++ if (status == -EOPNOTSUPP) + return status; + + /* Reset PHY */ +@@ -974,7 +973,7 @@ static s32 ixgbe_reset_hw_82599(struct ixgbe_hw *hw) + } + + if (ctrl & IXGBE_CTRL_RST_MASK) { +- status = IXGBE_ERR_RESET_FAILED; ++ status = -EIO; + hw_dbg(hw, "Reset polling failed to complete.\n"); + } + +@@ -1093,7 +1092,7 @@ static s32 ixgbe_fdir_check_cmd_complete(struct ixgbe_hw *hw, u32 *fdircmd) + udelay(10); + } + +- return IXGBE_ERR_FDIR_CMD_INCOMPLETE; ++ return -EIO; + } + + /** +@@ -1155,7 +1154,7 @@ s32 ixgbe_reinit_fdir_tables_82599(struct ixgbe_hw *hw) + } + if (i >= IXGBE_FDIR_INIT_DONE_POLL) { + hw_dbg(hw, "Flow Director Signature poll time exceeded!\n"); +- return IXGBE_ERR_FDIR_REINIT_FAILED; ++ return -EIO; + } + + /* Clear FDIR statistics registers (read to clear) */ +@@ -1387,7 +1386,7 @@ s32 ixgbe_fdir_add_signature_filter_82599(struct ixgbe_hw *hw, + break; + default: + hw_dbg(hw, " Error on flow type input\n"); +- return IXGBE_ERR_CONFIG; ++ return -EIO; + } + + /* configure FDIRCMD register */ +@@ -1546,7 +1545,7 @@ s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, + break; + default: + hw_dbg(hw, " Error on vm pool mask\n"); +- return IXGBE_ERR_CONFIG; ++ return -EIO; + } + + switch (input_mask->formatted.flow_type & IXGBE_ATR_L4TYPE_MASK) { +@@ -1555,14 +1554,14 @@ s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, + if (input_mask->formatted.dst_port || + input_mask->formatted.src_port) { + hw_dbg(hw, " Error on src/dst port mask\n"); +- return IXGBE_ERR_CONFIG; ++ return -EIO; + } + break; + case IXGBE_ATR_L4TYPE_MASK: + break; + default: + hw_dbg(hw, " Error on flow type mask\n"); +- return IXGBE_ERR_CONFIG; ++ return -EIO; + } + + switch (ntohs(input_mask->formatted.vlan_id) & 0xEFFF) { +@@ -1583,7 +1582,7 @@ s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, + break; + default: + hw_dbg(hw, " Error on VLAN mask\n"); +- return IXGBE_ERR_CONFIG; ++ return -EIO; + } + + switch ((__force u16)input_mask->formatted.flex_bytes & 0xFFFF) { +@@ -1595,7 +1594,7 @@ s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, + break; + default: + hw_dbg(hw, " Error on flexible byte mask\n"); +- return IXGBE_ERR_CONFIG; ++ return -EIO; + } + + /* Now mask VM pool and destination IPv6 - bits 5 and 2 */ +@@ -1824,7 +1823,7 @@ static s32 ixgbe_identify_phy_82599(struct ixgbe_hw *hw) + + /* Return error if SFP module has been detected but is not supported */ + if (hw->phy.type == ixgbe_phy_sfp_unsupported) +- return IXGBE_ERR_SFP_NOT_SUPPORTED; ++ return -EOPNOTSUPP; + + return status; + } +@@ -1863,13 +1862,13 @@ static s32 ixgbe_enable_rx_dma_82599(struct ixgbe_hw *hw, u32 regval) + * Verifies that installed the firmware version is 0.6 or higher + * for SFI devices. All 82599 SFI devices should have version 0.6 or higher. + * +- * Returns IXGBE_ERR_EEPROM_VERSION if the FW is not present or +- * if the FW version is not supported. ++ * Return: -EACCES if the FW is not present or if the FW version is ++ * not supported. + **/ + static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw) + { +- s32 status = IXGBE_ERR_EEPROM_VERSION; + u16 fw_offset, fw_ptp_cfg_offset; ++ s32 status = -EACCES; + u16 offset; + u16 fw_version = 0; + +@@ -1883,7 +1882,7 @@ static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw) + goto fw_version_err; + + if (fw_offset == 0 || fw_offset == 0xFFFF) +- return IXGBE_ERR_EEPROM_VERSION; ++ return -EACCES; + + /* get the offset to the Pass Through Patch Configuration block */ + offset = fw_offset + IXGBE_FW_PASSTHROUGH_PATCH_CONFIG_PTR; +@@ -1891,7 +1890,7 @@ static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw) + goto fw_version_err; + + if (fw_ptp_cfg_offset == 0 || fw_ptp_cfg_offset == 0xFFFF) +- return IXGBE_ERR_EEPROM_VERSION; ++ return -EACCES; + + /* get the firmware version */ + offset = fw_ptp_cfg_offset + IXGBE_FW_PATCH_VERSION_4; +@@ -1905,7 +1904,7 @@ static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw) + + fw_version_err: + hw_err(hw, "eeprom read at offset %d failed\n", offset); +- return IXGBE_ERR_EEPROM_VERSION; ++ return -EACCES; + } + + /** +@@ -2038,7 +2037,7 @@ static s32 ixgbe_reset_pipeline_82599(struct ixgbe_hw *hw) + + if (!(anlp1_reg & IXGBE_ANLP1_AN_STATE_MASK)) { + hw_dbg(hw, "auto negotiation not completed\n"); +- ret_val = IXGBE_ERR_RESET_FAILED; ++ ret_val = -EIO; + goto reset_pipeline_out; + } + +@@ -2087,7 +2086,7 @@ static s32 ixgbe_read_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, + + if (!timeout) { + hw_dbg(hw, "Driver can't access resource, acquiring I2C bus timeout.\n"); +- status = IXGBE_ERR_I2C; ++ status = -EIO; + goto release_i2c_access; + } + } +@@ -2141,7 +2140,7 @@ static s32 ixgbe_write_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, + + if (!timeout) { + hw_dbg(hw, "Driver can't access resource, acquiring I2C bus timeout.\n"); +- status = IXGBE_ERR_I2C; ++ status = -EIO; + goto release_i2c_access; + } + } +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +index 878dd8dff528..b2a0f2aaa05b 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +@@ -124,7 +124,7 @@ s32 ixgbe_setup_fc_generic(struct ixgbe_hw *hw) + */ + if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { + hw_dbg(hw, "ixgbe_fc_rx_pause not valid in strict IEEE mode\n"); +- return IXGBE_ERR_INVALID_LINK_SETTINGS; ++ return -EINVAL; + } + + /* +@@ -215,7 +215,7 @@ s32 ixgbe_setup_fc_generic(struct ixgbe_hw *hw) + break; + default: + hw_dbg(hw, "Flow control param set incorrectly\n"); +- return IXGBE_ERR_CONFIG; ++ return -EIO; + } + + if (hw->mac.type != ixgbe_mac_X540) { +@@ -500,7 +500,7 @@ s32 ixgbe_read_pba_string_generic(struct ixgbe_hw *hw, u8 *pba_num, + + if (pba_num == NULL) { + hw_dbg(hw, "PBA string buffer was null\n"); +- return IXGBE_ERR_INVALID_ARGUMENT; ++ return -EINVAL; + } + + ret_val = hw->eeprom.ops.read(hw, IXGBE_PBANUM0_PTR, &data); +@@ -526,7 +526,7 @@ s32 ixgbe_read_pba_string_generic(struct ixgbe_hw *hw, u8 *pba_num, + /* we will need 11 characters to store the PBA */ + if (pba_num_size < 11) { + hw_dbg(hw, "PBA string buffer too small\n"); +- return IXGBE_ERR_NO_SPACE; ++ return -ENOSPC; + } + + /* extract hex string from data and pba_ptr */ +@@ -563,13 +563,13 @@ s32 ixgbe_read_pba_string_generic(struct ixgbe_hw *hw, u8 *pba_num, + + if (length == 0xFFFF || length == 0) { + hw_dbg(hw, "NVM PBA number section invalid length\n"); +- return IXGBE_ERR_PBA_SECTION; ++ return -EIO; + } + + /* check if pba_num buffer is big enough */ + if (pba_num_size < (((u32)length * 2) - 1)) { + hw_dbg(hw, "PBA string buffer too small\n"); +- return IXGBE_ERR_NO_SPACE; ++ return -ENOSPC; + } + + /* trim pba length from start of string */ +@@ -805,7 +805,7 @@ s32 ixgbe_led_on_generic(struct ixgbe_hw *hw, u32 index) + u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); + + if (index > 3) +- return IXGBE_ERR_PARAM; ++ return -EINVAL; + + /* To turn on the LED, set mode to ON. */ + led_reg &= ~IXGBE_LED_MODE_MASK(index); +@@ -826,7 +826,7 @@ s32 ixgbe_led_off_generic(struct ixgbe_hw *hw, u32 index) + u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); + + if (index > 3) +- return IXGBE_ERR_PARAM; ++ return -EINVAL; + + /* To turn off the LED, set mode to OFF. */ + led_reg &= ~IXGBE_LED_MODE_MASK(index); +@@ -904,11 +904,8 @@ s32 ixgbe_write_eeprom_buffer_bit_bang_generic(struct ixgbe_hw *hw, u16 offset, + + hw->eeprom.ops.init_params(hw); + +- if (words == 0) +- return IXGBE_ERR_INVALID_ARGUMENT; +- +- if (offset + words > hw->eeprom.word_size) +- return IXGBE_ERR_EEPROM; ++ if (words == 0 || (offset + words > hw->eeprom.word_size)) ++ return -EINVAL; + + /* + * The EEPROM page size cannot be queried from the chip. We do lazy +@@ -962,7 +959,7 @@ static s32 ixgbe_write_eeprom_buffer_bit_bang(struct ixgbe_hw *hw, u16 offset, + + if (ixgbe_ready_eeprom(hw) != 0) { + ixgbe_release_eeprom(hw); +- return IXGBE_ERR_EEPROM; ++ return -EIO; + } + + for (i = 0; i < words; i++) { +@@ -1028,7 +1025,7 @@ s32 ixgbe_write_eeprom_generic(struct ixgbe_hw *hw, u16 offset, u16 data) + hw->eeprom.ops.init_params(hw); + + if (offset >= hw->eeprom.word_size) +- return IXGBE_ERR_EEPROM; ++ return -EINVAL; + + return ixgbe_write_eeprom_buffer_bit_bang(hw, offset, 1, &data); + } +@@ -1050,11 +1047,8 @@ s32 ixgbe_read_eeprom_buffer_bit_bang_generic(struct ixgbe_hw *hw, u16 offset, + + hw->eeprom.ops.init_params(hw); + +- if (words == 0) +- return IXGBE_ERR_INVALID_ARGUMENT; +- +- if (offset + words > hw->eeprom.word_size) +- return IXGBE_ERR_EEPROM; ++ if (words == 0 || (offset + words > hw->eeprom.word_size)) ++ return -EINVAL; + + /* + * We cannot hold synchronization semaphores for too long +@@ -1099,7 +1093,7 @@ static s32 ixgbe_read_eeprom_buffer_bit_bang(struct ixgbe_hw *hw, u16 offset, + + if (ixgbe_ready_eeprom(hw) != 0) { + ixgbe_release_eeprom(hw); +- return IXGBE_ERR_EEPROM; ++ return -EIO; + } + + for (i = 0; i < words; i++) { +@@ -1142,7 +1136,7 @@ s32 ixgbe_read_eeprom_bit_bang_generic(struct ixgbe_hw *hw, u16 offset, + hw->eeprom.ops.init_params(hw); + + if (offset >= hw->eeprom.word_size) +- return IXGBE_ERR_EEPROM; ++ return -EINVAL; + + return ixgbe_read_eeprom_buffer_bit_bang(hw, offset, 1, data); + } +@@ -1165,11 +1159,8 @@ s32 ixgbe_read_eerd_buffer_generic(struct ixgbe_hw *hw, u16 offset, + + hw->eeprom.ops.init_params(hw); + +- if (words == 0) +- return IXGBE_ERR_INVALID_ARGUMENT; +- +- if (offset >= hw->eeprom.word_size) +- return IXGBE_ERR_EEPROM; ++ if (words == 0 || offset >= hw->eeprom.word_size) ++ return -EINVAL; + + for (i = 0; i < words; i++) { + eerd = ((offset + i) << IXGBE_EEPROM_RW_ADDR_SHIFT) | +@@ -1262,11 +1253,8 @@ s32 ixgbe_write_eewr_buffer_generic(struct ixgbe_hw *hw, u16 offset, + + hw->eeprom.ops.init_params(hw); + +- if (words == 0) +- return IXGBE_ERR_INVALID_ARGUMENT; +- +- if (offset >= hw->eeprom.word_size) +- return IXGBE_ERR_EEPROM; ++ if (words == 0 || offset >= hw->eeprom.word_size) ++ return -EINVAL; + + for (i = 0; i < words; i++) { + eewr = ((offset + i) << IXGBE_EEPROM_RW_ADDR_SHIFT) | +@@ -1328,7 +1316,7 @@ static s32 ixgbe_poll_eerd_eewr_done(struct ixgbe_hw *hw, u32 ee_reg) + } + udelay(5); + } +- return IXGBE_ERR_EEPROM; ++ return -EIO; + } + + /** +@@ -1344,7 +1332,7 @@ static s32 ixgbe_acquire_eeprom(struct ixgbe_hw *hw) + u32 i; + + if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM) != 0) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + + eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw)); + +@@ -1366,7 +1354,7 @@ static s32 ixgbe_acquire_eeprom(struct ixgbe_hw *hw) + hw_dbg(hw, "Could not acquire EEPROM grant\n"); + + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM); +- return IXGBE_ERR_EEPROM; ++ return -EIO; + } + + /* Setup EEPROM for Read/Write */ +@@ -1419,7 +1407,7 @@ static s32 ixgbe_get_eeprom_semaphore(struct ixgbe_hw *hw) + swsm = IXGBE_READ_REG(hw, IXGBE_SWSM(hw)); + if (swsm & IXGBE_SWSM_SMBI) { + hw_dbg(hw, "Software semaphore SMBI between device drivers not granted.\n"); +- return IXGBE_ERR_EEPROM; ++ return -EIO; + } + } + +@@ -1447,7 +1435,7 @@ static s32 ixgbe_get_eeprom_semaphore(struct ixgbe_hw *hw) + if (i >= timeout) { + hw_dbg(hw, "SWESMBI Software EEPROM semaphore not granted.\n"); + ixgbe_release_eeprom_semaphore(hw); +- return IXGBE_ERR_EEPROM; ++ return -EIO; + } + + return 0; +@@ -1503,7 +1491,7 @@ static s32 ixgbe_ready_eeprom(struct ixgbe_hw *hw) + */ + if (i >= IXGBE_EEPROM_MAX_RETRY_SPI) { + hw_dbg(hw, "SPI EEPROM Status error\n"); +- return IXGBE_ERR_EEPROM; ++ return -EIO; + } + + return 0; +@@ -1715,7 +1703,7 @@ s32 ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw) + for (i = IXGBE_PCIE_ANALOG_PTR; i < IXGBE_FW_PTR; i++) { + if (hw->eeprom.ops.read(hw, i, &pointer)) { + hw_dbg(hw, "EEPROM read failed\n"); +- return IXGBE_ERR_EEPROM; ++ return -EIO; + } + + /* If the pointer seems invalid */ +@@ -1724,7 +1712,7 @@ s32 ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw) + + if (hw->eeprom.ops.read(hw, pointer, &length)) { + hw_dbg(hw, "EEPROM read failed\n"); +- return IXGBE_ERR_EEPROM; ++ return -EIO; + } + + if (length == 0xFFFF || length == 0) +@@ -1733,7 +1721,7 @@ s32 ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw) + for (j = pointer + 1; j <= pointer + length; j++) { + if (hw->eeprom.ops.read(hw, j, &word)) { + hw_dbg(hw, "EEPROM read failed\n"); +- return IXGBE_ERR_EEPROM; ++ return -EIO; + } + checksum += word; + } +@@ -1786,7 +1774,7 @@ s32 ixgbe_validate_eeprom_checksum_generic(struct ixgbe_hw *hw, + * calculated checksum + */ + if (read_checksum != checksum) +- status = IXGBE_ERR_EEPROM_CHECKSUM; ++ status = -EIO; + + /* If the user cares, return the calculated checksum */ + if (checksum_val) +@@ -1845,7 +1833,7 @@ s32 ixgbe_set_rar_generic(struct ixgbe_hw *hw, u32 index, u8 *addr, u32 vmdq, + /* Make sure we are using a valid rar index range */ + if (index >= rar_entries) { + hw_dbg(hw, "RAR index %d is out of range.\n", index); +- return IXGBE_ERR_INVALID_ARGUMENT; ++ return -EINVAL; + } + + /* setup VMDq pool selection before this RAR gets enabled */ +@@ -1897,7 +1885,7 @@ s32 ixgbe_clear_rar_generic(struct ixgbe_hw *hw, u32 index) + /* Make sure we are using a valid rar index range */ + if (index >= rar_entries) { + hw_dbg(hw, "RAR index %d is out of range.\n", index); +- return IXGBE_ERR_INVALID_ARGUMENT; ++ return -EINVAL; + } + + /* +@@ -2146,7 +2134,7 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw) + + /* Validate the water mark configuration. */ + if (!hw->fc.pause_time) +- return IXGBE_ERR_INVALID_LINK_SETTINGS; ++ return -EINVAL; + + /* Low water mark of zero causes XOFF floods */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { +@@ -2155,7 +2143,7 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw) + if (!hw->fc.low_water[i] || + hw->fc.low_water[i] >= hw->fc.high_water[i]) { + hw_dbg(hw, "Invalid water mark configuration\n"); +- return IXGBE_ERR_INVALID_LINK_SETTINGS; ++ return -EINVAL; + } + } + } +@@ -2212,7 +2200,7 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw) + break; + default: + hw_dbg(hw, "Flow control param set incorrectly\n"); +- return IXGBE_ERR_CONFIG; ++ return -EIO; + } + + /* Set 802.3x based flow control settings. */ +@@ -2269,7 +2257,7 @@ s32 ixgbe_negotiate_fc(struct ixgbe_hw *hw, u32 adv_reg, u32 lp_reg, + u32 adv_sym, u32 adv_asm, u32 lp_sym, u32 lp_asm) + { + if ((!(adv_reg)) || (!(lp_reg))) +- return IXGBE_ERR_FC_NOT_NEGOTIATED; ++ return -EINVAL; + + if ((adv_reg & adv_sym) && (lp_reg & lp_sym)) { + /* +@@ -2321,7 +2309,7 @@ static s32 ixgbe_fc_autoneg_fiber(struct ixgbe_hw *hw) + linkstat = IXGBE_READ_REG(hw, IXGBE_PCS1GLSTA); + if ((!!(linkstat & IXGBE_PCS1GLSTA_AN_COMPLETE) == 0) || + (!!(linkstat & IXGBE_PCS1GLSTA_AN_TIMED_OUT) == 1)) +- return IXGBE_ERR_FC_NOT_NEGOTIATED; ++ return -EIO; + + pcs_anadv_reg = IXGBE_READ_REG(hw, IXGBE_PCS1GANA); + pcs_lpab_reg = IXGBE_READ_REG(hw, IXGBE_PCS1GANLP); +@@ -2353,12 +2341,12 @@ static s32 ixgbe_fc_autoneg_backplane(struct ixgbe_hw *hw) + */ + links = IXGBE_READ_REG(hw, IXGBE_LINKS); + if ((links & IXGBE_LINKS_KX_AN_COMP) == 0) +- return IXGBE_ERR_FC_NOT_NEGOTIATED; ++ return -EIO; + + if (hw->mac.type == ixgbe_mac_82599EB) { + links2 = IXGBE_READ_REG(hw, IXGBE_LINKS2); + if ((links2 & IXGBE_LINKS2_AN_SUPPORTED) == 0) +- return IXGBE_ERR_FC_NOT_NEGOTIATED; ++ return -EIO; + } + /* + * Read the 10g AN autoc and LP ability registers and resolve +@@ -2407,8 +2395,8 @@ static s32 ixgbe_fc_autoneg_copper(struct ixgbe_hw *hw) + **/ + void ixgbe_fc_autoneg(struct ixgbe_hw *hw) + { +- s32 ret_val = IXGBE_ERR_FC_NOT_NEGOTIATED; + ixgbe_link_speed speed; ++ s32 ret_val = -EIO; + bool link_up; + + /* +@@ -2510,7 +2498,7 @@ static u32 ixgbe_pcie_timeout_poll(struct ixgbe_hw *hw) + * @hw: pointer to hardware structure + * + * Disables PCI-Express primary access and verifies there are no pending +- * requests. IXGBE_ERR_PRIMARY_REQUESTS_PENDING is returned if primary disable ++ * requests. -EALREADY is returned if primary disable + * bit hasn't caused the primary requests to be disabled, else 0 + * is returned signifying primary requests disabled. + **/ +@@ -2575,7 +2563,7 @@ static s32 ixgbe_disable_pcie_primary(struct ixgbe_hw *hw) + } + + hw_dbg(hw, "PCIe transaction pending bit also did not clear.\n"); +- return IXGBE_ERR_PRIMARY_REQUESTS_PENDING; ++ return -EALREADY; + } + + /** +@@ -2600,7 +2588,7 @@ s32 ixgbe_acquire_swfw_sync(struct ixgbe_hw *hw, u32 mask) + * SW_FW_SYNC bits (not just NVM) + */ + if (ixgbe_get_eeprom_semaphore(hw)) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + + gssr = IXGBE_READ_REG(hw, IXGBE_GSSR); + if (!(gssr & (fwmask | swmask))) { +@@ -2620,7 +2608,7 @@ s32 ixgbe_acquire_swfw_sync(struct ixgbe_hw *hw, u32 mask) + ixgbe_release_swfw_sync(hw, gssr & (fwmask | swmask)); + + usleep_range(5000, 10000); +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + } + + /** +@@ -2757,7 +2745,7 @@ s32 ixgbe_blink_led_start_generic(struct ixgbe_hw *hw, u32 index) + s32 ret_val; + + if (index > 3) +- return IXGBE_ERR_PARAM; ++ return -EINVAL; + + /* + * Link must be up to auto-blink the LEDs; +@@ -2803,7 +2791,7 @@ s32 ixgbe_blink_led_stop_generic(struct ixgbe_hw *hw, u32 index) + s32 ret_val; + + if (index > 3) +- return IXGBE_ERR_PARAM; ++ return -EINVAL; + + ret_val = hw->mac.ops.prot_autoc_read(hw, &locked, &autoc_reg); + if (ret_val) +@@ -2963,7 +2951,7 @@ s32 ixgbe_clear_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq) + /* Make sure we are using a valid rar index range */ + if (rar >= rar_entries) { + hw_dbg(hw, "RAR index %d is out of range.\n", rar); +- return IXGBE_ERR_INVALID_ARGUMENT; ++ return -EINVAL; + } + + mpsar_lo = IXGBE_READ_REG(hw, IXGBE_MPSAR_LO(rar)); +@@ -3014,7 +3002,7 @@ s32 ixgbe_set_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq) + /* Make sure we are using a valid rar index range */ + if (rar >= rar_entries) { + hw_dbg(hw, "RAR index %d is out of range.\n", rar); +- return IXGBE_ERR_INVALID_ARGUMENT; ++ return -EINVAL; + } + + if (vmdq < 32) { +@@ -3091,7 +3079,7 @@ static s32 ixgbe_find_vlvf_slot(struct ixgbe_hw *hw, u32 vlan, bool vlvf_bypass) + * will simply bypass the VLVF if there are no entries present in the + * VLVF that contain our VLAN + */ +- first_empty_slot = vlvf_bypass ? IXGBE_ERR_NO_SPACE : 0; ++ first_empty_slot = vlvf_bypass ? -ENOSPC : 0; + + /* add VLAN enable bit for comparison */ + vlan |= IXGBE_VLVF_VIEN; +@@ -3115,7 +3103,7 @@ static s32 ixgbe_find_vlvf_slot(struct ixgbe_hw *hw, u32 vlan, bool vlvf_bypass) + if (!first_empty_slot) + hw_dbg(hw, "No space in VLVF.\n"); + +- return first_empty_slot ? : IXGBE_ERR_NO_SPACE; ++ return first_empty_slot ? : -ENOSPC; + } + + /** +@@ -3135,7 +3123,7 @@ s32 ixgbe_set_vfta_generic(struct ixgbe_hw *hw, u32 vlan, u32 vind, + s32 vlvf_index; + + if ((vlan > 4095) || (vind > 63)) +- return IXGBE_ERR_PARAM; ++ return -EINVAL; + + /* + * this is a 2 part operation - first the VFTA, then the +@@ -3611,7 +3599,8 @@ u8 ixgbe_calculate_checksum(u8 *buffer, u32 length) + * + * Communicates with the manageability block. On success return 0 + * else returns semaphore error when encountering an error acquiring +- * semaphore or IXGBE_ERR_HOST_INTERFACE_COMMAND when command fails. ++ * semaphore, -EINVAL when incorrect parameters passed or -EIO when ++ * command fails. + * + * This function assumes that the IXGBE_GSSR_SW_MNG_SM semaphore is held + * by the caller. +@@ -3624,7 +3613,7 @@ s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 length, + + if (!length || length > IXGBE_HI_MAX_BLOCK_BYTE_LENGTH) { + hw_dbg(hw, "Buffer length failure buffersize-%d.\n", length); +- return IXGBE_ERR_HOST_INTERFACE_COMMAND; ++ return -EINVAL; + } + + /* Set bit 9 of FWSTS clearing FW reset indication */ +@@ -3635,13 +3624,13 @@ s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 length, + hicr = IXGBE_READ_REG(hw, IXGBE_HICR); + if (!(hicr & IXGBE_HICR_EN)) { + hw_dbg(hw, "IXGBE_HOST_EN bit disabled.\n"); +- return IXGBE_ERR_HOST_INTERFACE_COMMAND; ++ return -EIO; + } + + /* Calculate length in DWORDs. We must be DWORD aligned */ + if (length % sizeof(u32)) { + hw_dbg(hw, "Buffer length failure, not aligned to dword"); +- return IXGBE_ERR_INVALID_ARGUMENT; ++ return -EINVAL; + } + + dword_len = length >> 2; +@@ -3666,7 +3655,7 @@ s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 length, + /* Check command successful completion. */ + if ((timeout && i == timeout) || + !(IXGBE_READ_REG(hw, IXGBE_HICR) & IXGBE_HICR_SV)) +- return IXGBE_ERR_HOST_INTERFACE_COMMAND; ++ return -EIO; + + return 0; + } +@@ -3686,7 +3675,7 @@ s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 length, + * in these cases. + * + * Communicates with the manageability block. On success return 0 +- * else return IXGBE_ERR_HOST_INTERFACE_COMMAND. ++ * else return -EIO or -EINVAL. + **/ + s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, + u32 length, u32 timeout, +@@ -3701,7 +3690,7 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, + + if (!length || length > IXGBE_HI_MAX_BLOCK_BYTE_LENGTH) { + hw_dbg(hw, "Buffer length failure buffersize-%d.\n", length); +- return IXGBE_ERR_HOST_INTERFACE_COMMAND; ++ return -EINVAL; + } + /* Take management host interface semaphore */ + status = hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_SW_MNG_SM); +@@ -3731,7 +3720,7 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, + + if (length < round_up(buf_len, 4) + hdr_size) { + hw_dbg(hw, "Buffer not large enough for reply message.\n"); +- status = IXGBE_ERR_HOST_INTERFACE_COMMAND; ++ status = -EIO; + goto rel_out; + } + +@@ -3762,8 +3751,8 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, + * + * Sends driver version number to firmware through the manageability + * block. On success return 0 +- * else returns IXGBE_ERR_SWFW_SYNC when encountering an error acquiring +- * semaphore or IXGBE_ERR_HOST_INTERFACE_COMMAND when command fails. ++ * else returns -EBUSY when encountering an error acquiring ++ * semaphore or -EIO when command fails. + **/ + s32 ixgbe_set_fw_drv_ver_generic(struct ixgbe_hw *hw, u8 maj, u8 min, + u8 build, u8 sub, __always_unused u16 len, +@@ -3799,7 +3788,7 @@ s32 ixgbe_set_fw_drv_ver_generic(struct ixgbe_hw *hw, u8 maj, u8 min, + FW_CEM_RESP_STATUS_SUCCESS) + ret_val = 0; + else +- ret_val = IXGBE_ERR_HOST_INTERFACE_COMMAND; ++ ret_val = -EIO; + + break; + } +@@ -3897,14 +3886,14 @@ static s32 ixgbe_get_ets_data(struct ixgbe_hw *hw, u16 *ets_cfg, + return status; + + if ((*ets_offset == 0x0000) || (*ets_offset == 0xFFFF)) +- return IXGBE_NOT_IMPLEMENTED; ++ return -EOPNOTSUPP; + + status = hw->eeprom.ops.read(hw, *ets_offset, ets_cfg); + if (status) + return status; + + if ((*ets_cfg & IXGBE_ETS_TYPE_MASK) != IXGBE_ETS_TYPE_EMC_SHIFTED) +- return IXGBE_NOT_IMPLEMENTED; ++ return -EOPNOTSUPP; + + return 0; + } +@@ -3927,7 +3916,7 @@ s32 ixgbe_get_thermal_sensor_data_generic(struct ixgbe_hw *hw) + + /* Only support thermal sensors attached to physical port 0 */ + if ((IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1)) +- return IXGBE_NOT_IMPLEMENTED; ++ return -EOPNOTSUPP; + + status = ixgbe_get_ets_data(hw, &ets_cfg, &ets_offset); + if (status) +@@ -3987,7 +3976,7 @@ s32 ixgbe_init_thermal_sensor_thresh_generic(struct ixgbe_hw *hw) + + /* Only support thermal sensors attached to physical port 0 */ + if ((IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1)) +- return IXGBE_NOT_IMPLEMENTED; ++ return -EOPNOTSUPP; + + status = ixgbe_get_ets_data(hw, &ets_cfg, &ets_offset); + if (status) +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +index 0bbad4a5cc2f..9f2820a08b72 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +@@ -3370,7 +3370,7 @@ static int ixgbe_get_module_eeprom(struct net_device *dev, + { + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_hw *hw = &adapter->hw; +- s32 status = IXGBE_ERR_PHY_ADDR_INVALID; ++ s32 status = -EFAULT; + u8 databyte = 0xFF; + int i = 0; + +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +index dd03b017dfc5..f7c6482d6b63 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +@@ -5512,7 +5512,7 @@ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw) + { + u32 speed; + bool autoneg, link_up = false; +- int ret = IXGBE_ERR_LINK_SETUP; ++ int ret = -EIO; + + if (hw->mac.ops.check_link) + ret = hw->mac.ops.check_link(hw, &speed, &link_up, false); +@@ -5983,13 +5983,13 @@ void ixgbe_reset(struct ixgbe_adapter *adapter) + err = hw->mac.ops.init_hw(hw); + switch (err) { + case 0: +- case IXGBE_ERR_SFP_NOT_PRESENT: +- case IXGBE_ERR_SFP_NOT_SUPPORTED: ++ case -ENOENT: ++ case -EOPNOTSUPP: + break; +- case IXGBE_ERR_PRIMARY_REQUESTS_PENDING: ++ case -EALREADY: + e_dev_err("primary disable timed out\n"); + break; +- case IXGBE_ERR_EEPROM_VERSION: ++ case -EACCES: + /* We are running on a pre-production device, log a warning */ + e_dev_warn("This device is a pre-production adapter/LOM. " + "Please be aware there may be issues associated with " +@@ -7829,10 +7829,10 @@ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter) + adapter->sfp_poll_time = jiffies + IXGBE_SFP_POLL_JIFFIES - 1; + + err = hw->phy.ops.identify_sfp(hw); +- if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) ++ if (err == -EOPNOTSUPP) + goto sfp_out; + +- if (err == IXGBE_ERR_SFP_NOT_PRESENT) { ++ if (err == -ENOENT) { + /* If no cable is present, then we need to reset + * the next time we find a good cable. */ + adapter->flags2 |= IXGBE_FLAG2_SFP_NEEDS_RESET; +@@ -7858,7 +7858,7 @@ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter) + else + err = hw->mac.ops.setup_sfp(hw); + +- if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) ++ if (err == -EOPNOTSUPP) + goto sfp_out; + + adapter->flags |= IXGBE_FLAG_NEED_LINK_CONFIG; +@@ -7867,8 +7867,8 @@ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter) + sfp_out: + clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state); + +- if ((err == IXGBE_ERR_SFP_NOT_SUPPORTED) && +- (adapter->netdev->reg_state == NETREG_REGISTERED)) { ++ if (err == -EOPNOTSUPP && ++ adapter->netdev->reg_state == NETREG_REGISTERED) { + e_dev_err("failed to initialize because an unsupported " + "SFP+ module type was detected.\n"); + e_dev_err("Reload the driver after installing a " +@@ -10922,9 +10922,9 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) + err = hw->mac.ops.reset_hw(hw); + hw->phy.reset_if_overtemp = false; + ixgbe_set_eee_capable(adapter); +- if (err == IXGBE_ERR_SFP_NOT_PRESENT) { ++ if (err == -ENOENT) { + err = 0; +- } else if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) { ++ } else if (err == -EOPNOTSUPP) { + e_dev_err("failed to load because an unsupported SFP+ or QSFP module type was detected.\n"); + e_dev_err("Reload the driver after installing a supported module.\n"); + goto err_sw_init; +@@ -11143,7 +11143,7 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) + + /* reset the hardware with the new settings */ + err = hw->mac.ops.start_hw(hw); +- if (err == IXGBE_ERR_EEPROM_VERSION) { ++ if (err == -EACCES) { + /* We are running on a pre-production device, log a warning */ + e_dev_warn("This device is a pre-production adapter/LOM. " + "Please be aware there may be issues associated " +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c +index 5679293e53f7..fe7ef5773369 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c +@@ -24,7 +24,7 @@ s32 ixgbe_read_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, u16 mbx_id) + size = mbx->size; + + if (!mbx->ops) +- return IXGBE_ERR_MBX; ++ return -EIO; + + return mbx->ops->read(hw, msg, size, mbx_id); + } +@@ -43,10 +43,10 @@ s32 ixgbe_write_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, u16 mbx_id) + struct ixgbe_mbx_info *mbx = &hw->mbx; + + if (size > mbx->size) +- return IXGBE_ERR_MBX; ++ return -EINVAL; + + if (!mbx->ops) +- return IXGBE_ERR_MBX; ++ return -EIO; + + return mbx->ops->write(hw, msg, size, mbx_id); + } +@@ -63,7 +63,7 @@ s32 ixgbe_check_for_msg(struct ixgbe_hw *hw, u16 mbx_id) + struct ixgbe_mbx_info *mbx = &hw->mbx; + + if (!mbx->ops) +- return IXGBE_ERR_MBX; ++ return -EIO; + + return mbx->ops->check_for_msg(hw, mbx_id); + } +@@ -80,7 +80,7 @@ s32 ixgbe_check_for_ack(struct ixgbe_hw *hw, u16 mbx_id) + struct ixgbe_mbx_info *mbx = &hw->mbx; + + if (!mbx->ops) +- return IXGBE_ERR_MBX; ++ return -EIO; + + return mbx->ops->check_for_ack(hw, mbx_id); + } +@@ -97,7 +97,7 @@ s32 ixgbe_check_for_rst(struct ixgbe_hw *hw, u16 mbx_id) + struct ixgbe_mbx_info *mbx = &hw->mbx; + + if (!mbx->ops) +- return IXGBE_ERR_MBX; ++ return -EIO; + + return mbx->ops->check_for_rst(hw, mbx_id); + } +@@ -115,12 +115,12 @@ static s32 ixgbe_poll_for_msg(struct ixgbe_hw *hw, u16 mbx_id) + int countdown = mbx->timeout; + + if (!countdown || !mbx->ops) +- return IXGBE_ERR_MBX; ++ return -EIO; + + while (mbx->ops->check_for_msg(hw, mbx_id)) { + countdown--; + if (!countdown) +- return IXGBE_ERR_MBX; ++ return -EIO; + udelay(mbx->usec_delay); + } + +@@ -140,12 +140,12 @@ static s32 ixgbe_poll_for_ack(struct ixgbe_hw *hw, u16 mbx_id) + int countdown = mbx->timeout; + + if (!countdown || !mbx->ops) +- return IXGBE_ERR_MBX; ++ return -EIO; + + while (mbx->ops->check_for_ack(hw, mbx_id)) { + countdown--; + if (!countdown) +- return IXGBE_ERR_MBX; ++ return -EIO; + udelay(mbx->usec_delay); + } + +@@ -169,7 +169,7 @@ static s32 ixgbe_read_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, + s32 ret_val; + + if (!mbx->ops) +- return IXGBE_ERR_MBX; ++ return -EIO; + + ret_val = ixgbe_poll_for_msg(hw, mbx_id); + if (ret_val) +@@ -197,7 +197,7 @@ static s32 ixgbe_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, + + /* exit if either we can't write or there isn't a defined timeout */ + if (!mbx->ops || !mbx->timeout) +- return IXGBE_ERR_MBX; ++ return -EIO; + + /* send msg */ + ret_val = mbx->ops->write(hw, msg, size, mbx_id); +@@ -217,7 +217,7 @@ static s32 ixgbe_check_for_bit_pf(struct ixgbe_hw *hw, u32 mask, s32 index) + return 0; + } + +- return IXGBE_ERR_MBX; ++ return -EIO; + } + + /** +@@ -238,7 +238,7 @@ static s32 ixgbe_check_for_msg_pf(struct ixgbe_hw *hw, u16 vf_number) + return 0; + } + +- return IXGBE_ERR_MBX; ++ return -EIO; + } + + /** +@@ -259,7 +259,7 @@ static s32 ixgbe_check_for_ack_pf(struct ixgbe_hw *hw, u16 vf_number) + return 0; + } + +- return IXGBE_ERR_MBX; ++ return -EIO; + } + + /** +@@ -295,7 +295,7 @@ static s32 ixgbe_check_for_rst_pf(struct ixgbe_hw *hw, u16 vf_number) + return 0; + } + +- return IXGBE_ERR_MBX; ++ return -EIO; + } + + /** +@@ -317,7 +317,7 @@ static s32 ixgbe_obtain_mbx_lock_pf(struct ixgbe_hw *hw, u16 vf_number) + if (p2v_mailbox & IXGBE_PFMAILBOX_PFU) + return 0; + +- return IXGBE_ERR_MBX; ++ return -EIO; + } + + /** +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h +index 8f4316b19278..6434c190e7a4 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h +@@ -7,7 +7,6 @@ + #include "ixgbe_type.h" + + #define IXGBE_VFMAILBOX_SIZE 16 /* 16 32 bit words - 64 bytes */ +-#define IXGBE_ERR_MBX -100 + + #define IXGBE_VFMAILBOX 0x002FC + #define IXGBE_VFMBMEM 0x00200 +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +index 689470c1e8ad..7c0a1a0a5eda 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +@@ -102,7 +102,7 @@ s32 ixgbe_read_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr, + csum = ~csum; + do { + if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + ixgbe_i2c_start(hw); + /* Device Address and write indication */ + if (ixgbe_out_i2c_byte_ack(hw, addr)) +@@ -150,7 +150,7 @@ s32 ixgbe_read_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr, + hw_dbg(hw, "I2C byte read combined error.\n"); + } while (retry < max_retry); + +- return IXGBE_ERR_I2C; ++ return -EIO; + } + + /** +@@ -179,7 +179,7 @@ s32 ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr, + csum = ~csum; + do { + if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + ixgbe_i2c_start(hw); + /* Device Address and write indication */ + if (ixgbe_out_i2c_byte_ack(hw, addr)) +@@ -215,7 +215,7 @@ s32 ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr, + hw_dbg(hw, "I2C byte write combined error.\n"); + } while (retry < max_retry); + +- return IXGBE_ERR_I2C; ++ return -EIO; + } + + /** +@@ -262,8 +262,8 @@ static bool ixgbe_probe_phy(struct ixgbe_hw *hw, u16 phy_addr) + **/ + s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw) + { ++ u32 status = -EFAULT; + u32 phy_addr; +- u32 status = IXGBE_ERR_PHY_ADDR_INVALID; + + if (!hw->phy.phy_semaphore_mask) { + if (hw->bus.lan_id) +@@ -282,7 +282,7 @@ s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw) + if (ixgbe_probe_phy(hw, phy_addr)) + return 0; + else +- return IXGBE_ERR_PHY_ADDR_INVALID; ++ return -EFAULT; + } + + for (phy_addr = 0; phy_addr < IXGBE_MAX_PHY_ADDR; phy_addr++) { +@@ -457,7 +457,7 @@ s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw) + + if (ctrl & MDIO_CTRL1_RESET) { + hw_dbg(hw, "PHY reset polling failed to complete.\n"); +- return IXGBE_ERR_RESET_FAILED; ++ return -EIO; + } + + return 0; +@@ -500,7 +500,7 @@ s32 ixgbe_read_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type, + + if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { + hw_dbg(hw, "PHY address command did not complete.\n"); +- return IXGBE_ERR_PHY; ++ return -EIO; + } + + /* Address cycle complete, setup and write the read +@@ -527,7 +527,7 @@ s32 ixgbe_read_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type, + + if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { + hw_dbg(hw, "PHY read command didn't complete\n"); +- return IXGBE_ERR_PHY; ++ return -EIO; + } + + /* Read operation is complete. Get the data +@@ -559,7 +559,7 @@ s32 ixgbe_read_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, + phy_data); + hw->mac.ops.release_swfw_sync(hw, gssr); + } else { +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + } + + return status; +@@ -604,7 +604,7 @@ s32 ixgbe_write_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, + + if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { + hw_dbg(hw, "PHY address cmd didn't complete\n"); +- return IXGBE_ERR_PHY; ++ return -EIO; + } + + /* +@@ -632,7 +632,7 @@ s32 ixgbe_write_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, + + if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { + hw_dbg(hw, "PHY write cmd didn't complete\n"); +- return IXGBE_ERR_PHY; ++ return -EIO; + } + + return 0; +@@ -657,7 +657,7 @@ s32 ixgbe_write_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, + phy_data); + hw->mac.ops.release_swfw_sync(hw, gssr); + } else { +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + } + + return status; +@@ -1430,7 +1430,7 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw) + + if ((phy_data & MDIO_CTRL1_RESET) != 0) { + hw_dbg(hw, "PHY reset did not complete.\n"); +- return IXGBE_ERR_PHY; ++ return -EIO; + } + + /* Get init offsets */ +@@ -1487,12 +1487,12 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw) + hw_dbg(hw, "SOL\n"); + } else { + hw_dbg(hw, "Bad control value\n"); +- return IXGBE_ERR_PHY; ++ return -EIO; + } + break; + default: + hw_dbg(hw, "Bad control type\n"); +- return IXGBE_ERR_PHY; ++ return -EIO; + } + } + +@@ -1500,7 +1500,7 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw) + + err_eeprom: + hw_err(hw, "eeprom read at offset %d failed\n", data_offset); +- return IXGBE_ERR_PHY; ++ return -EIO; + } + + /** +@@ -1518,10 +1518,10 @@ s32 ixgbe_identify_module_generic(struct ixgbe_hw *hw) + return ixgbe_identify_qsfp_module_generic(hw); + default: + hw->phy.sfp_type = ixgbe_sfp_type_not_present; +- return IXGBE_ERR_SFP_NOT_PRESENT; ++ return -ENOENT; + } + +- return IXGBE_ERR_SFP_NOT_PRESENT; ++ return -ENOENT; + } + + /** +@@ -1546,7 +1546,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) + + if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_fiber) { + hw->phy.sfp_type = ixgbe_sfp_type_not_present; +- return IXGBE_ERR_SFP_NOT_PRESENT; ++ return -ENOENT; + } + + /* LAN ID is needed for sfp_type determination */ +@@ -1561,7 +1561,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) + + if (identifier != IXGBE_SFF_IDENTIFIER_SFP) { + hw->phy.type = ixgbe_phy_sfp_unsupported; +- return IXGBE_ERR_SFP_NOT_SUPPORTED; ++ return -EOPNOTSUPP; + } + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_1GBE_COMP_CODES, +@@ -1752,7 +1752,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1)) { + hw->phy.type = ixgbe_phy_sfp_unsupported; +- return IXGBE_ERR_SFP_NOT_SUPPORTED; ++ return -EOPNOTSUPP; + } + + /* Anything else 82598-based is supported */ +@@ -1776,7 +1776,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) + } + hw_dbg(hw, "SFP+ module not supported\n"); + hw->phy.type = ixgbe_phy_sfp_unsupported; +- return IXGBE_ERR_SFP_NOT_SUPPORTED; ++ return -EOPNOTSUPP; + } + return 0; + +@@ -1786,7 +1786,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) + hw->phy.id = 0; + hw->phy.type = ixgbe_phy_unknown; + } +- return IXGBE_ERR_SFP_NOT_PRESENT; ++ return -ENOENT; + } + + /** +@@ -1813,7 +1813,7 @@ static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw) + + if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_fiber_qsfp) { + hw->phy.sfp_type = ixgbe_sfp_type_not_present; +- return IXGBE_ERR_SFP_NOT_PRESENT; ++ return -ENOENT; + } + + /* LAN ID is needed for sfp_type determination */ +@@ -1827,7 +1827,7 @@ static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw) + + if (identifier != IXGBE_SFF_IDENTIFIER_QSFP_PLUS) { + hw->phy.type = ixgbe_phy_sfp_unsupported; +- return IXGBE_ERR_SFP_NOT_SUPPORTED; ++ return -EOPNOTSUPP; + } + + hw->phy.id = identifier; +@@ -1895,7 +1895,7 @@ static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw) + } else { + /* unsupported module type */ + hw->phy.type = ixgbe_phy_sfp_unsupported; +- return IXGBE_ERR_SFP_NOT_SUPPORTED; ++ return -EOPNOTSUPP; + } + } + +@@ -1955,7 +1955,7 @@ static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw) + } + hw_dbg(hw, "QSFP module not supported\n"); + hw->phy.type = ixgbe_phy_sfp_unsupported; +- return IXGBE_ERR_SFP_NOT_SUPPORTED; ++ return -EOPNOTSUPP; + } + return 0; + } +@@ -1966,7 +1966,7 @@ static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw) + hw->phy.id = 0; + hw->phy.type = ixgbe_phy_unknown; + +- return IXGBE_ERR_SFP_NOT_PRESENT; ++ return -ENOENT; + } + + /** +@@ -1986,14 +1986,14 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, + u16 sfp_type = hw->phy.sfp_type; + + if (hw->phy.sfp_type == ixgbe_sfp_type_unknown) +- return IXGBE_ERR_SFP_NOT_SUPPORTED; ++ return -EOPNOTSUPP; + + if (hw->phy.sfp_type == ixgbe_sfp_type_not_present) +- return IXGBE_ERR_SFP_NOT_PRESENT; ++ return -ENOENT; + + if ((hw->device_id == IXGBE_DEV_ID_82598_SR_DUAL_PORT_EM) && + (hw->phy.sfp_type == ixgbe_sfp_type_da_cu)) +- return IXGBE_ERR_SFP_NOT_SUPPORTED; ++ return -EOPNOTSUPP; + + /* + * Limiting active cables and 1G Phys must be initialized as +@@ -2014,11 +2014,11 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, + if (hw->eeprom.ops.read(hw, IXGBE_PHY_INIT_OFFSET_NL, list_offset)) { + hw_err(hw, "eeprom read at %d failed\n", + IXGBE_PHY_INIT_OFFSET_NL); +- return IXGBE_ERR_SFP_NO_INIT_SEQ_PRESENT; ++ return -EIO; + } + + if ((!*list_offset) || (*list_offset == 0xFFFF)) +- return IXGBE_ERR_SFP_NO_INIT_SEQ_PRESENT; ++ return -EIO; + + /* Shift offset to first ID word */ + (*list_offset)++; +@@ -2037,7 +2037,7 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, + goto err_phy; + if ((!*data_offset) || (*data_offset == 0xFFFF)) { + hw_dbg(hw, "SFP+ module not supported\n"); +- return IXGBE_ERR_SFP_NOT_SUPPORTED; ++ return -EOPNOTSUPP; + } else { + break; + } +@@ -2050,14 +2050,14 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, + + if (sfp_id == IXGBE_PHY_INIT_END_NL) { + hw_dbg(hw, "No matching SFP+ module found\n"); +- return IXGBE_ERR_SFP_NOT_SUPPORTED; ++ return -EOPNOTSUPP; + } + + return 0; + + err_phy: + hw_err(hw, "eeprom read at offset %d failed\n", *list_offset); +- return IXGBE_ERR_PHY; ++ return -EIO; + } + + /** +@@ -2152,7 +2152,7 @@ static s32 ixgbe_read_i2c_byte_generic_int(struct ixgbe_hw *hw, u8 byte_offset, + + do { + if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + + ixgbe_i2c_start(hw); + +@@ -2268,7 +2268,7 @@ static s32 ixgbe_write_i2c_byte_generic_int(struct ixgbe_hw *hw, u8 byte_offset, + u32 swfw_mask = hw->phy.phy_semaphore_mask; + + if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + + do { + ixgbe_i2c_start(hw); +@@ -2510,7 +2510,7 @@ static s32 ixgbe_get_i2c_ack(struct ixgbe_hw *hw) + + if (ack == 1) { + hw_dbg(hw, "I2C ack was not received.\n"); +- status = IXGBE_ERR_I2C; ++ status = -EIO; + } + + ixgbe_lower_i2c_clk(hw, &i2cctl); +@@ -2582,7 +2582,7 @@ static s32 ixgbe_clock_out_i2c_bit(struct ixgbe_hw *hw, bool data) + udelay(IXGBE_I2C_T_LOW); + } else { + hw_dbg(hw, "I2C data was not set to %X\n", data); +- return IXGBE_ERR_I2C; ++ return -EIO; + } + + return 0; +@@ -2678,7 +2678,7 @@ static s32 ixgbe_set_i2c_data(struct ixgbe_hw *hw, u32 *i2cctl, bool data) + *i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); + if (data != ixgbe_get_i2c_data(hw, i2cctl)) { + hw_dbg(hw, "Error - I2C data was not set to %X.\n", data); +- return IXGBE_ERR_I2C; ++ return -EIO; + } + + return 0; +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +index ea88ac04ab9a..198ab9d97618 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +@@ -1329,7 +1329,7 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) + break; + default: + e_err(drv, "Unhandled Msg %8.8x\n", msgbuf[0]); +- retval = IXGBE_ERR_MBX; ++ retval = -EIO; + break; + } + +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +index 2b00db92b08f..4b19b1282f28 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +@@ -3665,45 +3665,6 @@ struct ixgbe_info { + const u32 *mvals; + }; + +- +-/* Error Codes */ +-#define IXGBE_ERR_EEPROM -1 +-#define IXGBE_ERR_EEPROM_CHECKSUM -2 +-#define IXGBE_ERR_PHY -3 +-#define IXGBE_ERR_CONFIG -4 +-#define IXGBE_ERR_PARAM -5 +-#define IXGBE_ERR_MAC_TYPE -6 +-#define IXGBE_ERR_UNKNOWN_PHY -7 +-#define IXGBE_ERR_LINK_SETUP -8 +-#define IXGBE_ERR_ADAPTER_STOPPED -9 +-#define IXGBE_ERR_INVALID_MAC_ADDR -10 +-#define IXGBE_ERR_DEVICE_NOT_SUPPORTED -11 +-#define IXGBE_ERR_PRIMARY_REQUESTS_PENDING -12 +-#define IXGBE_ERR_INVALID_LINK_SETTINGS -13 +-#define IXGBE_ERR_AUTONEG_NOT_COMPLETE -14 +-#define IXGBE_ERR_RESET_FAILED -15 +-#define IXGBE_ERR_SWFW_SYNC -16 +-#define IXGBE_ERR_PHY_ADDR_INVALID -17 +-#define IXGBE_ERR_I2C -18 +-#define IXGBE_ERR_SFP_NOT_SUPPORTED -19 +-#define IXGBE_ERR_SFP_NOT_PRESENT -20 +-#define IXGBE_ERR_SFP_NO_INIT_SEQ_PRESENT -21 +-#define IXGBE_ERR_NO_SAN_ADDR_PTR -22 +-#define IXGBE_ERR_FDIR_REINIT_FAILED -23 +-#define IXGBE_ERR_EEPROM_VERSION -24 +-#define IXGBE_ERR_NO_SPACE -25 +-#define IXGBE_ERR_OVERTEMP -26 +-#define IXGBE_ERR_FC_NOT_NEGOTIATED -27 +-#define IXGBE_ERR_FC_NOT_SUPPORTED -28 +-#define IXGBE_ERR_SFP_SETUP_NOT_COMPLETE -30 +-#define IXGBE_ERR_PBA_SECTION -31 +-#define IXGBE_ERR_INVALID_ARGUMENT -32 +-#define IXGBE_ERR_HOST_INTERFACE_COMMAND -33 +-#define IXGBE_ERR_FDIR_CMD_INCOMPLETE -38 +-#define IXGBE_ERR_FW_RESP_INVALID -39 +-#define IXGBE_ERR_TOKEN_RETRY -40 +-#define IXGBE_NOT_IMPLEMENTED 0x7FFFFFFF +- + #define IXGBE_FUSES0_GROUP(_i) (0x11158 + ((_i) * 4)) + #define IXGBE_FUSES0_300MHZ BIT(5) + #define IXGBE_FUSES0_REV_MASK (3u << 6) +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +index d5cfb51ff648..15325c549d9b 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +@@ -84,7 +84,7 @@ s32 ixgbe_reset_hw_X540(struct ixgbe_hw *hw) + status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask); + if (status) { + hw_dbg(hw, "semaphore failed with %d", status); +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + } + + ctrl = IXGBE_CTRL_RST; +@@ -103,7 +103,7 @@ s32 ixgbe_reset_hw_X540(struct ixgbe_hw *hw) + } + + if (ctrl & IXGBE_CTRL_RST_MASK) { +- status = IXGBE_ERR_RESET_FAILED; ++ status = -EIO; + hw_dbg(hw, "Reset polling failed to complete.\n"); + } + msleep(100); +@@ -220,7 +220,7 @@ static s32 ixgbe_read_eerd_X540(struct ixgbe_hw *hw, u16 offset, u16 *data) + s32 status; + + if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + + status = ixgbe_read_eerd_generic(hw, offset, data); + +@@ -243,7 +243,7 @@ static s32 ixgbe_read_eerd_buffer_X540(struct ixgbe_hw *hw, + s32 status; + + if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + + status = ixgbe_read_eerd_buffer_generic(hw, offset, words, data); + +@@ -264,7 +264,7 @@ static s32 ixgbe_write_eewr_X540(struct ixgbe_hw *hw, u16 offset, u16 data) + s32 status; + + if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + + status = ixgbe_write_eewr_generic(hw, offset, data); + +@@ -287,7 +287,7 @@ static s32 ixgbe_write_eewr_buffer_X540(struct ixgbe_hw *hw, + s32 status; + + if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + + status = ixgbe_write_eewr_buffer_generic(hw, offset, words, data); + +@@ -324,7 +324,7 @@ static s32 ixgbe_calc_eeprom_checksum_X540(struct ixgbe_hw *hw) + for (i = 0; i < checksum_last_word; i++) { + if (ixgbe_read_eerd_generic(hw, i, &word)) { + hw_dbg(hw, "EEPROM read failed\n"); +- return IXGBE_ERR_EEPROM; ++ return -EIO; + } + checksum += word; + } +@@ -349,7 +349,7 @@ static s32 ixgbe_calc_eeprom_checksum_X540(struct ixgbe_hw *hw) + + if (ixgbe_read_eerd_generic(hw, pointer, &length)) { + hw_dbg(hw, "EEPROM read failed\n"); +- return IXGBE_ERR_EEPROM; ++ return -EIO; + } + + /* Skip pointer section if length is invalid. */ +@@ -360,7 +360,7 @@ static s32 ixgbe_calc_eeprom_checksum_X540(struct ixgbe_hw *hw) + for (j = pointer + 1; j <= pointer + length; j++) { + if (ixgbe_read_eerd_generic(hw, j, &word)) { + hw_dbg(hw, "EEPROM read failed\n"); +- return IXGBE_ERR_EEPROM; ++ return -EIO; + } + checksum += word; + } +@@ -397,7 +397,7 @@ static s32 ixgbe_validate_eeprom_checksum_X540(struct ixgbe_hw *hw, + } + + if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + + status = hw->eeprom.ops.calc_checksum(hw); + if (status < 0) +@@ -418,7 +418,7 @@ static s32 ixgbe_validate_eeprom_checksum_X540(struct ixgbe_hw *hw, + */ + if (read_checksum != checksum) { + hw_dbg(hw, "Invalid EEPROM checksum"); +- status = IXGBE_ERR_EEPROM_CHECKSUM; ++ status = -EIO; + } + + /* If the user cares, return the calculated checksum */ +@@ -455,7 +455,7 @@ static s32 ixgbe_update_eeprom_checksum_X540(struct ixgbe_hw *hw) + } + + if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + + status = hw->eeprom.ops.calc_checksum(hw); + if (status < 0) +@@ -490,7 +490,7 @@ static s32 ixgbe_update_flash_X540(struct ixgbe_hw *hw) + s32 status; + + status = ixgbe_poll_flash_update_done_X540(hw); +- if (status == IXGBE_ERR_EEPROM) { ++ if (status == -EIO) { + hw_dbg(hw, "Flash update time out\n"); + return status; + } +@@ -540,7 +540,7 @@ static s32 ixgbe_poll_flash_update_done_X540(struct ixgbe_hw *hw) + return 0; + udelay(5); + } +- return IXGBE_ERR_EEPROM; ++ return -EIO; + } + + /** +@@ -575,7 +575,7 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) + * SW_FW_SYNC bits (not just NVM) + */ + if (ixgbe_get_swfw_sync_semaphore(hw)) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + + swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw)); + if (!(swfw_sync & (fwmask | swmask | hwmask))) { +@@ -599,7 +599,7 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) + * bits in the SW_FW_SYNC register. + */ + if (ixgbe_get_swfw_sync_semaphore(hw)) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw)); + if (swfw_sync & (fwmask | hwmask)) { + swfw_sync |= swmask; +@@ -622,11 +622,11 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) + rmask |= IXGBE_GSSR_I2C_MASK; + ixgbe_release_swfw_sync_X540(hw, rmask); + ixgbe_release_swfw_sync_semaphore(hw); +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + } + ixgbe_release_swfw_sync_semaphore(hw); + +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + } + + /** +@@ -680,7 +680,7 @@ static s32 ixgbe_get_swfw_sync_semaphore(struct ixgbe_hw *hw) + if (i == timeout) { + hw_dbg(hw, + "Software semaphore SMBI between device drivers not granted.\n"); +- return IXGBE_ERR_EEPROM; ++ return -EIO; + } + + /* Now get the semaphore between SW/FW through the REGSMP bit */ +@@ -697,7 +697,7 @@ static s32 ixgbe_get_swfw_sync_semaphore(struct ixgbe_hw *hw) + */ + hw_dbg(hw, "REGSMP Software NVM semaphore not granted\n"); + ixgbe_release_swfw_sync_semaphore(hw); +- return IXGBE_ERR_EEPROM; ++ return -EIO; + } + + /** +@@ -768,7 +768,7 @@ s32 ixgbe_blink_led_start_X540(struct ixgbe_hw *hw, u32 index) + bool link_up; + + if (index > 3) +- return IXGBE_ERR_PARAM; ++ return -EINVAL; + + /* Link should be up in order for the blink bit in the LED control + * register to work. Force link and speed in the MAC if link is down. +@@ -804,7 +804,7 @@ s32 ixgbe_blink_led_stop_X540(struct ixgbe_hw *hw, u32 index) + u32 ledctl_reg; + + if (index > 3) +- return IXGBE_ERR_PARAM; ++ return -EINVAL; + + /* Restore the LED to its default value. */ + ledctl_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +index aa4bf6c9a2f7..19de26520a88 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +@@ -206,13 +206,13 @@ static s32 ixgbe_reset_cs4227(struct ixgbe_hw *hw) + } + if (retry == IXGBE_CS4227_RETRIES) { + hw_err(hw, "CS4227 reset did not complete\n"); +- return IXGBE_ERR_PHY; ++ return -EIO; + } + + status = ixgbe_read_cs4227(hw, IXGBE_CS4227_EEPROM_STATUS, &value); + if (status || !(value & IXGBE_CS4227_EEPROM_LOAD_OK)) { + hw_err(hw, "CS4227 EEPROM did not load successfully\n"); +- return IXGBE_ERR_PHY; ++ return -EIO; + } + + return 0; +@@ -350,13 +350,13 @@ static s32 ixgbe_identify_phy_x550em(struct ixgbe_hw *hw) + static s32 ixgbe_read_phy_reg_x550em(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u16 *phy_data) + { +- return IXGBE_NOT_IMPLEMENTED; ++ return -EOPNOTSUPP; + } + + static s32 ixgbe_write_phy_reg_x550em(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u16 phy_data) + { +- return IXGBE_NOT_IMPLEMENTED; ++ return -EOPNOTSUPP; + } + + /** +@@ -463,7 +463,7 @@ s32 ixgbe_fw_phy_activity(struct ixgbe_hw *hw, u16 activity, + --retries; + } while (retries > 0); + +- return IXGBE_ERR_HOST_INTERFACE_COMMAND; ++ return -EIO; + } + + static const struct { +@@ -511,7 +511,7 @@ static s32 ixgbe_get_phy_id_fw(struct ixgbe_hw *hw) + hw->phy.id |= phy_id_lo & IXGBE_PHY_REVISION_MASK; + hw->phy.revision = phy_id_lo & ~IXGBE_PHY_REVISION_MASK; + if (!hw->phy.id || hw->phy.id == IXGBE_PHY_REVISION_MASK) +- return IXGBE_ERR_PHY_ADDR_INVALID; ++ return -EFAULT; + + hw->phy.autoneg_advertised = hw->phy.speeds_supported; + hw->phy.eee_speeds_supported = IXGBE_LINK_SPEED_100_FULL | +@@ -568,7 +568,7 @@ static s32 ixgbe_setup_fw_link(struct ixgbe_hw *hw) + + if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { + hw_err(hw, "rx_pause not valid in strict IEEE mode\n"); +- return IXGBE_ERR_INVALID_LINK_SETTINGS; ++ return -EINVAL; + } + + switch (hw->fc.requested_mode) { +@@ -675,7 +675,7 @@ static s32 ixgbe_iosf_wait(struct ixgbe_hw *hw, u32 *ctrl) + *ctrl = command; + if (i == IXGBE_MDIO_COMMAND_TIMEOUT) { + hw_dbg(hw, "IOSF wait timed out\n"); +- return IXGBE_ERR_PHY; ++ return -EIO; + } + + return 0; +@@ -715,7 +715,7 @@ static s32 ixgbe_read_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr, + error = (command & IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK) >> + IXGBE_SB_IOSF_CTRL_CMPL_ERR_SHIFT; + hw_dbg(hw, "Failed to read, error %x\n", error); +- return IXGBE_ERR_PHY; ++ return -EIO; + } + + if (!ret) +@@ -750,9 +750,9 @@ static s32 ixgbe_get_phy_token(struct ixgbe_hw *hw) + if (token_cmd.hdr.cmd_or_resp.ret_status == FW_PHY_TOKEN_OK) + return 0; + if (token_cmd.hdr.cmd_or_resp.ret_status != FW_PHY_TOKEN_RETRY) +- return IXGBE_ERR_FW_RESP_INVALID; ++ return -EIO; + +- return IXGBE_ERR_TOKEN_RETRY; ++ return -EAGAIN; + } + + /** +@@ -778,7 +778,7 @@ static s32 ixgbe_put_phy_token(struct ixgbe_hw *hw) + return status; + if (token_cmd.hdr.cmd_or_resp.ret_status == FW_PHY_TOKEN_OK) + return 0; +- return IXGBE_ERR_FW_RESP_INVALID; ++ return -EIO; + } + + /** +@@ -942,7 +942,7 @@ static s32 ixgbe_checksum_ptr_x550(struct ixgbe_hw *hw, u16 ptr, + local_buffer = buf; + } else { + if (buffer_size < ptr) +- return IXGBE_ERR_PARAM; ++ return -EINVAL; + local_buffer = &buffer[ptr]; + } + +@@ -960,7 +960,7 @@ static s32 ixgbe_checksum_ptr_x550(struct ixgbe_hw *hw, u16 ptr, + } + + if (buffer && ((u32)start + (u32)length > buffer_size)) +- return IXGBE_ERR_PARAM; ++ return -EINVAL; + + for (i = start; length; i++, length--) { + if (i == bufsz && !buffer) { +@@ -1012,7 +1012,7 @@ static s32 ixgbe_calc_checksum_X550(struct ixgbe_hw *hw, u16 *buffer, + local_buffer = eeprom_ptrs; + } else { + if (buffer_size < IXGBE_EEPROM_LAST_WORD) +- return IXGBE_ERR_PARAM; ++ return -EINVAL; + local_buffer = buffer; + } + +@@ -1148,7 +1148,7 @@ static s32 ixgbe_validate_eeprom_checksum_X550(struct ixgbe_hw *hw, + * calculated checksum + */ + if (read_checksum != checksum) { +- status = IXGBE_ERR_EEPROM_CHECKSUM; ++ status = -EIO; + hw_dbg(hw, "Invalid EEPROM checksum"); + } + +@@ -1203,7 +1203,7 @@ static s32 ixgbe_write_ee_hostif_X550(struct ixgbe_hw *hw, u16 offset, u16 data) + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM); + } else { + hw_dbg(hw, "write ee hostif failed to get semaphore"); +- status = IXGBE_ERR_SWFW_SYNC; ++ status = -EBUSY; + } + + return status; +@@ -1415,7 +1415,7 @@ static s32 ixgbe_write_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr, + error = (command & IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK) >> + IXGBE_SB_IOSF_CTRL_CMPL_ERR_SHIFT; + hw_dbg(hw, "Failed to write, error %x\n", error); +- return IXGBE_ERR_PHY; ++ return -EIO; + } + + out: +@@ -1558,7 +1558,7 @@ static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed) + + /* iXFI is only supported with X552 */ + if (mac->type != ixgbe_mac_X550EM_x) +- return IXGBE_ERR_LINK_SETUP; ++ return -EIO; + + /* Disable AN and force speed to 10G Serial. */ + status = ixgbe_read_iosf_sb_reg_x550(hw, +@@ -1580,7 +1580,7 @@ static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed) + break; + default: + /* Other link speeds are not supported by internal KR PHY. */ +- return IXGBE_ERR_LINK_SETUP; ++ return -EINVAL; + } + + status = ixgbe_write_iosf_sb_reg_x550(hw, +@@ -1611,7 +1611,7 @@ static s32 ixgbe_supported_sfp_modules_X550em(struct ixgbe_hw *hw, bool *linear) + { + switch (hw->phy.sfp_type) { + case ixgbe_sfp_type_not_present: +- return IXGBE_ERR_SFP_NOT_PRESENT; ++ return -ENOENT; + case ixgbe_sfp_type_da_cu_core0: + case ixgbe_sfp_type_da_cu_core1: + *linear = true; +@@ -1630,7 +1630,7 @@ static s32 ixgbe_supported_sfp_modules_X550em(struct ixgbe_hw *hw, bool *linear) + case ixgbe_sfp_type_1g_cu_core0: + case ixgbe_sfp_type_1g_cu_core1: + default: +- return IXGBE_ERR_SFP_NOT_SUPPORTED; ++ return -EOPNOTSUPP; + } + + return 0; +@@ -1660,7 +1660,7 @@ ixgbe_setup_mac_link_sfp_x550em(struct ixgbe_hw *hw, + * there is no reason to configure CS4227 and SFP not present error is + * not accepted in the setup MAC link flow. + */ +- if (status == IXGBE_ERR_SFP_NOT_PRESENT) ++ if (status == -ENOENT) + return 0; + + if (status) +@@ -1718,7 +1718,7 @@ static s32 ixgbe_setup_sfi_x550a(struct ixgbe_hw *hw, ixgbe_link_speed *speed) + break; + default: + /* Other link speeds are not supported by internal PHY. */ +- return IXGBE_ERR_LINK_SETUP; ++ return -EINVAL; + } + + (void)mac->ops.write_iosf_sb_reg(hw, +@@ -1803,7 +1803,7 @@ ixgbe_setup_mac_link_sfp_n(struct ixgbe_hw *hw, ixgbe_link_speed speed, + /* If no SFP module present, then return success. Return success since + * SFP not present error is not excepted in the setup MAC link flow. + */ +- if (ret_val == IXGBE_ERR_SFP_NOT_PRESENT) ++ if (ret_val == -ENOENT) + return 0; + + if (ret_val) +@@ -1853,7 +1853,7 @@ ixgbe_setup_mac_link_sfp_x550a(struct ixgbe_hw *hw, ixgbe_link_speed speed, + /* If no SFP module present, then return success. Return success since + * SFP not present error is not excepted in the setup MAC link flow. + */ +- if (ret_val == IXGBE_ERR_SFP_NOT_PRESENT) ++ if (ret_val == -ENOENT) + return 0; + + if (ret_val) +@@ -1863,7 +1863,7 @@ ixgbe_setup_mac_link_sfp_x550a(struct ixgbe_hw *hw, ixgbe_link_speed speed, + ixgbe_setup_kr_speed_x550em(hw, speed); + + if (hw->phy.mdio.prtad == MDIO_PRTAD_NONE) +- return IXGBE_ERR_PHY_ADDR_INVALID; ++ return -EFAULT; + + /* Get external PHY SKU id */ + ret_val = hw->phy.ops.read_reg(hw, IXGBE_CS4227_EFUSE_PDF_SKU, +@@ -1962,7 +1962,7 @@ static s32 ixgbe_check_link_t_X550em(struct ixgbe_hw *hw, + u16 i, autoneg_status; + + if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_copper) +- return IXGBE_ERR_CONFIG; ++ return -EIO; + + status = ixgbe_check_mac_link_generic(hw, speed, link_up, + link_up_wait_to_complete); +@@ -2145,9 +2145,9 @@ static s32 ixgbe_setup_sgmii_fw(struct ixgbe_hw *hw, ixgbe_link_speed speed, + */ + static void ixgbe_fc_autoneg_sgmii_x550em_a(struct ixgbe_hw *hw) + { +- s32 status = IXGBE_ERR_FC_NOT_NEGOTIATED; + u32 info[FW_PHY_ACT_DATA_COUNT] = { 0 }; + ixgbe_link_speed speed; ++ s32 status = -EIO; + bool link_up; + + /* AN should have completed when the cable was plugged in. +@@ -2165,7 +2165,7 @@ static void ixgbe_fc_autoneg_sgmii_x550em_a(struct ixgbe_hw *hw) + /* Check if auto-negotiation has completed */ + status = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_GET_LINK_INFO, &info); + if (status || !(info[0] & FW_PHY_ACT_GET_LINK_INFO_AN_COMPLETE)) { +- status = IXGBE_ERR_FC_NOT_NEGOTIATED; ++ status = -EIO; + goto out; + } + +@@ -2692,7 +2692,7 @@ static s32 ixgbe_setup_internal_phy_t_x550em(struct ixgbe_hw *hw) + u16 speed; + + if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_copper) +- return IXGBE_ERR_CONFIG; ++ return -EIO; + + if (!(hw->mac.type == ixgbe_mac_X550EM_x && + !(hw->phy.nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE))) { +@@ -2735,7 +2735,7 @@ static s32 ixgbe_setup_internal_phy_t_x550em(struct ixgbe_hw *hw) + break; + default: + /* Internal PHY does not support anything else */ +- return IXGBE_ERR_INVALID_LINK_SETTINGS; ++ return -EINVAL; + } + + return ixgbe_setup_ixfi_x550em(hw, &force_speed); +@@ -2767,7 +2767,7 @@ static s32 ixgbe_led_on_t_x550em(struct ixgbe_hw *hw, u32 led_idx) + u16 phy_data; + + if (led_idx >= IXGBE_X557_MAX_LED_INDEX) +- return IXGBE_ERR_PARAM; ++ return -EINVAL; + + /* To turn on the LED, set mode to ON. */ + hw->phy.ops.read_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx, +@@ -2789,7 +2789,7 @@ static s32 ixgbe_led_off_t_x550em(struct ixgbe_hw *hw, u32 led_idx) + u16 phy_data; + + if (led_idx >= IXGBE_X557_MAX_LED_INDEX) +- return IXGBE_ERR_PARAM; ++ return -EINVAL; + + /* To turn on the LED, set mode to ON. */ + hw->phy.ops.read_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx, +@@ -2813,8 +2813,9 @@ static s32 ixgbe_led_off_t_x550em(struct ixgbe_hw *hw, u32 led_idx) + * + * Sends driver version number to firmware through the manageability + * block. On success return 0 +- * else returns IXGBE_ERR_SWFW_SYNC when encountering an error acquiring +- * semaphore or IXGBE_ERR_HOST_INTERFACE_COMMAND when command fails. ++ * else returns -EBUSY when encountering an error acquiring ++ * semaphore, -EIO when command fails or -ENIVAL when incorrect ++ * params passed. + **/ + static s32 ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min, + u8 build, u8 sub, u16 len, +@@ -2825,7 +2826,7 @@ static s32 ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min, + int i; + + if (!len || !driver_ver || (len > sizeof(fw_cmd.driver_string))) +- return IXGBE_ERR_INVALID_ARGUMENT; ++ return -EINVAL; + + fw_cmd.hdr.cmd = FW_CEM_CMD_DRIVER_INFO; + fw_cmd.hdr.buf_len = FW_CEM_CMD_DRIVER_INFO_LEN + len; +@@ -2850,7 +2851,7 @@ static s32 ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min, + + if (fw_cmd.hdr.cmd_or_resp.ret_status != + FW_CEM_RESP_STATUS_SUCCESS) +- return IXGBE_ERR_HOST_INTERFACE_COMMAND; ++ return -EIO; + return 0; + } + +@@ -2907,7 +2908,7 @@ static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *hw) + /* Validate the requested mode */ + if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { + hw_err(hw, "ixgbe_fc_rx_pause not valid in strict IEEE mode\n"); +- return IXGBE_ERR_INVALID_LINK_SETTINGS; ++ return -EINVAL; + } + + /* 10gig parts do not have a word in the EEPROM to determine the +@@ -2942,7 +2943,7 @@ static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *hw) + break; + default: + hw_err(hw, "Flow control param set incorrectly\n"); +- return IXGBE_ERR_CONFIG; ++ return -EIO; + } + + switch (hw->device_id) { +@@ -2986,8 +2987,8 @@ static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *hw) + static void ixgbe_fc_autoneg_backplane_x550em_a(struct ixgbe_hw *hw) + { + u32 link_s1, lp_an_page_low, an_cntl_1; +- s32 status = IXGBE_ERR_FC_NOT_NEGOTIATED; + ixgbe_link_speed speed; ++ s32 status = -EIO; + bool link_up; + + /* AN should have completed when the cable was plugged in. +@@ -3013,7 +3014,7 @@ static void ixgbe_fc_autoneg_backplane_x550em_a(struct ixgbe_hw *hw) + + if (status || (link_s1 & IXGBE_KRM_LINK_S1_MAC_AN_COMPLETE) == 0) { + hw_dbg(hw, "Auto-Negotiation did not complete\n"); +- status = IXGBE_ERR_FC_NOT_NEGOTIATED; ++ status = -EIO; + goto out; + } + +@@ -3251,8 +3252,7 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw) + + /* Identify the PHY or SFP module */ + ret_val = phy->ops.identify(hw); +- if (ret_val == IXGBE_ERR_SFP_NOT_SUPPORTED || +- ret_val == IXGBE_ERR_PHY_ADDR_INVALID) ++ if (ret_val == -EOPNOTSUPP || ret_val == -EFAULT) + return ret_val; + + /* Setup function pointers based on detected hardware */ +@@ -3460,8 +3460,7 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) + + /* PHY ops must be identified and initialized prior to reset */ + status = hw->phy.ops.init(hw); +- if (status == IXGBE_ERR_SFP_NOT_SUPPORTED || +- status == IXGBE_ERR_PHY_ADDR_INVALID) ++ if (status == -EOPNOTSUPP || status == -EFAULT) + return status; + + /* start the external PHY */ +@@ -3477,7 +3476,7 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) + hw->phy.sfp_setup_needed = false; + } + +- if (status == IXGBE_ERR_SFP_NOT_SUPPORTED) ++ if (status == -EOPNOTSUPP) + return status; + + /* Reset PHY */ +@@ -3501,7 +3500,7 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) + status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask); + if (status) { + hw_dbg(hw, "semaphore failed with %d", status); +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + } + + ctrl |= IXGBE_READ_REG(hw, IXGBE_CTRL); +@@ -3519,7 +3518,7 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) + } + + if (ctrl & IXGBE_CTRL_RST_MASK) { +- status = IXGBE_ERR_RESET_FAILED; ++ status = -EIO; + hw_dbg(hw, "Reset polling failed to complete.\n"); + } + +@@ -3615,7 +3614,7 @@ static s32 ixgbe_setup_fc_backplane_x550em_a(struct ixgbe_hw *hw) + /* Validate the requested mode */ + if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { + hw_err(hw, "ixgbe_fc_rx_pause not valid in strict IEEE mode\n"); +- return IXGBE_ERR_INVALID_LINK_SETTINGS; ++ return -EINVAL; + } + + if (hw->fc.requested_mode == ixgbe_fc_default) +@@ -3672,7 +3671,7 @@ static s32 ixgbe_setup_fc_backplane_x550em_a(struct ixgbe_hw *hw) + break; + default: + hw_err(hw, "Flow control param set incorrectly\n"); +- return IXGBE_ERR_CONFIG; ++ return -EIO; + } + + status = hw->mac.ops.write_iosf_sb_reg(hw, +@@ -3768,7 +3767,7 @@ static s32 ixgbe_acquire_swfw_sync_x550em_a(struct ixgbe_hw *hw, u32 mask) + return 0; + if (hmask) + ixgbe_release_swfw_sync_X540(hw, hmask); +- if (status != IXGBE_ERR_TOKEN_RETRY) ++ if (status != -EAGAIN) + return status; + msleep(FW_PHY_TOKEN_DELAY); + } +@@ -3812,7 +3811,7 @@ static s32 ixgbe_read_phy_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr, + s32 status; + + if (hw->mac.ops.acquire_swfw_sync(hw, mask)) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + + status = hw->phy.ops.read_reg_mdi(hw, reg_addr, device_type, phy_data); + +@@ -3838,7 +3837,7 @@ static s32 ixgbe_write_phy_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr, + s32 status; + + if (hw->mac.ops.acquire_swfw_sync(hw, mask)) +- return IXGBE_ERR_SWFW_SYNC; ++ return -EBUSY; + + status = ixgbe_write_phy_reg_mdi(hw, reg_addr, device_type, phy_data); + hw->mac.ops.release_swfw_sync(hw, mask); +-- +2.43.0 + diff --git a/queue-6.6/kunit-run-test-suites-only-after-module-initializati.patch b/queue-6.6/kunit-run-test-suites-only-after-module-initializati.patch new file mode 100644 index 00000000000..6c5124de797 --- /dev/null +++ b/queue-6.6/kunit-run-test-suites-only-after-module-initializati.patch @@ -0,0 +1,137 @@ +From a00f99d94312a4ef2f3b64fb622ffc5cf854da99 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 10 Jan 2024 16:59:47 +0100 +Subject: kunit: run test suites only after module initialization completes + +From: Marco Pagani + +[ Upstream commit a1af6a2bfa0cb46d70b7df5352993e750da6c79b ] + +Commit 2810c1e99867 ("kunit: Fix wild-memory-access bug in +kunit_free_suite_set()") fixed a wild-memory-access bug that could have +happened during the loading phase of test suites built and executed as +loadable modules. However, it also introduced a problematic side effect +that causes test suites modules to crash when they attempt to register +fake devices. + +When a module is loaded, it traverses the MODULE_STATE_UNFORMED and +MODULE_STATE_COMING states before reaching the normal operating state +MODULE_STATE_LIVE. Finally, when the module is removed, it moves to +MODULE_STATE_GOING before being released. However, if the loading +function load_module() fails between complete_formation() and +do_init_module(), the module goes directly from MODULE_STATE_COMING to +MODULE_STATE_GOING without passing through MODULE_STATE_LIVE. + +This behavior was causing kunit_module_exit() to be called without +having first executed kunit_module_init(). Since kunit_module_exit() is +responsible for freeing the memory allocated by kunit_module_init() +through kunit_filter_suites(), this behavior was resulting in a +wild-memory-access bug. + +Commit 2810c1e99867 ("kunit: Fix wild-memory-access bug in +kunit_free_suite_set()") fixed this issue by running the tests when the +module is still in MODULE_STATE_COMING. However, modules in that state +are not fully initialized, lacking sysfs kobjects. Therefore, if a test +module attempts to register a fake device, it will inevitably crash. + +This patch proposes a different approach to fix the original +wild-memory-access bug while restoring the normal module execution flow +by making kunit_module_exit() able to detect if kunit_module_init() has +previously initialized the tests suite set. In this way, test modules +can once again register fake devices without crashing. + +This behavior is achieved by checking whether mod->kunit_suites is a +virtual or direct mapping address. If it is a virtual address, then +kunit_module_init() has allocated the suite_set in kunit_filter_suites() +using kmalloc_array(). On the contrary, if mod->kunit_suites is still +pointing to the original address that was set when looking up the +.kunit_test_suites section of the module, then the loading phase has +failed and there's no memory to be freed. + +v4: +- rebased on 6.8 +- noted that kunit_filter_suites() must return a virtual address +v3: +- add a comment to clarify why the start address is checked +v2: +- add include + +Fixes: 2810c1e99867 ("kunit: Fix wild-memory-access bug in kunit_free_suite_set()") +Reviewed-by: David Gow +Tested-by: Rae Moar +Tested-by: Richard Fitzgerald +Reviewed-by: Javier Martinez Canillas +Signed-off-by: Marco Pagani +Signed-off-by: Shuah Khan +Signed-off-by: Sasha Levin +--- + lib/kunit/executor.c | 4 ++++ + lib/kunit/test.c | 14 +++++++++++--- + 2 files changed, 15 insertions(+), 3 deletions(-) + +diff --git a/lib/kunit/executor.c b/lib/kunit/executor.c +index 1236b3cd2fbb..51013feba58b 100644 +--- a/lib/kunit/executor.c ++++ b/lib/kunit/executor.c +@@ -144,6 +144,10 @@ void kunit_free_suite_set(struct kunit_suite_set suite_set) + kfree(suite_set.start); + } + ++/* ++ * Filter and reallocate test suites. Must return the filtered test suites set ++ * allocated at a valid virtual address or NULL in case of error. ++ */ + struct kunit_suite_set + kunit_filter_suites(const struct kunit_suite_set *suite_set, + const char *filter_glob, +diff --git a/lib/kunit/test.c b/lib/kunit/test.c +index 7452d1a2acd9..1d151f6dc1cd 100644 +--- a/lib/kunit/test.c ++++ b/lib/kunit/test.c +@@ -16,6 +16,7 @@ + #include + #include + #include ++#include + + #include "debugfs.h" + #include "hooks-impl.h" +@@ -807,12 +808,19 @@ static void kunit_module_exit(struct module *mod) + }; + const char *action = kunit_action(); + ++ /* ++ * Check if the start address is a valid virtual address to detect ++ * if the module load sequence has failed and the suite set has not ++ * been initialized and filtered. ++ */ ++ if (!suite_set.start || !virt_addr_valid(suite_set.start)) ++ return; ++ + if (!action) + __kunit_test_suites_exit(mod->kunit_suites, + mod->num_kunit_suites); + +- if (suite_set.start) +- kunit_free_suite_set(suite_set); ++ kunit_free_suite_set(suite_set); + } + + static int kunit_module_notify(struct notifier_block *nb, unsigned long val, +@@ -822,12 +830,12 @@ static int kunit_module_notify(struct notifier_block *nb, unsigned long val, + + switch (val) { + case MODULE_STATE_LIVE: ++ kunit_module_init(mod); + break; + case MODULE_STATE_GOING: + kunit_module_exit(mod); + break; + case MODULE_STATE_COMING: +- kunit_module_init(mod); + break; + case MODULE_STATE_UNFORMED: + break; +-- +2.43.0 + diff --git a/queue-6.6/llc-call-sock_orphan-at-release-time.patch b/queue-6.6/llc-call-sock_orphan-at-release-time.patch new file mode 100644 index 00000000000..b775b753e78 --- /dev/null +++ b/queue-6.6/llc-call-sock_orphan-at-release-time.patch @@ -0,0 +1,205 @@ +From b6cd1b9f03a8479ae17134b2bef0ecb381191846 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 26 Jan 2024 16:55:32 +0000 +Subject: llc: call sock_orphan() at release time + +From: Eric Dumazet + +[ Upstream commit aa2b2eb3934859904c287bf5434647ba72e14c1c ] + +syzbot reported an interesting trace [1] caused by a stale sk->sk_wq +pointer in a closed llc socket. + +In commit ff7b11aa481f ("net: socket: set sock->sk to NULL after +calling proto_ops::release()") Eric Biggers hinted that some protocols +are missing a sock_orphan(), we need to perform a full audit. + +In net-next, I plan to clear sock->sk from sock_orphan() and +amend Eric patch to add a warning. + +[1] + BUG: KASAN: slab-use-after-free in list_empty include/linux/list.h:373 [inline] + BUG: KASAN: slab-use-after-free in waitqueue_active include/linux/wait.h:127 [inline] + BUG: KASAN: slab-use-after-free in sock_def_write_space_wfree net/core/sock.c:3384 [inline] + BUG: KASAN: slab-use-after-free in sock_wfree+0x9a8/0x9d0 net/core/sock.c:2468 +Read of size 8 at addr ffff88802f4fc880 by task ksoftirqd/1/27 + +CPU: 1 PID: 27 Comm: ksoftirqd/1 Not tainted 6.8.0-rc1-syzkaller-00049-g6098d87eaf31 #0 +Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-debian-1.16.2-1 04/01/2014 +Call Trace: + + __dump_stack lib/dump_stack.c:88 [inline] + dump_stack_lvl+0xd9/0x1b0 lib/dump_stack.c:106 + print_address_description mm/kasan/report.c:377 [inline] + print_report+0xc4/0x620 mm/kasan/report.c:488 + kasan_report+0xda/0x110 mm/kasan/report.c:601 + list_empty include/linux/list.h:373 [inline] + waitqueue_active include/linux/wait.h:127 [inline] + sock_def_write_space_wfree net/core/sock.c:3384 [inline] + sock_wfree+0x9a8/0x9d0 net/core/sock.c:2468 + skb_release_head_state+0xa3/0x2b0 net/core/skbuff.c:1080 + skb_release_all net/core/skbuff.c:1092 [inline] + napi_consume_skb+0x119/0x2b0 net/core/skbuff.c:1404 + e1000_unmap_and_free_tx_resource+0x144/0x200 drivers/net/ethernet/intel/e1000/e1000_main.c:1970 + e1000_clean_tx_irq drivers/net/ethernet/intel/e1000/e1000_main.c:3860 [inline] + e1000_clean+0x4a1/0x26e0 drivers/net/ethernet/intel/e1000/e1000_main.c:3801 + __napi_poll.constprop.0+0xb4/0x540 net/core/dev.c:6576 + napi_poll net/core/dev.c:6645 [inline] + net_rx_action+0x956/0xe90 net/core/dev.c:6778 + __do_softirq+0x21a/0x8de kernel/softirq.c:553 + run_ksoftirqd kernel/softirq.c:921 [inline] + run_ksoftirqd+0x31/0x60 kernel/softirq.c:913 + smpboot_thread_fn+0x660/0xa10 kernel/smpboot.c:164 + kthread+0x2c6/0x3a0 kernel/kthread.c:388 + ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:147 + ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:242 + + +Allocated by task 5167: + kasan_save_stack+0x33/0x50 mm/kasan/common.c:47 + kasan_save_track+0x14/0x30 mm/kasan/common.c:68 + unpoison_slab_object mm/kasan/common.c:314 [inline] + __kasan_slab_alloc+0x81/0x90 mm/kasan/common.c:340 + kasan_slab_alloc include/linux/kasan.h:201 [inline] + slab_post_alloc_hook mm/slub.c:3813 [inline] + slab_alloc_node mm/slub.c:3860 [inline] + kmem_cache_alloc_lru+0x142/0x6f0 mm/slub.c:3879 + alloc_inode_sb include/linux/fs.h:3019 [inline] + sock_alloc_inode+0x25/0x1c0 net/socket.c:308 + alloc_inode+0x5d/0x220 fs/inode.c:260 + new_inode_pseudo+0x16/0x80 fs/inode.c:1005 + sock_alloc+0x40/0x270 net/socket.c:634 + __sock_create+0xbc/0x800 net/socket.c:1535 + sock_create net/socket.c:1622 [inline] + __sys_socket_create net/socket.c:1659 [inline] + __sys_socket+0x14c/0x260 net/socket.c:1706 + __do_sys_socket net/socket.c:1720 [inline] + __se_sys_socket net/socket.c:1718 [inline] + __x64_sys_socket+0x72/0xb0 net/socket.c:1718 + do_syscall_x64 arch/x86/entry/common.c:52 [inline] + do_syscall_64+0xd3/0x250 arch/x86/entry/common.c:83 + entry_SYSCALL_64_after_hwframe+0x63/0x6b + +Freed by task 0: + kasan_save_stack+0x33/0x50 mm/kasan/common.c:47 + kasan_save_track+0x14/0x30 mm/kasan/common.c:68 + kasan_save_free_info+0x3f/0x60 mm/kasan/generic.c:640 + poison_slab_object mm/kasan/common.c:241 [inline] + __kasan_slab_free+0x121/0x1b0 mm/kasan/common.c:257 + kasan_slab_free include/linux/kasan.h:184 [inline] + slab_free_hook mm/slub.c:2121 [inline] + slab_free mm/slub.c:4299 [inline] + kmem_cache_free+0x129/0x350 mm/slub.c:4363 + i_callback+0x43/0x70 fs/inode.c:249 + rcu_do_batch kernel/rcu/tree.c:2158 [inline] + rcu_core+0x819/0x1680 kernel/rcu/tree.c:2433 + __do_softirq+0x21a/0x8de kernel/softirq.c:553 + +Last potentially related work creation: + kasan_save_stack+0x33/0x50 mm/kasan/common.c:47 + __kasan_record_aux_stack+0xba/0x100 mm/kasan/generic.c:586 + __call_rcu_common.constprop.0+0x9a/0x7b0 kernel/rcu/tree.c:2683 + destroy_inode+0x129/0x1b0 fs/inode.c:315 + iput_final fs/inode.c:1739 [inline] + iput.part.0+0x560/0x7b0 fs/inode.c:1765 + iput+0x5c/0x80 fs/inode.c:1755 + dentry_unlink_inode+0x292/0x430 fs/dcache.c:400 + __dentry_kill+0x1ca/0x5f0 fs/dcache.c:603 + dput.part.0+0x4ac/0x9a0 fs/dcache.c:845 + dput+0x1f/0x30 fs/dcache.c:835 + __fput+0x3b9/0xb70 fs/file_table.c:384 + task_work_run+0x14d/0x240 kernel/task_work.c:180 + exit_task_work include/linux/task_work.h:38 [inline] + do_exit+0xa8a/0x2ad0 kernel/exit.c:871 + do_group_exit+0xd4/0x2a0 kernel/exit.c:1020 + __do_sys_exit_group kernel/exit.c:1031 [inline] + __se_sys_exit_group kernel/exit.c:1029 [inline] + __x64_sys_exit_group+0x3e/0x50 kernel/exit.c:1029 + do_syscall_x64 arch/x86/entry/common.c:52 [inline] + do_syscall_64+0xd3/0x250 arch/x86/entry/common.c:83 + entry_SYSCALL_64_after_hwframe+0x63/0x6b + +The buggy address belongs to the object at ffff88802f4fc800 + which belongs to the cache sock_inode_cache of size 1408 +The buggy address is located 128 bytes inside of + freed 1408-byte region [ffff88802f4fc800, ffff88802f4fcd80) + +The buggy address belongs to the physical page: +page:ffffea0000bd3e00 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x2f4f8 +head:ffffea0000bd3e00 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0 +anon flags: 0xfff00000000840(slab|head|node=0|zone=1|lastcpupid=0x7ff) +page_type: 0xffffffff() +raw: 00fff00000000840 ffff888013b06b40 0000000000000000 0000000000000001 +raw: 0000000000000000 0000000080150015 00000001ffffffff 0000000000000000 +page dumped because: kasan: bad access detected +page_owner tracks the page as allocated +page last allocated via order 3, migratetype Reclaimable, gfp_mask 0xd20d0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC|__GFP_RECLAIMABLE), pid 4956, tgid 4956 (sshd), ts 31423924727, free_ts 0 + set_page_owner include/linux/page_owner.h:31 [inline] + post_alloc_hook+0x2d0/0x350 mm/page_alloc.c:1533 + prep_new_page mm/page_alloc.c:1540 [inline] + get_page_from_freelist+0xa28/0x3780 mm/page_alloc.c:3311 + __alloc_pages+0x22f/0x2440 mm/page_alloc.c:4567 + __alloc_pages_node include/linux/gfp.h:238 [inline] + alloc_pages_node include/linux/gfp.h:261 [inline] + alloc_slab_page mm/slub.c:2190 [inline] + allocate_slab mm/slub.c:2354 [inline] + new_slab+0xcc/0x3a0 mm/slub.c:2407 + ___slab_alloc+0x4af/0x19a0 mm/slub.c:3540 + __slab_alloc.constprop.0+0x56/0xa0 mm/slub.c:3625 + __slab_alloc_node mm/slub.c:3678 [inline] + slab_alloc_node mm/slub.c:3850 [inline] + kmem_cache_alloc_lru+0x379/0x6f0 mm/slub.c:3879 + alloc_inode_sb include/linux/fs.h:3019 [inline] + sock_alloc_inode+0x25/0x1c0 net/socket.c:308 + alloc_inode+0x5d/0x220 fs/inode.c:260 + new_inode_pseudo+0x16/0x80 fs/inode.c:1005 + sock_alloc+0x40/0x270 net/socket.c:634 + __sock_create+0xbc/0x800 net/socket.c:1535 + sock_create net/socket.c:1622 [inline] + __sys_socket_create net/socket.c:1659 [inline] + __sys_socket+0x14c/0x260 net/socket.c:1706 + __do_sys_socket net/socket.c:1720 [inline] + __se_sys_socket net/socket.c:1718 [inline] + __x64_sys_socket+0x72/0xb0 net/socket.c:1718 + do_syscall_x64 arch/x86/entry/common.c:52 [inline] + do_syscall_64+0xd3/0x250 arch/x86/entry/common.c:83 + entry_SYSCALL_64_after_hwframe+0x63/0x6b +page_owner free stack trace missing + +Memory state around the buggy address: + ffff88802f4fc780: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc + ffff88802f4fc800: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb +>ffff88802f4fc880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb + ^ + ffff88802f4fc900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb + ffff88802f4fc980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb + +Fixes: 43815482370c ("net: sock_def_readable() and friends RCU conversion") +Reported-and-tested-by: syzbot+32b89eaa102b372ff76d@syzkaller.appspotmail.com +Signed-off-by: Eric Dumazet +Cc: Eric Biggers +Cc: Kuniyuki Iwashima +Reviewed-by: Kuniyuki Iwashima +Link: https://lore.kernel.org/r/20240126165532.3396702-1-edumazet@google.com +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/llc/af_llc.c | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c +index 20551cfb7da6..fde1140d899e 100644 +--- a/net/llc/af_llc.c ++++ b/net/llc/af_llc.c +@@ -226,6 +226,8 @@ static int llc_ui_release(struct socket *sock) + } + netdev_put(llc->dev, &llc->dev_tracker); + sock_put(sk); ++ sock_orphan(sk); ++ sock->sk = NULL; + llc_sk_free(sk); + out: + return 0; +-- +2.43.0 + diff --git a/queue-6.6/net-dsa-mt7530-fix-10m-100m-speed-on-mt7988-switch.patch b/queue-6.6/net-dsa-mt7530-fix-10m-100m-speed-on-mt7988-switch.patch new file mode 100644 index 00000000000..cca146d76d7 --- /dev/null +++ b/queue-6.6/net-dsa-mt7530-fix-10m-100m-speed-on-mt7988-switch.patch @@ -0,0 +1,44 @@ +From 3593bd9d87aa4c2c45db5f4f5fac1cecb7609218 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 24 Jan 2024 05:17:25 +0000 +Subject: net: dsa: mt7530: fix 10M/100M speed on MT7988 switch +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Daniel Golle + +[ Upstream commit dfa988b4c7c3a48bde7c2713308920c7741fff29 ] + +Setup PMCR port register for actual speed and duplex on internally +connected PHYs of the MT7988 built-in switch. This fixes links with +speeds other than 1000M. + +Fixes: 110c18bfed41 ("net: dsa: mt7530: introduce driver for MT7988 built-in switch") +Signed-off-by: Daniel Golle +Reviewed-by: Vladimir Oltean +Acked-by: Arınç ÜNAL +Link: https://lore.kernel.org/r/a5b04dfa8256d8302f402545a51ac4c626fdba25.1706071272.git.daniel@makrotopia.org +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/dsa/mt7530.c | 3 +-- + 1 file changed, 1 insertion(+), 2 deletions(-) + +diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c +index 035a34b50f31..4b6ac3f29f8f 100644 +--- a/drivers/net/dsa/mt7530.c ++++ b/drivers/net/dsa/mt7530.c +@@ -2848,8 +2848,7 @@ static void mt753x_phylink_mac_link_up(struct dsa_switch *ds, int port, + /* MT753x MAC works in 1G full duplex mode for all up-clocked + * variants. + */ +- if (interface == PHY_INTERFACE_MODE_INTERNAL || +- interface == PHY_INTERFACE_MODE_TRGMII || ++ if (interface == PHY_INTERFACE_MODE_TRGMII || + (phy_interface_mode_is_8023z(interface))) { + speed = SPEED_1000; + duplex = DUPLEX_FULL; +-- +2.43.0 + diff --git a/queue-6.6/net-dsa-qca8k-fix-illegal-usage-of-gpio.patch b/queue-6.6/net-dsa-qca8k-fix-illegal-usage-of-gpio.patch new file mode 100644 index 00000000000..5af737a92f1 --- /dev/null +++ b/queue-6.6/net-dsa-qca8k-fix-illegal-usage-of-gpio.patch @@ -0,0 +1,53 @@ +From 49ee86dd0bea7e1c74d99a0ed57c75ea4070afbc Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 26 Jan 2024 11:49:35 +0100 +Subject: net: dsa: qca8k: fix illegal usage of GPIO +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Michal Vokáč + +[ Upstream commit c44fc98f0a8ffd94fa0bd291928e7e312ffc7ca4 ] + +When working with GPIO, its direction must be set either when the GPIO is +requested by gpiod_get*() or later on by one of the gpiod_direction_*() +functions. Neither of this is done here which results in undefined +behavior on some systems. + +As the reset GPIO is used right after it is requested here, it makes sense +to configure it as GPIOD_OUT_HIGH right away. With that, the following +gpiod_set_value_cansleep(1) becomes redundant and can be safely +removed. + +Fixes: a653f2f538f9 ("net: dsa: qca8k: introduce reset via gpio feature") +Signed-off-by: Michal Vokáč +Reviewed-by: Andrew Lunn +Link: https://lore.kernel.org/r/1706266175-3408-1-git-send-email-michal.vokac@ysoft.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/dsa/qca/qca8k-8xxx.c | 3 +-- + 1 file changed, 1 insertion(+), 2 deletions(-) + +diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c +index 368d53d3b1d6..17c28fe2d743 100644 +--- a/drivers/net/dsa/qca/qca8k-8xxx.c ++++ b/drivers/net/dsa/qca/qca8k-8xxx.c +@@ -2049,12 +2049,11 @@ qca8k_sw_probe(struct mdio_device *mdiodev) + priv->info = of_device_get_match_data(priv->dev); + + priv->reset_gpio = devm_gpiod_get_optional(priv->dev, "reset", +- GPIOD_ASIS); ++ GPIOD_OUT_HIGH); + if (IS_ERR(priv->reset_gpio)) + return PTR_ERR(priv->reset_gpio); + + if (priv->reset_gpio) { +- gpiod_set_value_cansleep(priv->reset_gpio, 1); + /* The active low duration must be greater than 10 ms + * and checkpatch.pl wants 20 ms. + */ +-- +2.43.0 + diff --git a/queue-6.6/net-ethernet-mtk_eth_soc-set-dma-coherent-mask-to-ge.patch b/queue-6.6/net-ethernet-mtk_eth_soc-set-dma-coherent-mask-to-ge.patch new file mode 100644 index 00000000000..b5d7ff3c39e --- /dev/null +++ b/queue-6.6/net-ethernet-mtk_eth_soc-set-dma-coherent-mask-to-ge.patch @@ -0,0 +1,41 @@ +From 55cf7a1a4a3f7d902361f018cdf19d86b9eaf3ab Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 24 Jan 2024 16:22:09 +0000 +Subject: net: ethernet: mtk_eth_soc: set DMA coherent mask to get PPE working + +From: Daniel Golle + +[ Upstream commit cae1f1c36661f28c92a1db9113961a9ebd61dbaa ] + +Set DMA coherent mask to 32-bit which makes PPE offloading engine start +working on BPi-R4 which got 4 GiB of RAM. + +Fixes: 2d75891ebc09 ("net: ethernet: mtk_eth_soc: support 36-bit DMA addressing on MT7988") +Suggested-by: Elad Yifee +Signed-off-by: Daniel Golle +Link: https://lore.kernel.org/r/97e90925368b405f0974b9b15f1b7377c4a329ad.1706113251.git.daniel@makrotopia.org +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/mediatek/mtk_eth_soc.c | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c +index 20afe79f380a..73ea1e22b1fa 100644 +--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c ++++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c +@@ -4757,7 +4757,10 @@ static int mtk_probe(struct platform_device *pdev) + } + + if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA)) { +- err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(36)); ++ err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(36)); ++ if (!err) ++ err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); ++ + if (err) { + dev_err(&pdev->dev, "Wrong DMA config\n"); + return -EINVAL; +-- +2.43.0 + diff --git a/queue-6.6/net-ipv4-fix-a-memleak-in-ip_setup_cork.patch b/queue-6.6/net-ipv4-fix-a-memleak-in-ip_setup_cork.patch new file mode 100644 index 00000000000..3aea33de8b7 --- /dev/null +++ b/queue-6.6/net-ipv4-fix-a-memleak-in-ip_setup_cork.patch @@ -0,0 +1,55 @@ +From 352bef12303ab69a8596bc4d893152d91bd7c050 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 29 Jan 2024 17:10:17 +0800 +Subject: net: ipv4: fix a memleak in ip_setup_cork + +From: Zhipeng Lu + +[ Upstream commit 5dee6d6923458e26966717f2a3eae7d09fc10bf6 ] + +When inetdev_valid_mtu fails, cork->opt should be freed if it is +allocated in ip_setup_cork. Otherwise there could be a memleak. + +Fixes: 501a90c94510 ("inet: protect against too small mtu values.") +Signed-off-by: Zhipeng Lu +Reviewed-by: Eric Dumazet +Link: https://lore.kernel.org/r/20240129091017.2938835-1-alexious@zju.edu.cn +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/ipv4/ip_output.c | 12 ++++++------ + 1 file changed, 6 insertions(+), 6 deletions(-) + +diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c +index 4ab877cf6d35..ea0247485757 100644 +--- a/net/ipv4/ip_output.c ++++ b/net/ipv4/ip_output.c +@@ -1285,6 +1285,12 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, + if (unlikely(!rt)) + return -EFAULT; + ++ cork->fragsize = ip_sk_use_pmtu(sk) ? ++ dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); ++ ++ if (!inetdev_valid_mtu(cork->fragsize)) ++ return -ENETUNREACH; ++ + /* + * setup for corking. + */ +@@ -1301,12 +1307,6 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, + cork->addr = ipc->addr; + } + +- cork->fragsize = ip_sk_use_pmtu(sk) ? +- dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); +- +- if (!inetdev_valid_mtu(cork->fragsize)) +- return -ENETUNREACH; +- + cork->gso_size = ipc->gso_size; + + cork->dst = &rt->dst; +-- +2.43.0 + diff --git a/queue-6.6/net-lan966x-fix-port-configuration-when-using-sgmii-.patch b/queue-6.6/net-lan966x-fix-port-configuration-when-using-sgmii-.patch new file mode 100644 index 00000000000..7ba30ffe6ad --- /dev/null +++ b/queue-6.6/net-lan966x-fix-port-configuration-when-using-sgmii-.patch @@ -0,0 +1,42 @@ +From 4d09bf9191734e0992726b33f48631167318e706 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 24 Jan 2024 11:17:58 +0100 +Subject: net: lan966x: Fix port configuration when using SGMII interface + +From: Horatiu Vultur + +[ Upstream commit 62b4248105353e7d1debd30ca5c57ec5e5f28e35 ] + +In case the interface between the MAC and the PHY is SGMII, then the bit +GIGA_MODE on the MAC side needs to be set regardless of the speed at +which it is running. + +Fixes: d28d6d2e37d1 ("net: lan966x: add port module support") +Signed-off-by: Horatiu Vultur +Reviewed-by: Maxime Chevallier +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/microchip/lan966x/lan966x_port.c | 5 +++-- + 1 file changed, 3 insertions(+), 2 deletions(-) + +diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c +index 92108d354051..2e83bbb9477e 100644 +--- a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c ++++ b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c +@@ -168,9 +168,10 @@ static void lan966x_port_link_up(struct lan966x_port *port) + lan966x_taprio_speed_set(port, config->speed); + + /* Also the GIGA_MODE_ENA(1) needs to be set regardless of the +- * port speed for QSGMII ports. ++ * port speed for QSGMII or SGMII ports. + */ +- if (phy_interface_num_ports(config->portmode) == 4) ++ if (phy_interface_num_ports(config->portmode) == 4 || ++ config->portmode == PHY_INTERFACE_MODE_SGMII) + mode = DEV_MAC_MODE_CFG_GIGA_MODE_ENA_SET(1); + + lan_wr(config->duplex | mode, +-- +2.43.0 + diff --git a/queue-6.6/net-phy-mediatek-ge-soc-sync-driver-with-mediatek-sd.patch b/queue-6.6/net-phy-mediatek-ge-soc-sync-driver-with-mediatek-sd.patch new file mode 100644 index 00000000000..526d4845a65 --- /dev/null +++ b/queue-6.6/net-phy-mediatek-ge-soc-sync-driver-with-mediatek-sd.patch @@ -0,0 +1,265 @@ +From 98810e9861d437aece68e01a1c53996523af2fa1 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 24 Jan 2024 05:18:23 +0000 +Subject: net: phy: mediatek-ge-soc: sync driver with MediaTek SDK + +From: Daniel Golle + +[ Upstream commit ff63cc2e95065bea978d2db01f7e7356cca3d021 ] + +Sync initialization and calibration routines with MediaTek's reference +driver. Improves compliance and resolves link stability issues with +CH340 IoT devices connected to MT798x built-in PHYs. + +Fixes: 98c485eaf509 ("net: phy: add driver for MediaTek SoC built-in GE PHYs") +Signed-off-by: Daniel Golle +Link: https://lore.kernel.org/r/f2195279c234c0f618946424b8236026126bc595.1706071311.git.daniel@makrotopia.org +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/phy/mediatek-ge-soc.c | 147 ++++++++++++++++-------------- + 1 file changed, 81 insertions(+), 66 deletions(-) + +diff --git a/drivers/net/phy/mediatek-ge-soc.c b/drivers/net/phy/mediatek-ge-soc.c +index 8a20d9889f10..0f3a1538a8b8 100644 +--- a/drivers/net/phy/mediatek-ge-soc.c ++++ b/drivers/net/phy/mediatek-ge-soc.c +@@ -489,7 +489,7 @@ static int tx_r50_fill_result(struct phy_device *phydev, u16 tx_r50_cal_val, + u16 reg, val; + + if (phydev->drv->phy_id == MTK_GPHY_ID_MT7988) +- bias = -2; ++ bias = -1; + + val = clamp_val(bias + tx_r50_cal_val, 0, 63); + +@@ -705,6 +705,11 @@ static int tx_vcm_cal_sw(struct phy_device *phydev, u8 rg_txreserve_x) + static void mt798x_phy_common_finetune(struct phy_device *phydev) + { + phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5); ++ /* SlvDSPreadyTime = 24, MasDSPreadyTime = 24 */ ++ __phy_write(phydev, 0x11, 0xc71); ++ __phy_write(phydev, 0x12, 0xc); ++ __phy_write(phydev, 0x10, 0x8fae); ++ + /* EnabRandUpdTrig = 1 */ + __phy_write(phydev, 0x11, 0x2f00); + __phy_write(phydev, 0x12, 0xe); +@@ -715,15 +720,56 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev) + __phy_write(phydev, 0x12, 0x0); + __phy_write(phydev, 0x10, 0x83aa); + +- /* TrFreeze = 0 */ ++ /* FfeUpdGainForce = 1(Enable), FfeUpdGainForceVal = 4 */ ++ __phy_write(phydev, 0x11, 0x240); ++ __phy_write(phydev, 0x12, 0x0); ++ __phy_write(phydev, 0x10, 0x9680); ++ ++ /* TrFreeze = 0 (mt7988 default) */ + __phy_write(phydev, 0x11, 0x0); + __phy_write(phydev, 0x12, 0x0); + __phy_write(phydev, 0x10, 0x9686); + ++ /* SSTrKp100 = 5 */ ++ /* SSTrKf100 = 6 */ ++ /* SSTrKp1000Mas = 5 */ ++ /* SSTrKf1000Mas = 6 */ + /* SSTrKp1000Slv = 5 */ ++ /* SSTrKf1000Slv = 6 */ + __phy_write(phydev, 0x11, 0xbaef); + __phy_write(phydev, 0x12, 0x2e); + __phy_write(phydev, 0x10, 0x968c); ++ phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0); ++} ++ ++static void mt7981_phy_finetune(struct phy_device *phydev) ++{ ++ u16 val[8] = { 0x01ce, 0x01c1, ++ 0x020f, 0x0202, ++ 0x03d0, 0x03c0, ++ 0x0013, 0x0005 }; ++ int i, k; ++ ++ /* 100M eye finetune: ++ * Keep middle level of TX MLT3 shapper as default. ++ * Only change TX MLT3 overshoot level here. ++ */ ++ for (k = 0, i = 1; i < 12; i++) { ++ if (i % 3 == 0) ++ continue; ++ phy_write_mmd(phydev, MDIO_MMD_VEND1, i, val[k++]); ++ } ++ ++ phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5); ++ /* ResetSyncOffset = 6 */ ++ __phy_write(phydev, 0x11, 0x600); ++ __phy_write(phydev, 0x12, 0x0); ++ __phy_write(phydev, 0x10, 0x8fc0); ++ ++ /* VgaDecRate = 1 */ ++ __phy_write(phydev, 0x11, 0x4c2a); ++ __phy_write(phydev, 0x12, 0x3e); ++ __phy_write(phydev, 0x10, 0x8fa4); + + /* MrvlTrFix100Kp = 3, MrvlTrFix100Kf = 2, + * MrvlTrFix1000Kp = 3, MrvlTrFix1000Kf = 2 +@@ -738,7 +784,7 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev) + __phy_write(phydev, 0x10, 0x8ec0); + phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0); + +- /* TR_OPEN_LOOP_EN = 1, lpf_x_average = 9*/ ++ /* TR_OPEN_LOOP_EN = 1, lpf_x_average = 9 */ + phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG234, + MTK_PHY_TR_OPEN_LOOP_EN_MASK | MTK_PHY_LPF_X_AVERAGE_MASK, + BIT(0) | FIELD_PREP(MTK_PHY_LPF_X_AVERAGE_MASK, 0x9)); +@@ -771,48 +817,6 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev) + phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_LDO_OUTPUT_V, 0x2222); + } + +-static void mt7981_phy_finetune(struct phy_device *phydev) +-{ +- u16 val[8] = { 0x01ce, 0x01c1, +- 0x020f, 0x0202, +- 0x03d0, 0x03c0, +- 0x0013, 0x0005 }; +- int i, k; +- +- /* 100M eye finetune: +- * Keep middle level of TX MLT3 shapper as default. +- * Only change TX MLT3 overshoot level here. +- */ +- for (k = 0, i = 1; i < 12; i++) { +- if (i % 3 == 0) +- continue; +- phy_write_mmd(phydev, MDIO_MMD_VEND1, i, val[k++]); +- } +- +- phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5); +- /* SlvDSPreadyTime = 24, MasDSPreadyTime = 24 */ +- __phy_write(phydev, 0x11, 0xc71); +- __phy_write(phydev, 0x12, 0xc); +- __phy_write(phydev, 0x10, 0x8fae); +- +- /* ResetSyncOffset = 6 */ +- __phy_write(phydev, 0x11, 0x600); +- __phy_write(phydev, 0x12, 0x0); +- __phy_write(phydev, 0x10, 0x8fc0); +- +- /* VgaDecRate = 1 */ +- __phy_write(phydev, 0x11, 0x4c2a); +- __phy_write(phydev, 0x12, 0x3e); +- __phy_write(phydev, 0x10, 0x8fa4); +- +- /* FfeUpdGainForce = 4 */ +- __phy_write(phydev, 0x11, 0x240); +- __phy_write(phydev, 0x12, 0x0); +- __phy_write(phydev, 0x10, 0x9680); +- +- phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0); +-} +- + static void mt7988_phy_finetune(struct phy_device *phydev) + { + u16 val[12] = { 0x0187, 0x01cd, 0x01c8, 0x0182, +@@ -827,17 +831,7 @@ static void mt7988_phy_finetune(struct phy_device *phydev) + /* TCT finetune */ + phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_TX_FILTER, 0x5); + +- /* Disable TX power saving */ +- phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RXADC_CTRL_RG7, +- MTK_PHY_DA_AD_BUF_BIAS_LP_MASK, 0x3 << 8); +- + phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5); +- +- /* SlvDSPreadyTime = 24, MasDSPreadyTime = 12 */ +- __phy_write(phydev, 0x11, 0x671); +- __phy_write(phydev, 0x12, 0xc); +- __phy_write(phydev, 0x10, 0x8fae); +- + /* ResetSyncOffset = 5 */ + __phy_write(phydev, 0x11, 0x500); + __phy_write(phydev, 0x12, 0x0); +@@ -845,13 +839,27 @@ static void mt7988_phy_finetune(struct phy_device *phydev) + + /* VgaDecRate is 1 at default on mt7988 */ + +- phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0); ++ /* MrvlTrFix100Kp = 6, MrvlTrFix100Kf = 7, ++ * MrvlTrFix1000Kp = 6, MrvlTrFix1000Kf = 7 ++ */ ++ __phy_write(phydev, 0x11, 0xb90a); ++ __phy_write(phydev, 0x12, 0x6f); ++ __phy_write(phydev, 0x10, 0x8f82); ++ ++ /* RemAckCntLimitCtrl = 1 */ ++ __phy_write(phydev, 0x11, 0xfbba); ++ __phy_write(phydev, 0x12, 0xc3); ++ __phy_write(phydev, 0x10, 0x87f8); + +- phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_2A30); +- /* TxClkOffset = 2 */ +- __phy_modify(phydev, MTK_PHY_ANARG_RG, MTK_PHY_TCLKOFFSET_MASK, +- FIELD_PREP(MTK_PHY_TCLKOFFSET_MASK, 0x2)); + phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0); ++ ++ /* TR_OPEN_LOOP_EN = 1, lpf_x_average = 10 */ ++ phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG234, ++ MTK_PHY_TR_OPEN_LOOP_EN_MASK | MTK_PHY_LPF_X_AVERAGE_MASK, ++ BIT(0) | FIELD_PREP(MTK_PHY_LPF_X_AVERAGE_MASK, 0xa)); ++ ++ /* rg_tr_lpf_cnt_val = 1023 */ ++ phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_LPF_CNT_VAL, 0x3ff); + } + + static void mt798x_phy_eee(struct phy_device *phydev) +@@ -884,11 +892,11 @@ static void mt798x_phy_eee(struct phy_device *phydev) + MTK_PHY_LPI_SLV_SEND_TX_EN, + FIELD_PREP(MTK_PHY_LPI_SLV_SEND_TX_TIMER_MASK, 0x120)); + +- phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG239, +- MTK_PHY_LPI_SEND_LOC_TIMER_MASK | +- MTK_PHY_LPI_TXPCS_LOC_RCV, +- FIELD_PREP(MTK_PHY_LPI_SEND_LOC_TIMER_MASK, 0x117)); ++ /* Keep MTK_PHY_LPI_SEND_LOC_TIMER as 375 */ ++ phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG239, ++ MTK_PHY_LPI_TXPCS_LOC_RCV); + ++ /* This also fixes some IoT issues, such as CH340 */ + phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG2C7, + MTK_PHY_MAX_GAIN_MASK | MTK_PHY_MIN_GAIN_MASK, + FIELD_PREP(MTK_PHY_MAX_GAIN_MASK, 0x8) | +@@ -922,7 +930,7 @@ static void mt798x_phy_eee(struct phy_device *phydev) + __phy_write(phydev, 0x12, 0x0); + __phy_write(phydev, 0x10, 0x9690); + +- /* REG_EEE_st2TrKf1000 = 3 */ ++ /* REG_EEE_st2TrKf1000 = 2 */ + __phy_write(phydev, 0x11, 0x114f); + __phy_write(phydev, 0x12, 0x2); + __phy_write(phydev, 0x10, 0x969a); +@@ -947,7 +955,7 @@ static void mt798x_phy_eee(struct phy_device *phydev) + __phy_write(phydev, 0x12, 0x0); + __phy_write(phydev, 0x10, 0x96b8); + +- /* REGEEE_wake_slv_tr_wait_dfesigdet_en = 1 */ ++ /* REGEEE_wake_slv_tr_wait_dfesigdet_en = 0 */ + __phy_write(phydev, 0x11, 0x1463); + __phy_write(phydev, 0x12, 0x0); + __phy_write(phydev, 0x10, 0x96ca); +@@ -1459,6 +1467,13 @@ static int mt7988_phy_probe(struct phy_device *phydev) + if (err) + return err; + ++ /* Disable TX power saving at probing to: ++ * 1. Meet common mode compliance test criteria ++ * 2. Make sure that TX-VCM calibration works fine ++ */ ++ phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RXADC_CTRL_RG7, ++ MTK_PHY_DA_AD_BUF_BIAS_LP_MASK, 0x3 << 8); ++ + return mt798x_phy_calibration(phydev); + } + +-- +2.43.0 + diff --git a/queue-6.6/net-sysfs-fix-sys-class-net-iface-path.patch b/queue-6.6/net-sysfs-fix-sys-class-net-iface-path.patch new file mode 100644 index 00000000000..7a0fa18aa49 --- /dev/null +++ b/queue-6.6/net-sysfs-fix-sys-class-net-iface-path.patch @@ -0,0 +1,127 @@ +From 77166198afef78632dfcc26142fc60575dd7d497 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 31 Jan 2024 02:21:49 -0800 +Subject: net: sysfs: Fix /sys/class/net/ path + +From: Breno Leitao + +[ Upstream commit ae3f4b44641dfff969604735a0dcbf931f383285 ] + +The documentation is pointing to the wrong path for the interface. +Documentation is pointing to /sys/class/, instead of +/sys/class/net/. + +Fix it by adding the `net/` directory before the interface. + +Fixes: 1a02ef76acfa ("net: sysfs: add documentation entries for /sys/class//queues") +Signed-off-by: Breno Leitao +Link: https://lore.kernel.org/r/20240131102150.728960-2-leitao@debian.org +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + .../ABI/testing/sysfs-class-net-queues | 22 +++++++++---------- + 1 file changed, 11 insertions(+), 11 deletions(-) + +diff --git a/Documentation/ABI/testing/sysfs-class-net-queues b/Documentation/ABI/testing/sysfs-class-net-queues +index 906ff3ca928a..5bff64d256c2 100644 +--- a/Documentation/ABI/testing/sysfs-class-net-queues ++++ b/Documentation/ABI/testing/sysfs-class-net-queues +@@ -1,4 +1,4 @@ +-What: /sys/class//queues/rx-/rps_cpus ++What: /sys/class/net//queues/rx-/rps_cpus + Date: March 2010 + KernelVersion: 2.6.35 + Contact: netdev@vger.kernel.org +@@ -8,7 +8,7 @@ Description: + network device queue. Possible values depend on the number + of available CPU(s) in the system. + +-What: /sys/class//queues/rx-/rps_flow_cnt ++What: /sys/class/net//queues/rx-/rps_flow_cnt + Date: April 2010 + KernelVersion: 2.6.35 + Contact: netdev@vger.kernel.org +@@ -16,7 +16,7 @@ Description: + Number of Receive Packet Steering flows being currently + processed by this particular network device receive queue. + +-What: /sys/class//queues/tx-/tx_timeout ++What: /sys/class/net//queues/tx-/tx_timeout + Date: November 2011 + KernelVersion: 3.3 + Contact: netdev@vger.kernel.org +@@ -24,7 +24,7 @@ Description: + Indicates the number of transmit timeout events seen by this + network interface transmit queue. + +-What: /sys/class//queues/tx-/tx_maxrate ++What: /sys/class/net//queues/tx-/tx_maxrate + Date: March 2015 + KernelVersion: 4.1 + Contact: netdev@vger.kernel.org +@@ -32,7 +32,7 @@ Description: + A Mbps max-rate set for the queue, a value of zero means disabled, + default is disabled. + +-What: /sys/class//queues/tx-/xps_cpus ++What: /sys/class/net//queues/tx-/xps_cpus + Date: November 2010 + KernelVersion: 2.6.38 + Contact: netdev@vger.kernel.org +@@ -42,7 +42,7 @@ Description: + network device transmit queue. Possible values depend on the + number of available CPU(s) in the system. + +-What: /sys/class//queues/tx-/xps_rxqs ++What: /sys/class/net//queues/tx-/xps_rxqs + Date: June 2018 + KernelVersion: 4.18.0 + Contact: netdev@vger.kernel.org +@@ -53,7 +53,7 @@ Description: + number of available receive queue(s) in the network device. + Default is disabled. + +-What: /sys/class//queues/tx-/byte_queue_limits/hold_time ++What: /sys/class/net//queues/tx-/byte_queue_limits/hold_time + Date: November 2011 + KernelVersion: 3.3 + Contact: netdev@vger.kernel.org +@@ -62,7 +62,7 @@ Description: + of this particular network device transmit queue. + Default value is 1000. + +-What: /sys/class//queues/tx-/byte_queue_limits/inflight ++What: /sys/class/net//queues/tx-/byte_queue_limits/inflight + Date: November 2011 + KernelVersion: 3.3 + Contact: netdev@vger.kernel.org +@@ -70,7 +70,7 @@ Description: + Indicates the number of bytes (objects) in flight on this + network device transmit queue. + +-What: /sys/class//queues/tx-/byte_queue_limits/limit ++What: /sys/class/net//queues/tx-/byte_queue_limits/limit + Date: November 2011 + KernelVersion: 3.3 + Contact: netdev@vger.kernel.org +@@ -79,7 +79,7 @@ Description: + on this network device transmit queue. This value is clamped + to be within the bounds defined by limit_max and limit_min. + +-What: /sys/class//queues/tx-/byte_queue_limits/limit_max ++What: /sys/class/net//queues/tx-/byte_queue_limits/limit_max + Date: November 2011 + KernelVersion: 3.3 + Contact: netdev@vger.kernel.org +@@ -88,7 +88,7 @@ Description: + queued on this network device transmit queue. See + include/linux/dynamic_queue_limits.h for the default value. + +-What: /sys/class//queues/tx-/byte_queue_limits/limit_min ++What: /sys/class/net//queues/tx-/byte_queue_limits/limit_min + Date: November 2011 + KernelVersion: 3.3 + Contact: netdev@vger.kernel.org +-- +2.43.0 + diff --git a/queue-6.6/netfilter-conntrack-correct-window-scaling-with-retr.patch b/queue-6.6/netfilter-conntrack-correct-window-scaling-with-retr.patch new file mode 100644 index 00000000000..4e6df0b5bcc --- /dev/null +++ b/queue-6.6/netfilter-conntrack-correct-window-scaling-with-retr.patch @@ -0,0 +1,84 @@ +From bd95f53a6c88e5178883a3d93352662c076e2128 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sun, 21 Jan 2024 21:51:44 +0000 +Subject: netfilter: conntrack: correct window scaling with retransmitted SYN + +From: Ryan Schaefer + +[ Upstream commit fb366fc7541a1de521ab3df58471746aa793b833 ] + +commit c7aab4f17021 ("netfilter: nf_conntrack_tcp: re-init for syn packets +only") introduces a bug where SYNs in ORIGINAL direction on reused 5-tuple +result in incorrect window scale negotiation. This commit merged the SYN +re-initialization and simultaneous open or SYN retransmits cases. Merging +this block added the logic in tcp_init_sender() that performed window scale +negotiation to the retransmitted syn case. Previously. this would only +result in updating the sender's scale and flags. After the merge the +additional logic results in improperly clearing the scale in ORIGINAL +direction before any packets in the REPLY direction are received. This +results in packets incorrectly being marked invalid for being +out-of-window. + +This can be reproduced with the following trace: + +Packet Sequence: +> Flags [S], seq 1687765604, win 62727, options [.. wscale 7], length 0 +> Flags [S], seq 1944817196, win 62727, options [.. wscale 7], length 0 + +In order to fix the issue, only evaluate window negotiation for packets +in the REPLY direction. This was tested with simultaneous open, fast +open, and the above reproduction. + +Fixes: c7aab4f17021 ("netfilter: nf_conntrack_tcp: re-init for syn packets only") +Signed-off-by: Ryan Schaefer +Signed-off-by: Pablo Neira Ayuso +Signed-off-by: Sasha Levin +--- + net/netfilter/nf_conntrack_proto_tcp.c | 10 ++++++---- + 1 file changed, 6 insertions(+), 4 deletions(-) + +diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c +index 4018acb1d674..53d46ebcb5f7 100644 +--- a/net/netfilter/nf_conntrack_proto_tcp.c ++++ b/net/netfilter/nf_conntrack_proto_tcp.c +@@ -457,7 +457,8 @@ static void tcp_init_sender(struct ip_ct_tcp_state *sender, + const struct sk_buff *skb, + unsigned int dataoff, + const struct tcphdr *tcph, +- u32 end, u32 win) ++ u32 end, u32 win, ++ enum ip_conntrack_dir dir) + { + /* SYN-ACK in reply to a SYN + * or SYN from reply direction in simultaneous open. +@@ -471,7 +472,8 @@ static void tcp_init_sender(struct ip_ct_tcp_state *sender, + * Both sides must send the Window Scale option + * to enable window scaling in either direction. + */ +- if (!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE && ++ if (dir == IP_CT_DIR_REPLY && ++ !(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE && + receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE)) { + sender->td_scale = 0; + receiver->td_scale = 0; +@@ -542,7 +544,7 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir, + if (tcph->syn) { + tcp_init_sender(sender, receiver, + skb, dataoff, tcph, +- end, win); ++ end, win, dir); + if (!tcph->ack) + /* Simultaneous open */ + return NFCT_TCP_ACCEPT; +@@ -585,7 +587,7 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir, + */ + tcp_init_sender(sender, receiver, + skb, dataoff, tcph, +- end, win); ++ end, win, dir); + + if (dir == IP_CT_DIR_REPLY && !tcph->ack) + return NFCT_TCP_ACCEPT; +-- +2.43.0 + diff --git a/queue-6.6/netfilter-ipset-fix-performance-regression-in-swap-o.patch b/queue-6.6/netfilter-ipset-fix-performance-regression-in-swap-o.patch new file mode 100644 index 00000000000..de91ddf407d --- /dev/null +++ b/queue-6.6/netfilter-ipset-fix-performance-regression-in-swap-o.patch @@ -0,0 +1,301 @@ +From a2337a34cfe7956a7342b96d41ccd74210fa8830 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 29 Jan 2024 10:57:01 +0100 +Subject: netfilter: ipset: fix performance regression in swap operation + +From: Jozsef Kadlecsik + +[ Upstream commit 97f7cf1cd80eeed3b7c808b7c12463295c751001 ] + +The patch "netfilter: ipset: fix race condition between swap/destroy +and kernel side add/del/test", commit 28628fa9 fixes a race condition. +But the synchronize_rcu() added to the swap function unnecessarily slows +it down: it can safely be moved to destroy and use call_rcu() instead. + +Eric Dumazet pointed out that simply calling the destroy functions as +rcu callback does not work: sets with timeout use garbage collectors +which need cancelling at destroy which can wait. Therefore the destroy +functions are split into two: cancelling garbage collectors safely at +executing the command received by netlink and moving the remaining +part only into the rcu callback. + +Link: https://lore.kernel.org/lkml/C0829B10-EAA6-4809-874E-E1E9C05A8D84@automattic.com/ +Fixes: 28628fa952fe ("netfilter: ipset: fix race condition between swap/destroy and kernel side add/del/test") +Reported-by: Ale Crismani +Reported-by: David Wang <00107082@163.com> +Tested-by: David Wang <00107082@163.com> +Signed-off-by: Jozsef Kadlecsik +Signed-off-by: Pablo Neira Ayuso +Signed-off-by: Sasha Levin +--- + include/linux/netfilter/ipset/ip_set.h | 4 +++ + net/netfilter/ipset/ip_set_bitmap_gen.h | 14 ++++++++-- + net/netfilter/ipset/ip_set_core.c | 37 +++++++++++++++++++------ + net/netfilter/ipset/ip_set_hash_gen.h | 15 ++++++++-- + net/netfilter/ipset/ip_set_list_set.c | 13 +++++++-- + 5 files changed, 65 insertions(+), 18 deletions(-) + +diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h +index e8c350a3ade1..e9f4f845d760 100644 +--- a/include/linux/netfilter/ipset/ip_set.h ++++ b/include/linux/netfilter/ipset/ip_set.h +@@ -186,6 +186,8 @@ struct ip_set_type_variant { + /* Return true if "b" set is the same as "a" + * according to the create set parameters */ + bool (*same_set)(const struct ip_set *a, const struct ip_set *b); ++ /* Cancel ongoing garbage collectors before destroying the set*/ ++ void (*cancel_gc)(struct ip_set *set); + /* Region-locking is used */ + bool region_lock; + }; +@@ -242,6 +244,8 @@ extern void ip_set_type_unregister(struct ip_set_type *set_type); + + /* A generic IP set */ + struct ip_set { ++ /* For call_cru in destroy */ ++ struct rcu_head rcu; + /* The name of the set */ + char name[IPSET_MAXNAMELEN]; + /* Lock protecting the set data */ +diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h +index 26ab0e9612d8..9523104a90da 100644 +--- a/net/netfilter/ipset/ip_set_bitmap_gen.h ++++ b/net/netfilter/ipset/ip_set_bitmap_gen.h +@@ -28,6 +28,7 @@ + #define mtype_del IPSET_TOKEN(MTYPE, _del) + #define mtype_list IPSET_TOKEN(MTYPE, _list) + #define mtype_gc IPSET_TOKEN(MTYPE, _gc) ++#define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) + #define mtype MTYPE + + #define get_ext(set, map, id) ((map)->extensions + ((set)->dsize * (id))) +@@ -57,9 +58,6 @@ mtype_destroy(struct ip_set *set) + { + struct mtype *map = set->data; + +- if (SET_WITH_TIMEOUT(set)) +- del_timer_sync(&map->gc); +- + if (set->dsize && set->extensions & IPSET_EXT_DESTROY) + mtype_ext_cleanup(set); + ip_set_free(map->members); +@@ -288,6 +286,15 @@ mtype_gc(struct timer_list *t) + add_timer(&map->gc); + } + ++static void ++mtype_cancel_gc(struct ip_set *set) ++{ ++ struct mtype *map = set->data; ++ ++ if (SET_WITH_TIMEOUT(set)) ++ del_timer_sync(&map->gc); ++} ++ + static const struct ip_set_type_variant mtype = { + .kadt = mtype_kadt, + .uadt = mtype_uadt, +@@ -301,6 +308,7 @@ static const struct ip_set_type_variant mtype = { + .head = mtype_head, + .list = mtype_list, + .same_set = mtype_same_set, ++ .cancel_gc = mtype_cancel_gc, + }; + + #endif /* __IP_SET_BITMAP_IP_GEN_H */ +diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c +index 4c133e06be1d..bcaad9c009fe 100644 +--- a/net/netfilter/ipset/ip_set_core.c ++++ b/net/netfilter/ipset/ip_set_core.c +@@ -1182,6 +1182,14 @@ ip_set_destroy_set(struct ip_set *set) + kfree(set); + } + ++static void ++ip_set_destroy_set_rcu(struct rcu_head *head) ++{ ++ struct ip_set *set = container_of(head, struct ip_set, rcu); ++ ++ ip_set_destroy_set(set); ++} ++ + static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const attr[]) + { +@@ -1193,8 +1201,6 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, + if (unlikely(protocol_min_failed(attr))) + return -IPSET_ERR_PROTOCOL; + +- /* Must wait for flush to be really finished in list:set */ +- rcu_barrier(); + + /* Commands are serialized and references are + * protected by the ip_set_ref_lock. +@@ -1206,8 +1212,10 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, + * counter, so if it's already zero, we can proceed + * without holding the lock. + */ +- read_lock_bh(&ip_set_ref_lock); + if (!attr[IPSET_ATTR_SETNAME]) { ++ /* Must wait for flush to be really finished in list:set */ ++ rcu_barrier(); ++ read_lock_bh(&ip_set_ref_lock); + for (i = 0; i < inst->ip_set_max; i++) { + s = ip_set(inst, i); + if (s && (s->ref || s->ref_netlink)) { +@@ -1221,6 +1229,8 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, + s = ip_set(inst, i); + if (s) { + ip_set(inst, i) = NULL; ++ /* Must cancel garbage collectors */ ++ s->variant->cancel_gc(s); + ip_set_destroy_set(s); + } + } +@@ -1228,6 +1238,9 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, + inst->is_destroyed = false; + } else { + u32 flags = flag_exist(info->nlh); ++ u16 features = 0; ++ ++ read_lock_bh(&ip_set_ref_lock); + s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]), + &i); + if (!s) { +@@ -1238,10 +1251,16 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, + ret = -IPSET_ERR_BUSY; + goto out; + } ++ features = s->type->features; + ip_set(inst, i) = NULL; + read_unlock_bh(&ip_set_ref_lock); +- +- ip_set_destroy_set(s); ++ if (features & IPSET_TYPE_NAME) { ++ /* Must wait for flush to be really finished */ ++ rcu_barrier(); ++ } ++ /* Must cancel garbage collectors */ ++ s->variant->cancel_gc(s); ++ call_rcu(&s->rcu, ip_set_destroy_set_rcu); + } + return 0; + out: +@@ -1394,9 +1413,6 @@ static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info, + ip_set(inst, to_id) = from; + write_unlock_bh(&ip_set_ref_lock); + +- /* Make sure all readers of the old set pointers are completed. */ +- synchronize_rcu(); +- + return 0; + } + +@@ -2409,8 +2425,11 @@ ip_set_fini(void) + { + nf_unregister_sockopt(&so_set); + nfnetlink_subsys_unregister(&ip_set_netlink_subsys); +- + unregister_pernet_subsys(&ip_set_net_ops); ++ ++ /* Wait for call_rcu() in destroy */ ++ rcu_barrier(); ++ + pr_debug("these are the famous last words\n"); + } + +diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h +index 7c2399541771..c62998b46f00 100644 +--- a/net/netfilter/ipset/ip_set_hash_gen.h ++++ b/net/netfilter/ipset/ip_set_hash_gen.h +@@ -221,6 +221,7 @@ static const union nf_inet_addr zeromask = {}; + #undef mtype_gc_do + #undef mtype_gc + #undef mtype_gc_init ++#undef mtype_cancel_gc + #undef mtype_variant + #undef mtype_data_match + +@@ -265,6 +266,7 @@ static const union nf_inet_addr zeromask = {}; + #define mtype_gc_do IPSET_TOKEN(MTYPE, _gc_do) + #define mtype_gc IPSET_TOKEN(MTYPE, _gc) + #define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) ++#define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) + #define mtype_variant IPSET_TOKEN(MTYPE, _variant) + #define mtype_data_match IPSET_TOKEN(MTYPE, _data_match) + +@@ -449,9 +451,6 @@ mtype_destroy(struct ip_set *set) + struct htype *h = set->data; + struct list_head *l, *lt; + +- if (SET_WITH_TIMEOUT(set)) +- cancel_delayed_work_sync(&h->gc.dwork); +- + mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true); + list_for_each_safe(l, lt, &h->ad) { + list_del(l); +@@ -598,6 +597,15 @@ mtype_gc_init(struct htable_gc *gc) + queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ); + } + ++static void ++mtype_cancel_gc(struct ip_set *set) ++{ ++ struct htype *h = set->data; ++ ++ if (SET_WITH_TIMEOUT(set)) ++ cancel_delayed_work_sync(&h->gc.dwork); ++} ++ + static int + mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags); +@@ -1440,6 +1448,7 @@ static const struct ip_set_type_variant mtype_variant = { + .uref = mtype_uref, + .resize = mtype_resize, + .same_set = mtype_same_set, ++ .cancel_gc = mtype_cancel_gc, + .region_lock = true, + }; + +diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c +index e162636525cf..6c3f28bc59b3 100644 +--- a/net/netfilter/ipset/ip_set_list_set.c ++++ b/net/netfilter/ipset/ip_set_list_set.c +@@ -426,9 +426,6 @@ list_set_destroy(struct ip_set *set) + struct list_set *map = set->data; + struct set_elem *e, *n; + +- if (SET_WITH_TIMEOUT(set)) +- timer_shutdown_sync(&map->gc); +- + list_for_each_entry_safe(e, n, &map->members, list) { + list_del(&e->list); + ip_set_put_byindex(map->net, e->id); +@@ -545,6 +542,15 @@ list_set_same_set(const struct ip_set *a, const struct ip_set *b) + a->extensions == b->extensions; + } + ++static void ++list_set_cancel_gc(struct ip_set *set) ++{ ++ struct list_set *map = set->data; ++ ++ if (SET_WITH_TIMEOUT(set)) ++ timer_shutdown_sync(&map->gc); ++} ++ + static const struct ip_set_type_variant set_variant = { + .kadt = list_set_kadt, + .uadt = list_set_uadt, +@@ -558,6 +564,7 @@ static const struct ip_set_type_variant set_variant = { + .head = list_set_head, + .list = list_set_list, + .same_set = list_set_same_set, ++ .cancel_gc = list_set_cancel_gc, + }; + + static void +-- +2.43.0 + diff --git a/queue-6.6/netfilter-nf_log-replace-bug_on-by-warn_on_once-when.patch b/queue-6.6/netfilter-nf_log-replace-bug_on-by-warn_on_once-when.patch new file mode 100644 index 00000000000..b5bbdc1014c --- /dev/null +++ b/queue-6.6/netfilter-nf_log-replace-bug_on-by-warn_on_once-when.patch @@ -0,0 +1,46 @@ +From f43ebf92a8dc43c39b832185c326eee075f701e5 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 29 Jan 2024 11:09:43 +0100 +Subject: netfilter: nf_log: replace BUG_ON by WARN_ON_ONCE when putting logger + +From: Pablo Neira Ayuso + +[ Upstream commit 259eb32971e9eb24d1777a28d82730659f50fdcb ] + +Module reference is bumped for each user, this should not ever happen. + +But BUG_ON check should use rcu_access_pointer() instead. + +If this ever happens, do WARN_ON_ONCE() instead of BUG_ON() and +consolidate pointer check under the rcu read side lock section. + +Fixes: fab4085f4e24 ("netfilter: log: nf_log_packet() as real unified interface") +Signed-off-by: Pablo Neira Ayuso +Signed-off-by: Sasha Levin +--- + net/netfilter/nf_log.c | 7 ++++--- + 1 file changed, 4 insertions(+), 3 deletions(-) + +diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c +index 8cc52d2bd31b..e16f158388bb 100644 +--- a/net/netfilter/nf_log.c ++++ b/net/netfilter/nf_log.c +@@ -193,11 +193,12 @@ void nf_logger_put(int pf, enum nf_log_type type) + return; + } + +- BUG_ON(loggers[pf][type] == NULL); +- + rcu_read_lock(); + logger = rcu_dereference(loggers[pf][type]); +- module_put(logger->me); ++ if (!logger) ++ WARN_ON_ONCE(1); ++ else ++ module_put(logger->me); + rcu_read_unlock(); + } + EXPORT_SYMBOL_GPL(nf_logger_put); +-- +2.43.0 + diff --git a/queue-6.6/netfilter-nf_tables-restrict-tunnel-object-to-nfprot.patch b/queue-6.6/netfilter-nf_tables-restrict-tunnel-object-to-nfprot.patch new file mode 100644 index 00000000000..3c3c7f7acdd --- /dev/null +++ b/queue-6.6/netfilter-nf_tables-restrict-tunnel-object-to-nfprot.patch @@ -0,0 +1,109 @@ +From d4cfc4b0623347a90f3a084e298678304b8d4760 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 23 Jan 2024 23:45:32 +0100 +Subject: netfilter: nf_tables: restrict tunnel object to NFPROTO_NETDEV + +From: Pablo Neira Ayuso + +[ Upstream commit 776d451648443f9884be4a1b4e38e8faf1c621f9 ] + +Bail out on using the tunnel dst template from other than netdev family. +Add the infrastructure to check for the family in objects. + +Fixes: af308b94a2a4 ("netfilter: nf_tables: add tunnel support") +Signed-off-by: Pablo Neira Ayuso +Signed-off-by: Sasha Levin +--- + include/net/netfilter/nf_tables.h | 2 ++ + net/netfilter/nf_tables_api.c | 14 +++++++++----- + net/netfilter/nft_tunnel.c | 1 + + 3 files changed, 12 insertions(+), 5 deletions(-) + +diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h +index 75972e211ba1..5bb8a83e2604 100644 +--- a/include/net/netfilter/nf_tables.h ++++ b/include/net/netfilter/nf_tables.h +@@ -1307,6 +1307,7 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, + * @type: stateful object numeric type + * @owner: module owner + * @maxattr: maximum netlink attribute ++ * @family: address family for AF-specific object types + * @policy: netlink attribute policy + */ + struct nft_object_type { +@@ -1316,6 +1317,7 @@ struct nft_object_type { + struct list_head list; + u32 type; + unsigned int maxattr; ++ u8 family; + struct module *owner; + const struct nla_policy *policy; + }; +diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c +index 4fc8348dd799..cb7d42a3faab 100644 +--- a/net/netfilter/nf_tables_api.c ++++ b/net/netfilter/nf_tables_api.c +@@ -7415,11 +7415,15 @@ static int nft_object_dump(struct sk_buff *skb, unsigned int attr, + return -1; + } + +-static const struct nft_object_type *__nft_obj_type_get(u32 objtype) ++static const struct nft_object_type *__nft_obj_type_get(u32 objtype, u8 family) + { + const struct nft_object_type *type; + + list_for_each_entry(type, &nf_tables_objects, list) { ++ if (type->family != NFPROTO_UNSPEC && ++ type->family != family) ++ continue; ++ + if (objtype == type->type) + return type; + } +@@ -7427,11 +7431,11 @@ static const struct nft_object_type *__nft_obj_type_get(u32 objtype) + } + + static const struct nft_object_type * +-nft_obj_type_get(struct net *net, u32 objtype) ++nft_obj_type_get(struct net *net, u32 objtype, u8 family) + { + const struct nft_object_type *type; + +- type = __nft_obj_type_get(objtype); ++ type = __nft_obj_type_get(objtype, family); + if (type != NULL && try_module_get(type->owner)) + return type; + +@@ -7524,7 +7528,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) + return -EOPNOTSUPP; + +- type = __nft_obj_type_get(objtype); ++ type = __nft_obj_type_get(objtype, family); + if (WARN_ON_ONCE(!type)) + return -ENOENT; + +@@ -7538,7 +7542,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, + if (!nft_use_inc(&table->use)) + return -EMFILE; + +- type = nft_obj_type_get(net, objtype); ++ type = nft_obj_type_get(net, objtype, family); + if (IS_ERR(type)) { + err = PTR_ERR(type); + goto err_type; +diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c +index 9f21953c7433..f735d79d8be5 100644 +--- a/net/netfilter/nft_tunnel.c ++++ b/net/netfilter/nft_tunnel.c +@@ -713,6 +713,7 @@ static const struct nft_object_ops nft_tunnel_obj_ops = { + + static struct nft_object_type nft_tunnel_obj_type __read_mostly = { + .type = NFT_OBJECT_TUNNEL, ++ .family = NFPROTO_NETDEV, + .ops = &nft_tunnel_obj_ops, + .maxattr = NFTA_TUNNEL_KEY_MAX, + .policy = nft_tunnel_key_policy, +-- +2.43.0 + diff --git a/queue-6.6/netfilter-nft_ct-sanitize-layer-3-and-4-protocol-num.patch b/queue-6.6/netfilter-nft_ct-sanitize-layer-3-and-4-protocol-num.patch new file mode 100644 index 00000000000..109bdf2d5af --- /dev/null +++ b/queue-6.6/netfilter-nft_ct-sanitize-layer-3-and-4-protocol-num.patch @@ -0,0 +1,60 @@ +From 98ce0345632d3edc744d0c1409291cab49d51e56 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 29 Jan 2024 13:12:33 +0100 +Subject: netfilter: nft_ct: sanitize layer 3 and 4 protocol number in custom + expectations + +From: Pablo Neira Ayuso + +[ Upstream commit 8059918a1377f2f1fff06af4f5a4ed3d5acd6bc4 ] + +- Disallow families other than NFPROTO_{IPV4,IPV6,INET}. +- Disallow layer 4 protocol with no ports, since destination port is a + mandatory attribute for this object. + +Fixes: 857b46027d6f ("netfilter: nft_ct: add ct expectations support") +Signed-off-by: Pablo Neira Ayuso +Signed-off-by: Sasha Levin +--- + net/netfilter/nft_ct.c | 24 ++++++++++++++++++++++++ + 1 file changed, 24 insertions(+) + +diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c +index 86bb9d7797d9..aac98a3c966e 100644 +--- a/net/netfilter/nft_ct.c ++++ b/net/netfilter/nft_ct.c +@@ -1250,7 +1250,31 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx, + if (tb[NFTA_CT_EXPECT_L3PROTO]) + priv->l3num = ntohs(nla_get_be16(tb[NFTA_CT_EXPECT_L3PROTO])); + ++ switch (priv->l3num) { ++ case NFPROTO_IPV4: ++ case NFPROTO_IPV6: ++ if (priv->l3num != ctx->family) ++ return -EINVAL; ++ ++ fallthrough; ++ case NFPROTO_INET: ++ break; ++ default: ++ return -EOPNOTSUPP; ++ } ++ + priv->l4proto = nla_get_u8(tb[NFTA_CT_EXPECT_L4PROTO]); ++ switch (priv->l4proto) { ++ case IPPROTO_TCP: ++ case IPPROTO_UDP: ++ case IPPROTO_UDPLITE: ++ case IPPROTO_DCCP: ++ case IPPROTO_SCTP: ++ break; ++ default: ++ return -EOPNOTSUPP; ++ } ++ + priv->dport = nla_get_be16(tb[NFTA_CT_EXPECT_DPORT]); + priv->timeout = nla_get_u32(tb[NFTA_CT_EXPECT_TIMEOUT]); + priv->size = nla_get_u8(tb[NFTA_CT_EXPECT_SIZE]); +-- +2.43.0 + diff --git a/queue-6.6/octeontx2-pf-remove-xdp-queues-on-program-detach.patch b/queue-6.6/octeontx2-pf-remove-xdp-queues-on-program-detach.patch new file mode 100644 index 00000000000..e5d2b3cf083 --- /dev/null +++ b/queue-6.6/octeontx2-pf-remove-xdp-queues-on-program-detach.patch @@ -0,0 +1,89 @@ +From f9fc88b884d7b289e250c6a897e8e25329975f24 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 30 Jan 2024 17:36:10 +0530 +Subject: octeontx2-pf: Remove xdp queues on program detach + +From: Geetha sowjanya + +[ Upstream commit 04f647c8e456fcfabe9c252a4dcaee03b586fa4f ] + +XDP queues are created/destroyed when a XDP program +is attached/detached. In current driver xdp_queues are not +getting destroyed on program exit due to incorrect xdp_queue +and tot_tx_queue count values. + +This patch fixes the issue by setting tot_tx_queue and xdp_queue +count to correct values. It also fixes xdp.data_hard_start address. + +Fixes: 06059a1a9a4a ("octeontx2-pf: Add XDP support to netdev PF") +Signed-off-by: Geetha sowjanya +Link: https://lore.kernel.org/r/20240130120610.16673-1-gakula@marvell.com +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c | 1 - + drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 3 +-- + drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c | 7 +++---- + 3 files changed, 4 insertions(+), 7 deletions(-) + +diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +index 53f6258a973c..8b7fc0af91ce 100644 +--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c ++++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +@@ -314,7 +314,6 @@ static int otx2_set_channels(struct net_device *dev, + pfvf->hw.tx_queues = channel->tx_count; + if (pfvf->xdp_prog) + pfvf->hw.xdp_queues = channel->rx_count; +- pfvf->hw.non_qos_queues = pfvf->hw.tx_queues + pfvf->hw.xdp_queues; + + if (if_up) + err = dev->netdev_ops->ndo_open(dev); +diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +index a57455aebff6..e5fe67e73865 100644 +--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c ++++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +@@ -1744,6 +1744,7 @@ int otx2_open(struct net_device *netdev) + /* RQ and SQs are mapped to different CQs, + * so find out max CQ IRQs (i.e CINTs) needed. + */ ++ pf->hw.non_qos_queues = pf->hw.tx_queues + pf->hw.xdp_queues; + pf->hw.cint_cnt = max3(pf->hw.rx_queues, pf->hw.tx_queues, + pf->hw.tc_tx_queues); + +@@ -2643,8 +2644,6 @@ static int otx2_xdp_setup(struct otx2_nic *pf, struct bpf_prog *prog) + xdp_features_clear_redirect_target(dev); + } + +- pf->hw.non_qos_queues += pf->hw.xdp_queues; +- + if (if_up) + otx2_open(pf->netdev); + +diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +index 4d519ea833b2..f828d32737af 100644 +--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c ++++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +@@ -1403,7 +1403,7 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf, + struct otx2_cq_queue *cq, + bool *need_xdp_flush) + { +- unsigned char *hard_start, *data; ++ unsigned char *hard_start; + int qidx = cq->cq_idx; + struct xdp_buff xdp; + struct page *page; +@@ -1417,9 +1417,8 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf, + + xdp_init_buff(&xdp, pfvf->rbsize, &cq->xdp_rxq); + +- data = (unsigned char *)phys_to_virt(pa); +- hard_start = page_address(page); +- xdp_prepare_buff(&xdp, hard_start, data - hard_start, ++ hard_start = (unsigned char *)phys_to_virt(pa); ++ xdp_prepare_buff(&xdp, hard_start, OTX2_HEAD_ROOM, + cqe->sg.seg_size, false); + + act = bpf_prog_run_xdp(prog, &xdp); +-- +2.43.0 + diff --git a/queue-6.6/pds_core-cancel-aq-work-on-teardown.patch b/queue-6.6/pds_core-cancel-aq-work-on-teardown.patch new file mode 100644 index 00000000000..de398680b37 --- /dev/null +++ b/queue-6.6/pds_core-cancel-aq-work-on-teardown.patch @@ -0,0 +1,53 @@ +From 99fbdc683a1064c86150a53f816d935dd6726965 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 29 Jan 2024 15:40:31 -0800 +Subject: pds_core: Cancel AQ work on teardown + +From: Brett Creeley + +[ Upstream commit d321067e2cfa4d5e45401a00912ca9da8d1af631 ] + +There is a small window where pdsc_work_thread() +calls pdsc_process_adminq() and pdsc_process_adminq() +passes the PDSC_S_STOPPING_DRIVER check and starts +to process adminq/notifyq work and then the driver +starts a fw_down cycle. This could cause some +undefined behavior if the notifyqcq/adminqcq are +free'd while pdsc_process_adminq() is running. Use +cancel_work_sync() on the adminqcq's work struct +to make sure any pending work items are cancelled +and any in progress work items are completed. + +Also, make sure to not call cancel_work_sync() if +the work item has not be initialized. Without this, +traces will happen in cases where a reset fails and +teardown is called again or if reset fails and the +driver is removed. + +Fixes: 01ba61b55b20 ("pds_core: Add adminq processing and commands") +Signed-off-by: Brett Creeley +Reviewed-by: Shannon Nelson +Reviewed-by: Przemek Kitszel +Link: https://lore.kernel.org/r/20240129234035.69802-3-brett.creeley@amd.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/amd/pds_core/core.c | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c +index 36f9b932b9e2..b58c166d438d 100644 +--- a/drivers/net/ethernet/amd/pds_core/core.c ++++ b/drivers/net/ethernet/amd/pds_core/core.c +@@ -466,6 +466,8 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing) + + if (!pdsc->pdev->is_virtfn) + pdsc_devcmd_reset(pdsc); ++ if (pdsc->adminqcq.work.func) ++ cancel_work_sync(&pdsc->adminqcq.work); + pdsc_qcq_free(pdsc, &pdsc->notifyqcq); + pdsc_qcq_free(pdsc, &pdsc->adminqcq); + +-- +2.43.0 + diff --git a/queue-6.6/pds_core-clear-bars-on-reset.patch b/queue-6.6/pds_core-clear-bars-on-reset.patch new file mode 100644 index 00000000000..ba8c06ccb2a --- /dev/null +++ b/queue-6.6/pds_core-clear-bars-on-reset.patch @@ -0,0 +1,158 @@ +From 65a4a27982b343aefa71859169eaf060f5c2794f Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 29 Jan 2024 15:40:34 -0800 +Subject: pds_core: Clear BARs on reset + +From: Brett Creeley + +[ Upstream commit e96094c1d11cce4deb5da3c0500d49041ab845b8 ] + +During reset the BARs might be accessed when they are +unmapped. This can cause unexpected issues, so fix it by +clearing the cached BAR values so they are not accessed +until they are re-mapped. + +Also, make sure any places that can access the BARs +when they are NULL are prevented. + +Fixes: 49ce92fbee0b ("pds_core: add FW update feature to devlink") +Signed-off-by: Brett Creeley +Reviewed-by: Shannon Nelson +Reviewed-by: Przemek Kitszel +Link: https://lore.kernel.org/r/20240129234035.69802-6-brett.creeley@amd.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/amd/pds_core/adminq.c | 28 +++++++++++++++------ + drivers/net/ethernet/amd/pds_core/dev.c | 9 ++++++- + drivers/net/ethernet/amd/pds_core/devlink.c | 3 ++- + drivers/net/ethernet/amd/pds_core/fw.c | 3 +++ + drivers/net/ethernet/amd/pds_core/main.c | 5 ++++ + 5 files changed, 38 insertions(+), 10 deletions(-) + +diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c +index 5edff33d56f3..ea773cfa0af6 100644 +--- a/drivers/net/ethernet/amd/pds_core/adminq.c ++++ b/drivers/net/ethernet/amd/pds_core/adminq.c +@@ -191,10 +191,16 @@ static int __pdsc_adminq_post(struct pdsc *pdsc, + + /* Check that the FW is running */ + if (!pdsc_is_fw_running(pdsc)) { +- u8 fw_status = ioread8(&pdsc->info_regs->fw_status); +- +- dev_info(pdsc->dev, "%s: post failed - fw not running %#02x:\n", +- __func__, fw_status); ++ if (pdsc->info_regs) { ++ u8 fw_status = ++ ioread8(&pdsc->info_regs->fw_status); ++ ++ dev_info(pdsc->dev, "%s: post failed - fw not running %#02x:\n", ++ __func__, fw_status); ++ } else { ++ dev_info(pdsc->dev, "%s: post failed - BARs not setup\n", ++ __func__); ++ } + ret = -ENXIO; + + goto err_out_unlock; +@@ -266,10 +272,16 @@ int pdsc_adminq_post(struct pdsc *pdsc, + break; + + if (!pdsc_is_fw_running(pdsc)) { +- u8 fw_status = ioread8(&pdsc->info_regs->fw_status); +- +- dev_dbg(pdsc->dev, "%s: post wait failed - fw not running %#02x:\n", +- __func__, fw_status); ++ if (pdsc->info_regs) { ++ u8 fw_status = ++ ioread8(&pdsc->info_regs->fw_status); ++ ++ dev_dbg(pdsc->dev, "%s: post wait failed - fw not running %#02x:\n", ++ __func__, fw_status); ++ } else { ++ dev_dbg(pdsc->dev, "%s: post wait failed - BARs not setup\n", ++ __func__); ++ } + err = -ENXIO; + break; + } +diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c +index eb178728edba..1d590eb463d0 100644 +--- a/drivers/net/ethernet/amd/pds_core/dev.c ++++ b/drivers/net/ethernet/amd/pds_core/dev.c +@@ -55,6 +55,9 @@ int pdsc_err_to_errno(enum pds_core_status_code code) + + bool pdsc_is_fw_running(struct pdsc *pdsc) + { ++ if (!pdsc->info_regs) ++ return false; ++ + pdsc->fw_status = ioread8(&pdsc->info_regs->fw_status); + pdsc->last_fw_time = jiffies; + pdsc->last_hb = ioread32(&pdsc->info_regs->fw_heartbeat); +@@ -175,13 +178,17 @@ int pdsc_devcmd_locked(struct pdsc *pdsc, union pds_core_dev_cmd *cmd, + { + int err; + ++ if (!pdsc->cmd_regs) ++ return -ENXIO; ++ + memcpy_toio(&pdsc->cmd_regs->cmd, cmd, sizeof(*cmd)); + pdsc_devcmd_dbell(pdsc); + err = pdsc_devcmd_wait(pdsc, cmd->opcode, max_seconds); +- memcpy_fromio(comp, &pdsc->cmd_regs->comp, sizeof(*comp)); + + if ((err == -ENXIO || err == -ETIMEDOUT) && pdsc->wq) + queue_work(pdsc->wq, &pdsc->health_work); ++ else ++ memcpy_fromio(comp, &pdsc->cmd_regs->comp, sizeof(*comp)); + + return err; + } +diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c +index d2abf32b93fe..d8218bb153d9 100644 +--- a/drivers/net/ethernet/amd/pds_core/devlink.c ++++ b/drivers/net/ethernet/amd/pds_core/devlink.c +@@ -111,7 +111,8 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req, + + mutex_lock(&pdsc->devcmd_lock); + err = pdsc_devcmd_locked(pdsc, &cmd, &comp, pdsc->devcmd_timeout * 2); +- memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list)); ++ if (!err) ++ memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list)); + mutex_unlock(&pdsc->devcmd_lock); + if (err && err != -EIO) + return err; +diff --git a/drivers/net/ethernet/amd/pds_core/fw.c b/drivers/net/ethernet/amd/pds_core/fw.c +index 90a811f3878a..fa626719e68d 100644 +--- a/drivers/net/ethernet/amd/pds_core/fw.c ++++ b/drivers/net/ethernet/amd/pds_core/fw.c +@@ -107,6 +107,9 @@ int pdsc_firmware_update(struct pdsc *pdsc, const struct firmware *fw, + + dev_info(pdsc->dev, "Installing firmware\n"); + ++ if (!pdsc->cmd_regs) ++ return -ENXIO; ++ + dl = priv_to_devlink(pdsc); + devlink_flash_update_status_notify(dl, "Preparing to flash", + NULL, 0, 0); +diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c +index 4c7f982c12a1..7471a751e4d8 100644 +--- a/drivers/net/ethernet/amd/pds_core/main.c ++++ b/drivers/net/ethernet/amd/pds_core/main.c +@@ -37,6 +37,11 @@ static void pdsc_unmap_bars(struct pdsc *pdsc) + struct pdsc_dev_bar *bars = pdsc->bars; + unsigned int i; + ++ pdsc->info_regs = NULL; ++ pdsc->cmd_regs = NULL; ++ pdsc->intr_status = NULL; ++ pdsc->intr_ctrl = NULL; ++ + for (i = 0; i < PDS_CORE_BARS_MAX; i++) { + if (bars[i].vaddr) + pci_iounmap(pdsc->pdev, bars[i].vaddr); +-- +2.43.0 + diff --git a/queue-6.6/pds_core-implement-pci-reset-handlers.patch b/queue-6.6/pds_core-implement-pci-reset-handlers.patch new file mode 100644 index 00000000000..a527a898a0a --- /dev/null +++ b/queue-6.6/pds_core-implement-pci-reset-handlers.patch @@ -0,0 +1,156 @@ +From bed0ccacdf6940ceef1556ba6574226f5ab1fdea Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 14 Sep 2023 15:31:59 -0700 +Subject: pds_core: implement pci reset handlers + +From: Shannon Nelson + +[ Upstream commit ffa55858330f267beec995fc4f68098c91311c64 ] + +Implement the callbacks for a nice PCI reset. These get called +when a user is nice enough to use the sysfs PCI reset entry, e.g. + echo 1 > /sys/bus/pci/devices/0000:2b:00.0/reset + +Signed-off-by: Shannon Nelson +Reviewed-by: Brett Creeley +Signed-off-by: David S. Miller +Stable-dep-of: 7e82a8745b95 ("pds_core: Prevent race issues involving the adminq") +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/amd/pds_core/core.c | 14 +++++-- + drivers/net/ethernet/amd/pds_core/core.h | 4 ++ + drivers/net/ethernet/amd/pds_core/main.c | 50 ++++++++++++++++++++++++ + 3 files changed, 65 insertions(+), 3 deletions(-) + +diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c +index dfb43ed60e27..cc5e3d1fe652 100644 +--- a/drivers/net/ethernet/amd/pds_core/core.c ++++ b/drivers/net/ethernet/amd/pds_core/core.c +@@ -514,7 +514,7 @@ void pdsc_stop(struct pdsc *pdsc) + PDS_CORE_INTR_MASK_SET); + } + +-static void pdsc_fw_down(struct pdsc *pdsc) ++void pdsc_fw_down(struct pdsc *pdsc) + { + union pds_core_notifyq_comp reset_event = { + .reset.ecode = cpu_to_le16(PDS_EVENT_RESET), +@@ -522,10 +522,13 @@ static void pdsc_fw_down(struct pdsc *pdsc) + }; + + if (test_and_set_bit(PDSC_S_FW_DEAD, &pdsc->state)) { +- dev_err(pdsc->dev, "%s: already happening\n", __func__); ++ dev_warn(pdsc->dev, "%s: already happening\n", __func__); + return; + } + ++ if (pdsc->pdev->is_virtfn) ++ return; ++ + /* Notify clients of fw_down */ + if (pdsc->fw_reporter) + devlink_health_report(pdsc->fw_reporter, "FW down reported", pdsc); +@@ -535,7 +538,7 @@ static void pdsc_fw_down(struct pdsc *pdsc) + pdsc_teardown(pdsc, PDSC_TEARDOWN_RECOVERY); + } + +-static void pdsc_fw_up(struct pdsc *pdsc) ++void pdsc_fw_up(struct pdsc *pdsc) + { + union pds_core_notifyq_comp reset_event = { + .reset.ecode = cpu_to_le16(PDS_EVENT_RESET), +@@ -548,6 +551,11 @@ static void pdsc_fw_up(struct pdsc *pdsc) + return; + } + ++ if (pdsc->pdev->is_virtfn) { ++ clear_bit(PDSC_S_FW_DEAD, &pdsc->state); ++ return; ++ } ++ + err = pdsc_setup(pdsc, PDSC_SETUP_RECOVERY); + if (err) + goto err_out; +diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h +index b1c1f1007b06..860bce1731c7 100644 +--- a/drivers/net/ethernet/amd/pds_core/core.h ++++ b/drivers/net/ethernet/amd/pds_core/core.h +@@ -309,4 +309,8 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data); + + int pdsc_firmware_update(struct pdsc *pdsc, const struct firmware *fw, + struct netlink_ext_ack *extack); ++ ++void pdsc_fw_down(struct pdsc *pdsc); ++void pdsc_fw_up(struct pdsc *pdsc); ++ + #endif /* _PDSC_H_ */ +diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c +index 3a45bf474a19..4c7f982c12a1 100644 +--- a/drivers/net/ethernet/amd/pds_core/main.c ++++ b/drivers/net/ethernet/amd/pds_core/main.c +@@ -445,12 +445,62 @@ static void pdsc_remove(struct pci_dev *pdev) + devlink_free(dl); + } + ++static void pdsc_reset_prepare(struct pci_dev *pdev) ++{ ++ struct pdsc *pdsc = pci_get_drvdata(pdev); ++ ++ pdsc_fw_down(pdsc); ++ ++ pci_free_irq_vectors(pdev); ++ pdsc_unmap_bars(pdsc); ++ pci_release_regions(pdev); ++ pci_disable_device(pdev); ++} ++ ++static void pdsc_reset_done(struct pci_dev *pdev) ++{ ++ struct pdsc *pdsc = pci_get_drvdata(pdev); ++ struct device *dev = pdsc->dev; ++ int err; ++ ++ err = pci_enable_device(pdev); ++ if (err) { ++ dev_err(dev, "Cannot enable PCI device: %pe\n", ERR_PTR(err)); ++ return; ++ } ++ pci_set_master(pdev); ++ ++ if (!pdev->is_virtfn) { ++ pcie_print_link_status(pdsc->pdev); ++ ++ err = pci_request_regions(pdsc->pdev, PDS_CORE_DRV_NAME); ++ if (err) { ++ dev_err(pdsc->dev, "Cannot request PCI regions: %pe\n", ++ ERR_PTR(err)); ++ return; ++ } ++ ++ err = pdsc_map_bars(pdsc); ++ if (err) ++ return; ++ } ++ ++ pdsc_fw_up(pdsc); ++} ++ ++static const struct pci_error_handlers pdsc_err_handler = { ++ /* FLR handling */ ++ .reset_prepare = pdsc_reset_prepare, ++ .reset_done = pdsc_reset_done, ++}; ++ + static struct pci_driver pdsc_driver = { + .name = PDS_CORE_DRV_NAME, + .id_table = pdsc_id_table, + .probe = pdsc_probe, + .remove = pdsc_remove, + .sriov_configure = pdsc_sriov_configure, ++ .err_handler = &pdsc_err_handler, + }; + + void *pdsc_get_pf_struct(struct pci_dev *vf_pdev) +-- +2.43.0 + diff --git a/queue-6.6/pds_core-prevent-race-issues-involving-the-adminq.patch b/queue-6.6/pds_core-prevent-race-issues-involving-the-adminq.patch new file mode 100644 index 00000000000..bdcbd933950 --- /dev/null +++ b/queue-6.6/pds_core-prevent-race-issues-involving-the-adminq.patch @@ -0,0 +1,203 @@ +From a73817269398d67b0a90d1226bb24efafad91a1f Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 29 Jan 2024 15:40:33 -0800 +Subject: pds_core: Prevent race issues involving the adminq + +From: Brett Creeley + +[ Upstream commit 7e82a8745b951b1e794cc780d46f3fbee5e93447 ] + +There are multiple paths that can result in using the pdsc's +adminq. + +[1] pdsc_adminq_isr and the resulting work from queue_work(), + i.e. pdsc_work_thread()->pdsc_process_adminq() + +[2] pdsc_adminq_post() + +When the device goes through reset via PCIe reset and/or +a fw_down/fw_up cycle due to bad PCIe state or bad device +state the adminq is destroyed and recreated. + +A NULL pointer dereference can happen if [1] or [2] happens +after the adminq is already destroyed. + +In order to fix this, add some further state checks and +implement reference counting for adminq uses. Reference +counting was used because multiple threads can attempt to +access the adminq at the same time via [1] or [2]. Additionally, +multiple clients (i.e. pds-vfio-pci) can be using [2] +at the same time. + +The adminq_refcnt is initialized to 1 when the adminq has been +allocated and is ready to use. Users/clients of the adminq +(i.e. [1] and [2]) will increment the refcnt when they are using +the adminq. When the driver goes into a fw_down cycle it will +set the PDSC_S_FW_DEAD bit and then wait for the adminq_refcnt +to hit 1. Setting the PDSC_S_FW_DEAD before waiting will prevent +any further adminq_refcnt increments. Waiting for the +adminq_refcnt to hit 1 allows for any current users of the adminq +to finish before the driver frees the adminq. Once the +adminq_refcnt hits 1 the driver clears the refcnt to signify that +the adminq is deleted and cannot be used. On the fw_up cycle the +driver will once again initialize the adminq_refcnt to 1 allowing +the adminq to be used again. + +Fixes: 01ba61b55b20 ("pds_core: Add adminq processing and commands") +Signed-off-by: Brett Creeley +Reviewed-by: Shannon Nelson +Reviewed-by: Przemek Kitszel +Link: https://lore.kernel.org/r/20240129234035.69802-5-brett.creeley@amd.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/amd/pds_core/adminq.c | 31 +++++++++++++++++----- + drivers/net/ethernet/amd/pds_core/core.c | 21 +++++++++++++++ + drivers/net/ethernet/amd/pds_core/core.h | 1 + + 3 files changed, 47 insertions(+), 6 deletions(-) + +diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c +index 68be5ea251fc..5edff33d56f3 100644 +--- a/drivers/net/ethernet/amd/pds_core/adminq.c ++++ b/drivers/net/ethernet/amd/pds_core/adminq.c +@@ -63,6 +63,15 @@ static int pdsc_process_notifyq(struct pdsc_qcq *qcq) + return nq_work; + } + ++static bool pdsc_adminq_inc_if_up(struct pdsc *pdsc) ++{ ++ if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER) || ++ pdsc->state & BIT_ULL(PDSC_S_FW_DEAD)) ++ return false; ++ ++ return refcount_inc_not_zero(&pdsc->adminq_refcnt); ++} ++ + void pdsc_process_adminq(struct pdsc_qcq *qcq) + { + union pds_core_adminq_comp *comp; +@@ -75,9 +84,9 @@ void pdsc_process_adminq(struct pdsc_qcq *qcq) + int aq_work = 0; + int credits; + +- /* Don't process AdminQ when shutting down */ +- if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER)) { +- dev_err(pdsc->dev, "%s: called while PDSC_S_STOPPING_DRIVER\n", ++ /* Don't process AdminQ when it's not up */ ++ if (!pdsc_adminq_inc_if_up(pdsc)) { ++ dev_err(pdsc->dev, "%s: called while adminq is unavailable\n", + __func__); + return; + } +@@ -124,6 +133,7 @@ void pdsc_process_adminq(struct pdsc_qcq *qcq) + pds_core_intr_credits(&pdsc->intr_ctrl[qcq->intx], + credits, + PDS_CORE_INTR_CRED_REARM); ++ refcount_dec(&pdsc->adminq_refcnt); + } + + void pdsc_work_thread(struct work_struct *work) +@@ -138,9 +148,9 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data) + struct pdsc *pdsc = data; + struct pdsc_qcq *qcq; + +- /* Don't process AdminQ when shutting down */ +- if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER)) { +- dev_err(pdsc->dev, "%s: called while PDSC_S_STOPPING_DRIVER\n", ++ /* Don't process AdminQ when it's not up */ ++ if (!pdsc_adminq_inc_if_up(pdsc)) { ++ dev_err(pdsc->dev, "%s: called while adminq is unavailable\n", + __func__); + return IRQ_HANDLED; + } +@@ -148,6 +158,7 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data) + qcq = &pdsc->adminqcq; + queue_work(pdsc->wq, &qcq->work); + pds_core_intr_mask(&pdsc->intr_ctrl[qcq->intx], PDS_CORE_INTR_MASK_CLEAR); ++ refcount_dec(&pdsc->adminq_refcnt); + + return IRQ_HANDLED; + } +@@ -231,6 +242,12 @@ int pdsc_adminq_post(struct pdsc *pdsc, + int err = 0; + int index; + ++ if (!pdsc_adminq_inc_if_up(pdsc)) { ++ dev_dbg(pdsc->dev, "%s: preventing adminq cmd %u\n", ++ __func__, cmd->opcode); ++ return -ENXIO; ++ } ++ + wc.qcq = &pdsc->adminqcq; + index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp, &wc); + if (index < 0) { +@@ -286,6 +303,8 @@ int pdsc_adminq_post(struct pdsc *pdsc, + queue_work(pdsc->wq, &pdsc->health_work); + } + ++ refcount_dec(&pdsc->adminq_refcnt); ++ + return err; + } + EXPORT_SYMBOL_GPL(pdsc_adminq_post); +diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c +index cc5e3d1fe652..e1f554f25329 100644 +--- a/drivers/net/ethernet/amd/pds_core/core.c ++++ b/drivers/net/ethernet/amd/pds_core/core.c +@@ -452,6 +452,7 @@ int pdsc_setup(struct pdsc *pdsc, bool init) + if (init) + pdsc_debugfs_add_viftype(pdsc); + ++ refcount_set(&pdsc->adminq_refcnt, 1); + clear_bit(PDSC_S_FW_DEAD, &pdsc->state); + return 0; + +@@ -514,6 +515,24 @@ void pdsc_stop(struct pdsc *pdsc) + PDS_CORE_INTR_MASK_SET); + } + ++static void pdsc_adminq_wait_and_dec_once_unused(struct pdsc *pdsc) ++{ ++ /* The driver initializes the adminq_refcnt to 1 when the adminq is ++ * allocated and ready for use. Other users/requesters will increment ++ * the refcnt while in use. If the refcnt is down to 1 then the adminq ++ * is not in use and the refcnt can be cleared and adminq freed. Before ++ * calling this function the driver will set PDSC_S_FW_DEAD, which ++ * prevent subsequent attempts to use the adminq and increment the ++ * refcnt to fail. This guarantees that this function will eventually ++ * exit. ++ */ ++ while (!refcount_dec_if_one(&pdsc->adminq_refcnt)) { ++ dev_dbg_ratelimited(pdsc->dev, "%s: adminq in use\n", ++ __func__); ++ cpu_relax(); ++ } ++} ++ + void pdsc_fw_down(struct pdsc *pdsc) + { + union pds_core_notifyq_comp reset_event = { +@@ -529,6 +548,8 @@ void pdsc_fw_down(struct pdsc *pdsc) + if (pdsc->pdev->is_virtfn) + return; + ++ pdsc_adminq_wait_and_dec_once_unused(pdsc); ++ + /* Notify clients of fw_down */ + if (pdsc->fw_reporter) + devlink_health_report(pdsc->fw_reporter, "FW down reported", pdsc); +diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h +index 860bce1731c7..d6d19f72df00 100644 +--- a/drivers/net/ethernet/amd/pds_core/core.h ++++ b/drivers/net/ethernet/amd/pds_core/core.h +@@ -184,6 +184,7 @@ struct pdsc { + struct mutex devcmd_lock; /* lock for dev_cmd operations */ + struct mutex config_lock; /* lock for configuration operations */ + spinlock_t adminq_lock; /* lock for adminq operations */ ++ refcount_t adminq_refcnt; + struct pds_core_dev_info_regs __iomem *info_regs; + struct pds_core_dev_cmd_regs __iomem *cmd_regs; + struct pds_core_intr __iomem *intr_ctrl; +-- +2.43.0 + diff --git a/queue-6.6/pds_core-rework-teardown-setup-flow-to-be-more-commo.patch b/queue-6.6/pds_core-rework-teardown-setup-flow-to-be-more-commo.patch new file mode 100644 index 00000000000..00d7b6d2808 --- /dev/null +++ b/queue-6.6/pds_core-rework-teardown-setup-flow-to-be-more-commo.patch @@ -0,0 +1,154 @@ +From a17bfbfbb57e5ed3eb1dbbdc3bb14c0fdf2fd1a3 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 29 Jan 2024 15:40:35 -0800 +Subject: pds_core: Rework teardown/setup flow to be more common + +From: Brett Creeley + +[ Upstream commit bc90fbe0c3182157d2be100a2f6c2edbb1820677 ] + +Currently the teardown/setup flow for driver probe/remove is quite +a bit different from the reset flows in pdsc_fw_down()/pdsc_fw_up(). +One key piece that's missing are the calls to pci_alloc_irq_vectors() +and pci_free_irq_vectors(). The pcie reset case is calling +pci_free_irq_vectors() on reset_prepare, but not calling the +corresponding pci_alloc_irq_vectors() on reset_done. This is causing +unexpected/unwanted interrupt behavior due to the adminq interrupt +being accidentally put into legacy interrupt mode. Also, the +pci_alloc_irq_vectors()/pci_free_irq_vectors() functions are being +called directly in probe/remove respectively. + +Fix this inconsistency by making the following changes: + 1. Always call pdsc_dev_init() in pdsc_setup(), which calls + pci_alloc_irq_vectors() and get rid of the now unused + pds_dev_reinit(). + 2. Always free/clear the pdsc->intr_info in pdsc_teardown() + since this structure will get re-alloced in pdsc_setup(). + 3. Move the calls of pci_free_irq_vectors() to pdsc_teardown() + since pci_alloc_irq_vectors() will always be called in + pdsc_setup()->pdsc_dev_init() for both the probe/remove and + reset flows. + 4. Make sure to only create the debugfs "identity" entry when it + doesn't already exist, which it will in the reset case because + it's already been created in the initial call to pdsc_dev_init(). + +Fixes: ffa55858330f ("pds_core: implement pci reset handlers") +Signed-off-by: Brett Creeley +Reviewed-by: Shannon Nelson +Link: https://lore.kernel.org/r/20240129234035.69802-7-brett.creeley@amd.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/amd/pds_core/core.c | 13 +++++-------- + drivers/net/ethernet/amd/pds_core/core.h | 1 - + drivers/net/ethernet/amd/pds_core/debugfs.c | 4 ++++ + drivers/net/ethernet/amd/pds_core/dev.c | 7 ------- + drivers/net/ethernet/amd/pds_core/main.c | 2 -- + 5 files changed, 9 insertions(+), 18 deletions(-) + +diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c +index e1f554f25329..eb73c921dc1e 100644 +--- a/drivers/net/ethernet/amd/pds_core/core.c ++++ b/drivers/net/ethernet/amd/pds_core/core.c +@@ -407,10 +407,7 @@ int pdsc_setup(struct pdsc *pdsc, bool init) + int numdescs; + int err; + +- if (init) +- err = pdsc_dev_init(pdsc); +- else +- err = pdsc_dev_reinit(pdsc); ++ err = pdsc_dev_init(pdsc); + if (err) + return err; + +@@ -479,10 +476,9 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing) + for (i = 0; i < pdsc->nintrs; i++) + pdsc_intr_free(pdsc, i); + +- if (removing) { +- kfree(pdsc->intr_info); +- pdsc->intr_info = NULL; +- } ++ kfree(pdsc->intr_info); ++ pdsc->intr_info = NULL; ++ pdsc->nintrs = 0; + } + + if (pdsc->kern_dbpage) { +@@ -490,6 +486,7 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing) + pdsc->kern_dbpage = NULL; + } + ++ pci_free_irq_vectors(pdsc->pdev); + set_bit(PDSC_S_FW_DEAD, &pdsc->state); + } + +diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h +index d6d19f72df00..f410f7d13205 100644 +--- a/drivers/net/ethernet/amd/pds_core/core.h ++++ b/drivers/net/ethernet/amd/pds_core/core.h +@@ -281,7 +281,6 @@ int pdsc_devcmd_locked(struct pdsc *pdsc, union pds_core_dev_cmd *cmd, + union pds_core_dev_comp *comp, int max_seconds); + int pdsc_devcmd_init(struct pdsc *pdsc); + int pdsc_devcmd_reset(struct pdsc *pdsc); +-int pdsc_dev_reinit(struct pdsc *pdsc); + int pdsc_dev_init(struct pdsc *pdsc); + + int pdsc_intr_alloc(struct pdsc *pdsc, char *name, +diff --git a/drivers/net/ethernet/amd/pds_core/debugfs.c b/drivers/net/ethernet/amd/pds_core/debugfs.c +index 8ec392299b7d..4e8579ca1c8c 100644 +--- a/drivers/net/ethernet/amd/pds_core/debugfs.c ++++ b/drivers/net/ethernet/amd/pds_core/debugfs.c +@@ -64,6 +64,10 @@ DEFINE_SHOW_ATTRIBUTE(identity); + + void pdsc_debugfs_add_ident(struct pdsc *pdsc) + { ++ /* This file will already exist in the reset flow */ ++ if (debugfs_lookup("identity", pdsc->dentry)) ++ return; ++ + debugfs_create_file("identity", 0400, pdsc->dentry, + pdsc, &identity_fops); + } +diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c +index 1d590eb463d0..f0e39ab40045 100644 +--- a/drivers/net/ethernet/amd/pds_core/dev.c ++++ b/drivers/net/ethernet/amd/pds_core/dev.c +@@ -309,13 +309,6 @@ static int pdsc_identify(struct pdsc *pdsc) + return 0; + } + +-int pdsc_dev_reinit(struct pdsc *pdsc) +-{ +- pdsc_init_devinfo(pdsc); +- +- return pdsc_identify(pdsc); +-} +- + int pdsc_dev_init(struct pdsc *pdsc) + { + unsigned int nintrs; +diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c +index 7471a751e4d8..7cc5a6b94939 100644 +--- a/drivers/net/ethernet/amd/pds_core/main.c ++++ b/drivers/net/ethernet/amd/pds_core/main.c +@@ -438,7 +438,6 @@ static void pdsc_remove(struct pci_dev *pdev) + mutex_destroy(&pdsc->config_lock); + mutex_destroy(&pdsc->devcmd_lock); + +- pci_free_irq_vectors(pdev); + pdsc_unmap_bars(pdsc); + pci_release_regions(pdev); + } +@@ -456,7 +455,6 @@ static void pdsc_reset_prepare(struct pci_dev *pdev) + + pdsc_fw_down(pdsc); + +- pci_free_irq_vectors(pdev); + pdsc_unmap_bars(pdsc); + pci_release_regions(pdev); + pci_disable_device(pdev); +-- +2.43.0 + diff --git a/queue-6.6/pds_core-use-struct-pdsc-for-the-pdsc_adminq_isr-pri.patch b/queue-6.6/pds_core-use-struct-pdsc-for-the-pdsc_adminq_isr-pri.patch new file mode 100644 index 00000000000..8f4b95da556 --- /dev/null +++ b/queue-6.6/pds_core-use-struct-pdsc-for-the-pdsc_adminq_isr-pri.patch @@ -0,0 +1,72 @@ +From a1f0fd84d2f6d70de72d1e837a9b4af21d5843dc Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 29 Jan 2024 15:40:32 -0800 +Subject: pds_core: Use struct pdsc for the pdsc_adminq_isr private data + +From: Brett Creeley + +[ Upstream commit 951705151e50f9022bc96ec8b3fd5697380b1df6 ] + +The initial design for the adminq interrupt was done based +on client drivers having their own adminq and adminq +interrupt. So, each client driver's adminq isr would use +their specific adminqcq for the private data struct. For the +time being the design has changed to only use a single +adminq for all clients. So, instead use the struct pdsc for +the private data to simplify things a bit. + +This also has the benefit of not dereferencing the adminqcq +to access the pdsc struct when the PDSC_S_STOPPING_DRIVER bit +is set and the adminqcq has actually been cleared/freed. + +Fixes: 01ba61b55b20 ("pds_core: Add adminq processing and commands") +Signed-off-by: Brett Creeley +Reviewed-by: Shannon Nelson +Reviewed-by: Przemek Kitszel +Link: https://lore.kernel.org/r/20240129234035.69802-4-brett.creeley@amd.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/amd/pds_core/adminq.c | 5 +++-- + drivers/net/ethernet/amd/pds_core/core.c | 2 +- + 2 files changed, 4 insertions(+), 3 deletions(-) + +diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c +index 5beadabc2136..68be5ea251fc 100644 +--- a/drivers/net/ethernet/amd/pds_core/adminq.c ++++ b/drivers/net/ethernet/amd/pds_core/adminq.c +@@ -135,8 +135,8 @@ void pdsc_work_thread(struct work_struct *work) + + irqreturn_t pdsc_adminq_isr(int irq, void *data) + { +- struct pdsc_qcq *qcq = data; +- struct pdsc *pdsc = qcq->pdsc; ++ struct pdsc *pdsc = data; ++ struct pdsc_qcq *qcq; + + /* Don't process AdminQ when shutting down */ + if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER)) { +@@ -145,6 +145,7 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data) + return IRQ_HANDLED; + } + ++ qcq = &pdsc->adminqcq; + queue_work(pdsc->wq, &qcq->work); + pds_core_intr_mask(&pdsc->intr_ctrl[qcq->intx], PDS_CORE_INTR_MASK_CLEAR); + +diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c +index b58c166d438d..dfb43ed60e27 100644 +--- a/drivers/net/ethernet/amd/pds_core/core.c ++++ b/drivers/net/ethernet/amd/pds_core/core.c +@@ -125,7 +125,7 @@ static int pdsc_qcq_intr_alloc(struct pdsc *pdsc, struct pdsc_qcq *qcq) + + snprintf(name, sizeof(name), "%s-%d-%s", + PDS_CORE_DRV_NAME, pdsc->pdev->bus->number, qcq->q.name); +- index = pdsc_intr_alloc(pdsc, name, pdsc_adminq_isr, qcq); ++ index = pdsc_intr_alloc(pdsc, name, pdsc_adminq_isr, pdsc); + if (index < 0) + return index; + qcq->intx = index; +-- +2.43.0 + diff --git a/queue-6.6/regulator-ti-abb-don-t-use-devm_platform_ioremap_res.patch b/queue-6.6/regulator-ti-abb-don-t-use-devm_platform_ioremap_res.patch new file mode 100644 index 00000000000..006e0bc8b73 --- /dev/null +++ b/queue-6.6/regulator-ti-abb-don-t-use-devm_platform_ioremap_res.patch @@ -0,0 +1,103 @@ +From 5ed74c001b3c23bb18cec08480d13def29d551f7 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 23 Jan 2024 12:14:56 +0100 +Subject: regulator: ti-abb: don't use devm_platform_ioremap_resource_byname + for shared interrupt register + +From: Romain Naour + +[ Upstream commit a67e1f0bd4564b485e0f0c3ed7f6bf17688be268 ] + +We can't use devm_platform_ioremap_resource_byname() to remap the +interrupt register that can be shared between +regulator-abb-{ivahd,dspeve,gpu} drivers instances. + +The combined helper introduce a call to devm_request_mem_region() that +creates a new busy resource region on PRM_IRQSTATUS_MPU register +(0x4ae06010). The first devm_request_mem_region() call succeeds for +regulator-abb-ivahd but fails for the two other regulator-abb-dspeve +and regulator-abb-gpu. + + # cat /proc/iomem | grep -i 4ae06 + 4ae06010-4ae06013 : 4ae07e34.regulator-abb-ivahd int-address + 4ae06014-4ae06017 : 4ae07ddc.regulator-abb-mpu int-address + +regulator-abb-dspeve and regulator-abb-gpu are missing due to +devm_request_mem_region() failure (EBUSY): + + [ 1.326660] ti_abb 4ae07e30.regulator-abb-dspeve: can't request region for resource [mem 0x4ae06010-0x4ae06013] + [ 1.326660] ti_abb: probe of 4ae07e30.regulator-abb-dspeve failed with error -16 + [ 1.327239] ti_abb 4ae07de4.regulator-abb-gpu: can't request region for resource [mem 0x4ae06010-0x4ae06013] + [ 1.327270] ti_abb: probe of 4ae07de4.regulator-abb-gpu failed with error -16 + +>From arm/boot/dts/dra7.dtsi: + +The abb_mpu is the only instance using its own interrupt register: + (0x4ae06014) PRM_IRQSTATUS_MPU_2, ABB_MPU_DONE_ST (bit 7) + +The other tree instances (abb_ivahd, abb_dspeve, abb_gpu) share +PRM_IRQSTATUS_MPU register (0x4ae06010) but use different bits +ABB_IVA_DONE_ST (bit 30), ABB_DSPEVE_DONE_ST( bit 29) and +ABB_GPU_DONE_ST (but 28). + +The commit b36c6b1887ff ("regulator: ti-abb: Make use of the helper +function devm_ioremap related") overlooked the following comment +implicitly explaining why devm_ioremap() is used in this case: + + /* + * We may have shared interrupt register offsets which are + * write-1-to-clear between domains ensuring exclusivity. + */ + +Fixes and partially reverts commit b36c6b1887ff ("regulator: ti-abb: +Make use of the helper function devm_ioremap related"). + +Improve the existing comment to avoid further conversion to +devm_platform_ioremap_resource_byname(). + +Fixes: b36c6b1887ff ("regulator: ti-abb: Make use of the helper function devm_ioremap related") +Signed-off-by: Romain Naour +Reviewed-by: Yoann Congal +Link: https://msgid.link/r/20240123111456.739381-1-romain.naour@smile.fr +Signed-off-by: Mark Brown +Signed-off-by: Sasha Levin +--- + drivers/regulator/ti-abb-regulator.c | 22 +++++++++++++++++++--- + 1 file changed, 19 insertions(+), 3 deletions(-) + +diff --git a/drivers/regulator/ti-abb-regulator.c b/drivers/regulator/ti-abb-regulator.c +index 86d2d80b4b41..ae5dcaea84df 100644 +--- a/drivers/regulator/ti-abb-regulator.c ++++ b/drivers/regulator/ti-abb-regulator.c +@@ -734,9 +734,25 @@ static int ti_abb_probe(struct platform_device *pdev) + return PTR_ERR(abb->setup_reg); + } + +- abb->int_base = devm_platform_ioremap_resource_byname(pdev, "int-address"); +- if (IS_ERR(abb->int_base)) +- return PTR_ERR(abb->int_base); ++ pname = "int-address"; ++ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, pname); ++ if (!res) { ++ dev_err(dev, "Missing '%s' IO resource\n", pname); ++ return -ENODEV; ++ } ++ /* ++ * The MPU interrupt status register (PRM_IRQSTATUS_MPU) is ++ * shared between regulator-abb-{ivahd,dspeve,gpu} driver ++ * instances. Therefore use devm_ioremap() rather than ++ * devm_platform_ioremap_resource_byname() to avoid busy ++ * resource region conflicts. ++ */ ++ abb->int_base = devm_ioremap(dev, res->start, ++ resource_size(res)); ++ if (!abb->int_base) { ++ dev_err(dev, "Unable to map '%s'\n", pname); ++ return -ENOMEM; ++ } + + /* Map Optional resources */ + pname = "efuse-address"; +-- +2.43.0 + diff --git a/queue-6.6/scsi-core-move-scsi_host_busy-out-of-host-lock-for-w.patch b/queue-6.6/scsi-core-move-scsi_host_busy-out-of-host-lock-for-w.patch new file mode 100644 index 00000000000..bb1d3e8ee5a --- /dev/null +++ b/queue-6.6/scsi-core-move-scsi_host_busy-out-of-host-lock-for-w.patch @@ -0,0 +1,116 @@ +From d5b948bafbca7c10ce1957da131fd37b07f9dcf4 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 12 Jan 2024 15:00:00 +0800 +Subject: scsi: core: Move scsi_host_busy() out of host lock for waking up EH + handler + +From: Ming Lei + +[ Upstream commit 4373534a9850627a2695317944898eb1283a2db0 ] + +Inside scsi_eh_wakeup(), scsi_host_busy() is called & checked with host +lock every time for deciding if error handler kthread needs to be waken up. + +This can be too heavy in case of recovery, such as: + + - N hardware queues + + - queue depth is M for each hardware queue + + - each scsi_host_busy() iterates over (N * M) tag/requests + +If recovery is triggered in case that all requests are in-flight, each +scsi_eh_wakeup() is strictly serialized, when scsi_eh_wakeup() is called +for the last in-flight request, scsi_host_busy() has been run for (N * M - +1) times, and request has been iterated for (N*M - 1) * (N * M) times. + +If both N and M are big enough, hard lockup can be triggered on acquiring +host lock, and it is observed on mpi3mr(128 hw queues, queue depth 8169). + +Fix the issue by calling scsi_host_busy() outside the host lock. We don't +need the host lock for getting busy count because host the lock never +covers that. + +[mkp: Drop unnecessary 'busy' variables pointed out by Bart] + +Cc: Ewan Milne +Fixes: 6eb045e092ef ("scsi: core: avoid host-wide host_busy counter for scsi_mq") +Signed-off-by: Ming Lei +Link: https://lore.kernel.org/r/20240112070000.4161982-1-ming.lei@redhat.com +Reviewed-by: Ewan D. Milne +Reviewed-by: Sathya Prakash Veerichetty +Tested-by: Sathya Prakash Veerichetty +Reviewed-by: Bart Van Assche +Signed-off-by: Martin K. Petersen +Signed-off-by: Sasha Levin +--- + drivers/scsi/scsi_error.c | 8 ++++---- + drivers/scsi/scsi_lib.c | 2 +- + drivers/scsi/scsi_priv.h | 2 +- + 3 files changed, 6 insertions(+), 6 deletions(-) + +diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c +index d983f4a0e9f1..3328b175a832 100644 +--- a/drivers/scsi/scsi_error.c ++++ b/drivers/scsi/scsi_error.c +@@ -61,11 +61,11 @@ static int scsi_eh_try_stu(struct scsi_cmnd *scmd); + static enum scsi_disposition scsi_try_to_abort_cmd(const struct scsi_host_template *, + struct scsi_cmnd *); + +-void scsi_eh_wakeup(struct Scsi_Host *shost) ++void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy) + { + lockdep_assert_held(shost->host_lock); + +- if (scsi_host_busy(shost) == shost->host_failed) { ++ if (busy == shost->host_failed) { + trace_scsi_eh_wakeup(shost); + wake_up_process(shost->ehandler); + SCSI_LOG_ERROR_RECOVERY(5, shost_printk(KERN_INFO, shost, +@@ -88,7 +88,7 @@ void scsi_schedule_eh(struct Scsi_Host *shost) + if (scsi_host_set_state(shost, SHOST_RECOVERY) == 0 || + scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY) == 0) { + shost->host_eh_scheduled++; +- scsi_eh_wakeup(shost); ++ scsi_eh_wakeup(shost, scsi_host_busy(shost)); + } + + spin_unlock_irqrestore(shost->host_lock, flags); +@@ -286,7 +286,7 @@ static void scsi_eh_inc_host_failed(struct rcu_head *head) + + spin_lock_irqsave(shost->host_lock, flags); + shost->host_failed++; +- scsi_eh_wakeup(shost); ++ scsi_eh_wakeup(shost, scsi_host_busy(shost)); + spin_unlock_irqrestore(shost->host_lock, flags); + } + +diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c +index c2f647a7c1b0..dfdffe55c5a6 100644 +--- a/drivers/scsi/scsi_lib.c ++++ b/drivers/scsi/scsi_lib.c +@@ -280,7 +280,7 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost, struct scsi_cmnd *cmd) + if (unlikely(scsi_host_in_recovery(shost))) { + spin_lock_irqsave(shost->host_lock, flags); + if (shost->host_failed || shost->host_eh_scheduled) +- scsi_eh_wakeup(shost); ++ scsi_eh_wakeup(shost, scsi_host_busy(shost)); + spin_unlock_irqrestore(shost->host_lock, flags); + } + rcu_read_unlock(); +diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h +index 3f0dfb97db6b..1fbfe1b52c9f 100644 +--- a/drivers/scsi/scsi_priv.h ++++ b/drivers/scsi/scsi_priv.h +@@ -92,7 +92,7 @@ extern void scmd_eh_abort_handler(struct work_struct *work); + extern enum blk_eh_timer_return scsi_timeout(struct request *req); + extern int scsi_error_handler(void *host); + extern enum scsi_disposition scsi_decide_disposition(struct scsi_cmnd *cmd); +-extern void scsi_eh_wakeup(struct Scsi_Host *shost); ++extern void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy); + extern void scsi_eh_scmd_add(struct scsi_cmnd *); + void scsi_eh_ready_devs(struct Scsi_Host *shost, + struct list_head *work_q, +-- +2.43.0 + diff --git a/queue-6.6/scsi-isci-fix-an-error-code-problem-in-isci_io_reque.patch b/queue-6.6/scsi-isci-fix-an-error-code-problem-in-isci_io_reque.patch new file mode 100644 index 00000000000..ee71b368e4d --- /dev/null +++ b/queue-6.6/scsi-isci-fix-an-error-code-problem-in-isci_io_reque.patch @@ -0,0 +1,38 @@ +From a90455370c015fd0c68b03fad0fb16a5a7f5c401 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 12 Jan 2024 12:19:27 +0800 +Subject: scsi: isci: Fix an error code problem in isci_io_request_build() + +From: Su Hui + +[ Upstream commit 658365c6b0857e6a306436e315a8633937e3af42 ] + +Clang static complains that Value stored to 'status' is never read. Return +'status' rather than 'SCI_SUCCESS'. + +Fixes: f1f52e75939b ("isci: uplevel request infrastructure") +Signed-off-by: Su Hui +Link: https://lore.kernel.org/r/20240112041926.3924315-1-suhui@nfschina.com +Reviewed-by: Artur Paszkiewicz +Signed-off-by: Martin K. Petersen +Signed-off-by: Sasha Levin +--- + drivers/scsi/isci/request.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c +index a7b3243b471d..7162a5029b37 100644 +--- a/drivers/scsi/isci/request.c ++++ b/drivers/scsi/isci/request.c +@@ -3390,7 +3390,7 @@ static enum sci_status isci_io_request_build(struct isci_host *ihost, + return SCI_FAILURE; + } + +- return SCI_SUCCESS; ++ return status; + } + + static struct isci_request *isci_request_from_tag(struct isci_host *ihost, u16 tag) +-- +2.43.0 + diff --git a/queue-6.6/selftests-bonding-check-initial-state.patch b/queue-6.6/selftests-bonding-check-initial-state.patch new file mode 100644 index 00000000000..4c45477c057 --- /dev/null +++ b/queue-6.6/selftests-bonding-check-initial-state.patch @@ -0,0 +1,64 @@ +From 289e7b540e0a624e4572c3c466b01f1c91949239 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 31 Jan 2024 09:08:45 -0500 +Subject: selftests: bonding: Check initial state + +From: Benjamin Poirier + +[ Upstream commit 8cc063ae1b3dbe416ce62a15d49af4c2314b45fe ] + +The purpose of the test_LAG_cleanup() function is to check that some +hardware addresses are removed from underlying devices after they have been +unenslaved. The test function simply checks that those addresses are not +present at the end. However, if the addresses were never added to begin +with due to some error in device setup, the test function currently passes. +This is a false positive since in that situation the test did not actually +exercise the intended functionality. + +Add a check that the expected addresses are indeed present after device +setup. This makes the test function more robust. + +I noticed this problem when running the team/dev_addr_lists.sh test on a +system without support for dummy and ipv6: + +tools/testing/selftests/drivers/net/team# ./dev_addr_lists.sh +Error: Unknown device type. +Error: Unknown device type. +This program is not intended to be run as root. +RTNETLINK answers: Operation not supported +TEST: team cleanup mode lacp [ OK ] + +Fixes: bbb774d921e2 ("net: Add tests for bonding and team address list management") +Signed-off-by: Benjamin Poirier +Link: https://lore.kernel.org/r/20240131140848.360618-3-bpoirier@nvidia.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + .../testing/selftests/drivers/net/bonding/lag_lib.sh | 11 +++++++++++ + 1 file changed, 11 insertions(+) + +diff --git a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh +index 2a268b17b61f..dbdd736a41d3 100644 +--- a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh ++++ b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh +@@ -48,6 +48,17 @@ test_LAG_cleanup() + ip link add mv0 link "$name" up address "$ucaddr" type macvlan + # Used to test dev->mc handling + ip address add "$addr6" dev "$name" ++ ++ # Check that addresses were added as expected ++ (grep_bridge_fdb "$ucaddr" bridge fdb show dev dummy1 || ++ grep_bridge_fdb "$ucaddr" bridge fdb show dev dummy2) >/dev/null ++ check_err $? "macvlan unicast address not found on a slave" ++ ++ # mcaddr is added asynchronously by addrconf_dad_work(), use busywait ++ (busywait 10000 grep_bridge_fdb "$mcaddr" bridge fdb show dev dummy1 || ++ grep_bridge_fdb "$mcaddr" bridge fdb show dev dummy2) >/dev/null ++ check_err $? "IPv6 solicited-node multicast mac address not found on a slave" ++ + ip link set dev "$name" down + ip link del "$name" + +-- +2.43.0 + diff --git a/queue-6.6/selftests-net-add-missing-config-for-big-tcp-tests.patch b/queue-6.6/selftests-net-add-missing-config-for-big-tcp-tests.patch new file mode 100644 index 00000000000..e11c9da09e9 --- /dev/null +++ b/queue-6.6/selftests-net-add-missing-config-for-big-tcp-tests.patch @@ -0,0 +1,70 @@ +From d7638efa3aedaaaa9c1da09cb36a5b7e32c1f789 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 26 Jan 2024 16:32:36 +0100 +Subject: selftests: net: add missing config for big tcp tests + +From: Paolo Abeni + +[ Upstream commit fcf67d82b8b878bdd95145382be43927bce07ec6 ] + +The big_tcp test-case requires a few kernel knobs currently +not specified in the net selftests config, causing the +following failure: + + # selftests: net: big_tcp.sh + # Error: Failed to load TC action module. + # We have an error talking to the kernel +... + # Testing for BIG TCP: + # CLI GSO | GW GRO | GW GSO | SER GRO + # ./big_tcp.sh: line 107: test: !=: unary operator expected +... + # on on on on : [FAIL_on_link1] + +Add the missing configs + +Fixes: 6bb382bcf742 ("selftests: add a selftest for big tcp") +Signed-off-by: Paolo Abeni +Acked-by: Aaron Conole +Acked-by: Xin Long +Link: https://lore.kernel.org/all/21630ecea872fea13f071342ac64ef52a991a9b5.1706282943.git.pabeni@redhat.com/ +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + tools/testing/selftests/net/config | 5 +++++ + 1 file changed, 5 insertions(+) + +diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config +index 19ff75051660..413ab9abcf1b 100644 +--- a/tools/testing/selftests/net/config ++++ b/tools/testing/selftests/net/config +@@ -29,7 +29,9 @@ CONFIG_NF_NAT=m + CONFIG_IP6_NF_IPTABLES=m + CONFIG_IP_NF_IPTABLES=m + CONFIG_IP6_NF_NAT=m ++CONFIG_IP6_NF_RAW=m + CONFIG_IP_NF_NAT=m ++CONFIG_IP_NF_RAW=m + CONFIG_IPV6_GRE=m + CONFIG_IPV6_SEG6_LWTUNNEL=y + CONFIG_L2TP_ETH=m +@@ -45,6 +47,8 @@ CONFIG_NF_TABLES=m + CONFIG_NF_TABLES_IPV6=y + CONFIG_NF_TABLES_IPV4=y + CONFIG_NFT_NAT=m ++CONFIG_NETFILTER_XT_MATCH_LENGTH=m ++CONFIG_NET_ACT_CT=m + CONFIG_NET_ACT_GACT=m + CONFIG_NET_CLS_BASIC=m + CONFIG_NET_CLS_U32=m +@@ -55,6 +59,7 @@ CONFIG_NET_SCH_HTB=m + CONFIG_NET_SCH_FQ=m + CONFIG_NET_SCH_ETF=m + CONFIG_NET_SCH_NETEM=y ++CONFIG_NF_FLOW_TABLE=m + CONFIG_PSAMPLE=m + CONFIG_TCP_MD5SIG=y + CONFIG_TEST_BLACKHOLE_DEV=m +-- +2.43.0 + diff --git a/queue-6.6/selftests-net-add-missing-config-for-geneve.patch b/queue-6.6/selftests-net-add-missing-config-for-geneve.patch new file mode 100644 index 00000000000..72809de6a74 --- /dev/null +++ b/queue-6.6/selftests-net-add-missing-config-for-geneve.patch @@ -0,0 +1,40 @@ +From 4d8d0b9486b48eb0ad54a1e6dd9d1685a3d6bd33 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 30 Jan 2024 10:12:18 +0000 +Subject: selftests: net: add missing config for GENEVE + +From: Matthias May + +[ Upstream commit c9ec85153fea6873c52ed4f5055c87263f1b54f9 ] + +l2_tos_ttl_inherit.sh verifies the inheritance of tos and ttl +for GRETAP, VXLAN and GENEVE. +Before testing it checks if the required module is available +and if not skips the tests accordingly. +Currently only GRETAP and VXLAN are tested because the GENEVE +module is missing. + +Fixes: b690842d12fd ("selftests/net: test l2 tunnel TOS/TTL inheriting") +Signed-off-by: Matthias May +Link: https://lore.kernel.org/r/20240130101157.196006-1-matthias.may@westermo.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + tools/testing/selftests/net/config | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config +index b4e811f17eb1..dad385f73612 100644 +--- a/tools/testing/selftests/net/config ++++ b/tools/testing/selftests/net/config +@@ -19,6 +19,7 @@ CONFIG_BRIDGE_VLAN_FILTERING=y + CONFIG_BRIDGE=y + CONFIG_CRYPTO_CHACHA20POLY1305=m + CONFIG_VLAN_8021Q=y ++CONFIG_GENEVE=m + CONFIG_IFB=y + CONFIG_INET_DIAG=y + CONFIG_IP_GRE=m +-- +2.43.0 + diff --git a/queue-6.6/selftests-net-add-missing-config-for-nf_target_ttl.patch b/queue-6.6/selftests-net-add-missing-config-for-nf_target_ttl.patch new file mode 100644 index 00000000000..2b09a1a1059 --- /dev/null +++ b/queue-6.6/selftests-net-add-missing-config-for-nf_target_ttl.patch @@ -0,0 +1,37 @@ +From 8f4643c4ba8a8315217492dc3bf76be01698f910 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 31 Jan 2024 08:56:05 -0800 +Subject: selftests: net: add missing config for NF_TARGET_TTL + +From: Jakub Kicinski + +[ Upstream commit 1939f738c73dfdb8389839bdc9624c765e3326e6 ] + +amt test uses the TTL iptables module: + + ip netns exec "${RELAY}" iptables -t mangle -I PREROUTING \ + -d 239.0.0.1 -j TTL --ttl-set 2 + +Fixes: c08e8baea78e ("selftests: add amt interface selftest script") +Link: https://lore.kernel.org/r/20240131165605.4051645-1-kuba@kernel.org +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + tools/testing/selftests/net/config | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config +index 98c6bd2228c6..24a7c7bcbbc1 100644 +--- a/tools/testing/selftests/net/config ++++ b/tools/testing/selftests/net/config +@@ -33,6 +33,7 @@ CONFIG_IP6_NF_NAT=m + CONFIG_IP6_NF_RAW=m + CONFIG_IP_NF_NAT=m + CONFIG_IP_NF_RAW=m ++CONFIG_IP_NF_TARGET_TTL=m + CONFIG_IPV6_GRE=m + CONFIG_IPV6_SEG6_LWTUNNEL=y + CONFIG_L2TP_ETH=m +-- +2.43.0 + diff --git a/queue-6.6/selftests-net-add-missing-config-for-nftables-backed.patch b/queue-6.6/selftests-net-add-missing-config-for-nftables-backed.patch new file mode 100644 index 00000000000..0ed0e35fd71 --- /dev/null +++ b/queue-6.6/selftests-net-add-missing-config-for-nftables-backed.patch @@ -0,0 +1,46 @@ +From 5c71820826ea0202a410c3384e378bb0f7deddfe Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 26 Jan 2024 12:13:08 -0800 +Subject: selftests: net: add missing config for nftables-backed iptables + +From: Jakub Kicinski + +[ Upstream commit 59c93583491ab15db109f9902524d241c4fa4c0b ] + +Modern OSes use iptables implementation with nf_tables as a backend, +e.g.: + +$ iptables -V +iptables v1.8.8 (nf_tables) + +Pablo points out that we need CONFIG_NFT_COMPAT to make that work, +otherwise we see a lot of: + + Warning: Extension DNAT revision 0 not supported, missing kernel module? + +with DNAT being just an example here, other modules we need +include udp, TTL, length etc. + +Link: https://lore.kernel.org/r/20240126201308.2903602-1-kuba@kernel.org +Signed-off-by: Jakub Kicinski +Stable-dep-of: f7c25d8e17dd ("selftests: net: add missing config for pmtu.sh tests") +Signed-off-by: Sasha Levin +--- + tools/testing/selftests/net/config | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config +index dad385f73612..77a173635a29 100644 +--- a/tools/testing/selftests/net/config ++++ b/tools/testing/selftests/net/config +@@ -62,6 +62,7 @@ CONFIG_NET_SCH_HTB=m + CONFIG_NET_SCH_FQ=m + CONFIG_NET_SCH_ETF=m + CONFIG_NET_SCH_NETEM=y ++CONFIG_NFT_COMPAT=m + CONFIG_NF_FLOW_TABLE=m + CONFIG_PSAMPLE=m + CONFIG_TCP_MD5SIG=y +-- +2.43.0 + diff --git a/queue-6.6/selftests-net-add-missing-config-for-pmtu.sh-tests.patch b/queue-6.6/selftests-net-add-missing-config-for-pmtu.sh-tests.patch new file mode 100644 index 00000000000..04c5bb8457e --- /dev/null +++ b/queue-6.6/selftests-net-add-missing-config-for-pmtu.sh-tests.patch @@ -0,0 +1,62 @@ +From 9b6fdd44034ae6030d18a143ee9bed1c61e1c1e0 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 30 Jan 2024 18:47:16 +0100 +Subject: selftests: net: add missing config for pmtu.sh tests + +From: Paolo Abeni + +[ Upstream commit f7c25d8e17dd759d97ca093faf92eeb7da7b3890 ] + +The mentioned test uses a few Kconfig still missing the +net config, add them. + +Before: + # Error: Specified qdisc kind is unknown. + # Error: Specified qdisc kind is unknown. + # Error: Qdisc not classful. + # We have an error talking to the kernel + # Error: Qdisc not classful. + # We have an error talking to the kernel + # policy_routing not supported + # TEST: ICMPv4 with DSCP and ECN: PMTU exceptions [SKIP] + +After: + # TEST: ICMPv4 with DSCP and ECN: PMTU exceptions [ OK ] + +Fixes: ec730c3e1f0e ("selftest: net: Test IPv4 PMTU exceptions with DSCP and ECN") +Signed-off-by: Paolo Abeni +Reviewed-by: Guillaume Nault +Reviewed-by: David Ahern +Link: https://lore.kernel.org/r/8d27bf6762a5c7b3acc457d6e6872c533040f9c1.1706635101.git.pabeni@redhat.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + tools/testing/selftests/net/config | 3 +++ + 1 file changed, 3 insertions(+) + +diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config +index 77a173635a29..98c6bd2228c6 100644 +--- a/tools/testing/selftests/net/config ++++ b/tools/testing/selftests/net/config +@@ -49,8 +49,10 @@ CONFIG_NF_TABLES_IPV6=y + CONFIG_NF_TABLES_IPV4=y + CONFIG_NFT_NAT=m + CONFIG_NETFILTER_XT_MATCH_LENGTH=m ++CONFIG_NET_ACT_CSUM=m + CONFIG_NET_ACT_CT=m + CONFIG_NET_ACT_GACT=m ++CONFIG_NET_ACT_PEDIT=m + CONFIG_NET_CLS_BASIC=m + CONFIG_NET_CLS_BPF=m + CONFIG_NET_CLS_MATCHALL=m +@@ -62,6 +64,7 @@ CONFIG_NET_SCH_HTB=m + CONFIG_NET_SCH_FQ=m + CONFIG_NET_SCH_ETF=m + CONFIG_NET_SCH_NETEM=y ++CONFIG_NET_SCH_PRIO=m + CONFIG_NFT_COMPAT=m + CONFIG_NF_FLOW_TABLE=m + CONFIG_PSAMPLE=m +-- +2.43.0 + diff --git a/queue-6.6/selftests-net-add-missing-matchall-classifier.patch b/queue-6.6/selftests-net-add-missing-matchall-classifier.patch new file mode 100644 index 00000000000..638137096b8 --- /dev/null +++ b/queue-6.6/selftests-net-add-missing-matchall-classifier.patch @@ -0,0 +1,59 @@ +From 96f394e48a20a38e7a083c943d4f853ef90c2fd2 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 29 Jan 2024 14:37:03 +0200 +Subject: selftests: net: Add missing matchall classifier + +From: Ido Schimmel + +[ Upstream commit b40f873a7c80dbafbb6f4a7a569f2dcaf969d283 ] + +One of the test cases in the test_bridge_backup_port.sh selftest relies +on a matchall classifier to drop unrelated traffic so that the Tx drop +counter on the VXLAN device will only be incremented as a result of +traffic generated by the test. + +However, the configuration option for the matchall classifier is +missing from the configuration file which might explain the failures we +see in the netdev CI [1]. + +Fix by adding CONFIG_NET_CLS_MATCHALL to the configuration file. + +[1] + # Backup nexthop ID - invalid IDs + # ------------------------------- + [...] + # TEST: Forwarding out of vx0 [ OK ] + # TEST: No forwarding using backup nexthop ID [ OK ] + # TEST: Tx drop increased [FAIL] + # TEST: IPv6 address family nexthop as backup nexthop [ OK ] + # TEST: No forwarding out of swp1 [ OK ] + # TEST: Forwarding out of vx0 [ OK ] + # TEST: No forwarding using backup nexthop ID [ OK ] + # TEST: Tx drop increased [FAIL] + [...] + +Fixes: b408453053fb ("selftests: net: Add bridge backup port and backup nexthop ID test") +Signed-off-by: Ido Schimmel +Acked-by: Nikolay Aleksandrov +Link: https://lore.kernel.org/r/20240129123703.1857843-1-idosch@nvidia.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + tools/testing/selftests/net/config | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config +index 56da5d52674c..b4e811f17eb1 100644 +--- a/tools/testing/selftests/net/config ++++ b/tools/testing/selftests/net/config +@@ -52,6 +52,7 @@ CONFIG_NET_ACT_CT=m + CONFIG_NET_ACT_GACT=m + CONFIG_NET_CLS_BASIC=m + CONFIG_NET_CLS_BPF=m ++CONFIG_NET_CLS_MATCHALL=m + CONFIG_NET_CLS_U32=m + CONFIG_NET_IPGRE_DEMUX=m + CONFIG_NET_IPGRE=m +-- +2.43.0 + diff --git a/queue-6.6/selftests-net-add-missing-required-classifier.patch b/queue-6.6/selftests-net-add-missing-required-classifier.patch new file mode 100644 index 00000000000..2a5fc63c939 --- /dev/null +++ b/queue-6.6/selftests-net-add-missing-required-classifier.patch @@ -0,0 +1,53 @@ +From b0043bd1c537c735a1e6e3cf694508a3a02562c7 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 25 Jan 2024 09:22:50 +0100 +Subject: selftests: net: add missing required classifier +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Paolo Abeni + +[ Upstream commit d3cb3b0088ca92082e2bebc40cc6894a632173e2 ] + +the udpgro_fraglist self-test uses the BPF classifiers, but the +current net self-test configuration does not include it, causing +CI failures: + + # selftests: net: udpgro_frglist.sh + # ipv6 + # tcp - over veth touching data + # -l 4 -6 -D 2001:db8::1 -t rx -4 -t + # Error: TC classifier not found. + # We have an error talking to the kernel + # Error: TC classifier not found. + # We have an error talking to the kernel + +Add the missing knob. + +Fixes: edae34a3ed92 ("selftests net: add UDP GRO fraglist + bpf self-tests") +Signed-off-by: Paolo Abeni +Reviewed-by: Maciej Żenczykowski +Reviewed-by: Eric Dumazet +Link: https://lore.kernel.org/r/7c3643763b331e9a400e1874fe089193c99a1c3f.1706170897.git.pabeni@redhat.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + tools/testing/selftests/net/config | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config +index 413ab9abcf1b..56da5d52674c 100644 +--- a/tools/testing/selftests/net/config ++++ b/tools/testing/selftests/net/config +@@ -51,6 +51,7 @@ CONFIG_NETFILTER_XT_MATCH_LENGTH=m + CONFIG_NET_ACT_CT=m + CONFIG_NET_ACT_GACT=m + CONFIG_NET_CLS_BASIC=m ++CONFIG_NET_CLS_BPF=m + CONFIG_NET_CLS_U32=m + CONFIG_NET_IPGRE_DEMUX=m + CONFIG_NET_IPGRE=m +-- +2.43.0 + diff --git a/queue-6.6/selftests-net-don-t-access-dev-stdout-in-pmtu.sh.patch b/queue-6.6/selftests-net-don-t-access-dev-stdout-in-pmtu.sh.patch new file mode 100644 index 00000000000..bdd2c5b482a --- /dev/null +++ b/queue-6.6/selftests-net-don-t-access-dev-stdout-in-pmtu.sh.patch @@ -0,0 +1,44 @@ +From fc7fa91148d86ce0991d3c4ad0d665417a555c6d Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 30 Jan 2024 18:47:18 +0100 +Subject: selftests: net: don't access /dev/stdout in pmtu.sh + +From: Paolo Abeni + +[ Upstream commit bc0970d5ac1d1317e212bdf55533935ecb6ae95c ] + +When running the pmtu.sh via the kselftest infra, accessing +/dev/stdout gives unexpected results: + # dd: failed to open '/dev/stdout': Device or resource busy + # TEST: IPv4, bridged vxlan4: PMTU exceptions [FAIL] + +Let dd use directly the standard output to fix the above: + # TEST: IPv4, bridged vxlan4: PMTU exceptions - nexthop objects [ OK ] + +Fixes: 136a1b434bbb ("selftests: net: test vxlan pmtu exceptions with tcp") +Signed-off-by: Paolo Abeni +Reviewed-by: Guillaume Nault +Reviewed-by: David Ahern +Link: https://lore.kernel.org/r/23d7592c5d77d75cff9b34f15c227f92e911c2ae.1706635101.git.pabeni@redhat.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + tools/testing/selftests/net/pmtu.sh | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh +index 1f1e9a49f59a..4a5f031be232 100755 +--- a/tools/testing/selftests/net/pmtu.sh ++++ b/tools/testing/selftests/net/pmtu.sh +@@ -1348,7 +1348,7 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() { + + sleep 1 + +- dd if=/dev/zero of=/dev/stdout status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3 ++ dd if=/dev/zero status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3 + + size=$(du -sb $tmpoutfile) + size=${size%%/tmp/*} +-- +2.43.0 + diff --git a/queue-6.6/selftests-net-enable-some-more-knobs.patch b/queue-6.6/selftests-net-enable-some-more-knobs.patch new file mode 100644 index 00000000000..a705079d6e5 --- /dev/null +++ b/queue-6.6/selftests-net-enable-some-more-knobs.patch @@ -0,0 +1,43 @@ +From 45c60d2c92ab52f7d8a17d0c88bf9bf0e0ccc81d Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 31 Jan 2024 18:52:29 +0100 +Subject: selftests: net: enable some more knobs + +From: Paolo Abeni + +[ Upstream commit c15a729c9d45aa142fb01a3afee822ab1f0e62a8 ] + +The rtnetlink tests require additional options currently +off by default. + +Fixes: 2766a11161cc ("selftests: rtnetlink: add ipsec offload API test") +Fixes: 5e596ee171ba ("selftests: add xfrm state-policy-monitor to rtnetlink.sh") +Signed-off-by: Paolo Abeni +Link: https://lore.kernel.org/r/9048ca58e49b962f35dba1dfb2beaf3dab3e0411.1706723341.git.pabeni@redhat.com/ +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + tools/testing/selftests/net/config | 3 +++ + 1 file changed, 3 insertions(+) + +diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config +index 24a7c7bcbbc1..3b749addd364 100644 +--- a/tools/testing/selftests/net/config ++++ b/tools/testing/selftests/net/config +@@ -22,6 +22,8 @@ CONFIG_VLAN_8021Q=y + CONFIG_GENEVE=m + CONFIG_IFB=y + CONFIG_INET_DIAG=y ++CONFIG_INET_ESP=y ++CONFIG_INET_ESP_OFFLOAD=y + CONFIG_IP_GRE=m + CONFIG_NETFILTER=y + CONFIG_NETFILTER_ADVANCED=y +@@ -93,3 +95,4 @@ CONFIG_IP_SCTP=m + CONFIG_NETFILTER_XT_MATCH_POLICY=m + CONFIG_CRYPTO_ARIA=y + CONFIG_XFRM_INTERFACE=m ++CONFIG_XFRM_USER=m +-- +2.43.0 + diff --git a/queue-6.6/selftests-net-explicitly-wait-for-listener-ready.patch b/queue-6.6/selftests-net-explicitly-wait-for-listener-ready.patch new file mode 100644 index 00000000000..3fc4df50a2c --- /dev/null +++ b/queue-6.6/selftests-net-explicitly-wait-for-listener-ready.patch @@ -0,0 +1,61 @@ +From f3359e0b2dcaca6f11a6c355ba2e1380030d8ac0 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 24 Jan 2024 22:33:22 +0100 +Subject: selftests: net: explicitly wait for listener ready + +From: Paolo Abeni + +[ Upstream commit 4acffb66630a0e4800880baa61a54ef18047ccd3 ] + +The UDP GRO forwarding test still hard-code an arbitrary pause +to wait for the UDP listener becoming ready in background. + +That causes sporadic failures depending on the host load. + +Replace the sleep with the existing helper waiting for the desired +port being exposed. + +Fixes: a062260a9d5f ("selftests: net: add UDP GRO forwarding self-tests") +Signed-off-by: Paolo Abeni +Reviewed-by: Willem de Bruijn +Link: https://lore.kernel.org/r/4d58900fb09cef42749cfcf2ad7f4b91a97d225c.1706131762.git.pabeni@redhat.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + tools/testing/selftests/net/udpgro_fwd.sh | 6 ++++-- + 1 file changed, 4 insertions(+), 2 deletions(-) + +diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh +index 5fa8659ab13d..d6b9c759043c 100755 +--- a/tools/testing/selftests/net/udpgro_fwd.sh ++++ b/tools/testing/selftests/net/udpgro_fwd.sh +@@ -1,6 +1,8 @@ + #!/bin/bash + # SPDX-License-Identifier: GPL-2.0 + ++source net_helper.sh ++ + BPF_FILE="xdp_dummy.o" + readonly BASE="ns-$(mktemp -u XXXXXX)" + readonly SRC=2 +@@ -119,7 +121,7 @@ run_test() { + ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 8000 + ip netns exec $NS_DST ./udpgso_bench_rx -C 1000 -R 10 -n 10 -l 1300 $rx_args & + local spid=$! +- sleep 0.1 ++ wait_local_port_listen "$NS_DST" 8000 udp + ip netns exec $NS_SRC ./udpgso_bench_tx $family -M 1 -s 13000 -S 1300 -D $dst + local retc=$? + wait $spid +@@ -168,7 +170,7 @@ run_bench() { + ip netns exec $NS_DST bash -c "echo 2 > /sys/class/net/veth$DST/queues/rx-0/rps_cpus" + ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 1000 -R 10 & + local spid=$! +- sleep 0.1 ++ wait_local_port_listen "$NS_DST" 8000 udp + ip netns exec $NS_SRC taskset 0x1 ./udpgso_bench_tx $family -l 3 -S 1300 -D $dst + local retc=$? + wait $spid +-- +2.43.0 + diff --git a/queue-6.6/selftests-net-fix-available-tunnels-detection.patch b/queue-6.6/selftests-net-fix-available-tunnels-detection.patch new file mode 100644 index 00000000000..e067cbf01f8 --- /dev/null +++ b/queue-6.6/selftests-net-fix-available-tunnels-detection.patch @@ -0,0 +1,77 @@ +From a971977417563ef633a7d86f2c2a6a439b2ad4c0 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 30 Jan 2024 18:47:17 +0100 +Subject: selftests: net: fix available tunnels detection + +From: Paolo Abeni + +[ Upstream commit e4e4b6d568d2549583cbda3f8ce567e586cb05da ] + +The pmtu.sh test tries to detect the tunnel protocols available +in the running kernel and properly skip the unsupported cases. + +In a few more complex setup, such detection is unsuccessful, as +the script currently ignores some intermediate error code at +setup time. + +Before: + # which: no nettest in (/bin:/sbin:/usr/bin:/usr/sbin:/usr/local/bin) + # TEST: vti6: PMTU exceptions (ESP-in-UDP) [FAIL] + # PMTU exception wasn't created after creating tunnel exceeding link layer MTU + # ./pmtu.sh: line 931: kill: (7543) - No such process + # ./pmtu.sh: line 931: kill: (7544) - No such process + +After: + # xfrm4 not supported + # TEST: vti4: PMTU exceptions [SKIP] + +Fixes: ece1278a9b81 ("selftests: net: add ESP-in-UDP PMTU test") +Signed-off-by: Paolo Abeni +Reviewed-by: Guillaume Nault +Reviewed-by: David Ahern +Link: https://lore.kernel.org/r/cab10e75fda618e6fff8c595b632f47db58b9309.1706635101.git.pabeni@redhat.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + tools/testing/selftests/net/pmtu.sh | 16 ++++++++-------- + 1 file changed, 8 insertions(+), 8 deletions(-) + +diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh +index b3b2dc5a630c..1f1e9a49f59a 100755 +--- a/tools/testing/selftests/net/pmtu.sh ++++ b/tools/testing/selftests/net/pmtu.sh +@@ -714,23 +714,23 @@ setup_xfrm6() { + } + + setup_xfrm4udp() { +- setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0" +- setup_nettest_xfrm 4 4500 ++ setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0" && \ ++ setup_nettest_xfrm 4 4500 + } + + setup_xfrm6udp() { +- setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0" +- setup_nettest_xfrm 6 4500 ++ setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0" && \ ++ setup_nettest_xfrm 6 4500 + } + + setup_xfrm4udprouted() { +- setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0" +- setup_nettest_xfrm 4 4500 ++ setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0" && \ ++ setup_nettest_xfrm 4 4500 + } + + setup_xfrm6udprouted() { +- setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0" +- setup_nettest_xfrm 6 4500 ++ setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0" && \ ++ setup_nettest_xfrm 6 4500 + } + + setup_routing_old() { +-- +2.43.0 + diff --git a/queue-6.6/selftests-net-give-more-time-for-gro-aggregation.patch b/queue-6.6/selftests-net-give-more-time-for-gro-aggregation.patch new file mode 100644 index 00000000000..fef2c144cf7 --- /dev/null +++ b/queue-6.6/selftests-net-give-more-time-for-gro-aggregation.patch @@ -0,0 +1,48 @@ +From 2545403b5379e99d3edb5b7f8d91cbc06264d30d Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 25 Jan 2024 19:09:06 +0100 +Subject: selftests: net: give more time for GRO aggregation + +From: Paolo Abeni + +[ Upstream commit 89abe628375301fedb68770644df845d49018d8b ] + +The gro.sh test-case relay on the gro_flush_timeout to ensure +that all the segments belonging to any given batch are properly +aggregated. + +The other end, the sender is a user-space program transmitting +each packet with a separate write syscall. A busy host and/or +stracing the sender program can make the relevant segments reach +the GRO engine after the flush timeout triggers. + +Give the GRO flush timeout more slack, to avoid sporadic self-tests +failures. + +Fixes: 9af771d2ec04 ("selftests/net: allow GRO coalesce test on veth") +Signed-off-by: Paolo Abeni +Reviewed-by: Eric Dumazet +Tested-by: Eric Dumazet +Link: https://lore.kernel.org/r/bffec2beab3a5672dd13ecabe4fad81d2155b367.1706206101.git.pabeni@redhat.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + tools/testing/selftests/net/setup_veth.sh | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/tools/testing/selftests/net/setup_veth.sh b/tools/testing/selftests/net/setup_veth.sh +index 1003ddf7b3b2..227fd1076f21 100644 +--- a/tools/testing/selftests/net/setup_veth.sh ++++ b/tools/testing/selftests/net/setup_veth.sh +@@ -8,7 +8,7 @@ setup_veth_ns() { + local -r ns_mac="$4" + + [[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}" +- echo 100000 > "/sys/class/net/${ns_dev}/gro_flush_timeout" ++ echo 1000000 > "/sys/class/net/${ns_dev}/gro_flush_timeout" + ip link set dev "${ns_dev}" netns "${ns_name}" mtu 65535 + ip -netns "${ns_name}" link set dev "${ns_dev}" up + +-- +2.43.0 + diff --git a/queue-6.6/selftests-net-remove-dependency-on-ebpf-tests.patch b/queue-6.6/selftests-net-remove-dependency-on-ebpf-tests.patch new file mode 100644 index 00000000000..343dc1fb647 --- /dev/null +++ b/queue-6.6/selftests-net-remove-dependency-on-ebpf-tests.patch @@ -0,0 +1,192 @@ +From cfc5384849467a98813caef79c0c7aa78f6965f0 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 24 Jan 2024 22:33:20 +0100 +Subject: selftests: net: remove dependency on ebpf tests + +From: Paolo Abeni + +[ Upstream commit 98cb12eb52a780e682bea8372fdb2912c08132dd ] + +Several net tests requires an XDP program build under the ebpf +directory, and error out if such program is not available. + +That makes running successful net test hard, let's duplicate into the +net dir the [very small] program, re-using the existing rules to build +it, and finally dropping the bogus dependency. + +Signed-off-by: Paolo Abeni +Reviewed-by: Willem de Bruijn +Link: https://lore.kernel.org/r/28e7af7c031557f691dc8045ee41dd549dd5e74c.1706131762.git.pabeni@redhat.com +Signed-off-by: Jakub Kicinski +Stable-dep-of: 4acffb66630a ("selftests: net: explicitly wait for listener ready") +Signed-off-by: Sasha Levin +--- + tools/testing/selftests/net/Makefile | 5 +++-- + tools/testing/selftests/net/udpgro.sh | 4 ++-- + tools/testing/selftests/net/udpgro_bench.sh | 4 ++-- + tools/testing/selftests/net/udpgro_frglist.sh | 6 +++--- + tools/testing/selftests/net/udpgro_fwd.sh | 2 +- + tools/testing/selftests/net/veth.sh | 4 ++-- + tools/testing/selftests/net/xdp_dummy.c | 13 +++++++++++++ + 7 files changed, 26 insertions(+), 12 deletions(-) + create mode 100644 tools/testing/selftests/net/xdp_dummy.c + +diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile +index 4a2881d43989..de4506e2a412 100644 +--- a/tools/testing/selftests/net/Makefile ++++ b/tools/testing/selftests/net/Makefile +@@ -84,6 +84,7 @@ TEST_PROGS += sctp_vrf.sh + TEST_GEN_FILES += sctp_hello + TEST_GEN_FILES += csum + TEST_GEN_FILES += nat6to4.o ++TEST_GEN_FILES += xdp_dummy.o + TEST_GEN_FILES += ip_local_port_range + TEST_GEN_FILES += bind_wildcard + TEST_PROGS += test_vxlan_mdb.sh +@@ -100,7 +101,7 @@ $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread -lcrypto + $(OUTPUT)/tcp_inq: LDLIBS += -lpthread + $(OUTPUT)/bind_bhash: LDLIBS += -lpthread + +-# Rules to generate bpf obj nat6to4.o ++# Rules to generate bpf objs + CLANG ?= clang + SCRATCH_DIR := $(OUTPUT)/tools + BUILD_DIR := $(SCRATCH_DIR)/build +@@ -135,7 +136,7 @@ endif + + CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) + +-$(OUTPUT)/nat6to4.o: nat6to4.c $(BPFOBJ) | $(MAKE_DIRS) ++$(OUTPUT)/nat6to4.o $(OUTPUT)/xdp_dummy.o: $(OUTPUT)/%.o : %.c $(BPFOBJ) | $(MAKE_DIRS) + $(CLANG) -O2 --target=bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@ + + $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ +diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh +index 0c743752669a..3f09ac78f445 100755 +--- a/tools/testing/selftests/net/udpgro.sh ++++ b/tools/testing/selftests/net/udpgro.sh +@@ -5,7 +5,7 @@ + + readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" + +-BPF_FILE="../bpf/xdp_dummy.bpf.o" ++BPF_FILE="xdp_dummy.o" + + # set global exit status, but never reset nonzero one. + check_err() +@@ -198,7 +198,7 @@ run_all() { + } + + if [ ! -f ${BPF_FILE} ]; then +- echo "Missing ${BPF_FILE}. Build bpf selftest first" ++ echo "Missing ${BPF_FILE}. Run 'make' first" + exit -1 + fi + +diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh +index 894972877e8b..65ff1d424008 100755 +--- a/tools/testing/selftests/net/udpgro_bench.sh ++++ b/tools/testing/selftests/net/udpgro_bench.sh +@@ -5,7 +5,7 @@ + + readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" + +-BPF_FILE="../bpf/xdp_dummy.bpf.o" ++BPF_FILE="xdp_dummy.o" + + cleanup() { + local -r jobs="$(jobs -p)" +@@ -83,7 +83,7 @@ run_all() { + } + + if [ ! -f ${BPF_FILE} ]; then +- echo "Missing ${BPF_FILE}. Build bpf selftest first" ++ echo "Missing ${BPF_FILE}. Run 'make' first" + exit -1 + fi + +diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh +index 0a6359bed0b9..bd51d386b52e 100755 +--- a/tools/testing/selftests/net/udpgro_frglist.sh ++++ b/tools/testing/selftests/net/udpgro_frglist.sh +@@ -5,7 +5,7 @@ + + readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" + +-BPF_FILE="../bpf/xdp_dummy.bpf.o" ++BPF_FILE="xdp_dummy.o" + + cleanup() { + local -r jobs="$(jobs -p)" +@@ -84,12 +84,12 @@ run_all() { + } + + if [ ! -f ${BPF_FILE} ]; then +- echo "Missing ${BPF_FILE}. Build bpf selftest first" ++ echo "Missing ${BPF_FILE}. Run 'make' first" + exit -1 + fi + + if [ ! -f nat6to4.o ]; then +- echo "Missing nat6to4 helper. Build bpf nat6to4.o selftest first" ++ echo "Missing nat6to4 helper. Run 'make' first" + exit -1 + fi + +diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh +index c079565add39..5fa8659ab13d 100755 +--- a/tools/testing/selftests/net/udpgro_fwd.sh ++++ b/tools/testing/selftests/net/udpgro_fwd.sh +@@ -1,7 +1,7 @@ + #!/bin/bash + # SPDX-License-Identifier: GPL-2.0 + +-BPF_FILE="../bpf/xdp_dummy.bpf.o" ++BPF_FILE="xdp_dummy.o" + readonly BASE="ns-$(mktemp -u XXXXXX)" + readonly SRC=2 + readonly DST=1 +diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh +index 2d073595c620..27574bbf2d63 100755 +--- a/tools/testing/selftests/net/veth.sh ++++ b/tools/testing/selftests/net/veth.sh +@@ -1,7 +1,7 @@ + #!/bin/sh + # SPDX-License-Identifier: GPL-2.0 + +-BPF_FILE="../bpf/xdp_dummy.bpf.o" ++BPF_FILE="xdp_dummy.o" + readonly STATS="$(mktemp -p /tmp ns-XXXXXX)" + readonly BASE=`basename $STATS` + readonly SRC=2 +@@ -218,7 +218,7 @@ while getopts "hs:" option; do + done + + if [ ! -f ${BPF_FILE} ]; then +- echo "Missing ${BPF_FILE}. Build bpf selftest first" ++ echo "Missing ${BPF_FILE}. Run 'make' first" + exit 1 + fi + +diff --git a/tools/testing/selftests/net/xdp_dummy.c b/tools/testing/selftests/net/xdp_dummy.c +new file mode 100644 +index 000000000000..d988b2e0cee8 +--- /dev/null ++++ b/tools/testing/selftests/net/xdp_dummy.c +@@ -0,0 +1,13 @@ ++// SPDX-License-Identifier: GPL-2.0 ++ ++#define KBUILD_MODNAME "xdp_dummy" ++#include ++#include ++ ++SEC("xdp") ++int xdp_dummy_prog(struct xdp_md *ctx) ++{ ++ return XDP_PASS; ++} ++ ++char _license[] SEC("license") = "GPL"; +-- +2.43.0 + diff --git a/queue-6.6/selftests-team-add-missing-config-options.patch b/queue-6.6/selftests-team-add-missing-config-options.patch new file mode 100644 index 00000000000..b270909a2cc --- /dev/null +++ b/queue-6.6/selftests-team-add-missing-config-options.patch @@ -0,0 +1,40 @@ +From 250642fc886b522c369f7b3965a240dfed13ddb3 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 31 Jan 2024 09:08:44 -0500 +Subject: selftests: team: Add missing config options + +From: Benjamin Poirier + +[ Upstream commit 7b6fb3050d8f5e2b6858eef344e47ac1f5442827 ] + +Similar to commit dd2d40acdbb2 ("selftests: bonding: Add more missing +config options"), add more networking-specific config options which are +needed for team device tests. + +For testing, I used the minimal config generated by virtme-ng and I added +the options in the config file. Afterwards, the team device test passed. + +Fixes: bbb774d921e2 ("net: Add tests for bonding and team address list management") +Reviewed-by: Petr Machata +Signed-off-by: Benjamin Poirier +Link: https://lore.kernel.org/r/20240131140848.360618-2-bpoirier@nvidia.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + tools/testing/selftests/drivers/net/team/config | 4 +++- + 1 file changed, 3 insertions(+), 1 deletion(-) + +diff --git a/tools/testing/selftests/drivers/net/team/config b/tools/testing/selftests/drivers/net/team/config +index 265b6882cc21..b5e3a3aad4bf 100644 +--- a/tools/testing/selftests/drivers/net/team/config ++++ b/tools/testing/selftests/drivers/net/team/config +@@ -1,3 +1,5 @@ ++CONFIG_DUMMY=y ++CONFIG_IPV6=y ++CONFIG_MACVLAN=y + CONFIG_NET_TEAM=y + CONFIG_NET_TEAM_MODE_LOADBALANCE=y +-CONFIG_MACVLAN=y +-- +2.43.0 + diff --git a/queue-6.6/series b/queue-6.6/series index cc2e663a671..f778eb5217c 100644 --- a/queue-6.6/series +++ b/queue-6.6/series @@ -267,3 +267,55 @@ wifi-cfg80211-fix-rcu-dereference-in-__cfg80211_bss_.patch drm-using-mul_u32_u32-requires-linux-math64.h.patch drm-amdkfd-only-flush-mes-process-context-if-mes-sup.patch riscv-fix-build-error-on-rv32-xip.patch +scsi-isci-fix-an-error-code-problem-in-isci_io_reque.patch +kunit-run-test-suites-only-after-module-initializati.patch +regulator-ti-abb-don-t-use-devm_platform_ioremap_res.patch +scsi-core-move-scsi_host_busy-out-of-host-lock-for-w.patch +hid-hidraw-fix-a-problem-of-memory-leak-in-hidraw_re.patch +selftests-net-remove-dependency-on-ebpf-tests.patch +selftests-net-explicitly-wait-for-listener-ready.patch +gve-fix-skb-truesize-underestimation.patch +net-ethernet-mtk_eth_soc-set-dma-coherent-mask-to-ge.patch +net-phy-mediatek-ge-soc-sync-driver-with-mediatek-sd.patch +selftests-net-add-missing-config-for-big-tcp-tests.patch +selftests-net-add-missing-required-classifier.patch +selftests-net-give-more-time-for-gro-aggregation.patch +ip6_tunnel-make-sure-to-pull-inner-header-in-__ip6_t.patch +net-dsa-mt7530-fix-10m-100m-speed-on-mt7988-switch.patch +ipmr-fix-kernel-panic-when-forwarding-mcast-packets.patch +net-lan966x-fix-port-configuration-when-using-sgmii-.patch +tcp-add-sanity-checks-to-rx-zerocopy.patch +e1000e-correct-maximum-frequency-adjustment-values.patch +ixgbe-refactor-returning-internal-error-codes.patch +ixgbe-refactor-overtemp-event-handling.patch +ixgbe-fix-an-error-handling-path-in-ixgbe_read_iosf_.patch +net-dsa-qca8k-fix-illegal-usage-of-gpio.patch +ipv6-ensure-natural-alignment-of-const-ipv6-loopback.patch +llc-call-sock_orphan-at-release-time.patch +selftests-net-add-missing-matchall-classifier.patch +bridge-mcast-fix-disabled-snooping-after-long-uptime.patch +devlink-fix-referring-to-hw_addr-attribute-during-st.patch +selftests-net-add-missing-config-for-geneve.patch +netfilter-conntrack-correct-window-scaling-with-retr.patch +netfilter-nf_tables-restrict-tunnel-object-to-nfprot.patch +netfilter-ipset-fix-performance-regression-in-swap-o.patch +netfilter-nf_log-replace-bug_on-by-warn_on_once-when.patch +netfilter-nft_ct-sanitize-layer-3-and-4-protocol-num.patch +net-ipv4-fix-a-memleak-in-ip_setup_cork.patch +af_unix-fix-lockdep-positive-in-sk_diag_dump_icons.patch +pds_core-cancel-aq-work-on-teardown.patch +pds_core-use-struct-pdsc-for-the-pdsc_adminq_isr-pri.patch +pds_core-implement-pci-reset-handlers.patch +pds_core-prevent-race-issues-involving-the-adminq.patch +pds_core-clear-bars-on-reset.patch +pds_core-rework-teardown-setup-flow-to-be-more-commo.patch +selftests-net-add-missing-config-for-nftables-backed.patch +selftests-net-add-missing-config-for-pmtu.sh-tests.patch +selftests-net-fix-available-tunnels-detection.patch +selftests-net-don-t-access-dev-stdout-in-pmtu.sh.patch +octeontx2-pf-remove-xdp-queues-on-program-detach.patch +net-sysfs-fix-sys-class-net-iface-path.patch +selftests-team-add-missing-config-options.patch +selftests-bonding-check-initial-state.patch +selftests-net-add-missing-config-for-nf_target_ttl.patch +selftests-net-enable-some-more-knobs.patch diff --git a/queue-6.6/tcp-add-sanity-checks-to-rx-zerocopy.patch b/queue-6.6/tcp-add-sanity-checks-to-rx-zerocopy.patch new file mode 100644 index 00000000000..6da7c324f37 --- /dev/null +++ b/queue-6.6/tcp-add-sanity-checks-to-rx-zerocopy.patch @@ -0,0 +1,78 @@ +From 59563124589dec9cf592d0d59e846232fa48b1b3 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 25 Jan 2024 10:33:17 +0000 +Subject: tcp: add sanity checks to rx zerocopy + +From: Eric Dumazet + +[ Upstream commit 577e4432f3ac810049cb7e6b71f4d96ec7c6e894 ] + +TCP rx zerocopy intent is to map pages initially allocated +from NIC drivers, not pages owned by a fs. + +This patch adds to can_map_frag() these additional checks: + +- Page must not be a compound one. +- page->mapping must be NULL. + +This fixes the panic reported by ZhangPeng. + +syzbot was able to loopback packets built with sendfile(), +mapping pages owned by an ext4 file to TCP rx zerocopy. + +r3 = socket$inet_tcp(0x2, 0x1, 0x0) +mmap(&(0x7f0000ff9000/0x4000)=nil, 0x4000, 0x0, 0x12, r3, 0x0) +r4 = socket$inet_tcp(0x2, 0x1, 0x0) +bind$inet(r4, &(0x7f0000000000)={0x2, 0x4e24, @multicast1}, 0x10) +connect$inet(r4, &(0x7f00000006c0)={0x2, 0x4e24, @empty}, 0x10) +r5 = openat$dir(0xffffffffffffff9c, &(0x7f00000000c0)='./file0\x00', + 0x181e42, 0x0) +fallocate(r5, 0x0, 0x0, 0x85b8) +sendfile(r4, r5, 0x0, 0x8ba0) +getsockopt$inet_tcp_TCP_ZEROCOPY_RECEIVE(r4, 0x6, 0x23, + &(0x7f00000001c0)={&(0x7f0000ffb000/0x3000)=nil, 0x3000, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0}, &(0x7f0000000440)=0x40) +r6 = openat$dir(0xffffffffffffff9c, &(0x7f00000000c0)='./file0\x00', + 0x181e42, 0x0) + +Fixes: 93ab6cc69162 ("tcp: implement mmap() for zero copy receive") +Link: https://lore.kernel.org/netdev/5106a58e-04da-372a-b836-9d3d0bd2507b@huawei.com/T/ +Reported-and-bisected-by: ZhangPeng +Signed-off-by: Eric Dumazet +Cc: Arjun Roy +Cc: Matthew Wilcox +Cc: linux-mm@vger.kernel.org +Cc: Andrew Morton +Cc: linux-fsdevel@vger.kernel.org +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/ipv4/tcp.c | 12 +++++++++++- + 1 file changed, 11 insertions(+), 1 deletion(-) + +diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c +index fb417aee86e6..ab1308affa08 100644 +--- a/net/ipv4/tcp.c ++++ b/net/ipv4/tcp.c +@@ -1786,7 +1786,17 @@ static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb, + + static bool can_map_frag(const skb_frag_t *frag) + { +- return skb_frag_size(frag) == PAGE_SIZE && !skb_frag_off(frag); ++ struct page *page; ++ ++ if (skb_frag_size(frag) != PAGE_SIZE || skb_frag_off(frag)) ++ return false; ++ ++ page = skb_frag_page(frag); ++ ++ if (PageCompound(page) || page->mapping) ++ return false; ++ ++ return true; + } + + static int find_next_mappable_frag(const skb_frag_t *frag, +-- +2.43.0 +